Andrew Murray <amurray@thegoodpenguin.co.uk> <amurray@embedded-bits.co.uk>
Andrew Murray <amurray@thegoodpenguin.co.uk> <andrew.murray@arm.com>
Andrew Vasquez <andrew.vasquez@qlogic.com>
+Andrey Konovalov <andreyknvl@gmail.com> <andreyknvl@google.com>
Andrey Ryabinin <ryabinin.a.a@gmail.com> <a.ryabinin@samsung.com>
Andrey Ryabinin <ryabinin.a.a@gmail.com> <aryabinin@virtuozzo.com>
Andy Adamson <andros@citi.umich.edu>
Changbin Du <changbin.du@intel.com> <changbin.du@intel.com>
Chao Yu <chao@kernel.org> <chao2.yu@samsung.com>
Chao Yu <chao@kernel.org> <yuchao0@huawei.com>
+Chris Chiu <chris.chiu@canonical.com> <chiu@endlessm.com>
+Chris Chiu <chris.chiu@canonical.com> <chiu@endlessos.org>
Christophe Ricard <christophe.ricard@gmail.com>
Christoph Hellwig <hch@lst.de>
Corey Minyard <minyard@acm.org>
Johan Hovold <johan@kernel.org> <johan@hovoldconsulting.com>
John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
John Stultz <johnstul@us.ibm.com>
+Jordan Crouse <jordan@cosmicpenguin.net> <jcrouse@codeaurora.org>
<josh@joshtriplett.org> <josh@freedesktop.org>
<josh@joshtriplett.org> <josh@kernel.org>
<josh@joshtriplett.org> <josht@linux.vnet.ibm.com>
Morten Welinder <welinder@darter.rentec.com>
Morten Welinder <welinder@troll.com>
Mythri P K <mythripk@ti.com>
+Nadia Yvette Chambers <nyc@holomorphy.com> William Lee Irwin III <wli@holomorphy.com>
Nathan Chancellor <nathan@kernel.org> <natechancellor@gmail.com>
Nguyen Anh Quynh <aquynh@gmail.com>
+Nicholas Piggin <npiggin@gmail.com> <npiggen@suse.de>
+Nicholas Piggin <npiggin@gmail.com> <npiggin@kernel.dk>
+Nicholas Piggin <npiggin@gmail.com> <npiggin@suse.de>
+Nicholas Piggin <npiggin@gmail.com> <nickpiggin@yahoo.com.au>
+Nicholas Piggin <npiggin@gmail.com> <piggin@cyberone.com.au>
Nicolas Ferre <nicolas.ferre@microchip.com> <nicolas.ferre@atmel.com>
Nicolas Pitre <nico@fluxnic.net> <nicolas.pitre@linaro.org>
Nicolas Pitre <nico@fluxnic.net> <nico@linaro.org>
What: /sys/kernel/debug/moxtet/input
Date: March 2019
KernelVersion: 5.3
-Contact: Marek Behún <marek.behun@nic.cz>
+Contact: Marek Behún <kabel@kernel.org>
Description: (Read) Read input from the shift registers, in hexadecimal.
Returns N+1 bytes, where N is the number of Moxtet connected
modules. The first byte is from the CPU board itself.
What: /sys/kernel/debug/moxtet/output
Date: March 2019
KernelVersion: 5.3
-Contact: Marek Behún <marek.behun@nic.cz>
+Contact: Marek Behún <kabel@kernel.org>
Description: (RW) Read last written value to the shift registers, in
hexadecimal, or write values to the shift registers, also
in hexadecimal.
What: /sys/kernel/debug/turris-mox-rwtm/do_sign
Date: Jun 2020
KernelVersion: 5.8
-Contact: Marek Behún <marek.behun@nic.cz>
+Contact: Marek Behún <kabel@kernel.org>
Description:
======= ===========================================================
What: /sys/bus/moxtet/devices/moxtet-<name>.<addr>/module_description
Date: March 2019
KernelVersion: 5.3
-Contact: Marek Behún <marek.behun@nic.cz>
+Contact: Marek Behún <kabel@kernel.org>
Description: (Read) Moxtet module description. Format: string
What: /sys/bus/moxtet/devices/moxtet-<name>.<addr>/module_id
Date: March 2019
KernelVersion: 5.3
-Contact: Marek Behún <marek.behun@nic.cz>
+Contact: Marek Behún <kabel@kernel.org>
Description: (Read) Moxtet module ID. Format: %x
What: /sys/bus/moxtet/devices/moxtet-<name>.<addr>/module_name
Date: March 2019
KernelVersion: 5.3
-Contact: Marek Behún <marek.behun@nic.cz>
+Contact: Marek Behún <kabel@kernel.org>
Description: (Read) Moxtet module name. Format: string
What: /sys/class/leds/<led>/device/brightness
Date: July 2020
KernelVersion: 5.9
-Contact: Marek Behún <marek.behun@nic.cz>
+Contact: Marek Behún <kabel@kernel.org>
Description: (RW) On the front panel of the Turris Omnia router there is also
a button which can be used to control the intensity of all the
LEDs at once, so that if they are too bright, user can dim them.
The uv_type entry contains the hub revision number.
This value can be used to identify the UV system version::
- "0.*" = Hubless UV ('*' is subtype)
+ "0.*" = Hubless UV ('*' is subtype)
"3.0" = UV2
"5.0" = UV3
"7.0" = UV4
What: /sys/firmware/turris-mox-rwtm/board_version
Date: August 2019
KernelVersion: 5.4
-Contact: Marek Behún <marek.behun@nic.cz>
+Contact: Marek Behún <kabel@kernel.org>
Description: (Read) Board version burned into eFuses of this Turris Mox board.
Format: %i
What: /sys/firmware/turris-mox-rwtm/mac_address*
Date: August 2019
KernelVersion: 5.4
-Contact: Marek Behún <marek.behun@nic.cz>
+Contact: Marek Behún <kabel@kernel.org>
Description: (Read) MAC addresses burned into eFuses of this Turris Mox board.
Format: %pM
What: /sys/firmware/turris-mox-rwtm/pubkey
Date: August 2019
KernelVersion: 5.4
-Contact: Marek Behún <marek.behun@nic.cz>
+Contact: Marek Behún <kabel@kernel.org>
Description: (Read) ECDSA public key (in pubkey hex compressed form) computed
as pair to the ECDSA private key burned into eFuses of this
Turris Mox Board.
What: /sys/firmware/turris-mox-rwtm/ram_size
Date: August 2019
KernelVersion: 5.4
-Contact: Marek Behún <marek.behun@nic.cz>
+Contact: Marek Behún <kabel@kernel.org>
Description: (Read) RAM size in MiB of this Turris Mox board as was detected
during manufacturing and burned into eFuses. Can be 512 or 1024.
Format: %i
What: /sys/firmware/turris-mox-rwtm/serial_number
Date: August 2019
KernelVersion: 5.4
-Contact: Marek Behún <marek.behun@nic.cz>
+Contact: Marek Behún <kabel@kernel.org>
Description: (Read) Serial number burned into eFuses of this Turris Mox device.
Format: %016X
Description:
The current state of the log write grant head. It
represents the total log reservation of all currently
- oustanding transactions, including regrants due to
+ outstanding transactions, including regrants due to
rolling transactions. The grant head is exported in
"cycle:bytes" format.
Users: xfstests
state is kept private from the host.
Not valid if the kernel is running in EL2.
- Defaults to VHE/nVHE based on hardware support and
- the value of CONFIG_ARM64_VHE.
+ Defaults to VHE/nVHE based on hardware support.
kvm-arm.vgic_v3_group0_trap=
[KVM,ARM] Trap guest accesses to GICv3 group-0
fully seed the kernel's CRNG. Default is controlled
by CONFIG_RANDOM_TRUST_CPU.
+ randomize_kstack_offset=
+ [KNL] Enable or disable kernel stack offset
+ randomization, which provides roughly 5 bits of
+ entropy, frustrating memory corruption attacks
+ that depend on stack address determinism or
+ cross-syscall address exposures. This is only
+ available on architectures that have defined
+ CONFIG_HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET.
+ Format: <bool> (1/Y/y=enable, 0/N/n=disable)
+ Default is CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT.
+
ras=option[,option,...] [KNL] RAS-specific options
cec_disable [X86]
spia_peddr=
split_lock_detect=
- [X86] Enable split lock detection
+ [X86] Enable split lock detection or bus lock detection
When enabled (and if hardware support is present), atomic
instructions that access data across cache line
- boundaries will result in an alignment check exception.
+ boundaries will result in an alignment check exception
+ for split lock detection or a debug exception for
+ bus lock detection.
off - not enabled
- warn - the kernel will emit rate limited warnings
+ warn - the kernel will emit rate-limited warnings
about applications triggering the #AC
- exception. This mode is the default on CPUs
- that supports split lock detection.
+ exception or the #DB exception. This mode is
+ the default on CPUs that support split lock
+ detection or bus lock detection. Default
+ behavior is by #AC if both features are
+ enabled in hardware.
fatal - the kernel will send SIGBUS to applications
- that trigger the #AC exception.
+ that trigger the #AC exception or the #DB
+ exception. Default behavior is by #AC if
+ both features are enabled in hardware.
If an #AC exception is hit in the kernel or in
firmware (i.e. not while executing in user mode)
the kernel will oops in either "warn" or "fatal"
mode.
+ #DB exception for bus lock is triggered only when
+ CPL > 0.
+
srbds= [X86,INTEL]
Control the Special Register Buffer Data Sampling
(SRBDS) mitigation.
See Documentation/admin-guide/mm/transhuge.rst
for more details.
+ trusted.source= [KEYS]
+ Format: <string>
+ This parameter identifies the trust source as a backend
+ for trusted keys implementation. Supported trust
+ sources:
+ - "tpm"
+ - "tee"
+ If not specified then it defaults to iterating through
+ the trust source list starting with TPM and assigns the
+ first trust source as a backend which is initialized
+ successfully during iteration.
+
tsc= Disable clocksource stability checks for TSC.
Format: <string>
[x86] reliable: mark tsc clocksource as reliable, this
$# perf stat -a -e hisi_sccl3_l3c0/rd_hit_cpipe/ sleep 5
$# perf stat -a -e hisi_sccl3_l3c0/config=0x02/ sleep 5
+For HiSilicon uncore PMU v2 whose identifier is 0x30, the topology is the same
+as PMU v1, but some new functions are added to the hardware.
+
+(a) L3C PMU supports filtering by core/thread within the cluster which can be
+specified as a bitmap::
+
+ $# perf stat -a -e hisi_sccl3_l3c0/config=0x02,tt_core=0x3/ sleep 5
+
+This will only count the operations from core/thread 0 and 1 in this cluster.
+
+(b) Tracetag allow the user to chose to count only read, write or atomic
+operations via the tt_req parameeter in perf. The default value counts all
+operations. tt_req is 3bits, 3'b100 represents read operations, 3'b101
+represents write operations, 3'b110 represents atomic store operations and
+3'b111 represents atomic non-store operations, other values are reserved::
+
+ $# perf stat -a -e hisi_sccl3_l3c0/config=0x02,tt_req=0x4/ sleep 5
+
+This will only count the read operations in this cluster.
+
+(c) Datasrc allows the user to check where the data comes from. It is 5 bits.
+Some important codes are as follows:
+5'b00001: comes from L3C in this die;
+5'b01000: comes from L3C in the cross-die;
+5'b01001: comes from L3C which is in another socket;
+5'b01110: comes from the local DDR;
+5'b01111: comes from the cross-die DDR;
+5'b10000: comes from cross-socket DDR;
+etc, it is mainly helpful to find that the data source is nearest from the CPU
+cores. If datasrc_cfg is used in the multi-chips, the datasrc_skt shall be
+configured in perf command::
+
+ $# perf stat -a -e hisi_sccl3_l3c0/config=0xb9,datasrc_cfg=0xE/,
+ hisi_sccl3_l3c0/config=0xb9,datasrc_cfg=0xF/ sleep 5
+
+(d)Some HiSilicon SoCs encapsulate multiple CPU and IO dies. Each CPU die
+contains several Compute Clusters (CCLs). The I/O dies are called Super I/O
+clusters (SICL) containing multiple I/O clusters (ICLs). Each CCL/ICL in the
+SoC has a unique ID. Each ID is 11bits, include a 6-bit SCCL-ID and 5-bit
+CCL/ICL-ID. For I/O die, the ICL-ID is followed by:
+5'b00000: I/O_MGMT_ICL;
+5'b00001: Network_ICL;
+5'b00011: HAC_ICL;
+5'b10000: PCIe_ICL;
+
+Users could configure IDs to count data come from specific CCL/ICL, by setting
+srcid_cmd & srcid_msk, and data desitined for specific CCL/ICL by setting
+tgtid_cmd & tgtid_msk. A set bit in srcid_msk/tgtid_msk means the PMU will not
+check the bit when matching against the srcid_cmd/tgtid_cmd.
+
+If all of these options are disabled, it can works by the default value that
+doesn't distinguish the filter condition and ID information and will return
+the total counter values in the PMU counters.
+
The current driver does not support sampling. So "perf record" is unsupported.
Also attach to a task is unsupported as the events are all uncore.
- Recommended: BERT, EINJ, ERST, HEST, PCCT, SSDT
- - Optional: BGRT, CPEP, CSRT, DBG2, DRTM, ECDT, FACS, FPDT, IORT,
- MCHI, MPST, MSCT, NFIT, PMTT, RASF, SBST, SLIT, SPMI, SRAT, STAO,
- TCPA, TPM2, UEFI, XENV
+ - Optional: BGRT, CPEP, CSRT, DBG2, DRTM, ECDT, FACS, FPDT, IBFT,
+ IORT, MCHI, MPST, MSCT, NFIT, PMTT, RASF, SBST, SLIT, SPMI, SRAT,
+ STAO, TCPA, TPM2, UEFI, XENV
- - Not supported: BOOT, DBGP, DMAR, ETDT, HPET, IBFT, IVRS, LPIT,
- MSDM, OEMx, PSDT, RSDT, SLIC, WAET, WDAT, WDRT, WPBT
+ - Not supported: BOOT, DBGP, DMAR, ETDT, HPET, IVRS, LPIT, MSDM, OEMx,
+ PSDT, RSDT, SLIC, WAET, WDAT, WDRT, WPBT
====== ========================================================================
Table Usage for ARMv8 Linux
- System registers
- All writable architected system registers at the exception level where
- the kernel image will be entered must be initialised by software at a
- higher exception level to prevent execution in an UNKNOWN state.
+ All writable architected system registers at or below the exception
+ level where the kernel image will be entered must be initialised by
+ software at a higher exception level to prevent execution in an UNKNOWN
+ state.
- SCR_EL3.FIQ must have the same value across all CPUs the kernel is
executing on.
having 0b1 set for the corresponding bit for each of the auxiliary
counters present.
+ For CPUs with the Fine Grained Traps (FEAT_FGT) extension present:
+
+ - If EL3 is present and the kernel is entered at EL2:
+
+ - SCR_EL3.FGTEn (bit 27) must be initialised to 0b1.
+
The requirements described above for CPU mode, caches, MMUs, architected
timers, coherency and system registers apply to all CPUs. All CPUs must
enter the kernel in the same exception level.
KVM_GET/SET_REG_* ioctls and mask those features from cpufeature ID
register. Any attempt to use the Pointer Authentication instructions will
result in an UNDEFINED exception being injected into the guest.
+
+
+Enabling and disabling keys
+---------------------------
+
+The prctl PR_PAC_SET_ENABLED_KEYS allows the user program to control which
+PAC keys are enabled in a particular task. It takes two arguments, the
+first being a bitmask of PR_PAC_APIAKEY, PR_PAC_APIBKEY, PR_PAC_APDAKEY
+and PR_PAC_APDBKEY specifying which keys shall be affected by this prctl,
+and the second being a bitmask of the same bits specifying whether the key
+should be enabled or disabled. For example::
+
+ prctl(PR_PAC_SET_ENABLED_KEYS,
+ PR_PAC_APIAKEY | PR_PAC_APIBKEY | PR_PAC_APDAKEY | PR_PAC_APDBKEY,
+ PR_PAC_APIBKEY, 0, 0);
+
+disables all keys except the IB key.
+
+The main reason why this is useful is to enable a userspace ABI that uses PAC
+instructions to sign and authenticate function pointers and other pointers
+exposed outside of the function, while still allowing binaries conforming to
+the ABI to interoperate with legacy binaries that do not sign or authenticate
+pointers.
+
+The idea is that a dynamic loader or early startup code would issue this
+prctl very early after establishing that a process may load legacy binaries,
+but before executing any PAC instructions.
+
+For compatibility with previous kernel versions, processes start up with IA,
+IB, DA and DB enabled, and are reset to this state on exec(). Processes created
+via fork() and clone() inherit the key enabled state from the calling process.
+
+It is recommended to avoid disabling the IA key, as this has higher performance
+overhead than disabling any of the other keys.
| Marvell | ARM-MMU-500 | #582743 | N/A |
+----------------+-----------------+-----------------+-----------------------------+
+----------------+-----------------+-----------------+-----------------------------+
+| NVIDIA | Carmel Core | N/A | NVIDIA_CARMEL_CNP_ERRATUM |
++----------------+-----------------+-----------------+-----------------------------+
++----------------+-----------------+-----------------+-----------------------------+
| Freescale/NXP | LS2080A/LS1043A | A-008585 | FSL_ERRATUM_A008585 |
+----------------+-----------------+-----------------+-----------------------------+
+----------------+-----------------+-----------------+-----------------------------+
during creation and with the same restrictions as for ``mmap()`` above
(e.g. data, bss, stack).
-The AArch64 Tagged Address ABI has two stages of relaxation depending
+The AArch64 Tagged Address ABI has two stages of relaxation depending on
how the user addresses are used by the kernel:
1. User addresses not accessed by the kernel but used for address space
- ``kasan=off`` or ``=on`` controls whether KASAN is enabled (default: ``on``).
+- ``kasan.mode=sync`` or ``=async`` controls whether KASAN is configured in
+ synchronous or asynchronous mode of execution (default: ``sync``).
+ Synchronous mode: a bad access is detected immediately when a tag
+ check fault occurs.
+ Asynchronous mode: a bad access detection is delayed. When a tag check
+ fault occurs, the information is stored in hardware (in the TFSR_EL1
+ register for arm64). The kernel periodically checks the hardware and
+ only reports tag faults during these checks.
+
- ``kasan.stacktrace=off`` or ``=on`` disables or enables alloc and free stack
traces collection (default: ``on``).
enum:
- ti,j721e-sa2ul
- ti,am654-sa2ul
+ - ti,am64-sa2ul
reg:
maxItems: 1
description:
Address translation for the possible RNG child node for SA2UL
+ clocks:
+ items:
+ - description: Clock used by PKA
+ - description: Main Input Clock
+ - description: Clock used by rng
+
+ clock-names:
+ items:
+ - const: pka_in_clk
+ - const: x1_clk
+ - const: x2_clk
+
patternProperties:
"^rng@[a-f0-9]+$":
type: object
- power-domains
- dmas
- dma-names
- - dma-coherent
+
+if:
+ properties:
+ compatible:
+ enum:
+ - ti,j721e-sa2ul
+ - ti,am654-sa2ul
+then:
+ required:
+ - dma-coherent
additionalProperties: false
- "#thermal-sensor-cells" Used to expose itself to thermal fw.
Read more about iio bindings at
- Documentation/devicetree/bindings/iio/iio-bindings.txt
+ https://github.com/devicetree-org/dt-schema/blob/master/schemas/iio/
Example:
ncp15wb473@0 {
title: Bindings for GPIO bitbanged I2C
maintainers:
- - Wolfram Sang <wolfram@the-dreams.de>
+ - Wolfram Sang <wsa@kernel.org>
allOf:
- $ref: /schemas/i2c/i2c-controller.yaml#
title: Freescale Inter IC (I2C) and High Speed Inter IC (HS-I2C) for i.MX
maintainers:
- - Wolfram Sang <wolfram@the-dreams.de>
+ - Oleksij Rempel <o.rempel@pengutronix.de>
allOf:
- $ref: /schemas/i2c/i2c-controller.yaml#
Industrial I/O subsystem bindings for ADC controller found in
Ingenic JZ47xx SoCs.
- ADC clients must use the format described in iio-bindings.txt, giving
- a phandle and IIO specifier pair ("io-channels") to the ADC controller.
+ ADC clients must use the format described in
+ https://github.com/devicetree-org/dt-schema/blob/master/schemas/iio/iio-consumer.yaml,
+ giving a phandle and IIO specifier pair ("io-channels") to the ADC controller.
properties:
compatible:
description: >
List of phandle and IIO specifier pairs.
Each pair defines one ADC channel to which a joystick axis is connected.
- See Documentation/devicetree/bindings/iio/iio-bindings.txt for details.
+ See
+ https://github.com/devicetree-org/dt-schema/blob/master/schemas/iio/iio-consumer.yaml
+ for details.
'#address-cells':
const: 1
- compatible: must be "resistive-adc-touch"
The device must be connected to an ADC device that provides channels for
position measurement and optional pressure.
-Refer to ../iio/iio-bindings.txt for details
+Refer to
+https://github.com/devicetree-org/dt-schema/blob/master/schemas/iio/iio-consumer.yaml
+for details
+
- iio-channels: must have at least two channels connected to an ADC device.
These should correspond to the channels exposed by the ADC device and should
have the right index as the ADC device registers them. These channels
--- /dev/null
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/interrupt-controller/idt,32434-pic.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: IDT 79RC32434 Interrupt Controller Device Tree Bindings
+
+maintainers:
+ - Thomas Bogendoerfer <tsbogend@alpha.franken.de>
+
+allOf:
+ - $ref: /schemas/interrupt-controller.yaml#
+
+properties:
+ "#interrupt-cells":
+ const: 1
+
+ compatible:
+ const: idt,32434-pic
+
+ reg:
+ maxItems: 1
+
+ interrupt-controller: true
+
+required:
+ - "#interrupt-cells"
+ - compatible
+ - reg
+ - interrupt-controller
+
+additionalProperties: false
+
+examples:
+ - |
+ idtpic3: interrupt-controller@3800c {
+ compatible = "idt,32434-pic";
+ reg = <0x3800c 0x0c>;
+
+ interrupt-controller;
+ #interrupt-cells = <1>;
+
+ interrupt-parent = <&cpuintc>;
+ interrupts = <3>;
+ };
+
+...
- enum:
- ingenic,jz4775-intc
- ingenic,jz4770-intc
+ - ingenic,jz4760b-intc
- const: ingenic,jz4760-intc
- items:
- const: ingenic,x1000-intc
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/interrupt-controller/nuvoton,wpcm450-aic.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Nuvoton WPCM450 Advanced Interrupt Controller bindings
+
+maintainers:
+ - Jonathan Neuschäfer <j.neuschaefer@gmx.net>
+
+properties:
+ '#interrupt-cells':
+ const: 2
+
+ compatible:
+ const: nuvoton,wpcm450-aic
+
+ interrupt-controller: true
+
+ reg:
+ maxItems: 1
+
+additionalProperties: false
+
+required:
+ - '#interrupt-cells'
+ - compatible
+ - reg
+ - interrupt-controller
+
+examples:
+ - |
+ aic: interrupt-controller@b8002000 {
+ compatible = "nuvoton,wpcm450-aic";
+ reg = <0xb8002000 0x1000>;
+ interrupt-controller;
+ #interrupt-cells = <2>;
+ };
Value type: <string>
Definition: Should contain "qcom,<soc>-pdc" and "qcom,pdc"
- "qcom,sc7180-pdc": For SC7180
+ - "qcom,sc7280-pdc": For SC7280
- "qcom,sdm845-pdc": For SDM845
- "qcom,sdm8250-pdc": For SM8250
- "qcom,sdm8350-pdc": For SM8350
title: CZ.NIC's Turris Omnia LEDs driver
maintainers:
- - Marek Behún <marek.behun@nic.cz>
+ - Marek Behún <kabel@kernel.org>
description:
This module adds support for the RGB LEDs found on the front panel of the
pwm|regulator|rtc|sysctrl|usb]";
A few child devices require ADC channels from the GPADC node. Those follow the
- standard bindings from iio/iio-bindings.txt and iio/adc/adc.txt
+ standard bindings from
+ https://github.com/devicetree-org/dt-schema/blob/master/schemas/iio/iio-consumer.yaml
+ and Documentation/devicetree/bindings/iio/adc/adc.yaml
abx500-temp : io-channels "aux1" and "aux2" for measuring external
temperatures.
The sub-functions of CPCAP get their own node with their own compatible values,
which are described in the following files:
-- ../power/supply/cpcap-battery.txt
-- ../power/supply/cpcap-charger.txt
-- ../regulator/cpcap-regulator.txt
-- ../phy/phy-cpcap-usb.txt
-- ../input/cpcap-pwrbutton.txt
-- ../rtc/cpcap-rtc.txt
-- ../leds/leds-cpcap.txt
-- ../iio/adc/cpcap-adc.txt
+- Documentation/devicetree/bindings/power/supply/cpcap-battery.txt
+- Documentation/devicetree/bindings/power/supply/cpcap-charger.txt
+- Documentation/devicetree/bindings/regulator/cpcap-regulator.txt
+- Documentation/devicetree/bindings/phy/phy-cpcap-usb.txt
+- Documentation/devicetree/bindings/input/cpcap-pwrbutton.txt
+- Documentation/devicetree/bindings/rtc/cpcap-rtc.txt
+- Documentation/devicetree/bindings/leds/leds-cpcap.txt
+- Documentation/devicetree/bindings/iio/adc/motorola,cpcap-adc.yaml
The only exception is the audio codec. Instead of a compatible value its
node must be named "audio-codec".
- interrupts
- interrupt-names
-additionalProperties: false
+unevaluatedProperties: false
examples:
- |
description:
Reference to an nvmem node for the MAC address
- nvmem-cells-names:
+ nvmem-cell-names:
const: mac-address
phy-connection-type:
step is 60ps. The default value is the neutral setting, so setting
rxc-skew-ps=<0> actually results in -900 picoseconds adjustment.
+ The KSZ9031 hardware supports a range of skew values from negative to
+ positive, where the specific range is property dependent. All values
+ specified in the devicetree are offset by the minimum value so they
+ can be represented as positive integers in the devicetree since it's
+ difficult to represent a negative number in the devictree.
+
+ The following 5-bit values table apply to rxc-skew-ps and txc-skew-ps.
+
+ Pad Skew Value Delay (ps) Devicetree Value
+ ------------------------------------------------------
+ 0_0000 -900ps 0
+ 0_0001 -840ps 60
+ 0_0010 -780ps 120
+ 0_0011 -720ps 180
+ 0_0100 -660ps 240
+ 0_0101 -600ps 300
+ 0_0110 -540ps 360
+ 0_0111 -480ps 420
+ 0_1000 -420ps 480
+ 0_1001 -360ps 540
+ 0_1010 -300ps 600
+ 0_1011 -240ps 660
+ 0_1100 -180ps 720
+ 0_1101 -120ps 780
+ 0_1110 -60ps 840
+ 0_1111 0ps 900
+ 1_0000 60ps 960
+ 1_0001 120ps 1020
+ 1_0010 180ps 1080
+ 1_0011 240ps 1140
+ 1_0100 300ps 1200
+ 1_0101 360ps 1260
+ 1_0110 420ps 1320
+ 1_0111 480ps 1380
+ 1_1000 540ps 1440
+ 1_1001 600ps 1500
+ 1_1010 660ps 1560
+ 1_1011 720ps 1620
+ 1_1100 780ps 1680
+ 1_1101 840ps 1740
+ 1_1110 900ps 1800
+ 1_1111 960ps 1860
+
+ The following 4-bit values table apply to the txdX-skew-ps, rxdX-skew-ps
+ data pads, and the rxdv-skew-ps, txen-skew-ps control pads.
+
+ Pad Skew Value Delay (ps) Devicetree Value
+ ------------------------------------------------------
+ 0000 -420ps 0
+ 0001 -360ps 60
+ 0010 -300ps 120
+ 0011 -240ps 180
+ 0100 -180ps 240
+ 0101 -120ps 300
+ 0110 -60ps 360
+ 0111 0ps 420
+ 1000 60ps 480
+ 1001 120ps 540
+ 1010 180ps 600
+ 1011 240ps 660
+ 1100 300ps 720
+ 1101 360ps 780
+ 1110 420ps 840
+ 1111 480ps 900
+
Optional properties:
Maximum value of 1860, default value 900:
Examples:
+ /* Attach to an Ethernet device with autodetected PHY */
+ &enet {
+ rxc-skew-ps = <1800>;
+ rxdv-skew-ps = <0>;
+ txc-skew-ps = <1800>;
+ txen-skew-ps = <0>;
+ status = "okay";
+ };
+
+ /* Attach to an explicitly-specified PHY */
mdio {
phy0: ethernet-phy@0 {
- rxc-skew-ps = <3000>;
+ rxc-skew-ps = <1800>;
rxdv-skew-ps = <0>;
- txc-skew-ps = <3000>;
+ txc-skew-ps = <1800>;
txen-skew-ps = <0>;
reg = <0>;
};
phy = <&phy0>;
phy-mode = "rgmii-id";
};
+
+References
+
+ Micrel ksz9021rl/rn Data Sheet, Revision 1.2. Dated 2/13/2014.
+ http://www.micrel.com/_PDF/Ethernet/datasheets/ksz9021rl-rn_ds.pdf
+
+ Micrel ksz9031rnx Data Sheet, Revision 2.1. Dated 11/20/2014.
+ http://www.micrel.com/_PDF/Ethernet/datasheets/KSZ9031RNX.pdf
+
+Notes:
+
+ Note that a previous version of the Micrel ksz9021rl/rn Data Sheet
+ was missing extended register 106 (transmit data pad skews), and
+ incorrectly specified the ps per step as 200ps/step instead of
+ 120ps/step. The latest update to this document reflects the latest
+ revision of the Micrel specification even though usage in the kernel
+ still reflects that incorrect document.
clock-names:
const: ipsec
+ resets:
+ maxItems: 1
+
+ reset-names:
+ const: ipsec
+
interrupts:
maxItems: 1
- compatible
- reg
+if:
+ properties:
+ compatible:
+ enum:
+ - brcm,bcm6368-rng
+then:
+ required:
+ - clocks
+ - clock-names
+ - resets
+ - reset-names
+
additionalProperties: false
examples:
clocks = <&periph_clk 18>;
clock-names = "ipsec";
+
+ resets = <&periph_rst 4>;
+ reset-names = "ipsec";
};
- fsl,vf610-spdif
- fsl,imx6sx-spdif
- fsl,imx8qm-spdif
+ - fsl,imx8qxp-spdif
+ - fsl,imx8mq-spdif
+ - fsl,imx8mm-spdif
+ - fsl,imx8mn-spdif
reg:
maxItems: 1
enum:
- ingenic,jz4740-tcu
- ingenic,jz4725b-tcu
+ - ingenic,jz4760-tcu
+ - ingenic,jz4760b-tcu
- ingenic,jz4770-tcu
- ingenic,jz4780-tcu
- ingenic,x1000-tcu
- enum:
- ingenic,jz4740-tcu
- ingenic,jz4725b-tcu
- - ingenic,jz4770-tcu
+ - ingenic,jz4760-tcu
- ingenic,x1000-tcu
- const: simple-mfd
- items:
- - const: ingenic,jz4780-tcu
- - const: ingenic,jz4770-tcu
+ - enum:
+ - ingenic,jz4780-tcu
+ - ingenic,jz4770-tcu
+ - ingenic,jz4760b-tcu
+ - const: ingenic,jz4760-tcu
- const: simple-mfd
reg:
- items:
- enum:
- ingenic,jz4770-watchdog
+ - ingenic,jz4760b-watchdog
+ - ingenic,jz4760-watchdog
- ingenic,jz4725b-watchdog
- const: ingenic,jz4740-watchdog
- ingenic,jz4725b-pwm
- items:
- enum:
+ - ingenic,jz4760-pwm
+ - ingenic,jz4760b-pwm
- ingenic,jz4770-pwm
- ingenic,jz4780-pwm
- const: ingenic,jz4740-pwm
oneOf:
- enum:
- ingenic,jz4725b-ost
- - ingenic,jz4770-ost
+ - ingenic,jz4760b-ost
- items:
- - const: ingenic,jz4780-ost
- - const: ingenic,jz4770-ost
+ - const: ingenic,jz4760-ost
+ - const: ingenic,jz4725b-ost
+ - items:
+ - enum:
+ - ingenic,jz4780-ost
+ - ingenic,jz4770-ost
+ - const: ingenic,jz4760b-ost
reg:
maxItems: 1
#include <dt-bindings/clock/jz4770-cgu.h>
#include <dt-bindings/clock/ingenic,tcu.h>
tcu: timer@10002000 {
- compatible = "ingenic,jz4770-tcu", "simple-mfd";
+ compatible = "ingenic,jz4770-tcu", "ingenic,jz4760-tcu", "simple-mfd";
reg = <0x10002000 0x1000>;
#address-cells = <1>;
#size-cells = <1>;
};
ost: timer@e0 {
- compatible = "ingenic,jz4770-ost";
+ compatible = "ingenic,jz4770-ost", "ingenic,jz4760b-ost";
reg = <0xe0 0x20>;
clocks = <&tcu TCU_CLK_OST>;
timer counters.
Required properties:
-- compatible : "nuvoton,npcm750-timer" for Poleg NPCM750.
+- compatible : "nuvoton,npcm750-timer" for Poleg NPCM750, or
+ "nuvoton,wpcm450-timer" for Hermon WPCM450.
- reg : Offset and length of the register set for the device.
- interrupts : Contain the timer interrupt of timer 0.
- clocks : phandle of timer reference clock (usually a 25 MHz clock).
- renesas,r8a774e1-cmt0 # 32-bit CMT0 on RZ/G2H
- renesas,r8a7795-cmt0 # 32-bit CMT0 on R-Car H3
- renesas,r8a7796-cmt0 # 32-bit CMT0 on R-Car M3-W
+ - renesas,r8a77961-cmt0 # 32-bit CMT0 on R-Car M3-W+
- renesas,r8a77965-cmt0 # 32-bit CMT0 on R-Car M3-N
- renesas,r8a77970-cmt0 # 32-bit CMT0 on R-Car V3M
- renesas,r8a77980-cmt0 # 32-bit CMT0 on R-Car V3H
- renesas,r8a77990-cmt0 # 32-bit CMT0 on R-Car E3
- renesas,r8a77995-cmt0 # 32-bit CMT0 on R-Car D3
+ - renesas,r8a779a0-cmt0 # 32-bit CMT0 on R-Car V3U
- const: renesas,rcar-gen3-cmt0 # 32-bit CMT0 on R-Car Gen3 and RZ/G2
- items:
- renesas,r8a774e1-cmt1 # 48-bit CMT on RZ/G2H
- renesas,r8a7795-cmt1 # 48-bit CMT on R-Car H3
- renesas,r8a7796-cmt1 # 48-bit CMT on R-Car M3-W
+ - renesas,r8a77961-cmt1 # 48-bit CMT on R-Car M3-W+
- renesas,r8a77965-cmt1 # 48-bit CMT on R-Car M3-N
- renesas,r8a77970-cmt1 # 48-bit CMT on R-Car V3M
- renesas,r8a77980-cmt1 # 48-bit CMT on R-Car V3H
- renesas,r8a77990-cmt1 # 48-bit CMT on R-Car E3
- renesas,r8a77995-cmt1 # 48-bit CMT on R-Car D3
+ - renesas,r8a779a0-cmt1 # 48-bit CMT on R-Car V3U
- const: renesas,rcar-gen3-cmt1 # 48-bit CMT on R-Car Gen3 and RZ/G2
reg:
- renesas,tmu-r8a774e1 # RZ/G2H
- renesas,tmu-r8a7778 # R-Car M1A
- renesas,tmu-r8a7779 # R-Car H1
+ - renesas,tmu-r8a7795 # R-Car H3
+ - renesas,tmu-r8a7796 # R-Car M3-W
+ - renesas,tmu-r8a77961 # R-Car M3-W+
+ - renesas,tmu-r8a77965 # R-Car M3-N
- renesas,tmu-r8a77970 # R-Car V3M
- renesas,tmu-r8a77980 # R-Car V3H
+ - renesas,tmu-r8a77990 # R-Car E3
+ - renesas,tmu-r8a77995 # R-Car D3
- const: renesas,tmu
reg:
Level: Intermediate
+Remove automatic page mapping from dma-buf importing
+----------------------------------------------------
+
+When importing dma-bufs, the dma-buf and PRIME frameworks automatically map
+imported pages into the importer's DMA area. drm_gem_prime_fd_to_handle() and
+drm_gem_prime_handle_to_fd() require that importers call dma_buf_attach()
+even if they never do actual device DMA, but only CPU access through
+dma_buf_vmap(). This is a problem for USB devices, which do not support DMA
+operations.
+
+To fix the issue, automatic page mappings should be removed from the
+buffer-sharing code. Fixing this is a bit more involved, since the import/export
+cache is also tied to &drm_gem_object.import_attach. Meanwhile we paper over
+this problem for USB devices by fishing out the USB host controller device, as
+long as that supports DMA. Otherwise importing can still needlessly fail.
+
+Contact: Thomas Zimmermann <tzimmermann@suse.de>, Daniel Vetter
+
+Level: Advanced
+
+
Better Testing
==============
If use_carrier is 0, then the MII monitor will first query the
device's (via ioctl) MII registers and check the link state. If that
request fails (not just that it returns carrier down), then the MII
-monitor will make an ethtool ETHOOL_GLINK request to attempt to obtain
+monitor will make an ethtool ETHTOOL_GLINK request to attempt to obtain
the same information. If both methods fail (i.e., the driver either
does not support or had some error in processing both the MII register
and ethtool requests), then the MII monitor will assume the link is
Tx
--
-end_start_xmit() is called by the stack. This function does the following:
+ena_start_xmit() is called by the stack. This function does the following:
- Maps data buffers (skb->data and frags).
- Populates ena_buf for the push buffer (if the driver and device are
``devlink-dpipe`` should change according to the changes done by the
standard configuration tools.
-For example, it’s quiet common to implement Access Control Lists (ACL)
+For example, it’s quite common to implement Access Control Lists (ACL)
using Ternary Content Addressable Memory (TCAM). The TCAM memory can be
divided into TCAM regions. Complex TC filters can have multiple rules with
different priorities and different lookup keys. On the other hand hardware
-------------
A subfunction devlink port is created but it is not active yet. That means the
entities are created on devlink side, the e-switch port representor is created,
-but the subfunction device itself it not created. A user might use e-switch port
+but the subfunction device itself is not created. A user might use e-switch port
representor to do settings, putting it into bridge, adding TC rules, etc. A user
might as well configure the hardware address (such as MAC address) of the
subfunction while subfunction is inactive.
* - Term
- Definitions
* - ``PCI device``
- - A physical PCI device having one or more PCI bus consists of one or
+ - A physical PCI device having one or more PCI buses consists of one or
more PCI controllers.
* - ``PCI controller``
- A controller consists of potentially multiple physical functions,
PAUSE_GET
-============
+=========
-Gets channel counts like ``ETHTOOL_GPAUSE`` ioctl request.
+Gets pause frame settings like ``ETHTOOL_GPAUSEPARAM`` ioctl request.
Request contents:
Each member has a corresponding attribute defined.
PAUSE_SET
-============
+=========
Sets pause parameters like ``ETHTOOL_GPAUSEPARAM`` ioctl request.
EEE_GET
=======
-Gets channel counts like ``ETHTOOL_GEEE`` ioctl request.
+Gets Energy Efficient Ethernet settings like ``ETHTOOL_GEEE`` ioctl request.
Request contents:
EEE_SET
=======
-Sets pause parameters like ``ETHTOOL_GEEEPARAM`` ioctl request.
+Sets Energy Efficient Ethernet parameters like ``ETHTOOL_SEEE`` ioctl request.
Request contents:
ip6frag_time - INTEGER
Time in seconds to keep an IPv6 fragment in memory.
-IPv6 Segment Routing:
-
-seg6_flowlabel - INTEGER
- Controls the behaviour of computing the flowlabel of outer
- IPv6 header in case of SR T.encaps
-
- == =======================================================
- -1 set flowlabel to zero.
- 0 copy flowlabel from Inner packet in case of Inner IPv6
- (Set flowlabel to 0 in case IPv4/L2)
- 1 Compute the flowlabel using seg6_make_flowlabel()
- == =======================================================
-
- Default is 0.
-
``conf/default/*``:
Change the interface-specific default settings.
the patches the way they would look like if your latest patch series was to be
merged.
-How can I tell what patches are queued up for backporting to the various stable releases?
------------------------------------------------------------------------------------------
-Normally Greg Kroah-Hartman collects stable commits himself, but for
-networking, Dave collects up patches he deems critical for the
-networking subsystem, and then hands them off to Greg.
-
-There is a patchworks queue that you can see here:
-
- https://patchwork.kernel.org/bundle/netdev/stable/?state=*
-
-It contains the patches which Dave has selected, but not yet handed off
-to Greg. If Greg already has the patch, then it will be here:
-
- https://git.kernel.org/pub/scm/linux/kernel/git/stable/stable-queue.git
-
-A quick way to find whether the patch is in this stable-queue is to
-simply clone the repo, and then git grep the mainline commit ID, e.g.
-::
-
- stable-queue$ git grep -l 284041ef21fdf2e
- releases/3.0.84/ipv6-fix-possible-crashes-in-ip6_cork_release.patch
- releases/3.4.51/ipv6-fix-possible-crashes-in-ip6_cork_release.patch
- releases/3.9.8/ipv6-fix-possible-crashes-in-ip6_cork_release.patch
- stable/stable-queue$
-
-I see a network patch and I think it should be backported to stable. Should I request it via stable@vger.kernel.org like the references in the kernel's Documentation/process/stable-kernel-rules.rst file say?
----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
-No, not for networking. Check the stable queues as per above first
-to see if it is already queued. If not, then send a mail to netdev,
-listing the upstream commit ID and why you think it should be a stable
-candidate.
-
-Before you jump to go do the above, do note that the normal stable rules
-in :ref:`Documentation/process/stable-kernel-rules.rst <stable_kernel_rules>`
-still apply. So you need to explicitly indicate why it is a critical
-fix and exactly what users are impacted. In addition, you need to
-convince yourself that you *really* think it has been overlooked,
-vs. having been considered and rejected.
-
-Generally speaking, the longer it has had a chance to "soak" in
-mainline, the better the odds that it is an OK candidate for stable. So
-scrambling to request a commit be added the day after it appears should
-be avoided.
-
-I have created a network patch and I think it should be backported to stable. Should I add a Cc: stable@vger.kernel.org like the references in the kernel's Documentation/ directory say?
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
-No. See above answer. In short, if you think it really belongs in
-stable, then ensure you write a decent commit log that describes who
-gets impacted by the bug fix and how it manifests itself, and when the
-bug was introduced. If you do that properly, then the commit will get
-handled appropriately and most likely get put in the patchworks stable
-queue if it really warrants it.
-
-If you think there is some valid information relating to it being in
-stable that does *not* belong in the commit log, then use the three dash
-marker line as described in
-:ref:`Documentation/process/submitting-patches.rst <the_canonical_patch_format>`
-to temporarily embed that information into the patch that you send.
-
-Are all networking bug fixes backported to all stable releases?
+Are there special rules regarding stable submissions on netdev?
---------------------------------------------------------------
-Due to capacity, Dave could only take care of the backports for the
-last two stable releases. For earlier stable releases, each stable
-branch maintainer is supposed to take care of them. If you find any
-patch is missing from an earlier stable branch, please notify
-stable@vger.kernel.org with either a commit ID or a formal patch
-backported, and CC Dave and other relevant networking developers.
+While it used to be the case that netdev submissions were not supposed
+to carry explicit ``CC: stable@vger.kernel.org`` tags that is no longer
+the case today. Please follow the standard stable rules in
+:ref:`Documentation/process/stable-kernel-rules.rst <stable_kernel_rules>`,
+and make sure you include appropriate Fixes tags!
Is the comment style convention different for the networking content?
---------------------------------------------------------------------
* 1 - Drop SR packets without HMAC, validate SR packets with HMAC
Default is 0.
+
+seg6_flowlabel - INTEGER
+ Controls the behaviour of computing the flowlabel of outer
+ IPv6 header in case of SR T.encaps
+
+ == =======================================================
+ -1 set flowlabel to zero.
+ 0 copy flowlabel from Inner packet in case of Inner IPv6
+ (Set flowlabel to 0 in case IPv4/L2)
+ 1 Compute the flowlabel using seg6_make_flowlabel()
+ == =======================================================
+
+ Default is 0.
The NIC driver offering ipsec offload will need to implement these
callbacks to make the offload available to the network stack's
-XFRM subsytem. Additionally, the feature bits NETIF_F_HW_ESP and
+XFRM subsystem. Additionally, the feature bits NETIF_F_HW_ESP and
NETIF_F_HW_ESP_TX_CSUM will signal the availability of the offload.
Procedure for submitting patches to the -stable tree
----------------------------------------------------
- - If the patch covers files in net/ or drivers/net please follow netdev stable
- submission guidelines as described in
- :ref:`Documentation/networking/netdev-FAQ.rst <netdev-FAQ>`
- after first checking the stable networking queue at
- https://patchwork.kernel.org/bundle/netdev/stable/?state=*
- to ensure the requested patch is not already queued up.
- Security patches should not be handled (solely) by the -stable review
process but should follow the procedures in
:ref:`Documentation/admin-guide/security-bugs.rst <securitybugs>`.
:ref:`Documentation/process/stable-kernel-rules.rst <stable_kernel_rules>`
in addition to this file.
-Note, however, that some subsystem maintainers want to come to their own
-conclusions on which patches should go to the stable trees. The networking
-maintainer, in particular, would rather not see individual developers
-adding lines like the above to their patches.
-
If changes affect userland-kernel interfaces, please send the MAN-PAGES
maintainer (as listed in the MAINTAINERS file) a man-pages patch, or at
least a notification of the change, so that some information makes its way
key ring service. Both of these new types are variable length symmetric keys,
and in both cases all keys are created in the kernel, and user space sees,
stores, and loads only encrypted blobs. Trusted Keys require the availability
-of a Trusted Platform Module (TPM) chip for greater security, while Encrypted
-Keys can be used on any system. All user level blobs, are displayed and loaded
-in hex ascii for convenience, and are integrity verified.
+of a Trust Source for greater security, while Encrypted Keys can be used on any
+system. All user level blobs, are displayed and loaded in hex ASCII for
+convenience, and are integrity verified.
-Trusted Keys use a TPM both to generate and to seal the keys. Keys are sealed
-under a 2048 bit RSA key in the TPM, and optionally sealed to specified PCR
-(integrity measurement) values, and only unsealed by the TPM, if PCRs and blob
-integrity verifications match. A loaded Trusted Key can be updated with new
-(future) PCR values, so keys are easily migrated to new pcr values, such as
-when the kernel and initramfs are updated. The same key can have many saved
-blobs under different PCR values, so multiple boots are easily supported.
-TPM 1.2
--------
+Trust Source
+============
-By default, trusted keys are sealed under the SRK, which has the default
-authorization value (20 zeros). This can be set at takeownership time with the
-trouser's utility: "tpm_takeownership -u -z".
+A trust source provides the source of security for Trusted Keys. This
+section lists currently supported trust sources, along with their security
+considerations. Whether or not a trust source is sufficiently safe depends
+on the strength and correctness of its implementation, as well as the threat
+environment for a specific use case. Since the kernel doesn't know what the
+environment is, and there is no metric of trust, it is dependent on the
+consumer of the Trusted Keys to determine if the trust source is sufficiently
+safe.
-TPM 2.0
--------
+ * Root of trust for storage
-The user must first create a storage key and make it persistent, so the key is
-available after reboot. This can be done using the following commands.
+ (1) TPM (Trusted Platform Module: hardware device)
+
+ Rooted to Storage Root Key (SRK) which never leaves the TPM that
+ provides crypto operation to establish root of trust for storage.
+
+ (2) TEE (Trusted Execution Environment: OP-TEE based on Arm TrustZone)
+
+ Rooted to Hardware Unique Key (HUK) which is generally burnt in on-chip
+ fuses and is accessible to TEE only.
+
+ * Execution isolation
+
+ (1) TPM
+
+ Fixed set of operations running in isolated execution environment.
+
+ (2) TEE
+
+ Customizable set of operations running in isolated execution
+ environment verified via Secure/Trusted boot process.
+
+ * Optional binding to platform integrity state
+
+ (1) TPM
+
+ Keys can be optionally sealed to specified PCR (integrity measurement)
+ values, and only unsealed by the TPM, if PCRs and blob integrity
+ verifications match. A loaded Trusted Key can be updated with new
+ (future) PCR values, so keys are easily migrated to new PCR values,
+ such as when the kernel and initramfs are updated. The same key can
+ have many saved blobs under different PCR values, so multiple boots are
+ easily supported.
+
+ (2) TEE
+
+ Relies on Secure/Trusted boot process for platform integrity. It can
+ be extended with TEE based measured boot process.
+
+ * Interfaces and APIs
+
+ (1) TPM
+
+ TPMs have well-documented, standardized interfaces and APIs.
+
+ (2) TEE
+
+ TEEs have well-documented, standardized client interface and APIs. For
+ more details refer to ``Documentation/staging/tee.rst``.
+
+
+ * Threat model
+
+ The strength and appropriateness of a particular TPM or TEE for a given
+ purpose must be assessed when using them to protect security-relevant data.
+
+
+Key Generation
+==============
+
+Trusted Keys
+------------
+
+New keys are created from random numbers generated in the trust source. They
+are encrypted/decrypted using a child key in the storage key hierarchy.
+Encryption and decryption of the child key must be protected by a strong
+access control policy within the trust source.
+
+ * TPM (hardware device) based RNG
+
+ Strength of random numbers may vary from one device manufacturer to
+ another.
+
+ * TEE (OP-TEE based on Arm TrustZone) based RNG
+
+ RNG is customizable as per platform needs. It can either be direct output
+ from platform specific hardware RNG or a software based Fortuna CSPRNG
+ which can be seeded via multiple entropy sources.
+
+Encrypted Keys
+--------------
+
+Encrypted keys do not depend on a trust source, and are faster, as they use AES
+for encryption/decryption. New keys are created from kernel-generated random
+numbers, and are encrypted/decrypted using a specified ‘master’ key. The
+‘master’ key can either be a trusted-key or user-key type. The main disadvantage
+of encrypted keys is that if they are not rooted in a trusted key, they are only
+as secure as the user key encrypting them. The master user key should therefore
+be loaded in as secure a way as possible, preferably early in boot.
+
+
+Usage
+=====
+
+Trusted Keys usage: TPM
+-----------------------
+
+TPM 1.2: By default, trusted keys are sealed under the SRK, which has the
+default authorization value (20 bytes of 0s). This can be set at takeownership
+time with the TrouSerS utility: "tpm_takeownership -u -z".
+
+TPM 2.0: The user must first create a storage key and make it persistent, so the
+key is available after reboot. This can be done using the following commands.
With the IBM TSS 2 stack::
Trusted Keys can be 32 - 128 bytes (256 - 1024 bits), the upper limit is to fit
within the 2048 bit SRK (RSA) keylength, with all necessary structure/padding.
-Encrypted keys do not depend on a TPM, and are faster, as they use AES for
-encryption/decryption. New keys are created from kernel generated random
-numbers, and are encrypted/decrypted using a specified 'master' key. The
-'master' key can either be a trusted-key or user-key type. The main
-disadvantage of encrypted keys is that if they are not rooted in a trusted key,
-they are only as secure as the user key encrypting them. The master user key
-should therefore be loaded in as secure a way as possible, preferably early in
-boot.
+Trusted Keys usage: TEE
+-----------------------
+
+Usage::
+
+ keyctl add trusted name "new keylen" ring
+ keyctl add trusted name "load hex_blob" ring
+ keyctl print keyid
+
+"keyctl print" returns an ASCII hex copy of the sealed key, which is in format
+specific to TEE device implementation. The key length for new keys is always
+in bytes. Trusted Keys can be 32 - 128 bytes (256 - 1024 bits).
+
+Encrypted Keys usage
+--------------------
The decrypted portion of encrypted keys can contain either a simple symmetric
key or a more complex structure. The format of the more complex structure is
format:= 'default | ecryptfs | enc32'
key-type:= 'trusted' | 'user'
-
-Examples of trusted and encrypted key usage:
+Examples of trusted and encrypted key usage
+-------------------------------------------
Create and save a trusted key named "kmk" of length 32 bytes.
f1f8fff03ad0acb083725535636addb08d73dedb9832da198081e5deae84bfaf0409c22b
e4a8aea2b607ec96931e6f4d4fe563ba
-Reseal a trusted key under new pcr values::
+Reseal (TPM specific) a trusted key under new PCR values::
$ keyctl update 268728824 "update pcrinfo=`cat pcr.blob`"
$ keyctl print 268728824
7ef6a24defe4846104209bf0c3eced7fa1a672ed5b125fc9d8cd88b476a658a4434644ef
df8ae9a178e9f83ba9f08d10fa47e4226b98b0702f06b3b8
+
The initial consumer of trusted keys is EVM, which at boot time needs a high
-quality symmetric key for HMAC protection of file metadata. The use of a
+quality symmetric key for HMAC protection of file metadata. The use of a
trusted key provides strong guarantees that the EVM key has not been
-compromised by a user level problem, and when sealed to specific boot PCR
-values, protects against boot and offline attacks. Create and save an
+compromised by a user level problem, and when sealed to a platform integrity
+state, protects against boot and offline attacks. Create and save an
encrypted key "evm" using the above trusted key "kmk":
option 1: omitting 'format'::
Another new format 'enc32' has been defined in order to support encrypted keys
with payload size of 32 bytes. This will initially be used for nvdimm security
but may expand to other usages that require 32 bytes payload.
+
+
+TPM 2.0 ASN.1 Key Format
+------------------------
+
+The TPM 2.0 ASN.1 key format is designed to be easily recognisable,
+even in binary form (fixing a problem we had with the TPM 1.2 ASN.1
+format) and to be extensible for additions like importable keys and
+policy::
+
+ TPMKey ::= SEQUENCE {
+ type OBJECT IDENTIFIER
+ emptyAuth [0] EXPLICIT BOOLEAN OPTIONAL
+ parent INTEGER
+ pubkey OCTET STRING
+ privkey OCTET STRING
+ }
+
+type is what distinguishes the key even in binary form since the OID
+is provided by the TCG to be unique and thus forms a recognizable
+binary pattern at offset 3 in the key. The OIDs currently made
+available are::
+
+ 2.23.133.10.1.3 TPM Loadable key. This is an asymmetric key (Usually
+ RSA2048 or Elliptic Curve) which can be imported by a
+ TPM2_Load() operation.
+
+ 2.23.133.10.1.4 TPM Importable Key. This is an asymmetric key (Usually
+ RSA2048 or Elliptic Curve) which can be imported by a
+ TPM2_Import() operation.
+
+ 2.23.133.10.1.5 TPM Sealed Data. This is a set of data (up to 128
+ bytes) which is sealed by the TPM. It usually
+ represents a symmetric key and must be unsealed before
+ use.
+
+The trusted key code only uses the TPM Sealed Data OID.
+
+emptyAuth is true if the key has well known authorization "". If it
+is false or not present, the key requires an explicit authorization
+phrase. This is used by most user space consumers to decide whether
+to prompt for a password.
+
+parent represents the parent key handle, either in the 0x81 MSO space,
+like 0x81000001 for the RSA primary storage key. Userspace programmes
+also support specifying the primary handle in the 0x40 MSO space. If
+this happens the Elliptic Curve variant of the primary key using the
+TCG defined template will be generated on the fly into a volatile
+object and used as the parent. The current kernel code only supports
+the 0x81 MSO form.
+
+pubkey is the binary representation of TPM2B_PRIVATE excluding the
+initial TPM2B header, which can be reconstructed from the ASN.1 octet
+string length.
+
+privkey is the binary representation of TPM2B_PUBLIC excluding the
+initial TPM2B header which can be reconstructed from the ASN.1 octed
+string length.
be retrieved using KVM_CAP_ARM_VM_IPA_SIZE of the KVM_CHECK_EXTENSION
ioctl() at run-time.
+Creation of the VM will fail if the requested IPA size (whether it is
+implicit or explicit) is unsupported on the host.
+
Please note that configuring the IPA size does not affect the capability
exposed by the guest CPUs in ID_AA64MMFR0_EL1[PARange]. It only affects
size of the address translated by the stage2 level (guest physical to
Define which vcpu is the Bootstrap Processor (BSP). Values are the same
as the vcpu id in KVM_CREATE_VCPU. If this ioctl is not called, the default
-is vcpu 0.
+is vcpu 0. This ioctl has to be called before vcpu creation,
+otherwise it will return EBUSY error.
4.42 KVM_GET_XSAVE
allows user space to deflect and potentially handle various MSR accesses
into user space.
-If a vCPU is in running state while this ioctl is invoked, the vCPU may
-experience inconsistent filtering behavior on MSR accesses.
+Note, invoking this ioctl with a vCPU is running is inherently racy. However,
+KVM does guarantee that vCPUs will see either the previous filter or the new
+filter, e.g. MSRs with identical settings in both the old and new filter will
+have deterministic behavior.
4.127 KVM_XEN_HVM_SET_ATTR
--------------------------
configured with a library OS and run-time which permits the application to run.
The enclave run-time and library OS work together to execute the application
when a thread enters the enclave.
+
+Impact of Potential Kernel SGX Bugs
+===================================
+
+EPC leaks
+---------
+
+When EPC page leaks happen, a WARNING like this is shown in dmesg:
+
+"EREMOVE returned ... and an EPC page was leaked. SGX may become unusable..."
+
+This is effectively a kernel use-after-free of an EPC page, and due
+to the way SGX works, the bug is detected at freeing. Rather than
+adding the page back to the pool of available EPC pages, the kernel
+intentionally leaks the page to avoid additional errors in the future.
+
+When this happens, the kernel will likely soon leak more EPC pages, and
+SGX will likely become unusable because the memory available to SGX is
+limited. However, while this may be fatal to SGX, the rest of the kernel
+is unlikely to be impacted and should continue to work.
+
+As a result, when this happpens, user should stop running any new
+SGX workloads, (or just any new workloads), and migrate all valuable
+workloads. Although a machine reboot can recover all EPC memory, the bug
+should be reported to Linux developers.
+
+
+Virtual EPC
+===========
+
+The implementation has also a virtual EPC driver to support SGX enclaves
+in guests. Unlike the SGX driver, an EPC page allocated by the virtual
+EPC driver doesn't have a specific enclave associated with it. This is
+because KVM doesn't track how a guest uses EPC pages.
+
+As a result, the SGX core page reclaimer doesn't support reclaiming EPC
+pages allocated to KVM guests through the virtual EPC driver. If the
+user wants to deploy SGX applications both on the host and in guests
+on the same machine, the user should reserve enough EPC (by taking out
+total virtual EPC size of all SGX VMs from the physical EPC size) for
+host SGX applications so they can run with acceptable performance.
L: linux-api@vger.kernel.org
F: include/linux/syscalls.h
F: kernel/sys_ni.c
-F: include/uapi/
-F: arch/*/include/uapi/
+X: include/uapi/
+X: arch/*/include/uapi/
ABIT UGURU 1,2 HARDWARE MONITOR DRIVER
M: Hans de Goede <hdegoede@redhat.com>
M: Christian Brauner <christian@brauner.io>
M: Hridya Valsaraju <hridya@google.com>
M: Suren Baghdasaryan <surenb@google.com>
-L: devel@driverdev.osuosl.org
+L: linux-kernel@vger.kernel.org
S: Supported
T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging.git
F: drivers/android/
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/sunxi/linux.git
+L: linux-sunxi@lists.linux.dev
F: arch/arm/mach-sunxi/
F: arch/arm64/boot/dts/allwinner/
F: drivers/clk/sunxi-ng/
F: drivers/pinctrl/sunxi/
F: drivers/soc/sunxi/
+N: allwinner
N: sun[x456789]i
N: sun50i
F: drivers/pinctrl/pinctrl-gemini.c
F: drivers/rtc/rtc-ftrtc010.c
-ARM/CZ.NIC TURRIS MOX SUPPORT
-M: Marek Behun <marek.behun@nic.cz>
+ARM/CZ.NIC TURRIS SUPPORT
+M: Marek Behun <kabel@kernel.org>
S: Maintained
-W: http://mox.turris.cz
+W: https://www.turris.cz/
F: Documentation/ABI/testing/debugfs-moxtet
F: Documentation/ABI/testing/sysfs-bus-moxtet-devices
F: Documentation/ABI/testing/sysfs-firmware-turris-mox-rwtm
F: Documentation/devicetree/bindings/bus/moxtet.txt
F: Documentation/devicetree/bindings/firmware/cznic,turris-mox-rwtm.txt
F: Documentation/devicetree/bindings/gpio/gpio-moxtet.txt
+F: Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml
+F: Documentation/devicetree/bindings/watchdog/armada-37xx-wdt.txt
F: drivers/bus/moxtet.c
F: drivers/firmware/turris-mox-rwtm.c
+F: drivers/leds/leds-turris-omnia.c
+F: drivers/mailbox/armada-37xx-rwtm-mailbox.c
F: drivers/gpio/gpio-moxtet.c
+F: drivers/watchdog/armada_37xx_wdt.c
+F: include/dt-bindings/bus/moxtet.h
+F: include/linux/armada-37xx-rwtm-mailbox.h
F: include/linux/moxtet.h
ARM/EZX SMARTPHONES (A780, A910, A1200, E680, ROKR E2 and ROKR E6)
N: sc2731
ARM/STI ARCHITECTURE
-M: Patrice Chotard <patrice.chotard@st.com>
+M: Patrice Chotard <patrice.chotard@foss.st.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
W: http://www.stlinux.com
ARM/STM32 ARCHITECTURE
M: Maxime Coquelin <mcoquelin.stm32@gmail.com>
-M: Alexandre Torgue <alexandre.torgue@st.com>
+M: Alexandre Torgue <alexandre.torgue@foss.st.com>
L: linux-stm32@st-md-mailman.stormreply.com (moderated for non-subscribers)
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
F: drivers/md/bcache/
BDISP ST MEDIA DRIVER
-M: Fabien Dessenne <fabien.dessenne@st.com>
+M: Fabien Dessenne <fabien.dessenne@foss.st.com>
L: linux-media@vger.kernel.org
S: Supported
W: https://linuxtv.org
L: linux-pm@vger.kernel.org
S: Maintained
T: git git://github.com/broadcom/stblinux.git
-F: drivers/soc/bcm/bcm-pmb.c
+F: drivers/soc/bcm/bcm63xx/bcm-pmb.c
F: include/dt-bindings/soc/bcm-pmb.h
BROADCOM SPECIFIC AMBA DRIVER (BCMA)
F: drivers/platform/x86/dell/dell-wmi.c
DELTA ST MEDIA DRIVER
-M: Hugues Fruchet <hugues.fruchet@st.com>
+M: Hugues Fruchet <hugues.fruchet@foss.st.com>
L: linux-media@vger.kernel.org
S: Supported
W: https://linuxtv.org
M: Daniel Vetter <daniel@ffwll.ch>
L: dri-devel@lists.freedesktop.org
S: Maintained
-B: https://bugs.freedesktop.org/
+B: https://gitlab.freedesktop.org/drm
C: irc://chat.freenode.net/dri-devel
T: git git://anongit.freedesktop.org/drm/drm
F: Documentation/devicetree/bindings/display/
DRM DRIVERS FOR STI
M: Benjamin Gaignard <benjamin.gaignard@linaro.org>
-M: Vincent Abriou <vincent.abriou@st.com>
L: dri-devel@lists.freedesktop.org
S: Maintained
T: git git://anongit.freedesktop.org/drm/drm-misc
F: drivers/gpu/drm/sti
DRM DRIVERS FOR STM
-M: Yannick Fertre <yannick.fertre@st.com>
-M: Philippe Cornu <philippe.cornu@st.com>
+M: Yannick Fertre <yannick.fertre@foss.st.com>
+M: Philippe Cornu <philippe.cornu@foss.st.com>
M: Benjamin Gaignard <benjamin.gaignard@linaro.org>
-M: Vincent Abriou <vincent.abriou@st.com>
L: dri-devel@lists.freedesktop.org
S: Maintained
T: git git://anongit.freedesktop.org/drm/drm-misc
F: drivers/i2c/busses/i2c-cpm.c
FREESCALE IMX / MXC FEC DRIVER
-M: Fugang Duan <fugang.duan@nxp.com>
+M: Joakim Zhang <qiangqing.zhang@nxp.com>
L: netdev@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/net/fsl-fec.txt
GENERIC PHY FRAMEWORK
M: Kishon Vijay Abraham I <kishon@ti.com>
M: Vinod Koul <vkoul@kernel.org>
-L: linux-kernel@vger.kernel.org
+L: linux-phy@lists.infradead.org
S: Supported
+Q: https://patchwork.kernel.org/project/linux-phy/list/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/phy/linux-phy.git
F: Documentation/devicetree/bindings/phy/
F: drivers/phy/
HISILICON STAGING DRIVERS FOR HIKEY 960/970
M: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
-L: devel@driverdev.osuosl.org
S: Maintained
F: drivers/staging/hikey9xx/
F: mm/hugetlb.c
HVA ST MEDIA DRIVER
-M: Jean-Christophe Trotin <jean-christophe.trotin@st.com>
+M: Jean-Christophe Trotin <jean-christophe.trotin@foss.st.com>
L: linux-media@vger.kernel.org
S: Supported
W: https://linuxtv.org
IBM Power SRIOV Virtual NIC Device Driver
M: Dany Madden <drt@linux.ibm.com>
-M: Lijun Pan <ljp@linux.ibm.com>
M: Sukadev Bhattiprolu <sukadev@linux.ibm.com>
+R: Thomas Falcon <tlfalcon@linux.ibm.com>
+R: Lijun Pan <lijunp213@gmail.com>
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/ethernet/ibm/ibmvnic.*
F: include/linux/ide.h
IDE/ATAPI DRIVERS
-M: Borislav Petkov <bp@alien8.de>
L: linux-ide@vger.kernel.org
-S: Maintained
+S: Orphan
F: Documentation/cdrom/ide-cd.rst
F: drivers/ide/ide-cd*
T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/sgx
F: Documentation/x86/sgx.rst
F: arch/x86/entry/vdso/vsgx.S
+F: arch/x86/include/asm/sgx.h
F: arch/x86/include/uapi/asm/sgx.h
F: arch/x86/kernel/cpu/sgx/*
F: tools/testing/selftests/sgx/*
F: include/keys/trusted_tpm.h
F: security/keys/trusted-keys/
+KEYS-TRUSTED-TEE
+M: Sumit Garg <sumit.garg@linaro.org>
+L: linux-integrity@vger.kernel.org
+L: keyrings@vger.kernel.org
+S: Supported
+F: include/keys/trusted_tee.h
+F: security/keys/trusted-keys/trusted_tee.c
+
KEYS/KEYRINGS
M: David Howells <dhowells@redhat.com>
M: Jarkko Sakkinen <jarkko@kernel.org>
LED SUBSYSTEM
M: Pavel Machek <pavel@ucw.cz>
-R: Dan Murphy <dmurphy@ti.com>
L: linux-leds@vger.kernel.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/pavel/linux-leds.git
MARVELL MWIFIEX WIRELESS DRIVER
M: Amitkumar Karwar <amitkarwar@gmail.com>
-M: Ganapathi Bhat <ganapathi.bhat@nxp.com>
+M: Ganapathi Bhat <ganapathi017@gmail.com>
+M: Sharvari Harisangam <sharvari.harisangam@nxp.com>
M: Xinming Hu <huxinming820@gmail.com>
L: linux-wireless@vger.kernel.org
S: Maintained
F: drivers/media/radio/radio-maxiradio*
MCAN MMIO DEVICE DRIVER
-M: Dan Murphy <dmurphy@ti.com>
M: Pankaj Sharma <pankj.sharma@samsung.com>
L: linux-can@vger.kernel.org
S: Maintained
F: drivers/media/dvb-frontends/stv6111*
MEDIA DRIVERS FOR STM32 - DCMI
-M: Hugues Fruchet <hugues.fruchet@st.com>
+M: Hugues Fruchet <hugues.fruchet@foss.st.com>
L: linux-media@vger.kernel.org
S: Supported
T: git git://linuxtv.org/media_tree.git
M: Mat Martineau <mathew.j.martineau@linux.intel.com>
M: Matthieu Baerts <matthieu.baerts@tessares.net>
L: netdev@vger.kernel.org
-L: mptcp@lists.01.org
+L: mptcp@lists.linux.dev
S: Maintained
W: https://github.com/multipath-tcp/mptcp_net-next/wiki
B: https://github.com/multipath-tcp/mptcp_net-next/issues
QLOGIC QLGE 10Gb ETHERNET DRIVER
M: Manish Chopra <manishc@marvell.com>
M: GR-Linux-NIC-Dev@marvell.com
-L: netdev@vger.kernel.org
-S: Supported
-F: drivers/staging/qlge/
-
-QLOGIC QLGE 10Gb ETHERNET DRIVER
M: Coiby Xu <coiby.xu@gmail.com>
L: netdev@vger.kernel.org
-S: Maintained
+S: Supported
F: Documentation/networking/device_drivers/qlogic/qlge.rst
+F: drivers/staging/qlge/
QM1D1B0004 MEDIA DRIVER
M: Akihiro Tsukada <tskd08@gmail.com>
S: Maintained
F: drivers/iommu/arm/arm-smmu/qcom_iommu.c
+QUALCOMM IPC ROUTER (QRTR) DRIVER
+M: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+L: linux-arm-msm@vger.kernel.org
+S: Maintained
+F: include/trace/events/qrtr.h
+F: include/uapi/linux/qrtr.h
+F: net/qrtr/
+
QUALCOMM IPCC MAILBOX DRIVER
M: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
L: linux-arm-msm@vger.kernel.org
REMOTE PROCESSOR (REMOTEPROC) SUBSYSTEM
M: Ohad Ben-Cohen <ohad@wizery.com>
M: Bjorn Andersson <bjorn.andersson@linaro.org>
+M: Mathieu Poirier <mathieu.poirier@linaro.org>
L: linux-remoteproc@vger.kernel.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/andersson/remoteproc.git rproc-next
REMOTE PROCESSOR MESSAGING (RPMSG) SUBSYSTEM
M: Ohad Ben-Cohen <ohad@wizery.com>
M: Bjorn Andersson <bjorn.andersson@linaro.org>
+M: Mathieu Poirier <mathieu.poirier@linaro.org>
L: linux-remoteproc@vger.kernel.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/andersson/remoteproc.git rpmsg-next
S390 VFIO AP DRIVER
M: Tony Krowiak <akrowiak@linux.ibm.com>
-M: Pierre Morel <pmorel@linux.ibm.com>
M: Halil Pasic <pasic@linux.ibm.com>
+M: Jason Herne <jjherne@linux.ibm.com>
L: linux-s390@vger.kernel.org
S: Supported
W: http://www.ibm.com/developerworks/linux/linux390/
S390 VFIO-CCW DRIVER
M: Cornelia Huck <cohuck@redhat.com>
M: Eric Farman <farman@linux.ibm.com>
+M: Matthew Rosato <mjrosato@linux.ibm.com>
R: Halil Pasic <pasic@linux.ibm.com>
L: linux-s390@vger.kernel.org
L: kvm@vger.kernel.org
S390 VFIO-PCI DRIVER
M: Matthew Rosato <mjrosato@linux.ibm.com>
+M: Eric Farman <farman@linux.ibm.com>
L: linux-s390@vger.kernel.org
L: kvm@vger.kernel.org
S: Supported
SPIDERNET NETWORK DRIVER for CELL
M: Ishizaki Kou <kou.ishizaki@toshiba.co.jp>
+M: Geoff Levand <geoff@infradead.org>
L: netdev@vger.kernel.org
-S: Supported
+L: linuxppc-dev@lists.ozlabs.org
+S: Maintained
F: Documentation/networking/device_drivers/ethernet/toshiba/spider_net.rst
F: drivers/net/ethernet/toshiba/spider_net*
F: drivers/media/i2c/st-mipid02.c
ST STM32 I2C/SMBUS DRIVER
-M: Pierre-Yves MORDRET <pierre-yves.mordret@st.com>
+M: Pierre-Yves MORDRET <pierre-yves.mordret@foss.st.com>
+M: Alain Volmat <alain.volmat@foss.st.com>
L: linux-i2c@vger.kernel.org
S: Maintained
F: drivers/i2c/busses/i2c-stm32*
STAGING SUBSYSTEM
M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-L: devel@driverdev.osuosl.org
+L: linux-staging@lists.linux.dev
S: Supported
T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging.git
F: drivers/staging/
F: kernel/static_call.c
STI AUDIO (ASoC) DRIVERS
-M: Arnaud Pouliquen <arnaud.pouliquen@st.com>
+M: Arnaud Pouliquen <arnaud.pouliquen@foss.st.com>
L: alsa-devel@alsa-project.org (moderated for non-subscribers)
S: Maintained
F: Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt
F: drivers/media/usb/stk1160/
STM32 AUDIO (ASoC) DRIVERS
-M: Olivier Moysan <olivier.moysan@st.com>
-M: Arnaud Pouliquen <arnaud.pouliquen@st.com>
+M: Olivier Moysan <olivier.moysan@foss.st.com>
+M: Arnaud Pouliquen <arnaud.pouliquen@foss.st.com>
L: alsa-devel@alsa-project.org (moderated for non-subscribers)
S: Maintained
F: Documentation/devicetree/bindings/iio/adc/st,stm32-*.yaml
F: sound/soc/stm/
STM32 TIMER/LPTIMER DRIVERS
-M: Fabrice Gasnier <fabrice.gasnier@st.com>
+M: Fabrice Gasnier <fabrice.gasnier@foss.st.com>
S: Maintained
F: Documentation/ABI/testing/*timer-stm32
F: Documentation/devicetree/bindings/*/*stm32-*timer*
STMMAC ETHERNET DRIVER
M: Giuseppe Cavallaro <peppe.cavallaro@st.com>
-M: Alexandre Torgue <alexandre.torgue@st.com>
+M: Alexandre Torgue <alexandre.torgue@foss.st.com>
M: Jose Abreu <joabreu@synopsys.com>
L: netdev@vger.kernel.org
S: Supported
F: drivers/thermal/ti-soc-thermal/
TI BQ27XXX POWER SUPPLY DRIVER
-R: Dan Murphy <dmurphy@ti.com>
F: drivers/power/supply/bq27xxx_battery.c
F: drivers/power/supply/bq27xxx_battery_i2c.c
F: include/linux/power/bq27xxx_battery.h
F: sound/soc/codecs/tas571x*
TI TCAN4X5X DEVICE DRIVER
-M: Dan Murphy <dmurphy@ti.com>
L: linux-can@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/net/can/tcan4x5x.txt
M: Martyn Welch <martyn@welchs.me.uk>
M: Manohar Vanga <manohar.vanga@gmail.com>
M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-L: devel@driverdev.osuosl.org
+L: linux-kernel@vger.kernel.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git
F: Documentation/driver-api/vme.rst
F: drivers/infiniband/hw/vmw_pvrdma/
VMware PVSCSI driver
-M: Jim Gill <jgill@vmware.com>
+M: Vishal Bhakta <vbhakta@vmware.com>
M: VMware PV-Drivers <pv-drivers@vmware.com>
L: linux-scsi@vger.kernel.org
S: Maintained
VERSION = 5
PATCHLEVEL = 12
SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION =
NAME = Frozen Wasteland
# *DOCUMENTATION*
$(version_h) headers headers_% archheaders archscripts \
%asm-generic kernelversion %src-pkg dt_binding_check \
outputmakefile
-no-sync-config-targets := $(no-dot-config-targets) %install kernelrelease
+no-sync-config-targets := $(no-dot-config-targets) %install kernelrelease \
+ image_name
single-targets := %.a %.i %.ko %.lds %.ll %.lst %.mod %.o %.s %.symtypes %/
config-build :=
-I$(objtree)/arch/$(SRCARCH)/include/generated/uapi \
-I$(srctree)/include/uapi \
-I$(objtree)/include/generated/uapi \
+ -include $(srctree)/include/linux/compiler-version.h \
-include $(srctree)/include/linux/kconfig.h
# Use LINUXINCLUDE when you must reference the include/ directory.
KBUILD_CFLAGS += -enable-trivial-auto-var-init-zero-knowing-it-will-be-removed-from-clang
endif
+# While VLAs have been removed, GCC produces unreachable stack probes
+# for the randomize_kstack_offset feature. Disable it for all compilers.
+KBUILD_CFLAGS += $(call cc-option, -fno-stack-clash-protection)
+
DEBUG_CFLAGS :=
# Workaround for GCC versions < 5.0
def_bool y
# Clang >= 11: https://github.com/ClangBuiltLinux/linux/issues/510
depends on CC_IS_CLANG && CLANG_VERSION >= 110000 && LD_IS_LLD
- depends on $(success,test $(LLVM) -eq 1)
depends on $(success,test $(LLVM_IAS) -eq 1)
depends on $(success,$(NM) --help | head -n 1 | grep -qi llvm)
depends on $(success,$(AR) --help | head -n 1 | grep -qi llvm)
depends on ARCH_SUPPORTS_LTO_CLANG
depends on !FTRACE_MCOUNT_USE_RECORDMCOUNT
- depends on !KASAN
+ depends on !KASAN || KASAN_HW_TAGS
depends on !GCOV_KERNEL
help
The compiler and Kconfig options support building with Clang's
backing virtual mappings with real shadow memory, and KASAN_VMALLOC
must be enabled.
+config HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
+ def_bool n
+ help
+ An arch should select this symbol if it can support kernel stack
+ offset randomization with calls to add_random_kstack_offset()
+ during syscall entry and choose_random_kstack_offset() during
+ syscall exit. Careful removal of -fstack-protector-strong and
+ -fstack-protector should also be applied to the entry code and
+ closely examined, as the artificial stack bump looks like an array
+ to the compiler, so it will attempt to add canary checks regardless
+ of the static branch state.
+
+config RANDOMIZE_KSTACK_OFFSET_DEFAULT
+ bool "Randomize kernel stack offset on syscall entry"
+ depends on HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
+ help
+ The kernel stack offset can be randomized (after pt_regs) by
+ roughly 5 bits of entropy, frustrating memory corruption
+ attacks that depend on stack address determinism or
+ cross-syscall address exposures. This feature is controlled
+ by kernel boot param "randomize_kstack_offset=on/off", and this
+ config chooses the default boot state.
+
config ARCH_OPTIONAL_KERNEL_RWX
def_bool n
memory {
device_type = "memory";
/* CONFIG_LINUX_RAM_BASE needs to match low mem start */
- reg = <0x0 0x80000000 0x0 0x20000000 /* 512 MB low mem */
+ reg = <0x0 0x80000000 0x0 0x40000000 /* 1 GB low mem */
0x1 0x00000000 0x0 0x40000000>; /* 1 GB highmem */
};
sizeof(sf->uc.uc_mcontext.regs.scratch));
err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(sigset_t));
- return err;
+ return err ? -EFAULT : 0;
}
static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf)
&(sf->uc.uc_mcontext.regs.scratch),
sizeof(sf->uc.uc_mcontext.regs.scratch));
if (err)
- return err;
+ return -EFAULT;
set_current_blocked(&set);
regs->bta = uregs.scratch.bta;
const void *table_start, unsigned long table_size,
const u8 *header_start, unsigned long header_size)
{
- const u8 *ptr = header_start + 4;
- const u8 *end = header_start + header_size;
-
table->core.pc = (unsigned long)core_start;
table->core.range = core_size;
table->init.pc = (unsigned long)init_start;
table->init.range = init_size;
table->address = table_start;
table->size = table_size;
-
- /* See if the linker provided table looks valid. */
- if (header_size <= 4
- || header_start[0] != 1
- || (void *)read_pointer(&ptr, end, header_start[1]) != table_start
- || header_start[2] == DW_EH_PE_omit
- || read_pointer(&ptr, end, header_start[2]) <= 0
- || header_start[3] == DW_EH_PE_omit)
- header_start = NULL;
-
+ /* To avoid the pointer addition with NULL pointer.*/
+ if (header_start != NULL) {
+ const u8 *ptr = header_start + 4;
+ const u8 *end = header_start + header_size;
+ /* See if the linker provided table looks valid. */
+ if (header_size <= 4
+ || header_start[0] != 1
+ || (void *)read_pointer(&ptr, end, header_start[1])
+ != table_start
+ || header_start[2] == DW_EH_PE_omit
+ || read_pointer(&ptr, end, header_start[2]) <= 0
+ || header_start[3] == DW_EH_PE_omit)
+ header_start = NULL;
+ }
table->hdrsz = header_size;
smp_wmb();
table->header = header_start;
select ARM_AMBA
imply ARM_PATCH_PHYS_VIRT
select ARM_VIC
+ select GENERIC_IRQ_MULTI_HANDLER
select AUTO_ZRELADDR
select CLKDEV_LOOKUP
select CLKSRC_MMIO
config NR_CPUS
int "Maximum number of CPUs (2-32)"
- range 2 32
+ range 2 16 if DEBUG_KMAP_LOCAL
+ range 2 32 if !DEBUG_KMAP_LOCAL
depends on SMP
default "4"
+ help
+ The maximum number of CPUs that the kernel can support.
+ Up to 32 CPUs can be supported, or up to 16 if kmap_local()
+ debugging is enabled, which uses half of the per-CPU fixmap
+ slots as guard regions.
config HOTPLUG_CPU
bool "Support for hot-pluggable CPUs"
ethernet1 = &cpsw_emac1;
spi0 = &spi0;
spi1 = &spi1;
+ mmc0 = &mmc1;
+ mmc1 = &mmc2;
+ mmc2 = &mmc3;
};
cpus {
ranges = <MBUS_ID(0xf0, 0x01) 0 0xf1000000 0x100000
MBUS_ID(0x01, 0x1d) 0 0xfff00000 0x100000
MBUS_ID(0x09, 0x19) 0 0xf1100000 0x10000
- MBUS_ID(0x09, 0x15) 0 0xf1110000 0x10000>;
+ MBUS_ID(0x09, 0x15) 0 0xf1110000 0x10000
+ MBUS_ID(0x0c, 0x04) 0 0xf1200000 0x100000>;
internal-regs {
phy1: ethernet-phy@1 {
compatible = "ethernet-phy-ieee802.3-c22";
reg = <1>;
+ marvell,reg-init = <3 18 0 0x4985>;
/* irq is connected to &pcawan pin 7 */
};
};
&pinctrl {
- atmel,mux-mask = <
- /* A B C */
- 0xFFFFFE7F 0xC0E0397F 0xEF00019D /* pioA */
- 0x03FFFFFF 0x02FC7E68 0x00780000 /* pioB */
- 0xffffffff 0xF83FFFFF 0xB800F3FC /* pioC */
- 0x003FFFFF 0x003F8000 0x00000000 /* pioD */
- >;
-
adc {
pinctrl_adc_default: adc_default {
atmel,pins = <AT91_PIOB 15 AT91_PERIPH_A AT91_PINCTRL_NONE>;
pinctrl-0 = <&pinctrl_macb0_default>;
phy-mode = "rmii";
- ethernet-phy@0 {
- reg = <0x0>;
+ ethernet-phy@7 {
+ reg = <0x7>;
interrupt-parent = <&pioA>;
interrupts = <PIN_PD31 IRQ_TYPE_LEVEL_LOW>;
pinctrl-names = "default";
#reset-cells = <1>;
};
- bsc_intr: interrupt-controller@7ef00040 {
- compatible = "brcm,bcm2711-l2-intc", "brcm,l2-intc";
- reg = <0x7ef00040 0x30>;
- interrupts = <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>;
- interrupt-controller;
- #interrupt-cells = <1>;
- };
-
aon_intr: interrupt-controller@7ef00100 {
compatible = "brcm,bcm2711-l2-intc", "brcm,l2-intc";
reg = <0x7ef00100 0x30>;
reg = <0x7ef04500 0x100>, <0x7ef00b00 0x300>;
reg-names = "bsc", "auto-i2c";
clock-frequency = <97500>;
- interrupt-parent = <&bsc_intr>;
- interrupts = <0>;
status = "disabled";
};
reg = <0x7ef09500 0x100>, <0x7ef05b00 0x300>;
reg-names = "bsc", "auto-i2c";
clock-frequency = <97500>;
- interrupt-parent = <&bsc_intr>;
- interrupts = <1>;
status = "disabled";
};
};
};
};
- target-module@34000 { /* 0x48034000, ap 7 46.0 */
+ timer3_target: target-module@34000 { /* 0x48034000, ap 7 46.0 */
compatible = "ti,sysc-omap4-timer", "ti,sysc";
reg = <0x34000 0x4>,
<0x34010 0x4>;
};
};
- target-module@36000 { /* 0x48036000, ap 9 4e.0 */
+ timer4_target: target-module@36000 { /* 0x48036000, ap 9 4e.0 */
compatible = "ti,sysc-omap4-timer", "ti,sysc";
reg = <0x36000 0x4>,
<0x36010 0x4>;
timer {
compatible = "arm,armv7-timer";
+ status = "disabled"; /* See ARM architected timer wrap erratum i940 */
interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
<GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
<GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
assigned-clock-parents = <&sys_32k_ck>;
};
};
+
+/* Local timers, see ARM architected timer wrap erratum i940 */
+&timer3_target {
+ ti,no-reset-on-init;
+ ti,no-idle;
+ timer@0 {
+ assigned-clocks = <&l4per_clkctrl DRA7_L4PER_TIMER3_CLKCTRL 24>;
+ assigned-clock-parents = <&timer_sys_clk_div>;
+ };
+};
+
+&timer4_target {
+ ti,no-reset-on-init;
+ ti,no-idle;
+ timer@0 {
+ assigned-clocks = <&l4per_clkctrl DRA7_L4PER_TIMER4_CLKCTRL 24>;
+ assigned-clock-parents = <&timer_sys_clk_div>;
+ };
+};
pinctrl-0 = <&pinctrl_usdhc2>;
cd-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
wp-gpios = <&gpio1 2 GPIO_ACTIVE_HIGH>;
+ vmmc-supply = <&vdd_sd1_reg>;
status = "disabled";
};
&pinctrl_usdhc3_cdwp>;
cd-gpios = <&gpio1 27 GPIO_ACTIVE_LOW>;
wp-gpios = <&gpio1 29 GPIO_ACTIVE_HIGH>;
+ vmmc-supply = <&vdd_sd0_reg>;
status = "disabled";
};
micrel,led-mode = <1>;
clocks = <&clks IMX6UL_CLK_ENET_REF>;
clock-names = "rmii-ref";
- reset-gpios = <&gpio_spi 1 GPIO_ACTIVE_LOW>;
- reset-assert-us = <10000>;
- reset-deassert-us = <100>;
};
micrel,led-mode = <1>;
clocks = <&clks IMX6UL_CLK_ENET2_REF>;
clock-names = "rmii-ref";
- reset-gpios = <&gpio_spi 2 GPIO_ACTIVE_LOW>;
- reset-assert-us = <10000>;
- reset-deassert-us = <100>;
};
};
};
status = "okay";
};
+&gpio_spi {
+ eth0-phy-hog {
+ gpio-hog;
+ gpios = <1 GPIO_ACTIVE_HIGH>;
+ output-high;
+ line-name = "eth0-phy";
+ };
+
+ eth1-phy-hog {
+ gpio-hog;
+ gpios = <2 GPIO_ACTIVE_HIGH>;
+ output-high;
+ line-name = "eth1-phy";
+ };
+};
+
&i2c1 {
clock-frequency = <100000>;
pinctrl-names = "default";
};
&gpmi {
+ fsl,use-minimum-ecc;
status = "okay";
};
i2c0 = &i2c1;
i2c1 = &i2c2;
i2c2 = &i2c3;
+ mmc0 = &mmc1;
+ mmc1 = &mmc2;
+ mmc2 = &mmc3;
serial0 = &uart1;
serial1 = &uart2;
serial2 = &uart3;
i2c1 = &i2c2;
i2c2 = &i2c3;
i2c3 = &i2c4;
+ mmc0 = &mmc1;
+ mmc1 = &mmc2;
+ mmc2 = &mmc3;
+ mmc3 = &mmc4;
+ mmc4 = &mmc5;
serial0 = &uart1;
serial1 = &uart2;
serial2 = &uart3;
ti,max-div = <2>;
};
- sha2md5_fck: sha2md5_fck@15c8 {
- #clock-cells = <0>;
- compatible = "ti,gate-clock";
- clocks = <&l3_div_ck>;
- ti,bit-shift = <1>;
- reg = <0x15c8>;
- };
-
usb_phy_cm_clk32k: usb_phy_cm_clk32k@640 {
#clock-cells = <0>;
compatible = "ti,gate-clock";
i2c2 = &i2c3;
i2c3 = &i2c4;
i2c4 = &i2c5;
+ mmc0 = &mmc1;
+ mmc1 = &mmc2;
+ mmc2 = &mmc3;
+ mmc3 = &mmc4;
+ mmc4 = &mmc5;
serial0 = &uart1;
serial1 = &uart2;
serial2 = &uart3;
compatible = "microchip,sam9x60-pinctrl", "atmel,at91sam9x5-pinctrl", "atmel,at91rm9200-pinctrl", "simple-bus";
ranges = <0xfffff400 0xfffff400 0x800>;
+ /* mux-mask corresponding to sam9x60 SoC in TFBGA228L package */
+ atmel,mux-mask = <
+ /* A B C */
+ 0xffffffff 0xffe03fff 0xef00019d /* pioA */
+ 0x03ffffff 0x02fc7e7f 0x00780000 /* pioB */
+ 0xffffffff 0xffffffff 0xf83fffff /* pioC */
+ 0x003fffff 0x003f8000 0x00000000 /* pioD */
+ >;
+
pioA: gpio@fffff400 {
compatible = "microchip,sam9x60-gpio", "atmel,at91sam9x5-gpio", "atmel,at91rm9200-gpio";
reg = <0xfffff400 0x200>;
__hround \out2, \out3, \in2, \in1, \in0, \in3, \in1, \in0, 0, \sz, \op, \oldcpsr
.endm
- .macro __rev, out, in
- .if __LINUX_ARM_ARCH__ < 6
- lsl t0, \in, #24
- and t1, \in, #0xff00
- and t2, \in, #0xff0000
- orr \out, t0, \in, lsr #24
- orr \out, \out, t1, lsl #8
- orr \out, \out, t2, lsr #8
- .else
- rev \out, \in
- .endif
- .endm
-
- .macro __adrl, out, sym, c
- .if __LINUX_ARM_ARCH__ < 7
- ldr\c \out, =\sym
- .else
- movw\c \out, #:lower16:\sym
- movt\c \out, #:upper16:\sym
- .endif
- .endm
-
.macro do_crypt, round, ttab, ltab, bsz
push {r3-r11, lr}
ldr r7, [in, #12]
#ifdef CONFIG_CPU_BIG_ENDIAN
- __rev r4, r4
- __rev r5, r5
- __rev r6, r6
- __rev r7, r7
+ rev_l r4, t0
+ rev_l r5, t0
+ rev_l r6, t0
+ rev_l r7, t0
#endif
eor r4, r4, r8
eor r6, r6, r10
eor r7, r7, r11
- __adrl ttab, \ttab
+ mov_l ttab, \ttab
/*
* Disable interrupts and prefetch the 1024-byte 'ft' or 'it' table into
* L1 cache, assuming cacheline size >= 32. This is a hardening measure
2: .ifb \ltab
add ttab, ttab, #1
.else
- __adrl ttab, \ltab
+ mov_l ttab, \ltab
// Prefetch inverse S-box for final round; see explanation above
.set i, 0
.rept 256 / 64
\round r4, r5, r6, r7, r8, r9, r10, r11, \bsz, b, rounds
#ifdef CONFIG_CPU_BIG_ENDIAN
- __rev r4, r4
- __rev r5, r5
- __rev r6, r6
- __rev r7, r7
+ rev_l r4, t0
+ rev_l r5, t0
+ rev_l r6, t0
+ rev_l r7, t0
#endif
ldr out, [sp]
static void __exit blake2b_neon_mod_exit(void)
{
- return crypto_unregister_shashes(blake2b_neon_algs,
- ARRAY_SIZE(blake2b_neon_algs));
+ crypto_unregister_shashes(blake2b_neon_algs,
+ ARRAY_SIZE(blake2b_neon_algs));
}
module_init(blake2b_neon_mod_init);
*/
#include <linux/linkage.h>
+#include <asm/assembler.h>
// Registers used to hold message words temporarily. There aren't
// enough ARM registers to hold the whole message block, so we have to
#endif
.endm
+.macro _le32_bswap a, tmp
+#ifdef __ARMEB__
+ rev_l \a, \tmp
+#endif
+.endm
+
+.macro _le32_bswap_8x a, b, c, d, e, f, g, h, tmp
+ _le32_bswap \a, \tmp
+ _le32_bswap \b, \tmp
+ _le32_bswap \c, \tmp
+ _le32_bswap \d, \tmp
+ _le32_bswap \e, \tmp
+ _le32_bswap \f, \tmp
+ _le32_bswap \g, \tmp
+ _le32_bswap \h, \tmp
+.endm
+
// Execute a quarter-round of BLAKE2s by mixing two columns or two diagonals.
// (a0, b0, c0, d0) and (a1, b1, c1, d1) give the registers containing the two
// columns/diagonals. s0-s1 are the word offsets to the message words the first
tst r1, #3
bne .Lcopy_block_misaligned
ldmia r1!, {r2-r9}
+ _le32_bswap_8x r2, r3, r4, r5, r6, r7, r8, r9, r14
stmia r12!, {r2-r9}
ldmia r1!, {r2-r9}
+ _le32_bswap_8x r2, r3, r4, r5, r6, r7, r8, r9, r14
stmia r12, {r2-r9}
.Lcopy_block_done:
str r1, [sp, #68] // Update message pointer
1:
#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
ldr r3, [r1], #4
+ _le32_bswap r3, r4
#else
ldrb r3, [r1, #0]
ldrb r4, [r1, #1]
X14 .req r12
X15 .req r14
-.macro __rev out, in, t0, t1, t2
-.if __LINUX_ARM_ARCH__ >= 6
- rev \out, \in
-.else
- lsl \t0, \in, #24
- and \t1, \in, #0xff00
- and \t2, \in, #0xff0000
- orr \out, \t0, \in, lsr #24
- orr \out, \out, \t1, lsl #8
- orr \out, \out, \t2, lsr #8
-.endif
-.endm
-
-.macro _le32_bswap x, t0, t1, t2
+.macro _le32_bswap_4x a, b, c, d, tmp
#ifdef __ARMEB__
- __rev \x, \x, \t0, \t1, \t2
+ rev_l \a, \tmp
+ rev_l \b, \tmp
+ rev_l \c, \tmp
+ rev_l \d, \tmp
#endif
.endm
-.macro _le32_bswap_4x a, b, c, d, t0, t1, t2
- _le32_bswap \a, \t0, \t1, \t2
- _le32_bswap \b, \t0, \t1, \t2
- _le32_bswap \c, \t0, \t1, \t2
- _le32_bswap \d, \t0, \t1, \t2
-.endm
-
.macro __ldrd a, b, src, offset
#if __LINUX_ARM_ARCH__ >= 6
ldrd \a, \b, [\src, #\offset]
add X1, X1, r9
add X2, X2, r10
add X3, X3, r11
- _le32_bswap_4x X0, X1, X2, X3, r8, r9, r10
+ _le32_bswap_4x X0, X1, X2, X3, r8
ldmia r12!, {r8-r11}
eor X0, X0, r8
eor X1, X1, r9
ldmia r12!, {X0-X3}
add X6, r10, X6, ror #brot
add X7, r11, X7, ror #brot
- _le32_bswap_4x X4, X5, X6, X7, r8, r9, r10
+ _le32_bswap_4x X4, X5, X6, X7, r8
eor X4, X4, X0
eor X5, X5, X1
eor X6, X6, X2
add r1, r1, r9 // x9
add r6, r6, r10 // x10
add r7, r7, r11 // x11
- _le32_bswap_4x r0, r1, r6, r7, r8, r9, r10
+ _le32_bswap_4x r0, r1, r6, r7, r8
ldmia r12!, {r8-r11}
eor r0, r0, r8 // x8
eor r1, r1, r9 // x9
add r3, r9, r3, ror #drot // x13
add r4, r10, r4, ror #drot // x14
add r5, r11, r5, ror #drot // x15
- _le32_bswap_4x r2, r3, r4, r5, r9, r10, r11
+ _le32_bswap_4x r2, r3, r4, r5, r9
ldr r9, [sp, #72] // load LEN
eor r2, r2, r0 // x12
eor r3, r3, r1 // x13
add X1, X1, r9
add X2, X2, r10
add X3, X3, r11
- _le32_bswap_4x X0, X1, X2, X3, r8, r9, r10
+ _le32_bswap_4x X0, X1, X2, X3, r8
stmia r14!, {X0-X3}
// Save keystream for x4-x7
add X5, r9, X5, ror #brot
add X6, r10, X6, ror #brot
add X7, r11, X7, ror #brot
- _le32_bswap_4x X4, X5, X6, X7, r8, r9, r10
+ _le32_bswap_4x X4, X5, X6, X7, r8
add r8, sp, #64
stmia r14!, {X4-X7}
add r1, r1, r9 // x9
add r6, r6, r10 // x10
add r7, r7, r11 // x11
- _le32_bswap_4x r0, r1, r6, r7, r8, r9, r10
+ _le32_bswap_4x r0, r1, r6, r7, r8
stmia r14!, {r0,r1,r6,r7}
__ldrd r8, r9, sp, 144
__ldrd r10, r11, sp, 152
add r3, r9, r3, ror #drot // x13
add r4, r10, r4, ror #drot // x14
add r5, r11, r5, ror #drot // x15
- _le32_bswap_4x r2, r3, r4, r5, r9, r10, r11
+ _le32_bswap_4x r2, r3, r4, r5, r9
stmia r14, {r2-r5}
// Stack: ks0-ks15 unused0-unused7 x0-x15 OUT IN LEN
#include <linux/linkage.h>
.text
-.fpu neon
.arch armv7-a
+.fpu neon
.align 4
ENTRY(curve25519_neon)
static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
-void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key)
+void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE])
{
poly1305_init_arm(&dctx->h, key);
dctx->s[0] = get_unaligned_le32(key + 16);
#define _ASM_ARM_PARAVIRT_H
#ifdef CONFIG_PARAVIRT
+#include <linux/static_call_types.h>
+
struct static_key;
extern struct static_key paravirt_steal_enabled;
extern struct static_key paravirt_steal_rq_enabled;
-struct pv_time_ops {
- unsigned long long (*steal_clock)(int cpu);
-};
-
-struct paravirt_patch_template {
- struct pv_time_ops time;
-};
+u64 dummy_steal_clock(int cpu);
-extern struct paravirt_patch_template pv_ops;
+DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock);
static inline u64 paravirt_steal_clock(int cpu)
{
- return pv_ops.time.steal_clock(cpu);
+ return static_call(pv_steal_clock)(cpu);
}
#endif
--- /dev/null
+#include <xen/arm/swiotlb-xen.h>
#include <linux/export.h>
#include <linux/jump_label.h>
#include <linux/types.h>
+#include <linux/static_call.h>
#include <asm/paravirt.h>
struct static_key paravirt_steal_enabled;
struct static_key paravirt_steal_rq_enabled;
-struct paravirt_patch_template pv_ops;
-EXPORT_SYMBOL_GPL(pv_ops);
+static u64 native_steal_clock(int cpu)
+{
+ return 0;
+}
+
+DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock);
#include <asm/mach-types.h>
/* cats host-specific stuff */
-static int irqmap_cats[] __initdata = { IRQ_PCI, IRQ_IN0, IRQ_IN1, IRQ_IN3 };
+static int irqmap_cats[] = { IRQ_PCI, IRQ_IN0, IRQ_IN1, IRQ_IN3 };
static u8 cats_no_swizzle(struct pci_dev *dev, u8 *pin)
{
return 0;
}
-static int __init cats_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+static int cats_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
if (dev->irq >= 255)
return -1; /* not a valid interrupt. */
#include <asm/mach/pci.h>
#include <asm/mach-types.h>
-static int irqmap_ebsa285[] __initdata = { IRQ_IN3, IRQ_IN1, IRQ_IN0, IRQ_PCI };
+static int irqmap_ebsa285[] = { IRQ_IN3, IRQ_IN1, IRQ_IN0, IRQ_PCI };
-static int __init ebsa285_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+static int ebsa285_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
if (dev->vendor == PCI_VENDOR_ID_CONTAQ &&
dev->device == PCI_DEVICE_ID_CONTAQ_82C693)
* We now use the slot ID instead of the device identifiers to select
* which interrupt is routed where.
*/
-static int __init netwinder_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+static int netwinder_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
switch (slot) {
case 0: /* host bridge */
#include <asm/mach/pci.h>
#include <asm/mach-types.h>
-static int irqmap_personal_server[] __initdata = {
+static int irqmap_personal_server[] = {
IRQ_IN0, IRQ_IN1, IRQ_IN2, IRQ_IN3, 0, 0, 0,
IRQ_DOORBELLHOST, IRQ_DMA1, IRQ_DMA2, IRQ_PCI
};
-static int __init personal_server_map_irq(const struct pci_dev *dev, u8 slot,
- u8 pin)
+static int personal_server_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
{
unsigned char line;
#include <linux/module.h>
#include <linux/irq.h>
#include <linux/irqdomain.h>
+#include <linux/irqchip.h>
#include <linux/io.h>
#include <linux/of.h>
#include <linux/of_address.h>
* interrupts. It registers the interrupt enable and disable functions
* to the kernel for each interrupt source.
*/
-void __init mxc_init_irq(void __iomem *irqbase)
+static void __init mxc_init_irq(void __iomem *irqbase)
{
struct device_node *np;
int irq_base;
printk(KERN_INFO "MXC IRQ initialized\n");
}
+
+static int __init imx_avic_init(struct device_node *node,
+ struct device_node *parent)
+{
+ void __iomem *avic_base;
+
+ avic_base = of_iomap(node, 0);
+ BUG_ON(!avic_base);
+ mxc_init_irq(avic_base);
+ return 0;
+}
+
+IRQCHIP_DECLARE(imx_avic, "fsl,avic", imx_avic_init);
void imx21_init_early(void);
void imx31_init_early(void);
void imx35_init_early(void);
-void mxc_init_irq(void __iomem *);
void mx31_init_irq(void);
void mx35_init_irq(void);
void mxc_set_cpu_type(unsigned int type);
mxc_set_cpu_type(MXC_CPU_MX1);
}
-static void __init imx1_init_irq(void)
-{
- void __iomem *avic_addr;
-
- avic_addr = ioremap(MX1_AVIC_ADDR, SZ_4K);
- WARN_ON(!avic_addr);
-
- mxc_init_irq(avic_addr);
-}
-
static const char * const imx1_dt_board_compat[] __initconst = {
"fsl,imx1",
NULL
DT_MACHINE_START(IMX1_DT, "Freescale i.MX1 (Device Tree Support)")
.init_early = imx1_init_early,
- .init_irq = imx1_init_irq,
.dt_compat = imx1_dt_board_compat,
.restart = mxc_restart,
MACHINE_END
imx_aips_allow_unprivileged_access("fsl,imx25-aips");
}
-static void __init mx25_init_irq(void)
-{
- struct device_node *np;
- void __iomem *avic_base;
-
- np = of_find_compatible_node(NULL, NULL, "fsl,avic");
- avic_base = of_iomap(np, 0);
- BUG_ON(!avic_base);
- mxc_init_irq(avic_base);
-}
-
static const char * const imx25_dt_board_compat[] __initconst = {
"fsl,imx25",
NULL
.init_early = imx25_init_early,
.init_machine = imx25_dt_init,
.init_late = imx25_pm_init,
- .init_irq = mx25_init_irq,
.dt_compat = imx25_dt_board_compat,
MACHINE_END
mxc_set_cpu_type(MXC_CPU_MX27);
}
-static void __init mx27_init_irq(void)
-{
- void __iomem *avic_base;
- struct device_node *np;
-
- np = of_find_compatible_node(NULL, NULL, "fsl,avic");
- avic_base = of_iomap(np, 0);
- BUG_ON(!avic_base);
- mxc_init_irq(avic_base);
-}
-
static const char * const imx27_dt_board_compat[] __initconst = {
"fsl,imx27",
NULL
DT_MACHINE_START(IMX27_DT, "Freescale i.MX27 (Device Tree Support)")
.map_io = mx27_map_io,
.init_early = imx27_init_early,
- .init_irq = mx27_init_irq,
.init_late = imx27_pm_init,
.dt_compat = imx27_dt_board_compat,
MACHINE_END
DT_MACHINE_START(IMX31_DT, "Freescale i.MX31 (Device Tree Support)")
.map_io = mx31_map_io,
.init_early = imx31_init_early,
- .init_irq = mx31_init_irq,
.dt_compat = imx31_dt_board_compat,
MACHINE_END
.l2c_aux_mask = ~0,
.map_io = mx35_map_io,
.init_early = imx35_init_early,
- .init_irq = mx35_init_irq,
.dt_compat = imx35_dt_board_compat,
MACHINE_END
mx3_ccm_base = of_iomap(np, 0);
BUG_ON(!mx3_ccm_base);
}
-
-void __init mx31_init_irq(void)
-{
- void __iomem *avic_base;
- struct device_node *np;
-
- np = of_find_compatible_node(NULL, NULL, "fsl,imx31-avic");
- avic_base = of_iomap(np, 0);
- BUG_ON(!avic_base);
-
- mxc_init_irq(avic_base);
-}
#endif /* ifdef CONFIG_SOC_IMX31 */
#ifdef CONFIG_SOC_IMX35
mx3_ccm_base = of_iomap(np, 0);
BUG_ON(!mx3_ccm_base);
}
-
-void __init mx35_init_irq(void)
-{
- void __iomem *avic_base;
- struct device_node *np;
-
- np = of_find_compatible_node(NULL, NULL, "fsl,imx35-avic");
- avic_base = of_iomap(np, 0);
- BUG_ON(!avic_base);
-
- mxc_init_irq(avic_base);
-}
#endif /* ifdef CONFIG_SOC_IMX35 */
static long long __init keystone_pv_fixup(void)
{
long long offset;
- phys_addr_t mem_start, mem_end;
+ u64 mem_start, mem_end;
mem_start = memblock_start_of_DRAM();
mem_end = memblock_end_of_DRAM();
if (mem_start < KEYSTONE_HIGH_PHYS_START ||
mem_end > KEYSTONE_HIGH_PHYS_END) {
pr_crit("Invalid address space for memory (%08llx-%08llx)\n",
- (u64)mem_start, (u64)mem_end);
+ mem_start, mem_end);
return 0;
}
#include <linux/platform_data/gpio-omap.h>
#include <asm/assembler.h>
+#include <asm/irq.h>
#include "ams-delta-fiq.h"
#include "board-ams-delta.h"
}
/* Clocks are needed early, see drivers/clocksource for the rest */
-void __init __maybe_unused omap_init_time_of(void)
+static void __init __maybe_unused omap_init_time_of(void)
{
omap_clk_init();
timer_probe();
*/
#include <linux/arm-smccc.h>
+#include <linux/cpu_pm.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/io.h>
#include "common.h"
#include "omap-secure.h"
+#include "soc.h"
static phys_addr_t omap_secure_memblock_base;
{
omap_optee_init_check();
}
+
+/*
+ * Dummy dispatcher call after core OSWR and MPU off. Updates the ROM return
+ * address after MMU has been re-enabled after CPU1 has been woken up again.
+ * Otherwise the ROM code will attempt to use the earlier physical return
+ * address that got set with MMU off when waking up CPU1. Only used on secure
+ * devices.
+ */
+static int cpu_notifier(struct notifier_block *nb, unsigned long cmd, void *v)
+{
+ switch (cmd) {
+ case CPU_CLUSTER_PM_EXIT:
+ omap_secure_dispatcher(OMAP4_PPA_SERVICE_0,
+ FLAG_START_CRITICAL,
+ 0, 0, 0, 0, 0);
+ break;
+ default:
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block secure_notifier_block = {
+ .notifier_call = cpu_notifier,
+};
+
+static int __init secure_pm_init(void)
+{
+ if (omap_type() == OMAP2_DEVICE_TYPE_GP || !soc_is_omap44xx())
+ return 0;
+
+ cpu_pm_register_notifier(&secure_notifier_block);
+
+ return 0;
+}
+omap_arch_initcall(secure_pm_init);
#define OMAP5_DRA7_MON_SET_ACR_INDEX 0x107
/* Secure PPA(Primary Protected Application) APIs */
+#define OMAP4_PPA_SERVICE_0 0x21
#define OMAP4_PPA_L2_POR_INDEX 0x23
#define OMAP4_PPA_CPU_ACTRL_SMP_INDEX 0x25
omap_voltage_register_pmic(voltdm, &omap443x_max8952_mpu);
if (of_machine_is_compatible("motorola,droid-bionic")) {
- voltdm = voltdm_lookup("mpu");
+ voltdm = voltdm_lookup("core");
omap_voltage_register_pmic(voltdm, &omap_cpcap_core);
- voltdm = voltdm_lookup("mpu");
+ voltdm = voltdm_lookup("iva");
omap_voltage_register_pmic(voltdm, &omap_cpcap_iva);
} else {
voltdm = voltdm_lookup("core");
extern struct omap_sr_data omap_sr_pdata[];
-static int __init sr_dev_init(struct omap_hwmod *oh, void *user)
+static int __init sr_init_by_name(const char *name, const char *voltdm)
{
struct omap_sr_data *sr_data = NULL;
struct omap_volt_data *volt_data;
- struct omap_smartreflex_dev_attr *sr_dev_attr;
static int i;
- if (!strncmp(oh->name, "smartreflex_mpu_iva", 20) ||
- !strncmp(oh->name, "smartreflex_mpu", 16))
+ if (!strncmp(name, "smartreflex_mpu_iva", 20) ||
+ !strncmp(name, "smartreflex_mpu", 16))
sr_data = &omap_sr_pdata[OMAP_SR_MPU];
- else if (!strncmp(oh->name, "smartreflex_core", 17))
+ else if (!strncmp(name, "smartreflex_core", 17))
sr_data = &omap_sr_pdata[OMAP_SR_CORE];
- else if (!strncmp(oh->name, "smartreflex_iva", 16))
+ else if (!strncmp(name, "smartreflex_iva", 16))
sr_data = &omap_sr_pdata[OMAP_SR_IVA];
if (!sr_data) {
- pr_err("%s: Unknown instance %s\n", __func__, oh->name);
+ pr_err("%s: Unknown instance %s\n", __func__, name);
return -EINVAL;
}
- sr_dev_attr = (struct omap_smartreflex_dev_attr *)oh->dev_attr;
- if (!sr_dev_attr || !sr_dev_attr->sensor_voltdm_name) {
- pr_err("%s: No voltage domain specified for %s. Cannot initialize\n",
- __func__, oh->name);
- goto exit;
- }
-
- sr_data->name = oh->name;
+ sr_data->name = name;
if (cpu_is_omap343x())
sr_data->ip_type = 1;
else
}
}
- sr_data->voltdm = voltdm_lookup(sr_dev_attr->sensor_voltdm_name);
+ sr_data->voltdm = voltdm_lookup(voltdm);
if (!sr_data->voltdm) {
pr_err("%s: Unable to get voltage domain pointer for VDD %s\n",
- __func__, sr_dev_attr->sensor_voltdm_name);
+ __func__, voltdm);
goto exit;
}
return 0;
}
+static int __init sr_dev_init(struct omap_hwmod *oh, void *user)
+{
+ struct omap_smartreflex_dev_attr *sr_dev_attr;
+
+ sr_dev_attr = (struct omap_smartreflex_dev_attr *)oh->dev_attr;
+ if (!sr_dev_attr || !sr_dev_attr->sensor_voltdm_name) {
+ pr_err("%s: No voltage domain specified for %s. Cannot initialize\n",
+ __func__, oh->name);
+ return 0;
+ }
+
+ return sr_init_by_name(oh->name, sr_dev_attr->sensor_voltdm_name);
+}
+
/*
* API to be called from board files to enable smartreflex
* autocompensation at init.
sr_enable_on_init = true;
}
+static const char * const omap4_sr_instances[] = {
+ "mpu",
+ "iva",
+ "core",
+};
+
+static const char * const dra7_sr_instances[] = {
+ "mpu",
+ "core",
+};
+
int __init omap_devinit_smartreflex(void)
{
+ const char * const *sr_inst = NULL;
+ int i, nr_sr = 0;
+
+ if (soc_is_omap44xx()) {
+ sr_inst = omap4_sr_instances;
+ nr_sr = ARRAY_SIZE(omap4_sr_instances);
+
+ } else if (soc_is_dra7xx()) {
+ sr_inst = dra7_sr_instances;
+ nr_sr = ARRAY_SIZE(dra7_sr_instances);
+ }
+
+ if (nr_sr) {
+ const char *name, *voltdm;
+
+ for (i = 0; i < nr_sr; i++) {
+ name = kasprintf(GFP_KERNEL, "smartreflex_%s", sr_inst[i]);
+ voltdm = sr_inst[i];
+ sr_init_by_name(name, voltdm);
+ }
+
+ return 0;
+ }
+
return omap_hwmod_for_each_by_class("smartreflex", sr_dev_init, NULL);
}
#endif
static int mst_pcmcia0_irqs[11] = {
- [0 ... 10] = -1,
+ [0 ... 4] = -1,
[5] = MAINSTONE_S0_CD_IRQ,
+ [6 ... 7] = -1,
[8] = MAINSTONE_S0_STSCHG_IRQ,
+ [9] = -1,
[10] = MAINSTONE_S0_IRQ,
};
static int mst_pcmcia1_irqs[11] = {
- [0 ... 10] = -1,
+ [0 ... 4] = -1,
[5] = MAINSTONE_S1_CD_IRQ,
+ [6 ... 7] = -1,
[8] = MAINSTONE_S1_STSCHG_IRQ,
+ [9] = -1,
[10] = MAINSTONE_S1_IRQ,
};
}
irq_set_irq_wake(fpga->irq, 1);
- fpga->irqdomain = irq_domain_add_linear(pdev->dev.of_node,
- CPLDS_NB_IRQ,
- &cplds_irq_domain_ops, fpga);
+ if (base_irq)
+ fpga->irqdomain = irq_domain_add_legacy(pdev->dev.of_node,
+ CPLDS_NB_IRQ,
+ base_irq, 0,
+ &cplds_irq_domain_ops,
+ fpga);
+ else
+ fpga->irqdomain = irq_domain_add_linear(pdev->dev.of_node,
+ CPLDS_NB_IRQ,
+ &cplds_irq_domain_ops,
+ fpga);
if (!fpga->irqdomain)
return -ENODEV;
- if (base_irq) {
- ret = irq_create_strict_mappings(fpga->irqdomain, base_irq, 0,
- CPLDS_NB_IRQ);
- if (ret) {
- dev_err(&pdev->dev, "couldn't create the irq mapping %d..%d\n",
- base_irq, base_irq + CPLDS_NB_IRQ);
- return ret;
- }
- }
-
return 0;
}
pte_t *pte = pte_offset_fixmap(pmd_off_k(vaddr), vaddr);
/* Make sure fixmap region does not exceed available allocation. */
- BUILD_BUG_ON(FIXADDR_START + (__end_of_fixed_addresses * PAGE_SIZE) >
- FIXADDR_END);
+ BUILD_BUG_ON(__fix_to_virt(__end_of_fixed_addresses) < FIXADDR_START);
BUG_ON(idx >= __end_of_fixed_addresses);
/* we only support device mappings until pgprot_kernel has been set */
phys_addr_t mem_end;
phys_addr_t reg_start, reg_end;
unsigned int mem_max_regions;
+ bool first = true;
int num;
u64 i;
#endif
for_each_mem_range(i, ®_start, ®_end) {
- if (i == 0) {
+ if (first) {
phys_addr_t phys_offset = PHYS_OFFSET;
/*
mem_start = reg_start;
mem_end = reg_end;
specified_mem_size = mem_end - mem_start;
+ first = false;
} else {
/*
* memblock auto merges contiguous blocks, remove
{
phys_addr_t mem_end;
phys_addr_t reg_start, reg_end;
+ bool first = true;
u64 i;
for_each_mem_range(i, ®_start, ®_end) {
- if (i == 0) {
+ if (first) {
phys_addr_t phys_offset = PHYS_OFFSET;
/*
if (reg_start != phys_offset)
panic("First memory bank must be contiguous from PHYS_OFFSET");
mem_end = reg_end;
+ first = false;
} else {
/*
* memblock auto merges contiguous blocks, remove
static struct undef_hook uprobes_arm_break_hook = {
.instr_mask = 0x0fffffff,
.instr_val = (UPROBE_SWBP_ARM_INSN & 0x0fffffff),
- .cpsr_mask = MODE_MASK,
+ .cpsr_mask = (PSR_T_BIT | MODE_MASK),
.cpsr_val = USR_MODE,
.fn = uprobe_trap_handler,
};
static struct undef_hook uprobes_arm_ss_hook = {
.instr_mask = 0x0fffffff,
.instr_val = (UPROBE_SS_ARM_INSN & 0x0fffffff),
- .cpsr_mask = MODE_MASK,
+ .cpsr_mask = (PSR_T_BIT | MODE_MASK),
.cpsr_val = USR_MODE,
.fn = uprobe_trap_handler,
};
return;
}
+int xen_swiotlb_detect(void)
+{
+ if (!xen_domain())
+ return 0;
+ if (xen_feature(XENFEAT_direct_mapped))
+ return 1;
+ /* legacy case */
+ if (!xen_feature(XENFEAT_not_direct_mapped) && xen_initial_domain())
+ return 1;
+ return 0;
+}
+
static int __init xen_mm_init(void)
{
struct gnttab_cache_flush cflush;
- if (!xen_initial_domain())
+ if (!xen_swiotlb_detect())
return 0;
xen_swiotlb_init(1, false);
#include <xen/xen.h>
#include <xen/interface/memory.h>
+#include <xen/grant_table.h>
#include <xen/page.h>
#include <xen/swiotlb-xen.h>
map_ops[i].status = GNTST_general_error;
unmap.host_addr = map_ops[i].host_addr,
unmap.handle = map_ops[i].handle;
- map_ops[i].handle = ~0;
+ map_ops[i].handle = INVALID_GRANT_HANDLE;
if (map_ops[i].flags & GNTMAP_device_map)
unmap.dev_bus_addr = map_ops[i].dev_bus_addr;
else
return 0;
}
-EXPORT_SYMBOL_GPL(set_foreign_p2m_mapping);
int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
struct gnttab_unmap_grant_ref *kunmap_ops,
return 0;
}
-EXPORT_SYMBOL_GPL(clear_foreign_p2m_mapping);
bool __set_phys_to_machine_multi(unsigned long pfn,
unsigned long mfn, unsigned long nr_pages)
select GENERIC_CPU_AUTOPROBE
select GENERIC_CPU_VULNERABILITIES
select GENERIC_EARLY_IOREMAP
+ select GENERIC_FIND_FIRST_BIT
select GENERIC_IDLE_POLL_SETUP
select GENERIC_IRQ_IPI
- select GENERIC_IRQ_MULTI_HANDLER
select GENERIC_IRQ_PROBE
select GENERIC_IRQ_SHOW
select GENERIC_IRQ_SHOW_LEVEL
select HAVE_ARCH_JUMP_LABEL
select HAVE_ARCH_JUMP_LABEL_RELATIVE
select HAVE_ARCH_KASAN if !(ARM64_16K_PAGES && ARM64_VA_BITS_48)
+ select HAVE_ARCH_KASAN_VMALLOC if HAVE_ARCH_KASAN
select HAVE_ARCH_KASAN_SW_TAGS if HAVE_ARCH_KASAN
select HAVE_ARCH_KASAN_HW_TAGS if (HAVE_ARCH_KASAN && ARM64_MTE)
select HAVE_ARCH_KFENCE
select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
select HAVE_ARCH_PFN_VALID
select HAVE_ARCH_PREL32_RELOCATIONS
+ select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
select HAVE_ARCH_SECCOMP_FILTER
select HAVE_ARCH_STACKLEAK
select HAVE_ARCH_THREAD_STRUCT_WHITELIST
select IOMMU_DMA if IOMMU_SUPPORT
select IRQ_DOMAIN
select IRQ_FORCED_THREADING
+ select KASAN_VMALLOC if KASAN_GENERIC
select MODULES_USE_ELF_RELA
select NEED_DMA_MAP_STATE
select NEED_SG_DMA_LENGTH
If unsure, say Y.
+config NVIDIA_CARMEL_CNP_ERRATUM
+ bool "NVIDIA Carmel CNP: CNP on Carmel semantically different than ARM cores"
+ default y
+ help
+ If CNP is enabled on Carmel cores, non-sharable TLBIs on a core will not
+ invalidate shared TLB entries installed by a different core, as it would
+ on standard ARM cores.
+
+ If unsure, say Y.
+
config SOCIONEXT_SYNQUACER_PREITS
bool "Socionext Synquacer: Workaround for GICv3 pre-ITS"
default y
config SYS_SUPPORTS_HUGETLBFS
def_bool y
-config ARCH_WANT_HUGE_PMD_SHARE
-
config ARCH_HAS_CACHE_LINE_SIZE
def_bool y
+config ARCH_HAS_FILTER_PGPROT
+ def_bool y
+
config ARCH_ENABLE_SPLIT_PMD_PTLOCK
def_bool y if PGTABLE_LEVELS > 2
config FORCE_MAX_ZONEORDER
int
- default "14" if (ARM64_64K_PAGES && TRANSPARENT_HUGEPAGE)
- default "12" if (ARM64_16K_PAGES && TRANSPARENT_HUGEPAGE)
+ default "14" if ARM64_64K_PAGES
+ default "12" if ARM64_16K_PAGES
default "11"
help
The kernel memory allocator divides physically contiguous memory
config AS_HAS_LDAPR
def_bool $(as-instr,.arch_extension rcpc)
+config AS_HAS_LSE_ATOMICS
+ def_bool $(as-instr,.arch_extension lse)
+
config ARM64_LSE_ATOMICS
bool
default ARM64_USE_LSE_ATOMICS
- depends on $(as-instr,.arch_extension lse)
+ depends on AS_HAS_LSE_ATOMICS
config ARM64_USE_LSE_ATOMICS
bool "Atomic instructions"
built with binutils >= 2.25 in order for the new instructions
to be used.
-config ARM64_VHE
- bool "Enable support for Virtualization Host Extensions (VHE)"
- default y
- help
- Virtualization Host Extensions (VHE) allow the kernel to run
- directly at EL2 (instead of EL1) on processors that support
- it. This leads to better performance for KVM, as they reduce
- the cost of the world switch.
-
- Selecting this option allows the VHE feature to be detected
- at runtime, and does not affect processors that do not
- implement this feature.
-
endmenu
menu "ARMv8.2 architectural features"
default y
depends on ARM64_AS_HAS_MTE && ARM64_TAGGED_ADDR_ABI
depends on AS_HAS_ARMV8_5
+ depends on AS_HAS_LSE_ATOMICS
# Required for tag checking in the uaccess routines
depends on ARM64_PAN
select ARCH_USES_HIGH_VMA_FLAGS
endmenu
+menu "ARMv8.7 architectural features"
+
+config ARM64_EPAN
+ bool "Enable support for Enhanced Privileged Access Never (EPAN)"
+ default y
+ depends on ARM64_PAN
+ help
+ Enhanced Privileged Access Never (EPAN) allows Privileged
+ Access Never to be used with Execute-only mappings.
+
+ The feature is detected at runtime, and will remain disabled
+ if the cpu does not implement the feature.
+endmenu
+
config ARM64_SVE
bool "ARM Scalable Vector Extension support"
default y
- depends on !KVM || ARM64_VHE
help
The Scalable Vector Extension (SVE) is an extension to the AArch64
execution state which complements and extends the SIMD functionality
booting the kernel. If unsure and you are not observing these
symptoms, you should assume that it is safe to say Y.
- CPUs that support SVE are architecturally required to support the
- Virtualization Host Extensions (VHE), so the kernel makes no
- provision for supporting SVE alongside KVM without VHE enabled.
- Thus, you will need to enable CONFIG_ARM64_VHE if you want to support
- KVM in the same kernel image.
-
config ARM64_MODULE_PLTS
bool "Use PLTs to allow module memory to spill over into vmalloc area"
depends on MODULES
the boot loader doesn't provide any, the default kernel command
string provided in CMDLINE will be used.
-config CMDLINE_EXTEND
- bool "Extend bootloader kernel arguments"
- help
- The command-line arguments provided by the boot loader will be
- appended to the default kernel command string.
-
config CMDLINE_FORCE
bool "Always use the default kernel command string"
help
};
};
};
+
+&mmc0 {
+ broken-cd; /* card detect is broken on *some* boards */
+};
vmmc-supply = <®_dcdc1>;
disable-wp;
bus-width = <4>;
- cd-gpios = <&pio 5 6 GPIO_ACTIVE_LOW>; /* PF6 */
+ cd-gpios = <&pio 5 6 GPIO_ACTIVE_HIGH>; /* PF6 push-pull switch */
status = "okay";
};
vcc-pm-supply = <®_aldo1>;
};
-&rtc {
- clocks = <&ext_osc32k>;
-};
-
&spdif {
status = "okay";
};
compatible = "allwinner,sun8i-a23-rsb";
reg = <0x07083000 0x400>;
interrupts = <GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>;
- clocks = <&r_ccu 13>;
+ clocks = <&r_ccu CLK_R_APB2_RSB>;
clock-frequency = <3000000>;
- resets = <&r_ccu 7>;
+ resets = <&r_ccu RST_R_APB2_RSB>;
pinctrl-names = "default";
pinctrl-0 = <&r_rsb_pins>;
status = "disabled";
ranges = <0x0 0x00 0x1700000 0x100000>;
reg = <0x00 0x1700000 0x0 0x100000>;
interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>;
+ dma-coherent;
sec_jr0: jr@10000 {
compatible = "fsl,sec-v5.4-job-ring",
ranges = <0x0 0x00 0x1700000 0x100000>;
reg = <0x00 0x1700000 0x0 0x100000>;
interrupts = <0 75 0x4>;
+ dma-coherent;
sec_jr0: jr@10000 {
compatible = "fsl,sec-v5.4-job-ring",
ranges = <0x0 0x00 0x1700000 0x100000>;
reg = <0x00 0x1700000 0x0 0x100000>;
interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>;
+ dma-coherent;
sec_jr0: jr@10000 {
compatible = "fsl,sec-v5.4-job-ring",
#define MX8MM_IOMUXC_SD1_CMD_USDHC1_CMD 0x0A4 0x30C 0x000 0x0 0x0
#define MX8MM_IOMUXC_SD1_CMD_GPIO2_IO1 0x0A4 0x30C 0x000 0x5 0x0
#define MX8MM_IOMUXC_SD1_DATA0_USDHC1_DATA0 0x0A8 0x310 0x000 0x0 0x0
-#define MX8MM_IOMUXC_SD1_DATA0_GPIO2_IO2 0x0A8 0x31 0x000 0x5 0x0
+#define MX8MM_IOMUXC_SD1_DATA0_GPIO2_IO2 0x0A8 0x310 0x000 0x5 0x0
#define MX8MM_IOMUXC_SD1_DATA1_USDHC1_DATA1 0x0AC 0x314 0x000 0x0 0x0
#define MX8MM_IOMUXC_SD1_DATA1_GPIO2_IO3 0x0AC 0x314 0x000 0x5 0x0
#define MX8MM_IOMUXC_SD1_DATA2_USDHC1_DATA2 0x0B0 0x318 0x000 0x0 0x0
&i2c2 {
clock-frequency = <400000>;
- pinctrl-names = "default";
+ pinctrl-names = "default", "gpio";
pinctrl-0 = <&pinctrl_i2c2>;
pinctrl-1 = <&pinctrl_i2c2_gpio>;
sda-gpios = <&gpio5 17 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
&i2c1 {
clock-frequency = <400000>;
- pinctrl-names = "default";
+ pinctrl-names = "default", "gpio";
pinctrl-0 = <&pinctrl_i2c1>;
pinctrl-1 = <&pinctrl_i2c1_gpio>;
sda-gpios = <&gpio5 15 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>;
#define MX8MQ_IOMUXC_SD1_CMD_USDHC1_CMD 0x0A4 0x30C 0x000 0x0 0x0
#define MX8MQ_IOMUXC_SD1_CMD_GPIO2_IO1 0x0A4 0x30C 0x000 0x5 0x0
#define MX8MQ_IOMUXC_SD1_DATA0_USDHC1_DATA0 0x0A8 0x310 0x000 0x0 0x0
-#define MX8MQ_IOMUXC_SD1_DATA0_GPIO2_IO2 0x0A8 0x31 0x000 0x5 0x0
+#define MX8MQ_IOMUXC_SD1_DATA0_GPIO2_IO2 0x0A8 0x310 0x000 0x5 0x0
#define MX8MQ_IOMUXC_SD1_DATA1_USDHC1_DATA1 0x0AC 0x314 0x000 0x0 0x0
#define MX8MQ_IOMUXC_SD1_DATA1_GPIO2_IO3 0x0AC 0x314 0x000 0x5 0x0
#define MX8MQ_IOMUXC_SD1_DATA2_USDHC1_DATA2 0x0B0 0x318 0x000 0x0 0x0
// SPDX-License-Identifier: (GPL-2.0+ OR MIT)
/*
* Device Tree file for CZ.NIC Turris Mox Board
- * 2019 by Marek Behun <marek.behun@nic.cz>
+ * 2019 by Marek Behún <kabel@kernel.org>
*/
/dts-v1/;
};
CP11X_LABEL(sata0): sata@540000 {
- compatible = "marvell,armada-8k-ahci";
+ compatible = "marvell,armada-8k-ahci",
+ "generic-ahci";
reg = <0x540000 0x30000>;
dma-coherent;
+ interrupts = <107 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&CP11X_LABEL(clk) 1 15>,
<&CP11X_LABEL(clk) 1 16>;
#address-cells = <1>;
status = "disabled";
sata-port@0 {
- interrupts = <109 IRQ_TYPE_LEVEL_HIGH>;
reg = <0>;
};
sata-port@1 {
- interrupts = <107 IRQ_TYPE_LEVEL_HIGH>;
reg = <1>;
};
};
model = "NVIDIA Jetson TX2 Developer Kit";
compatible = "nvidia,p2771-0000", "nvidia,tegra186";
- aconnect {
+ aconnect@2900000 {
status = "okay";
dma-controller@2930000 {
};
chosen {
- bootargs = "earlycon console=ttyS0,115200n8";
+ bootargs = "earlycon console=ttyS0,115200n8 fw_devlink=on";
stdout-path = "serial0:115200n8";
};
snps,rxpbl = <8>;
};
- aconnect {
+ aconnect@2900000 {
compatible = "nvidia,tegra186-aconnect",
"nvidia,tegra210-aconnect";
clocks = <&bpmp TEGRA186_CLK_APE>,
reg = <0x1a>;
interrupt-parent = <&gpio>;
interrupts = <TEGRA194_MAIN_GPIO(S, 5) GPIO_ACTIVE_HIGH>;
+ clocks = <&bpmp TEGRA194_CLK_AUD_MCLK>;
+ clock-names = "mclk";
realtek,jd-src = <2>;
sound-name-prefix = "CVB-RT";
rt5658_ep: endpoint {
remote-endpoint = <&i2s1_dap_ep>;
mclk-fs = <256>;
- clocks = <&bpmp TEGRA194_CLK_AUD_MCLK>;
};
};
};
model = "NVIDIA Jetson Xavier NX (SD-card)";
compatible = "nvidia,p3668-0000", "nvidia,tegra194";
+ aliases {
+ mmc0 = "/bus@0/mmc@3400000";
+ };
+
bus@0 {
/* SDMMC1 (SD/MMC) */
mmc@3400000 {
model = "NVIDIA Jetson Xavier NX (eMMC)";
compatible = "nvidia,p3668-0001", "nvidia,tegra194";
+ aliases {
+ mmc0 = "/bus@0/mmc@3460000";
+ };
+
bus@0 {
/* SDMMC4 (eMMC) */
mmc@3460000 {
i2c5 = "/bus@0/i2c@31c0000";
i2c6 = "/bus@0/i2c@c250000";
i2c7 = "/bus@0/i2c@31e0000";
- mmc0 = "/bus@0/mmc@3460000";
rtc0 = "/bpmp/i2c/pmic@3c";
rtc1 = "/bus@0/rtc@c2a0000";
serial0 = &tcu;
CONFIG_CMA_SIZE_MBYTES=32
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_INFO=y
+CONFIG_DEBUG_INFO_REDUCED=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_FS=y
CONFIG_DEBUG_KERNEL=y
ins vctr.d[0], x8
/* apply carry to N counter blocks for N := x12 */
+ cbz x12, 2f
adr x16, 1f
sub x16, x16, x12, lsl #3
br x16
cbz w5, .Lmacout
encrypt_block v0, w2, x1, x7, w8
st1 {v0.16b}, [x4] /* return dg */
- cond_yield .Lmacout, x7
+ cond_yield .Lmacout, x7, x8
b .Lmacloop4x
.Lmac1x:
add w3, w3, #4
static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon);
-void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key)
+void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE])
{
poly1305_init_arm64(&dctx->h, key);
dctx->s[0] = get_unaligned_le32(key + 16);
add dgav.4s, dgav.4s, dg0v.4s
cbz w2, 2f
- cond_yield 3f, x5
+ cond_yield 3f, x5, x6
b 0b
/*
/* handled all input blocks? */
cbz w2, 2f
- cond_yield 3f, x5
+ cond_yield 3f, x5, x6
b 0b
/*
eor v0.16b, v0.16b, v31.16b
cbnz w8, 3b
- cond_yield 3f, x8
+ cond_yield 4f, x8, x9
cbnz w2, 0b
/* save state */
-3: st1 { v0.1d- v3.1d}, [x0], #32
+4: st1 { v0.1d- v3.1d}, [x0], #32
st1 { v4.1d- v7.1d}, [x0], #32
st1 { v8.1d-v11.1d}, [x0], #32
st1 {v12.1d-v15.1d}, [x0], #32
add v10.2d, v10.2d, v2.2d
add v11.2d, v11.2d, v3.2d
- cond_yield 3f, x4
+ cond_yield 3f, x4, x5
/* handled all input blocks? */
cbnz w2, 0b
.popsection
.subsection 1
663: \insn2
-664: .previous
- .org . - (664b-663b) + (662b-661b)
+664: .org . - (664b-663b) + (662b-661b)
.org . - (662b-661b) + (664b-663b)
+ .previous
.endif
.endm
*/
.macro alternative_endif
664:
+ .org . - (664b-663b) + (662b-661b)
+ .org . - (662b-661b) + (664b-663b)
.if .Lasm_alt_mode==0
.previous
.endif
- .org . - (664b-663b) + (662b-661b)
- .org . - (662b-661b) + (664b-663b)
.endm
/*
static inline void gic_arch_enable_irqs(void)
{
- asm volatile ("msr daifclr, #2" : : : "memory");
+ asm volatile ("msr daifclr, #3" : : : "memory");
}
#endif /* __ASSEMBLY__ */
isb();
}
-/*
- * Ensure that reads of the counter are treated the same as memory reads
- * for the purposes of ordering by subsequent memory barriers.
- *
- * This insanity brought to you by speculative system register reads,
- * out-of-order memory accesses, sequence locks and Thomas Gleixner.
- *
- * http://lists.infradead.org/pipermail/linux-arm-kernel/2019-February/631195.html
- */
-#define arch_counter_enforce_ordering(val) do { \
- u64 tmp, _val = (val); \
- \
- asm volatile( \
- " eor %0, %1, %1\n" \
- " add %0, sp, %0\n" \
- " ldr xzr, [%0]" \
- : "=r" (tmp) : "r" (_val)); \
-} while (0)
-
static __always_inline u64 __arch_counter_get_cntpct_stable(void)
{
u64 cnt;
return cnt;
}
-#undef arch_counter_enforce_ordering
-
static inline int arch_timer_arch_init(void)
{
return 0;
* so use the base value of ldp as thread.keys_user and offset as
* thread.keys_user.ap*.
*/
- .macro ptrauth_keys_install_user tsk, tmp1, tmp2, tmp3
+ .macro __ptrauth_keys_install_user tsk, tmp1, tmp2, tmp3
mov \tmp1, #THREAD_KEYS_USER
add \tmp1, \tsk, \tmp1
-alternative_if_not ARM64_HAS_ADDRESS_AUTH
- b .Laddr_auth_skip_\@
-alternative_else_nop_endif
ldp \tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APIA]
msr_s SYS_APIAKEYLO_EL1, \tmp2
msr_s SYS_APIAKEYHI_EL1, \tmp3
- ldp \tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APIB]
- msr_s SYS_APIBKEYLO_EL1, \tmp2
- msr_s SYS_APIBKEYHI_EL1, \tmp3
- ldp \tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APDA]
- msr_s SYS_APDAKEYLO_EL1, \tmp2
- msr_s SYS_APDAKEYHI_EL1, \tmp3
- ldp \tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APDB]
- msr_s SYS_APDBKEYLO_EL1, \tmp2
- msr_s SYS_APDBKEYHI_EL1, \tmp3
-.Laddr_auth_skip_\@:
-alternative_if ARM64_HAS_GENERIC_AUTH
- ldp \tmp2, \tmp3, [\tmp1, #PTRAUTH_USER_KEY_APGA]
- msr_s SYS_APGAKEYLO_EL1, \tmp2
- msr_s SYS_APGAKEYHI_EL1, \tmp3
-alternative_else_nop_endif
.endm
.macro __ptrauth_keys_install_kernel_nosync tsk, tmp1, tmp2, tmp3
#include <asm-generic/export.h>
#include <asm/asm-offsets.h>
+#include <asm/alternative.h>
#include <asm/cpufeature.h>
#include <asm/cputype.h>
#include <asm/debug-monitors.h>
#include <asm/ptrace.h>
#include <asm/thread_info.h>
+ /*
+ * Provide a wxN alias for each wN register so what we can paste a xN
+ * reference after a 'w' to obtain the 32-bit version.
+ */
+ .irp n,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30
+ wx\n .req w\n
+ .endr
+
.macro save_and_disable_daif, flags
mrs \flags, daif
msr daifset, #0xf
msr daif, \flags
.endm
- /* IRQ is the lowest priority flag, unconditionally unmask the rest. */
- .macro enable_da_f
- msr daifclr, #(8 | 4 | 1)
+ /* IRQ/FIQ are the lowest priority flags, unconditionally unmask the rest. */
+ .macro enable_da
+ msr daifclr, #(8 | 4)
.endm
/*
*/
.macro save_and_disable_irq, flags
mrs \flags, daif
- msr daifset, #2
+ msr daifset, #3
.endm
.macro restore_irq, flags
isb
.endm
-/*
- * Check whether to yield to another runnable task from kernel mode NEON code
- * (which runs with preemption disabled).
- *
- * if_will_cond_yield_neon
- * // pre-yield patchup code
- * do_cond_yield_neon
- * // post-yield patchup code
- * endif_yield_neon <label>
- *
- * where <label> is optional, and marks the point where execution will resume
- * after a yield has been performed. If omitted, execution resumes right after
- * the endif_yield_neon invocation. Note that the entire sequence, including
- * the provided patchup code, will be omitted from the image if
- * CONFIG_PREEMPTION is not defined.
- *
- * As a convenience, in the case where no patchup code is required, the above
- * sequence may be abbreviated to
- *
- * cond_yield_neon <label>
- *
- * Note that the patchup code does not support assembler directives that change
- * the output section, any use of such directives is undefined.
- *
- * The yield itself consists of the following:
- * - Check whether the preempt count is exactly 1 and a reschedule is also
- * needed. If so, calling of preempt_enable() in kernel_neon_end() will
- * trigger a reschedule. If it is not the case, yielding is pointless.
- * - Disable and re-enable kernel mode NEON, and branch to the yield fixup
- * code.
- *
- * This macro sequence may clobber all CPU state that is not guaranteed by the
- * AAPCS to be preserved across an ordinary function call.
- */
-
- .macro cond_yield_neon, lbl
- if_will_cond_yield_neon
- do_cond_yield_neon
- endif_yield_neon \lbl
- .endm
-
- .macro if_will_cond_yield_neon
-#ifdef CONFIG_PREEMPTION
- get_current_task x0
- ldr x0, [x0, #TSK_TI_PREEMPT]
- sub x0, x0, #PREEMPT_DISABLE_OFFSET
- cbz x0, .Lyield_\@
- /* fall through to endif_yield_neon */
- .subsection 1
-.Lyield_\@ :
-#else
- .section ".discard.cond_yield_neon", "ax"
-#endif
- .endm
-
- .macro do_cond_yield_neon
- bl kernel_neon_end
- bl kernel_neon_begin
- .endm
-
- .macro endif_yield_neon, lbl
- .ifnb \lbl
- b \lbl
- .else
- b .Lyield_out_\@
- .endif
- .previous
-.Lyield_out_\@ :
- .endm
-
/*
- * Check whether preempt-disabled code should yield as soon as it
- * is able. This is the case if re-enabling preemption a single
- * time results in a preempt count of zero, and the TIF_NEED_RESCHED
- * flag is set. (Note that the latter is stored negated in the
- * top word of the thread_info::preempt_count field)
+ * Check whether preempt/bh-disabled asm code should yield as soon as
+ * it is able. This is the case if we are currently running in task
+ * context, and either a softirq is pending, or the TIF_NEED_RESCHED
+ * flag is set and re-enabling preemption a single time would result in
+ * a preempt count of zero. (Note that the TIF_NEED_RESCHED flag is
+ * stored negated in the top word of the thread_info::preempt_count
+ * field)
*/
- .macro cond_yield, lbl:req, tmp:req
-#ifdef CONFIG_PREEMPTION
+ .macro cond_yield, lbl:req, tmp:req, tmp2:req
get_current_task \tmp
ldr \tmp, [\tmp, #TSK_TI_PREEMPT]
+ /*
+ * If we are serving a softirq, there is no point in yielding: the
+ * softirq will not be preempted no matter what we do, so we should
+ * run to completion as quickly as we can.
+ */
+ tbnz \tmp, #SOFTIRQ_SHIFT, .Lnoyield_\@
+#ifdef CONFIG_PREEMPTION
sub \tmp, \tmp, #PREEMPT_DISABLE_OFFSET
cbz \tmp, \lbl
#endif
+ adr_l \tmp, irq_stat + IRQ_CPUSTAT_SOFTIRQ_PENDING
+ this_cpu_offset \tmp2
+ ldr w\tmp, [\tmp, \tmp2]
+ cbnz w\tmp, \lbl // yield on pending softirq in task context
+.Lnoyield_\@:
.endm
/*
#define psb_csync() asm volatile("hint #17" : : : "memory")
#define csdb() asm volatile("hint #20" : : : "memory")
-#define spec_bar() asm volatile(ALTERNATIVE("dsb nsh\nisb\n", \
- SB_BARRIER_INSN"nop\n", \
- ARM64_HAS_SB))
-
#ifdef CONFIG_ARM64_PSEUDO_NMI
#define pmr_sync() \
do { \
return mask;
}
+/*
+ * Ensure that reads of the counter are treated the same as memory reads
+ * for the purposes of ordering by subsequent memory barriers.
+ *
+ * This insanity brought to you by speculative system register reads,
+ * out-of-order memory accesses, sequence locks and Thomas Gleixner.
+ *
+ * http://lists.infradead.org/pipermail/linux-arm-kernel/2019-February/631195.html
+ */
+#define arch_counter_enforce_ordering(val) do { \
+ u64 tmp, _val = (val); \
+ \
+ asm volatile( \
+ " eor %0, %1, %1\n" \
+ " add %0, sp, %0\n" \
+ " ldr xzr, [%0]" \
+ : "=r" (tmp) : "r" (_val)); \
+} while (0)
+
#define __smp_mb() dmb(ish)
#define __smp_rmb() dmb(ishld)
#define __smp_wmb() dmb(ishst)
} while (--n > 0);
sum += ((sum >> 32) | (sum << 32));
- return csum_fold((__force u32)(sum >> 32));
+ return csum_fold((__force __wsum)(sum >> 32));
}
#define ip_fast_csum ip_fast_csum
#define ARM64_WORKAROUND_1508412 58
#define ARM64_HAS_LDAPR 59
#define ARM64_KVM_PROTECTED_MODE 60
+#define ARM64_WORKAROUND_NVIDIA_CARMEL_CNP 61
+#define ARM64_HAS_EPAN 62
-#define ARM64_NCAPS 61
+#define ARM64_NCAPS 63
#endif /* __ASM_CPUCAPS_H */
s64 safe_val; /* safe value for FTR_EXACT features */
};
+/*
+ * Describe the early feature override to the core override code:
+ *
+ * @val Values that are to be merged into the final
+ * sanitised value of the register. Only the bitfields
+ * set to 1 in @mask are valid
+ * @mask Mask of the features that are overridden by @val
+ *
+ * A @mask field set to full-1 indicates that the corresponding field
+ * in @val is a valid override.
+ *
+ * A @mask field set to full-0 with the corresponding @val field set
+ * to full-0 denotes that this field has no override
+ *
+ * A @mask field set to full-0 with the corresponding @val field set
+ * to full-1 denotes thath this field has an invalid override.
+ */
struct arm64_ftr_override {
u64 val;
u64 mask;
#include <asm/ptrace.h>
#define DAIF_PROCCTX 0
-#define DAIF_PROCCTX_NOIRQ PSR_I_BIT
-#define DAIF_ERRCTX (PSR_I_BIT | PSR_A_BIT)
+#define DAIF_PROCCTX_NOIRQ (PSR_I_BIT | PSR_F_BIT)
+#define DAIF_ERRCTX (PSR_A_BIT | PSR_I_BIT | PSR_F_BIT)
#define DAIF_MASK (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT)
if (system_uses_irq_prio_masking()) {
/* If IRQs are masked with PMR, reflect it in the flags */
if (read_sysreg_s(SYS_ICC_PMR_EL1) != GIC_PRIO_IRQON)
- flags |= PSR_I_BIT;
+ flags |= PSR_I_BIT | PSR_F_BIT;
}
return flags;
bool irq_disabled = flags & PSR_I_BIT;
WARN_ON(system_has_prio_mask_debugging() &&
- !(read_sysreg(daif) & PSR_I_BIT));
+ (read_sysreg(daif) & (PSR_I_BIT | PSR_F_BIT)) != (PSR_I_BIT | PSR_F_BIT));
if (!irq_disabled) {
trace_hardirqs_on();
* If interrupts are disabled but we can take
* asynchronous errors, we can take NMIs
*/
- flags &= ~PSR_I_BIT;
+ flags &= ~(PSR_I_BIT | PSR_F_BIT);
pmr = GIC_PRIO_IRQOFF;
} else {
pmr = GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET;
.Lskip_sve_\@:
.endm
+/* Disable any fine grained traps */
+.macro __init_el2_fgt
+ mrs x1, id_aa64mmfr0_el1
+ ubfx x1, x1, #ID_AA64MMFR0_FGT_SHIFT, #4
+ cbz x1, .Lskip_fgt_\@
+
+ msr_s SYS_HDFGRTR_EL2, xzr
+ msr_s SYS_HDFGWTR_EL2, xzr
+ msr_s SYS_HFGRTR_EL2, xzr
+ msr_s SYS_HFGWTR_EL2, xzr
+ msr_s SYS_HFGITR_EL2, xzr
+
+ mrs x1, id_aa64pfr0_el1 // AMU traps UNDEF without AMU
+ ubfx x1, x1, #ID_AA64PFR0_AMU_SHIFT, #4
+ cbz x1, .Lskip_fgt_\@
+
+ msr_s SYS_HAFGRTR_EL2, xzr
+.Lskip_fgt_\@:
+.endm
+
.macro __init_el2_nvhe_prepare_eret
mov x0, #INIT_PSTATE_EL1
msr spsr_el2, x0
__init_el2_nvhe_idregs
__init_el2_nvhe_cptr
__init_el2_nvhe_sve
+ __init_el2_fgt
__init_el2_nvhe_prepare_eret
.endm
extern void sve_load_from_fpsimd_state(struct user_fpsimd_state const *state,
unsigned long vq_minus_1);
extern unsigned int sve_get_vl(void);
+extern void sve_set_vq(unsigned long vq_minus_1);
struct arm64_cpu_capabilities;
extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused);
struct pt_regs;
+int set_handle_irq(void (*handle_irq)(struct pt_regs *));
+#define set_handle_irq set_handle_irq
+int set_handle_fiq(void (*handle_fiq)(struct pt_regs *));
+
static inline int nr_legacy_irqs(void)
{
return 0;
#ifndef __ASM_IRQ_WORK_H
#define __ASM_IRQ_WORK_H
+extern void arch_irq_work_raise(void);
+
static inline bool arch_irq_work_has_interrupt(void)
{
return true;
/*
* Aarch64 has flags for masking: Debug, Asynchronous (serror), Interrupts and
- * FIQ exceptions, in the 'daif' register. We mask and unmask them in 'dai'
+ * FIQ exceptions, in the 'daif' register. We mask and unmask them in 'daif'
* order:
* Masking debug exceptions causes all other exceptions to be masked too/
- * Masking SError masks irq, but not debug exceptions. Masking irqs has no
- * side effects for other flags. Keeping to this order makes it easier for
- * entry.S to know which exceptions should be unmasked.
- *
- * FIQ is never expected, but we mask it when we disable debug exceptions, and
- * unmask it at all other times.
+ * Masking SError masks IRQ/FIQ, but not debug exceptions. IRQ and FIQ are
+ * always masked and unmasked together, and have no side effects for other
+ * flags. Keeping to this order makes it easier for entry.S to know which
+ * exceptions should be unmasked.
*/
/*
}
asm volatile(ALTERNATIVE(
- "msr daifclr, #2 // arch_local_irq_enable",
+ "msr daifclr, #3 // arch_local_irq_enable",
__msr_s(SYS_ICC_PMR_EL1, "%0"),
ARM64_HAS_IRQ_PRIO_MASKING)
:
}
asm volatile(ALTERNATIVE(
- "msr daifset, #2 // arch_local_irq_disable",
+ "msr daifset, #3 // arch_local_irq_disable",
__msr_s(SYS_ICC_PMR_EL1, "%0"),
ARM64_HAS_IRQ_PRIO_MASKING)
:
#define CPTR_EL2_DEFAULT CPTR_EL2_RES1
/* Hyp Debug Configuration Register bits */
+#define MDCR_EL2_TTRF (1 << 19)
#define MDCR_EL2_TPMS (1 << 14)
#define MDCR_EL2_E2PB_MASK (UL(0x3))
#define MDCR_EL2_E2PB_SHIFT (UL(12))
#define __KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context 2
#define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa 3
#define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid 4
-#define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_local_vmid 5
+#define __KVM_HOST_SMCCC_FUNC___kvm_flush_cpu_context 5
#define __KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff 6
#define __KVM_HOST_SMCCC_FUNC___kvm_enable_ssbs 7
-#define __KVM_HOST_SMCCC_FUNC___vgic_v3_get_ich_vtr_el2 8
+#define __KVM_HOST_SMCCC_FUNC___vgic_v3_get_gic_config 8
#define __KVM_HOST_SMCCC_FUNC___vgic_v3_read_vmcr 9
#define __KVM_HOST_SMCCC_FUNC___vgic_v3_write_vmcr 10
#define __KVM_HOST_SMCCC_FUNC___vgic_v3_init_lrs 11
#define __bp_harden_hyp_vecs CHOOSE_HYP_SYM(__bp_harden_hyp_vecs)
extern void __kvm_flush_vm_context(void);
+extern void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu);
extern void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, phys_addr_t ipa,
int level);
extern void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu);
-extern void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu);
extern void __kvm_timer_set_cntvoff(u64 cntvoff);
extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
-extern u64 __vgic_v3_get_ich_vtr_el2(void);
+extern u64 __vgic_v3_get_gic_config(void);
extern u64 __vgic_v3_read_vmcr(void);
extern void __vgic_v3_write_vmcr(u32 vmcr);
extern void __vgic_v3_init_lrs(void);
void __debug_switch_to_guest(struct kvm_vcpu *vcpu);
void __debug_switch_to_host(struct kvm_vcpu *vcpu);
+#ifdef __KVM_NVHE_HYPERVISOR__
+void __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu);
+void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu);
+#endif
+
void __fpsimd_save_state(struct user_fpsimd_state *fp_regs);
void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs);
void __noreturn hyp_panic(void);
#ifdef __KVM_NVHE_HYPERVISOR__
-void __noreturn __hyp_do_panic(bool restore_host, u64 spsr, u64 elr, u64 par);
+void __noreturn __hyp_do_panic(struct kvm_cpu_context *host_ctxt, u64 spsr,
+ u64 elr, u64 par);
#endif
#endif /* __ARM64_KVM_HYP_H__ */
}
#ifdef CONFIG_KASAN_HW_TAGS
-#define arch_enable_tagging() mte_enable_kernel()
+#define arch_enable_tagging_sync() mte_enable_kernel_sync()
+#define arch_enable_tagging_async() mte_enable_kernel_async()
#define arch_set_tagging_report_once(state) mte_set_report_once(state)
+#define arch_force_async_tag_fault() mte_check_tfsr_exit()
#define arch_init_tags(max_tag) mte_init_tags(max_tag)
#define arch_get_random_tag() mte_get_random_tag()
#define arch_get_mem_tag(addr) mte_get_mem_tag(addr)
#define ARCH_PFN_OFFSET ((unsigned long)PHYS_PFN_OFFSET)
#if !defined(CONFIG_SPARSEMEM_VMEMMAP) || defined(CONFIG_DEBUG_VIRTUAL)
+#define page_to_virt(x) ({ \
+ __typeof__(x) __page = x; \
+ void *__addr = __va(page_to_phys(__page)); \
+ (void *)__tag_set((const void *)__addr, page_kasan_tag(__page));\
+})
#define virt_to_page(x) pfn_to_page(virt_to_pfn(x))
#else
#define page_to_virt(x) ({ \
extern u64 idmap_t0sz;
extern u64 idmap_ptrs_per_pgd;
-static inline bool __cpu_uses_extended_idmap(void)
-{
- if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52))
- return false;
-
- return unlikely(idmap_t0sz != TCR_T0SZ(VA_BITS));
-}
-
-/*
- * True if the extended ID map requires an extra level of translation table
- * to be configured.
- */
-static inline bool __cpu_uses_extended_idmap_level(void)
-{
- return ARM64_HW_PGTABLE_LEVELS(64 - idmap_t0sz) > CONFIG_PGTABLE_LEVELS;
-}
-
/*
* Ensure TCR.T0SZ is set to the provided value.
*/
} while (curr != end);
}
-void mte_enable_kernel(void);
+void mte_enable_kernel_sync(void);
+void mte_enable_kernel_async(void);
void mte_init_tags(u64 max_tag);
void mte_set_report_once(bool state);
{
}
-static inline void mte_enable_kernel(void)
+static inline void mte_enable_kernel_sync(void)
+{
+}
+
+static inline void mte_enable_kernel_async(void)
{
}
void mte_sync_tags(pte_t *ptep, pte_t pte);
void mte_copy_page_tags(void *kto, const void *kfrom);
-void flush_mte_state(void);
+void mte_thread_init_user(void);
void mte_thread_switch(struct task_struct *next);
+void mte_suspend_enter(void);
void mte_suspend_exit(void);
long set_mte_ctrl(struct task_struct *task, unsigned long arg);
long get_mte_ctrl(struct task_struct *task);
int mte_ptrace_copy_tags(struct task_struct *child, long request,
unsigned long addr, unsigned long data);
-void mte_assign_mem_tag_range(void *addr, size_t size);
-
#else /* CONFIG_ARM64_MTE */
/* unused if !CONFIG_ARM64_MTE, silence the compiler */
static inline void mte_copy_page_tags(void *kto, const void *kfrom)
{
}
-static inline void flush_mte_state(void)
+static inline void mte_thread_init_user(void)
{
}
static inline void mte_thread_switch(struct task_struct *next)
{
}
+static inline void mte_suspend_enter(void)
+{
+}
static inline void mte_suspend_exit(void)
{
}
return -EIO;
}
-static inline void mte_assign_mem_tag_range(void *addr, size_t size)
+#endif /* CONFIG_ARM64_MTE */
+
+#ifdef CONFIG_KASAN_HW_TAGS
+/* Whether the MTE asynchronous mode is enabled. */
+DECLARE_STATIC_KEY_FALSE(mte_async_mode);
+
+static inline bool system_uses_mte_async_mode(void)
{
+ return static_branch_unlikely(&mte_async_mode);
}
-#endif /* CONFIG_ARM64_MTE */
+void mte_check_tfsr_el1(void);
+
+static inline void mte_check_tfsr_entry(void)
+{
+ mte_check_tfsr_el1();
+}
+
+static inline void mte_check_tfsr_exit(void)
+{
+ /*
+ * The asynchronous faults are sync'ed automatically with
+ * TFSR_EL1 on kernel entry but for exit an explicit dsb()
+ * is required.
+ */
+ dsb(nsh);
+ isb();
+
+ mte_check_tfsr_el1();
+}
+#else
+static inline bool system_uses_mte_async_mode(void)
+{
+ return false;
+}
+static inline void mte_check_tfsr_el1(void)
+{
+}
+static inline void mte_check_tfsr_entry(void)
+{
+}
+static inline void mte_check_tfsr_exit(void)
+{
+}
+#endif /* CONFIG_KASAN_HW_TAGS */
#endif /* __ASSEMBLY__ */
#endif /* __ASM_MTE_H */
#define _ASM_ARM64_PARAVIRT_H
#ifdef CONFIG_PARAVIRT
+#include <linux/static_call_types.h>
+
struct static_key;
extern struct static_key paravirt_steal_enabled;
extern struct static_key paravirt_steal_rq_enabled;
-struct pv_time_ops {
- unsigned long long (*steal_clock)(int cpu);
-};
-
-struct paravirt_patch_template {
- struct pv_time_ops time;
-};
+u64 dummy_steal_clock(int cpu);
-extern struct paravirt_patch_template pv_ops;
+DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock);
static inline u64 paravirt_steal_clock(int cpu)
{
- return pv_ops.time.steal_clock(cpu);
+ return static_call(pv_steal_clock)(cpu);
}
int __init pv_time_init(void);
static inline void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmdp)
{
- __pud_populate(pudp, __pa(pmdp), PMD_TYPE_TABLE);
+ pudval_t pudval = PUD_TYPE_TABLE;
+
+ pudval |= (mm == &init_mm) ? PUD_TABLE_UXN : PUD_TABLE_PXN;
+ __pud_populate(pudp, __pa(pmdp), pudval);
}
#else
static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot)
static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4dp, pud_t *pudp)
{
- __p4d_populate(p4dp, __pa(pudp), PUD_TYPE_TABLE);
+ p4dval_t p4dval = P4D_TYPE_TABLE;
+
+ p4dval |= (mm == &init_mm) ? P4D_TABLE_UXN : P4D_TABLE_PXN;
+ __p4d_populate(p4dp, __pa(pudp), p4dval);
}
#else
static inline void __p4d_populate(p4d_t *p4dp, phys_addr_t pudp, p4dval_t prot)
static inline void
pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, pte_t *ptep)
{
- /*
- * The pmd must be loaded with the physical address of the PTE table
- */
- __pmd_populate(pmdp, __pa(ptep), PMD_TYPE_TABLE);
+ VM_BUG_ON(mm != &init_mm);
+ __pmd_populate(pmdp, __pa(ptep), PMD_TYPE_TABLE | PMD_TABLE_UXN);
}
static inline void
pmd_populate(struct mm_struct *mm, pmd_t *pmdp, pgtable_t ptep)
{
- __pmd_populate(pmdp, page_to_phys(ptep), PMD_TYPE_TABLE);
+ VM_BUG_ON(mm == &init_mm);
+ __pmd_populate(pmdp, page_to_phys(ptep), PMD_TYPE_TABLE | PMD_TABLE_PXN);
}
#define pmd_pgtable(pmd) pmd_page(pmd)
/*
* Hardware page table definitions.
*
+ * Level 0 descriptor (P4D).
+ */
+#define P4D_TYPE_TABLE (_AT(p4dval_t, 3) << 0)
+#define P4D_TABLE_BIT (_AT(p4dval_t, 1) << 1)
+#define P4D_TYPE_MASK (_AT(p4dval_t, 3) << 0)
+#define P4D_TYPE_SECT (_AT(p4dval_t, 1) << 0)
+#define P4D_SECT_RDONLY (_AT(p4dval_t, 1) << 7) /* AP[2] */
+#define P4D_TABLE_PXN (_AT(p4dval_t, 1) << 59)
+#define P4D_TABLE_UXN (_AT(p4dval_t, 1) << 60)
+
+/*
* Level 1 descriptor (PUD).
*/
#define PUD_TYPE_TABLE (_AT(pudval_t, 3) << 0)
#define PUD_TYPE_MASK (_AT(pudval_t, 3) << 0)
#define PUD_TYPE_SECT (_AT(pudval_t, 1) << 0)
#define PUD_SECT_RDONLY (_AT(pudval_t, 1) << 7) /* AP[2] */
+#define PUD_TABLE_PXN (_AT(pudval_t, 1) << 59)
+#define PUD_TABLE_UXN (_AT(pudval_t, 1) << 60)
/*
* Level 2 descriptor (PMD).
#define PMD_SECT_CONT (_AT(pmdval_t, 1) << 52)
#define PMD_SECT_PXN (_AT(pmdval_t, 1) << 53)
#define PMD_SECT_UXN (_AT(pmdval_t, 1) << 54)
+#define PMD_TABLE_PXN (_AT(pmdval_t, 1) << 59)
+#define PMD_TABLE_UXN (_AT(pmdval_t, 1) << 60)
/*
* AttrIndx[2:0] encoding (mapping attributes defined in the MAIR* registers).
#define _PAGE_DEFAULT (_PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
#define PAGE_KERNEL __pgprot(PROT_NORMAL)
-#define PAGE_KERNEL_TAGGED __pgprot(PROT_NORMAL_TAGGED)
#define PAGE_KERNEL_RO __pgprot((PROT_NORMAL & ~PTE_WRITE) | PTE_RDONLY)
#define PAGE_KERNEL_ROX __pgprot((PROT_NORMAL & ~(PTE_WRITE | PTE_PXN)) | PTE_RDONLY)
#define PAGE_KERNEL_EXEC __pgprot(PROT_NORMAL & ~PTE_PXN)
#define PAGE_SHARED_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_WRITE)
#define PAGE_READONLY __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
#define PAGE_READONLY_EXEC __pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN)
+#define PAGE_EXECONLY __pgprot(_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN)
#define __P000 PAGE_NONE
#define __P001 PAGE_READONLY
#define __P010 PAGE_READONLY
#define __P011 PAGE_READONLY
-#define __P100 PAGE_READONLY_EXEC
+#define __P100 PAGE_EXECONLY
#define __P101 PAGE_READONLY_EXEC
#define __P110 PAGE_READONLY_EXEC
#define __P111 PAGE_READONLY_EXEC
#define __S001 PAGE_READONLY
#define __S010 PAGE_SHARED
#define __S011 PAGE_SHARED
-#define __S100 PAGE_READONLY_EXEC
+#define __S100 PAGE_EXECONLY
#define __S101 PAGE_READONLY_EXEC
#define __S110 PAGE_SHARED_EXEC
#define __S111 PAGE_SHARED_EXEC
#define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte))
#define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID))
+/*
+ * Execute-only user mappings do not have the PTE_USER bit set. All valid
+ * kernel mappings have the PTE_UXN bit set.
+ */
#define pte_valid_not_user(pte) \
- ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
-#define pte_valid_user(pte) \
- ((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER))
-
+ ((pte_val(pte) & (PTE_VALID | PTE_USER | PTE_UXN)) == (PTE_VALID | PTE_UXN))
/*
* Could the pte be present in the TLB? We must check mm_tlb_flush_pending
* so that we don't erroneously return false for pages that have been
(mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte))
/*
- * p??_access_permitted() is true for valid user mappings (subject to the
- * write permission check). PROT_NONE mappings do not have the PTE_VALID bit
- * set.
+ * p??_access_permitted() is true for valid user mappings (PTE_USER
+ * bit set, subject to the write permission check). For execute-only
+ * mappings, like PROT_EXEC with EPAN (both PTE_USER and PTE_UXN bits
+ * not set) must return false. PROT_NONE mappings do not have the
+ * PTE_VALID bit set.
*/
#define pte_access_permitted(pte, write) \
- (pte_valid_user(pte) && (!(write) || pte_write(pte)))
+ (((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) && (!(write) || pte_write(pte)))
#define pmd_access_permitted(pmd, write) \
(pte_access_permitted(pmd_pte(pmd), (write)))
#define pud_access_permitted(pud, write) \
__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN)
#define pgprot_device(prot) \
__pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_PXN | PTE_UXN)
+#define pgprot_tagged(prot) \
+ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_TAGGED))
+#define pgprot_mhp pgprot_tagged
/*
* DMA allocations for non-coherent devices use what the Arm architecture calls
* "Normal non-cacheable" memory, which permits speculation, unaligned accesses
}
#define arch_wants_old_prefaulted_pte arch_wants_old_prefaulted_pte
+static inline pgprot_t arch_filter_pgprot(pgprot_t prot)
+{
+ if (cpus_have_const_cap(ARM64_HAS_EPAN))
+ return prot;
+
+ if (pgprot_val(prot) != pgprot_val(PAGE_EXECONLY))
+ return prot;
+
+ return PAGE_READONLY_EXEC;
+}
+
+
#endif /* !__ASSEMBLY__ */
#endif /* __ASM_PGTABLE_H */
#define __ASM_POINTER_AUTH_H
#include <linux/bitops.h>
+#include <linux/prctl.h>
#include <linux/random.h>
#include <asm/cpufeature.h>
struct ptrauth_key apia;
};
+#define __ptrauth_key_install_nosync(k, v) \
+do { \
+ struct ptrauth_key __pki_v = (v); \
+ write_sysreg_s(__pki_v.lo, SYS_ ## k ## KEYLO_EL1); \
+ write_sysreg_s(__pki_v.hi, SYS_ ## k ## KEYHI_EL1); \
+} while (0)
+
+static inline void ptrauth_keys_install_user(struct ptrauth_keys_user *keys)
+{
+ if (system_supports_address_auth()) {
+ __ptrauth_key_install_nosync(APIB, keys->apib);
+ __ptrauth_key_install_nosync(APDA, keys->apda);
+ __ptrauth_key_install_nosync(APDB, keys->apdb);
+ }
+
+ if (system_supports_generic_auth())
+ __ptrauth_key_install_nosync(APGA, keys->apga);
+}
+
static inline void ptrauth_keys_init_user(struct ptrauth_keys_user *keys)
{
if (system_supports_address_auth()) {
if (system_supports_generic_auth())
get_random_bytes(&keys->apga, sizeof(keys->apga));
-}
-#define __ptrauth_key_install_nosync(k, v) \
-do { \
- struct ptrauth_key __pki_v = (v); \
- write_sysreg_s(__pki_v.lo, SYS_ ## k ## KEYLO_EL1); \
- write_sysreg_s(__pki_v.hi, SYS_ ## k ## KEYHI_EL1); \
-} while (0)
+ ptrauth_keys_install_user(keys);
+}
static __always_inline void ptrauth_keys_init_kernel(struct ptrauth_keys_kernel *keys)
{
extern int ptrauth_prctl_reset_keys(struct task_struct *tsk, unsigned long arg);
+extern int ptrauth_set_enabled_keys(struct task_struct *tsk, unsigned long keys,
+ unsigned long enabled);
+extern int ptrauth_get_enabled_keys(struct task_struct *tsk);
+
static inline unsigned long ptrauth_strip_insn_pac(unsigned long ptr)
{
return ptrauth_clear_pac(ptr);
isb();
}
-#define ptrauth_thread_init_user(tsk) \
- ptrauth_keys_init_user(&(tsk)->thread.keys_user)
+#define ptrauth_suspend_exit() \
+ ptrauth_keys_install_user(¤t->thread.keys_user)
+
+#define ptrauth_thread_init_user() \
+ do { \
+ ptrauth_keys_init_user(¤t->thread.keys_user); \
+ \
+ /* enable all keys */ \
+ if (system_supports_address_auth()) \
+ set_task_sctlr_el1(current->thread.sctlr_user | \
+ SCTLR_ELx_ENIA | SCTLR_ELx_ENIB | \
+ SCTLR_ELx_ENDA | SCTLR_ELx_ENDB); \
+ } while (0)
+
+#define ptrauth_thread_switch_user(tsk) \
+ ptrauth_keys_install_user(&(tsk)->thread.keys_user)
+
#define ptrauth_thread_init_kernel(tsk) \
ptrauth_keys_init_kernel(&(tsk)->thread.keys_kernel)
#define ptrauth_thread_switch_kernel(tsk) \
#else /* CONFIG_ARM64_PTR_AUTH */
#define ptrauth_enable()
#define ptrauth_prctl_reset_keys(tsk, arg) (-EINVAL)
+#define ptrauth_set_enabled_keys(tsk, keys, enabled) (-EINVAL)
+#define ptrauth_get_enabled_keys(tsk) (-EINVAL)
#define ptrauth_strip_insn_pac(lr) (lr)
-#define ptrauth_thread_init_user(tsk)
+#define ptrauth_suspend_exit()
+#define ptrauth_thread_init_user()
#define ptrauth_thread_init_kernel(tsk)
+#define ptrauth_thread_switch_user(tsk)
#define ptrauth_thread_switch_kernel(tsk)
#endif /* CONFIG_ARM64_PTR_AUTH */
+#define PR_PAC_ENABLED_KEYS_MASK \
+ (PR_PAC_APIAKEY | PR_PAC_APIBKEY | PR_PAC_APDAKEY | PR_PAC_APDBKEY)
+
#endif /* __ASM_POINTER_AUTH_H */
struct ptrauth_keys_kernel keys_kernel;
#endif
#ifdef CONFIG_ARM64_MTE
- u64 sctlr_tcf0;
u64 gcr_user_excl;
#endif
+ u64 sctlr_user;
};
+#define SCTLR_USER_MASK \
+ (SCTLR_ELx_ENIA | SCTLR_ELx_ENIB | SCTLR_ELx_ENDA | SCTLR_ELx_ENDB | \
+ SCTLR_EL1_TCF0_MASK)
+
static inline void arch_thread_struct_whitelist(unsigned long *offset,
unsigned long *size)
{
unsigned long get_wchan(struct task_struct *p);
+void set_task_sctlr_el1(u64 sctlr);
+
/* Thread switching */
extern struct task_struct *cpu_switch_to(struct task_struct *prev,
struct task_struct *next);
+asmlinkage void arm64_preempt_schedule_irq(void);
+
#define task_pt_regs(p) \
((struct pt_regs *)(THREAD_SIZE + task_stack_page(p)) - 1)
/* PR_PAC_RESET_KEYS prctl */
#define PAC_RESET_KEYS(tsk, arg) ptrauth_prctl_reset_keys(tsk, arg)
+/* PR_PAC_{SET,GET}_ENABLED_KEYS prctl */
+#define PAC_SET_ENABLED_KEYS(tsk, keys, enabled) \
+ ptrauth_set_enabled_keys(tsk, keys, enabled)
+#define PAC_GET_ENABLED_KEYS(tsk) ptrauth_get_enabled_keys(tsk)
+
#ifdef CONFIG_ARM64_TAGGED_ADDR_ABI
/* PR_{SET,GET}_TAGGED_ADDR_CTRL prctl */
long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg);
void ptdump_walk(struct seq_file *s, struct ptdump_info *info);
#ifdef CONFIG_PTDUMP_DEBUGFS
-void ptdump_debugfs_register(struct ptdump_info *info, const char *name);
+void __init ptdump_debugfs_register(struct ptdump_info *info, const char *name);
#else
static inline void ptdump_debugfs_register(struct ptdump_info *info,
const char *name) { }
extern void crash_smp_send_stop(void);
extern bool smp_crash_stop_failed(void);
+extern void panic_smp_self_stop(void);
#endif /* ifndef __ASSEMBLY__ */
return false;
}
-static inline void start_backtrace(struct stackframe *frame,
- unsigned long fp, unsigned long pc)
-{
- frame->fp = fp;
- frame->pc = pc;
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
- frame->graph = 0;
-#endif
-
- /*
- * Prime the first unwind.
- *
- * In unwind_frame() we'll check that the FP points to a valid stack,
- * which can't be STACK_TYPE_UNKNOWN, and the first unwind will be
- * treated as a transition to whichever stack that happens to be. The
- * prev_fp value won't be used, but we set it to 0 such that it is
- * definitely not an accessible stack address.
- */
- bitmap_zero(frame->stacks_done, __NR_STACK_TYPES);
- frame->prev_fp = 0;
- frame->prev_type = STACK_TYPE_UNKNOWN;
-}
+void start_backtrace(struct stackframe *frame, unsigned long fp,
+ unsigned long pc);
#endif /* __ASM_STACKTRACE_H */
#define SYS_PMCCFILTR_EL0 sys_reg(3, 3, 14, 15, 7)
#define SYS_SCTLR_EL2 sys_reg(3, 4, 1, 0, 0)
+#define SYS_HFGRTR_EL2 sys_reg(3, 4, 1, 1, 4)
+#define SYS_HFGWTR_EL2 sys_reg(3, 4, 1, 1, 5)
+#define SYS_HFGITR_EL2 sys_reg(3, 4, 1, 1, 6)
#define SYS_ZCR_EL2 sys_reg(3, 4, 1, 2, 0)
#define SYS_TRFCR_EL2 sys_reg(3, 4, 1, 2, 1)
#define SYS_DACR32_EL2 sys_reg(3, 4, 3, 0, 0)
+#define SYS_HDFGRTR_EL2 sys_reg(3, 4, 3, 1, 4)
+#define SYS_HDFGWTR_EL2 sys_reg(3, 4, 3, 1, 5)
+#define SYS_HAFGRTR_EL2 sys_reg(3, 4, 3, 1, 6)
#define SYS_SPSR_EL2 sys_reg(3, 4, 4, 0, 0)
#define SYS_ELR_EL2 sys_reg(3, 4, 4, 0, 1)
#define SYS_IFSR32_EL2 sys_reg(3, 4, 5, 0, 1)
#define SCTLR_ELx_TCF_ASYNC (UL(0x2) << SCTLR_ELx_TCF_SHIFT)
#define SCTLR_ELx_TCF_MASK (UL(0x3) << SCTLR_ELx_TCF_SHIFT)
+#define SCTLR_ELx_ENIA_SHIFT 31
+
#define SCTLR_ELx_ITFSB (BIT(37))
-#define SCTLR_ELx_ENIA (BIT(31))
+#define SCTLR_ELx_ENIA (BIT(SCTLR_ELx_ENIA_SHIFT))
#define SCTLR_ELx_ENIB (BIT(30))
#define SCTLR_ELx_ENDA (BIT(27))
#define SCTLR_ELx_EE (BIT(25))
(SCTLR_EL2_RES1 | ENDIAN_SET_EL2)
/* SCTLR_EL1 specific flags. */
+#define SCTLR_EL1_EPAN (BIT(57))
#define SCTLR_EL1_ATA0 (BIT(42))
#define SCTLR_EL1_TCF0_SHIFT 38
SCTLR_EL1_SED | SCTLR_ELx_I | SCTLR_EL1_DZE | SCTLR_EL1_UCT | \
SCTLR_EL1_NTWE | SCTLR_ELx_IESB | SCTLR_EL1_SPAN | SCTLR_ELx_ITFSB | \
SCTLR_ELx_ATA | SCTLR_EL1_ATA0 | ENDIAN_SET_EL1 | SCTLR_EL1_UCI | \
- SCTLR_EL1_RES1)
+ SCTLR_EL1_EPAN | SCTLR_EL1_RES1)
/* MAIR_ELx memory attributes (used by Linux) */
#define MAIR_ATTR_DEVICE_nGnRnE UL(0x00)
#define ID_AA64MMFR0_PARANGE_48 0x5
#define ID_AA64MMFR0_PARANGE_52 0x6
+#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_DEFAULT 0x0
+#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_NONE 0x1
+#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_MIN 0x2
+#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_MAX 0x7
+
#ifdef CONFIG_ARM64_PA_BITS_52
#define ID_AA64MMFR0_PARANGE_MAX ID_AA64MMFR0_PARANGE_52
#else
#define ID_PFR1_PROGMOD_SHIFT 0
#if defined(CONFIG_ARM64_4K_PAGES)
-#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN4_SHIFT
-#define ID_AA64MMFR0_TGRAN_SUPPORTED ID_AA64MMFR0_TGRAN4_SUPPORTED
+#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN4_SHIFT
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN4_SUPPORTED
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX 0x7
#elif defined(CONFIG_ARM64_16K_PAGES)
-#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN16_SHIFT
-#define ID_AA64MMFR0_TGRAN_SUPPORTED ID_AA64MMFR0_TGRAN16_SUPPORTED
+#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN16_SHIFT
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN16_SUPPORTED
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX 0xF
#elif defined(CONFIG_ARM64_64K_PAGES)
-#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN64_SHIFT
-#define ID_AA64MMFR0_TGRAN_SUPPORTED ID_AA64MMFR0_TGRAN64_SUPPORTED
+#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN64_SHIFT
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN64_SUPPORTED
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX 0x7
#endif
#define MVFR2_FPMISC_SHIFT 4
#define arch_setup_new_exec arch_setup_new_exec
void arch_release_task_struct(struct task_struct *tsk);
+int arch_dup_task_struct(struct task_struct *dst,
+ struct task_struct *src);
#endif
#include <asm/cpufeature.h>
#include <asm/mmu.h>
+#include <asm/mte.h>
#include <asm/ptrace.h>
#include <asm/memory.h>
#include <asm/extable.h>
ARM64_MTE, CONFIG_KASAN_HW_TAGS));
}
+/*
+ * These functions disable tag checking only if in MTE async mode
+ * since the sync mode generates exceptions synchronously and the
+ * nofault or load_unaligned_zeropad can handle them.
+ */
+static inline void __uaccess_disable_tco_async(void)
+{
+ if (system_uses_mte_async_mode())
+ __uaccess_disable_tco();
+}
+
+static inline void __uaccess_enable_tco_async(void)
+{
+ if (system_uses_mte_async_mode())
+ __uaccess_enable_tco();
+}
+
static inline void uaccess_disable_privileged(void)
{
__uaccess_disable_tco();
do { \
int __gkn_err = 0; \
\
+ __uaccess_enable_tco_async(); \
__raw_get_mem("ldr", *((type *)(dst)), \
(__force type *)(src), __gkn_err); \
+ __uaccess_disable_tco_async(); \
if (unlikely(__gkn_err)) \
goto err_label; \
} while (0)
do { \
int __pkn_err = 0; \
\
+ __uaccess_enable_tco_async(); \
__raw_put_mem("str", *((type *)(src)), \
(__force type *)(dst), __pkn_err); \
+ __uaccess_disable_tco_async(); \
if (unlikely(__pkn_err)) \
goto err_label; \
} while(0)
*/
isb();
asm volatile("mrs %0, cntvct_el0" : "=r" (res) :: "memory");
- /*
- * This isb() is required to prevent that the seq lock is
- * speculated.#
- */
- isb();
+ arch_counter_enforce_ordering(res);
return res;
}
*/
static inline unsigned long load_unaligned_zeropad(const void *addr)
{
- unsigned long ret, offset;
+ unsigned long ret, tmp;
+
+ __uaccess_enable_tco_async();
/* Load word from unaligned pointer addr */
asm(
"2:\n"
" .pushsection .fixup,\"ax\"\n"
" .align 2\n"
- "3: and %1, %2, #0x7\n"
- " bic %2, %2, #0x7\n"
- " ldr %0, [%2]\n"
+ "3: bic %1, %2, #0x7\n"
+ " ldr %0, [%1]\n"
+ " and %1, %2, #0x7\n"
" lsl %1, %1, #0x3\n"
#ifndef __AARCH64EB__
" lsr %0, %0, %1\n"
" b 2b\n"
" .popsection\n"
_ASM_EXTABLE(1b, 3b)
- : "=&r" (ret), "=&r" (offset)
+ : "=&r" (ret), "=&r" (tmp)
: "r" (addr), "Q" (*(unsigned long *)addr));
+ __uaccess_disable_tco_async();
+
return ret;
}
--- /dev/null
+#include <xen/arm/swiotlb-xen.h>
CFLAGS_REMOVE_insn.o = $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE)
+# Remove stack protector to avoid triggering unneeded stack canary
+# checks due to randomize_kstack_offset.
+CFLAGS_REMOVE_syscall.o = -fstack-protector -fstack-protector-strong
+CFLAGS_syscall.o += -fno-stack-protector
+
# Object file lists.
obj-y := debug-monitors.o entry.o irq.o fpsimd.o \
entry-common.o entry-fpsimd.o process.o ptrace.o \
#endif
BLANK();
DEFINE(THREAD_CPU_CONTEXT, offsetof(struct task_struct, thread.cpu_context));
+ DEFINE(THREAD_SCTLR_USER, offsetof(struct task_struct, thread.sctlr_user));
#ifdef CONFIG_ARM64_PTR_AUTH
DEFINE(THREAD_KEYS_USER, offsetof(struct task_struct, thread.keys_user));
DEFINE(THREAD_KEYS_KERNEL, offsetof(struct task_struct, thread.keys_kernel));
DEFINE(DMA_FROM_DEVICE, DMA_FROM_DEVICE);
BLANK();
DEFINE(PREEMPT_DISABLE_OFFSET, PREEMPT_DISABLE_OFFSET);
+ DEFINE(SOFTIRQ_SHIFT, SOFTIRQ_SHIFT);
+ DEFINE(IRQ_CPUSTAT_SOFTIRQ_PENDING, offsetof(irq_cpustat_t, __softirq_pending));
BLANK();
DEFINE(CPU_BOOT_STACK, offsetof(struct secondary_data, stack));
DEFINE(CPU_BOOT_TASK, offsetof(struct secondary_data, task));
#endif
#ifdef CONFIG_ARM64_PTR_AUTH
DEFINE(PTRAUTH_USER_KEY_APIA, offsetof(struct ptrauth_keys_user, apia));
- DEFINE(PTRAUTH_USER_KEY_APIB, offsetof(struct ptrauth_keys_user, apib));
- DEFINE(PTRAUTH_USER_KEY_APDA, offsetof(struct ptrauth_keys_user, apda));
- DEFINE(PTRAUTH_USER_KEY_APDB, offsetof(struct ptrauth_keys_user, apdb));
- DEFINE(PTRAUTH_USER_KEY_APGA, offsetof(struct ptrauth_keys_user, apga));
DEFINE(PTRAUTH_KERNEL_KEY_APIA, offsetof(struct ptrauth_keys_kernel, apia));
BLANK();
#endif
1, 0),
},
#endif
+#ifdef CONFIG_NVIDIA_CARMEL_CNP_ERRATUM
+ {
+ /* NVIDIA Carmel */
+ .desc = "NVIDIA Carmel CNP erratum",
+ .capability = ARM64_WORKAROUND_NVIDIA_CARMEL_CNP,
+ ERRATA_MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL),
+ },
+#endif
{
}
};
* of support.
*/
S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64DFR0_PMUVER_SHIFT, 4, 0),
- ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64DFR0_TRACEVER_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64DFR0_DEBUGVER_SHIFT, 4, 0x6),
ARM64_FTR_END,
};
reg->name,
ftrp->shift + ftrp->width - 1,
ftrp->shift, str, tmp);
+ } else if ((ftr_mask & reg->override->val) == ftr_mask) {
+ reg->override->val &= ~ftr_mask;
+ pr_warn("%s[%d:%d]: impossible override, ignored\n",
+ reg->name,
+ ftrp->shift + ftrp->width - 1,
+ ftrp->shift);
}
val = arm64_ftr_set_value(ftrp, val, ftr_new);
* may share TLB entries with a CPU stuck in the crashed
* kernel.
*/
- if (is_kdump_kernel())
+ if (is_kdump_kernel())
+ return false;
+
+ if (cpus_have_const_cap(ARM64_WORKAROUND_NVIDIA_CARMEL_CNP))
return false;
return has_cpuid_feature(entry, scope);
}
#endif
-#ifdef CONFIG_ARM64_VHE
static bool runs_at_el2(const struct arm64_cpu_capabilities *entry, int __unused)
{
return is_kernel_in_hyp_mode();
if (!alternative_is_applied(ARM64_HAS_VIRT_HOST_EXTN))
write_sysreg(read_sysreg(tpidr_el1), tpidr_el2);
}
-#endif
static void cpu_has_fwb(const struct arm64_cpu_capabilities *__unused)
{
.cpu_enable = cpu_enable_pan,
},
#endif /* CONFIG_ARM64_PAN */
+#ifdef CONFIG_ARM64_EPAN
+ {
+ .desc = "Enhanced Privileged Access Never",
+ .capability = ARM64_HAS_EPAN,
+ .type = ARM64_CPUCAP_SYSTEM_FEATURE,
+ .matches = has_cpuid_feature,
+ .sys_reg = SYS_ID_AA64MMFR1_EL1,
+ .field_pos = ID_AA64MMFR1_PAN_SHIFT,
+ .sign = FTR_UNSIGNED,
+ .min_field_value = 3,
+ },
+#endif /* CONFIG_ARM64_EPAN */
#ifdef CONFIG_ARM64_LSE_ATOMICS
{
.desc = "LSE atomic instructions",
.type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
.matches = has_no_hw_prefetch,
},
-#ifdef CONFIG_ARM64_VHE
{
.desc = "Virtualization Host Extensions",
.capability = ARM64_HAS_VIRT_HOST_EXTN,
.matches = runs_at_el2,
.cpu_enable = cpu_copy_el2regs,
},
-#endif /* CONFIG_ARM64_VHE */
{
.desc = "32-bit EL0 Support",
.capability = ARM64_HAS_32BIT_EL0,
* with the CLIDR_EL1 fields to avoid triggering false warnings
* when there is a mismatch across the CPUs. Keep track of the
* effective value of the CTR_EL0 in our internal records for
- * acurate sanity check and feature enablement.
+ * accurate sanity check and feature enablement.
*/
info->reg_ctr = read_cpuid_effective_cachetype();
info->reg_dczid = read_cpuid(DCZID_EL0);
ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos)
{
memcpy(buf, phys_to_virt((phys_addr_t)*ppos), count);
+ *ppos += count;
+
return count;
}
lockdep_hardirqs_off(CALLER_ADDR0);
rcu_irq_enter_check_tick();
trace_hardirqs_off_finish();
+
+ mte_check_tfsr_entry();
}
/*
{
lockdep_assert_irqs_disabled();
+ mte_check_tfsr_exit();
+
if (interrupts_enabled(regs)) {
if (regs->exit_rcu) {
trace_hardirqs_on_prepare();
asmlinkage void noinstr exit_to_user_mode(void)
{
+ mte_check_tfsr_exit();
+
trace_hardirqs_on_prepare();
lockdep_hardirqs_on_prepare(CALLER_ADDR0);
user_enter_irqoff();
ret
SYM_FUNC_END(sve_get_vl)
+SYM_FUNC_START(sve_set_vq)
+ sve_load_vq x0, x1, x2
+ ret
+SYM_FUNC_END(sve_set_vq)
+
/*
* Load SVE state from FPSIMD state.
*
.endm
/* Check for MTE asynchronous tag check faults */
- .macro check_mte_async_tcf, flgs, tmp
+ .macro check_mte_async_tcf, tmp, ti_flags
#ifdef CONFIG_ARM64_MTE
+ .arch_extension lse
alternative_if_not ARM64_MTE
b 1f
alternative_else_nop_endif
mrs_s \tmp, SYS_TFSRE0_EL1
tbz \tmp, #SYS_TFSR_EL1_TF0_SHIFT, 1f
/* Asynchronous TCF occurred for TTBR0 access, set the TI flag */
- orr \flgs, \flgs, #_TIF_MTE_ASYNC_FAULT
- str \flgs, [tsk, #TSK_TI_FLAGS]
+ mov \tmp, #_TIF_MTE_ASYNC_FAULT
+ add \ti_flags, tsk, #TSK_TI_FLAGS
+ stset \tmp, [\ti_flags]
msr_s SYS_TFSRE0_EL1, xzr
1:
#endif
disable_step_tsk x19, x20
/* Check for asynchronous tag check faults in user space */
- check_mte_async_tcf x19, x22
+ check_mte_async_tcf x22, x23
apply_ssbd 1, x22, x23
- ptrauth_keys_install_kernel tsk, x20, x22, x23
+#ifdef CONFIG_ARM64_PTR_AUTH
+alternative_if ARM64_HAS_ADDRESS_AUTH
+ /*
+ * Enable IA for in-kernel PAC if the task had it disabled. Although
+ * this could be implemented with an unconditional MRS which would avoid
+ * a load, this was measured to be slower on Cortex-A75 and Cortex-A76.
+ *
+ * Install the kernel IA key only if IA was enabled in the task. If IA
+ * was disabled on kernel exit then we would have left the kernel IA
+ * installed so there is no need to install it again.
+ */
+ ldr x0, [tsk, THREAD_SCTLR_USER]
+ tbz x0, SCTLR_ELx_ENIA_SHIFT, 1f
+ __ptrauth_keys_install_kernel_nosync tsk, x20, x22, x23
+ b 2f
+1:
+ mrs x0, sctlr_el1
+ orr x0, x0, SCTLR_ELx_ENIA
+ msr sctlr_el1, x0
+2:
+ isb
+alternative_else_nop_endif
+#endif
mte_set_kernel_gcr x22, x23
3:
scs_save tsk, x0
- /* No kernel C function calls after this as user keys are set. */
- ptrauth_keys_install_user tsk, x0, x1, x2
+#ifdef CONFIG_ARM64_PTR_AUTH
+alternative_if ARM64_HAS_ADDRESS_AUTH
+ /*
+ * IA was enabled for in-kernel PAC. Disable it now if needed, or
+ * alternatively install the user's IA. All other per-task keys and
+ * SCTLR bits were updated on task switch.
+ *
+ * No kernel C function calls after this.
+ */
+ ldr x0, [tsk, THREAD_SCTLR_USER]
+ tbz x0, SCTLR_ELx_ENIA_SHIFT, 1f
+ __ptrauth_keys_install_user tsk, x0, x1, x2
+ b 2f
+1:
+ mrs x0, sctlr_el1
+ bic x0, x0, SCTLR_ELx_ENIA
+ msr sctlr_el1, x0
+2:
+alternative_else_nop_endif
+#endif
mte_set_user_gcr tsk, x0, x1
/*
* Interrupt handling.
*/
- .macro irq_handler
- ldr_l x1, handle_arch_irq
+ .macro irq_handler, handler:req
+ ldr_l x1, \handler
mov x0, sp
irq_stack_entry
blr x1
irq_stack_exit
.endm
-#ifdef CONFIG_ARM64_PSEUDO_NMI
- /*
- * Set res to 0 if irqs were unmasked in interrupted context.
- * Otherwise set res to non-0 value.
- */
- .macro test_irqs_unmasked res:req, pmr:req
-alternative_if ARM64_HAS_IRQ_PRIO_MASKING
- sub \res, \pmr, #GIC_PRIO_IRQON
-alternative_else
- mov \res, xzr
-alternative_endif
- .endm
-#endif
-
.macro gic_prio_kentry_setup, tmp:req
#ifdef CONFIG_ARM64_PSEUDO_NMI
alternative_if ARM64_HAS_IRQ_PRIO_MASKING
#endif
.endm
+ .macro el1_interrupt_handler, handler:req
+ gic_prio_irq_setup pmr=x20, tmp=x1
+ enable_da
+
+ mov x0, sp
+ bl enter_el1_irq_or_nmi
+
+ irq_handler \handler
+
+#ifdef CONFIG_PREEMPTION
+ ldr x24, [tsk, #TSK_TI_PREEMPT] // get preempt count
+alternative_if ARM64_HAS_IRQ_PRIO_MASKING
+ /*
+ * DA were cleared at start of handling, and IF are cleared by
+ * the GIC irqchip driver using gic_arch_enable_irqs() for
+ * normal IRQs. If anything is set, it means we come back from
+ * an NMI instead of a normal IRQ, so skip preemption
+ */
+ mrs x0, daif
+ orr x24, x24, x0
+alternative_else_nop_endif
+ cbnz x24, 1f // preempt count != 0 || NMI return path
+ bl arm64_preempt_schedule_irq // irq en/disable is done inside
+1:
+#endif
+
+ mov x0, sp
+ bl exit_el1_irq_or_nmi
+ .endm
+
+ .macro el0_interrupt_handler, handler:req
+ gic_prio_irq_setup pmr=x20, tmp=x0
+ user_exit_irqoff
+ enable_da
+
+ tbz x22, #55, 1f
+ bl do_el0_irq_bp_hardening
+1:
+ irq_handler \handler
+ .endm
+
.text
/*
kernel_ventry 1, sync // Synchronous EL1h
kernel_ventry 1, irq // IRQ EL1h
- kernel_ventry 1, fiq_invalid // FIQ EL1h
+ kernel_ventry 1, fiq // FIQ EL1h
kernel_ventry 1, error // Error EL1h
kernel_ventry 0, sync // Synchronous 64-bit EL0
kernel_ventry 0, irq // IRQ 64-bit EL0
- kernel_ventry 0, fiq_invalid // FIQ 64-bit EL0
+ kernel_ventry 0, fiq // FIQ 64-bit EL0
kernel_ventry 0, error // Error 64-bit EL0
#ifdef CONFIG_COMPAT
kernel_ventry 0, sync_compat, 32 // Synchronous 32-bit EL0
kernel_ventry 0, irq_compat, 32 // IRQ 32-bit EL0
- kernel_ventry 0, fiq_invalid_compat, 32 // FIQ 32-bit EL0
+ kernel_ventry 0, fiq_compat, 32 // FIQ 32-bit EL0
kernel_ventry 0, error_compat, 32 // Error 32-bit EL0
#else
kernel_ventry 0, sync_invalid, 32 // Synchronous 32-bit EL0
inv_entry 0, BAD_ERROR
SYM_CODE_END(el0_error_invalid)
-#ifdef CONFIG_COMPAT
-SYM_CODE_START_LOCAL(el0_fiq_invalid_compat)
- inv_entry 0, BAD_FIQ, 32
-SYM_CODE_END(el0_fiq_invalid_compat)
-#endif
-
SYM_CODE_START_LOCAL(el1_sync_invalid)
inv_entry 1, BAD_SYNC
SYM_CODE_END(el1_sync_invalid)
.align 6
SYM_CODE_START_LOCAL_NOALIGN(el1_irq)
kernel_entry 1
- gic_prio_irq_setup pmr=x20, tmp=x1
- enable_da_f
-
- mov x0, sp
- bl enter_el1_irq_or_nmi
-
- irq_handler
-
-#ifdef CONFIG_PREEMPTION
- ldr x24, [tsk, #TSK_TI_PREEMPT] // get preempt count
-alternative_if ARM64_HAS_IRQ_PRIO_MASKING
- /*
- * DA_F were cleared at start of handling. If anything is set in DAIF,
- * we come back from an NMI, so skip preemption
- */
- mrs x0, daif
- orr x24, x24, x0
-alternative_else_nop_endif
- cbnz x24, 1f // preempt count != 0 || NMI return path
- bl arm64_preempt_schedule_irq // irq en/disable is done inside
-1:
-#endif
-
- mov x0, sp
- bl exit_el1_irq_or_nmi
-
+ el1_interrupt_handler handle_arch_irq
kernel_exit 1
SYM_CODE_END(el1_irq)
+SYM_CODE_START_LOCAL_NOALIGN(el1_fiq)
+ kernel_entry 1
+ el1_interrupt_handler handle_arch_fiq
+ kernel_exit 1
+SYM_CODE_END(el1_fiq)
+
/*
* EL0 mode handlers.
*/
b el0_irq_naked
SYM_CODE_END(el0_irq_compat)
+SYM_CODE_START_LOCAL_NOALIGN(el0_fiq_compat)
+ kernel_entry 0, 32
+ b el0_fiq_naked
+SYM_CODE_END(el0_fiq_compat)
+
SYM_CODE_START_LOCAL_NOALIGN(el0_error_compat)
kernel_entry 0, 32
b el0_error_naked
SYM_CODE_START_LOCAL_NOALIGN(el0_irq)
kernel_entry 0
el0_irq_naked:
- gic_prio_irq_setup pmr=x20, tmp=x0
- user_exit_irqoff
- enable_da_f
-
- tbz x22, #55, 1f
- bl do_el0_irq_bp_hardening
-1:
- irq_handler
-
+ el0_interrupt_handler handle_arch_irq
b ret_to_user
SYM_CODE_END(el0_irq)
+SYM_CODE_START_LOCAL_NOALIGN(el0_fiq)
+ kernel_entry 0
+el0_fiq_naked:
+ el0_interrupt_handler handle_arch_fiq
+ b ret_to_user
+SYM_CODE_END(el0_fiq)
+
SYM_CODE_START_LOCAL(el1_error)
kernel_entry 1
mrs x1, esr_el1
mov x0, sp
mov x1, x25
bl do_serror
- enable_da_f
+ enable_da
b ret_to_user
SYM_CODE_END(el0_error)
*/
static void get_cpu_fpsimd_context(void)
{
- preempt_disable();
+ local_bh_disable();
__get_cpu_fpsimd_context();
}
static void put_cpu_fpsimd_context(void)
{
__put_cpu_fpsimd_context();
- preempt_enable();
+ local_bh_enable();
}
static bool have_cpu_fpsimd_context(void)
WARN_ON(!system_supports_fpsimd());
WARN_ON(!have_cpu_fpsimd_context());
- if (system_supports_sve() && test_thread_flag(TIF_SVE))
+ if (IS_ENABLED(CONFIG_ARM64_SVE) && test_thread_flag(TIF_SVE))
sve_load_state(sve_pffr(¤t->thread),
¤t->thread.uw.fpsimd_state.fpsr,
sve_vq_from_vl(current->thread.sve_vl) - 1);
WARN_ON(!have_cpu_fpsimd_context());
if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {
- if (system_supports_sve() && test_thread_flag(TIF_SVE)) {
+ if (IS_ENABLED(CONFIG_ARM64_SVE) &&
+ test_thread_flag(TIF_SVE)) {
if (WARN_ON(sve_get_vl() != last->sve_vl)) {
/*
* Can't save the user regs, so current would
* Trapped SVE access
*
* Storage is allocated for the full SVE state, the current FPSIMD
- * register contents are migrated across, and TIF_SVE is set so that
- * the SVE access trap will be disabled the next time this task
- * reaches ret_to_user.
+ * register contents are migrated across, and the access trap is
+ * disabled.
*
* TIF_SVE should be clear on entry: otherwise, fpsimd_restore_current_state()
* would have disabled the SVE access trap for userspace during
get_cpu_fpsimd_context();
- fpsimd_save();
-
- /* Force ret_to_user to reload the registers: */
- fpsimd_flush_task_state(current);
-
- fpsimd_to_sve(current);
if (test_and_set_thread_flag(TIF_SVE))
WARN_ON(1); /* SVE access shouldn't have trapped */
+ /*
+ * Convert the FPSIMD state to SVE, zeroing all the state that
+ * is not shared with FPSIMD. If (as is likely) the current
+ * state is live in the registers then do this there and
+ * update our metadata for the current task including
+ * disabling the trap, otherwise update our in-memory copy.
+ */
+ if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) {
+ sve_set_vq(sve_vq_from_vl(current->thread.sve_vl) - 1);
+ sve_flush_live();
+ fpsimd_bind_task_to_cpu();
+ } else {
+ fpsimd_to_sve(current);
+ }
+
put_cpu_fpsimd_context();
}
void fpsimd_signal_preserve_current_state(void)
{
fpsimd_preserve_current_state();
- if (system_supports_sve() && test_thread_flag(TIF_SVE))
+ if (test_thread_flag(TIF_SVE))
sve_to_fpsimd(current);
}
get_cpu_fpsimd_context();
current->thread.uw.fpsimd_state = *state;
- if (system_supports_sve() && test_thread_flag(TIF_SVE))
+ if (test_thread_flag(TIF_SVE))
fpsimd_to_sve(current);
task_fpsimd_load();
*/
adrp x5, __idmap_text_end
clz x5, x5
- cmp x5, TCR_T0SZ(VA_BITS) // default T0SZ small enough?
+ cmp x5, TCR_T0SZ(VA_BITS_MIN) // default T0SZ small enough?
b.ge 1f // .. then skip VA range extension
adr_l x6, idmap_t0sz
* booted in EL1 or EL2 respectively.
*/
SYM_FUNC_START(init_kernel_el)
- mov_q x0, INIT_SCTLR_EL1_MMU_OFF
- msr sctlr_el1, x0
-
mrs x0, CurrentEL
cmp x0, #CurrentEL_EL2
b.eq init_el2
SYM_INNER_LABEL(init_el1, SYM_L_LOCAL)
+ mov_q x0, INIT_SCTLR_EL1_MMU_OFF
+ msr sctlr_el1, x0
isb
mov_q x0, INIT_PSTATE_EL1
msr spsr_el1, x0
msr vbar_el2, x0
isb
+ /*
+ * Fruity CPUs seem to have HCR_EL2.E2H set to RES1,
+ * making it impossible to start in nVHE mode. Is that
+ * compliant with the architecture? Absolutely not!
+ */
+ mrs x0, hcr_el2
+ and x0, x0, #HCR_E2H
+ cbz x0, 1f
+
+ /* Switching to VHE requires a sane SCTLR_EL1 as a start */
+ mov_q x0, INIT_SCTLR_EL1_MMU_OFF
+ msr_s SYS_SCTLR_EL12, x0
+
+ /*
+ * Force an eret into a helper "function", and let it return
+ * to our original caller... This makes sure that we have
+ * initialised the basic PSTATE state.
+ */
+ mov x0, #INIT_PSTATE_EL2
+ msr spsr_el1, x0
+ adr x0, __cpu_stick_to_vhe
+ msr elr_el1, x0
+ eret
+
+1:
+ mov_q x0, INIT_SCTLR_EL1_MMU_OFF
+ msr sctlr_el1, x0
+
msr elr_el2, lr
mov w0, #BOOT_CPU_MODE_EL2
eret
+
+__cpu_stick_to_vhe:
+ mov x0, #HVC_VHE_RESTART
+ hvc #0
+ mov x0, #BOOT_CPU_MODE_EL2
+ ret
SYM_FUNC_END(init_kernel_el)
/*
SYM_FUNC_START(__enable_mmu)
mrs x2, ID_AA64MMFR0_EL1
ubfx x2, x2, #ID_AA64MMFR0_TGRAN_SHIFT, 4
- cmp x2, #ID_AA64MMFR0_TGRAN_SUPPORTED
- b.ne __no_granule_support
+ cmp x2, #ID_AA64MMFR0_TGRAN_SUPPORTED_MIN
+ b.lt __no_granule_support
+ cmp x2, #ID_AA64MMFR0_TGRAN_SUPPORTED_MAX
+ b.gt __no_granule_support
update_early_cpu_boot_status 0, x2, x3
adrp x2, idmap_pg_dir
phys_to_ttbr x1, x1
ventry el2_fiq_invalid // FIQ EL2t
ventry el2_error_invalid // Error EL2t
- ventry el2_sync_invalid // Synchronous EL2h
+ ventry elx_sync // Synchronous EL2h
ventry el2_irq_invalid // IRQ EL2h
ventry el2_fiq_invalid // FIQ EL2h
ventry el2_error_invalid // Error EL2h
- ventry el1_sync // Synchronous 64-bit EL1
+ ventry elx_sync // Synchronous 64-bit EL1
ventry el1_irq_invalid // IRQ 64-bit EL1
ventry el1_fiq_invalid // FIQ 64-bit EL1
ventry el1_error_invalid // Error 64-bit EL1
.align 11
-SYM_CODE_START_LOCAL(el1_sync)
+SYM_CODE_START_LOCAL(elx_sync)
cmp x0, #HVC_SET_VECTORS
b.ne 1f
msr vbar_el2, x1
9: mov x0, xzr
eret
-SYM_CODE_END(el1_sync)
+SYM_CODE_END(elx_sync)
// nVHE? No way! Give me the real thing!
SYM_CODE_START_LOCAL(mutate_to_vhe)
* Entry point to switch to VHE if deemed capable
*/
SYM_FUNC_START(switch_to_vhe)
-#ifdef CONFIG_ARM64_VHE
// Need to have booted at EL2
adr_l x1, __boot_cpu_mode
ldr w0, [x1]
mov x0, #HVC_VHE_RESTART
hvc #0
1:
-#endif
ret
SYM_FUNC_END(switch_to_vhe)
struct {
char name[FTR_DESC_FIELD_LEN];
u8 shift;
+ bool (*filter)(u64 val);
} fields[];
};
+static bool __init mmfr1_vh_filter(u64 val)
+{
+ /*
+ * If we ever reach this point while running VHE, we're
+ * guaranteed to be on one of these funky, VHE-stuck CPUs. If
+ * the user was trying to force nVHE on us, proceed with
+ * attitude adjustment.
+ */
+ return !(is_kernel_in_hyp_mode() && val == 0);
+}
+
static const struct ftr_set_desc mmfr1 __initconst = {
.name = "id_aa64mmfr1",
.override = &id_aa64mmfr1_override,
.fields = {
- { "vh", ID_AA64MMFR1_VHE_SHIFT },
+ { "vh", ID_AA64MMFR1_VHE_SHIFT, mmfr1_vh_filter },
{}
},
};
if (find_field(cmdline, regs[i], f, &v))
continue;
+ /*
+ * If an override gets filtered out, advertise
+ * it by setting the value to 0xf, but
+ * clearing the mask... Yes, this is fragile.
+ */
+ if (regs[i]->fields[f].filter &&
+ !regs[i]->fields[f].filter(v)) {
+ regs[i]->override->val |= mask;
+ regs[i]->override->mask &= ~mask;
+ continue;
+ }
+
regs[i]->override->val &= ~mask;
regs[i]->override->val |= (v << shift) & mask;
regs[i]->override->mask |= mask;
} while (1);
}
-static __init void parse_cmdline(void)
+static __init const u8 *get_bootargs_cmdline(void)
{
- if (!IS_ENABLED(CONFIG_CMDLINE_FORCE)) {
- const u8 *prop;
- void *fdt;
- int node;
+ const u8 *prop;
+ void *fdt;
+ int node;
- fdt = get_early_fdt_ptr();
- if (!fdt)
- goto out;
+ fdt = get_early_fdt_ptr();
+ if (!fdt)
+ return NULL;
- node = fdt_path_offset(fdt, "/chosen");
- if (node < 0)
- goto out;
+ node = fdt_path_offset(fdt, "/chosen");
+ if (node < 0)
+ return NULL;
- prop = fdt_getprop(fdt, node, "bootargs", NULL);
- if (!prop)
- goto out;
+ prop = fdt_getprop(fdt, node, "bootargs", NULL);
+ if (!prop)
+ return NULL;
- __parse_cmdline(prop, true);
+ return strlen(prop) ? prop : NULL;
+}
- if (!IS_ENABLED(CONFIG_CMDLINE_EXTEND))
- return;
- }
+static __init void parse_cmdline(void)
+{
+ const u8 *prop = get_bootargs_cmdline();
+
+ if (IS_ENABLED(CONFIG_CMDLINE_FORCE) || !prop)
+ __parse_cmdline(CONFIG_CMDLINE, true);
-out:
- __parse_cmdline(CONFIG_CMDLINE, true);
+ if (!IS_ENABLED(CONFIG_CMDLINE_FORCE) && prop)
+ __parse_cmdline(prop, true);
}
/* Keep checkers quiet */
/* Array containing bases of nVHE per-CPU memory regions. */
KVM_NVHE_ALIAS(kvm_arm_hyp_percpu_base);
+/* PMU available static key */
+KVM_NVHE_ALIAS(kvm_arm_pmu_available);
+
#endif /* CONFIG_KVM */
#endif /* __ARM64_KERNEL_IMAGE_VARS_H */
}
#endif
+static void default_handle_irq(struct pt_regs *regs)
+{
+ panic("IRQ taken without a root IRQ handler\n");
+}
+
+static void default_handle_fiq(struct pt_regs *regs)
+{
+ panic("FIQ taken without a root FIQ handler\n");
+}
+
+void (*handle_arch_irq)(struct pt_regs *) __ro_after_init = default_handle_irq;
+void (*handle_arch_fiq)(struct pt_regs *) __ro_after_init = default_handle_fiq;
+
+int __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
+{
+ if (handle_arch_irq != default_handle_irq)
+ return -EBUSY;
+
+ handle_arch_irq = handle_irq;
+ pr_info("Root IRQ handler: %ps\n", handle_irq);
+ return 0;
+}
+
+int __init set_handle_fiq(void (*handle_fiq)(struct pt_regs *))
+{
+ if (handle_arch_fiq != default_handle_fiq)
+ return -EBUSY;
+
+ handle_arch_fiq = handle_fiq;
+ pr_info("Root FIQ handler: %ps\n", handle_fiq);
+ return 0;
+}
+
void __init init_IRQ(void)
{
init_irq_stacks();
init_irq_scs();
irqchip_init();
- if (!handle_arch_irq)
- panic("No interrupt controller found.");
if (system_uses_irq_prio_masking()) {
/*
/* use the top 16 bits to randomize the linear region */
memstart_offset_seed = seed >> 48;
- if (IS_ENABLED(CONFIG_KASAN_GENERIC) ||
- IS_ENABLED(CONFIG_KASAN_SW_TAGS))
+ if (!IS_ENABLED(CONFIG_KASAN_VMALLOC) &&
+ (IS_ENABLED(CONFIG_KASAN_GENERIC) ||
+ IS_ENABLED(CONFIG_KASAN_SW_TAGS)))
/*
- * KASAN does not expect the module region to intersect the
- * vmalloc region, since shadow memory is allocated for each
- * module at load time, whereas the vmalloc region is shadowed
- * by KASAN zero pages. So keep modules out of the vmalloc
- * region if KASAN is enabled, and put the kernel well within
- * 4 GB of the module region.
+ * KASAN without KASAN_VMALLOC does not expect the module region
+ * to intersect the vmalloc region, since shadow memory is
+ * allocated for each module at load time, whereas the vmalloc
+ * region is shadowed by KASAN zero pages. So keep modules
+ * out of the vmalloc region if KASAN is enabled without
+ * KASAN_VMALLOC, and put the kernel well within 4 GB of the
+ * module region.
*/
return offset % SZ_2G;
NUMA_NO_NODE, __builtin_return_address(0));
if (!p && IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) &&
- !IS_ENABLED(CONFIG_KASAN_GENERIC) &&
- !IS_ENABLED(CONFIG_KASAN_SW_TAGS))
+ (IS_ENABLED(CONFIG_KASAN_VMALLOC) ||
+ (!IS_ENABLED(CONFIG_KASAN_GENERIC) &&
+ !IS_ENABLED(CONFIG_KASAN_SW_TAGS))))
/*
- * KASAN can only deal with module allocations being served
- * from the reserved module region, since the remainder of
- * the vmalloc region is already backed by zero shadow pages,
- * and punching holes into it is non-trivial. Since the module
- * region is not randomized when KASAN is enabled, it is even
+ * KASAN without KASAN_VMALLOC can only deal with module
+ * allocations being served from the reserved module region,
+ * since the remainder of the vmalloc region is already
+ * backed by zero shadow pages, and punching holes into it
+ * is non-trivial. Since the module region is not randomized
+ * when KASAN is enabled without KASAN_VMALLOC, it is even
* less likely that the module region gets exhausted, so we
* can simply omit this fallback in that case.
*/
static bool report_fault_once = true;
+#ifdef CONFIG_KASAN_HW_TAGS
+/* Whether the MTE asynchronous mode is enabled. */
+DEFINE_STATIC_KEY_FALSE(mte_async_mode);
+EXPORT_SYMBOL_GPL(mte_async_mode);
+#endif
+
static void mte_sync_page_tags(struct page *page, pte_t *ptep, bool check_swap)
{
pte_t old_pte = READ_ONCE(*ptep);
write_sysreg_s(SYS_GCR_EL1_RRND | gcr_kernel_excl, SYS_GCR_EL1);
}
-void mte_enable_kernel(void)
+static inline void __mte_enable_kernel(const char *mode, unsigned long tcf)
{
/* Enable MTE Sync Mode for EL1. */
- sysreg_clear_set(sctlr_el1, SCTLR_ELx_TCF_MASK, SCTLR_ELx_TCF_SYNC);
+ sysreg_clear_set(sctlr_el1, SCTLR_ELx_TCF_MASK, tcf);
isb();
+
+ pr_info_once("MTE: enabled in %s mode at EL1\n", mode);
+}
+
+#ifdef CONFIG_KASAN_HW_TAGS
+void mte_enable_kernel_sync(void)
+{
+ /*
+ * Make sure we enter this function when no PE has set
+ * async mode previously.
+ */
+ WARN_ONCE(system_uses_mte_async_mode(),
+ "MTE async mode enabled system wide!");
+
+ __mte_enable_kernel("synchronous", SCTLR_ELx_TCF_SYNC);
}
+void mte_enable_kernel_async(void)
+{
+ __mte_enable_kernel("asynchronous", SCTLR_ELx_TCF_ASYNC);
+
+ /*
+ * MTE async mode is set system wide by the first PE that
+ * executes this function.
+ *
+ * Note: If in future KASAN acquires a runtime switching
+ * mode in between sync and async, this strategy needs
+ * to be reviewed.
+ */
+ if (!system_uses_mte_async_mode())
+ static_branch_enable(&mte_async_mode);
+}
+#endif
+
void mte_set_report_once(bool state)
{
WRITE_ONCE(report_fault_once, state);
return READ_ONCE(report_fault_once);
}
-static void update_sctlr_el1_tcf0(u64 tcf0)
+#ifdef CONFIG_KASAN_HW_TAGS
+void mte_check_tfsr_el1(void)
{
- /* ISB required for the kernel uaccess routines */
- sysreg_clear_set(sctlr_el1, SCTLR_EL1_TCF0_MASK, tcf0);
- isb();
-}
+ u64 tfsr_el1;
-static void set_sctlr_el1_tcf0(u64 tcf0)
-{
- /*
- * mte_thread_switch() checks current->thread.sctlr_tcf0 as an
- * optimisation. Disable preemption so that it does not see
- * the variable update before the SCTLR_EL1.TCF0 one.
- */
- preempt_disable();
- current->thread.sctlr_tcf0 = tcf0;
- update_sctlr_el1_tcf0(tcf0);
- preempt_enable();
+ if (!system_supports_mte())
+ return;
+
+ tfsr_el1 = read_sysreg_s(SYS_TFSR_EL1);
+
+ if (unlikely(tfsr_el1 & SYS_TFSR_EL1_TF1)) {
+ /*
+ * Note: isb() is not required after this direct write
+ * because there is no indirect read subsequent to it
+ * (per ARM DDI 0487F.c table D13-1).
+ */
+ write_sysreg_s(0, SYS_TFSR_EL1);
+
+ kasan_report_async();
+ }
}
+#endif
static void update_gcr_el1_excl(u64 excl)
{
*/
}
-void flush_mte_state(void)
+void mte_thread_init_user(void)
{
if (!system_supports_mte())
return;
write_sysreg_s(0, SYS_TFSRE0_EL1);
clear_thread_flag(TIF_MTE_ASYNC_FAULT);
/* disable tag checking */
- set_sctlr_el1_tcf0(SCTLR_EL1_TCF0_NONE);
+ set_task_sctlr_el1((current->thread.sctlr_user & ~SCTLR_EL1_TCF0_MASK) |
+ SCTLR_EL1_TCF0_NONE);
/* reset tag generation mask */
set_gcr_el1_excl(SYS_GCR_EL1_EXCL_MASK);
}
void mte_thread_switch(struct task_struct *next)
{
+ /*
+ * Check if an async tag exception occurred at EL1.
+ *
+ * Note: On the context switch path we rely on the dsb() present
+ * in __switch_to() to guarantee that the indirect writes to TFSR_EL1
+ * are synchronized before this point.
+ */
+ isb();
+ mte_check_tfsr_el1();
+}
+
+void mte_suspend_enter(void)
+{
if (!system_supports_mte())
return;
- /* avoid expensive SCTLR_EL1 accesses if no change */
- if (current->thread.sctlr_tcf0 != next->thread.sctlr_tcf0)
- update_sctlr_el1_tcf0(next->thread.sctlr_tcf0);
+ /*
+ * The barriers are required to guarantee that the indirect writes
+ * to TFSR_EL1 are synchronized before we report the state.
+ */
+ dsb(nsh);
+ isb();
+
+ /* Report SYS_TFSR_EL1 before suspend entry */
+ mte_check_tfsr_el1();
}
void mte_suspend_exit(void)
long set_mte_ctrl(struct task_struct *task, unsigned long arg)
{
- u64 tcf0;
+ u64 sctlr = task->thread.sctlr_user & ~SCTLR_EL1_TCF0_MASK;
u64 gcr_excl = ~((arg & PR_MTE_TAG_MASK) >> PR_MTE_TAG_SHIFT) &
SYS_GCR_EL1_EXCL_MASK;
switch (arg & PR_MTE_TCF_MASK) {
case PR_MTE_TCF_NONE:
- tcf0 = SCTLR_EL1_TCF0_NONE;
+ sctlr |= SCTLR_EL1_TCF0_NONE;
break;
case PR_MTE_TCF_SYNC:
- tcf0 = SCTLR_EL1_TCF0_SYNC;
+ sctlr |= SCTLR_EL1_TCF0_SYNC;
break;
case PR_MTE_TCF_ASYNC:
- tcf0 = SCTLR_EL1_TCF0_ASYNC;
+ sctlr |= SCTLR_EL1_TCF0_ASYNC;
break;
default:
return -EINVAL;
}
if (task != current) {
- task->thread.sctlr_tcf0 = tcf0;
+ task->thread.sctlr_user = sctlr;
task->thread.gcr_user_excl = gcr_excl;
} else {
- set_sctlr_el1_tcf0(tcf0);
+ set_task_sctlr_el1(sctlr);
set_gcr_el1_excl(gcr_excl);
}
ret = incl << PR_MTE_TAG_SHIFT;
- switch (task->thread.sctlr_tcf0) {
+ switch (task->thread.sctlr_user & SCTLR_EL1_TCF0_MASK) {
case SCTLR_EL1_TCF0_NONE:
ret |= PR_MTE_TCF_NONE;
break;
#include <linux/reboot.h>
#include <linux/slab.h>
#include <linux/types.h>
+#include <linux/static_call.h>
#include <asm/paravirt.h>
#include <asm/pvclock-abi.h>
struct static_key paravirt_steal_enabled;
struct static_key paravirt_steal_rq_enabled;
-struct paravirt_patch_template pv_ops;
-EXPORT_SYMBOL_GPL(pv_ops);
+static u64 native_steal_clock(int cpu)
+{
+ return 0;
+}
+
+DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock);
struct pv_time_stolen_time_region {
struct pvclock_vcpu_stolen_time *kaddr;
early_param("no-steal-acc", parse_no_stealacc);
/* return stolen time in ns by asking the hypervisor */
-static u64 pv_steal_clock(int cpu)
+static u64 para_steal_clock(int cpu)
{
struct pv_time_stolen_time_region *reg;
if (ret)
return ret;
- pv_ops.time.steal_clock = pv_steal_clock;
+ static_call_update(pv_steal_clock, para_steal_clock);
static_key_slow_inc(¶virt_steal_enabled);
if (steal_acc)
return pmnc & BIT(ARMV8_IDX_TO_COUNTER(idx));
}
-static inline u32 armv8pmu_read_evcntr(int idx)
+static inline u64 armv8pmu_read_evcntr(int idx)
{
u32 counter = ARMV8_IDX_TO_COUNTER(idx);
static inline u64 armv8pmu_read_hw_counter(struct perf_event *event)
{
int idx = event->hw.idx;
- u64 val = 0;
+ u64 val = armv8pmu_read_evcntr(idx);
- val = armv8pmu_read_evcntr(idx);
if (armv8pmu_event_is_chained(event))
val = (val << 32) | armv8pmu_read_evcntr(idx - 1);
return val;
{
struct hw_perf_event *hwc = &event->hw;
int idx = hwc->idx;
- u64 value = 0;
+ u64 value;
if (idx == ARMV8_IDX_CYCLE_COUNTER)
value = read_sysreg(pmccntr_el0);
get_random_bytes(&keys->apdb, sizeof(keys->apdb));
if (arg & PR_PAC_APGAKEY)
get_random_bytes(&keys->apga, sizeof(keys->apga));
+ ptrauth_keys_install_user(keys);
return 0;
}
+
+static u64 arg_to_enxx_mask(unsigned long arg)
+{
+ u64 sctlr_enxx_mask = 0;
+
+ WARN_ON(arg & ~PR_PAC_ENABLED_KEYS_MASK);
+ if (arg & PR_PAC_APIAKEY)
+ sctlr_enxx_mask |= SCTLR_ELx_ENIA;
+ if (arg & PR_PAC_APIBKEY)
+ sctlr_enxx_mask |= SCTLR_ELx_ENIB;
+ if (arg & PR_PAC_APDAKEY)
+ sctlr_enxx_mask |= SCTLR_ELx_ENDA;
+ if (arg & PR_PAC_APDBKEY)
+ sctlr_enxx_mask |= SCTLR_ELx_ENDB;
+ return sctlr_enxx_mask;
+}
+
+int ptrauth_set_enabled_keys(struct task_struct *tsk, unsigned long keys,
+ unsigned long enabled)
+{
+ u64 sctlr = tsk->thread.sctlr_user;
+
+ if (!system_supports_address_auth())
+ return -EINVAL;
+
+ if (is_compat_thread(task_thread_info(tsk)))
+ return -EINVAL;
+
+ if ((keys & ~PR_PAC_ENABLED_KEYS_MASK) || (enabled & ~keys))
+ return -EINVAL;
+
+ sctlr &= ~arg_to_enxx_mask(keys);
+ sctlr |= arg_to_enxx_mask(enabled);
+ if (tsk == current)
+ set_task_sctlr_el1(sctlr);
+ else
+ tsk->thread.sctlr_user = sctlr;
+
+ return 0;
+}
+
+int ptrauth_get_enabled_keys(struct task_struct *tsk)
+{
+ int retval = 0;
+
+ if (!system_supports_address_auth())
+ return -EINVAL;
+
+ if (is_compat_thread(task_thread_info(tsk)))
+ return -EINVAL;
+
+ if (tsk->thread.sctlr_user & SCTLR_ELx_ENIA)
+ retval |= PR_PAC_APIAKEY;
+ if (tsk->thread.sctlr_user & SCTLR_ELx_ENIB)
+ retval |= PR_PAC_APIBKEY;
+ if (tsk->thread.sctlr_user & SCTLR_ELx_ENDA)
+ retval |= PR_PAC_APDAKEY;
+ if (tsk->thread.sctlr_user & SCTLR_ELx_ENDB)
+ retval |= PR_PAC_APDBKEY;
+
+ return retval;
+}
* normal page fault.
*/
instruction_pointer_set(regs, (unsigned long) cur->addr);
- if (!instruction_pointer(regs))
- BUG();
+ BUG_ON(!instruction_pointer(regs));
- if (kcb->kprobe_status == KPROBE_REENTER)
+ if (kcb->kprobe_status == KPROBE_REENTER) {
restore_previous_kprobe(kcb);
- else
+ } else {
+ kprobes_restore_local_irqflag(kcb, regs);
reset_current_kprobe();
+ }
break;
case KPROBE_HIT_ACTIVE:
#include <asm/processor.h>
#include <asm/pointer_auth.h>
#include <asm/stacktrace.h>
+#include <asm/switch_to.h>
+#include <asm/system_misc.h>
#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK)
#include <linux/stackprotector.h>
unsigned long daif_bits;
daif_bits = read_sysreg(daif);
- write_sysreg(daif_bits | PSR_I_BIT, daif);
+ write_sysreg(daif_bits | PSR_I_BIT | PSR_F_BIT, daif);
/*
* Unmask PMR before going idle to make sure interrupts can
tls_thread_flush();
flush_ptrace_hw_breakpoint(current);
flush_tagged_addr_state();
- flush_mte_state();
}
void release_thread(struct task_struct *dead_task)
write_sysreg(val, cntkctl_el1);
}
+static void update_sctlr_el1(u64 sctlr)
+{
+ /*
+ * EnIA must not be cleared while in the kernel as this is necessary for
+ * in-kernel PAC. It will be cleared on kernel exit if needed.
+ */
+ sysreg_clear_set(sctlr_el1, SCTLR_USER_MASK & ~SCTLR_ELx_ENIA, sctlr);
+
+ /* ISB required for the kernel uaccess routines when setting TCF0. */
+ isb();
+}
+
+void set_task_sctlr_el1(u64 sctlr)
+{
+ /*
+ * __switch_to() checks current->thread.sctlr as an
+ * optimisation. Disable preemption so that it does not see
+ * the variable update before the SCTLR_EL1 one.
+ */
+ preempt_disable();
+ current->thread.sctlr_user = sctlr;
+ update_sctlr_el1(sctlr);
+ preempt_enable();
+}
+
/*
* Thread switching.
*/
entry_task_switch(next);
ssbs_thread_switch(next);
erratum_1418040_thread_switch(prev, next);
+ ptrauth_thread_switch_user(next);
/*
* Complete any pending TLB or cache maintenance on this CPU in case
* registers.
*/
mte_thread_switch(next);
+ /* avoid expensive SCTLR_EL1 accesses if no change */
+ if (prev->thread.sctlr_user != next->thread.sctlr_user)
+ update_sctlr_el1(next->thread.sctlr_user);
/* the actual thread switch */
last = cpu_switch_to(prev, next);
{
current->mm->context.flags = is_compat_task() ? MMCF_AARCH32 : 0;
- ptrauth_thread_init_user(current);
+ ptrauth_thread_init_user();
+ mte_thread_init_user();
if (task_spec_ssb_noexec(current)) {
arch_prctl_spec_ctrl_set(current, PR_SPEC_STORE_BYPASS,
return membuf_write(&to, &uregs, sizeof(uregs));
}
+static int pac_enabled_keys_get(struct task_struct *target,
+ const struct user_regset *regset,
+ struct membuf to)
+{
+ long enabled_keys = ptrauth_get_enabled_keys(target);
+
+ if (IS_ERR_VALUE(enabled_keys))
+ return enabled_keys;
+
+ return membuf_write(&to, &enabled_keys, sizeof(enabled_keys));
+}
+
+static int pac_enabled_keys_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ int ret;
+ long enabled_keys = ptrauth_get_enabled_keys(target);
+
+ if (IS_ERR_VALUE(enabled_keys))
+ return enabled_keys;
+
+ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &enabled_keys, 0,
+ sizeof(long));
+ if (ret)
+ return ret;
+
+ return ptrauth_set_enabled_keys(target, PR_PAC_ENABLED_KEYS_MASK,
+ enabled_keys);
+}
+
#ifdef CONFIG_CHECKPOINT_RESTORE
static __uint128_t pac_key_to_user(const struct ptrauth_key *key)
{
#endif
#ifdef CONFIG_ARM64_PTR_AUTH
REGSET_PAC_MASK,
+ REGSET_PAC_ENABLED_KEYS,
#ifdef CONFIG_CHECKPOINT_RESTORE
REGSET_PACA_KEYS,
REGSET_PACG_KEYS,
.regset_get = pac_mask_get,
/* this cannot be set dynamically */
},
+ [REGSET_PAC_ENABLED_KEYS] = {
+ .core_note_type = NT_ARM_PAC_ENABLED_KEYS,
+ .n = 1,
+ .size = sizeof(long),
+ .align = sizeof(long),
+ .regset_get = pac_enabled_keys_get,
+ .set = pac_enabled_keys_set,
+ },
#ifdef CONFIG_CHECKPOINT_RESTORE
[REGSET_PACA_KEYS] = {
.core_note_type = NT_ARM_PACA_KEYS,
*/
bl cpu_do_resume
-#if defined(CONFIG_KASAN) && CONFIG_KASAN_STACK
+#if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK)
mov x0, sp
bl kasan_unpoison_task_stack_below
#endif
cpuflags = read_sysreg(daif);
WARN_ON(!(cpuflags & PSR_I_BIT));
+ WARN_ON(!(cpuflags & PSR_F_BIT));
gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET);
}
* add sp, sp, #0x10
*/
+
+void start_backtrace(struct stackframe *frame, unsigned long fp,
+ unsigned long pc)
+{
+ frame->fp = fp;
+ frame->pc = pc;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ frame->graph = 0;
+#endif
+
+ /*
+ * Prime the first unwind.
+ *
+ * In unwind_frame() we'll check that the FP points to a valid stack,
+ * which can't be STACK_TYPE_UNKNOWN, and the first unwind will be
+ * treated as a transition to whichever stack that happens to be. The
+ * prev_fp value won't be used, but we set it to 0 such that it is
+ * definitely not an accessible stack address.
+ */
+ bitmap_zero(frame->stacks_done, __NR_STACK_TYPES);
+ frame->prev_fp = 0;
+ frame->prev_type = STACK_TYPE_UNKNOWN;
+}
+
/*
* Unwind from one frame record (A) to the next frame record (B).
*
#ifdef CONFIG_STACKTRACE
-void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
- struct task_struct *task, struct pt_regs *regs)
+noinline void arch_stack_walk(stack_trace_consume_fn consume_entry,
+ void *cookie, struct task_struct *task,
+ struct pt_regs *regs)
{
struct stackframe frame;
start_backtrace(&frame, regs->regs[29], regs->pc);
else if (task == current)
start_backtrace(&frame,
- (unsigned long)__builtin_frame_address(0),
- (unsigned long)arch_stack_walk);
+ (unsigned long)__builtin_frame_address(1),
+ (unsigned long)__builtin_return_address(0));
else
start_backtrace(&frame, thread_saved_fp(task),
thread_saved_pc(task));
*/
spectre_v4_enable_mitigation(NULL);
- /* Restore additional MTE-specific configuration */
+ /* Restore additional feature-specific configuration */
mte_suspend_exit();
+ ptrauth_suspend_exit();
}
/*
unsigned long flags;
struct sleep_stack_data state;
+ /* Report any MTE async fault before going to suspend */
+ mte_suspend_enter();
+
/*
* From this point debug exceptions are disabled to prevent
* updates to mdscr register (saved and restored along with
#include <linux/errno.h>
#include <linux/nospec.h>
#include <linux/ptrace.h>
+#include <linux/randomize_kstack.h>
#include <linux/syscalls.h>
#include <asm/daifflags.h>
{
long ret;
+ add_random_kstack_offset();
+
if (scno < sc_nr) {
syscall_fn_t syscall_fn;
syscall_fn = syscall_table[array_index_nospec(scno, sc_nr)];
ret = lower_32_bits(ret);
regs->regs[0] = ret;
+
+ /*
+ * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(),
+ * but not enough for arm64 stack utilization comfort. To keep
+ * reasonable stack head room, reduce the maximum offset to 9 bits.
+ *
+ * The actual entropy will be further reduced by the compiler when
+ * applying stack alignment constraints: the AAPCS mandates a
+ * 16-byte (i.e. 4-bit) aligned SP at function boundaries.
+ *
+ * The resulting 5 bits of entropy is seen in SP[8:4].
+ */
+ choose_random_kstack_offset(get_random_int() & 0x1FF);
}
static inline bool has_syscall_work(unsigned long flags)
return 0;
}
-static int __vdso_init(enum vdso_abi abi)
+static int __init __vdso_init(enum vdso_abi abi)
{
int i;
struct page **vdso_pagelist;
static struct page *aarch32_vectors_page __ro_after_init;
static struct page *aarch32_sig_page __ro_after_init;
+static int aarch32_sigpage_mremap(const struct vm_special_mapping *sm,
+ struct vm_area_struct *new_vma)
+{
+ current->mm->context.sigpage = (void *)new_vma->vm_start;
+
+ return 0;
+}
+
static struct vm_special_mapping aarch32_vdso_maps[] = {
[AA32_MAP_VECTORS] = {
.name = "[vectors]", /* ABI */
[AA32_MAP_SIGPAGE] = {
.name = "[sigpage]", /* ABI */
.pages = &aarch32_sig_page,
+ .mremap = aarch32_sigpage_mremap,
},
[AA32_MAP_VVAR] = {
.name = "[vvar]",
if (!IS_ENABLED(CONFIG_KUSER_HELPERS))
return 0;
- vdso_page = get_zeroed_page(GFP_ATOMIC);
+ vdso_page = get_zeroed_page(GFP_KERNEL);
if (!vdso_page)
return -ENOMEM;
memcpy((void *)(vdso_page + 0x1000 - kuser_sz), __kuser_helper_start,
kuser_sz);
aarch32_vectors_page = virt_to_page(vdso_page);
- flush_dcache_page(aarch32_vectors_page);
return 0;
}
+#define COMPAT_SIGPAGE_POISON_WORD 0xe7fddef1
static int aarch32_alloc_sigpage(void)
{
extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[];
int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start;
- unsigned long sigpage;
+ __le32 poison = cpu_to_le32(COMPAT_SIGPAGE_POISON_WORD);
+ void *sigpage;
- sigpage = get_zeroed_page(GFP_ATOMIC);
+ sigpage = (void *)__get_free_page(GFP_KERNEL);
if (!sigpage)
return -ENOMEM;
- memcpy((void *)sigpage, __aarch32_sigret_code_start, sigret_sz);
+ memset32(sigpage, (__force u32)poison, PAGE_SIZE / sizeof(poison));
+ memcpy(sigpage, __aarch32_sigret_code_start, sigret_sz);
aarch32_sig_page = virt_to_page(sigpage);
- flush_dcache_page(aarch32_sig_page);
return 0;
}
-static int __aarch32_alloc_vdso_pages(void)
+static int __init __aarch32_alloc_vdso_pages(void)
{
if (!IS_ENABLED(CONFIG_COMPAT_VDSO))
last_ran = this_cpu_ptr(mmu->last_vcpu_ran);
/*
+ * We guarantee that both TLBs and I-cache are private to each
+ * vcpu. If detecting that a vcpu from the same VM has
+ * previously run on the same physical CPU, call into the
+ * hypervisor code to nuke the relevant contexts.
+ *
* We might get preempted before the vCPU actually runs, but
* over-invalidation doesn't affect correctness.
*/
if (*last_ran != vcpu->vcpu_id) {
- kvm_call_hyp(__kvm_tlb_flush_local_vmid, mmu);
+ kvm_call_hyp(__kvm_flush_cpu_context, mmu);
*last_ran = vcpu->vcpu_id;
}
* - Debug ROM Address (MDCR_EL2_TDRA)
* - OS related registers (MDCR_EL2_TDOSA)
* - Statistical profiler (MDCR_EL2_TPMS/MDCR_EL2_E2PB)
+ * - Self-hosted Trace Filter controls (MDCR_EL2_TTRF)
*
* Additionally, KVM only traps guest accesses to the debug registers if
* the guest is not actively using them (see the KVM_ARM64_DEBUG_DIRTY
vcpu->arch.mdcr_el2 = __this_cpu_read(mdcr_el2) & MDCR_EL2_HPMN_MASK;
vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM |
MDCR_EL2_TPMS |
+ MDCR_EL2_TTRF |
MDCR_EL2_TPMCR |
MDCR_EL2_TDRA |
MDCR_EL2_TDOSA);
// If the hyp context is loaded, go straight to hyp_panic
get_loaded_vcpu x0, x1
- cbz x0, hyp_panic
+ cbnz x0, 1f
+ b hyp_panic
+1:
// The hyp context is saved so make sure it is restored to allow
// hyp_panic to run at hyp and, subsequently, panic to run in the host.
// This makes use of __guest_exit to avoid duplication but sets the
// current state is saved to the guest context but it will only be
// accurate if the guest had been completely restored.
adr_this_cpu x0, kvm_hyp_ctxt, x1
- adr x1, hyp_panic
+ adr_l x1, hyp_panic
str x1, [x0, #CPU_XREG_OFFSET(30)]
get_vcpu_ptr x1, x0
// Now restore the hyp regs
restore_callee_saved_regs x2
- set_loaded_vcpu xzr, x1, x2
+ set_loaded_vcpu xzr, x2, x3
alternative_if ARM64_HAS_RAS_EXTN
// If we have the RAS extensions we can consume a pending error
* counter, which could make a PMXEVCNTR_EL0 access UNDEF at
* EL1 instead of being trapped to EL2.
*/
- write_sysreg(0, pmselr_el0);
- write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
+ if (kvm_arm_support_pmu_v3()) {
+ write_sysreg(0, pmselr_el0);
+ write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
+ }
write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
}
static inline void __deactivate_traps_common(void)
{
write_sysreg(0, hstr_el2);
- write_sysreg(0, pmuserenr_el0);
+ if (kvm_arm_support_pmu_v3())
+ write_sysreg(0, pmuserenr_el0);
}
static inline void ___activate_traps(struct kvm_vcpu *vcpu)
write_sysreg_s(pmscr_el1, SYS_PMSCR_EL1);
}
-void __debug_switch_to_guest(struct kvm_vcpu *vcpu)
+void __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu)
{
/* Disable and flush SPE data generation */
__debug_save_spe(&vcpu->arch.host_debug_state.pmscr_el1);
+}
+
+void __debug_switch_to_guest(struct kvm_vcpu *vcpu)
+{
__debug_switch_to_guest_common(vcpu);
}
-void __debug_switch_to_host(struct kvm_vcpu *vcpu)
+void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu)
{
__debug_restore_spe(vcpu->arch.host_debug_state.pmscr_el1);
+}
+
+void __debug_switch_to_host(struct kvm_vcpu *vcpu)
+{
__debug_switch_to_host_common(vcpu);
}
SYM_FUNC_END(__host_enter)
/*
- * void __noreturn __hyp_do_panic(bool restore_host, u64 spsr, u64 elr, u64 par);
+ * void __noreturn __hyp_do_panic(struct kvm_cpu_context *host_ctxt, u64 spsr,
+ * u64 elr, u64 par);
*/
SYM_FUNC_START(__hyp_do_panic)
/* Prepare and exit to the host's panic funciton. */
hyp_kimg_va lr, x6
msr elr_el2, lr
- /* Set the panic format string. Use the, now free, LR as scratch. */
- ldr lr, =__hyp_panic_string
- hyp_kimg_va lr, x6
+ mov x29, x0
+
+ /* Load the format string into x0 and arguments into x1-7 */
+ ldr x0, =__hyp_panic_string
+ hyp_kimg_va x0, x6
/* Load the format arguments into x1-7. */
mov x6, x3
mrs x5, hpfar_el2
/* Enter the host, conditionally restoring the host context. */
- cmp x0, xzr
- mov x0, lr
- b.eq __host_enter_without_restoring
+ cbz x29, __host_enter_without_restoring
b __host_enter_for_panic
SYM_FUNC_END(__hyp_do_panic)
__kvm_tlb_flush_vmid(kern_hyp_va(mmu));
}
-static void handle___kvm_tlb_flush_local_vmid(struct kvm_cpu_context *host_ctxt)
+static void handle___kvm_flush_cpu_context(struct kvm_cpu_context *host_ctxt)
{
DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1);
- __kvm_tlb_flush_local_vmid(kern_hyp_va(mmu));
+ __kvm_flush_cpu_context(kern_hyp_va(mmu));
}
static void handle___kvm_timer_set_cntvoff(struct kvm_cpu_context *host_ctxt)
write_sysreg_el2(tmp, SYS_SCTLR);
}
-static void handle___vgic_v3_get_ich_vtr_el2(struct kvm_cpu_context *host_ctxt)
+static void handle___vgic_v3_get_gic_config(struct kvm_cpu_context *host_ctxt)
{
- cpu_reg(host_ctxt, 1) = __vgic_v3_get_ich_vtr_el2();
+ cpu_reg(host_ctxt, 1) = __vgic_v3_get_gic_config();
}
static void handle___vgic_v3_read_vmcr(struct kvm_cpu_context *host_ctxt)
HANDLE_FUNC(__kvm_flush_vm_context),
HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa),
HANDLE_FUNC(__kvm_tlb_flush_vmid),
- HANDLE_FUNC(__kvm_tlb_flush_local_vmid),
+ HANDLE_FUNC(__kvm_flush_cpu_context),
HANDLE_FUNC(__kvm_timer_set_cntvoff),
HANDLE_FUNC(__kvm_enable_ssbs),
- HANDLE_FUNC(__vgic_v3_get_ich_vtr_el2),
+ HANDLE_FUNC(__vgic_v3_get_gic_config),
HANDLE_FUNC(__vgic_v3_read_vmcr),
HANDLE_FUNC(__vgic_v3_write_vmcr),
HANDLE_FUNC(__vgic_v3_init_lrs),
pmu_switch_needed = __pmu_switch_to_guest(host_ctxt);
__sysreg_save_state_nvhe(host_ctxt);
+ /*
+ * We must flush and disable the SPE buffer for nVHE, as
+ * the translation regime(EL1&0) is going to be loaded with
+ * that of the guest. And we must do this before we change the
+ * translation regime to EL2 (via MDCR_EL2_E2PB == 0) and
+ * before we load guest Stage1.
+ */
+ __debug_save_host_buffers_nvhe(vcpu);
__adjust_pc(vcpu);
if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)
__fpsimd_save_fpexc32(vcpu);
+ __debug_switch_to_host(vcpu);
/*
* This must come after restoring the host sysregs, since a non-VHE
* system may enable SPE here and make use of the TTBRs.
*/
- __debug_switch_to_host(vcpu);
+ __debug_restore_host_buffers_nvhe(vcpu);
if (pmu_switch_needed)
__pmu_switch_to_host(host_ctxt);
u64 spsr = read_sysreg_el2(SYS_SPSR);
u64 elr = read_sysreg_el2(SYS_ELR);
u64 par = read_sysreg_par();
- bool restore_host = true;
struct kvm_cpu_context *host_ctxt;
struct kvm_vcpu *vcpu;
__sysreg_restore_state_nvhe(host_ctxt);
}
- __hyp_do_panic(restore_host, spsr, elr, par);
+ __hyp_do_panic(host_ctxt, spsr, elr, par);
unreachable();
}
__tlb_switch_to_host(&cxt);
}
-void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
+void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu)
{
struct tlb_inv_context cxt;
__tlb_switch_to_guest(mmu, &cxt);
__tlbi(vmalle1);
+ asm volatile("ic iallu");
dsb(nsh);
isb();
goto out;
if (!table) {
+ data->addr = ALIGN_DOWN(data->addr, kvm_granule_size(level));
data->addr += kvm_granule_size(level);
goto out;
}
__gic_v3_set_lr(0, i);
}
-u64 __vgic_v3_get_ich_vtr_el2(void)
+/*
+ * Return the GIC CPU configuration:
+ * - [31:0] ICH_VTR_EL2
+ * - [62:32] RES0
+ * - [63] MMIO (GICv2) capable
+ */
+u64 __vgic_v3_get_gic_config(void)
{
- return read_gicreg(ICH_VTR_EL2);
+ u64 val, sre = read_gicreg(ICC_SRE_EL1);
+ unsigned long flags = 0;
+
+ /*
+ * To check whether we have a MMIO-based (GICv2 compatible)
+ * CPU interface, we need to disable the system register
+ * view. To do that safely, we have to prevent any interrupt
+ * from firing (which would be deadly).
+ *
+ * Note that this only makes sense on VHE, as interrupts are
+ * already masked for nVHE as part of the exception entry to
+ * EL2.
+ */
+ if (has_vhe())
+ flags = local_daif_save();
+
+ /*
+ * Table 11-2 "Permitted ICC_SRE_ELx.SRE settings" indicates
+ * that to be able to set ICC_SRE_EL1.SRE to 0, all the
+ * interrupt overrides must be set. You've got to love this.
+ */
+ sysreg_clear_set(hcr_el2, 0, HCR_AMO | HCR_FMO | HCR_IMO);
+ isb();
+ write_gicreg(0, ICC_SRE_EL1);
+ isb();
+
+ val = read_gicreg(ICC_SRE_EL1);
+
+ write_gicreg(sre, ICC_SRE_EL1);
+ isb();
+ sysreg_clear_set(hcr_el2, HCR_AMO | HCR_FMO | HCR_IMO, 0);
+ isb();
+
+ if (has_vhe())
+ local_daif_restore(flags);
+
+ val = (val & ICC_SRE_EL1_SRE) ? 0 : (1ULL << 63);
+ val |= read_gicreg(ICH_VTR_EL2);
+
+ return val;
}
u64 __vgic_v3_read_vmcr(void)
__tlb_switch_to_host(&cxt);
}
-void __kvm_tlb_flush_local_vmid(struct kvm_s2_mmu *mmu)
+void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu)
{
struct tlb_inv_context cxt;
__tlb_switch_to_guest(mmu, &cxt);
__tlbi(vmalle1);
+ asm volatile("ic iallu");
dsb(nsh);
isb();
* Prevent userspace from creating a memory region outside of the IPA
* space addressable by the KVM guest IPA space.
*/
- if (memslot->base_gfn + memslot->npages >=
- (kvm_phys_size(kvm) >> PAGE_SHIFT))
+ if ((memslot->base_gfn + memslot->npages) > (kvm_phys_size(kvm) >> PAGE_SHIFT))
return -EFAULT;
mmap_read_lock(current->mm);
#include <asm/kvm_emulate.h>
+DEFINE_STATIC_KEY_FALSE(kvm_arm_pmu_available);
+
static int kvm_is_in_guest(void)
{
return kvm_get_running_vcpu() != NULL;
int kvm_perf_init(void)
{
+ /*
+ * Check if HW_PERF_EVENTS are supported by checking the number of
+ * hardware performance counters. This could ensure the presence of
+ * a physical PMU and CONFIG_PERF_EVENT is selected.
+ */
+ if (IS_ENABLED(CONFIG_ARM_PMU) && perf_num_counters() > 0)
+ static_branch_enable(&kvm_arm_pmu_available);
+
return perf_register_guest_info_callbacks(&kvm_guest_cbs);
}
return val & mask;
}
-bool kvm_arm_support_pmu_v3(void)
-{
- /*
- * Check if HW_PERF_EVENTS are supported by checking the number of
- * hardware performance counters. This could ensure the presence of
- * a physical PMU and CONFIG_PERF_EVENT is selected.
- */
- return (perf_num_counters() > 0);
-}
-
int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu)
{
if (!kvm_vcpu_has_pmu(vcpu))
}
switch (cpuid_feature_extract_unsigned_field(mmfr0, tgran_2)) {
- default:
- case 1:
+ case ID_AA64MMFR0_TGRAN_2_SUPPORTED_NONE:
kvm_err("PAGE_SIZE not supported at Stage-2, giving up\n");
return -EINVAL;
- case 0:
+ case ID_AA64MMFR0_TGRAN_2_SUPPORTED_DEFAULT:
kvm_debug("PAGE_SIZE supported at Stage-2 (default)\n");
break;
- case 2:
+ case ID_AA64MMFR0_TGRAN_2_SUPPORTED_MIN ... ID_AA64MMFR0_TGRAN_2_SUPPORTED_MAX:
kvm_debug("PAGE_SIZE supported at Stage-2 (advertised)\n");
break;
+ default:
+ kvm_err("Unsupported value for TGRAN_2, giving up\n");
+ return -EINVAL;
}
kvm_ipa_limit = id_aa64mmfr0_parange_to_phys_shift(parange);
- WARN(kvm_ipa_limit < KVM_PHYS_SHIFT,
- "KVM IPA Size Limit (%d bits) is smaller than default size\n",
- kvm_ipa_limit);
- kvm_info("IPA Size Limit: %d bits\n", kvm_ipa_limit);
+ kvm_info("IPA Size Limit: %d bits%s\n", kvm_ipa_limit,
+ ((kvm_ipa_limit < KVM_PHYS_SHIFT) ?
+ " (Reduced IPA size, limited VM/VMM compatibility)" : ""));
return 0;
}
return -EINVAL;
} else {
phys_shift = KVM_PHYS_SHIFT;
+ if (phys_shift > kvm_ipa_limit) {
+ pr_warn_once("%s using unsupported default IPA limit, upgrade your VMM\n",
+ current->comm);
+ return -EINVAL;
+ }
}
mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
}
break;
case GICD_TYPER2:
- if (kvm_vgic_global_state.has_gicv4_1)
+ if (kvm_vgic_global_state.has_gicv4_1 && gic_cpuif_has_vsgi())
value = GICD_TYPER2_nASSGIcap;
break;
case GICD_IIDR:
dist->enabled = val & GICD_CTLR_ENABLE_SS_G1;
/* Not a GICv4.1? No HW SGIs */
- if (!kvm_vgic_global_state.has_gicv4_1)
+ if (!kvm_vgic_global_state.has_gicv4_1 || !gic_cpuif_has_vsgi())
val &= ~GICD_CTLR_nASSGIreq;
/* Dist stays enabled? nASSGIreq is RO */
*/
int vgic_v3_probe(const struct gic_kvm_info *info)
{
- u32 ich_vtr_el2 = kvm_call_hyp_ret(__vgic_v3_get_ich_vtr_el2);
+ u64 ich_vtr_el2 = kvm_call_hyp_ret(__vgic_v3_get_gic_config);
+ bool has_v2;
int ret;
+ has_v2 = ich_vtr_el2 >> 63;
+ ich_vtr_el2 = (u32)ich_vtr_el2;
+
/*
* The ListRegs field is 5 bits, but there is an architectural
* maximum of 16 list registers. Just ignore bit 4...
gicv4_enable ? "en" : "dis");
}
+ kvm_vgic_global_state.vcpu_base = 0;
+
if (!info->vcpu.start) {
kvm_info("GICv3: no GICV resource entry\n");
- kvm_vgic_global_state.vcpu_base = 0;
+ } else if (!has_v2) {
+ pr_warn(FW_BUG "CPU interface incapable of MMIO access\n");
} else if (!PAGE_ALIGNED(info->vcpu.start)) {
pr_warn("GICV physical address 0x%llx not page aligned\n",
(unsigned long long)info->vcpu.start);
- kvm_vgic_global_state.vcpu_base = 0;
} else {
kvm_vgic_global_state.vcpu_base = info->vcpu.start;
kvm_vgic_global_state.can_emulate_gicv2 = true;
iommu_setup_dma_ops(dev, dma_base, size);
#ifdef CONFIG_XEN
- if (xen_initial_domain())
+ if (xen_swiotlb_detect())
dev->dma_ops = &xen_swiotlb_dma_ops;
#endif
}
const struct fault_info *inf;
struct mm_struct *mm = current->mm;
vm_fault_t fault;
- unsigned long vm_flags = VM_ACCESS_FLAGS;
+ unsigned long vm_flags;
unsigned int mm_flags = FAULT_FLAG_DEFAULT;
unsigned long addr = untagged_addr(far);
if (user_mode(regs))
mm_flags |= FAULT_FLAG_USER;
+ /*
+ * vm_flags tells us what bits we must have in vma->vm_flags
+ * for the fault to be benign, __do_page_fault() would check
+ * vma->vm_flags & vm_flags and returns an error if the
+ * intersection is empty
+ */
if (is_el0_instruction_abort(esr)) {
+ /* It was exec fault */
vm_flags = VM_EXEC;
mm_flags |= FAULT_FLAG_INSTRUCTION;
} else if (is_write_abort(esr)) {
+ /* It was write fault */
vm_flags = VM_WRITE;
mm_flags |= FAULT_FLAG_WRITE;
+ } else {
+ /* It was read fault */
+ vm_flags = VM_READ;
+ /* Write implies read */
+ vm_flags |= VM_WRITE;
+ /* If EPAN is absent then exec implies read */
+ if (!cpus_have_const_cap(ARM64_HAS_EPAN))
+ vm_flags |= VM_EXEC;
}
if (is_ttbr0_addr(addr) && is_el1_permission_fault(addr, esr, regs)) {
int pfn_valid(unsigned long pfn)
{
- phys_addr_t addr = pfn << PAGE_SHIFT;
+ phys_addr_t addr = PFN_PHYS(pfn);
- if ((addr >> PAGE_SHIFT) != pfn)
+ /*
+ * Ensure the upper PAGE_SHIFT bits are clear in the
+ * pfn. Else it might lead to false positives when
+ * some of the upper bits are set, but the lower bits
+ * match a valid pfn.
+ */
+ if (PHYS_PFN(addr) != pfn)
return 0;
#ifdef CONFIG_SPARSEMEM
+{
+ struct mem_section *ms;
+
if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
return 0;
- if (!valid_section(__pfn_to_section(pfn)))
+ ms = __pfn_to_section(pfn);
+ if (!valid_section(ms))
return 0;
+
+ /*
+ * ZONE_DEVICE memory does not have the memblock entries.
+ * memblock_is_map_memory() check for ZONE_DEVICE based
+ * addresses will always fail. Even the normal hotplugged
+ * memory will never have MEMBLOCK_NOMAP flag set in their
+ * memblock entries. Skip memblock search for all non early
+ * memory sections covering all of hotplug memory including
+ * both normal and ZONE_DEVICE based.
+ */
+ if (!early_section(ms))
+ return pfn_section_valid(ms, pfn);
+}
#endif
return memblock_is_map_memory(addr);
}
phys_addr_t pmd_phys = early ?
__pa_symbol(kasan_early_shadow_pmd)
: kasan_alloc_zeroed_page(node);
- __pud_populate(pudp, pmd_phys, PMD_TYPE_TABLE);
+ __pud_populate(pudp, pmd_phys, PUD_TYPE_TABLE);
}
return early ? pmd_offset_kimg(pudp, addr) : pmd_offset(pudp, addr);
phys_addr_t pud_phys = early ?
__pa_symbol(kasan_early_shadow_pud)
: kasan_alloc_zeroed_page(node);
- __p4d_populate(p4dp, pud_phys, PMD_TYPE_TABLE);
+ __p4d_populate(p4dp, pud_phys, P4D_TYPE_TABLE);
}
return early ? pud_offset_kimg(p4dp, addr) : pud_offset(p4dp, addr);
{
u64 kimg_shadow_start, kimg_shadow_end;
u64 mod_shadow_start, mod_shadow_end;
+ u64 vmalloc_shadow_end;
phys_addr_t pa_start, pa_end;
u64 i;
- kimg_shadow_start = (u64)kasan_mem_to_shadow(_text) & PAGE_MASK;
- kimg_shadow_end = PAGE_ALIGN((u64)kasan_mem_to_shadow(_end));
+ kimg_shadow_start = (u64)kasan_mem_to_shadow(KERNEL_START) & PAGE_MASK;
+ kimg_shadow_end = PAGE_ALIGN((u64)kasan_mem_to_shadow(KERNEL_END));
mod_shadow_start = (u64)kasan_mem_to_shadow((void *)MODULES_VADDR);
mod_shadow_end = (u64)kasan_mem_to_shadow((void *)MODULES_END);
+ vmalloc_shadow_end = (u64)kasan_mem_to_shadow((void *)VMALLOC_END);
+
/*
* We are going to perform proper setup of shadow memory.
* At first we should unmap early shadow (clear_pgds() call below).
clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
kasan_map_populate(kimg_shadow_start, kimg_shadow_end,
- early_pfn_to_nid(virt_to_pfn(lm_alias(_text))));
+ early_pfn_to_nid(virt_to_pfn(lm_alias(KERNEL_START))));
kasan_populate_early_shadow(kasan_mem_to_shadow((void *)PAGE_END),
(void *)mod_shadow_start);
- kasan_populate_early_shadow((void *)kimg_shadow_end,
- (void *)KASAN_SHADOW_END);
- if (kimg_shadow_start > mod_shadow_end)
- kasan_populate_early_shadow((void *)mod_shadow_end,
- (void *)kimg_shadow_start);
+ if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) {
+ BUILD_BUG_ON(VMALLOC_START != MODULES_END);
+ kasan_populate_early_shadow((void *)vmalloc_shadow_end,
+ (void *)KASAN_SHADOW_END);
+ } else {
+ kasan_populate_early_shadow((void *)kimg_shadow_end,
+ (void *)KASAN_SHADOW_END);
+ if (kimg_shadow_start > mod_shadow_end)
+ kasan_populate_early_shadow((void *)mod_shadow_end,
+ (void *)kimg_shadow_start);
+ }
for_each_mem_range(i, &pa_start, &pa_end) {
void *start = (void *)__phys_to_virt(pa_start);
#define NO_BLOCK_MAPPINGS BIT(0)
#define NO_CONT_MAPPINGS BIT(1)
+#define NO_EXEC_MAPPINGS BIT(2) /* assumes FEAT_HPDS is not used */
-u64 idmap_t0sz = TCR_T0SZ(VA_BITS);
+u64 idmap_t0sz = TCR_T0SZ(VA_BITS_MIN);
u64 idmap_ptrs_per_pgd = PTRS_PER_PGD;
u64 __section(".mmuoff.data.write") vabits_actual;
BUG_ON(pmd_sect(pmd));
if (pmd_none(pmd)) {
+ pmdval_t pmdval = PMD_TYPE_TABLE | PMD_TABLE_UXN;
phys_addr_t pte_phys;
+
+ if (flags & NO_EXEC_MAPPINGS)
+ pmdval |= PMD_TABLE_PXN;
BUG_ON(!pgtable_alloc);
pte_phys = pgtable_alloc(PAGE_SHIFT);
- __pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE);
+ __pmd_populate(pmdp, pte_phys, pmdval);
pmd = READ_ONCE(*pmdp);
}
BUG_ON(pmd_bad(pmd));
*/
BUG_ON(pud_sect(pud));
if (pud_none(pud)) {
+ pudval_t pudval = PUD_TYPE_TABLE | PUD_TABLE_UXN;
phys_addr_t pmd_phys;
+
+ if (flags & NO_EXEC_MAPPINGS)
+ pudval |= PUD_TABLE_PXN;
BUG_ON(!pgtable_alloc);
pmd_phys = pgtable_alloc(PMD_SHIFT);
- __pud_populate(pudp, pmd_phys, PUD_TYPE_TABLE);
+ __pud_populate(pudp, pmd_phys, pudval);
pud = READ_ONCE(*pudp);
}
BUG_ON(pud_bad(pud));
p4d_t p4d = READ_ONCE(*p4dp);
if (p4d_none(p4d)) {
+ p4dval_t p4dval = P4D_TYPE_TABLE | P4D_TABLE_UXN;
phys_addr_t pud_phys;
+
+ if (flags & NO_EXEC_MAPPINGS)
+ p4dval |= P4D_TABLE_PXN;
BUG_ON(!pgtable_alloc);
pud_phys = pgtable_alloc(PUD_SHIFT);
- __p4d_populate(p4dp, pud_phys, PUD_TYPE_TABLE);
+ __p4d_populate(p4dp, pud_phys, p4dval);
p4d = READ_ONCE(*p4dp);
}
BUG_ON(p4d_bad(p4d));
static void __init map_mem(pgd_t *pgdp)
{
+ static const u64 direct_map_end = _PAGE_END(VA_BITS_MIN);
phys_addr_t kernel_start = __pa_symbol(_stext);
phys_addr_t kernel_end = __pa_symbol(__init_begin);
phys_addr_t start, end;
- int flags = 0;
+ int flags = NO_EXEC_MAPPINGS;
u64 i;
+ /*
+ * Setting hierarchical PXNTable attributes on table entries covering
+ * the linear region is only possible if it is guaranteed that no table
+ * entries at any level are being shared between the linear region and
+ * the vmalloc region. Check whether this is true for the PGD level, in
+ * which case it is guaranteed to be true for all other levels as well.
+ */
+ BUILD_BUG_ON(pgd_index(direct_map_end - 1) == pgd_index(direct_map_end));
+
if (rodata_full || crash_mem_map || debug_pagealloc_enabled())
- flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
+ flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
/*
* Take care not to create a writable alias for the
* if MTE is present. Otherwise, it has the same attributes as
* PAGE_KERNEL.
*/
- __map_memblock(pgdp, start, end, PAGE_KERNEL_TAGGED, flags);
+ __map_memblock(pgdp, start, end, pgprot_tagged(PAGE_KERNEL),
+ flags);
}
/*
pudp = pud_offset_kimg(p4dp, addr);
} else {
if (p4d_none(p4d))
- __p4d_populate(p4dp, __pa_symbol(bm_pud), PUD_TYPE_TABLE);
+ __p4d_populate(p4dp, __pa_symbol(bm_pud), P4D_TYPE_TABLE);
pudp = fixmap_pud(addr);
}
if (pud_none(READ_ONCE(*pudp)))
- __pud_populate(pudp, __pa_symbol(bm_pmd), PMD_TYPE_TABLE);
+ __pud_populate(pudp, __pa_symbol(bm_pmd), PUD_TYPE_TABLE);
pmdp = fixmap_pmd(addr);
__pmd_populate(pmdp, __pa_symbol(bm_pte), PMD_TYPE_TABLE);
struct range arch_get_mappable_range(void)
{
struct range mhp_range;
+ u64 start_linear_pa = __pa(_PAGE_OFFSET(vabits_actual));
+ u64 end_linear_pa = __pa(PAGE_END - 1);
+
+ if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
+ /*
+ * Check for a wrap, it is possible because of randomized linear
+ * mapping the start physical address is actually bigger than
+ * the end physical address. In this case set start to zero
+ * because [0, end_linear_pa] range must still be able to cover
+ * all addressable physical addresses.
+ */
+ if (start_linear_pa > end_linear_pa)
+ start_linear_pa = 0;
+ }
+
+ WARN_ON(start_linear_pa > end_linear_pa);
/*
* Linear mapping region is the range [PAGE_OFFSET..(PAGE_END - 1)]
* range which can be mapped inside this linear mapping range, must
* also be derived from its end points.
*/
- mhp_range.start = __pa(_PAGE_OFFSET(vabits_actual));
- mhp_range.end = __pa(PAGE_END - 1);
+ mhp_range.start = start_linear_pa;
+ mhp_range.end = end_linear_pa;
+
return mhp_range;
}
int arch_add_memory(int nid, u64 start, u64 size,
struct mhp_params *params)
{
- int ret, flags = 0;
+ int ret, flags = NO_EXEC_MAPPINGS;
VM_BUG_ON(!mhp_range_allowed(start, size, true));
*/
if (rodata_full || debug_pagealloc_enabled() ||
IS_ENABLED(CONFIG_KFENCE))
- flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
+ flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
__create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),
size, params->pgprot, __pgd_pgtable_alloc,
reset_amuserenr_el0 x1 // Disable AMU access from EL0
/*
- * Memory region attributes
+ * Default values for VMSA control registers. These will be adjusted
+ * below depending on detected CPU features.
*/
- mov_q x5, MAIR_EL1_SET
-#ifdef CONFIG_ARM64_MTE
- mte_tcr .req x20
-
- mov mte_tcr, #0
+ mair .req x17
+ tcr .req x16
+ mov_q mair, MAIR_EL1_SET
+ mov_q tcr, TCR_TxSZ(VA_BITS) | TCR_CACHE_FLAGS | TCR_SMP_FLAGS | \
+ TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \
+ TCR_TBI0 | TCR_A1 | TCR_KASAN_SW_FLAGS
+#ifdef CONFIG_ARM64_MTE
/*
* Update MAIR_EL1, GCR_EL1 and TFSR*_EL1 if MTE is supported
* (ID_AA64PFR1_EL1[11:8] > 1).
/* Normal Tagged memory type at the corresponding MAIR index */
mov x10, #MAIR_ATTR_NORMAL_TAGGED
- bfi x5, x10, #(8 * MT_NORMAL_TAGGED), #8
+ bfi mair, x10, #(8 * MT_NORMAL_TAGGED), #8
/* initialize GCR_EL1: all non-zero tags excluded by default */
mov x10, #(SYS_GCR_EL1_RRND | SYS_GCR_EL1_EXCL_MASK)
msr_s SYS_TFSRE0_EL1, xzr
/* set the TCR_EL1 bits */
- mov_q mte_tcr, TCR_KASAN_HW_FLAGS
+ mov_q x10, TCR_KASAN_HW_FLAGS
+ orr tcr, tcr, x10
1:
#endif
- msr mair_el1, x5
- /*
- * Set/prepare TCR and TTBR. TCR_EL1.T1SZ gets further
- * adjusted if the kernel is compiled with 52bit VA support.
- */
- mov_q x10, TCR_TxSZ(VA_BITS) | TCR_CACHE_FLAGS | TCR_SMP_FLAGS | \
- TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \
- TCR_TBI0 | TCR_A1 | TCR_KASAN_SW_FLAGS
-#ifdef CONFIG_ARM64_MTE
- orr x10, x10, mte_tcr
- .unreq mte_tcr
-#endif
- tcr_clear_errata_bits x10, x9, x5
+ tcr_clear_errata_bits tcr, x9, x5
#ifdef CONFIG_ARM64_VA_BITS_52
ldr_l x9, vabits_actual
sub x9, xzr, x9
add x9, x9, #64
- tcr_set_t1sz x10, x9
+ tcr_set_t1sz tcr, x9
#else
ldr_l x9, idmap_t0sz
#endif
- tcr_set_t0sz x10, x9
+ tcr_set_t0sz tcr, x9
/*
* Set the IPS bits in TCR_EL1.
*/
- tcr_compute_pa_size x10, #TCR_IPS_SHIFT, x5, x6
+ tcr_compute_pa_size tcr, #TCR_IPS_SHIFT, x5, x6
#ifdef CONFIG_ARM64_HW_AFDBM
/*
* Enable hardware update of the Access Flags bit.
mrs x9, ID_AA64MMFR1_EL1
and x9, x9, #0xf
cbz x9, 1f
- orr x10, x10, #TCR_HA // hardware Access flag update
+ orr tcr, tcr, #TCR_HA // hardware Access flag update
1:
#endif /* CONFIG_ARM64_HW_AFDBM */
- msr tcr_el1, x10
+ msr mair_el1, mair
+ msr tcr_el1, tcr
/*
* Prepare SCTLR
*/
mov_q x0, INIT_SCTLR_EL1_MMU_ON
ret // return to head.S
+
+ .unreq mair
+ .unreq tcr
SYM_FUNC_END(__cpu_setup)
ptdump_walk_pgd(&st.ptdump, info->mm, NULL);
}
-static void ptdump_initialize(void)
+static void __init ptdump_initialize(void)
{
unsigned i, j;
pr_info("Checked W+X mappings: passed, no W+X pages found\n");
}
-static int ptdump_init(void)
+static int __init ptdump_init(void)
{
address_markers[PAGE_END_NR].start_address = PAGE_END;
#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
}
DEFINE_SHOW_ATTRIBUTE(ptdump);
-void ptdump_debugfs_register(struct ptdump_info *info, const char *name)
+void __init ptdump_debugfs_register(struct ptdump_info *info, const char *name)
{
debugfs_create_file(name, 0400, NULL, info, &ptdump_fops);
}
int "Maximum zone order"
default "11"
-config RAM_BASE
+config DRAM_BASE
hex "DRAM start addr (the same with memory-section in dts)"
default 0x0
#define SSEG_SIZE 0x20000000
#define LOWMEM_LIMIT (SSEG_SIZE * 2)
-#define PHYS_OFFSET_OFFSET (CONFIG_RAM_BASE & (SSEG_SIZE - 1))
+#define PHYS_OFFSET_OFFSET (CONFIG_DRAM_BASE & (SSEG_SIZE - 1))
#ifndef __ASSEMBLY__
return 0;
}
-/* Ftrace callback handler for kprobes -- called under preepmt disabed */
+/* Ftrace callback handler for kprobes -- called under preepmt disabled */
void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *ops, struct ftrace_regs *fregs)
{
CONFIG_SCSI_FC_ATTRS=y
CONFIG_SCSI_SYM53C8XX_2=y
CONFIG_SCSI_QLOGIC_1280=y
-CONFIG_ATA=y
-CONFIG_ATA_PIIX=y
CONFIG_SATA_VITESSE=y
CONFIG_MD=y
CONFIG_BLK_DEV_MD=m
static inline unsigned long user_stack_pointer(struct pt_regs *regs)
{
- /* FIXME: should this be bspstore + nr_dirty regs? */
- return regs->ar_bspstore;
+ return regs->r12;
}
static inline int is_syscall_success(struct pt_regs *regs)
unsigned long __ip = instruction_pointer(regs); \
(__ip & ~3UL) + ((__ip & 3UL) << 2); \
})
-/*
- * Why not default? Because user_stack_pointer() on ia64 gives register
- * stack backing store instead...
- */
-#define current_user_stack_pointer() (current_pt_regs()->r12)
/* given a pointer to a task_struct, return the user's pt_regs */
# define task_pt_regs(t) (((struct pt_regs *) ((char *) (t) + IA64_STK_OFFSET)) - 1)
static inline long syscall_get_error(struct task_struct *task,
struct pt_regs *regs)
{
- return regs->r10 == -1 ? regs->r8:0;
+ return regs->r10 == -1 ? -regs->r8:0;
}
static inline long syscall_get_return_value(struct task_struct *task,
char *buf) \
{ \
u32 cpu=dev->id; \
- return sprintf(buf, "%lx\n", name[cpu]); \
+ return sprintf(buf, "%llx\n", name[cpu]); \
}
#define store(name) \
#ifdef ERR_INJ_DEBUG
printk(KERN_DEBUG "pal_mc_err_inject for cpu%d:\n", cpu);
- printk(KERN_DEBUG "err_type_info=%lx,\n", err_type_info[cpu]);
- printk(KERN_DEBUG "err_struct_info=%lx,\n", err_struct_info[cpu]);
- printk(KERN_DEBUG "err_data_buffer=%lx, %lx, %lx.\n",
+ printk(KERN_DEBUG "err_type_info=%llx,\n", err_type_info[cpu]);
+ printk(KERN_DEBUG "err_struct_info=%llx,\n", err_struct_info[cpu]);
+ printk(KERN_DEBUG "err_data_buffer=%llx, %llx, %llx.\n",
err_data_buffer[cpu].data1,
err_data_buffer[cpu].data2,
err_data_buffer[cpu].data3);
#ifdef ERR_INJ_DEBUG
printk(KERN_DEBUG "Returns: status=%d,\n", (int)status[cpu]);
- printk(KERN_DEBUG "capabilities=%lx,\n", capabilities[cpu]);
- printk(KERN_DEBUG "resources=%lx\n", resources[cpu]);
+ printk(KERN_DEBUG "capabilities=%llx,\n", capabilities[cpu]);
+ printk(KERN_DEBUG "resources=%llx\n", resources[cpu]);
#endif
return size;
}
char *buf)
{
unsigned int cpu=dev->id;
- return sprintf(buf, "%lx\n", phys_addr[cpu]);
+ return sprintf(buf, "%llx\n", phys_addr[cpu]);
}
static ssize_t
ret = get_user_pages_fast(virt_addr, 1, FOLL_WRITE, NULL);
if (ret<=0) {
#ifdef ERR_INJ_DEBUG
- printk("Virtual address %lx is not existing.\n",virt_addr);
+ printk("Virtual address %llx is not existing.\n", virt_addr);
#endif
return -EINVAL;
}
{
unsigned int cpu=dev->id;
- return sprintf(buf, "%lx, %lx, %lx\n",
+ return sprintf(buf, "%llx, %llx, %llx\n",
err_data_buffer[cpu].data1,
err_data_buffer[cpu].data2,
err_data_buffer[cpu].data3);
int ret;
#ifdef ERR_INJ_DEBUG
- printk("write err_data_buffer=[%lx,%lx,%lx] on cpu%d\n",
+ printk("write err_data_buffer=[%llx,%llx,%llx] on cpu%d\n",
err_data_buffer[cpu].data1,
err_data_buffer[cpu].data2,
err_data_buffer[cpu].data3,
cpu);
#endif
- ret=sscanf(buf, "%lx, %lx, %lx",
+ ret = sscanf(buf, "%llx, %llx, %llx",
&err_data_buffer[cpu].data1,
&err_data_buffer[cpu].data2,
&err_data_buffer[cpu].data3);
data = mca_bootmem();
first_time = 0;
} else
- data = (void *)__get_free_pages(GFP_KERNEL,
+ data = (void *)__get_free_pages(GFP_ATOMIC,
get_order(sz));
if (!data)
panic("Could not allocate MCA memory for cpu %d\n",
{
struct syscall_get_set_args *args = data;
struct pt_regs *pt = args->regs;
- unsigned long *krbs, cfm, ndirty;
+ unsigned long *krbs, cfm, ndirty, nlocals, nouts;
int i, count;
if (unw_unwind_to_user(info) < 0)
return;
+ /*
+ * We get here via a few paths:
+ * - break instruction: cfm is shared with caller.
+ * syscall args are in out= regs, locals are non-empty.
+ * - epsinstruction: cfm is set by br.call
+ * locals don't exist.
+ *
+ * For both cases argguments are reachable in cfm.sof - cfm.sol.
+ * CFM: [ ... | sor: 17..14 | sol : 13..7 | sof : 6..0 ]
+ */
cfm = pt->cr_ifs;
+ nlocals = (cfm >> 7) & 0x7f; /* aka sol */
+ nouts = (cfm & 0x7f) - nlocals; /* aka sof - sol */
krbs = (unsigned long *)info->task + IA64_RBS_OFFSET/8;
ndirty = ia64_rse_num_regs(krbs, krbs + (pt->loadrs >> 19));
count = 0;
if (in_syscall(pt))
- count = min_t(int, args->n, cfm & 0x7f);
+ count = min_t(int, args->n, nouts);
+ /* Iterate over outs. */
for (i = 0; i < count; i++) {
+ int j = ndirty + nlocals + i + args->i;
if (args->rw)
- *ia64_rse_skip_regs(krbs, ndirty + i + args->i) =
- args->args[i];
+ *ia64_rse_skip_regs(krbs, j) = args->args[i];
else
- args->args[i] = *ia64_rse_skip_regs(krbs,
- ndirty + i + args->i);
+ args->args[i] = *ia64_rse_skip_regs(krbs, j);
}
if (!args->rw) {
* acpi_boot_init() (which builds the node_to_cpu_mask array) hasn't been
* called yet. Note that node 0 will also count all non-existent cpus.
*/
-static int __meminit early_nr_cpus_node(int node)
+static int early_nr_cpus_node(int node)
{
int cpu, n = 0;
* compute_pernodesize - compute size of pernode data
* @node: the node id.
*/
-static unsigned long __meminit compute_pernodesize(int node)
+static unsigned long compute_pernodesize(int node)
{
unsigned long pernodesize = 0, cpus;
}
}
-static void __meminit scatter_node_data(void)
+static void scatter_node_data(void)
{
pg_data_t **dst;
int node;
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_BLAKE2S=m
CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES=y
CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_DES=m
CONFIG_CRYPTO_FCRYPT=m
CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_SM4=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_BLAKE2S=m
CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES=y
CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_DES=m
CONFIG_CRYPTO_FCRYPT=m
CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_SM4=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_BLAKE2S=m
CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES=y
CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_DES=m
CONFIG_CRYPTO_FCRYPT=m
CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_SM4=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_BLAKE2S=m
CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES=y
CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_DES=m
CONFIG_CRYPTO_FCRYPT=m
CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_SM4=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_BLAKE2S=m
CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES=y
CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_DES=m
CONFIG_CRYPTO_FCRYPT=m
CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_SM4=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_BLAKE2S=m
CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES=y
CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_DES=m
CONFIG_CRYPTO_FCRYPT=m
CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_SM4=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_BLAKE2S=m
CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES=y
CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_DES=m
CONFIG_CRYPTO_FCRYPT=m
CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_SM4=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_BLAKE2S=m
CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES=y
CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_DES=m
CONFIG_CRYPTO_FCRYPT=m
CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_SM4=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_BLAKE2S=m
CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES=y
CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_DES=m
CONFIG_CRYPTO_FCRYPT=m
CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_SM4=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_BLAKE2S=m
CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES=y
CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_DES=m
CONFIG_CRYPTO_FCRYPT=m
CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_SM4=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_BLAKE2S=m
CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES=y
CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_DES=m
CONFIG_CRYPTO_FCRYPT=m
CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_SM4=m
CONFIG_CRYPTO_VMAC=m
CONFIG_CRYPTO_BLAKE2S=m
CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES=y
CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_DES=m
CONFIG_CRYPTO_FCRYPT=m
CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_SM4=m
ssin.o ssinh.o stan.o stanh.o sto_res.o stwotox.o tbldo.o util.o \
x_bsun.o x_fline.o x_operr.o x_ovfl.o x_snan.o x_store.o \
x_unfl.o x_unimp.o x_unsupp.o bugfix.o skeleton.o
-
-EXTRA_LDFLAGS := -x
-
-$(OS_OBJS): fpsp.h
# for more details.
obj-y := fskeleton.o iskeleton.o os.o
-
-EXTRA_LDFLAGS := -x
#define PCC_INT_ENAB 0x08
#define PCC_TIMER_INT_CLR 0x80
+
+#define PCC_TIMER_TIC_EN 0x01
+#define PCC_TIMER_COC_EN 0x02
#define PCC_TIMER_CLR_OVF 0x04
#define PCC_LEVEL_ABORT 0x07
((__p) - pgdat->node_mem_map) + pgdat->node_start_pfn; \
})
#else
-#define ARCH_PFN_OFFSET (m68k_memory[0].addr)
+#define ARCH_PFN_OFFSET (m68k_memory[0].addr >> PAGE_SHIFT)
#include <asm-generic/memory_model.h>
#endif
-#define virt_addr_valid(kaddr) ((void *)(kaddr) >= (void *)PAGE_OFFSET && (void *)(kaddr) < high_memory)
+#define virt_addr_valid(kaddr) ((unsigned long)(kaddr) >= PAGE_OFFSET && (unsigned long)(kaddr) < (unsigned long)high_memory)
#define pfn_valid(pfn) virt_addr_valid(pfn_to_virt(pfn))
#endif /* __ASSEMBLY__ */
#define page_to_pfn(page) virt_to_pfn(page_to_virt(page))
#define pfn_valid(pfn) ((pfn) < max_mapnr)
-#define virt_addr_valid(kaddr) (((void *)(kaddr) >= (void *)PAGE_OFFSET) && \
- ((void *)(kaddr) < (void *)memory_end))
+#define virt_addr_valid(kaddr) (((unsigned long)(kaddr) >= PAGE_OFFSET) && \
+ ((unsigned long)(kaddr) < memory_end))
#endif /* __ASSEMBLY__ */
case 4: /* FD_STATUS */
*(sun3x_fdc.status_r) = value;
break;
- };
+ }
return;
}
ret = -EPERM;
if (!capable(CAP_SYS_ADMIN))
goto out;
+
+ mmap_read_lock(current->mm);
} else {
struct vm_area_struct *vma;
$(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)')
syscall := $(src)/syscall.tbl
-syshdr := $(srctree)/$(src)/syscallhdr.sh
-systbl := $(srctree)/$(src)/syscalltbl.sh
+syshdr := $(srctree)/scripts/syscallhdr.sh
+systbl := $(srctree)/scripts/syscalltbl.sh
quiet_cmd_syshdr = SYSHDR $@
- cmd_syshdr = $(CONFIG_SHELL) '$(syshdr)' '$<' '$@' \
- '$(syshdr_abis_$(basetarget))' \
- '$(syshdr_pfx_$(basetarget))' \
- '$(syshdr_offset_$(basetarget))'
+ cmd_syshdr = $(CONFIG_SHELL) $(syshdr) --emit-nr $< $@
quiet_cmd_systbl = SYSTBL $@
- cmd_systbl = $(CONFIG_SHELL) '$(systbl)' '$<' '$@' \
- '$(systbl_abis_$(basetarget))' \
- '$(systbl_abi_$(basetarget))' \
- '$(systbl_offset_$(basetarget))'
+ cmd_systbl = $(CONFIG_SHELL) $(systbl) $< $@
$(uapi)/unistd_32.h: $(syscall) $(syshdr) FORCE
$(call if_changed,syshdr)
+++ /dev/null
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-
-in="$1"
-out="$2"
-my_abis=`echo "($3)" | tr ',' '|'`
-prefix="$4"
-offset="$5"
-
-fileguard=_UAPI_ASM_M68K_`basename "$out" | sed \
- -e 'y/abcdefghijklmnopqrstuvwxyz/ABCDEFGHIJKLMNOPQRSTUVWXYZ/' \
- -e 's/[^A-Z0-9_]/_/g' -e 's/__/_/g'`
-grep -E "^[0-9A-Fa-fXx]+[[:space:]]+${my_abis}" "$in" | sort -n | (
- printf "#ifndef %s\n" "${fileguard}"
- printf "#define %s\n" "${fileguard}"
- printf "\n"
-
- nxt=0
- while read nr abi name entry ; do
- if [ -z "$offset" ]; then
- printf "#define __NR_%s%s\t%s\n" \
- "${prefix}" "${name}" "${nr}"
- else
- printf "#define __NR_%s%s\t(%s + %s)\n" \
- "${prefix}" "${name}" "${offset}" "${nr}"
- fi
- nxt=$((nr+1))
- done
-
- printf "\n"
- printf "#ifdef __KERNEL__\n"
- printf "#define __NR_syscalls\t%s\n" "${nxt}"
- printf "#endif\n"
- printf "\n"
- printf "#endif /* %s */\n" "${fileguard}"
-) > "$out"
+++ /dev/null
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-
-in="$1"
-out="$2"
-my_abis=`echo "($3)" | tr ',' '|'`
-my_abi="$4"
-offset="$5"
-
-emit() {
- t_nxt="$1"
- t_nr="$2"
- t_entry="$3"
-
- while [ $t_nxt -lt $t_nr ]; do
- printf "__SYSCALL(%s, sys_ni_syscall, )\n" "${t_nxt}"
- t_nxt=$((t_nxt+1))
- done
- printf "__SYSCALL(%s, %s, )\n" "${t_nxt}" "${t_entry}"
-}
-
-grep -E "^[0-9A-Fa-fXx]+[[:space:]]+${my_abis}" "$in" | sort -n | (
- nxt=0
- if [ -z "$offset" ]; then
- offset=0
- fi
-
- while read nr abi name entry ; do
- emit $((nxt+offset)) $((nr+offset)) $entry
- nxt=$((nr+1))
- done
-) > "$out"
#define sys_mmap2 sys_mmap_pgoff
#endif
-#define __SYSCALL(nr, entry, nargs) .long entry
+#define __SYSCALL(nr, entry) .long entry
.section .rodata
ALIGN
ENTRY(sys_call_table)
#include <asm/syscall_table.h>
-#undef __SYSCALL
unsigned long flags;
local_irq_save(flags);
- m147_pcc->t1_int_cntrl = PCC_TIMER_INT_CLR;
- m147_pcc->t1_cntrl = PCC_TIMER_CLR_OVF;
+ m147_pcc->t1_cntrl = PCC_TIMER_CLR_OVF | PCC_TIMER_COC_EN |
+ PCC_TIMER_TIC_EN;
+ m147_pcc->t1_int_cntrl = PCC_INT_ENAB | PCC_TIMER_INT_CLR |
+ PCC_LEVEL_TIMER1;
clk_total += PCC_TIMER_CYCLES;
legacy_timer_tick(1);
local_irq_restore(flags);
/* Init the clock with a value */
/* The clock counter increments until 0xFFFF then reloads */
m147_pcc->t1_preload = PCC_TIMER_PRELOAD;
- m147_pcc->t1_cntrl = 0x0; /* clear timer */
- m147_pcc->t1_cntrl = 0x3; /* start timer */
- m147_pcc->t1_int_cntrl = PCC_TIMER_INT_CLR; /* clear pending ints */
- m147_pcc->t1_int_cntrl = PCC_INT_ENAB|PCC_LEVEL_TIMER1;
+ m147_pcc->t1_cntrl = PCC_TIMER_CLR_OVF | PCC_TIMER_COC_EN |
+ PCC_TIMER_TIC_EN;
+ m147_pcc->t1_int_cntrl = PCC_INT_ENAB | PCC_TIMER_INT_CLR |
+ PCC_LEVEL_TIMER1;
clocksource_register_hz(&mvme147_clk, PCC_TIMER_CLOCK_FREQ);
}
#define PCCTOVR1_COC_EN 0x02
#define PCCTOVR1_OVR_CLR 0x04
+#define PCCTIC1_INT_LEVEL 6
#define PCCTIC1_INT_CLR 0x08
#define PCCTIC1_INT_EN 0x10
unsigned long flags;
local_irq_save(flags);
- out_8(PCCTIC1, in_8(PCCTIC1) | PCCTIC1_INT_CLR);
- out_8(PCCTOVR1, PCCTOVR1_OVR_CLR);
+ out_8(PCCTOVR1, PCCTOVR1_OVR_CLR | PCCTOVR1_TIC_EN | PCCTOVR1_COC_EN);
+ out_8(PCCTIC1, PCCTIC1_INT_EN | PCCTIC1_INT_CLR | PCCTIC1_INT_LEVEL);
clk_total += PCC_TIMER_CYCLES;
legacy_timer_tick(1);
local_irq_restore(flags);
int irq;
/* Using PCCchip2 or MC2 chip tick timer 1 */
- out_be32(PCCTCNT1, 0);
- out_be32(PCCTCMP1, PCC_TIMER_CYCLES);
- out_8(PCCTOVR1, in_8(PCCTOVR1) | PCCTOVR1_TIC_EN | PCCTOVR1_COC_EN);
- out_8(PCCTIC1, PCCTIC1_INT_EN | 6);
if (request_irq(MVME16x_IRQ_TIMER, mvme16x_timer_int, IRQF_TIMER, "timer",
NULL))
panic ("Couldn't register timer int");
+ out_be32(PCCTCNT1, 0);
+ out_be32(PCCTCMP1, PCC_TIMER_CYCLES);
+ out_8(PCCTOVR1, PCCTOVR1_OVR_CLR | PCCTOVR1_TIC_EN | PCCTOVR1_COC_EN);
+ out_8(PCCTIC1, PCCTIC1_INT_EN | PCCTIC1_INT_CLR | PCCTIC1_INT_LEVEL);
+
clocksource_register_hz(&mvme16x_clk, PCC_TIMER_CLOCK_FREQ);
if (brdno == 0x0162 || brdno == 0x172)
#include <asm/addrspace.h>
#include <asm/unaligned.h>
+#include <asm-generic/vmlinux.lds.h>
/*
* These two variables specify the free mem region
/* last four bytes is always image size in little endian */
image_size = get_unaligned_le32((void *)&__image_end - 4);
+ /* The device tree's address must be properly aligned */
+ image_size = ALIGN(image_size, STRUCT_ALIGNMENT);
+
+ puts("Copy device tree to address ");
+ puthex(VMLINUX_LOAD_ADDRESS_ULL + image_size);
+ puts("\n");
+
/* copy dtb to where the booted kernel will expect it */
memcpy((void *)VMLINUX_LOAD_ADDRESS_ULL + image_size,
__appended_dtb, dtb_size);
obj-$(CONFIG_CRYPTO_POLY1305_MIPS) += poly1305-mips.o
poly1305-mips-y := poly1305-core.o poly1305-glue.o
-perlasm-flavour-$(CONFIG_CPU_MIPS32) := o32
-perlasm-flavour-$(CONFIG_CPU_MIPS64) := 64
+perlasm-flavour-$(CONFIG_32BIT) := o32
+perlasm-flavour-$(CONFIG_64BIT) := 64
quiet_cmd_perlasm = PERLASM $@
cmd_perlasm = $(PERL) $(<) $(perlasm-flavour-y) $(@)
asmlinkage void poly1305_blocks_mips(void *state, const u8 *src, u32 len, u32 hibit);
asmlinkage void poly1305_emit_mips(void *state, u8 *digest, const u32 *nonce);
-void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key)
+void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE])
{
poly1305_init_mips(&dctx->h, key);
dctx->s[0] = get_unaligned_le32(key + 16);
extern void (*board_cache_error_setup)(void);
extern int register_nmi_notifier(struct notifier_block *nb);
+extern void reserve_exception_space(phys_addr_t addr, unsigned long size);
extern char except_vec_nmi[];
+#define VECTORSPACING 0x100 /* for EI/VI mode */
+
#define nmi_notifier(fn, pri) \
({ \
static struct notifier_block fn##_nb = { \
#include <asm/elf.h>
#include <asm/pgtable-bits.h>
#include <asm/spram.h>
+#include <asm/traps.h>
#include <linux/uaccess.h>
#include "fpu-probe.h"
c->cputype = CPU_BMIPS3300;
__cpu_name[cpu] = "Broadcom BMIPS3300";
set_elf_platform(cpu, "bmips3300");
+ reserve_exception_space(0x400, VECTORSPACING * 64);
break;
case PRID_IMP_BMIPS43XX: {
int rev = c->processor_id & PRID_REV_MASK;
__cpu_name[cpu] = "Broadcom BMIPS4380";
set_elf_platform(cpu, "bmips4380");
c->options |= MIPS_CPU_RIXI;
+ reserve_exception_space(0x400, VECTORSPACING * 64);
} else {
c->cputype = CPU_BMIPS4350;
__cpu_name[cpu] = "Broadcom BMIPS4350";
__cpu_name[cpu] = "Broadcom BMIPS5000";
set_elf_platform(cpu, "bmips5000");
c->options |= MIPS_CPU_ULRI | MIPS_CPU_RIXI;
+ reserve_exception_space(0x1000, VECTORSPACING * 64);
break;
}
}
if (cpu == 0)
__ua_limit = ~((1ull << cpu_vmbits) - 1);
#endif
+
+ reserve_exception_space(0, 0x1000);
}
void cpu_report(void)
#include <asm/fpu.h>
#include <asm/mipsregs.h>
#include <asm/elf.h>
+#include <asm/traps.h>
#include "fpu-probe.h"
cpu_set_fpu_opts(c);
else
cpu_set_nofpu_opts(c);
+
+ reserve_exception_space(0, 0x400);
}
void cpu_report(void)
#include <asm/prom.h>
#ifdef CONFIG_MIPS_ELF_APPENDED_DTB
-const char __section(".appended_dtb") __appended_dtb[0x100000];
+char __section(".appended_dtb") __appended_dtb[0x100000];
#endif /* CONFIG_MIPS_ELF_APPENDED_DTB */
struct cpuinfo_mips cpu_data[NR_CPUS] __read_mostly;
nmi_exit();
}
-#define VECTORSPACING 0x100 /* for EI/VI mode */
-
unsigned long ebase;
EXPORT_SYMBOL_GPL(ebase);
unsigned long exception_handlers[32];
unsigned long vi_handlers[64];
+void reserve_exception_space(phys_addr_t addr, unsigned long size)
+{
+ memblock_reserve(addr, size);
+}
+
void __init *set_except_vector(int n, void *addr)
{
unsigned long handler = (unsigned long) addr;
if (!cpu_has_mips_r2_r6) {
ebase = CAC_BASE;
- ebase_pa = virt_to_phys((void *)ebase);
vec_size = 0x400;
-
- memblock_reserve(ebase_pa, vec_size);
} else {
if (cpu_has_veic || cpu_has_vint)
vec_size = 0x200 + VECTORSPACING*64;
}
#ifdef CONFIG_MIPS_ELF_APPENDED_DTB
+ STRUCT_ALIGN();
.appended_dtb : AT(ADDR(.appended_dtb) - LOAD_OFFSET) {
*(.appended_dtb)
KEEP(*(.appended_dtb))
#endif
#ifdef CONFIG_MIPS_RAW_APPENDED_DTB
+ .fill : {
+ FILL(0);
+ BYTE(0);
+ STRUCT_ALIGN();
+ }
__appended_dtb = .;
/* leave space for appended DTB */
. += 0x100000;
}
#ifdef CONFIG_CPU_XLP
-static const struct irq_domain_ops xlp_pic_irq_domain_ops = {
- .xlate = irq_domain_xlate_onetwocell,
-};
-
static int __init xlp_of_pic_init(struct device_node *node,
struct device_node *parent)
{
xlp_pic_domain = irq_domain_add_legacy(node, n_picirqs,
nlm_irq_to_xirq(socid, PIC_IRQ_BASE), PIC_IRQ_BASE,
- &xlp_pic_irq_domain_ops, NULL);
+ &irq_domain_simple_ops, NULL);
if (xlp_pic_domain == NULL) {
pr_err("PIC %pOFn: Creating legacy domain failed!\n", node);
return -EINVAL;
{
struct address_space *mapping;
- mapping = page_mapping(page);
+ mapping = page_mapping_file(page);
if (mapping && !mapping_mapped(mapping))
set_bit(PG_dcache_dirty, &page->flags);
else {
def_bool y
depends on PA8X00 || PA7200
+config PARISC_HUGE_KERNEL
+ def_bool y if !MODULES || UBSAN || FTRACE || COMPILE_TEST
+
config MLONGCALLS
- def_bool y if !MODULES || UBSAN || FTRACE
- bool "Enable the -mlong-calls compiler option for big kernels" if MODULES && !UBSAN && !FTRACE
+ def_bool y if PARISC_HUGE_KERNEL
+ bool "Enable the -mlong-calls compiler option for big kernels" if !PARISC_HUGE_KERNEL
depends on PA8X00
help
If you configure the kernel to include many drivers built-in instead
#endif
case 4: return __cmpxchg_u32((unsigned int *)ptr,
(unsigned int)old, (unsigned int)new_);
- case 1: return __cmpxchg_u8((u8 *)ptr, (u8)old, (u8)new_);
+ case 1: return __cmpxchg_u8((u8 *)ptr, old & 0xff, new_ & 0xff);
}
__cmpxchg_called_with_bad_pointer();
return old;
regs->gr[23] = 0; \
} while(0)
-struct task_struct;
struct mm_struct;
/* Free all resources held by a thread. */
};
#ifdef CONFIG_64BIT
-#include <linux/compat.h>
-
static int gpr32_get(struct task_struct *target,
const struct user_regset *regset,
struct membuf to)
* Floating-point emulation code
* Copyright (C) 2001 Hewlett-Packard (Paul Bame) <bame@debian.org>
*/
-/*
- * BEGIN_DESC
- *
- * File:
- * @(#) pa/fp/fpu.h $Revision: 1.1 $
- *
- * Purpose:
- * <<please update with a synopis of the functionality provided by this file>>
- *
- *
- * END_DESC
-*/
-
-#ifdef __NO_PA_HDRS
- PA header file -- do not include this header file for non-PA builds.
-#endif
-
#ifndef _MACHINE_FPU_INCLUDED /* allows multiple inclusion */
#define _MACHINE_FPU_INCLUDED
-#if 0
-#ifndef _SYS_STDSYMS_INCLUDED
-# include <sys/stdsyms.h>
-#endif /* _SYS_STDSYMS_INCLUDED */
-#include <machine/pdc/pdc_rqsts.h>
-#endif
-
#define PA83_FPU_FLAG 0x00000001
#define PA89_FPU_FLAG 0x00000002
#define PA2_0_FPU_FLAG 0x00000010
#define COPR_FP 0x00000080 /* Floating point -- Coprocessor 0 */
#define SFU_MPY_DIVIDE 0x00008000 /* Multiply/Divide __ SFU 0 */
-
#define EM_FPU_TYPE_OFFSET 272
/* version of EMULATION software for COPR,0,0 instruction */
#define EMULATION_VERSION 4
/*
- * The only was to differeniate between TIMEX and ROLEX (or PCX-S and PCX-T)
- * is thorough the potential type field from the PDC_MODEL call. The
- * following flags are used at assist this differeniation.
+ * The only way to differentiate between TIMEX and ROLEX (or PCX-S and PCX-T)
+ * is through the potential type field from the PDC_MODEL call.
+ * The following flags are used to assist this differentiation.
*/
#define ROLEX_POTENTIAL_KEY_FLAGS PDC_MODEL_CPU_KEY_WORD_TO_IO
#define TIMEX_POTENTIAL_KEY_FLAGS (PDC_MODEL_CPU_KEY_QUAD_STORE | \
PDC_MODEL_CPU_KEY_RECIP_SQRT)
-
#endif /* ! _MACHINE_FPU_INCLUDED */
src += bytes;
len -= bytes;
- };
+ }
memcpy((char *)sctx->buffer, src, len);
return 0;
#endif
#define OP_RT_RA_MASK 0xffff0000UL
-#define LIS_R2 0x3c020000UL
-#define ADDIS_R2_R12 0x3c4c0000UL
-#define ADDI_R2_R2 0x38420000UL
+#define LIS_R2 (PPC_INST_ADDIS | __PPC_RT(R2))
+#define ADDIS_R2_R12 (PPC_INST_ADDIS | __PPC_RT(R2) | __PPC_RA(R12))
+#define ADDI_R2_R2 (PPC_INST_ADDI | __PPC_RT(R2) | __PPC_RA(R2))
+
static inline unsigned long ppc_function_entry(void *func)
{
#include <linux/bug.h>
#include <asm/cputable.h>
-static inline bool early_cpu_has_feature(unsigned long feature)
+static __always_inline bool early_cpu_has_feature(unsigned long feature)
{
return !!((CPU_FTRS_ALWAYS & feature) ||
(CPU_FTRS_POSSIBLE & cur_cpu_spec->cpu_features & feature));
return static_branch_likely(&cpu_feature_keys[i]);
}
#else
-static inline bool cpu_has_feature(unsigned long feature)
+static __always_inline bool cpu_has_feature(unsigned long feature)
{
return early_cpu_has_feature(feature);
}
#define mfdcr(rn) \
({unsigned int rval; \
if (__builtin_constant_p(rn) && rn < 1024) \
- asm volatile("mfdcr %0," __stringify(rn) \
- : "=r" (rval)); \
+ asm volatile("mfdcr %0, %1" : "=r" (rval) \
+ : "n" (rn)); \
else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR))) \
rval = mfdcrx(rn); \
else \
#define mtdcr(rn, v) \
do { \
if (__builtin_constant_p(rn) && rn < 1024) \
- asm volatile("mtdcr " __stringify(rn) ",%0" \
- : : "r" (v)); \
+ asm volatile("mtdcr %0, %1" \
+ : : "n" (rn), "r" (v)); \
else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR))) \
mtdcrx(rn, v); \
else \
DECLARE_INTERRUPT_HANDLER(CacheLockingException);
DECLARE_INTERRUPT_HANDLER(SPEFloatingPointException);
DECLARE_INTERRUPT_HANDLER(SPEFloatingPointRoundException);
-DECLARE_INTERRUPT_HANDLER(unrecoverable_exception);
DECLARE_INTERRUPT_HANDLER(WatchdogException);
DECLARE_INTERRUPT_HANDLER(kernel_bad_stack);
DECLARE_INTERRUPT_HANDLER_ASYNC(TAUException);
+void unrecoverable_exception(struct pt_regs *regs);
+
void replay_system_reset(void);
void replay_soft_interrupts(void);
#define MMU_FTRS_ALWAYS 0
#endif
-static inline bool early_mmu_has_feature(unsigned long feature)
+static __always_inline bool early_mmu_has_feature(unsigned long feature)
{
if (MMU_FTRS_ALWAYS & feature)
return true;
}
-static inline bool mmu_has_feature(unsigned long feature)
+static __always_inline bool mmu_has_feature(unsigned long feature)
{
return early_mmu_has_feature(feature);
}
#define TRAP_FLAGS_MASK 0x11
#define TRAP(regs) ((regs)->trap & ~TRAP_FLAGS_MASK)
#define FULL_REGS(regs) (((regs)->trap & 1) == 0)
-#define SET_FULL_REGS(regs) ((regs)->trap |= 1)
+#define SET_FULL_REGS(regs) ((regs)->trap &= ~1)
#endif
#define CHECK_FULL_REGS(regs) BUG_ON(!FULL_REGS(regs))
#define NV_REG_POISON 0xdeadbeefdeadbeefUL
#define TRAP_FLAGS_MASK 0x1F
#define TRAP(regs) ((regs)->trap & ~TRAP_FLAGS_MASK)
#define FULL_REGS(regs) (((regs)->trap & 1) == 0)
-#define SET_FULL_REGS(regs) ((regs)->trap |= 1)
+#define SET_FULL_REGS(regs) ((regs)->trap &= ~1)
#define IS_CRITICAL_EXC(regs) (((regs)->trap & 2) != 0)
#define IS_MCHECK_EXC(regs) (((regs)->trap & 4) != 0)
#define IS_DEBUG_EXC(regs) (((regs)->trap & 8) != 0)
{
msr_check_and_clear(MSR_FP|MSR_VEC|MSR_VSX);
}
+#else
+static inline void enable_kernel_vsx(void)
+{
+ BUILD_BUG();
+}
+
+static inline void disable_kernel_vsx(void)
+{
+ BUILD_BUG();
+}
#endif
#ifdef CONFIG_SPE
const char *name;
const struct vio_device_id *id_table;
int (*probe)(struct vio_dev *dev, const struct vio_device_id *id);
- int (*remove)(struct vio_dev *dev);
+ void (*remove)(struct vio_dev *dev);
/* A driver must have a get_desired_dma() function to
* be loaded in a CMO environment if it uses DMA.
*/
targets += prom_init_check
clean-files := vmlinux.lds
+
+# Force dependency (incbin is bad)
+$(obj)/vdso32_wrapper.o : $(obj)/vdso32/vdso32.so.dbg
+$(obj)/vdso64_wrapper.o : $(obj)/vdso64/vdso64.so.dbg
ld r10,PACAKMSR(r13) /* get MSR value for kernel */
/* MSR[RI] is clear iff using SRR regs */
- .if IHSRR == EXC_HV_OR_STD
+ .if IHSRR_IF_HVMODE
BEGIN_FTR_SECTION
xori r10,r10,MSR_RI
END_FTR_SECTION_IFCLR(CPU_FTR_HVMODE)
cmplw 0,r1,r3
#endif
mfspr r2, SPRN_SDR1
- li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
+ li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC | _PAGE_USER
rlwinm r2, r2, 28, 0xfffff000
#ifdef CONFIG_MODULES
bgt- 112f
lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
+ li r1,_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_EXEC
addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
#endif
112: rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */
lis r1, TASK_SIZE@h /* check if kernel address */
cmplw 0,r1,r3
mfspr r2, SPRN_SDR1
- li r1, _PAGE_PRESENT | _PAGE_ACCESSED
+ li r1, _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER
rlwinm r2, r2, 28, 0xfffff000
bgt- 112f
lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
+ li r1, _PAGE_PRESENT | _PAGE_ACCESSED
addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
112: rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */
lwz r2,0(r2) /* get pmd entry */
lis r1, TASK_SIZE@h /* check if kernel address */
cmplw 0,r1,r3
mfspr r2, SPRN_SDR1
- li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED
+ li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER
rlwinm r2, r2, 28, 0xfffff000
bgt- 112f
lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
+ li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT | _PAGE_ACCESSED
addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
112: rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */
lwz r2,0(r2) /* get pmd entry */
* enabled when the interrupt handler returns (indicating a process-context /
* synchronous interrupt) then irqs_enabled should be true.
*/
-static notrace inline bool __prep_irq_for_enabled_exit(bool clear_ri)
+static notrace __always_inline bool __prep_irq_for_enabled_exit(bool clear_ri)
{
/* This must be done with RI=1 because tracing may touch vmaps */
trace_hardirqs_on();
return ret;
}
-void unrecoverable_exception(struct pt_regs *regs);
void preempt_schedule_irq(void);
notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsigned long msr)
CFLAGS_ptrace-view.o += -DUTS_MACHINE='"$(UTS_MACHINE)"'
obj-y += ptrace.o ptrace-view.o
-obj-$(CONFIG_PPC_FPU_REGS) += ptrace-fpu.o
+obj-y += ptrace-fpu.o
obj-$(CONFIG_COMPAT) += ptrace32.o
obj-$(CONFIG_VSX) += ptrace-vsx.o
ifneq ($(CONFIG_VSX),y)
-obj-$(CONFIG_PPC_FPU_REGS) += ptrace-novsx.o
+obj-y += ptrace-novsx.o
endif
obj-$(CONFIG_ALTIVEC) += ptrace-altivec.o
obj-$(CONFIG_SPE) += ptrace-spe.o
extern const struct user_regset_view user_ppc_native_view;
/* ptrace-fpu */
-#ifdef CONFIG_PPC_FPU_REGS
int ptrace_get_fpr(struct task_struct *child, int index, unsigned long *data);
int ptrace_put_fpr(struct task_struct *child, int index, unsigned long data);
-#else
-static inline int
-ptrace_get_fpr(struct task_struct *child, int index, unsigned long *data)
-{
- return -EIO;
-}
-
-static inline int
-ptrace_put_fpr(struct task_struct *child, int index, unsigned long data)
-{
- return -EIO;
-}
-#endif
/* ptrace-(no)adv */
void ppc_gethwdinfo(struct ppc_debug_info *dbginfo);
int ptrace_get_fpr(struct task_struct *child, int index, unsigned long *data)
{
+#ifdef CONFIG_PPC_FPU_REGS
unsigned int fpidx = index - PT_FPR0;
+#endif
if (index > PT_FPSCR)
return -EIO;
+#ifdef CONFIG_PPC_FPU_REGS
flush_fp_to_thread(child);
if (fpidx < (PT_FPSCR - PT_FPR0))
memcpy(data, &child->thread.TS_FPR(fpidx), sizeof(long));
else
*data = child->thread.fp_state.fpscr;
+#else
+ *data = 0;
+#endif
return 0;
}
int ptrace_put_fpr(struct task_struct *child, int index, unsigned long data)
{
+#ifdef CONFIG_PPC_FPU_REGS
unsigned int fpidx = index - PT_FPR0;
+#endif
if (index > PT_FPSCR)
return -EIO;
+#ifdef CONFIG_PPC_FPU_REGS
flush_fp_to_thread(child);
if (fpidx < (PT_FPSCR - PT_FPR0))
memcpy(&child->thread.TS_FPR(fpidx), &data, sizeof(long));
else
child->thread.fp_state.fpscr = data;
+#endif
return 0;
}
int fpr_get(struct task_struct *target, const struct user_regset *regset,
struct membuf to)
{
+#ifdef CONFIG_PPC_FPU_REGS
BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
offsetof(struct thread_fp_state, fpr[32]));
flush_fp_to_thread(target);
return membuf_write(&to, &target->thread.fp_state, 33 * sizeof(u64));
+#else
+ return membuf_write(&to, &empty_zero_page, 33 * sizeof(u64));
+#endif
}
/*
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
+#ifdef CONFIG_PPC_FPU_REGS
BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) !=
offsetof(struct thread_fp_state, fpr[32]));
return user_regset_copyin(&pos, &count, &kbuf, &ubuf,
&target->thread.fp_state, 0, -1);
+#else
+ return 0;
+#endif
}
.size = sizeof(long), .align = sizeof(long),
.regset_get = gpr_get, .set = gpr_set
},
-#ifdef CONFIG_PPC_FPU_REGS
[REGSET_FPR] = {
.core_note_type = NT_PRFPREG, .n = ELF_NFPREG,
.size = sizeof(double), .align = sizeof(double),
.regset_get = fpr_get, .set = fpr_set
},
-#endif
#ifdef CONFIG_ALTIVEC
[REGSET_VMX] = {
.core_note_type = NT_PPC_VMX, .n = 34,
else
prepare_save_user_regs(1);
- if (!user_write_access_begin(frame, sizeof(*frame)))
+ if (!user_access_begin(frame, sizeof(*frame)))
goto badframe;
/* Put the siginfo & fill in most of the ucontext */
unsafe_put_user(PPC_INST_ADDI + __NR_rt_sigreturn, &mctx->mc_pad[0],
failed);
unsafe_put_user(PPC_INST_SC, &mctx->mc_pad[1], failed);
+ asm("dcbst %y0; sync; icbi %y0; sync" :: "Z" (mctx->mc_pad[0]));
}
unsafe_put_sigset_t(&frame->uc.uc_sigmask, oldset, failed);
- user_write_access_end();
+ user_access_end();
if (copy_siginfo_to_user(&frame->info, &ksig->info))
goto badframe;
- if (tramp == (unsigned long)mctx->mc_pad)
- flush_icache_range(tramp, tramp + 2 * sizeof(unsigned long));
-
regs->link = tramp;
#ifdef CONFIG_PPC_FPU_REGS
return 0;
failed:
- user_write_access_end();
+ user_access_end();
badframe:
signal_fault(tsk, regs, "handle_rt_signal32", frame);
else
prepare_save_user_regs(1);
- if (!user_write_access_begin(frame, sizeof(*frame)))
+ if (!user_access_begin(frame, sizeof(*frame)))
goto badframe;
sc = (struct sigcontext __user *) &frame->sctx;
/* Set up the sigreturn trampoline: li r0,sigret; sc */
unsafe_put_user(PPC_INST_ADDI + __NR_sigreturn, &mctx->mc_pad[0], failed);
unsafe_put_user(PPC_INST_SC, &mctx->mc_pad[1], failed);
+ asm("dcbst %y0; sync; icbi %y0; sync" :: "Z" (mctx->mc_pad[0]));
}
- user_write_access_end();
-
- if (tramp == (unsigned long)mctx->mc_pad)
- flush_icache_range(tramp, tramp + 2 * sizeof(unsigned long));
+ user_access_end();
regs->link = tramp;
return 0;
failed:
- user_write_access_end();
+ user_access_end();
badframe:
signal_fault(tsk, regs, "handle_signal32", frame);
* in the MSR is 0. This indicates that SRR0/1 are live, and that
* we therefore lost state by taking this exception.
*/
-DEFINE_INTERRUPT_HANDLER(unrecoverable_exception)
+void unrecoverable_exception(struct pt_regs *regs)
{
pr_emerg("Unrecoverable exception %lx at %lx (msr=%lx)\n",
regs->trap, regs->nip, regs->msr);
V_FUNCTION_BEGIN(__kernel_time)
cvdso_call_time __c_kernel_time
V_FUNCTION_END(__kernel_time)
+
+/* Routines for restoring integer registers, called by the compiler. */
+/* Called with r11 pointing to the stack header word of the caller of the */
+/* function, just beyond the end of the integer restore area. */
+_GLOBAL(_restgpr_31_x)
+_GLOBAL(_rest32gpr_31_x)
+ lwz r0,4(r11)
+ lwz r31,-4(r11)
+ mtlr r0
+ mr r1,r11
+ blr
if (!address_ok(regs, ea, size) || copy_mem_in(mem, ea, size, regs))
return -EFAULT;
- nr_vsx_regs = size / sizeof(__vector128);
+ nr_vsx_regs = max(1ul, size / sizeof(__vector128));
emulate_vsx_load(op, buf, mem, cross_endian);
preempt_disable();
if (reg < 32) {
if (!address_ok(regs, ea, size))
return -EFAULT;
- nr_vsx_regs = size / sizeof(__vector128);
+ nr_vsx_regs = max(1ul, size / sizeof(__vector128));
preempt_disable();
if (reg < 32) {
/* FP regs + extensions */
if (!(mmcra & MMCRA_SAMPLE_ENABLE) || sdar_valid)
*addrp = mfspr(SPRN_SDAR);
- if (is_kernel_addr(mfspr(SPRN_SDAR)) && perf_allow_kernel(&event->attr) != 0)
+ if (is_kernel_addr(mfspr(SPRN_SDAR)) && event->attr.exclude_kernel)
*addrp = 0;
}
* addresses, hence include a check before filtering code
*/
if (!(ppmu->flags & PPMU_ARCH_31) &&
- is_kernel_addr(addr) && perf_allow_kernel(&event->attr) != 0)
+ is_kernel_addr(addr) && event->attr.exclude_kernel)
continue;
/* Branches are read most recent first (ie. mfbhrb 0 is
want_v = hpte_encode_avpn(vpn, psize, ssize);
- flags = (newpp & 7) | H_AVPN;
+ flags = (newpp & (HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_LO)) | H_AVPN;
+ flags |= (newpp & HPTE_R_KEY_HI) >> 48;
if (mmu_has_feature(MMU_FTR_KERNEL_RO))
/* Move pp0 into bit 8 (IBM 55) */
flags |= (newpp & HPTE_R_PP0) >> 55;
return ret;
}
+/**
+ * struct pseries_suspend_info - State shared between CPUs for join/suspend.
+ * @counter: Threads are to increment this upon resuming from suspend
+ * or if an error is received from H_JOIN. The thread which performs
+ * the first increment (i.e. sets it to 1) is responsible for
+ * waking the other threads.
+ * @done: False if join/suspend is in progress. True if the operation is
+ * complete (successful or not).
+ */
+struct pseries_suspend_info {
+ atomic_t counter;
+ bool done;
+};
+
static int do_join(void *arg)
{
- atomic_t *counter = arg;
+ struct pseries_suspend_info *info = arg;
+ atomic_t *counter = &info->counter;
long hvrc;
int ret;
+retry:
/* Must ensure MSR.EE off for H_JOIN. */
hard_irq_disable();
hvrc = plpar_hcall_norets(H_JOIN);
case H_SUCCESS:
/*
* The suspend is complete and this cpu has received a
- * prod.
+ * prod, or we've received a stray prod from unrelated
+ * code (e.g. paravirt spinlocks) and we need to join
+ * again.
+ *
+ * This barrier orders the return from H_JOIN above vs
+ * the load of info->done. It pairs with the barrier
+ * in the wakeup/prod path below.
*/
+ smp_mb();
+ if (READ_ONCE(info->done) == false) {
+ pr_info_ratelimited("premature return from H_JOIN on CPU %i, retrying",
+ smp_processor_id());
+ goto retry;
+ }
ret = 0;
break;
case H_BAD_MODE:
if (atomic_inc_return(counter) == 1) {
pr_info("CPU %u waking all threads\n", smp_processor_id());
+ WRITE_ONCE(info->done, true);
+ /*
+ * This barrier orders the store to info->done vs subsequent
+ * H_PRODs to wake the other CPUs. It pairs with the barrier
+ * in the H_SUCCESS case above.
+ */
+ smp_mb();
prod_others();
}
/*
int ret;
while (true) {
- atomic_t counter = ATOMIC_INIT(0);
+ struct pseries_suspend_info info;
unsigned long vasi_state;
int vasi_err;
- ret = stop_machine(do_join, &counter, cpu_online_mask);
+ info = (struct pseries_suspend_info) {
+ .counter = ATOMIC_INIT(0),
+ .done = false,
+ };
+
+ ret = stop_machine(do_join, &info, cpu_online_mask);
if (ret == 0)
break;
/*
* Copyright 2006-2007 Michael Ellerman, IBM Corp.
*/
+#include <linux/crash_dump.h>
#include <linux/device.h>
#include <linux/irq.h>
#include <linux/msi.h>
return hwirq;
}
- virq = irq_create_mapping_affinity(NULL, hwirq,
- entry->affinity);
+ /*
+ * Depending on the number of online CPUs in the original
+ * kernel, it is likely for CPU #0 to be offline in a kdump
+ * kernel. The associated IRQs in the affinity mappings
+ * provided by irq_create_affinity_masks() are thus not
+ * started by irq_startup(), as per-design for managed IRQs.
+ * This can be a problem with multi-queue block devices driven
+ * by blk-mq : such a non-started IRQ is very likely paired
+ * with the single queue enforced by blk-mq during kdump (see
+ * blk_mq_alloc_tag_set()). This causes the device to remain
+ * silent and likely hangs the guest at some point.
+ *
+ * We don't really care for fine-grained affinity when doing
+ * kdump actually : simply ignore the pre-computed affinity
+ * masks in this case and let the default mask with all CPUs
+ * be used when creating the IRQ mappings.
+ */
+ if (is_kdump_kernel())
+ virq = irq_create_mapping(NULL, hwirq);
+ else
+ virq = irq_create_mapping_affinity(NULL, hwirq,
+ entry->affinity);
if (!virq) {
pr_debug("rtas_msi: Failed mapping hwirq %d\n", hwirq);
struct vio_dev *viodev = to_vio_dev(dev);
struct vio_driver *viodrv = to_vio_driver(dev->driver);
struct device *devptr;
- int ret = 1;
/*
* Hold a reference to the device after the remove function is called
devptr = get_device(dev);
if (viodrv->remove)
- ret = viodrv->remove(viodev);
+ viodrv->remove(viodev);
- if (!ret && firmware_has_feature(FW_FEATURE_CMO))
+ if (firmware_has_feature(FW_FEATURE_CMO))
vio_cmo_bus_remove(viodev);
put_device(devptr);
- return ret;
+ return 0;
}
/**
select PCI_MSI if PCI
select RISCV_INTC
select RISCV_TIMER if RISCV_SBI
- select SPARSEMEM_STATIC if 32BIT
select SPARSE_IRQ
select SYSCTL_EXCEPTION_TRACE
select THREAD_INFO_IN_TASK
config ARCH_SPARSEMEM_ENABLE
def_bool y
depends on MMU
- select SPARSEMEM_VMEMMAP_ENABLE
+ select SPARSEMEM_STATIC if 32BIT && SPARSEMEM
+ select SPARSEMEM_VMEMMAP_ENABLE if 64BIT
config ARCH_SELECT_MEMORY_MODEL
def_bool ARCH_SPARSEMEM_ENABLE
# Common NUMA Features
config NUMA
bool "NUMA Memory Allocation and Scheduler Support"
- depends on SMP
+ depends on SMP && MMU
select GENERIC_ARCH_NUMA
select OF_NUMA
select ARCH_SUPPORTS_NUMA_BALANCING
select SIFIVE_PLIC
select ARCH_HAS_RESET_CONTROLLER
select PINCTRL
+ select COMMON_CLK
+ select COMMON_CLK_K210
help
This enables support for Canaan Kendryte K210 SoC platform hardware.
long long __ashrti3(long long a, int b);
long long __ashlti3(long long a, int b);
+
+#define DECLARE_DO_ERROR_INFO(name) asmlinkage void name(struct pt_regs *regs)
+
+DECLARE_DO_ERROR_INFO(do_trap_unknown);
+DECLARE_DO_ERROR_INFO(do_trap_insn_misaligned);
+DECLARE_DO_ERROR_INFO(do_trap_insn_fault);
+DECLARE_DO_ERROR_INFO(do_trap_insn_illegal);
+DECLARE_DO_ERROR_INFO(do_trap_load_fault);
+DECLARE_DO_ERROR_INFO(do_trap_load_misaligned);
+DECLARE_DO_ERROR_INFO(do_trap_store_misaligned);
+DECLARE_DO_ERROR_INFO(do_trap_store_fault);
+DECLARE_DO_ERROR_INFO(do_trap_ecall_u);
+DECLARE_DO_ERROR_INFO(do_trap_ecall_s);
+DECLARE_DO_ERROR_INFO(do_trap_ecall_m);
+DECLARE_DO_ERROR_INFO(do_trap_break);
+
#endif /* _ASM_RISCV_PROTOTYPES_H */
#include <asm-generic/irq.h>
+extern void __init init_IRQ(void);
+
#endif /* _ASM_RISCV_IRQ_H */
int riscv_of_parent_hartid(struct device_node *node);
extern void riscv_fill_hwcap(void);
+extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
#endif /* __ASSEMBLY__ */
extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
unsigned int n);
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
+ unsigned long frame_pointer);
+int do_syscall_trace_enter(struct pt_regs *regs);
+void do_syscall_trace_exit(struct pt_regs *regs);
+
/**
* regs_get_register() - get register value from its offset
* @regs: pt_regs from which register value is gotten
SBI_EXT_RFENCE_REMOTE_FENCE_I = 0,
SBI_EXT_RFENCE_REMOTE_SFENCE_VMA,
SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID,
- SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA,
SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID,
- SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA,
+ SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA,
SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID,
+ SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA,
};
enum sbi_ext_hsm_fid {
return 0;
}
+extern void time_init(void);
+
#endif /* _ASM_RISCV_TIMEX_H */
* data types like structures or arrays.
*
* @ptr must have pointer-to-simple-variable type, and @x must be assignable
- * to the result of dereferencing @ptr.
+ * to the result of dereferencing @ptr. The value of @x is copied to avoid
+ * re-ordering where @x is evaluated inside the block that enables user-space
+ * access (thus bypassing user space protection if @x is a function).
*
* Caller must check the pointer with access_ok() before calling this
* function.
#define __put_user(x, ptr) \
({ \
__typeof__(*(ptr)) __user *__gu_ptr = (ptr); \
+ __typeof__(*__gu_ptr) __val = (x); \
long __pu_err = 0; \
\
__chk_user_ptr(__gu_ptr); \
\
__enable_user_access(); \
- __put_user_nocheck(x, __gu_ptr, __pu_err); \
+ __put_user_nocheck(__val, __gu_ptr, __pu_err); \
__disable_user_access(); \
\
__pu_err; \
CFLAGS_REMOVE_patch.o = $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_sbi.o = $(CC_FLAGS_FTRACE)
endif
+CFLAGS_syscall_table.o += $(call cc-option,-Wno-override-init,)
extra-y += head.o
extra-y += vmlinux.lds
*/
andi t0, s1, SR_PIE
beqz t0, 1f
+ /* kprobes, entered via ebreak, must have interrupts disabled. */
+ li t0, EXC_BREAKPOINT
+ beq s4, t0, 1f
#ifdef CONFIG_TRACE_IRQFLAGS
call trace_hardirqs_on
#endif
#endif
.section ".rodata"
+ .align LGREG
/* Exception vector table */
ENTRY(excp_vect_table)
RISCV_PTR do_trap_insn_misaligned
#include <linux/kprobes.h>
-/* Ftrace callback handler for kprobes -- called under preepmt disabed */
+/* Ftrace callback handler for kprobes -- called under preepmt disabled */
void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
- struct ftrace_ops *ops, struct ftrace_regs *regs)
+ struct ftrace_ops *ops, struct ftrace_regs *fregs)
{
struct kprobe *p;
+ struct pt_regs *regs;
struct kprobe_ctlblk *kcb;
+ int bit;
+ bit = ftrace_test_recursion_trylock(ip, parent_ip);
+ if (bit < 0)
+ return;
+
+ preempt_disable_notrace();
p = get_kprobe((kprobe_opcode_t *)ip);
if (unlikely(!p) || kprobe_disabled(p))
- return;
+ goto out;
+ regs = ftrace_get_regs(fregs);
kcb = get_kprobe_ctlblk();
if (kprobe_running()) {
kprobes_inc_nmissed_count(p);
} else {
- unsigned long orig_ip = instruction_pointer(&(regs->regs));
+ unsigned long orig_ip = instruction_pointer(regs);
- instruction_pointer_set(&(regs->regs), ip);
+ instruction_pointer_set(regs, ip);
__this_cpu_write(current_kprobe, p);
kcb->kprobe_status = KPROBE_HIT_ACTIVE;
- if (!p->pre_handler || !p->pre_handler(p, &(regs->regs))) {
+ if (!p->pre_handler || !p->pre_handler(p, regs)) {
/*
* Emulate singlestep (and also recover regs->pc)
* as if there is a nop
*/
- instruction_pointer_set(&(regs->regs),
+ instruction_pointer_set(regs,
(unsigned long)p->addr + MCOUNT_INSN_SIZE);
if (unlikely(p->post_handler)) {
kcb->kprobe_status = KPROBE_HIT_SSDONE;
- p->post_handler(p, &(regs->regs), 0);
+ p->post_handler(p, regs, 0);
}
- instruction_pointer_set(&(regs->regs), orig_ip);
+ instruction_pointer_set(regs, orig_ip);
}
/*
*/
__this_cpu_write(current_kprobe, NULL);
}
+out:
+ preempt_enable_notrace();
+ ftrace_test_recursion_unlock(bit);
}
NOKPROBE_SYMBOL(kprobe_ftrace_handler);
* normal page fault.
*/
regs->epc = (unsigned long) cur->addr;
- if (!instruction_pointer(regs))
- BUG();
+ BUG_ON(!instruction_pointer(regs));
if (kcb->kprobe_status == KPROBE_REENTER)
restore_previous_kprobe(kcb);
#include <linux/cpu.h>
#include <linux/kernel.h>
#include <linux/sched.h>
+#include <linux/sched/debug.h>
#include <linux/sched/task_stack.h>
#include <linux/tick.h>
#include <linux/ptrace.h>
EXPORT_SYMBOL(sbi_clear_ipi);
/**
- * sbi_set_timer_v01() - Program the timer for next timer event.
+ * __sbi_set_timer_v01() - Program the timer for next timer event.
* @stime_value: The value after which next timer event should fire.
*
* Return: None
bss_res.end = __pa_symbol(__bss_stop) - 1;
bss_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
- mem_res_sz = (memblock.memory.cnt + memblock.reserved.cnt) * sizeof(*mem_res);
+ /* + 1 as memblock_alloc() might increase memblock.reserved.cnt */
+ mem_res_sz = (memblock.memory.cnt + memblock.reserved.cnt + 1) * sizeof(*mem_res);
mem_res = memblock_alloc(mem_res_sz, SMP_CACHE_BYTES);
if (!mem_res)
panic("%s: Failed to allocate %zu bytes\n", __func__, mem_res_sz);
#include <asm/stacktrace.h>
-register const unsigned long sp_in_global __asm__("sp");
+register unsigned long sp_in_global __asm__("sp");
#ifdef CONFIG_FRAME_POINTER
#include <linux/delay.h>
#include <asm/sbi.h>
#include <asm/processor.h>
+#include <asm/timex.h>
unsigned long riscv_timebase;
EXPORT_SYMBOL_GPL(riscv_timebase);
#include <linux/module.h>
#include <linux/irq.h>
+#include <asm/asm-prototypes.h>
#include <asm/bug.h>
#include <asm/processor.h>
#include <asm/ptrace.h>
else
die(regs, "Kernel BUG");
}
+NOKPROBE_SYMBOL(do_trap_break);
#ifdef CONFIG_GENERIC_BUG
int is_valid_bugaddr(unsigned long pc)
}
return;
}
+NOKPROBE_SYMBOL(do_page_fault);
memset(start, KASAN_SHADOW_INIT, end - start);
}
-void __init kasan_shallow_populate(void *start, void *end)
+static void __init kasan_shallow_populate(void *start, void *end)
{
unsigned long vaddr = (unsigned long)start & PAGE_MASK;
unsigned long vend = PAGE_ALIGN((unsigned long)end);
}
vaddr += PAGE_SIZE;
}
+
+ local_flush_tlb_all();
}
void __init kasan_init(void)
break;
kasan_populate(kasan_mem_to_shadow(start), kasan_mem_to_shadow(end));
- };
+ }
for (i = 0; i < PTRS_PER_PTE; i++)
set_pte(&kasan_early_shadow_pte[i],
CONFIG_IP_VS_SH=m
CONFIG_IP_VS_SED=m
CONFIG_IP_VS_NQ=m
+CONFIG_IP_VS_TWOS=m
CONFIG_IP_VS_FTP=m
CONFIG_IP_VS_PE_SIP=m
-CONFIG_NF_TABLES_IPV4=y
CONFIG_NFT_FIB_IPV4=m
CONFIG_NF_TABLES_ARP=y
CONFIG_IP_NF_IPTABLES=m
CONFIG_IP_NF_ARPTABLES=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
-CONFIG_NF_TABLES_IPV6=y
CONFIG_NFT_FIB_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP6_NF_MATCH_AH=m
# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
# CONFIG_NET_VENDOR_ATHEROS is not set
-# CONFIG_NET_VENDOR_AURORA is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
# CONFIG_NET_VENDOR_BROCADE is not set
# CONFIG_NET_VENDOR_CADENCE is not set
CONFIG_VIRTIO_INPUT=y
CONFIG_VHOST_NET=m
CONFIG_VHOST_VSOCK=m
-# CONFIG_SURFACE_PLATFORMS is not set
CONFIG_S390_CCW_IOMMU=y
CONFIG_S390_AP_IOMMU=y
CONFIG_EXT4_FS=y
CONFIG_PROC_KCORE=y
CONFIG_TMPFS=y
CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_TMPFS_INODE64=y
CONFIG_HUGETLBFS=y
CONFIG_CONFIGFS_FS=m
CONFIG_ECRYPT_FS=m
CONFIG_CRYPTO_CRC32=m
CONFIG_CRYPTO_BLAKE2S=m
CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_ANUBIS=m
CONFIG_CRYPTO_DES=m
CONFIG_CRYPTO_FCRYPT=m
CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_SM4=m
CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER=y
CONFIG_SLUB_DEBUG_ON=y
CONFIG_SLUB_STATS=y
-CONFIG_DEBUG_KMEMLEAK=y
-CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF=y
CONFIG_DEBUG_STACK_USAGE=y
CONFIG_DEBUG_VM=y
CONFIG_DEBUG_VM_VMACACHE=y
-CONFIG_DEBUG_VM_RB=y
CONFIG_DEBUG_VM_PGFLAGS=y
CONFIG_DEBUG_MEMORY_INIT=y
CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m
CONFIG_HIST_TRIGGERS=y
CONFIG_FTRACE_STARTUP_TEST=y
# CONFIG_EVENT_TRACE_STARTUP_TEST is not set
+CONFIG_DEBUG_ENTRY=y
CONFIG_NOTIFIER_ERROR_INJECTION=m
CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m
CONFIG_FAULT_INJECTION=y
CONFIG_ATOMIC64_SELFTEST=y
CONFIG_TEST_BITOPS=m
CONFIG_TEST_BPF=m
-CONFIG_DEBUG_ENTRY=y
CONFIG_IP_VS_SH=m
CONFIG_IP_VS_SED=m
CONFIG_IP_VS_NQ=m
+CONFIG_IP_VS_TWOS=m
CONFIG_IP_VS_FTP=m
CONFIG_IP_VS_PE_SIP=m
-CONFIG_NF_TABLES_IPV4=y
CONFIG_NFT_FIB_IPV4=m
CONFIG_NF_TABLES_ARP=y
CONFIG_IP_NF_IPTABLES=m
CONFIG_IP_NF_ARPTABLES=m
CONFIG_IP_NF_ARPFILTER=m
CONFIG_IP_NF_ARP_MANGLE=m
-CONFIG_NF_TABLES_IPV6=y
CONFIG_NFT_FIB_IPV6=m
CONFIG_IP6_NF_IPTABLES=m
CONFIG_IP6_NF_MATCH_AH=m
# CONFIG_NET_VENDOR_AQUANTIA is not set
# CONFIG_NET_VENDOR_ARC is not set
# CONFIG_NET_VENDOR_ATHEROS is not set
-# CONFIG_NET_VENDOR_AURORA is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
# CONFIG_NET_VENDOR_BROCADE is not set
# CONFIG_NET_VENDOR_CADENCE is not set
CONFIG_VIRTIO_INPUT=y
CONFIG_VHOST_NET=m
CONFIG_VHOST_VSOCK=m
-# CONFIG_SURFACE_PLATFORMS is not set
CONFIG_S390_CCW_IOMMU=y
CONFIG_S390_AP_IOMMU=y
CONFIG_EXT4_FS=y
CONFIG_PROC_KCORE=y
CONFIG_TMPFS=y
CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_TMPFS_INODE64=y
CONFIG_HUGETLBFS=y
CONFIG_CONFIGFS_FS=m
CONFIG_ECRYPT_FS=m
CONFIG_CRYPTO_CRC32=m
CONFIG_CRYPTO_BLAKE2S=m
CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_RMD128=m
CONFIG_CRYPTO_RMD160=m
-CONFIG_CRYPTO_RMD256=m
-CONFIG_CRYPTO_RMD320=m
CONFIG_CRYPTO_SHA3=m
-CONFIG_CRYPTO_TGR192=m
CONFIG_CRYPTO_WP512=m
CONFIG_CRYPTO_AES_TI=m
CONFIG_CRYPTO_ANUBIS=m
CONFIG_CRYPTO_DES=m
CONFIG_CRYPTO_FCRYPT=m
CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_SALSA20=m
CONFIG_CRYPTO_SEED=m
CONFIG_CRYPTO_SERPENT=m
CONFIG_CRYPTO_SM4=m
# CONFIG_SECCOMP is not set
# CONFIG_GCC_PLUGINS is not set
CONFIG_PARTITION_ADVANCED=y
-CONFIG_IBM_PARTITION=y
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
# CONFIG_COMPACTION is not set
# CONFIG_MIGRATION is not set
# CONFIG_HID is not set
# CONFIG_VIRTIO_MENU is not set
# CONFIG_VHOST_MENU is not set
-# CONFIG_SURFACE_PLATFORMS is not set
# CONFIG_IOMMU_SUPPORT is not set
# CONFIG_DNOTIFY is not set
# CONFIG_INOTIFY_USER is not set
-CONFIG_CONFIGFS_FS=y
# CONFIG_MISC_FILESYSTEMS is not set
# CONFIG_NETWORK_FILESYSTEMS is not set
CONFIG_LSM="yama,loadpin,safesetid,integrity"
struct s390_idle_data {
seqcount_t seqcount;
- unsigned long long idle_count;
- unsigned long long idle_time;
- unsigned long long clock_idle_enter;
- unsigned long long clock_idle_exit;
- unsigned long long timer_idle_enter;
- unsigned long long timer_idle_exit;
+ unsigned long idle_count;
+ unsigned long idle_time;
+ unsigned long clock_idle_enter;
+ unsigned long clock_idle_exit;
+ unsigned long timer_idle_enter;
+ unsigned long timer_idle_exit;
unsigned long mt_cycles_enter[8];
};
----------------------------------------------------------------------------- */
/* Base stuff */
int zpci_create_device(u32 fid, u32 fh, enum zpci_state state);
-void zpci_remove_device(struct zpci_dev *zdev);
+void zpci_remove_device(struct zpci_dev *zdev, bool set_error);
int zpci_enable_device(struct zpci_dev *);
int zpci_disable_device(struct zpci_dev *);
int zpci_register_ioat(struct zpci_dev *, u8, u64, u64, u64);
STACK_TYPE_IRQ,
STACK_TYPE_NODAT,
STACK_TYPE_RESTART,
+ STACK_TYPE_MCCK,
};
struct stack_info {
/* Query TOD offset result */
struct ptff_qto {
- unsigned long long physical_clock;
- unsigned long long tod_offset;
- unsigned long long logical_tod_offset;
- unsigned long long tod_epoch_difference;
+ unsigned long physical_clock;
+ unsigned long tod_offset;
+ unsigned long logical_tod_offset;
+ unsigned long tod_epoch_difference;
} __packed;
static inline int ptff_query(unsigned int nr)
rc; \
})
-static inline unsigned long long local_tick_disable(void)
+static inline unsigned long local_tick_disable(void)
{
- unsigned long long old;
+ unsigned long old;
old = S390_lowcore.clock_comparator;
S390_lowcore.clock_comparator = clock_comparator_max;
return old;
}
-static inline void local_tick_enable(unsigned long long comp)
+static inline void local_tick_enable(unsigned long comp)
{
S390_lowcore.clock_comparator = comp;
set_clock_comparator(S390_lowcore.clock_comparator);
#define CLOCK_TICK_RATE 1193180 /* Underlying HZ */
-typedef unsigned long long cycles_t;
+typedef unsigned long cycles_t;
-static inline unsigned long long get_tod_clock(void)
+static inline unsigned long get_tod_clock(void)
{
union tod_clock clk;
return clk.tod;
}
-static inline unsigned long long get_tod_clock_fast(void)
+static inline unsigned long get_tod_clock_fast(void)
{
#ifdef CONFIG_HAVE_MARCH_Z9_109_FEATURES
- unsigned long long clk;
+ unsigned long clk;
asm volatile("stckf %0" : "=Q" (clk) : : "cc");
return clk;
* Therefore preemption must be disabled, otherwise the returned
* value is not guaranteed to be monotonic.
*/
-static inline unsigned long long get_tod_clock_monotonic(void)
+static inline unsigned long get_tod_clock_monotonic(void)
{
- unsigned long long tod;
+ unsigned long tod;
preempt_disable_notrace();
tod = get_tod_clock() - tod_clock_base.tod;
* -> ns = (th * 125) + ((tl * 125) >> 9);
*
*/
-static inline unsigned long long tod_to_ns(unsigned long long todval)
+static inline unsigned long tod_to_ns(unsigned long todval)
{
return ((todval >> 9) * 125) + (((todval & 0x1ff) * 125) >> 9);
}
*
* Returns: true if a is later than b
*/
-static inline int tod_after(unsigned long long a, unsigned long long b)
+static inline int tod_after(unsigned long a, unsigned long b)
{
if (MACHINE_HAS_SCC)
- return (long long) a > (long long) b;
+ return (long) a > (long) b;
return a > b;
}
*
* Returns: true if a is later than b
*/
-static inline int tod_after_eq(unsigned long long a, unsigned long long b)
+static inline int tod_after_eq(unsigned long a, unsigned long b)
{
if (MACHINE_HAS_SCC)
- return (long long) a >= (long long) b;
+ return (long) a >= (long) b;
return a >= b;
}
#include <vdso/datapage.h>
struct arch_vdso_data {
- __u64 tod_steering_delta;
+ __s64 tod_steering_delta;
__u64 tod_steering_end;
};
static int diag8_response(int cmdlen, char *response, int *rlen)
{
+ unsigned long _cmdlen = cmdlen | 0x40000000L;
+ unsigned long _rlen = *rlen;
register unsigned long reg2 asm ("2") = (addr_t) cpcmd_buf;
register unsigned long reg3 asm ("3") = (addr_t) response;
- register unsigned long reg4 asm ("4") = cmdlen | 0x40000000L;
- register unsigned long reg5 asm ("5") = *rlen;
+ register unsigned long reg4 asm ("4") = _cmdlen;
+ register unsigned long reg5 asm ("5") = _rlen;
asm volatile(
" diag %2,%0,0x8\n"
return in_stack(sp, info, STACK_TYPE_NODAT, top - THREAD_SIZE, top);
}
+static bool in_mcck_stack(unsigned long sp, struct stack_info *info)
+{
+ unsigned long frame_size, top;
+
+ frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
+ top = S390_lowcore.mcck_stack + frame_size;
+ return in_stack(sp, info, STACK_TYPE_MCCK, top - THREAD_SIZE, top);
+}
+
static bool in_restart_stack(unsigned long sp, struct stack_info *info)
{
unsigned long frame_size, top;
/* Check per-cpu stacks */
if (!in_irq_stack(sp, info) &&
!in_nodat_stack(sp, info) &&
- !in_restart_stack(sp, info))
+ !in_restart_stack(sp, info) &&
+ !in_mcck_stack(sp, info))
goto unknown;
recursion_check:
brasl %r14,.Lcleanup_sie_int
#endif
0: CHECK_STACK __LC_SAVE_AREA_ASYNC
- lgr %r11,%r15
aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE)
- stg %r11,__SF_BACKCHAIN(%r15)
j 2f
1: BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP
lctlg %c1,%c1,__LC_KERNEL_ASCE
lg %r15,__LC_KERNEL_STACK
- xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
-2: la %r11,STACK_FRAME_OVERHEAD(%r15)
+2: xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
+ la %r11,STACK_FRAME_OVERHEAD(%r15)
stmg %r0,%r7,__PT_R0(%r11)
# clear user controlled registers to prevent speculative use
xgr %r0,%r0
* Load idle PSW.
*/
ENTRY(psw_idle)
+ stg %r14,(__SF_GPRS+8*8)(%r15)
stg %r3,__SF_EMPTY(%r15)
larl %r1,psw_idle_exit
stg %r1,__SF_EMPTY+8(%r15)
void arch_cpu_idle(void)
{
struct s390_idle_data *idle = this_cpu_ptr(&s390_idle);
- unsigned long long idle_time;
+ unsigned long idle_time;
unsigned long psw_mask;
/* Wait for external, I/O or machine check interrupt. */
struct device_attribute *attr, char *buf)
{
struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
- unsigned long long idle_count;
+ unsigned long idle_count;
unsigned int seq;
do {
if (READ_ONCE(idle->clock_idle_enter))
idle_count++;
} while (read_seqcount_retry(&idle->seqcount, seq));
- return sprintf(buf, "%llu\n", idle_count);
+ return sprintf(buf, "%lu\n", idle_count);
}
DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL);
static ssize_t show_idle_time(struct device *dev,
struct device_attribute *attr, char *buf)
{
- unsigned long long now, idle_time, idle_enter, idle_exit, in_idle;
+ unsigned long now, idle_time, idle_enter, idle_exit, in_idle;
struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
unsigned int seq;
}
}
idle_time += in_idle;
- return sprintf(buf, "%llu\n", idle_time >> 12);
+ return sprintf(buf, "%lu\n", idle_time >> 12);
}
DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL);
u64 arch_cpu_idle_time(int cpu)
{
struct s390_idle_data *idle = &per_cpu(s390_idle, cpu);
- unsigned long long now, idle_enter, idle_exit, in_idle;
+ unsigned long now, idle_enter, idle_exit, in_idle;
unsigned int seq;
do {
memcpy(®s->int_code, &S390_lowcore.ext_cpu_addr, 4);
regs->int_parm = S390_lowcore.ext_params;
- regs->int_parm_long = *(unsigned long *)S390_lowcore.ext_params2;
+ regs->int_parm_long = S390_lowcore.ext_params2;
from_idle = !user_mode(regs) && regs->psw.addr == (unsigned long)psw_idle_exit;
if (from_idle)
case CPUMF_CTR_SET_MAX:
/* The counter could not be associated to a counter set */
return -EINVAL;
- };
+ }
/* Initialize for using the CPU-measurement counter facility */
if (!atomic_inc_not_zero(&num_events)) {
#include <asm/timex.h>
#include <asm/debug.h>
-#include <asm/perf_cpum_cf_diag.h>
+#include <asm/hwctrset.h>
#define CF_DIAG_CTRSET_DEF 0xfeef /* Counter set header mark */
-#define CF_DIAG_MIN_INTERVAL 60 /* Minimum counter set read */
/* interval in seconds */
-static unsigned long cf_diag_interval = CF_DIAG_MIN_INTERVAL;
static unsigned int cf_diag_cpu_speed;
static debug_info_t *cf_diag_dbg;
static struct cf_diag_ctrset {
unsigned long ctrset; /* Bit mask of counter set to read */
cpumask_t mask; /* CPU mask to read from */
- time64_t lastread; /* Epoch counter set last read */
} cf_diag_ctrset;
static void cf_diag_ctrset_clear(void)
{
struct cf_diag_call_on_cpu_parm p;
cpumask_var_t mask;
- time64_t now;
- int rc = 0;
+ int rc;
debug_sprintf_event(cf_diag_dbg, 5, "%s\n", __func__);
if (!alloc_cpumask_var(&mask, GFP_KERNEL))
return -ENOMEM;
- now = ktime_get_seconds();
- if (cf_diag_ctrset.lastread + cf_diag_interval > now) {
- debug_sprintf_event(cf_diag_dbg, 5, "%s now %lld "
- " lastread %lld\n", __func__, now,
- cf_diag_ctrset.lastread);
- rc = -EAGAIN;
- goto out;
- } else {
- cf_diag_ctrset.lastread = now;
- }
+
p.sets = cf_diag_ctrset.ctrset;
cpumask_and(mask, &cf_diag_ctrset.mask, cpu_online_mask);
on_each_cpu_mask(mask, cf_diag_cpu_read, &p, 1);
rc = cf_diag_all_copy(arg, mask);
-out:
free_cpumask_var(mask);
debug_sprintf_event(cf_diag_dbg, 5, "%s rc %d\n", __func__, rc);
return rc;
*/
static size_t cf_diag_needspace(unsigned int sets)
{
- struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
+ struct cpu_cf_events *cpuhw = get_cpu_ptr(&cpu_cf_events);
size_t bytes = 0;
int i;
sizeof(((struct s390_ctrset_cpudata *)0)->no_sets));
debug_sprintf_event(cf_diag_dbg, 5, "%s bytes %ld\n", __func__,
bytes);
+ put_cpu_ptr(&cpu_cf_events);
return bytes;
}
if (!new)
panic("Couldn't allocate machine check stack");
WRITE_ONCE(S390_lowcore.mcck_stack, new + STACK_INIT_OFFSET);
- memblock_free(old, THREAD_SIZE);
+ memblock_free_late(old, THREAD_SIZE);
return 0;
}
early_initcall(stack_realloc);
}
}
-/*
- * This function returns an error if it detects any unreliable features of the
- * stack. Otherwise it guarantees that the stack trace is reliable.
- *
- * If the task is not 'current', the caller *must* ensure the task is inactive.
- */
int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry,
void *cookie, struct task_struct *task)
{
unsigned char ptff_function_mask[16];
-static unsigned long long lpar_offset;
-static unsigned long long initial_leap_seconds;
-static unsigned long long tod_steering_end;
-static long long tod_steering_delta;
+static unsigned long lpar_offset;
+static unsigned long initial_leap_seconds;
+static unsigned long tod_steering_end;
+static long tod_steering_delta;
/*
* Get time offsets with PTFF
{
struct ptff_qto qto;
struct ptff_qui qui;
+ int cs;
/* Initialize TOD steering parameters */
tod_steering_end = tod_clock_base.tod;
- vdso_data->arch_data.tod_steering_end = tod_steering_end;
+ for (cs = 0; cs < CS_BASES; cs++)
+ vdso_data[cs].arch_data.tod_steering_end = tod_steering_end;
if (!test_facility(28))
return;
/* get initial leap seconds */
if (ptff_query(PTFF_QUI) && ptff(&qui, sizeof(qui), PTFF_QUI) == 0)
- initial_leap_seconds = (unsigned long long)
+ initial_leap_seconds = (unsigned long)
((long) qui.old_leap * 4096000000L);
}
static u64 read_tod_clock(struct clocksource *cs)
{
- unsigned long long now, adj;
+ unsigned long now, adj;
preempt_disable(); /* protect from changes to steering parameters */
now = get_tod_clock();
* Apply clock delta to the global data structures.
* This is called once on the CPU that performed the clock sync.
*/
-static void clock_sync_global(unsigned long long delta)
+static void clock_sync_global(unsigned long delta)
{
unsigned long now, adj;
struct ptff_qto qto;
+ int cs;
/* Fixup the monotonic sched clock. */
tod_clock_base.eitod += delta;
-(adj >> 15) : (adj >> 15);
tod_steering_delta += delta;
if ((abs(tod_steering_delta) >> 48) != 0)
- panic("TOD clock sync offset %lli is too large to drift\n",
+ panic("TOD clock sync offset %li is too large to drift\n",
tod_steering_delta);
tod_steering_end = now + (abs(tod_steering_delta) << 15);
- vdso_data->arch_data.tod_steering_end = tod_steering_end;
+ for (cs = 0; cs < CS_BASES; cs++) {
+ vdso_data[cs].arch_data.tod_steering_end = tod_steering_end;
+ vdso_data[cs].arch_data.tod_steering_delta = tod_steering_delta;
+ }
/* Update LPAR offset. */
if (ptff_query(PTFF_QTO) && ptff(&qto, sizeof(qto), PTFF_QTO) == 0)
* Apply clock delta to the per-CPU data structures of this CPU.
* This is called for each online CPU after the call to clock_sync_global.
*/
-static void clock_sync_local(unsigned long long delta)
+static void clock_sync_local(unsigned long delta)
{
/* Add the delta to the clock comparator. */
if (S390_lowcore.clock_comparator != clock_comparator_max) {
struct clock_sync_data {
atomic_t cpus;
int in_sync;
- unsigned long long clock_delta;
+ unsigned long clock_delta;
};
/*
static int stp_sync_clock(void *data)
{
struct clock_sync_data *sync = data;
- unsigned long long clock_delta, flags;
+ u64 clock_delta, flags;
static int first;
int rc;
mutex_lock(&stp_mutex);
if (stpinfo_valid())
- ret = sprintf(buf, "%016llx\n",
- *(unsigned long long *) stp_info.ctnid);
+ ret = sprintf(buf, "%016lx\n",
+ *(unsigned long *) stp_info.ctnid);
mutex_unlock(&stp_mutex);
return ret;
}
if (!stzi.lsoib.p)
return sprintf(buf, "0,0\n");
- return sprintf(buf, "%llu,%d\n",
+ return sprintf(buf, "%lu,%d\n",
tod_to_ns(stzi.lsoib.nlsout - TOD_UNIX_EPOCH) / NSEC_PER_SEC,
stzi.lsoib.nlso - stzi.lsoib.also);
}
}
info = info->next;
}
- if (cpumask_empty(&mask))
- cpumask_copy(&mask, cpumask_of(cpu));
break;
case TOPOLOGY_MODE_PACKAGE:
cpumask_copy(&mask, cpu_present_mask);
avg_steal = S390_lowcore.avg_steal_timer / 2;
if ((s64) steal > 0) {
S390_lowcore.steal_timer = 0;
- account_steal_time(steal);
+ account_steal_time(cputime_to_nsecs(steal));
avg_steal += steal;
}
S390_lowcore.avg_steal_timer = avg_steal;
/* already expired? */
if (cputm >> 63)
return 0;
- return min(sltime, tod_to_ns(cputm));
+ return min_t(u64, sltime, tod_to_ns(cputm));
}
} else if (cpu_timer_interrupts_enabled(vcpu)) {
sltime = kvm_s390_get_cpu_timer(vcpu);
}
EXPORT_SYMBOL_GPL(zpci_disable_device);
-void zpci_remove_device(struct zpci_dev *zdev)
+/* zpci_remove_device - Removes the given zdev from the PCI core
+ * @zdev: the zdev to be removed from the PCI core
+ * @set_error: if true the device's error state is set to permanent failure
+ *
+ * Sets a zPCI device to a configured but offline state; the zPCI
+ * device is still accessible through its hotplug slot and the zPCI
+ * API but is removed from the common code PCI bus, making it
+ * no longer available to drivers.
+ */
+void zpci_remove_device(struct zpci_dev *zdev, bool set_error)
{
struct zpci_bus *zbus = zdev->zbus;
struct pci_dev *pdev;
+ if (!zdev->zbus->bus)
+ return;
+
pdev = pci_get_slot(zbus->bus, zdev->devfn);
if (pdev) {
- if (pdev->is_virtfn)
- return zpci_iov_remove_virtfn(pdev, zdev->vfn);
+ if (set_error)
+ pdev->error_state = pci_channel_io_perm_failure;
+ if (pdev->is_virtfn) {
+ zpci_iov_remove_virtfn(pdev, zdev->vfn);
+ /* balance pci_get_slot */
+ pci_dev_put(pdev);
+ return;
+ }
pci_stop_and_remove_bus_device_locked(pdev);
+ /* balance pci_get_slot */
+ pci_dev_put(pdev);
}
}
struct zpci_dev *zdev = container_of(kref, struct zpci_dev, kref);
if (zdev->zbus->bus)
- zpci_remove_device(zdev);
+ zpci_remove_device(zdev, false);
switch (zdev->state) {
case ZPCI_FN_STATE_ONLINE:
static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf)
{
struct zpci_dev *zdev = get_zdev_by_fid(ccdf->fid);
- struct pci_dev *pdev = NULL;
enum zpci_state state;
+ struct pci_dev *pdev;
int ret;
- if (zdev && zdev->zbus->bus)
- pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn);
-
zpci_err("avail CCDF:\n");
zpci_err_hex(ccdf, sizeof(*ccdf));
case 0x0303: /* Deconfiguration requested */
if (!zdev)
break;
- if (pdev)
- zpci_remove_device(zdev);
+ zpci_remove_device(zdev, false);
ret = zpci_disable_device(zdev);
if (ret)
case 0x0304: /* Configured -> Standby|Reserved */
if (!zdev)
break;
- if (pdev) {
- /* Give the driver a hint that the function is
- * already unusable. */
- pdev->error_state = pci_channel_io_perm_failure;
- zpci_remove_device(zdev);
- }
+ /* Give the driver a hint that the function is
+ * already unusable.
+ */
+ zpci_remove_device(zdev, true);
zdev->fh = ccdf->fh;
zpci_disable_device(zdev);
CONFIG_NET_ETHERNET=y
CONFIG_MII=m
CONFIG_SUNLANCE=m
-CONFIG_HAPPYMEAL=m
+CONFIG_HAPPYMEAL=y
CONFIG_SUNGEM=m
CONFIG_SUNVNET=m
CONFIG_LDMVSW=m
CONFIG_CRC16=m
CONFIG_LIBCRC32C=m
CONFIG_VCC=m
-CONFIG_ATA=y
CONFIG_PATA_CMD64X=y
-CONFIG_HAPPYMEAL=y
CONFIG_IP_PNP=y
CONFIG_IP_PNP_DHCP=y
CONFIG_DEVTMPFS=y
#include <asm/ptrace.h>
#include <asm/processor.h>
-#include <asm/extable_64.h>
#include <asm/spitfire.h>
#include <asm/adi.h>
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __ASM_EXTABLE64_H
-#define __ASM_EXTABLE64_H
+#ifndef __ASM_EXTABLE_H
+#define __ASM_EXTABLE_H
/*
* The exception table consists of pairs of addresses: the first is the
* address of an instruction that is allowed to fault, and the second is
unsigned long fsr;
unsigned long fpqdepth;
struct fpq fpqueue[16];
- unsigned long flags;
mm_segment_t current_ds;
};
-#define SPARC_FLAG_KTHREAD 0x1 /* task is a kernel thread */
-#define SPARC_FLAG_UNALIGNED 0x2 /* is allowed to do unaligned accesses */
-
#define INIT_THREAD { \
- .flags = SPARC_FLAG_KTHREAD, \
.current_ds = KERNEL_DS, \
+ .kregs = (struct pt_regs *)(init_stack+THREAD_SIZE)-1 \
}
/* Do necessary setup to start up a newly executed thread. */
.task = &tsk, \
.current_ds = ASI_P, \
.preempt_count = INIT_PREEMPT_COUNT, \
+ .kregs = (struct pt_regs *)(init_stack+THREAD_SIZE)-1 \
}
/* how to get the thread information struct from C */
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef ___ASM_SPARC_UACCESS_H
#define ___ASM_SPARC_UACCESS_H
+
+#include <asm/extable.h>
+
#if defined(__sparc__) && defined(__arch64__)
#include <asm/uaccess_64.h>
#else
#include <asm/processor.h>
-#define ARCH_HAS_SORT_EXTABLE
-#define ARCH_HAS_SEARCH_EXTABLE
-
/* Sparc is not segmented, however we need to be able to fool access_ok()
* when doing system calls from kernel mode legitimately.
*
#define __access_ok(addr, size) (__user_ok((addr) & get_fs().seg, (size)))
#define access_ok(addr, size) __access_ok((unsigned long)(addr), size)
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue. No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path. This means when everything is well,
- * we don't even have to jump over them. Further, they do not intrude
- * on our cache or tlb entries.
- *
- * There is a special way how to put a range of potentially faulting
- * insns (like twenty ldd/std's with now intervening other instructions)
- * You specify address of first in insn and 0 in fixup and in the next
- * exception_table_entry you specify last potentially faulting insn + 1
- * and in fixup the routine which should handle the fault.
- * That fixup code will get
- * (faulting_insn_address - first_insn_in_the_range_address)/4
- * in %g2 (ie. index of the faulting instruction in the range).
- */
-
-struct exception_table_entry
-{
- unsigned long insn, fixup;
-};
-
-/* Returns 0 if exception not found and fixup otherwise. */
-unsigned long search_extables_range(unsigned long addr, unsigned long *g2);
-
/* Uh, these should become the main single-value transfer routines..
* They automatically use the right size if we just have the right
* pointer type..
unsigned long ret;
__asm__ __volatile__ (
- ".section __ex_table,#alloc\n\t"
- ".align 4\n\t"
- ".word 1f,3\n\t"
- ".previous\n\t"
"mov %2, %%o1\n"
- "1:\n\t"
"call __bzero\n\t"
" mov %1, %%o0\n\t"
"mov %%o0, %0\n"
#include <linux/string.h>
#include <asm/asi.h>
#include <asm/spitfire.h>
-#include <asm/extable_64.h>
#include <asm/processor.h>
/* I want a kernel stack NOW! */
set init_thread_union, %g1
- set (THREAD_SIZE - STACKFRAME_SZ), %g2
+ set (THREAD_SIZE - STACKFRAME_SZ - TRACEREG_SZ), %g2
add %g1, %g2, %sp
mov 0, %fp /* And for good luck */
wr %g0, ASI_P, %asi
mov 1, %g1
sllx %g1, THREAD_SHIFT, %g1
- sub %g1, (STACKFRAME_SZ + STACK_BIAS), %g1
+ sub %g1, (STACKFRAME_SZ + STACK_BIAS + TRACEREG_SZ), %g1
add %g6, %g1, %sp
/* Set per-cpu pointer initially to zero, this makes
clear_thread_flag(TIF_USEDFPU);
#endif
}
-
- /* This task is no longer a kernel thread. */
- if (current->thread.flags & SPARC_FLAG_KTHREAD) {
- current->thread.flags &= ~SPARC_FLAG_KTHREAD;
-
- /* We must fixup kregs as well. */
- /* XXX This was not fixed for ti for a while, worked. Unused? */
- current->thread.kregs = (struct pt_regs *)
- (task_stack_page(current) + (THREAD_SIZE - TRACEREG_SZ));
- }
}
static inline struct sparc_stackf __user *
extern int nwindows;
unsigned long psr;
memset(new_stack, 0, STACKFRAME_SZ + TRACEREG_SZ);
- p->thread.flags |= SPARC_FLAG_KTHREAD;
p->thread.current_ds = KERNEL_DS;
ti->kpc = (((unsigned long) ret_from_kernel_thread) - 0x8);
childregs->u_regs[UREG_G1] = sp; /* function */
}
memcpy(new_stack, (char *)regs - STACKFRAME_SZ, STACKFRAME_SZ + TRACEREG_SZ);
childregs->u_regs[UREG_FP] = sp;
- p->thread.flags &= ~SPARC_FLAG_KTHREAD;
p->thread.current_ds = USER_DS;
ti->kpc = (((unsigned long) ret_from_fork) - 0x8);
ti->kpsr = current->thread.fork_kpsr | PSR_PIL;
}
struct tt_entry *sparc_ttable;
-static struct pt_regs fake_swapper_regs;
/* Called from head_32.S - before we have setup anything
* in the kernel. Be very careful with what you do here.
(*(linux_dbvec->teach_debugger))();
}
- init_task.thread.kregs = &fake_swapper_regs;
-
/* Run-time patch instructions to match the cpu model */
per_cpu_patch();
char reboot_command[COMMAND_LINE_SIZE];
-static struct pt_regs fake_swapper_regs = { { 0, }, 0, 0, 0, 0 };
-
static void __init per_cpu_patch(void)
{
struct cpuid_patch_entry *p;
rd_image_start = ram_flags & RAMDISK_IMAGE_START_MASK;
#endif
- task_thread_info(&init_task)->kregs = &fake_swapper_regs;
-
#ifdef CONFIG_IP_PNP
if (!ic_set_manually) {
phandle chosen = prom_finddevice("/chosen");
asi = (regs->tstate >> 24); /* saved %asi */
else
asi = (insn >> 5); /* immediate asi */
- if ((asi & 0xf2) == ASI_PNF) {
- if (insn & 0x1000000) { /* op3[5:4]=3 */
- handle_ldf_stq(insn, regs);
- return true;
- } else if (insn & 0x200000) { /* op3[2], stores */
+ if ((asi & 0xf6) == ASI_PNF) {
+ if (insn & 0x200000) /* op3[2], stores */
return false;
- }
- handle_ld_nf(insn, regs);
+ if (insn & 0x1000000) /* op3[5:4]=3 (fp) */
+ handle_ldf_stq(insn, regs);
+ else
+ handle_ld_nf(insn, regs);
return true;
}
}
#include <linux/uaccess.h>
#include <linux/smp.h>
#include <linux/perf_event.h>
+#include <linux/extable.h>
#include <asm/setup.h>
static void kernel_mna_trap_fault(struct pt_regs *regs, unsigned int insn)
{
- unsigned long g2 = regs->u_regs [UREG_G2];
- unsigned long fixup = search_extables_range(regs->pc, &g2);
+ const struct exception_table_entry *entry;
- if (!fixup) {
+ entry = search_exception_tables(regs->pc);
+ if (!entry) {
unsigned long address = compute_effective_address(regs, insn);
if(address < PAGE_SIZE) {
printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference in mna handler");
die_if_kernel("Oops", regs);
/* Not reached */
}
- regs->pc = fixup;
+ regs->pc = entry->fixup;
regs->npc = regs->pc + 4;
- regs->u_regs [UREG_G2] = g2;
}
asmlinkage void kernel_unaligned_trap(struct pt_regs *regs, unsigned int insn)
}
}
-static inline int ok_for_user(struct pt_regs *regs, unsigned int insn,
- enum direction dir)
-{
- unsigned int reg;
- int size = ((insn >> 19) & 3) == 3 ? 8 : 4;
-
- if ((regs->pc | regs->npc) & 3)
- return 0;
-
- /* Must access_ok() in all the necessary places. */
-#define WINREG_ADDR(regnum) \
- ((void __user *)(((unsigned long *)regs->u_regs[UREG_FP])+(regnum)))
-
- reg = (insn >> 25) & 0x1f;
- if (reg >= 16) {
- if (!access_ok(WINREG_ADDR(reg - 16), size))
- return -EFAULT;
- }
- reg = (insn >> 14) & 0x1f;
- if (reg >= 16) {
- if (!access_ok(WINREG_ADDR(reg - 16), size))
- return -EFAULT;
- }
- if (!(insn & 0x2000)) {
- reg = (insn & 0x1f);
- if (reg >= 16) {
- if (!access_ok(WINREG_ADDR(reg - 16), size))
- return -EFAULT;
- }
- }
-#undef WINREG_ADDR
- return 0;
-}
-
-static void user_mna_trap_fault(struct pt_regs *regs, unsigned int insn)
+asmlinkage void user_unaligned_trap(struct pt_regs *regs, unsigned int insn)
{
send_sig_fault(SIGBUS, BUS_ADRALN,
(void __user *)safe_compute_effective_address(regs, insn),
0, current);
}
-
-asmlinkage void user_unaligned_trap(struct pt_regs *regs, unsigned int insn)
-{
- enum direction dir;
-
- if(!(current->thread.flags & SPARC_FLAG_UNALIGNED) ||
- (((insn >> 30) & 3) != 3))
- goto kill_user;
- dir = decode_direction(insn);
- if(!ok_for_user(regs, insn, dir)) {
- goto kill_user;
- } else {
- int err, size = decode_access_size(insn);
- unsigned long addr;
-
- if(floating_point_load_or_store_p(insn)) {
- printk("User FPU load/store unaligned unsupported.\n");
- goto kill_user;
- }
-
- addr = compute_effective_address(regs, insn);
- perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr);
- switch(dir) {
- case load:
- err = do_int_load(fetch_reg_addr(((insn>>25)&0x1f),
- regs),
- size, (unsigned long *) addr,
- decode_signedness(insn));
- break;
-
- case store:
- err = do_int_store(((insn>>25)&0x1f), size,
- (unsigned long *) addr, regs);
- break;
-
- case both:
- /*
- * This was supported in 2.4. However, we question
- * the value of SWAP instruction across word boundaries.
- */
- printk("Unaligned SWAP unsupported.\n");
- err = -EFAULT;
- break;
-
- default:
- unaligned_panic("Impossible user unaligned trap.");
- goto out;
- }
- if (err)
- goto kill_user;
- else
- advance(regs);
- goto out;
- }
-
-kill_user:
- user_mna_trap_fault(regs, insn);
-out:
- ;
-}
.text; \
.align 4
-#define EXT(start,end) \
- .section __ex_table,ALLOC; \
- .align 4; \
- .word start, 0, end, cc_fault; \
- .text; \
- .align 4
-
/* This aligned version executes typically in 8.5 superscalar cycles, this
* is the best I can do. I say 8.5 because the final add will pair with
* the next ldd in the main unrolled loop. Thus the pipe is always full.
* please check the fixup code below as well.
*/
#define CSUMCOPY_BIGCHUNK_ALIGNED(src, dst, sum, off, t0, t1, t2, t3, t4, t5, t6, t7) \
- ldd [src + off + 0x00], t0; \
- ldd [src + off + 0x08], t2; \
+ EX(ldd [src + off + 0x00], t0); \
+ EX(ldd [src + off + 0x08], t2); \
addxcc t0, sum, sum; \
- ldd [src + off + 0x10], t4; \
+ EX(ldd [src + off + 0x10], t4); \
addxcc t1, sum, sum; \
- ldd [src + off + 0x18], t6; \
+ EX(ldd [src + off + 0x18], t6); \
addxcc t2, sum, sum; \
- std t0, [dst + off + 0x00]; \
+ EX(std t0, [dst + off + 0x00]); \
addxcc t3, sum, sum; \
- std t2, [dst + off + 0x08]; \
+ EX(std t2, [dst + off + 0x08]); \
addxcc t4, sum, sum; \
- std t4, [dst + off + 0x10]; \
+ EX(std t4, [dst + off + 0x10]); \
addxcc t5, sum, sum; \
- std t6, [dst + off + 0x18]; \
+ EX(std t6, [dst + off + 0x18]); \
addxcc t6, sum, sum; \
addxcc t7, sum, sum;
* Viking MXCC into streaming mode. Ho hum...
*/
#define CSUMCOPY_BIGCHUNK(src, dst, sum, off, t0, t1, t2, t3, t4, t5, t6, t7) \
- ldd [src + off + 0x00], t0; \
- ldd [src + off + 0x08], t2; \
- ldd [src + off + 0x10], t4; \
- ldd [src + off + 0x18], t6; \
- st t0, [dst + off + 0x00]; \
+ EX(ldd [src + off + 0x00], t0); \
+ EX(ldd [src + off + 0x08], t2); \
+ EX(ldd [src + off + 0x10], t4); \
+ EX(ldd [src + off + 0x18], t6); \
+ EX(st t0, [dst + off + 0x00]); \
addxcc t0, sum, sum; \
- st t1, [dst + off + 0x04]; \
+ EX(st t1, [dst + off + 0x04]); \
addxcc t1, sum, sum; \
- st t2, [dst + off + 0x08]; \
+ EX(st t2, [dst + off + 0x08]); \
addxcc t2, sum, sum; \
- st t3, [dst + off + 0x0c]; \
+ EX(st t3, [dst + off + 0x0c]); \
addxcc t3, sum, sum; \
- st t4, [dst + off + 0x10]; \
+ EX(st t4, [dst + off + 0x10]); \
addxcc t4, sum, sum; \
- st t5, [dst + off + 0x14]; \
+ EX(st t5, [dst + off + 0x14]); \
addxcc t5, sum, sum; \
- st t6, [dst + off + 0x18]; \
+ EX(st t6, [dst + off + 0x18]); \
addxcc t6, sum, sum; \
- st t7, [dst + off + 0x1c]; \
+ EX(st t7, [dst + off + 0x1c]); \
addxcc t7, sum, sum;
/* Yuck, 6 superscalar cycles... */
#define CSUMCOPY_LASTCHUNK(src, dst, sum, off, t0, t1, t2, t3) \
- ldd [src - off - 0x08], t0; \
- ldd [src - off - 0x00], t2; \
+ EX(ldd [src - off - 0x08], t0); \
+ EX(ldd [src - off - 0x00], t2); \
addxcc t0, sum, sum; \
- st t0, [dst - off - 0x08]; \
+ EX(st t0, [dst - off - 0x08]); \
addxcc t1, sum, sum; \
- st t1, [dst - off - 0x04]; \
+ EX(st t1, [dst - off - 0x04]); \
addxcc t2, sum, sum; \
- st t2, [dst - off - 0x00]; \
+ EX(st t2, [dst - off - 0x00]); \
addxcc t3, sum, sum; \
- st t3, [dst - off + 0x04];
+ EX(st t3, [dst - off + 0x04]);
/* Handle the end cruft code out of band for better cache patterns. */
cc_end_cruft:
CSUMCOPY_BIGCHUNK(%o0,%o1,%g7,0x20,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
CSUMCOPY_BIGCHUNK(%o0,%o1,%g7,0x40,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
CSUMCOPY_BIGCHUNK(%o0,%o1,%g7,0x60,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
-10: EXT(5b, 10b) ! note for exception handling
sub %g1, 128, %g1 ! detract from length
addx %g0, %g7, %g7 ! add in last carry bit
andcc %g1, 0xffffff80, %g0 ! more to csum?
CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x28,%g2,%g3,%g4,%g5)
CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x18,%g2,%g3,%g4,%g5)
CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x08,%g2,%g3,%g4,%g5)
-12: EXT(cctbl, 12b) ! note for exception table handling
- addx %g0, %g7, %g7
+12: addx %g0, %g7, %g7
andcc %o3, 0xf, %g0 ! check for low bits set
ccte: bne cc_end_cruft ! something left, handle it out of band
andcc %o3, 8, %g0 ! begin checks for that code
CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x20,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x40,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x60,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
-11: EXT(ccdbl, 11b) ! note for exception table handling
sub %g1, 128, %g1 ! detract from length
addx %g0, %g7, %g7 ! add in last carry bit
andcc %g1, 0xffffff80, %g0 ! more to csum?
/* Work around cpp -rob */
#define ALLOC #alloc
#define EXECINSTR #execinstr
+
+#define EX_ENTRY(l1, l2) \
+ .section __ex_table,ALLOC; \
+ .align 4; \
+ .word l1, l2; \
+ .text;
+
#define EX(x,y,a,b) \
98: x,y; \
.section .fixup,ALLOC,EXECINSTR; \
.align 4; \
-99: ba fixupretl; \
- a, b, %g3; \
- .section __ex_table,ALLOC; \
- .align 4; \
- .word 98b, 99b; \
- .text; \
- .align 4
+99: retl; \
+ a, b, %o0; \
+ EX_ENTRY(98b, 99b)
#define EX2(x,y,c,d,e,a,b) \
98: x,y; \
.section .fixup,ALLOC,EXECINSTR; \
.align 4; \
99: c, d, e; \
- ba fixupretl; \
- a, b, %g3; \
- .section __ex_table,ALLOC; \
- .align 4; \
- .word 98b, 99b; \
- .text; \
- .align 4
+ retl; \
+ a, b, %o0; \
+ EX_ENTRY(98b, 99b)
#define EXO2(x,y) \
98: x, y; \
- .section __ex_table,ALLOC; \
- .align 4; \
- .word 98b, 97f; \
- .text; \
- .align 4
+ EX_ENTRY(98b, 97f)
-#define EXT(start,end,handler) \
- .section __ex_table,ALLOC; \
- .align 4; \
- .word start, 0, end, handler; \
- .text; \
- .align 4
+#define LD(insn, src, offset, reg, label) \
+98: insn [%src + (offset)], %reg; \
+ .section .fixup,ALLOC,EXECINSTR; \
+99: ba label; \
+ mov offset, %g5; \
+ EX_ENTRY(98b, 99b)
-/* Please do not change following macros unless you change logic used
- * in .fixup at the end of this file as well
- */
+#define ST(insn, dst, offset, reg, label) \
+98: insn %reg, [%dst + (offset)]; \
+ .section .fixup,ALLOC,EXECINSTR; \
+99: ba label; \
+ mov offset, %g5; \
+ EX_ENTRY(98b, 99b)
/* Both these macros have to start with exactly the same insn */
+/* left: g7 + (g1 % 128) - offset */
#define MOVE_BIGCHUNK(src, dst, offset, t0, t1, t2, t3, t4, t5, t6, t7) \
- ldd [%src + (offset) + 0x00], %t0; \
- ldd [%src + (offset) + 0x08], %t2; \
- ldd [%src + (offset) + 0x10], %t4; \
- ldd [%src + (offset) + 0x18], %t6; \
- st %t0, [%dst + (offset) + 0x00]; \
- st %t1, [%dst + (offset) + 0x04]; \
- st %t2, [%dst + (offset) + 0x08]; \
- st %t3, [%dst + (offset) + 0x0c]; \
- st %t4, [%dst + (offset) + 0x10]; \
- st %t5, [%dst + (offset) + 0x14]; \
- st %t6, [%dst + (offset) + 0x18]; \
- st %t7, [%dst + (offset) + 0x1c];
-
+ LD(ldd, src, offset + 0x00, t0, bigchunk_fault) \
+ LD(ldd, src, offset + 0x08, t2, bigchunk_fault) \
+ LD(ldd, src, offset + 0x10, t4, bigchunk_fault) \
+ LD(ldd, src, offset + 0x18, t6, bigchunk_fault) \
+ ST(st, dst, offset + 0x00, t0, bigchunk_fault) \
+ ST(st, dst, offset + 0x04, t1, bigchunk_fault) \
+ ST(st, dst, offset + 0x08, t2, bigchunk_fault) \
+ ST(st, dst, offset + 0x0c, t3, bigchunk_fault) \
+ ST(st, dst, offset + 0x10, t4, bigchunk_fault) \
+ ST(st, dst, offset + 0x14, t5, bigchunk_fault) \
+ ST(st, dst, offset + 0x18, t6, bigchunk_fault) \
+ ST(st, dst, offset + 0x1c, t7, bigchunk_fault)
+
+/* left: g7 + (g1 % 128) - offset */
#define MOVE_BIGALIGNCHUNK(src, dst, offset, t0, t1, t2, t3, t4, t5, t6, t7) \
- ldd [%src + (offset) + 0x00], %t0; \
- ldd [%src + (offset) + 0x08], %t2; \
- ldd [%src + (offset) + 0x10], %t4; \
- ldd [%src + (offset) + 0x18], %t6; \
- std %t0, [%dst + (offset) + 0x00]; \
- std %t2, [%dst + (offset) + 0x08]; \
- std %t4, [%dst + (offset) + 0x10]; \
- std %t6, [%dst + (offset) + 0x18];
+ LD(ldd, src, offset + 0x00, t0, bigchunk_fault) \
+ LD(ldd, src, offset + 0x08, t2, bigchunk_fault) \
+ LD(ldd, src, offset + 0x10, t4, bigchunk_fault) \
+ LD(ldd, src, offset + 0x18, t6, bigchunk_fault) \
+ ST(std, dst, offset + 0x00, t0, bigchunk_fault) \
+ ST(std, dst, offset + 0x08, t2, bigchunk_fault) \
+ ST(std, dst, offset + 0x10, t4, bigchunk_fault) \
+ ST(std, dst, offset + 0x18, t6, bigchunk_fault)
+ .section .fixup,#alloc,#execinstr
+bigchunk_fault:
+ sub %g7, %g5, %o0
+ and %g1, 127, %g1
+ retl
+ add %o0, %g1, %o0
+
+/* left: offset + 16 + (g1 % 16) */
#define MOVE_LASTCHUNK(src, dst, offset, t0, t1, t2, t3) \
- ldd [%src - (offset) - 0x10], %t0; \
- ldd [%src - (offset) - 0x08], %t2; \
- st %t0, [%dst - (offset) - 0x10]; \
- st %t1, [%dst - (offset) - 0x0c]; \
- st %t2, [%dst - (offset) - 0x08]; \
- st %t3, [%dst - (offset) - 0x04];
+ LD(ldd, src, -(offset + 0x10), t0, lastchunk_fault) \
+ LD(ldd, src, -(offset + 0x08), t2, lastchunk_fault) \
+ ST(st, dst, -(offset + 0x10), t0, lastchunk_fault) \
+ ST(st, dst, -(offset + 0x0c), t1, lastchunk_fault) \
+ ST(st, dst, -(offset + 0x08), t2, lastchunk_fault) \
+ ST(st, dst, -(offset + 0x04), t3, lastchunk_fault)
-#define MOVE_HALFCHUNK(src, dst, offset, t0, t1, t2, t3) \
- lduh [%src + (offset) + 0x00], %t0; \
- lduh [%src + (offset) + 0x02], %t1; \
- lduh [%src + (offset) + 0x04], %t2; \
- lduh [%src + (offset) + 0x06], %t3; \
- sth %t0, [%dst + (offset) + 0x00]; \
- sth %t1, [%dst + (offset) + 0x02]; \
- sth %t2, [%dst + (offset) + 0x04]; \
- sth %t3, [%dst + (offset) + 0x06];
+ .section .fixup,#alloc,#execinstr
+lastchunk_fault:
+ and %g1, 15, %g1
+ retl
+ sub %g1, %g5, %o0
+/* left: o3 + (o2 % 16) - offset */
+#define MOVE_HALFCHUNK(src, dst, offset, t0, t1, t2, t3) \
+ LD(lduh, src, offset + 0x00, t0, halfchunk_fault) \
+ LD(lduh, src, offset + 0x02, t1, halfchunk_fault) \
+ LD(lduh, src, offset + 0x04, t2, halfchunk_fault) \
+ LD(lduh, src, offset + 0x06, t3, halfchunk_fault) \
+ ST(sth, dst, offset + 0x00, t0, halfchunk_fault) \
+ ST(sth, dst, offset + 0x02, t1, halfchunk_fault) \
+ ST(sth, dst, offset + 0x04, t2, halfchunk_fault) \
+ ST(sth, dst, offset + 0x06, t3, halfchunk_fault)
+
+/* left: o3 + (o2 % 16) + offset + 2 */
#define MOVE_SHORTCHUNK(src, dst, offset, t0, t1) \
- ldub [%src - (offset) - 0x02], %t0; \
- ldub [%src - (offset) - 0x01], %t1; \
- stb %t0, [%dst - (offset) - 0x02]; \
- stb %t1, [%dst - (offset) - 0x01];
+ LD(ldub, src, -(offset + 0x02), t0, halfchunk_fault) \
+ LD(ldub, src, -(offset + 0x01), t1, halfchunk_fault) \
+ ST(stb, dst, -(offset + 0x02), t0, halfchunk_fault) \
+ ST(stb, dst, -(offset + 0x01), t1, halfchunk_fault)
+
+ .section .fixup,#alloc,#execinstr
+halfchunk_fault:
+ and %o2, 15, %o2
+ sub %o3, %g5, %o3
+ retl
+ add %o2, %o3, %o0
+
+/* left: offset + 2 + (o2 % 2) */
+#define MOVE_LAST_SHORTCHUNK(src, dst, offset, t0, t1) \
+ LD(ldub, src, -(offset + 0x02), t0, last_shortchunk_fault) \
+ LD(ldub, src, -(offset + 0x01), t1, last_shortchunk_fault) \
+ ST(stb, dst, -(offset + 0x02), t0, last_shortchunk_fault) \
+ ST(stb, dst, -(offset + 0x01), t1, last_shortchunk_fault)
+
+ .section .fixup,#alloc,#execinstr
+last_shortchunk_fault:
+ and %o2, 1, %o2
+ retl
+ sub %o2, %g5, %o0
.text
.align 4
MOVE_BIGCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5)
MOVE_BIGCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5)
MOVE_BIGCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5)
-80:
- EXT(5b, 80b, 50f)
subcc %g7, 128, %g7
add %o1, 128, %o1
bne 5b
jmpl %o5 + %lo(copy_user_table_end), %g0
add %o0, %g7, %o0
-copy_user_table:
MOVE_LASTCHUNK(o1, o0, 0x60, g2, g3, g4, g5)
MOVE_LASTCHUNK(o1, o0, 0x50, g2, g3, g4, g5)
MOVE_LASTCHUNK(o1, o0, 0x40, g2, g3, g4, g5)
MOVE_LASTCHUNK(o1, o0, 0x10, g2, g3, g4, g5)
MOVE_LASTCHUNK(o1, o0, 0x00, g2, g3, g4, g5)
copy_user_table_end:
- EXT(copy_user_table, copy_user_table_end, 51f)
be copy_user_last7
andcc %g1, 4, %g0
MOVE_BIGALIGNCHUNK(o1, o0, 0x20, o2, o3, o4, o5, g2, g3, g4, g5)
MOVE_BIGALIGNCHUNK(o1, o0, 0x40, o2, o3, o4, o5, g2, g3, g4, g5)
MOVE_BIGALIGNCHUNK(o1, o0, 0x60, o2, o3, o4, o5, g2, g3, g4, g5)
-81:
- EXT(ldd_std, 81b, 52f)
subcc %g7, 128, %g7
add %o1, 128, %o1
bne ldd_std
10:
MOVE_HALFCHUNK(o1, o0, 0x00, g2, g3, g4, g5)
MOVE_HALFCHUNK(o1, o0, 0x08, g2, g3, g4, g5)
-82:
- EXT(10b, 82b, 53f)
subcc %o3, 0x10, %o3
add %o1, 0x10, %o1
bne 10b
MOVE_SHORTCHUNK(o1, o0, -0x0c, g2, g3)
MOVE_SHORTCHUNK(o1, o0, -0x0e, g2, g3)
MOVE_SHORTCHUNK(o1, o0, -0x10, g2, g3)
-83:
- EXT(byte_chunk, 83b, 54f)
subcc %o3, 0x10, %o3
add %o1, 0x10, %o1
bne byte_chunk
add %o1, %o3, %o1
jmpl %o5 + %lo(short_table_end), %g0
andcc %o2, 1, %g0
-84:
- MOVE_SHORTCHUNK(o1, o0, 0x0c, g2, g3)
- MOVE_SHORTCHUNK(o1, o0, 0x0a, g2, g3)
- MOVE_SHORTCHUNK(o1, o0, 0x08, g2, g3)
- MOVE_SHORTCHUNK(o1, o0, 0x06, g2, g3)
- MOVE_SHORTCHUNK(o1, o0, 0x04, g2, g3)
- MOVE_SHORTCHUNK(o1, o0, 0x02, g2, g3)
- MOVE_SHORTCHUNK(o1, o0, 0x00, g2, g3)
+ MOVE_LAST_SHORTCHUNK(o1, o0, 0x0c, g2, g3)
+ MOVE_LAST_SHORTCHUNK(o1, o0, 0x0a, g2, g3)
+ MOVE_LAST_SHORTCHUNK(o1, o0, 0x08, g2, g3)
+ MOVE_LAST_SHORTCHUNK(o1, o0, 0x06, g2, g3)
+ MOVE_LAST_SHORTCHUNK(o1, o0, 0x04, g2, g3)
+ MOVE_LAST_SHORTCHUNK(o1, o0, 0x02, g2, g3)
+ MOVE_LAST_SHORTCHUNK(o1, o0, 0x00, g2, g3)
short_table_end:
- EXT(84b, short_table_end, 55f)
be 1f
nop
EX(ldub [%o1], %g2, add %g0, 1)
.section .fixup,#alloc,#execinstr
.align 4
97:
- mov %o2, %g3
-fixupretl:
retl
- mov %g3, %o0
-
-/* exception routine sets %g2 to (broken_insn - first_insn)>>2 */
-50:
-/* This magic counts how many bytes are left when crash in MOVE_BIGCHUNK
- * happens. This is derived from the amount ldd reads, st stores, etc.
- * x = g2 % 12;
- * g3 = g1 + g7 - ((g2 / 12) * 32 + (x < 4) ? 0 : (x - 4) * 4);
- * o0 += (g2 / 12) * 32;
- */
- cmp %g2, 12
- add %o0, %g7, %o0
- bcs 1f
- cmp %g2, 24
- bcs 2f
- cmp %g2, 36
- bcs 3f
- nop
- sub %g2, 12, %g2
- sub %g7, 32, %g7
-3: sub %g2, 12, %g2
- sub %g7, 32, %g7
-2: sub %g2, 12, %g2
- sub %g7, 32, %g7
-1: cmp %g2, 4
- bcs,a 60f
- clr %g2
- sub %g2, 4, %g2
- sll %g2, 2, %g2
-60: and %g1, 0x7f, %g3
- sub %o0, %g7, %o0
- add %g3, %g7, %g3
- ba fixupretl
- sub %g3, %g2, %g3
-51:
-/* i = 41 - g2; j = i % 6;
- * g3 = (g1 & 15) + (i / 6) * 16 + (j < 4) ? (j + 1) * 4 : 16;
- * o0 -= (i / 6) * 16 + 16;
- */
- neg %g2
- and %g1, 0xf, %g1
- add %g2, 41, %g2
- add %o0, %g1, %o0
-1: cmp %g2, 6
- bcs,a 2f
- cmp %g2, 4
- add %g1, 16, %g1
- b 1b
- sub %g2, 6, %g2
-2: bcc,a 2f
- mov 16, %g2
- inc %g2
- sll %g2, 2, %g2
-2: add %g1, %g2, %g3
- ba fixupretl
- sub %o0, %g3, %o0
-52:
-/* g3 = g1 + g7 - (g2 / 8) * 32 + (g2 & 4) ? (g2 & 3) * 8 : 0;
- o0 += (g2 / 8) * 32 */
- andn %g2, 7, %g4
- add %o0, %g7, %o0
- andcc %g2, 4, %g0
- and %g2, 3, %g2
- sll %g4, 2, %g4
- sll %g2, 3, %g2
- bne 60b
- sub %g7, %g4, %g7
- ba 60b
- clr %g2
-53:
-/* g3 = o3 + (o2 & 15) - (g2 & 8) - (g2 & 4) ? (g2 & 3) * 2 : 0;
- o0 += (g2 & 8) */
- and %g2, 3, %g4
- andcc %g2, 4, %g0
- and %g2, 8, %g2
- sll %g4, 1, %g4
- be 1f
- add %o0, %g2, %o0
- add %g2, %g4, %g2
-1: and %o2, 0xf, %g3
- add %g3, %o3, %g3
- ba fixupretl
- sub %g3, %g2, %g3
-54:
-/* g3 = o3 + (o2 & 15) - (g2 / 4) * 2 - (g2 & 2) ? (g2 & 1) : 0;
- o0 += (g2 / 4) * 2 */
- srl %g2, 2, %o4
- and %g2, 1, %o5
- srl %g2, 1, %g2
- add %o4, %o4, %o4
- and %o5, %g2, %o5
- and %o2, 0xf, %o2
- add %o0, %o4, %o0
- sub %o3, %o5, %o3
- sub %o2, %o4, %o2
- ba fixupretl
- add %o2, %o3, %g3
-55:
-/* i = 27 - g2;
- g3 = (o2 & 1) + i / 4 * 2 + !(i & 3);
- o0 -= i / 4 * 2 + 1 */
- neg %g2
- and %o2, 1, %o2
- add %g2, 27, %g2
- srl %g2, 2, %o5
- andcc %g2, 3, %g0
- mov 1, %g2
- add %o5, %o5, %o5
- be,a 1f
- clr %g2
-1: add %g2, %o5, %g3
- sub %o0, %g3, %o0
- ba fixupretl
- add %g3, %o2, %g3
+ mov %o2, %o0
.globl __copy_user_end
__copy_user_end:
98: x,y; \
.section .fixup,ALLOC,EXECINSTR; \
.align 4; \
-99: ba 30f; \
+99: retl; \
a, b, %o0; \
.section __ex_table,ALLOC; \
.align 4; \
.text; \
.align 4
-#define EXT(start,end,handler) \
+#define STORE(source, base, offset, n) \
+98: std source, [base + offset + n]; \
+ .section .fixup,ALLOC,EXECINSTR; \
+ .align 4; \
+99: ba 30f; \
+ sub %o3, n - offset, %o3; \
.section __ex_table,ALLOC; \
.align 4; \
- .word start, 0, end, handler; \
+ .word 98b, 99b; \
.text; \
- .align 4
+ .align 4;
+
+#define STORE_LAST(source, base, offset, n) \
+ EX(std source, [base - offset - n], \
+ add %o1, offset + n);
/* Please don't change these macros, unless you change the logic
* in the .fixup section below as well.
* Store 64 bytes at (BASE + OFFSET) using value SOURCE. */
-#define ZERO_BIG_BLOCK(base, offset, source) \
- std source, [base + offset + 0x00]; \
- std source, [base + offset + 0x08]; \
- std source, [base + offset + 0x10]; \
- std source, [base + offset + 0x18]; \
- std source, [base + offset + 0x20]; \
- std source, [base + offset + 0x28]; \
- std source, [base + offset + 0x30]; \
- std source, [base + offset + 0x38];
+#define ZERO_BIG_BLOCK(base, offset, source) \
+ STORE(source, base, offset, 0x00); \
+ STORE(source, base, offset, 0x08); \
+ STORE(source, base, offset, 0x10); \
+ STORE(source, base, offset, 0x18); \
+ STORE(source, base, offset, 0x20); \
+ STORE(source, base, offset, 0x28); \
+ STORE(source, base, offset, 0x30); \
+ STORE(source, base, offset, 0x38);
#define ZERO_LAST_BLOCKS(base, offset, source) \
- std source, [base - offset - 0x38]; \
- std source, [base - offset - 0x30]; \
- std source, [base - offset - 0x28]; \
- std source, [base - offset - 0x20]; \
- std source, [base - offset - 0x18]; \
- std source, [base - offset - 0x10]; \
- std source, [base - offset - 0x08]; \
- std source, [base - offset - 0x00];
+ STORE_LAST(source, base, offset, 0x38); \
+ STORE_LAST(source, base, offset, 0x30); \
+ STORE_LAST(source, base, offset, 0x28); \
+ STORE_LAST(source, base, offset, 0x20); \
+ STORE_LAST(source, base, offset, 0x18); \
+ STORE_LAST(source, base, offset, 0x10); \
+ STORE_LAST(source, base, offset, 0x08); \
+ STORE_LAST(source, base, offset, 0x00);
.text
.align 4
.globl memset
EXPORT_SYMBOL(__bzero)
EXPORT_SYMBOL(memset)
- .globl __memset_start, __memset_end
-__memset_start:
memset:
mov %o0, %g1
mov 1, %g4
ZERO_BIG_BLOCK(%o0, 0x00, %g2)
subcc %o3, 128, %o3
ZERO_BIG_BLOCK(%o0, 0x40, %g2)
-11:
- EXT(10b, 11b, 20f)
bne 10b
add %o0, 128, %o0
jmp %o4
add %o0, %o2, %o0
-12:
ZERO_LAST_BLOCKS(%o0, 0x48, %g2)
ZERO_LAST_BLOCKS(%o0, 0x08, %g2)
13:
- EXT(12b, 13b, 21f)
be 8f
andcc %o1, 4, %g0
5:
retl
clr %o0
-__memset_end:
.section .fixup,#alloc,#execinstr
.align 4
-20:
- cmp %g2, 8
- bleu 1f
- and %o1, 0x7f, %o1
- sub %g2, 9, %g2
- add %o3, 64, %o3
-1:
- sll %g2, 3, %g2
- add %o3, %o1, %o0
- b 30f
- sub %o0, %g2, %o0
-21:
- mov 8, %o0
- and %o1, 7, %o1
- sub %o0, %g2, %o0
- sll %o0, 3, %o0
- b 30f
- add %o0, %o1, %o0
30:
-/* %o4 is faulting address, %o5 is %pc where fault occurred */
- save %sp, -104, %sp
- mov %i5, %o0
- mov %i7, %o1
- call lookup_fault
- mov %i4, %o2
- ret
- restore
+ and %o1, 0x7f, %o1
+ retl
+ add %o3, %o1, %o0
.globl __bzero_end
__bzero_end:
obj-$(CONFIG_SPARC64) += ultra.o tlb.o tsb.o
obj-y += fault_$(BITS).o
obj-y += init_$(BITS).o
-obj-$(CONFIG_SPARC32) += extable.o srmmu.o iommu.o io-unit.o
+obj-$(CONFIG_SPARC32) += srmmu.o iommu.o io-unit.o
obj-$(CONFIG_SPARC32) += srmmu_access.o
obj-$(CONFIG_SPARC32) += hypersparc.o viking.o tsunami.o swift.o
obj-$(CONFIG_SPARC32) += leon_mm.o
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0
-/*
- * linux/arch/sparc/mm/extable.c
- */
-
-#include <linux/module.h>
-#include <linux/extable.h>
-#include <linux/uaccess.h>
-
-void sort_extable(struct exception_table_entry *start,
- struct exception_table_entry *finish)
-{
-}
-
-/* Caller knows they are in a range if ret->fixup == 0 */
-const struct exception_table_entry *
-search_extable(const struct exception_table_entry *base,
- const size_t num,
- unsigned long value)
-{
- int i;
-
- /* Single insn entries are encoded as:
- * word 1: insn address
- * word 2: fixup code address
- *
- * Range entries are encoded as:
- * word 1: first insn address
- * word 2: 0
- * word 3: last insn address + 4 bytes
- * word 4: fixup code address
- *
- * Deleted entries are encoded as:
- * word 1: unused
- * word 2: -1
- *
- * See asm/uaccess.h for more details.
- */
-
- /* 1. Try to find an exact match. */
- for (i = 0; i < num; i++) {
- if (base[i].fixup == 0) {
- /* A range entry, skip both parts. */
- i++;
- continue;
- }
-
- /* A deleted entry; see trim_init_extable */
- if (base[i].fixup == -1)
- continue;
-
- if (base[i].insn == value)
- return &base[i];
- }
-
- /* 2. Try to find a range match. */
- for (i = 0; i < (num - 1); i++) {
- if (base[i].fixup)
- continue;
-
- if (base[i].insn <= value && base[i + 1].insn > value)
- return &base[i];
-
- i++;
- }
-
- return NULL;
-}
-
-#ifdef CONFIG_MODULES
-/* We could memmove them around; easier to mark the trimmed ones. */
-void trim_init_extable(struct module *m)
-{
- unsigned int i;
- bool range;
-
- for (i = 0; i < m->num_exentries; i += range ? 2 : 1) {
- range = m->extable[i].fixup == 0;
-
- if (within_module_init(m->extable[i].insn, m)) {
- m->extable[i].fixup = -1;
- if (range)
- m->extable[i+1].fixup = -1;
- }
- if (range)
- i++;
- }
-}
-#endif /* CONFIG_MODULES */
-
-/* Special extable search, which handles ranges. Returns fixup */
-unsigned long search_extables_range(unsigned long addr, unsigned long *g2)
-{
- const struct exception_table_entry *entry;
-
- entry = search_exception_tables(addr);
- if (!entry)
- return 0;
-
- /* Inside range? Fix g2 and return correct fixup */
- if (!entry->fixup) {
- *g2 = (addr - entry->insn) / 4;
- return (entry + 1)->fixup;
- }
-
- return entry->fixup;
-}
#include <linux/interrupt.h>
#include <linux/kdebug.h>
#include <linux/uaccess.h>
+#include <linux/extable.h>
#include <asm/page.h>
#include <asm/openprom.h>
die_if_kernel("Oops", regs);
}
-asmlinkage int lookup_fault(unsigned long pc, unsigned long ret_pc,
- unsigned long address)
-{
- struct pt_regs regs;
- unsigned long g2;
- unsigned int insn;
- int i;
-
- i = search_extables_range(ret_pc, &g2);
- switch (i) {
- case 3:
- /* load & store will be handled by fixup */
- return 3;
-
- case 1:
- /* store will be handled by fixup, load will bump out */
- /* for _to_ macros */
- insn = *((unsigned int *) pc);
- if ((insn >> 21) & 1)
- return 1;
- break;
-
- case 2:
- /* load will be handled by fixup, store will bump out */
- /* for _from_ macros */
- insn = *((unsigned int *) pc);
- if (!((insn >> 21) & 1) || ((insn>>19)&0x3f) == 15)
- return 2;
- break;
-
- default:
- break;
- }
-
- memset(®s, 0, sizeof(regs));
- regs.pc = pc;
- regs.npc = pc + 4;
- __asm__ __volatile__(
- "rd %%psr, %0\n\t"
- "nop\n\t"
- "nop\n\t"
- "nop\n" : "=r" (regs.psr));
- unhandled_fault(address, current, ®s);
-
- /* Not reached */
- return 0;
-}
-
static inline void
show_signal_msg(struct pt_regs *regs, int sig, int code,
unsigned long address, struct task_struct *tsk)
struct vm_area_struct *vma;
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
- unsigned int fixup;
- unsigned long g2;
int from_user = !(regs->psr & PSR_PS);
int code;
vm_fault_t fault;
/* Is this in ex_table? */
no_context:
- g2 = regs->u_regs[UREG_G2];
if (!from_user) {
- fixup = search_extables_range(regs->pc, &g2);
- /* Values below 10 are reserved for other things */
- if (fixup > 10) {
- extern const unsigned int __memset_start[];
- extern const unsigned int __memset_end[];
+ const struct exception_table_entry *entry;
+ entry = search_exception_tables(regs->pc);
#ifdef DEBUG_EXCEPTIONS
- printk("Exception: PC<%08lx> faddr<%08lx>\n",
- regs->pc, address);
- printk("EX_TABLE: insn<%08lx> fixup<%08x> g2<%08lx>\n",
- regs->pc, fixup, g2);
+ printk("Exception: PC<%08lx> faddr<%08lx>\n",
+ regs->pc, address);
+ printk("EX_TABLE: insn<%08lx> fixup<%08x>\n",
+ regs->pc, entry->fixup);
#endif
- if ((regs->pc >= (unsigned long)__memset_start &&
- regs->pc < (unsigned long)__memset_end)) {
- regs->u_regs[UREG_I4] = address;
- regs->u_regs[UREG_I5] = regs->pc;
- }
- regs->u_regs[UREG_G2] = g2;
- regs->pc = fixup;
- regs->npc = regs->pc + 4;
- return;
- }
+ regs->pc = entry->fixup;
+ regs->npc = regs->pc + 4;
+ return;
}
unhandled_fault(address, tsk, regs);
/* SPDX-License-Identifier: GPL-2.0 */
/* fault_32.c - visible as they are called from assembler */
-asmlinkage int lookup_fault(unsigned long pc, unsigned long ret_pc,
- unsigned long address);
asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
unsigned long address);
select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if X86_64
select HAVE_ARCH_USERFAULTFD_WP if X86_64 && USERFAULTFD
select HAVE_ARCH_VMAP_STACK if X86_64
+ select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
select HAVE_ARCH_WITHIN_STACK_FRAMES
select HAVE_ASM_MODVERSIONS
select HAVE_CMPXCHG_DOUBLE
depends on X86_EXTENDED_PLATFORM
depends on NUMA
depends on EFI
+ depends on KEXEC_CORE
depends on X86_X2APIC
depends on PCI
help
config PARAVIRT
bool "Enable paravirtualization code"
+ depends on HAVE_STATIC_CALL
help
This changes the kernel so it can modify itself when it is run
under a hypervisor, potentially improving performance significantly
config HIGHMEM64G
bool "64GB"
- depends on !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !WINCHIP3D && !MK6
+ depends on !M486SX && !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !WINCHIP3D && !MK6
select X86_PAE
help
Select this if you have a 32-bit processor and more than 4
select ARCH_USE_MEMREMAP_PROT
select ARCH_HAS_FORCE_DMA_UNENCRYPTED
select INSTRUCTION_DECODER
+ select ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
help
Say yes to enable support for the encryption of system memory.
This requires an AMD processor that supports Secure Memory
depends on CRYPTO_SHA256=y
select SRCU
select MMU_NOTIFIER
+ select NUMA_KEEP_MEMINFO if NUMA
help
Intel(R) Software Guard eXtensions (SGX) is a set of CPU instructions
that can be used by applications to set aside private regions of code
REALMODE_CFLAGS := -m16 -g -Os -DDISABLE_BRANCH_PROFILING \
-Wall -Wstrict-prototypes -march=i386 -mregparm=3 \
-fno-strict-aliasing -fomit-frame-pointer -fno-pic \
- -mno-mmx -mno-sse
+ -mno-mmx -mno-sse $(call cc-option,-fcf-protection=none)
REALMODE_CFLAGS += -ffreestanding
REALMODE_CFLAGS += -fno-stack-protector
REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -Wno-address-of-packed-member)
REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), $(cc_stack_align4))
+REALMODE_CFLAGS += $(CLANG_FLAGS)
export REALMODE_CFLAGS
# BITS is used as extension for files which are available in a 32 bit
# Disable relocation relaxation in case the link is not PIE.
KBUILD_CFLAGS += $(call as-option,-Wa$(comma)-mrelax-relocations=no)
KBUILD_CFLAGS += -include $(srctree)/include/linux/hidden.h
+KBUILD_CFLAGS += $(CLANG_FLAGS)
# sev-es.c indirectly inludes inat-table.h which is generated during
# compilation and stored in $(objtree). Add the directory to the includes so
* Early support for invoking 32-bit EFI services from a 64-bit kernel.
*
* Because this thunking occurs before ExitBootServices() we have to
- * restore the firmware's 32-bit GDT before we make EFI serivce calls,
+ * restore the firmware's 32-bit GDT before we make EFI service calls,
* since the firmware's 32-bit IDT is still currently installed and it
* needs to be able to service interrupts.
*
#include <asm/asm-offsets.h>
#include <asm/bootparam.h>
#include <asm/desc_defs.h>
+#include <asm/trapnr.h>
#include "pgtable.h"
/*
movl %eax, %gs
movl %eax, %ss
-/* setup a stack and make sure cpu supports long mode. */
+ /* Setup a stack and load CS from current GDT */
leal rva(boot_stack_end)(%ebp), %esp
+ pushl $__KERNEL32_CS
+ leal rva(1f)(%ebp), %eax
+ pushl %eax
+ lretl
+1:
+
+ /* Setup Exception handling for SEV-ES */
+ call startup32_load_idt
+
+ /* Make sure cpu supports long mode. */
call verify_cpu
testl %eax, %eax
jnz .Lno_longmode
*/
call get_sev_encryption_bit
xorl %edx, %edx
+#ifdef CONFIG_AMD_MEM_ENCRYPT
testl %eax, %eax
jz 1f
subl $32, %eax /* Encryption bit is always above bit 31 */
bts %eax, %edx /* Set encryption mask for page tables */
+ /*
+ * Mark SEV as active in sev_status so that startup32_check_sev_cbit()
+ * will do a check. The sev_status memory will be fully initialized
+ * with the contents of MSR_AMD_SEV_STATUS later in
+ * set_sev_encryption_mask(). For now it is sufficient to know that SEV
+ * is active.
+ */
+ movl $1, rva(sev_status)(%ebp)
1:
+#endif
/* Initialize Page tables to 0 */
leal rva(pgtable)(%ebx), %edi
/*
* Setup for the jump to 64bit mode
*
- * When the jump is performend we will be in long mode but
+ * When the jump is performed we will be in long mode but
* in 32bit compatibility mode with EFER.LME = 1, CS.L = 0, CS.D = 1
* (and in turn EFER.LMA = 1). To jump into 64bit mode we use
* the new gdt/idt that has __KERNEL_CS with CS.L = 1.
movl %esi, %edx
1:
#endif
+ /* Check if the C-bit position is correct when SEV is active */
+ call startup32_check_sev_cbit
+
pushl $__KERNEL_CS
pushl %eax
.endr
SYM_DATA_END_LABEL(boot_idt, SYM_L_GLOBAL, boot_idt_end)
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+SYM_DATA_START(boot32_idt_desc)
+ .word boot32_idt_end - boot32_idt - 1
+ .long 0
+SYM_DATA_END(boot32_idt_desc)
+ .balign 8
+SYM_DATA_START(boot32_idt)
+ .rept 32
+ .quad 0
+ .endr
+SYM_DATA_END_LABEL(boot32_idt, SYM_L_GLOBAL, boot32_idt_end)
+#endif
+
#ifdef CONFIG_EFI_STUB
SYM_DATA(image_offset, .long 0)
#endif
SYM_DATA_END(loaded_image_proto)
#endif
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+ __HEAD
+ .code32
+/*
+ * Write an IDT entry into boot32_idt
+ *
+ * Parameters:
+ *
+ * %eax: Handler address
+ * %edx: Vector number
+ *
+ * Physical offset is expected in %ebp
+ */
+SYM_FUNC_START(startup32_set_idt_entry)
+ push %ebx
+ push %ecx
+
+ /* IDT entry address to %ebx */
+ leal rva(boot32_idt)(%ebp), %ebx
+ shl $3, %edx
+ addl %edx, %ebx
+
+ /* Build IDT entry, lower 4 bytes */
+ movl %eax, %edx
+ andl $0x0000ffff, %edx # Target code segment offset [15:0]
+ movl $__KERNEL32_CS, %ecx # Target code segment selector
+ shl $16, %ecx
+ orl %ecx, %edx
+
+ /* Store lower 4 bytes to IDT */
+ movl %edx, (%ebx)
+
+ /* Build IDT entry, upper 4 bytes */
+ movl %eax, %edx
+ andl $0xffff0000, %edx # Target code segment offset [31:16]
+ orl $0x00008e00, %edx # Present, Type 32-bit Interrupt Gate
+
+ /* Store upper 4 bytes to IDT */
+ movl %edx, 4(%ebx)
+
+ pop %ecx
+ pop %ebx
+ ret
+SYM_FUNC_END(startup32_set_idt_entry)
+#endif
+
+SYM_FUNC_START(startup32_load_idt)
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+ /* #VC handler */
+ leal rva(startup32_vc_handler)(%ebp), %eax
+ movl $X86_TRAP_VC, %edx
+ call startup32_set_idt_entry
+
+ /* Load IDT */
+ leal rva(boot32_idt)(%ebp), %eax
+ movl %eax, rva(boot32_idt_desc+2)(%ebp)
+ lidt rva(boot32_idt_desc)(%ebp)
+#endif
+ ret
+SYM_FUNC_END(startup32_load_idt)
+
+/*
+ * Check for the correct C-bit position when the startup_32 boot-path is used.
+ *
+ * The check makes use of the fact that all memory is encrypted when paging is
+ * disabled. The function creates 64 bits of random data using the RDRAND
+ * instruction. RDRAND is mandatory for SEV guests, so always available. If the
+ * hypervisor violates that the kernel will crash right here.
+ *
+ * The 64 bits of random data are stored to a memory location and at the same
+ * time kept in the %eax and %ebx registers. Since encryption is always active
+ * when paging is off the random data will be stored encrypted in main memory.
+ *
+ * Then paging is enabled. When the C-bit position is correct all memory is
+ * still mapped encrypted and comparing the register values with memory will
+ * succeed. An incorrect C-bit position will map all memory unencrypted, so that
+ * the compare will use the encrypted random data and fail.
+ */
+SYM_FUNC_START(startup32_check_sev_cbit)
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+ pushl %eax
+ pushl %ebx
+ pushl %ecx
+ pushl %edx
+
+ /* Check for non-zero sev_status */
+ movl rva(sev_status)(%ebp), %eax
+ testl %eax, %eax
+ jz 4f
+
+ /*
+ * Get two 32-bit random values - Don't bail out if RDRAND fails
+ * because it is better to prevent forward progress if no random value
+ * can be gathered.
+ */
+1: rdrand %eax
+ jnc 1b
+2: rdrand %ebx
+ jnc 2b
+
+ /* Store to memory and keep it in the registers */
+ movl %eax, rva(sev_check_data)(%ebp)
+ movl %ebx, rva(sev_check_data+4)(%ebp)
+
+ /* Enable paging to see if encryption is active */
+ movl %cr0, %edx /* Backup %cr0 in %edx */
+ movl $(X86_CR0_PG | X86_CR0_PE), %ecx /* Enable Paging and Protected mode */
+ movl %ecx, %cr0
+
+ cmpl %eax, rva(sev_check_data)(%ebp)
+ jne 3f
+ cmpl %ebx, rva(sev_check_data+4)(%ebp)
+ jne 3f
+
+ movl %edx, %cr0 /* Restore previous %cr0 */
+
+ jmp 4f
+
+3: /* Check failed - hlt the machine */
+ hlt
+ jmp 3b
+
+4:
+ popl %edx
+ popl %ecx
+ popl %ebx
+ popl %eax
+#endif
+ ret
+SYM_FUNC_END(startup32_check_sev_cbit)
+
/*
* Stack and heap for uncompression
*/
load_boot_idt(&boot_idt_desc);
}
+
+void cleanup_exception_handling(void)
+{
+ /*
+ * Flush GHCB from cache and map it encrypted again when running as
+ * SEV-ES guest.
+ */
+ sev_es_shutdown_ghcb();
+
+ /* Set a null-idt, disabling #PF and #VC handling */
+ boot_idt_desc.size = 0;
+ boot_idt_desc.address = 0;
+ load_boot_idt(&boot_idt_desc);
+}
if (slot_area_index == MAX_SLOT_AREA) {
debug_putstr("Aborted e820/efi memmap scan (slot_areas full)!\n");
- return 1;
+ return true;
}
- return 0;
+ return false;
}
#if defined(CONFIG_MEMORY_HOTREMOVE) && defined(CONFIG_ACPI)
push %ecx
push %edx
- /* Check if running under a hypervisor */
- movl $1, %eax
- cpuid
- bt $31, %ecx /* Check the hypervisor bit */
- jnc .Lno_sev
-
movl $0x80000000, %eax /* CPUID to check the highest leaf */
cpuid
cmpl $0x8000001f, %eax /* See if 0x8000001f is available */
ret
SYM_FUNC_END(get_sev_encryption_bit)
+/**
+ * sev_es_req_cpuid - Request a CPUID value from the Hypervisor using
+ * the GHCB MSR protocol
+ *
+ * @%eax: Register to request (0=EAX, 1=EBX, 2=ECX, 3=EDX)
+ * @%edx: CPUID Function
+ *
+ * Returns 0 in %eax on success, non-zero on failure
+ * %edx returns CPUID value on success
+ */
+SYM_CODE_START_LOCAL(sev_es_req_cpuid)
+ shll $30, %eax
+ orl $0x00000004, %eax
+ movl $MSR_AMD64_SEV_ES_GHCB, %ecx
+ wrmsr
+ rep; vmmcall # VMGEXIT
+ rdmsr
+
+ /* Check response */
+ movl %eax, %ecx
+ andl $0x3ffff000, %ecx # Bits [12-29] MBZ
+ jnz 2f
+
+ /* Check return code */
+ andl $0xfff, %eax
+ cmpl $5, %eax
+ jne 2f
+
+ /* All good - return success */
+ xorl %eax, %eax
+1:
+ ret
+2:
+ movl $-1, %eax
+ jmp 1b
+SYM_CODE_END(sev_es_req_cpuid)
+
+SYM_CODE_START(startup32_vc_handler)
+ pushl %eax
+ pushl %ebx
+ pushl %ecx
+ pushl %edx
+
+ /* Keep CPUID function in %ebx */
+ movl %eax, %ebx
+
+ /* Check if error-code == SVM_EXIT_CPUID */
+ cmpl $0x72, 16(%esp)
+ jne .Lfail
+
+ movl $0, %eax # Request CPUID[fn].EAX
+ movl %ebx, %edx # CPUID fn
+ call sev_es_req_cpuid # Call helper
+ testl %eax, %eax # Check return code
+ jnz .Lfail
+ movl %edx, 12(%esp) # Store result
+
+ movl $1, %eax # Request CPUID[fn].EBX
+ movl %ebx, %edx # CPUID fn
+ call sev_es_req_cpuid # Call helper
+ testl %eax, %eax # Check return code
+ jnz .Lfail
+ movl %edx, 8(%esp) # Store result
+
+ movl $2, %eax # Request CPUID[fn].ECX
+ movl %ebx, %edx # CPUID fn
+ call sev_es_req_cpuid # Call helper
+ testl %eax, %eax # Check return code
+ jnz .Lfail
+ movl %edx, 4(%esp) # Store result
+
+ movl $3, %eax # Request CPUID[fn].EDX
+ movl %ebx, %edx # CPUID fn
+ call sev_es_req_cpuid # Call helper
+ testl %eax, %eax # Check return code
+ jnz .Lfail
+ movl %edx, 0(%esp) # Store result
+
+ /*
+ * Sanity check CPUID results from the Hypervisor. See comment in
+ * do_vc_no_ghcb() for more details on why this is necessary.
+ */
+
+ /* Fail if SEV leaf not available in CPUID[0x80000000].EAX */
+ cmpl $0x80000000, %ebx
+ jne .Lcheck_sev
+ cmpl $0x8000001f, 12(%esp)
+ jb .Lfail
+ jmp .Ldone
+
+.Lcheck_sev:
+ /* Fail if SEV bit not set in CPUID[0x8000001f].EAX[1] */
+ cmpl $0x8000001f, %ebx
+ jne .Ldone
+ btl $1, 12(%esp)
+ jnc .Lfail
+
+.Ldone:
+ popl %edx
+ popl %ecx
+ popl %ebx
+ popl %eax
+
+ /* Remove error code */
+ addl $4, %esp
+
+ /* Jump over CPUID instruction */
+ addl $2, (%esp)
+
+ iret
+.Lfail:
+ /* Send terminate request to Hypervisor */
+ movl $0x100, %eax
+ xorl %edx, %edx
+ movl $MSR_AMD64_SEV_ES_GHCB, %ecx
+ wrmsr
+ rep; vmmcall
+
+ /* If request fails, go to hlt loop */
+ hlt
+ jmp .Lfail
+SYM_CODE_END(startup32_vc_handler)
+
.code64
#include "../../kernel/sev_verify_cbit.S"
-
SYM_FUNC_START(set_sev_encryption_mask)
#ifdef CONFIG_AMD_MEM_ENCRYPT
push %rbp
error("Destination address too large");
#endif
#ifndef CONFIG_RELOCATABLE
- if ((unsigned long)output != LOAD_PHYSICAL_ADDR)
- error("Destination address does not match LOAD_PHYSICAL_ADDR");
if (virt_addr != LOAD_PHYSICAL_ADDR)
error("Destination virtual address changed when not relocatable");
#endif
handle_relocations(output, output_len, virt_addr);
debug_putstr("done.\nBooting the kernel.\n");
- /*
- * Flush GHCB from cache and map it encrypted again when running as
- * SEV-ES guest.
- */
- sev_es_shutdown_ghcb();
+ /* Disable exception handling before booting the kernel */
+ cleanup_exception_handling();
return output;
}
extern gate_desc boot_idt[BOOT_IDT_ENTRIES];
extern struct desc_ptr boot_idt_desc;
+#ifdef CONFIG_X86_64
+void cleanup_exception_handling(void);
+#else
+static inline void cleanup_exception_handling(void) { }
+#endif
+
/* IDT Entry Points */
void boot_page_fault(void);
void boot_stage1_vc(void);
}
finish:
- if (result == ES_OK) {
+ if (result == ES_OK)
vc_finish_insn(&ctxt);
- } else if (result != ES_RETRY) {
- /*
- * For now, just halt the machine. That makes debugging easier,
- * later we just call sev_es_terminate() here.
- */
- while (true)
- asm volatile("hlt\n");
- }
+ else if (result != ES_RETRY)
+ sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST);
}
/*
* Copyright 2012 Xyratex Technology Limited
*
- * Wrappers for kernel crypto shash api to pclmulqdq crc32 imlementation.
+ * Wrappers for kernel crypto shash api to pclmulqdq crc32 implementation.
*/
#include <linux/init.h>
#include <linux/module.h>
);
}
-/* Computes the field substraction of two field elements */
+/* Computes the field subtraction of two field elements */
static inline void fsub(u64 *out, const u64 *f1, const u64 *f2)
{
asm volatile(
- /* Compute the raw substraction of f1-f2 */
+ /* Compute the raw subtraction of f1-f2 */
" movq 0(%1), %%r8;"
" subq 0(%2), %%r8;"
" movq 8(%1), %%r9;"
" mov $38, %%rcx;"
" cmovc %%rcx, %%rax;"
- /* Step 2: Substract carry*38 from the original difference */
+ /* Step 2: Subtract carry*38 from the original difference */
" sub %%rax, %%r8;"
" sbb $0, %%r9;"
" sbb $0, %%r10;"
#include <asm/simd.h>
asmlinkage void poly1305_init_x86_64(void *ctx,
- const u8 key[POLY1305_KEY_SIZE]);
+ const u8 key[POLY1305_BLOCK_SIZE]);
asmlinkage void poly1305_blocks_x86_64(void *ctx, const u8 *inp,
const size_t len, const u32 padbit);
asmlinkage void poly1305_emit_x86_64(void *ctx, u8 mac[POLY1305_DIGEST_SIZE],
state->is_base2_26 = 0;
}
-static void poly1305_simd_init(void *ctx, const u8 key[POLY1305_KEY_SIZE])
+static void poly1305_simd_init(void *ctx, const u8 key[POLY1305_BLOCK_SIZE])
{
poly1305_init_x86_64(ctx, key);
}
poly1305_emit_avx(ctx, mac, nonce);
}
-void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key)
+void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE])
{
poly1305_simd_init(&dctx->h, key);
dctx->s[0] = get_unaligned_le32(&key[16]);
/*
* Combined G1 & G2 function. Reordered with help of rotates to have moves
- * at begining.
+ * at beginning.
*/
#define g1g2_3(ab, cd, Tx0, Tx1, Tx2, Tx3, Ty0, Ty1, Ty2, Ty3, x, y) \
/* G1,1 && G2,1 */ \
* storing blocks in 64bit registers to allow three blocks to
* be processed parallel. Parallel operation then allows gaining
* more performance than was trade off, on out-of-order CPUs.
- * However Atom does not benefit from this parallellism and
+ * However Atom does not benefit from this parallelism and
* should be blacklisted.
*/
return true;
#ifdef CONFIG_X86_64
__visible noinstr void do_syscall_64(unsigned long nr, struct pt_regs *regs)
{
+ add_random_kstack_offset();
nr = syscall_enter_from_user_mode(regs, nr);
instrumentation_begin();
{
unsigned int nr = syscall_32_enter(regs);
+ add_random_kstack_offset();
/*
* Subtlety here: if ptrace pokes something larger than 2^32-1 into
* orig_ax, the unsigned int return value truncates it. This may
unsigned int nr = syscall_32_enter(regs);
int res;
+ add_random_kstack_offset();
/*
* This cannot use syscall_enter_from_user_mode() as it has to
* fetch EBP before invoking any of the syscall entry work
regs->ax = -EFAULT;
instrumentation_end();
- syscall_exit_to_user_mode(regs);
+ local_irq_disable();
+ irqentry_exit_to_user_mode(regs);
return false;
}
#include <asm/processor-flags.h>
#include <asm/irq_vectors.h>
#include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
#include <asm/asm.h>
#include <asm/smap.h>
#include <asm/frame.h>
*
* Lets build a 5 entry IRET frame after that, such that struct pt_regs
* is complete and in particular regs->sp is correct. This gives us
- * the original 6 enties as gap:
+ * the original 6 entries as gap:
*
* 14*4(%esp) - <previous context>
* 13*4(%esp) - gap / flags
* will soon execute iret and the tracer was already set to
* the irqstate after the IRET:
*/
- DISABLE_INTERRUPTS(CLBR_ANY)
+ cli
lss (%esp), %esp /* switch to espfix segment */
.Lend_\@:
#endif /* CONFIG_X86_ESPFIX32 */
* when returning from IPI handler and when returning from
* scheduler to user-space.
*/
- INTERRUPT_RETURN
+ iret
.section .fixup, "ax"
SYM_CODE_START(asm_iret_error)
.macro DEBUG_ENTRY_ASSERT_IRQS_OFF
#ifdef CONFIG_DEBUG_ENTRY
pushq %rax
- SAVE_FLAGS(CLBR_RAX)
+ SAVE_FLAGS
testl $X86_EFLAGS_IF, %eax
jz .Lokay_\@
ud2
/*
* No need to switch back to the IST stack. The current stack is either
* identical to the stack in the IRET frame or the VC fall-back stack,
- * so it is definitly mapped even with PTI enabled.
+ * so it is definitely mapped even with PTI enabled.
*/
jmp paranoid_exit
/* Switch to the kernel stack */
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+SYM_INNER_LABEL(entry_SYSCALL_compat_safe_stack, SYM_L_GLOBAL)
+
/* Construct struct pt_regs on stack */
pushq $__USER32_DS /* pt_regs->ss */
pushq %r8 /* pt_regs->sp */
/*
* Figure out the struct name. If we're writing to a .so file,
- * generate raw output insted.
+ * generate raw output instead.
*/
name = strdup(argv[3]);
namelen = strlen(name);
if (offset + len > data_len)
fail("section to extract overruns input data");
- fprintf(outfile, "static const unsigned char %s[%lu] = {", name, len);
+ fprintf(outfile, "static const unsigned char %s[%zu] = {", name, len);
BITSFUNC(copy)(outfile, data + offset, len);
fprintf(outfile, "\n};\n\n");
}
#include <linux/linkage.h>
#include <asm/dwarf2.h>
#include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
.text
.globl __kernel_vsyscall
* anyone with an AMD CPU, for example). Nonetheless, we try to keep
* it working approximately as well as it ever worked.
*
- * This link may eludicate some of the history:
+ * This link may elucidate some of the history:
* https://android-review.googlesource.com/#/q/Iac3295376d61ef83e713ac9b528f3b50aa780cd7
* personally, I find it hard to understand what's going on there.
*
mmap_write_lock(mm);
/*
* Check if we have already mapped vdso blob - fail to prevent
- * abusing from userspace install_speciall_mapping, which may
+ * abusing from userspace install_special_mapping, which may
* not do accounting and rlimit right.
* We could search vma near context.vdso, but it's a slowpath,
* so let's explicitly check all VMAs to be completely sure.
/*
* If the return from callback is zero or negative, return immediately,
- * else re-execute ENCLU with the postive return value interpreted as
+ * else re-execute ENCLU with the positive return value interpreted as
* the requested ENCLU function.
*/
cmp $0, %eax
/*
* Check each counter for overflow and wait for it to be reset by the
* NMI if it has overflowed. This relies on the fact that all active
- * counters are always enabled when this function is caled and
+ * counters are always enabled when this function is called and
* ARCH_PERFMON_EVENTSEL_INT is always set.
*/
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
#define IOMMU_PC_DEVID_MATCH_REG 0x20
#define IOMMU_PC_COUNTER_REPORT_REG 0x28
-/* maximun specified bank/counters */
+/* maximum specified bank/counters */
#define PC_MAX_SPEC_BNKS 64
#define PC_MAX_SPEC_CNTRS 16
DEFINE_STATIC_CALL_NULL(x86_pmu_drain_pebs, *x86_pmu.drain_pebs);
DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_aliases, *x86_pmu.pebs_aliases);
-DEFINE_STATIC_CALL_NULL(x86_pmu_guest_get_msrs, *x86_pmu.guest_get_msrs);
+/*
+ * This one is magic, it will get called even when PMU init fails (because
+ * there is no PMU), in which case it should simply return NULL.
+ */
+DEFINE_STATIC_CALL_RET0(x86_pmu_guest_get_msrs, *x86_pmu.guest_get_msrs);
u64 __read_mostly hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
};
/*
- * Initialize interator that runs through all events and counters.
+ * Initialize iterator that runs through all events and counters.
*/
static void perf_sched_init(struct perf_sched *sched, struct event_constraint **constraints,
int num, int wmin, int wmax, int gpmax)
x86_perf_event_update(event);
}
-static inline struct perf_guest_switch_msr *
-perf_guest_get_msrs_nop(int *nr)
-{
- *nr = 0;
- return NULL;
-}
-
static int __init init_hw_perf_events(void)
{
struct x86_pmu_quirk *quirk;
x86_pmu.read = _x86_pmu_read;
if (!x86_pmu.guest_get_msrs)
- x86_pmu.guest_get_msrs = perf_guest_get_msrs_nop;
+ x86_pmu.guest_get_msrs = (void *)&__static_call_return0;
x86_pmu_static_call_update();
* we cannot use the user mapping since it will not be available
* if we're not running the owning process.
*
- * With PTI we can't use the kernal map either, because its not
+ * With PTI we can't use the kernel map either, because its not
* there when we run userspace.
*
* For now, disable this driver when using PTI.
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
INTEL_UEVENT_CONSTRAINT(0x0148, 0x4), /* L1D_PEND_MISS.PENDING */
- INTEL_UEVENT_CONSTRAINT(0x0279, 0xf), /* IDQ.EMTPY */
+ INTEL_UEVENT_CONSTRAINT(0x0279, 0xf), /* IDQ.EMPTY */
INTEL_UEVENT_CONSTRAINT(0x019c, 0xf), /* IDQ_UOPS_NOT_DELIVERED.CORE */
INTEL_UEVENT_CONSTRAINT(0x02a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_LDM_PENDING */
INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */
* magic three (non-counting) events 0x4300B5, 0x4300D2, and 0x4300B1 either
* in sequence on the same PMC or on different PMCs.
*
- * In practise it appears some of these events do in fact count, and
+ * In practice it appears some of these events do in fact count, and
* we need to program all 4 events.
*/
static void intel_pmu_nhm_workaround(void)
/*
* The metric is reported as an 8bit integer fraction
- * suming up to 0xff.
+ * summing up to 0xff.
* slots-in-metric = (Metric / 0xff) * slots
*/
val = (metric >> ((idx - INTEL_PMC_IDX_METRIC_BASE) * 8)) & 0xff;
* processing loop coming after that the function, otherwise
* phony regular samples may be generated in the sampling buffer
* not marked with the EXACT tag. Another possibility is to have
- * one PEBS event and at least one non-PEBS event whic hoverflows
+ * one PEBS event and at least one non-PEBS event which overflows
* while PEBS has armed. In this case, bit 62 of GLOBAL_STATUS will
* not be set, yet the overflow status bit for the PEBS counter will
* be on Skylake.
}
/*
- * Intel Perf mertrics
+ * Intel Perf metrics
*/
if (__test_and_clear_bit(GLOBAL_STATUS_PERF_METRICS_OVF_BIT, (unsigned long *)&status)) {
handled++;
return ret;
if (event->attr.precise_ip) {
+ if ((event->attr.config & INTEL_ARCH_EVENT_MASK) == INTEL_FIXED_VLBR_EVENT)
+ return -EINVAL;
+
if (!(event->attr.freq || (event->attr.wakeup_events && !event->attr.watermark))) {
event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
if (!(event->attr.sample_type &
- ~intel_pmu_large_pebs_flags(event)))
+ ~intel_pmu_large_pebs_flags(event))) {
event->hw.flags |= PERF_X86_EVENT_LARGE_PEBS;
+ event->attach_state |= PERF_ATTACH_SCHED_CB;
+ }
}
if (x86_pmu.pebs_aliases)
x86_pmu.pebs_aliases(event);
ret = intel_pmu_setup_lbr_filter(event);
if (ret)
return ret;
+ event->attach_state |= PERF_ATTACH_SCHED_CB;
/*
* BTS is set up earlier in this path, so don't account twice
INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 3, 0x07000009),
INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 4, 0x0f000009),
INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 5, 0x0e000002),
- INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_X, 2, 0x0b000014),
+ INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_X, 1, 0x0b000014),
INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 3, 0x00000021),
INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 4, 0x00000000),
INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 5, 0x00000000),
/*
* Disable the check for real HW, so we don't
- * mess with potentionaly enabled registers:
+ * mess with potentially enabled registers:
*/
if (!boot_cpu_has(X86_FEATURE_HYPERVISOR))
return true;
{
int bit;
- /* disable event that reported as not presend by cpuid */
+ /* disable event that reported as not present by cpuid */
for_each_set_bit(bit, x86_pmu.events_mask, ARRAY_SIZE(intel_arch_events_map)) {
intel_perfmon_event_map[intel_arch_events_map[bit].id] = 0;
pr_warn("CPUID marked event: \'%s\' unavailable\n",
*
* [-period, 0]
*
- * the difference between two consequtive reads is:
+ * the difference between two consecutive reads is:
*
* A) value2 - value1;
* when no overflows have happened in between,
*/
if (!pebs_status && cpuc->pebs_enabled &&
!(cpuc->pebs_enabled & (cpuc->pebs_enabled-1)))
- pebs_status = cpuc->pebs_enabled;
+ pebs_status = p->status = cpuc->pebs_enabled;
bit = find_first_bit((unsigned long *)&pebs_status,
x86_pmu.max_pebs_events);
/*
* The LBR logs any address in the IP, even if the IP just
* faulted. This means userspace can control the from address.
- * Ensure we don't blindy read any address by validating it is
+ * Ensure we don't blindly read any address by validating it is
* a known text address.
*/
if (kernel_text_address(from)) {
unsigned int escr_msr[2]; /* ESCR MSR for this event */
unsigned int escr_emask; /* valid ESCR EventMask bits */
unsigned int shared; /* event is shared across threads */
- char cntr[2][P4_CNTR_LIMIT]; /* counter index (offset), -1 on abscence */
+ char cntr[2][P4_CNTR_LIMIT]; /* counter index (offset), -1 on absence */
};
struct p4_pebs_bind {
* it's needed for mapping P4_PEBS_CONFIG_METRIC_MASK bits of
* event configuration to find out which values are to be
* written into MSR_IA32_PEBS_ENABLE and MSR_P4_PEBS_MATRIX_VERT
- * resgisters
+ * registers
*/
static struct p4_pebs_bind p4_pebs_bind_map[] = {
P4_GEN_PEBS_BIND(1stl_cache_load_miss_retired, 0x0000001, 0x0000001),
.get_event_constraints = x86_get_event_constraints,
/*
* IF HT disabled we may need to use all
- * ARCH_P4_MAX_CCCR counters simulaneously
+ * ARCH_P4_MAX_CCCR counters simultaneously
* though leave it restricted at moment assuming
* HT is on
*/
/*
* Setting bit 0 (TraceEn in RTIT_CTL MSR) in the attr.config
- * clears the assomption that BranchEn must always be enabled,
+ * clears the assumption that BranchEn must always be enabled,
* as was the case with the first implementation of PT.
* If this bit is not set, the legacy behavior is preserved
* for compatibility with the older userspace.
* | [63] | 00h | VALID - When set, indicates the CPU bus
* numbers have been initialized. (RO)
* |[62:48]| --- | Reserved
- * |[47:40]| 00h | BUS_NUM_5 — Return the bus number BIOS assigned
+ * |[47:40]| 00h | BUS_NUM_5 - Return the bus number BIOS assigned
* CPUBUSNO(5). (RO)
- * |[39:32]| 00h | BUS_NUM_4 — Return the bus number BIOS assigned
+ * |[39:32]| 00h | BUS_NUM_4 - Return the bus number BIOS assigned
* CPUBUSNO(4). (RO)
- * |[31:24]| 00h | BUS_NUM_3 — Return the bus number BIOS assigned
+ * |[31:24]| 00h | BUS_NUM_3 - Return the bus number BIOS assigned
* CPUBUSNO(3). (RO)
- * |[23:16]| 00h | BUS_NUM_2 — Return the bus number BIOS assigned
+ * |[23:16]| 00h | BUS_NUM_2 - Return the bus number BIOS assigned
* CPUBUSNO(2). (RO)
- * |[15:8] | 00h | BUS_NUM_1 — Return the bus number BIOS assigned
+ * |[15:8] | 00h | BUS_NUM_1 - Return the bus number BIOS assigned
* CPUBUSNO(1). (RO)
- * | [7:0] | 00h | BUS_NUM_0 — Return the bus number BIOS assigned
+ * | [7:0] | 00h | BUS_NUM_0 - Return the bus number BIOS assigned
* CPUBUSNO(0). (RO)
*/
#define SKX_MSR_CPU_BUS_NUMBER 0x300
SNBEP_PCI_QPI_PORT0_FILTER,
SNBEP_PCI_QPI_PORT1_FILTER,
BDX_PCI_QPI_PORT2_FILTER,
- HSWEP_PCI_PCU_3,
};
static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event)
NULL,
};
-void hswep_uncore_cpu_init(void)
+#define HSWEP_PCU_DID 0x2fc0
+#define HSWEP_PCU_CAPID4_OFFET 0x94
+#define hswep_get_chop(_cap) (((_cap) >> 6) & 0x3)
+
+static bool hswep_has_limit_sbox(unsigned int device)
{
- int pkg = boot_cpu_data.logical_proc_id;
+ struct pci_dev *dev = pci_get_device(PCI_VENDOR_ID_INTEL, device, NULL);
+ u32 capid4;
+
+ if (!dev)
+ return false;
+
+ pci_read_config_dword(dev, HSWEP_PCU_CAPID4_OFFET, &capid4);
+ if (!hswep_get_chop(capid4))
+ return true;
+ return false;
+}
+
+void hswep_uncore_cpu_init(void)
+{
if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
/* Detect 6-8 core systems with only two SBOXes */
- if (uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3]) {
- u32 capid4;
-
- pci_read_config_dword(uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3],
- 0x94, &capid4);
- if (((capid4 >> 6) & 0x3) == 0)
- hswep_uncore_sbox.num_boxes = 2;
- }
+ if (hswep_has_limit_sbox(HSWEP_PCU_DID))
+ hswep_uncore_sbox.num_boxes = 2;
uncore_msr_uncores = hswep_msr_uncores;
}
.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
SNBEP_PCI_QPI_PORT1_FILTER),
},
- { /* PCU.3 (for Capability registers) */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fc0),
- .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
- HSWEP_PCI_PCU_3),
- },
{ /* end: all zeroes */ }
};
EVENT_CONSTRAINT_END
};
+#define BDX_PCU_DID 0x6fc0
+
void bdx_uncore_cpu_init(void)
{
- int pkg = topology_phys_to_logical_pkg(boot_cpu_data.phys_proc_id);
-
if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
uncore_msr_uncores = bdx_msr_uncores;
- /* BDX-DE doesn't have SBOX */
- if (boot_cpu_data.x86_model == 86) {
- uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL;
/* Detect systems with no SBOXes */
- } else if (uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3]) {
- struct pci_dev *pdev;
- u32 capid4;
-
- pdev = uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3];
- pci_read_config_dword(pdev, 0x94, &capid4);
- if (((capid4 >> 6) & 0x3) == 0)
- bdx_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL;
- }
+ if ((boot_cpu_data.x86_model == 86) || hswep_has_limit_sbox(BDX_PCU_DID))
+ uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL;
+
hswep_uncore_pcu.constraints = bdx_uncore_pcu_constraints;
}
.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
BDX_PCI_QPI_PORT2_FILTER),
},
- { /* PCU.3 (for Capability registers) */
- PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fc0),
- .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
- HSWEP_PCI_PCU_3),
- },
{ /* end: all zeroes */ }
};
{
int bit;
- /* disable event that reported as not presend by cpuid */
+ /* disable event that reported as not present by cpuid */
for_each_set_bit(bit, x86_pmu.events_mask, ARRAY_SIZE(zx_arch_events_map)) {
zx_pmon_event_map[zx_arch_events_map[bit].id] = 0;
pr_warn("CPUID marked event: \'%s\' unavailable\n",
static inline bool hv_reenlightenment_available(void)
{
/*
- * Check for required features and priviliges to make TSC frequency
+ * Check for required features and privileges to make TSC frequency
* change notifications work.
*/
return ms_hyperv.features & HV_ACCESS_FREQUENCY_MSRS &&
/*
* Reset the hypercall page as it is going to be invalidated
- * accross hibernation. Setting hv_hypercall_pg to NULL ensures
+ * across hibernation. Setting hv_hypercall_pg to NULL ensures
* that any subsequent hypercall operation fails safely instead of
* crashing due to an access of an invalid page. The hypercall page
* pointer is restored on resume.
* Functions to keep the agpgart mappings coherent with the MMU. The
* GART gives the CPU a physical alias of pages in memory. The alias
* region is mapped uncacheable. Make sure there are no conflicting
- * mappings with different cachability attributes for the same
+ * mappings with different cacheability attributes for the same
* page. This avoids data corruption on some CPUs.
*/
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_ALTERNATIVE_ASM_H
-#define _ASM_X86_ALTERNATIVE_ASM_H
-
-#ifdef __ASSEMBLY__
-
-#include <asm/asm.h>
-
-#ifdef CONFIG_SMP
- .macro LOCK_PREFIX
-672: lock
- .pushsection .smp_locks,"a"
- .balign 4
- .long 672b - .
- .popsection
- .endm
-#else
- .macro LOCK_PREFIX
- .endm
-#endif
-
-/*
- * objtool annotation to ignore the alternatives and only consider the original
- * instruction(s).
- */
-.macro ANNOTATE_IGNORE_ALTERNATIVE
- .Lannotate_\@:
- .pushsection .discard.ignore_alts
- .long .Lannotate_\@ - .
- .popsection
-.endm
-
-/*
- * Issue one struct alt_instr descriptor entry (need to put it into
- * the section .altinstructions, see below). This entry contains
- * enough information for the alternatives patching code to patch an
- * instruction. See apply_alternatives().
- */
-.macro altinstruction_entry orig alt feature orig_len alt_len pad_len
- .long \orig - .
- .long \alt - .
- .word \feature
- .byte \orig_len
- .byte \alt_len
- .byte \pad_len
-.endm
-
-/*
- * Define an alternative between two instructions. If @feature is
- * present, early code in apply_alternatives() replaces @oldinstr with
- * @newinstr. ".skip" directive takes care of proper instruction padding
- * in case @newinstr is longer than @oldinstr.
- */
-.macro ALTERNATIVE oldinstr, newinstr, feature
-140:
- \oldinstr
-141:
- .skip -(((144f-143f)-(141b-140b)) > 0) * ((144f-143f)-(141b-140b)),0x90
-142:
-
- .pushsection .altinstructions,"a"
- altinstruction_entry 140b,143f,\feature,142b-140b,144f-143f,142b-141b
- .popsection
-
- .pushsection .altinstr_replacement,"ax"
-143:
- \newinstr
-144:
- .popsection
-.endm
-
-#define old_len 141b-140b
-#define new_len1 144f-143f
-#define new_len2 145f-144f
-
-/*
- * gas compatible max based on the idea from:
- * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
- *
- * The additional "-" is needed because gas uses a "true" value of -1.
- */
-#define alt_max_short(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b)))))
-
-
-/*
- * Same as ALTERNATIVE macro above but for two alternatives. If CPU
- * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has
- * @feature2, it replaces @oldinstr with @feature2.
- */
-.macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2
-140:
- \oldinstr
-141:
- .skip -((alt_max_short(new_len1, new_len2) - (old_len)) > 0) * \
- (alt_max_short(new_len1, new_len2) - (old_len)),0x90
-142:
-
- .pushsection .altinstructions,"a"
- altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f,142b-141b
- altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f,142b-141b
- .popsection
-
- .pushsection .altinstr_replacement,"ax"
-143:
- \newinstr1
-144:
- \newinstr2
-145:
- .popsection
-.endm
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* _ASM_X86_ALTERNATIVE_ASM_H */
#ifndef _ASM_X86_ALTERNATIVE_H
#define _ASM_X86_ALTERNATIVE_H
-#ifndef __ASSEMBLY__
-
#include <linux/types.h>
-#include <linux/stddef.h>
#include <linux/stringify.h>
#include <asm/asm.h>
+#define ALTINSTR_FLAG_INV (1 << 15)
+#define ALT_NOT(feat) ((feat) | ALTINSTR_FLAG_INV)
+
+#ifndef __ASSEMBLY__
+
+#include <linux/stddef.h>
+
/*
* Alternative inline assembly for SMP.
*
" .byte " alt_rlen(num) "\n" /* replacement len */ \
" .byte " alt_pad_len "\n" /* pad len */
-#define ALTINSTR_REPLACEMENT(newinstr, feature, num) /* replacement */ \
+#define ALTINSTR_REPLACEMENT(newinstr, num) /* replacement */ \
"# ALT: replacement " #num "\n" \
b_replacement(num)":\n\t" newinstr "\n" e_replacement(num) ":\n"
ALTINSTR_ENTRY(feature, 1) \
".popsection\n" \
".pushsection .altinstr_replacement, \"ax\"\n" \
- ALTINSTR_REPLACEMENT(newinstr, feature, 1) \
+ ALTINSTR_REPLACEMENT(newinstr, 1) \
".popsection\n"
#define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\
ALTINSTR_ENTRY(feature2, 2) \
".popsection\n" \
".pushsection .altinstr_replacement, \"ax\"\n" \
- ALTINSTR_REPLACEMENT(newinstr1, feature1, 1) \
- ALTINSTR_REPLACEMENT(newinstr2, feature2, 2) \
+ ALTINSTR_REPLACEMENT(newinstr1, 1) \
+ ALTINSTR_REPLACEMENT(newinstr2, 2) \
".popsection\n"
+/* If @feature is set, patch in @newinstr_yes, otherwise @newinstr_no. */
+#define ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) \
+ ALTERNATIVE_2(oldinstr, newinstr_no, X86_FEATURE_ALWAYS, \
+ newinstr_yes, feature)
+
#define ALTERNATIVE_3(oldinsn, newinsn1, feat1, newinsn2, feat2, newinsn3, feat3) \
OLDINSTR_3(oldinsn, 1, 2, 3) \
".pushsection .altinstructions,\"a\"\n" \
ALTINSTR_ENTRY(feat3, 3) \
".popsection\n" \
".pushsection .altinstr_replacement, \"ax\"\n" \
- ALTINSTR_REPLACEMENT(newinsn1, feat1, 1) \
- ALTINSTR_REPLACEMENT(newinsn2, feat2, 2) \
- ALTINSTR_REPLACEMENT(newinsn3, feat3, 3) \
+ ALTINSTR_REPLACEMENT(newinsn1, 1) \
+ ALTINSTR_REPLACEMENT(newinsn2, 2) \
+ ALTINSTR_REPLACEMENT(newinsn3, 3) \
".popsection\n"
/*
#define alternative_2(oldinstr, newinstr1, feature1, newinstr2, feature2) \
asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2) ::: "memory")
+#define alternative_ternary(oldinstr, feature, newinstr_yes, newinstr_no) \
+ asm_inline volatile(ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) ::: "memory")
+
/*
* Alternative inline assembly with input.
*
*/
#define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr
+#else /* __ASSEMBLY__ */
+
+#ifdef CONFIG_SMP
+ .macro LOCK_PREFIX
+672: lock
+ .pushsection .smp_locks,"a"
+ .balign 4
+ .long 672b - .
+ .popsection
+ .endm
+#else
+ .macro LOCK_PREFIX
+ .endm
+#endif
+
+/*
+ * objtool annotation to ignore the alternatives and only consider the original
+ * instruction(s).
+ */
+.macro ANNOTATE_IGNORE_ALTERNATIVE
+ .Lannotate_\@:
+ .pushsection .discard.ignore_alts
+ .long .Lannotate_\@ - .
+ .popsection
+.endm
+
+/*
+ * Issue one struct alt_instr descriptor entry (need to put it into
+ * the section .altinstructions, see below). This entry contains
+ * enough information for the alternatives patching code to patch an
+ * instruction. See apply_alternatives().
+ */
+.macro altinstruction_entry orig alt feature orig_len alt_len pad_len
+ .long \orig - .
+ .long \alt - .
+ .word \feature
+ .byte \orig_len
+ .byte \alt_len
+ .byte \pad_len
+.endm
+
+/*
+ * Define an alternative between two instructions. If @feature is
+ * present, early code in apply_alternatives() replaces @oldinstr with
+ * @newinstr. ".skip" directive takes care of proper instruction padding
+ * in case @newinstr is longer than @oldinstr.
+ */
+.macro ALTERNATIVE oldinstr, newinstr, feature
+140:
+ \oldinstr
+141:
+ .skip -(((144f-143f)-(141b-140b)) > 0) * ((144f-143f)-(141b-140b)),0x90
+142:
+
+ .pushsection .altinstructions,"a"
+ altinstruction_entry 140b,143f,\feature,142b-140b,144f-143f,142b-141b
+ .popsection
+
+ .pushsection .altinstr_replacement,"ax"
+143:
+ \newinstr
+144:
+ .popsection
+.endm
+
+#define old_len 141b-140b
+#define new_len1 144f-143f
+#define new_len2 145f-144f
+
+/*
+ * gas compatible max based on the idea from:
+ * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax
+ *
+ * The additional "-" is needed because gas uses a "true" value of -1.
+ */
+#define alt_max_short(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b)))))
+
+
+/*
+ * Same as ALTERNATIVE macro above but for two alternatives. If CPU
+ * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has
+ * @feature2, it replaces @oldinstr with @feature2.
+ */
+.macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2
+140:
+ \oldinstr
+141:
+ .skip -((alt_max_short(new_len1, new_len2) - (old_len)) > 0) * \
+ (alt_max_short(new_len1, new_len2) - (old_len)),0x90
+142:
+
+ .pushsection .altinstructions,"a"
+ altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f,142b-141b
+ altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f,142b-141b
+ .popsection
+
+ .pushsection .altinstr_replacement,"ax"
+143:
+ \newinstr1
+144:
+ \newinstr2
+145:
+ .popsection
+.endm
+
+/* If @feature is set, patch in @newinstr_yes, otherwise @newinstr_no. */
+#define ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) \
+ ALTERNATIVE_2 oldinstr, newinstr_no, X86_FEATURE_ALWAYS, \
+ newinstr_yes, feature
+
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_ALTERNATIVE_H */
/*
* Constants for operation sizes. On 32-bit, the 64-bit size it set to
* -1 because sizeof will never return -1, thereby making those switch
- * case statements guaranteeed dead code which the compiler will
+ * case statements guaranteed dead code which the compiler will
* eliminate, and allowing the "missing symbol in the default case" to
* indicate a usage error.
*/
unsigned int x86_model(unsigned int sig);
unsigned int x86_stepping(unsigned int sig);
#ifdef CONFIG_CPU_SUP_INTEL
-extern void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c);
+extern void __init sld_setup(struct cpuinfo_x86 *c);
extern void switch_to_sld(unsigned long tifn);
extern bool handle_user_split_lock(struct pt_regs *regs, long error_code);
extern bool handle_guest_split_lock(unsigned long ip);
+extern void handle_bus_lock(struct pt_regs *regs);
#else
-static inline void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c) {}
+static inline void __init sld_setup(struct cpuinfo_x86 *c) {}
static inline void switch_to_sld(unsigned long tifn) {}
static inline bool handle_user_split_lock(struct pt_regs *regs, long error_code)
{
{
return false;
}
+
+static inline void handle_bus_lock(struct pt_regs *regs) {}
#endif
#ifdef CONFIG_IA32_FEAT_CTL
void init_ia32_feat_ctl(struct cpuinfo_x86 *c);
#include <asm/asm.h>
#include <linux/bitops.h>
+#include <asm/alternative.h>
enum cpuid_leafs
{
*/
static __always_inline bool _static_cpu_has(u16 bit)
{
- asm_volatile_goto("1: jmp 6f\n"
- "2:\n"
- ".skip -(((5f-4f) - (2b-1b)) > 0) * "
- "((5f-4f) - (2b-1b)),0x90\n"
- "3:\n"
- ".section .altinstructions,\"a\"\n"
- " .long 1b - .\n" /* src offset */
- " .long 4f - .\n" /* repl offset */
- " .word %P[always]\n" /* always replace */
- " .byte 3b - 1b\n" /* src len */
- " .byte 5f - 4f\n" /* repl len */
- " .byte 3b - 2b\n" /* pad len */
- ".previous\n"
- ".section .altinstr_replacement,\"ax\"\n"
- "4: jmp %l[t_no]\n"
- "5:\n"
- ".previous\n"
- ".section .altinstructions,\"a\"\n"
- " .long 1b - .\n" /* src offset */
- " .long 0\n" /* no replacement */
- " .word %P[feature]\n" /* feature bit */
- " .byte 3b - 1b\n" /* src len */
- " .byte 0\n" /* repl len */
- " .byte 0\n" /* pad len */
- ".previous\n"
- ".section .altinstr_aux,\"ax\"\n"
- "6:\n"
- " testb %[bitnum],%[cap_byte]\n"
- " jnz %l[t_yes]\n"
- " jmp %l[t_no]\n"
- ".previous\n"
+ asm_volatile_goto(
+ ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]")
+ ".section .altinstr_aux,\"ax\"\n"
+ "6:\n"
+ " testb %[bitnum],%[cap_byte]\n"
+ " jnz %l[t_yes]\n"
+ " jmp %l[t_no]\n"
+ ".previous\n"
: : [feature] "i" (bit),
- [always] "i" (X86_FEATURE_ALWAYS),
[bitnum] "i" (1 << (bit & 7)),
[cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3])
: : t_yes, t_no);
#define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */
#define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */
#define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */
+#define X86_FEATURE_PVUNLOCK ( 8*32+20) /* "" PV unlock function */
+#define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* "" PV vcpu_is_preempted function */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
#define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */
#define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* #AC for split lock */
#define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */
+#define X86_FEATURE_SGX1 (11*32+ 8) /* "" Basic SGX */
+#define X86_FEATURE_SGX2 (11*32+ 9) /* "" SGX Enclave Dynamic Memory Management (EDMM) */
/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */
#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* POPCNT for vectors of DW/QW */
#define X86_FEATURE_LA57 (16*32+16) /* 5-level page tables */
#define X86_FEATURE_RDPID (16*32+22) /* RDPID instruction */
+#define X86_FEATURE_BUS_LOCK_DETECT (16*32+24) /* Bus Lock detect */
#define X86_FEATURE_CLDEMOTE (16*32+25) /* CLDEMOTE instruction */
#define X86_FEATURE_MOVDIRI (16*32+27) /* MOVDIRI instruction */
#define X86_FEATURE_MOVDIR64B (16*32+28) /* MOVDIR64B instruction */
*
* The decision process for determining the results are:
*
- * CPU: | lacks NX* | has NX, ia32 | has NX, x86_64 |
- * ELF: | | | |
+ * CPU: | lacks NX* | has NX, ia32 | has NX, x86_64 |
+ * ELF: | | | |
* ---------------------|------------|------------------|----------------|
- * missing PT_GNU_STACK | exec-all | exec-all | exec-none |
- * PT_GNU_STACK == RWX | exec-stack | exec-stack | exec-stack |
- * PT_GNU_STACK == RW | exec-none | exec-none | exec-none |
+ * missing PT_GNU_STACK | exec-all | exec-all | exec-none |
+ * PT_GNU_STACK == RWX | exec-stack | exec-stack | exec-stack |
+ * PT_GNU_STACK == RW | exec-none | exec-none | exec-none |
*
* exec-all : all PROT_READ user mappings are executable, except when
* backed by files on a noexec-filesystem.
#ifndef _ASM_X86_ENTRY_COMMON_H
#define _ASM_X86_ENTRY_COMMON_H
+#include <linux/randomize_kstack.h>
#include <linux/user-return-notifier.h>
#include <asm/nospec-branch.h>
*/
current_thread_info()->status &= ~(TS_COMPAT | TS_I386_REGS_POKED);
#endif
+
+ /*
+ * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(),
+ * but not enough for x86 stack utilization comfort. To keep
+ * reasonable stack head room, reduce the maximum offset to 8 bits.
+ *
+ * The actual entropy will be further reduced by the compiler when
+ * applying stack alignment constraints (see cc_stack_align4/8 in
+ * arch/x86/Makefile), which will remove the 3 (x86_64) or 2 (ia32)
+ * low bits from any entropy chosen here.
+ *
+ * Therefore, final stack offset entropy will be 5 (x86_64) or
+ * 6 (ia32) bits.
+ */
+ choose_random_kstack_offset(rdtsc() & 0xFF);
}
#define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare
/*
* Dummy trap number so the low level ASM macro vector number checks do not
* match which results in emitting plain IDTENTRY stubs without bells and
- * whistels.
+ * whistles.
*/
#define X86_TRAP_OTHER 0xFFFF
int insn_get_code_seg_params(struct pt_regs *regs);
int insn_fetch_from_user(struct pt_regs *regs,
unsigned char buf[MAX_INSN_SIZE]);
+int insn_fetch_from_user_inatomic(struct pt_regs *regs,
+ unsigned char buf[MAX_INSN_SIZE]);
bool insn_decode(struct insn *insn, struct pt_regs *regs,
unsigned char buf[MAX_INSN_SIZE], int buf_size);
#define MKTME_INVALID_ENC_ALG 4
#define MKTME_DEVICE_BUSY 5
-/* Hardware requires the structure to be 256 byte alinged. Otherwise #GP(0). */
+/* Hardware requires the structure to be 256 byte aligned. Otherwise #GP(0). */
struct mktme_key_program {
u16 keyid;
u32 keyid_ctrl;
#define _ASM_X86_INTEL_PT_H
#define PT_CPUID_LEAVES 2
-#define PT_CPUID_REGS_NUM 4 /* number of regsters (eax, ebx, ecx, edx) */
+#define PT_CPUID_REGS_NUM 4 /* number of registers (eax, ebx, ecx, edx) */
enum pt_capabilities {
PT_CAP_max_subleaf = 0,
/*
* ISA I/O bus memory addresses are 1:1 with the physical address.
* However, we truncate the address to unsigned int to avoid undesirable
- * promitions in legacy drivers.
+ * promotions in legacy drivers.
*/
static inline unsigned int isa_virt_to_bus(volatile void *address)
{
/*
* Macro to invoke __do_softirq on the irq stack. This is only called from
- * task context when bottom halfs are about to be reenabled and soft
+ * task context when bottom halves are about to be reenabled and soft
* interrupts are pending to be processed. The interrupt stack cannot be in
* use here.
*/
}
#else
-#define ENABLE_INTERRUPTS(x) sti
-#define DISABLE_INTERRUPTS(x) cli
-
#ifdef CONFIG_X86_64
#ifdef CONFIG_DEBUG_ENTRY
-#define SAVE_FLAGS(x) pushfq; popq %rax
+#define SAVE_FLAGS pushfq; popq %rax
#endif
#define INTERRUPT_RETURN jmp native_iret
-#else
-#define INTERRUPT_RETURN iret
#endif
#endif /* __ASSEMBLY__ */
else
set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT));
- /* Flush this CPU's TLB. */
+ /*
+ * Flush this CPU's TLB, assuming whoever did the allocation/free is
+ * likely to continue running on this CPU.
+ */
+ preempt_disable();
flush_tlb_one_kernel(addr);
+ preempt_enable();
return true;
}
u64 options;
};
+/* Current state of Hyper-V TSC page clocksource */
+enum hv_tsc_page_status {
+ /* TSC page was not set up or disabled */
+ HV_TSC_PAGE_UNSET = 0,
+ /* TSC page MSR was written by the guest, update pending */
+ HV_TSC_PAGE_GUEST_CHANGED,
+ /* TSC page MSR was written by KVM userspace, update pending */
+ HV_TSC_PAGE_HOST_CHANGED,
+ /* TSC page was properly set up and is currently active */
+ HV_TSC_PAGE_SET,
+ /* TSC page is currently being updated and therefore is inactive */
+ HV_TSC_PAGE_UPDATING,
+ /* TSC page was set up with an inaccessible GPA */
+ HV_TSC_PAGE_BROKEN,
+};
+
/* Hyper-V emulation context */
struct kvm_hv {
struct mutex hv_lock;
u64 hv_guest_os_id;
u64 hv_hypercall;
u64 hv_tsc_page;
+ enum hv_tsc_page_status hv_tsc_page_status;
/* Hyper-v based guest crash (NT kernel bugcheck) parameters */
u64 hv_crash_param[HV_X64_MSR_CRASH_PARAMS];
KVM_IRQCHIP_SPLIT, /* created with KVM_CAP_SPLIT_IRQCHIP */
};
+struct kvm_x86_msr_filter {
+ u8 count;
+ bool default_allow:1;
+ struct msr_bitmap_range ranges[16];
+};
+
#define APICV_INHIBIT_REASON_DISABLE 0
#define APICV_INHIBIT_REASON_HYPERV 1
#define APICV_INHIBIT_REASON_NESTED 2
struct kvm_pit *vpit;
atomic_t vapics_in_nmi_mode;
struct mutex apic_map_lock;
- struct kvm_apic_map *apic_map;
+ struct kvm_apic_map __rcu *apic_map;
atomic_t apic_map_dirty;
bool apic_access_page_done;
bool guest_can_read_msr_platform_info;
bool exception_payload_enabled;
+ bool bus_lock_detection_enabled;
+
/* Deflect RDMSR and WRMSR to user space when they trigger a #GP */
u32 user_space_msr_mask;
+ struct kvm_x86_msr_filter __rcu *msr_filter;
- struct {
- u8 count;
- bool default_allow:1;
- struct msr_bitmap_range ranges[16];
- } msr_filter;
-
- bool bus_lock_detection_enabled;
-
- struct kvm_pmu_event_filter *pmu_event_filter;
+ struct kvm_pmu_event_filter __rcu *pmu_event_filter;
struct task_struct *nx_lpage_recovery_thread;
#ifdef CONFIG_X86_64
/*
* EMULTYPE_NO_DECODE - Set when re-emulating an instruction (after completing
* userspace I/O) to indicate that the emulation context
- * should be resued as is, i.e. skip initialization of
+ * should be reused as is, i.e. skip initialization of
* emulation context, instruction fetch and decode.
*
* EMULTYPE_TRAP_UD - Set when emulating an intercepted #UD from hardware.
*
* EMULTYPE_VMWARE_GP - Set when emulating an intercepted #GP for VMware
* backdoor emulation, which is opt in via module param.
- * VMware backoor emulation handles select instructions
+ * VMware backdoor emulation handles select instructions
* and reinjects the #GP for all other cases.
*
* EMULTYPE_PF - Set when emulating MMIO by way of an intercepted #PF, in which
#define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */
#define DEBUGCTLMSR_BTF_SHIFT 1
#define DEBUGCTLMSR_BTF (1UL << 1) /* single-step on branches */
+#define DEBUGCTLMSR_BUS_LOCK_DETECT (1UL << 2)
#define DEBUGCTLMSR_TR (1UL << 6)
#define DEBUGCTLMSR_BTS (1UL << 7)
#define DEBUGCTLMSR_BTINT (1UL << 8)
#define MSR_IA32_APICBASE_ENABLE (1<<11)
#define MSR_IA32_APICBASE_BASE (0xfffff<<12)
-#define MSR_IA32_TSCDEADLINE 0x000006e0
-
#define MSR_IA32_UCODE_WRITE 0x00000079
#define MSR_IA32_UCODE_REV 0x0000008b
#include <linux/objtool.h>
#include <asm/alternative.h>
-#include <asm/alternative-asm.h>
#include <asm/cpufeatures.h>
#include <asm/msr-index.h>
#include <asm/unwind_hints.h>
/*
* Google experimented with loop-unrolling and this turned out to be
- * the optimal version — two calls, each with their own speculation
+ * the optimal version - two calls, each with their own speculation
* trap should their return address end up getting used, in a loop.
*/
#define __FILL_RETURN_BUFFER(reg, nr, sp) \
#include <linux/bug.h>
#include <linux/types.h>
#include <linux/cpumask.h>
+#include <linux/static_call_types.h>
#include <asm/frame.h>
-static inline unsigned long long paravirt_sched_clock(void)
+u64 dummy_steal_clock(int cpu);
+u64 dummy_sched_clock(void);
+
+DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock);
+DECLARE_STATIC_CALL(pv_sched_clock, dummy_sched_clock);
+
+void paravirt_set_sched_clock(u64 (*func)(void));
+
+static inline u64 paravirt_sched_clock(void)
{
- return PVOP_CALL0(unsigned long long, time.sched_clock);
+ return static_call(pv_sched_clock)();
}
struct static_key;
static inline u64 paravirt_steal_clock(int cpu)
{
- return PVOP_CALL1(u64, time.steal_clock, cpu);
+ return static_call(pv_steal_clock)(cpu);
}
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+void __init paravirt_set_cap(void);
+#endif
+
/* The paravirtualized I/O functions */
static inline void slow_down_io(void)
{
static inline unsigned long read_cr2(void)
{
- return PVOP_CALLEE0(unsigned long, mmu.read_cr2);
+ return PVOP_ALT_CALLEE0(unsigned long, mmu.read_cr2,
+ "mov %%cr2, %%rax;",
+ ALT_NOT(X86_FEATURE_XENPV));
}
static inline void write_cr2(unsigned long x)
static inline unsigned long __read_cr3(void)
{
- return PVOP_CALL0(unsigned long, mmu.read_cr3);
+ return PVOP_ALT_CALL0(unsigned long, mmu.read_cr3,
+ "mov %%cr3, %%rax;", ALT_NOT(X86_FEATURE_XENPV));
}
static inline void write_cr3(unsigned long x)
{
- PVOP_VCALL1(mmu.write_cr3, x);
+ PVOP_ALT_VCALL1(mmu.write_cr3, x,
+ "mov %%rdi, %%cr3", ALT_NOT(X86_FEATURE_XENPV));
}
static inline void __write_cr4(unsigned long x)
static inline void wbinvd(void)
{
- PVOP_VCALL0(cpu.wbinvd);
+ PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT(X86_FEATURE_XENPV));
}
static inline u64 paravirt_read_msr(unsigned msr)
static inline pte_t __pte(pteval_t val)
{
- return (pte_t) { PVOP_CALLEE1(pteval_t, mmu.make_pte, val) };
+ return (pte_t) { PVOP_ALT_CALLEE1(pteval_t, mmu.make_pte, val,
+ "mov %%rdi, %%rax",
+ ALT_NOT(X86_FEATURE_XENPV)) };
}
static inline pteval_t pte_val(pte_t pte)
{
- return PVOP_CALLEE1(pteval_t, mmu.pte_val, pte.pte);
+ return PVOP_ALT_CALLEE1(pteval_t, mmu.pte_val, pte.pte,
+ "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
}
static inline pgd_t __pgd(pgdval_t val)
{
- return (pgd_t) { PVOP_CALLEE1(pgdval_t, mmu.make_pgd, val) };
+ return (pgd_t) { PVOP_ALT_CALLEE1(pgdval_t, mmu.make_pgd, val,
+ "mov %%rdi, %%rax",
+ ALT_NOT(X86_FEATURE_XENPV)) };
}
static inline pgdval_t pgd_val(pgd_t pgd)
{
- return PVOP_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd);
+ return PVOP_ALT_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd,
+ "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
}
#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
static inline pmd_t __pmd(pmdval_t val)
{
- return (pmd_t) { PVOP_CALLEE1(pmdval_t, mmu.make_pmd, val) };
+ return (pmd_t) { PVOP_ALT_CALLEE1(pmdval_t, mmu.make_pmd, val,
+ "mov %%rdi, %%rax",
+ ALT_NOT(X86_FEATURE_XENPV)) };
}
static inline pmdval_t pmd_val(pmd_t pmd)
{
- return PVOP_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd);
+ return PVOP_ALT_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd,
+ "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
}
static inline void set_pud(pud_t *pudp, pud_t pud)
{
pudval_t ret;
- ret = PVOP_CALLEE1(pudval_t, mmu.make_pud, val);
+ ret = PVOP_ALT_CALLEE1(pudval_t, mmu.make_pud, val,
+ "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
return (pud_t) { ret };
}
static inline pudval_t pud_val(pud_t pud)
{
- return PVOP_CALLEE1(pudval_t, mmu.pud_val, pud.pud);
+ return PVOP_ALT_CALLEE1(pudval_t, mmu.pud_val, pud.pud,
+ "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
}
static inline void pud_clear(pud_t *pudp)
static inline p4d_t __p4d(p4dval_t val)
{
- p4dval_t ret = PVOP_CALLEE1(p4dval_t, mmu.make_p4d, val);
+ p4dval_t ret = PVOP_ALT_CALLEE1(p4dval_t, mmu.make_p4d, val,
+ "mov %%rdi, %%rax",
+ ALT_NOT(X86_FEATURE_XENPV));
return (p4d_t) { ret };
}
static inline p4dval_t p4d_val(p4d_t p4d)
{
- return PVOP_CALLEE1(p4dval_t, mmu.p4d_val, p4d.p4d);
+ return PVOP_ALT_CALLEE1(p4dval_t, mmu.p4d_val, p4d.p4d,
+ "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV));
}
static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd)
static __always_inline void pv_queued_spin_unlock(struct qspinlock *lock)
{
- PVOP_VCALLEE1(lock.queued_spin_unlock, lock);
+ PVOP_ALT_VCALLEE1(lock.queued_spin_unlock, lock,
+ "movb $0, (%%" _ASM_ARG1 ");",
+ ALT_NOT(X86_FEATURE_PVUNLOCK));
}
static __always_inline void pv_wait(u8 *ptr, u8 val)
static __always_inline bool pv_vcpu_is_preempted(long cpu)
{
- return PVOP_CALLEE1(bool, lock.vcpu_is_preempted, cpu);
+ return PVOP_ALT_CALLEE1(bool, lock.vcpu_is_preempted, cpu,
+ "xor %%" _ASM_AX ", %%" _ASM_AX ";",
+ ALT_NOT(X86_FEATURE_VCPUPREEMPT));
}
void __raw_callee_save___native_queued_spin_unlock(struct qspinlock *lock);
#ifdef CONFIG_PARAVIRT_XXL
static inline notrace unsigned long arch_local_save_flags(void)
{
- return PVOP_CALLEE0(unsigned long, irq.save_fl);
+ return PVOP_ALT_CALLEE0(unsigned long, irq.save_fl, "pushf; pop %%rax;",
+ ALT_NOT(X86_FEATURE_XENPV));
}
static inline notrace void arch_local_irq_disable(void)
{
- PVOP_VCALLEE0(irq.irq_disable);
+ PVOP_ALT_VCALLEE0(irq.irq_disable, "cli;", ALT_NOT(X86_FEATURE_XENPV));
}
static inline notrace void arch_local_irq_enable(void)
{
- PVOP_VCALLEE0(irq.irq_enable);
+ PVOP_ALT_VCALLEE0(irq.irq_enable, "sti;", ALT_NOT(X86_FEATURE_XENPV));
}
static inline notrace unsigned long arch_local_irq_save(void)
.popsection
-#define COND_PUSH(set, mask, reg) \
- .if ((~(set)) & mask); push %reg; .endif
-#define COND_POP(set, mask, reg) \
- .if ((~(set)) & mask); pop %reg; .endif
-
#ifdef CONFIG_X86_64
-
-#define PV_SAVE_REGS(set) \
- COND_PUSH(set, CLBR_RAX, rax); \
- COND_PUSH(set, CLBR_RCX, rcx); \
- COND_PUSH(set, CLBR_RDX, rdx); \
- COND_PUSH(set, CLBR_RSI, rsi); \
- COND_PUSH(set, CLBR_RDI, rdi); \
- COND_PUSH(set, CLBR_R8, r8); \
- COND_PUSH(set, CLBR_R9, r9); \
- COND_PUSH(set, CLBR_R10, r10); \
- COND_PUSH(set, CLBR_R11, r11)
-#define PV_RESTORE_REGS(set) \
- COND_POP(set, CLBR_R11, r11); \
- COND_POP(set, CLBR_R10, r10); \
- COND_POP(set, CLBR_R9, r9); \
- COND_POP(set, CLBR_R8, r8); \
- COND_POP(set, CLBR_RDI, rdi); \
- COND_POP(set, CLBR_RSI, rsi); \
- COND_POP(set, CLBR_RDX, rdx); \
- COND_POP(set, CLBR_RCX, rcx); \
- COND_POP(set, CLBR_RAX, rax)
+#ifdef CONFIG_PARAVIRT_XXL
#define PARA_PATCH(off) ((off) / 8)
#define PARA_SITE(ptype, ops) _PVSITE(ptype, ops, .quad, 8)
#define PARA_INDIRECT(addr) *addr(%rip)
-#else
-#define PV_SAVE_REGS(set) \
- COND_PUSH(set, CLBR_EAX, eax); \
- COND_PUSH(set, CLBR_EDI, edi); \
- COND_PUSH(set, CLBR_ECX, ecx); \
- COND_PUSH(set, CLBR_EDX, edx)
-#define PV_RESTORE_REGS(set) \
- COND_POP(set, CLBR_EDX, edx); \
- COND_POP(set, CLBR_ECX, ecx); \
- COND_POP(set, CLBR_EDI, edi); \
- COND_POP(set, CLBR_EAX, eax)
-
-#define PARA_PATCH(off) ((off) / 4)
-#define PARA_SITE(ptype, ops) _PVSITE(ptype, ops, .long, 4)
-#define PARA_INDIRECT(addr) *%cs:addr
-#endif
-#ifdef CONFIG_PARAVIRT_XXL
#define INTERRUPT_RETURN \
- PARA_SITE(PARA_PATCH(PV_CPU_iret), \
- ANNOTATE_RETPOLINE_SAFE; \
- jmp PARA_INDIRECT(pv_ops+PV_CPU_iret);)
-
-#define DISABLE_INTERRUPTS(clobbers) \
- PARA_SITE(PARA_PATCH(PV_IRQ_irq_disable), \
- PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
- ANNOTATE_RETPOLINE_SAFE; \
- call PARA_INDIRECT(pv_ops+PV_IRQ_irq_disable); \
- PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
-
-#define ENABLE_INTERRUPTS(clobbers) \
- PARA_SITE(PARA_PATCH(PV_IRQ_irq_enable), \
- PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
- ANNOTATE_RETPOLINE_SAFE; \
- call PARA_INDIRECT(pv_ops+PV_IRQ_irq_enable); \
- PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
-#endif
+ ANNOTATE_RETPOLINE_SAFE; \
+ ALTERNATIVE_TERNARY("jmp *paravirt_iret(%rip);", \
+ X86_FEATURE_XENPV, "jmp xen_iret;", "jmp native_iret;")
-#ifdef CONFIG_X86_64
-#ifdef CONFIG_PARAVIRT_XXL
#ifdef CONFIG_DEBUG_ENTRY
-#define SAVE_FLAGS(clobbers) \
- PARA_SITE(PARA_PATCH(PV_IRQ_save_fl), \
- PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
- ANNOTATE_RETPOLINE_SAFE; \
- call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl); \
- PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
+.macro PARA_IRQ_save_fl
+ PARA_SITE(PARA_PATCH(PV_IRQ_save_fl),
+ ANNOTATE_RETPOLINE_SAFE;
+ call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl);)
+.endm
+
+#define SAVE_FLAGS ALTERNATIVE "PARA_IRQ_save_fl;", "pushf; pop %rax;", \
+ ALT_NOT(X86_FEATURE_XENPV)
#endif
#endif /* CONFIG_PARAVIRT_XXL */
#endif /* CONFIG_X86_64 */
{
}
#endif
+
+#ifndef CONFIG_PARAVIRT_SPINLOCKS
+static inline void paravirt_set_cap(void)
+{
+}
+#endif
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_PARAVIRT_H */
#define _ASM_X86_PARAVIRT_TYPES_H
/* Bitmask of what can be clobbered: usually at least eax. */
-#define CLBR_NONE 0
#define CLBR_EAX (1 << 0)
#define CLBR_ECX (1 << 1)
#define CLBR_EDX (1 << 2)
#define CLBR_ARG_REGS (CLBR_EAX | CLBR_EDX | CLBR_ECX)
#define CLBR_RET_REG (CLBR_EAX | CLBR_EDX)
-#define CLBR_SCRATCH (0)
#else
#define CLBR_RAX CLBR_EAX
#define CLBR_RCX CLBR_ECX
#define CLBR_ARG_REGS (CLBR_RDI | CLBR_RSI | CLBR_RDX | \
CLBR_RCX | CLBR_R8 | CLBR_R9)
#define CLBR_RET_REG (CLBR_RAX)
-#define CLBR_SCRATCH (CLBR_R10 | CLBR_R11)
#endif /* X86_64 */
-#define CLBR_CALLEE_SAVE ((CLBR_ARG_REGS | CLBR_SCRATCH) & ~CLBR_RET_REG)
-
#ifndef __ASSEMBLY__
#include <asm/desc_defs.h>
const char *name;
};
-struct pv_init_ops {
- /*
- * Patch may replace one of the defined code sequences with
- * arbitrary code, subject to the same register constraints.
- * This generally means the code is not free to clobber any
- * registers other than EAX. The patch function should return
- * the number of bytes of code generated, as we nop pad the
- * rest in generic code.
- */
- unsigned (*patch)(u8 type, void *insn_buff,
- unsigned long addr, unsigned len);
-} __no_randomize_layout;
-
#ifdef CONFIG_PARAVIRT_XXL
struct pv_lazy_ops {
/* Set deferred update mode, used for batching operations. */
} __no_randomize_layout;
#endif
-struct pv_time_ops {
- unsigned long long (*sched_clock)(void);
- unsigned long long (*steal_clock)(int cpu);
-} __no_randomize_layout;
-
struct pv_cpu_ops {
/* hooks for various privileged instructions */
void (*io_delay)(void);
u64 (*read_pmc)(int counter);
- /* Normal iret. Jump to this with the standard iret stack
- frame set up. */
- void (*iret)(void);
-
void (*start_context_switch)(struct task_struct *prev);
void (*end_context_switch)(struct task_struct *next);
#endif
* number for each function using the offset which we use to indicate
* what to patch. */
struct paravirt_patch_template {
- struct pv_init_ops init;
- struct pv_time_ops time;
struct pv_cpu_ops cpu;
struct pv_irq_ops irq;
struct pv_mmu_ops mmu;
extern struct pv_info pv_info;
extern struct paravirt_patch_template pv_ops;
+extern void (*paravirt_iret)(void);
#define PARAVIRT_PATCH(x) \
(offsetof(struct paravirt_patch_template, x) / sizeof(void *))
/* Simple instruction patching code. */
#define NATIVE_LABEL(a,x,b) "\n\t.globl " a #x "_" #b "\n" a #x "_" #b ":\n\t"
-unsigned paravirt_patch_ident_64(void *insn_buff, unsigned len);
-unsigned paravirt_patch_default(u8 type, void *insn_buff, unsigned long addr, unsigned len);
-unsigned paravirt_patch_insns(void *insn_buff, unsigned len, const char *start, const char *end);
-
-unsigned native_patch(u8 type, void *insn_buff, unsigned long addr, unsigned len);
+unsigned int paravirt_patch(u8 type, void *insn_buff, unsigned long addr, unsigned int len);
int paravirt_disable_iospace(void);
* on the stack. All caller-save registers (eax,edx,ecx) are expected
* to be modified (either clobbered or used for return values).
* X86_64, on the other hand, already specifies a register-based calling
- * conventions, returning at %rax, with parameteres going on %rdi, %rsi,
+ * conventions, returning at %rax, with parameters going on %rdi, %rsi,
* %rdx, and %rcx. Note that for this reason, x86_64 does not need any
* special handling for dealing with 4 arguments, unlike i386.
* However, x86_64 also have to clobber all caller saved registers, which
* makes sure the incoming and outgoing types are always correct.
*/
#ifdef CONFIG_X86_32
-#define PVOP_VCALL_ARGS \
+#define PVOP_CALL_ARGS \
unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx;
-#define PVOP_CALL_ARGS PVOP_VCALL_ARGS
-
#define PVOP_CALL_ARG1(x) "a" ((unsigned long)(x))
#define PVOP_CALL_ARG2(x) "d" ((unsigned long)(x))
#define PVOP_CALL_ARG3(x) "c" ((unsigned long)(x))
#define VEXTRA_CLOBBERS
#else /* CONFIG_X86_64 */
/* [re]ax isn't an arg, but the return val */
-#define PVOP_VCALL_ARGS \
+#define PVOP_CALL_ARGS \
unsigned long __edi = __edi, __esi = __esi, \
__edx = __edx, __ecx = __ecx, __eax = __eax;
-#define PVOP_CALL_ARGS PVOP_VCALL_ARGS
-
#define PVOP_CALL_ARG1(x) "D" ((unsigned long)(x))
#define PVOP_CALL_ARG2(x) "S" ((unsigned long)(x))
#define PVOP_CALL_ARG3(x) "d" ((unsigned long)(x))
#define PVOP_TEST_NULL(op) ((void)pv_ops.op)
#endif
-#define PVOP_RETMASK(rettype) \
+#define PVOP_RETVAL(rettype) \
({ unsigned long __mask = ~0UL; \
+ BUILD_BUG_ON(sizeof(rettype) > sizeof(unsigned long)); \
switch (sizeof(rettype)) { \
case 1: __mask = 0xffUL; break; \
case 2: __mask = 0xffffUL; break; \
case 4: __mask = 0xffffffffUL; break; \
default: break; \
} \
- __mask; \
+ __mask & __eax; \
})
-#define ____PVOP_CALL(rettype, op, clbr, call_clbr, extra_clbr, \
- pre, post, ...) \
+#define ____PVOP_CALL(ret, op, clbr, call_clbr, extra_clbr, ...) \
({ \
- rettype __ret; \
PVOP_CALL_ARGS; \
PVOP_TEST_NULL(op); \
- /* This is 32-bit specific, but is okay in 64-bit */ \
- /* since this condition will never hold */ \
- if (sizeof(rettype) > sizeof(unsigned long)) { \
- asm volatile(pre \
- paravirt_alt(PARAVIRT_CALL) \
- post \
- : call_clbr, ASM_CALL_CONSTRAINT \
- : paravirt_type(op), \
- paravirt_clobber(clbr), \
- ##__VA_ARGS__ \
- : "memory", "cc" extra_clbr); \
- __ret = (rettype)((((u64)__edx) << 32) | __eax); \
- } else { \
- asm volatile(pre \
- paravirt_alt(PARAVIRT_CALL) \
- post \
- : call_clbr, ASM_CALL_CONSTRAINT \
- : paravirt_type(op), \
- paravirt_clobber(clbr), \
- ##__VA_ARGS__ \
- : "memory", "cc" extra_clbr); \
- __ret = (rettype)(__eax & PVOP_RETMASK(rettype)); \
- } \
- __ret; \
+ asm volatile(paravirt_alt(PARAVIRT_CALL) \
+ : call_clbr, ASM_CALL_CONSTRAINT \
+ : paravirt_type(op), \
+ paravirt_clobber(clbr), \
+ ##__VA_ARGS__ \
+ : "memory", "cc" extra_clbr); \
+ ret; \
})
-#define __PVOP_CALL(rettype, op, pre, post, ...) \
- ____PVOP_CALL(rettype, op, CLBR_ANY, PVOP_CALL_CLOBBERS, \
- EXTRA_CLOBBERS, pre, post, ##__VA_ARGS__)
-
-#define __PVOP_CALLEESAVE(rettype, op, pre, post, ...) \
- ____PVOP_CALL(rettype, op.func, CLBR_RET_REG, \
- PVOP_CALLEE_CLOBBERS, , \
- pre, post, ##__VA_ARGS__)
-
-
-#define ____PVOP_VCALL(op, clbr, call_clbr, extra_clbr, pre, post, ...) \
+#define ____PVOP_ALT_CALL(ret, op, alt, cond, clbr, call_clbr, \
+ extra_clbr, ...) \
({ \
- PVOP_VCALL_ARGS; \
+ PVOP_CALL_ARGS; \
PVOP_TEST_NULL(op); \
- asm volatile(pre \
- paravirt_alt(PARAVIRT_CALL) \
- post \
+ asm volatile(ALTERNATIVE(paravirt_alt(PARAVIRT_CALL), \
+ alt, cond) \
: call_clbr, ASM_CALL_CONSTRAINT \
: paravirt_type(op), \
paravirt_clobber(clbr), \
##__VA_ARGS__ \
: "memory", "cc" extra_clbr); \
+ ret; \
})
-#define __PVOP_VCALL(op, pre, post, ...) \
- ____PVOP_VCALL(op, CLBR_ANY, PVOP_VCALL_CLOBBERS, \
- VEXTRA_CLOBBERS, \
- pre, post, ##__VA_ARGS__)
+#define __PVOP_CALL(rettype, op, ...) \
+ ____PVOP_CALL(PVOP_RETVAL(rettype), op, CLBR_ANY, \
+ PVOP_CALL_CLOBBERS, EXTRA_CLOBBERS, ##__VA_ARGS__)
+
+#define __PVOP_ALT_CALL(rettype, op, alt, cond, ...) \
+ ____PVOP_ALT_CALL(PVOP_RETVAL(rettype), op, alt, cond, CLBR_ANY,\
+ PVOP_CALL_CLOBBERS, EXTRA_CLOBBERS, \
+ ##__VA_ARGS__)
+
+#define __PVOP_CALLEESAVE(rettype, op, ...) \
+ ____PVOP_CALL(PVOP_RETVAL(rettype), op.func, CLBR_RET_REG, \
+ PVOP_CALLEE_CLOBBERS, , ##__VA_ARGS__)
+
+#define __PVOP_ALT_CALLEESAVE(rettype, op, alt, cond, ...) \
+ ____PVOP_ALT_CALL(PVOP_RETVAL(rettype), op.func, alt, cond, \
+ CLBR_RET_REG, PVOP_CALLEE_CLOBBERS, , ##__VA_ARGS__)
+
+
+#define __PVOP_VCALL(op, ...) \
+ (void)____PVOP_CALL(, op, CLBR_ANY, PVOP_VCALL_CLOBBERS, \
+ VEXTRA_CLOBBERS, ##__VA_ARGS__)
+
+#define __PVOP_ALT_VCALL(op, alt, cond, ...) \
+ (void)____PVOP_ALT_CALL(, op, alt, cond, CLBR_ANY, \
+ PVOP_VCALL_CLOBBERS, VEXTRA_CLOBBERS, \
+ ##__VA_ARGS__)
-#define __PVOP_VCALLEESAVE(op, pre, post, ...) \
- ____PVOP_VCALL(op.func, CLBR_RET_REG, \
- PVOP_VCALLEE_CLOBBERS, , \
- pre, post, ##__VA_ARGS__)
+#define __PVOP_VCALLEESAVE(op, ...) \
+ (void)____PVOP_CALL(, op.func, CLBR_RET_REG, \
+ PVOP_VCALLEE_CLOBBERS, , ##__VA_ARGS__)
+#define __PVOP_ALT_VCALLEESAVE(op, alt, cond, ...) \
+ (void)____PVOP_ALT_CALL(, op.func, alt, cond, CLBR_RET_REG, \
+ PVOP_VCALLEE_CLOBBERS, , ##__VA_ARGS__)
#define PVOP_CALL0(rettype, op) \
- __PVOP_CALL(rettype, op, "", "")
+ __PVOP_CALL(rettype, op)
#define PVOP_VCALL0(op) \
- __PVOP_VCALL(op, "", "")
+ __PVOP_VCALL(op)
+#define PVOP_ALT_CALL0(rettype, op, alt, cond) \
+ __PVOP_ALT_CALL(rettype, op, alt, cond)
+#define PVOP_ALT_VCALL0(op, alt, cond) \
+ __PVOP_ALT_VCALL(op, alt, cond)
#define PVOP_CALLEE0(rettype, op) \
- __PVOP_CALLEESAVE(rettype, op, "", "")
+ __PVOP_CALLEESAVE(rettype, op)
#define PVOP_VCALLEE0(op) \
- __PVOP_VCALLEESAVE(op, "", "")
+ __PVOP_VCALLEESAVE(op)
+#define PVOP_ALT_CALLEE0(rettype, op, alt, cond) \
+ __PVOP_ALT_CALLEESAVE(rettype, op, alt, cond)
+#define PVOP_ALT_VCALLEE0(op, alt, cond) \
+ __PVOP_ALT_VCALLEESAVE(op, alt, cond)
#define PVOP_CALL1(rettype, op, arg1) \
- __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1))
+ __PVOP_CALL(rettype, op, PVOP_CALL_ARG1(arg1))
#define PVOP_VCALL1(op, arg1) \
- __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1))
+ __PVOP_VCALL(op, PVOP_CALL_ARG1(arg1))
+#define PVOP_ALT_VCALL1(op, arg1, alt, cond) \
+ __PVOP_ALT_VCALL(op, alt, cond, PVOP_CALL_ARG1(arg1))
#define PVOP_CALLEE1(rettype, op, arg1) \
- __PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1))
+ __PVOP_CALLEESAVE(rettype, op, PVOP_CALL_ARG1(arg1))
#define PVOP_VCALLEE1(op, arg1) \
- __PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1))
+ __PVOP_VCALLEESAVE(op, PVOP_CALL_ARG1(arg1))
+#define PVOP_ALT_CALLEE1(rettype, op, arg1, alt, cond) \
+ __PVOP_ALT_CALLEESAVE(rettype, op, alt, cond, PVOP_CALL_ARG1(arg1))
+#define PVOP_ALT_VCALLEE1(op, arg1, alt, cond) \
+ __PVOP_ALT_VCALLEESAVE(op, alt, cond, PVOP_CALL_ARG1(arg1))
#define PVOP_CALL2(rettype, op, arg1, arg2) \
- __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \
- PVOP_CALL_ARG2(arg2))
+ __PVOP_CALL(rettype, op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2))
#define PVOP_VCALL2(op, arg1, arg2) \
- __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1), \
- PVOP_CALL_ARG2(arg2))
-
-#define PVOP_CALLEE2(rettype, op, arg1, arg2) \
- __PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \
- PVOP_CALL_ARG2(arg2))
-#define PVOP_VCALLEE2(op, arg1, arg2) \
- __PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1), \
- PVOP_CALL_ARG2(arg2))
-
+ __PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2))
#define PVOP_CALL3(rettype, op, arg1, arg2, arg3) \
- __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \
+ __PVOP_CALL(rettype, op, PVOP_CALL_ARG1(arg1), \
PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3))
#define PVOP_VCALL3(op, arg1, arg2, arg3) \
- __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1), \
+ __PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), \
PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3))
-/* This is the only difference in x86_64. We can make it much simpler */
-#ifdef CONFIG_X86_32
#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4) \
__PVOP_CALL(rettype, op, \
- "push %[_arg4];", "lea 4(%%esp),%%esp;", \
- PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \
- PVOP_CALL_ARG3(arg3), [_arg4] "mr" ((u32)(arg4)))
-#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4) \
- __PVOP_VCALL(op, \
- "push %[_arg4];", "lea 4(%%esp),%%esp;", \
- "0" ((u32)(arg1)), "1" ((u32)(arg2)), \
- "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4)))
-#else
-#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4) \
- __PVOP_CALL(rettype, op, "", "", \
PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \
PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4) \
- __PVOP_VCALL(op, "", "", \
- PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \
+ __PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \
PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
-#endif
/* Lazy mode for batching updates / context switch */
enum paravirt_lazy_mode {
/*
* clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
*
- * dst - pointer to pgd range anwhere on a pgd page
+ * dst - pointer to pgd range anywhere on a pgd page
* src - ""
* count - the number of pgds to copy.
*
struct x86_hw_tss {
u32 reserved1;
u64 sp0;
-
- /*
- * We store cpu_current_top_of_stack in sp1 so it's always accessible.
- * Linux does not use ring 1, so sp1 is not otherwise needed.
- */
u64 sp1;
/*
char stack[IRQ_STACK_SIZE];
} __aligned(IRQ_STACK_SIZE);
-#ifdef CONFIG_X86_32
DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack);
-#else
-/* The RO copy can't be accessed with this_cpu_xyz(), so use the RW copy. */
-#define cpu_current_top_of_stack cpu_tss_rw.x86_tss.sp1
-#endif
#ifdef CONFIG_X86_64
struct fixed_percpu_data {
struct io_bitmap *io_bitmap;
/*
- * IOPL. Priviledge level dependent I/O permission which is
+ * IOPL. Privilege level dependent I/O permission which is
* emulated via the I/O bitmap to prevent user space from disabling
* interrupts.
*/
*size = fpu_kernel_xstate_size;
}
-/*
- * Thread-synchronous status.
- *
- * This is different from the flags in that nobody else
- * ever touches our thread-synchronous status, so we don't
- * have to worry about atomic accesses.
- */
-#define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/
-
static inline void
native_load_sp0(unsigned long sp0)
{
#include <asm/ldt.h>
+struct task_struct;
+
/* misc architecture specific prototypes */
void syscall_init(void);
void entry_SYSENTER_compat(void);
void __end_entry_SYSENTER_compat(void);
void entry_SYSCALL_compat(void);
+void entry_SYSCALL_compat_safe_stack(void);
void entry_INT80_compat(void);
#ifdef CONFIG_XEN_PV
void xen_entry_INT80_compat(void);
#include <asm/paravirt_types.h>
#endif
+#include <asm/proto.h>
+
struct cpuinfo_x86;
struct task_struct;
#ifdef CONFIG_X86_64
#define current_user_stack_pointer() current_pt_regs()->sp
#define compat_user_stack_pointer() current_pt_regs()->sp
+
+static inline bool ip_within_syscall_gap(struct pt_regs *regs)
+{
+ bool ret = (regs->ip >= (unsigned long)entry_SYSCALL_64 &&
+ regs->ip < (unsigned long)entry_SYSCALL_64_safe_stack);
+
+#ifdef CONFIG_IA32_EMULATION
+ ret = ret || (regs->ip >= (unsigned long)entry_SYSCALL_compat &&
+ regs->ip < (unsigned long)entry_SYSCALL_compat_safe_stack);
+#endif
+
+ return ret;
+}
#endif
static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
/*
* The set_memory_* API can be used to change various attributes of a virtual
* address range. The attributes include:
- * Cachability : UnCached, WriteCombining, WriteThrough, WriteBack
- * Executability : eXeutable, NoteXecutable
+ * Cacheability : UnCached, WriteCombining, WriteThrough, WriteBack
+ * Executability : eXecutable, NoteXecutable
* Read/Write : ReadOnly, ReadWrite
* Presence : NotPresent
* Encryption : Encrypted, Decrypted
: : "i" (sz)); \
}
-/* Helper for reserving space for arrays of things */
-#define RESERVE_BRK_ARRAY(type, name, entries) \
- type *name; \
- RESERVE_BRK(name, sizeof(type) * entries)
-
extern void probe_roms(void);
#ifdef __i386__
/**
* Copyright(c) 2016-20 Intel Corporation.
*
- * Contains data structures defined by the SGX architecture. Data structures
- * defined by the Linux software stack should not be placed here.
+ * Intel Software Guard Extensions (SGX) support.
*/
-#ifndef _ASM_X86_SGX_ARCH_H
-#define _ASM_X86_SGX_ARCH_H
+#ifndef _ASM_X86_SGX_H
+#define _ASM_X86_SGX_H
#include <linux/bits.h>
#include <linux/types.h>
+/*
+ * This file contains both data structures defined by SGX architecture and Linux
+ * defined software data structures and functions. The two should not be mixed
+ * together for better readibility. The architectural definitions come first.
+ */
+
/* The SGX specific CPUID function. */
#define SGX_CPUID 0x12
/* EPC enumeration. */
/* The bitmask for the EPC section type. */
#define SGX_CPUID_EPC_MASK GENMASK(3, 0)
+enum sgx_encls_function {
+ ECREATE = 0x00,
+ EADD = 0x01,
+ EINIT = 0x02,
+ EREMOVE = 0x03,
+ EDGBRD = 0x04,
+ EDGBWR = 0x05,
+ EEXTEND = 0x06,
+ ELDU = 0x08,
+ EBLOCK = 0x09,
+ EPA = 0x0A,
+ EWB = 0x0B,
+ ETRACK = 0x0C,
+ EAUG = 0x0D,
+ EMODPR = 0x0E,
+ EMODT = 0x0F,
+};
+
/**
* enum sgx_return_code - The return code type for ENCLS, ENCLU and ENCLV
* %SGX_NOT_TRACKED: Previous ETRACK's shootdown sequence has not
* been completed yet.
+ * %SGX_CHILD_PRESENT SECS has child pages present in the EPC.
* %SGX_INVALID_EINITTOKEN: EINITTOKEN is invalid and enclave signer's
* public key does not match IA32_SGXLEPUBKEYHASH.
* %SGX_UNMASKED_EVENT: An unmasked event, e.g. INTR, was received
*/
enum sgx_return_code {
SGX_NOT_TRACKED = 11,
+ SGX_CHILD_PRESENT = 13,
SGX_INVALID_EINITTOKEN = 16,
SGX_UNMASKED_EVENT = 128,
};
* @header1: constant byte string
* @vendor: must be either 0x0000 or 0x8086
* @date: YYYYMMDD in BCD
- * @header2: costant byte string
+ * @header2: constant byte string
* @swdefined: software defined value
*/
struct sgx_sigstruct_header {
#define SGX_LAUNCH_TOKEN_SIZE 304
-#endif /* _ASM_X86_SGX_ARCH_H */
+/*
+ * Do not put any hardware-defined SGX structure representations below this
+ * comment!
+ */
+
+#ifdef CONFIG_X86_SGX_KVM
+int sgx_virt_ecreate(struct sgx_pageinfo *pageinfo, void __user *secs,
+ int *trapnr);
+int sgx_virt_einit(void __user *sigstruct, void __user *token,
+ void __user *secs, u64 *lepubkeyhash, int *trapnr);
+#endif
+
+int sgx_set_attribute(unsigned long *allowed_attributes,
+ unsigned int attribute_fd);
+
+#endif /* _ASM_X86_SGX_H */
#include <asm/nops.h>
#include <asm/cpufeatures.h>
+#include <asm/alternative.h>
/* "Raw" instruction opcodes */
#define __ASM_CLAC ".byte 0x0f,0x01,0xca"
#ifdef __ASSEMBLY__
-#include <asm/alternative-asm.h>
-
#ifdef CONFIG_X86_SMAP
#define ASM_CLAC \
#else /* __ASSEMBLY__ */
-#include <asm/alternative.h>
-
#ifdef CONFIG_X86_SMAP
static __always_inline void clac(void)
unsigned long flags;
asm volatile ("# smap_save\n\t"
- ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP)
- "pushf; pop %0; " __ASM_CLAC "\n\t"
- "1:"
+ ALTERNATIVE("", "pushf; pop %0; " __ASM_CLAC "\n\t",
+ X86_FEATURE_SMAP)
: "=rm" (flags) : : "memory", "cc");
return flags;
static __always_inline void smap_restore(unsigned long flags)
{
asm volatile ("# smap_restore\n\t"
- ALTERNATIVE("jmp 1f", "", X86_FEATURE_SMAP)
- "push %0; popf\n\t"
- "1:"
+ ALTERNATIVE("", "push %0; popf\n\t",
+ X86_FEATURE_SMAP)
: : "g" (flags) : "memory", "cc");
}
void play_dead_common(void);
void wbinvd_on_cpu(int cpu);
int wbinvd_on_all_cpus(void);
+void cond_wakeup_cpu0(void);
void native_smp_send_reschedule(int cpu);
void native_send_call_func_ipi(const struct cpumask *mask);
else
this_cpu_write(cpu_tss_rw.x86_tss.sp1, task->thread.sp0);
#else
- /*
- * x86-64 updates x86_tss.sp1 via cpu_current_top_of_stack. That
- * doesn't work on x86-32 because sp1 and
- * cpu_current_top_of_stack have different values (because of
- * the non-zero stack-padding on 32bit).
- */
+ /* Xen PV enters the kernel on the thread stack. */
if (static_cpu_has(X86_FEATURE_XENPV))
load_sp0(task_top_of_stack(task));
#endif
}
#define __COND_SYSCALL(abi, name) \
+ __weak long __##abi##_##name(const struct pt_regs *__unused); \
__weak long __##abi##_##name(const struct pt_regs *__unused) \
{ \
return sys_ni_syscall(); \
#endif
}
-#else /* !__ASSEMBLY__ */
-
-#ifdef CONFIG_X86_64
-# define cpu_current_top_of_stack (cpu_tss_rw + TSS_sp1)
-#endif
+#endif /* !__ASSEMBLY__ */
-#endif
+/*
+ * Thread-synchronous status.
+ *
+ * This is different from the flags in that nobody else
+ * ever touches our thread-synchronous status, so we don't
+ * have to worry about atomic accesses.
+ */
+#define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/
+#ifndef __ASSEMBLY__
#ifdef CONFIG_COMPAT
#define TS_I386_REGS_POKED 0x0004 /* regs poked by 32-bit ptracer */
+
+#define arch_set_restart_data(restart) \
+ do { restart->arch_data = current_thread_info()->status; } while (0)
+
#endif
-#ifndef __ASSEMBLY__
#ifdef CONFIG_X86_32
#define in_ia32_syscall() true
#ifndef _ASM_UV_GEO_H
#define _ASM_UV_GEO_H
-/* Type declaractions */
+/* Type declarations */
/* Size of a geoid_s structure (must be before decl. of geoid_u) */
#define GEOID_SIZE 8
*
* Note there are NO leds on a UV system. This register is only
* used by the system controller to monitor system-wide operation.
- * There are 64 regs per node. With Nahelem cpus (2 cores per node,
+ * There are 64 regs per node. With Nehalem cpus (2 cores per node,
* 8 cpus per core, 2 threads per cpu) there are 32 cpu threads on
* a node.
*
#endif
/*
- * The maximum amount of extra memory compared to the base size. The
- * main scaling factor is the size of struct page. At extreme ratios
- * of base:extra, all the base memory can be filled with page
- * structures for the extra memory, leaving no space for anything
- * else.
- *
- * 10x seems like a reasonable balance between scaling flexibility and
- * leaving a practically usable system.
- */
-#define XEN_EXTRA_MEM_RATIO (10)
-
-/*
* Helper functions to write or read unsigned long values to/from
* memory, when the access may fault.
*/
* handling of page tables.
*
* These enums should only ever be used by x86 code, and the code that uses
- * it should be well contained and compartamentalized.
+ * it should be well contained and compartmentalized.
*
* KVM and Xen HVM do not have a subarch as these are expected to follow
* standard x86 boot entries. If there is a genuine need for "hypervisor" type
* @X86_SUBARCH_XEN: Used for Xen guest types which follow the PV boot path,
* which start at asm startup_xen() entry point and later jump to the C
* xen_start_kernel() entry point. Both domU and dom0 type of guests are
- * currently supportd through this PV boot path.
+ * currently supported through this PV boot path.
* @X86_SUBARCH_INTEL_MID: Used for Intel MID (Mobile Internet Device) platform
* systems which do not have the PCI legacy interfaces.
* @X86_SUBARCH_CE4100: Used for Intel CE media processor (CE4100) SoC
#define DR_TRAP3 (0x8) /* db3 */
#define DR_TRAP_BITS (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)
+#define DR_BUS_LOCK (0x800) /* bus_lock */
#define DR_STEP (0x4000) /* single-step */
#define DR_SWITCH (0x8000) /* task switch */
* The msqid64_ds structure for x86 architecture with x32 ABI.
*
* On x86-32 and x86-64 we can just use the generic definition, but
- * x32 uses the same binary layout as x86_64, which is differnet
+ * x32 uses the same binary layout as x86_64, which is different
* from other 32-bit architectures.
*/
* Most exceptions reported on ENCLU, including those that occur within the
* enclave, are fixed up and reported synchronously instead of being delivered
* via a standard signal. Debug Exceptions (#DB) and Breakpoints (#BP) are
- * never fixed up and are always delivered via standard signals. On synchrously
+ * never fixed up and are always delivered via standard signals. On synchronously
* reported exceptions, -EFAULT is returned and details about the exception are
* recorded in @run.exception, the optional sgx_enclave_exception struct.
*
* The shmid64_ds structure for x86 architecture with x32 ABI.
*
* On x86-32 and x86-64 we can just use the generic definition, but
- * x32 uses the same binary layout as x86_64, which is differnet
+ * x32 uses the same binary layout as x86_64, which is different
* from other 32-bit architectures.
*/
* The 64-bit FPU frame. (FXSAVE format and later)
*
* Note1: If sw_reserved.magic1 == FP_XSTATE_MAGIC1 then the structure is
- * larger: 'struct _xstate'. Note that 'struct _xstate' embedds
+ * larger: 'struct _xstate'. Note that 'struct _xstate' embeds
* 'struct _fpstate' so that you can always assume the _fpstate portion
* exists so that you can check the magic value.
*
KCSAN_SANITIZE := n
OBJECT_FILES_NON_STANDARD_test_nx.o := y
-OBJECT_FILES_NON_STANDARD_paravirt_patch.o := y
ifdef CONFIG_FRAME_POINTER
OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y
obj-$(CONFIG_DEBUG_NMI_SELFTEST) += nmi_selftest.o
obj-$(CONFIG_KVM_GUEST) += kvm.o kvmclock.o
-obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch.o
+obj-$(CONFIG_PARAVIRT) += paravirt.o
obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o
obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o
obj-$(CONFIG_X86_PMEM_LEGACY_DEVICE) += pmem.o
EXPORT_SYMBOL(acpi_unregister_ioapic);
/**
- * acpi_ioapic_registered - Check whether IOAPIC assoicatied with @gsi_base
+ * acpi_ioapic_registered - Check whether IOAPIC associated with @gsi_base
* has been registered
* @handle: ACPI handle of the IOAPIC device
* @gsi_base: GSI base associated with the IOAPIC
/*
* Initialize the ACPI boot-time table parser.
*/
- if (acpi_table_init()) {
+ if (acpi_locate_initial_tables())
disable_acpi();
- return;
- }
+ else
+ acpi_reserve_initial_tables();
+}
+
+int __init early_acpi_boot_init(void)
+{
+ if (acpi_disabled)
+ return 1;
+
+ acpi_table_init_complete();
acpi_table_parse(ACPI_SIG_BOOT, acpi_parse_sbf);
} else {
printk(KERN_WARNING PREFIX "Disabling ACPI support\n");
disable_acpi();
- return;
+ return 1;
}
}
-}
-
-int __init early_acpi_boot_init(void)
-{
- /*
- * If acpi_disabled, bail out
- */
- if (acpi_disabled)
- return 1;
/*
* Process the Multiple APIC Description Table (MADT), if present
else if (strcmp(arg, "noirq") == 0) {
acpi_noirq_set();
}
- /* "acpi=copy_dsdt" copys DSDT */
+ /* "acpi=copy_dsdt" copies DSDT */
else if (strcmp(arg, "copy_dsdt") == 0) {
acpi_gbl_copy_dsdt_locally = 1;
}
* x86_acpi_enter_sleep_state - enter sleep state
* @state: Sleep state to enter.
*
- * Wrapper around acpi_enter_sleep_state() to be called by assmebly.
+ * Wrapper around acpi_enter_sleep_state() to be called by assembly.
*/
asmlinkage acpi_status __visible x86_acpi_enter_sleep_state(u8 state)
{
movq pt_regs_r14(%rax), %r14
movq pt_regs_r15(%rax), %r15
-#if defined(CONFIG_KASAN) && CONFIG_KASAN_STACK
+#if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK)
/*
* The suspend path may have poisoned some areas deeper in the stack,
* which we now need to unpoison.
#include <asm/insn.h>
#include <asm/io.h>
#include <asm/fixmap.h>
+#include <asm/paravirt.h>
int __read_mostly alternatives_patched;
*/
for (a = start; a < end; a++) {
int insn_buff_sz = 0;
+ /* Mask away "NOT" flag bit for feature to test. */
+ u16 feature = a->cpuid & ~ALTINSTR_FLAG_INV;
instr = (u8 *)&a->instr_offset + a->instr_offset;
replacement = (u8 *)&a->repl_offset + a->repl_offset;
BUG_ON(a->instrlen > sizeof(insn_buff));
- BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32);
- if (!boot_cpu_has(a->cpuid)) {
+ BUG_ON(feature >= (NCAPINTS + NBUGINTS) * 32);
+
+ /*
+ * Patch if either:
+ * - feature is present
+ * - feature not present but ALTINSTR_FLAG_INV is set to mean,
+ * patch if feature is *NOT* present.
+ */
+ if (!boot_cpu_has(feature) == !(a->cpuid & ALTINSTR_FLAG_INV)) {
if (a->padlen > 1)
optimize_nops(a, instr);
continue;
}
- DPRINTK("feat: %d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d), pad: %d",
- a->cpuid >> 5,
- a->cpuid & 0x1f,
+ DPRINTK("feat: %s%d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d), pad: %d",
+ (a->cpuid & ALTINSTR_FLAG_INV) ? "!" : "",
+ feature >> 5,
+ feature & 0x1f,
instr, instr, a->instrlen,
replacement, a->replacementlen, a->padlen);
BUG_ON(p->len > MAX_PATCH_LEN);
/* prep the buffer with the original instructions */
memcpy(insn_buff, p->instr, p->len);
- used = pv_ops.init.patch(p->type, insn_buff, (unsigned long)p->instr, p->len);
+ used = paravirt_patch(p->type, insn_buff, (unsigned long)p->instr, p->len);
BUG_ON(used > p->len);
* patching.
*/
+ /*
+ * Paravirt patching and alternative patching can be combined to
+ * replace a function call with a short direct code sequence (e.g.
+ * by setting a constant return value instead of doing that in an
+ * external function).
+ * In order to make this work the following sequence is required:
+ * 1. set (artificial) features depending on used paravirt
+ * functions which can later influence alternative patching
+ * 2. apply paravirt patching (generally replacing an indirect
+ * function call with a direct one)
+ * 3. apply alternative patching (e.g. replacing a direct function
+ * call with a custom code sequence)
+ * Doing paravirt patching after alternative patching would clobber
+ * the optimization of the custom code with a function call again.
+ */
+ paravirt_set_cap();
+
+ /*
+ * First patch paravirt functions, such that we overwrite the indirect
+ * call with the direct call.
+ */
+ apply_paravirt(__parainstructions, __parainstructions_end);
+
+ /*
+ * Then patch alternatives, such that those paravirt calls that are in
+ * alternatives can be overwritten by their immediate fragments.
+ */
apply_alternatives(__alt_instructions, __alt_instructions_end);
#ifdef CONFIG_SMP
}
#endif
- apply_paravirt(__parainstructions, __parainstructions_end);
-
restart_nmi();
alternatives_patched = 1;
}
// SPDX-License-Identifier: GPL-2.0-only
/*
- * Shared support code for AMD K8 northbridges and derivates.
+ * Shared support code for AMD K8 northbridges and derivatives.
* Copyright 2006 Andi Kleen, SUSE Labs.
*/
if (this_cpu_has(X86_FEATURE_ARAT)) {
lapic_clockevent.features &= ~CLOCK_EVT_FEAT_C3STOP;
- /* Make LAPIC timer preferrable over percpu HPET */
+ /* Make LAPIC timer preferable over percpu HPET */
lapic_clockevent.rating = 150;
}
* In this functions we calibrate APIC bus clocks to the external timer.
*
* We want to do the calibration only once since we want to have local timer
- * irqs syncron. CPUs connected by the same APIC bus have the very same bus
+ * irqs synchronous. CPUs connected by the same APIC bus have the very same bus
* frequency.
*
* This was previously done by reading the PIT/HPET and waiting for a wrap
* Most probably by now the CPU has serviced that pending interrupt and it
* might not have done the ack_APIC_irq() because it thought, interrupt
* came from i8259 as ExtInt. LAPIC did not get EOI so it does not clear
- * the ISR bit and cpu thinks it has already serivced the interrupt. Hence
+ * the ISR bit and cpu thinks it has already serviced the interrupt. Hence
* a vector might get locked. It was noticed for timer irq (vector
* 0x31). Issue an extra EOI to clear ISR.
*
*/
/*
* Actually disabling the focus CPU check just makes the hang less
- * frequent as it makes the interrupt distributon model be more
+ * frequent as it makes the interrupt distribution model be more
* like LRU than MRU (the short-term load is more even across CPUs).
*/
/*
* Without IR, all CPUs can be addressed by IOAPIC/MSI only
- * in physical mode, and CPUs with an APIC ID that cannnot
+ * in physical mode, and CPUs with an APIC ID that cannot
* be addressed must not be brought online.
*/
x2apic_set_max_apicid(apic_limit);
[0 ... NR_CPUS - 1] = -1,
};
+bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
+{
+ return phys_id == cpuid_to_apicid[cpu];
+}
+
#ifdef CONFIG_SMP
/**
* apic_id_is_primary_thread - Check whether APIC ID belongs to a primary thread
/*
* setup_IO_APIC_irqs() programs all legacy IRQs with default trigger
- * and polarity attirbutes. So allow the first user to reprogram the
+ * and polarity attributes. So allow the first user to reprogram the
* pin with real trigger and polarity attributes.
*/
if (irq < nr_legacy_irqs() && data->count == 1) {
/*
* Legacy ISA IRQ has already been allocated, just add pin to
- * the pin list assoicated with this IRQ and program the IOAPIC
+ * the pin list associated with this IRQ and program the IOAPIC
* entry. The IOAPIC entry
*/
if (irq_data && irq_data->parent_data) {
if (idx >= 0 && test_bit(mp_irqs[idx].srcbus, mp_bus_not_pci)) {
irq = mp_irqs[idx].srcbusirq;
legacy = mp_is_legacy_irq(irq);
+ /*
+ * IRQ2 is unusable for historical reasons on systems which
+ * have a legacy PIC. See the comment vs. IRQ2 further down.
+ *
+ * If this gets removed at some point then the related code
+ * in lapic_assign_system_vectors() needs to be adjusted as
+ * well.
+ */
+ if (legacy && irq == PIC_CASCADE_IR)
+ return -EINVAL;
}
mutex_lock(&ioapic_mutex);
* with masking the ioapic entry and then polling until
* Remote IRR was clear before reprogramming the
* ioapic I don't trust the Remote IRR bit to be
- * completey accurate.
+ * completely accurate.
*
* However there appears to be no other way to plug
* this race, so if the Remote IRR bit is not
/*
* Tail end of clearing remote IRR bit (either by delivering the EOI
* message via io-apic EOI register write or simulating it using
- * mask+edge followed by unnask+level logic) manually when the
+ * mask+edge followed by unmask+level logic) manually when the
* level triggered interrupt is seen as the edge triggered interrupt
* at the cpu.
*/
if ((info->flags & X86_IRQ_ALLOC_CONTIGUOUS_VECTORS) && nr_irqs > 1)
return -ENOSYS;
+ /*
+ * Catch any attempt to touch the cascade interrupt on a PIC
+ * equipped system.
+ */
+ if (WARN_ON_ONCE(info->flags & X86_IRQ_ALLOC_LEGACY &&
+ virq == PIC_CASCADE_IR))
+ return -EINVAL;
+
for (i = 0; i < nr_irqs; i++) {
irqd = irq_domain_get_irq_data(domain, virq + i);
BUG_ON(!irqd);
/* Mark the preallocated legacy interrupts */
for (i = 0; i < nr_legacy_irqs(); i++) {
+ /*
+ * Don't touch the cascade interrupt. It's unusable
+ * on PIC equipped machines. See the large comment
+ * in the IO/APIC code.
+ */
if (i != PIC_CASCADE_IR)
irq_matrix_assign(vector_matrix, ISA_IRQ_VECTOR(i));
}
*
* But in case of cpu hotplug this should be a non issue
* because if the affinity update happens right before all
- * cpus rendevouz in stop machine, there is no way that the
+ * cpus rendezvous in stop machine, there is no way that the
* interrupt can be blocked on the target cpu because all cpus
* loops first with interrupts enabled in stop machine, so the
* old vector is not yet cleaned up when the interrupt fires.
* of the interrupt on the apic/system bus would be delayed
* beyond the point where the target cpu disables interrupts
* in stop machine. I doubt that it can happen, but at least
- * there is a theroretical chance. Virtualization might be
+ * there is a theoretical chance. Virtualization might be
* able to expose this, but AFAICT the IOAPIC emulation is not
* as stupid as the real hardware.
*
return ret;
}
+/* UV system found, check which APIC MODE BIOS already selected */
+static void __init early_set_apic_mode(void)
+{
+ if (x2apic_enabled())
+ uv_system_type = UV_X2APIC;
+ else
+ uv_system_type = UV_LEGACY_APIC;
+}
+
static int __init uv_set_system_type(char *_oem_id, char *_oem_table_id)
{
/* Save OEM_ID passed from ACPI MADT */
else
uv_hubless_system |= 0x8;
- /* Copy APIC type */
+ /* Copy OEM Table ID */
uv_stringify(sizeof(oem_table_id), oem_table_id, _oem_table_id);
pr_info("UV: OEM IDs %s/%s, SystemType %d, HUBLESS ID %x\n",
oem_id, oem_table_id, uv_system_type, uv_hubless_system);
+
return 0;
}
early_set_hub_type();
/* Other UV setup functions */
+ early_set_apic_mode();
early_get_pnodeid();
early_get_apic_socketid_shift();
x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range;
if (uv_set_system_type(_oem_id, _oem_table_id) == 0)
return 0;
- /* Save and Decode OEM Table ID */
+ /* Save for display of the OEM Table ID */
uv_stringify(sizeof(oem_table_id), oem_table_id, _oem_table_id);
- /* This is the most common hardware variant, x2apic mode */
- if (!strcmp(oem_table_id, "UVX"))
- uv_system_type = UV_X2APIC;
-
- /* Only used for very small systems, usually 1 chassis, legacy mode */
- else if (!strcmp(oem_table_id, "UVL"))
- uv_system_type = UV_LEGACY_APIC;
-
- else
- goto badbios;
-
pr_info("UV: OEM IDs %s/%s, System/UVType %d/0x%x, HUB RevID %d\n",
oem_id, oem_table_id, uv_system_type, is_uv(UV_ANY),
uv_min_hub_revision_id);
return 0;
-
-badbios:
- pr_err("UV: UVarchtype:%s not supported\n", uv_archtype);
- BUG();
}
enum uv_system_type get_uv_system_type(void)
if (rc < 0)
return rc;
+ /* Set section block size for current node memory */
+ set_block_size();
+
/* Create user access node */
if (rc >= 0)
uv_setup_proc_files(1);
* Remove APM dependencies in arch/i386/kernel/process.c
* Remove APM dependencies in drivers/char/sysrq.c
* Reset time across standby.
- * Allow more inititialisation on SMP.
+ * Allow more initialisation on SMP.
* Remove CONFIG_APM_POWER_OFF and make it boot time
* configurable (default on).
* Make debug only a boot time parameter (remove APM_DEBUG).
* not cleared until it is acknowledged.
*
* Additional information is returned in the info pointer, providing
- * that APM 1.2 is in use. If no messges are pending the value 0x80
+ * that APM 1.2 is in use. If no messages are pending the value 0x80
* is returned (No power management events pending).
*/
static int apm_get_event(apm_event_t *event, apm_eventinfo_t *info)
* status which gives the rough battery status, and current power
* source. The bat value returned give an estimate as a percentage
* of life and a status value for the battery. The estimated life
- * if reported is a lifetime in secodnds/minutes at current powwer
+ * if reported is a lifetime in seconds/minutes at current power
* consumption.
*/
OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext);
#endif
-#ifdef CONFIG_PARAVIRT_XXL
- BLANK();
- OFFSET(PV_IRQ_irq_disable, paravirt_patch_template, irq.irq_disable);
- OFFSET(PV_IRQ_irq_enable, paravirt_patch_template, irq.irq_enable);
- OFFSET(PV_CPU_iret, paravirt_patch_template, cpu.iret);
-#endif
-
#ifdef CONFIG_XEN
BLANK();
OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask);
static int __cache_amd_cpumap_setup(unsigned int cpu, int index,
struct _cpuid4_info_regs *base)
{
- struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+ struct cpu_cacheinfo *this_cpu_ci;
struct cacheinfo *this_leaf;
int i, sibling;
if (pk)
pk->pkru = init_pkru_value;
/*
- * Seting X86_CR4_PKE will cause the X86_FEATURE_OSPKE
+ * Setting X86_CR4_PKE will cause the X86_FEATURE_OSPKE
* cpuid bit to be set. We need to ensure that we
* update that bit in this CPU's "cpu_info".
*/
cpu_set_bug_bits(c);
- cpu_set_core_cap_bits(c);
+ sld_setup(c);
fpu__init_system(c);
* where GS is unused by the prev and next threads.
*
* Since neither vendor documents this anywhere that I can see,
- * detect it directly instead of hardcoding the choice by
+ * detect it directly instead of hard-coding the choice by
* vendor.
*
* I've designated AMD's behavior as the "bug" because it's
DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
EXPORT_PER_CPU_SYMBOL(__preempt_count);
+DEFINE_PER_CPU(unsigned long, cpu_current_top_of_stack) = TOP_OF_INIT_STACK;
+
/* May not be marked __init: used by software suspend */
void syscall_init(void)
{
{ X86_FEATURE_AVX512_FP16, X86_FEATURE_AVX512BW },
{ X86_FEATURE_ENQCMD, X86_FEATURE_XSAVES },
{ X86_FEATURE_PER_THREAD_MBA, X86_FEATURE_MBA },
+ { X86_FEATURE_SGX_LC, X86_FEATURE_SGX },
+ { X86_FEATURE_SGX1, X86_FEATURE_SGX },
+ { X86_FEATURE_SGX2, X86_FEATURE_SGX1 },
{}
};
mark_tsc_unstable("cyrix 5510/5520 detected");
}
#endif
- c->x86_cache_size = 16; /* Yep 16K integrated cache thats it */
+ c->x86_cache_size = 16; /* Yep 16K integrated cache that's it */
/* GXm supports extended cpuid levels 'ala' AMD */
if (c->cpuid_level == 2) {
}
#endif /* CONFIG_X86_VMX_FEATURE_NAMES */
-static void clear_sgx_caps(void)
-{
- setup_clear_cpu_cap(X86_FEATURE_SGX);
- setup_clear_cpu_cap(X86_FEATURE_SGX_LC);
-}
-
static int __init nosgx(char *str)
{
- clear_sgx_caps();
+ setup_clear_cpu_cap(X86_FEATURE_SGX);
return 0;
}
void init_ia32_feat_ctl(struct cpuinfo_x86 *c)
{
+ bool enable_sgx_kvm = false, enable_sgx_driver = false;
bool tboot = tboot_enabled();
- bool enable_sgx;
+ bool enable_vmx;
u64 msr;
if (rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr)) {
clear_cpu_cap(c, X86_FEATURE_VMX);
- clear_sgx_caps();
+ clear_cpu_cap(c, X86_FEATURE_SGX);
return;
}
- /*
- * Enable SGX if and only if the kernel supports SGX and Launch Control
- * is supported, i.e. disable SGX if the LE hash MSRs can't be written.
- */
- enable_sgx = cpu_has(c, X86_FEATURE_SGX) &&
- cpu_has(c, X86_FEATURE_SGX_LC) &&
- IS_ENABLED(CONFIG_X86_SGX);
+ enable_vmx = cpu_has(c, X86_FEATURE_VMX) &&
+ IS_ENABLED(CONFIG_KVM_INTEL);
+
+ if (cpu_has(c, X86_FEATURE_SGX) && IS_ENABLED(CONFIG_X86_SGX)) {
+ /*
+ * Separate out SGX driver enabling from KVM. This allows KVM
+ * guests to use SGX even if the kernel SGX driver refuses to
+ * use it. This happens if flexible Launch Control is not
+ * available.
+ */
+ enable_sgx_driver = cpu_has(c, X86_FEATURE_SGX_LC);
+ enable_sgx_kvm = enable_vmx && IS_ENABLED(CONFIG_X86_SGX_KVM);
+ }
if (msr & FEAT_CTL_LOCKED)
goto update_caps;
* i.e. KVM is enabled, to avoid unnecessarily adding an attack vector
* for the kernel, e.g. using VMX to hide malicious code.
*/
- if (cpu_has(c, X86_FEATURE_VMX) && IS_ENABLED(CONFIG_KVM_INTEL)) {
+ if (enable_vmx) {
msr |= FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX;
if (tboot)
msr |= FEAT_CTL_VMX_ENABLED_INSIDE_SMX;
}
- if (enable_sgx)
- msr |= FEAT_CTL_SGX_ENABLED | FEAT_CTL_SGX_LC_ENABLED;
+ if (enable_sgx_kvm || enable_sgx_driver) {
+ msr |= FEAT_CTL_SGX_ENABLED;
+ if (enable_sgx_driver)
+ msr |= FEAT_CTL_SGX_LC_ENABLED;
+ }
wrmsrl(MSR_IA32_FEAT_CTL, msr);
}
update_sgx:
- if (!(msr & FEAT_CTL_SGX_ENABLED) ||
- !(msr & FEAT_CTL_SGX_LC_ENABLED) || !enable_sgx) {
- if (enable_sgx)
- pr_err_once("SGX disabled by BIOS\n");
- clear_sgx_caps();
+ if (!(msr & FEAT_CTL_SGX_ENABLED)) {
+ if (enable_sgx_kvm || enable_sgx_driver)
+ pr_err_once("SGX disabled by BIOS.\n");
+ clear_cpu_cap(c, X86_FEATURE_SGX);
+ return;
+ }
+
+ /*
+ * VMX feature bit may be cleared due to being disabled in BIOS,
+ * in which case SGX virtualization cannot be supported either.
+ */
+ if (!cpu_has(c, X86_FEATURE_VMX) && enable_sgx_kvm) {
+ pr_err_once("SGX virtualization disabled due to lack of VMX.\n");
+ enable_sgx_kvm = 0;
+ }
+
+ if (!(msr & FEAT_CTL_SGX_LC_ENABLED) && enable_sgx_driver) {
+ if (!enable_sgx_kvm) {
+ pr_err_once("SGX Launch Control is locked. Disable SGX.\n");
+ clear_cpu_cap(c, X86_FEATURE_SGX);
+ } else {
+ pr_err_once("SGX Launch Control is locked. Support SGX virtualization only.\n");
+ clear_cpu_cap(c, X86_FEATURE_SGX_LC);
+ }
}
}
};
/*
- * Default to sld_off because most systems do not support split lock detection
- * split_lock_setup() will switch this to sld_warn on systems that support
- * split lock detect, unless there is a command line override.
+ * Default to sld_off because most systems do not support split lock detection.
+ * sld_state_setup() will switch this to sld_warn on systems that support
+ * split lock/bus lock detect, unless there is a command line override.
*/
static enum split_lock_detect_state sld_state __ro_after_init = sld_off;
static u64 msr_test_ctrl_cache __ro_after_init;
* The operating system must reload CR3 to cause the TLB to be flushed"
*
* As a result, boot_cpu_has(X86_FEATURE_PGE) in arch/x86/include/asm/tlbflush.h
- * should be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE
+ * should be false so that __flush_tlb_all() causes CR3 instead of CR4.PGE
* to be modified.
*/
if (c->x86 == 5 && c->x86_model == 9) {
}
static void split_lock_init(void);
+static void bus_lock_init(void);
static void init_intel(struct cpuinfo_x86 *c)
{
tsx_disable();
split_lock_init();
+ bus_lock_init();
intel_init_thermal(c);
}
return ctrl == tmp;
}
-static void __init split_lock_setup(void)
+static void __init sld_state_setup(void)
{
enum split_lock_detect_state state = sld_warn;
char arg[20];
int i, ret;
- if (!split_lock_verify_msr(false)) {
- pr_info("MSR access failed: Disabled\n");
+ if (!boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT) &&
+ !boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT))
return;
- }
ret = cmdline_find_option(boot_command_line, "split_lock_detect",
arg, sizeof(arg));
}
}
}
+ sld_state = state;
+}
- switch (state) {
- case sld_off:
- pr_info("disabled\n");
+static void __init __split_lock_setup(void)
+{
+ if (!split_lock_verify_msr(false)) {
+ pr_info("MSR access failed: Disabled\n");
return;
- case sld_warn:
- pr_info("warning about user-space split_locks\n");
- break;
- case sld_fatal:
- pr_info("sending SIGBUS on user-space split_locks\n");
- break;
}
rdmsrl(MSR_TEST_CTRL, msr_test_ctrl_cache);
return;
}
- sld_state = state;
+ /* Restore the MSR to its cached value. */
+ wrmsrl(MSR_TEST_CTRL, msr_test_ctrl_cache);
+
setup_force_cpu_cap(X86_FEATURE_SPLIT_LOCK_DETECT);
}
}
EXPORT_SYMBOL_GPL(handle_guest_split_lock);
+static void bus_lock_init(void)
+{
+ u64 val;
+
+ /*
+ * Warn and fatal are handled by #AC for split lock if #AC for
+ * split lock is supported.
+ */
+ if (!boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT) ||
+ (boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT) &&
+ (sld_state == sld_warn || sld_state == sld_fatal)) ||
+ sld_state == sld_off)
+ return;
+
+ /*
+ * Enable #DB for bus lock. All bus locks are handled in #DB except
+ * split locks are handled in #AC in the fatal case.
+ */
+ rdmsrl(MSR_IA32_DEBUGCTLMSR, val);
+ val |= DEBUGCTLMSR_BUS_LOCK_DETECT;
+ wrmsrl(MSR_IA32_DEBUGCTLMSR, val);
+}
+
bool handle_user_split_lock(struct pt_regs *regs, long error_code)
{
if ((regs->flags & X86_EFLAGS_AC) || sld_state == sld_fatal)
return true;
}
+void handle_bus_lock(struct pt_regs *regs)
+{
+ switch (sld_state) {
+ case sld_off:
+ break;
+ case sld_warn:
+ pr_warn_ratelimited("#DB: %s/%d took a bus_lock trap at address: 0x%lx\n",
+ current->comm, current->pid, regs->ip);
+ break;
+ case sld_fatal:
+ force_sig_fault(SIGBUS, BUS_ADRALN, NULL);
+ break;
+ }
+}
+
/*
* This function is called only when switching between tasks with
* different split-lock detection modes. It sets the MSR for the
{}
};
-void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c)
+static void __init split_lock_setup(struct cpuinfo_x86 *c)
{
const struct x86_cpu_id *m;
u64 ia32_core_caps;
}
cpu_model_supports_sld = true;
- split_lock_setup();
+ __split_lock_setup();
+}
+
+static void sld_state_show(void)
+{
+ if (!boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT) &&
+ !boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT))
+ return;
+
+ switch (sld_state) {
+ case sld_off:
+ pr_info("disabled\n");
+ break;
+ case sld_warn:
+ if (boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT))
+ pr_info("#AC: crashing the kernel on kernel split_locks and warning on user-space split_locks\n");
+ else if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT))
+ pr_info("#DB: warning on user-space bus_locks\n");
+ break;
+ case sld_fatal:
+ if (boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT)) {
+ pr_info("#AC: crashing the kernel on kernel split_locks and sending SIGBUS on user-space split_locks\n");
+ } else if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT)) {
+ pr_info("#DB: sending SIGBUS on user-space bus_locks%s\n",
+ boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT) ?
+ " from non-WB" : "");
+ }
+ break;
+ }
+}
+
+void __init sld_setup(struct cpuinfo_x86 *c)
+{
+ split_lock_setup(c);
+ sld_state_setup();
+ sld_state_show();
}
* Check if the address reported by the CPU is in a format we can parse.
* It would be possible to add code for most other cases, but all would
* be somewhat complicated (e.g. segment offset would require an instruction
- * parser). So only support physical addresses up to page granuality for now.
+ * parser). So only support physical addresses up to page granularity for now.
*/
int mce_usable_address(struct mce *m)
{
MCE_INJECT_SET(misc);
MCE_INJECT_SET(addr);
MCE_INJECT_SET(synd);
+MCE_INJECT_SET(ipid);
#define MCE_INJECT_GET(reg) \
static int inj_##reg##_get(void *data, u64 *val) \
MCE_INJECT_GET(misc);
MCE_INJECT_GET(addr);
MCE_INJECT_GET(synd);
+MCE_INJECT_GET(ipid);
DEFINE_SIMPLE_ATTRIBUTE(status_fops, inj_status_get, inj_status_set, "%llx\n");
DEFINE_SIMPLE_ATTRIBUTE(misc_fops, inj_misc_get, inj_misc_set, "%llx\n");
DEFINE_SIMPLE_ATTRIBUTE(addr_fops, inj_addr_get, inj_addr_set, "%llx\n");
DEFINE_SIMPLE_ATTRIBUTE(synd_fops, inj_synd_get, inj_synd_set, "%llx\n");
+DEFINE_SIMPLE_ATTRIBUTE(ipid_fops, inj_ipid_get, inj_ipid_set, "%llx\n");
static void setup_inj_struct(struct mce *m)
{
"\t is present in hardware. \n"
"\t - \"th\": Trigger APIC interrupt for Threshold errors. Causes threshold \n"
"\t APIC interrupt handler to handle the error. \n"
+"\n"
+"ipid:\t IPID (AMD-specific)\n"
"\n";
static ssize_t
{ .name = "misc", .fops = &misc_fops, .perm = S_IRUSR | S_IWUSR },
{ .name = "addr", .fops = &addr_fops, .perm = S_IRUSR | S_IWUSR },
{ .name = "synd", .fops = &synd_fops, .perm = S_IRUSR | S_IWUSR },
+ { .name = "ipid", .fops = &ipid_fops, .perm = S_IRUSR | S_IWUSR },
{ .name = "bank", .fops = &bank_fops, .perm = S_IRUSR | S_IWUSR },
{ .name = "flags", .fops = &flags_fops, .perm = S_IRUSR | S_IWUSR },
{ .name = "cpu", .fops = &extcpu_fops, .perm = S_IRUSR | S_IWUSR },
MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_STATUS_UC|MCI_STATUS_AR)
),
MCESEV(
- KEEP, "Non signalled machine check",
+ KEEP, "Non signaled machine check",
SER, BITCLR(MCI_STATUS_S)
),
if (val != 1)
return size;
- tmp_ret = microcode_ops->request_microcode_fw(bsp, µcode_pdev->dev, true);
- if (tmp_ret != UCODE_NEW)
- return size;
-
get_online_cpus();
ret = check_online_cpus();
if (ret)
goto put;
+ tmp_ret = microcode_ops->request_microcode_fw(bsp, µcode_pdev->dev, true);
+ if (tmp_ret != UCODE_NEW)
+ goto put;
+
mutex_lock(µcode_mutex);
ret = microcode_reload_late();
mutex_unlock(µcode_mutex);
#ifdef CONFIG_X86_LOCAL_APIC
/*
* Prior to WS2016 Debug-VM sends NMIs to all CPUs which makes
- * it dificult to process CHANNELMSG_UNLOAD in case of crash. Handle
+ * it difficult to process CHANNELMSG_UNLOAD in case of crash. Handle
* unknown NMI on the first CPU which gets it.
*/
static int hv_nmi_unknown(unsigned int val, struct pt_regs *regs)
/*
* Hyper-V doesn't provide irq remapping for IO-APIC. To enable x2apic,
- * set x2apic destination mode to physcial mode when x2apic is available
+ * set x2apic destination mode to physical mode when x2apic is available
* and Hyper-V IOMMU driver makes sure cpus assigned with IO-APIC irqs
* have 8-bit APIC id.
*/
state->range_sizek = sizek - second_sizek;
}
-/* Mininum size of mtrr block that can take hole: */
+/* Minimum size of mtrr block that can take hole: */
static u64 mtrr_chunk_size __initdata = (256ULL<<20);
static int __init parse_mtrr_chunk_size_opt(char *p)
*
* This routine is called in two cases:
*
- * 1. very earily time of software resume, when there absolutely
+ * 1. very early time of software resume, when there absolutely
* isn't mtrr entry changes;
*
* 2. cpu hotadd time. We let mtrr_add/del_page hold cpuhotplug
* Intel(R) Xeon(R) CPU E5-2608L v3 @ 2.00GHz
* Intel(R) Xeon(R) CPU E5-2658A v3 @ 2.20GHz
*
- * Probe by trying to write the first of the L3 cach mask registers
+ * Probe by trying to write the first of the L3 cache mask registers
* and checking that the bits stick. Max CLOSids is always 4 and max cbm length
* is always 20 on hsw server parts. The minimum cache bitmask length
* allowed for HSW server is always 2 bits. Hardcode all of them.
* adjust the bandwidth percentage values via the IA32_MBA_THRTL_MSRs so
* that:
*
- * current bandwdith(cur_bw) < user specified bandwidth(user_bw)
+ * current bandwidth(cur_bw) < user specified bandwidth(user_bw)
*
* This uses the MBM counters to measure the bandwidth and MBA throttle
* MSRs to control the bandwidth for a particular rdtgrp. It builds on the
* timer. Having 1s interval makes the calculation of bandwidth simpler.
*
* Although MBA's goal is to restrict the bandwidth to a maximum, there may
- * be a need to increase the bandwidth to avoid uncecessarily restricting
+ * be a need to increase the bandwidth to avoid unnecessarily restricting
* the L2 <-> L3 traffic.
*
* Since MBA controls the L2 external bandwidth where as MBM measures the
/*
* Delta values are updated dynamically package wise for each
- * rdtgrp everytime the throttle MSR changes value.
+ * rdtgrp every time the throttle MSR changes value.
*
* This is because (1)the increase in bandwidth is not perfectly
* linear and only "approximately" linear even when the hardware
* If the thread does not get on the CPU for whatever
* reason and the process which sets up the region is
* interrupted then this will leave the thread in runnable
- * state and once it gets on the CPU it will derefence
+ * state and once it gets on the CPU it will dereference
* the cleared, but not freed, plr struct resulting in an
* empty pseudo-locking loop.
*/
* group is removed from user space via a "rmdir" from userspace or the
* unmount of the resctrl filesystem. On removal the resource group does
* not go back to pseudo-locksetup mode before it is removed, instead it is
- * removed directly. There is thus assymmetry with the creation where the
+ * removed directly. There is thus asymmetry with the creation where the
* &struct pseudo_lock_region is removed here while it was not created in
* rdtgroup_pseudo_lock_create().
*
// SPDX-License-Identifier: GPL-2.0-only
/*
- * User interface for Resource Alloction in Resource Director Technology(RDT)
+ * User interface for Resource Allocation in Resource Director Technology(RDT)
*
* Copyright (C) 2016 Intel Corporation
*
/*
* This is safe against resctrl_sched_in() called from __switch_to()
* because __switch_to() is executed with interrupts disabled. A local call
- * from update_closid_rmid() is proteced against __switch_to() because
+ * from update_closid_rmid() is protected against __switch_to() because
* preemption is disabled.
*/
static void update_cpu_closid_rmid(void *info)
/*
* This creates a directory mon_data which contains the monitored data.
*
- * mon_data has one directory for each domain whic are named
+ * mon_data has one directory for each domain which are named
* in the format mon_<domain_name>_<domain_id>. For ex: A mon_data
* with L3 domain looks as below:
* ./mon_data:
{ X86_FEATURE_CDP_L2, CPUID_ECX, 2, 0x00000010, 2 },
{ X86_FEATURE_MBA, CPUID_EBX, 3, 0x00000010, 0 },
{ X86_FEATURE_PER_THREAD_MBA, CPUID_ECX, 0, 0x00000010, 3 },
+ { X86_FEATURE_SGX1, CPUID_EAX, 0, 0x00000012, 0 },
+ { X86_FEATURE_SGX2, CPUID_EAX, 1, 0x00000012, 0 },
{ X86_FEATURE_HW_PSTATE, CPUID_EDX, 7, 0x80000007, 0 },
{ X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 },
{ X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 },
encl.o \
ioctl.o \
main.o
+obj-$(CONFIG_X86_SGX_KVM) += virt.o
.get_unmapped_area = sgx_get_unmapped_area,
};
-const struct file_operations sgx_provision_fops = {
- .owner = THIS_MODULE,
-};
-
static struct miscdevice sgx_dev_enclave = {
.minor = MISC_DYNAMIC_MINOR,
.name = "sgx_enclave",
.fops = &sgx_encl_fops,
};
-static struct miscdevice sgx_dev_provision = {
- .minor = MISC_DYNAMIC_MINOR,
- .name = "sgx_provision",
- .nodename = "sgx_provision",
- .fops = &sgx_provision_fops,
-};
-
int __init sgx_drv_init(void)
{
unsigned int eax, ebx, ecx, edx;
if (ret)
return ret;
- ret = misc_register(&sgx_dev_provision);
- if (ret) {
- misc_deregister(&sgx_dev_enclave);
- return ret;
- }
-
return 0;
}
#include <linux/shmem_fs.h>
#include <linux/suspend.h>
#include <linux/sched/mm.h>
-#include "arch.h"
+#include <asm/sgx.h>
#include "encl.h"
#include "encls.h"
#include "sgx.h"
ret = __sgx_encl_eldu(encl_page, epc_page, secs_page);
if (ret) {
- sgx_free_epc_page(epc_page);
+ sgx_encl_free_epc_page(epc_page);
return ERR_PTR(ret);
}
if (sgx_unmark_page_reclaimable(entry->epc_page))
continue;
- sgx_free_epc_page(entry->epc_page);
+ sgx_encl_free_epc_page(entry->epc_page);
encl->secs_child_cnt--;
entry->epc_page = NULL;
}
xa_destroy(&encl->page_array);
if (!encl->secs_child_cnt && encl->secs.epc_page) {
- sgx_free_epc_page(encl->secs.epc_page);
+ sgx_encl_free_epc_page(encl->secs.epc_page);
encl->secs.epc_page = NULL;
}
va_page = list_first_entry(&encl->va_pages, struct sgx_va_page,
list);
list_del(&va_page->list);
- sgx_free_epc_page(va_page->epc_page);
+ sgx_encl_free_epc_page(va_page->epc_page);
kfree(va_page);
}
ret = __epa(sgx_get_epc_virt_addr(epc_page));
if (ret) {
WARN_ONCE(1, "EPA returned %d (0x%x)", ret, ret);
- sgx_free_epc_page(epc_page);
+ sgx_encl_free_epc_page(epc_page);
return ERR_PTR(-EFAULT);
}
return slot == SGX_VA_SLOT_COUNT;
}
+
+/**
+ * sgx_encl_free_epc_page - free an EPC page assigned to an enclave
+ * @page: EPC page to be freed
+ *
+ * Free an EPC page assigned to an enclave. It does EREMOVE for the page, and
+ * only upon success, it puts the page back to free page list. Otherwise, it
+ * gives a WARNING to indicate page is leaked.
+ */
+void sgx_encl_free_epc_page(struct sgx_epc_page *page)
+{
+ int ret;
+
+ WARN_ON_ONCE(page->flags & SGX_EPC_PAGE_RECLAIMER_TRACKED);
+
+ ret = __eremove(sgx_get_epc_virt_addr(page));
+ if (WARN_ONCE(ret, EREMOVE_ERROR_MESSAGE, ret, ret))
+ return;
+
+ sgx_free_epc_page(page);
+}
unsigned int sgx_alloc_va_slot(struct sgx_va_page *va_page);
void sgx_free_va_slot(struct sgx_va_page *va_page, unsigned int offset);
bool sgx_va_page_full(struct sgx_va_page *va_page);
+void sgx_encl_free_epc_page(struct sgx_epc_page *page);
#endif /* _X86_ENCL_H */
#include <asm/traps.h>
#include "sgx.h"
-enum sgx_encls_function {
- ECREATE = 0x00,
- EADD = 0x01,
- EINIT = 0x02,
- EREMOVE = 0x03,
- EDGBRD = 0x04,
- EDGBWR = 0x05,
- EEXTEND = 0x06,
- ELDU = 0x08,
- EBLOCK = 0x09,
- EPA = 0x0A,
- EWB = 0x0B,
- ETRACK = 0x0C,
-};
-
/**
* ENCLS_FAULT_FLAG - flag signifying an ENCLS return code is a trapnr
*
} while (0); \
}
+/*
+ * encls_faulted() - Check if an ENCLS leaf faulted given an error code
+ * @ret: the return value of an ENCLS leaf function call
+ *
+ * Return:
+ * - true: ENCLS leaf faulted.
+ * - false: Otherwise.
+ */
+static inline bool encls_faulted(int ret)
+{
+ return ret & ENCLS_FAULT_FLAG;
+}
+
/**
* encls_failed() - Check if an ENCLS function failed
* @ret: the return value of an ENCLS function call
*/
static inline bool encls_failed(int ret)
{
- if (ret & ENCLS_FAULT_FLAG)
+ if (encls_faulted(ret))
return ENCLS_TRAPNR(ret) != X86_TRAP_PF;
return !!ret;
/* Copyright(c) 2016-20 Intel Corporation. */
#include <asm/mman.h>
+#include <asm/sgx.h>
#include <linux/mman.h>
#include <linux/delay.h>
#include <linux/file.h>
encl->page_cnt--;
if (va_page) {
- sgx_free_epc_page(va_page->epc_page);
+ sgx_encl_free_epc_page(va_page->epc_page);
list_del(&va_page->list);
kfree(va_page);
}
return 0;
err_out:
- sgx_free_epc_page(encl->secs.epc_page);
+ sgx_encl_free_epc_page(encl->secs.epc_page);
encl->secs.epc_page = NULL;
err_out_backing:
mmap_read_unlock(current->mm);
err_out_free:
- sgx_free_epc_page(epc_page);
+ sgx_encl_free_epc_page(epc_page);
kfree(encl_page);
return ret;
void *token)
{
u64 mrsigner[4];
- int i, j, k;
+ int i, j;
void *addr;
int ret;
preempt_disable();
- for (k = 0; k < 4; k++)
- wrmsrl(MSR_IA32_SGXLEPUBKEYHASH0 + k, mrsigner[k]);
+ sgx_update_lepubkeyhash(mrsigner);
ret = __einit(sigstruct, token, addr);
}
}
- if (ret & ENCLS_FAULT_FLAG) {
+ if (encls_faulted(ret)) {
if (encls_failed(ret))
ENCLS_WARN(ret, "EINIT");
{
struct sgx_sigstruct *sigstruct;
struct sgx_enclave_init init_arg;
- struct page *initp_page;
void *token;
int ret;
if (copy_from_user(&init_arg, arg, sizeof(init_arg)))
return -EFAULT;
- initp_page = alloc_page(GFP_KERNEL);
- if (!initp_page)
+ /*
+ * 'sigstruct' must be on a page boundary and 'token' on a 512 byte
+ * boundary. kmalloc() will give this alignment when allocating
+ * PAGE_SIZE bytes.
+ */
+ sigstruct = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!sigstruct)
return -ENOMEM;
- sigstruct = kmap(initp_page);
token = (void *)((unsigned long)sigstruct + PAGE_SIZE / 2);
memset(token, 0, SGX_LAUNCH_TOKEN_SIZE);
ret = sgx_encl_init(encl, sigstruct, token);
out:
- kunmap(initp_page);
- __free_page(initp_page);
+ kfree(sigstruct);
return ret;
}
static long sgx_ioc_enclave_provision(struct sgx_encl *encl, void __user *arg)
{
struct sgx_enclave_provision params;
- struct file *file;
if (copy_from_user(¶ms, arg, sizeof(params)))
return -EFAULT;
- file = fget(params.fd);
- if (!file)
- return -EINVAL;
-
- if (file->f_op != &sgx_provision_fops) {
- fput(file);
- return -EINVAL;
- }
-
- encl->attributes_mask |= SGX_ATTR_PROVISIONKEY;
-
- fput(file);
- return 0;
+ return sgx_set_attribute(&encl->attributes_mask, params.fd);
}
long sgx_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
// SPDX-License-Identifier: GPL-2.0
/* Copyright(c) 2016-20 Intel Corporation. */
+#include <linux/file.h>
#include <linux/freezer.h>
#include <linux/highmem.h>
#include <linux/kthread.h>
+#include <linux/miscdevice.h>
#include <linux/pagemap.h>
#include <linux/ratelimit.h>
#include <linux/sched/mm.h>
#include <linux/sched/signal.h>
#include <linux/slab.h>
+#include <asm/sgx.h>
#include "driver.h"
#include "encl.h"
#include "encls.h"
* with sgx_reclaimer_lock acquired.
*/
static LIST_HEAD(sgx_active_page_list);
-
static DEFINE_SPINLOCK(sgx_reclaimer_lock);
+/* The free page list lock protected variables prepend the lock. */
+static unsigned long sgx_nr_free_pages;
+
+/* Nodes with one or more EPC sections. */
+static nodemask_t sgx_numa_mask;
+
+/*
+ * Array with one list_head for each possible NUMA node. Each
+ * list contains all the sgx_epc_section's which are on that
+ * node.
+ */
+static struct sgx_numa_node *sgx_numa_nodes;
+
+static LIST_HEAD(sgx_dirty_page_list);
+
/*
- * Reset dirty EPC pages to uninitialized state. Laundry can be left with SECS
- * pages whose child pages blocked EREMOVE.
+ * Reset post-kexec EPC pages to the uninitialized state. The pages are removed
+ * from the input list, and made available for the page allocator. SECS pages
+ * prepending their children in the input list are left intact.
*/
-static void sgx_sanitize_section(struct sgx_epc_section *section)
+static void __sgx_sanitize_pages(struct list_head *dirty_page_list)
{
struct sgx_epc_page *page;
LIST_HEAD(dirty);
int ret;
- /* init_laundry_list is thread-local, no need for a lock: */
- while (!list_empty(§ion->init_laundry_list)) {
+ /* dirty_page_list is thread-local, no need for a lock: */
+ while (!list_empty(dirty_page_list)) {
if (kthread_should_stop())
return;
- /* needed for access to ->page_list: */
- spin_lock(§ion->lock);
-
- page = list_first_entry(§ion->init_laundry_list,
- struct sgx_epc_page, list);
+ page = list_first_entry(dirty_page_list, struct sgx_epc_page, list);
ret = __eremove(sgx_get_epc_virt_addr(page));
- if (!ret)
- list_move(&page->list, §ion->page_list);
- else
+ if (!ret) {
+ /*
+ * page is now sanitized. Make it available via the SGX
+ * page allocator:
+ */
+ list_del(&page->list);
+ sgx_free_epc_page(page);
+ } else {
+ /* The page is not yet clean - move to the dirty list. */
list_move_tail(&page->list, &dirty);
-
- spin_unlock(§ion->lock);
+ }
cond_resched();
}
- list_splice(&dirty, §ion->init_laundry_list);
+ list_splice(&dirty, dirty_page_list);
}
static bool sgx_reclaimer_age(struct sgx_epc_page *epc_page)
/*
* Swap page to the regular memory transformed to the blocked state by using
- * EBLOCK, which means that it can no loger be referenced (no new TLB entries).
+ * EBLOCK, which means that it can no longer be referenced (no new TLB entries).
*
* The first trial just tries to write the page assuming that some other thread
- * has reset the count for threads inside the enlave by using ETRACK, and
+ * has reset the count for threads inside the enclave by using ETRACK, and
* previous thread count has been zeroed out. The second trial calls ETRACK
* before EWB. If that fails we kick all the HW threads out, and then do EWB,
* which should be guaranteed the succeed.
sgx_encl_ewb(encl->secs.epc_page, &secs_backing);
- sgx_free_epc_page(encl->secs.epc_page);
+ sgx_encl_free_epc_page(encl->secs.epc_page);
encl->secs.epc_page = NULL;
sgx_encl_put_backing(&secs_backing, true);
struct sgx_epc_section *section;
struct sgx_encl_page *encl_page;
struct sgx_epc_page *epc_page;
+ struct sgx_numa_node *node;
pgoff_t page_index;
int cnt = 0;
int ret;
epc_page->flags &= ~SGX_EPC_PAGE_RECLAIMER_TRACKED;
section = &sgx_epc_sections[epc_page->section];
- spin_lock(§ion->lock);
- list_add_tail(&epc_page->list, §ion->page_list);
- section->free_cnt++;
- spin_unlock(§ion->lock);
- }
-}
-
-static unsigned long sgx_nr_free_pages(void)
-{
- unsigned long cnt = 0;
- int i;
-
- for (i = 0; i < sgx_nr_epc_sections; i++)
- cnt += sgx_epc_sections[i].free_cnt;
+ node = section->node;
- return cnt;
+ spin_lock(&node->lock);
+ list_add_tail(&epc_page->list, &node->free_page_list);
+ sgx_nr_free_pages++;
+ spin_unlock(&node->lock);
+ }
}
static bool sgx_should_reclaim(unsigned long watermark)
{
- return sgx_nr_free_pages() < watermark &&
- !list_empty(&sgx_active_page_list);
+ return sgx_nr_free_pages < watermark && !list_empty(&sgx_active_page_list);
}
static int ksgxd(void *p)
{
- int i;
-
set_freezable();
/*
* Sanitize pages in order to recover from kexec(). The 2nd pass is
* required for SECS pages, whose child pages blocked EREMOVE.
*/
- for (i = 0; i < sgx_nr_epc_sections; i++)
- sgx_sanitize_section(&sgx_epc_sections[i]);
-
- for (i = 0; i < sgx_nr_epc_sections; i++) {
- sgx_sanitize_section(&sgx_epc_sections[i]);
+ __sgx_sanitize_pages(&sgx_dirty_page_list);
+ __sgx_sanitize_pages(&sgx_dirty_page_list);
- /* Should never happen. */
- if (!list_empty(&sgx_epc_sections[i].init_laundry_list))
- WARN(1, "EPC section %d has unsanitized pages.\n", i);
- }
+ /* sanity check: */
+ WARN_ON(!list_empty(&sgx_dirty_page_list));
while (!kthread_should_stop()) {
if (try_to_freeze())
return true;
}
-static struct sgx_epc_page *__sgx_alloc_epc_page_from_section(struct sgx_epc_section *section)
+static struct sgx_epc_page *__sgx_alloc_epc_page_from_node(int nid)
{
- struct sgx_epc_page *page;
+ struct sgx_numa_node *node = &sgx_numa_nodes[nid];
+ struct sgx_epc_page *page = NULL;
- spin_lock(§ion->lock);
+ spin_lock(&node->lock);
- if (list_empty(§ion->page_list)) {
- spin_unlock(§ion->lock);
+ if (list_empty(&node->free_page_list)) {
+ spin_unlock(&node->lock);
return NULL;
}
- page = list_first_entry(§ion->page_list, struct sgx_epc_page, list);
+ page = list_first_entry(&node->free_page_list, struct sgx_epc_page, list);
list_del_init(&page->list);
- section->free_cnt--;
+ sgx_nr_free_pages--;
+
+ spin_unlock(&node->lock);
- spin_unlock(§ion->lock);
return page;
}
/**
* __sgx_alloc_epc_page() - Allocate an EPC page
*
- * Iterate through EPC sections and borrow a free EPC page to the caller. When a
- * page is no longer needed it must be released with sgx_free_epc_page().
+ * Iterate through NUMA nodes and reserve ia free EPC page to the caller. Start
+ * from the NUMA node, where the caller is executing.
*
* Return:
- * an EPC page,
- * -errno on error
+ * - an EPC page: A borrowed EPC pages were available.
+ * - NULL: Out of EPC pages.
*/
struct sgx_epc_page *__sgx_alloc_epc_page(void)
{
- struct sgx_epc_section *section;
struct sgx_epc_page *page;
- int i;
+ int nid_of_current = numa_node_id();
+ int nid = nid_of_current;
- for (i = 0; i < sgx_nr_epc_sections; i++) {
- section = &sgx_epc_sections[i];
+ if (node_isset(nid_of_current, sgx_numa_mask)) {
+ page = __sgx_alloc_epc_page_from_node(nid_of_current);
+ if (page)
+ return page;
+ }
+
+ /* Fall back to the non-local NUMA nodes: */
+ while (true) {
+ nid = next_node_in(nid, sgx_numa_mask);
+ if (nid == nid_of_current)
+ break;
- page = __sgx_alloc_epc_page_from_section(section);
+ page = __sgx_alloc_epc_page_from_node(nid);
if (page)
return page;
}
* sgx_free_epc_page() - Free an EPC page
* @page: an EPC page
*
- * Call EREMOVE for an EPC page and insert it back to the list of free pages.
+ * Put the EPC page back to the list of free pages. It's the caller's
+ * responsibility to make sure that the page is in uninitialized state. In other
+ * words, do EREMOVE, EWB or whatever operation is necessary before calling
+ * this function.
*/
void sgx_free_epc_page(struct sgx_epc_page *page)
{
struct sgx_epc_section *section = &sgx_epc_sections[page->section];
- int ret;
+ struct sgx_numa_node *node = section->node;
- WARN_ON_ONCE(page->flags & SGX_EPC_PAGE_RECLAIMER_TRACKED);
+ spin_lock(&node->lock);
- ret = __eremove(sgx_get_epc_virt_addr(page));
- if (WARN_ONCE(ret, "EREMOVE returned %d (0x%x)", ret, ret))
- return;
+ list_add_tail(&page->list, &node->free_page_list);
+ sgx_nr_free_pages++;
- spin_lock(§ion->lock);
- list_add_tail(&page->list, §ion->page_list);
- section->free_cnt++;
- spin_unlock(§ion->lock);
+ spin_unlock(&node->lock);
}
static bool __init sgx_setup_epc_section(u64 phys_addr, u64 size,
}
section->phys_addr = phys_addr;
- spin_lock_init(§ion->lock);
- INIT_LIST_HEAD(§ion->page_list);
- INIT_LIST_HEAD(§ion->init_laundry_list);
for (i = 0; i < nr_pages; i++) {
section->pages[i].section = index;
section->pages[i].flags = 0;
section->pages[i].owner = NULL;
- list_add_tail(§ion->pages[i].list, §ion->init_laundry_list);
+ list_add_tail(§ion->pages[i].list, &sgx_dirty_page_list);
}
- section->free_cnt = nr_pages;
return true;
}
{
u32 eax, ebx, ecx, edx, type;
u64 pa, size;
+ int nid;
int i;
+ sgx_numa_nodes = kmalloc_array(num_possible_nodes(), sizeof(*sgx_numa_nodes), GFP_KERNEL);
+ if (!sgx_numa_nodes)
+ return false;
+
for (i = 0; i < ARRAY_SIZE(sgx_epc_sections); i++) {
cpuid_count(SGX_CPUID, i + SGX_CPUID_EPC, &eax, &ebx, &ecx, &edx);
break;
}
+ nid = numa_map_to_online_node(phys_to_target_node(pa));
+ if (nid == NUMA_NO_NODE) {
+ /* The physical address is already printed above. */
+ pr_warn(FW_BUG "Unable to map EPC section to online node. Fallback to the NUMA node 0.\n");
+ nid = 0;
+ }
+
+ if (!node_isset(nid, sgx_numa_mask)) {
+ spin_lock_init(&sgx_numa_nodes[nid].lock);
+ INIT_LIST_HEAD(&sgx_numa_nodes[nid].free_page_list);
+ node_set(nid, sgx_numa_mask);
+ }
+
+ sgx_epc_sections[i].node = &sgx_numa_nodes[nid];
+
sgx_nr_epc_sections++;
}
return true;
}
+/*
+ * Update the SGX_LEPUBKEYHASH MSRs to the values specified by caller.
+ * Bare-metal driver requires to update them to hash of enclave's signer
+ * before EINIT. KVM needs to update them to guest's virtual MSR values
+ * before doing EINIT from guest.
+ */
+void sgx_update_lepubkeyhash(u64 *lepubkeyhash)
+{
+ int i;
+
+ WARN_ON_ONCE(preemptible());
+
+ for (i = 0; i < 4; i++)
+ wrmsrl(MSR_IA32_SGXLEPUBKEYHASH0 + i, lepubkeyhash[i]);
+}
+
+const struct file_operations sgx_provision_fops = {
+ .owner = THIS_MODULE,
+};
+
+static struct miscdevice sgx_dev_provision = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = "sgx_provision",
+ .nodename = "sgx_provision",
+ .fops = &sgx_provision_fops,
+};
+
+/**
+ * sgx_set_attribute() - Update allowed attributes given file descriptor
+ * @allowed_attributes: Pointer to allowed enclave attributes
+ * @attribute_fd: File descriptor for specific attribute
+ *
+ * Append enclave attribute indicated by file descriptor to allowed
+ * attributes. Currently only SGX_ATTR_PROVISIONKEY indicated by
+ * /dev/sgx_provision is supported.
+ *
+ * Return:
+ * -0: SGX_ATTR_PROVISIONKEY is appended to allowed_attributes
+ * -EINVAL: Invalid, or not supported file descriptor
+ */
+int sgx_set_attribute(unsigned long *allowed_attributes,
+ unsigned int attribute_fd)
+{
+ struct file *file;
+
+ file = fget(attribute_fd);
+ if (!file)
+ return -EINVAL;
+
+ if (file->f_op != &sgx_provision_fops) {
+ fput(file);
+ return -EINVAL;
+ }
+
+ *allowed_attributes |= SGX_ATTR_PROVISIONKEY;
+
+ fput(file);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(sgx_set_attribute);
+
static int __init sgx_init(void)
{
int ret;
goto err_page_cache;
}
- ret = sgx_drv_init();
+ ret = misc_register(&sgx_dev_provision);
if (ret)
goto err_kthread;
+ /*
+ * Always try to initialize the native *and* KVM drivers.
+ * The KVM driver is less picky than the native one and
+ * can function if the native one is not supported on the
+ * current system or fails to initialize.
+ *
+ * Error out only if both fail to initialize.
+ */
+ ret = sgx_drv_init();
+
+ if (sgx_vepc_init() && ret)
+ goto err_provision;
+
return 0;
+err_provision:
+ misc_deregister(&sgx_dev_provision);
+
err_kthread:
kthread_stop(ksgxd_tsk);
#include <linux/rwsem.h>
#include <linux/types.h>
#include <asm/asm.h>
-#include "arch.h"
+#include <asm/sgx.h>
#undef pr_fmt
#define pr_fmt(fmt) "sgx: " fmt
+#define EREMOVE_ERROR_MESSAGE \
+ "EREMOVE returned %d (0x%x) and an EPC page was leaked. SGX may become unusable. " \
+ "Refer to Documentation/x86/sgx.rst for more information."
+
#define SGX_MAX_EPC_SECTIONS 8
#define SGX_EEXTEND_BLOCK_SIZE 256
#define SGX_NR_TO_SCAN 16
};
/*
+ * Contains the tracking data for NUMA nodes having EPC pages. Most importantly,
+ * the free page list local to the node is stored here.
+ */
+struct sgx_numa_node {
+ struct list_head free_page_list;
+ spinlock_t lock;
+};
+
+/*
* The firmware can define multiple chunks of EPC to the different areas of the
* physical memory e.g. for memory areas of the each node. This structure is
* used to store EPC pages for one EPC section and virtual memory area where
* the pages have been mapped.
- *
- * 'lock' must be held before accessing 'page_list' or 'free_cnt'.
*/
struct sgx_epc_section {
unsigned long phys_addr;
void *virt_addr;
struct sgx_epc_page *pages;
-
- spinlock_t lock;
- struct list_head page_list;
- unsigned long free_cnt;
-
- /*
- * Pages which need EREMOVE run on them before they can be
- * used. Only safe to be accessed in ksgxd and init code.
- * Not protected by locks.
- */
- struct list_head init_laundry_list;
+ struct sgx_numa_node *node;
};
extern struct sgx_epc_section sgx_epc_sections[SGX_MAX_EPC_SECTIONS];
int sgx_unmark_page_reclaimable(struct sgx_epc_page *page);
struct sgx_epc_page *sgx_alloc_epc_page(void *owner, bool reclaim);
+#ifdef CONFIG_X86_SGX_KVM
+int __init sgx_vepc_init(void);
+#else
+static inline int __init sgx_vepc_init(void)
+{
+ return -ENODEV;
+}
+#endif
+
+void sgx_update_lepubkeyhash(u64 *lepubkeyhash);
+
#endif /* _X86_SGX_H */
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Device driver to expose SGX enclave memory to KVM guests.
+ *
+ * Copyright(c) 2021 Intel Corporation.
+ */
+
+#include <linux/miscdevice.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/signal.h>
+#include <linux/slab.h>
+#include <linux/xarray.h>
+#include <asm/sgx.h>
+#include <uapi/asm/sgx.h>
+
+#include "encls.h"
+#include "sgx.h"
+
+struct sgx_vepc {
+ struct xarray page_array;
+ struct mutex lock;
+};
+
+/*
+ * Temporary SECS pages that cannot be EREMOVE'd due to having child in other
+ * virtual EPC instances, and the lock to protect it.
+ */
+static struct mutex zombie_secs_pages_lock;
+static struct list_head zombie_secs_pages;
+
+static int __sgx_vepc_fault(struct sgx_vepc *vepc,
+ struct vm_area_struct *vma, unsigned long addr)
+{
+ struct sgx_epc_page *epc_page;
+ unsigned long index, pfn;
+ int ret;
+
+ WARN_ON(!mutex_is_locked(&vepc->lock));
+
+ /* Calculate index of EPC page in virtual EPC's page_array */
+ index = vma->vm_pgoff + PFN_DOWN(addr - vma->vm_start);
+
+ epc_page = xa_load(&vepc->page_array, index);
+ if (epc_page)
+ return 0;
+
+ epc_page = sgx_alloc_epc_page(vepc, false);
+ if (IS_ERR(epc_page))
+ return PTR_ERR(epc_page);
+
+ ret = xa_err(xa_store(&vepc->page_array, index, epc_page, GFP_KERNEL));
+ if (ret)
+ goto err_free;
+
+ pfn = PFN_DOWN(sgx_get_epc_phys_addr(epc_page));
+
+ ret = vmf_insert_pfn(vma, addr, pfn);
+ if (ret != VM_FAULT_NOPAGE) {
+ ret = -EFAULT;
+ goto err_delete;
+ }
+
+ return 0;
+
+err_delete:
+ xa_erase(&vepc->page_array, index);
+err_free:
+ sgx_free_epc_page(epc_page);
+ return ret;
+}
+
+static vm_fault_t sgx_vepc_fault(struct vm_fault *vmf)
+{
+ struct vm_area_struct *vma = vmf->vma;
+ struct sgx_vepc *vepc = vma->vm_private_data;
+ int ret;
+
+ mutex_lock(&vepc->lock);
+ ret = __sgx_vepc_fault(vepc, vma, vmf->address);
+ mutex_unlock(&vepc->lock);
+
+ if (!ret)
+ return VM_FAULT_NOPAGE;
+
+ if (ret == -EBUSY && (vmf->flags & FAULT_FLAG_ALLOW_RETRY)) {
+ mmap_read_unlock(vma->vm_mm);
+ return VM_FAULT_RETRY;
+ }
+
+ return VM_FAULT_SIGBUS;
+}
+
+static const struct vm_operations_struct sgx_vepc_vm_ops = {
+ .fault = sgx_vepc_fault,
+};
+
+static int sgx_vepc_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ struct sgx_vepc *vepc = file->private_data;
+
+ if (!(vma->vm_flags & VM_SHARED))
+ return -EINVAL;
+
+ vma->vm_ops = &sgx_vepc_vm_ops;
+ /* Don't copy VMA in fork() */
+ vma->vm_flags |= VM_PFNMAP | VM_IO | VM_DONTDUMP | VM_DONTCOPY;
+ vma->vm_private_data = vepc;
+
+ return 0;
+}
+
+static int sgx_vepc_free_page(struct sgx_epc_page *epc_page)
+{
+ int ret;
+
+ /*
+ * Take a previously guest-owned EPC page and return it to the
+ * general EPC page pool.
+ *
+ * Guests can not be trusted to have left this page in a good
+ * state, so run EREMOVE on the page unconditionally. In the
+ * case that a guest properly EREMOVE'd this page, a superfluous
+ * EREMOVE is harmless.
+ */
+ ret = __eremove(sgx_get_epc_virt_addr(epc_page));
+ if (ret) {
+ /*
+ * Only SGX_CHILD_PRESENT is expected, which is because of
+ * EREMOVE'ing an SECS still with child, in which case it can
+ * be handled by EREMOVE'ing the SECS again after all pages in
+ * virtual EPC have been EREMOVE'd. See comments in below in
+ * sgx_vepc_release().
+ *
+ * The user of virtual EPC (KVM) needs to guarantee there's no
+ * logical processor is still running in the enclave in guest,
+ * otherwise EREMOVE will get SGX_ENCLAVE_ACT which cannot be
+ * handled here.
+ */
+ WARN_ONCE(ret != SGX_CHILD_PRESENT, EREMOVE_ERROR_MESSAGE,
+ ret, ret);
+ return ret;
+ }
+
+ sgx_free_epc_page(epc_page);
+
+ return 0;
+}
+
+static int sgx_vepc_release(struct inode *inode, struct file *file)
+{
+ struct sgx_vepc *vepc = file->private_data;
+ struct sgx_epc_page *epc_page, *tmp, *entry;
+ unsigned long index;
+
+ LIST_HEAD(secs_pages);
+
+ xa_for_each(&vepc->page_array, index, entry) {
+ /*
+ * Remove all normal, child pages. sgx_vepc_free_page()
+ * will fail if EREMOVE fails, but this is OK and expected on
+ * SECS pages. Those can only be EREMOVE'd *after* all their
+ * child pages. Retries below will clean them up.
+ */
+ if (sgx_vepc_free_page(entry))
+ continue;
+
+ xa_erase(&vepc->page_array, index);
+ }
+
+ /*
+ * Retry EREMOVE'ing pages. This will clean up any SECS pages that
+ * only had children in this 'epc' area.
+ */
+ xa_for_each(&vepc->page_array, index, entry) {
+ epc_page = entry;
+ /*
+ * An EREMOVE failure here means that the SECS page still
+ * has children. But, since all children in this 'sgx_vepc'
+ * have been removed, the SECS page must have a child on
+ * another instance.
+ */
+ if (sgx_vepc_free_page(epc_page))
+ list_add_tail(&epc_page->list, &secs_pages);
+
+ xa_erase(&vepc->page_array, index);
+ }
+
+ /*
+ * SECS pages are "pinned" by child pages, and "unpinned" once all
+ * children have been EREMOVE'd. A child page in this instance
+ * may have pinned an SECS page encountered in an earlier release(),
+ * creating a zombie. Since some children were EREMOVE'd above,
+ * try to EREMOVE all zombies in the hopes that one was unpinned.
+ */
+ mutex_lock(&zombie_secs_pages_lock);
+ list_for_each_entry_safe(epc_page, tmp, &zombie_secs_pages, list) {
+ /*
+ * Speculatively remove the page from the list of zombies,
+ * if the page is successfully EREMOVE'd it will be added to
+ * the list of free pages. If EREMOVE fails, throw the page
+ * on the local list, which will be spliced on at the end.
+ */
+ list_del(&epc_page->list);
+
+ if (sgx_vepc_free_page(epc_page))
+ list_add_tail(&epc_page->list, &secs_pages);
+ }
+
+ if (!list_empty(&secs_pages))
+ list_splice_tail(&secs_pages, &zombie_secs_pages);
+ mutex_unlock(&zombie_secs_pages_lock);
+
+ kfree(vepc);
+
+ return 0;
+}
+
+static int sgx_vepc_open(struct inode *inode, struct file *file)
+{
+ struct sgx_vepc *vepc;
+
+ vepc = kzalloc(sizeof(struct sgx_vepc), GFP_KERNEL);
+ if (!vepc)
+ return -ENOMEM;
+ mutex_init(&vepc->lock);
+ xa_init(&vepc->page_array);
+
+ file->private_data = vepc;
+
+ return 0;
+}
+
+static const struct file_operations sgx_vepc_fops = {
+ .owner = THIS_MODULE,
+ .open = sgx_vepc_open,
+ .release = sgx_vepc_release,
+ .mmap = sgx_vepc_mmap,
+};
+
+static struct miscdevice sgx_vepc_dev = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = "sgx_vepc",
+ .nodename = "sgx_vepc",
+ .fops = &sgx_vepc_fops,
+};
+
+int __init sgx_vepc_init(void)
+{
+ /* SGX virtualization requires KVM to work */
+ if (!cpu_feature_enabled(X86_FEATURE_VMX))
+ return -ENODEV;
+
+ INIT_LIST_HEAD(&zombie_secs_pages);
+ mutex_init(&zombie_secs_pages_lock);
+
+ return misc_register(&sgx_vepc_dev);
+}
+
+/**
+ * sgx_virt_ecreate() - Run ECREATE on behalf of guest
+ * @pageinfo: Pointer to PAGEINFO structure
+ * @secs: Userspace pointer to SECS page
+ * @trapnr: trap number injected to guest in case of ECREATE error
+ *
+ * Run ECREATE on behalf of guest after KVM traps ECREATE for the purpose
+ * of enforcing policies of guest's enclaves, and return the trap number
+ * which should be injected to guest in case of any ECREATE error.
+ *
+ * Return:
+ * - 0: ECREATE was successful.
+ * - <0: on error.
+ */
+int sgx_virt_ecreate(struct sgx_pageinfo *pageinfo, void __user *secs,
+ int *trapnr)
+{
+ int ret;
+
+ /*
+ * @secs is an untrusted, userspace-provided address. It comes from
+ * KVM and is assumed to be a valid pointer which points somewhere in
+ * userspace. This can fault and call SGX or other fault handlers when
+ * userspace mapping @secs doesn't exist.
+ *
+ * Add a WARN() to make sure @secs is already valid userspace pointer
+ * from caller (KVM), who should already have handled invalid pointer
+ * case (for instance, made by malicious guest). All other checks,
+ * such as alignment of @secs, are deferred to ENCLS itself.
+ */
+ if (WARN_ON_ONCE(!access_ok(secs, PAGE_SIZE)))
+ return -EINVAL;
+
+ __uaccess_begin();
+ ret = __ecreate(pageinfo, (void *)secs);
+ __uaccess_end();
+
+ if (encls_faulted(ret)) {
+ *trapnr = ENCLS_TRAPNR(ret);
+ return -EFAULT;
+ }
+
+ /* ECREATE doesn't return an error code, it faults or succeeds. */
+ WARN_ON_ONCE(ret);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(sgx_virt_ecreate);
+
+static int __sgx_virt_einit(void __user *sigstruct, void __user *token,
+ void __user *secs)
+{
+ int ret;
+
+ /*
+ * Make sure all userspace pointers from caller (KVM) are valid.
+ * All other checks deferred to ENCLS itself. Also see comment
+ * for @secs in sgx_virt_ecreate().
+ */
+#define SGX_EINITTOKEN_SIZE 304
+ if (WARN_ON_ONCE(!access_ok(sigstruct, sizeof(struct sgx_sigstruct)) ||
+ !access_ok(token, SGX_EINITTOKEN_SIZE) ||
+ !access_ok(secs, PAGE_SIZE)))
+ return -EINVAL;
+
+ __uaccess_begin();
+ ret = __einit((void *)sigstruct, (void *)token, (void *)secs);
+ __uaccess_end();
+
+ return ret;
+}
+
+/**
+ * sgx_virt_einit() - Run EINIT on behalf of guest
+ * @sigstruct: Userspace pointer to SIGSTRUCT structure
+ * @token: Userspace pointer to EINITTOKEN structure
+ * @secs: Userspace pointer to SECS page
+ * @lepubkeyhash: Pointer to guest's *virtual* SGX_LEPUBKEYHASH MSR values
+ * @trapnr: trap number injected to guest in case of EINIT error
+ *
+ * Run EINIT on behalf of guest after KVM traps EINIT. If SGX_LC is available
+ * in host, SGX driver may rewrite the hardware values at wish, therefore KVM
+ * needs to update hardware values to guest's virtual MSR values in order to
+ * ensure EINIT is executed with expected hardware values.
+ *
+ * Return:
+ * - 0: EINIT was successful.
+ * - <0: on error.
+ */
+int sgx_virt_einit(void __user *sigstruct, void __user *token,
+ void __user *secs, u64 *lepubkeyhash, int *trapnr)
+{
+ int ret;
+
+ if (!cpu_feature_enabled(X86_FEATURE_SGX_LC)) {
+ ret = __sgx_virt_einit(sigstruct, token, secs);
+ } else {
+ preempt_disable();
+
+ sgx_update_lepubkeyhash(lepubkeyhash);
+
+ ret = __sgx_virt_einit(sigstruct, token, secs);
+ preempt_enable();
+ }
+
+ /* Propagate up the error from the WARN_ON_ONCE in __sgx_virt_einit() */
+ if (ret == -EINVAL)
+ return ret;
+
+ if (encls_faulted(ret)) {
+ *trapnr = ENCLS_TRAPNR(ret);
+ return -EFAULT;
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(sgx_virt_einit);
#ifdef CONFIG_SMP
/*
- * Check if given CPUID extended toplogy "leaf" is implemented
+ * Check if given CPUID extended topology "leaf" is implemented
*/
static int check_extended_topology_leaf(int leaf)
{
return 0;
}
/*
- * Return best CPUID Extended Toplogy Leaf supported
+ * Return best CPUID Extended Topology Leaf supported
*/
static int detect_extended_topology_leaf(struct cpuinfo_x86 *c)
{
#include <linux/clocksource.h>
#include <linux/cpu.h>
#include <linux/reboot.h>
+#include <linux/static_call.h>
#include <asm/div64.h>
#include <asm/x86_init.h>
#include <asm/hypervisor.h>
vmware_cyc2ns_setup();
if (vmw_sched_clock)
- pv_ops.time.sched_clock = vmware_sched_clock;
+ paravirt_set_sched_clock(vmware_sched_clock);
if (vmware_is_stealclock_available()) {
has_steal_clock = true;
- pv_ops.time.steal_clock = vmware_steal_clock;
+ static_call_update(pv_steal_clock, vmware_steal_clock);
/* We use reboot notifier only to disable steal clock */
register_reboot_notifier(&vmware_pv_reboot_nb);
{
setup_force_cpu_cap(X86_FEATURE_CONSTANT_TSC);
setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
+ if (vmware_tsc_khz)
+ setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
if (vmware_hypercall_mode == CPUID_VMWARE_FEATURES_ECX_VMCALL)
setup_force_cpu_cap(X86_FEATURE_VMCALL);
else if (vmware_hypercall_mode == CPUID_VMWARE_FEATURES_ECX_VMMCALL)
struct crash_memmap_data cmd;
struct crash_mem *cmem;
- cmem = vzalloc(sizeof(struct crash_mem));
+ cmem = vzalloc(struct_size(cmem, ranges, 1));
if (!cmem)
return -ENOMEM;
#endif
/*
- * Allocate the requested number of bytes with the requsted alignment
+ * Allocate the requested number of bytes with the requested alignment
* and return (the physical address) to the caller. Also register this
* range in the 'kexec' E820 table as a reserved range.
*
static void __init setup_xstate_features(void)
{
u32 eax, ebx, ecx, edx, i;
- /* start at the beginnning of the "extended state" */
+ /* start at the beginning of the "extended state" */
unsigned int last_good_offset = offsetof(struct xregs_state,
extended_state_area);
/*
static bool __head check_la57_support(unsigned long physaddr)
{
/*
- * 5-level paging is detected and enabled at kernel decomression
+ * 5-level paging is detected and enabled at kernel decompression
* stage. Only check if it has been enabled there.
*/
if (!(native_read_cr4() & X86_CR4_LA57))
* after that.
*
* Note, that X86_64 cannot install the real #PF handler in
- * idt_setup_early_traps() because the memory intialization needs the #PF
+ * idt_setup_early_traps() because the memory initialization needs the #PF
* handler from the early_idt_handler_array to initialize the early page
* tables.
*/
irq_migrate_all_off_this_cpu();
/*
- * We can remove mdelay() and then send spuriuous interrupts to
+ * We can remove mdelay() and then send spurious interrupts to
* new cpu targets for all the irqs that were handled previously by
* this cpu. While it works, I have seen spurious interrupt messages
* (nothing wrong but still...).
* Updated by: Tom Rini <trini@kernel.crashing.org>
* Updated by: Jason Wessel <jason.wessel@windriver.com>
* Modified for 386 by Jim Kingdon, Cygnus Support.
- * Origianl kgdb, compatibility with 2.1.xx kernel by
+ * Original kgdb, compatibility with 2.1.xx kernel by
* David Grothe <dave@gcom.com>
* Integrated into 2.2.5 kernel by Tigran Aivazian <tigran@sco.com>
* X86_64 changes from Andi Kleen's patch merged by Jim Houston
struct perf_event **pevent;
/*
- * Pre-allocate the hw breakpoint structions in the non-atomic
+ * Pre-allocate the hw breakpoint instructions in the non-atomic
* portion of kgdb because this operation requires mutexs to
* complete.
*/
#include "common.h"
-/* Ftrace callback handler for kprobes -- called under preepmt disabed */
+/* Ftrace callback handler for kprobes -- called under preempt disabled */
void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *ops, struct ftrace_regs *fregs)
{
if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
has_steal_clock = 1;
- pv_ops.time.steal_clock = kvm_steal_clock;
+ static_call_update(pv_steal_clock, kvm_steal_clock);
}
if (pv_tlb_flush_supported()) {
static void kvm_wait(u8 *ptr, u8 val)
{
- unsigned long flags;
-
if (in_nmi())
return;
- local_irq_save(flags);
-
- if (READ_ONCE(*ptr) != val)
- goto out;
-
/*
* halt until it's our turn and kicked. Note that we do safe halt
* for irq enabled case to avoid hang when lock info is overwritten
* in irq spinlock slowpath and no spurious interrupt occur to save us.
*/
- if (arch_irqs_disabled_flags(flags))
- halt();
- else
- safe_halt();
+ if (irqs_disabled()) {
+ if (READ_ONCE(*ptr) == val)
+ halt();
+ } else {
+ local_irq_disable();
-out:
- local_irq_restore(flags);
+ if (READ_ONCE(*ptr) == val)
+ safe_halt();
+
+ local_irq_enable();
+ }
}
#ifdef CONFIG_X86_32
if (!stable)
clear_sched_clock_stable();
kvm_sched_clock_offset = kvm_clock_read();
- pv_ops.time.sched_clock = kvm_sched_clock_read;
+ paravirt_set_sched_clock(kvm_sched_clock_read);
pr_info("kvm-clock: using sched offset of %llu cycles",
kvm_sched_clock_offset);
static int __init kvm_setup_vsyscall_timeinfo(void)
{
-#ifdef CONFIG_X86_64
- u8 flags;
+ kvmclock_init_mem();
- if (!per_cpu(hv_clock_per_cpu, 0) || !kvmclock_vsyscall)
- return 0;
+#ifdef CONFIG_X86_64
+ if (per_cpu(hv_clock_per_cpu, 0) && kvmclock_vsyscall) {
+ u8 flags;
- flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
- if (!(flags & PVCLOCK_TSC_STABLE_BIT))
- return 0;
+ flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
+ if (!(flags & PVCLOCK_TSC_STABLE_BIT))
+ return 0;
- kvm_clock.vdso_clock_mode = VDSO_CLOCKMODE_PVCLOCK;
+ kvm_clock.vdso_clock_mode = VDSO_CLOCKMODE_PVCLOCK;
+ }
#endif
- kvmclock_init_mem();
-
return 0;
}
early_initcall(kvm_setup_vsyscall_timeinfo);
{
struct desc_ptr curidt;
- /* x86-64 supports unaliged loads & stores */
+ /* x86-64 supports unaligned loads & stores */
curidt.size = limit;
curidt.address = (unsigned long)newidt;
return pv_ops.lock.vcpu_is_preempted.func ==
__raw_callee_save___native_vcpu_is_preempted;
}
+
+void __init paravirt_set_cap(void)
+{
+ if (!pv_is_native_spin_unlock())
+ setup_force_cpu_cap(X86_FEATURE_PVUNLOCK);
+
+ if (!pv_is_native_vcpu_is_preempted())
+ setup_force_cpu_cap(X86_FEATURE_VCPUPREEMPT);
+}
#include <linux/highmem.h>
#include <linux/kprobes.h>
#include <linux/pgtable.h>
+#include <linux/static_call.h>
#include <asm/bug.h>
#include <asm/paravirt.h>
}
/* Undefined instruction for dealing with missing ops pointers. */
-static const unsigned char ud2a[] = { 0x0f, 0x0b };
+static void paravirt_BUG(void)
+{
+ BUG();
+}
struct branch {
unsigned char opcode;
{
return x;
}
-
-static unsigned paravirt_patch_jmp(void *insn_buff, const void *target,
- unsigned long addr, unsigned len)
-{
- struct branch *b = insn_buff;
- unsigned long delta = (unsigned long)target - (addr+5);
-
- if (len < 5) {
-#ifdef CONFIG_RETPOLINE
- WARN_ONCE(1, "Failing to patch indirect JMP in %ps\n", (void *)addr);
-#endif
- return len; /* call too long for patch site */
- }
-
- b->opcode = 0xe9; /* jmp */
- b->delta = delta;
-
- return 5;
-}
#endif
DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key);
static_branch_disable(&virt_spin_lock_key);
}
-unsigned paravirt_patch_default(u8 type, void *insn_buff,
- unsigned long addr, unsigned len)
+unsigned int paravirt_patch(u8 type, void *insn_buff, unsigned long addr,
+ unsigned int len)
{
/*
* Neat trick to map patch type back to the call within the
unsigned ret;
if (opfunc == NULL)
- /* If there's no function, patch it with a ud2a (BUG) */
- ret = paravirt_patch_insns(insn_buff, len, ud2a, ud2a+sizeof(ud2a));
+ /* If there's no function, patch it with paravirt_BUG() */
+ ret = paravirt_patch_call(insn_buff, paravirt_BUG, addr, len);
else if (opfunc == _paravirt_nop)
ret = 0;
-
-#ifdef CONFIG_PARAVIRT_XXL
- /* identity functions just return their single argument */
- else if (opfunc == _paravirt_ident_64)
- ret = paravirt_patch_ident_64(insn_buff, len);
-
- else if (type == PARAVIRT_PATCH(cpu.iret))
- /* If operation requires a jmp, then jmp */
- ret = paravirt_patch_jmp(insn_buff, opfunc, addr, len);
-#endif
else
/* Otherwise call the function. */
ret = paravirt_patch_call(insn_buff, opfunc, addr, len);
return ret;
}
-unsigned paravirt_patch_insns(void *insn_buff, unsigned len,
- const char *start, const char *end)
-{
- unsigned insn_len = end - start;
-
- /* Alternative instruction is too large for the patch site and we cannot continue: */
- BUG_ON(insn_len > len || start == NULL);
-
- memcpy(insn_buff, start, insn_len);
-
- return insn_len;
-}
-
struct static_key paravirt_steal_enabled;
struct static_key paravirt_steal_rq_enabled;
return 0;
}
+DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock);
+DEFINE_STATIC_CALL(pv_sched_clock, native_sched_clock);
+
+void paravirt_set_sched_clock(u64 (*func)(void))
+{
+ static_call_update(pv_sched_clock, func);
+}
+
/* These are in entry.S */
extern void native_iret(void);
#define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_64)
struct paravirt_patch_template pv_ops = {
- /* Init ops. */
- .init.patch = native_patch,
-
- /* Time ops. */
- .time.sched_clock = native_sched_clock,
- .time.steal_clock = native_steal_clock,
-
/* Cpu ops. */
.cpu.io_delay = native_io_delay,
.cpu.load_sp0 = native_load_sp0,
- .cpu.iret = native_iret,
-
#ifdef CONFIG_X86_IOPL_IOPERM
.cpu.invalidate_io_bitmap = native_tss_invalidate_io_bitmap,
.cpu.update_io_bitmap = native_tss_update_io_bitmap,
NOKPROBE_SYMBOL(native_get_debugreg);
NOKPROBE_SYMBOL(native_set_debugreg);
NOKPROBE_SYMBOL(native_load_idt);
+
+void (*paravirt_iret)(void) = native_iret;
#endif
EXPORT_SYMBOL(pv_ops);
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/stringify.h>
-
-#include <asm/paravirt.h>
-#include <asm/asm-offsets.h>
-
-#define PSTART(d, m) \
- patch_data_##d.m
-
-#define PEND(d, m) \
- (PSTART(d, m) + sizeof(patch_data_##d.m))
-
-#define PATCH(d, m, insn_buff, len) \
- paravirt_patch_insns(insn_buff, len, PSTART(d, m), PEND(d, m))
-
-#define PATCH_CASE(ops, m, data, insn_buff, len) \
- case PARAVIRT_PATCH(ops.m): \
- return PATCH(data, ops##_##m, insn_buff, len)
-
-#ifdef CONFIG_PARAVIRT_XXL
-struct patch_xxl {
- const unsigned char irq_irq_disable[1];
- const unsigned char irq_irq_enable[1];
- const unsigned char irq_save_fl[2];
- const unsigned char mmu_read_cr2[3];
- const unsigned char mmu_read_cr3[3];
- const unsigned char mmu_write_cr3[3];
- const unsigned char cpu_wbinvd[2];
- const unsigned char mov64[3];
-};
-
-static const struct patch_xxl patch_data_xxl = {
- .irq_irq_disable = { 0xfa }, // cli
- .irq_irq_enable = { 0xfb }, // sti
- .irq_save_fl = { 0x9c, 0x58 }, // pushf; pop %[re]ax
- .mmu_read_cr2 = { 0x0f, 0x20, 0xd0 }, // mov %cr2, %[re]ax
- .mmu_read_cr3 = { 0x0f, 0x20, 0xd8 }, // mov %cr3, %[re]ax
- .mmu_write_cr3 = { 0x0f, 0x22, 0xdf }, // mov %rdi, %cr3
- .cpu_wbinvd = { 0x0f, 0x09 }, // wbinvd
- .mov64 = { 0x48, 0x89, 0xf8 }, // mov %rdi, %rax
-};
-
-unsigned int paravirt_patch_ident_64(void *insn_buff, unsigned int len)
-{
- return PATCH(xxl, mov64, insn_buff, len);
-}
-# endif /* CONFIG_PARAVIRT_XXL */
-
-#ifdef CONFIG_PARAVIRT_SPINLOCKS
-struct patch_lock {
- unsigned char queued_spin_unlock[3];
- unsigned char vcpu_is_preempted[2];
-};
-
-static const struct patch_lock patch_data_lock = {
- .vcpu_is_preempted = { 0x31, 0xc0 }, // xor %eax, %eax
-
-# ifdef CONFIG_X86_64
- .queued_spin_unlock = { 0xc6, 0x07, 0x00 }, // movb $0, (%rdi)
-# else
- .queued_spin_unlock = { 0xc6, 0x00, 0x00 }, // movb $0, (%eax)
-# endif
-};
-#endif /* CONFIG_PARAVIRT_SPINLOCKS */
-
-unsigned int native_patch(u8 type, void *insn_buff, unsigned long addr,
- unsigned int len)
-{
- switch (type) {
-
-#ifdef CONFIG_PARAVIRT_XXL
- PATCH_CASE(irq, save_fl, xxl, insn_buff, len);
- PATCH_CASE(irq, irq_enable, xxl, insn_buff, len);
- PATCH_CASE(irq, irq_disable, xxl, insn_buff, len);
-
- PATCH_CASE(mmu, read_cr2, xxl, insn_buff, len);
- PATCH_CASE(mmu, read_cr3, xxl, insn_buff, len);
- PATCH_CASE(mmu, write_cr3, xxl, insn_buff, len);
-
- PATCH_CASE(cpu, wbinvd, xxl, insn_buff, len);
-#endif
-
-#ifdef CONFIG_PARAVIRT_SPINLOCKS
- case PARAVIRT_PATCH(lock.queued_spin_unlock):
- if (pv_is_native_spin_unlock())
- return PATCH(lock, queued_spin_unlock, insn_buff, len);
- break;
-
- case PARAVIRT_PATCH(lock.vcpu_is_preempted):
- if (pv_is_native_vcpu_is_preempted())
- return PATCH(lock, vcpu_is_preempted, insn_buff, len);
- break;
-#endif
- default:
- break;
- }
-
- return paravirt_patch_default(type, insn_buff, addr, len);
-}
*/
.sp0 = (1UL << (BITS_PER_LONG-1)) + 1,
- /*
- * .sp1 is cpu_current_top_of_stack. The init task never
- * runs user code, but cpu_current_top_of_stack should still
- * be well defined before the first context switch.
- */
+#ifdef CONFIG_X86_32
.sp1 = TOP_OF_INIT_STACK,
-#ifdef CONFIG_X86_32
.ss0 = __KERNEL_DS,
.ss1 = __KERNEL_CS,
#endif
* First HT sibling to come up on the core. Link shared state of
* the first HT sibling to itself. The siblings on the same core
* which come up later will see the shared state pointer and link
- * themself to the state of this CPU.
+ * themselves to the state of this CPU.
*/
st->shared_state = st;
}
/*
* Assumption here is that last_value, a global accumulator, always goes
* forward. If we are less than that, we should not be much smaller.
- * We assume there is an error marging we're inside, and then the correction
+ * We assume there is an error margin we're inside, and then the correction
* does not sacrifice accuracy.
*
* For reads: global may have changed between test and return,
* - Write protect disabled
* - No task switch
* - Don't do FP software emulation.
- * - Proctected mode enabled
+ * - Protected mode enabled
*/
movl %cr0, %eax
andl $~(X86_CR0_PG | X86_CR0_AM | X86_CR0_WP | X86_CR0_TS | X86_CR0_EM), %eax
* - Write protect disabled
* - No task switch
* - Don't do FP software emulation.
- * - Proctected mode enabled
+ * - Protected mode enabled
*/
movq %cr0, %rax
andq $~(X86_CR0_AM | X86_CR0_WP | X86_CR0_TS | X86_CR0_EM), %rax
/*
* Range of the BSS area. The size of the BSS area is determined
- * at link time, with RESERVE_BRK*() facility reserving additional
+ * at link time, with RESERVE_BRK() facility reserving additional
* chunks.
*/
unsigned long _brk_start = (unsigned long)__brk_base;
printk(KERN_DEBUG "reserving inaccessible SNB gfx pages\n");
/*
- * Reserve all memory below the 1 MB mark that has not
- * already been reserved.
+ * SandyBridge integrated graphics devices have a bug that prevents
+ * them from accessing certain memory ranges, namely anything below
+ * 1M and in the pages listed in bad_pages[] above.
+ *
+ * To avoid these pages being ever accessed by SNB gfx devices
+ * reserve all memory below the 1 MB mark and bad_pages that have
+ * not already been reserved at boot time.
*/
memblock_reserve(0, 1<<20);
-
+
for (i = 0; i < ARRAY_SIZE(bad_pages); i++) {
if (memblock_reserve(bad_pages[i], PAGE_SIZE))
printk(KERN_WARNING "failed to reserve 0x%08lx\n",
}
}
-/*
- * Here we put platform-specific memory range workarounds, i.e.
- * memory known to be corrupt or otherwise in need to be reserved on
- * specific platforms.
- *
- * If this gets used more widely it could use a real dispatch mechanism.
- */
-static void __init trim_platform_memory_ranges(void)
-{
- trim_snb_memory();
-}
-
static void __init trim_bios_range(void)
{
/*
early_param("reservelow", parse_reservelow);
-static void __init trim_low_memory_range(void)
+static void __init early_reserve_memory(void)
{
+ /*
+ * Reserve the memory occupied by the kernel between _text and
+ * __end_of_kernel_reserve symbols. Any kernel sections after the
+ * __end_of_kernel_reserve symbol must be explicitly reserved with a
+ * separate memblock_reserve() or they will be discarded.
+ */
+ memblock_reserve(__pa_symbol(_text),
+ (unsigned long)__end_of_kernel_reserve - (unsigned long)_text);
+
+ /*
+ * The first 4Kb of memory is a BIOS owned area, but generally it is
+ * not listed as such in the E820 table.
+ *
+ * Reserve the first memory page and typically some additional
+ * memory (64KiB by default) since some BIOSes are known to corrupt
+ * low memory. See the Kconfig help text for X86_RESERVE_LOW.
+ *
+ * In addition, make sure page 0 is always reserved because on
+ * systems with L1TF its contents can be leaked to user processes.
+ */
memblock_reserve(0, ALIGN(reserve_low, PAGE_SIZE));
+
+ early_reserve_initrd();
+
+ if (efi_enabled(EFI_BOOT))
+ efi_memblock_x86_reserve_range();
+
+ memblock_x86_reserve_range_setup_data();
+
+ reserve_ibft_region();
+ reserve_bios_regions();
}
-
+
/*
* Dump out kernel offset information on panic.
*/
void __init setup_arch(char **cmdline_p)
{
- /*
- * Reserve the memory occupied by the kernel between _text and
- * __end_of_kernel_reserve symbols. Any kernel sections after the
- * __end_of_kernel_reserve symbol must be explicitly reserved with a
- * separate memblock_reserve() or they will be discarded.
- */
- memblock_reserve(__pa_symbol(_text),
- (unsigned long)__end_of_kernel_reserve - (unsigned long)_text);
-
- /*
- * Make sure page 0 is always reserved because on systems with
- * L1TF its contents can be leaked to user processes.
- */
- memblock_reserve(0, PAGE_SIZE);
-
- early_reserve_initrd();
-
- /*
- * At this point everything still needed from the boot loader
- * or BIOS or kernel text should be early reserved or marked not
- * RAM in e820. All other memory is free game.
- */
-
#ifdef CONFIG_X86_32
memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data));
parse_early_param();
- if (efi_enabled(EFI_BOOT))
- efi_memblock_x86_reserve_range();
+ /*
+ * Do some memory reservations *before* memory is added to
+ * memblock, so memblock allocations won't overwrite it.
+ * Do it after early param, so we could get (unlikely) panic from
+ * serial.
+ *
+ * After this point everything still needed from the boot loader or
+ * firmware or kernel text should be early reserved or marked not
+ * RAM in e820. All other memory is free game.
+ */
+ early_reserve_memory();
+
#ifdef CONFIG_MEMORY_HOTPLUG
/*
* Memory used by the kernel cannot be hot-removed because Linux
x86_report_nx();
- /* after early param, so could get panic from serial */
- memblock_x86_reserve_range_setup_data();
-
if (acpi_mps_check()) {
#ifdef CONFIG_X86_LOCAL_APIC
disable_apic = 1;
*/
find_smp_config();
- reserve_ibft_region();
-
early_alloc_pgt_buf();
/*
* Need to conclude brk, before e820__memblock_setup()
- * it could use memblock_find_in_range, could overlap with
- * brk area.
+ * it could use memblock_find_in_range, could overlap with
+ * brk area.
*/
reserve_brk();
*/
sev_setup_arch();
- reserve_bios_regions();
-
efi_fake_memmap();
efi_find_mirror();
efi_esrt_init();
reserve_real_mode();
- trim_platform_memory_ranges();
- trim_low_memory_range();
+ /*
+ * Reserving memory causing GPU hangs on Sandy Bridge integrated
+ * graphics devices should be done after we allocated memory under
+ * 1M for the real mode trampoline.
+ */
+ trim_snb_memory();
init_mem_mapping();
reserve_initrd();
acpi_table_upgrade();
+ /* Look for ACPI tables and reserve memory occupied by them. */
+ acpi_boot_table_init();
vsmp_init();
early_platform_quirks();
- /*
- * Parse the ACPI tables for possible boot-time SMP configuration.
- */
- acpi_boot_table_init();
-
early_acpi_boot_init();
initmem_init();
return true;
}
-static void sev_es_terminate(unsigned int reason)
+static void __noreturn sev_es_terminate(unsigned int reason)
{
u64 val = GHCB_SEV_TERMINATE;
* make it accessible to the hypervisor.
*
* In particular, check for:
- * - Hypervisor CPUID bit
* - Availability of CPUID leaf 0x8000001f
* - SEV CPUID bit.
*
* can't be checked here.
*/
- if ((fn == 1 && !(regs->cx & BIT(31))))
- /* Hypervisor bit */
- goto fail;
- else if (fn == 0x80000000 && (regs->ax < 0x8000001f))
+ if (fn == 0x80000000 && (regs->ax < 0x8000001f))
/* SEV leaf check */
goto fail;
else if ((fn == 0x8000001f && !(regs->ax & BIT(1))))
return;
fail:
- sev_es_wr_ghcb_msr(GHCB_SEV_TERMINATE);
- VMGEXIT();
-
- /* Shouldn't get here - if we do halt the machine */
- while (true)
- asm volatile("hlt\n");
+ /* Terminate the guest */
+ sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST);
}
static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt,
cea_set_pte((void *)vaddr, pa, PAGE_KERNEL);
}
-static __always_inline bool on_vc_stack(unsigned long sp)
+static __always_inline bool on_vc_stack(struct pt_regs *regs)
{
+ unsigned long sp = regs->sp;
+
+ /* User-mode RSP is not trusted */
+ if (user_mode(regs))
+ return false;
+
+ /* SYSCALL gap still has user-mode RSP */
+ if (ip_within_syscall_gap(regs))
+ return false;
+
return ((sp >= __this_cpu_ist_bottom_va(VC)) && (sp < __this_cpu_ist_top_va(VC)));
}
/*
- * This function handles the case when an NMI is raised in the #VC exception
- * handler entry code. In this case, the IST entry for #VC must be adjusted, so
- * that any subsequent #VC exception will not overwrite the stack contents of the
- * interrupted #VC handler.
+ * This function handles the case when an NMI is raised in the #VC
+ * exception handler entry code, before the #VC handler has switched off
+ * its IST stack. In this case, the IST entry for #VC must be adjusted,
+ * so that any nested #VC exception will not overwrite the stack
+ * contents of the interrupted #VC handler.
*
* The IST entry is adjusted unconditionally so that it can be also be
- * unconditionally adjusted back in sev_es_ist_exit(). Otherwise a nested
- * sev_es_ist_exit() call may adjust back the IST entry too early.
+ * unconditionally adjusted back in __sev_es_ist_exit(). Otherwise a
+ * nested sev_es_ist_exit() call may adjust back the IST entry too
+ * early.
+ *
+ * The __sev_es_ist_enter() and __sev_es_ist_exit() functions always run
+ * on the NMI IST stack, as they are only called from NMI handling code
+ * right now.
*/
void noinstr __sev_es_ist_enter(struct pt_regs *regs)
{
unsigned long old_ist, new_ist;
/* Read old IST entry */
- old_ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]);
+ new_ist = old_ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]);
- /* Make room on the IST stack */
- if (on_vc_stack(regs->sp))
- new_ist = ALIGN_DOWN(regs->sp, 8) - sizeof(old_ist);
- else
- new_ist = old_ist - sizeof(old_ist);
+ /*
+ * If NMI happened while on the #VC IST stack, set the new IST
+ * value below regs->sp, so that the interrupted stack frame is
+ * not overwritten by subsequent #VC exceptions.
+ */
+ if (on_vc_stack(regs))
+ new_ist = regs->sp;
- /* Store old IST entry */
+ /*
+ * Reserve additional 8 bytes and store old IST value so this
+ * adjustment can be unrolled in __sev_es_ist_exit().
+ */
+ new_ist -= sizeof(old_ist);
*(unsigned long *)new_ist = old_ist;
/* Set new IST entry */
int res;
if (user_mode(ctxt->regs)) {
- res = insn_fetch_from_user(ctxt->regs, buffer);
+ res = insn_fetch_from_user_inatomic(ctxt->regs, buffer);
if (!res) {
ctxt->fi.vector = X86_TRAP_PF;
ctxt->fi.error_code = X86_PF_INSTR | X86_PF_USER;
return ES_EXCEPTION;
}
- insn_init(&ctxt->insn, buffer, MAX_INSN_SIZE - res, 1);
+ insn_init(&ctxt->insn, buffer, MAX_INSN_SIZE, 1);
insn_get_length(&ctxt->insn);
}
DEFINE_IDTENTRY_VC_SAFE_STACK(exc_vmm_communication)
{
struct sev_es_runtime_data *data = this_cpu_read(runtime_data);
+ irqentry_state_t irq_state;
struct ghcb_state state;
struct es_em_ctxt ctxt;
enum es_result result;
struct ghcb *ghcb;
- lockdep_assert_irqs_disabled();
-
/*
* Handle #DB before calling into !noinstr code to avoid recursive #DB.
*/
return;
}
+ irq_state = irqentry_nmi_enter(regs);
+ lockdep_assert_irqs_disabled();
instrumentation_begin();
/*
out:
instrumentation_end();
+ irqentry_nmi_exit(regs, irq_state);
return;
* SS descriptor, but we do need SS to be valid. It's possible
* that the old SS is entirely bogus -- this can happen if the
* signal we're trying to deliver is #GP or #SS caused by a bad
- * SS value. We also have a compatbility issue here: DOSEMU
+ * SS value. We also have a compatibility issue here: DOSEMU
* relies on the contents of the SS register indicating the
* SS value at the time of the signal, even though that code in
* DOSEMU predates sigreturn's ability to restore SS. (DOSEMU
static inline unsigned long get_nr_restart_syscall(const struct pt_regs *regs)
{
- /*
- * This function is fundamentally broken as currently
- * implemented.
- *
- * The idea is that we want to trigger a call to the
- * restart_block() syscall and that we want in_ia32_syscall(),
- * in_x32_syscall(), etc. to match whatever they were in the
- * syscall being restarted. We assume that the syscall
- * instruction at (regs->ip - 2) matches whatever syscall
- * instruction we used to enter in the first place.
- *
- * The problem is that we can get here when ptrace pokes
- * syscall-like values into regs even if we're not in a syscall
- * at all.
- *
- * For now, we maintain historical behavior and guess based on
- * stored state. We could do better by saving the actual
- * syscall arch in restart_block or (with caveats on x32) by
- * checking if regs->ip points to 'int $0x80'. The current
- * behavior is incorrect if a tracer has a different bitness
- * than the tracee.
- */
#ifdef CONFIG_IA32_EMULATION
- if (current_thread_info()->status & (TS_COMPAT|TS_I386_REGS_POKED))
+ if (current->restart_block.arch_data & TS_COMPAT)
return __NR_ia32_restart_syscall;
#endif
#ifdef CONFIG_X86_X32_ABI
* 5AP. symmetric IO mode (normal Linux operation) not affected.
* 'noapic' mode has vector 0xf filled out properly.
* 6AP. 'noapic' mode might be affected - fixed in later steppings
- * 7AP. We do not assume writes to the LVT deassering IRQs
+ * 7AP. We do not assume writes to the LVT deasserting IRQs
* 8AP. We do not enable low power mode (deep sleep) during MP bootup
* 9AP. We do not use mixed mode
*
}
/*
* Don't wait longer than 10 ms if the caller didn't
- * reqeust it. If wait is true, the machine hangs here if
+ * request it. If wait is true, the machine hangs here if
* one or more CPUs do not reach shutdown state.
*/
timeout = USEC_PER_MSEC * 10;
int ncpus;
/*
- * Today neither Intel nor AMD support heterogenous systems so
+ * Today neither Intel nor AMD support heterogeneous systems so
* extrapolate the boot cpu's data to all packages.
*/
ncpus = cpu_data(0).booted_cores * topology_max_smt_threads();
local_irq_disable();
}
-static bool wakeup_cpu0(void)
+/**
+ * cond_wakeup_cpu0 - Wake up CPU0 if needed.
+ *
+ * If NMI wants to wake up CPU0, start CPU0.
+ */
+void cond_wakeup_cpu0(void)
{
if (smp_processor_id() == 0 && enable_start_cpu0)
- return true;
-
- return false;
+ start_cpu0();
}
+EXPORT_SYMBOL_GPL(cond_wakeup_cpu0);
/*
* We need to flush the caches before going to sleep, lest we have
__monitor(mwait_ptr, 0, 0);
mb();
__mwait(eax, 0);
- /*
- * If NMI wants to wake up CPU0, start CPU0.
- */
- if (wakeup_cpu0())
- start_cpu0();
+
+ cond_wakeup_cpu0();
}
}
while (1) {
native_halt();
- /*
- * If NMI wants to wake up CPU0, start CPU0.
- */
- if (wakeup_cpu0())
- start_cpu0();
+
+ cond_wakeup_cpu0();
}
}
}
}
-/*
- * This function returns an error if it detects any unreliable features of the
- * stack. Otherwise it guarantees that the stack trace is reliable.
- *
- * If the task is not 'current', the caller *must* ensure the task is inactive.
- */
int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry,
void *cookie, struct task_struct *task)
{
* EFI Quirks
* Several EFI systems do not correctly advertise their boot framebuffers.
* Hence, we use this static table of known broken machines and fix up the
- * information so framebuffer drivers can load corectly.
+ * information so framebuffer drivers can load correctly.
*/
#include <linux/dmi.h>
return tboot != NULL;
}
+/* noinline to prevent gcc from warning about dereferencing constant fixaddr */
+static noinline __init bool check_tboot_version(void)
+{
+ if (memcmp(&tboot_uuid, &tboot->uuid, sizeof(tboot->uuid))) {
+ pr_warn("tboot at 0x%llx is invalid\n", boot_params.tboot_addr);
+ return false;
+ }
+
+ if (tboot->version < 5) {
+ pr_warn("tboot version is invalid: %u\n", tboot->version);
+ return false;
+ }
+
+ pr_info("found shared page at phys addr 0x%llx:\n",
+ boot_params.tboot_addr);
+ pr_debug("version: %d\n", tboot->version);
+ pr_debug("log_addr: 0x%08x\n", tboot->log_addr);
+ pr_debug("shutdown_entry: 0x%x\n", tboot->shutdown_entry);
+ pr_debug("tboot_base: 0x%08x\n", tboot->tboot_base);
+ pr_debug("tboot_size: 0x%x\n", tboot->tboot_size);
+
+ return true;
+}
+
void __init tboot_probe(void)
{
/* Look for valid page-aligned address for shared page. */
/* Map and check for tboot UUID. */
set_fixmap(FIX_TBOOT_BASE, boot_params.tboot_addr);
- tboot = (struct tboot *)fix_to_virt(FIX_TBOOT_BASE);
- if (memcmp(&tboot_uuid, &tboot->uuid, sizeof(tboot->uuid))) {
- pr_warn("tboot at 0x%llx is invalid\n", boot_params.tboot_addr);
+ tboot = (void *)fix_to_virt(FIX_TBOOT_BASE);
+ if (!check_tboot_version())
tboot = NULL;
- return;
- }
- if (tboot->version < 5) {
- pr_warn("tboot version is invalid: %u\n", tboot->version);
- tboot = NULL;
- return;
- }
-
- pr_info("found shared page at phys addr 0x%llx:\n",
- boot_params.tboot_addr);
- pr_debug("version: %d\n", tboot->version);
- pr_debug("log_addr: 0x%08x\n", tboot->log_addr);
- pr_debug("shutdown_entry: 0x%x\n", tboot->shutdown_entry);
- pr_debug("tboot_base: 0x%08x\n", tboot->tboot_base);
- pr_debug("tboot_size: 0x%x\n", tboot->tboot_size);
}
static pgd_t *tboot_pg_dir;
* Two known BSP/CPU0 dependencies: Resume from suspend/hibernate
* depends on BSP. PIC interrupts depend on BSP.
*
- * If the BSP depencies are under control, one can tell kernel to
+ * If the BSP dependencies are under control, one can tell kernel to
* enable BSP hotplug. This basically adds a control file and
* one can attempt to offline BSP.
*/
/*
* Adjust our frame so that we return straight to the #GP
* vector with the expected RSP value. This is safe because
- * we won't enable interupts or schedule before we invoke
+ * we won't enable interrupts or schedule before we invoke
* general_protection, so nothing will clobber the stack
* frame we just set up.
*
tsk->thread.trap_nr = X86_TRAP_GP;
if (fixup_vdso_exception(regs, X86_TRAP_GP, error_code, 0))
- return;
+ goto exit;
show_signal(tsk, SIGSEGV, "", desc, regs, error_code);
force_sig(SIGSEGV);
* In the SYSCALL entry path the RSP value comes from user-space - don't
* trust it and switch to the current kernel stack
*/
- if (regs->ip >= (unsigned long)entry_SYSCALL_64 &&
- regs->ip < (unsigned long)entry_SYSCALL_64_safe_stack) {
+ if (ip_within_syscall_gap(regs)) {
sp = this_cpu_read(cpu_current_top_of_stack);
goto sync;
}
goto out_irq;
}
+ /* #DB for bus lock can only be triggered from userspace. */
+ if (dr6 & DR_BUS_LOCK)
+ handle_bus_lock(regs);
+
/* Add the virtual_dr6 bits for signals. */
dr6 |= current->thread.virtual_dr6;
if (dr6 & (DR_STEP | DR_TRAP_BITS) || icebp)
goto exit;
if (fixup_vdso_exception(regs, trapnr, 0, 0))
- return;
+ goto exit;
force_sig_fault(SIGFPE, si_code,
(void __user *)uprobe_get_trap_addr(regs));
#include <linux/percpu.h>
#include <linux/timex.h>
#include <linux/static_key.h>
+#include <linux/static_call.h>
#include <asm/hpet.h>
#include <asm/timer.h>
bool using_native_sched_clock(void)
{
- return pv_ops.time.sched_clock == native_sched_clock;
+ return static_call_query(pv_sched_clock) == native_sched_clock;
}
#else
unsigned long long
* 2) Reference counter. If available we use the HPET or the
* PMTIMER as a reference to check the sanity of that value.
* We use separate TSC readouts and check inside of the
- * reference read for any possible disturbance. We dicard
+ * reference read for any possible disturbance. We discard
* disturbed values here as well. We do that around the PIT
* calibration delay loop as we have to wait for a certain
* amount of time anyway.
* very small window right after one CPU updated cycle_last under
* xtime/vsyscall_gtod lock and the other CPU reads a TSC value which
* is smaller than the cycle_last reference value due to a TSC which
- * is slighty behind. This delta is nowhere else observable, but in
+ * is slightly behind. This delta is nowhere else observable, but in
* that case it results in a forward time jump in the range of hours
* due to the unsigned delta calculation of the time keeping core
* code, which is necessary to support wrapping clocksources like pm
* corresponding clocksource
* @cycles: System counter value
* @cs: Clocksource corresponding to system counter value. Used
- * by timekeeping code to verify comparibility of two cycle
+ * by timekeeping code to verify comparability of two cycle
* values.
*/
/*
* Add the result to the previous adjustment value.
*
- * The adjustement value is slightly off by the overhead of the
+ * The adjustment value is slightly off by the overhead of the
* sync mechanism (observed values are ~200 TSC cycles), but this
* really depends on CPU, node distance and frequency. So
* compensating for this is hard to get right. Experiments show
* by whether the operand is a register or a memory location.
* If operand is a register, return as many bytes as the operand
* size. If operand is memory, return only the two least
- * siginificant bytes.
+ * significant bytes.
*/
if (X86_MODRM_MOD(insn->modrm.value) == 3)
*data_size = insn->opnd_bytes;
#define orc_warn_current(args...) \
({ \
- if (state->task == current) \
+ if (state->task == current && !state->error) \
orc_warn(args); \
})
if (!stack_access_ok(state, addr, sizeof(struct pt_regs)))
return false;
- *ip = regs->ip;
- *sp = regs->sp;
+ *ip = READ_ONCE_NOCHECK(regs->ip);
+ *sp = READ_ONCE_NOCHECK(regs->sp);
return true;
}
if (!stack_access_ok(state, addr, IRET_FRAME_SIZE))
return false;
- *ip = regs->ip;
- *sp = regs->sp;
+ *ip = READ_ONCE_NOCHECK(regs->ip);
+ *sp = READ_ONCE_NOCHECK(regs->sp);
return true;
}
return false;
if (state->full_regs) {
- *val = ((unsigned long *)state->regs)[reg];
+ *val = READ_ONCE_NOCHECK(((unsigned long *)state->regs)[reg]);
return true;
}
if (state->prev_regs) {
- *val = ((unsigned long *)state->prev_regs)[reg];
+ *val = READ_ONCE_NOCHECK(((unsigned long *)state->prev_regs)[reg]);
return true;
}
To compile this as a module, choose M here: the module
will be called kvm-intel.
+config X86_SGX_KVM
+ bool "Software Guard eXtensions (SGX) Virtualization"
+ depends on X86_SGX && KVM_INTEL
+ help
+
+ Enables KVM guests to create SGX enclaves.
+
+ This includes support to expose "raw" unreclaimable enclave memory to
+ guests via a device node, e.g. /dev/sgx_vepc.
+
+ If unsure, say N.
+
config KVM_AMD
tristate "KVM for AMD processors support"
depends on KVM
# SPDX-License-Identifier: GPL-2.0
-ccflags-y += -Iarch/x86/kvm
+ccflags-y += -I $(srctree)/arch/x86/kvm
ccflags-$(CONFIG_KVM_WERROR) += -Werror
ifeq ($(CONFIG_FRAME_POINTER),y)
* - Centaur: 0xc0000000 - 0xcfffffff
*
* The Hypervisor class is further subdivided into sub-classes that each act as
- * their own indepdent class associated with a 0x100 byte range. E.g. if Qemu
+ * their own independent class associated with a 0x100 byte range. E.g. if Qemu
* is advertising support for both HyperV and KVM, the resulting Hypervisor
* CPUID sub-classes are:
*
}
/*
- * Now load segment descriptors. If fault happenes at this stage
+ * Now load segment descriptors. If fault happens at this stage
* it is handled in a context of new task
*/
ret = __load_segment_descriptor(ctxt, tss->ldt_selector, VCPU_SREG_LDTR,
u64 tsc;
/*
- * The guest has not set up the TSC page or the clock isn't
- * stable, fall back to get_kvmclock_ns.
+ * Fall back to get_kvmclock_ns() when TSC page hasn't been set up,
+ * is broken, disabled or being updated.
*/
- if (!hv->tsc_ref.tsc_sequence)
+ if (hv->hv_tsc_page_status != HV_TSC_PAGE_SET)
return div_u64(get_kvmclock_ns(kvm), 100);
vcpu = kvm_get_vcpu(kvm, 0);
return true;
}
+/*
+ * Don't touch TSC page values if the guest has opted for TSC emulation after
+ * migration. KVM doesn't fully support reenlightenment notifications and TSC
+ * access emulation and Hyper-V is known to expect the values in TSC page to
+ * stay constant before TSC access emulation is disabled from guest side
+ * (HV_X64_MSR_TSC_EMULATION_STATUS). KVM userspace is expected to preserve TSC
+ * frequency and guest visible TSC value across migration (and prevent it when
+ * TSC scaling is unsupported).
+ */
+static inline bool tsc_page_update_unsafe(struct kvm_hv *hv)
+{
+ return (hv->hv_tsc_page_status != HV_TSC_PAGE_GUEST_CHANGED) &&
+ hv->hv_tsc_emulation_control;
+}
+
void kvm_hv_setup_tsc_page(struct kvm *kvm,
struct pvclock_vcpu_time_info *hv_clock)
{
BUILD_BUG_ON(sizeof(tsc_seq) != sizeof(hv->tsc_ref.tsc_sequence));
BUILD_BUG_ON(offsetof(struct ms_hyperv_tsc_page, tsc_sequence) != 0);
- if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE))
+ if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN ||
+ hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET)
return;
mutex_lock(&hv->hv_lock);
*/
if (unlikely(kvm_read_guest(kvm, gfn_to_gpa(gfn),
&tsc_seq, sizeof(tsc_seq))))
+ goto out_err;
+
+ if (tsc_seq && tsc_page_update_unsafe(hv)) {
+ if (kvm_read_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref)))
+ goto out_err;
+
+ hv->hv_tsc_page_status = HV_TSC_PAGE_SET;
goto out_unlock;
+ }
/*
* While we're computing and writing the parameters, force the
hv->tsc_ref.tsc_sequence = 0;
if (kvm_write_guest(kvm, gfn_to_gpa(gfn),
&hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence)))
- goto out_unlock;
+ goto out_err;
if (!compute_tsc_page_parameters(hv_clock, &hv->tsc_ref))
- goto out_unlock;
+ goto out_err;
/* Ensure sequence is zero before writing the rest of the struct. */
smp_wmb();
if (kvm_write_guest(kvm, gfn_to_gpa(gfn), &hv->tsc_ref, sizeof(hv->tsc_ref)))
- goto out_unlock;
+ goto out_err;
/*
* Now switch to the TSC page mechanism by writing the sequence.
smp_wmb();
hv->tsc_ref.tsc_sequence = tsc_seq;
- kvm_write_guest(kvm, gfn_to_gpa(gfn),
- &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence));
+ if (kvm_write_guest(kvm, gfn_to_gpa(gfn),
+ &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence)))
+ goto out_err;
+
+ hv->hv_tsc_page_status = HV_TSC_PAGE_SET;
+ goto out_unlock;
+
+out_err:
+ hv->hv_tsc_page_status = HV_TSC_PAGE_BROKEN;
+out_unlock:
+ mutex_unlock(&hv->hv_lock);
+}
+
+void kvm_hv_invalidate_tsc_page(struct kvm *kvm)
+{
+ struct kvm_hv *hv = to_kvm_hv(kvm);
+ u64 gfn;
+
+ if (hv->hv_tsc_page_status == HV_TSC_PAGE_BROKEN ||
+ hv->hv_tsc_page_status == HV_TSC_PAGE_UNSET ||
+ tsc_page_update_unsafe(hv))
+ return;
+
+ mutex_lock(&hv->hv_lock);
+
+ if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE))
+ goto out_unlock;
+
+ /* Preserve HV_TSC_PAGE_GUEST_CHANGED/HV_TSC_PAGE_HOST_CHANGED states */
+ if (hv->hv_tsc_page_status == HV_TSC_PAGE_SET)
+ hv->hv_tsc_page_status = HV_TSC_PAGE_UPDATING;
+
+ gfn = hv->hv_tsc_page >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
+
+ hv->tsc_ref.tsc_sequence = 0;
+ if (kvm_write_guest(kvm, gfn_to_gpa(gfn),
+ &hv->tsc_ref, sizeof(hv->tsc_ref.tsc_sequence)))
+ hv->hv_tsc_page_status = HV_TSC_PAGE_BROKEN;
+
out_unlock:
mutex_unlock(&hv->hv_lock);
}
}
case HV_X64_MSR_REFERENCE_TSC:
hv->hv_tsc_page = data;
- if (hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE)
+ if (hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE) {
+ if (!host)
+ hv->hv_tsc_page_status = HV_TSC_PAGE_GUEST_CHANGED;
+ else
+ hv->hv_tsc_page_status = HV_TSC_PAGE_HOST_CHANGED;
kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
+ } else {
+ hv->hv_tsc_page_status = HV_TSC_PAGE_UNSET;
+ }
break;
case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
return kvm_hv_msr_set_crash_data(kvm,
hv->hv_tsc_emulation_control = data;
break;
case HV_X64_MSR_TSC_EMULATION_STATUS:
+ if (data && !host)
+ return 1;
+
hv->hv_tsc_emulation_status = data;
break;
case HV_X64_MSR_TIME_REF_COUNT:
void kvm_hv_setup_tsc_page(struct kvm *kvm,
struct pvclock_vcpu_time_info *hv_clock);
+void kvm_hv_invalidate_tsc_page(struct kvm *kvm);
void kvm_hv_init_vm(struct kvm *kvm);
void kvm_hv_destroy_vm(struct kvm *kvm);
const struct kvm_irq_routing_entry *ue)
{
/* We can't check irqchip_in_kernel() here as some callers are
- * currently inititalizing the irqchip. Other callers should therefore
+ * currently initializing the irqchip. Other callers should therefore
* check kvm_arch_can_set_irq_routing() before calling this function.
*/
switch (ue->type) {
}
if (kvm_use_posted_timer_interrupt(apic->vcpu)) {
- kvm_wait_lapic_expire(vcpu);
+ /*
+ * Ensure the guest's timer has truly expired before posting an
+ * interrupt. Open code the relevant checks to avoid querying
+ * lapic_timer_int_injected(), which will be false since the
+ * interrupt isn't yet injected. Waiting until after injecting
+ * is not an option since that won't help a posted interrupt.
+ */
+ if (vcpu->arch.apic->lapic_timer.expired_tscdeadline &&
+ vcpu->arch.apic->lapic_timer.timer_advance_ns)
+ __kvm_wait_lapic_expire(vcpu);
kvm_apic_inject_pending_timer_irqs(apic);
return;
}
apic_update_ppr(apic);
hrtimer_cancel(&apic->lapic_timer.timer);
+ apic->lapic_timer.expired_tscdeadline = 0;
apic_update_lvtt(apic);
apic_manage_nmi_watchdog(apic, kvm_lapic_get_reg(apic, APIC_LVT0));
update_divide_count(apic);
/*
* No need to care whether allocation memory is successful
- * or not since pte prefetch is skiped if it does not have
+ * or not since pte prefetch is skipped if it does not have
* enough objects in the cache.
*/
mmu_topup_memory_caches(vcpu, true);
struct kvm_mmu_page *sp;
unsigned int ratio;
LIST_HEAD(invalid_list);
+ bool flush = false;
ulong to_zap;
rcu_idx = srcu_read_lock(&kvm->srcu);
lpage_disallowed_link);
WARN_ON_ONCE(!sp->lpage_disallowed);
if (is_tdp_mmu_page(sp)) {
- kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn,
- sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level));
+ flush |= kvm_tdp_mmu_zap_sp(kvm, sp);
} else {
kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
WARN_ON_ONCE(sp->lpage_disallowed);
}
if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) {
- kvm_mmu_commit_zap_page(kvm, &invalid_list);
+ kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush);
cond_resched_rwlock_write(&kvm->mmu_lock);
+ flush = false;
}
}
- kvm_mmu_commit_zap_page(kvm, &invalid_list);
+ kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush);
write_unlock(&kvm->mmu_lock);
srcu_read_unlock(&kvm->srcu, rcu_idx);
#ifdef CONFIG_X86_64
bool tdp_mmu_page;
- /* Used for freeing the page asyncronously if it is a TDP MMU page. */
+ /* Used for freeing the page asynchronously if it is a TDP MMU page. */
struct rcu_head rcu_head;
#endif
};
return to_shadow_page(__pa(sptep));
}
+static inline int kvm_mmu_page_as_id(struct kvm_mmu_page *sp)
+{
+ return sp->role.smm ? 1 : 0;
+}
+
static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu)
{
/*
}
/*
+ * Return the TDP iterator to the root PT and allow it to continue its
+ * traversal over the paging structure from there.
+ */
+void tdp_iter_restart(struct tdp_iter *iter)
+{
+ iter->yielded_gfn = iter->next_last_level_gfn;
+ iter->level = iter->root_level;
+
+ iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level);
+ tdp_iter_refresh_sptep(iter);
+
+ iter->valid = true;
+}
+
+/*
* Sets a TDP iterator to walk a pre-order traversal of the paging structure
* rooted at root_pt, starting with the walk to translate next_last_level_gfn.
*/
WARN_ON(root_level > PT64_ROOT_MAX_LEVEL);
iter->next_last_level_gfn = next_last_level_gfn;
- iter->yielded_gfn = iter->next_last_level_gfn;
iter->root_level = root_level;
iter->min_level = min_level;
- iter->level = root_level;
- iter->pt_path[iter->level - 1] = (tdp_ptep_t)root_pt;
-
- iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level);
- tdp_iter_refresh_sptep(iter);
+ iter->pt_path[iter->root_level - 1] = (tdp_ptep_t)root_pt;
+ iter->as_id = kvm_mmu_page_as_id(sptep_to_sp(root_pt));
- iter->valid = true;
+ tdp_iter_restart(iter);
}
/*
iter->valid = false;
}
-tdp_ptep_t tdp_iter_root_pt(struct tdp_iter *iter)
-{
- return iter->pt_path[iter->root_level - 1];
-}
-
int min_level;
/* The iterator's current level within the paging structure */
int level;
+ /* The address space ID, i.e. SMM vs. regular. */
+ int as_id;
/* A snapshot of the value at sptep */
u64 old_spte;
/*
void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level,
int min_level, gfn_t next_last_level_gfn);
void tdp_iter_next(struct tdp_iter *iter);
-tdp_ptep_t tdp_iter_root_pt(struct tdp_iter *iter);
+void tdp_iter_restart(struct tdp_iter *iter);
#endif /* __KVM_X86_MMU_TDP_ITER_H */
list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link)
static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
- gfn_t start, gfn_t end, bool can_yield);
+ gfn_t start, gfn_t end, bool can_yield, bool flush);
void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root)
{
list_del(&root->link);
- zap_gfn_range(kvm, root, 0, max_gfn, false);
+ zap_gfn_range(kvm, root, 0, max_gfn, false, false);
free_page((unsigned long)root->spt);
kmem_cache_free(mmu_page_header_cache, root);
u64 old_spte, u64 new_spte, int level,
bool shared);
-static int kvm_mmu_page_as_id(struct kvm_mmu_page *sp)
-{
- return sp->role.smm ? 1 : 0;
-}
-
static void handle_changed_spte_acc_track(u64 old_spte, u64 new_spte, int level)
{
bool pfn_changed = spte_to_pfn(old_spte) != spte_to_pfn(new_spte);
*
* Given a page table that has been removed from the TDP paging structure,
* iterates through the page table to clear SPTEs and free child page tables.
+ *
+ * Note that pt is passed in as a tdp_ptep_t, but it does not need RCU
+ * protection. Since this thread removed it from the paging structure,
+ * this thread will be responsible for ensuring the page is freed. Hence the
+ * early rcu_dereferences in the function.
*/
-static void handle_removed_tdp_mmu_page(struct kvm *kvm, u64 *pt,
+static void handle_removed_tdp_mmu_page(struct kvm *kvm, tdp_ptep_t pt,
bool shared)
{
- struct kvm_mmu_page *sp = sptep_to_sp(pt);
+ struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(pt));
int level = sp->role.level;
gfn_t base_gfn = sp->gfn;
u64 old_child_spte;
tdp_mmu_unlink_page(kvm, sp, shared);
for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
- sptep = pt + i;
+ sptep = rcu_dereference(pt) + i;
gfn = base_gfn + (i * KVM_PAGES_PER_HPAGE(level - 1));
if (shared) {
cpu_relax();
}
} else {
+ /*
+ * If the SPTE is not MMU-present, there is no backing
+ * page associated with the SPTE and so no side effects
+ * that need to be recorded, and exclusive ownership of
+ * mmu_lock ensures the SPTE can't be made present.
+ * Note, zapping MMIO SPTEs is also unnecessary as they
+ * are guarded by the memslots generation, not by being
+ * unreachable.
+ */
old_child_spte = READ_ONCE(*sptep);
+ if (!is_shadow_present_pte(old_child_spte))
+ continue;
/*
* Marking the SPTE as a removed SPTE is not
* If this warning were to trigger it would indicate that there was a
* missing MMU notifier or a race with some notifier handler.
* A present, leaf SPTE should never be directly replaced with another
- * present leaf SPTE pointing to a differnt PFN. A notifier handler
+ * present leaf SPTE pointing to a different PFN. A notifier handler
* should be zapping the SPTE before the main MM's page table is
* changed, or the SPTE should be zeroed, and the TLBs flushed by the
* thread before replacement.
/*
* Crash the host to prevent error propagation and guest data
- * courruption.
+ * corruption.
*/
BUG();
}
struct tdp_iter *iter,
u64 new_spte)
{
- u64 *root_pt = tdp_iter_root_pt(iter);
- struct kvm_mmu_page *root = sptep_to_sp(root_pt);
- int as_id = kvm_mmu_page_as_id(root);
-
lockdep_assert_held_read(&kvm->mmu_lock);
/*
new_spte) != iter->old_spte)
return false;
- handle_changed_spte(kvm, as_id, iter->gfn, iter->old_spte, new_spte,
- iter->level, true);
+ handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte,
+ new_spte, iter->level, true);
return true;
}
/*
* No other thread can overwrite the removed SPTE as they
* must either wait on the MMU lock or use
- * tdp_mmu_set_spte_atomic which will not overrite the
+ * tdp_mmu_set_spte_atomic which will not overwrite the
* special removed SPTE value. No bookkeeping is needed
* here since the SPTE is going from non-present
* to non-present.
*/
- WRITE_ONCE(*iter->sptep, 0);
+ WRITE_ONCE(*rcu_dereference(iter->sptep), 0);
return true;
}
u64 new_spte, bool record_acc_track,
bool record_dirty_log)
{
- tdp_ptep_t root_pt = tdp_iter_root_pt(iter);
- struct kvm_mmu_page *root = sptep_to_sp(root_pt);
- int as_id = kvm_mmu_page_as_id(root);
-
lockdep_assert_held_write(&kvm->mmu_lock);
/*
WRITE_ONCE(*rcu_dereference(iter->sptep), new_spte);
- __handle_changed_spte(kvm, as_id, iter->gfn, iter->old_spte, new_spte,
- iter->level, false);
+ __handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte,
+ new_spte, iter->level, false);
if (record_acc_track)
handle_changed_spte_acc_track(iter->old_spte, new_spte,
iter->level);
if (record_dirty_log)
- handle_changed_spte_dirty_log(kvm, as_id, iter->gfn,
+ handle_changed_spte_dirty_log(kvm, iter->as_id, iter->gfn,
iter->old_spte, new_spte,
iter->level);
}
WARN_ON(iter->gfn > iter->next_last_level_gfn);
- tdp_iter_start(iter, iter->pt_path[iter->root_level - 1],
- iter->root_level, iter->min_level,
- iter->next_last_level_gfn);
+ tdp_iter_restart(iter);
return true;
}
* scheduler needs the CPU or there is contention on the MMU lock. If this
* function cannot yield, it will not release the MMU lock or reschedule and
* the caller must ensure it does not supply too large a GFN range, or the
- * operation can cause a soft lockup.
+ * operation can cause a soft lockup. Note, in some use cases a flush may be
+ * required by prior actions. Ensure the pending flush is performed prior to
+ * yielding.
*/
static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
- gfn_t start, gfn_t end, bool can_yield)
+ gfn_t start, gfn_t end, bool can_yield, bool flush)
{
struct tdp_iter iter;
- bool flush_needed = false;
rcu_read_lock();
tdp_root_for_each_pte(iter, root, start, end) {
if (can_yield &&
- tdp_mmu_iter_cond_resched(kvm, &iter, flush_needed)) {
- flush_needed = false;
+ tdp_mmu_iter_cond_resched(kvm, &iter, flush)) {
+ flush = false;
continue;
}
continue;
tdp_mmu_set_spte(kvm, &iter, 0);
- flush_needed = true;
+ flush = true;
}
rcu_read_unlock();
- return flush_needed;
+ return flush;
}
/*
* SPTEs have been cleared and a TLB flush is needed before releasing the
* MMU lock.
*/
-bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end)
+bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end,
+ bool can_yield)
{
struct kvm_mmu_page *root;
bool flush = false;
for_each_tdp_mmu_root_yield_safe(kvm, root)
- flush |= zap_gfn_range(kvm, root, start, end, true);
+ flush = zap_gfn_range(kvm, root, start, end, can_yield, flush);
return flush;
}
struct kvm_mmu_page *root, gfn_t start,
gfn_t end, unsigned long unused)
{
- return zap_gfn_range(kvm, root, start, end, false);
+ return zap_gfn_range(kvm, root, start, end, false, false);
}
int kvm_tdp_mmu_zap_hva_range(struct kvm *kvm, unsigned long start,
hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu);
void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root);
-bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end);
+bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end,
+ bool can_yield);
+static inline bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start,
+ gfn_t end)
+{
+ return __kvm_tdp_mmu_zap_gfn_range(kvm, start, end, true);
+}
+static inline bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+ gfn_t end = sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level);
+
+ /*
+ * Don't allow yielding, as the caller may have a flush pending. Note,
+ * if mmu_lock is held for write, zapping will never yield in this case,
+ * but explicitly disallow it for safety. The TDP MMU does not yield
+ * until it has made forward progress (steps sideways), and when zapping
+ * a single shadow page that it's guaranteed to see (thus the mmu_lock
+ * requirement), its "step sideways" will always step beyond the bounds
+ * of the shadow page's gfn range and stop iterating before yielding.
+ */
+ lockdep_assert_held_write(&kvm->mmu_lock);
+ return __kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn, end, false);
+}
void kvm_tdp_mmu_zap_all(struct kvm *kvm);
int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
/* returns general purpose PMC with the specified MSR. Note that it can be
* used for both PERFCTRn and EVNTSELn; that is why it accepts base as a
- * paramenter to tell them apart.
+ * parameter to tell them apart.
*/
static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr,
u32 base)
struct amd_svm_iommu_ir *ir;
/**
- * In some cases, the existing irte is updaed and re-set,
+ * In some cases, the existing irte is updated and re-set,
* so we need to check here if it's already been * added
* to the ir_list.
*/
* Here, we setup with legacy mode in the following cases:
* 1. When cannot target interrupt to a specific vcpu.
* 2. Unsetting posted interrupt.
- * 3. APIC virtialization is disabled for the vcpu.
+ * 3. APIC virtualization is disabled for the vcpu.
* 4. IRQ has incompatible delivery mode (SMI, INIT, etc)
*/
if (!get_pi_vcpu_info(kvm, e, &vcpu_info, &svm) && set &&
return true;
}
-static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12)
+static bool nested_vmcb_check_save(struct vcpu_svm *svm, struct vmcb *vmcb12)
{
struct kvm_vcpu *vcpu = &svm->vcpu;
bool vmcb12_lma;
+ /*
+ * FIXME: these should be done after copying the fields,
+ * to avoid TOC/TOU races. For these save area checks
+ * the possible damage is limited since kvm_set_cr0 and
+ * kvm_set_cr4 handle failure; EFER_SVME is an exception
+ * so it is force-set later in nested_prepare_vmcb_save.
+ */
if ((vmcb12->save.efer & EFER_SVME) == 0)
return false;
if (!kvm_is_valid_cr4(&svm->vcpu, vmcb12->save.cr4))
return false;
- return nested_vmcb_check_controls(&vmcb12->control);
+ return true;
}
static void load_nested_vmcb_control(struct vcpu_svm *svm,
svm->vmcb->save.gdtr = vmcb12->save.gdtr;
svm->vmcb->save.idtr = vmcb12->save.idtr;
kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags | X86_EFLAGS_FIXED);
- svm_set_efer(&svm->vcpu, vmcb12->save.efer);
+
+ /*
+ * Force-set EFER_SVME even though it is checked earlier on the
+ * VMCB12, because the guest can flip the bit between the check
+ * and now. Clearing EFER_SVME would call svm_free_nested.
+ */
+ svm_set_efer(&svm->vcpu, vmcb12->save.efer | EFER_SVME);
+
svm_set_cr0(&svm->vcpu, vmcb12->save.cr0);
svm_set_cr4(&svm->vcpu, vmcb12->save.cr4);
svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = vmcb12->save.cr2;
svm->nested.vmcb12_gpa = vmcb12_gpa;
- load_nested_vmcb_control(svm, &vmcb12->control);
nested_prepare_vmcb_control(svm);
nested_prepare_vmcb_save(svm, vmcb12);
if (WARN_ON_ONCE(!svm->nested.initialized))
return -EINVAL;
- if (!nested_vmcb_checks(svm, vmcb12)) {
+ load_nested_vmcb_control(svm, &vmcb12->control);
+
+ if (!nested_vmcb_check_save(svm, vmcb12) ||
+ !nested_vmcb_check_controls(&svm->nested.ctl)) {
vmcb12->control.exit_code = SVM_EXIT_ERR;
vmcb12->control.exit_code_hi = 0;
vmcb12->control.exit_info_1 = 0;
*/
if (!(save->cr0 & X86_CR0_PG))
goto out_free;
+ if (!(save->efer & EFER_SVME))
+ goto out_free;
/*
* All checks done, we can enter guest mode. L1 control fields
static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr,
enum pmu_type type)
{
+ struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
+
switch (msr) {
case MSR_F15H_PERF_CTL0:
case MSR_F15H_PERF_CTL1:
case MSR_F15H_PERF_CTL3:
case MSR_F15H_PERF_CTL4:
case MSR_F15H_PERF_CTL5:
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE))
+ return NULL;
+ fallthrough;
case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3:
if (type != PMU_TYPE_EVNTSEL)
return NULL;
case MSR_F15H_PERF_CTR3:
case MSR_F15H_PERF_CTR4:
case MSR_F15H_PERF_CTR5:
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE))
+ return NULL;
+ fallthrough;
case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3:
if (type != PMU_TYPE_COUNTER)
return NULL;
hostsa = (struct vmcb_save_area *)(page_address(sd->save_area) + 0x400);
hostsa->xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
- /* PKRU is restored on VMEXIT, save the curent host value */
+ /* PKRU is restored on VMEXIT, save the current host value */
hostsa->pkru = read_pkru();
/* MSR_IA32_XSS is restored on VMEXIT, save the currnet host value */
{ .index = MSR_INVALID, .always = false },
};
-/* enable NPT for AMD64 and X86 with PAE */
-#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
-bool npt_enabled = true;
-#else
-bool npt_enabled;
-#endif
-
/*
* These 2 parameters are used to config the controls for Pause-Loop Exiting:
* pause_filter_count: On processors that support Pause filtering(indicated
static unsigned short pause_filter_count_max = KVM_SVM_DEFAULT_PLE_WINDOW_MAX;
module_param(pause_filter_count_max, ushort, 0444);
-/* allow nested paging (virtualized MMU) for all guests */
-static int npt = true;
-module_param(npt, int, S_IRUGO);
+/*
+ * Use nested page tables by default. Note, NPT may get forced off by
+ * svm_hardware_setup() if it's unsupported by hardware or the host kernel.
+ */
+bool npt_enabled = true;
+module_param_named(npt, npt_enabled, bool, 0444);
/* allow nested virtualization in KVM/SVM */
static int nested = true;
goto err;
}
- if (!boot_cpu_has(X86_FEATURE_NPT))
+ /*
+ * KVM's MMU doesn't support using 2-level paging for itself, and thus
+ * NPT isn't supported if the host is using 2-level paging since host
+ * CR4 is unchanged on VMRUN.
+ */
+ if (!IS_ENABLED(CONFIG_X86_64) && !IS_ENABLED(CONFIG_X86_PAE))
npt_enabled = false;
- if (npt_enabled && !npt)
+ if (!boot_cpu_has(X86_FEATURE_NPT))
npt_enabled = false;
kvm_configure_mmu(npt_enabled, get_max_npt_level(), PG_LEVEL_1G);
*
* This happens because CPU microcode reading instruction bytes
* uses a special opcode which attempts to read data using CPL=0
- * priviledges. The microcode reads CS:RIP and if it hits a SMAP
+ * privileges. The microcode reads CS:RIP and if it hits a SMAP
* fault, it gives up and returns no instruction bytes.
*
* Detection:
* snapshot restore (migration).
*
* In this flow, it is assumed that vmcs12 cache was
- * trasferred as part of captured nVMX state and should
+ * transferred as part of captured nVMX state and should
* therefore not be read from guest memory (which may not
* exist on destination host yet).
*/
#include "vmx.h"
/*
- * We maintian a per-CPU linked-list of vCPU, so in wakeup_handler() we
+ * We maintain a per-CPU linked-list of vCPU, so in wakeup_handler() we
* can find which vCPU should be waken up.
*/
static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu);
/*
* MTCFreq, CycThresh and PSBFreq encodings check, any MSR write that
- * utilize encodings marked reserved will casue a #GP fault.
+ * utilize encodings marked reserved will cause a #GP fault.
*/
value = intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc_periods);
if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc) &&
struct vcpu_vmx *vmx = to_vmx(vcpu);
/*
- * Update real mode segment cache. It may be not up-to-date if sement
+ * Update real mode segment cache. It may be not up-to-date if segment
* register was written while vcpu was in a guest mode.
*/
vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES);
exit_reason.basic != EXIT_REASON_PML_FULL &&
exit_reason.basic != EXIT_REASON_APIC_ACCESS &&
exit_reason.basic != EXIT_REASON_TASK_SWITCH)) {
+ int ndata = 3;
+
vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
- vcpu->run->internal.ndata = 3;
vcpu->run->internal.data[0] = vectoring_info;
vcpu->run->internal.data[1] = exit_reason.full;
vcpu->run->internal.data[2] = vcpu->arch.exit_qualification;
if (exit_reason.basic == EXIT_REASON_EPT_MISCONFIG) {
- vcpu->run->internal.ndata++;
- vcpu->run->internal.data[3] =
+ vcpu->run->internal.data[ndata++] =
vmcs_read64(GUEST_PHYSICAL_ADDRESS);
}
- vcpu->run->internal.data[vcpu->run->internal.ndata++] =
- vcpu->arch.last_vmentry_cpu;
+ vcpu->run->internal.data[ndata++] = vcpu->arch.last_vmentry_cpu;
+ vcpu->run->internal.ndata = ndata;
return 0;
}
int i, nr_msrs;
struct perf_guest_switch_msr *msrs;
+ /* Note, nr_msrs may be garbage if perf_guest_get_msrs() returns NULL. */
msrs = perf_guest_get_msrs(&nr_msrs);
-
if (!msrs)
return;
if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_topa_output))
vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_TOPA;
- /* If CPUID.(EAX=14H,ECX=0):ECX[3]=1 FabircEn can be set */
+ /* If CPUID.(EAX=14H,ECX=0):ECX[3]=1 FabricEn can be set */
if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_output_subsys))
vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_FABRIC_EN;
/*
* lapic timer advance (tscdeadline mode only) in nanoseconds. '-1' enables
- * adaptive tuning starting from default advancment of 1000ns. '0' disables
+ * adaptive tuning starting from default advancement of 1000ns. '0' disables
* advancement entirely. Any other value is used as-is and disables adaptive
- * tuning, i.e. allows priveleged userspace to set an exact advancement time.
+ * tuning, i.e. allows privileged userspace to set an exact advancement time.
*/
static int __read_mostly lapic_timer_advance_ns = -1;
module_param(lapic_timer_advance_ns, int, S_IRUGO | S_IWUSR);
* When called, it means the previous get/set msr reached an invalid msr.
* Return true if we want to ignore/silent this failed msr access.
*/
-static bool kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr,
- u64 data, bool write)
+static bool kvm_msr_ignored_check(u32 msr, u64 data, bool write)
{
const char *op = write ? "wrmsr" : "rdmsr";
MSR_KVM_PV_EOI_EN, MSR_KVM_ASYNC_PF_INT, MSR_KVM_ASYNC_PF_ACK,
MSR_IA32_TSC_ADJUST,
- MSR_IA32_TSCDEADLINE,
+ MSR_IA32_TSC_DEADLINE,
MSR_IA32_ARCH_CAPABILITIES,
MSR_IA32_PERF_CAPABILITIES,
MSR_IA32_MISC_ENABLE,
/*
* If nx_huge_pages is enabled, KVM's shadow paging will ensure that
* the nested hypervisor runs with NX huge pages. If it is not,
- * L1 is anyway vulnerable to ITLB_MULTIHIT explots from other
+ * L1 is anyway vulnerable to ITLB_MULTIHIT exploits from other
* L1 guests, so it need not worry about its own (L2) guests.
*/
data |= ARCH_CAP_PSCHANGE_MC_NO;
if (r == KVM_MSR_RET_INVALID) {
/* Unconditionally clear the output for simplicity */
*data = 0;
- if (kvm_msr_ignored_check(vcpu, index, 0, false))
+ if (kvm_msr_ignored_check(index, 0, false))
r = 0;
}
bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type)
{
+ struct kvm_x86_msr_filter *msr_filter;
+ struct msr_bitmap_range *ranges;
struct kvm *kvm = vcpu->kvm;
- struct msr_bitmap_range *ranges = kvm->arch.msr_filter.ranges;
- u32 count = kvm->arch.msr_filter.count;
- u32 i;
- bool r = kvm->arch.msr_filter.default_allow;
+ bool allowed;
int idx;
+ u32 i;
- /* MSR filtering not set up or x2APIC enabled, allow everything */
- if (!count || (index >= 0x800 && index <= 0x8ff))
+ /* x2APIC MSRs do not support filtering. */
+ if (index >= 0x800 && index <= 0x8ff)
return true;
- /* Prevent collision with set_msr_filter */
idx = srcu_read_lock(&kvm->srcu);
- for (i = 0; i < count; i++) {
+ msr_filter = srcu_dereference(kvm->arch.msr_filter, &kvm->srcu);
+ if (!msr_filter) {
+ allowed = true;
+ goto out;
+ }
+
+ allowed = msr_filter->default_allow;
+ ranges = msr_filter->ranges;
+
+ for (i = 0; i < msr_filter->count; i++) {
u32 start = ranges[i].base;
u32 end = start + ranges[i].nmsrs;
u32 flags = ranges[i].flags;
unsigned long *bitmap = ranges[i].bitmap;
if ((index >= start) && (index < end) && (flags & type)) {
- r = !!test_bit(index - start, bitmap);
+ allowed = !!test_bit(index - start, bitmap);
break;
}
}
+out:
srcu_read_unlock(&kvm->srcu, idx);
- return r;
+ return allowed;
}
EXPORT_SYMBOL_GPL(kvm_msr_allowed);
int ret = __kvm_set_msr(vcpu, index, data, host_initiated);
if (ret == KVM_MSR_RET_INVALID)
- if (kvm_msr_ignored_check(vcpu, index, data, true))
+ if (kvm_msr_ignored_check(index, data, true))
ret = 0;
return ret;
if (ret == KVM_MSR_RET_INVALID) {
/* Unconditionally clear *data for simplicity */
*data = 0;
- if (kvm_msr_ignored_check(vcpu, index, 0, false))
+ if (kvm_msr_ignored_check(index, 0, false))
ret = 0;
}
ret = EXIT_FASTPATH_EXIT_HANDLED;
}
break;
- case MSR_IA32_TSCDEADLINE:
+ case MSR_IA32_TSC_DEADLINE:
data = kvm_read_edx_eax(vcpu);
if (!handle_fastpath_set_tscdeadline(vcpu, data)) {
kvm_skip_emulated_instruction(vcpu);
kvm_vcpu_write_tsc_offset(vcpu, offset);
raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
- spin_lock(&kvm->arch.pvclock_gtod_sync_lock);
+ spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags);
if (!matched) {
kvm->arch.nr_vcpus_matched_tsc = 0;
} else if (!already_matched) {
}
kvm_track_tsc_matching(vcpu);
- spin_unlock(&kvm->arch.pvclock_gtod_sync_lock);
+ spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags);
}
static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu,
int i;
struct kvm_vcpu *vcpu;
struct kvm_arch *ka = &kvm->arch;
+ unsigned long flags;
+
+ kvm_hv_invalidate_tsc_page(kvm);
- spin_lock(&ka->pvclock_gtod_sync_lock);
kvm_make_mclock_inprogress_request(kvm);
+
/* no guest entries from this point */
+ spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
pvclock_update_vm_gtod_copy(kvm);
+ spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
kvm_for_each_vcpu(i, vcpu, kvm)
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
/* guest entries allowed */
kvm_for_each_vcpu(i, vcpu, kvm)
kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu);
-
- spin_unlock(&ka->pvclock_gtod_sync_lock);
#endif
}
{
struct kvm_arch *ka = &kvm->arch;
struct pvclock_vcpu_time_info hv_clock;
+ unsigned long flags;
u64 ret;
- spin_lock(&ka->pvclock_gtod_sync_lock);
+ spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
if (!ka->use_master_clock) {
- spin_unlock(&ka->pvclock_gtod_sync_lock);
+ spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
return get_kvmclock_base_ns() + ka->kvmclock_offset;
}
hv_clock.tsc_timestamp = ka->master_cycle_now;
hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
- spin_unlock(&ka->pvclock_gtod_sync_lock);
+ spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
/* both __this_cpu_read() and rdtsc() should be on the same cpu */
get_cpu();
* If the host uses TSC clock, then passthrough TSC as stable
* to the guest.
*/
- spin_lock(&ka->pvclock_gtod_sync_lock);
+ spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
use_master_clock = ka->use_master_clock;
if (use_master_clock) {
host_tsc = ka->master_cycle_now;
kernel_ns = ka->master_kernel_ns;
}
- spin_unlock(&ka->pvclock_gtod_sync_lock);
+ spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
/* Keep irq disabled to prevent changes to the clock */
local_irq_save(flags);
return kvm_set_apic_base(vcpu, msr_info);
case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
return kvm_x2apic_msr_write(vcpu, msr, data);
- case MSR_IA32_TSCDEADLINE:
+ case MSR_IA32_TSC_DEADLINE:
kvm_set_lapic_tscdeadline_msr(vcpu, data);
break;
case MSR_IA32_TSC_ADJUST:
break;
case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data);
- case MSR_IA32_TSCDEADLINE:
+ case MSR_IA32_TSC_DEADLINE:
msr_info->data = kvm_get_lapic_tscdeadline_msr(vcpu);
break;
case MSR_IA32_TSC_ADJUST:
{
struct kvm_host_map map;
struct kvm_steal_time *st;
- int idx;
if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
return;
if (vcpu->arch.st.preempted)
return;
- /*
- * Take the srcu lock as memslots will be accessed to check the gfn
- * cache generation against the memslots generation.
- */
- idx = srcu_read_lock(&vcpu->kvm->srcu);
-
if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, &map,
&vcpu->arch.st.cache, true))
- goto out;
+ return;
st = map.hva +
offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS);
st->preempted = vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED;
kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, true);
-
-out:
- srcu_read_unlock(&vcpu->kvm->srcu, idx);
}
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
+ int idx;
+
if (vcpu->preempted && !vcpu->arch.guest_state_protected)
vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu);
+ /*
+ * Take the srcu lock as memslots will be accessed to check the gfn
+ * cache generation against the memslots generation.
+ */
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
if (kvm_xen_msr_enabled(vcpu->kvm))
kvm_xen_runstate_set_preempted(vcpu);
else
kvm_steal_time_set_preempted(vcpu);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
static_call(kvm_x86_vcpu_put)(vcpu);
vcpu->arch.last_host_tsc = rdtsc();
return r;
}
-static void kvm_clear_msr_filter(struct kvm *kvm)
+static struct kvm_x86_msr_filter *kvm_alloc_msr_filter(bool default_allow)
+{
+ struct kvm_x86_msr_filter *msr_filter;
+
+ msr_filter = kzalloc(sizeof(*msr_filter), GFP_KERNEL_ACCOUNT);
+ if (!msr_filter)
+ return NULL;
+
+ msr_filter->default_allow = default_allow;
+ return msr_filter;
+}
+
+static void kvm_free_msr_filter(struct kvm_x86_msr_filter *msr_filter)
{
u32 i;
- u32 count = kvm->arch.msr_filter.count;
- struct msr_bitmap_range ranges[16];
- mutex_lock(&kvm->lock);
- kvm->arch.msr_filter.count = 0;
- memcpy(ranges, kvm->arch.msr_filter.ranges, count * sizeof(ranges[0]));
- mutex_unlock(&kvm->lock);
- synchronize_srcu(&kvm->srcu);
+ if (!msr_filter)
+ return;
+
+ for (i = 0; i < msr_filter->count; i++)
+ kfree(msr_filter->ranges[i].bitmap);
- for (i = 0; i < count; i++)
- kfree(ranges[i].bitmap);
+ kfree(msr_filter);
}
-static int kvm_add_msr_filter(struct kvm *kvm, struct kvm_msr_filter_range *user_range)
+static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter,
+ struct kvm_msr_filter_range *user_range)
{
- struct msr_bitmap_range *ranges = kvm->arch.msr_filter.ranges;
struct msr_bitmap_range range;
unsigned long *bitmap = NULL;
size_t bitmap_size;
goto err;
}
- /* Everything ok, add this range identifier to our global pool */
- ranges[kvm->arch.msr_filter.count] = range;
- /* Make sure we filled the array before we tell anyone to walk it */
- smp_wmb();
- kvm->arch.msr_filter.count++;
+ /* Everything ok, add this range identifier. */
+ msr_filter->ranges[msr_filter->count] = range;
+ msr_filter->count++;
return 0;
err:
static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp)
{
struct kvm_msr_filter __user *user_msr_filter = argp;
+ struct kvm_x86_msr_filter *new_filter, *old_filter;
struct kvm_msr_filter filter;
bool default_allow;
- int r = 0;
bool empty = true;
+ int r = 0;
u32 i;
if (copy_from_user(&filter, user_msr_filter, sizeof(filter)))
if (empty && !default_allow)
return -EINVAL;
- kvm_clear_msr_filter(kvm);
+ new_filter = kvm_alloc_msr_filter(default_allow);
+ if (!new_filter)
+ return -ENOMEM;
- kvm->arch.msr_filter.default_allow = default_allow;
-
- /*
- * Protect from concurrent calls to this function that could trigger
- * a TOCTOU violation on kvm->arch.msr_filter.count.
- */
- mutex_lock(&kvm->lock);
for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) {
- r = kvm_add_msr_filter(kvm, &filter.ranges[i]);
- if (r)
- break;
+ r = kvm_add_msr_filter(new_filter, &filter.ranges[i]);
+ if (r) {
+ kvm_free_msr_filter(new_filter);
+ return r;
+ }
}
+ mutex_lock(&kvm->lock);
+
+ /* The per-VM filter is protected by kvm->lock... */
+ old_filter = srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1);
+
+ rcu_assign_pointer(kvm->arch.msr_filter, new_filter);
+ synchronize_srcu(&kvm->srcu);
+
+ kvm_free_msr_filter(old_filter);
+
kvm_make_all_cpus_request(kvm, KVM_REQ_MSR_FILTER_CHANGED);
mutex_unlock(&kvm->lock);
- return r;
+ return 0;
}
long kvm_arch_vm_ioctl(struct file *filp,
}
#endif
case KVM_SET_CLOCK: {
+ struct kvm_arch *ka = &kvm->arch;
struct kvm_clock_data user_ns;
u64 now_ns;
* pvclock_update_vm_gtod_copy().
*/
kvm_gen_update_masterclock(kvm);
- now_ns = get_kvmclock_ns(kvm);
- kvm->arch.kvmclock_offset += user_ns.clock - now_ns;
+
+ /*
+ * This pairs with kvm_guest_time_update(): when masterclock is
+ * in use, we use master_kernel_ns + kvmclock_offset to set
+ * unsigned 'system_time' so if we use get_kvmclock_ns() (which
+ * is slightly ahead) here we risk going negative on unsigned
+ * 'system_time' when 'user_ns.clock' is very small.
+ */
+ spin_lock_irq(&ka->pvclock_gtod_sync_lock);
+ if (kvm->arch.use_master_clock)
+ now_ns = ka->master_kernel_ns;
+ else
+ now_ns = get_kvmclock_base_ns();
+ ka->kvmclock_offset = user_ns.clock - now_ns;
+ spin_unlock_irq(&ka->pvclock_gtod_sync_lock);
+
kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE);
break;
}
int cpu = get_cpu();
cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask);
- smp_call_function_many(vcpu->arch.wbinvd_dirty_mask,
+ on_each_cpu_mask(vcpu->arch.wbinvd_dirty_mask,
wbinvd_ipi, NULL, 1);
put_cpu();
cpumask_clear(vcpu->arch.wbinvd_dirty_mask);
struct kvm *kvm;
struct kvm_vcpu *vcpu;
int cpu;
+ unsigned long flags;
mutex_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list)
list_for_each_entry(kvm, &vm_list, vm_list) {
struct kvm_arch *ka = &kvm->arch;
- spin_lock(&ka->pvclock_gtod_sync_lock);
-
+ spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
pvclock_update_vm_gtod_copy(kvm);
+ spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
kvm_for_each_vcpu(cpu, vcpu, kvm)
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
kvm_for_each_vcpu(cpu, vcpu, kvm)
kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu);
-
- spin_unlock(&ka->pvclock_gtod_sync_lock);
}
mutex_unlock(&kvm_lock);
}
return (void __user *)hva;
} else {
if (!slot || !slot->npages)
- return 0;
+ return NULL;
old_npages = slot->npages;
hva = slot->userspace_addr;
void kvm_arch_destroy_vm(struct kvm *kvm)
{
- u32 i;
-
if (current->mm == kvm->mm) {
/*
* Free memory regions allocated on behalf of userspace,
mutex_unlock(&kvm->slots_lock);
}
static_call_cond(kvm_x86_vm_destroy)(kvm);
- for (i = 0; i < kvm->arch.msr_filter.count; i++)
- kfree(kvm->arch.msr_filter.ranges[i].bitmap);
+ kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1));
kvm_pic_destroy(kvm);
kvm_ioapic_destroy(kvm);
kvm_free_vcpus(kvm);
void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock, int sec_hi_ofs);
void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip);
-void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr);
u64 get_kvmclock_ns(struct kvm *kvm);
int kvm_read_guest_virt(struct kvm_vcpu *vcpu,
*/
#include <linux/linkage.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
/* if you want SMP support, implement these with real spinlocks */
.macro LOCK reg
*/
#include <linux/linkage.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
.macro read64 reg
movl %ebx, %eax
#include <linux/linkage.h>
#include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
#include <asm/export.h>
/*
#include <asm/asm-offsets.h>
#include <asm/thread_info.h>
#include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
#include <asm/asm.h>
#include <asm/smap.h>
#include <asm/export.h>
* resolve_seg_reg() - obtain segment register index
* @insn: Instruction with operands
* @regs: Register values as seen when entering kernel mode
- * @regoff: Operand offset, in pt_regs, used to deterimine segment register
+ * @regoff: Operand offset, in pt_regs, used to determine segment register
*
* Determine the segment register associated with the operands and, if
* applicable, prefixes and the instruction pointed by @insn.
* @insn: Instruction containing ModRM byte
* @regs: Register values as seen when entering kernel mode
* @offs1: Offset of the first operand register
- * @offs2: Offset of the second opeand register, if applicable
+ * @offs2: Offset of the second operand register, if applicable
*
* Obtain the offset, in pt_regs, of the registers indicated by the ModRM byte
* in @insn. This function is to be used with 16-bit address encodings. The
* If ModRM.mod is 0 and ModRM.rm is 110b, then we use displacement-
* only addressing. This means that no registers are involved in
* computing the effective address. Thus, ensure that the first
- * register offset is invalild. The second register offset is already
+ * register offset is invalid. The second register offset is already
* invalid under the aforementioned conditions.
*/
if ((X86_MODRM_MOD(insn->modrm.value) == 0) &&
}
}
+static unsigned long insn_get_effective_ip(struct pt_regs *regs)
+{
+ unsigned long seg_base = 0;
+
+ /*
+ * If not in user-space long mode, a custom code segment could be in
+ * use. This is true in protected mode (if the process defined a local
+ * descriptor table), or virtual-8086 mode. In most of the cases
+ * seg_base will be zero as in USER_CS.
+ */
+ if (!user_64bit_mode(regs)) {
+ seg_base = insn_get_seg_base(regs, INAT_SEG_REG_CS);
+ if (seg_base == -1L)
+ return 0;
+ }
+
+ return seg_base + regs->ip;
+}
+
/**
* insn_fetch_from_user() - Copy instruction bytes from user-space memory
* @regs: Structure with register values as seen when entering kernel mode
*/
int insn_fetch_from_user(struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE])
{
- unsigned long seg_base = 0;
+ unsigned long ip;
int not_copied;
- /*
- * If not in user-space long mode, a custom code segment could be in
- * use. This is true in protected mode (if the process defined a local
- * descriptor table), or virtual-8086 mode. In most of the cases
- * seg_base will be zero as in USER_CS.
- */
- if (!user_64bit_mode(regs)) {
- seg_base = insn_get_seg_base(regs, INAT_SEG_REG_CS);
- if (seg_base == -1L)
- return 0;
- }
+ ip = insn_get_effective_ip(regs);
+ if (!ip)
+ return 0;
+
+ not_copied = copy_from_user(buf, (void __user *)ip, MAX_INSN_SIZE);
+ return MAX_INSN_SIZE - not_copied;
+}
+
+/**
+ * insn_fetch_from_user_inatomic() - Copy instruction bytes from user-space memory
+ * while in atomic code
+ * @regs: Structure with register values as seen when entering kernel mode
+ * @buf: Array to store the fetched instruction
+ *
+ * Gets the linear address of the instruction and copies the instruction bytes
+ * to the buf. This function must be used in atomic context.
+ *
+ * Returns:
+ *
+ * Number of instruction bytes copied.
+ *
+ * 0 if nothing was copied.
+ */
+int insn_fetch_from_user_inatomic(struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE])
+{
+ unsigned long ip;
+ int not_copied;
+
+ ip = insn_get_effective_ip(regs);
+ if (!ip)
+ return 0;
- not_copied = copy_from_user(buf, (void __user *)(seg_base + regs->ip),
- MAX_INSN_SIZE);
+ not_copied = __copy_from_user_inatomic(buf, (void __user *)ip, MAX_INSN_SIZE);
return MAX_INSN_SIZE - not_copied;
}
#include <linux/linkage.h>
#include <asm/errno.h>
#include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
#include <asm/export.h>
.pushsection .noinstr.text, "ax"
*/
#include <linux/linkage.h>
#include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
#include <asm/export.h>
#undef memmove
#include <linux/linkage.h>
#include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
#include <asm/export.h>
/*
* tested so far for any MMX solution figured.
*
* 22/09/2000 - Arjan van de Ven
- * Improved for non-egineering-sample Athlons
+ * Improved for non-engineering-sample Athlons
*
*/
#include <linux/hardirq.h>
rv->err = wrmsr_safe_regs(rv->regs);
}
-int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 *regs)
+int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8])
{
int err;
struct msr_regs_info rv;
}
EXPORT_SYMBOL(rdmsr_safe_regs_on_cpu);
-int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 *regs)
+int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8])
{
int err;
struct msr_regs_info rv;
* argument @m.
*
*/
-int msr_read(u32 msr, struct msr *m)
+static int msr_read(u32 msr, struct msr *m)
{
int err;
u64 val;
* @msr: MSR to write
* @m: value to write
*/
-int msr_write(u32 msr, struct msr *m)
+static int msr_write(u32 msr, struct msr *m)
{
return wrmsrl_safe(msr, m->q);
}
#include <linux/linkage.h>
#include <asm/dwarf2.h>
#include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
#include <asm/export.h>
#include <asm/nospec-branch.h>
#include <asm/unwind_hints.h>
single_arg_error(st0_ptr, st0_tag);
}
-static int fsin(FPU_REG *st0_ptr, u_char tag)
+static int f_sin(FPU_REG *st0_ptr, u_char tag)
{
u_char arg_sign = getsign(st0_ptr);
}
}
+static void fsin(FPU_REG *st0_ptr, u_char tag)
+{
+ f_sin(st0_ptr, tag);
+}
+
static int f_cos(FPU_REG *st0_ptr, u_char tag)
{
u_char st0_sign;
}
reg_copy(st0_ptr, &arg);
- if (!fsin(st0_ptr, st0_tag)) {
+ if (!f_sin(st0_ptr, st0_tag)) {
push();
FPU_copy_to_reg0(&arg, st0_tag);
f_cos(&st(0), st0_tag);
}
static FUNC_ST0 const trig_table_b[] = {
- fprem, fyl2xp1, fsqrt_, fsincos, frndint_, fscale, (FUNC_ST0) fsin, fcos
+ fprem, fyl2xp1, fsqrt_, fsincos, frndint_, fscale, fsin, fcos
};
void FPU_trigb(void)
/* The return value (in eax) is zero if the result is exact,
if bits are changed due to rounding, truncation, etc, then
a non-zero value is returned */
-/* Overflow is signalled by a non-zero return value (in eax).
+/* Overflow is signaled by a non-zero return value (in eax).
In the case of overflow, the returned significand always has the
largest possible value */
int FPU_round_to_int(FPU_REG *r, u_char tag)
#ifdef PECULIAR_486
/*
* This implements a special feature of 80486 behaviour.
- * Underflow will be signalled even if the number is
+ * Underflow will be signaled even if the number is
* not a denormal after rounding.
* This difference occurs only for masked underflow, and not
* in the unmasked case.
* userspace task is trying to access some valid (from guest's point of
* view) memory which is not currently mapped by the host (e.g. the
* memory is swapped out). Note, the corresponding "page ready" event
- * which is injected when the memory becomes available, is delived via
+ * which is injected when the memory becomes available, is delivered via
* an interrupt mechanism and not a #PF exception
* (see arch/x86/kernel/kvm.c: sysvec_kvm_asyncpf_interrupt()).
*
*
* In case the fault hit a RCU idle region the conditional entry
* code reenabled RCU to avoid subsequent wreckage which helps
- * debugability.
+ * debuggability.
*/
state = irqentry_enter(regs);
/*
* We need to define the tracepoints somewhere, and tlb.c
- * is only compied when SMP=y.
+ * is only compiled when SMP=y.
*/
#define CREATE_TRACE_POINTS
#include <trace/events/tlb.h>
#ifdef CONFIG_X86_64
if (max_pfn > max_low_pfn) {
- /* can we preseve max_low_pfn ?*/
+ /* can we preserve max_low_pfn ?*/
max_low_pfn = max_pfn;
}
#else
{
/*
* end could be not aligned, and We can not align that,
- * decompresser could be confused by aligned initrd_end
+ * decompressor could be confused by aligned initrd_end
* We already reserve the end partial page before in
* - i386_start_kernel()
* - x86_64_start_kernel()
/*
* With folded p4d, pgd_none() is always false, we need to
- * handle synchonization on p4d level.
+ * handle synchronization on p4d level.
*/
MAYBE_BUILD_BUG_ON(pgd_none(*pgd_ref));
p4d_ref = p4d_offset(pgd_ref, addr);
if (PAGE_ALIGNED(addr) && PAGE_ALIGNED(next)) {
/*
* Do not free direct mapping pages since they were
- * freed when offlining, or simplely not in use.
+ * freed when offlining, or simply not in use.
*/
if (!direct)
free_pagetable(pte_page(*pte), 0);
*
* If we are not removing the whole page, it means
* other page structs in this page are being used and
- * we canot remove them. So fill the unused page_structs
+ * we cannot remove them. So fill the unused page_structs
* with 0xFD, and remove the page when it is wholly
* filled with 0xFD.
*/
memory_tb = DIV_ROUND_UP(max_pfn << PAGE_SHIFT, 1UL << TB_SHIFT) +
CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING;
- /* Adapt phyiscal memory region size based on available memory */
+ /* Adapt physical memory region size based on available memory */
if (memory_tb < kaslr_regions[0].size_tb)
kaslr_regions[0].size_tb = memory_tb;
// SPDX-License-Identifier: GPL-2.0
/* Support for MMIO probes.
- * Benfit many code from kprobes
+ * Benefit many code from kprobes
* (C) 2002 Louis Zhuang <louis.zhuang@intel.com>.
* 2007 Alexander Eichner
* 2008 Pekka Paalanen <pq@iki.fi>
#include <linux/kernel.h>
#include <linux/bitops.h>
#include <linux/dma-mapping.h>
+#include <linux/virtio_config.h>
#include <asm/tlbflush.h>
#include <asm/fixmap.h>
if (pgprot_val(old_prot) == pgprot_val(new_prot))
return;
- pa = pfn << page_level_shift(level);
+ pa = pfn << PAGE_SHIFT;
size = page_level_size(level);
/*
print_mem_encrypt_feature_info();
}
+int arch_has_restricted_virtio_memory_access(void)
+{
+ return sev_active();
+}
+EXPORT_SYMBOL_GPL(arch_has_restricted_virtio_memory_access);
* - stack page (PAGE_SIZE)
* - encryption routine page (PAGE_SIZE)
* - intermediate copy buffer (PMD_PAGE_SIZE)
- * R8 - physcial address of the pagetables to use for encryption
+ * R8 - physical address of the pagetables to use for encryption
*/
push %rbp
#define AMD_SME_BIT BIT(0)
#define AMD_SEV_BIT BIT(1)
- /*
- * Set the feature mask (SME or SEV) based on whether we are
- * running under a hypervisor.
- */
- eax = 1;
- ecx = 0;
- native_cpuid(&eax, &ebx, &ecx, &edx);
- feature_mask = (ecx & BIT(31)) ? AMD_SEV_BIT : AMD_SME_BIT;
+
+ /* Check the SEV MSR whether SEV or SME is enabled */
+ sev_status = __rdmsr(MSR_AMD64_SEV);
+ feature_mask = (sev_status & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT;
/*
* Check for the SME/SEV feature:
/* Check if memory encryption is enabled */
if (feature_mask == AMD_SME_BIT) {
+ /*
+ * No SME if Hypervisor bit is set. This check is here to
+ * prevent a guest from trying to enable SME. For running as a
+ * KVM guest the MSR_K8_SYSCFG will be sufficient, but there
+ * might be other hypervisors which emulate that MSR as non-zero
+ * or even pass it through to the guest.
+ * A malicious hypervisor can still trick a guest into this
+ * path, but there is no way to protect against that.
+ */
+ eax = 1;
+ ecx = 0;
+ native_cpuid(&eax, &ebx, &ecx, &edx);
+ if (ecx & BIT(31))
+ return;
+
/* For SME, check the SYSCFG MSR */
msr = __rdmsr(MSR_K8_SYSCFG);
if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT))
return;
} else {
- /* For SEV, check the SEV MSR */
- msr = __rdmsr(MSR_AMD64_SEV);
- if (!(msr & MSR_AMD64_SEV_ENABLED))
- return;
-
- /* Save SEV_STATUS to avoid reading MSR again */
- sev_status = msr;
-
/* SEV state cannot be controlled by a command line option */
sme_me_mask = me_mask;
sev_enabled = true;
/**
- * lookup_memtype - Looksup the memory type for a physical address
+ * lookup_memtype - Looks up the memory type for a physical address
* @paddr: physical address of which memory type needs to be looked up
*
* Only to be called when PAT is enabled
memtype_free(start, end);
}
+#ifdef CONFIG_X86_PAT
int arch_io_reserve_memtype_wc(resource_size_t start, resource_size_t size)
{
enum page_cache_mode type = _PAGE_CACHE_MODE_WC;
memtype_free_io(start, start + size);
}
EXPORT_SYMBOL(arch_io_free_memtype_wc);
+#endif
pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t vma_prot)
* end up in this kind of memory, for instance.
*
* This could be optimized, but it is only intended to be
- * used at inititalization time, and keeping it
+ * used at initialization time, and keeping it
* unoptimized should increase the testing coverage for
* the more obscure platforms.
*/
/*
* Called from the FPU code when creating a fresh set of FPU
* registers. This is called from a very specific context where
- * we know the FPU regstiers are safe for use and we can use PKRU
+ * we know the FPU registers are safe for use and we can use PKRU
* directly.
*/
void copy_init_pkru_to_fpregs(void)
* global, so set it as global in both copies. Note:
* the X86_FEATURE_PGE check is not _required_ because
* the CPU ignores _PAGE_GLOBAL when PGE is not
- * supported. The check keeps consistentency with
+ * supported. The check keeps consistency with
* code that only set this bit when supported.
*/
if (boot_cpu_has(X86_FEATURE_PGE))
for_each_possible_cpu(cpu) {
/*
- * The SYSCALL64 entry code needs to be able to find the
- * thread stack and needs one word of scratch space in which
- * to spill a register. All of this lives in the TSS, in
- * the sp1 and sp2 slots.
+ * The SYSCALL64 entry code needs one word of scratch space
+ * in which to spill a register. It lives in the sp2 slot
+ * of the CPU's TSS.
*
* This is done for all possible CPUs during boot to ensure
* that it's propagated to all mms.
static inline bool pti_kernel_image_global_ok(void)
{
/*
- * Systems with PCIDs get litlle benefit from global
+ * Systems with PCIDs get little benefit from global
* kernel text and are not worth the downsides.
*/
if (cpu_feature_enabled(X86_FEATURE_PCID))
#ifdef CONFIG_PAGE_TABLE_ISOLATION
/*
- * Make sure that the dynamic ASID space does not confict with the
+ * Make sure that the dynamic ASID space does not conflict with the
* bit we are using to switch between user and kernel ASIDs.
*/
BUILD_BUG_ON(TLB_NR_DYN_ASIDS >= (1 << X86_CR3_PTI_PCID_USER_BIT));
* 3, we'd be break the invariant: we'd update local_tlb_gen above
* 1 without the full flush that's needed for tlb_gen 2.
*
- * 2. f->new_tlb_gen == mm_tlb_gen. This is purely an optimiation.
+ * 2. f->new_tlb_gen == mm_tlb_gen. This is purely an optimization.
* Partial TLB flushes are not all that much cheaper than full TLB
* flushes, so it seems unlikely that it would be a performance win
* to do a partial flush if that won't bring our TLB fully up to
static inline void put_flush_tlb_info(void)
{
#ifdef CONFIG_DEBUG_VM
- /* Complete reentrency prevention checks */
+ /* Complete reentrancy prevention checks */
barrier();
this_cpu_dec(flush_tlb_info_idx);
#endif
insn->imm == (BPF_XOR | BPF_FETCH)) {
u8 *branch_target;
bool is64 = BPF_SIZE(insn->code) == BPF_DW;
+ u32 real_src_reg = src_reg;
/*
* Can't be implemented with a single x86 insn.
/* Will need RAX as a CMPXCHG operand so save R0 */
emit_mov_reg(&prog, true, BPF_REG_AX, BPF_REG_0);
+ if (src_reg == BPF_REG_0)
+ real_src_reg = BPF_REG_AX;
+
branch_target = prog;
/* Load old value */
emit_ldx(&prog, BPF_SIZE(insn->code),
* put the result in the AUX_REG.
*/
emit_mov_reg(&prog, is64, AUX_REG, BPF_REG_0);
- maybe_emit_mod(&prog, AUX_REG, src_reg, is64);
+ maybe_emit_mod(&prog, AUX_REG, real_src_reg, is64);
EMIT2(simple_alu_opcodes[BPF_OP(insn->imm)],
- add_2reg(0xC0, AUX_REG, src_reg));
+ add_2reg(0xC0, AUX_REG, real_src_reg));
/* Attempt to swap in new value */
err = emit_atomic(&prog, BPF_CMPXCHG,
dst_reg, AUX_REG, insn->off,
*/
EMIT2(X86_JNE, -(prog - branch_target) - 2);
/* Return the pre-modification value */
- emit_mov_reg(&prog, is64, src_reg, BPF_REG_0);
+ emit_mov_reg(&prog, is64, real_src_reg, BPF_REG_0);
/* Restore R0 after clobbering RAX */
emit_mov_reg(&prog, true, BPF_REG_0, BPF_REG_AX);
break;
if (is_imm8(jmp_offset)) {
if (jmp_padding) {
/* To keep the jmp_offset valid, the extra bytes are
- * padded before the jump insn, so we substract the
+ * padded before the jump insn, so we subtract the
* 2 bytes of jmp_cond insn from INSN_SZ_DIFF.
*
* If the previous pass already emits an imm8
if (jmp_padding) {
/* To avoid breaking jmp_offset, the extra bytes
* are padded before the actual jmp insn, so
- * 2 bytes is substracted from INSN_SZ_DIFF.
+ * 2 bytes is subtracted from INSN_SZ_DIFF.
*
* If the previous pass already emits an imm8
* jmp, there is nothing to pad (0 byte).
}
if (image) {
- if (unlikely(proglen + ilen > oldproglen)) {
+ /*
+ * When populating the image, assert that:
+ *
+ * i) We do not write beyond the allocated space, and
+ * ii) addrs[i] did not change from the prior run, in order
+ * to validate assumptions made for computing branch
+ * displacements.
+ */
+ if (unlikely(proglen + ilen > oldproglen ||
+ proglen + ilen != addrs[i])) {
pr_err("bpf_jit: fatal error\n");
return -EFAULT;
}
* add rsp, 8 // skip eth_type_trans's frame
* ret // return to its caller
*/
-int arch_prepare_bpf_trampoline(void *image, void *image_end,
+int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
const struct btf_func_model *m, u32 flags,
struct bpf_tramp_progs *tprogs,
void *orig_call)
save_regs(m, &prog, nr_args, stack_size);
+ if (flags & BPF_TRAMP_F_CALL_ORIG) {
+ /* arg1: mov rdi, im */
+ emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im);
+ if (emit_call(&prog, __bpf_tramp_enter, prog)) {
+ ret = -EINVAL;
+ goto cleanup;
+ }
+ }
+
if (fentry->nr_progs)
if (invoke_bpf(m, &prog, fentry, stack_size))
return -EINVAL;
}
if (flags & BPF_TRAMP_F_CALL_ORIG) {
- if (fentry->nr_progs || fmod_ret->nr_progs)
- restore_regs(m, &prog, nr_args, stack_size);
+ restore_regs(m, &prog, nr_args, stack_size);
/* call original function */
if (emit_call(&prog, orig_call, prog)) {
}
/* remember return value in a stack for bpf prog to access */
emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
+ im->ip_after_call = prog;
+ memcpy(prog, ideal_nops[NOP_ATOMIC5], X86_PATCH_SIZE);
+ prog += X86_PATCH_SIZE;
}
if (fmod_ret->nr_progs) {
* the return value is only updated on the stack and still needs to be
* restored to R0.
*/
- if (flags & BPF_TRAMP_F_CALL_ORIG)
+ if (flags & BPF_TRAMP_F_CALL_ORIG) {
+ im->ip_epilogue = prog;
+ /* arg1: mov rdi, im */
+ emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im);
+ if (emit_call(&prog, __bpf_tramp_exit, prog)) {
+ ret = -EINVAL;
+ goto cleanup;
+ }
/* restore original return value back into RAX */
emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8);
+ }
EMIT1(0x5B); /* pop rbx */
EMIT1(0xC9); /* leave */
padding = true;
goto skip_init_addrs;
}
- addrs = kmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL);
+ addrs = kvmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL);
if (!addrs) {
prog = orig_prog;
goto out_addrs;
if (image)
bpf_prog_fill_jited_linfo(prog, addrs + 1);
out_addrs:
- kfree(addrs);
+ kvfree(addrs);
kfree(jit_data);
prog->aux->jit_data = NULL;
}
}
if (image) {
- if (unlikely(proglen + ilen > oldproglen)) {
+ /*
+ * When populating the image, assert that:
+ *
+ * i) We do not write beyond the allocated space, and
+ * ii) addrs[i] did not change from the prior run, in order
+ * to validate assumptions made for computing branch
+ * displacements.
+ */
+ if (unlikely(proglen + ilen > oldproglen ||
+ proglen + ilen != addrs[i])) {
pr_err("bpf_jit: fatal error\n");
return -EFAULT;
}
* The BIOS only gives options "DISABLED" and "AUTO". This code sets
* the corresponding register-value to enable the soundcard.
*
- * The soundcard is only enabled, if the mainborad is identified
+ * The soundcard is only enabled, if the mainboard is identified
* via DMI-tables and the soundcard is detected to be off.
*/
static void pci_fixup_msi_k8t_onboard_sound(struct pci_dev *dev)
}
/*
- * Certain firmware versions are way too sentimential and still believe
+ * Certain firmware versions are way too sentimental and still believe
* they are exclusive and unquestionable owners of the first physical page,
* even though they explicitly mark it as EFI_CONVENTIONAL_MEMORY
* (but then write-access it later during SetVirtualAddressMap()).
* in a kernel thread and user context. Preemption needs to remain disabled
* while the EFI-mm is borrowed. mmgrab()/mmdrop() is not used because the mm
* can not change under us.
- * It should be ensured that there are no concurent calls to this function.
+ * It should be ensured that there are no concurrent calls to this function.
*/
void efi_enter_mm(void)
{
* 1.4.4 with SGX enabled booting Linux via Fedora 24's
* grub2-efi on a hard disk. (And no, I don't know why
* this happened, but Linux should still try to boot rather
- * panicing early.)
+ * panicking early.)
*/
rm_size = real_mode_size_needed();
if (rm_size && (start + rm_size) < (1<<20) && size >= rm_size) {
* Buggy efi_reset_system() is handled differently from other EFI
* Runtime Services as it doesn't use efi_rts_wq. Although,
* native_machine_emergency_restart() says that machine_real_restart()
- * could fail, it's better not to compilcate this fault handler
+ * could fail, it's better not to complicate this fault handler
* because this case occurs *very* rarely and hence could be improved
* on a need by basis.
*/
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* imr.c -- Intel Isolated Memory Region driver
*
* Copyright(c) 2013 Intel Corporation.
/*
* Setup an unlocked IMR around the physical extent of the kernel
- * from the beginning of the .text secton to the end of the
+ * from the beginning of the .text section to the end of the
* .rodata section as one physically contiguous block.
*
* We don't round up @size since it is already PAGE_SIZE aligned.
// SPDX-License-Identifier: GPL-2.0
-/**
+/*
* imr_selftest.c -- Intel Isolated Memory Region self-test driver
*
* Copyright(c) 2013 Intel Corporation.
EXPORT_SYMBOL(iosf_mbi_available);
/*
- **************** P-Unit/kernel shared I2C bus arbritration ****************
+ **************** P-Unit/kernel shared I2C bus arbitration ****************
*
* Some Bay Trail and Cherry Trail devices have the P-Unit and us (the kernel)
* share a single I2C bus to the PMIC. Below are helpers to arbitrate the
/* mcrx */
debugfs_create_x32("mcrx", 0660, iosf_dbg, &dbg_mcrx);
- /* mcr - initiates mailbox tranaction */
+ /* mcr - initiates mailbox transaction */
debugfs_create_file("mcr", 0660, iosf_dbg, &dbg_mcr, &iosf_mcr_fops);
}
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Sébastien Hinderer <Sebastien.Hinderer@ens-lyon.org>");
MODULE_DESCRIPTION("A power_off handler for Iris devices from EuroBraille");
-MODULE_SUPPORTED_DEVICE("Eurobraille/Iris");
static bool force;
* wake-on-close. This is implemented as standard by the XO-1.5 DSDT.
*
* We provide here a sysfs attribute that will additionally enable
- * wake-on-close behavior. This is useful (e.g.) when we oportunistically
+ * wake-on-close behavior. This is useful (e.g.) when we opportunistically
* suspend with the display running; if the lid is then closed, we want to
* wake up to turn the display off.
*
const size_t chunk_size = max(PAGE_SIZE, size);
/*
- * To mimimize the number of allocations, grab at least
+ * To minimize the number of allocations, grab at least
* PAGE_SIZE of memory (that's an arbitrary choice that's
* fast enough on the platforms we care about while minimizing
* wasted bootmem) and hand off chunks of it to callers.
* the boot start info structure.
* - `cr0`: bit 0 (PE) must be set. All the other writeable bits are cleared.
* - `cr4`: all bits are cleared.
- * - `cs `: must be a 32-bit read/execute code segment with a base of ‘0’
- * and a limit of ‘0xFFFFFFFF’. The selector value is unspecified.
+ * - `cs `: must be a 32-bit read/execute code segment with a base of `0`
+ * and a limit of `0xFFFFFFFF`. The selector value is unspecified.
* - `ds`, `es`: must be a 32-bit read/write data segment with a base of
- * ‘0’ and a limit of ‘0xFFFFFFFF’. The selector values are all
+ * `0` and a limit of `0xFFFFFFFF`. The selector values are all
* unspecified.
* - `tr`: must be a 32-bit TSS (active) with a base of '0' and a limit
* of '0x67'.
#include <asm/kdebug.h>
#include <asm/local64.h>
#include <asm/nmi.h>
+#include <asm/reboot.h>
#include <asm/traps.h>
#include <asm/uv/uv.h>
#include <asm/uv/uv_hub.h>
static atomic_t uv_nmi_slave_continue;
static cpumask_var_t uv_nmi_cpu_mask;
+static atomic_t uv_nmi_kexec_failed;
+
/* Values for uv_nmi_slave_continue */
#define SLAVE_CLEAR 0
#define SLAVE_CONTINUE 1
touch_nmi_watchdog();
}
-static atomic_t uv_nmi_kexec_failed;
-
-#if defined(CONFIG_KEXEC_CORE)
-static void uv_nmi_kdump(int cpu, int master, struct pt_regs *regs)
+static void uv_nmi_kdump(int cpu, int main, struct pt_regs *regs)
{
+ /* Check if kdump kernel loaded for both main and secondary CPUs */
+ if (!kexec_crash_image) {
+ if (main)
+ pr_err("UV: NMI error: kdump kernel not loaded\n");
+ return;
+ }
+
/* Call crash to dump system state */
- if (master) {
+ if (main) {
pr_emerg("UV: NMI executing crash_kexec on CPU%d\n", cpu);
crash_kexec(regs);
- pr_emerg("UV: crash_kexec unexpectedly returned, ");
+ pr_emerg("UV: crash_kexec unexpectedly returned\n");
atomic_set(&uv_nmi_kexec_failed, 1);
- if (!kexec_crash_image) {
- pr_cont("crash kernel not loaded\n");
- return;
- }
- pr_cont("kexec busy, stalling cpus while waiting\n");
- }
- /* If crash exec fails the slaves should return, otherwise stall */
- while (atomic_read(&uv_nmi_kexec_failed) == 0)
- mdelay(10);
-}
+ } else { /* secondary */
-#else /* !CONFIG_KEXEC_CORE */
-static inline void uv_nmi_kdump(int cpu, int master, struct pt_regs *regs)
-{
- if (master)
- pr_err("UV: NMI kdump: KEXEC not supported in this kernel\n");
- atomic_set(&uv_nmi_kexec_failed, 1);
+ /* If kdump kernel fails, secondaries will exit this loop */
+ while (atomic_read(&uv_nmi_kexec_failed) == 0) {
+
+ /* Once shootdown cpus starts, they do not return */
+ run_crash_ipi_callback(regs);
+
+ mdelay(10);
+ }
+ }
}
-#endif /* !CONFIG_KEXEC_CORE */
#ifdef CONFIG_KGDB
#ifdef CONFIG_KGDB_KDB
* Call KGDB/KDB from NMI handler
*
* Note that if both KGDB and KDB are configured, then the action of 'kgdb' or
- * 'kdb' has no affect on which is used. See the KGDB documention for further
+ * 'kdb' has no affect on which is used. See the KGDB documentation for further
* information.
*/
static void uv_call_kgdb_kdb(int cpu, struct pt_regs *regs, int master)
/*
* When bsp_check() is called in hibernate and suspend, cpu hotplug
- * is disabled already. So it's unnessary to handle race condition between
+ * is disabled already. So it's unnecessary to handle race condition between
* cpumask query and cpu hotplug.
*/
static int bsp_check(void)
*ptr += phys_base;
}
- /* Must be perfomed *after* relocation. */
+ /* Must be performed *after* relocation. */
trampoline_header = (struct trampoline_header *)
__va(real_mode_header->trampoline_header);
.read_pmc = xen_read_pmc,
- .iret = xen_iret,
-
.load_tr_desc = paravirt_nop,
.set_ldt = xen_set_ldt,
.load_gdt = xen_load_gdt,
/* Install Xen paravirt ops */
pv_info = xen_info;
- pv_ops.init.patch = paravirt_patch_default;
pv_ops.cpu = xen_cpu_ops;
+ paravirt_iret = xen_iret;
xen_init_irq_ops();
/*
rmd.prot = prot;
/*
* We use the err_ptr to indicate if there we are doing a contiguous
- * mapping or a discontigious mapping.
+ * mapping or a discontiguous mapping.
*/
rmd.contiguous = !err_ptr;
rmd.no_translate = no_translate;
unsigned long xen_max_p2m_pfn __read_mostly;
EXPORT_SYMBOL_GPL(xen_max_p2m_pfn);
-#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG_LIMIT
-#define P2M_LIMIT CONFIG_XEN_BALLOON_MEMORY_HOTPLUG_LIMIT
+#ifdef CONFIG_XEN_MEMORY_HOTPLUG_LIMIT
+#define P2M_LIMIT CONFIG_XEN_MEMORY_HOTPLUG_LIMIT
#else
#define P2M_LIMIT 0
#endif
xen_p2m_last_pfn = xen_max_p2m_pfn;
p2m_limit = (phys_addr_t)P2M_LIMIT * 1024 * 1024 * 1024 / PAGE_SIZE;
- if (!p2m_limit && IS_ENABLED(CONFIG_XEN_UNPOPULATED_ALLOC))
- p2m_limit = xen_start_info->nr_pages * XEN_EXTRA_MEM_RATIO;
-
vm.flags = VM_ALLOC;
vm.size = ALIGN(sizeof(unsigned long) * max(xen_max_p2m_pfn, p2m_limit),
PMD_SIZE * PMDS_PER_MID_PAGE);
map_ops[i].status = GNTST_general_error;
unmap[0].host_addr = map_ops[i].host_addr,
unmap[0].handle = map_ops[i].handle;
- map_ops[i].handle = ~0;
+ map_ops[i].handle = INVALID_GRANT_HANDLE;
if (map_ops[i].flags & GNTMAP_device_map)
unmap[0].dev_bus_addr = map_ops[i].dev_bus_addr;
else
kmap_ops[i].status = GNTST_general_error;
unmap[1].host_addr = kmap_ops[i].host_addr,
unmap[1].handle = kmap_ops[i].handle;
- kmap_ops[i].handle = ~0;
+ kmap_ops[i].handle = INVALID_GRANT_HANDLE;
if (kmap_ops[i].flags & GNTMAP_device_map)
unmap[1].dev_bus_addr = kmap_ops[i].dev_bus_addr;
else
out:
return ret;
}
-EXPORT_SYMBOL_GPL(set_foreign_p2m_mapping);
int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
struct gnttab_unmap_grant_ref *kunmap_ops,
return ret;
}
-EXPORT_SYMBOL_GPL(clear_foreign_p2m_mapping);
#ifdef CONFIG_XEN_DEBUG_FS
#include <linux/debugfs.h>
} xen_remap_buf __initdata __aligned(PAGE_SIZE);
static unsigned long xen_remap_mfn __initdata = INVALID_P2M_ENTRY;
+/*
+ * The maximum amount of extra memory compared to the base size. The
+ * main scaling factor is the size of struct page. At extreme ratios
+ * of base:extra, all the base memory can be filled with page
+ * structures for the extra memory, leaving no space for anything
+ * else.
+ *
+ * 10x seems like a reasonable balance between scaling flexibility and
+ * leaving a practically usable system.
+ */
+#define EXTRA_MEM_RATIO (10)
+
static bool xen_512gb_limit __initdata = IS_ENABLED(CONFIG_XEN_512GB);
static void __init xen_parse_512gb(void)
extra_pages += max_pages - max_pfn;
/*
- * Clamp the amount of extra memory to a XEN_EXTRA_MEM_RATIO
+ * Clamp the amount of extra memory to a EXTRA_MEM_RATIO
* factor the base size.
*
* Make sure we have no memory above max_pages, as this area
* isn't handled by the p2m management.
*/
- extra_pages = min3(XEN_EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
+ extra_pages = min3(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
extra_pages, max_pages - max_pfn);
i = 0;
addr = xen_e820_table.entries[0].addr;
}
}
-static const struct pv_time_ops xen_time_ops __initconst = {
- .sched_clock = xen_sched_clock,
- .steal_clock = xen_steal_clock,
-};
-
static struct pvclock_vsyscall_time_info *xen_clock __read_mostly;
static u64 xen_clock_value_saved;
pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
}
-void __init xen_init_time_ops(void)
+static void __init xen_init_time_common(void)
{
xen_sched_clock_offset = xen_clocksource_read();
- pv_ops.time = xen_time_ops;
+ static_call_update(pv_steal_clock, xen_steal_clock);
+ paravirt_set_sched_clock(xen_sched_clock);
+
+ x86_platform.calibrate_tsc = xen_tsc_khz;
+ x86_platform.get_wallclock = xen_get_wallclock;
+}
+
+void __init xen_init_time_ops(void)
+{
+ xen_init_time_common();
x86_init.timers.timer_init = xen_time_init;
x86_init.timers.setup_percpu_clockev = x86_init_noop;
x86_cpuinit.setup_percpu_clockev = x86_init_noop;
- x86_platform.calibrate_tsc = xen_tsc_khz;
- x86_platform.get_wallclock = xen_get_wallclock;
/* Dom0 uses the native method to set the hardware RTC. */
if (!xen_initial_domain())
x86_platform.set_wallclock = xen_set_wallclock;
return;
}
- xen_sched_clock_offset = xen_clocksource_read();
- pv_ops.time = xen_time_ops;
+ xen_init_time_common();
+
x86_init.timers.setup_percpu_clockev = xen_time_init;
x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents;
- x86_platform.calibrate_tsc = xen_tsc_khz;
- x86_platform.get_wallclock = xen_get_wallclock;
x86_platform.set_wallclock = xen_set_wallclock;
}
#endif
LOAD_CP_REGS_TAB(7)
/*
- * coprocessor_flush(struct thread_info*, index)
- * a2 a3
- *
- * Save coprocessor registers for coprocessor 'index'.
- * The register values are saved to or loaded from the coprocessor area
- * inside the task_info structure.
- *
- * Note that this function doesn't update the coprocessor_owner information!
- *
- */
-
-ENTRY(coprocessor_flush)
-
- /* reserve 4 bytes on stack to save a0 */
- abi_entry(4)
-
- s32i a0, a1, 0
- movi a0, .Lsave_cp_regs_jump_table
- addx8 a3, a3, a0
- l32i a4, a3, 4
- l32i a3, a3, 0
- add a2, a2, a4
- beqz a3, 1f
- callx0 a3
-1: l32i a0, a1, 0
-
- abi_ret(4)
-
-ENDPROC(coprocessor_flush)
-
-/*
* Entry condition:
*
* a0: trashed, original value saved on stack (PT_AREG0)
ENDPROC(fast_coprocessor)
+ .text
+
+/*
+ * coprocessor_flush(struct thread_info*, index)
+ * a2 a3
+ *
+ * Save coprocessor registers for coprocessor 'index'.
+ * The register values are saved to or loaded from the coprocessor area
+ * inside the task_info structure.
+ *
+ * Note that this function doesn't update the coprocessor_owner information!
+ *
+ */
+
+ENTRY(coprocessor_flush)
+
+ /* reserve 4 bytes on stack to save a0 */
+ abi_entry(4)
+
+ s32i a0, a1, 0
+ movi a0, .Lsave_cp_regs_jump_table
+ addx8 a3, a3, a0
+ l32i a4, a3, 4
+ l32i a3, a3, 0
+ add a2, a2, a4
+ beqz a3, 1f
+ callx0 a3
+1: l32i a0, a1, 0
+
+ abi_ret(4)
+
+ENDPROC(coprocessor_flush)
+
.data
ENTRY(coprocessor_owner)
*/
fault = handle_mm_fault(vma, address, flags, regs);
- if (fault_signal_pending(fault, regs))
+ if (fault_signal_pending(fault, regs)) {
+ if (!user_mode(regs))
+ goto bad_page_fault;
return;
+ }
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
{ .nr_vecs = 16, .name = "biovec-16" },
{ .nr_vecs = 64, .name = "biovec-64" },
{ .nr_vecs = 128, .name = "biovec-128" },
- { .nr_vecs = BIO_MAX_PAGES, .name = "biovec-max" },
+ { .nr_vecs = BIO_MAX_VECS, .name = "biovec-max" },
};
static struct biovec_slab *biovec_slab(unsigned short nr_vecs)
return &bvec_slabs[1];
case 65 ... 128:
return &bvec_slabs[2];
- case 129 ... BIO_MAX_PAGES:
+ case 129 ... BIO_MAX_VECS:
return &bvec_slabs[3];
default:
BUG();
void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned short nr_vecs)
{
- BIO_BUG_ON(nr_vecs > BIO_MAX_PAGES);
+ BIO_BUG_ON(nr_vecs > BIO_MAX_VECS);
- if (nr_vecs == BIO_MAX_PAGES)
+ if (nr_vecs == BIO_MAX_VECS)
mempool_free(bv, pool);
else if (nr_vecs > BIO_INLINE_VECS)
kmem_cache_free(biovec_slab(nr_vecs)->slab, bv);
/*
* Try a slab allocation first for all smaller allocations. If that
* fails and __GFP_DIRECT_RECLAIM is set retry with the mempool.
- * The mempool is sized to handle up to BIO_MAX_PAGES entries.
+ * The mempool is sized to handle up to BIO_MAX_VECS entries.
*/
- if (*nr_vecs < BIO_MAX_PAGES) {
+ if (*nr_vecs < BIO_MAX_VECS) {
struct bio_vec *bvl;
bvl = kmem_cache_alloc(bvs->slab, bvec_alloc_gfp(gfp_mask));
if (likely(bvl) || !(gfp_mask & __GFP_DIRECT_RECLAIM))
return bvl;
- *nr_vecs = BIO_MAX_PAGES;
+ *nr_vecs = BIO_MAX_VECS;
}
return mempool_alloc(pool, gfp_mask);
{
struct bio *parent = bio->bi_private;
- if (!parent->bi_status)
+ if (bio->bi_status && !parent->bi_status)
parent->bi_status = bio->bi_status;
bio_put(bio);
return parent;
}
EXPORT_SYMBOL_GPL(bio_release_pages);
-static int bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
+static void __bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
{
WARN_ON_ONCE(bio->bi_max_vecs);
bio->bi_iter.bi_size = iter->count;
bio_set_flag(bio, BIO_NO_PAGE_REF);
bio_set_flag(bio, BIO_CLONED);
+}
+static int bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
+{
+ __bio_iov_bvec_set(bio, iter);
iov_iter_advance(iter, iter->count);
return 0;
}
+static int bio_iov_bvec_set_append(struct bio *bio, struct iov_iter *iter)
+{
+ struct request_queue *q = bio->bi_bdev->bd_disk->queue;
+ struct iov_iter i = *iter;
+
+ iov_iter_truncate(&i, queue_max_zone_append_sectors(q) << 9);
+ __bio_iov_bvec_set(bio, &i);
+ iov_iter_advance(iter, i.count);
+ return 0;
+}
+
#define PAGE_PTRS_PER_BVEC (sizeof(struct bio_vec) / sizeof(struct page *))
/**
int ret = 0;
if (iov_iter_is_bvec(iter)) {
- if (WARN_ON_ONCE(bio_op(bio) == REQ_OP_ZONE_APPEND))
- return -EINVAL;
+ if (bio_op(bio) == REQ_OP_ZONE_APPEND)
+ return bio_iov_bvec_set_append(bio, iter);
return bio_iov_bvec_set(bio, iter);
}
lockdep_assert_held(&blkg->q->queue_lock);
+ memset(sum, 0, sizeof(*sum));
rcu_read_lock();
blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) {
struct blkg_rwstat *rwstat;
rwstat = (void *)pos_blkg + off;
for (i = 0; i < BLKG_RWSTAT_NR; i++)
- sum->cnt[i] = blkg_rwstat_read_counter(rwstat, i);
+ sum->cnt[i] += blkg_rwstat_read_counter(rwstat, i);
}
rcu_read_unlock();
}
bio_for_each_segment(bv, bio, iter) {
num_sectors += bv.bv_len >> SECTOR_SHIFT;
- if (++i == BIO_MAX_PAGES)
+ if (++i == BIO_MAX_VECS)
break;
}
if (num_sectors < bio_sectors(bio)) {
{
sector_t pages = DIV_ROUND_UP_SECTOR_T(nr_sects, PAGE_SIZE / 512);
- return min(pages, (sector_t)BIO_MAX_PAGES);
+ return min(pages, (sector_t)BIO_MAX_VECS);
}
static int __blkdev_issue_zero_pages(struct block_device *bdev,
if (!iov_iter_count(iter))
return -EINVAL;
- bio = bio_kmalloc(gfp_mask, iov_iter_npages(iter, BIO_MAX_PAGES));
+ bio = bio_kmalloc(gfp_mask, iov_iter_npages(iter, BIO_MAX_VECS));
if (!bio)
return -ENOMEM;
bio->bi_opf |= req_op(rq);
switch (bio_op(rq->bio)) {
case REQ_OP_DISCARD:
case REQ_OP_SECURE_ERASE:
+ if (queue_max_discard_segments(rq->q) > 1) {
+ struct bio *bio = rq->bio;
+
+ for_each_bio(bio)
+ nr_phys_segs++;
+ return nr_phys_segs;
+ }
+ return 1;
case REQ_OP_WRITE_ZEROES:
return 0;
case REQ_OP_WRITE_SAME:
RQF_NAME(QUIET),
RQF_NAME(ELVPRIV),
RQF_NAME(IO_STAT),
- RQF_NAME(ALLOCED),
RQF_NAME(PM),
RQF_NAME(HASHED),
RQF_NAME(STATS),
*/
if (op == REQ_OP_ZONE_RESET &&
blkdev_allow_reset_all_zones(bdev, sector, nr_sectors)) {
- bio->bi_opf = REQ_OP_ZONE_RESET_ALL;
+ bio->bi_opf = REQ_OP_ZONE_RESET_ALL | REQ_SYNC;
break;
}
return 0;
}
+static int blkdev_truncate_zone_range(struct block_device *bdev, fmode_t mode,
+ const struct blk_zone_range *zrange)
+{
+ loff_t start, end;
+
+ if (zrange->sector + zrange->nr_sectors <= zrange->sector ||
+ zrange->sector + zrange->nr_sectors > get_capacity(bdev->bd_disk))
+ /* Out of range */
+ return -EINVAL;
+
+ start = zrange->sector << SECTOR_SHIFT;
+ end = ((zrange->sector + zrange->nr_sectors) << SECTOR_SHIFT) - 1;
+
+ return truncate_bdev_range(bdev, mode, start, end);
+}
+
/*
* BLKRESETZONE, BLKOPENZONE, BLKCLOSEZONE and BLKFINISHZONE ioctl processing.
* Called from blkdev_ioctl.
struct request_queue *q;
struct blk_zone_range zrange;
enum req_opf op;
+ int ret;
if (!argp)
return -EINVAL;
switch (cmd) {
case BLKRESETZONE:
op = REQ_OP_ZONE_RESET;
+
+ /* Invalidate the page cache, including dirty pages. */
+ ret = blkdev_truncate_zone_range(bdev, mode, &zrange);
+ if (ret)
+ return ret;
break;
case BLKOPENZONE:
op = REQ_OP_ZONE_OPEN;
return -ENOTTY;
}
- return blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors,
- GFP_KERNEL);
+ ret = blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors,
+ GFP_KERNEL);
+
+ /*
+ * Invalidate the page cache again for zone reset: writes can only be
+ * direct for zoned devices so concurrent writes would not add any page
+ * to the page cache after/during reset. The page cache may be filled
+ * again due to concurrent reads though and dropping the pages for
+ * these is fine.
+ */
+ if (!ret && cmd == BLKRESETZONE)
+ ret = blkdev_truncate_zone_range(bdev, mode, &zrange);
+
+ return ret;
}
static inline unsigned long *blk_alloc_zone_bitmap(int node,
* - The point of cloning the biovec is to produce a bio with a biovec
* the caller can modify: bi_idx and bi_bvec_done should be 0.
*
- * - The original bio could've had more than BIO_MAX_PAGES biovecs; if
+ * - The original bio could've had more than BIO_MAX_VECS biovecs; if
* we tried to clone the whole thing bio_alloc_bioset() would fail.
* But the clone should succeed as long as the number of biovecs we
- * actually need to allocate is fewer than BIO_MAX_PAGES.
+ * actually need to allocate is fewer than BIO_MAX_VECS.
*
* - Lastly, bi_vcnt should not be looked at or relied upon by code
* that does not own the bio - reason being drivers don't use it for
int sectors = 0;
bio_for_each_segment(from, *bio_orig, iter) {
- if (i++ < BIO_MAX_PAGES)
+ if (i++ < BIO_MAX_VECS)
sectors += from.bv_len >> 9;
if (page_to_pfn(from.bv_page) > q->limits.bounce_pfn)
bounce = true;
kobject_create_and_add("holders", &ddev->kobj);
disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj);
- if (disk->flags & GENHD_FL_HIDDEN) {
- dev_set_uevent_suppress(ddev, 0);
+ if (disk->flags & GENHD_FL_HIDDEN)
return;
- }
disk_scan_partitions(disk);
return -EINVAL;
if (!capable(CAP_SYS_ADMIN))
return -EACCES;
+ if (bdev->bd_part_count)
+ return -EBUSY;
/*
* Reopen the device to revalidate the driver state and force a
int err;
/*
+ * disk_max_parts() won't be zero, either GENHD_FL_EXT_DEVT is set
+ * or 'minors' is passed to alloc_disk().
+ */
+ if (partno >= disk_max_parts(disk))
+ return ERR_PTR(-EINVAL);
+
+ /*
* Partitions are not supported on zoned block devices that are used as
* such.
*/
wrapper to incorporate the list into the kernel. Each <hash> should
be a string of hex digits.
+config SYSTEM_REVOCATION_LIST
+ bool "Provide system-wide ring of revocation certificates"
+ depends on SYSTEM_BLACKLIST_KEYRING
+ depends on PKCS7_MESSAGE_PARSER=y
+ help
+ If set, this allows revocation certificates to be stored in the
+ blacklist keyring and implements a hook whereby a PKCS#7 message can
+ be checked to see if it matches such a certificate.
+
+config SYSTEM_REVOCATION_KEYS
+ string "X.509 certificates to be preloaded into the system blacklist keyring"
+ depends on SYSTEM_REVOCATION_LIST
+ help
+ If set, this option should be the filename of a PEM-formatted file
+ containing X.509 certificates to be included in the default blacklist
+ keyring.
+
endmenu
# Makefile for the linux kernel signature checking certificates.
#
-obj-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += system_keyring.o system_certificates.o
-obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist.o
+obj-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += system_keyring.o system_certificates.o common.o
+obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist.o common.o
+obj-$(CONFIG_SYSTEM_REVOCATION_LIST) += revocation_certificates.o
ifneq ($(CONFIG_SYSTEM_BLACKLIST_HASH_LIST),"")
obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist_hashes.o
else
$(call if_changed,extract_certs,$(SYSTEM_TRUSTED_KEYS_SRCPREFIX)$(CONFIG_SYSTEM_TRUSTED_KEYS))
endif # CONFIG_SYSTEM_TRUSTED_KEYRING
-clean-files := x509_certificate_list .x509.list
+clean-files := x509_certificate_list .x509.list x509_revocation_list
ifeq ($(CONFIG_MODULE_SIG),y)
###############################################################################
$(obj)/signing_key.x509: scripts/extract-cert $(X509_DEP) FORCE
$(call if_changed,extract_certs,$(MODULE_SIG_KEY_SRCPREFIX)$(CONFIG_MODULE_SIG_KEY))
endif # CONFIG_MODULE_SIG
+
+ifeq ($(CONFIG_SYSTEM_REVOCATION_LIST),y)
+
+$(eval $(call config_filename,SYSTEM_REVOCATION_KEYS))
+
+$(obj)/revocation_certificates.o: $(obj)/x509_revocation_list
+
+quiet_cmd_extract_certs = EXTRACT_CERTS $(patsubst "%",%,$(2))
+ cmd_extract_certs = scripts/extract-cert $(2) $@
+
+targets += x509_revocation_list
+$(obj)/x509_revocation_list: scripts/extract-cert $(SYSTEM_REVOCATION_KEYS_SRCPREFIX)$(SYSTEM_REVOCATION_KEYS_FILENAME) FORCE
+ $(call if_changed,extract_certs,$(SYSTEM_REVOCATION_KEYS_SRCPREFIX)$(CONFIG_SYSTEM_REVOCATION_KEYS))
+endif
#include <linux/uidgid.h>
#include <keys/system_keyring.h>
#include "blacklist.h"
+#include "common.h"
static struct key *blacklist_keyring;
+#ifdef CONFIG_SYSTEM_REVOCATION_LIST
+extern __initconst const u8 revocation_certificate_list[];
+extern __initconst const unsigned long revocation_certificate_list_size;
+#endif
+
/*
* The description must be a type prefix, a colon and then an even number of
* hex digits. The hash is kept in the description.
}
EXPORT_SYMBOL_GPL(is_binary_blacklisted);
+#ifdef CONFIG_SYSTEM_REVOCATION_LIST
+/**
+ * add_key_to_revocation_list - Add a revocation certificate to the blacklist
+ * @data: The data blob containing the certificate
+ * @size: The size of data blob
+ */
+int add_key_to_revocation_list(const char *data, size_t size)
+{
+ key_ref_t key;
+
+ key = key_create_or_update(make_key_ref(blacklist_keyring, true),
+ "asymmetric",
+ NULL,
+ data,
+ size,
+ ((KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW),
+ KEY_ALLOC_NOT_IN_QUOTA | KEY_ALLOC_BUILT_IN);
+
+ if (IS_ERR(key)) {
+ pr_err("Problem with revocation key (%ld)\n", PTR_ERR(key));
+ return PTR_ERR(key);
+ }
+
+ return 0;
+}
+
+/**
+ * is_key_on_revocation_list - Determine if the key for a PKCS#7 message is revoked
+ * @pkcs7: The PKCS#7 message to check
+ */
+int is_key_on_revocation_list(struct pkcs7_message *pkcs7)
+{
+ int ret;
+
+ ret = pkcs7_validate_trust(pkcs7, blacklist_keyring);
+
+ if (ret == 0)
+ return -EKEYREJECTED;
+
+ return -ENOKEY;
+}
+#endif
+
/*
* Initialise the blacklist
*/
* Must be initialised before we try and load the keys into the keyring.
*/
device_initcall(blacklist_init);
+
+#ifdef CONFIG_SYSTEM_REVOCATION_LIST
+/*
+ * Load the compiled-in list of revocation X.509 certificates.
+ */
+static __init int load_revocation_certificate_list(void)
+{
+ if (revocation_certificate_list_size)
+ pr_notice("Loading compiled-in revocation X.509 certificates\n");
+
+ return load_certificate_list(revocation_certificate_list, revocation_certificate_list_size,
+ blacklist_keyring);
+}
+late_initcall(load_revocation_certificate_list);
+#endif
#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <crypto/pkcs7.h>
extern const char __initconst *const blacklist_hashes[];
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/kernel.h>
+#include <linux/key.h>
+#include "common.h"
+
+int load_certificate_list(const u8 cert_list[],
+ const unsigned long list_size,
+ const struct key *keyring)
+{
+ key_ref_t key;
+ const u8 *p, *end;
+ size_t plen;
+
+ p = cert_list;
+ end = p + list_size;
+ while (p < end) {
+ /* Each cert begins with an ASN.1 SEQUENCE tag and must be more
+ * than 256 bytes in size.
+ */
+ if (end - p < 4)
+ goto dodgy_cert;
+ if (p[0] != 0x30 &&
+ p[1] != 0x82)
+ goto dodgy_cert;
+ plen = (p[2] << 8) | p[3];
+ plen += 4;
+ if (plen > end - p)
+ goto dodgy_cert;
+
+ key = key_create_or_update(make_key_ref(keyring, 1),
+ "asymmetric",
+ NULL,
+ p,
+ plen,
+ ((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+ KEY_USR_VIEW | KEY_USR_READ),
+ KEY_ALLOC_NOT_IN_QUOTA |
+ KEY_ALLOC_BUILT_IN |
+ KEY_ALLOC_BYPASS_RESTRICTION);
+ if (IS_ERR(key)) {
+ pr_err("Problem loading in-kernel X.509 certificate (%ld)\n",
+ PTR_ERR(key));
+ } else {
+ pr_notice("Loaded X.509 cert '%s'\n",
+ key_ref_to_ptr(key)->description);
+ key_ref_put(key);
+ }
+ p += plen;
+ }
+
+ return 0;
+
+dodgy_cert:
+ pr_err("Problem parsing in-kernel X.509 certificate list\n");
+ return 0;
+}
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef _CERT_COMMON_H
+#define _CERT_COMMON_H
+
+int load_certificate_list(const u8 cert_list[], const unsigned long list_size,
+ const struct key *keyring);
+
+#endif
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/export.h>
+#include <linux/init.h>
+
+ __INITRODATA
+
+ .align 8
+ .globl revocation_certificate_list
+revocation_certificate_list:
+__revocation_list_start:
+ .incbin "certs/x509_revocation_list"
+__revocation_list_end:
+
+ .align 8
+ .globl revocation_certificate_list_size
+revocation_certificate_list_size:
+#ifdef CONFIG_64BIT
+ .quad __revocation_list_end - __revocation_list_start
+#else
+ .long __revocation_list_end - __revocation_list_start
+#endif
#include <keys/asymmetric-type.h>
#include <keys/system_keyring.h>
#include <crypto/pkcs7.h>
+#include "common.h"
static struct key *builtin_trusted_keys;
#ifdef CONFIG_SECONDARY_TRUSTED_KEYRING
*/
static __init int load_system_certificate_list(void)
{
- key_ref_t key;
- const u8 *p, *end;
- size_t plen;
-
pr_notice("Loading compiled-in X.509 certificates\n");
- p = system_certificate_list;
- end = p + system_certificate_list_size;
- while (p < end) {
- /* Each cert begins with an ASN.1 SEQUENCE tag and must be more
- * than 256 bytes in size.
- */
- if (end - p < 4)
- goto dodgy_cert;
- if (p[0] != 0x30 &&
- p[1] != 0x82)
- goto dodgy_cert;
- plen = (p[2] << 8) | p[3];
- plen += 4;
- if (plen > end - p)
- goto dodgy_cert;
-
- key = key_create_or_update(make_key_ref(builtin_trusted_keys, 1),
- "asymmetric",
- NULL,
- p,
- plen,
- ((KEY_POS_ALL & ~KEY_POS_SETATTR) |
- KEY_USR_VIEW | KEY_USR_READ),
- KEY_ALLOC_NOT_IN_QUOTA |
- KEY_ALLOC_BUILT_IN |
- KEY_ALLOC_BYPASS_RESTRICTION);
- if (IS_ERR(key)) {
- pr_err("Problem loading in-kernel X.509 certificate (%ld)\n",
- PTR_ERR(key));
- } else {
- pr_notice("Loaded X.509 cert '%s'\n",
- key_ref_to_ptr(key)->description);
- key_ref_put(key);
- }
- p += plen;
- }
-
- return 0;
-
-dodgy_cert:
- pr_err("Problem parsing in-kernel X.509 certificate list\n");
- return 0;
+ return load_certificate_list(system_certificate_list, system_certificate_list_size,
+ builtin_trusted_keys);
}
late_initcall(load_system_certificate_list);
pr_devel("PKCS#7 platform keyring is not available\n");
goto error;
}
+
+ ret = is_key_on_revocation_list(pkcs7);
+ if (ret != -ENOKEY) {
+ pr_devel("PKCS#7 platform key is on revocation list\n");
+ goto error;
+ }
}
ret = pkcs7_validate_trust(pkcs7, trusted_keys);
if (ret < 0) {
help
Generic implementation of the ECDH algorithm
+config CRYPTO_ECDSA
+ tristate "ECDSA (NIST P192, P256 etc.) algorithm"
+ select CRYPTO_ECC
+ select CRYPTO_AKCIPHER
+ select ASN1
+ help
+ Elliptic Curve Digital Signature Algorithm (NIST P192, P256 etc.)
+ is A NIST cryptographic standard algorithm. Only signature verification
+ is implemented.
+
config CRYPTO_ECRDSA
tristate "EC-RDSA (GOST 34.10) algorithm"
select CRYPTO_ECC
config CRYPTO_POLY1305_MIPS
tristate "Poly1305 authenticator algorithm (MIPS optimized)"
- depends on CPU_MIPS32 || (CPU_MIPS64 && 64BIT)
+ depends on MIPS
select CRYPTO_ARCH_HAVE_LIB_POLY1305
config CRYPTO_MD4
config CRYPTO_CAMELLIA
tristate "Camellia cipher algorithms"
- depends on CRYPTO
select CRYPTO_ALGAPI
help
Camellia cipher algorithms module.
config CRYPTO_CAMELLIA_X86_64
tristate "Camellia cipher algorithm (x86_64)"
depends on X86 && 64BIT
- depends on CRYPTO
select CRYPTO_SKCIPHER
imply CRYPTO_CTR
help
config CRYPTO_CAMELLIA_AESNI_AVX_X86_64
tristate "Camellia cipher algorithm (x86_64/AES-NI/AVX)"
depends on X86 && 64BIT
- depends on CRYPTO
select CRYPTO_SKCIPHER
select CRYPTO_CAMELLIA_X86_64
select CRYPTO_SIMD
config CRYPTO_CAMELLIA_AESNI_AVX2_X86_64
tristate "Camellia cipher algorithm (x86_64/AES-NI/AVX2)"
depends on X86 && 64BIT
- depends on CRYPTO
select CRYPTO_CAMELLIA_AESNI_AVX_X86_64
help
Camellia cipher algorithm module (x86_64/AES-NI/AVX2).
config CRYPTO_CAMELLIA_SPARC64
tristate "Camellia cipher algorithm (SPARC64)"
depends on SPARC64
- depends on CRYPTO
select CRYPTO_ALGAPI
select CRYPTO_SKCIPHER
help
obj-$(CONFIG_CRYPTO_SM2) += sm2_generic.o
+$(obj)/ecdsasignature.asn1.o: $(obj)/ecdsasignature.asn1.c $(obj)/ecdsasignature.asn1.h
+$(obj)/ecdsa.o: $(obj)/ecdsasignature.asn1.h
+ecdsa_generic-y += ecdsa.o
+ecdsa_generic-y += ecdsasignature.asn1.o
+obj-$(CONFIG_CRYPTO_ECDSA) += ecdsa_generic.o
+
crypto_acompress-y := acompress.o
crypto_acompress-y += scompress.o
obj-$(CONFIG_CRYPTO_ACOMP2) += crypto_acompress.o
u8 bytes[AEGIS_BLOCK_SIZE];
};
+struct aegis_state;
+
+extern int aegis128_have_aes_insn;
+
#define AEGIS_BLOCK_ALIGN (__alignof__(union aegis_block))
#define AEGIS_ALIGNED(p) IS_ALIGNED((uintptr_t)p, AEGIS_BLOCK_ALIGN)
+bool crypto_aegis128_have_simd(void);
+void crypto_aegis128_update_simd(struct aegis_state *state, const void *msg);
+void crypto_aegis128_init_simd(struct aegis_state *state,
+ const union aegis_block *key,
+ const u8 *iv);
+void crypto_aegis128_encrypt_chunk_simd(struct aegis_state *state, u8 *dst,
+ const u8 *src, unsigned int size);
+void crypto_aegis128_decrypt_chunk_simd(struct aegis_state *state, u8 *dst,
+ const u8 *src, unsigned int size);
+int crypto_aegis128_final_simd(struct aegis_state *state,
+ union aegis_block *tag_xor,
+ unsigned int assoclen,
+ unsigned int cryptlen,
+ unsigned int authsize);
+
static __always_inline void crypto_aegis_block_xor(union aegis_block *dst,
const union aegis_block *src)
{
return false;
}
-bool crypto_aegis128_have_simd(void);
-void crypto_aegis128_update_simd(struct aegis_state *state, const void *msg);
-void crypto_aegis128_init_simd(struct aegis_state *state,
- const union aegis_block *key,
- const u8 *iv);
-void crypto_aegis128_encrypt_chunk_simd(struct aegis_state *state, u8 *dst,
- const u8 *src, unsigned int size);
-void crypto_aegis128_decrypt_chunk_simd(struct aegis_state *state, u8 *dst,
- const u8 *src, unsigned int size);
-int crypto_aegis128_final_simd(struct aegis_state *state,
- union aegis_block *tag_xor,
- unsigned int assoclen,
- unsigned int cryptlen,
- unsigned int authsize);
-
static void crypto_aegis128_update(struct aegis_state *state)
{
union aegis_block tmp;
return IS_ENABLED(CONFIG_ARM64);
}
-void crypto_aegis128_init_simd(union aegis_block *state,
+void crypto_aegis128_init_simd(struct aegis_state *state,
const union aegis_block *key,
const u8 *iv)
{
kernel_neon_end();
}
-void crypto_aegis128_update_simd(union aegis_block *state, const void *msg)
+void crypto_aegis128_update_simd(struct aegis_state *state, const void *msg)
{
kernel_neon_begin();
crypto_aegis128_update_neon(state, msg);
kernel_neon_end();
}
-void crypto_aegis128_encrypt_chunk_simd(union aegis_block *state, u8 *dst,
+void crypto_aegis128_encrypt_chunk_simd(struct aegis_state *state, u8 *dst,
const u8 *src, unsigned int size)
{
kernel_neon_begin();
kernel_neon_end();
}
-void crypto_aegis128_decrypt_chunk_simd(union aegis_block *state, u8 *dst,
+void crypto_aegis128_decrypt_chunk_simd(struct aegis_state *state, u8 *dst,
const u8 *src, unsigned int size)
{
kernel_neon_begin();
kernel_neon_end();
}
-int crypto_aegis128_final_simd(union aegis_block *state,
+int crypto_aegis128_final_simd(struct aegis_state *state,
union aegis_block *tag_xor,
unsigned int assoclen,
unsigned int cryptlen,
/**
* af_alg_alloc_tsgl - allocate the TX SGL
*
- * @sk socket of connection to user space
- * @return: 0 upon success, < 0 upon error
+ * @sk: socket of connection to user space
+ * Return: 0 upon success, < 0 upon error
*/
static int af_alg_alloc_tsgl(struct sock *sk)
{
}
/**
- * aead_count_tsgl - Count number of TX SG entries
+ * af_alg_count_tsgl - Count number of TX SG entries
*
* The counting starts from the beginning of the SGL to @bytes. If
- * an offset is provided, the counting of the SG entries starts at the offset.
+ * an @offset is provided, the counting of the SG entries starts at the @offset.
*
- * @sk socket of connection to user space
- * @bytes Count the number of SG entries holding given number of bytes.
- * @offset Start the counting of SG entries from the given offset.
- * @return Number of TX SG entries found given the constraints
+ * @sk: socket of connection to user space
+ * @bytes: Count the number of SG entries holding given number of bytes.
+ * @offset: Start the counting of SG entries from the given offset.
+ * Return: Number of TX SG entries found given the constraints
*/
unsigned int af_alg_count_tsgl(struct sock *sk, size_t bytes, size_t offset)
{
EXPORT_SYMBOL_GPL(af_alg_count_tsgl);
/**
- * aead_pull_tsgl - Release the specified buffers from TX SGL
+ * af_alg_pull_tsgl - Release the specified buffers from TX SGL
*
- * If @dst is non-null, reassign the pages to dst. The caller must release
+ * If @dst is non-null, reassign the pages to @dst. The caller must release
* the pages. If @dst_offset is given only reassign the pages to @dst starting
* at the @dst_offset (byte). The caller must ensure that @dst is large
* enough (e.g. by using af_alg_count_tsgl with the same offset).
*
- * @sk socket of connection to user space
- * @used Number of bytes to pull from TX SGL
- * @dst If non-NULL, buffer is reassigned to dst SGL instead of releasing. The
- * caller must release the buffers in dst.
- * @dst_offset Reassign the TX SGL from given offset. All buffers before
- * reaching the offset is released.
+ * @sk: socket of connection to user space
+ * @used: Number of bytes to pull from TX SGL
+ * @dst: If non-NULL, buffer is reassigned to dst SGL instead of releasing. The
+ * caller must release the buffers in dst.
+ * @dst_offset: Reassign the TX SGL from given offset. All buffers before
+ * reaching the offset is released.
*/
void af_alg_pull_tsgl(struct sock *sk, size_t used, struct scatterlist *dst,
size_t dst_offset)
/**
* af_alg_free_areq_sgls - Release TX and RX SGLs of the request
*
- * @areq Request holding the TX and RX SGL
+ * @areq: Request holding the TX and RX SGL
*/
static void af_alg_free_areq_sgls(struct af_alg_async_req *areq)
{
/**
* af_alg_wait_for_wmem - wait for availability of writable memory
*
- * @sk socket of connection to user space
- * @flags If MSG_DONTWAIT is set, then only report if function would sleep
- * @return 0 when writable memory is available, < 0 upon error
+ * @sk: socket of connection to user space
+ * @flags: If MSG_DONTWAIT is set, then only report if function would sleep
+ * Return: 0 when writable memory is available, < 0 upon error
*/
static int af_alg_wait_for_wmem(struct sock *sk, unsigned int flags)
{
/**
* af_alg_wmem_wakeup - wakeup caller when writable memory is available
*
- * @sk socket of connection to user space
+ * @sk: socket of connection to user space
*/
void af_alg_wmem_wakeup(struct sock *sk)
{
/**
* af_alg_wait_for_data - wait for availability of TX data
*
- * @sk socket of connection to user space
- * @flags If MSG_DONTWAIT is set, then only report if function would sleep
- * @min Set to minimum request size if partial requests are allowed.
- * @return 0 when writable memory is available, < 0 upon error
+ * @sk: socket of connection to user space
+ * @flags: If MSG_DONTWAIT is set, then only report if function would sleep
+ * @min: Set to minimum request size if partial requests are allowed.
+ * Return: 0 when writable memory is available, < 0 upon error
*/
int af_alg_wait_for_data(struct sock *sk, unsigned flags, unsigned min)
{
/**
* af_alg_data_wakeup - wakeup caller when new data can be sent to kernel
*
- * @sk socket of connection to user space
+ * @sk: socket of connection to user space
*/
static void af_alg_data_wakeup(struct sock *sk)
{
*
* In addition, the ctx is filled with the information sent via CMSG.
*
- * @sock socket of connection to user space
- * @msg message from user space
- * @size size of message from user space
- * @ivsize the size of the IV for the cipher operation to verify that the
+ * @sock: socket of connection to user space
+ * @msg: message from user space
+ * @size: size of message from user space
+ * @ivsize: the size of the IV for the cipher operation to verify that the
* user-space-provided IV has the right size
- * @return the number of copied data upon success, < 0 upon error
+ * Return: the number of copied data upon success, < 0 upon error
*/
int af_alg_sendmsg(struct socket *sock, struct msghdr *msg, size_t size,
unsigned int ivsize)
/**
* af_alg_sendpage - sendpage system call handler
+ * @sock: socket of connection to user space to write to
+ * @page: data to send
+ * @offset: offset into page to begin sending
+ * @size: length of data
+ * @flags: message send/receive flags
*
* This is a generic implementation of sendpage to fill ctx->tsgl_list.
*/
/**
* af_alg_free_resources - release resources required for crypto request
+ * @areq: Request holding the TX and RX SGL
*/
void af_alg_free_resources(struct af_alg_async_req *areq)
{
/**
* af_alg_async_cb - AIO callback handler
+ * @_req: async request info
+ * @err: if non-zero, error result to be returned via ki_complete();
+ * otherwise return the AIO output length via ki_complete().
*
* This handler cleans up the struct af_alg_async_req upon completion of the
* AIO operation.
/**
* af_alg_poll - poll system call handler
+ * @file: file pointer
+ * @sock: socket to poll
+ * @wait: poll_table
*/
__poll_t af_alg_poll(struct file *file, struct socket *sock,
poll_table *wait)
/**
* af_alg_alloc_areq - allocate struct af_alg_async_req
*
- * @sk socket of connection to user space
- * @areqlen size of struct af_alg_async_req + crypto_*_reqsize
- * @return allocated data structure or ERR_PTR upon error
+ * @sk: socket of connection to user space
+ * @areqlen: size of struct af_alg_async_req + crypto_*_reqsize
+ * Return: allocated data structure or ERR_PTR upon error
*/
struct af_alg_async_req *af_alg_alloc_areq(struct sock *sk,
unsigned int areqlen)
* af_alg_get_rsgl - create the RX SGL for the output data from the crypto
* operation
*
- * @sk socket of connection to user space
- * @msg user space message
- * @flags flags used to invoke recvmsg with
- * @areq instance of the cryptographic request that will hold the RX SGL
- * @maxsize maximum number of bytes to be pulled from user space
- * @outlen number of bytes in the RX SGL
- * @return 0 on success, < 0 upon error
+ * @sk: socket of connection to user space
+ * @msg: user space message
+ * @flags: flags used to invoke recvmsg with
+ * @areq: instance of the cryptographic request that will hold the RX SGL
+ * @maxsize: maximum number of bytes to be pulled from user space
+ * @outlen: number of bytes in the RX SGL
+ * Return: 0 on success, < 0 upon error
*/
int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags,
struct af_alg_async_req *areq, size_t maxsize,
{
struct crypto_alg *alg;
- if (unlikely(!mem))
+ if (IS_ERR_OR_NULL(mem))
return;
alg = tfm->__crt_alg;
#include <linux/slab.h>
#include <linux/seq_file.h>
#include <linux/scatterlist.h>
+#include <linux/asn1.h>
#include <keys/asymmetric-subtype.h>
#include <crypto/public_key.h>
#include <crypto/akcipher.h>
return n >= CRYPTO_MAX_ALG_NAME ? -EINVAL : 0;
}
- if (strcmp(encoding, "raw") == 0) {
+ if (strcmp(encoding, "raw") == 0 ||
+ strcmp(encoding, "x962") == 0) {
strcpy(alg_name, pkey->pkey_algo);
return 0;
}
ctx->cert->sig->hash_algo = "sha224";
goto rsa_pkcs1;
+ case OID_id_ecdsa_with_sha1:
+ ctx->cert->sig->hash_algo = "sha1";
+ goto ecdsa;
+
+ case OID_id_ecdsa_with_sha224:
+ ctx->cert->sig->hash_algo = "sha224";
+ goto ecdsa;
+
+ case OID_id_ecdsa_with_sha256:
+ ctx->cert->sig->hash_algo = "sha256";
+ goto ecdsa;
+
+ case OID_id_ecdsa_with_sha384:
+ ctx->cert->sig->hash_algo = "sha384";
+ goto ecdsa;
+
+ case OID_id_ecdsa_with_sha512:
+ ctx->cert->sig->hash_algo = "sha512";
+ goto ecdsa;
+
case OID_gost2012Signature256:
ctx->cert->sig->hash_algo = "streebog256";
goto ecrdsa;
ctx->cert->sig->encoding = "raw";
ctx->algo_oid = ctx->last_oid;
return 0;
+ecdsa:
+ ctx->cert->sig->pkey_algo = "ecdsa";
+ ctx->cert->sig->encoding = "x962";
+ ctx->algo_oid = ctx->last_oid;
+ return 0;
}
/*
if (strcmp(ctx->cert->sig->pkey_algo, "rsa") == 0 ||
strcmp(ctx->cert->sig->pkey_algo, "ecrdsa") == 0 ||
- strcmp(ctx->cert->sig->pkey_algo, "sm2") == 0) {
+ strcmp(ctx->cert->sig->pkey_algo, "sm2") == 0 ||
+ strcmp(ctx->cert->sig->pkey_algo, "ecdsa") == 0) {
/* Discard the BIT STRING metadata */
if (vlen < 1 || *(const u8 *)value != 0)
return -EBADMSG;
const void *value, size_t vlen)
{
struct x509_parse_context *ctx = context;
+ enum OID oid;
ctx->key_algo = ctx->last_oid;
switch (ctx->last_oid) {
ctx->cert->pub->pkey_algo = "ecrdsa";
break;
case OID_id_ecPublicKey:
- ctx->cert->pub->pkey_algo = "sm2";
+ if (parse_OID(ctx->params, ctx->params_size, &oid) != 0)
+ return -EBADMSG;
+
+ switch (oid) {
+ case OID_sm2:
+ ctx->cert->pub->pkey_algo = "sm2";
+ break;
+ case OID_id_prime192v1:
+ ctx->cert->pub->pkey_algo = "ecdsa-nist-p192";
+ break;
+ case OID_id_prime256v1:
+ ctx->cert->pub->pkey_algo = "ecdsa-nist-p256";
+ break;
+ case OID_id_ansip384r1:
+ ctx->cert->pub->pkey_algo = "ecdsa-nist-p384";
+ break;
+ default:
+ return -ENOPKG;
+ }
break;
default:
return -ENOPKG;
}
ret = -EKEYREJECTED;
- if (strcmp(cert->pub->pkey_algo, cert->sig->pkey_algo) != 0)
+ if (strcmp(cert->pub->pkey_algo, cert->sig->pkey_algo) != 0 &&
+ (strncmp(cert->pub->pkey_algo, "ecdsa-", 6) != 0 ||
+ strcmp(cert->sig->pkey_algo, "ecdsa") != 0))
goto out;
ret = public_key_verify_signature(cert->pub, cert->sig);
-/* GPL HEADER START
- *
- * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 only,
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License version 2 for more details (a copy is included
- * in the LICENSE file that accompanied this code).
- *
- * You should have received a copy of the GNU General Public License
- * version 2 along with this program; If not, see http://www.gnu.org/licenses
- *
- * Please visit http://www.xyratex.com/contact if you need additional
- * information or have any questions.
- *
- * GPL HEADER END
- */
-
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright 2012 Xyratex Technology Limited
*/
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
+#include <crypto/ecc_curve.h>
#include <linux/module.h>
#include <linux/random.h>
#include <linux/slab.h>
u64 m_high;
} uint128_t;
-static inline const struct ecc_curve *ecc_get_curve(unsigned int curve_id)
+/* Returns curv25519 curve param */
+const struct ecc_curve *ecc_get_curve25519(void)
+{
+ return &ecc_25519;
+}
+EXPORT_SYMBOL(ecc_get_curve25519);
+
+const struct ecc_curve *ecc_get_curve(unsigned int curve_id)
{
switch (curve_id) {
/* In FIPS mode only allow P256 and higher */
return fips_enabled ? NULL : &nist_p192;
case ECC_CURVE_NIST_P256:
return &nist_p256;
+ case ECC_CURVE_NIST_P384:
+ return &nist_p384;
default:
return NULL;
}
}
+EXPORT_SYMBOL(ecc_get_curve);
static u64 *ecc_alloc_digits_space(unsigned int ndigits)
{
}
EXPORT_SYMBOL(vli_is_zero);
-/* Returns nonzero if bit bit of vli is set. */
+/* Returns nonzero if bit of vli is set. */
static u64 vli_test_bit(const u64 *vli, unsigned int bit)
{
return (vli[bit / 64] & ((u64)1 << (bit % 64)));
}
}
+#define SL32OR32(x32, y32) (((u64)x32 << 32) | y32)
+#define AND64H(x64) (x64 & 0xffFFffFF00000000ull)
+#define AND64L(x64) (x64 & 0x00000000ffFFffFFull)
+
+/* Computes result = product % curve_prime
+ * from "Mathematical routines for the NIST prime elliptic curves"
+ */
+static void vli_mmod_fast_384(u64 *result, const u64 *product,
+ const u64 *curve_prime, u64 *tmp)
+{
+ int carry;
+ const unsigned int ndigits = 6;
+
+ /* t */
+ vli_set(result, product, ndigits);
+
+ /* s1 */
+ tmp[0] = 0; // 0 || 0
+ tmp[1] = 0; // 0 || 0
+ tmp[2] = SL32OR32(product[11], (product[10]>>32)); //a22||a21
+ tmp[3] = product[11]>>32; // 0 ||a23
+ tmp[4] = 0; // 0 || 0
+ tmp[5] = 0; // 0 || 0
+ carry = vli_lshift(tmp, tmp, 1, ndigits);
+ carry += vli_add(result, result, tmp, ndigits);
+
+ /* s2 */
+ tmp[0] = product[6]; //a13||a12
+ tmp[1] = product[7]; //a15||a14
+ tmp[2] = product[8]; //a17||a16
+ tmp[3] = product[9]; //a19||a18
+ tmp[4] = product[10]; //a21||a20
+ tmp[5] = product[11]; //a23||a22
+ carry += vli_add(result, result, tmp, ndigits);
+
+ /* s3 */
+ tmp[0] = SL32OR32(product[11], (product[10]>>32)); //a22||a21
+ tmp[1] = SL32OR32(product[6], (product[11]>>32)); //a12||a23
+ tmp[2] = SL32OR32(product[7], (product[6])>>32); //a14||a13
+ tmp[3] = SL32OR32(product[8], (product[7]>>32)); //a16||a15
+ tmp[4] = SL32OR32(product[9], (product[8]>>32)); //a18||a17
+ tmp[5] = SL32OR32(product[10], (product[9]>>32)); //a20||a19
+ carry += vli_add(result, result, tmp, ndigits);
+
+ /* s4 */
+ tmp[0] = AND64H(product[11]); //a23|| 0
+ tmp[1] = (product[10]<<32); //a20|| 0
+ tmp[2] = product[6]; //a13||a12
+ tmp[3] = product[7]; //a15||a14
+ tmp[4] = product[8]; //a17||a16
+ tmp[5] = product[9]; //a19||a18
+ carry += vli_add(result, result, tmp, ndigits);
+
+ /* s5 */
+ tmp[0] = 0; // 0|| 0
+ tmp[1] = 0; // 0|| 0
+ tmp[2] = product[10]; //a21||a20
+ tmp[3] = product[11]; //a23||a22
+ tmp[4] = 0; // 0|| 0
+ tmp[5] = 0; // 0|| 0
+ carry += vli_add(result, result, tmp, ndigits);
+
+ /* s6 */
+ tmp[0] = AND64L(product[10]); // 0 ||a20
+ tmp[1] = AND64H(product[10]); //a21|| 0
+ tmp[2] = product[11]; //a23||a22
+ tmp[3] = 0; // 0 || 0
+ tmp[4] = 0; // 0 || 0
+ tmp[5] = 0; // 0 || 0
+ carry += vli_add(result, result, tmp, ndigits);
+
+ /* d1 */
+ tmp[0] = SL32OR32(product[6], (product[11]>>32)); //a12||a23
+ tmp[1] = SL32OR32(product[7], (product[6]>>32)); //a14||a13
+ tmp[2] = SL32OR32(product[8], (product[7]>>32)); //a16||a15
+ tmp[3] = SL32OR32(product[9], (product[8]>>32)); //a18||a17
+ tmp[4] = SL32OR32(product[10], (product[9]>>32)); //a20||a19
+ tmp[5] = SL32OR32(product[11], (product[10]>>32)); //a22||a21
+ carry -= vli_sub(result, result, tmp, ndigits);
+
+ /* d2 */
+ tmp[0] = (product[10]<<32); //a20|| 0
+ tmp[1] = SL32OR32(product[11], (product[10]>>32)); //a22||a21
+ tmp[2] = (product[11]>>32); // 0 ||a23
+ tmp[3] = 0; // 0 || 0
+ tmp[4] = 0; // 0 || 0
+ tmp[5] = 0; // 0 || 0
+ carry -= vli_sub(result, result, tmp, ndigits);
+
+ /* d3 */
+ tmp[0] = 0; // 0 || 0
+ tmp[1] = AND64H(product[11]); //a23|| 0
+ tmp[2] = product[11]>>32; // 0 ||a23
+ tmp[3] = 0; // 0 || 0
+ tmp[4] = 0; // 0 || 0
+ tmp[5] = 0; // 0 || 0
+ carry -= vli_sub(result, result, tmp, ndigits);
+
+ if (carry < 0) {
+ do {
+ carry += vli_add(result, result, curve_prime, ndigits);
+ } while (carry < 0);
+ } else {
+ while (carry || vli_cmp(curve_prime, result, ndigits) != 1)
+ carry -= vli_sub(result, result, curve_prime, ndigits);
+ }
+
+}
+
+#undef SL32OR32
+#undef AND64H
+#undef AND64L
+
/* Computes result = product % curve_prime for different curve_primes.
*
* Note that curve_primes are distinguished just by heuristic check and
* not by complete conformance check.
*/
static bool vli_mmod_fast(u64 *result, u64 *product,
- const u64 *curve_prime, unsigned int ndigits)
+ const struct ecc_curve *curve)
{
u64 tmp[2 * ECC_MAX_DIGITS];
+ const u64 *curve_prime = curve->p;
+ const unsigned int ndigits = curve->g.ndigits;
- /* Currently, both NIST primes have -1 in lowest qword. */
- if (curve_prime[0] != -1ull) {
+ /* All NIST curves have name prefix 'nist_' */
+ if (strncmp(curve->name, "nist_", 5) != 0) {
/* Try to handle Pseudo-Marsenne primes. */
if (curve_prime[ndigits - 1] == -1ull) {
vli_mmod_special(result, product, curve_prime,
case 4:
vli_mmod_fast_256(result, product, curve_prime, tmp);
break;
+ case 6:
+ vli_mmod_fast_384(result, product, curve_prime, tmp);
+ break;
default:
pr_err_ratelimited("ecc: unsupported digits size!\n");
return false;
/* Computes result = (left * right) % curve_prime. */
static void vli_mod_mult_fast(u64 *result, const u64 *left, const u64 *right,
- const u64 *curve_prime, unsigned int ndigits)
+ const struct ecc_curve *curve)
{
u64 product[2 * ECC_MAX_DIGITS];
- vli_mult(product, left, right, ndigits);
- vli_mmod_fast(result, product, curve_prime, ndigits);
+ vli_mult(product, left, right, curve->g.ndigits);
+ vli_mmod_fast(result, product, curve);
}
/* Computes result = left^2 % curve_prime. */
static void vli_mod_square_fast(u64 *result, const u64 *left,
- const u64 *curve_prime, unsigned int ndigits)
+ const struct ecc_curve *curve)
{
u64 product[2 * ECC_MAX_DIGITS];
- vli_square(product, left, ndigits);
- vli_mmod_fast(result, product, curve_prime, ndigits);
+ vli_square(product, left, curve->g.ndigits);
+ vli_mmod_fast(result, product, curve);
}
#define EVEN(vli) (!(vli[0] & 1))
/* Double in place */
static void ecc_point_double_jacobian(u64 *x1, u64 *y1, u64 *z1,
- u64 *curve_prime, unsigned int ndigits)
+ const struct ecc_curve *curve)
{
/* t1 = x, t2 = y, t3 = z */
u64 t4[ECC_MAX_DIGITS];
u64 t5[ECC_MAX_DIGITS];
+ const u64 *curve_prime = curve->p;
+ const unsigned int ndigits = curve->g.ndigits;
if (vli_is_zero(z1, ndigits))
return;
/* t4 = y1^2 */
- vli_mod_square_fast(t4, y1, curve_prime, ndigits);
+ vli_mod_square_fast(t4, y1, curve);
/* t5 = x1*y1^2 = A */
- vli_mod_mult_fast(t5, x1, t4, curve_prime, ndigits);
+ vli_mod_mult_fast(t5, x1, t4, curve);
/* t4 = y1^4 */
- vli_mod_square_fast(t4, t4, curve_prime, ndigits);
+ vli_mod_square_fast(t4, t4, curve);
/* t2 = y1*z1 = z3 */
- vli_mod_mult_fast(y1, y1, z1, curve_prime, ndigits);
+ vli_mod_mult_fast(y1, y1, z1, curve);
/* t3 = z1^2 */
- vli_mod_square_fast(z1, z1, curve_prime, ndigits);
+ vli_mod_square_fast(z1, z1, curve);
/* t1 = x1 + z1^2 */
vli_mod_add(x1, x1, z1, curve_prime, ndigits);
/* t3 = x1 - z1^2 */
vli_mod_sub(z1, x1, z1, curve_prime, ndigits);
/* t1 = x1^2 - z1^4 */
- vli_mod_mult_fast(x1, x1, z1, curve_prime, ndigits);
+ vli_mod_mult_fast(x1, x1, z1, curve);
/* t3 = 2*(x1^2 - z1^4) */
vli_mod_add(z1, x1, x1, curve_prime, ndigits);
/* t1 = 3/2*(x1^2 - z1^4) = B */
/* t3 = B^2 */
- vli_mod_square_fast(z1, x1, curve_prime, ndigits);
+ vli_mod_square_fast(z1, x1, curve);
/* t3 = B^2 - A */
vli_mod_sub(z1, z1, t5, curve_prime, ndigits);
/* t3 = B^2 - 2A = x3 */
/* t5 = A - x3 */
vli_mod_sub(t5, t5, z1, curve_prime, ndigits);
/* t1 = B * (A - x3) */
- vli_mod_mult_fast(x1, x1, t5, curve_prime, ndigits);
+ vli_mod_mult_fast(x1, x1, t5, curve);
/* t4 = B * (A - x3) - y1^4 = y3 */
vli_mod_sub(t4, x1, t4, curve_prime, ndigits);
}
/* Modify (x1, y1) => (x1 * z^2, y1 * z^3) */
-static void apply_z(u64 *x1, u64 *y1, u64 *z, u64 *curve_prime,
- unsigned int ndigits)
+static void apply_z(u64 *x1, u64 *y1, u64 *z, const struct ecc_curve *curve)
{
u64 t1[ECC_MAX_DIGITS];
- vli_mod_square_fast(t1, z, curve_prime, ndigits); /* z^2 */
- vli_mod_mult_fast(x1, x1, t1, curve_prime, ndigits); /* x1 * z^2 */
- vli_mod_mult_fast(t1, t1, z, curve_prime, ndigits); /* z^3 */
- vli_mod_mult_fast(y1, y1, t1, curve_prime, ndigits); /* y1 * z^3 */
+ vli_mod_square_fast(t1, z, curve); /* z^2 */
+ vli_mod_mult_fast(x1, x1, t1, curve); /* x1 * z^2 */
+ vli_mod_mult_fast(t1, t1, z, curve); /* z^3 */
+ vli_mod_mult_fast(y1, y1, t1, curve); /* y1 * z^3 */
}
/* P = (x1, y1) => 2P, (x2, y2) => P' */
static void xycz_initial_double(u64 *x1, u64 *y1, u64 *x2, u64 *y2,
- u64 *p_initial_z, u64 *curve_prime,
- unsigned int ndigits)
+ u64 *p_initial_z, const struct ecc_curve *curve)
{
u64 z[ECC_MAX_DIGITS];
+ const unsigned int ndigits = curve->g.ndigits;
vli_set(x2, x1, ndigits);
vli_set(y2, y1, ndigits);
if (p_initial_z)
vli_set(z, p_initial_z, ndigits);
- apply_z(x1, y1, z, curve_prime, ndigits);
+ apply_z(x1, y1, z, curve);
- ecc_point_double_jacobian(x1, y1, z, curve_prime, ndigits);
+ ecc_point_double_jacobian(x1, y1, z, curve);
- apply_z(x2, y2, z, curve_prime, ndigits);
+ apply_z(x2, y2, z, curve);
}
/* Input P = (x1, y1, Z), Q = (x2, y2, Z)
* Output P' = (x1', y1', Z3), P + Q = (x3, y3, Z3)
* or P => P', Q => P + Q
*/
-static void xycz_add(u64 *x1, u64 *y1, u64 *x2, u64 *y2, u64 *curve_prime,
- unsigned int ndigits)
+static void xycz_add(u64 *x1, u64 *y1, u64 *x2, u64 *y2,
+ const struct ecc_curve *curve)
{
/* t1 = X1, t2 = Y1, t3 = X2, t4 = Y2 */
u64 t5[ECC_MAX_DIGITS];
+ const u64 *curve_prime = curve->p;
+ const unsigned int ndigits = curve->g.ndigits;
/* t5 = x2 - x1 */
vli_mod_sub(t5, x2, x1, curve_prime, ndigits);
/* t5 = (x2 - x1)^2 = A */
- vli_mod_square_fast(t5, t5, curve_prime, ndigits);
+ vli_mod_square_fast(t5, t5, curve);
/* t1 = x1*A = B */
- vli_mod_mult_fast(x1, x1, t5, curve_prime, ndigits);
+ vli_mod_mult_fast(x1, x1, t5, curve);
/* t3 = x2*A = C */
- vli_mod_mult_fast(x2, x2, t5, curve_prime, ndigits);
+ vli_mod_mult_fast(x2, x2, t5, curve);
/* t4 = y2 - y1 */
vli_mod_sub(y2, y2, y1, curve_prime, ndigits);
/* t5 = (y2 - y1)^2 = D */
- vli_mod_square_fast(t5, y2, curve_prime, ndigits);
+ vli_mod_square_fast(t5, y2, curve);
/* t5 = D - B */
vli_mod_sub(t5, t5, x1, curve_prime, ndigits);
/* t3 = C - B */
vli_mod_sub(x2, x2, x1, curve_prime, ndigits);
/* t2 = y1*(C - B) */
- vli_mod_mult_fast(y1, y1, x2, curve_prime, ndigits);
+ vli_mod_mult_fast(y1, y1, x2, curve);
/* t3 = B - x3 */
vli_mod_sub(x2, x1, t5, curve_prime, ndigits);
/* t4 = (y2 - y1)*(B - x3) */
- vli_mod_mult_fast(y2, y2, x2, curve_prime, ndigits);
+ vli_mod_mult_fast(y2, y2, x2, curve);
/* t4 = y3 */
vli_mod_sub(y2, y2, y1, curve_prime, ndigits);
* Output P + Q = (x3, y3, Z3), P - Q = (x3', y3', Z3)
* or P => P - Q, Q => P + Q
*/
-static void xycz_add_c(u64 *x1, u64 *y1, u64 *x2, u64 *y2, u64 *curve_prime,
- unsigned int ndigits)
+static void xycz_add_c(u64 *x1, u64 *y1, u64 *x2, u64 *y2,
+ const struct ecc_curve *curve)
{
/* t1 = X1, t2 = Y1, t3 = X2, t4 = Y2 */
u64 t5[ECC_MAX_DIGITS];
u64 t6[ECC_MAX_DIGITS];
u64 t7[ECC_MAX_DIGITS];
+ const u64 *curve_prime = curve->p;
+ const unsigned int ndigits = curve->g.ndigits;
/* t5 = x2 - x1 */
vli_mod_sub(t5, x2, x1, curve_prime, ndigits);
/* t5 = (x2 - x1)^2 = A */
- vli_mod_square_fast(t5, t5, curve_prime, ndigits);
+ vli_mod_square_fast(t5, t5, curve);
/* t1 = x1*A = B */
- vli_mod_mult_fast(x1, x1, t5, curve_prime, ndigits);
+ vli_mod_mult_fast(x1, x1, t5, curve);
/* t3 = x2*A = C */
- vli_mod_mult_fast(x2, x2, t5, curve_prime, ndigits);
+ vli_mod_mult_fast(x2, x2, t5, curve);
/* t4 = y2 + y1 */
vli_mod_add(t5, y2, y1, curve_prime, ndigits);
/* t4 = y2 - y1 */
/* t6 = C - B */
vli_mod_sub(t6, x2, x1, curve_prime, ndigits);
/* t2 = y1 * (C - B) */
- vli_mod_mult_fast(y1, y1, t6, curve_prime, ndigits);
+ vli_mod_mult_fast(y1, y1, t6, curve);
/* t6 = B + C */
vli_mod_add(t6, x1, x2, curve_prime, ndigits);
/* t3 = (y2 - y1)^2 */
- vli_mod_square_fast(x2, y2, curve_prime, ndigits);
+ vli_mod_square_fast(x2, y2, curve);
/* t3 = x3 */
vli_mod_sub(x2, x2, t6, curve_prime, ndigits);
/* t7 = B - x3 */
vli_mod_sub(t7, x1, x2, curve_prime, ndigits);
/* t4 = (y2 - y1)*(B - x3) */
- vli_mod_mult_fast(y2, y2, t7, curve_prime, ndigits);
+ vli_mod_mult_fast(y2, y2, t7, curve);
/* t4 = y3 */
vli_mod_sub(y2, y2, y1, curve_prime, ndigits);
/* t7 = (y2 + y1)^2 = F */
- vli_mod_square_fast(t7, t5, curve_prime, ndigits);
+ vli_mod_square_fast(t7, t5, curve);
/* t7 = x3' */
vli_mod_sub(t7, t7, t6, curve_prime, ndigits);
/* t6 = x3' - B */
vli_mod_sub(t6, t7, x1, curve_prime, ndigits);
/* t6 = (y2 + y1)*(x3' - B) */
- vli_mod_mult_fast(t6, t6, t5, curve_prime, ndigits);
+ vli_mod_mult_fast(t6, t6, t5, curve);
/* t2 = y3' */
vli_mod_sub(y1, t6, y1, curve_prime, ndigits);
vli_set(rx[1], point->x, ndigits);
vli_set(ry[1], point->y, ndigits);
- xycz_initial_double(rx[1], ry[1], rx[0], ry[0], initial_z, curve_prime,
- ndigits);
+ xycz_initial_double(rx[1], ry[1], rx[0], ry[0], initial_z, curve);
for (i = num_bits - 2; i > 0; i--) {
nb = !vli_test_bit(scalar, i);
- xycz_add_c(rx[1 - nb], ry[1 - nb], rx[nb], ry[nb], curve_prime,
- ndigits);
- xycz_add(rx[nb], ry[nb], rx[1 - nb], ry[1 - nb], curve_prime,
- ndigits);
+ xycz_add_c(rx[1 - nb], ry[1 - nb], rx[nb], ry[nb], curve);
+ xycz_add(rx[nb], ry[nb], rx[1 - nb], ry[1 - nb], curve);
}
nb = !vli_test_bit(scalar, 0);
- xycz_add_c(rx[1 - nb], ry[1 - nb], rx[nb], ry[nb], curve_prime,
- ndigits);
+ xycz_add_c(rx[1 - nb], ry[1 - nb], rx[nb], ry[nb], curve);
/* Find final 1/Z value. */
/* X1 - X0 */
vli_mod_sub(z, rx[1], rx[0], curve_prime, ndigits);
/* Yb * (X1 - X0) */
- vli_mod_mult_fast(z, z, ry[1 - nb], curve_prime, ndigits);
+ vli_mod_mult_fast(z, z, ry[1 - nb], curve);
/* xP * Yb * (X1 - X0) */
- vli_mod_mult_fast(z, z, point->x, curve_prime, ndigits);
+ vli_mod_mult_fast(z, z, point->x, curve);
/* 1 / (xP * Yb * (X1 - X0)) */
vli_mod_inv(z, z, curve_prime, point->ndigits);
/* yP / (xP * Yb * (X1 - X0)) */
- vli_mod_mult_fast(z, z, point->y, curve_prime, ndigits);
+ vli_mod_mult_fast(z, z, point->y, curve);
/* Xb * yP / (xP * Yb * (X1 - X0)) */
- vli_mod_mult_fast(z, z, rx[1 - nb], curve_prime, ndigits);
+ vli_mod_mult_fast(z, z, rx[1 - nb], curve);
/* End 1/Z calculation */
- xycz_add(rx[nb], ry[nb], rx[1 - nb], ry[1 - nb], curve_prime, ndigits);
+ xycz_add(rx[nb], ry[nb], rx[1 - nb], ry[1 - nb], curve);
- apply_z(rx[0], ry[0], z, curve_prime, ndigits);
+ apply_z(rx[0], ry[0], z, curve);
vli_set(result->x, rx[0], ndigits);
vli_set(result->y, ry[0], ndigits);
vli_mod_sub(z, result->x, p->x, curve->p, ndigits);
vli_set(px, p->x, ndigits);
vli_set(py, p->y, ndigits);
- xycz_add(px, py, result->x, result->y, curve->p, ndigits);
+ xycz_add(px, py, result->x, result->y, curve);
vli_mod_inv(z, z, curve->p, ndigits);
- apply_z(result->x, result->y, z, curve->p, ndigits);
+ apply_z(result->x, result->y, z, curve);
}
/* Computes R = u1P + u2Q mod p using Shamir's trick.
points[2] = q;
points[3] = ∑
- num_bits = max(vli_num_bits(u1, ndigits),
- vli_num_bits(u2, ndigits));
+ num_bits = max(vli_num_bits(u1, ndigits), vli_num_bits(u2, ndigits));
i = num_bits - 1;
idx = (!!vli_test_bit(u1, i)) | ((!!vli_test_bit(u2, i)) << 1);
point = points[idx];
z[0] = 1;
for (--i; i >= 0; i--) {
- ecc_point_double_jacobian(rx, ry, z, curve->p, ndigits);
+ ecc_point_double_jacobian(rx, ry, z, curve);
idx = (!!vli_test_bit(u1, i)) | ((!!vli_test_bit(u2, i)) << 1);
point = points[idx];
if (point) {
vli_set(tx, point->x, ndigits);
vli_set(ty, point->y, ndigits);
- apply_z(tx, ty, z, curve->p, ndigits);
+ apply_z(tx, ty, z, curve);
vli_mod_sub(tz, rx, tx, curve->p, ndigits);
- xycz_add(tx, ty, rx, ry, curve->p, ndigits);
- vli_mod_mult_fast(z, z, tz, curve->p, ndigits);
+ xycz_add(tx, ty, rx, ry, curve);
+ vli_mod_mult_fast(z, z, tz, curve);
}
}
vli_mod_inv(z, z, curve->p, ndigits);
- apply_z(rx, ry, z, curve->p, ndigits);
+ apply_z(rx, ry, z, curve);
}
EXPORT_SYMBOL(ecc_point_mult_shamir);
-static inline void ecc_swap_digits(const u64 *in, u64 *out,
- unsigned int ndigits)
-{
- const __be64 *src = (__force __be64 *)in;
- int i;
-
- for (i = 0; i < ndigits; i++)
- out[i] = be64_to_cpu(src[ndigits - 1 - i]);
-}
-
static int __ecc_is_key_valid(const struct ecc_curve *curve,
const u64 *private_key, unsigned int ndigits)
{
return -EINVAL;
/* Check 3: Verify that y^2 == (x^3 + a·x + b) mod p */
- vli_mod_square_fast(yy, pk->y, curve->p, pk->ndigits); /* y^2 */
- vli_mod_square_fast(xxx, pk->x, curve->p, pk->ndigits); /* x^2 */
- vli_mod_mult_fast(xxx, xxx, pk->x, curve->p, pk->ndigits); /* x^3 */
- vli_mod_mult_fast(w, curve->a, pk->x, curve->p, pk->ndigits); /* a·x */
+ vli_mod_square_fast(yy, pk->y, curve); /* y^2 */
+ vli_mod_square_fast(xxx, pk->x, curve); /* x^2 */
+ vli_mod_mult_fast(xxx, xxx, pk->x, curve); /* x^3 */
+ vli_mod_mult_fast(w, curve->a, pk->x, curve); /* a·x */
vli_mod_add(w, w, curve->b, curve->p, pk->ndigits); /* a·x + b */
vli_mod_add(w, w, xxx, curve->p, pk->ndigits); /* x^3 + a·x + b */
if (vli_cmp(yy, w, pk->ndigits) != 0) /* Equation */
#ifndef _CRYPTO_ECC_H
#define _CRYPTO_ECC_H
+#include <crypto/ecc_curve.h>
+
/* One digit is u64 qword. */
#define ECC_CURVE_NIST_P192_DIGITS 3
#define ECC_CURVE_NIST_P256_DIGITS 4
-#define ECC_MAX_DIGITS (512 / 64)
+#define ECC_CURVE_NIST_P384_DIGITS 6
+#define ECC_MAX_DIGITS (512 / 64) /* due to ecrdsa */
#define ECC_DIGITS_TO_BYTES_SHIFT 3
-/**
- * struct ecc_point - elliptic curve point in affine coordinates
- *
- * @x: X coordinate in vli form.
- * @y: Y coordinate in vli form.
- * @ndigits: Length of vlis in u64 qwords.
- */
-struct ecc_point {
- u64 *x;
- u64 *y;
- u8 ndigits;
-};
+#define ECC_MAX_BYTES (ECC_MAX_DIGITS << ECC_DIGITS_TO_BYTES_SHIFT)
#define ECC_POINT_INIT(x, y, ndigits) (struct ecc_point) { x, y, ndigits }
/**
- * struct ecc_curve - definition of elliptic curve
- *
- * @name: Short name of the curve.
- * @g: Generator point of the curve.
- * @p: Prime number, if Barrett's reduction is used for this curve
- * pre-calculated value 'mu' is appended to the @p after ndigits.
- * Use of Barrett's reduction is heuristically determined in
- * vli_mmod_fast().
- * @n: Order of the curve group.
- * @a: Curve parameter a.
- * @b: Curve parameter b.
+ * ecc_swap_digits() - Copy ndigits from big endian array to native array
+ * @in: Input array
+ * @out: Output array
+ * @ndigits: Number of digits to copy
*/
-struct ecc_curve {
- char *name;
- struct ecc_point g;
- u64 *p;
- u64 *n;
- u64 *a;
- u64 *b;
-};
+static inline void ecc_swap_digits(const u64 *in, u64 *out, unsigned int ndigits)
+{
+ const __be64 *src = (__force __be64 *)in;
+ int i;
+
+ for (i = 0; i < ndigits; i++)
+ out[i] = be64_to_cpu(src[ndigits - 1 - i]);
+}
/**
* ecc_is_key_valid() - Validate a given ECDH private key
.b = nist_p256_b
};
+/* NIST P-384 */
+static u64 nist_p384_g_x[] = { 0x3A545E3872760AB7ull, 0x5502F25DBF55296Cull,
+ 0x59F741E082542A38ull, 0x6E1D3B628BA79B98ull,
+ 0x8Eb1C71EF320AD74ull, 0xAA87CA22BE8B0537ull };
+static u64 nist_p384_g_y[] = { 0x7A431D7C90EA0E5Full, 0x0A60B1CE1D7E819Dull,
+ 0xE9DA3113B5F0B8C0ull, 0xF8F41DBD289A147Cull,
+ 0x5D9E98BF9292DC29ull, 0x3617DE4A96262C6Full };
+static u64 nist_p384_p[] = { 0x00000000FFFFFFFFull, 0xFFFFFFFF00000000ull,
+ 0xFFFFFFFFFFFFFFFEull, 0xFFFFFFFFFFFFFFFFull,
+ 0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFFFFFFFFFFull };
+static u64 nist_p384_n[] = { 0xECEC196ACCC52973ull, 0x581A0DB248B0A77Aull,
+ 0xC7634D81F4372DDFull, 0xFFFFFFFFFFFFFFFFull,
+ 0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFFFFFFFFFFull };
+static u64 nist_p384_a[] = { 0x00000000FFFFFFFCull, 0xFFFFFFFF00000000ull,
+ 0xFFFFFFFFFFFFFFFEull, 0xFFFFFFFFFFFFFFFFull,
+ 0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFFFFFFFFFFull };
+static u64 nist_p384_b[] = { 0x2a85c8edd3ec2aefull, 0xc656398d8a2ed19dull,
+ 0x0314088f5013875aull, 0x181d9c6efe814112ull,
+ 0x988e056be3f82d19ull, 0xb3312fa7e23ee7e4ull };
+static struct ecc_curve nist_p384 = {
+ .name = "nist_384",
+ .g = {
+ .x = nist_p384_g_x,
+ .y = nist_p384_g_y,
+ .ndigits = 6,
+ },
+ .p = nist_p384_p,
+ .n = nist_p384_n,
+ .a = nist_p384_a,
+ .b = nist_p384_b
+};
+
+/* curve25519 */
+static u64 curve25519_g_x[] = { 0x0000000000000009, 0x0000000000000000,
+ 0x0000000000000000, 0x0000000000000000 };
+static u64 curve25519_p[] = { 0xffffffffffffffed, 0xffffffffffffffff,
+ 0xffffffffffffffff, 0x7fffffffffffffff };
+static u64 curve25519_a[] = { 0x000000000001DB41, 0x0000000000000000,
+ 0x0000000000000000, 0x0000000000000000 };
+static const struct ecc_curve ecc_25519 = {
+ .name = "curve25519",
+ .g = {
+ .x = curve25519_g_x,
+ .ndigits = 4,
+ },
+ .p = curve25519_p,
+ .a = curve25519_a,
+};
+
#endif
return kpp_tfm_ctx(tfm);
}
-static unsigned int ecdh_supported_curve(unsigned int curve_id)
-{
- switch (curve_id) {
- case ECC_CURVE_NIST_P192: return ECC_CURVE_NIST_P192_DIGITS;
- case ECC_CURVE_NIST_P256: return ECC_CURVE_NIST_P256_DIGITS;
- default: return 0;
- }
-}
-
static int ecdh_set_secret(struct crypto_kpp *tfm, const void *buf,
unsigned int len)
{
struct ecdh_ctx *ctx = ecdh_get_ctx(tfm);
struct ecdh params;
- unsigned int ndigits;
if (crypto_ecdh_decode_key(buf, len, ¶ms) < 0 ||
- params.key_size > sizeof(ctx->private_key))
+ params.key_size > sizeof(u64) * ctx->ndigits)
return -EINVAL;
- ndigits = ecdh_supported_curve(params.curve_id);
- if (!ndigits)
- return -EINVAL;
-
- ctx->curve_id = params.curve_id;
- ctx->ndigits = ndigits;
-
if (!params.key || !params.key_size)
return ecc_gen_privkey(ctx->curve_id, ctx->ndigits,
ctx->private_key);
return ctx->ndigits << (ECC_DIGITS_TO_BYTES_SHIFT + 1);
}
-static struct kpp_alg ecdh = {
+static int ecdh_nist_p192_init_tfm(struct crypto_kpp *tfm)
+{
+ struct ecdh_ctx *ctx = ecdh_get_ctx(tfm);
+
+ ctx->curve_id = ECC_CURVE_NIST_P192;
+ ctx->ndigits = ECC_CURVE_NIST_P192_DIGITS;
+
+ return 0;
+}
+
+static struct kpp_alg ecdh_nist_p192 = {
.set_secret = ecdh_set_secret,
.generate_public_key = ecdh_compute_value,
.compute_shared_secret = ecdh_compute_value,
.max_size = ecdh_max_size,
+ .init = ecdh_nist_p192_init_tfm,
.base = {
- .cra_name = "ecdh",
+ .cra_name = "ecdh-nist-p192",
.cra_driver_name = "ecdh-generic",
.cra_priority = 100,
.cra_module = THIS_MODULE,
},
};
+static int ecdh_nist_p256_init_tfm(struct crypto_kpp *tfm)
+{
+ struct ecdh_ctx *ctx = ecdh_get_ctx(tfm);
+
+ ctx->curve_id = ECC_CURVE_NIST_P256;
+ ctx->ndigits = ECC_CURVE_NIST_P256_DIGITS;
+
+ return 0;
+}
+
+static struct kpp_alg ecdh_nist_p256 = {
+ .set_secret = ecdh_set_secret,
+ .generate_public_key = ecdh_compute_value,
+ .compute_shared_secret = ecdh_compute_value,
+ .max_size = ecdh_max_size,
+ .init = ecdh_nist_p256_init_tfm,
+ .base = {
+ .cra_name = "ecdh-nist-p256",
+ .cra_driver_name = "ecdh-generic",
+ .cra_priority = 100,
+ .cra_module = THIS_MODULE,
+ .cra_ctxsize = sizeof(struct ecdh_ctx),
+ },
+};
+
+static bool ecdh_nist_p192_registered;
+
static int ecdh_init(void)
{
- return crypto_register_kpp(&ecdh);
+ int ret;
+
+ ret = crypto_register_kpp(&ecdh_nist_p192);
+ ecdh_nist_p192_registered = ret == 0;
+
+ return crypto_register_kpp(&ecdh_nist_p256);
}
static void ecdh_exit(void)
{
- crypto_unregister_kpp(&ecdh);
+ if (ecdh_nist_p192_registered)
+ crypto_unregister_kpp(&ecdh_nist_p192);
+ crypto_unregister_kpp(&ecdh_nist_p256);
}
subsys_initcall(ecdh_init);
#include <crypto/ecdh.h>
#include <crypto/kpp.h>
-#define ECDH_KPP_SECRET_MIN_SIZE (sizeof(struct kpp_secret) + 2 * sizeof(short))
+#define ECDH_KPP_SECRET_MIN_SIZE (sizeof(struct kpp_secret) + sizeof(short))
static inline u8 *ecdh_pack_data(void *dst, const void *src, size_t sz)
{
return -EINVAL;
ptr = ecdh_pack_data(ptr, &secret, sizeof(secret));
- ptr = ecdh_pack_data(ptr, ¶ms->curve_id, sizeof(params->curve_id));
ptr = ecdh_pack_data(ptr, ¶ms->key_size, sizeof(params->key_size));
ecdh_pack_data(ptr, params->key, params->key_size);
if (unlikely(len < secret.len))
return -EINVAL;
- ptr = ecdh_unpack_data(¶ms->curve_id, ptr, sizeof(params->curve_id));
ptr = ecdh_unpack_data(¶ms->key_size, ptr, sizeof(params->key_size));
if (secret.len != crypto_ecdh_key_len(params))
return -EINVAL;
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (c) 2021 IBM Corporation
+ */
+
+#include <linux/module.h>
+#include <crypto/internal/akcipher.h>
+#include <crypto/akcipher.h>
+#include <crypto/ecdh.h>
+#include <linux/asn1_decoder.h>
+#include <linux/scatterlist.h>
+
+#include "ecc.h"
+#include "ecdsasignature.asn1.h"
+
+struct ecc_ctx {
+ unsigned int curve_id;
+ const struct ecc_curve *curve;
+
+ bool pub_key_set;
+ u64 x[ECC_MAX_DIGITS]; /* pub key x and y coordinates */
+ u64 y[ECC_MAX_DIGITS];
+ struct ecc_point pub_key;
+};
+
+struct ecdsa_signature_ctx {
+ const struct ecc_curve *curve;
+ u64 r[ECC_MAX_DIGITS];
+ u64 s[ECC_MAX_DIGITS];
+};
+
+/*
+ * Get the r and s components of a signature from the X509 certificate.
+ */
+static int ecdsa_get_signature_rs(u64 *dest, size_t hdrlen, unsigned char tag,
+ const void *value, size_t vlen, unsigned int ndigits)
+{
+ size_t keylen = ndigits * sizeof(u64);
+ ssize_t diff = vlen - keylen;
+ const char *d = value;
+ u8 rs[ECC_MAX_BYTES];
+
+ if (!value || !vlen)
+ return -EINVAL;
+
+ /* diff = 0: 'value' has exacly the right size
+ * diff > 0: 'value' has too many bytes; one leading zero is allowed that
+ * makes the value a positive integer; error on more
+ * diff < 0: 'value' is missing leading zeros, which we add
+ */
+ if (diff > 0) {
+ /* skip over leading zeros that make 'value' a positive int */
+ if (*d == 0) {
+ vlen -= 1;
+ diff--;
+ d++;
+ }
+ if (diff)
+ return -EINVAL;
+ }
+ if (-diff >= keylen)
+ return -EINVAL;
+
+ if (diff) {
+ /* leading zeros not given in 'value' */
+ memset(rs, 0, -diff);
+ }
+
+ memcpy(&rs[-diff], d, vlen);
+
+ ecc_swap_digits((u64 *)rs, dest, ndigits);
+
+ return 0;
+}
+
+int ecdsa_get_signature_r(void *context, size_t hdrlen, unsigned char tag,
+ const void *value, size_t vlen)
+{
+ struct ecdsa_signature_ctx *sig = context;
+
+ return ecdsa_get_signature_rs(sig->r, hdrlen, tag, value, vlen,
+ sig->curve->g.ndigits);
+}
+
+int ecdsa_get_signature_s(void *context, size_t hdrlen, unsigned char tag,
+ const void *value, size_t vlen)
+{
+ struct ecdsa_signature_ctx *sig = context;
+
+ return ecdsa_get_signature_rs(sig->s, hdrlen, tag, value, vlen,
+ sig->curve->g.ndigits);
+}
+
+static int _ecdsa_verify(struct ecc_ctx *ctx, const u64 *hash, const u64 *r, const u64 *s)
+{
+ const struct ecc_curve *curve = ctx->curve;
+ unsigned int ndigits = curve->g.ndigits;
+ u64 s1[ECC_MAX_DIGITS];
+ u64 u1[ECC_MAX_DIGITS];
+ u64 u2[ECC_MAX_DIGITS];
+ u64 x1[ECC_MAX_DIGITS];
+ u64 y1[ECC_MAX_DIGITS];
+ struct ecc_point res = ECC_POINT_INIT(x1, y1, ndigits);
+
+ /* 0 < r < n and 0 < s < n */
+ if (vli_is_zero(r, ndigits) || vli_cmp(r, curve->n, ndigits) >= 0 ||
+ vli_is_zero(s, ndigits) || vli_cmp(s, curve->n, ndigits) >= 0)
+ return -EBADMSG;
+
+ /* hash is given */
+ pr_devel("hash : %016llx %016llx ... %016llx\n",
+ hash[ndigits - 1], hash[ndigits - 2], hash[0]);
+
+ /* s1 = (s^-1) mod n */
+ vli_mod_inv(s1, s, curve->n, ndigits);
+ /* u1 = (hash * s1) mod n */
+ vli_mod_mult_slow(u1, hash, s1, curve->n, ndigits);
+ /* u2 = (r * s1) mod n */
+ vli_mod_mult_slow(u2, r, s1, curve->n, ndigits);
+ /* res = u1*G + u2 * pub_key */
+ ecc_point_mult_shamir(&res, u1, &curve->g, u2, &ctx->pub_key, curve);
+
+ /* res.x = res.x mod n (if res.x > order) */
+ if (unlikely(vli_cmp(res.x, curve->n, ndigits) == 1))
+ /* faster alternative for NIST p384, p256 & p192 */
+ vli_sub(res.x, res.x, curve->n, ndigits);
+
+ if (!vli_cmp(res.x, r, ndigits))
+ return 0;
+
+ return -EKEYREJECTED;
+}
+
+/*
+ * Verify an ECDSA signature.
+ */
+static int ecdsa_verify(struct akcipher_request *req)
+{
+ struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+ struct ecc_ctx *ctx = akcipher_tfm_ctx(tfm);
+ size_t keylen = ctx->curve->g.ndigits * sizeof(u64);
+ struct ecdsa_signature_ctx sig_ctx = {
+ .curve = ctx->curve,
+ };
+ u8 rawhash[ECC_MAX_BYTES];
+ u64 hash[ECC_MAX_DIGITS];
+ unsigned char *buffer;
+ ssize_t diff;
+ int ret;
+
+ if (unlikely(!ctx->pub_key_set))
+ return -EINVAL;
+
+ buffer = kmalloc(req->src_len + req->dst_len, GFP_KERNEL);
+ if (!buffer)
+ return -ENOMEM;
+
+ sg_pcopy_to_buffer(req->src,
+ sg_nents_for_len(req->src, req->src_len + req->dst_len),
+ buffer, req->src_len + req->dst_len, 0);
+
+ ret = asn1_ber_decoder(&ecdsasignature_decoder, &sig_ctx,
+ buffer, req->src_len);
+ if (ret < 0)
+ goto error;
+
+ /* if the hash is shorter then we will add leading zeros to fit to ndigits */
+ diff = keylen - req->dst_len;
+ if (diff >= 0) {
+ if (diff)
+ memset(rawhash, 0, diff);
+ memcpy(&rawhash[diff], buffer + req->src_len, req->dst_len);
+ } else if (diff < 0) {
+ /* given hash is longer, we take the left-most bytes */
+ memcpy(&rawhash, buffer + req->src_len, keylen);
+ }
+
+ ecc_swap_digits((u64 *)rawhash, hash, ctx->curve->g.ndigits);
+
+ ret = _ecdsa_verify(ctx, hash, sig_ctx.r, sig_ctx.s);
+
+error:
+ kfree(buffer);
+
+ return ret;
+}
+
+static int ecdsa_ecc_ctx_init(struct ecc_ctx *ctx, unsigned int curve_id)
+{
+ ctx->curve_id = curve_id;
+ ctx->curve = ecc_get_curve(curve_id);
+ if (!ctx->curve)
+ return -EINVAL;
+
+ return 0;
+}
+
+
+static void ecdsa_ecc_ctx_deinit(struct ecc_ctx *ctx)
+{
+ ctx->pub_key_set = false;
+}
+
+static int ecdsa_ecc_ctx_reset(struct ecc_ctx *ctx)
+{
+ unsigned int curve_id = ctx->curve_id;
+ int ret;
+
+ ecdsa_ecc_ctx_deinit(ctx);
+ ret = ecdsa_ecc_ctx_init(ctx, curve_id);
+ if (ret == 0)
+ ctx->pub_key = ECC_POINT_INIT(ctx->x, ctx->y,
+ ctx->curve->g.ndigits);
+ return ret;
+}
+
+/*
+ * Set the public key given the raw uncompressed key data from an X509
+ * certificate. The key data contain the concatenated X and Y coordinates of
+ * the public key.
+ */
+static int ecdsa_set_pub_key(struct crypto_akcipher *tfm, const void *key, unsigned int keylen)
+{
+ struct ecc_ctx *ctx = akcipher_tfm_ctx(tfm);
+ const unsigned char *d = key;
+ const u64 *digits = (const u64 *)&d[1];
+ unsigned int ndigits;
+ int ret;
+
+ ret = ecdsa_ecc_ctx_reset(ctx);
+ if (ret < 0)
+ return ret;
+
+ if (keylen < 1 || (((keylen - 1) >> 1) % sizeof(u64)) != 0)
+ return -EINVAL;
+ /* we only accept uncompressed format indicated by '4' */
+ if (d[0] != 4)
+ return -EINVAL;
+
+ keylen--;
+ ndigits = (keylen >> 1) / sizeof(u64);
+ if (ndigits != ctx->curve->g.ndigits)
+ return -EINVAL;
+
+ ecc_swap_digits(digits, ctx->pub_key.x, ndigits);
+ ecc_swap_digits(&digits[ndigits], ctx->pub_key.y, ndigits);
+ ret = ecc_is_pubkey_valid_full(ctx->curve, &ctx->pub_key);
+
+ ctx->pub_key_set = ret == 0;
+
+ return ret;
+}
+
+static void ecdsa_exit_tfm(struct crypto_akcipher *tfm)
+{
+ struct ecc_ctx *ctx = akcipher_tfm_ctx(tfm);
+
+ ecdsa_ecc_ctx_deinit(ctx);
+}
+
+static unsigned int ecdsa_max_size(struct crypto_akcipher *tfm)
+{
+ struct ecc_ctx *ctx = akcipher_tfm_ctx(tfm);
+
+ return ctx->pub_key.ndigits << ECC_DIGITS_TO_BYTES_SHIFT;
+}
+
+static int ecdsa_nist_p384_init_tfm(struct crypto_akcipher *tfm)
+{
+ struct ecc_ctx *ctx = akcipher_tfm_ctx(tfm);
+
+ return ecdsa_ecc_ctx_init(ctx, ECC_CURVE_NIST_P384);
+}
+
+static struct akcipher_alg ecdsa_nist_p384 = {
+ .verify = ecdsa_verify,
+ .set_pub_key = ecdsa_set_pub_key,
+ .max_size = ecdsa_max_size,
+ .init = ecdsa_nist_p384_init_tfm,
+ .exit = ecdsa_exit_tfm,
+ .base = {
+ .cra_name = "ecdsa-nist-p384",
+ .cra_driver_name = "ecdsa-nist-p384-generic",
+ .cra_priority = 100,
+ .cra_module = THIS_MODULE,
+ .cra_ctxsize = sizeof(struct ecc_ctx),
+ },
+};
+
+static int ecdsa_nist_p256_init_tfm(struct crypto_akcipher *tfm)
+{
+ struct ecc_ctx *ctx = akcipher_tfm_ctx(tfm);
+
+ return ecdsa_ecc_ctx_init(ctx, ECC_CURVE_NIST_P256);
+}
+
+static struct akcipher_alg ecdsa_nist_p256 = {
+ .verify = ecdsa_verify,
+ .set_pub_key = ecdsa_set_pub_key,
+ .max_size = ecdsa_max_size,
+ .init = ecdsa_nist_p256_init_tfm,
+ .exit = ecdsa_exit_tfm,
+ .base = {
+ .cra_name = "ecdsa-nist-p256",
+ .cra_driver_name = "ecdsa-nist-p256-generic",
+ .cra_priority = 100,
+ .cra_module = THIS_MODULE,
+ .cra_ctxsize = sizeof(struct ecc_ctx),
+ },
+};
+
+static int ecdsa_nist_p192_init_tfm(struct crypto_akcipher *tfm)
+{
+ struct ecc_ctx *ctx = akcipher_tfm_ctx(tfm);
+
+ return ecdsa_ecc_ctx_init(ctx, ECC_CURVE_NIST_P192);
+}
+
+static struct akcipher_alg ecdsa_nist_p192 = {
+ .verify = ecdsa_verify,
+ .set_pub_key = ecdsa_set_pub_key,
+ .max_size = ecdsa_max_size,
+ .init = ecdsa_nist_p192_init_tfm,
+ .exit = ecdsa_exit_tfm,
+ .base = {
+ .cra_name = "ecdsa-nist-p192",
+ .cra_driver_name = "ecdsa-nist-p192-generic",
+ .cra_priority = 100,
+ .cra_module = THIS_MODULE,
+ .cra_ctxsize = sizeof(struct ecc_ctx),
+ },
+};
+static bool ecdsa_nist_p192_registered;
+
+static int ecdsa_init(void)
+{
+ int ret;
+
+ /* NIST p192 may not be available in FIPS mode */
+ ret = crypto_register_akcipher(&ecdsa_nist_p192);
+ ecdsa_nist_p192_registered = ret == 0;
+
+ ret = crypto_register_akcipher(&ecdsa_nist_p256);
+ if (ret)
+ goto nist_p256_error;
+
+ ret = crypto_register_akcipher(&ecdsa_nist_p384);
+ if (ret)
+ goto nist_p384_error;
+
+ return 0;
+
+nist_p384_error:
+ crypto_unregister_akcipher(&ecdsa_nist_p256);
+
+nist_p256_error:
+ if (ecdsa_nist_p192_registered)
+ crypto_unregister_akcipher(&ecdsa_nist_p192);
+ return ret;
+}
+
+static void ecdsa_exit(void)
+{
+ if (ecdsa_nist_p192_registered)
+ crypto_unregister_akcipher(&ecdsa_nist_p192);
+ crypto_unregister_akcipher(&ecdsa_nist_p256);
+ crypto_unregister_akcipher(&ecdsa_nist_p384);
+}
+
+subsys_initcall(ecdsa_init);
+module_exit(ecdsa_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Stefan Berger <stefanb@linux.ibm.com>");
+MODULE_DESCRIPTION("ECDSA generic algorithm");
+MODULE_ALIAS_CRYPTO("ecdsa-generic");
--- /dev/null
+ECDSASignature ::= SEQUENCE {
+ r INTEGER ({ ecdsa_get_signature_r }),
+ s INTEGER ({ ecdsa_get_signature_s })
+}
} while (0)
/* Rotate right one 64 bit number as a 56 bit number */
-#define ror56_64(k, n) \
-do { \
- k = (k >> n) | ((k & ((1 << n) - 1)) << (56 - n)); \
-} while (0)
+#define ror56_64(k, n) (k = (k >> n) | ((k & ((1 << n) - 1)) << (56 - n)))
/*
* Sboxes for Feistel network derived from
if (!ec)
return -1;
- while (0 < len) {
+ while (len > 0) {
unsigned int tocopy;
jent_gen_entropy(ec);
}
/* verify and set the oversampling rate */
- if (0 == osr)
+ if (osr == 0)
osr = 1; /* minimum sampling rate is 1 */
entropy_collector->osr = osr;
* etc. with the goal to clear it to get the worst case
* measurements.
*/
- if (CLEARCACHE > i)
+ if (i < CLEARCACHE)
continue;
if (stuck)
* should not fail. The value of 3 should cover the NTP case being
* performed during our test run.
*/
- if (3 < time_backwards)
+ if (time_backwards > 3)
return JENT_ENOMONOTONIC;
/*
scatterwalk_start(walk, sg);
scatterwalk_advance(walk, skip);
break;
- } else
- skip -= sg->length;
+ }
+ skip -= sg->length;
sg = sg_next(sg);
}
}
u8 *buf = NULL;
int err;
- crypto_stats_get(alg);
if (!seed && slen) {
buf = kmalloc(slen, GFP_KERNEL);
- if (!buf) {
- crypto_alg_put(alg);
+ if (!buf)
return -ENOMEM;
- }
err = get_random_bytes_wait(buf, slen);
- if (err) {
- crypto_alg_put(alg);
+ if (err)
goto out;
- }
seed = buf;
}
+ crypto_stats_get(alg);
err = crypto_rng_alg(tfm)->seed(tfm, seed, slen);
crypto_stats_rng_seed(alg, err);
out:
u32 *k = ctx->expkey;
u8 *k8 = (u8 *)k;
u32 r0, r1, r2, r3, r4;
+ __le32 *lk;
int i;
/* Copy key, add padding */
while (i < SERPENT_MAX_KEY_SIZE)
k8[i++] = 0;
+ lk = (__le32 *)k;
+ k[0] = le32_to_cpu(lk[0]);
+ k[1] = le32_to_cpu(lk[1]);
+ k[2] = le32_to_cpu(lk[2]);
+ k[3] = le32_to_cpu(lk[3]);
+ k[4] = le32_to_cpu(lk[4]);
+ k[5] = le32_to_cpu(lk[5]);
+ k[6] = le32_to_cpu(lk[6]);
+ k[7] = le32_to_cpu(lk[7]);
+
/* Expand key using polynomial */
- r0 = le32_to_cpu(k[3]);
- r1 = le32_to_cpu(k[4]);
- r2 = le32_to_cpu(k[5]);
- r3 = le32_to_cpu(k[6]);
- r4 = le32_to_cpu(k[7]);
-
- keyiter(le32_to_cpu(k[0]), r0, r4, r2, 0, 0);
- keyiter(le32_to_cpu(k[1]), r1, r0, r3, 1, 1);
- keyiter(le32_to_cpu(k[2]), r2, r1, r4, 2, 2);
- keyiter(le32_to_cpu(k[3]), r3, r2, r0, 3, 3);
- keyiter(le32_to_cpu(k[4]), r4, r3, r1, 4, 4);
- keyiter(le32_to_cpu(k[5]), r0, r4, r2, 5, 5);
- keyiter(le32_to_cpu(k[6]), r1, r0, r3, 6, 6);
- keyiter(le32_to_cpu(k[7]), r2, r1, r4, 7, 7);
+ r0 = k[3];
+ r1 = k[4];
+ r2 = k[5];
+ r3 = k[6];
+ r4 = k[7];
+
+ keyiter(k[0], r0, r4, r2, 0, 0);
+ keyiter(k[1], r1, r0, r3, 1, 1);
+ keyiter(k[2], r2, r1, r4, 2, 2);
+ keyiter(k[3], r3, r2, r0, 3, 3);
+ keyiter(k[4], r4, r3, r1, 4, 4);
+ keyiter(k[5], r0, r4, r2, 5, 5);
+ keyiter(k[6], r1, r0, r3, 6, 6);
+ keyiter(k[7], r2, r1, r4, 7, 7);
keyiter(k[0], r3, r2, r0, 8, 8);
keyiter(k[1], r4, r3, r1, 9, 9);
return err;
}
-static inline const void *sg_data(struct scatterlist *sg)
-{
- return page_address(sg_page(sg)) + sg->offset;
-}
-
/* Test one hash test vector in one configuration, using the shash API */
static int test_shash_vec_cfg(const struct hash_testvec *vec,
const char *vec_name,
return 0;
if (cfg->nosimd)
crypto_disable_simd_for_test();
- err = crypto_shash_digest(desc, sg_data(&tsgl->sgl[0]),
+ err = crypto_shash_digest(desc, sg_virt(&tsgl->sgl[0]),
tsgl->sgl[0].length, result);
if (cfg->nosimd)
crypto_reenable_simd_for_test();
cfg->finalization_type == FINALIZATION_TYPE_FINUP) {
if (divs[i]->nosimd)
crypto_disable_simd_for_test();
- err = crypto_shash_finup(desc, sg_data(&tsgl->sgl[i]),
+ err = crypto_shash_finup(desc, sg_virt(&tsgl->sgl[i]),
tsgl->sgl[i].length, result);
if (divs[i]->nosimd)
crypto_reenable_simd_for_test();
}
if (divs[i]->nosimd)
crypto_disable_simd_for_test();
- err = crypto_shash_update(desc, sg_data(&tsgl->sgl[i]),
+ err = crypto_shash_update(desc, sg_virt(&tsgl->sgl[i]),
tsgl->sgl[i].length);
if (divs[i]->nosimd)
crypto_reenable_simd_for_test();
}
}, {
#endif
- .alg = "ecdh",
+#ifndef CONFIG_CRYPTO_FIPS
+ .alg = "ecdh-nist-p192",
.test = alg_test_kpp,
.fips_allowed = 1,
.suite = {
- .kpp = __VECS(ecdh_tv_template)
+ .kpp = __VECS(ecdh_p192_tv_template)
+ }
+ }, {
+#endif
+ .alg = "ecdh-nist-p256",
+ .test = alg_test_kpp,
+ .fips_allowed = 1,
+ .suite = {
+ .kpp = __VECS(ecdh_p256_tv_template)
+ }
+ }, {
+ .alg = "ecdsa-nist-p192",
+ .test = alg_test_akcipher,
+ .suite = {
+ .akcipher = __VECS(ecdsa_nist_p192_tv_template)
+ }
+ }, {
+ .alg = "ecdsa-nist-p256",
+ .test = alg_test_akcipher,
+ .suite = {
+ .akcipher = __VECS(ecdsa_nist_p256_tv_template)
+ }
+ }, {
+ .alg = "ecdsa-nist-p384",
+ .test = alg_test_akcipher,
+ .suite = {
+ .akcipher = __VECS(ecdsa_nist_p384_tv_template)
}
}, {
.alg = "ecrdsa",
};
/*
+ * ECDSA test vectors.
+ */
+static const struct akcipher_testvec ecdsa_nist_p192_tv_template[] = {
+ {
+ .key =
+ "\x04\xf7\x46\xf8\x2f\x15\xf6\x22\x8e\xd7\x57\x4f\xcc\xe7\xbb\xc1"
+ "\xd4\x09\x73\xcf\xea\xd0\x15\x07\x3d\xa5\x8a\x8a\x95\x43\xe4\x68"
+ "\xea\xc6\x25\xc1\xc1\x01\x25\x4c\x7e\xc3\x3c\xa6\x04\x0a\xe7\x08"
+ "\x98",
+ .key_len = 49,
+ .params =
+ "\x30\x13\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x08\x2a\x86\x48"
+ "\xce\x3d\x03\x01\x01",
+ .param_len = 21,
+ .m =
+ "\xcd\xb9\xd2\x1c\xb7\x6f\xcd\x44\xb3\xfd\x63\xea\xa3\x66\x7f\xae"
+ "\x63\x85\xe7\x82",
+ .m_size = 20,
+ .algo = OID_id_ecdsa_with_sha1,
+ .c =
+ "\x30\x35\x02\x19\x00\xba\xe5\x93\x83\x6e\xb6\x3b\x63\xa0\x27\x91"
+ "\xc6\xf6\x7f\xc3\x09\xad\x59\xad\x88\x27\xd6\x92\x6b\x02\x18\x10"
+ "\x68\x01\x9d\xba\xce\x83\x08\xef\x95\x52\x7b\xa0\x0f\xe4\x18\x86"
+ "\x80\x6f\xa5\x79\x77\xda\xd0",
+ .c_size = 55,
+ .public_key_vec = true,
+ .siggen_sigver_test = true,
+ }, {
+ .key =
+ "\x04\xb6\x4b\xb1\xd1\xac\xba\x24\x8f\x65\xb2\x60\x00\x90\xbf\xbd"
+ "\x78\x05\x73\xe9\x79\x1d\x6f\x7c\x0b\xd2\xc3\x93\xa7\x28\xe1\x75"
+ "\xf7\xd5\x95\x1d\x28\x10\xc0\x75\x50\x5c\x1a\x4f\x3f\x8f\xa5\xee"
+ "\xa3",
+ .key_len = 49,
+ .params =
+ "\x30\x13\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x08\x2a\x86\x48"
+ "\xce\x3d\x03\x01\x01",
+ .param_len = 21,
+ .m =
+ "\x8d\xd6\xb8\x3e\xe5\xff\x23\xf6\x25\xa2\x43\x42\x74\x45\xa7\x40"
+ "\x3a\xff\x2f\xe1\xd3\xf6\x9f\xe8\x33\xcb\x12\x11",
+ .m_size = 28,
+ .algo = OID_id_ecdsa_with_sha224,
+ .c =
+ "\x30\x34\x02\x18\x5a\x8b\x82\x69\x7e\x8a\x0a\x09\x14\xf8\x11\x2b"
+ "\x55\xdc\xae\x37\x83\x7b\x12\xe6\xb6\x5b\xcb\xd4\x02\x18\x6a\x14"
+ "\x4f\x53\x75\xc8\x02\x48\xeb\xc3\x92\x0f\x1e\x72\xee\xc4\xa3\xe3"
+ "\x5c\x99\xdb\x92\x5b\x36",
+ .c_size = 54,
+ .public_key_vec = true,
+ .siggen_sigver_test = true,
+ }, {
+ .key =
+ "\x04\xe2\x51\x24\x9b\xf7\xb6\x32\x82\x39\x66\x3d\x5b\xec\x3b\xae"
+ "\x0c\xd5\xf2\x67\xd1\xc7\xe1\x02\xe4\xbf\x90\x62\xb8\x55\x75\x56"
+ "\x69\x20\x5e\xcb\x4e\xca\x33\xd6\xcb\x62\x6b\x94\xa9\xa2\xe9\x58"
+ "\x91",
+ .key_len = 49,
+ .params =
+ "\x30\x13\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x08\x2a\x86\x48"
+ "\xce\x3d\x03\x01\x01",
+ .param_len = 21,
+ .m =
+ "\x35\xec\xa1\xa0\x9e\x14\xde\x33\x03\xb6\xf6\xbd\x0c\x2f\xb2\xfd"
+ "\x1f\x27\x82\xa5\xd7\x70\x3f\xef\xa0\x82\x69\x8e\x73\x31\x8e\xd7",
+ .m_size = 32,
+ .algo = OID_id_ecdsa_with_sha256,
+ .c =
+ "\x30\x35\x02\x18\x3f\x72\x3f\x1f\x42\xd2\x3f\x1d\x6b\x1a\x58\x56"
+ "\xf1\x8f\xf7\xfd\x01\x48\xfb\x5f\x72\x2a\xd4\x8f\x02\x19\x00\xb3"
+ "\x69\x43\xfd\x48\x19\x86\xcf\x32\xdd\x41\x74\x6a\x51\xc7\xd9\x7d"
+ "\x3a\x97\xd9\xcd\x1a\x6a\x49",
+ .c_size = 55,
+ .public_key_vec = true,
+ .siggen_sigver_test = true,
+ }, {
+ .key =
+ "\x04\x5a\x13\xfe\x68\x86\x4d\xf4\x17\xc7\xa4\xe5\x8c\x65\x57\xb7"
+ "\x03\x73\x26\x57\xfb\xe5\x58\x40\xd8\xfd\x49\x05\xab\xf1\x66\x1f"
+ "\xe2\x9d\x93\x9e\xc2\x22\x5a\x8b\x4f\xf3\x77\x22\x59\x7e\xa6\x4e"
+ "\x8b",
+ .key_len = 49,
+ .params =
+ "\x30\x13\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x08\x2a\x86\x48"
+ "\xce\x3d\x03\x01\x01",
+ .param_len = 21,
+ .m =
+ "\x9d\x2e\x1a\x8f\xed\x6c\x4b\x61\xae\xac\xd5\x19\x79\xce\x67\xf9"
+ "\xa0\x34\xeb\xb0\x81\xf9\xd9\xdc\x6e\xb3\x5c\xa8\x69\xfc\x8a\x61"
+ "\x39\x81\xfb\xfd\x5c\x30\x6b\xa8\xee\xed\x89\xaf\xa3\x05\xe4\x78",
+ .m_size = 48,
+ .algo = OID_id_ecdsa_with_sha384,
+ .c =
+ "\x30\x35\x02\x19\x00\xf0\xa3\x38\xce\x2b\xf8\x9d\x1a\xcf\x7f\x34"
+ "\xb4\xb4\xe5\xc5\x00\xdd\x15\xbb\xd6\x8c\xa7\x03\x78\x02\x18\x64"
+ "\xbc\x5a\x1f\x82\x96\x61\xd7\xd1\x01\x77\x44\x5d\x53\xa4\x7c\x93"
+ "\x12\x3b\x3b\x28\xfb\x6d\xe1",
+ .c_size = 55,
+ .public_key_vec = true,
+ .siggen_sigver_test = true,
+ }, {
+ .key =
+ "\x04\xd5\xf2\x6e\xc3\x94\x5c\x52\xbc\xdf\x86\x6c\x14\xd1\xca\xea"
+ "\xcc\x72\x3a\x8a\xf6\x7a\x3a\x56\x36\x3b\xca\xc6\x94\x0e\x17\x1d"
+ "\x9e\xa0\x58\x28\xf9\x4b\xe6\xd1\xa5\x44\x91\x35\x0d\xe7\xf5\x11"
+ "\x57",
+ .key_len = 49,
+ .params =
+ "\x30\x13\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x08\x2a\x86\x48"
+ "\xce\x3d\x03\x01\x01",
+ .param_len = 21,
+ .m =
+ "\xd5\x4b\xe9\x36\xda\xd8\x6e\xc0\x50\x03\xbe\x00\x43\xff\xf0\x23"
+ "\xac\xa2\x42\xe7\x37\x77\x79\x52\x8f\x3e\xc0\x16\xc1\xfc\x8c\x67"
+ "\x16\xbc\x8a\x5d\x3b\xd3\x13\xbb\xb6\xc0\x26\x1b\xeb\x33\xcc\x70"
+ "\x4a\xf2\x11\x37\xe8\x1b\xba\x55\xac\x69\xe1\x74\x62\x7c\x6e\xb5",
+ .m_size = 64,
+ .algo = OID_id_ecdsa_with_sha512,
+ .c =
+ "\x30\x35\x02\x19\x00\x88\x5b\x8f\x59\x43\xbf\xcf\xc6\xdd\x3f\x07"
+ "\x87\x12\xa0\xd4\xac\x2b\x11\x2d\x1c\xb6\x06\xc9\x6c\x02\x18\x73"
+ "\xb4\x22\x9a\x98\x73\x3c\x83\xa9\x14\x2a\x5e\xf5\xe5\xfb\x72\x28"
+ "\x6a\xdf\x97\xfd\x82\x76\x24",
+ .c_size = 55,
+ .public_key_vec = true,
+ .siggen_sigver_test = true,
+ },
+};
+
+static const struct akcipher_testvec ecdsa_nist_p256_tv_template[] = {
+ {
+ .key =
+ "\x04\xb9\x7b\xbb\xd7\x17\x64\xd2\x7e\xfc\x81\x5d\x87\x06\x83\x41"
+ "\x22\xd6\x9a\xaa\x87\x17\xec\x4f\x63\x55\x2f\x94\xba\xdd\x83\xe9"
+ "\x34\x4b\xf3\xe9\x91\x13\x50\xb6\xcb\xca\x62\x08\xe7\x3b\x09\xdc"
+ "\xc3\x63\x4b\x2d\xb9\x73\x53\xe4\x45\xe6\x7c\xad\xe7\x6b\xb0\xe8"
+ "\xaf",
+ .key_len = 65,
+ .params =
+ "\x30\x13\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x08\x2a\x86\x48"
+ "\xce\x3d\x03\x01\x07",
+ .param_len = 21,
+ .m =
+ "\xc2\x2b\x5f\x91\x78\x34\x26\x09\x42\x8d\x6f\x51\xb2\xc5\xaf\x4c"
+ "\x0b\xde\x6a\x42",
+ .m_size = 20,
+ .algo = OID_id_ecdsa_with_sha1,
+ .c =
+ "\x30\x46\x02\x21\x00\xf9\x25\xce\x9f\x3a\xa6\x35\x81\xcf\xd4\xe7"
+ "\xb7\xf0\x82\x56\x41\xf7\xd4\xad\x8d\x94\x5a\x69\x89\xee\xca\x6a"
+ "\x52\x0e\x48\x4d\xcc\x02\x21\x00\xd7\xe4\xef\x52\x66\xd3\x5b\x9d"
+ "\x8a\xfa\x54\x93\x29\xa7\x70\x86\xf1\x03\x03\xf3\x3b\xe2\x73\xf7"
+ "\xfb\x9d\x8b\xde\xd4\x8d\x6f\xad",
+ .c_size = 72,
+ .public_key_vec = true,
+ .siggen_sigver_test = true,
+ }, {
+ .key =
+ "\x04\x8b\x6d\xc0\x33\x8e\x2d\x8b\x67\xf5\xeb\xc4\x7f\xa0\xf5\xd9"
+ "\x7b\x03\xa5\x78\x9a\xb5\xea\x14\xe4\x23\xd0\xaf\xd7\x0e\x2e\xa0"
+ "\xc9\x8b\xdb\x95\xf8\xb3\xaf\xac\x00\x2c\x2c\x1f\x7a\xfd\x95\x88"
+ "\x43\x13\xbf\xf3\x1c\x05\x1a\x14\x18\x09\x3f\xd6\x28\x3e\xc5\xa0"
+ "\xd4",
+ .key_len = 65,
+ .params =
+ "\x30\x13\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x08\x2a\x86\x48"
+ "\xce\x3d\x03\x01\x07",
+ .param_len = 21,
+ .m =
+ "\x1a\x15\xbc\xa3\xe4\xed\x3a\xb8\x23\x67\xc6\xc4\x34\xf8\x6c\x41"
+ "\x04\x0b\xda\xc5\x77\xfa\x1c\x2d\xe6\x2c\x3b\xe0",
+ .m_size = 28,
+ .algo = OID_id_ecdsa_with_sha224,
+ .c =
+ "\x30\x44\x02\x20\x20\x43\xfa\xc0\x9f\x9d\x7b\xe7\xae\xce\x77\x59"
+ "\x1a\xdb\x59\xd5\x34\x62\x79\xcb\x6a\x91\x67\x2e\x7d\x25\xd8\x25"
+ "\xf5\x81\xd2\x1e\x02\x20\x5f\xf8\x74\xf8\x57\xd0\x5e\x54\x76\x20"
+ "\x4a\x77\x22\xec\xc8\x66\xbf\x50\x05\x58\x39\x0e\x26\x92\xce\xd5"
+ "\x2e\x8b\xde\x5a\x04\x0e",
+ .c_size = 70,
+ .public_key_vec = true,
+ .siggen_sigver_test = true,
+ }, {
+ .key =
+ "\x04\xf1\xea\xc4\x53\xf3\xb9\x0e\x9f\x7e\xad\xe3\xea\xd7\x0e\x0f"
+ "\xd6\x98\x9a\xca\x92\x4d\x0a\x80\xdb\x2d\x45\xc7\xec\x4b\x97\x00"
+ "\x2f\xe9\x42\x6c\x29\xdc\x55\x0e\x0b\x53\x12\x9b\x2b\xad\x2c\xe9"
+ "\x80\xe6\xc5\x43\xc2\x1d\x5e\xbb\x65\x21\x50\xb6\x37\xb0\x03\x8e"
+ "\xb8",
+ .key_len = 65,
+ .params =
+ "\x30\x13\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x08\x2a\x86\x48"
+ "\xce\x3d\x03\x01\x07",
+ .param_len = 21,
+ .m =
+ "\x8f\x43\x43\x46\x64\x8f\x6b\x96\xdf\x89\xdd\xa9\x01\xc5\x17\x6b"
+ "\x10\xa6\xd8\x39\x61\xdd\x3c\x1a\xc8\x8b\x59\xb2\xdc\x32\x7a\xa4",
+ .m_size = 32,
+ .algo = OID_id_ecdsa_with_sha256,
+ .c =
+ "\x30\x45\x02\x20\x08\x31\xfa\x74\x0d\x1d\x21\x5d\x09\xdc\x29\x63"
+ "\xa8\x1a\xad\xfc\xac\x44\xc3\xe8\x24\x11\x2d\xa4\x91\xdc\x02\x67"
+ "\xdc\x0c\xd0\x82\x02\x21\x00\xbd\xff\xce\xee\x42\xc3\x97\xff\xf9"
+ "\xa9\x81\xac\x4a\x50\xd0\x91\x0a\x6e\x1b\xc4\xaf\xe1\x83\xc3\x4f"
+ "\x2a\x65\x35\x23\xe3\x1d\xfa",
+ .c_size = 71,
+ .public_key_vec = true,
+ .siggen_sigver_test = true,
+ }, {
+ .key =
+ "\x04\xc5\xc6\xea\x60\xc9\xce\xad\x02\x8d\xf5\x3e\x24\xe3\x52\x1d"
+ "\x28\x47\x3b\xc3\x6b\xa4\x99\x35\x99\x11\x88\x88\xc8\xf4\xee\x7e"
+ "\x8c\x33\x8f\x41\x03\x24\x46\x2b\x1a\x82\xf9\x9f\xe1\x97\x1b\x00"
+ "\xda\x3b\x24\x41\xf7\x66\x33\x58\x3d\x3a\x81\xad\xcf\x16\xe9\xe2"
+ "\x7c",
+ .key_len = 65,
+ .params =
+ "\x30\x13\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x08\x2a\x86\x48"
+ "\xce\x3d\x03\x01\x07",
+ .param_len = 21,
+ .m =
+ "\x3e\x78\x70\xfb\xcd\x66\xba\x91\xa1\x79\xff\x1e\x1c\x6b\x78\xe6"
+ "\xc0\x81\x3a\x65\x97\x14\x84\x36\x14\x1a\x9a\xb7\xc5\xab\x84\x94"
+ "\x5e\xbb\x1b\x34\x71\xcb\x41\xe1\xf6\xfc\x92\x7b\x34\xbb\x86\xbb",
+ .m_size = 48,
+ .algo = OID_id_ecdsa_with_sha384,
+ .c =
+ "\x30\x46\x02\x21\x00\x8e\xf3\x6f\xdc\xf8\x69\xa6\x2e\xd0\x2e\x95"
+ "\x54\xd1\x95\x64\x93\x08\xb2\x6b\x24\x94\x48\x46\x5e\xf2\xe4\x6c"
+ "\xc7\x94\xb1\xd5\xfe\x02\x21\x00\xeb\xa7\x80\x26\xdc\xf9\x3a\x44"
+ "\x19\xfb\x5f\x92\xf4\xc9\x23\x37\x69\xf4\x3b\x4f\x47\xcf\x9b\x16"
+ "\xc0\x60\x11\x92\xdc\x17\x89\x12",
+ .c_size = 72,
+ .public_key_vec = true,
+ .siggen_sigver_test = true,
+ }, {
+ .key =
+ "\x04\xd7\x27\x46\x49\xf6\x26\x85\x12\x40\x76\x8e\xe2\xe6\x2a\x7a"
+ "\x83\xb1\x4e\x7a\xeb\x3b\x5c\x67\x4a\xb5\xa4\x92\x8c\x69\xff\x38"
+ "\xee\xd9\x4e\x13\x29\x59\xad\xde\x6b\xbb\x45\x31\xee\xfd\xd1\x1b"
+ "\x64\xd3\xb5\xfc\xaf\x9b\x4b\x88\x3b\x0e\xb7\xd6\xdf\xf1\xd5\x92"
+ "\xbf",
+ .key_len = 65,
+ .params =
+ "\x30\x13\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x08\x2a\x86\x48"
+ "\xce\x3d\x03\x01\x07",
+ .param_len = 21,
+ .m =
+ "\x57\xb7\x9e\xe9\x05\x0a\x8c\x1b\xc9\x13\xe5\x4a\x24\xc7\xe2\xe9"
+ "\x43\xc3\xd1\x76\x62\xf4\x98\x1a\x9c\x13\xb0\x20\x1b\xe5\x39\xca"
+ "\x4f\xd9\x85\x34\x95\xa2\x31\xbc\xbb\xde\xdd\x76\xbb\x61\xe3\xcf"
+ "\x9d\xc0\x49\x7a\xf3\x7a\xc4\x7d\xa8\x04\x4b\x8d\xb4\x4d\x5b\xd6",
+ .m_size = 64,
+ .algo = OID_id_ecdsa_with_sha512,
+ .c =
+ "\x30\x45\x02\x21\x00\xb8\x6d\x87\x81\x43\xdf\xfb\x9f\x40\xea\x44"
+ "\x81\x00\x4e\x29\x08\xed\x8c\x73\x30\x6c\x22\xb3\x97\x76\xf6\x04"
+ "\x99\x09\x37\x4d\xfa\x02\x20\x1e\xb9\x75\x31\xf6\x04\xa5\x4d\xf8"
+ "\x00\xdd\xab\xd4\xc0\x2b\xe6\x5c\xad\xc3\x78\x1c\xc2\xc1\x19\x76"
+ "\x31\x79\x4a\xe9\x81\x6a\xee",
+ .c_size = 71,
+ .public_key_vec = true,
+ .siggen_sigver_test = true,
+ },
+};
+
+static const struct akcipher_testvec ecdsa_nist_p384_tv_template[] = {
+ {
+ .key = /* secp384r1(sha1) */
+ "\x04\x89\x25\xf3\x97\x88\xcb\xb0\x78\xc5\x72\x9a\x14\x6e\x7a\xb1"
+ "\x5a\xa5\x24\xf1\x95\x06\x9e\x28\xfb\xc4\xb9\xbe\x5a\x0d\xd9\x9f"
+ "\xf3\xd1\x4d\x2d\x07\x99\xbd\xda\xa7\x66\xec\xbb\xea\xba\x79\x42"
+ "\xc9\x34\x89\x6a\xe7\x0b\xc3\xf2\xfe\x32\x30\xbe\xba\xf9\xdf\x7e"
+ "\x4b\x6a\x07\x8e\x26\x66\x3f\x1d\xec\xa2\x57\x91\x51\xdd\x17\x0e"
+ "\x0b\x25\xd6\x80\x5c\x3b\xe6\x1a\x98\x48\x91\x45\x7a\x73\xb0\xc3"
+ "\xf1",
+ .key_len = 97,
+ .params =
+ "\x30\x10\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x05\x2b\x81\x04"
+ "\x00\x22",
+ .param_len = 18,
+ .m =
+ "\x12\x55\x28\xf0\x77\xd5\xb6\x21\x71\x32\x48\xcd\x28\xa8\x25\x22"
+ "\x3a\x69\xc1\x93",
+ .m_size = 20,
+ .algo = OID_id_ecdsa_with_sha1,
+ .c =
+ "\x30\x66\x02\x31\x00\xf5\x0f\x24\x4c\x07\x93\x6f\x21\x57\x55\x07"
+ "\x20\x43\x30\xde\xa0\x8d\x26\x8e\xae\x63\x3f\xbc\x20\x3a\xc6\xf1"
+ "\x32\x3c\xce\x70\x2b\x78\xf1\x4c\x26\xe6\x5b\x86\xcf\xec\x7c\x7e"
+ "\xd0\x87\xd7\xd7\x6e\x02\x31\x00\xcd\xbb\x7e\x81\x5d\x8f\x63\xc0"
+ "\x5f\x63\xb1\xbe\x5e\x4c\x0e\xa1\xdf\x28\x8c\x1b\xfa\xf9\x95\x88"
+ "\x74\xa0\x0f\xbf\xaf\xc3\x36\x76\x4a\xa1\x59\xf1\x1c\xa4\x58\x26"
+ "\x79\x12\x2a\xb7\xc5\x15\x92\xc5",
+ .c_size = 104,
+ .public_key_vec = true,
+ .siggen_sigver_test = true,
+ }, {
+ .key = /* secp384r1(sha224) */
+ "\x04\x69\x6c\xcf\x62\xee\xd0\x0d\xe5\xb5\x2f\x70\x54\xcf\x26\xa0"
+ "\xd9\x98\x8d\x92\x2a\xab\x9b\x11\xcb\x48\x18\xa1\xa9\x0d\xd5\x18"
+ "\x3e\xe8\x29\x6e\xf6\xe4\xb5\x8e\xc7\x4a\xc2\x5f\x37\x13\x99\x05"
+ "\xb6\xa4\x9d\xf9\xfb\x79\x41\xe7\xd7\x96\x9f\x73\x3b\x39\x43\xdc"
+ "\xda\xf4\x06\xb9\xa5\x29\x01\x9d\x3b\xe1\xd8\x68\x77\x2a\xf4\x50"
+ "\x6b\x93\x99\x6c\x66\x4c\x42\x3f\x65\x60\x6c\x1c\x0b\x93\x9b\x9d"
+ "\xe0",
+ .key_len = 97,
+ .params =
+ "\x30\x10\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x05\x2b\x81\x04"
+ "\x00\x22",
+ .param_len = 18,
+ .m =
+ "\x12\x80\xb6\xeb\x25\xe2\x3d\xf0\x21\x32\x96\x17\x3a\x38\x39\xfd"
+ "\x1f\x05\x34\x7b\xb8\xf9\x71\x66\x03\x4f\xd5\xe5",
+ .m_size = 28,
+ .algo = OID_id_ecdsa_with_sha224,
+ .c =
+ "\x30\x66\x02\x31\x00\x8a\x51\x84\xce\x13\x1e\xd2\xdc\xec\xcb\xe4"
+ "\x89\x47\xb2\xf7\xbc\x97\xf1\xc8\x72\x26\xcf\x5a\x5e\xc5\xda\xb4"
+ "\xe3\x93\x07\xe0\x99\xc9\x9c\x11\xb8\x10\x01\xc5\x41\x3f\xdd\x15"
+ "\x1b\x68\x2b\x9d\x8b\x02\x31\x00\x8b\x03\x2c\xfc\x1f\xd1\xa9\xa4"
+ "\x4b\x00\x08\x31\x6c\xf5\xd5\xf6\xdf\xd8\x68\xa2\x64\x42\x65\xf3"
+ "\x4d\xd0\xc6\x6e\xb0\xe9\xfc\x14\x9f\x19\xd0\x42\x8b\x93\xc2\x11"
+ "\x88\x2b\x82\x26\x5e\x1c\xda\xfb",
+ .c_size = 104,
+ .public_key_vec = true,
+ .siggen_sigver_test = true,
+ }, {
+ .key = /* secp384r1(sha256) */
+ "\x04\xee\xd6\xda\x3e\x94\x90\x00\x27\xed\xf8\x64\x55\xd6\x51\x9a"
+ "\x1f\x52\x00\x63\x78\xf1\xa9\xfd\x75\x4c\x9e\xb2\x20\x1a\x91\x5a"
+ "\xba\x7a\xa3\xe5\x6c\xb6\x25\x68\x4b\xe8\x13\xa6\x54\x87\x2c\x0e"
+ "\xd0\x83\x95\xbc\xbf\xc5\x28\x4f\x77\x1c\x46\xa6\xf0\xbc\xd4\xa4"
+ "\x8d\xc2\x8f\xb3\x32\x37\x40\xd6\xca\xf8\xae\x07\x34\x52\x39\x52"
+ "\x17\xc3\x34\x29\xd6\x40\xea\x5c\xb9\x3f\xfb\x32\x2e\x12\x33\xbc"
+ "\xab",
+ .key_len = 97,
+ .params =
+ "\x30\x10\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x05\x2b\x81\x04"
+ "\x00\x22",
+ .param_len = 18,
+ .m =
+ "\xaa\xe7\xfd\x03\x26\xcb\x94\x71\xe4\xce\x0f\xc5\xff\xa6\x29\xa3"
+ "\xe1\xcc\x4c\x35\x4e\xde\xca\x80\xab\x26\x0c\x25\xe6\x68\x11\xc2",
+ .m_size = 32,
+ .algo = OID_id_ecdsa_with_sha256,
+ .c =
+ "\x30\x64\x02\x30\x08\x09\x12\x9d\x6e\x96\x64\xa6\x8e\x3f\x7e\xce"
+ "\x0a\x9b\xaa\x59\xcc\x47\x53\x87\xbc\xbd\x83\x3f\xaf\x06\x3f\x84"
+ "\x04\xe2\xf9\x67\xb6\xc6\xfc\x70\x2e\x66\x3c\x77\xc8\x8d\x2c\x79"
+ "\x3a\x8e\x32\xc4\x02\x30\x40\x34\xb8\x90\xa9\x80\xab\x47\x26\xa2"
+ "\xb0\x89\x42\x0a\xda\xd9\xdd\xce\xbc\xb2\x97\xf4\x9c\xf3\x15\x68"
+ "\xc0\x75\x3e\x23\x5e\x36\x4f\x8d\xde\x1e\x93\x8d\x95\xbb\x10\x0e"
+ "\xf4\x1f\x39\xca\x4d\x43",
+ .c_size = 102,
+ .public_key_vec = true,
+ .siggen_sigver_test = true,
+ }, {
+ .key = /* secp384r1(sha384) */
+ "\x04\x3a\x2f\x62\xe7\x1a\xcf\x24\xd0\x0b\x7c\xe0\xed\x46\x0a\x4f"
+ "\x74\x16\x43\xe9\x1a\x25\x7c\x55\xff\xf0\x29\x68\x66\x20\x91\xf9"
+ "\xdb\x2b\xf6\xb3\x6c\x54\x01\xca\xc7\x6a\x5c\x0d\xeb\x68\xd9\x3c"
+ "\xf1\x01\x74\x1f\xf9\x6c\xe5\x5b\x60\xe9\x7f\x5d\xb3\x12\x80\x2a"
+ "\xd8\x67\x92\xc9\x0e\x4c\x4c\x6b\xa1\xb2\xa8\x1e\xac\x1c\x97\xd9"
+ "\x21\x67\xe5\x1b\x5a\x52\x31\x68\xd6\xee\xf0\x19\xb0\x55\xed\x89"
+ "\x9e",
+ .key_len = 97,
+ .params =
+ "\x30\x10\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x05\x2b\x81\x04"
+ "\x00\x22",
+ .param_len = 18,
+ .m =
+ "\x8d\xf2\xc0\xe9\xa8\xf3\x8e\x44\xc4\x8c\x1a\xa0\xb8\xd7\x17\xdf"
+ "\xf2\x37\x1b\xc6\xe3\xf5\x62\xcc\x68\xf5\xd5\x0b\xbf\x73\x2b\xb1"
+ "\xb0\x4c\x04\x00\x31\xab\xfe\xc8\xd6\x09\xc8\xf2\xea\xd3\x28\xff",
+ .m_size = 48,
+ .algo = OID_id_ecdsa_with_sha384,
+ .c =
+ "\x30\x66\x02\x31\x00\x9b\x28\x68\xc0\xa1\xea\x8c\x50\xee\x2e\x62"
+ "\x35\x46\xfa\x00\xd8\x2d\x7a\x91\x5f\x49\x2d\x22\x08\x29\xe6\xfb"
+ "\xca\x8c\xd6\xb6\xb4\x3b\x1f\x07\x8f\x15\x02\xfe\x1d\xa2\xa4\xc8"
+ "\xf2\xea\x9d\x11\x1f\x02\x31\x00\xfc\x50\xf6\x43\xbd\x50\x82\x0e"
+ "\xbf\xe3\x75\x24\x49\xac\xfb\xc8\x71\xcd\x8f\x18\x99\xf0\x0f\x13"
+ "\x44\x92\x8c\x86\x99\x65\xb3\x97\x96\x17\x04\xc9\x05\x77\xf1\x8e"
+ "\xab\x8d\x4e\xde\xe6\x6d\x9b\x66",
+ .c_size = 104,
+ .public_key_vec = true,
+ .siggen_sigver_test = true,
+ }, {
+ .key = /* secp384r1(sha512) */
+ "\x04\xb4\xe7\xc1\xeb\x64\x25\x22\x46\xc3\x86\x61\x80\xbe\x1e\x46"
+ "\xcb\xf6\x05\xc2\xee\x73\x83\xbc\xea\x30\x61\x4d\x40\x05\x41\xf4"
+ "\x8c\xe3\x0e\x5c\xf0\x50\xf2\x07\x19\xe8\x4f\x25\xbe\xee\x0c\x95"
+ "\x54\x36\x86\xec\xc2\x20\x75\xf3\x89\xb5\x11\xa1\xb7\xf5\xaf\xbe"
+ "\x81\xe4\xc3\x39\x06\xbd\xe4\xfe\x68\x1c\x6d\x99\x2b\x1b\x63\xfa"
+ "\xdf\x42\x5c\xc2\x5a\xc7\x0c\xf4\x15\xf7\x1b\xa3\x2e\xd7\x00\xac"
+ "\xa3",
+ .key_len = 97,
+ .params =
+ "\x30\x10\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x05\x2b\x81\x04"
+ "\x00\x22",
+ .param_len = 18,
+ .m =
+ "\xe8\xb7\x52\x7d\x1a\x44\x20\x05\x53\x6b\x3a\x68\xf2\xe7\x6c\xa1"
+ "\xae\x9d\x84\xbb\xba\x52\x43\x3e\x2c\x42\x78\x49\xbf\x78\xb2\x71"
+ "\xeb\xe1\xe0\xe8\x42\x7b\x11\xad\x2b\x99\x05\x1d\x36\xe6\xac\xfc"
+ "\x55\x73\xf0\x15\x63\x39\xb8\x6a\x6a\xc5\x91\x5b\xca\x6a\xa8\x0e",
+ .m_size = 64,
+ .algo = OID_id_ecdsa_with_sha512,
+ .c =
+ "\x30\x63\x02\x2f\x1d\x20\x94\x77\xfe\x31\xfa\x4d\xc6\xef\xda\x02"
+ "\xe7\x0f\x52\x9a\x02\xde\x93\xe8\x83\xe4\x84\x4c\xfc\x6f\x80\xe3"
+ "\xaf\xb3\xd9\xdc\x2b\x43\x0e\x6a\xb3\x53\x6f\x3e\xb3\xc7\xa8\xb3"
+ "\x17\x77\xd1\x02\x30\x63\xf6\xf0\x3d\x5f\x5f\x99\x3f\xde\x3a\x3d"
+ "\x16\xaf\xb4\x52\x6a\xec\x63\xe3\x0c\xec\x50\xdc\xcc\xc4\x6a\x03"
+ "\x5f\x8d\x7a\xf9\xfb\x34\xe4\x8b\x80\xa5\xb6\xda\x2c\x4e\x45\xcf"
+ "\x3c\x93\xff\x50\x5d",
+ .c_size = 101,
+ .public_key_vec = true,
+ .siggen_sigver_test = true,
+ },
+};
+
+/*
* EC-RDSA test vectors are generated by gost-engine.
*/
static const struct akcipher_testvec ecrdsa_tv_template[] = {
}
};
-static const struct kpp_testvec ecdh_tv_template[] = {
- {
#ifndef CONFIG_CRYPTO_FIPS
+static const struct kpp_testvec ecdh_p192_tv_template[] = {
+ {
.secret =
#ifdef __LITTLE_ENDIAN
"\x02\x00" /* type */
- "\x20\x00" /* len */
- "\x01\x00" /* curve_id */
+ "\x1e\x00" /* len */
"\x18\x00" /* key_size */
#else
"\x00\x02" /* type */
- "\x00\x20" /* len */
- "\x00\x01" /* curve_id */
+ "\x00\x1e" /* len */
"\x00\x18" /* key_size */
#endif
"\xb5\x05\xb1\x71\x1e\xbf\x8c\xda"
.b_public_size = 48,
.expected_a_public_size = 48,
.expected_ss_size = 24
- }, {
+ }
+};
#endif
+
+static const struct kpp_testvec ecdh_p256_tv_template[] = {
+ {
.secret =
#ifdef __LITTLE_ENDIAN
"\x02\x00" /* type */
- "\x28\x00" /* len */
- "\x02\x00" /* curve_id */
+ "\x26\x00" /* len */
"\x20\x00" /* key_size */
#else
"\x00\x02" /* type */
- "\x00\x28" /* len */
- "\x00\x02" /* curve_id */
+ "\x00\x26" /* len */
"\x00\x20" /* key_size */
#endif
"\x24\xd1\x21\xeb\xe5\xcf\x2d\x83"
.secret =
#ifdef __LITTLE_ENDIAN
"\x02\x00" /* type */
- "\x08\x00" /* len */
- "\x02\x00" /* curve_id */
+ "\x06\x00" /* len */
"\x00\x00", /* key_size */
#else
"\x00\x02" /* type */
- "\x00\x08" /* len */
- "\x00\x02" /* curve_id */
+ "\x00\x06" /* len */
"\x00\x00", /* key_size */
#endif
.b_secret =
#ifdef __LITTLE_ENDIAN
"\x02\x00" /* type */
- "\x28\x00" /* len */
- "\x02\x00" /* curve_id */
+ "\x26\x00" /* len */
"\x20\x00" /* key_size */
#else
"\x00\x02" /* type */
- "\x00\x28" /* len */
- "\x00\x02" /* curve_id */
+ "\x00\x26" /* len */
"\x00\x20" /* key_size */
#endif
"\x24\xd1\x21\xeb\xe5\xcf\x2d\x83"
* just create and link the new node(s) here.
*/
new_node =
- ACPI_ALLOCATE_ZEROED(sizeof(struct acpi_namespace_node));
+ acpi_ns_create_node(*ACPI_CAST_PTR(u32, init_val->name));
if (!new_node) {
status = AE_NO_MEMORY;
goto unlock_and_exit;
}
- ACPI_COPY_NAMESEG(new_node->name.ascii, init_val->name);
new_node->descriptor_type = ACPI_DESC_TYPE_NAMED;
new_node->type = init_val->type;
#ifndef _ACPI_INTERNAL_H_
#define _ACPI_INTERNAL_H_
+#include <linux/idr.h>
+
#define PREFIX "ACPI: "
int early_acpi_osi_init(void);
extern struct list_head acpi_bus_id_list;
+#define ACPI_MAX_DEVICE_INSTANCES 4096
+
struct acpi_device_bus_id {
const char *bus_id;
- unsigned int instance_no;
+ struct ida instance_ida;
struct list_head node;
};
*/
#ifdef CONFIG_X86
#include <asm/apic.h>
+#include <asm/cpu.h>
#endif
#define _COMPONENT ACPI_PROCESSOR_COMPONENT
wait_for_freeze();
} else
return -ENODEV;
+
+#if defined(CONFIG_X86) && defined(CONFIG_HOTPLUG_CPU)
+ cond_wakeup_cpu0();
+#endif
}
/* Never reached */
list_for_each_entry(acpi_device_bus_id, &acpi_bus_id_list, node)
if (!strcmp(acpi_device_bus_id->bus_id,
acpi_device_hid(device))) {
- if (acpi_device_bus_id->instance_no > 0)
- acpi_device_bus_id->instance_no--;
- else {
+ ida_simple_remove(&acpi_device_bus_id->instance_ida, device->pnp.instance_no);
+ if (ida_is_empty(&acpi_device_bus_id->instance_ida)) {
list_del(&acpi_device_bus_id->node);
kfree_const(acpi_device_bus_id->bus_id);
kfree(acpi_device_bus_id);
return NULL;
}
+static int acpi_device_set_name(struct acpi_device *device,
+ struct acpi_device_bus_id *acpi_device_bus_id)
+{
+ struct ida *instance_ida = &acpi_device_bus_id->instance_ida;
+ int result;
+
+ result = ida_simple_get(instance_ida, 0, ACPI_MAX_DEVICE_INSTANCES, GFP_KERNEL);
+ if (result < 0)
+ return result;
+
+ device->pnp.instance_no = result;
+ dev_set_name(&device->dev, "%s:%02x", acpi_device_bus_id->bus_id, result);
+ return 0;
+}
+
int acpi_device_add(struct acpi_device *device,
void (*release)(struct device *))
{
acpi_device_bus_id = acpi_device_bus_id_match(acpi_device_hid(device));
if (acpi_device_bus_id) {
- acpi_device_bus_id->instance_no++;
+ result = acpi_device_set_name(device, acpi_device_bus_id);
+ if (result)
+ goto err_unlock;
} else {
acpi_device_bus_id = kzalloc(sizeof(*acpi_device_bus_id),
GFP_KERNEL);
goto err_unlock;
}
+ ida_init(&acpi_device_bus_id->instance_ida);
+
+ result = acpi_device_set_name(device, acpi_device_bus_id);
+ if (result) {
+ kfree(acpi_device_bus_id);
+ goto err_unlock;
+ }
+
list_add_tail(&acpi_device_bus_id->node, &acpi_bus_id_list);
}
- dev_set_name(&device->dev, "%s:%02x", acpi_device_bus_id->bus_id, acpi_device_bus_id->instance_no);
if (device->parent)
list_add_tail(&device->node, &device->parent->children);
device_initialize(&device->dev);
dev_set_uevent_suppress(&device->dev, true);
acpi_init_coherency(device);
+ /* Assume there are unmet deps to start with. */
+ device->dep_unmet = 1;
}
void acpi_device_add_finalize(struct acpi_device *device)
{
struct acpi_dep_data *dep;
+ adev->dep_unmet = 0;
+
mutex_lock(&acpi_dep_list_lock);
list_for_each_entry(dep, &acpi_dep_list, node) {
return AE_CTRL_DEPTH;
acpi_scan_init_hotplug(device);
- if (!check_dep)
+ /*
+ * If check_dep is true at this point, the device has no dependencies,
+ * or the creation of the device object would have been postponed above.
+ */
+ if (check_dep)
+ device->dep_unmet = 0;
+ else
acpi_scan_dep_init(device);
out:
}
/*
- * acpi_table_init()
+ * acpi_locate_initial_tables()
*
* find RSDP, find and checksum SDT/XSDT.
* checksum all tables, print SDT/XSDT
* result: sdt_entry[] is initialized
*/
-int __init acpi_table_init(void)
+int __init acpi_locate_initial_tables(void)
{
acpi_status status;
status = acpi_initialize_tables(initial_tables, ACPI_MAX_TABLES, 0);
if (ACPI_FAILURE(status))
return -EINVAL;
- acpi_table_initrd_scan();
+ return 0;
+}
+
+void __init acpi_reserve_initial_tables(void)
+{
+ int i;
+
+ for (i = 0; i < ACPI_MAX_TABLES; i++) {
+ struct acpi_table_desc *table_desc = &initial_tables[i];
+ u64 start = table_desc->address;
+ u64 size = table_desc->length;
+
+ if (!start || !size)
+ break;
+
+ pr_info("Reserving %4s table memory at [mem 0x%llx-0x%llx]\n",
+ table_desc->signature.ascii, start, start + size - 1);
+
+ memblock_reserve(start, size);
+ }
+}
+
+void __init acpi_table_init_complete(void)
+{
+ acpi_table_initrd_scan();
check_multiple_madt();
+}
+
+int __init acpi_table_init(void)
+{
+ int ret;
+
+ ret = acpi_locate_initial_tables();
+ if (ret)
+ return ret;
+
+ acpi_table_init_complete();
+
return 0;
}
},
},
{
+ .callback = video_detect_force_vendor,
.ident = "Sony VPCEH3U1E",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"),
}
submitted++;
ATM_SKB(skb)->vcc = vcc;
- tasklet_disable(&ENI_DEV(vcc->dev)->task);
+ tasklet_disable_in_atomic(&ENI_DEV(vcc->dev)->task);
res = do_tx(skb);
tasklet_enable(&ENI_DEV(vcc->dev)->task);
if (res == enq_ok) return 0;
return rc;
err_eni_release:
- eni_do_release(dev);
+ dev->phy = NULL;
+ iounmap(ENI_DEV(dev)->ioaddr);
err_unregister:
atm_dev_deregister(dev);
err_free_consistent:
MODULE_AUTHOR("Christophe Lizzi - credits to Uwe Dannowski and Heikki Vatiainen");
MODULE_DESCRIPTION("FORE Systems 200E-series ATM driver - version " FORE200E_VERSION);
-MODULE_SUPPORTED_DEVICE("PCA-200E, SBA-200E");
-
static const int fore200e_rx_buf_nbr[ BUFFER_SCHEME_NBR ][ BUFFER_MAGN_NBR ] = {
{ BUFFER_S1_NBR, BUFFER_L1_NBR },
{
unsigned long flags;
- if (!(dev->dev_data = kmalloc(sizeof(struct idt77105_priv),GFP_KERNEL)))
+ if (!(dev->phy_data = kmalloc(sizeof(struct idt77105_priv),GFP_KERNEL)))
return -ENOMEM;
PRIV(dev)->dev = dev;
spin_lock_irqsave(&idt77105_priv_lock, flags);
else
idt77105_all = walk->next;
dev->phy = NULL;
- dev->dev_data = NULL;
+ dev->phy_data = NULL;
kfree(walk);
break;
}
conf1_write(lanai);
#endif
iounmap(lanai->base);
+ lanai->base = NULL;
error_pci:
pci_disable_device(lanai->pci);
error:
static void lanai_dev_close(struct atm_dev *atmdev)
{
struct lanai_dev *lanai = (struct lanai_dev *) atmdev->dev_data;
+ if (lanai->base==NULL)
+ return;
printk(KERN_INFO DEV_LABEL "(itf %d): shutting down interface\n",
lanai->number);
lanai_timed_poll_stop(lanai);
struct atm_dev *atmdev;
int result;
- lanai = kmalloc(sizeof(*lanai), GFP_KERNEL);
+ lanai = kzalloc(sizeof(*lanai), GFP_KERNEL);
if (lanai == NULL) {
printk(KERN_ERR DEV_LABEL
": couldn't allocate dev_data structure!\n");
static int uPD98402_start(struct atm_dev *dev)
{
DPRINTK("phy_start\n");
- if (!(dev->dev_data = kmalloc(sizeof(struct uPD98402_priv),GFP_KERNEL)))
+ if (!(dev->phy_data = kmalloc(sizeof(struct uPD98402_priv),GFP_KERNEL)))
return -ENOMEM;
spin_lock_init(&PRIV(dev)->lock);
memset(&PRIV(dev)->sonet_stats,0,sizeof(struct k_sonet_stats));
char c;
for (; count-- > 0; (*ppos)++, tmp++) {
- if (!in_interrupt() && (((count + 1) & 0x1f) == 0))
+ if (((count + 1) & 0x1f) == 0) {
/*
- * let's be a little nice with other processes
- * that need some CPU
+ * charlcd_write() is invoked as a VFS->write() callback
+ * and as such it is always invoked from preemptible
+ * context and may sleep.
*/
- schedule();
+ cond_resched();
+ }
if (get_user(c, tmp))
return -EFAULT;
int count = strlen(s);
for (; count-- > 0; tmp++) {
- if (!in_interrupt() && (((count + 1) & 0x1f) == 0))
- /*
- * let's be a little nice with other processes
- * that need some CPU
- */
- schedule();
+ if (((count + 1) & 0x1f) == 0)
+ cond_resched();
charlcd_write_char(lcd, *tmp);
}
get_device(dev);
+ kfree(dev->p->deferred_probe_reason);
+ dev->p->deferred_probe_reason = NULL;
+
/*
* Drop the mutex while probing each device; the probe path may
* manipulate the deferred list
static void deferred_probe_timeout_work_func(struct work_struct *work)
{
- struct device_private *private, *p;
+ struct device_private *p;
driver_deferred_probe_timeout = 0;
driver_deferred_probe_trigger();
flush_work(&deferred_probe_work);
- list_for_each_entry_safe(private, p, &deferred_probe_pending_list, deferred_probe)
- dev_info(private->device, "deferred probe pending\n");
+ mutex_lock(&deferred_probe_mutex);
+ list_for_each_entry(p, &deferred_probe_pending_list, deferred_probe)
+ dev_info(p->device, "deferred probe pending\n");
+ mutex_unlock(&deferred_probe_mutex);
wake_up_all(&probe_timeout_waitqueue);
}
static DECLARE_DELAYED_WORK(deferred_probe_timeout_work, deferred_probe_timeout_work_func);
return 0;
}
-static void rpm_put_suppliers(struct device *dev)
+static void __rpm_put_suppliers(struct device *dev, bool try_to_suspend)
{
struct device_link *link;
device_links_read_lock_held()) {
while (refcount_dec_not_one(&link->rpm_active))
- pm_runtime_put(link->supplier);
+ pm_runtime_put_noidle(link->supplier);
+
+ if (try_to_suspend)
+ pm_request_idle(link->supplier);
}
}
+static void rpm_put_suppliers(struct device *dev)
+{
+ __rpm_put_suppliers(dev, true);
+}
+
+static void rpm_suspend_suppliers(struct device *dev)
+{
+ struct device_link *link;
+ int idx = device_links_read_lock();
+
+ list_for_each_entry_rcu(link, &dev->links.suppliers, c_node,
+ device_links_read_lock_held())
+ pm_request_idle(link->supplier);
+
+ device_links_read_unlock(idx);
+}
+
/**
* __rpm_callback - Run a given runtime PM callback for a given device.
* @cb: Runtime PM callback to run.
static int __rpm_callback(int (*cb)(struct device *), struct device *dev)
__releases(&dev->power.lock) __acquires(&dev->power.lock)
{
- bool use_links = dev->power.links_count > 0;
- bool get = false;
int retval, idx;
- bool put;
+ bool use_links = dev->power.links_count > 0;
if (dev->power.irq_safe) {
spin_unlock(&dev->power.lock);
- } else if (!use_links) {
- spin_unlock_irq(&dev->power.lock);
} else {
- get = dev->power.runtime_status == RPM_RESUMING;
-
spin_unlock_irq(&dev->power.lock);
- /* Resume suppliers if necessary. */
- if (get) {
+ /*
+ * Resume suppliers if necessary.
+ *
+ * The device's runtime PM status cannot change until this
+ * routine returns, so it is safe to read the status outside of
+ * the lock.
+ */
+ if (use_links && dev->power.runtime_status == RPM_RESUMING) {
idx = device_links_read_lock();
retval = rpm_get_suppliers(dev);
- if (retval)
+ if (retval) {
+ rpm_put_suppliers(dev);
goto fail;
+ }
device_links_read_unlock(idx);
}
if (dev->power.irq_safe) {
spin_lock(&dev->power.lock);
- return retval;
- }
-
- spin_lock_irq(&dev->power.lock);
-
- if (!use_links)
- return retval;
-
- /*
- * If the device is suspending and the callback has returned success,
- * drop the usage counters of the suppliers that have been reference
- * counted on its resume.
- *
- * Do that if the resume fails too.
- */
- put = dev->power.runtime_status == RPM_SUSPENDING && !retval;
- if (put)
- __update_runtime_status(dev, RPM_SUSPENDED);
- else
- put = get && retval;
-
- if (put) {
- spin_unlock_irq(&dev->power.lock);
+ } else {
+ /*
+ * If the device is suspending and the callback has returned
+ * success, drop the usage counters of the suppliers that have
+ * been reference counted on its resume.
+ *
+ * Do that if resume fails too.
+ */
+ if (use_links
+ && ((dev->power.runtime_status == RPM_SUSPENDING && !retval)
+ || (dev->power.runtime_status == RPM_RESUMING && retval))) {
+ idx = device_links_read_lock();
- idx = device_links_read_lock();
+ __rpm_put_suppliers(dev, false);
fail:
- rpm_put_suppliers(dev);
-
- device_links_read_unlock(idx);
+ device_links_read_unlock(idx);
+ }
spin_lock_irq(&dev->power.lock);
}
goto out;
}
+ if (dev->power.irq_safe)
+ goto out;
+
/* Maybe the parent is now able to suspend. */
- if (parent && !parent->power.ignore_children && !dev->power.irq_safe) {
+ if (parent && !parent->power.ignore_children) {
spin_unlock(&dev->power.lock);
spin_lock(&parent->power.lock);
spin_lock(&dev->power.lock);
}
+ /* Maybe the suppliers are now able to suspend. */
+ if (dev->power.links_count > 0) {
+ spin_unlock_irq(&dev->power.lock);
+
+ rpm_suspend_suppliers(dev);
+
+ spin_lock_irq(&dev->power.lock);
+ }
out:
trace_rpm_return_int_rcuidle(dev, _THIS_IP_, retval);
device_links_read_lock_held())
if (link->flags & DL_FLAG_PM_RUNTIME) {
link->supplier_preactivated = true;
- refcount_inc(&link->rpm_active);
pm_runtime_get_sync(link->supplier);
+ refcount_inc(&link->rpm_active);
}
device_links_read_unlock(idx);
void pm_runtime_put_suppliers(struct device *dev)
{
struct device_link *link;
+ unsigned long flags;
+ bool put;
int idx;
idx = device_links_read_lock();
device_links_read_lock_held())
if (link->supplier_preactivated) {
link->supplier_preactivated = false;
- if (refcount_dec_not_one(&link->rpm_active))
+ spin_lock_irqsave(&dev->power.lock, flags);
+ put = pm_runtime_status_suspended(dev) &&
+ refcount_dec_not_one(&link->rpm_active);
+ spin_unlock_irqrestore(&dev->power.lock, flags);
+ if (put)
pm_runtime_put(link->supplier);
}
if (software_node_to_swnode(node))
return -EEXIST;
+ if (node->parent && !parent)
+ return -EINVAL;
+
return PTR_ERR_OR_ZERO(swnode_register(node, parent, 0));
}
EXPORT_SYMBOL_GPL(software_node_register);
/**
* device_add_software_node - Assign software node to a device
* @dev: The device the software node is meant for.
- * @swnode: The software node.
+ * @node: The software node.
*
- * This function will register @swnode and make it the secondary firmware node
- * pointer of @dev. If @dev has no primary node, then @swnode will become the primary
- * node.
+ * This function will make @node the secondary firmware node pointer of @dev. If
+ * @dev has no primary node, then @node will become the primary node. The
+ * function will register @node automatically if it wasn't already registered.
*/
-int device_add_software_node(struct device *dev, const struct software_node *swnode)
+int device_add_software_node(struct device *dev, const struct software_node *node)
{
+ struct swnode *swnode;
int ret;
/* Only one software node per device. */
if (dev_to_swnode(dev))
return -EBUSY;
- ret = software_node_register(swnode);
- if (ret)
- return ret;
+ swnode = software_node_to_swnode(node);
+ if (swnode) {
+ kobject_get(&swnode->kobj);
+ } else {
+ ret = software_node_register(node);
+ if (ret)
+ return ret;
+
+ swnode = software_node_to_swnode(node);
+ }
- set_secondary_fwnode(dev, software_node_fwnode(swnode));
+ set_secondary_fwnode(dev, &swnode->fwnode);
return 0;
}
* A followup commit may allow even bigger BIO sizes,
* once we thought that through. */
#define DRBD_MAX_BIO_SIZE (1U << 20)
-#if DRBD_MAX_BIO_SIZE > (BIO_MAX_PAGES << PAGE_SHIFT)
+#if DRBD_MAX_BIO_SIZE > (BIO_MAX_VECS << PAGE_SHIFT)
#error Architecture not supported: DRBD_MAX_BIO_SIZE > BIO_MAX_SIZE
#endif
#define DRBD_MAX_BIO_SIZE_SAFE (1U << 12) /* Works always = 4k */
module_param(FLOPPY_IRQ, int, 0);
module_param(FLOPPY_DMA, int, 0);
MODULE_AUTHOR("Alain L. Knaff");
-MODULE_SUPPORTED_DEVICE("fd");
MODULE_LICENSE("GPL");
/* This doesn't actually get used other than for module information */
}
if (dev->zoned)
- cmd->error = null_process_zoned_cmd(cmd, op,
- sector, nr_sectors);
+ sts = null_process_zoned_cmd(cmd, op, sector, nr_sectors);
else
- cmd->error = null_process_cmd(cmd, op, sector, nr_sectors);
+ sts = null_process_cmd(cmd, op, sector, nr_sectors);
+
+ /* Do not overwrite errors (e.g. timeout errors) */
+ if (cmd->error == BLK_STS_OK)
+ cmd->error = sts;
out:
nullb_complete_cmd(cmd);
static enum blk_eh_timer_return null_timeout_rq(struct request *rq, bool res)
{
+ struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq);
+
pr_info("rq %p timed out\n", rq);
- blk_mq_complete_request(rq);
+
+ /*
+ * If the device is marked as blocking (i.e. memory backed or zoned
+ * device), the submission path may be blocked waiting for resources
+ * and cause real timeouts. For these real timeouts, the submission
+ * path will complete the request using blk_mq_complete_request().
+ * Only fake timeouts need to execute blk_mq_complete_request() here.
+ */
+ cmd->error = BLK_STS_TIMEOUT;
+ if (cmd->fake_timeout)
+ blk_mq_complete_request(rq);
return BLK_EH_DONE;
}
cmd->rq = bd->rq;
cmd->error = BLK_STS_OK;
cmd->nq = nq;
+ cmd->fake_timeout = should_timeout_request(bd->rq);
blk_mq_start_request(bd->rq);
return BLK_STS_OK;
}
}
- if (should_timeout_request(bd->rq))
+ if (cmd->fake_timeout)
return BLK_STS_OK;
return null_handle_cmd(cmd, sector, nr_sectors, req_op(bd->rq));
blk_status_t error;
struct nullb_queue *nq;
struct hrtimer timer;
+ bool fake_timeout;
};
struct nullb_queue {
card->event_wq = create_singlethread_workqueue(DRIVER_NAME"_event");
if (!card->event_wq) {
dev_err(CARD_TO_DEV(card), "Failed card event setup.\n");
+ st = -ENOMEM;
goto failed_event_handler;
}
if (card->mm_pages[0].desc == NULL ||
card->mm_pages[1].desc == NULL) {
dev_printk(KERN_ERR, &card->dev->dev, "alloc failed\n");
+ ret = -ENOMEM;
goto failed_alloc;
}
reset_page(&card->mm_pages[0]);
spin_lock_init(&card->lock);
card->queue = blk_alloc_queue(NUMA_NO_NODE);
- if (!card->queue)
+ if (!card->queue) {
+ ret = -ENOMEM;
goto failed_alloc;
+ }
tasklet_init(&card->tasklet, process_page, (unsigned long)card);
out:
for (i = last_map; i < num; i++) {
/* Don't zap current batch's valid persistent grants. */
- if(i >= last_map + segs_to_map)
+ if(i >= map_until)
pages[i]->persistent_gnt = NULL;
pages[i]->handle = BLKBACK_INVALID_HANDLE;
}
struct work_struct free_work;
unsigned int nr_ring_pages;
+ bool multi_ref;
/* All rings for this device. */
struct xen_blkif_ring *rings;
unsigned int nr_rings;
for (i = 0; i < nr_grefs; i++) {
char ring_ref_name[RINGREF_NAME_LEN];
- snprintf(ring_ref_name, RINGREF_NAME_LEN, "ring-ref%u", i);
+ if (blkif->multi_ref)
+ snprintf(ring_ref_name, RINGREF_NAME_LEN, "ring-ref%u", i);
+ else {
+ WARN_ON(i != 0);
+ snprintf(ring_ref_name, RINGREF_NAME_LEN, "ring-ref");
+ }
+
err = xenbus_scanf(XBT_NIL, dir, ring_ref_name,
"%u", &ring_ref[i]);
if (err != 1) {
- if (nr_grefs == 1)
- break;
-
err = -EINVAL;
xenbus_dev_fatal(dev, err, "reading %s/%s",
dir, ring_ref_name);
}
}
- if (err != 1) {
- WARN_ON(nr_grefs != 1);
-
- err = xenbus_scanf(XBT_NIL, dir, "ring-ref", "%u",
- &ring_ref[0]);
- if (err != 1) {
- err = -EINVAL;
- xenbus_dev_fatal(dev, err, "reading %s/ring-ref", dir);
- return err;
- }
- }
-
err = -ENOMEM;
for (i = 0; i < nr_grefs * XEN_BLKIF_REQS_PER_PAGE; i++) {
req = kzalloc(sizeof(*req), GFP_KERNEL);
blkif->nr_rings, blkif->blk_protocol, protocol,
blkif->vbd.feature_gnt_persistent ? "persistent grants" : "");
- ring_page_order = xenbus_read_unsigned(dev->otherend,
- "ring-page-order", 0);
-
- if (ring_page_order > xen_blkif_max_ring_order) {
+ err = xenbus_scanf(XBT_NIL, dev->otherend, "ring-page-order", "%u",
+ &ring_page_order);
+ if (err != 1) {
+ blkif->nr_ring_pages = 1;
+ blkif->multi_ref = false;
+ } else if (ring_page_order <= xen_blkif_max_ring_order) {
+ blkif->nr_ring_pages = 1 << ring_page_order;
+ blkif->multi_ref = true;
+ } else {
err = -EINVAL;
xenbus_dev_fatal(dev, err,
"requested ring page order %d exceed max:%d",
return err;
}
- blkif->nr_ring_pages = 1 << ring_page_order;
-
if (blkif->nr_rings == 1)
return read_per_ring_refs(&blkif->rings[0], dev->otherend);
else {
}
/*
- * physcial-sector-size is a newer field, so old backends may not
+ * physical-sector-size is a newer field, so old backends may not
* provide this. Assume physical sector size to be the same as
* sector_size in that case.
*/
struct bio_vec bio_vec;
struct page *page;
ssize_t ret = len;
- int mode;
+ int mode, err;
unsigned long blk_idx = 0;
if (sysfs_streq(buf, "idle"))
if (strncmp(buf, PAGE_WB_SIG, sizeof(PAGE_WB_SIG) - 1))
return -EINVAL;
- ret = kstrtol(buf + sizeof(PAGE_WB_SIG) - 1, 10, &index);
- if (ret || index >= nr_pages)
+ if (kstrtol(buf + sizeof(PAGE_WB_SIG) - 1, 10, &index) ||
+ index >= nr_pages)
return -EINVAL;
nr_pages = 1;
goto release_init_lock;
}
- while (nr_pages--) {
+ for (; nr_pages != 0; index++, nr_pages--) {
struct bio_vec bvec;
bvec.bv_page = page;
* XXX: A single page IO would be inefficient for write
* but it would be not bad as starter.
*/
- ret = submit_bio_wait(&bio);
- if (ret) {
+ err = submit_bio_wait(&bio);
+ if (err) {
zram_slot_lock(zram, index);
zram_clear_flag(zram, index, ZRAM_UNDER_WB);
zram_clear_flag(zram, index, ZRAM_IDLE);
zram_slot_unlock(zram, index);
+ /*
+ * Return last IO error unless every IO were
+ * not suceeded.
+ */
+ ret = err;
continue;
}
module_exit(rsi_91x_bt_module_exit);
MODULE_AUTHOR("Redpine Signals Inc");
MODULE_DESCRIPTION("RSI BT driver");
-MODULE_SUPPORTED_DEVICE("RSI-BT");
MODULE_LICENSE("Dual BSD/GPL");
data->diag = NULL;
}
- if (!enable_autosuspend)
- usb_disable_autosuspend(data->udev);
+ if (enable_autosuspend)
+ usb_enable_autosuspend(data->udev);
err = hci_register_dev(hdev);
if (err < 0)
gpiod_put(data->reset_gpio);
hci_free_dev(hdev);
-
- if (!enable_autosuspend)
- usb_enable_autosuspend(data->udev);
}
#ifdef CONFIG_PM
/*
* Turris Mox module configuration bus driver
*
- * Copyright (C) 2019 Marek Behun <marek.behun@nic.cz>
+ * Copyright (C) 2019 Marek Behún <kabel@kernel.org>
*/
#include <dt-bindings/bus/moxtet.h>
}
module_exit(moxtet_exit);
-MODULE_AUTHOR("Marek Behun <marek.behun@nic.cz>");
+MODULE_AUTHOR("Marek Behun <kabel@kernel.org>");
MODULE_DESCRIPTION("CZ.NIC's Turris Mox module configuration bus");
MODULE_LICENSE("GPL v2");
* This part of the memory is above 4 GB, so we don't
* care for the MBus bridge hole.
*/
- if (reg_start >= 0x100000000ULL)
+ if ((u64)reg_start >= 0x100000000ULL)
continue;
/*
*/
l3->debug_irq = platform_get_irq(pdev, 0);
ret = devm_request_irq(l3->dev, l3->debug_irq, l3_interrupt_handler,
- 0x0, "l3-dbg-irq", l3);
+ IRQF_NO_THREAD, "l3-dbg-irq", l3);
if (ret) {
dev_err(l3->dev, "request_irq failed for %d\n",
l3->debug_irq);
l3->app_irq = platform_get_irq(pdev, 1);
ret = devm_request_irq(l3->dev, l3->app_irq, l3_interrupt_handler,
- 0x0, "l3-app-irq", l3);
+ IRQF_NO_THREAD, "l3-app-irq", l3);
if (ret)
dev_err(l3->dev, "request_irq failed for %d\n", l3->app_irq);
pm_runtime_put_sync(&pdev->dev);
pm_runtime_disable(&pdev->dev);
- reset_control_assert(ddata->rsts);
+
+ if (!reset_control_status(ddata->rsts))
+ reset_control_assert(ddata->rsts);
unprepare:
sysc_unprepare(ddata);
config AGP_PARISC
tristate "HP Quicksilver AGP support"
- depends on AGP && PARISC && 64BIT
+ depends on AGP && PARISC && 64BIT && IOMMU_SBA
help
This option gives you AGP GART support for the HP Quicksilver
AGP bus adapter on HP PA-RISC machines (Ok, just on the C8000
MODULE_LICENSE("GPL");
MODULE_ALIAS_MISCDEV(AC_MINOR);
-MODULE_SUPPORTED_DEVICE("ac");
-
-
static struct applicom_board {
unsigned long PhysIO;
void __iomem *RamIO;
static int ba431_trng_probe(struct platform_device *pdev)
{
struct ba431_trng *ba431;
- struct resource *res;
int ret;
ba431 = devm_kzalloc(&pdev->dev, sizeof(*ba431), GFP_KERNEL);
ba431->dev = &pdev->dev;
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- ba431->base = devm_ioremap_resource(&pdev->dev, res);
+ ba431->base = devm_platform_ioremap_resource(pdev, 0);
if (IS_ERR(ba431->base))
return PTR_ERR(ba431->base);
platform_set_drvdata(pdev, ba431);
- ret = hwrng_register(&ba431->rng);
+ ret = devm_hwrng_register(&pdev->dev, &ba431->rng);
if (ret) {
dev_err(&pdev->dev, "BA431 registration failed (%d)\n", ret);
return ret;
return 0;
}
-static int ba431_trng_remove(struct platform_device *pdev)
-{
- struct ba431_trng *ba431 = platform_get_drvdata(pdev);
-
- hwrng_unregister(&ba431->rng);
-
- return 0;
-}
-
static const struct of_device_id ba431_trng_dt_ids[] = {
{ .compatible = "silex-insight,ba431-rng", .data = NULL },
{ /* sentinel */ }
.of_match_table = ba431_trng_dt_ids,
},
.probe = ba431_trng_probe,
- .remove = ba431_trng_remove,
};
module_platform_driver(ba431_trng_driver);
#include <linux/platform_device.h>
#include <linux/printk.h>
#include <linux/clk.h>
+#include <linux/reset.h>
#define RNG_CTRL 0x0
#define RNG_STATUS 0x4
void __iomem *base;
bool mask_interrupts;
struct clk *clk;
+ struct reset_control *reset;
};
static inline struct bcm2835_rng_priv *to_rng_priv(struct hwrng *rng)
int ret = 0;
u32 val;
- if (!IS_ERR(priv->clk)) {
- ret = clk_prepare_enable(priv->clk);
- if (ret)
- return ret;
- }
+ ret = clk_prepare_enable(priv->clk);
+ if (ret)
+ return ret;
+
+ ret = reset_control_reset(priv->reset);
+ if (ret)
+ return ret;
if (priv->mask_interrupts) {
/* mask the interrupt */
/* disable rng hardware */
rng_writel(priv, 0, RNG_CTRL);
- if (!IS_ERR(priv->clk))
- clk_disable_unprepare(priv->clk);
+ clk_disable_unprepare(priv->clk);
}
struct bcm2835_rng_of_data {
return PTR_ERR(priv->base);
/* Clock is optional on most platforms */
- priv->clk = devm_clk_get(dev, NULL);
- if (PTR_ERR(priv->clk) == -EPROBE_DEFER)
- return -EPROBE_DEFER;
+ priv->clk = devm_clk_get_optional(dev, NULL);
+ if (IS_ERR(priv->clk))
+ return PTR_ERR(priv->clk);
+
+ priv->reset = devm_reset_control_get_optional_exclusive(dev, NULL);
+ if (IS_ERR(priv->reset))
+ return PTR_ERR(priv->reset);
priv->rng.name = pdev->name;
priv->rng.init = bcm2835_rng_init;
static int cctrng_probe(struct platform_device *pdev)
{
- struct resource *req_mem_cc_regs = NULL;
struct cctrng_drvdata *drvdata;
struct device *dev = &pdev->dev;
int rc = 0;
drvdata->circ.buf = (char *)drvdata->data_buf;
- /* Get device resources */
- /* First CC registers space */
- req_mem_cc_regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- /* Map registers space */
- drvdata->cc_base = devm_ioremap_resource(dev, req_mem_cc_regs);
+ drvdata->cc_base = devm_platform_ioremap_resource(pdev, 0);
if (IS_ERR(drvdata->cc_base)) {
dev_err(dev, "Failed to ioremap registers");
return PTR_ERR(drvdata->cc_base);
}
- dev_dbg(dev, "Got MEM resource (%s): %pR\n", req_mem_cc_regs->name,
- req_mem_cc_regs);
- dev_dbg(dev, "CC registers mapped from %pa to 0x%p\n",
- &req_mem_cc_regs->start, drvdata->cc_base);
-
/* Then IRQ */
irq = platform_get_irq(pdev, 0);
- if (irq < 0) {
- dev_err(dev, "Failed getting IRQ resource\n");
+ if (irq < 0)
return irq;
- }
/* parse sampling rate from device tree */
rc = cc_trng_parse_sampling_ratio(drvdata);
atomic_set(&drvdata->pending_hw, 1);
/* registration of the hwrng device */
- rc = hwrng_register(&drvdata->rng);
+ rc = devm_hwrng_register(dev, &drvdata->rng);
if (rc) {
dev_err(dev, "Could not register hwrng device.\n");
goto post_pm_err;
dev_dbg(dev, "Releasing cctrng resources...\n");
- hwrng_unregister(&drvdata->rng);
-
cc_trng_pm_fini(drvdata);
cc_trng_clk_fini(drvdata);
struct device_attribute *attr,
char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%d\n", cur_rng_set_by_user);
+ return sysfs_emit(buf, "%d\n", cur_rng_set_by_user);
}
static DEVICE_ATTR(rng_current, S_IRUGO | S_IWUSR,
*/
#include <linux/hw_random.h>
+#include <linux/io.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/stop_machine.h>
#include <linux/delay.h>
#include <linux/slab.h>
-#include <asm/io.h>
#define PFX KBUILD_MODNAME ": "
#include <linux/of_address.h>
#include <linux/interrupt.h>
#include <linux/clk.h>
-
-#include <asm/io.h>
+#include <linux/io.h>
#define RNG_REG_STATUS_RDY (1 << 0)
static int of_get_omap_rng_device_details(struct omap_rng_dev *priv,
struct platform_device *pdev)
{
- const struct of_device_id *match;
struct device *dev = &pdev->dev;
int irq, err;
- match = of_match_device(of_match_ptr(omap_rng_of_match), dev);
- if (!match) {
- dev_err(dev, "no compatible OF match\n");
- return -EINVAL;
- }
- priv->pdata = match->data;
+ priv->pdata = of_device_get_match_data(dev);
+ if (!priv->pdata)
+ return -ENODEV;
+
if (of_device_is_compatible(dev->of_node, "ti,omap4-rng") ||
of_device_is_compatible(dev->of_node, "inside-secure,safexcel-eip76")) {
priv->rng.name = pdev->name;
priv->rng.read = pic32_rng_read;
- ret = hwrng_register(&priv->rng);
+ ret = devm_hwrng_register(&pdev->dev, &priv->rng);
if (ret)
goto err_register;
{
struct pic32_rng *rng = platform_get_drvdata(pdev);
- hwrng_unregister(&rng->rng);
writel(0, rng->base + RNGCON);
clk_disable_unprepare(rng->clk);
return 0;
return hwrng_register(&pseries_rng);
}
-static int pseries_rng_remove(struct vio_dev *dev)
+static void pseries_rng_remove(struct vio_dev *dev)
{
hwrng_unregister(&pseries_rng);
- return 0;
}
static const struct vio_device_id pseries_rng_driver_ids[] = {
int ret;
struct xiphera_trng *trng;
struct device *dev = &pdev->dev;
- struct resource *res;
trng = devm_kzalloc(dev, sizeof(*trng), GFP_KERNEL);
if (!trng)
return -ENOMEM;
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- trng->mem = devm_ioremap_resource(dev, res);
+ trng->mem = devm_platform_ioremap_resource(pdev, 0);
if (IS_ERR(trng->mem))
return PTR_ERR(trng->mem);
unsigned short add_ptr;
unsigned short input_rotate;
int entropy_count;
- unsigned int initialized:1;
unsigned int last_data_init:1;
__u8 last_data[EXTRACT_SIZE];
};
*/
static void credit_entropy_bits(struct entropy_store *r, int nbits)
{
- int entropy_count, orig, has_initialized = 0;
+ int entropy_count, orig;
const int pool_size = r->poolinfo->poolfracbits;
int nfrac = nbits << ENTROPY_SHIFT;
if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig)
goto retry;
- if (has_initialized) {
- r->initialized = 1;
- kill_fasync(&fasync, SIGIO, POLL_IN);
- }
-
trace_credit_entropy_bits(r->name, nbits,
entropy_count >> ENTROPY_SHIFT, _RET_IP_);
if (r == &input_pool) {
int entropy_bits = entropy_count >> ENTROPY_SHIFT;
- if (crng_init < 2) {
- if (entropy_bits < 128)
- return;
+ if (crng_init < 2 && entropy_bits >= 128)
crng_reseed(&primary_crng, r);
- entropy_bits = ENTROPY_BITS(r);
- }
}
}
static void __maybe_unused crng_initialize_secondary(struct crng_state *crng)
{
- memcpy(&crng->state[0], "expand 32-byte k", 16);
+ chacha_init_consts(crng->state);
_get_random_bytes(&crng->state[4], sizeof(__u32) * 12);
crng_init_try_arch(crng);
crng->init_time = jiffies - CRNG_RESEED_INTERVAL - 1;
static void __init crng_initialize_primary(struct crng_state *crng)
{
- memcpy(&crng->state[0], "expand 32-byte k", 16);
+ chacha_init_consts(crng->state);
_extract_entropy(&input_pool, &crng->state[4], sizeof(__u32) * 12, 0);
if (crng_init_try_arch_early(crng) && trust_cpu) {
invalidate_batched_entropy();
}
/*
- * This function does the actual extraction for extract_entropy and
- * extract_entropy_user.
+ * This function does the actual extraction for extract_entropy.
*
* Note: we assume that .poolwords is a multiple of 16 words.
*/
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jonathan Buzzard <jonathan@buzzard.org.uk>");
MODULE_DESCRIPTION("Toshiba laptop SMM driver");
-MODULE_SUPPORTED_DEVICE("toshiba");
static DEFINE_MUTEX(tosh_mutex);
static int tosh_fn;
};
};
+/* Check that the given log is indeed a TPM2 log. */
+static bool tpm_is_tpm2_log(void *bios_event_log, u64 len)
+{
+ struct tcg_efi_specid_event_head *efispecid;
+ struct tcg_pcr_event *event_header;
+ int n;
+
+ if (len < sizeof(*event_header))
+ return false;
+ len -= sizeof(*event_header);
+ event_header = bios_event_log;
+
+ if (len < sizeof(*efispecid))
+ return false;
+ efispecid = (struct tcg_efi_specid_event_head *)event_header->event;
+
+ n = memcmp(efispecid->signature, TCG_SPECID_SIG,
+ sizeof(TCG_SPECID_SIG));
+ return n == 0;
+}
+
/* read binary bios log */
int tpm_read_log_acpi(struct tpm_chip *chip)
{
struct acpi_table_tpm2 *tbl;
struct acpi_tpm2_phy *tpm2_phy;
int format;
+ int ret;
log = &chip->log;
log->bios_event_log_end = log->bios_event_log + len;
+ ret = -EIO;
virt = acpi_os_map_iomem(start, len);
if (!virt)
goto err;
memcpy_fromio(log->bios_event_log, virt, len);
acpi_os_unmap_iomem(virt, len);
+
+ if (chip->flags & TPM_CHIP_FLAG_TPM2 &&
+ !tpm_is_tpm2_log(log->bios_event_log, len)) {
+ /* try EFI log next */
+ ret = -ENODEV;
+ goto err;
+ }
+
return format;
err:
kfree(log->bios_event_log);
log->bios_event_log = NULL;
- return -EIO;
+ return ret;
}
int log_version;
int rc = 0;
+ if (chip->flags & TPM_CHIP_FLAG_VIRTUAL)
+ return;
+
rc = tpm_read_log(chip);
if (rc < 0)
return;
{
struct efi_tcg2_final_events_table *final_tbl = NULL;
+ int final_events_log_size = efi_tpm_final_log_size;
struct linux_efi_tpm_eventlog *log_tbl;
struct tpm_bios_log *log;
u32 log_size;
ret = tpm_log_version;
if (efi.tpm_final_log == EFI_INVALID_TABLE_ADDR ||
- efi_tpm_final_log_size == 0 ||
+ final_events_log_size == 0 ||
tpm_log_version != EFI_TCG2_EVENT_LOG_FORMAT_TCG_2)
goto out;
final_tbl = memremap(efi.tpm_final_log,
- sizeof(*final_tbl) + efi_tpm_final_log_size,
+ sizeof(*final_tbl) + final_events_log_size,
MEMREMAP_WB);
if (!final_tbl) {
pr_err("Could not map UEFI TPM final log\n");
goto out;
}
- efi_tpm_final_log_size -= log_tbl->final_events_preboot_size;
+ /*
+ * The 'final events log' size excludes the 'final events preboot log'
+ * at its beginning.
+ */
+ final_events_log_size -= log_tbl->final_events_preboot_size;
+ /*
+ * Allocate memory for the 'combined log' where we will append the
+ * 'final events log' to.
+ */
tmp = krealloc(log->bios_event_log,
- log_size + efi_tpm_final_log_size,
+ log_size + final_events_log_size,
GFP_KERNEL);
if (!tmp) {
kfree(log->bios_event_log);
log->bios_event_log = tmp;
/*
- * Copy any of the final events log that didn't also end up in the
- * main log. Events can be logged in both if events are generated
+ * Append any of the 'final events log' that didn't also end up in the
+ * 'main log'. Events can be logged in both if events are generated
* between GetEventLog() and ExitBootServices().
*/
memcpy((void *)log->bios_event_log + log_size,
final_tbl->events + log_tbl->final_events_preboot_size,
- efi_tpm_final_log_size);
+ final_events_log_size);
+ /*
+ * The size of the 'combined log' is the size of the 'main log' plus
+ * the size of the 'final events log'.
+ */
log->bios_event_log_end = log->bios_event_log +
- log_size + efi_tpm_final_log_size;
+ log_size + final_events_log_size;
out:
memunmap(final_tbl);
*
* Return: Always 0.
*/
-static int tpm_ibmvtpm_remove(struct vio_dev *vdev)
+static void tpm_ibmvtpm_remove(struct vio_dev *vdev)
{
struct tpm_chip *chip = dev_get_drvdata(&vdev->dev);
struct ibmvtpm_dev *ibmvtpm = dev_get_drvdata(&chip->dev);
kfree(ibmvtpm);
/* For tpm_ibmvtpm_get_desired_dma */
dev_set_drvdata(&vdev->dev, NULL);
-
- return 0;
}
/**
expected = be32_to_cpup((__be32 *)(buf + 2));
if (expected > buf_len) {
dev_err(&chip->dev, "Buffer too small to receive i2c data\n");
+ rc = -E2BIG;
goto out_err;
}
static void devm_clk_hw_register_fixed_factor_release(struct device *dev, void *res)
{
- clk_hw_unregister_fixed_factor(&((struct clk_fixed_factor *)res)->hw);
+ struct clk_fixed_factor *fix = res;
+
+ /*
+ * We can not use clk_hw_unregister_fixed_factor, since it will kfree()
+ * the hw, resulting in double free. Just unregister the hw and let
+ * devres code kfree() it.
+ */
+ clk_hw_unregister(&fix->hw);
}
static struct clk_hw *
/* search the list of notifiers for this clk */
list_for_each_entry(cn, &clk_notifier_list, node)
if (cn->clk == clk)
- break;
+ goto found;
/* if clk wasn't in the notifier list, allocate new clk_notifier */
- if (cn->clk != clk) {
- cn = kzalloc(sizeof(*cn), GFP_KERNEL);
- if (!cn)
- goto out;
+ cn = kzalloc(sizeof(*cn), GFP_KERNEL);
+ if (!cn)
+ goto out;
- cn->clk = clk;
- srcu_init_notifier_head(&cn->notifier_head);
+ cn->clk = clk;
+ srcu_init_notifier_head(&cn->notifier_head);
- list_add(&cn->node, &clk_notifier_list);
- }
+ list_add(&cn->node, &clk_notifier_list);
+found:
ret = srcu_notifier_chain_register(&cn->notifier_head, nb);
clk->core->notifier_count++;
*/
int clk_notifier_unregister(struct clk *clk, struct notifier_block *nb)
{
- struct clk_notifier *cn = NULL;
- int ret = -EINVAL;
+ struct clk_notifier *cn;
+ int ret = -ENOENT;
if (!clk || !nb)
return -EINVAL;
clk_prepare_lock();
- list_for_each_entry(cn, &clk_notifier_list, node)
- if (cn->clk == clk)
- break;
-
- if (cn->clk == clk) {
- ret = srcu_notifier_chain_unregister(&cn->notifier_head, nb);
+ list_for_each_entry(cn, &clk_notifier_list, node) {
+ if (cn->clk == clk) {
+ ret = srcu_notifier_chain_unregister(&cn->notifier_head, nb);
- clk->core->notifier_count--;
+ clk->core->notifier_count--;
- /* XXX the notifier code should handle this better */
- if (!cn->notifier_head.head) {
- srcu_cleanup_notifier_head(&cn->notifier_head);
- list_del(&cn->node);
- kfree(cn);
+ /* XXX the notifier code should handle this better */
+ if (!cn->notifier_head.head) {
+ srcu_cleanup_notifier_head(&cn->notifier_head);
+ list_del(&cn->node);
+ kfree(cn);
+ }
+ break;
}
-
- } else {
- ret = -ENOENT;
}
clk_prepare_unlock();
.name = "cam_cc_bps_clk_src",
.parent_data = cam_cc_parent_data_2,
.num_parents = 5,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
.name = "cam_cc_cci_0_clk_src",
.parent_data = cam_cc_parent_data_5,
.num_parents = 3,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
.name = "cam_cc_cci_1_clk_src",
.parent_data = cam_cc_parent_data_5,
.num_parents = 3,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
.name = "cam_cc_cphy_rx_clk_src",
.parent_data = cam_cc_parent_data_3,
.num_parents = 6,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
.name = "cam_cc_csi0phytimer_clk_src",
.parent_data = cam_cc_parent_data_0,
.num_parents = 4,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
.name = "cam_cc_csi1phytimer_clk_src",
.parent_data = cam_cc_parent_data_0,
.num_parents = 4,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
.name = "cam_cc_csi2phytimer_clk_src",
.parent_data = cam_cc_parent_data_0,
.num_parents = 4,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
.name = "cam_cc_csi3phytimer_clk_src",
.parent_data = cam_cc_parent_data_0,
.num_parents = 4,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
.name = "cam_cc_fast_ahb_clk_src",
.parent_data = cam_cc_parent_data_0,
.num_parents = 4,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
.name = "cam_cc_icp_clk_src",
.parent_data = cam_cc_parent_data_2,
.num_parents = 5,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
.name = "cam_cc_ife_0_clk_src",
.parent_data = cam_cc_parent_data_4,
.num_parents = 4,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
.name = "cam_cc_ife_0_csid_clk_src",
.parent_data = cam_cc_parent_data_3,
.num_parents = 6,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
.name = "cam_cc_ife_1_clk_src",
.parent_data = cam_cc_parent_data_4,
.num_parents = 4,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
.name = "cam_cc_ife_1_csid_clk_src",
.parent_data = cam_cc_parent_data_3,
.num_parents = 6,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
.parent_data = cam_cc_parent_data_4,
.num_parents = 4,
.flags = CLK_SET_RATE_PARENT,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
.name = "cam_cc_ife_lite_csid_clk_src",
.parent_data = cam_cc_parent_data_3,
.num_parents = 6,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
.name = "cam_cc_ipe_0_clk_src",
.parent_data = cam_cc_parent_data_2,
.num_parents = 5,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
.name = "cam_cc_jpeg_clk_src",
.parent_data = cam_cc_parent_data_2,
.num_parents = 5,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
.name = "cam_cc_lrme_clk_src",
.parent_data = cam_cc_parent_data_6,
.num_parents = 5,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
.name = "cam_cc_mclk0_clk_src",
.parent_data = cam_cc_parent_data_1,
.num_parents = 3,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
.name = "cam_cc_mclk1_clk_src",
.parent_data = cam_cc_parent_data_1,
.num_parents = 3,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
.name = "cam_cc_mclk2_clk_src",
.parent_data = cam_cc_parent_data_1,
.num_parents = 3,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
.name = "cam_cc_mclk3_clk_src",
.parent_data = cam_cc_parent_data_1,
.num_parents = 3,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
.name = "cam_cc_mclk4_clk_src",
.parent_data = cam_cc_parent_data_1,
.num_parents = 3,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
.parent_data = cam_cc_parent_data_0,
.num_parents = 4,
.flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_shared_ops,
},
};
struct clk_rate_request parent_req = { };
struct clk_rcg2_gfx3d *cgfx = to_clk_rcg2_gfx3d(hw);
struct clk_hw *xo, *p0, *p1, *p2;
- unsigned long request, p0_rate;
+ unsigned long p0_rate;
+ u8 mux_div = cgfx->div;
int ret;
p0 = cgfx->hws[0];
return 0;
}
- request = req->rate;
- if (cgfx->div > 1)
- parent_req.rate = request = request * cgfx->div;
+ if (mux_div == 0)
+ mux_div = 1;
+
+ parent_req.rate = req->rate * mux_div;
/* This has to be a fixed rate PLL */
p0_rate = clk_hw_get_rate(p0);
- if (request == p0_rate) {
+ if (parent_req.rate == p0_rate) {
req->rate = req->best_parent_rate = p0_rate;
req->best_parent_hw = p0;
return 0;
if (req->best_parent_hw == p0) {
/* Are we going back to a previously used rate? */
- if (clk_hw_get_rate(p2) == request)
+ if (clk_hw_get_rate(p2) == parent_req.rate)
req->best_parent_hw = p2;
else
req->best_parent_hw = p1;
return ret;
req->rate = req->best_parent_rate = parent_req.rate;
- if (cgfx->div > 1)
- req->rate /= cgfx->div;
+ req->rate /= mux_div;
return 0;
}
.num_clks = ARRAY_SIZE(sm8350_rpmh_clocks),
};
+/* Resource name must match resource id present in cmd-db */
+DEFINE_CLK_RPMH_ARC(sc7280, bi_tcxo, bi_tcxo_ao, "xo.lvl", 0x3, 4);
+
static struct clk_hw *sc7280_rpmh_clocks[] = {
- [RPMH_CXO_CLK] = &sdm845_bi_tcxo.hw,
- [RPMH_CXO_CLK_A] = &sdm845_bi_tcxo_ao.hw,
+ [RPMH_CXO_CLK] = &sc7280_bi_tcxo.hw,
+ [RPMH_CXO_CLK_A] = &sc7280_bi_tcxo_ao.hw,
[RPMH_LN_BB_CLK2] = &sdm845_ln_bb_clk2.hw,
[RPMH_LN_BB_CLK2_A] = &sdm845_ln_bb_clk2_ao.hw,
[RPMH_RF_CLK1] = &sdm845_rf_clk1.hw,
.name = "gcc_sdcc1_apps_clk_src",
.parent_data = gcc_parent_data_1,
.num_parents = 5,
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_floor_ops,
},
};
.name = "gcc_sdcc1_ice_core_clk_src",
.parent_data = gcc_parent_data_0,
.num_parents = 4,
- .ops = &clk_rcg2_floor_ops,
+ .ops = &clk_rcg2_ops,
},
};
val = readl(socfpgaclk->div_reg) >> socfpgaclk->shift;
val &= GENMASK(socfpgaclk->width - 1, 0);
/* Check for GPIO_DB_CLK by its offset */
- if ((int) socfpgaclk->div_reg & SOCFPGA_GPIO_DB_CLK_OFFSET)
+ if ((uintptr_t) socfpgaclk->div_reg & SOCFPGA_GPIO_DB_CLK_OFFSET)
div = val + 1;
else
div = (1 << val);
static unsigned arch_timers_present __initdata;
-static void __iomem *arch_counter_base;
+static void __iomem *arch_counter_base __ro_after_init;
struct arch_timer {
void __iomem *base;
#define to_arch_timer(e) container_of(e, struct arch_timer, evt)
-static u32 arch_timer_rate;
-static int arch_timer_ppi[ARCH_TIMER_MAX_TIMER_PPI];
+static u32 arch_timer_rate __ro_after_init;
+u32 arch_timer_rate1 __ro_after_init;
+static int arch_timer_ppi[ARCH_TIMER_MAX_TIMER_PPI] __ro_after_init;
static struct clock_event_device __percpu *arch_timer_evt;
-static enum arch_timer_ppi_nr arch_timer_uses_ppi = ARCH_TIMER_VIRT_PPI;
-static bool arch_timer_c3stop;
-static bool arch_timer_mem_use_virtual;
-static bool arch_counter_suspend_stop;
+static enum arch_timer_ppi_nr arch_timer_uses_ppi __ro_after_init = ARCH_TIMER_VIRT_PPI;
+static bool arch_timer_c3stop __ro_after_init;
+static bool arch_timer_mem_use_virtual __ro_after_init;
+static bool arch_counter_suspend_stop __ro_after_init;
#ifdef CONFIG_GENERIC_GETTIMEOFDAY
static enum vdso_clock_mode vdso_default = VDSO_CLOCKMODE_ARCHTIMER;
#else
#endif /* CONFIG_GENERIC_GETTIMEOFDAY */
static cpumask_t evtstrm_available = CPU_MASK_NONE;
-static bool evtstrm_enable = IS_ENABLED(CONFIG_ARM_ARCH_TIMER_EVTSTREAM);
+static bool evtstrm_enable __ro_after_init = IS_ENABLED(CONFIG_ARM_ARCH_TIMER_EVTSTREAM);
static int __init early_evtstrm_cfg(char *buf)
{
* to exist on arm64. arm doesn't use this before DT is probed so even
* if we don't have the cp15 accessors we won't have a problem.
*/
-u64 (*arch_timer_read_counter)(void) = arch_counter_get_cntvct;
+u64 (*arch_timer_read_counter)(void) __ro_after_init = arch_counter_get_cntvct;
EXPORT_SYMBOL_GPL(arch_timer_read_counter);
static u64 arch_counter_read(struct clocksource *cs)
* rate was probed first, and don't verify that others match. If the first node
* probed has a clock-frequency property, this overrides the HW register.
*/
-static void arch_timer_of_configure_rate(u32 rate, struct device_node *np)
+static void __init arch_timer_of_configure_rate(u32 rate, struct device_node *np)
{
/* Who has more than one independent system counter? */
if (arch_timer_rate)
pr_warn("frequency not available\n");
}
-static void arch_timer_banner(unsigned type)
+static void __init arch_timer_banner(unsigned type)
{
pr_info("%s%s%s timer(s) running at %lu.%02luMHz (%s%s%s).\n",
type & ARCH_TIMER_TYPE_CP15 ? "cp15" : "",
#define RATE_32K 32768
-#define TIMER_MODE_CONTINOUS 0x1
+#define TIMER_MODE_CONTINUOUS 0x1
#define TIMER_DOWNCOUNT_VAL 0xffffffff
#define PRCMU_TIMER_REF 0
/*
* The A9 sub system expects the timer to be configured as
- * a continous looping timer.
+ * a continuous looping timer.
* The PRCMU should configure it but if it for some reason
* don't we do it here.
*/
if (readl(clksrc_dbx500_timer_base + PRCMU_TIMER_MODE) !=
- TIMER_MODE_CONTINOUS) {
- writel(TIMER_MODE_CONTINOUS,
+ TIMER_MODE_CONTINUOUS) {
+ writel(TIMER_MODE_CONTINUOUS,
clksrc_dbx500_timer_base + PRCMU_TIMER_MODE);
writel(TIMER_DOWNCOUNT_VAL,
clksrc_dbx500_timer_base + PRCMU_TIMER_REF);
}
/*
- * Not all implementations use a periphal clock, so don't panic
+ * Not all implementations use a peripheral clock, so don't panic
* if it's not present
*/
pclk = of_clk_get_by_name(np, "pclk");
return 0;
timer_clk = of_clk_get_by_name(np, "timer");
- if (IS_ERR(timer_clk))
- return PTR_ERR(timer_clk);
+ if (IS_ERR(timer_clk)) {
+ ret = PTR_ERR(timer_clk);
+ goto out_pclk_disable;
+ }
ret = clk_prepare_enable(timer_clk);
if (ret)
- return ret;
+ goto out_timer_clk_put;
*rate = clk_get_rate(timer_clk);
- if (!(*rate))
- return -EINVAL;
+ if (!(*rate)) {
+ ret = -EINVAL;
+ goto out_timer_clk_disable;
+ }
return 0;
+
+out_timer_clk_disable:
+ clk_disable_unprepare(timer_clk);
+out_timer_clk_put:
+ clk_put(timer_clk);
+out_pclk_disable:
+ if (!IS_ERR(pclk)) {
+ clk_disable_unprepare(pclk);
+ clk_put(pclk);
+ }
+ iounmap(*base);
+ return ret;
}
static int __init add_clockevent(struct device_node *event_timer)
static __always_inline void hv_setup_sched_clock(void *sched_clock)
{
/* We're on x86/x64 *and* using PV ops */
- pv_ops.time.sched_clock = sched_clock;
+ paravirt_set_sched_clock(sched_clock);
}
#else /* !CONFIG_GENERIC_SCHED_CLOCK && !CONFIG_PARAVIRT */
static __always_inline void hv_setup_sched_clock(void *sched_clock) {}
{
/*
* Try to set up the TSC page clocksource. If it succeeds, we're
- * done. Otherwise, set up the MSR clocksoruce. At least one of
+ * done. Otherwise, set up the MSR clocksource. At least one of
* these will always be available except on very old versions of
* Hyper-V on x86. In that case we won't have a Hyper-V
* clocksource, but Linux will still run with a clocksource based
return PTR_ERR(ost->regs);
map = device_node_to_regmap(dev->parent->of_node);
- if (!map) {
+ if (IS_ERR(map)) {
dev_err(dev, "regmap not found");
- return -EINVAL;
+ return PTR_ERR(map);
}
ost->clk = devm_clk_get(dev, "ost");
.is64bit = false,
};
-static const struct ingenic_ost_soc_info jz4770_ost_soc_info = {
+static const struct ingenic_ost_soc_info jz4760b_ost_soc_info = {
.is64bit = true,
};
static const struct of_device_id ingenic_ost_of_match[] = {
{ .compatible = "ingenic,jz4725b-ost", .data = &jz4725b_ost_soc_info, },
- { .compatible = "ingenic,jz4770-ost", .data = &jz4770_ost_soc_info, },
+ { .compatible = "ingenic,jz4760b-ost", .data = &jz4760b_ost_soc_info, },
+ { .compatible = "ingenic,jz4770-ost", .data = &jz4760b_ost_soc_info, },
{ }
};
static const struct of_device_id ingenic_tcu_of_match[] = {
{ .compatible = "ingenic,jz4740-tcu", .data = &jz4740_soc_info, },
{ .compatible = "ingenic,jz4725b-tcu", .data = &jz4725b_soc_info, },
+ { .compatible = "ingenic,jz4760-tcu", .data = &jz4740_soc_info, },
{ .compatible = "ingenic,jz4770-tcu", .data = &jz4740_soc_info, },
{ .compatible = "ingenic,x1000-tcu", .data = &jz4740_soc_info, },
{ /* sentinel */ }
TIMER_OF_DECLARE(jz4740_tcu_intc, "ingenic,jz4740-tcu", ingenic_tcu_init);
TIMER_OF_DECLARE(jz4725b_tcu_intc, "ingenic,jz4725b-tcu", ingenic_tcu_init);
+TIMER_OF_DECLARE(jz4760_tcu_intc, "ingenic,jz4760-tcu", ingenic_tcu_init);
TIMER_OF_DECLARE(jz4770_tcu_intc, "ingenic,jz4770-tcu", ingenic_tcu_init);
TIMER_OF_DECLARE(x1000_tcu_intc, "ingenic,x1000-tcu", ingenic_tcu_init);
sh_cmt_write_cmcsr(ch, SH_CMT16_CMCSR_CMIE |
SH_CMT16_CMCSR_CKS512);
} else {
- sh_cmt_write_cmcsr(ch, SH_CMT32_CMCSR_CMM |
- SH_CMT32_CMCSR_CMTOUT_IE |
+ u32 cmtout = ch->cmt->info->model <= SH_CMT_48BIT ?
+ SH_CMT32_CMCSR_CMTOUT_IE : 0;
+ sh_cmt_write_cmcsr(ch, cmtout | SH_CMT32_CMCSR_CMM |
SH_CMT32_CMCSR_CMR_IRQ |
SH_CMT32_CMCSR_CKS_RCLK8);
}
tcaddr = tc.regs;
if (bits == 32) {
- /* use apropriate function to read 32 bit counter */
+ /* use appropriate function to read 32 bit counter */
clksrc.read = tc_get_cycles32;
- /* setup ony channel 0 */
+ /* setup only channel 0 */
tcb_setup_single_chan(&tc, best_divisor_idx);
tc_sched_clock = tc_sched_clock_read32;
tc_delay_timer.read_current_timer = tc_delay_timer_read32;
* to the MOD register latches the value into a buffer. The MOD
* register is updated with the value of its write buffer with
* the following scenario:
- * a, the counter source clock is diabled.
+ * a, the counter source clock is disabled.
*/
ftm_counter_disable(priv->clkevt_base);
break;
}
- /* Use the bigest prescaler if we didn't match one. */
+ /* Use the biggest prescaler if we didn't match one. */
if (*pres == MCHP_PIT64B_PRES_MAX)
*pres = MCHP_PIT64B_PRES_MAX - 1;
}
return 0;
}
+TIMER_OF_DECLARE(wpcm450, "nuvoton,wpcm450-timer", npcm7xx_timer_init);
TIMER_OF_DECLARE(npcm7xx, "nuvoton,npcm750-timer", npcm7xx_timer_init);
}
/**
- * timer_of_cleanup - release timer_of ressources
+ * timer_of_cleanup - release timer_of resources
* @to: timer_of structure
*
- * Release the ressources that has been used in timer_of_init().
+ * Release the resources that has been used in timer_of_init().
* This function should be called in init error cases
*/
void __init timer_of_cleanup(struct timer_of *to)
pistachio_clocksource_read_cycles(struct clocksource *cs)
{
struct pistachio_clocksource *pcs = to_pistachio_clocksource(cs);
- u32 counter, overflw;
+ u32 counter, overflow;
unsigned long flags;
/*
*/
raw_spin_lock_irqsave(&pcs->lock, flags);
- overflw = gpt_readl(pcs->base, TIMER_CURRENT_OVERFLOW_VALUE, 0);
+ overflow = gpt_readl(pcs->base, TIMER_CURRENT_OVERFLOW_VALUE, 0);
counter = gpt_readl(pcs->base, TIMER_CURRENT_VALUE, 0);
raw_spin_unlock_irqrestore(&pcs->lock, flags);
#include <linux/clk.h>
#include <linux/clocksource.h>
#include <linux/clockchips.h>
+#include <linux/cpuhotplug.h>
#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/iopoll.h>
struct dmtimer_systimer *t = &clkevt->t;
void __iomem *pend = t->base + t->pend;
- writel_relaxed(0xffffffff - cycles, t->base + t->counter);
while (readl_relaxed(pend) & WP_TCRR)
cpu_relax();
+ writel_relaxed(0xffffffff - cycles, t->base + t->counter);
- writel_relaxed(OMAP_TIMER_CTRL_ST, t->base + t->ctrl);
while (readl_relaxed(pend) & WP_TCLR)
cpu_relax();
+ writel_relaxed(OMAP_TIMER_CTRL_ST, t->base + t->ctrl);
return 0;
}
dmtimer_clockevent_shutdown(evt);
/* Looks like we need to first set the load value separately */
- writel_relaxed(clkevt->period, t->base + t->load);
while (readl_relaxed(pend) & WP_TLDR)
cpu_relax();
+ writel_relaxed(clkevt->period, t->base + t->load);
- writel_relaxed(clkevt->period, t->base + t->counter);
while (readl_relaxed(pend) & WP_TCRR)
cpu_relax();
+ writel_relaxed(clkevt->period, t->base + t->counter);
- writel_relaxed(OMAP_TIMER_CTRL_AR | OMAP_TIMER_CTRL_ST,
- t->base + t->ctrl);
while (readl_relaxed(pend) & WP_TCLR)
cpu_relax();
+ writel_relaxed(OMAP_TIMER_CTRL_AR | OMAP_TIMER_CTRL_ST,
+ t->base + t->ctrl);
return 0;
}
writel_relaxed(OMAP_TIMER_INT_OVERFLOW, t->base + t->wakeup);
}
-static int __init dmtimer_clockevent_init(struct device_node *np)
+static int __init dmtimer_clkevt_init_common(struct dmtimer_clockevent *clkevt,
+ struct device_node *np,
+ unsigned int features,
+ const struct cpumask *cpumask,
+ const char *name,
+ int rating)
{
- struct dmtimer_clockevent *clkevt;
struct clock_event_device *dev;
struct dmtimer_systimer *t;
int error;
- clkevt = kzalloc(sizeof(*clkevt), GFP_KERNEL);
- if (!clkevt)
- return -ENOMEM;
-
t = &clkevt->t;
dev = &clkevt->dev;
* We mostly use cpuidle_coupled with ARM local timers for runtime,
* so there's probably no use for CLOCK_EVT_FEAT_DYNIRQ here.
*/
- dev->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
- dev->rating = 300;
+ dev->features = features;
+ dev->rating = rating;
dev->set_next_event = dmtimer_set_next_event;
dev->set_state_shutdown = dmtimer_clockevent_shutdown;
dev->set_state_periodic = dmtimer_set_periodic;
dev->set_state_oneshot = dmtimer_clockevent_shutdown;
+ dev->set_state_oneshot_stopped = dmtimer_clockevent_shutdown;
dev->tick_resume = dmtimer_clockevent_shutdown;
- dev->cpumask = cpu_possible_mask;
+ dev->cpumask = cpumask;
dev->irq = irq_of_parse_and_map(np, 0);
- if (!dev->irq) {
- error = -ENXIO;
- goto err_out_free;
- }
+ if (!dev->irq)
+ return -ENXIO;
error = dmtimer_systimer_setup(np, &clkevt->t);
if (error)
- goto err_out_free;
+ return error;
clkevt->period = 0xffffffff - DIV_ROUND_CLOSEST(t->rate, HZ);
writel_relaxed(OMAP_TIMER_CTRL_POSTED, t->base + t->ifctrl);
error = request_irq(dev->irq, dmtimer_clockevent_interrupt,
- IRQF_TIMER, "clockevent", clkevt);
+ IRQF_TIMER, name, clkevt);
if (error)
goto err_out_unmap;
writel_relaxed(OMAP_TIMER_INT_OVERFLOW, t->base + t->irq_ena);
writel_relaxed(OMAP_TIMER_INT_OVERFLOW, t->base + t->wakeup);
- pr_info("TI gptimer clockevent: %s%lu Hz at %pOF\n",
- of_find_property(np, "ti,timer-alwon", NULL) ?
+ pr_info("TI gptimer %s: %s%lu Hz at %pOF\n",
+ name, of_find_property(np, "ti,timer-alwon", NULL) ?
"always-on " : "", t->rate, np->parent);
- clockevents_config_and_register(dev, t->rate,
- 3, /* Timer internal resynch latency */
+ return 0;
+
+err_out_unmap:
+ iounmap(t->base);
+
+ return error;
+}
+
+static int __init dmtimer_clockevent_init(struct device_node *np)
+{
+ struct dmtimer_clockevent *clkevt;
+ int error;
+
+ clkevt = kzalloc(sizeof(*clkevt), GFP_KERNEL);
+ if (!clkevt)
+ return -ENOMEM;
+
+ error = dmtimer_clkevt_init_common(clkevt, np,
+ CLOCK_EVT_FEAT_PERIODIC |
+ CLOCK_EVT_FEAT_ONESHOT,
+ cpu_possible_mask, "clockevent",
+ 300);
+ if (error)
+ goto err_out_free;
+
+ clockevents_config_and_register(&clkevt->dev, clkevt->t.rate,
+ 3, /* Timer internal resync latency */
0xffffffff);
if (of_machine_is_compatible("ti,am33xx") ||
of_machine_is_compatible("ti,am43")) {
- dev->suspend = omap_clockevent_idle;
- dev->resume = omap_clockevent_unidle;
+ clkevt->dev.suspend = omap_clockevent_idle;
+ clkevt->dev.resume = omap_clockevent_unidle;
}
return 0;
-err_out_unmap:
- iounmap(t->base);
-
err_out_free:
kfree(clkevt);
return error;
}
+/* Dmtimer as percpu timer. See dra7 ARM architected timer wrap erratum i940 */
+static DEFINE_PER_CPU(struct dmtimer_clockevent, dmtimer_percpu_timer);
+
+static int __init dmtimer_percpu_timer_init(struct device_node *np, int cpu)
+{
+ struct dmtimer_clockevent *clkevt;
+ int error;
+
+ if (!cpu_possible(cpu))
+ return -EINVAL;
+
+ if (!of_property_read_bool(np->parent, "ti,no-reset-on-init") ||
+ !of_property_read_bool(np->parent, "ti,no-idle"))
+ pr_warn("Incomplete dtb for percpu dmtimer %pOF\n", np->parent);
+
+ clkevt = per_cpu_ptr(&dmtimer_percpu_timer, cpu);
+
+ error = dmtimer_clkevt_init_common(clkevt, np, CLOCK_EVT_FEAT_ONESHOT,
+ cpumask_of(cpu), "percpu-dmtimer",
+ 500);
+ if (error)
+ return error;
+
+ return 0;
+}
+
+/* See TRM for timer internal resynch latency */
+static int omap_dmtimer_starting_cpu(unsigned int cpu)
+{
+ struct dmtimer_clockevent *clkevt = per_cpu_ptr(&dmtimer_percpu_timer, cpu);
+ struct clock_event_device *dev = &clkevt->dev;
+ struct dmtimer_systimer *t = &clkevt->t;
+
+ clockevents_config_and_register(dev, t->rate, 3, ULONG_MAX);
+ irq_force_affinity(dev->irq, cpumask_of(cpu));
+
+ return 0;
+}
+
+static int __init dmtimer_percpu_timer_startup(void)
+{
+ struct dmtimer_clockevent *clkevt = per_cpu_ptr(&dmtimer_percpu_timer, 0);
+ struct dmtimer_systimer *t = &clkevt->t;
+
+ if (t->sysc) {
+ cpuhp_setup_state(CPUHP_AP_TI_GP_TIMER_STARTING,
+ "clockevents/omap/gptimer:starting",
+ omap_dmtimer_starting_cpu, NULL);
+ }
+
+ return 0;
+}
+subsys_initcall(dmtimer_percpu_timer_startup);
+
+static int __init dmtimer_percpu_quirk_init(struct device_node *np, u32 pa)
+{
+ struct device_node *arm_timer;
+
+ arm_timer = of_find_compatible_node(NULL, NULL, "arm,armv7-timer");
+ if (of_device_is_available(arm_timer)) {
+ pr_warn_once("ARM architected timer wrap issue i940 detected\n");
+ return 0;
+ }
+
+ if (pa == 0x48034000) /* dra7 dmtimer3 */
+ return dmtimer_percpu_timer_init(np, 0);
+ else if (pa == 0x48036000) /* dra7 dmtimer4 */
+ return dmtimer_percpu_timer_init(np, 1);
+
+ return 0;
+}
+
/* Clocksource */
static struct dmtimer_clocksource *
to_dmtimer_clocksource(struct clocksource *cs)
if (clockevent == pa)
return dmtimer_clockevent_init(np);
+ if (of_machine_is_compatible("ti,dra7"))
+ return dmtimer_percpu_quirk_init(np, pa);
+
return 0;
}
/*
* The value for the LDVAL register trigger is calculated as:
* LDVAL trigger = (period / clock period) - 1
- * The pit is a 32-bit down count timer, when the conter value
+ * The pit is a 32-bit down count timer, when the counter value
* reaches 0, it will generate an interrupt, thus the minimal
* LDVAL trigger value is 1. And then the min_delta is
* minimal LDVAL trigger value + 1, and the max_delta is full 32-bit.
struct counter_device counter;
struct regmap *regmap;
struct clk *clk;
- u32 ceiling;
+ u32 max_arr;
bool enabled;
struct stm32_timer_regs bak;
};
* @STM32_COUNT_ENCODER_MODE_3: counts on both TI1FP1 and TI2FP2 edges
*/
enum stm32_count_function {
- STM32_COUNT_SLAVE_MODE_DISABLED = -1,
+ STM32_COUNT_SLAVE_MODE_DISABLED,
STM32_COUNT_ENCODER_MODE_1,
STM32_COUNT_ENCODER_MODE_2,
STM32_COUNT_ENCODER_MODE_3,
};
static enum counter_count_function stm32_count_functions[] = {
+ [STM32_COUNT_SLAVE_MODE_DISABLED] = COUNTER_COUNT_FUNCTION_INCREASE,
[STM32_COUNT_ENCODER_MODE_1] = COUNTER_COUNT_FUNCTION_QUADRATURE_X2_A,
[STM32_COUNT_ENCODER_MODE_2] = COUNTER_COUNT_FUNCTION_QUADRATURE_X2_B,
[STM32_COUNT_ENCODER_MODE_3] = COUNTER_COUNT_FUNCTION_QUADRATURE_X4,
const unsigned long val)
{
struct stm32_timer_cnt *const priv = counter->priv;
+ u32 ceiling;
- if (val > priv->ceiling)
+ regmap_read(priv->regmap, TIM_ARR, &ceiling);
+ if (val > ceiling)
return -EINVAL;
return regmap_write(priv->regmap, TIM_CNT, val);
regmap_read(priv->regmap, TIM_SMCR, &smcr);
switch (smcr & TIM_SMCR_SMS) {
+ case 0:
+ *function = STM32_COUNT_SLAVE_MODE_DISABLED;
+ return 0;
case 1:
*function = STM32_COUNT_ENCODER_MODE_1;
return 0;
case 3:
*function = STM32_COUNT_ENCODER_MODE_3;
return 0;
+ default:
+ return -EINVAL;
}
-
- return -EINVAL;
}
static int stm32_count_function_set(struct counter_device *counter,
u32 cr1, sms;
switch (function) {
+ case STM32_COUNT_SLAVE_MODE_DISABLED:
+ sms = 0;
+ break;
case STM32_COUNT_ENCODER_MODE_1:
sms = 1;
break;
sms = 3;
break;
default:
- sms = 0;
- break;
+ return -EINVAL;
}
/* Store enable status */
regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_CEN, 0);
- /* TIMx_ARR register shouldn't be buffered (ARPE=0) */
- regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_ARPE, 0);
- regmap_write(priv->regmap, TIM_ARR, priv->ceiling);
-
regmap_update_bits(priv->regmap, TIM_SMCR, TIM_SMCR_SMS, sms);
/* Make sure that registers are updated */
if (ret)
return ret;
+ if (ceiling > priv->max_arr)
+ return -ERANGE;
+
/* TIMx_ARR register shouldn't be buffered (ARPE=0) */
regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_ARPE, 0);
regmap_write(priv->regmap, TIM_ARR, ceiling);
- priv->ceiling = ceiling;
return len;
}
size_t function;
int err;
- /* Default action mode (e.g. STM32_COUNT_SLAVE_MODE_DISABLED) */
- *action = STM32_SYNAPSE_ACTION_NONE;
-
err = stm32_count_function_get(counter, count, &function);
if (err)
- return 0;
+ return err;
switch (function) {
+ case STM32_COUNT_SLAVE_MODE_DISABLED:
+ /* counts on internal clock when CEN=1 */
+ *action = STM32_SYNAPSE_ACTION_NONE;
+ return 0;
case STM32_COUNT_ENCODER_MODE_1:
/* counts up/down on TI1FP1 edge depending on TI2FP2 level */
if (synapse->signal->id == count->synapses[0].signal->id)
*action = STM32_SYNAPSE_ACTION_BOTH_EDGES;
- break;
+ else
+ *action = STM32_SYNAPSE_ACTION_NONE;
+ return 0;
case STM32_COUNT_ENCODER_MODE_2:
/* counts up/down on TI2FP2 edge depending on TI1FP1 level */
if (synapse->signal->id == count->synapses[1].signal->id)
*action = STM32_SYNAPSE_ACTION_BOTH_EDGES;
- break;
+ else
+ *action = STM32_SYNAPSE_ACTION_NONE;
+ return 0;
case STM32_COUNT_ENCODER_MODE_3:
/* counts up/down on both TI1FP1 and TI2FP2 edges */
*action = STM32_SYNAPSE_ACTION_BOTH_EDGES;
- break;
+ return 0;
+ default:
+ return -EINVAL;
}
-
- return 0;
}
static const struct counter_ops stm32_timer_cnt_ops = {
priv->regmap = ddata->regmap;
priv->clk = ddata->clk;
- priv->ceiling = ddata->max_arr;
+ priv->max_arr = ddata->max_arr;
priv->counter.name = dev_name(dev);
priv->counter.parent = dev;
static const struct of_device_id blacklist[] __initconst = {
{ .compatible = "allwinner,sun50i-h6", },
+ { .compatible = "arm,vexpress", },
+
{ .compatible = "calxeda,highbank", },
{ .compatible = "calxeda,ecx-2000", },
__ATTR_RO(_name##_frequencies)
/*
- * show_scaling_available_frequencies - show available normal frequencies for
+ * scaling_available_frequencies_show - show available normal frequencies for
* the specified CPU
*/
static ssize_t scaling_available_frequencies_show(struct cpufreq_policy *policy,
EXPORT_SYMBOL_GPL(cpufreq_freq_attr_scaling_available_freqs);
/*
- * show_available_boost_freqs - show available boost frequencies for
+ * scaling_boost_frequencies_show - show available boost frequencies for
* the specified CPU
*/
static ssize_t scaling_boost_frequencies_show(struct cpufreq_policy *policy,
}
base = ioremap(res->start, resource_size(res));
- if (IS_ERR(base)) {
+ if (!base) {
dev_err(dev, "failed to map resource %pR\n", res);
- ret = PTR_ERR(base);
+ ret = -ENOMEM;
goto release_region;
}
error:
kfree(data);
unmap_base:
- iounmap(data->base);
+ iounmap(base);
release_region:
release_mem_region(res->start, resource_size(res));
return ret;
config CRYPTO_DEV_SUN8I_CE_HASH
bool "Enable support for hash on sun8i-ce"
depends on CRYPTO_DEV_SUN8I_CE
- select MD5
- select SHA1
- select SHA256
- select SHA512
+ select CRYPTO_MD5
+ select CRYPTO_SHA1
+ select CRYPTO_SHA256
+ select CRYPTO_SHA512
help
Say y to enable support for hash algorithms.
config CRYPTO_DEV_SUN8I_SS_HASH
bool "Enable support for hash on sun8i-ss"
depends on CRYPTO_DEV_SUN8I_SS
- select MD5
- select SHA1
- select SHA256
+ select CRYPTO_MD5
+ select CRYPTO_SHA1
+ select CRYPTO_SHA256
help
Say y to enable support for hash algorithms.
sizeof(struct sun4i_cipher_req_ctx) +
crypto_skcipher_reqsize(op->fallback_tfm));
- err = pm_runtime_get_sync(op->ss->dev);
+ err = pm_runtime_resume_and_get(op->ss->dev);
if (err < 0)
goto error_pm;
{
struct sun4i_ss_ctx *ss = dev_get_drvdata(dev);
- if (ss->reset)
- reset_control_assert(ss->reset);
+ reset_control_assert(ss->reset);
clk_disable_unprepare(ss->ssclk);
clk_disable_unprepare(ss->busclk);
goto err_enable;
}
- if (ss->reset) {
- err = reset_control_deassert(ss->reset);
- if (err) {
- dev_err(ss->dev, "Cannot deassert reset control\n");
- goto err_enable;
- }
+ err = reset_control_deassert(ss->reset);
+ if (err) {
+ dev_err(ss->dev, "Cannot deassert reset control\n");
+ goto err_enable;
}
return err;
dev_dbg(&pdev->dev, "clock ahb_ss acquired\n");
ss->reset = devm_reset_control_get_optional(&pdev->dev, "ahb");
- if (IS_ERR(ss->reset)) {
- if (PTR_ERR(ss->reset) == -EPROBE_DEFER)
- return PTR_ERR(ss->reset);
+ if (IS_ERR(ss->reset))
+ return PTR_ERR(ss->reset);
+ if (!ss->reset)
dev_info(&pdev->dev, "no reset control found\n");
- ss->reset = NULL;
- }
/*
* Check that clock have the correct rates given in the datasheet
* this info could be useful
*/
- err = pm_runtime_get_sync(ss->dev);
+ err = pm_runtime_resume_and_get(ss->dev);
if (err < 0)
goto error_pm;
algt = container_of(alg, struct sun4i_ss_alg_template, alg.hash);
op->ss = algt->ss;
- err = pm_runtime_get_sync(op->ss->dev);
+ err = pm_runtime_resume_and_get(op->ss->dev);
if (err < 0)
return err;
algt = container_of(alg, struct sun4i_ss_alg_template, alg.rng);
ss = algt->ss;
- err = pm_runtime_get_sync(ss->dev);
+ err = pm_runtime_resume_and_get(ss->dev);
if (err < 0)
return err;
theend_sgs:
if (areq->src == areq->dst) {
- dma_unmap_sg(ce->dev, areq->src, nr_sgs, DMA_BIDIRECTIONAL);
+ dma_unmap_sg(ce->dev, areq->src, sg_nents(areq->src),
+ DMA_BIDIRECTIONAL);
} else {
if (nr_sgs > 0)
- dma_unmap_sg(ce->dev, areq->src, nr_sgs, DMA_TO_DEVICE);
- dma_unmap_sg(ce->dev, areq->dst, nr_sgd, DMA_FROM_DEVICE);
+ dma_unmap_sg(ce->dev, areq->src, sg_nents(areq->src),
+ DMA_TO_DEVICE);
+ dma_unmap_sg(ce->dev, areq->dst, sg_nents(areq->dst),
+ DMA_FROM_DEVICE);
}
theend_iv:
if (err)
goto error_alg;
- err = pm_runtime_get_sync(ce->dev);
+ err = pm_runtime_resume_and_get(ce->dev);
if (err < 0)
goto error_alg;
err = sun8i_ce_run_task(ce, flow, crypto_tfm_alg_name(areq->base.tfm));
dma_unmap_single(ce->dev, addr_pad, j * 4, DMA_TO_DEVICE);
- dma_unmap_sg(ce->dev, areq->src, nr_sgs, DMA_TO_DEVICE);
+ dma_unmap_sg(ce->dev, areq->src, sg_nents(areq->src),
+ DMA_TO_DEVICE);
dma_unmap_single(ce->dev, addr_res, digestsize, DMA_FROM_DEVICE);
dma_iv = dma_map_single(ce->dev, ctx->seed, ctx->slen, DMA_TO_DEVICE);
if (dma_mapping_error(ce->dev, dma_iv)) {
dev_err(ce->dev, "Cannot DMA MAP IV\n");
+ err = -EFAULT;
goto err_iv;
}
theend_sgs:
if (areq->src == areq->dst) {
- dma_unmap_sg(ss->dev, areq->src, nr_sgs, DMA_BIDIRECTIONAL);
+ dma_unmap_sg(ss->dev, areq->src, sg_nents(areq->src),
+ DMA_BIDIRECTIONAL);
} else {
- dma_unmap_sg(ss->dev, areq->src, nr_sgs, DMA_TO_DEVICE);
- dma_unmap_sg(ss->dev, areq->dst, nr_sgd, DMA_FROM_DEVICE);
+ dma_unmap_sg(ss->dev, areq->src, sg_nents(areq->src),
+ DMA_TO_DEVICE);
+ dma_unmap_sg(ss->dev, areq->dst, sg_nents(areq->dst),
+ DMA_FROM_DEVICE);
}
theend_iv:
op->enginectx.op.prepare_request = NULL;
op->enginectx.op.unprepare_request = NULL;
- err = pm_runtime_get_sync(op->ss->dev);
+ err = pm_runtime_resume_and_get(op->ss->dev);
if (err < 0) {
dev_err(op->ss->dev, "pm error %d\n", err);
goto error_pm;
if (err)
goto error_alg;
- err = pm_runtime_get_sync(ss->dev);
+ err = pm_runtime_resume_and_get(ss->dev);
if (err < 0)
goto error_alg;
bf = (__le32 *)pad;
result = kzalloc(digestsize, GFP_KERNEL | GFP_DMA);
- if (!result)
+ if (!result) {
+ kfree(pad);
return -ENOMEM;
+ }
for (i = 0; i < MAX_SG; i++) {
rctx->t_dst[i].addr = 0;
err = sun8i_ss_run_hash_task(ss, rctx, crypto_tfm_alg_name(areq->base.tfm));
dma_unmap_single(ss->dev, addr_pad, j * 4, DMA_TO_DEVICE);
- dma_unmap_sg(ss->dev, areq->src, nr_sgs, DMA_TO_DEVICE);
+ dma_unmap_sg(ss->dev, areq->src, sg_nents(areq->src),
+ DMA_TO_DEVICE);
dma_unmap_single(ss->dev, addr_res, digestsize, DMA_FROM_DEVICE);
- kfree(pad);
-
memcpy(areq->result, result, algt->alg.hash.halg.digestsize);
- kfree(result);
theend:
+ kfree(pad);
+ kfree(result);
crypto_finalize_hash_request(engine, breq, err);
return 0;
}
dma_iv = dma_map_single(ss->dev, ctx->seed, ctx->slen, DMA_TO_DEVICE);
if (dma_mapping_error(ss->dev, dma_iv)) {
dev_err(ss->dev, "Cannot DMA MAP IV\n");
- return -EFAULT;
+ err = -EFAULT;
+ goto err_free;
}
dma_dst = dma_map_single(ss->dev, d, todo, DMA_FROM_DEVICE);
memcpy(ctx->seed, d + dlen, ctx->slen);
}
memzero_explicit(d, todo);
+err_free:
kfree(d);
return err;
// SPDX-License-Identifier: GPL-2.0-or-later
-/**
+/*
* AMCC SoC PPC4xx Crypto Driver
*
* Copyright (c) 2008 Applied Micro Circuits Corporation.
return crypto4xx_crypt(req, AES_IV_SIZE, true, true);
}
-/**
+/*
* AES Functions
*/
static int crypto4xx_setkey_aes(struct crypto_skcipher *cipher,
return crypto_aead_setkey(ctx->sw_cipher.aead, key, keylen);
}
-/**
+/*
* AES-CCM Functions
*/
return crypto_aead_setauthsize(ctx->sw_cipher.aead, authsize);
}
-/**
+/*
* AES-GCM Functions
*/
return crypto4xx_crypt_aes_gcm(req, true);
}
-/**
+/*
* HASH SHA1 Functions
*/
static int crypto4xx_hash_alg_init(struct crypto_tfm *tfm,
ctx->sa_len, 0, NULL);
}
-/**
+/*
* SHA1 Algorithm
*/
int crypto4xx_sha1_alg_init(struct crypto_tfm *tfm)
// SPDX-License-Identifier: GPL-2.0-or-later
-/**
+/*
* AMCC SoC PPC4xx Crypto Driver
*
* Copyright (c) 2008 Applied Micro Circuits Corporation.
#define PPC4XX_SEC_VERSION_STR "0.5"
-/**
+/*
* PPC4xx Crypto Engine Initialization Routine
*/
static void crypto4xx_hw_init(struct crypto4xx_device *dev)
ctx->sa_len = 0;
}
-/**
+/*
* alloc memory for the gather ring
* no need to alloc buf for the ring
* gdr_tail, gdr_head and gdr_count are initialized by this function
return tail;
}
-/**
+/*
* alloc memory for the gather ring
* no need to alloc buf for the ring
* gdr_tail, gdr_head and gdr_count are initialized by this function
return &dev->gdr[idx];
}
-/**
+/*
* alloc memory for the scatter ring
* need to alloc buf for the ring
* sdr_tail, sdr_head and sdr_count are initialized by this function
return is_busy ? -EBUSY : -EINPROGRESS;
}
-/**
+/*
* Algorithm Registration Functions
*/
static void crypto4xx_ctx_init(struct crypto4xx_alg *amcc_alg,
} while (head != tail);
}
-/**
+/*
* Top Half of isr.
*/
static inline irqreturn_t crypto4xx_interrupt_handler(int irq, void *data,
return 0;
}
-/**
+/*
* Supported Crypto Algorithms
*/
static struct crypto4xx_alg_common crypto4xx_alg[] = {
} },
};
-/**
+/*
* Module Initialization Routine
*/
static int crypto4xx_probe(struct platform_device *ofdev)
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/**
+/*
* AMCC SoC PPC4xx Crypto Driver
*
* Copyright (c) 2008 Applied Micro Circuits Corporation.
int crypto4xx_hash_update(struct ahash_request *req);
int crypto4xx_hash_init(struct ahash_request *req);
-/**
+/*
* Note: Only use this function to copy items that is word aligned.
*/
static inline void crypto4xx_memcpy_swab32(u32 *dst, const void *buf,
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/**
+/*
* AMCC SoC PPC4xx Crypto Driver
*
* Copyright (c) 2008 Applied Micro Circuits Corporation.
#define CRYPTO4XX_PRNG_LFSR_L 0x00070030
#define CRYPTO4XX_PRNG_LFSR_H 0x00070034
-/**
+/*
* Initialize CRYPTO ENGINE registers, and memory bases.
*/
#define PPC4XX_PDR_POLL 0x3ff
#define PPC4XX_INT_TIMEOUT_CNT 0
#define PPC4XX_INT_TIMEOUT_CNT_REVB 0x3FF
#define PPC4XX_INT_CFG 1
-/**
+/*
* all follow define are ad hoc
*/
#define PPC4XX_RING_RETRY 100
#define PPC4XX_SDR_SIZE PPC4XX_NUM_SD
#define PPC4XX_GDR_SIZE PPC4XX_NUM_GD
-/**
+/*
* Generic Security Association (SA) with all possible fields. These will
* never likely used except for reference purpose. These structure format
* can be not changed as the hardware expects them to be layout as defined.
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/**
+/*
* AMCC SoC PPC4xx Crypto Driver
*
* Copyright (c) 2008 Applied Micro Circuits Corporation.
#define AES_IV_SIZE 16
-/**
+/*
* Contents of Dynamic Security Association (SA) with all possible fields
*/
union dynamic_sa_contents {
#define SA_AES_KEY_LEN_256 4
#define SA_REV2 1
-/**
+/*
* The follow defines bits sa_command_1
* In Basic hash mode this bit define simple hash or hmac.
* In IPsec mode, this bit define muting control.
union sa_command_1 sa_command_1;
} __attribute__((packed));
-/**
+/*
* State Record for Security Association (SA)
*/
struct sa_state_record {
};
} __attribute__((packed));
-/**
+/*
* Security Association (SA) for AES128
*
*/
#define SA_AES192_LEN (sizeof(struct dynamic_sa_aes192)/4)
#define SA_AES192_CONTENTS 0x3e000062
-/**
+/*
* Security Association (SA) for AES256
*/
struct dynamic_sa_aes256 {
#define SA_AES256_CONTENTS 0x3e000082
#define SA_AES_CONTENTS 0x3e000002
-/**
+/*
* Security Association (SA) for AES128 CCM
*/
struct dynamic_sa_aes128_ccm {
#define SA_AES128_CCM_CONTENTS 0x3e000042
#define SA_AES_CCM_CONTENTS 0x3e000002
-/**
+/*
* Security Association (SA) for AES128_GCM
*/
struct dynamic_sa_aes128_gcm {
#define SA_AES128_GCM_CONTENTS 0x3e000442
#define SA_AES_GCM_CONTENTS 0x3e000402
-/**
+/*
* Security Association (SA) for HASH160: HMAC-SHA1
*/
struct dynamic_sa_hash160 {
/* SPDX-License-Identifier: GPL-2.0-or-later */
-/**
+/*
* AMCC SoC PPC4xx Crypto Driver
*
* Copyright (c) 2008 Applied Micro Circuits Corporation.
dma_unmap_single(mc->dev, phykeyiv, keyivlen, DMA_TO_DEVICE);
if (areq->src == areq->dst) {
- dma_unmap_sg(mc->dev, areq->src, nr_sgs, DMA_BIDIRECTIONAL);
+ dma_unmap_sg(mc->dev, areq->src, sg_nents(areq->src), DMA_BIDIRECTIONAL);
} else {
- dma_unmap_sg(mc->dev, areq->src, nr_sgs, DMA_TO_DEVICE);
- dma_unmap_sg(mc->dev, areq->dst, nr_sgd, DMA_FROM_DEVICE);
+ dma_unmap_sg(mc->dev, areq->src, sg_nents(areq->src), DMA_TO_DEVICE);
+ dma_unmap_sg(mc->dev, areq->dst, sg_nents(areq->dst), DMA_FROM_DEVICE);
}
if (areq->iv && ivsize > 0) {
struct meson_dev *mc;
int err, i;
- if (!pdev->dev.of_node)
- return -ENODEV;
-
mc = devm_kzalloc(&pdev->dev, sizeof(*mc), GFP_KERNEL);
if (!mc)
return -ENOMEM;
static struct atmel_ecc_driver_data driver_data;
/**
- * atmel_ecdh_ctx - transformation context
+ * struct atmel_ecdh_ctx - transformation context
* @client : pointer to i2c client device
* @fallback : used for unsupported curves or when user wants to use its own
* private key.
* of the user to not call set_secret() while
* generate_public_key() or compute_shared_secret() are in flight.
* @curve_id : elliptic curve id
- * @n_sz : size in bytes of the n prime
* @do_fallback: true when the device doesn't support the curve or when the user
* wants to use its own private key.
*/
struct crypto_kpp *fallback;
const u8 *public_key;
unsigned int curve_id;
- size_t n_sz;
bool do_fallback;
};
int status)
{
struct kpp_request *req = areq;
- struct atmel_ecdh_ctx *ctx = work_data->ctx;
struct atmel_i2c_cmd *cmd = &work_data->cmd;
size_t copied, n_sz;
goto free_work_data;
/* might want less than we've got */
- n_sz = min_t(size_t, ctx->n_sz, req->dst_len);
+ n_sz = min_t(size_t, ATMEL_ECC_NIST_P256_N_SIZE, req->dst_len);
/* copy the shared secret */
copied = sg_copy_from_buffer(req->dst, sg_nents_for_len(req->dst, n_sz),
kpp_request_complete(req, status);
}
-static unsigned int atmel_ecdh_supported_curve(unsigned int curve_id)
-{
- if (curve_id == ECC_CURVE_NIST_P256)
- return ATMEL_ECC_NIST_P256_N_SIZE;
-
- return 0;
-}
-
/*
* A random private key is generated and stored in the device. The device
* returns the pair public key.
return -EINVAL;
}
- ctx->n_sz = atmel_ecdh_supported_curve(params.curve_id);
- if (!ctx->n_sz || params.key_size) {
+ if (params.key_size) {
/* fallback to ecdh software implementation */
ctx->do_fallback = true;
return crypto_kpp_set_secret(ctx->fallback, buf, len);
goto free_cmd;
ctx->do_fallback = false;
- ctx->curve_id = params.curve_id;
atmel_i2c_init_genkey_cmd(cmd, DATA_SLOT_2);
struct crypto_kpp *fallback;
struct atmel_ecdh_ctx *ctx = kpp_tfm_ctx(tfm);
+ ctx->curve_id = ECC_CURVE_NIST_P256;
ctx->client = atmel_ecc_i2c_client_alloc();
if (IS_ERR(ctx->client)) {
pr_err("tfm - i2c_client binding failed\n");
return ATMEL_ECC_PUBKEY_SIZE;
}
-static struct kpp_alg atmel_ecdh = {
+static struct kpp_alg atmel_ecdh_nist_p256 = {
.set_secret = atmel_ecdh_set_secret,
.generate_public_key = atmel_ecdh_generate_public_key,
.compute_shared_secret = atmel_ecdh_compute_shared_secret,
.max_size = atmel_ecdh_max_size,
.base = {
.cra_flags = CRYPTO_ALG_NEED_FALLBACK,
- .cra_name = "ecdh",
+ .cra_name = "ecdh-nist-p256",
.cra_driver_name = "atmel-ecdh",
.cra_priority = ATMEL_ECC_PRIORITY,
.cra_module = THIS_MODULE,
&driver_data.i2c_client_list);
spin_unlock(&driver_data.i2c_list_lock);
- ret = crypto_register_kpp(&atmel_ecdh);
+ ret = crypto_register_kpp(&atmel_ecdh_nist_p256);
if (ret) {
spin_lock(&driver_data.i2c_list_lock);
list_del(&i2c_priv->i2c_client_list_node);
spin_unlock(&driver_data.i2c_list_lock);
dev_err(&client->dev, "%s alg registration failed\n",
- atmel_ecdh.base.cra_driver_name);
+ atmel_ecdh_nist_p256.base.cra_driver_name);
} else {
dev_info(&client->dev, "atmel ecc algorithms registered in /proc/crypto\n");
}
return -EBUSY;
}
- crypto_unregister_kpp(&atmel_ecdh);
+ crypto_unregister_kpp(&atmel_ecdh_nist_p256);
spin_lock(&driver_data.i2c_list_lock);
list_del(&i2c_priv->i2c_client_list_node);
}
if (bus_clk_rate > 1000000L) {
- dev_err(dev, "%d exceeds maximum supported clock frequency (1MHz)\n",
+ dev_err(dev, "%u exceeds maximum supported clock frequency (1MHz)\n",
bus_clk_rate);
return -EINVAL;
}
ctx->flags = 0;
- dev_dbg(dd->dev, "init: digest size: %d\n",
+ dev_dbg(dd->dev, "init: digest size: %u\n",
crypto_ahash_digestsize(tfm));
switch (crypto_ahash_digestsize(tfm)) {
struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
int err;
- dev_dbg(dd->dev, "handling new req, op: %lu, nbytes: %d\n",
+ dev_dbg(dd->dev, "handling new req, op: %lu, nbytes: %u\n",
ctx->op, req->nbytes);
err = atmel_sha_hw_init(dd);
tdes_dd->io_base = devm_ioremap_resource(&pdev->dev, tdes_res);
if (IS_ERR(tdes_dd->io_base)) {
- dev_err(dev, "can't ioremap\n");
err = PTR_ERR(tdes_dd->io_base);
goto err_tasklet_kill;
}
* a SPU response message for an AEAD request. Includes buffers to catch SPU
* message headers and the response data.
* @mssg: mailbox message containing the receive sg
+ * @req: Crypto API request
* @rctx: crypto request context
* @rx_frag_num: number of scatterlist elements required to hold the
* SPU response message
/**
* rfc4543_gcm_esp_setkey() - setkey operation for RFC4543 variant of GCM/GMAC.
- * cipher: AEAD structure
- * key: Key followed by 4 bytes of salt
- * keylen: Length of key plus salt, in bytes
+ * @cipher: AEAD structure
+ * @key: Key followed by 4 bytes of salt
+ * @keylen: Length of key plus salt, in bytes
*
* Extracts salt from key and stores it to be prepended to IV on each request.
* Digest is always 16 bytes
* @cipher_mode: Algo type
* @data_size: Length of plaintext (bytes)
*
- * @Return: Length of padding, in bytes
+ * Return: Length of padding, in bytes
*/
u32 spum_gcm_ccm_pad_len(enum spu_cipher_mode cipher_mode,
unsigned int data_size)
}
/**
- * spu_aead_ivlen() - Calculate the length of the AEAD IV to be included
+ * spum_aead_ivlen() - Calculate the length of the AEAD IV to be included
* in a SPU request after the AAD and before the payload.
* @cipher_mode: cipher mode
- * @iv_ctr_len: initialization vector length in bytes
+ * @iv_len: initialization vector length in bytes
*
* In Linux ~4.2 and later, the assoc_data sg includes the IV. So no need
* to include the IV as a separate field in the SPU request msg.
/**
* spum_digest_size() - Determine the size of a hash digest to expect the SPU to
* return.
- * alg_digest_size: Number of bytes in the final digest for the given algo
- * alg: The hash algorithm
- * htype: Type of hash operation (init, update, full, etc)
+ * @alg_digest_size: Number of bytes in the final digest for the given algo
+ * @alg: The hash algorithm
+ * @htype: Type of hash operation (init, update, full, etc)
*
* When doing incremental hashing for an algorithm with a truncated hash
* (e.g., SHA224), the SPU returns the full digest so that it can be fed back as
* @aead_parms: Parameters related to AEAD operation
* @data_size: Length of data to be encrypted or authenticated. If AEAD, does
* not include length of AAD.
-
+ *
* Return: the length of the SPU header in bytes. 0 if an error occurs.
*/
u32 spum_create_request(u8 *spu_hdr,
* setkey() time in spu_cipher_req_init().
* @spu_hdr: Start of the request message header (MH field)
* @spu_req_hdr_len: Length in bytes of the SPU request header
- * @isInbound: 0 encrypt, 1 decrypt
+ * @is_inbound: 0 encrypt, 1 decrypt
* @cipher_parms: Parameters describing cipher operation to be performed
* @data_size: Length of the data in the BD field
*
/**
* spu2_fmd_init() - At setkey time, initialize the fixed meta data for
* subsequent skcipher requests for this context.
- * @spu2_cipher_type: Cipher algorithm
+ * @fmd: Start of FMD field to be written
+ * @spu2_type: Cipher algorithm
* @spu2_mode: Cipher mode
* @cipher_key_len: Length of cipher key, in bytes
* @cipher_iv_len: Length of cipher initialization vector, in bytes
* SPU request packet.
* @fmd: Start of FMD field to be written
* @is_inbound: true if decrypting. false if encrypting.
- * @authFirst: true if alg authenticates before encrypting
+ * @auth_first: true if alg authenticates before encrypting
* @protocol: protocol selector
* @cipher_type: cipher algorithm
* @cipher_mode: cipher mode
* spu2_fmd_ctrl1_write() - Write ctrl1 field in fixed metadata (FMD) field of
* SPU request packet.
* @fmd: Start of FMD field to be written
+ * @is_inbound: true if decrypting. false if encrypting.
* @assoc_size: Length of additional associated data, in bytes
* @auth_key_len: Length of authentication key, in bytes
* @cipher_key_len: Length of cipher key, in bytes
}
/**
- * spu_payload_length() - Given a SPU2 message header, extract the payload
+ * spu2_payload_length() - Given a SPU2 message header, extract the payload
* length.
* @spu_hdr: Start of SPU message header (FMD)
*
}
/**
- * spu_response_hdr_len() - Determine the expected length of a SPU response
+ * spu2_response_hdr_len() - Determine the expected length of a SPU response
* header.
* @auth_key_len: Length of authentication key, in bytes
* @enc_key_len: Length of encryption key, in bytes
+ * @is_hash: Unused
*
* For SPU2, includes just FMD. OMD is never requested.
*
}
/**
- * spu_hash_pad_len() - Calculate the length of hash padding required to extend
+ * spu2_hash_pad_len() - Calculate the length of hash padding required to extend
* data to a full block size.
* @hash_alg: hash algorithm
* @hash_mode: hash mode
}
/**
- * spu2_gcm_ccm_padlen() - Determine the length of GCM/CCM padding for either
+ * spu2_gcm_ccm_pad_len() - Determine the length of GCM/CCM padding for either
* the AAD field or the data.
+ * @cipher_mode: Unused
+ * @data_size: Unused
*
* Return: 0. Unlike SPU-M, SPU2 hardware does any GCM/CCM padding required.
*/
}
/**
- * spu_assoc_resp_len() - Determine the size of the AAD2 buffer needed to catch
+ * spu2_assoc_resp_len() - Determine the size of the AAD2 buffer needed to catch
* associated data in a SPU2 output packet.
* @cipher_mode: cipher mode
* @assoc_len: length of additional associated data, in bytes
return resp_len;
}
-/*
- * spu_aead_ivlen() - Calculate the length of the AEAD IV to be included
+/**
+ * spu2_aead_ivlen() - Calculate the length of the AEAD IV to be included
* in a SPU request after the AAD and before the payload.
* @cipher_mode: cipher mode
- * @iv_ctr_len: initialization vector length in bytes
+ * @iv_len: initialization vector length in bytes
*
* For SPU2, AEAD IV is included in OMD and does not need to be repeated
* prior to the payload.
/**
* spu2_digest_size() - Determine the size of a hash digest to expect the SPU to
* return.
- * alg_digest_size: Number of bytes in the final digest for the given algo
- * alg: The hash algorithm
- * htype: Type of hash operation (init, update, full, etc)
+ * @alg_digest_size: Number of bytes in the final digest for the given algo
+ * @alg: The hash algorithm
+ * @htype: Type of hash operation (init, update, full, etc)
*
*/
u32 spu2_digest_size(u32 alg_digest_size, enum hash_alg alg,
}
/**
- * spu_create_request() - Build a SPU2 request message header, includint FMD and
+ * spu2_create_request() - Build a SPU2 request message header, includint FMD and
* OMD.
* @spu_hdr: Start of buffer where SPU request header is to be written
* @req_opts: SPU request message options
}
/**
- * spu_cipher_req_init() - Build an skcipher SPU2 request message header,
+ * spu2_cipher_req_init() - Build an skcipher SPU2 request message header,
* including FMD and OMD.
* @spu_hdr: Location of start of SPU request (FMD field)
* @cipher_parms: Parameters describing cipher request
}
/**
- * spu_cipher_req_finish() - Finish building a SPU request message header for a
+ * spu2_cipher_req_finish() - Finish building a SPU request message header for a
* block cipher request.
* @spu_hdr: Start of the request message header (MH field)
* @spu_req_hdr_len: Length in bytes of the SPU request header
- * @isInbound: 0 encrypt, 1 decrypt
+ * @is_inbound: 0 encrypt, 1 decrypt
* @cipher_parms: Parameters describing cipher operation to be performed
* @data_size: Length of the data in the BD field
*
}
/**
- * spu_request_pad() - Create pad bytes at the end of the data.
+ * spu2_request_pad() - Create pad bytes at the end of the data.
* @pad_start: Start of buffer where pad bytes are to be written
* @gcm_padding: Length of GCM padding, in bytes
* @hash_pad_len: Number of bytes of padding extend data to full block
}
/**
- * spu_status_process() - Process the status from a SPU response message.
+ * spu2_status_process() - Process the status from a SPU response message.
* @statp: start of STATUS word
*
* Return: 0 - if status is good and response should be processed
* @from_skip: number of bytes to skip in from_sg. Non-zero when previous
* request included part of the buffer in entry in from_sg.
* Assumes from_skip < from_sg->length.
- * @from_nents number of entries in from_sg
- * @length number of bytes to copy. may reach this limit before exhausting
+ * @from_nents: number of entries in from_sg
+ * @length: number of bytes to copy. may reach this limit before exhausting
* from_sg.
*
* Copies the entries themselves, not the data in the entries. Assumes to_sg has
* @adata: authentication algorithm details
* @cdata: encryption algorithm details
* @authsize: authentication tag (a.k.a. ICV / MAC) size
+ * @xts_key_fallback: true if fallback tfm needs to be used due
+ * to unsupported xts key lengths
+ * @fallback: xts fallback tfm
*/
struct caam_ctx {
struct caam_flc flc[NUM_OP];
}
/**
- * Count leading zeros, need it to strip, from a given scatterlist
+ * caam_rsa_count_leading_zeros - Count leading zeros, need it to strip,
+ * from a given scatterlist
*
* @sgl : scatterlist to count zeros from
* @nbytes: number of zeros, in bytes, to strip
#include <linux/moduleparam.h>
#include <linux/pci.h>
#include <linux/printk.h>
-#include <linux/version.h>
#include "cptpf.h"
#include "nitrox_isr.h"
#include "nitrox_mbx.h"
-/**
+/*
* One vector for each type of ring
* - NPS packet ring, AQMQ ring and ZQMQ ring
*/
}
}
-/**
+/*
* nps_core_int_isr - interrupt handler for NITROX errors and
* mailbox communication
*/
struct device *dev = DEV(ndev);
- dma_unmap_sg(dev, sr->in.sg, sr->in.sgmap_cnt, DMA_BIDIRECTIONAL);
+ dma_unmap_sg(dev, sr->in.sg, sg_nents(sr->in.sg),
+ DMA_BIDIRECTIONAL);
dma_unmap_single(dev, sr->in.sgcomp_dma, sr->in.sgcomp_len,
DMA_TO_DEVICE);
kfree(sr->in.sgcomp);
sr->in.sg = NULL;
sr->in.sgmap_cnt = 0;
- dma_unmap_sg(dev, sr->out.sg, sr->out.sgmap_cnt,
+ dma_unmap_sg(dev, sr->out.sg, sg_nents(sr->out.sg),
DMA_BIDIRECTIONAL);
dma_unmap_single(dev, sr->out.sgcomp_dma, sr->out.sgcomp_len,
DMA_TO_DEVICE);
return 0;
incomp_err:
- dma_unmap_sg(dev, req->src, nents, DMA_BIDIRECTIONAL);
+ dma_unmap_sg(dev, req->src, sg_nents(req->src), DMA_BIDIRECTIONAL);
sr->in.sgmap_cnt = 0;
return ret;
}
return 0;
outcomp_map_err:
- dma_unmap_sg(dev, req->dst, nents, DMA_BIDIRECTIONAL);
+ dma_unmap_sg(dev, req->dst, sg_nents(req->dst), DMA_BIDIRECTIONAL);
sr->out.sgmap_cnt = 0;
sr->out.sg = NULL;
return ret;
#include <linux/seq_file.h>
#include <linux/string.h>
#include <linux/types.h>
-#include <linux/version.h>
/* Device specific zlib function definitions */
#include "zip_device.h"
#define CCP_CRYPTO_MAX_QLEN 100
static struct ccp_crypto_queue req_queue;
-static spinlock_t req_queue_lock;
+static DEFINE_SPINLOCK(req_queue_lock);
struct ccp_crypto_cmd {
struct list_head entry;
return ret;
}
- spin_lock_init(&req_queue_lock);
INIT_LIST_HEAD(&req_queue.cmds);
req_queue.backlog = &req_queue.cmds;
req_queue.cmd_count = 0;
return ccp->cmd_q_count == suspended;
}
-int ccp_dev_suspend(struct sp_device *sp)
+void ccp_dev_suspend(struct sp_device *sp)
{
struct ccp_device *ccp = sp->ccp_data;
unsigned long flags;
/* If there's no device there's nothing to do */
if (!ccp)
- return 0;
+ return;
spin_lock_irqsave(&ccp->cmd_lock, flags);
while (!ccp_queues_suspended(ccp))
wait_event_interruptible(ccp->suspend_queue,
ccp_queues_suspended(ccp));
-
- return 0;
}
-int ccp_dev_resume(struct sp_device *sp)
+void ccp_dev_resume(struct sp_device *sp)
{
struct ccp_device *ccp = sp->ccp_data;
unsigned long flags;
/* If there's no device there's nothing to do */
if (!ccp)
- return 0;
+ return;
spin_lock_irqsave(&ccp->cmd_lock, flags);
}
spin_unlock_irqrestore(&ccp->cmd_lock, flags);
-
- return 0;
}
int ccp_dev_init(struct sp_device *sp)
dst.address += CCP_ECC_OUTPUT_SIZE;
ccp_reverse_get_dm_area(&dst, 0, ecc->u.pm.result.y, 0,
CCP_ECC_MODULUS_BYTES);
- dst.address += CCP_ECC_OUTPUT_SIZE;
/* Restore the workarea address */
dst.address = save;
#include <linux/ccp.h>
#include <linux/firmware.h>
#include <linux/gfp.h>
+#include <linux/cpufeature.h>
#include <asm/smp.h>
struct sev_device *sev;
int ret = -ENOMEM;
+ if (!boot_cpu_has(X86_FEATURE_SEV)) {
+ dev_info_once(dev, "SEV: memory encryption not enabled by BIOS\n");
+ return 0;
+ }
+
sev = devm_kzalloc(dev, sizeof(*sev), GFP_KERNEL);
if (!sev)
goto e_err;
int sp_suspend(struct sp_device *sp)
{
- int ret;
-
if (sp->dev_vdata->ccp_vdata) {
- ret = ccp_dev_suspend(sp);
- if (ret)
- return ret;
+ ccp_dev_suspend(sp);
}
return 0;
int sp_resume(struct sp_device *sp)
{
- int ret;
-
if (sp->dev_vdata->ccp_vdata) {
- ret = ccp_dev_resume(sp);
- if (ret)
- return ret;
+ ccp_dev_resume(sp);
}
return 0;
int ccp_dev_init(struct sp_device *sp);
void ccp_dev_destroy(struct sp_device *sp);
-int ccp_dev_suspend(struct sp_device *sp);
-int ccp_dev_resume(struct sp_device *sp);
+void ccp_dev_suspend(struct sp_device *sp);
+void ccp_dev_resume(struct sp_device *sp);
#else /* !CONFIG_CRYPTO_DEV_SP_CCP */
return 0;
}
static inline void ccp_dev_destroy(struct sp_device *sp) { }
-
-static inline int ccp_dev_suspend(struct sp_device *sp)
-{
- return 0;
-}
-static inline int ccp_dev_resume(struct sp_device *sp)
-{
- return 0;
-}
+static inline void ccp_dev_suspend(struct sp_device *sp) { }
+static inline void ccp_dev_resume(struct sp_device *sp) { }
#endif /* CONFIG_CRYPTO_DEV_SP_CCP */
#ifdef CONFIG_CRYPTO_DEV_SP_PSP
{ PCI_VDEVICE(AMD, 0x1468), (kernel_ulong_t)&dev_vdata[2] },
{ PCI_VDEVICE(AMD, 0x1486), (kernel_ulong_t)&dev_vdata[3] },
{ PCI_VDEVICE(AMD, 0x15DF), (kernel_ulong_t)&dev_vdata[4] },
+ { PCI_VDEVICE(AMD, 0x1649), (kernel_ulong_t)&dev_vdata[4] },
/* Last entry must be zero */
{ 0, }
};
* Author: Rijo Thomas <Rijo-john.Thomas@amd.com>
* Author: Devaraj Rangasamy <Devaraj.Rangasamy@amd.com>
*
- * Copyright 2019 Advanced Micro Devices, Inc.
+ * Copyright (C) 2019,2021 Advanced Micro Devices, Inc.
*/
#include <linux/types.h>
if (!start_addr)
return -ENOMEM;
+ memset(start_addr, 0x0, ring_size);
rb_mgr->ring_start = start_addr;
rb_mgr->ring_size = ring_size;
rb_mgr->ring_pa = __psp_pa(start_addr);
void *buf, size_t len, struct tee_ring_cmd **resp)
{
struct tee_ring_cmd *cmd;
- u32 rptr, wptr;
int nloop = 1000, ret = 0;
+ u32 rptr;
*resp = NULL;
mutex_lock(&tee->rb_mgr.mutex);
- wptr = tee->rb_mgr.wptr;
-
- /* Check if ring buffer is full */
+ /* Loop until empty entry found in ring buffer */
do {
+ /* Get pointer to ring buffer command entry */
+ cmd = (struct tee_ring_cmd *)
+ (tee->rb_mgr.ring_start + tee->rb_mgr.wptr);
+
rptr = ioread32(tee->io_regs + tee->vdata->ring_rptr_reg);
- if (!(wptr + sizeof(struct tee_ring_cmd) == rptr))
+ /* Check if ring buffer is full or command entry is waiting
+ * for response from TEE
+ */
+ if (!(tee->rb_mgr.wptr + sizeof(struct tee_ring_cmd) == rptr ||
+ cmd->flag == CMD_WAITING_FOR_RESPONSE))
break;
- dev_info(tee->dev, "tee: ring buffer full. rptr = %u wptr = %u\n",
- rptr, wptr);
+ dev_dbg(tee->dev, "tee: ring buffer full. rptr = %u wptr = %u\n",
+ rptr, tee->rb_mgr.wptr);
- /* Wait if ring buffer is full */
+ /* Wait if ring buffer is full or TEE is processing data */
mutex_unlock(&tee->rb_mgr.mutex);
schedule_timeout_interruptible(msecs_to_jiffies(10));
mutex_lock(&tee->rb_mgr.mutex);
} while (--nloop);
- if (!nloop && (wptr + sizeof(struct tee_ring_cmd) == rptr)) {
- dev_err(tee->dev, "tee: ring buffer full. rptr = %u wptr = %u\n",
- rptr, wptr);
+ if (!nloop &&
+ (tee->rb_mgr.wptr + sizeof(struct tee_ring_cmd) == rptr ||
+ cmd->flag == CMD_WAITING_FOR_RESPONSE)) {
+ dev_err(tee->dev, "tee: ring buffer full. rptr = %u wptr = %u response flag %u\n",
+ rptr, tee->rb_mgr.wptr, cmd->flag);
ret = -EBUSY;
goto unlock;
}
- /* Pointer to empty data entry in ring buffer */
- cmd = (struct tee_ring_cmd *)(tee->rb_mgr.ring_start + wptr);
+ /* Do not submit command if PSP got disabled while processing any
+ * command in another thread
+ */
+ if (psp_dead) {
+ ret = -EBUSY;
+ goto unlock;
+ }
/* Write command data into ring buffer */
cmd->cmd_id = cmd_id;
memset(&cmd->buf[0], 0, sizeof(cmd->buf));
memcpy(&cmd->buf[0], buf, len);
+ /* Indicate driver is waiting for response */
+ cmd->flag = CMD_WAITING_FOR_RESPONSE;
+
/* Update local copy of write pointer */
tee->rb_mgr.wptr += sizeof(struct tee_ring_cmd);
if (tee->rb_mgr.wptr >= tee->rb_mgr.ring_size)
struct tee_ring_cmd *resp,
unsigned int timeout)
{
- /* ~5ms sleep per loop => nloop = timeout * 200 */
- int nloop = timeout * 200;
+ /* ~1ms sleep per loop => nloop = timeout * 1000 */
+ int nloop = timeout * 1000;
while (--nloop) {
if (resp->cmd_state == TEE_CMD_STATE_COMPLETED)
return 0;
- usleep_range(5000, 5100);
+ usleep_range(1000, 1100);
}
dev_err(tee->dev, "tee: command 0x%x timed out, disabling PSP\n",
return ret;
ret = tee_wait_cmd_completion(tee, resp, TEE_DEFAULT_TIMEOUT);
- if (ret)
+ if (ret) {
+ resp->flag = CMD_RESPONSE_TIMEDOUT;
return ret;
+ }
memcpy(buf, &resp->buf[0], len);
*status = resp->status;
+ resp->flag = CMD_RESPONSE_COPIED;
+
return 0;
}
EXPORT_SYMBOL(psp_tee_process_cmd);
/* SPDX-License-Identifier: MIT */
/*
- * Copyright 2019 Advanced Micro Devices, Inc.
+ * Copyright (C) 2019,2021 Advanced Micro Devices, Inc.
*
* Author: Rijo Thomas <Rijo-john.Thomas@amd.com>
* Author: Devaraj Rangasamy <Devaraj.Rangasamy@amd.com>
#include <linux/mutex.h>
#define TEE_DEFAULT_TIMEOUT 10
-#define MAX_BUFFER_SIZE 992
+#define MAX_BUFFER_SIZE 988
/**
* enum tee_ring_cmd_id - TEE interface commands for ring buffer configuration
};
/**
+ * enum cmd_resp_state - TEE command's response status maintained by driver
+ * @CMD_RESPONSE_INVALID: initial state when no command is written to ring
+ * @CMD_WAITING_FOR_RESPONSE: driver waiting for response from TEE
+ * @CMD_RESPONSE_TIMEDOUT: failed to get response from TEE
+ * @CMD_RESPONSE_COPIED: driver has copied response from TEE
+ */
+enum cmd_resp_state {
+ CMD_RESPONSE_INVALID,
+ CMD_WAITING_FOR_RESPONSE,
+ CMD_RESPONSE_TIMEDOUT,
+ CMD_RESPONSE_COPIED,
+};
+
+/**
* struct tee_ring_cmd - Structure of the command buffer in TEE ring
* @cmd_id: refers to &enum tee_cmd_id. Command id for the ring buffer
* interface
* @pdata: private data (currently unused)
* @res1: reserved region
* @buf: TEE command specific buffer
+ * @flag: refers to &enum cmd_resp_state
*/
struct tee_ring_cmd {
u32 cmd_id;
u64 pdata;
u32 res1[2];
u8 buf[MAX_BUFFER_SIZE];
+ u32 flag;
/* Total size: 1024 bytes */
} __packed;
req_mem_cc_regs = platform_get_resource(plat_dev, IORESOURCE_MEM, 0);
/* Map registers space */
new_drvdata->cc_base = devm_ioremap_resource(dev, req_mem_cc_regs);
- if (IS_ERR(new_drvdata->cc_base)) {
- dev_err(dev, "Failed to ioremap registers");
+ if (IS_ERR(new_drvdata->cc_base))
return PTR_ERR(new_drvdata->cc_base);
- }
dev_dbg(dev, "Got MEM resource (%s): %pR\n", req_mem_cc_regs->name,
req_mem_cc_regs);
return container_of(ctx->dev, struct uld_ctx, dev);
}
-static inline int is_ofld_imm(const struct sk_buff *skb)
-{
- return (skb->len <= SGE_MAX_WR_LEN);
-}
-
static inline void chcr_init_hctx_per_wr(struct chcr_ahash_req_ctx *reqctx)
{
memset(&reqctx->hctx_wr, 0, sizeof(struct chcr_hctx_per_wr));
struct uld_ctx *u_ctx = ULD_CTX(ctx);
unsigned int tx_channel_id, rx_channel_id;
unsigned int txqidx = 0, rxqidx = 0;
- unsigned int qid, fid;
+ unsigned int qid, fid, portno;
get_qidxs(req, &txqidx, &rxqidx);
qid = u_ctx->lldi.rxq_ids[rxqidx];
fid = u_ctx->lldi.rxq_ids[0];
+ portno = rxqidx / ctx->rxq_perchan;
tx_channel_id = txqidx / ctx->txq_perchan;
- rx_channel_id = rxqidx / ctx->rxq_perchan;
+ rx_channel_id = cxgb4_port_e2cchan(u_ctx->lldi.ports[portno]);
chcr_req->wreq.op_to_cctx_size = FILL_WR_OP_CCTX_SIZE;
/**
* create_cipher_wr - form the WR for cipher operations
- * @req: cipher req.
- * @ctx: crypto driver context of the request.
- * @qid: ingress qid where response of this WR should be received.
- * @op_type: encryption or decryption
+ * @wrparam: Container for create_cipher_wr()'s parameters
*/
static struct sk_buff *create_cipher_wr(struct cipher_wr_param *wrparam)
{
struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(wrparam->req);
struct chcr_context *ctx = c_ctx(tfm);
+ struct uld_ctx *u_ctx = ULD_CTX(ctx);
struct ablk_ctx *ablkctx = ABLK_CTX(ctx);
struct sk_buff *skb = NULL;
struct chcr_wr *chcr_req;
struct adapter *adap = padap(ctx->dev);
unsigned int rx_channel_id = reqctx->rxqidx / ctx->rxq_perchan;
+ rx_channel_id = cxgb4_port_e2cchan(u_ctx->lldi.ports[rx_channel_id]);
nents = sg_nents_xlen(reqctx->dstsg, wrparam->bytes, CHCR_DST_SG_SIZE,
reqctx->dst_ofst);
dst_size = get_space_for_phys_dsgl(nents);
/**
* create_hash_wr - Create hash work request
- * @req - Cipher req base
+ * @req: Cipher req base
+ * @param: Container for create_hash_wr()'s parameters
*/
static struct sk_buff *create_hash_wr(struct ahash_request *req,
struct hash_wr_param *param)
int error = 0;
unsigned int rx_channel_id = req_ctx->rxqidx / ctx->rxq_perchan;
+ rx_channel_id = cxgb4_port_e2cchan(u_ctx->lldi.ports[rx_channel_id]);
transhdr_len = HASH_TRANSHDR_SIZE(param->kctx_len);
req_ctx->hctx_wr.imm = (transhdr_len + param->bfr_len +
param->sg_len) <= SGE_MAX_WR_LEN;
{
struct crypto_aead *tfm = crypto_aead_reqtfm(req);
struct chcr_context *ctx = a_ctx(tfm);
+ struct uld_ctx *u_ctx = ULD_CTX(ctx);
struct chcr_aead_ctx *aeadctx = AEAD_CTX(ctx);
struct chcr_authenc_ctx *actx = AUTHENC_CTX(aeadctx);
struct chcr_aead_reqctx *reqctx = aead_request_ctx(req);
struct adapter *adap = padap(ctx->dev);
unsigned int rx_channel_id = reqctx->rxqidx / ctx->rxq_perchan;
+ rx_channel_id = cxgb4_port_e2cchan(u_ctx->lldi.ports[rx_channel_id]);
if (req->cryptlen == 0)
return NULL;
struct dsgl_walk dsgl_walk;
unsigned int authsize = crypto_aead_authsize(tfm);
struct chcr_context *ctx = a_ctx(tfm);
+ struct uld_ctx *u_ctx = ULD_CTX(ctx);
u32 temp;
unsigned int rx_channel_id = reqctx->rxqidx / ctx->rxq_perchan;
+ rx_channel_id = cxgb4_port_e2cchan(u_ctx->lldi.ports[rx_channel_id]);
dsgl_walk_init(&dsgl_walk, phys_cpl);
dsgl_walk_add_page(&dsgl_walk, IV + reqctx->b0_len, reqctx->iv_dma);
temp = req->assoclen + req->cryptlen +
struct chcr_skcipher_req_ctx *reqctx = skcipher_request_ctx(req);
struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(wrparam->req);
struct chcr_context *ctx = c_ctx(tfm);
+ struct uld_ctx *u_ctx = ULD_CTX(ctx);
struct dsgl_walk dsgl_walk;
unsigned int rx_channel_id = reqctx->rxqidx / ctx->rxq_perchan;
+ rx_channel_id = cxgb4_port_e2cchan(u_ctx->lldi.ports[rx_channel_id]);
dsgl_walk_init(&dsgl_walk, phys_cpl);
dsgl_walk_add_sg(&dsgl_walk, reqctx->dstsg, wrparam->bytes,
reqctx->dst_ofst);
{
struct crypto_aead *tfm = crypto_aead_reqtfm(req);
struct chcr_context *ctx = a_ctx(tfm);
+ struct uld_ctx *u_ctx = ULD_CTX(ctx);
struct chcr_aead_ctx *aeadctx = AEAD_CTX(ctx);
struct chcr_aead_reqctx *reqctx = aead_request_ctx(req);
unsigned int cipher_mode = CHCR_SCMD_CIPHER_MODE_AES_CCM;
unsigned int tag_offset = 0, auth_offset = 0;
unsigned int assoclen;
+ rx_channel_id = cxgb4_port_e2cchan(u_ctx->lldi.ports[rx_channel_id]);
+
if (get_aead_subtype(tfm) == CRYPTO_ALG_SUB_TYPE_AEAD_RFC4309)
assoclen = req->assoclen - 8;
else
{
struct crypto_aead *tfm = crypto_aead_reqtfm(req);
struct chcr_context *ctx = a_ctx(tfm);
+ struct uld_ctx *u_ctx = ULD_CTX(ctx);
struct chcr_aead_ctx *aeadctx = AEAD_CTX(ctx);
struct chcr_aead_reqctx *reqctx = aead_request_ctx(req);
struct sk_buff *skb = NULL;
struct adapter *adap = padap(ctx->dev);
unsigned int rx_channel_id = reqctx->rxqidx / ctx->rxq_perchan;
+ rx_channel_id = cxgb4_port_e2cchan(u_ctx->lldi.ports[rx_channel_id]);
if (get_aead_subtype(tfm) == CRYPTO_ALG_SUB_TYPE_AEAD_RFC4106)
assoclen = req->assoclen - 8;
-/**
+/*
* This file is part of the Chelsio T4/T5/T6 Ethernet driver for Linux.
*
* Copyright (C) 2011-2016 Chelsio Communications. All rights reserved.
struct uld_ctx *u_ctx;
/* Create the device and add it in the device list */
- pr_info_once("%s - version %s\n", DRV_DESC, DRV_VERSION);
+ pr_info_once("%s\n", DRV_DESC);
if (!(lld->ulp_crypto & ULP_CRYPTO_LOOKASIDE))
return ERR_PTR(-EOPNOTSUPP);
MODULE_DESCRIPTION("Crypto Co-processor for Chelsio Terminator cards.");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Chelsio Communications");
-MODULE_VERSION(DRV_VERSION);
#include "cxgb4_uld.h"
#define DRV_MODULE_NAME "chcr"
-#define DRV_VERSION "1.0.0.0-ko"
#define DRV_DESC "Chelsio T6 Crypto Co-processor Driver"
#define MAX_PENDING_REQ_TO_HW 20
/* Static structures */
static void __iomem *_iobase;
-static spinlock_t lock;
+static DEFINE_SPINLOCK(lock);
/* Write a 128 bit field (either a writable key or IV) */
static inline void
goto erequest;
}
- spin_lock_init(&lock);
-
/* Clear any pending activity */
iowrite32(AES_INTR_PENDING | AES_INTR_MASK, _iobase + AES_INTR_REG);
select CRYPTO_DEV_HISI_QM
select CRYPTO_DH
select CRYPTO_RSA
+ select CRYPTO_CURVE25519
+ select CRYPTO_ECDH
help
Support for HiSilicon HPRE(High Performance RSA Engine)
accelerator, which can accelerate RSA and DH algorithms.
#define HPRE_PF_DEF_Q_NUM 64
#define HPRE_PF_DEF_Q_BASE 0
+/*
+ * type used in qm sqc DW6.
+ * 0 - Algorithm which has been supported in V2, like RSA, DH and so on;
+ * 1 - ECC algorithm in V3.
+ */
+#define HPRE_V2_ALG_TYPE 0
+#define HPRE_V3_ECC_ALG_TYPE 1
+
enum {
HPRE_CLUSTER0,
HPRE_CLUSTER1,
};
enum hpre_ctrl_dbgfs_file {
- HPRE_CURRENT_QM,
HPRE_CLEAR_ENABLE,
HPRE_CLUSTER_CTRL,
HPRE_DEBUG_FILE_NUM,
HPRE_ALG_KG_CRT = 0x3,
HPRE_ALG_DH_G2 = 0x4,
HPRE_ALG_DH = 0x5,
+ HPRE_ALG_ECC_MUL = 0xD,
+ /* shared by x25519 and x448, but x448 is not supported now */
+ HPRE_ALG_CURVE25519_MUL = 0x10,
};
struct hpre_sqe {
__le32 rsvd1[_HPRE_SQE_ALIGN_EXT];
};
-struct hisi_qp *hpre_create_qp(void);
-int hpre_algs_register(void);
-void hpre_algs_unregister(void);
+struct hisi_qp *hpre_create_qp(u8 type);
+int hpre_algs_register(struct hisi_qm *qm);
+void hpre_algs_unregister(struct hisi_qm *qm);
#endif
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2019 HiSilicon Limited. */
#include <crypto/akcipher.h>
+#include <crypto/curve25519.h>
#include <crypto/dh.h>
+#include <crypto/ecc_curve.h>
+#include <crypto/ecdh.h>
#include <crypto/internal/akcipher.h>
#include <crypto/internal/kpp.h>
#include <crypto/internal/rsa.h>
#define HPRE_DFX_SEC_TO_US 1000000
#define HPRE_DFX_US_TO_NS 1000
+/* size in bytes of the n prime */
+#define HPRE_ECC_NIST_P192_N_SIZE 24
+#define HPRE_ECC_NIST_P256_N_SIZE 32
+
+/* size in bytes */
+#define HPRE_ECC_HW256_KSZ_B 32
+
typedef void (*hpre_cb)(struct hpre_ctx *ctx, void *sqe);
struct hpre_rsa_ctx {
* else if base if the counterpart public key we
* compute the shared secret
* ZZ = yb^xa mod p; [RFC2631 sec 2.1.1]
+ * low address: d--->n, please refer to Hisilicon HPRE UM
*/
- char *xa_p; /* low address: d--->n, please refer to Hisilicon HPRE UM */
+ char *xa_p;
dma_addr_t dma_xa_p;
char *g; /* m */
dma_addr_t dma_g;
};
+struct hpre_ecdh_ctx {
+ /* low address: p->a->k->b */
+ unsigned char *p;
+ dma_addr_t dma_p;
+
+ /* low address: x->y */
+ unsigned char *g;
+ dma_addr_t dma_g;
+};
+
+struct hpre_curve25519_ctx {
+ /* low address: p->a->k */
+ unsigned char *p;
+ dma_addr_t dma_p;
+
+ /* gx coordinate */
+ unsigned char *g;
+ dma_addr_t dma_g;
+};
+
struct hpre_ctx {
struct hisi_qp *qp;
struct hpre_asym_request **req_list;
union {
struct hpre_rsa_ctx rsa;
struct hpre_dh_ctx dh;
+ struct hpre_ecdh_ctx ecdh;
+ struct hpre_curve25519_ctx curve25519;
};
+ /* for ecc algorithms */
+ unsigned int curve_id;
};
struct hpre_asym_request {
union {
struct akcipher_request *rsa;
struct kpp_request *dh;
+ struct kpp_request *ecdh;
+ struct kpp_request *curve25519;
} areq;
int err;
int req_id;
}
}
-static struct hisi_qp *hpre_get_qp_and_start(void)
+static struct hisi_qp *hpre_get_qp_and_start(u8 type)
{
struct hisi_qp *qp;
int ret;
- qp = hpre_create_qp();
+ qp = hpre_create_qp(type);
if (!qp) {
pr_err("Can not create hpre qp!\n");
return ERR_PTR(-ENODEV);
dma_addr_t tmp;
tmp = le64_to_cpu(sqe->in);
- if (unlikely(!tmp))
- return;
if (src) {
if (req->src)
}
tmp = le64_to_cpu(sqe->out);
- if (unlikely(!tmp))
- return;
if (req->dst) {
if (dst)
static int hpre_alg_res_post_hf(struct hpre_ctx *ctx, struct hpre_sqe *sqe,
void **kreq)
{
+ struct device *dev = HPRE_DEV(ctx);
struct hpre_asym_request *req;
- int err, id, done;
+ unsigned int err, done, alg;
+ int id;
#define HPRE_NO_HW_ERR 0
#define HPRE_HW_TASK_DONE 3
#define HREE_HW_ERR_MASK 0x7ff
#define HREE_SQE_DONE_MASK 0x3
+#define HREE_ALG_TYPE_MASK 0x1f
id = (int)le16_to_cpu(sqe->tag);
req = ctx->req_list[id];
hpre_rm_req_from_ctx(req);
HREE_SQE_DONE_MASK;
if (likely(err == HPRE_NO_HW_ERR && done == HPRE_HW_TASK_DONE))
- return 0;
+ return 0;
+
+ alg = le32_to_cpu(sqe->dw0) & HREE_ALG_TYPE_MASK;
+ dev_err_ratelimited(dev, "alg[0x%x] error: done[0x%x], etype[0x%x]\n",
+ alg, done, err);
return -EINVAL;
}
struct hpre_sqe *sqe = resp;
struct hpre_asym_request *req = ctx->req_list[le16_to_cpu(sqe->tag)];
-
if (unlikely(!req)) {
atomic64_inc(&dfx[HPRE_INVALID_REQ_CNT].value);
return;
req->cb(ctx, resp);
}
-static int hpre_ctx_init(struct hpre_ctx *ctx)
+static void hpre_stop_qp_and_put(struct hisi_qp *qp)
+{
+ hisi_qm_stop_qp(qp);
+ hisi_qm_free_qps(&qp, 1);
+}
+
+static int hpre_ctx_init(struct hpre_ctx *ctx, u8 type)
{
struct hisi_qp *qp;
+ int ret;
- qp = hpre_get_qp_and_start();
+ qp = hpre_get_qp_and_start(type);
if (IS_ERR(qp))
return PTR_ERR(qp);
qp->qp_ctx = ctx;
qp->req_cb = hpre_alg_cb;
- return hpre_ctx_set(ctx, qp, QM_Q_DEPTH);
+ ret = hpre_ctx_set(ctx, qp, QM_Q_DEPTH);
+ if (ret)
+ hpre_stop_qp_and_put(qp);
+
+ return ret;
}
static int hpre_msg_request_set(struct hpre_ctx *ctx, void *req, bool is_rsa)
return ret;
}
-#ifdef CONFIG_CRYPTO_DH
static int hpre_dh_compute_value(struct kpp_request *req)
{
struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
{
struct hpre_ctx *ctx = kpp_tfm_ctx(tfm);
- return hpre_ctx_init(ctx);
+ return hpre_ctx_init(ctx, HPRE_V2_ALG_TYPE);
}
static void hpre_dh_exit_tfm(struct crypto_kpp *tfm)
hpre_dh_clear_ctx(ctx, true);
}
-#endif
static void hpre_rsa_drop_leading_zeros(const char **ptr, size_t *len)
{
return PTR_ERR(ctx->rsa.soft_tfm);
}
- ret = hpre_ctx_init(ctx);
+ ret = hpre_ctx_init(ctx, HPRE_V2_ALG_TYPE);
if (ret)
crypto_free_akcipher(ctx->rsa.soft_tfm);
crypto_free_akcipher(ctx->rsa.soft_tfm);
}
+static void hpre_key_to_big_end(u8 *data, int len)
+{
+ int i, j;
+ u8 tmp;
+
+ for (i = 0; i < len / 2; i++) {
+ j = len - i - 1;
+ tmp = data[j];
+ data[j] = data[i];
+ data[i] = tmp;
+ }
+}
+
+static void hpre_ecc_clear_ctx(struct hpre_ctx *ctx, bool is_clear_all,
+ bool is_ecdh)
+{
+ struct device *dev = HPRE_DEV(ctx);
+ unsigned int sz = ctx->key_sz;
+ unsigned int shift = sz << 1;
+
+ if (is_clear_all)
+ hisi_qm_stop_qp(ctx->qp);
+
+ if (is_ecdh && ctx->ecdh.p) {
+ /* ecdh: p->a->k->b */
+ memzero_explicit(ctx->ecdh.p + shift, sz);
+ dma_free_coherent(dev, sz << 3, ctx->ecdh.p, ctx->ecdh.dma_p);
+ ctx->ecdh.p = NULL;
+ } else if (!is_ecdh && ctx->curve25519.p) {
+ /* curve25519: p->a->k */
+ memzero_explicit(ctx->curve25519.p + shift, sz);
+ dma_free_coherent(dev, sz << 2, ctx->curve25519.p,
+ ctx->curve25519.dma_p);
+ ctx->curve25519.p = NULL;
+ }
+
+ hpre_ctx_clear(ctx, is_clear_all);
+}
+
+static unsigned int hpre_ecdh_supported_curve(unsigned short id)
+{
+ switch (id) {
+ case ECC_CURVE_NIST_P192:
+ case ECC_CURVE_NIST_P256:
+ return HPRE_ECC_HW256_KSZ_B;
+ default:
+ break;
+ }
+
+ return 0;
+}
+
+static void fill_curve_param(void *addr, u64 *param, unsigned int cur_sz, u8 ndigits)
+{
+ unsigned int sz = cur_sz - (ndigits - 1) * sizeof(u64);
+ u8 i = 0;
+
+ while (i < ndigits - 1) {
+ memcpy(addr + sizeof(u64) * i, ¶m[i], sizeof(u64));
+ i++;
+ }
+
+ memcpy(addr + sizeof(u64) * i, ¶m[ndigits - 1], sz);
+ hpre_key_to_big_end((u8 *)addr, cur_sz);
+}
+
+static int hpre_ecdh_fill_curve(struct hpre_ctx *ctx, struct ecdh *params,
+ unsigned int cur_sz)
+{
+ unsigned int shifta = ctx->key_sz << 1;
+ unsigned int shiftb = ctx->key_sz << 2;
+ void *p = ctx->ecdh.p + ctx->key_sz - cur_sz;
+ void *a = ctx->ecdh.p + shifta - cur_sz;
+ void *b = ctx->ecdh.p + shiftb - cur_sz;
+ void *x = ctx->ecdh.g + ctx->key_sz - cur_sz;
+ void *y = ctx->ecdh.g + shifta - cur_sz;
+ const struct ecc_curve *curve = ecc_get_curve(ctx->curve_id);
+ char *n;
+
+ if (unlikely(!curve))
+ return -EINVAL;
+
+ n = kzalloc(ctx->key_sz, GFP_KERNEL);
+ if (!n)
+ return -ENOMEM;
+
+ fill_curve_param(p, curve->p, cur_sz, curve->g.ndigits);
+ fill_curve_param(a, curve->a, cur_sz, curve->g.ndigits);
+ fill_curve_param(b, curve->b, cur_sz, curve->g.ndigits);
+ fill_curve_param(x, curve->g.x, cur_sz, curve->g.ndigits);
+ fill_curve_param(y, curve->g.y, cur_sz, curve->g.ndigits);
+ fill_curve_param(n, curve->n, cur_sz, curve->g.ndigits);
+
+ if (params->key_size == cur_sz && memcmp(params->key, n, cur_sz) >= 0) {
+ kfree(n);
+ return -EINVAL;
+ }
+
+ kfree(n);
+ return 0;
+}
+
+static unsigned int hpre_ecdh_get_curvesz(unsigned short id)
+{
+ switch (id) {
+ case ECC_CURVE_NIST_P192:
+ return HPRE_ECC_NIST_P192_N_SIZE;
+ case ECC_CURVE_NIST_P256:
+ return HPRE_ECC_NIST_P256_N_SIZE;
+ default:
+ break;
+ }
+
+ return 0;
+}
+
+static int hpre_ecdh_set_param(struct hpre_ctx *ctx, struct ecdh *params)
+{
+ struct device *dev = HPRE_DEV(ctx);
+ unsigned int sz, shift, curve_sz;
+ int ret;
+
+ ctx->key_sz = hpre_ecdh_supported_curve(ctx->curve_id);
+ if (!ctx->key_sz)
+ return -EINVAL;
+
+ curve_sz = hpre_ecdh_get_curvesz(ctx->curve_id);
+ if (!curve_sz || params->key_size > curve_sz)
+ return -EINVAL;
+
+ sz = ctx->key_sz;
+
+ if (!ctx->ecdh.p) {
+ ctx->ecdh.p = dma_alloc_coherent(dev, sz << 3, &ctx->ecdh.dma_p,
+ GFP_KERNEL);
+ if (!ctx->ecdh.p)
+ return -ENOMEM;
+ }
+
+ shift = sz << 2;
+ ctx->ecdh.g = ctx->ecdh.p + shift;
+ ctx->ecdh.dma_g = ctx->ecdh.dma_p + shift;
+
+ ret = hpre_ecdh_fill_curve(ctx, params, curve_sz);
+ if (ret) {
+ dev_err(dev, "failed to fill curve_param, ret = %d!\n", ret);
+ dma_free_coherent(dev, sz << 3, ctx->ecdh.p, ctx->ecdh.dma_p);
+ ctx->ecdh.p = NULL;
+ return ret;
+ }
+
+ return 0;
+}
+
+static bool hpre_key_is_zero(char *key, unsigned short key_sz)
+{
+ int i;
+
+ for (i = 0; i < key_sz; i++)
+ if (key[i])
+ return false;
+
+ return true;
+}
+
+static int hpre_ecdh_set_secret(struct crypto_kpp *tfm, const void *buf,
+ unsigned int len)
+{
+ struct hpre_ctx *ctx = kpp_tfm_ctx(tfm);
+ struct device *dev = HPRE_DEV(ctx);
+ unsigned int sz, sz_shift;
+ struct ecdh params;
+ int ret;
+
+ if (crypto_ecdh_decode_key(buf, len, ¶ms) < 0) {
+ dev_err(dev, "failed to decode ecdh key!\n");
+ return -EINVAL;
+ }
+
+ if (hpre_key_is_zero(params.key, params.key_size)) {
+ dev_err(dev, "Invalid hpre key!\n");
+ return -EINVAL;
+ }
+
+ hpre_ecc_clear_ctx(ctx, false, true);
+
+ ret = hpre_ecdh_set_param(ctx, ¶ms);
+ if (ret < 0) {
+ dev_err(dev, "failed to set hpre param, ret = %d!\n", ret);
+ return ret;
+ }
+
+ sz = ctx->key_sz;
+ sz_shift = (sz << 1) + sz - params.key_size;
+ memcpy(ctx->ecdh.p + sz_shift, params.key, params.key_size);
+
+ return 0;
+}
+
+static void hpre_ecdh_hw_data_clr_all(struct hpre_ctx *ctx,
+ struct hpre_asym_request *req,
+ struct scatterlist *dst,
+ struct scatterlist *src)
+{
+ struct device *dev = HPRE_DEV(ctx);
+ struct hpre_sqe *sqe = &req->req;
+ dma_addr_t dma;
+
+ dma = le64_to_cpu(sqe->in);
+
+ if (src && req->src)
+ dma_free_coherent(dev, ctx->key_sz << 2, req->src, dma);
+
+ dma = le64_to_cpu(sqe->out);
+
+ if (req->dst)
+ dma_free_coherent(dev, ctx->key_sz << 1, req->dst, dma);
+ if (dst)
+ dma_unmap_single(dev, dma, ctx->key_sz << 1, DMA_FROM_DEVICE);
+}
+
+static void hpre_ecdh_cb(struct hpre_ctx *ctx, void *resp)
+{
+ unsigned int curve_sz = hpre_ecdh_get_curvesz(ctx->curve_id);
+ struct hpre_dfx *dfx = ctx->hpre->debug.dfx;
+ struct hpre_asym_request *req = NULL;
+ struct kpp_request *areq;
+ u64 overtime_thrhld;
+ char *p;
+ int ret;
+
+ ret = hpre_alg_res_post_hf(ctx, resp, (void **)&req);
+ areq = req->areq.ecdh;
+ areq->dst_len = ctx->key_sz << 1;
+
+ overtime_thrhld = atomic64_read(&dfx[HPRE_OVERTIME_THRHLD].value);
+ if (overtime_thrhld && hpre_is_bd_timeout(req, overtime_thrhld))
+ atomic64_inc(&dfx[HPRE_OVER_THRHLD_CNT].value);
+
+ p = sg_virt(areq->dst);
+ memmove(p, p + ctx->key_sz - curve_sz, curve_sz);
+ memmove(p + curve_sz, p + areq->dst_len - curve_sz, curve_sz);
+
+ hpre_ecdh_hw_data_clr_all(ctx, req, areq->dst, areq->src);
+ kpp_request_complete(areq, ret);
+
+ atomic64_inc(&dfx[HPRE_RECV_CNT].value);
+}
+
+static int hpre_ecdh_msg_request_set(struct hpre_ctx *ctx,
+ struct kpp_request *req)
+{
+ struct hpre_asym_request *h_req;
+ struct hpre_sqe *msg;
+ int req_id;
+ void *tmp;
+
+ if (req->dst_len < ctx->key_sz << 1) {
+ req->dst_len = ctx->key_sz << 1;
+ return -EINVAL;
+ }
+
+ tmp = kpp_request_ctx(req);
+ h_req = PTR_ALIGN(tmp, HPRE_ALIGN_SZ);
+ h_req->cb = hpre_ecdh_cb;
+ h_req->areq.ecdh = req;
+ msg = &h_req->req;
+ memset(msg, 0, sizeof(*msg));
+ msg->key = cpu_to_le64(ctx->ecdh.dma_p);
+
+ msg->dw0 |= cpu_to_le32(0x1U << HPRE_SQE_DONE_SHIFT);
+ msg->task_len1 = (ctx->key_sz >> HPRE_BITS_2_BYTES_SHIFT) - 1;
+ h_req->ctx = ctx;
+
+ req_id = hpre_add_req_to_ctx(h_req);
+ if (req_id < 0)
+ return -EBUSY;
+
+ msg->tag = cpu_to_le16((u16)req_id);
+ return 0;
+}
+
+static int hpre_ecdh_src_data_init(struct hpre_asym_request *hpre_req,
+ struct scatterlist *data, unsigned int len)
+{
+ struct hpre_sqe *msg = &hpre_req->req;
+ struct hpre_ctx *ctx = hpre_req->ctx;
+ struct device *dev = HPRE_DEV(ctx);
+ unsigned int tmpshift;
+ dma_addr_t dma = 0;
+ void *ptr;
+ int shift;
+
+ /* Src_data include gx and gy. */
+ shift = ctx->key_sz - (len >> 1);
+ if (unlikely(shift < 0))
+ return -EINVAL;
+
+ ptr = dma_alloc_coherent(dev, ctx->key_sz << 2, &dma, GFP_KERNEL);
+ if (unlikely(!ptr))
+ return -ENOMEM;
+
+ tmpshift = ctx->key_sz << 1;
+ scatterwalk_map_and_copy(ptr + tmpshift, data, 0, len, 0);
+ memcpy(ptr + shift, ptr + tmpshift, len >> 1);
+ memcpy(ptr + ctx->key_sz + shift, ptr + tmpshift + (len >> 1), len >> 1);
+
+ hpre_req->src = ptr;
+ msg->in = cpu_to_le64(dma);
+ return 0;
+}
+
+static int hpre_ecdh_dst_data_init(struct hpre_asym_request *hpre_req,
+ struct scatterlist *data, unsigned int len)
+{
+ struct hpre_sqe *msg = &hpre_req->req;
+ struct hpre_ctx *ctx = hpre_req->ctx;
+ struct device *dev = HPRE_DEV(ctx);
+ dma_addr_t dma = 0;
+
+ if (unlikely(!data || !sg_is_last(data) || len != ctx->key_sz << 1)) {
+ dev_err(dev, "data or data length is illegal!\n");
+ return -EINVAL;
+ }
+
+ hpre_req->dst = NULL;
+ dma = dma_map_single(dev, sg_virt(data), len, DMA_FROM_DEVICE);
+ if (unlikely(dma_mapping_error(dev, dma))) {
+ dev_err(dev, "dma map data err!\n");
+ return -ENOMEM;
+ }
+
+ msg->out = cpu_to_le64(dma);
+ return 0;
+}
+
+static int hpre_ecdh_compute_value(struct kpp_request *req)
+{
+ struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
+ struct hpre_ctx *ctx = kpp_tfm_ctx(tfm);
+ struct device *dev = HPRE_DEV(ctx);
+ void *tmp = kpp_request_ctx(req);
+ struct hpre_asym_request *hpre_req = PTR_ALIGN(tmp, HPRE_ALIGN_SZ);
+ struct hpre_sqe *msg = &hpre_req->req;
+ int ret;
+
+ ret = hpre_ecdh_msg_request_set(ctx, req);
+ if (unlikely(ret)) {
+ dev_err(dev, "failed to set ecdh request, ret = %d!\n", ret);
+ return ret;
+ }
+
+ if (req->src) {
+ ret = hpre_ecdh_src_data_init(hpre_req, req->src, req->src_len);
+ if (unlikely(ret)) {
+ dev_err(dev, "failed to init src data, ret = %d!\n", ret);
+ goto clear_all;
+ }
+ } else {
+ msg->in = cpu_to_le64(ctx->ecdh.dma_g);
+ }
+
+ ret = hpre_ecdh_dst_data_init(hpre_req, req->dst, req->dst_len);
+ if (unlikely(ret)) {
+ dev_err(dev, "failed to init dst data, ret = %d!\n", ret);
+ goto clear_all;
+ }
+
+ msg->dw0 = cpu_to_le32(le32_to_cpu(msg->dw0) | HPRE_ALG_ECC_MUL);
+ ret = hpre_send(ctx, msg);
+ if (likely(!ret))
+ return -EINPROGRESS;
+
+clear_all:
+ hpre_rm_req_from_ctx(hpre_req);
+ hpre_ecdh_hw_data_clr_all(ctx, hpre_req, req->dst, req->src);
+ return ret;
+}
+
+static unsigned int hpre_ecdh_max_size(struct crypto_kpp *tfm)
+{
+ struct hpre_ctx *ctx = kpp_tfm_ctx(tfm);
+
+ /* max size is the pub_key_size, include x and y */
+ return ctx->key_sz << 1;
+}
+
+static int hpre_ecdh_nist_p192_init_tfm(struct crypto_kpp *tfm)
+{
+ struct hpre_ctx *ctx = kpp_tfm_ctx(tfm);
+
+ ctx->curve_id = ECC_CURVE_NIST_P192;
+
+ return hpre_ctx_init(ctx, HPRE_V3_ECC_ALG_TYPE);
+}
+
+static int hpre_ecdh_nist_p256_init_tfm(struct crypto_kpp *tfm)
+{
+ struct hpre_ctx *ctx = kpp_tfm_ctx(tfm);
+
+ ctx->curve_id = ECC_CURVE_NIST_P256;
+
+ return hpre_ctx_init(ctx, HPRE_V3_ECC_ALG_TYPE);
+}
+
+static void hpre_ecdh_exit_tfm(struct crypto_kpp *tfm)
+{
+ struct hpre_ctx *ctx = kpp_tfm_ctx(tfm);
+
+ hpre_ecc_clear_ctx(ctx, true, true);
+}
+
+static void hpre_curve25519_fill_curve(struct hpre_ctx *ctx, const void *buf,
+ unsigned int len)
+{
+ u8 secret[CURVE25519_KEY_SIZE] = { 0 };
+ unsigned int sz = ctx->key_sz;
+ const struct ecc_curve *curve;
+ unsigned int shift = sz << 1;
+ void *p;
+
+ /*
+ * The key from 'buf' is in little-endian, we should preprocess it as
+ * the description in rfc7748: "k[0] &= 248, k[31] &= 127, k[31] |= 64",
+ * then convert it to big endian. Only in this way, the result can be
+ * the same as the software curve-25519 that exists in crypto.
+ */
+ memcpy(secret, buf, len);
+ curve25519_clamp_secret(secret);
+ hpre_key_to_big_end(secret, CURVE25519_KEY_SIZE);
+
+ p = ctx->curve25519.p + sz - len;
+
+ curve = ecc_get_curve25519();
+
+ /* fill curve parameters */
+ fill_curve_param(p, curve->p, len, curve->g.ndigits);
+ fill_curve_param(p + sz, curve->a, len, curve->g.ndigits);
+ memcpy(p + shift, secret, len);
+ fill_curve_param(p + shift + sz, curve->g.x, len, curve->g.ndigits);
+ memzero_explicit(secret, CURVE25519_KEY_SIZE);
+}
+
+static int hpre_curve25519_set_param(struct hpre_ctx *ctx, const void *buf,
+ unsigned int len)
+{
+ struct device *dev = HPRE_DEV(ctx);
+ unsigned int sz = ctx->key_sz;
+ unsigned int shift = sz << 1;
+
+ /* p->a->k->gx */
+ if (!ctx->curve25519.p) {
+ ctx->curve25519.p = dma_alloc_coherent(dev, sz << 2,
+ &ctx->curve25519.dma_p,
+ GFP_KERNEL);
+ if (!ctx->curve25519.p)
+ return -ENOMEM;
+ }
+
+ ctx->curve25519.g = ctx->curve25519.p + shift + sz;
+ ctx->curve25519.dma_g = ctx->curve25519.dma_p + shift + sz;
+
+ hpre_curve25519_fill_curve(ctx, buf, len);
+
+ return 0;
+}
+
+static int hpre_curve25519_set_secret(struct crypto_kpp *tfm, const void *buf,
+ unsigned int len)
+{
+ struct hpre_ctx *ctx = kpp_tfm_ctx(tfm);
+ struct device *dev = HPRE_DEV(ctx);
+ int ret = -EINVAL;
+
+ if (len != CURVE25519_KEY_SIZE ||
+ !crypto_memneq(buf, curve25519_null_point, CURVE25519_KEY_SIZE)) {
+ dev_err(dev, "key is null or key len is not 32bytes!\n");
+ return ret;
+ }
+
+ /* Free old secret if any */
+ hpre_ecc_clear_ctx(ctx, false, false);
+
+ ctx->key_sz = CURVE25519_KEY_SIZE;
+ ret = hpre_curve25519_set_param(ctx, buf, CURVE25519_KEY_SIZE);
+ if (ret) {
+ dev_err(dev, "failed to set curve25519 param, ret = %d!\n", ret);
+ hpre_ecc_clear_ctx(ctx, false, false);
+ return ret;
+ }
+
+ return 0;
+}
+
+static void hpre_curve25519_hw_data_clr_all(struct hpre_ctx *ctx,
+ struct hpre_asym_request *req,
+ struct scatterlist *dst,
+ struct scatterlist *src)
+{
+ struct device *dev = HPRE_DEV(ctx);
+ struct hpre_sqe *sqe = &req->req;
+ dma_addr_t dma;
+
+ dma = le64_to_cpu(sqe->in);
+
+ if (src && req->src)
+ dma_free_coherent(dev, ctx->key_sz, req->src, dma);
+
+ dma = le64_to_cpu(sqe->out);
+
+ if (req->dst)
+ dma_free_coherent(dev, ctx->key_sz, req->dst, dma);
+ if (dst)
+ dma_unmap_single(dev, dma, ctx->key_sz, DMA_FROM_DEVICE);
+}
+
+static void hpre_curve25519_cb(struct hpre_ctx *ctx, void *resp)
+{
+ struct hpre_dfx *dfx = ctx->hpre->debug.dfx;
+ struct hpre_asym_request *req = NULL;
+ struct kpp_request *areq;
+ u64 overtime_thrhld;
+ int ret;
+
+ ret = hpre_alg_res_post_hf(ctx, resp, (void **)&req);
+ areq = req->areq.curve25519;
+ areq->dst_len = ctx->key_sz;
+
+ overtime_thrhld = atomic64_read(&dfx[HPRE_OVERTIME_THRHLD].value);
+ if (overtime_thrhld && hpre_is_bd_timeout(req, overtime_thrhld))
+ atomic64_inc(&dfx[HPRE_OVER_THRHLD_CNT].value);
+
+ hpre_key_to_big_end(sg_virt(areq->dst), CURVE25519_KEY_SIZE);
+
+ hpre_curve25519_hw_data_clr_all(ctx, req, areq->dst, areq->src);
+ kpp_request_complete(areq, ret);
+
+ atomic64_inc(&dfx[HPRE_RECV_CNT].value);
+}
+
+static int hpre_curve25519_msg_request_set(struct hpre_ctx *ctx,
+ struct kpp_request *req)
+{
+ struct hpre_asym_request *h_req;
+ struct hpre_sqe *msg;
+ int req_id;
+ void *tmp;
+
+ if (unlikely(req->dst_len < ctx->key_sz)) {
+ req->dst_len = ctx->key_sz;
+ return -EINVAL;
+ }
+
+ tmp = kpp_request_ctx(req);
+ h_req = PTR_ALIGN(tmp, HPRE_ALIGN_SZ);
+ h_req->cb = hpre_curve25519_cb;
+ h_req->areq.curve25519 = req;
+ msg = &h_req->req;
+ memset(msg, 0, sizeof(*msg));
+ msg->key = cpu_to_le64(ctx->curve25519.dma_p);
+
+ msg->dw0 |= cpu_to_le32(0x1U << HPRE_SQE_DONE_SHIFT);
+ msg->task_len1 = (ctx->key_sz >> HPRE_BITS_2_BYTES_SHIFT) - 1;
+ h_req->ctx = ctx;
+
+ req_id = hpre_add_req_to_ctx(h_req);
+ if (req_id < 0)
+ return -EBUSY;
+
+ msg->tag = cpu_to_le16((u16)req_id);
+ return 0;
+}
+
+static void hpre_curve25519_src_modulo_p(u8 *ptr)
+{
+ int i;
+
+ for (i = 0; i < CURVE25519_KEY_SIZE - 1; i++)
+ ptr[i] = 0;
+
+ /* The modulus is ptr's last byte minus '0xed'(last byte of p) */
+ ptr[i] -= 0xed;
+}
+
+static int hpre_curve25519_src_init(struct hpre_asym_request *hpre_req,
+ struct scatterlist *data, unsigned int len)
+{
+ struct hpre_sqe *msg = &hpre_req->req;
+ struct hpre_ctx *ctx = hpre_req->ctx;
+ struct device *dev = HPRE_DEV(ctx);
+ u8 p[CURVE25519_KEY_SIZE] = { 0 };
+ const struct ecc_curve *curve;
+ dma_addr_t dma = 0;
+ u8 *ptr;
+
+ if (len != CURVE25519_KEY_SIZE) {
+ dev_err(dev, "sourc_data len is not 32bytes, len = %u!\n", len);
+ return -EINVAL;
+ }
+
+ ptr = dma_alloc_coherent(dev, ctx->key_sz, &dma, GFP_KERNEL);
+ if (unlikely(!ptr))
+ return -ENOMEM;
+
+ scatterwalk_map_and_copy(ptr, data, 0, len, 0);
+
+ if (!crypto_memneq(ptr, curve25519_null_point, CURVE25519_KEY_SIZE)) {
+ dev_err(dev, "gx is null!\n");
+ goto err;
+ }
+
+ /*
+ * Src_data(gx) is in little-endian order, MSB in the final byte should
+ * be masked as described in RFC7748, then transform it to big-endian
+ * form, then hisi_hpre can use the data.
+ */
+ ptr[31] &= 0x7f;
+ hpre_key_to_big_end(ptr, CURVE25519_KEY_SIZE);
+
+ curve = ecc_get_curve25519();
+
+ fill_curve_param(p, curve->p, CURVE25519_KEY_SIZE, curve->g.ndigits);
+
+ /*
+ * When src_data equals (2^255 - 19) ~ (2^255 - 1), it is out of p,
+ * we get its modulus to p, and then use it.
+ */
+ if (memcmp(ptr, p, ctx->key_sz) >= 0)
+ hpre_curve25519_src_modulo_p(ptr);
+
+ hpre_req->src = ptr;
+ msg->in = cpu_to_le64(dma);
+ return 0;
+
+err:
+ dma_free_coherent(dev, ctx->key_sz, ptr, dma);
+ return -EINVAL;
+}
+
+static int hpre_curve25519_dst_init(struct hpre_asym_request *hpre_req,
+ struct scatterlist *data, unsigned int len)
+{
+ struct hpre_sqe *msg = &hpre_req->req;
+ struct hpre_ctx *ctx = hpre_req->ctx;
+ struct device *dev = HPRE_DEV(ctx);
+ dma_addr_t dma = 0;
+
+ if (!data || !sg_is_last(data) || len != ctx->key_sz) {
+ dev_err(dev, "data or data length is illegal!\n");
+ return -EINVAL;
+ }
+
+ hpre_req->dst = NULL;
+ dma = dma_map_single(dev, sg_virt(data), len, DMA_FROM_DEVICE);
+ if (unlikely(dma_mapping_error(dev, dma))) {
+ dev_err(dev, "dma map data err!\n");
+ return -ENOMEM;
+ }
+
+ msg->out = cpu_to_le64(dma);
+ return 0;
+}
+
+static int hpre_curve25519_compute_value(struct kpp_request *req)
+{
+ struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
+ struct hpre_ctx *ctx = kpp_tfm_ctx(tfm);
+ struct device *dev = HPRE_DEV(ctx);
+ void *tmp = kpp_request_ctx(req);
+ struct hpre_asym_request *hpre_req = PTR_ALIGN(tmp, HPRE_ALIGN_SZ);
+ struct hpre_sqe *msg = &hpre_req->req;
+ int ret;
+
+ ret = hpre_curve25519_msg_request_set(ctx, req);
+ if (unlikely(ret)) {
+ dev_err(dev, "failed to set curve25519 request, ret = %d!\n", ret);
+ return ret;
+ }
+
+ if (req->src) {
+ ret = hpre_curve25519_src_init(hpre_req, req->src, req->src_len);
+ if (unlikely(ret)) {
+ dev_err(dev, "failed to init src data, ret = %d!\n",
+ ret);
+ goto clear_all;
+ }
+ } else {
+ msg->in = cpu_to_le64(ctx->curve25519.dma_g);
+ }
+
+ ret = hpre_curve25519_dst_init(hpre_req, req->dst, req->dst_len);
+ if (unlikely(ret)) {
+ dev_err(dev, "failed to init dst data, ret = %d!\n", ret);
+ goto clear_all;
+ }
+
+ msg->dw0 = cpu_to_le32(le32_to_cpu(msg->dw0) | HPRE_ALG_CURVE25519_MUL);
+ ret = hpre_send(ctx, msg);
+ if (likely(!ret))
+ return -EINPROGRESS;
+
+clear_all:
+ hpre_rm_req_from_ctx(hpre_req);
+ hpre_curve25519_hw_data_clr_all(ctx, hpre_req, req->dst, req->src);
+ return ret;
+}
+
+static unsigned int hpre_curve25519_max_size(struct crypto_kpp *tfm)
+{
+ struct hpre_ctx *ctx = kpp_tfm_ctx(tfm);
+
+ return ctx->key_sz;
+}
+
+static int hpre_curve25519_init_tfm(struct crypto_kpp *tfm)
+{
+ struct hpre_ctx *ctx = kpp_tfm_ctx(tfm);
+
+ return hpre_ctx_init(ctx, HPRE_V3_ECC_ALG_TYPE);
+}
+
+static void hpre_curve25519_exit_tfm(struct crypto_kpp *tfm)
+{
+ struct hpre_ctx *ctx = kpp_tfm_ctx(tfm);
+
+ hpre_ecc_clear_ctx(ctx, true, false);
+}
+
static struct akcipher_alg rsa = {
.sign = hpre_rsa_dec,
.verify = hpre_rsa_enc,
},
};
-#ifdef CONFIG_CRYPTO_DH
static struct kpp_alg dh = {
.set_secret = hpre_dh_set_secret,
.generate_public_key = hpre_dh_compute_value,
.cra_module = THIS_MODULE,
},
};
-#endif
-int hpre_algs_register(void)
+static struct kpp_alg ecdh_nist_p192 = {
+ .set_secret = hpre_ecdh_set_secret,
+ .generate_public_key = hpre_ecdh_compute_value,
+ .compute_shared_secret = hpre_ecdh_compute_value,
+ .max_size = hpre_ecdh_max_size,
+ .init = hpre_ecdh_nist_p192_init_tfm,
+ .exit = hpre_ecdh_exit_tfm,
+ .reqsize = sizeof(struct hpre_asym_request) + HPRE_ALIGN_SZ,
+ .base = {
+ .cra_ctxsize = sizeof(struct hpre_ctx),
+ .cra_priority = HPRE_CRYPTO_ALG_PRI,
+ .cra_name = "ecdh-nist-p192",
+ .cra_driver_name = "hpre-ecdh",
+ .cra_module = THIS_MODULE,
+ },
+};
+
+static struct kpp_alg ecdh_nist_p256 = {
+ .set_secret = hpre_ecdh_set_secret,
+ .generate_public_key = hpre_ecdh_compute_value,
+ .compute_shared_secret = hpre_ecdh_compute_value,
+ .max_size = hpre_ecdh_max_size,
+ .init = hpre_ecdh_nist_p256_init_tfm,
+ .exit = hpre_ecdh_exit_tfm,
+ .reqsize = sizeof(struct hpre_asym_request) + HPRE_ALIGN_SZ,
+ .base = {
+ .cra_ctxsize = sizeof(struct hpre_ctx),
+ .cra_priority = HPRE_CRYPTO_ALG_PRI,
+ .cra_name = "ecdh-nist-p256",
+ .cra_driver_name = "hpre-ecdh",
+ .cra_module = THIS_MODULE,
+ },
+};
+
+static struct kpp_alg curve25519_alg = {
+ .set_secret = hpre_curve25519_set_secret,
+ .generate_public_key = hpre_curve25519_compute_value,
+ .compute_shared_secret = hpre_curve25519_compute_value,
+ .max_size = hpre_curve25519_max_size,
+ .init = hpre_curve25519_init_tfm,
+ .exit = hpre_curve25519_exit_tfm,
+ .reqsize = sizeof(struct hpre_asym_request) + HPRE_ALIGN_SZ,
+ .base = {
+ .cra_ctxsize = sizeof(struct hpre_ctx),
+ .cra_priority = HPRE_CRYPTO_ALG_PRI,
+ .cra_name = "curve25519",
+ .cra_driver_name = "hpre-curve25519",
+ .cra_module = THIS_MODULE,
+ },
+};
+
+
+static int hpre_register_ecdh(void)
+{
+ int ret;
+
+ ret = crypto_register_kpp(&ecdh_nist_p192);
+ if (ret)
+ return ret;
+
+ ret = crypto_register_kpp(&ecdh_nist_p256);
+ if (ret) {
+ crypto_unregister_kpp(&ecdh_nist_p192);
+ return ret;
+ }
+
+ return 0;
+}
+
+static void hpre_unregister_ecdh(void)
+{
+ crypto_unregister_kpp(&ecdh_nist_p256);
+ crypto_unregister_kpp(&ecdh_nist_p192);
+}
+
+int hpre_algs_register(struct hisi_qm *qm)
{
int ret;
ret = crypto_register_akcipher(&rsa);
if (ret)
return ret;
-#ifdef CONFIG_CRYPTO_DH
+
ret = crypto_register_kpp(&dh);
if (ret)
- crypto_unregister_akcipher(&rsa);
-#endif
+ goto unreg_rsa;
+
+ if (qm->ver >= QM_HW_V3) {
+ ret = hpre_register_ecdh();
+ if (ret)
+ goto unreg_dh;
+ ret = crypto_register_kpp(&curve25519_alg);
+ if (ret)
+ goto unreg_ecdh;
+ }
+ return 0;
+unreg_ecdh:
+ hpre_unregister_ecdh();
+unreg_dh:
+ crypto_unregister_kpp(&dh);
+unreg_rsa:
+ crypto_unregister_akcipher(&rsa);
return ret;
}
-void hpre_algs_unregister(void)
+void hpre_algs_unregister(struct hisi_qm *qm)
{
- crypto_unregister_akcipher(&rsa);
-#ifdef CONFIG_CRYPTO_DH
+ if (qm->ver >= QM_HW_V3) {
+ crypto_unregister_kpp(&curve25519_alg);
+ hpre_unregister_ecdh();
+ }
+
crypto_unregister_kpp(&dh);
-#endif
+ crypto_unregister_akcipher(&rsa);
}
#include <linux/uacce.h>
#include "hpre.h"
-#define HPRE_QUEUE_NUM_V2 1024
#define HPRE_QM_ABNML_INT_MASK 0x100004
#define HPRE_CTRL_CNT_CLR_CE_BIT BIT(0)
#define HPRE_COMM_CNT_CLR_CE 0x0
};
static const char * const hpre_debug_file_name[] = {
- [HPRE_CURRENT_QM] = "current_qm",
[HPRE_CLEAR_ENABLE] = "rdclr_en",
[HPRE_CLUSTER_CTRL] = "cluster_ctrl",
};
module_param_cb(vfs_num, &vfs_num_ops, &vfs_num, 0444);
MODULE_PARM_DESC(vfs_num, "Number of VFs to enable(1-63), 0(default)");
-struct hisi_qp *hpre_create_qp(void)
+struct hisi_qp *hpre_create_qp(u8 type)
{
int node = cpu_to_node(smp_processor_id());
struct hisi_qp *qp = NULL;
int ret;
- ret = hisi_qm_alloc_qps_node(&hpre_devices, 1, 0, node, &qp);
+ if (type != HPRE_V2_ALG_TYPE && type != HPRE_V3_ECC_ALG_TYPE)
+ return NULL;
+
+ /*
+ * type: 0 - RSA/DH. algorithm supported in V2,
+ * 1 - ECC algorithm in V3.
+ */
+ ret = hisi_qm_alloc_qps_node(&hpre_devices, 1, type, node, &qp);
if (!ret)
return qp;
return NULL;
}
-static void hpre_pasid_enable(struct hisi_qm *qm)
+static void hpre_config_pasid(struct hisi_qm *qm)
{
- u32 val;
-
- val = readl_relaxed(qm->io_base + HPRE_DATA_RUSER_CFG);
- val |= BIT(HPRE_PASID_EN_BIT);
- writel_relaxed(val, qm->io_base + HPRE_DATA_RUSER_CFG);
- val = readl_relaxed(qm->io_base + HPRE_DATA_WUSER_CFG);
- val |= BIT(HPRE_PASID_EN_BIT);
- writel_relaxed(val, qm->io_base + HPRE_DATA_WUSER_CFG);
-}
+ u32 val1, val2;
-static void hpre_pasid_disable(struct hisi_qm *qm)
-{
- u32 val;
+ if (qm->ver >= QM_HW_V3)
+ return;
- val = readl_relaxed(qm->io_base + HPRE_DATA_RUSER_CFG);
- val &= ~BIT(HPRE_PASID_EN_BIT);
- writel_relaxed(val, qm->io_base + HPRE_DATA_RUSER_CFG);
- val = readl_relaxed(qm->io_base + HPRE_DATA_WUSER_CFG);
- val &= ~BIT(HPRE_PASID_EN_BIT);
- writel_relaxed(val, qm->io_base + HPRE_DATA_WUSER_CFG);
+ val1 = readl_relaxed(qm->io_base + HPRE_DATA_RUSER_CFG);
+ val2 = readl_relaxed(qm->io_base + HPRE_DATA_WUSER_CFG);
+ if (qm->use_sva) {
+ val1 |= BIT(HPRE_PASID_EN_BIT);
+ val2 |= BIT(HPRE_PASID_EN_BIT);
+ } else {
+ val1 &= ~BIT(HPRE_PASID_EN_BIT);
+ val2 &= ~BIT(HPRE_PASID_EN_BIT);
+ }
+ writel_relaxed(val1, qm->io_base + HPRE_DATA_RUSER_CFG);
+ writel_relaxed(val2, qm->io_base + HPRE_DATA_WUSER_CFG);
}
static int hpre_cfg_by_dsm(struct hisi_qm *qm)
}
/*
- * For Kunpeng 920, we shoul disable FLR triggered by hardware (BME/PM/SRIOV).
+ * For Kunpeng 920, we should disable FLR triggered by hardware (BME/PM/SRIOV).
* Or it may stay in D3 state when we bind and unbind hpre quickly,
* as it does FLR triggered by hardware.
*/
if (qm->ver == QM_HW_V2) {
ret = hpre_cfg_by_dsm(qm);
if (ret)
- dev_err(dev, "acpi_evaluate_dsm err.\n");
+ return ret;
disable_flr_of_bme(qm);
-
- /* Enable data buffer pasid */
- if (qm->use_sva)
- hpre_pasid_enable(qm);
}
+ /* Config data buffer pasid needed by Kunpeng 920 */
+ hpre_config_pasid(qm);
+
return ret;
}
unsigned long offset;
int i;
- /* clear current_qm */
- writel(0x0, qm->io_base + QM_DFX_MB_CNT_VF);
- writel(0x0, qm->io_base + QM_DFX_DB_CNT_VF);
-
/* clear clusterX/cluster_ctrl */
for (i = 0; i < clusters_num; i++) {
offset = HPRE_CLSTR_BASE + i * HPRE_CLSTR_ADDR_INTRVL;
return &hpre->qm;
}
-static u32 hpre_current_qm_read(struct hpre_debugfs_file *file)
-{
- struct hisi_qm *qm = hpre_file_to_qm(file);
-
- return readl(qm->io_base + QM_DFX_MB_CNT_VF);
-}
-
-static int hpre_current_qm_write(struct hpre_debugfs_file *file, u32 val)
-{
- struct hisi_qm *qm = hpre_file_to_qm(file);
- u32 num_vfs = qm->vfs_num;
- u32 vfq_num, tmp;
-
- if (val > num_vfs)
- return -EINVAL;
-
- /* According PF or VF Dev ID to calculation curr_qm_qp_num and store */
- if (val == 0) {
- qm->debug.curr_qm_qp_num = qm->qp_num;
- } else {
- vfq_num = (qm->ctrl_qp_num - qm->qp_num) / num_vfs;
- if (val == num_vfs) {
- qm->debug.curr_qm_qp_num =
- qm->ctrl_qp_num - qm->qp_num - (num_vfs - 1) * vfq_num;
- } else {
- qm->debug.curr_qm_qp_num = vfq_num;
- }
- }
-
- writel(val, qm->io_base + QM_DFX_MB_CNT_VF);
- writel(val, qm->io_base + QM_DFX_DB_CNT_VF);
-
- tmp = val |
- (readl(qm->io_base + QM_DFX_SQE_CNT_VF_SQN) & CURRENT_Q_MASK);
- writel(tmp, qm->io_base + QM_DFX_SQE_CNT_VF_SQN);
-
- tmp = val |
- (readl(qm->io_base + QM_DFX_CQE_CNT_VF_CQN) & CURRENT_Q_MASK);
- writel(tmp, qm->io_base + QM_DFX_CQE_CNT_VF_CQN);
-
- return 0;
-}
-
static u32 hpre_clear_enable_read(struct hpre_debugfs_file *file)
{
struct hisi_qm *qm = hpre_file_to_qm(file);
~HPRE_CTRL_CNT_CLR_CE_BIT) | val;
writel(tmp, qm->io_base + HPRE_CTRL_CNT_CLR_CE);
- return 0;
+ return 0;
}
static u32 hpre_cluster_inqry_read(struct hpre_debugfs_file *file)
writel(val, qm->io_base + offset + HPRE_CLUSTER_INQURY);
- return 0;
+ return 0;
}
static ssize_t hpre_ctrl_debug_read(struct file *filp, char __user *buf,
spin_lock_irq(&file->lock);
switch (file->type) {
- case HPRE_CURRENT_QM:
- val = hpre_current_qm_read(file);
- break;
case HPRE_CLEAR_ENABLE:
val = hpre_clear_enable_read(file);
break;
spin_lock_irq(&file->lock);
switch (file->type) {
- case HPRE_CURRENT_QM:
- ret = hpre_current_qm_write(file, val);
- if (ret)
- goto err_input;
- break;
case HPRE_CLEAR_ENABLE:
ret = hpre_clear_enable_write(file, val);
if (ret)
{
int ret;
- ret = hpre_create_debugfs_file(qm, NULL, HPRE_CURRENT_QM,
- HPRE_CURRENT_QM);
- if (ret)
- return ret;
-
ret = hpre_create_debugfs_file(qm, NULL, HPRE_CLEAR_ENABLE,
HPRE_CLEAR_ENABLE);
if (ret)
}
if (pdev->revision >= QM_HW_V3)
- qm->algs = "rsa\ndh\necdh\nx25519\nx448\necdsa\nsm2\n";
+ qm->algs = "rsa\ndh\necdh\nx25519\nx448\necdsa\nsm2";
else
- qm->algs = "rsa\ndh\n";
+ qm->algs = "rsa\ndh";
qm->mode = uacce_mode;
qm->pdev = pdev;
qm->ver = pdev->revision;
HPRE_ADDR(qm, HPRE_AM_OOO_SHUTDOWN_ENB));
}
+static void hpre_err_info_init(struct hisi_qm *qm)
+{
+ struct hisi_qm_err_info *err_info = &qm->err_info;
+
+ err_info->ce = QM_BASE_CE;
+ err_info->fe = 0;
+ err_info->ecc_2bits_mask = HPRE_CORE_ECC_2BIT_ERR |
+ HPRE_OOO_ECC_2BIT_ERR;
+ err_info->dev_ce_mask = HPRE_HAC_RAS_CE_ENABLE;
+ err_info->msi_wr_port = HPRE_WR_MSI_PORT;
+ err_info->acpi_rst = "HRST";
+ err_info->nfe = QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT;
+}
+
static const struct hisi_qm_err_ini hpre_err_ini = {
.hw_init = hpre_set_user_domain_and_cache,
.hw_err_enable = hpre_hw_error_enable,
.clear_dev_hw_err_status = hpre_clear_hw_err_status,
.log_dev_hw_err = hpre_log_hw_error,
.open_axi_master_ooo = hpre_open_axi_master_ooo,
- .err_info = {
- .ce = QM_BASE_CE,
- .nfe = QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT,
- .fe = 0,
- .ecc_2bits_mask = HPRE_CORE_ECC_2BIT_ERR |
- HPRE_OOO_ECC_2BIT_ERR,
- .dev_ce_mask = HPRE_HAC_RAS_CE_ENABLE,
- .msi_wr_port = HPRE_WR_MSI_PORT,
- .acpi_rst = "HRST",
- }
+ .err_info_init = hpre_err_info_init,
};
static int hpre_pf_probe_init(struct hpre *hpre)
struct hisi_qm *qm = &hpre->qm;
int ret;
- qm->ctrl_qp_num = HPRE_QUEUE_NUM_V2;
-
ret = hpre_set_user_domain_and_cache(qm);
if (ret)
return ret;
qm->err_ini = &hpre_err_ini;
+ qm->err_ini->err_info_init(qm);
hisi_qm_dev_err_init(qm);
return 0;
hisi_qm_stop(qm, QM_NORMAL);
if (qm->fun_type == QM_HW_PF) {
- if (qm->use_sva && qm->ver == QM_HW_V2)
- hpre_pasid_disable(qm);
hpre_cnt_regs_clear(qm);
qm->debug.curr_qm_qp_num = 0;
hisi_qm_dev_err_uninit(qm);
hisi_qm_uninit(qm);
}
-
static const struct pci_error_handlers hpre_err_handler = {
.error_detected = hisi_qm_dev_err_detected,
.slot_reset = hisi_qm_dev_slot_reset,
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Zaibo Xu <xuzaibo@huawei.com>");
+MODULE_AUTHOR("Meng Yu <yumeng18@huawei.com>");
MODULE_DESCRIPTION("Driver for HiSilicon HPRE accelerator");
#define QM_MB_CMD_SQC_BT 0x4
#define QM_MB_CMD_CQC_BT 0x5
#define QM_MB_CMD_SQC_VFT_V2 0x6
+#define QM_MB_CMD_STOP_QP 0x8
#define QM_MB_CMD_SEND_BASE 0x300
#define QM_MB_EVENT_SHIFT 8
#define QM_DB_PRIORITY_SHIFT_V1 48
#define QM_DOORBELL_SQ_CQ_BASE_V2 0x1000
#define QM_DOORBELL_EQ_AEQ_BASE_V2 0x2000
+#define QM_QUE_ISO_CFG_V 0x0030
+#define QM_QUE_ISO_EN 0x100154
+#define QM_CAPBILITY 0x100158
+#define QM_QP_NUN_MASK GENMASK(10, 0)
+#define QM_QP_DB_INTERVAL 0x10000
+#define QM_QP_MAX_NUM_SHIFT 11
#define QM_DB_CMD_SHIFT_V2 12
#define QM_DB_RAND_SHIFT_V2 16
#define QM_DB_INDEX_SHIFT_V2 32
#define QM_DFX_CNT_CLR_CE 0x100118
#define QM_ABNORMAL_INT_SOURCE 0x100000
-#define QM_ABNORMAL_INT_SOURCE_CLR GENMASK(12, 0)
+#define QM_ABNORMAL_INT_SOURCE_CLR GENMASK(14, 0)
#define QM_ABNORMAL_INT_MASK 0x100004
-#define QM_ABNORMAL_INT_MASK_VALUE 0x1fff
+#define QM_ABNORMAL_INT_MASK_VALUE 0x7fff
#define QM_ABNORMAL_INT_STATUS 0x100008
#define QM_ABNORMAL_INT_SET 0x10000c
#define QM_ABNORMAL_INF00 0x100010
#define ACC_AM_ROB_ECC_INT_STS 0x300104
#define ACC_ROB_ECC_ERR_MULTPL BIT(1)
+#define QM_DFX_MB_CNT_VF 0x104010
+#define QM_DFX_DB_CNT_VF 0x104020
+#define QM_DFX_SQE_CNT_VF_SQN 0x104030
+#define QM_DFX_CQE_CNT_VF_CQN 0x104040
+#define QM_DFX_QN_SHIFT 16
+#define CURRENT_FUN_MASK GENMASK(5, 0)
+#define CURRENT_Q_MASK GENMASK(31, 16)
+
#define POLL_PERIOD 10
#define POLL_TIMEOUT 1000
#define WAIT_PERIOD_US_MAX 200
#define QM_CACHE_WB_DONE 0x208
#define PCI_BAR_2 2
+#define PCI_BAR_4 4
#define QM_SQE_DATA_ALIGN_MASK GENMASK(6, 0)
#define QMC_ALIGN(sz) ALIGN(sz, 32)
void (*hw_error_init)(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe);
void (*hw_error_uninit)(struct hisi_qm *qm);
enum acc_err_result (*hw_error_handle)(struct hisi_qm *qm);
+ int (*stop_qp)(struct hisi_qp *qp);
};
struct qm_dfx_item {
};
static const char * const qm_debug_file_name[] = {
+ [CURRENT_QM] = "current_qm",
[CURRENT_Q] = "current_q",
[CLEAR_ENABLE] = "clear_enable",
};
{ .int_msk = BIT(10), .msg = "qm_db_timeout" },
{ .int_msk = BIT(11), .msg = "qm_of_fifo_of" },
{ .int_msk = BIT(12), .msg = "qm_db_random_invalid" },
+ { .int_msk = BIT(13), .msg = "qm_mailbox_timeout" },
+ { .int_msk = BIT(14), .msg = "qm_flr_timeout" },
{ /* sentinel */ }
};
static void qm_db_v2(struct hisi_qm *qm, u16 qn, u8 cmd, u16 index, u8 priority)
{
- u64 doorbell;
- u64 dbase;
+ void __iomem *io_base = qm->io_base;
u16 randata = 0;
+ u64 doorbell;
if (cmd == QM_DOORBELL_CMD_SQ || cmd == QM_DOORBELL_CMD_CQ)
- dbase = QM_DOORBELL_SQ_CQ_BASE_V2;
+ io_base = qm->db_io_base + (u64)qn * qm->db_interval +
+ QM_DOORBELL_SQ_CQ_BASE_V2;
else
- dbase = QM_DOORBELL_EQ_AEQ_BASE_V2;
+ io_base += QM_DOORBELL_EQ_AEQ_BASE_V2;
doorbell = qn | ((u64)cmd << QM_DB_CMD_SHIFT_V2) |
((u64)randata << QM_DB_RAND_SHIFT_V2) |
((u64)index << QM_DB_INDEX_SHIFT_V2) |
((u64)priority << QM_DB_PRIORITY_SHIFT_V2);
- writeq(doorbell, qm->io_base + dbase);
+ writeq(doorbell, io_base);
}
static void qm_db(struct hisi_qm *qm, u16 qn, u8 cmd, u16 index, u8 priority)
return 0;
}
+static int qm_get_vf_qp_num(struct hisi_qm *qm, u32 fun_num)
+{
+ u32 remain_q_num, vfq_num;
+ u32 num_vfs = qm->vfs_num;
+
+ vfq_num = (qm->ctrl_qp_num - qm->qp_num) / num_vfs;
+ if (vfq_num >= qm->max_qp_num)
+ return qm->max_qp_num;
+
+ remain_q_num = (qm->ctrl_qp_num - qm->qp_num) % num_vfs;
+ if (vfq_num + remain_q_num <= qm->max_qp_num)
+ return fun_num == num_vfs ? vfq_num + remain_q_num : vfq_num;
+
+ /*
+ * if vfq_num + remain_q_num > max_qp_num, the last VFs,
+ * each with one more queue.
+ */
+ return fun_num + remain_q_num > num_vfs ? vfq_num + 1 : vfq_num;
+}
+
static struct hisi_qm *file_to_qm(struct debugfs_file *file)
{
struct qm_debug *debug = file->debug;
return 0;
}
+static u32 current_qm_read(struct debugfs_file *file)
+{
+ struct hisi_qm *qm = file_to_qm(file);
+
+ return readl(qm->io_base + QM_DFX_MB_CNT_VF);
+}
+
+static int current_qm_write(struct debugfs_file *file, u32 val)
+{
+ struct hisi_qm *qm = file_to_qm(file);
+ u32 tmp;
+
+ if (val > qm->vfs_num)
+ return -EINVAL;
+
+ /* According PF or VF Dev ID to calculation curr_qm_qp_num and store */
+ if (!val)
+ qm->debug.curr_qm_qp_num = qm->qp_num;
+ else
+ qm->debug.curr_qm_qp_num = qm_get_vf_qp_num(qm, val);
+
+ writel(val, qm->io_base + QM_DFX_MB_CNT_VF);
+ writel(val, qm->io_base + QM_DFX_DB_CNT_VF);
+
+ tmp = val |
+ (readl(qm->io_base + QM_DFX_SQE_CNT_VF_SQN) & CURRENT_Q_MASK);
+ writel(tmp, qm->io_base + QM_DFX_SQE_CNT_VF_SQN);
+
+ tmp = val |
+ (readl(qm->io_base + QM_DFX_CQE_CNT_VF_CQN) & CURRENT_Q_MASK);
+ writel(tmp, qm->io_base + QM_DFX_CQE_CNT_VF_CQN);
+
+ return 0;
+}
+
static ssize_t qm_debug_read(struct file *filp, char __user *buf,
size_t count, loff_t *pos)
{
mutex_lock(&file->lock);
switch (index) {
+ case CURRENT_QM:
+ val = current_qm_read(file);
+ break;
case CURRENT_Q:
val = current_q_read(file);
break;
mutex_lock(&file->lock);
switch (index) {
+ case CURRENT_QM:
+ ret = current_qm_write(file, val);
+ break;
case CURRENT_Q:
ret = current_q_write(file, val);
- if (ret)
- goto err_input;
break;
case CLEAR_ENABLE:
ret = clear_enable_write(file, val);
- if (ret)
- goto err_input;
break;
default:
ret = -EINVAL;
- goto err_input;
}
mutex_unlock(&file->lock);
- return count;
+ if (ret)
+ return ret;
-err_input:
- mutex_unlock(&file->lock);
- return ret;
+ return count;
}
static const struct file_operations qm_debug_fops = {
.write = qm_cmd_write,
};
-static void qm_create_debugfs_file(struct hisi_qm *qm, enum qm_debug_file index)
+static void qm_create_debugfs_file(struct hisi_qm *qm, struct dentry *dir,
+ enum qm_debug_file index)
{
- struct dentry *qm_d = qm->debug.qm_d;
struct debugfs_file *file = qm->debug.files + index;
- debugfs_create_file(qm_debug_file_name[index], 0600, qm_d, file,
+ debugfs_create_file(qm_debug_file_name[index], 0600, dir, file,
&qm_debug_fops);
file->index = index;
if (val == (QM_DB_RANDOM_INVALID | QM_BASE_CE)) {
writel(error_status, qm->io_base +
QM_ABNORMAL_INT_SOURCE);
- writel(qm->err_ini->err_info.nfe,
+ writel(qm->err_info.nfe,
qm->io_base + QM_RAS_NFE_ENABLE);
return ACC_ERR_RECOVERED;
}
return ACC_ERR_RECOVERED;
}
+static int qm_stop_qp(struct hisi_qp *qp)
+{
+ return qm_mb(qp->qm, QM_MB_CMD_STOP_QP, 0, qp->qp_id, 0);
+}
+
static const struct hisi_qm_hw_ops qm_hw_ops_v1 = {
.qm_db = qm_db_v1,
.get_irq_num = qm_get_irq_num_v1,
.hw_error_handle = qm_hw_error_handle_v2,
};
+static const struct hisi_qm_hw_ops qm_hw_ops_v3 = {
+ .get_vft = qm_get_vft_v2,
+ .qm_db = qm_db_v2,
+ .get_irq_num = qm_get_irq_num_v2,
+ .hw_error_init = qm_hw_error_init_v2,
+ .hw_error_uninit = qm_hw_error_uninit_v2,
+ .hw_error_handle = qm_hw_error_handle_v2,
+ .stop_qp = qm_stop_qp,
+};
+
static void *qm_get_avail_sqe(struct hisi_qp *qp)
{
struct hisi_qp_status *qp_status = &qp->qp_status;
if (qm->err_status.is_qm_ecc_mbit || qm->err_status.is_dev_ecc_mbit)
return 0;
+ /* Kunpeng930 supports drain qp by device */
+ if (qm->ops->stop_qp) {
+ ret = qm->ops->stop_qp(qp);
+ if (ret)
+ dev_err(dev, "Failed to stop qp(%u)!\n", qp->qp_id);
+ return ret;
+ }
+
addr = qm_ctx_alloc(qm, size, &dma_addr);
if (IS_ERR(addr)) {
dev_err(dev, "Failed to alloc ctx for sqc and cqc!\n");
{
struct hisi_qp *qp = q->priv;
struct hisi_qm *qm = qp->qm;
+ resource_size_t phys_base = qm->db_phys_base +
+ qp->qp_id * qm->db_interval;
size_t sz = vma->vm_end - vma->vm_start;
struct pci_dev *pdev = qm->pdev;
struct device *dev = &pdev->dev;
if (qm->ver == QM_HW_V1) {
if (sz > PAGE_SIZE * QM_DOORBELL_PAGE_NR)
return -EINVAL;
- } else {
+ } else if (qm->ver == QM_HW_V2 || !qm->use_db_isolation) {
if (sz > PAGE_SIZE * (QM_DOORBELL_PAGE_NR +
QM_DOORBELL_SQ_CQ_BASE_V2 / PAGE_SIZE))
return -EINVAL;
+ } else {
+ if (sz > qm->db_interval)
+ return -EINVAL;
}
vma->vm_flags |= VM_IO;
return remap_pfn_range(vma, vma->vm_start,
- qm->phys_base >> PAGE_SHIFT,
+ phys_base >> PAGE_SHIFT,
sz, pgprot_noncached(vma->vm_page_prot));
case UACCE_QFRT_DUS:
if (sz != qp->qdma.size)
uacce->priv = qm;
uacce->algs = qm->algs;
- if (qm->ver == QM_HW_V1) {
- mmio_page_nr = QM_DOORBELL_PAGE_NR;
+ if (qm->ver == QM_HW_V1)
uacce->api_ver = HISI_QM_API_VER_BASE;
- } else {
+ else if (qm->ver == QM_HW_V2)
+ uacce->api_ver = HISI_QM_API_VER2_BASE;
+ else
+ uacce->api_ver = HISI_QM_API_VER3_BASE;
+
+ if (qm->ver == QM_HW_V1)
+ mmio_page_nr = QM_DOORBELL_PAGE_NR;
+ else if (qm->ver == QM_HW_V2 || !qm->use_db_isolation)
mmio_page_nr = QM_DOORBELL_PAGE_NR +
QM_DOORBELL_SQ_CQ_BASE_V2 / PAGE_SIZE;
- uacce->api_ver = HISI_QM_API_VER2_BASE;
- }
+ else
+ mmio_page_nr = qm->db_interval / PAGE_SIZE;
dus_page_nr = (PAGE_SIZE - 1 + qm->sqe_size * QM_Q_DEPTH +
sizeof(struct qm_cqe) * QM_Q_DEPTH) >> PAGE_SHIFT;
if (qm->ver == QM_HW_V1)
qm->ops = &qm_hw_ops_v1;
- else
+ else if (qm->ver == QM_HW_V2)
qm->ops = &qm_hw_ops_v2;
+ else
+ qm->ops = &qm_hw_ops_v3;
pci_set_drvdata(pdev, qm);
mutex_init(&qm->mailbox_lock);
qm->misc_ctl = false;
}
-static void hisi_qm_pci_uninit(struct hisi_qm *qm)
+static void qm_put_pci_res(struct hisi_qm *qm)
{
struct pci_dev *pdev = qm->pdev;
- pci_free_irq_vectors(pdev);
+ if (qm->use_db_isolation)
+ iounmap(qm->db_io_base);
+
iounmap(qm->io_base);
pci_release_mem_regions(pdev);
+}
+
+static void hisi_qm_pci_uninit(struct hisi_qm *qm)
+{
+ struct pci_dev *pdev = qm->pdev;
+
+ pci_free_irq_vectors(pdev);
+ qm_put_pci_res(qm);
pci_disable_device(pdev);
}
hisi_qm_cache_wb(qm);
dma_free_coherent(dev, qm->qdma.size,
qm->qdma.va, qm->qdma.dma);
- memset(&qm->qdma, 0, sizeof(qm->qdma));
}
qm_irq_unregister(qm);
{
int ret;
- WARN_ON(!qm->qdma.dma);
+ WARN_ON(!qm->qdma.va);
if (qm->fun_type == QM_HW_PF) {
ret = qm_dev_mem_reset(qm);
qm->debug.qm_d = qm_d;
/* only show this in PF */
- if (qm->fun_type == QM_HW_PF)
+ if (qm->fun_type == QM_HW_PF) {
+ qm_create_debugfs_file(qm, qm->debug.debug_root, CURRENT_QM);
for (i = CURRENT_Q; i < DEBUG_FILE_NUM; i++)
- qm_create_debugfs_file(qm, i);
+ qm_create_debugfs_file(qm, qm_d, i);
+ }
debugfs_create_file("regs", 0444, qm->debug.qm_d, qm, &qm_regs_fops);
struct qm_dfx_registers *regs;
int i;
+ /* clear current_qm */
+ writel(0x0, qm->io_base + QM_DFX_MB_CNT_VF);
+ writel(0x0, qm->io_base + QM_DFX_DB_CNT_VF);
+
/* clear current_q */
writel(0x0, qm->io_base + QM_DFX_SQE_CNT_VF_SQN);
writel(0x0, qm->io_base + QM_DFX_CQE_CNT_VF_CQN);
static void qm_hw_error_init(struct hisi_qm *qm)
{
- const struct hisi_qm_err_info *err_info = &qm->err_ini->err_info;
+ struct hisi_qm_err_info *err_info = &qm->err_info;
if (!qm->ops->hw_error_init) {
dev_err(&qm->pdev->dev, "QM doesn't support hw error handling!\n");
static int qm_vf_q_assign(struct hisi_qm *qm, u32 num_vfs)
{
- u32 remain_q_num, q_num, i, j;
+ u32 remain_q_num, vfs_q_num, act_q_num, q_num, i, j;
+ u32 max_qp_num = qm->max_qp_num;
u32 q_base = qm->qp_num;
int ret;
if (!num_vfs)
return -EINVAL;
- remain_q_num = qm->ctrl_qp_num - qm->qp_num;
+ vfs_q_num = qm->ctrl_qp_num - qm->qp_num;
- /* If remain queues not enough, return error. */
- if (qm->ctrl_qp_num < qm->qp_num || remain_q_num < num_vfs)
+ /* If vfs_q_num is less than num_vfs, return error. */
+ if (vfs_q_num < num_vfs)
return -EINVAL;
- q_num = remain_q_num / num_vfs;
- for (i = 1; i <= num_vfs; i++) {
- if (i == num_vfs)
- q_num += remain_q_num % num_vfs;
- ret = hisi_qm_set_vft(qm, i, q_base, q_num);
+ q_num = vfs_q_num / num_vfs;
+ remain_q_num = vfs_q_num % num_vfs;
+
+ for (i = num_vfs; i > 0; i--) {
+ /*
+ * if q_num + remain_q_num > max_qp_num in last vf, divide the
+ * remaining queues equally.
+ */
+ if (i == num_vfs && q_num + remain_q_num <= max_qp_num) {
+ act_q_num = q_num + remain_q_num;
+ remain_q_num = 0;
+ } else if (remain_q_num > 0) {
+ act_q_num = q_num + 1;
+ remain_q_num--;
+ } else {
+ act_q_num = q_num;
+ }
+
+ act_q_num = min_t(int, act_q_num, max_qp_num);
+ ret = hisi_qm_set_vft(qm, i, q_base, act_q_num);
if (ret) {
- for (j = i; j > 0; j--)
+ for (j = num_vfs; j > i; j--)
hisi_qm_set_vft(qm, j, 0, 0);
return ret;
}
- q_base += q_num;
+ q_base += act_q_num;
}
return 0;
/* get device hardware error status */
err_sts = qm->err_ini->get_dev_hw_err_status(qm);
if (err_sts) {
- if (err_sts & qm->err_ini->err_info.ecc_2bits_mask)
+ if (err_sts & qm->err_info.ecc_2bits_mask)
qm->err_status.is_dev_ecc_mbit = true;
if (qm->err_ini->log_dev_hw_err)
qm->err_ini->log_dev_hw_err(qm, err_sts);
/* ce error does not need to be reset */
- if ((err_sts | qm->err_ini->err_info.dev_ce_mask) ==
- qm->err_ini->err_info.dev_ce_mask) {
+ if ((err_sts | qm->err_info.dev_ce_mask) ==
+ qm->err_info.dev_ce_mask) {
if (qm->err_ini->clear_dev_hw_err_status)
qm->err_ini->clear_dev_hw_err_status(qm,
err_sts);
acpi_status s;
s = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev),
- qm->err_ini->err_info.acpi_rst,
+ qm->err_info.acpi_rst,
NULL, &value);
if (ACPI_FAILURE(s)) {
pci_err(pdev, "NO controller reset method!\n");
/* temporarily close the OOO port used for PEH to write out MSI */
value = readl(qm->io_base + ACC_AM_CFG_PORT_WR_EN);
- writel(value & ~qm->err_ini->err_info.msi_wr_port,
+ writel(value & ~qm->err_info.msi_wr_port,
qm->io_base + ACC_AM_CFG_PORT_WR_EN);
/* clear dev ecc 2bit error source if having */
- value = qm_get_dev_err_status(qm) &
- qm->err_ini->err_info.ecc_2bits_mask;
+ value = qm_get_dev_err_status(qm) & qm->err_info.ecc_2bits_mask;
if (value && qm->err_ini->clear_dev_hw_err_status)
qm->err_ini->clear_dev_hw_err_status(qm, value);
/* open the OOO port for PEH to write out MSI */
value = readl(qm->io_base + ACC_AM_CFG_PORT_WR_EN);
- value |= qm->err_ini->err_info.msi_wr_port;
+ value |= qm->err_info.msi_wr_port;
writel(value, qm->io_base + ACC_AM_CFG_PORT_WR_EN);
qm->err_status.is_qm_ecc_mbit = false;
if (ret)
return ret;
- return (qm_get_dev_err_status(qm) &
- qm->err_ini->err_info.ecc_2bits_mask);
+ return (qm_get_dev_err_status(qm) & qm->err_info.ecc_2bits_mask);
}
void hisi_qm_reset_prepare(struct pci_dev *pdev)
mutex_unlock(&qm_list->lock);
if (flag) {
- ret = qm_list->register_to_crypto();
+ ret = qm_list->register_to_crypto(qm);
if (ret) {
mutex_lock(&qm_list->lock);
list_del(&qm->list);
mutex_unlock(&qm_list->lock);
if (list_empty(&qm_list->list))
- qm_list->unregister_from_crypto();
+ qm_list->unregister_from_crypto(qm);
}
EXPORT_SYMBOL_GPL(hisi_qm_alg_unregister);
-static int hisi_qm_pci_init(struct hisi_qm *qm)
+static int qm_get_qp_num(struct hisi_qm *qm)
+{
+ if (qm->ver == QM_HW_V1)
+ qm->ctrl_qp_num = QM_QNUM_V1;
+ else if (qm->ver == QM_HW_V2)
+ qm->ctrl_qp_num = QM_QNUM_V2;
+ else
+ qm->ctrl_qp_num = readl(qm->io_base + QM_CAPBILITY) &
+ QM_QP_NUN_MASK;
+
+ if (qm->use_db_isolation)
+ qm->max_qp_num = (readl(qm->io_base + QM_CAPBILITY) >>
+ QM_QP_MAX_NUM_SHIFT) & QM_QP_NUN_MASK;
+ else
+ qm->max_qp_num = qm->ctrl_qp_num;
+
+ /* check if qp number is valid */
+ if (qm->qp_num > qm->max_qp_num) {
+ dev_err(&qm->pdev->dev, "qp num(%u) is more than max qp num(%u)!\n",
+ qm->qp_num, qm->max_qp_num);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int qm_get_pci_res(struct hisi_qm *qm)
{
struct pci_dev *pdev = qm->pdev;
struct device *dev = &pdev->dev;
- unsigned int num_vec;
int ret;
- ret = pci_enable_device_mem(pdev);
- if (ret < 0) {
- dev_err(dev, "Failed to enable device mem!\n");
- return ret;
- }
-
ret = pci_request_mem_regions(pdev, qm->dev_name);
if (ret < 0) {
dev_err(dev, "Failed to request mem regions!\n");
- goto err_disable_pcidev;
+ return ret;
}
qm->phys_base = pci_resource_start(pdev, PCI_BAR_2);
- qm->phys_size = pci_resource_len(qm->pdev, PCI_BAR_2);
- qm->io_base = ioremap(qm->phys_base, qm->phys_size);
+ qm->io_base = ioremap(qm->phys_base, pci_resource_len(pdev, PCI_BAR_2));
if (!qm->io_base) {
ret = -EIO;
- goto err_release_mem_regions;
+ goto err_request_mem_regions;
+ }
+
+ if (qm->ver > QM_HW_V2) {
+ if (qm->fun_type == QM_HW_PF)
+ qm->use_db_isolation = readl(qm->io_base +
+ QM_QUE_ISO_EN) & BIT(0);
+ else
+ qm->use_db_isolation = readl(qm->io_base +
+ QM_QUE_ISO_CFG_V) & BIT(0);
+ }
+
+ if (qm->use_db_isolation) {
+ qm->db_interval = QM_QP_DB_INTERVAL;
+ qm->db_phys_base = pci_resource_start(pdev, PCI_BAR_4);
+ qm->db_io_base = ioremap(qm->db_phys_base,
+ pci_resource_len(pdev, PCI_BAR_4));
+ if (!qm->db_io_base) {
+ ret = -EIO;
+ goto err_ioremap;
+ }
+ } else {
+ qm->db_phys_base = qm->phys_base;
+ qm->db_io_base = qm->io_base;
+ qm->db_interval = 0;
}
+ if (qm->fun_type == QM_HW_PF) {
+ ret = qm_get_qp_num(qm);
+ if (ret)
+ goto err_db_ioremap;
+ }
+
+ return 0;
+
+err_db_ioremap:
+ if (qm->use_db_isolation)
+ iounmap(qm->db_io_base);
+err_ioremap:
+ iounmap(qm->io_base);
+err_request_mem_regions:
+ pci_release_mem_regions(pdev);
+ return ret;
+}
+
+static int hisi_qm_pci_init(struct hisi_qm *qm)
+{
+ struct pci_dev *pdev = qm->pdev;
+ struct device *dev = &pdev->dev;
+ unsigned int num_vec;
+ int ret;
+
+ ret = pci_enable_device_mem(pdev);
+ if (ret < 0) {
+ dev_err(dev, "Failed to enable device mem!\n");
+ return ret;
+ }
+
+ ret = qm_get_pci_res(qm);
+ if (ret)
+ goto err_disable_pcidev;
+
ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
if (ret < 0)
- goto err_iounmap;
+ goto err_get_pci_res;
pci_set_master(pdev);
if (!qm->ops->get_irq_num) {
ret = -EOPNOTSUPP;
- goto err_iounmap;
+ goto err_get_pci_res;
}
num_vec = qm->ops->get_irq_num(qm);
ret = pci_alloc_irq_vectors(pdev, num_vec, num_vec, PCI_IRQ_MSI);
if (ret < 0) {
dev_err(dev, "Failed to enable MSI vectors!\n");
- goto err_iounmap;
+ goto err_get_pci_res;
}
return 0;
-err_iounmap:
- iounmap(qm->io_base);
-err_release_mem_regions:
- pci_release_mem_regions(pdev);
+err_get_pci_res:
+ qm_put_pci_res(qm);
err_disable_pcidev:
pci_disable_device(pdev);
return ret;
hisi_qm_pre_init(qm);
- ret = qm_alloc_uacce(qm);
- if (ret < 0)
- dev_warn(dev, "fail to alloc uacce (%d)\n", ret);
-
ret = hisi_qm_pci_init(qm);
if (ret)
- goto err_remove_uacce;
+ return ret;
ret = qm_irq_register(qm);
if (ret)
- goto err_pci_uninit;
+ goto err_pci_init;
if (qm->fun_type == QM_HW_VF && qm->ver != QM_HW_V1) {
/* v2 starts to support get vft by mailbox */
ret = hisi_qm_get_vft(qm, &qm->qp_base, &qm->qp_num);
if (ret)
- goto err_irq_unregister;
+ goto err_irq_register;
}
+ ret = qm_alloc_uacce(qm);
+ if (ret < 0)
+ dev_warn(dev, "fail to alloc uacce (%d)\n", ret);
+
ret = hisi_qm_memory_init(qm);
if (ret)
- goto err_irq_unregister;
+ goto err_alloc_uacce;
INIT_WORK(&qm->work, qm_work_process);
if (qm->fun_type == QM_HW_PF)
return 0;
-err_irq_unregister:
- qm_irq_unregister(qm);
-err_pci_uninit:
- hisi_qm_pci_uninit(qm);
-err_remove_uacce:
+err_alloc_uacce:
uacce_remove(qm->uacce);
qm->uacce = NULL;
+err_irq_register:
+ qm_irq_unregister(qm);
+err_pci_init:
+ hisi_qm_pci_uninit(qm);
return ret;
}
EXPORT_SYMBOL_GPL(hisi_qm_init);
#define PEH_AXUSER_CFG 0x401001
#define PEH_AXUSER_CFG_ENABLE 0xffffffff
-#define QM_DFX_MB_CNT_VF 0x104010
-#define QM_DFX_DB_CNT_VF 0x104020
-#define QM_DFX_SQE_CNT_VF_SQN 0x104030
-#define QM_DFX_CQE_CNT_VF_CQN 0x104040
-#define QM_DFX_QN_SHIFT 16
-#define CURRENT_FUN_MASK GENMASK(5, 0)
-#define CURRENT_Q_MASK GENMASK(31, 16)
-
#define QM_AXI_RRESP BIT(0)
#define QM_AXI_BRESP BIT(1)
#define QM_ECC_MBIT BIT(2)
#define QM_DB_TIMEOUT BIT(10)
#define QM_OF_FIFO_OF BIT(11)
#define QM_DB_RANDOM_INVALID BIT(12)
+#define QM_MAILBOX_TIMEOUT BIT(13)
+#define QM_FLR_TIMEOUT BIT(14)
#define QM_BASE_NFE (QM_AXI_RRESP | QM_AXI_BRESP | QM_ECC_MBIT | \
QM_ACC_GET_TASK_TIMEOUT | QM_DB_TIMEOUT | \
- QM_OF_FIFO_OF | QM_DB_RANDOM_INVALID)
+ QM_OF_FIFO_OF | QM_DB_RANDOM_INVALID | \
+ QM_MAILBOX_TIMEOUT | QM_FLR_TIMEOUT)
#define QM_BASE_CE QM_ECC_1BIT
#define QM_Q_DEPTH 1024
};
enum qm_debug_file {
+ CURRENT_QM,
CURRENT_Q,
CLEAR_ENABLE,
DEBUG_FILE_NUM,
void (*open_axi_master_ooo)(struct hisi_qm *qm);
void (*close_axi_master_ooo)(struct hisi_qm *qm);
void (*log_dev_hw_err)(struct hisi_qm *qm, u32 err_sts);
- struct hisi_qm_err_info err_info;
+ void (*err_info_init)(struct hisi_qm *qm);
};
struct hisi_qm_list {
struct mutex lock;
struct list_head list;
- int (*register_to_crypto)(void);
- void (*unregister_from_crypto)(void);
+ int (*register_to_crypto)(struct hisi_qm *qm);
+ void (*unregister_from_crypto)(struct hisi_qm *qm);
};
struct hisi_qm {
const char *dev_name;
struct pci_dev *pdev;
void __iomem *io_base;
+ void __iomem *db_io_base;
u32 sqe_size;
u32 qp_base;
u32 qp_num;
u32 qp_in_used;
u32 ctrl_qp_num;
+ u32 max_qp_num;
u32 vfs_num;
+ u32 db_interval;
struct list_head list;
struct hisi_qm_list *qm_list;
struct hisi_qm_status status;
const struct hisi_qm_err_ini *err_ini;
+ struct hisi_qm_err_info err_info;
struct hisi_qm_err_status err_status;
unsigned long misc_ctl; /* driver removing and reset sched */
const char *algs;
bool use_sva;
bool is_frozen;
+
+ /* doorbell isolation enable */
+ bool use_db_isolation;
resource_size_t phys_base;
- resource_size_t phys_size;
+ resource_size_t db_phys_base;
struct uacce_device *uacce;
int mode;
};
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2016-2017 Hisilicon Limited. */
+/* Copyright (c) 2016-2017 HiSilicon Limited. */
#include <linux/crypto.h>
#include <linux/dma-mapping.h>
#include <linux/dmapool.h>
// SPDX-License-Identifier: GPL-2.0
/*
- * Driver for the Hisilicon SEC units found on Hip06 Hip07
+ * Driver for the HiSilicon SEC units found on Hip06 Hip07
*
- * Copyright (c) 2016-2017 Hisilicon Limited.
+ * Copyright (c) 2016-2017 HiSilicon Limited.
*/
#include <linux/acpi.h>
#include <linux/atomic.h>
IORESOURCE_MEM,
2 + queue->queue_id);
if (!res) {
- dev_err(dev, "Failed to get queue %d memory resource\n",
+ dev_err(dev, "Failed to get queue %u memory resource\n",
queue->queue_id);
return -ENOMEM;
}
struct sec_dev_info *info = queue->dev_info;
if (queue->queue_id >= SEC_Q_NUM) {
- dev_err(info->dev, "No queue %d\n", queue->queue_id);
+ dev_err(info->dev, "No queue %u\n", queue->queue_id);
return -ENODEV;
}
if (!queue->in_use) {
- dev_err(info->dev, "Queue %d is idle\n", queue->queue_id);
+ dev_err(info->dev, "Queue %u is idle\n", queue->queue_id);
return -ENODEV;
}
/**
* sec_queue_empty() - Is this hardware queue currently empty.
+ * @queue: The queue to test
*
* We need to know if we have an empty queue for some of the chaining modes
* as if it is not empty we may need to hold the message in a software queue
module_platform_driver(sec_driver);
MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Hisilicon Security Accelerators");
+MODULE_DESCRIPTION("HiSilicon Security Accelerators");
MODULE_AUTHOR("Zaibo Xu <xuzaibo@huawei.com");
MODULE_AUTHOR("Jonathan Cameron <jonathan.cameron@huawei.com>");
/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (c) 2016-2017 Hisilicon Limited. */
+/* Copyright (c) 2016-2017 HiSilicon Limited. */
#ifndef _SEC_DRV_H_
#define _SEC_DRV_H_
#ifndef __HISI_SEC_V2_H
#define __HISI_SEC_V2_H
-#include <linux/list.h>
-
#include "../qm.h"
#include "sec_crypto.h"
int err_type;
int req_id;
- int flag;
+ u32 flag;
/* Status of the SEC request */
bool fake_busy;
bool pbuf_supported;
struct sec_cipher_ctx c_ctx;
struct sec_auth_ctx a_ctx;
+ struct device *dev;
};
enum sec_endian {
};
enum sec_debug_file_index {
- SEC_CURRENT_QM,
SEC_CLEAR_ENABLE,
SEC_DEBUG_FILE_NUM,
};
void sec_destroy_qps(struct hisi_qp **qps, int qp_num);
struct hisi_qp **sec_create_qps(void);
-int sec_register_to_crypto(void);
-void sec_unregister_from_crypto(void);
+int sec_register_to_crypto(struct hisi_qm *qm);
+void sec_unregister_from_crypto(struct hisi_qm *qm);
#endif
#include <crypto/des.h>
#include <crypto/hash.h>
#include <crypto/internal/aead.h>
+#include <crypto/internal/des.h>
#include <crypto/sha1.h>
#include <crypto/sha2.h>
#include <crypto/skcipher.h>
#define SEC_TOTAL_IV_SZ (SEC_IV_SIZE * QM_Q_DEPTH)
#define SEC_SGL_SGE_NR 128
-#define SEC_CTX_DEV(ctx) (&(ctx)->sec->qm.pdev->dev)
#define SEC_CIPHER_AUTH 0xfe
#define SEC_AUTH_CIPHER 0x1
#define SEC_MAX_MAC_LEN 64
0, QM_Q_DEPTH, GFP_ATOMIC);
mutex_unlock(&qp_ctx->req_lock);
if (unlikely(req_id < 0)) {
- dev_err(SEC_CTX_DEV(req->ctx), "alloc req id fail!\n");
+ dev_err(req->ctx->dev, "alloc req id fail!\n");
return req_id;
}
int req_id = req->req_id;
if (unlikely(req_id < 0 || req_id >= QM_Q_DEPTH)) {
- dev_err(SEC_CTX_DEV(req->ctx), "free request id invalid!\n");
+ dev_err(req->ctx->dev, "free request id invalid!\n");
return;
}
aead_req->cryptlen + aead_req->assoclen -
authsize);
if (unlikely(sz != authsize || memcmp(mac_out, mac, sz))) {
- dev_err(SEC_CTX_DEV(req->ctx), "aead verify failure!\n");
+ dev_err(req->ctx->dev, "aead verify failure!\n");
return -EBADMSG;
}
if (unlikely(req->err_type || done != SEC_SQE_DONE ||
(ctx->alg_type == SEC_SKCIPHER && flag != SEC_SQE_CFLAG) ||
(ctx->alg_type == SEC_AEAD && flag != SEC_SQE_AEAD_FLAG))) {
- dev_err(SEC_CTX_DEV(ctx),
+ dev_err_ratelimited(ctx->dev,
"err_type[%d],done[%d],flag[%d]\n",
req->err_type, done, flag);
err = -EIO;
static int sec_alg_resource_alloc(struct sec_ctx *ctx,
struct sec_qp_ctx *qp_ctx)
{
- struct device *dev = SEC_CTX_DEV(ctx);
struct sec_alg_res *res = qp_ctx->res;
+ struct device *dev = ctx->dev;
int ret;
ret = sec_alloc_civ_resource(dev, res);
static void sec_alg_resource_free(struct sec_ctx *ctx,
struct sec_qp_ctx *qp_ctx)
{
- struct device *dev = SEC_CTX_DEV(ctx);
+ struct device *dev = ctx->dev;
sec_free_civ_resource(dev, qp_ctx->res);
static int sec_create_qp_ctx(struct hisi_qm *qm, struct sec_ctx *ctx,
int qp_ctx_id, int alg_type)
{
- struct device *dev = SEC_CTX_DEV(ctx);
+ struct device *dev = ctx->dev;
struct sec_qp_ctx *qp_ctx;
struct hisi_qp *qp;
int ret = -ENOMEM;
static void sec_release_qp_ctx(struct sec_ctx *ctx,
struct sec_qp_ctx *qp_ctx)
{
- struct device *dev = SEC_CTX_DEV(ctx);
+ struct device *dev = ctx->dev;
hisi_qm_stop_qp(qp_ctx->qp);
sec_alg_resource_free(ctx, qp_ctx);
sec = container_of(ctx->qps[0]->qm, struct sec_dev, qm);
ctx->sec = sec;
+ ctx->dev = &sec->qm.pdev->dev;
ctx->hlf_q_num = sec->ctx_q_num >> 1;
ctx->pbuf_supported = ctx->sec->iommu_used;
err_sec_release_qp_ctx:
for (i = i - 1; i >= 0; i--)
sec_release_qp_ctx(ctx, &ctx->qp_ctx[i]);
-
kfree(ctx->qp_ctx);
err_destroy_qps:
sec_destroy_qps(ctx->qps, sec->ctx_q_num);
-
return ret;
}
{
struct sec_cipher_ctx *c_ctx = &ctx->c_ctx;
- c_ctx->c_key = dma_alloc_coherent(SEC_CTX_DEV(ctx), SEC_MAX_KEY_SIZE,
+ c_ctx->c_key = dma_alloc_coherent(ctx->dev, SEC_MAX_KEY_SIZE,
&c_ctx->c_key_dma, GFP_KERNEL);
if (!c_ctx->c_key)
return -ENOMEM;
struct sec_cipher_ctx *c_ctx = &ctx->c_ctx;
memzero_explicit(c_ctx->c_key, SEC_MAX_KEY_SIZE);
- dma_free_coherent(SEC_CTX_DEV(ctx), SEC_MAX_KEY_SIZE,
+ dma_free_coherent(ctx->dev, SEC_MAX_KEY_SIZE,
c_ctx->c_key, c_ctx->c_key_dma);
}
{
struct sec_auth_ctx *a_ctx = &ctx->a_ctx;
- a_ctx->a_key = dma_alloc_coherent(SEC_CTX_DEV(ctx), SEC_MAX_KEY_SIZE,
+ a_ctx->a_key = dma_alloc_coherent(ctx->dev, SEC_MAX_KEY_SIZE,
&a_ctx->a_key_dma, GFP_KERNEL);
if (!a_ctx->a_key)
return -ENOMEM;
struct sec_auth_ctx *a_ctx = &ctx->a_ctx;
memzero_explicit(a_ctx->a_key, SEC_MAX_KEY_SIZE);
- dma_free_coherent(SEC_CTX_DEV(ctx), SEC_MAX_KEY_SIZE,
+ dma_free_coherent(ctx->dev, SEC_MAX_KEY_SIZE,
a_ctx->a_key, a_ctx->a_key_dma);
}
crypto_skcipher_set_reqsize(tfm, sizeof(struct sec_req));
ctx->c_ctx.ivsize = crypto_skcipher_ivsize(tfm);
if (ctx->c_ctx.ivsize > SEC_IV_SIZE) {
- dev_err(SEC_CTX_DEV(ctx), "get error skcipher iv size!\n");
+ pr_err("get error skcipher iv size!\n");
return -EINVAL;
}
sec_ctx_base_uninit(ctx);
}
-static int sec_skcipher_3des_setkey(struct sec_cipher_ctx *c_ctx,
+static int sec_skcipher_3des_setkey(struct crypto_skcipher *tfm, const u8 *key,
const u32 keylen,
const enum sec_cmode c_mode)
{
+ struct sec_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct sec_cipher_ctx *c_ctx = &ctx->c_ctx;
+ int ret;
+
+ ret = verify_skcipher_des3_key(tfm, key);
+ if (ret)
+ return ret;
+
switch (keylen) {
case SEC_DES3_2KEY_SIZE:
c_ctx->c_key_len = SEC_CKEY_3DES_2KEY;
{
struct sec_ctx *ctx = crypto_skcipher_ctx(tfm);
struct sec_cipher_ctx *c_ctx = &ctx->c_ctx;
+ struct device *dev = ctx->dev;
int ret;
if (c_mode == SEC_CMODE_XTS) {
ret = xts_verify_key(tfm, key, keylen);
if (ret) {
- dev_err(SEC_CTX_DEV(ctx), "xts mode key err!\n");
+ dev_err(dev, "xts mode key err!\n");
return ret;
}
}
switch (c_alg) {
case SEC_CALG_3DES:
- ret = sec_skcipher_3des_setkey(c_ctx, keylen, c_mode);
+ ret = sec_skcipher_3des_setkey(tfm, key, keylen, c_mode);
break;
case SEC_CALG_AES:
case SEC_CALG_SM4:
}
if (ret) {
- dev_err(SEC_CTX_DEV(ctx), "set sec key err!\n");
+ dev_err(dev, "set sec key err!\n");
return ret;
}
struct aead_request *aead_req = req->aead_req.aead_req;
struct sec_cipher_req *c_req = &req->c_req;
struct sec_qp_ctx *qp_ctx = req->qp_ctx;
- struct device *dev = SEC_CTX_DEV(ctx);
+ struct device *dev = ctx->dev;
int copy_size, pbuf_length;
int req_id = req->req_id;
copy_size = c_req->c_len;
pbuf_length = sg_copy_to_buffer(src, sg_nents(src),
- qp_ctx->res[req_id].pbuf,
- copy_size);
-
+ qp_ctx->res[req_id].pbuf,
+ copy_size);
if (unlikely(pbuf_length != copy_size)) {
dev_err(dev, "copy src data to pbuf error!\n");
return -EINVAL;
}
c_req->c_in_dma = qp_ctx->res[req_id].pbuf_dma;
-
- if (!c_req->c_in_dma) {
- dev_err(dev, "fail to set pbuffer address!\n");
- return -ENOMEM;
- }
-
c_req->c_out_dma = c_req->c_in_dma;
return 0;
struct aead_request *aead_req = req->aead_req.aead_req;
struct sec_cipher_req *c_req = &req->c_req;
struct sec_qp_ctx *qp_ctx = req->qp_ctx;
- struct device *dev = SEC_CTX_DEV(ctx);
+ struct device *dev = ctx->dev;
int copy_size, pbuf_length;
int req_id = req->req_id;
pbuf_length = sg_copy_from_buffer(dst, sg_nents(dst),
qp_ctx->res[req_id].pbuf,
copy_size);
-
if (unlikely(pbuf_length != copy_size))
dev_err(dev, "copy pbuf data to dst error!\n");
}
struct sec_aead_req *a_req = &req->aead_req;
struct sec_qp_ctx *qp_ctx = req->qp_ctx;
struct sec_alg_res *res = &qp_ctx->res[req->req_id];
- struct device *dev = SEC_CTX_DEV(ctx);
+ struct device *dev = ctx->dev;
int ret;
if (req->use_pbuf) {
struct scatterlist *src, struct scatterlist *dst)
{
struct sec_cipher_req *c_req = &req->c_req;
- struct device *dev = SEC_CTX_DEV(ctx);
+ struct device *dev = ctx->dev;
if (req->use_pbuf) {
sec_cipher_pbuf_unmap(ctx, req, dst);
{
struct sec_ctx *ctx = crypto_aead_ctx(tfm);
struct sec_cipher_ctx *c_ctx = &ctx->c_ctx;
+ struct device *dev = ctx->dev;
struct crypto_authenc_keys keys;
int ret;
ret = sec_aead_aes_set_key(c_ctx, &keys);
if (ret) {
- dev_err(SEC_CTX_DEV(ctx), "set sec cipher key err!\n");
+ dev_err(dev, "set sec cipher key err!\n");
goto bad_key;
}
ret = sec_aead_auth_set_key(&ctx->a_ctx, &keys);
if (ret) {
- dev_err(SEC_CTX_DEV(ctx), "set sec auth key err!\n");
+ dev_err(dev, "set sec auth key err!\n");
goto bad_key;
}
sz = sg_pcopy_to_buffer(sgl, sg_nents(sgl), iv, iv_size,
cryptlen - iv_size);
if (unlikely(sz != iv_size))
- dev_err(SEC_CTX_DEV(req->ctx), "copy output iv error!\n");
+ dev_err(req->ctx->dev, "copy output iv error!\n");
}
static struct sec_req *sec_back_req_clear(struct sec_ctx *ctx,
ret = sec_skcipher_bd_fill(ctx, req);
if (unlikely(ret)) {
- dev_err(SEC_CTX_DEV(ctx), "skcipher bd fill is error!\n");
+ dev_err(ctx->dev, "skcipher bd fill is error!\n");
return ret;
}
a_req->assoclen);
if (unlikely(sz != authsize)) {
- dev_err(SEC_CTX_DEV(req->ctx), "copy out mac err!\n");
+ dev_err(c->dev, "copy out mac err!\n");
err = -EINVAL;
}
}
ret = ctx->req_op->bd_send(ctx, req);
if (unlikely((ret != -EBUSY && ret != -EINPROGRESS) ||
(ret == -EBUSY && !(req->flag & CRYPTO_TFM_REQ_MAY_BACKLOG)))) {
- dev_err_ratelimited(SEC_CTX_DEV(ctx), "send sec request failed!\n");
+ dev_err_ratelimited(ctx->dev, "send sec request failed!\n");
goto err_send_req;
}
ctx->alg_type = SEC_AEAD;
ctx->c_ctx.ivsize = crypto_aead_ivsize(tfm);
if (ctx->c_ctx.ivsize > SEC_IV_SIZE) {
- dev_err(SEC_CTX_DEV(ctx), "get error aead iv size!\n");
+ dev_err(ctx->dev, "get error aead iv size!\n");
return -EINVAL;
}
auth_ctx->hash_tfm = crypto_alloc_shash(hash_name, 0, 0);
if (IS_ERR(auth_ctx->hash_tfm)) {
- dev_err(SEC_CTX_DEV(ctx), "aead alloc shash error!\n");
+ dev_err(ctx->dev, "aead alloc shash error!\n");
sec_aead_exit(tfm);
return PTR_ERR(auth_ctx->hash_tfm);
}
return sec_aead_ctx_init(tfm, "sha512");
}
+
+static int sec_skcipher_cryptlen_ckeck(struct sec_ctx *ctx,
+ struct sec_req *sreq)
+{
+ u32 cryptlen = sreq->c_req.sk_req->cryptlen;
+ struct device *dev = ctx->dev;
+ u8 c_mode = ctx->c_ctx.c_mode;
+ int ret = 0;
+
+ switch (c_mode) {
+ case SEC_CMODE_XTS:
+ if (unlikely(cryptlen < AES_BLOCK_SIZE)) {
+ dev_err(dev, "skcipher XTS mode input length error!\n");
+ ret = -EINVAL;
+ }
+ break;
+ case SEC_CMODE_ECB:
+ case SEC_CMODE_CBC:
+ if (unlikely(cryptlen & (AES_BLOCK_SIZE - 1))) {
+ dev_err(dev, "skcipher AES input length error!\n");
+ ret = -EINVAL;
+ }
+ break;
+ default:
+ ret = -EINVAL;
+ }
+
+ return ret;
+}
+
static int sec_skcipher_param_check(struct sec_ctx *ctx, struct sec_req *sreq)
{
struct skcipher_request *sk_req = sreq->c_req.sk_req;
- struct device *dev = SEC_CTX_DEV(ctx);
+ struct device *dev = ctx->dev;
u8 c_alg = ctx->c_ctx.c_alg;
if (unlikely(!sk_req->src || !sk_req->dst)) {
}
return 0;
} else if (c_alg == SEC_CALG_AES || c_alg == SEC_CALG_SM4) {
- if (unlikely(sk_req->cryptlen & (AES_BLOCK_SIZE - 1))) {
- dev_err(dev, "skcipher aes input length error!\n");
- return -EINVAL;
- }
- return 0;
+ return sec_skcipher_cryptlen_ckeck(ctx, sreq);
}
+
dev_err(dev, "skcipher algorithm error!\n");
return -EINVAL;
static int sec_aead_param_check(struct sec_ctx *ctx, struct sec_req *sreq)
{
- u8 c_alg = ctx->c_ctx.c_alg;
struct aead_request *req = sreq->aead_req.aead_req;
struct crypto_aead *tfm = crypto_aead_reqtfm(req);
size_t authsize = crypto_aead_authsize(tfm);
+ struct device *dev = ctx->dev;
+ u8 c_alg = ctx->c_ctx.c_alg;
if (unlikely(!req->src || !req->dst || !req->cryptlen ||
req->assoclen > SEC_MAX_AAD_LEN)) {
- dev_err(SEC_CTX_DEV(ctx), "aead input param error!\n");
+ dev_err(dev, "aead input param error!\n");
return -EINVAL;
}
/* Support AES only */
if (unlikely(c_alg != SEC_CALG_AES)) {
- dev_err(SEC_CTX_DEV(ctx), "aead crypto alg error!\n");
+ dev_err(dev, "aead crypto alg error!\n");
return -EINVAL;
}
if (sreq->c_req.encrypt)
sreq->c_req.c_len = req->cryptlen - authsize;
if (unlikely(sreq->c_req.c_len & (AES_BLOCK_SIZE - 1))) {
- dev_err(SEC_CTX_DEV(ctx), "aead crypto length error!\n");
+ dev_err(dev, "aead crypto length error!\n");
return -EINVAL;
}
AES_BLOCK_SIZE, AES_BLOCK_SIZE, SHA512_DIGEST_SIZE),
};
-int sec_register_to_crypto(void)
+int sec_register_to_crypto(struct hisi_qm *qm)
{
int ret;
return ret;
}
-void sec_unregister_from_crypto(void)
+void sec_unregister_from_crypto(struct hisi_qm *qm)
{
crypto_unregister_skciphers(sec_skciphers,
ARRAY_SIZE(sec_skciphers));
};
struct sec_sqe_type2 {
-
/*
* mac_len: 0~4 bits
* a_key_len: 5~10 bits
/* c_pad_len_field: 0~1 bits */
__le16 c_pad_len_field;
-
__le64 long_a_data_len;
__le64 a_ivin_addr;
__le64 a_key_addr;
struct sec_sqe_type2 type2;
};
-int sec_register_to_crypto(void);
-void sec_unregister_from_crypto(void);
+int sec_register_to_crypto(struct hisi_qm *qm);
+void sec_unregister_from_crypto(struct hisi_qm *qm);
#endif
#define SEC_VF_NUM 63
#define SEC_QUEUE_NUM_V1 4096
-#define SEC_QUEUE_NUM_V2 1024
#define SEC_PF_PCI_DEVICE_ID 0xa255
#define SEC_VF_PCI_DEVICE_ID 0xa256
#define SEC_CTX_Q_NUM_MAX 32
#define SEC_CTRL_CNT_CLR_CE 0x301120
-#define SEC_CTRL_CNT_CLR_CE_BIT BIT(0)
-#define SEC_ENGINE_PF_CFG_OFF 0x300000
-#define SEC_ACC_COMMON_REG_OFF 0x1000
+#define SEC_CTRL_CNT_CLR_CE_BIT BIT(0)
#define SEC_CORE_INT_SOURCE 0x301010
#define SEC_CORE_INT_MASK 0x301000
#define SEC_CORE_INT_STATUS 0x301008
#define SEC_CORE_SRAM_ECC_ERR_INFO 0x301C14
-#define SEC_ECC_NUM(err) (((err) >> 16) & 0xFF)
-#define SEC_ECC_ADDR(err) ((err) >> 0)
+#define SEC_ECC_NUM 16
+#define SEC_ECC_MASH 0xFF
#define SEC_CORE_INT_DISABLE 0x0
-#define SEC_CORE_INT_ENABLE 0x1ff
-#define SEC_CORE_INT_CLEAR 0x1ff
+#define SEC_CORE_INT_ENABLE 0x7c1ff
+#define SEC_CORE_INT_CLEAR 0x7c1ff
#define SEC_SAA_ENABLE 0x17f
#define SEC_RAS_CE_REG 0x301050
#define SEC_RAS_NFE_REG 0x301058
#define SEC_RAS_CE_ENB_MSK 0x88
#define SEC_RAS_FE_ENB_MSK 0x0
-#define SEC_RAS_NFE_ENB_MSK 0x177
-#define SEC_RAS_DISABLE 0x0
-#define SEC_MEM_START_INIT_REG 0x0100
-#define SEC_MEM_INIT_DONE_REG 0x0104
+#define SEC_RAS_NFE_ENB_MSK 0x7c177
+#define SEC_RAS_DISABLE 0x0
+#define SEC_MEM_START_INIT_REG 0x301100
+#define SEC_MEM_INIT_DONE_REG 0x301104
-#define SEC_CONTROL_REG 0x0200
+#define SEC_CONTROL_REG 0x301200
#define SEC_TRNG_EN_SHIFT 8
#define SEC_CLK_GATE_ENABLE BIT(3)
#define SEC_CLK_GATE_DISABLE (~BIT(3))
#define SEC_AXI_SHUTDOWN_ENABLE BIT(12)
#define SEC_AXI_SHUTDOWN_DISABLE 0xFFFFEFFF
-#define SEC_INTERFACE_USER_CTRL0_REG 0x0220
-#define SEC_INTERFACE_USER_CTRL1_REG 0x0224
-#define SEC_SAA_EN_REG 0x0270
-#define SEC_BD_ERR_CHK_EN_REG0 0x0380
-#define SEC_BD_ERR_CHK_EN_REG1 0x0384
-#define SEC_BD_ERR_CHK_EN_REG3 0x038c
+#define SEC_INTERFACE_USER_CTRL0_REG 0x301220
+#define SEC_INTERFACE_USER_CTRL1_REG 0x301224
+#define SEC_SAA_EN_REG 0x301270
+#define SEC_BD_ERR_CHK_EN_REG0 0x301380
+#define SEC_BD_ERR_CHK_EN_REG1 0x301384
+#define SEC_BD_ERR_CHK_EN_REG3 0x30138c
#define SEC_USER0_SMMU_NORMAL (BIT(23) | BIT(15))
#define SEC_USER1_SMMU_NORMAL (BIT(31) | BIT(23) | BIT(15) | BIT(7))
#define SEC_SQE_MASK_OFFSET 64
#define SEC_SQE_MASK_LEN 48
-#define SEC_ADDR(qm, offset) ((qm)->io_base + (offset) + \
- SEC_ENGINE_PF_CFG_OFF + SEC_ACC_COMMON_REG_OFF)
-
struct sec_hw_error {
u32 int_msk;
const char *msg;
};
static const struct sec_hw_error sec_hw_errors[] = {
- {.int_msk = BIT(0), .msg = "sec_axi_rresp_err_rint"},
- {.int_msk = BIT(1), .msg = "sec_axi_bresp_err_rint"},
- {.int_msk = BIT(2), .msg = "sec_ecc_2bit_err_rint"},
- {.int_msk = BIT(3), .msg = "sec_ecc_1bit_err_rint"},
- {.int_msk = BIT(4), .msg = "sec_req_trng_timeout_rint"},
- {.int_msk = BIT(5), .msg = "sec_fsm_hbeat_rint"},
- {.int_msk = BIT(6), .msg = "sec_channel_req_rng_timeout_rint"},
- {.int_msk = BIT(7), .msg = "sec_bd_err_rint"},
- {.int_msk = BIT(8), .msg = "sec_chain_buff_err_rint"},
- { /* sentinel */ }
+ {
+ .int_msk = BIT(0),
+ .msg = "sec_axi_rresp_err_rint"
+ },
+ {
+ .int_msk = BIT(1),
+ .msg = "sec_axi_bresp_err_rint"
+ },
+ {
+ .int_msk = BIT(2),
+ .msg = "sec_ecc_2bit_err_rint"
+ },
+ {
+ .int_msk = BIT(3),
+ .msg = "sec_ecc_1bit_err_rint"
+ },
+ {
+ .int_msk = BIT(4),
+ .msg = "sec_req_trng_timeout_rint"
+ },
+ {
+ .int_msk = BIT(5),
+ .msg = "sec_fsm_hbeat_rint"
+ },
+ {
+ .int_msk = BIT(6),
+ .msg = "sec_channel_req_rng_timeout_rint"
+ },
+ {
+ .int_msk = BIT(7),
+ .msg = "sec_bd_err_rint"
+ },
+ {
+ .int_msk = BIT(8),
+ .msg = "sec_chain_buff_err_rint"
+ },
+ {
+ .int_msk = BIT(14),
+ .msg = "sec_no_secure_access"
+ },
+ {
+ .int_msk = BIT(15),
+ .msg = "sec_wrapping_key_auth_err"
+ },
+ {
+ .int_msk = BIT(16),
+ .msg = "sec_km_key_crc_fail"
+ },
+ {
+ .int_msk = BIT(17),
+ .msg = "sec_axi_poison_err"
+ },
+ {
+ .int_msk = BIT(18),
+ .msg = "sec_sva_err"
+ },
+ {}
};
static const char * const sec_dbg_file_name[] = {
- [SEC_CURRENT_QM] = "current_qm",
[SEC_CLEAR_ENABLE] = "clear_enable",
};
"cannot access a register in VF!\n");
return SEC_LE;
}
- reg = readl_relaxed(qm->io_base + SEC_ENGINE_PF_CFG_OFF +
- SEC_ACC_COMMON_REG_OFF + SEC_CONTROL_REG);
-
+ reg = readl_relaxed(qm->io_base + SEC_CONTROL_REG);
/* BD little endian mode */
if (!(reg & BIT(0)))
return SEC_LE;
u32 reg;
/* disable clock gate control */
- reg = readl_relaxed(SEC_ADDR(qm, SEC_CONTROL_REG));
+ reg = readl_relaxed(qm->io_base + SEC_CONTROL_REG);
reg &= SEC_CLK_GATE_DISABLE;
- writel_relaxed(reg, SEC_ADDR(qm, SEC_CONTROL_REG));
+ writel_relaxed(reg, qm->io_base + SEC_CONTROL_REG);
- writel_relaxed(0x1, SEC_ADDR(qm, SEC_MEM_START_INIT_REG));
+ writel_relaxed(0x1, qm->io_base + SEC_MEM_START_INIT_REG);
- ret = readl_relaxed_poll_timeout(SEC_ADDR(qm, SEC_MEM_INIT_DONE_REG),
+ ret = readl_relaxed_poll_timeout(qm->io_base + SEC_MEM_INIT_DONE_REG,
reg, reg & 0x1, SEC_DELAY_10_US,
SEC_POLL_TIMEOUT_US);
if (ret) {
return ret;
}
- reg = readl_relaxed(SEC_ADDR(qm, SEC_CONTROL_REG));
+ reg = readl_relaxed(qm->io_base + SEC_CONTROL_REG);
reg |= (0x1 << SEC_TRNG_EN_SHIFT);
- writel_relaxed(reg, SEC_ADDR(qm, SEC_CONTROL_REG));
+ writel_relaxed(reg, qm->io_base + SEC_CONTROL_REG);
- reg = readl_relaxed(SEC_ADDR(qm, SEC_INTERFACE_USER_CTRL0_REG));
+ reg = readl_relaxed(qm->io_base + SEC_INTERFACE_USER_CTRL0_REG);
reg |= SEC_USER0_SMMU_NORMAL;
- writel_relaxed(reg, SEC_ADDR(qm, SEC_INTERFACE_USER_CTRL0_REG));
+ writel_relaxed(reg, qm->io_base + SEC_INTERFACE_USER_CTRL0_REG);
- reg = readl_relaxed(SEC_ADDR(qm, SEC_INTERFACE_USER_CTRL1_REG));
+ reg = readl_relaxed(qm->io_base + SEC_INTERFACE_USER_CTRL1_REG);
reg &= SEC_USER1_SMMU_MASK;
if (qm->use_sva && qm->ver == QM_HW_V2)
reg |= SEC_USER1_SMMU_SVA;
else
reg |= SEC_USER1_SMMU_NORMAL;
- writel_relaxed(reg, SEC_ADDR(qm, SEC_INTERFACE_USER_CTRL1_REG));
+ writel_relaxed(reg, qm->io_base + SEC_INTERFACE_USER_CTRL1_REG);
writel(SEC_SINGLE_PORT_MAX_TRANS,
qm->io_base + AM_CFG_SINGLE_PORT_MAX_TRANS);
- writel(SEC_SAA_ENABLE, SEC_ADDR(qm, SEC_SAA_EN_REG));
+ writel(SEC_SAA_ENABLE, qm->io_base + SEC_SAA_EN_REG);
/* Enable sm4 extra mode, as ctr/ecb */
writel_relaxed(SEC_BD_ERR_CHK_EN0,
- SEC_ADDR(qm, SEC_BD_ERR_CHK_EN_REG0));
+ qm->io_base + SEC_BD_ERR_CHK_EN_REG0);
/* Enable sm4 xts mode multiple iv */
writel_relaxed(SEC_BD_ERR_CHK_EN1,
- SEC_ADDR(qm, SEC_BD_ERR_CHK_EN_REG1));
+ qm->io_base + SEC_BD_ERR_CHK_EN_REG1);
writel_relaxed(SEC_BD_ERR_CHK_EN3,
- SEC_ADDR(qm, SEC_BD_ERR_CHK_EN_REG3));
+ qm->io_base + SEC_BD_ERR_CHK_EN_REG3);
/* config endian */
- reg = readl_relaxed(SEC_ADDR(qm, SEC_CONTROL_REG));
+ reg = readl_relaxed(qm->io_base + SEC_CONTROL_REG);
reg |= sec_get_endian(qm);
- writel_relaxed(reg, SEC_ADDR(qm, SEC_CONTROL_REG));
+ writel_relaxed(reg, qm->io_base + SEC_CONTROL_REG);
return 0;
}
{
int i;
- /* clear current_qm */
- writel(0x0, qm->io_base + QM_DFX_MB_CNT_VF);
- writel(0x0, qm->io_base + QM_DFX_DB_CNT_VF);
-
/* clear sec dfx regs */
writel(0x1, qm->io_base + SEC_CTRL_CNT_CLR_CE);
for (i = 0; i < ARRAY_SIZE(sec_dfx_regs); i++)
return;
}
- val = readl(SEC_ADDR(qm, SEC_CONTROL_REG));
+ val = readl(qm->io_base + SEC_CONTROL_REG);
/* clear SEC hw error source if having */
writel(SEC_CORE_INT_CLEAR, qm->io_base + SEC_CORE_INT_SOURCE);
/* enable SEC block master OOO when m-bit error occur */
val = val | SEC_AXI_SHUTDOWN_ENABLE;
- writel(val, SEC_ADDR(qm, SEC_CONTROL_REG));
+ writel(val, qm->io_base + SEC_CONTROL_REG);
}
static void sec_hw_error_disable(struct hisi_qm *qm)
{
u32 val;
- val = readl(SEC_ADDR(qm, SEC_CONTROL_REG));
+ val = readl(qm->io_base + SEC_CONTROL_REG);
/* disable RAS int */
writel(SEC_RAS_DISABLE, qm->io_base + SEC_RAS_CE_REG);
/* disable SEC block master OOO when m-bit error occur */
val = val & SEC_AXI_SHUTDOWN_DISABLE;
- writel(val, SEC_ADDR(qm, SEC_CONTROL_REG));
-}
-
-static u32 sec_current_qm_read(struct sec_debug_file *file)
-{
- struct hisi_qm *qm = file->qm;
-
- return readl(qm->io_base + QM_DFX_MB_CNT_VF);
-}
-
-static int sec_current_qm_write(struct sec_debug_file *file, u32 val)
-{
- struct hisi_qm *qm = file->qm;
- u32 vfq_num;
- u32 tmp;
-
- if (val > qm->vfs_num)
- return -EINVAL;
-
- /* According PF or VF Dev ID to calculation curr_qm_qp_num and store */
- if (!val) {
- qm->debug.curr_qm_qp_num = qm->qp_num;
- } else {
- vfq_num = (qm->ctrl_qp_num - qm->qp_num) / qm->vfs_num;
-
- if (val == qm->vfs_num)
- qm->debug.curr_qm_qp_num =
- qm->ctrl_qp_num - qm->qp_num -
- (qm->vfs_num - 1) * vfq_num;
- else
- qm->debug.curr_qm_qp_num = vfq_num;
- }
-
- writel(val, qm->io_base + QM_DFX_MB_CNT_VF);
- writel(val, qm->io_base + QM_DFX_DB_CNT_VF);
-
- tmp = val |
- (readl(qm->io_base + QM_DFX_SQE_CNT_VF_SQN) & CURRENT_Q_MASK);
- writel(tmp, qm->io_base + QM_DFX_SQE_CNT_VF_SQN);
-
- tmp = val |
- (readl(qm->io_base + QM_DFX_CQE_CNT_VF_CQN) & CURRENT_Q_MASK);
- writel(tmp, qm->io_base + QM_DFX_CQE_CNT_VF_CQN);
-
- return 0;
+ writel(val, qm->io_base + SEC_CONTROL_REG);
}
static u32 sec_clear_enable_read(struct sec_debug_file *file)
spin_lock_irq(&file->lock);
switch (file->index) {
- case SEC_CURRENT_QM:
- val = sec_current_qm_read(file);
- break;
case SEC_CLEAR_ENABLE:
val = sec_clear_enable_read(file);
break;
spin_lock_irq(&file->lock);
switch (file->index) {
- case SEC_CURRENT_QM:
- ret = sec_current_qm_write(file, val);
- if (ret)
- goto err_input;
- break;
case SEC_CLEAR_ENABLE:
ret = sec_clear_enable_write(file, val);
if (ret)
int i;
if (qm->pdev->device == SEC_PF_PCI_DEVICE_ID) {
- for (i = SEC_CURRENT_QM; i < SEC_DEBUG_FILE_NUM; i++) {
+ for (i = SEC_CLEAR_ENABLE; i < SEC_DEBUG_FILE_NUM; i++) {
spin_lock_init(&sec->debug.files[i].lock);
sec->debug.files[i].index = i;
sec->debug.files[i].qm = qm;
err_val = readl(qm->io_base +
SEC_CORE_SRAM_ECC_ERR_INFO);
dev_err(dev, "multi ecc sram num=0x%x\n",
- SEC_ECC_NUM(err_val));
+ ((err_val) >> SEC_ECC_NUM) &
+ SEC_ECC_MASH);
}
}
errs++;
{
u32 val;
- val = readl(SEC_ADDR(qm, SEC_CONTROL_REG));
- writel(val & SEC_AXI_SHUTDOWN_DISABLE, SEC_ADDR(qm, SEC_CONTROL_REG));
- writel(val | SEC_AXI_SHUTDOWN_ENABLE, SEC_ADDR(qm, SEC_CONTROL_REG));
+ val = readl(qm->io_base + SEC_CONTROL_REG);
+ writel(val & SEC_AXI_SHUTDOWN_DISABLE, qm->io_base + SEC_CONTROL_REG);
+ writel(val | SEC_AXI_SHUTDOWN_ENABLE, qm->io_base + SEC_CONTROL_REG);
+}
+
+static void sec_err_info_init(struct hisi_qm *qm)
+{
+ struct hisi_qm_err_info *err_info = &qm->err_info;
+
+ err_info->ce = QM_BASE_CE;
+ err_info->fe = 0;
+ err_info->ecc_2bits_mask = SEC_CORE_INT_STATUS_M_ECC;
+ err_info->dev_ce_mask = SEC_RAS_CE_ENB_MSK;
+ err_info->msi_wr_port = BIT(0);
+ err_info->acpi_rst = "SRST";
+ err_info->nfe = QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT |
+ QM_ACC_WB_NOT_READY_TIMEOUT;
}
static const struct hisi_qm_err_ini sec_err_ini = {
.clear_dev_hw_err_status = sec_clear_hw_err_status,
.log_dev_hw_err = sec_log_hw_error,
.open_axi_master_ooo = sec_open_axi_master_ooo,
- .err_info = {
- .ce = QM_BASE_CE,
- .nfe = QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT |
- QM_ACC_WB_NOT_READY_TIMEOUT,
- .fe = 0,
- .ecc_2bits_mask = SEC_CORE_INT_STATUS_M_ECC,
- .dev_ce_mask = SEC_RAS_CE_ENB_MSK,
- .msi_wr_port = BIT(0),
- .acpi_rst = "SRST",
- }
+ .err_info_init = sec_err_info_init,
};
static int sec_pf_probe_init(struct sec_dev *sec)
struct hisi_qm *qm = &sec->qm;
int ret;
- if (qm->ver == QM_HW_V1)
- qm->ctrl_qp_num = SEC_QUEUE_NUM_V1;
- else
- qm->ctrl_qp_num = SEC_QUEUE_NUM_V2;
-
qm->err_ini = &sec_err_ini;
+ qm->err_ini->err_info_init(qm);
ret = sec_set_user_domain_and_cache(qm);
if (ret)
qm->pdev = pdev;
qm->ver = pdev->revision;
- qm->algs = "cipher\ndigest\naead\n";
+ qm->algs = "cipher\ndigest\naead";
qm->mode = uacce_mode;
qm->sqe_size = SEC_SQE_SIZE;
qm->dev_name = sec_name;
if (ret)
pci_warn(pdev, "Failed to init debugfs!\n");
- ret = hisi_qm_alg_register(qm, &sec_devices);
- if (ret < 0) {
- pr_err("Failed to register driver to crypto.\n");
- goto err_qm_stop;
+ if (qm->qp_num >= ctx_q_num) {
+ ret = hisi_qm_alg_register(qm, &sec_devices);
+ if (ret < 0) {
+ pr_err("Failed to register driver to crypto.\n");
+ goto err_qm_stop;
+ }
+ } else {
+ pci_warn(qm->pdev,
+ "Failed to use kernel mode, qp not enough!\n");
}
if (qm->uacce) {
struct hisi_qm *qm = pci_get_drvdata(pdev);
hisi_qm_wait_task_finish(qm, &sec_devices);
- hisi_qm_alg_unregister(qm, &sec_devices);
+ if (qm->qp_num >= ctx_q_num)
+ hisi_qm_alg_unregister(qm, &sec_devices);
+
if (qm->fun_type == QM_HW_PF && qm->vfs_num)
hisi_qm_sriov_disable(pdev, true);
struct hisi_acc_sgl_pool *hisi_acc_create_sgl_pool(struct device *dev,
u32 count, u32 sge_nr)
{
- u32 sgl_size, block_size, sgl_num_per_block, block_num, remain_sgl = 0;
+ u32 sgl_size, block_size, sgl_num_per_block, block_num, remain_sgl;
struct hisi_acc_sgl_pool *pool;
struct mem_block *block;
u32 i, j;
sgl_size = sizeof(struct acc_hw_sge) * sge_nr +
sizeof(struct hisi_acc_hw_sgl);
+
+ /*
+ * the pool may allocate a block of memory of size PAGE_SIZE * 2^(MAX_ORDER - 1),
+ * block size may exceed 2^31 on ia64, so the max of block size is 2^31
+ */
block_size = 1 << (PAGE_SHIFT + MAX_ORDER <= 32 ?
PAGE_SHIFT + MAX_ORDER - 1 : 31);
sgl_num_per_block = block_size / sgl_size;
block[i].sgl = dma_alloc_coherent(dev, block_size,
&block[i].sgl_dma,
GFP_KERNEL);
- if (!block[i].sgl)
+ if (!block[i].sgl) {
+ dev_err(dev, "Fail to allocate hw SG buffer!\n");
goto err_free_mem;
+ }
block[i].size = block_size;
}
block[i].sgl = dma_alloc_coherent(dev, remain_sgl * sgl_size,
&block[i].sgl_dma,
GFP_KERNEL);
- if (!block[i].sgl)
+ if (!block[i].sgl) {
+ dev_err(dev, "Fail to allocate remained hw SG buffer!\n");
goto err_free_mem;
+ }
block[i].size = remain_sgl * sgl_size;
}
{
hw_sge->buf = sg_dma_address(sgl);
hw_sge->len = cpu_to_le32(sg_dma_len(sgl));
+ hw_sge->page_ctrl = sg_virt(sgl);
}
static void inc_hw_sgl_sge(struct hisi_acc_hw_sgl *hw_sgl)
hw_sgl->entry_sum_in_chain = cpu_to_le16(sum);
}
+static void clear_hw_sgl_sge(struct hisi_acc_hw_sgl *hw_sgl)
+{
+ struct acc_hw_sge *hw_sge = hw_sgl->sge_entries;
+ int i;
+
+ for (i = 0; i < le16_to_cpu(hw_sgl->entry_sum_in_sgl); i++) {
+ hw_sge[i].page_ctrl = NULL;
+ hw_sge[i].buf = 0;
+ hw_sge[i].len = 0;
+ }
+}
+
/**
* hisi_acc_sg_buf_map_to_hw_sgl - Map a scatterlist to a hw sgl.
* @dev: The device which hw sgl belongs to.
sg_n = sg_nents(sgl);
sg_n_mapped = dma_map_sg(dev, sgl, sg_n, DMA_BIDIRECTIONAL);
- if (!sg_n_mapped)
+ if (!sg_n_mapped) {
+ dev_err(dev, "DMA mapping for SG error!\n");
return ERR_PTR(-EINVAL);
+ }
if (sg_n_mapped > pool->sge_nr) {
- dma_unmap_sg(dev, sgl, sg_n, DMA_BIDIRECTIONAL);
+ dev_err(dev, "the number of entries in input scatterlist is bigger than SGL pool setting.\n");
return ERR_PTR(-EINVAL);
}
curr_hw_sgl = acc_get_sgl(pool, index, &curr_sgl_dma);
if (IS_ERR(curr_hw_sgl)) {
+ dev_err(dev, "Get SGL error!\n");
dma_unmap_sg(dev, sgl, sg_n, DMA_BIDIRECTIONAL);
return ERR_PTR(-ENOMEM);
return;
dma_unmap_sg(dev, sgl, sg_nents(sgl), DMA_BIDIRECTIONAL);
-
+ clear_hw_sgl_sge(hw_sgl);
hw_sgl->entry_sum_in_chain = 0;
hw_sgl->entry_sum_in_sgl = 0;
hw_sgl->entry_length_in_sgl = 0;
#define HISI_TRNG_REG 0x00F0
#define HISI_TRNG_BYTES 4
#define HISI_TRNG_QUALITY 512
+#define HISI_TRNG_VERSION 0x01B8
+#define HISI_TRNG_VER_V1 GENMASK(31, 0)
#define SLEEP_US 10
#define TIMEOUT_US 10000
#define SW_DRBG_NUM_SHIFT 2
struct hisi_trng_list *trng_list;
struct list_head list;
struct hwrng rng;
+ u32 ver;
bool is_used;
struct mutex mutex;
};
return PTR_ERR(trng->base);
trng->is_used = false;
+ trng->ver = readl(trng->base + HISI_TRNG_VERSION);
if (!trng_devices.is_init) {
INIT_LIST_HEAD(&trng_devices.list);
mutex_init(&trng_devices.lock);
}
hisi_trng_add_to_list(trng);
- if (atomic_inc_return(&trng_active_devs) == 1) {
+ if (trng->ver != HISI_TRNG_VER_V1 &&
+ atomic_inc_return(&trng_active_devs) == 1) {
ret = crypto_register_rng(&hisi_trng_alg);
if (ret) {
dev_err(&pdev->dev,
return ret;
err_crypto_unregister:
- if (atomic_dec_return(&trng_active_devs) == 0)
+ if (trng->ver != HISI_TRNG_VER_V1 &&
+ atomic_dec_return(&trng_active_devs) == 0)
crypto_unregister_rng(&hisi_trng_alg);
err_remove_from_list:
while (hisi_trng_del_from_list(trng))
;
- if (atomic_dec_return(&trng_active_devs) == 0)
+ if (trng->ver != HISI_TRNG_VER_V1 &&
+ atomic_dec_return(&trng_active_devs) == 0)
crypto_unregister_rng(&hisi_trng_alg);
return 0;
u32 consumed;
u32 produced;
u32 comp_data_length;
+ /*
+ * status: 0~7 bits
+ * rsvd: 8~31 bits
+ */
u32 dw3;
u32 input_data_length;
- u32 lba_l;
- u32 lba_h;
+ u32 dw5;
+ u32 dw6;
+ /*
+ * in_sge_data_offset: 0~23 bits
+ * rsvd: 24~27 bits
+ * sqe_type: 29~31 bits
+ */
u32 dw7;
+ /*
+ * out_sge_data_offset: 0~23 bits
+ * rsvd: 24~31 bits
+ */
u32 dw8;
+ /*
+ * request_type: 0~7 bits
+ * buffer_type: 8~11 bits
+ * rsvd: 13~31 bits
+ */
u32 dw9;
u32 dw10;
- u32 priv_info;
+ u32 dw11;
u32 dw12;
- u32 tag;
+ /* tag: in sqe type 0 */
+ u32 dw13;
u32 dest_avail_out;
- u32 rsvd0;
- u32 comp_head_addr_l;
- u32 comp_head_addr_h;
+ u32 dw15;
+ u32 dw16;
+ u32 dw17;
u32 source_addr_l;
u32 source_addr_h;
u32 dest_addr_l;
u32 dest_addr_h;
- u32 stream_ctx_addr_l;
- u32 stream_ctx_addr_h;
- u32 cipher_key1_addr_l;
- u32 cipher_key1_addr_h;
- u32 cipher_key2_addr_l;
- u32 cipher_key2_addr_h;
+ u32 dw22;
+ u32 dw23;
+ u32 dw24;
+ u32 dw25;
+ /* tag: in sqe type 3 */
+ u32 dw26;
+ u32 dw27;
u32 rsvd1[4];
};
int zip_create_qps(struct hisi_qp **qps, int ctx_num, int node);
-int hisi_zip_register_to_crypto(void);
-void hisi_zip_unregister_from_crypto(void);
+int hisi_zip_register_to_crypto(struct hisi_qm *qm);
+void hisi_zip_unregister_from_crypto(struct hisi_qm *qm);
#endif
#define HZIP_BD_STATUS_M GENMASK(7, 0)
/* hisi_zip_sqe dw7 */
#define HZIP_IN_SGE_DATA_OFFSET_M GENMASK(23, 0)
+#define HZIP_SQE_TYPE_M GENMASK(31, 28)
/* hisi_zip_sqe dw8 */
#define HZIP_OUT_SGE_DATA_OFFSET_M GENMASK(23, 0)
/* hisi_zip_sqe dw9 */
struct hisi_zip_ctx *ctx;
};
+struct hisi_zip_sqe_ops {
+ u8 sqe_type;
+ void (*fill_addr)(struct hisi_zip_sqe *sqe, struct hisi_zip_req *req);
+ void (*fill_buf_size)(struct hisi_zip_sqe *sqe, struct hisi_zip_req *req);
+ void (*fill_buf_type)(struct hisi_zip_sqe *sqe, u8 buf_type);
+ void (*fill_req_type)(struct hisi_zip_sqe *sqe, u8 req_type);
+ void (*fill_tag)(struct hisi_zip_sqe *sqe, struct hisi_zip_req *req);
+ void (*fill_sqe_type)(struct hisi_zip_sqe *sqe, u8 sqe_type);
+ u32 (*get_tag)(struct hisi_zip_sqe *sqe);
+ u32 (*get_status)(struct hisi_zip_sqe *sqe);
+ u32 (*get_dstlen)(struct hisi_zip_sqe *sqe);
+};
+
struct hisi_zip_ctx {
struct hisi_zip_qp_ctx qp_ctx[HZIP_CTX_Q_NUM];
+ const struct hisi_zip_sqe_ops *ops;
};
static int sgl_sge_nr_set(const char *val, const struct kernel_param *kp)
module_param_cb(sgl_sge_nr, &sgl_sge_nr_ops, &sgl_sge_nr, 0444);
MODULE_PARM_DESC(sgl_sge_nr, "Number of sge in sgl(1-255)");
-static void hisi_zip_config_buf_type(struct hisi_zip_sqe *sqe, u8 buf_type)
+static u16 get_extra_field_size(const u8 *start)
+{
+ return *((u16 *)start) + GZIP_HEAD_FEXTRA_XLEN;
+}
+
+static u32 get_name_field_size(const u8 *start)
+{
+ return strlen(start) + 1;
+}
+
+static u32 get_comment_field_size(const u8 *start)
+{
+ return strlen(start) + 1;
+}
+
+static u32 __get_gzip_head_size(const u8 *src)
+{
+ u8 head_flg = *(src + GZIP_HEAD_FLG_SHIFT);
+ u32 size = GZIP_HEAD_FEXTRA_SHIFT;
+
+ if (head_flg & GZIP_HEAD_FEXTRA_BIT)
+ size += get_extra_field_size(src + size);
+ if (head_flg & GZIP_HEAD_FNAME_BIT)
+ size += get_name_field_size(src + size);
+ if (head_flg & GZIP_HEAD_FCOMMENT_BIT)
+ size += get_comment_field_size(src + size);
+ if (head_flg & GZIP_HEAD_FHCRC_BIT)
+ size += GZIP_HEAD_FHCRC_SIZE;
+
+ return size;
+}
+
+static size_t __maybe_unused get_gzip_head_size(struct scatterlist *sgl)
+{
+ char buf[HZIP_GZIP_HEAD_BUF];
+
+ sg_copy_to_buffer(sgl, sg_nents(sgl), buf, sizeof(buf));
+
+ return __get_gzip_head_size(buf);
+}
+
+static int add_comp_head(struct scatterlist *dst, u8 req_type)
+{
+ int head_size = TO_HEAD_SIZE(req_type);
+ const u8 *head = TO_HEAD(req_type);
+ int ret;
+
+ ret = sg_copy_from_buffer(dst, sg_nents(dst), head, head_size);
+ if (ret != head_size) {
+ pr_err("the head size of buffer is wrong (%d)!\n", ret);
+ return -ENOMEM;
+ }
+
+ return head_size;
+}
+
+static int get_comp_head_size(struct acomp_req *acomp_req, u8 req_type)
+{
+ if (!acomp_req->src || !acomp_req->slen)
+ return -EINVAL;
+
+ if (req_type == HZIP_ALG_TYPE_GZIP &&
+ acomp_req->slen < GZIP_HEAD_FEXTRA_SHIFT)
+ return -EINVAL;
+
+ switch (req_type) {
+ case HZIP_ALG_TYPE_ZLIB:
+ return TO_HEAD_SIZE(HZIP_ALG_TYPE_ZLIB);
+ case HZIP_ALG_TYPE_GZIP:
+ return TO_HEAD_SIZE(HZIP_ALG_TYPE_GZIP);
+ default:
+ pr_err("request type does not support!\n");
+ return -EINVAL;
+ }
+}
+
+static struct hisi_zip_req *hisi_zip_create_req(struct acomp_req *req,
+ struct hisi_zip_qp_ctx *qp_ctx,
+ size_t head_size, bool is_comp)
+{
+ struct hisi_zip_req_q *req_q = &qp_ctx->req_q;
+ struct hisi_zip_req *q = req_q->q;
+ struct hisi_zip_req *req_cache;
+ int req_id;
+
+ write_lock(&req_q->req_lock);
+
+ req_id = find_first_zero_bit(req_q->req_bitmap, req_q->size);
+ if (req_id >= req_q->size) {
+ write_unlock(&req_q->req_lock);
+ dev_dbg(&qp_ctx->qp->qm->pdev->dev, "req cache is full!\n");
+ return ERR_PTR(-EAGAIN);
+ }
+ set_bit(req_id, req_q->req_bitmap);
+
+ req_cache = q + req_id;
+ req_cache->req_id = req_id;
+ req_cache->req = req;
+
+ if (is_comp) {
+ req_cache->sskip = 0;
+ req_cache->dskip = head_size;
+ } else {
+ req_cache->sskip = head_size;
+ req_cache->dskip = 0;
+ }
+
+ write_unlock(&req_q->req_lock);
+
+ return req_cache;
+}
+
+static void hisi_zip_remove_req(struct hisi_zip_qp_ctx *qp_ctx,
+ struct hisi_zip_req *req)
+{
+ struct hisi_zip_req_q *req_q = &qp_ctx->req_q;
+
+ write_lock(&req_q->req_lock);
+ clear_bit(req->req_id, req_q->req_bitmap);
+ memset(req, 0, sizeof(struct hisi_zip_req));
+ write_unlock(&req_q->req_lock);
+}
+
+static void hisi_zip_fill_addr(struct hisi_zip_sqe *sqe, struct hisi_zip_req *req)
+{
+ sqe->source_addr_l = lower_32_bits(req->dma_src);
+ sqe->source_addr_h = upper_32_bits(req->dma_src);
+ sqe->dest_addr_l = lower_32_bits(req->dma_dst);
+ sqe->dest_addr_h = upper_32_bits(req->dma_dst);
+}
+
+static void hisi_zip_fill_buf_size(struct hisi_zip_sqe *sqe, struct hisi_zip_req *req)
+{
+ struct acomp_req *a_req = req->req;
+
+ sqe->input_data_length = a_req->slen - req->sskip;
+ sqe->dest_avail_out = a_req->dlen - req->dskip;
+ sqe->dw7 = FIELD_PREP(HZIP_IN_SGE_DATA_OFFSET_M, req->sskip);
+ sqe->dw8 = FIELD_PREP(HZIP_OUT_SGE_DATA_OFFSET_M, req->dskip);
+}
+
+static void hisi_zip_fill_buf_type(struct hisi_zip_sqe *sqe, u8 buf_type)
{
u32 val;
- val = (sqe->dw9) & ~HZIP_BUF_TYPE_M;
+ val = sqe->dw9 & ~HZIP_BUF_TYPE_M;
val |= FIELD_PREP(HZIP_BUF_TYPE_M, buf_type);
sqe->dw9 = val;
}
-static void hisi_zip_config_tag(struct hisi_zip_sqe *sqe, u32 tag)
+static void hisi_zip_fill_req_type(struct hisi_zip_sqe *sqe, u8 req_type)
+{
+ u32 val;
+
+ val = sqe->dw9 & ~HZIP_REQ_TYPE_M;
+ val |= FIELD_PREP(HZIP_REQ_TYPE_M, req_type);
+ sqe->dw9 = val;
+}
+
+static void hisi_zip_fill_tag_v1(struct hisi_zip_sqe *sqe, struct hisi_zip_req *req)
+{
+ sqe->dw13 = req->req_id;
+}
+
+static void hisi_zip_fill_tag_v2(struct hisi_zip_sqe *sqe, struct hisi_zip_req *req)
+{
+ sqe->dw26 = req->req_id;
+}
+
+static void hisi_zip_fill_sqe_type(struct hisi_zip_sqe *sqe, u8 sqe_type)
{
- sqe->tag = tag;
+ u32 val;
+
+ val = sqe->dw7 & ~HZIP_SQE_TYPE_M;
+ val |= FIELD_PREP(HZIP_SQE_TYPE_M, sqe_type);
+ sqe->dw7 = val;
}
-static void hisi_zip_fill_sqe(struct hisi_zip_sqe *sqe, u8 req_type,
- dma_addr_t s_addr, dma_addr_t d_addr, u32 slen,
- u32 dlen, u32 sskip, u32 dskip)
+static void hisi_zip_fill_sqe(struct hisi_zip_ctx *ctx, struct hisi_zip_sqe *sqe,
+ u8 req_type, struct hisi_zip_req *req)
{
+ const struct hisi_zip_sqe_ops *ops = ctx->ops;
+
memset(sqe, 0, sizeof(struct hisi_zip_sqe));
- sqe->input_data_length = slen - sskip;
- sqe->dw7 = FIELD_PREP(HZIP_IN_SGE_DATA_OFFSET_M, sskip);
- sqe->dw8 = FIELD_PREP(HZIP_OUT_SGE_DATA_OFFSET_M, dskip);
- sqe->dw9 = FIELD_PREP(HZIP_REQ_TYPE_M, req_type);
- sqe->dest_avail_out = dlen - dskip;
- sqe->source_addr_l = lower_32_bits(s_addr);
- sqe->source_addr_h = upper_32_bits(s_addr);
- sqe->dest_addr_l = lower_32_bits(d_addr);
- sqe->dest_addr_h = upper_32_bits(d_addr);
+ ops->fill_addr(sqe, req);
+ ops->fill_buf_size(sqe, req);
+ ops->fill_buf_type(sqe, HZIP_SGL);
+ ops->fill_req_type(sqe, req_type);
+ ops->fill_tag(sqe, req);
+ ops->fill_sqe_type(sqe, ops->sqe_type);
+}
+
+static int hisi_zip_do_work(struct hisi_zip_req *req,
+ struct hisi_zip_qp_ctx *qp_ctx)
+{
+ struct hisi_acc_sgl_pool *pool = qp_ctx->sgl_pool;
+ struct hisi_zip_dfx *dfx = &qp_ctx->zip_dev->dfx;
+ struct acomp_req *a_req = req->req;
+ struct hisi_qp *qp = qp_ctx->qp;
+ struct device *dev = &qp->qm->pdev->dev;
+ struct hisi_zip_sqe zip_sqe;
+ int ret;
+
+ if (!a_req->src || !a_req->slen || !a_req->dst || !a_req->dlen)
+ return -EINVAL;
+
+ req->hw_src = hisi_acc_sg_buf_map_to_hw_sgl(dev, a_req->src, pool,
+ req->req_id << 1, &req->dma_src);
+ if (IS_ERR(req->hw_src)) {
+ dev_err(dev, "failed to map the src buffer to hw sgl (%ld)!\n",
+ PTR_ERR(req->hw_src));
+ return PTR_ERR(req->hw_src);
+ }
+
+ req->hw_dst = hisi_acc_sg_buf_map_to_hw_sgl(dev, a_req->dst, pool,
+ (req->req_id << 1) + 1,
+ &req->dma_dst);
+ if (IS_ERR(req->hw_dst)) {
+ ret = PTR_ERR(req->hw_dst);
+ dev_err(dev, "failed to map the dst buffer to hw slg (%d)!\n",
+ ret);
+ goto err_unmap_input;
+ }
+
+ hisi_zip_fill_sqe(qp_ctx->ctx, &zip_sqe, qp->req_type, req);
+
+ /* send command to start a task */
+ atomic64_inc(&dfx->send_cnt);
+ ret = hisi_qp_send(qp, &zip_sqe);
+ if (ret < 0) {
+ atomic64_inc(&dfx->send_busy_cnt);
+ ret = -EAGAIN;
+ dev_dbg_ratelimited(dev, "failed to send request!\n");
+ goto err_unmap_output;
+ }
+
+ return -EINPROGRESS;
+
+err_unmap_output:
+ hisi_acc_sg_buf_unmap(dev, a_req->dst, req->hw_dst);
+err_unmap_input:
+ hisi_acc_sg_buf_unmap(dev, a_req->src, req->hw_src);
+ return ret;
+}
+
+static u32 hisi_zip_get_tag_v1(struct hisi_zip_sqe *sqe)
+{
+ return sqe->dw13;
+}
+
+static u32 hisi_zip_get_tag_v2(struct hisi_zip_sqe *sqe)
+{
+ return sqe->dw26;
+}
+
+static u32 hisi_zip_get_status(struct hisi_zip_sqe *sqe)
+{
+ return sqe->dw3 & HZIP_BD_STATUS_M;
+}
+
+static u32 hisi_zip_get_dstlen(struct hisi_zip_sqe *sqe)
+{
+ return sqe->produced;
+}
+
+static void hisi_zip_acomp_cb(struct hisi_qp *qp, void *data)
+{
+ struct hisi_zip_qp_ctx *qp_ctx = qp->qp_ctx;
+ const struct hisi_zip_sqe_ops *ops = qp_ctx->ctx->ops;
+ struct hisi_zip_dfx *dfx = &qp_ctx->zip_dev->dfx;
+ struct hisi_zip_req_q *req_q = &qp_ctx->req_q;
+ struct device *dev = &qp->qm->pdev->dev;
+ struct hisi_zip_sqe *sqe = data;
+ u32 tag = ops->get_tag(sqe);
+ struct hisi_zip_req *req = req_q->q + tag;
+ struct acomp_req *acomp_req = req->req;
+ u32 status, dlen, head_size;
+ int err = 0;
+
+ atomic64_inc(&dfx->recv_cnt);
+ status = ops->get_status(sqe);
+ if (status != 0 && status != HZIP_NC_ERR) {
+ dev_err(dev, "%scompress fail in qp%u: %u, output: %u\n",
+ (qp->alg_type == 0) ? "" : "de", qp->qp_id, status,
+ sqe->produced);
+ atomic64_inc(&dfx->err_bd_cnt);
+ err = -EIO;
+ }
+
+ dlen = ops->get_dstlen(sqe);
+
+ hisi_acc_sg_buf_unmap(dev, acomp_req->src, req->hw_src);
+ hisi_acc_sg_buf_unmap(dev, acomp_req->dst, req->hw_dst);
+
+ head_size = (qp->alg_type == 0) ? TO_HEAD_SIZE(qp->req_type) : 0;
+ acomp_req->dlen = dlen + head_size;
+
+ if (acomp_req->base.complete)
+ acomp_request_complete(acomp_req, err);
+
+ hisi_zip_remove_req(qp_ctx, req);
+}
+
+static int hisi_zip_acompress(struct acomp_req *acomp_req)
+{
+ struct hisi_zip_ctx *ctx = crypto_tfm_ctx(acomp_req->base.tfm);
+ struct hisi_zip_qp_ctx *qp_ctx = &ctx->qp_ctx[HZIP_QPC_COMP];
+ struct device *dev = &qp_ctx->qp->qm->pdev->dev;
+ struct hisi_zip_req *req;
+ int head_size;
+ int ret;
+
+ /* let's output compression head now */
+ head_size = add_comp_head(acomp_req->dst, qp_ctx->qp->req_type);
+ if (head_size < 0) {
+ dev_err_ratelimited(dev, "failed to add comp head (%d)!\n",
+ head_size);
+ return head_size;
+ }
+
+ req = hisi_zip_create_req(acomp_req, qp_ctx, head_size, true);
+ if (IS_ERR(req))
+ return PTR_ERR(req);
+
+ ret = hisi_zip_do_work(req, qp_ctx);
+ if (ret != -EINPROGRESS) {
+ dev_info_ratelimited(dev, "failed to do compress (%d)!\n", ret);
+ hisi_zip_remove_req(qp_ctx, req);
+ }
+
+ return ret;
+}
+
+static int hisi_zip_adecompress(struct acomp_req *acomp_req)
+{
+ struct hisi_zip_ctx *ctx = crypto_tfm_ctx(acomp_req->base.tfm);
+ struct hisi_zip_qp_ctx *qp_ctx = &ctx->qp_ctx[HZIP_QPC_DECOMP];
+ struct device *dev = &qp_ctx->qp->qm->pdev->dev;
+ struct hisi_zip_req *req;
+ int head_size, ret;
+
+ head_size = get_comp_head_size(acomp_req, qp_ctx->qp->req_type);
+ if (head_size < 0) {
+ dev_err_ratelimited(dev, "failed to get comp head size (%d)!\n",
+ head_size);
+ return head_size;
+ }
+
+ req = hisi_zip_create_req(acomp_req, qp_ctx, head_size, false);
+ if (IS_ERR(req))
+ return PTR_ERR(req);
+
+ ret = hisi_zip_do_work(req, qp_ctx);
+ if (ret != -EINPROGRESS) {
+ dev_info_ratelimited(dev, "failed to do decompress (%d)!\n",
+ ret);
+ hisi_zip_remove_req(qp_ctx, req);
+ }
+
+ return ret;
}
static int hisi_zip_start_qp(struct hisi_qp *qp, struct hisi_zip_qp_ctx *ctx,
hisi_qm_release_qp(ctx->qp);
}
+static const struct hisi_zip_sqe_ops hisi_zip_ops_v1 = {
+ .sqe_type = 0,
+ .fill_addr = hisi_zip_fill_addr,
+ .fill_buf_size = hisi_zip_fill_buf_size,
+ .fill_buf_type = hisi_zip_fill_buf_type,
+ .fill_req_type = hisi_zip_fill_req_type,
+ .fill_tag = hisi_zip_fill_tag_v1,
+ .fill_sqe_type = hisi_zip_fill_sqe_type,
+ .get_tag = hisi_zip_get_tag_v1,
+ .get_status = hisi_zip_get_status,
+ .get_dstlen = hisi_zip_get_dstlen,
+};
+
+static const struct hisi_zip_sqe_ops hisi_zip_ops_v2 = {
+ .sqe_type = 0x3,
+ .fill_addr = hisi_zip_fill_addr,
+ .fill_buf_size = hisi_zip_fill_buf_size,
+ .fill_buf_type = hisi_zip_fill_buf_type,
+ .fill_req_type = hisi_zip_fill_req_type,
+ .fill_tag = hisi_zip_fill_tag_v2,
+ .fill_sqe_type = hisi_zip_fill_sqe_type,
+ .get_tag = hisi_zip_get_tag_v2,
+ .get_status = hisi_zip_get_status,
+ .get_dstlen = hisi_zip_get_dstlen,
+};
+
static int hisi_zip_ctx_init(struct hisi_zip_ctx *hisi_zip_ctx, u8 req_type, int node)
{
struct hisi_qp *qps[HZIP_CTX_Q_NUM] = { NULL };
+ struct hisi_zip_qp_ctx *qp_ctx;
struct hisi_zip *hisi_zip;
int ret, i, j;
for (i = 0; i < HZIP_CTX_Q_NUM; i++) {
/* alg_type = 0 for compress, 1 for decompress in hw sqe */
- ret = hisi_zip_start_qp(qps[i], &hisi_zip_ctx->qp_ctx[i], i,
- req_type);
+ qp_ctx = &hisi_zip_ctx->qp_ctx[i];
+ qp_ctx->ctx = hisi_zip_ctx;
+ ret = hisi_zip_start_qp(qps[i], qp_ctx, i, req_type);
if (ret) {
for (j = i - 1; j >= 0; j--)
hisi_qm_stop_qp(hisi_zip_ctx->qp_ctx[j].qp);
return ret;
}
- hisi_zip_ctx->qp_ctx[i].zip_dev = hisi_zip;
- }
-
- return 0;
-}
-
-static void hisi_zip_ctx_exit(struct hisi_zip_ctx *hisi_zip_ctx)
-{
- int i;
-
- for (i = 1; i >= 0; i--)
- hisi_zip_release_qp(&hisi_zip_ctx->qp_ctx[i]);
-}
-
-static u16 get_extra_field_size(const u8 *start)
-{
- return *((u16 *)start) + GZIP_HEAD_FEXTRA_XLEN;
-}
-
-static u32 get_name_field_size(const u8 *start)
-{
- return strlen(start) + 1;
-}
+ qp_ctx->zip_dev = hisi_zip;
+ }
-static u32 get_comment_field_size(const u8 *start)
-{
- return strlen(start) + 1;
+ if (hisi_zip->qm.ver < QM_HW_V3)
+ hisi_zip_ctx->ops = &hisi_zip_ops_v1;
+ else
+ hisi_zip_ctx->ops = &hisi_zip_ops_v2;
+
+ return 0;
}
-static u32 __get_gzip_head_size(const u8 *src)
+static void hisi_zip_ctx_exit(struct hisi_zip_ctx *hisi_zip_ctx)
{
- u8 head_flg = *(src + GZIP_HEAD_FLG_SHIFT);
- u32 size = GZIP_HEAD_FEXTRA_SHIFT;
-
- if (head_flg & GZIP_HEAD_FEXTRA_BIT)
- size += get_extra_field_size(src + size);
- if (head_flg & GZIP_HEAD_FNAME_BIT)
- size += get_name_field_size(src + size);
- if (head_flg & GZIP_HEAD_FCOMMENT_BIT)
- size += get_comment_field_size(src + size);
- if (head_flg & GZIP_HEAD_FHCRC_BIT)
- size += GZIP_HEAD_FHCRC_SIZE;
+ int i;
- return size;
+ for (i = 1; i >= 0; i--)
+ hisi_zip_release_qp(&hisi_zip_ctx->qp_ctx[i]);
}
static int hisi_zip_create_req_q(struct hisi_zip_ctx *ctx)
ctx->qp_ctx[i].sgl_pool);
}
-static void hisi_zip_remove_req(struct hisi_zip_qp_ctx *qp_ctx,
- struct hisi_zip_req *req)
-{
- struct hisi_zip_req_q *req_q = &qp_ctx->req_q;
-
- write_lock(&req_q->req_lock);
- clear_bit(req->req_id, req_q->req_bitmap);
- memset(req, 0, sizeof(struct hisi_zip_req));
- write_unlock(&req_q->req_lock);
-}
-
-static void hisi_zip_acomp_cb(struct hisi_qp *qp, void *data)
-{
- struct hisi_zip_sqe *sqe = data;
- struct hisi_zip_qp_ctx *qp_ctx = qp->qp_ctx;
- struct hisi_zip_dfx *dfx = &qp_ctx->zip_dev->dfx;
- struct hisi_zip_req_q *req_q = &qp_ctx->req_q;
- struct hisi_zip_req *req = req_q->q + sqe->tag;
- struct acomp_req *acomp_req = req->req;
- struct device *dev = &qp->qm->pdev->dev;
- u32 status, dlen, head_size;
- int err = 0;
-
- atomic64_inc(&dfx->recv_cnt);
- status = sqe->dw3 & HZIP_BD_STATUS_M;
- if (status != 0 && status != HZIP_NC_ERR) {
- dev_err(dev, "%scompress fail in qp%u: %u, output: %u\n",
- (qp->alg_type == 0) ? "" : "de", qp->qp_id, status,
- sqe->produced);
- atomic64_inc(&dfx->err_bd_cnt);
- err = -EIO;
- }
- dlen = sqe->produced;
-
- hisi_acc_sg_buf_unmap(dev, acomp_req->src, req->hw_src);
- hisi_acc_sg_buf_unmap(dev, acomp_req->dst, req->hw_dst);
-
- head_size = (qp->alg_type == 0) ? TO_HEAD_SIZE(qp->req_type) : 0;
- acomp_req->dlen = dlen + head_size;
-
- if (acomp_req->base.complete)
- acomp_request_complete(acomp_req, err);
-
- hisi_zip_remove_req(qp_ctx, req);
-}
-
static void hisi_zip_set_acomp_cb(struct hisi_zip_ctx *ctx,
void (*fn)(struct hisi_qp *, void *))
{
hisi_zip_ctx_exit(ctx);
}
-static int add_comp_head(struct scatterlist *dst, u8 req_type)
-{
- int head_size = TO_HEAD_SIZE(req_type);
- const u8 *head = TO_HEAD(req_type);
- int ret;
-
- ret = sg_copy_from_buffer(dst, sg_nents(dst), head, head_size);
- if (ret != head_size) {
- pr_err("the head size of buffer is wrong (%d)!\n", ret);
- return -ENOMEM;
- }
-
- return head_size;
-}
-
-static size_t __maybe_unused get_gzip_head_size(struct scatterlist *sgl)
-{
- char buf[HZIP_GZIP_HEAD_BUF];
-
- sg_copy_to_buffer(sgl, sg_nents(sgl), buf, sizeof(buf));
-
- return __get_gzip_head_size(buf);
-}
-
-static int get_comp_head_size(struct acomp_req *acomp_req, u8 req_type)
-{
- if (!acomp_req->src || !acomp_req->slen)
- return -EINVAL;
-
- if ((req_type == HZIP_ALG_TYPE_GZIP) &&
- (acomp_req->slen < GZIP_HEAD_FEXTRA_SHIFT))
- return -EINVAL;
-
- switch (req_type) {
- case HZIP_ALG_TYPE_ZLIB:
- return TO_HEAD_SIZE(HZIP_ALG_TYPE_ZLIB);
- case HZIP_ALG_TYPE_GZIP:
- return TO_HEAD_SIZE(HZIP_ALG_TYPE_GZIP);
- default:
- pr_err("request type does not support!\n");
- return -EINVAL;
- }
-}
-
-static struct hisi_zip_req *hisi_zip_create_req(struct acomp_req *req,
- struct hisi_zip_qp_ctx *qp_ctx,
- size_t head_size, bool is_comp)
-{
- struct hisi_zip_req_q *req_q = &qp_ctx->req_q;
- struct hisi_zip_req *q = req_q->q;
- struct hisi_zip_req *req_cache;
- int req_id;
-
- write_lock(&req_q->req_lock);
-
- req_id = find_first_zero_bit(req_q->req_bitmap, req_q->size);
- if (req_id >= req_q->size) {
- write_unlock(&req_q->req_lock);
- dev_dbg(&qp_ctx->qp->qm->pdev->dev, "req cache is full!\n");
- return ERR_PTR(-EAGAIN);
- }
- set_bit(req_id, req_q->req_bitmap);
-
- req_cache = q + req_id;
- req_cache->req_id = req_id;
- req_cache->req = req;
-
- if (is_comp) {
- req_cache->sskip = 0;
- req_cache->dskip = head_size;
- } else {
- req_cache->sskip = head_size;
- req_cache->dskip = 0;
- }
-
- write_unlock(&req_q->req_lock);
-
- return req_cache;
-}
-
-static int hisi_zip_do_work(struct hisi_zip_req *req,
- struct hisi_zip_qp_ctx *qp_ctx)
-{
- struct acomp_req *a_req = req->req;
- struct hisi_qp *qp = qp_ctx->qp;
- struct device *dev = &qp->qm->pdev->dev;
- struct hisi_acc_sgl_pool *pool = qp_ctx->sgl_pool;
- struct hisi_zip_dfx *dfx = &qp_ctx->zip_dev->dfx;
- struct hisi_zip_sqe zip_sqe;
- dma_addr_t input, output;
- int ret;
-
- if (!a_req->src || !a_req->slen || !a_req->dst || !a_req->dlen)
- return -EINVAL;
-
- req->hw_src = hisi_acc_sg_buf_map_to_hw_sgl(dev, a_req->src, pool,
- req->req_id << 1, &input);
- if (IS_ERR(req->hw_src)) {
- dev_err(dev, "failed to map the src buffer to hw sgl (%ld)!\n",
- PTR_ERR(req->hw_src));
- return PTR_ERR(req->hw_src);
- }
- req->dma_src = input;
-
- req->hw_dst = hisi_acc_sg_buf_map_to_hw_sgl(dev, a_req->dst, pool,
- (req->req_id << 1) + 1,
- &output);
- if (IS_ERR(req->hw_dst)) {
- ret = PTR_ERR(req->hw_dst);
- dev_err(dev, "failed to map the dst buffer to hw slg (%d)!\n",
- ret);
- goto err_unmap_input;
- }
- req->dma_dst = output;
-
- hisi_zip_fill_sqe(&zip_sqe, qp->req_type, input, output, a_req->slen,
- a_req->dlen, req->sskip, req->dskip);
- hisi_zip_config_buf_type(&zip_sqe, HZIP_SGL);
- hisi_zip_config_tag(&zip_sqe, req->req_id);
-
- /* send command to start a task */
- atomic64_inc(&dfx->send_cnt);
- ret = hisi_qp_send(qp, &zip_sqe);
- if (ret < 0) {
- atomic64_inc(&dfx->send_busy_cnt);
- ret = -EAGAIN;
- dev_dbg_ratelimited(dev, "failed to send request!\n");
- goto err_unmap_output;
- }
-
- return -EINPROGRESS;
-
-err_unmap_output:
- hisi_acc_sg_buf_unmap(dev, a_req->dst, req->hw_dst);
-err_unmap_input:
- hisi_acc_sg_buf_unmap(dev, a_req->src, req->hw_src);
- return ret;
-}
-
-static int hisi_zip_acompress(struct acomp_req *acomp_req)
-{
- struct hisi_zip_ctx *ctx = crypto_tfm_ctx(acomp_req->base.tfm);
- struct hisi_zip_qp_ctx *qp_ctx = &ctx->qp_ctx[HZIP_QPC_COMP];
- struct device *dev = &qp_ctx->qp->qm->pdev->dev;
- struct hisi_zip_req *req;
- int head_size;
- int ret;
-
- /* let's output compression head now */
- head_size = add_comp_head(acomp_req->dst, qp_ctx->qp->req_type);
- if (head_size < 0) {
- dev_err_ratelimited(dev, "failed to add comp head (%d)!\n",
- head_size);
- return head_size;
- }
-
- req = hisi_zip_create_req(acomp_req, qp_ctx, head_size, true);
- if (IS_ERR(req))
- return PTR_ERR(req);
-
- ret = hisi_zip_do_work(req, qp_ctx);
- if (ret != -EINPROGRESS) {
- dev_info_ratelimited(dev, "failed to do compress (%d)!\n", ret);
- hisi_zip_remove_req(qp_ctx, req);
- }
-
- return ret;
-}
-
-static int hisi_zip_adecompress(struct acomp_req *acomp_req)
-{
- struct hisi_zip_ctx *ctx = crypto_tfm_ctx(acomp_req->base.tfm);
- struct hisi_zip_qp_ctx *qp_ctx = &ctx->qp_ctx[HZIP_QPC_DECOMP];
- struct device *dev = &qp_ctx->qp->qm->pdev->dev;
- struct hisi_zip_req *req;
- int head_size, ret;
-
- head_size = get_comp_head_size(acomp_req, qp_ctx->qp->req_type);
- if (head_size < 0) {
- dev_err_ratelimited(dev, "failed to get comp head size (%d)!\n",
- head_size);
- return head_size;
- }
-
- req = hisi_zip_create_req(acomp_req, qp_ctx, head_size, false);
- if (IS_ERR(req))
- return PTR_ERR(req);
-
- ret = hisi_zip_do_work(req, qp_ctx);
- if (ret != -EINPROGRESS) {
- dev_info_ratelimited(dev, "failed to do decompress (%d)!\n",
- ret);
- hisi_zip_remove_req(qp_ctx, req);
- }
-
- return ret;
-}
-
static struct acomp_alg hisi_zip_acomp_zlib = {
.init = hisi_zip_acomp_init,
.exit = hisi_zip_acomp_exit,
}
};
-int hisi_zip_register_to_crypto(void)
+int hisi_zip_register_to_crypto(struct hisi_qm *qm)
{
int ret;
return ret;
}
-void hisi_zip_unregister_from_crypto(void)
+void hisi_zip_unregister_from_crypto(struct hisi_qm *qm)
{
crypto_unregister_acomp(&hisi_zip_acomp_gzip);
crypto_unregister_acomp(&hisi_zip_acomp_zlib);
#define PCI_DEVICE_ID_ZIP_VF 0xa251
#define HZIP_QUEUE_NUM_V1 4096
-#define HZIP_QUEUE_NUM_V2 1024
#define HZIP_CLOCK_GATE_CTRL 0x301004
#define COMP0_ENABLE BIT(0)
#define HZIP_CORE_INT_RAS_CE_ENABLE 0x1
#define HZIP_CORE_INT_RAS_NFE_ENB 0x301164
#define HZIP_CORE_INT_RAS_FE_ENB 0x301168
-#define HZIP_CORE_INT_RAS_NFE_ENABLE 0x7FE
+#define HZIP_CORE_INT_RAS_NFE_ENABLE 0x1FFE
#define HZIP_SRAM_ECC_ERR_NUM_SHIFT 16
#define HZIP_SRAM_ECC_ERR_ADDR_SHIFT 24
-#define HZIP_CORE_INT_MASK_ALL GENMASK(10, 0)
+#define HZIP_CORE_INT_MASK_ALL GENMASK(12, 0)
#define HZIP_COMP_CORE_NUM 2
#define HZIP_DECOMP_CORE_NUM 6
#define HZIP_CORE_NUM (HZIP_COMP_CORE_NUM + \
{ .int_msk = BIT(8), .msg = "zip_com_inf_err" },
{ .int_msk = BIT(9), .msg = "zip_enc_inf_err" },
{ .int_msk = BIT(10), .msg = "zip_pre_out_err" },
+ { .int_msk = BIT(11), .msg = "zip_axi_poison_err" },
+ { .int_msk = BIT(12), .msg = "zip_sva_err" },
{ /* sentinel */ }
};
enum ctrl_debug_file_index {
- HZIP_CURRENT_QM,
HZIP_CLEAR_ENABLE,
HZIP_DEBUG_FILE_NUM,
};
static const char * const ctrl_debug_file_name[] = {
- [HZIP_CURRENT_QM] = "current_qm",
[HZIP_CLEAR_ENABLE] = "clear_enable",
};
return &hisi_zip->qm;
}
-static u32 current_qm_read(struct ctrl_debug_file *file)
-{
- struct hisi_qm *qm = file_to_qm(file);
-
- return readl(qm->io_base + QM_DFX_MB_CNT_VF);
-}
-
-static int current_qm_write(struct ctrl_debug_file *file, u32 val)
-{
- struct hisi_qm *qm = file_to_qm(file);
- u32 vfq_num;
- u32 tmp;
-
- if (val > qm->vfs_num)
- return -EINVAL;
-
- /* According PF or VF Dev ID to calculation curr_qm_qp_num and store */
- if (val == 0) {
- qm->debug.curr_qm_qp_num = qm->qp_num;
- } else {
- vfq_num = (qm->ctrl_qp_num - qm->qp_num) / qm->vfs_num;
- if (val == qm->vfs_num)
- qm->debug.curr_qm_qp_num = qm->ctrl_qp_num -
- qm->qp_num - (qm->vfs_num - 1) * vfq_num;
- else
- qm->debug.curr_qm_qp_num = vfq_num;
- }
-
- writel(val, qm->io_base + QM_DFX_MB_CNT_VF);
- writel(val, qm->io_base + QM_DFX_DB_CNT_VF);
-
- tmp = val |
- (readl(qm->io_base + QM_DFX_SQE_CNT_VF_SQN) & CURRENT_Q_MASK);
- writel(tmp, qm->io_base + QM_DFX_SQE_CNT_VF_SQN);
-
- tmp = val |
- (readl(qm->io_base + QM_DFX_CQE_CNT_VF_CQN) & CURRENT_Q_MASK);
- writel(tmp, qm->io_base + QM_DFX_CQE_CNT_VF_CQN);
-
- return 0;
-}
-
static u32 clear_enable_read(struct ctrl_debug_file *file)
{
struct hisi_qm *qm = file_to_qm(file);
spin_lock_irq(&file->lock);
switch (file->index) {
- case HZIP_CURRENT_QM:
- val = current_qm_read(file);
- break;
case HZIP_CLEAR_ENABLE:
val = clear_enable_read(file);
break;
spin_lock_irq(&file->lock);
switch (file->index) {
- case HZIP_CURRENT_QM:
- ret = current_qm_write(file, val);
- if (ret)
- goto err_input;
- break;
case HZIP_CLEAR_ENABLE:
ret = clear_enable_write(file, val);
if (ret)
struct hisi_zip *zip = container_of(qm, struct hisi_zip, qm);
int i;
- for (i = HZIP_CURRENT_QM; i < HZIP_DEBUG_FILE_NUM; i++) {
+ for (i = HZIP_CLEAR_ENABLE; i < HZIP_DEBUG_FILE_NUM; i++) {
spin_lock_init(&zip->ctrl->files[i].lock);
zip->ctrl->files[i].ctrl = zip->ctrl;
zip->ctrl->files[i].index = i;
{
int i, j;
- /* clear current_qm */
- writel(0x0, qm->io_base + QM_DFX_MB_CNT_VF);
- writel(0x0, qm->io_base + QM_DFX_DB_CNT_VF);
-
/* enable register read_clear bit */
writel(HZIP_RD_CNT_CLR_CE_EN, qm->io_base + HZIP_SOFT_CTRL_CNT_CLR_CE);
for (i = 0; i < ARRAY_SIZE(core_offsets); i++)
qm->io_base + HZIP_CORE_INT_SET);
}
+static void hisi_zip_err_info_init(struct hisi_qm *qm)
+{
+ struct hisi_qm_err_info *err_info = &qm->err_info;
+
+ err_info->ce = QM_BASE_CE;
+ err_info->fe = 0;
+ err_info->ecc_2bits_mask = HZIP_CORE_INT_STATUS_M_ECC;
+ err_info->dev_ce_mask = HZIP_CORE_INT_RAS_CE_ENABLE;
+ err_info->msi_wr_port = HZIP_WR_PORT;
+ err_info->acpi_rst = "ZRST";
+ err_info->nfe = QM_BASE_NFE | QM_ACC_WB_NOT_READY_TIMEOUT;
+
+ if (qm->ver >= QM_HW_V3)
+ err_info->nfe |= QM_ACC_DO_TASK_TIMEOUT;
+}
+
static const struct hisi_qm_err_ini hisi_zip_err_ini = {
.hw_init = hisi_zip_set_user_domain_and_cache,
.hw_err_enable = hisi_zip_hw_error_enable,
.log_dev_hw_err = hisi_zip_log_hw_error,
.open_axi_master_ooo = hisi_zip_open_axi_master_ooo,
.close_axi_master_ooo = hisi_zip_close_axi_master_ooo,
- .err_info = {
- .ce = QM_BASE_CE,
- .nfe = QM_BASE_NFE |
- QM_ACC_WB_NOT_READY_TIMEOUT,
- .fe = 0,
- .ecc_2bits_mask = HZIP_CORE_INT_STATUS_M_ECC,
- .dev_ce_mask = HZIP_CORE_INT_RAS_CE_ENABLE,
- .msi_wr_port = HZIP_WR_PORT,
- .acpi_rst = "ZRST",
- }
+ .err_info_init = hisi_zip_err_info_init,
};
static int hisi_zip_pf_probe_init(struct hisi_zip *hisi_zip)
hisi_zip->ctrl = ctrl;
ctrl->hisi_zip = hisi_zip;
-
- if (qm->ver == QM_HW_V1)
- qm->ctrl_qp_num = HZIP_QUEUE_NUM_V1;
- else
- qm->ctrl_qp_num = HZIP_QUEUE_NUM_V2;
-
qm->err_ini = &hisi_zip_err_ini;
+ qm->err_ini->err_info_init(qm);
hisi_zip_set_user_domain_and_cache(qm);
hisi_qm_dev_err_init(qm);
hdev->io_base = devm_platform_ioremap_resource(pdev, 0);
if (IS_ERR(hdev->io_base)) {
err = PTR_ERR(hdev->io_base);
- dev_err(dev, "can't ioremap, returned %d\n", err);
-
goto res_err;
}
hash_res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
hdev->cpu_addr = devm_ioremap_resource(dev, hash_res);
if (IS_ERR(hdev->cpu_addr)) {
- dev_err(dev, "can't ioremap write port\n");
err = PTR_ERR(hdev->cpu_addr);
goto res_err;
}
/* Leave the DSE threads reset state */
writel(0, EIP197_HIA_DSE_THR(priv) + EIP197_HIA_DSE_THR_CTRL(pe));
- /* Configure the procesing engine thresholds */
+ /* Configure the processing engine thresholds */
writel(EIP197_PE_OUT_DBUF_THRES_MIN(opbuflo) |
EIP197_PE_OUT_DBUF_THRES_MAX(opbufhi),
EIP197_PE(priv) + EIP197_PE_OUT_DBUF_THRES(pe));
return 0;
}
-static spinlock_t desc_lock;
+static DEFINE_SPINLOCK(desc_lock);
static struct crypt_ctl *get_crypt_desc(void)
{
int i;
}
}
-static spinlock_t emerg_lock;
+static DEFINE_SPINLOCK(emerg_lock);
static struct crypt_ctl *get_crypt_desc_emerg(void)
{
int i;
if (IS_ERR(pdev))
return PTR_ERR(pdev);
- spin_lock_init(&desc_lock);
- spin_lock_init(&emerg_lock);
-
err = init_ixp_crypto(&pdev->dev);
if (err) {
platform_device_unregister(pdev);
}
aes_dev->base_reg = devm_ioremap_resource(&pdev->dev, aes_mem);
- if (IS_ERR(aes_dev->base_reg)) {
- dev_err(dev, "Failed to get base address\n");
+ if (IS_ERR(aes_dev->base_reg))
return PTR_ERR(aes_dev->base_reg);
- }
/* Get and request IRQ */
aes_dev->irq = platform_get_irq(pdev, 0);
/* Initialize crypto engine */
aes_dev->engine = crypto_engine_alloc_init(dev, true);
- if (!aes_dev->engine)
+ if (!aes_dev->engine) {
+ rc = -ENOMEM;
goto list_del;
+ }
rc = crypto_engine_start(aes_dev->engine);
if (rc) {
}
hcu_dev->io_base = devm_ioremap_resource(dev, hcu_mem);
- if (IS_ERR(hcu_dev->io_base)) {
- dev_err(dev, "Could not io-remap mem resource.\n");
+ if (IS_ERR(hcu_dev->io_base))
return PTR_ERR(hcu_dev->io_base);
- }
init_completion(&hcu_dev->irq_done);
/* Initialize crypto engine */
hcu_dev->engine = crypto_engine_alloc_init(dev, 1);
- if (!hcu_dev->engine)
+ if (!hcu_dev->engine) {
+ rc = -ENOMEM;
goto list_del;
+ }
rc = crypto_engine_start(hcu_dev->engine);
if (rc) {
#define OCS_HCU_WAIT_BUSY_TIMEOUT_US 1000000
/**
- * struct ocs_hcu_dma_list - An entry in an OCS DMA linked list.
+ * struct ocs_hcu_dma_entry - An entry in an OCS DMA linked list.
* @src_addr: Source address of the data.
* @src_len: Length of data to be fetched.
* @nxt_desc: Next descriptor to fetch.
};
/**
- * struct ocs_dma_list - OCS-specific DMA linked list.
+ * struct ocs_hcu_dma_list - OCS-specific DMA linked list.
* @head: The head of the list (points to the array backing the list).
* @tail: The current tail of the list; NULL if the list is empty.
* @dma_addr: The DMA address of @head (i.e., the DMA address of the backing
}
/**
- * ocs_hcu_digest() - Perform a hashing iteration.
+ * ocs_hcu_hash_update() - Perform a hashing iteration.
* @hcu_dev: The OCS HCU device to use.
* @ctx: The OCS HCU hashing context.
* @dma_list: The OCS DMA list mapping the input data to process.
}
/**
- * ocs_hcu_hash_final() - Update and finalize hash computation.
+ * ocs_hcu_hash_finup() - Update and finalize hash computation.
* @hcu_dev: The OCS HCU device to use.
* @ctx: The OCS HCU hashing context.
* @dma_list: The OCS DMA list mapping the input data to process.
int otx2_cpt_send_af_reg_requests(struct otx2_mbox *mbox,
struct pci_dev *pdev);
-int otx2_cpt_add_read_af_reg(struct otx2_mbox *mbox,
- struct pci_dev *pdev, u64 reg, u64 *val);
+int otx2_cpt_add_read_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev,
+ u64 reg, u64 *val, int blkaddr);
int otx2_cpt_add_write_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev,
- u64 reg, u64 val);
+ u64 reg, u64 val, int blkaddr);
int otx2_cpt_read_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev,
- u64 reg, u64 *val);
+ u64 reg, u64 *val, int blkaddr);
int otx2_cpt_write_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev,
- u64 reg, u64 val);
+ u64 reg, u64 val, int blkaddr);
struct otx2_cptlfs_info;
int otx2_cpt_attach_rscrs_msg(struct otx2_cptlfs_info *lfs);
int otx2_cpt_detach_rsrcs_msg(struct otx2_cptlfs_info *lfs);
}
int otx2_cpt_add_read_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev,
- u64 reg, u64 *val)
+ u64 reg, u64 *val, int blkaddr)
{
struct cpt_rd_wr_reg_msg *reg_msg;
reg_msg->is_write = 0;
reg_msg->reg_offset = reg;
reg_msg->ret_val = val;
+ reg_msg->blkaddr = blkaddr;
return 0;
}
int otx2_cpt_add_write_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev,
- u64 reg, u64 val)
+ u64 reg, u64 val, int blkaddr)
{
struct cpt_rd_wr_reg_msg *reg_msg;
reg_msg->is_write = 1;
reg_msg->reg_offset = reg;
reg_msg->val = val;
+ reg_msg->blkaddr = blkaddr;
return 0;
}
int otx2_cpt_read_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev,
- u64 reg, u64 *val)
+ u64 reg, u64 *val, int blkaddr)
{
int ret;
- ret = otx2_cpt_add_read_af_reg(mbox, pdev, reg, val);
+ ret = otx2_cpt_add_read_af_reg(mbox, pdev, reg, val, blkaddr);
if (ret)
return ret;
}
int otx2_cpt_write_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev,
- u64 reg, u64 val)
+ u64 reg, u64 val, int blkaddr)
{
int ret;
- ret = otx2_cpt_add_write_af_reg(mbox, pdev, reg, val);
+ ret = otx2_cpt_add_write_af_reg(mbox, pdev, reg, val, blkaddr);
if (ret)
return ret;
ret = otx2_cpt_read_af_reg(lfs->mbox, lfs->pdev,
CPT_AF_LFX_CTL(lf->slot),
- &lf_ctrl.u);
+ &lf_ctrl.u, lfs->blkaddr);
if (ret)
return ret;
ret = otx2_cpt_write_af_reg(lfs->mbox, lfs->pdev,
CPT_AF_LFX_CTL(lf->slot),
- lf_ctrl.u);
+ lf_ctrl.u, lfs->blkaddr);
return ret;
}
ret = otx2_cpt_read_af_reg(lfs->mbox, lfs->pdev,
CPT_AF_LFX_CTL(lf->slot),
- &lf_ctrl.u);
+ &lf_ctrl.u, lfs->blkaddr);
if (ret)
return ret;
ret = otx2_cpt_write_af_reg(lfs->mbox, lfs->pdev,
CPT_AF_LFX_CTL(lf->slot),
- lf_ctrl.u);
+ lf_ctrl.u, lfs->blkaddr);
return ret;
}
u8 kcrypto_eng_grp_num; /* Kernel crypto engine group number */
u8 kvf_limits; /* Kernel crypto limits */
atomic_t state; /* LF's state. started/reset */
+ int blkaddr; /* CPT blkaddr: BLKADDR_CPT0/BLKADDR_CPT1 */
};
static inline void otx2_cpt_free_instruction_queues(
u8 max_vfs; /* Maximum number of VFs supported by CPT */
u8 enabled_vfs; /* Number of enabled VFs */
u8 kvf_limits; /* Kernel crypto limits */
+ bool has_cpt1;
};
irqreturn_t otx2_cptpf_afpf_mbox_intr(int irq, void *arg);
return 0;
}
-static int cptpf_device_reset(struct otx2_cptpf_dev *cptpf)
+static int cptx_device_reset(struct otx2_cptpf_dev *cptpf, int blkaddr)
{
int timeout = 10, ret;
u64 reg = 0;
ret = otx2_cpt_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev,
- CPT_AF_BLK_RST, 0x1);
+ CPT_AF_BLK_RST, 0x1, blkaddr);
if (ret)
return ret;
do {
ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox, cptpf->pdev,
- CPT_AF_BLK_RST, ®);
+ CPT_AF_BLK_RST, ®, blkaddr);
if (ret)
return ret;
return ret;
}
+static int cptpf_device_reset(struct otx2_cptpf_dev *cptpf)
+{
+ int ret = 0;
+
+ if (cptpf->has_cpt1) {
+ ret = cptx_device_reset(cptpf, BLKADDR_CPT1);
+ if (ret)
+ return ret;
+ }
+ return cptx_device_reset(cptpf, BLKADDR_CPT0);
+}
+
+static void cptpf_check_block_implemented(struct otx2_cptpf_dev *cptpf)
+{
+ u64 cfg;
+
+ cfg = otx2_cpt_read64(cptpf->reg_base, BLKADDR_RVUM, 0,
+ RVU_PF_BLOCK_ADDRX_DISC(BLKADDR_CPT1));
+ if (cfg & BIT_ULL(11))
+ cptpf->has_cpt1 = true;
+}
+
static int cptpf_device_init(struct otx2_cptpf_dev *cptpf)
{
union otx2_cptx_af_constants1 af_cnsts1 = {0};
int ret = 0;
+ /* check if 'implemented' bit is set for block BLKADDR_CPT1 */
+ cptpf_check_block_implemented(cptpf);
/* Reset the CPT PF device */
ret = cptpf_device_reset(cptpf);
if (ret)
/* Get number of SE, IE and AE engines */
ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox, cptpf->pdev,
- CPT_AF_CONSTANTS1, &af_cnsts1.u);
+ CPT_AF_CONSTANTS1, &af_cnsts1.u,
+ BLKADDR_CPT0);
if (ret)
return ret;
}
static int __write_ucode_base(struct otx2_cptpf_dev *cptpf, int eng,
- dma_addr_t dma_addr)
+ dma_addr_t dma_addr, int blkaddr)
{
return otx2_cpt_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev,
CPT_AF_EXEX_UCODE_BASE(eng),
- (u64)dma_addr);
+ (u64)dma_addr, blkaddr);
}
-static int cpt_set_ucode_base(struct otx2_cpt_eng_grp_info *eng_grp, void *obj)
+static int cptx_set_ucode_base(struct otx2_cpt_eng_grp_info *eng_grp,
+ struct otx2_cptpf_dev *cptpf, int blkaddr)
{
- struct otx2_cptpf_dev *cptpf = obj;
struct otx2_cpt_engs_rsvd *engs;
dma_addr_t dma_addr;
int i, bit, ret;
/* Set PF number for microcode fetches */
ret = otx2_cpt_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev,
CPT_AF_PF_FUNC,
- cptpf->pf_id << RVU_PFVF_PF_SHIFT);
+ cptpf->pf_id << RVU_PFVF_PF_SHIFT, blkaddr);
if (ret)
return ret;
*/
for_each_set_bit(bit, engs->bmap, eng_grp->g->engs_num)
if (!eng_grp->g->eng_ref_cnt[bit]) {
- ret = __write_ucode_base(cptpf, bit, dma_addr);
+ ret = __write_ucode_base(cptpf, bit, dma_addr,
+ blkaddr);
if (ret)
return ret;
}
return 0;
}
-static int cpt_detach_and_disable_cores(struct otx2_cpt_eng_grp_info *eng_grp,
- void *obj)
+static int cpt_set_ucode_base(struct otx2_cpt_eng_grp_info *eng_grp, void *obj)
{
struct otx2_cptpf_dev *cptpf = obj;
- struct otx2_cpt_bitmap bmap;
+ int ret;
+
+ if (cptpf->has_cpt1) {
+ ret = cptx_set_ucode_base(eng_grp, cptpf, BLKADDR_CPT1);
+ if (ret)
+ return ret;
+ }
+ return cptx_set_ucode_base(eng_grp, cptpf, BLKADDR_CPT0);
+}
+
+static int cptx_detach_and_disable_cores(struct otx2_cpt_eng_grp_info *eng_grp,
+ struct otx2_cptpf_dev *cptpf,
+ struct otx2_cpt_bitmap bmap,
+ int blkaddr)
+{
int i, timeout = 10;
int busy, ret;
u64 reg = 0;
- bmap = get_cores_bmap(&cptpf->pdev->dev, eng_grp);
- if (!bmap.size)
- return -EINVAL;
-
/* Detach the cores from group */
for_each_set_bit(i, bmap.bits, bmap.size) {
ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox, cptpf->pdev,
- CPT_AF_EXEX_CTL2(i), ®);
+ CPT_AF_EXEX_CTL2(i), ®, blkaddr);
if (ret)
return ret;
ret = otx2_cpt_write_af_reg(&cptpf->afpf_mbox,
cptpf->pdev,
- CPT_AF_EXEX_CTL2(i), reg);
+ CPT_AF_EXEX_CTL2(i), reg,
+ blkaddr);
if (ret)
return ret;
}
for_each_set_bit(i, bmap.bits, bmap.size) {
ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox,
cptpf->pdev,
- CPT_AF_EXEX_STS(i), ®);
+ CPT_AF_EXEX_STS(i), ®,
+ blkaddr);
if (ret)
return ret;
if (!eng_grp->g->eng_ref_cnt[i]) {
ret = otx2_cpt_write_af_reg(&cptpf->afpf_mbox,
cptpf->pdev,
- CPT_AF_EXEX_CTL(i), 0x0);
+ CPT_AF_EXEX_CTL(i), 0x0,
+ blkaddr);
if (ret)
return ret;
}
return 0;
}
-static int cpt_attach_and_enable_cores(struct otx2_cpt_eng_grp_info *eng_grp,
- void *obj)
+static int cpt_detach_and_disable_cores(struct otx2_cpt_eng_grp_info *eng_grp,
+ void *obj)
{
struct otx2_cptpf_dev *cptpf = obj;
struct otx2_cpt_bitmap bmap;
- u64 reg = 0;
- int i, ret;
+ int ret;
bmap = get_cores_bmap(&cptpf->pdev->dev, eng_grp);
if (!bmap.size)
return -EINVAL;
+ if (cptpf->has_cpt1) {
+ ret = cptx_detach_and_disable_cores(eng_grp, cptpf, bmap,
+ BLKADDR_CPT1);
+ if (ret)
+ return ret;
+ }
+ return cptx_detach_and_disable_cores(eng_grp, cptpf, bmap,
+ BLKADDR_CPT0);
+}
+
+static int cptx_attach_and_enable_cores(struct otx2_cpt_eng_grp_info *eng_grp,
+ struct otx2_cptpf_dev *cptpf,
+ struct otx2_cpt_bitmap bmap,
+ int blkaddr)
+{
+ u64 reg = 0;
+ int i, ret;
+
/* Attach the cores to the group */
for_each_set_bit(i, bmap.bits, bmap.size) {
ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox, cptpf->pdev,
- CPT_AF_EXEX_CTL2(i), ®);
+ CPT_AF_EXEX_CTL2(i), ®, blkaddr);
if (ret)
return ret;
ret = otx2_cpt_write_af_reg(&cptpf->afpf_mbox,
cptpf->pdev,
- CPT_AF_EXEX_CTL2(i), reg);
+ CPT_AF_EXEX_CTL2(i), reg,
+ blkaddr);
if (ret)
return ret;
}
/* Enable the cores */
for_each_set_bit(i, bmap.bits, bmap.size) {
- ret = otx2_cpt_add_write_af_reg(&cptpf->afpf_mbox,
- cptpf->pdev,
- CPT_AF_EXEX_CTL(i), 0x1);
+ ret = otx2_cpt_add_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev,
+ CPT_AF_EXEX_CTL(i), 0x1,
+ blkaddr);
if (ret)
return ret;
}
- ret = otx2_cpt_send_af_reg_requests(&cptpf->afpf_mbox, cptpf->pdev);
+ return otx2_cpt_send_af_reg_requests(&cptpf->afpf_mbox, cptpf->pdev);
+}
- return ret;
+static int cpt_attach_and_enable_cores(struct otx2_cpt_eng_grp_info *eng_grp,
+ void *obj)
+{
+ struct otx2_cptpf_dev *cptpf = obj;
+ struct otx2_cpt_bitmap bmap;
+ int ret;
+
+ bmap = get_cores_bmap(&cptpf->pdev->dev, eng_grp);
+ if (!bmap.size)
+ return -EINVAL;
+
+ if (cptpf->has_cpt1) {
+ ret = cptx_attach_and_enable_cores(eng_grp, cptpf, bmap,
+ BLKADDR_CPT1);
+ if (ret)
+ return ret;
+ }
+ return cptx_attach_and_enable_cores(eng_grp, cptpf, bmap, BLKADDR_CPT0);
}
static int load_fw(struct device *dev, struct fw_info_t *fw_info,
return ret;
}
-int otx2_cpt_disable_all_cores(struct otx2_cptpf_dev *cptpf)
+static int cptx_disable_all_cores(struct otx2_cptpf_dev *cptpf, int total_cores,
+ int blkaddr)
{
- int i, ret, busy, total_cores;
- int timeout = 10;
- u64 reg = 0;
-
- total_cores = cptpf->eng_grps.avail.max_se_cnt +
- cptpf->eng_grps.avail.max_ie_cnt +
- cptpf->eng_grps.avail.max_ae_cnt;
+ int timeout = 10, ret;
+ int i, busy;
+ u64 reg;
/* Disengage the cores from groups */
for (i = 0; i < total_cores; i++) {
ret = otx2_cpt_add_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev,
- CPT_AF_EXEX_CTL2(i), 0x0);
+ CPT_AF_EXEX_CTL2(i), 0x0,
+ blkaddr);
if (ret)
return ret;
for (i = 0; i < total_cores; i++) {
ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox,
cptpf->pdev,
- CPT_AF_EXEX_STS(i), ®);
+ CPT_AF_EXEX_STS(i), ®,
+ blkaddr);
if (ret)
return ret;
/* Disable the cores */
for (i = 0; i < total_cores; i++) {
ret = otx2_cpt_add_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev,
- CPT_AF_EXEX_CTL(i), 0x0);
+ CPT_AF_EXEX_CTL(i), 0x0,
+ blkaddr);
if (ret)
return ret;
}
return otx2_cpt_send_af_reg_requests(&cptpf->afpf_mbox, cptpf->pdev);
}
+int otx2_cpt_disable_all_cores(struct otx2_cptpf_dev *cptpf)
+{
+ int total_cores, ret;
+
+ total_cores = cptpf->eng_grps.avail.max_se_cnt +
+ cptpf->eng_grps.avail.max_ie_cnt +
+ cptpf->eng_grps.avail.max_ae_cnt;
+
+ if (cptpf->has_cpt1) {
+ ret = cptx_disable_all_cores(cptpf, total_cores, BLKADDR_CPT1);
+ if (ret)
+ return ret;
+ }
+ return cptx_disable_all_cores(cptpf, total_cores, BLKADDR_CPT0);
+}
+
void otx2_cpt_cleanup_eng_grps(struct pci_dev *pdev,
struct otx2_cpt_eng_grps *eng_grps)
{
lfs->pdev = pdev;
lfs->reg_base = cptpf->reg_base;
lfs->mbox = &cptpf->afpf_mbox;
+ lfs->blkaddr = BLKADDR_CPT0;
ret = otx2_cptlf_init(&cptpf->lfs, OTX2_CPT_ALL_ENG_GRPS_MASK,
OTX2_CPT_QUEUE_HI_PRIO, 1);
if (ret)
return ret;
}
-static int nx842_remove(struct vio_dev *viodev)
+static void nx842_remove(struct vio_dev *viodev)
{
struct nx842_devdata *old_devdata;
unsigned long flags;
if (old_devdata)
kfree(old_devdata->counters);
kfree(old_devdata);
-
- return 0;
}
static const struct vio_device_id nx842_vio_driver_ids[] = {
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* AES CBC routines supporting the Power 7+ Nest Accelerators driver
*
* Copyright (C) 2011-2012 International Business Machines Inc.
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* AES CCM routines supporting the Power 7+ Nest Accelerators driver
*
* Copyright (C) 2012 International Business Machines Inc.
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* AES CTR routines supporting the Power 7+ Nest Accelerators driver
*
* Copyright (C) 2011-2012 International Business Machines Inc.
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* AES ECB routines supporting the Power 7+ Nest Accelerators driver
*
* Copyright (C) 2011-2012 International Business Machines Inc.
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* AES GCM routines supporting the Power 7+ Nest Accelerators driver
*
* Copyright (C) 2012 International Business Machines Inc.
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* AES XCBC routines supporting the Power 7+ Nest Accelerators driver
*
* Copyright (C) 2011-2012 International Business Machines Inc.
ret = find_nx_device_tree(dn, chip_id, vasid,
NX_CT_GZIP, "ibm,p9-nx-gzip", &ct_gzip);
- if (ret)
+ if (ret) {
+ of_node_put(dn);
return ret;
+ }
}
if (!ct_842 || !ct_gzip) {
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* SHA-256 routines supporting the Power 7+ Nest Accelerators driver
*
* Copyright (C) 2011-2012 International Business Machines Inc.
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* SHA-512 routines supporting the Power 7+ Nest Accelerators driver
*
* Copyright (C) 2011-2012 International Business Machines Inc.
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* Routines supporting the Power 7+ Nest Accelerators driver
*
* Copyright (C) 2011-2012 International Business Machines Inc.
* @sg: sg list head
* @end: sg lisg end
* @delta: is the amount we need to crop in order to bound the list.
- *
+ * @nbytes: length of data in the scatterlists or data length - whichever
+ * is greater.
*/
static long int trim_sg_list(struct nx_sg *sg,
struct nx_sg *end,
return nx_register_algs();
}
-static int nx_remove(struct vio_dev *viodev)
+static void nx_remove(struct vio_dev *viodev)
{
dev_dbg(&viodev->dev, "entering nx_remove for UA 0x%x\n",
viodev->unit_address);
nx_unregister_skcipher(&nx_ecb_aes_alg, NX_FC_AES,
NX_MODE_AES_ECB);
}
-
- return 0;
}
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* debugfs routines supporting the Power 7+ Nest Accelerators driver
*
* Copyright (C) 2011-2012 International Business Machines Inc.
dd->err = 0;
}
- err = pm_runtime_get_sync(dd->dev);
+ err = pm_runtime_resume_and_get(dd->dev);
if (err < 0) {
- pm_runtime_put_noidle(dd->dev);
dev_err(dd->dev, "failed to get sync: %d\n", err);
return err;
}
pm_runtime_set_autosuspend_delay(dev, DEFAULT_AUTOSUSPEND_DELAY);
pm_runtime_enable(dev);
- err = pm_runtime_get_sync(dev);
+ err = pm_runtime_resume_and_get(dev);
if (err < 0) {
dev_err(dev, "%s: failed to get_sync(%d)\n",
__func__, err);
static int omap_aes_resume(struct device *dev)
{
- pm_runtime_get_sync(dev);
+ pm_runtime_resume_and_get(dev);
return 0;
}
#endif
hw_data->uof_get_name = uof_get_name;
hw_data->uof_get_ae_mask = uof_get_ae_mask;
hw_data->set_msix_rttable = set_msix_default_rttable;
+ hw_data->set_ssm_wdtimer = adf_gen4_set_ssm_wdtimer;
adf_gen4_init_hw_csr_ops(&hw_data->csr_ops);
}
hw_data->enable_vf2pf_comms = adf_pf_enable_vf2pf_comms;
hw_data->reset_device = adf_reset_flr;
hw_data->min_iov_compat_ver = ADF_PFVF_COMPATIBILITY_VERSION;
+ hw_data->set_ssm_wdtimer = adf_gen2_set_ssm_wdtimer;
adf_gen2_init_hw_csr_ops(&hw_data->csr_ops);
}
if (ret)
goto out_err_free_reg;
- set_bit(ADF_STATUS_PF_RUNNING, &accel_dev->status);
-
ret = adf_dev_init(accel_dev);
if (ret)
goto out_err_dev_shutdown;
+ set_bit(ADF_STATUS_PF_RUNNING, &accel_dev->status);
+
ret = adf_dev_start(accel_dev);
if (ret)
goto out_err_dev_stop;
hw_data->enable_vf2pf_comms = adf_pf_enable_vf2pf_comms;
hw_data->reset_device = adf_reset_flr;
hw_data->min_iov_compat_ver = ADF_PFVF_COMPATIBILITY_VERSION;
+ hw_data->set_ssm_wdtimer = adf_gen2_set_ssm_wdtimer;
adf_gen2_init_hw_csr_ops(&hw_data->csr_ops);
}
if (ret)
goto out_err_free_reg;
- set_bit(ADF_STATUS_PF_RUNNING, &accel_dev->status);
-
ret = adf_dev_init(accel_dev);
if (ret)
goto out_err_dev_shutdown;
+ set_bit(ADF_STATUS_PF_RUNNING, &accel_dev->status);
+
ret = adf_dev_start(accel_dev);
if (ret)
goto out_err_dev_stop;
void (*configure_iov_threads)(struct adf_accel_dev *accel_dev,
bool enable);
void (*enable_ints)(struct adf_accel_dev *accel_dev);
+ void (*set_ssm_wdtimer)(struct adf_accel_dev *accel_dev);
int (*enable_vf2pf_comms)(struct adf_accel_dev *accel_dev);
void (*reset_device)(struct adf_accel_dev *accel_dev);
void (*set_msix_rttable)(struct adf_accel_dev *accel_dev);
return capabilities;
}
EXPORT_SYMBOL_GPL(adf_gen2_get_accel_cap);
+
+void adf_gen2_set_ssm_wdtimer(struct adf_accel_dev *accel_dev)
+{
+ struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+ u32 timer_val_pke = ADF_SSM_WDT_PKE_DEFAULT_VALUE;
+ u32 timer_val = ADF_SSM_WDT_DEFAULT_VALUE;
+ unsigned long accel_mask = hw_data->accel_mask;
+ void __iomem *pmisc_addr;
+ struct adf_bar *pmisc;
+ int pmisc_id;
+ u32 i = 0;
+
+ pmisc_id = hw_data->get_misc_bar_id(hw_data);
+ pmisc = &GET_BARS(accel_dev)[pmisc_id];
+ pmisc_addr = pmisc->virt_addr;
+
+ /* Configures WDT timers */
+ for_each_set_bit(i, &accel_mask, hw_data->num_accel) {
+ /* Enable WDT for sym and dc */
+ ADF_CSR_WR(pmisc_addr, ADF_SSMWDT(i), timer_val);
+ /* Enable WDT for pke */
+ ADF_CSR_WR(pmisc_addr, ADF_SSMWDTPKE(i), timer_val_pke);
+ }
+}
+EXPORT_SYMBOL_GPL(adf_gen2_set_ssm_wdtimer);
/* Power gating */
#define ADF_POWERGATE_PKE BIT(24)
+/* WDT timers
+ *
+ * Timeout is in cycles. Clock speed may vary across products but this
+ * value should be a few milli-seconds.
+ */
+#define ADF_SSM_WDT_DEFAULT_VALUE 0x200000
+#define ADF_SSM_WDT_PKE_DEFAULT_VALUE 0x2000000
+#define ADF_SSMWDT_OFFSET 0x54
+#define ADF_SSMWDTPKE_OFFSET 0x58
+#define ADF_SSMWDT(i) (ADF_SSMWDT_OFFSET + ((i) * 0x4000))
+#define ADF_SSMWDTPKE(i) (ADF_SSMWDTPKE_OFFSET + ((i) * 0x4000))
+
void adf_gen2_cfg_iov_thds(struct adf_accel_dev *accel_dev, bool enable,
int num_a_regs, int num_b_regs);
void adf_gen2_init_hw_csr_ops(struct adf_hw_csr_ops *csr_ops);
void adf_gen2_get_admin_info(struct admin_info *admin_csrs_info);
void adf_gen2_get_arb_info(struct arb_info *arb_info);
u32 adf_gen2_get_accel_cap(struct adf_accel_dev *accel_dev);
+void adf_gen2_set_ssm_wdtimer(struct adf_accel_dev *accel_dev);
#endif
csr_ops->write_csr_ring_srv_arb_en = write_csr_ring_srv_arb_en;
}
EXPORT_SYMBOL_GPL(adf_gen4_init_hw_csr_ops);
+
+static inline void adf_gen4_unpack_ssm_wdtimer(u64 value, u32 *upper,
+ u32 *lower)
+{
+ *lower = lower_32_bits(value);
+ *upper = upper_32_bits(value);
+}
+
+void adf_gen4_set_ssm_wdtimer(struct adf_accel_dev *accel_dev)
+{
+ struct adf_hw_device_data *hw_data = accel_dev->hw_device;
+ u64 timer_val_pke = ADF_SSM_WDT_PKE_DEFAULT_VALUE;
+ u64 timer_val = ADF_SSM_WDT_DEFAULT_VALUE;
+ u32 ssm_wdt_pke_high = 0;
+ u32 ssm_wdt_pke_low = 0;
+ u32 ssm_wdt_high = 0;
+ u32 ssm_wdt_low = 0;
+ void __iomem *pmisc_addr;
+ struct adf_bar *pmisc;
+ int pmisc_id;
+
+ pmisc_id = hw_data->get_misc_bar_id(hw_data);
+ pmisc = &GET_BARS(accel_dev)[pmisc_id];
+ pmisc_addr = pmisc->virt_addr;
+
+ /* Convert 64bit WDT timer value into 32bit values for
+ * mmio write to 32bit CSRs.
+ */
+ adf_gen4_unpack_ssm_wdtimer(timer_val, &ssm_wdt_high, &ssm_wdt_low);
+ adf_gen4_unpack_ssm_wdtimer(timer_val_pke, &ssm_wdt_pke_high,
+ &ssm_wdt_pke_low);
+
+ /* Enable WDT for sym and dc */
+ ADF_CSR_WR(pmisc_addr, ADF_SSMWDTL_OFFSET, ssm_wdt_low);
+ ADF_CSR_WR(pmisc_addr, ADF_SSMWDTH_OFFSET, ssm_wdt_high);
+ /* Enable WDT for pke */
+ ADF_CSR_WR(pmisc_addr, ADF_SSMWDTPKEL_OFFSET, ssm_wdt_pke_low);
+ ADF_CSR_WR(pmisc_addr, ADF_SSMWDTPKEH_OFFSET, ssm_wdt_pke_high);
+}
+EXPORT_SYMBOL_GPL(adf_gen4_set_ssm_wdtimer);
ADF_RING_BUNDLE_SIZE * (bank) + \
ADF_RING_CSR_RING_SRV_ARB_EN, (value))
-void adf_gen4_init_hw_csr_ops(struct adf_hw_csr_ops *csr_ops);
+/* WDT timers
+ *
+ * Timeout is in cycles. Clock speed may vary across products but this
+ * value should be a few milli-seconds.
+ */
+#define ADF_SSM_WDT_DEFAULT_VALUE 0x200000
+#define ADF_SSM_WDT_PKE_DEFAULT_VALUE 0x8000000
+#define ADF_SSMWDTL_OFFSET 0x54
+#define ADF_SSMWDTH_OFFSET 0x5C
+#define ADF_SSMWDTPKEL_OFFSET 0x58
+#define ADF_SSMWDTPKEH_OFFSET 0x60
+void adf_gen4_set_ssm_wdtimer(struct adf_accel_dev *accel_dev);
+void adf_gen4_init_hw_csr_ops(struct adf_hw_csr_ops *csr_ops);
#endif
return -EFAULT;
}
+ /* Set ssm watch dog timer */
+ if (hw_data->set_ssm_wdtimer)
+ hw_data->set_ssm_wdtimer(accel_dev);
+
list_for_each(list_itr, &service_table) {
service = list_entry(list_itr, struct service_hndl, list);
if (service->event_hld(accel_dev, ADF_EVENT_START)) {
ret = adf_isr_alloc_msix_entry_table(accel_dev);
if (ret)
- return ret;
- if (adf_enable_msix(accel_dev))
goto err_out;
- if (adf_setup_bh(accel_dev))
- goto err_out;
+ ret = adf_enable_msix(accel_dev);
+ if (ret)
+ goto err_free_msix_table;
- if (adf_request_irqs(accel_dev))
- goto err_out;
+ ret = adf_setup_bh(accel_dev);
+ if (ret)
+ goto err_disable_msix;
+
+ ret = adf_request_irqs(accel_dev);
+ if (ret)
+ goto err_cleanup_bh;
return 0;
+
+err_cleanup_bh:
+ adf_cleanup_bh(accel_dev);
+
+err_disable_msix:
+ adf_disable_msix(&accel_dev->accel_pci_dev);
+
+err_free_msix_table:
+ adf_isr_free_msix_entry_table(accel_dev);
+
err_out:
- adf_isr_resource_free(accel_dev);
- return -EFAULT;
+ return ret;
}
EXPORT_SYMBOL_GPL(adf_isr_resource_alloc);
* @msg: Message to send
* @vf_nr: VF number to which the message will be sent
*
- * Function sends a messge from the PF to a VF
+ * Function sends a message from the PF to a VF
*
* Return: 0 on success, error code otherwise.
*/
dev_err(&GET_DEV(accel_dev), "Ring address not aligned\n");
dma_free_coherent(&GET_DEV(accel_dev), ring_size_bytes,
ring->base_addr, ring->dma_addr);
+ ring->base_addr = NULL;
return -EFAULT;
}
* adf_vf2pf_init() - send init msg to PF
* @accel_dev: Pointer to acceleration VF device.
*
- * Function sends an init messge from the VF to a PF
+ * Function sends an init message from the VF to a PF
*
* Return: 0 on success, error code otherwise.
*/
* adf_vf2pf_shutdown() - send shutdown msg to PF
* @accel_dev: Pointer to acceleration VF device.
*
- * Function sends a shutdown messge from the VF to a PF
+ * Function sends a shutdown message from the VF to a PF
*
* Return: void
*/
goto err_out;
if (adf_setup_pf2vf_bh(accel_dev))
- goto err_out;
+ goto err_disable_msi;
if (adf_setup_bh(accel_dev))
- goto err_out;
+ goto err_cleanup_pf2vf_bh;
if (adf_request_msi_irq(accel_dev))
- goto err_out;
+ goto err_cleanup_bh;
return 0;
+
+err_cleanup_bh:
+ adf_cleanup_bh(accel_dev);
+
+err_cleanup_pf2vf_bh:
+ adf_cleanup_pf2vf_bh(accel_dev);
+
+err_disable_msi:
+ adf_disable_msi(accel_dev);
+
err_out:
- adf_vf_isr_resource_free(accel_dev);
return -EFAULT;
}
EXPORT_SYMBOL_GPL(adf_vf_isr_resource_alloc);
int n = sg_nents(sgl);
struct qat_alg_buf_list *bufl;
struct qat_alg_buf_list *buflout = NULL;
- dma_addr_t blp;
- dma_addr_t bloutp = 0;
+ dma_addr_t blp = DMA_MAPPING_ERROR;
+ dma_addr_t bloutp = DMA_MAPPING_ERROR;
struct scatterlist *sg;
size_t sz_out, sz = struct_size(bufl, bufers, n + 1);
if (unlikely(!bufl))
return -ENOMEM;
- blp = dma_map_single(dev, bufl, sz, DMA_TO_DEVICE);
- if (unlikely(dma_mapping_error(dev, blp)))
- goto err_in;
+ for_each_sg(sgl, sg, n, i)
+ bufl->bufers[i].addr = DMA_MAPPING_ERROR;
for_each_sg(sgl, sg, n, i) {
int y = sg_nctr;
sg_nctr++;
}
bufl->num_bufs = sg_nctr;
+ blp = dma_map_single(dev, bufl, sz, DMA_TO_DEVICE);
+ if (unlikely(dma_mapping_error(dev, blp)))
+ goto err_in;
qat_req->buf.bl = bufl;
qat_req->buf.blp = blp;
qat_req->buf.sz = sz;
dev_to_node(&GET_DEV(inst->accel_dev)));
if (unlikely(!buflout))
goto err_in;
- bloutp = dma_map_single(dev, buflout, sz_out, DMA_TO_DEVICE);
- if (unlikely(dma_mapping_error(dev, bloutp)))
- goto err_out;
+
bufers = buflout->bufers;
+ for_each_sg(sglout, sg, n, i)
+ bufers[i].addr = DMA_MAPPING_ERROR;
+
for_each_sg(sglout, sg, n, i) {
int y = sg_nctr;
}
buflout->num_bufs = sg_nctr;
buflout->num_mapped_bufs = sg_nctr;
+ bloutp = dma_map_single(dev, buflout, sz_out, DMA_TO_DEVICE);
+ if (unlikely(dma_mapping_error(dev, bloutp)))
+ goto err_out;
qat_req->buf.blout = buflout;
qat_req->buf.bloutp = bloutp;
qat_req->buf.sz_out = sz_out;
return 0;
err_out:
+ if (!dma_mapping_error(dev, bloutp))
+ dma_unmap_single(dev, bloutp, sz_out, DMA_TO_DEVICE);
+
n = sg_nents(sglout);
for (i = 0; i < n; i++)
if (!dma_mapping_error(dev, buflout->bufers[i].addr))
dma_unmap_single(dev, buflout->bufers[i].addr,
buflout->bufers[i].len,
DMA_BIDIRECTIONAL);
- if (!dma_mapping_error(dev, bloutp))
- dma_unmap_single(dev, bloutp, sz_out, DMA_TO_DEVICE);
kfree(buflout);
err_in:
+ if (!dma_mapping_error(dev, blp))
+ dma_unmap_single(dev, blp, sz, DMA_TO_DEVICE);
+
n = sg_nents(sgl);
for (i = 0; i < n; i++)
if (!dma_mapping_error(dev, bufl->bufers[i].addr))
bufl->bufers[i].len,
DMA_BIDIRECTIONAL);
- if (!dma_mapping_error(dev, blp))
- dma_unmap_single(dev, blp, sz, DMA_TO_DEVICE);
kfree(bufl);
dev_err(dev, "Failed to map buf for dma\n");
if (ret)
goto out_err_free_reg;
- set_bit(ADF_STATUS_PF_RUNNING, &accel_dev->status);
-
ret = adf_dev_init(accel_dev);
if (ret)
goto out_err_dev_shutdown;
+ set_bit(ADF_STATUS_PF_RUNNING, &accel_dev->status);
+
ret = adf_dev_start(accel_dev);
if (ret)
goto out_err_dev_stop;
struct scatterlist result_sg;
struct sg_table dst_tbl;
struct scatterlist *dst_sg;
- struct sg_table src_tbl;
struct scatterlist *src_sg;
unsigned int cryptlen;
struct skcipher_request fallback_req; // keep at the end
return cfg;
}
-static int qce_setup_regs_ahash(struct crypto_async_request *async_req,
- u32 totallen, u32 offset)
+static int qce_setup_regs_ahash(struct crypto_async_request *async_req)
{
struct ahash_request *req = ahash_request_cast(async_req);
struct crypto_ahash *ahash = __crypto_ahash_cast(async_req->tfm);
{
u32 xtskey[QCE_MAX_CIPHER_KEY_SIZE / sizeof(u32)] = {0};
unsigned int xtsklen = enckeylen / (2 * sizeof(u32));
- unsigned int xtsdusize;
qce_cpu_to_be32p_array((__be32 *)xtskey, enckey + enckeylen / 2,
enckeylen / 2);
qce_write_array(qce, REG_ENCR_XTS_KEY0, xtskey, xtsklen);
- /* xts du size 512B */
- xtsdusize = min_t(u32, QCE_SECTOR_SIZE, cryptlen);
- qce_write(qce, REG_ENCR_XTS_DU_SIZE, xtsdusize);
+ /* Set data unit size to cryptlen. Anything else causes
+ * crypto engine to return back incorrect results.
+ */
+ qce_write(qce, REG_ENCR_XTS_DU_SIZE, cryptlen);
}
-static int qce_setup_regs_skcipher(struct crypto_async_request *async_req,
- u32 totallen, u32 offset)
+static int qce_setup_regs_skcipher(struct crypto_async_request *async_req)
{
struct skcipher_request *req = skcipher_request_cast(async_req);
struct qce_cipher_reqctx *rctx = skcipher_request_ctx(req);
qce_write(qce, REG_ENCR_SEG_CFG, encr_cfg);
qce_write(qce, REG_ENCR_SEG_SIZE, rctx->cryptlen);
- qce_write(qce, REG_ENCR_SEG_START, offset & 0xffff);
+ qce_write(qce, REG_ENCR_SEG_START, 0);
if (IS_CTR(flags)) {
qce_write(qce, REG_CNTR_MASK, ~0);
qce_write(qce, REG_CNTR_MASK2, ~0);
}
- qce_write(qce, REG_SEG_SIZE, totallen);
+ qce_write(qce, REG_SEG_SIZE, rctx->cryptlen);
/* get little endianness */
config = qce_config_reg(qce, 1);
}
#endif
-int qce_start(struct crypto_async_request *async_req, u32 type, u32 totallen,
- u32 offset)
+int qce_start(struct crypto_async_request *async_req, u32 type)
{
switch (type) {
#ifdef CONFIG_CRYPTO_DEV_QCE_SKCIPHER
case CRYPTO_ALG_TYPE_SKCIPHER:
- return qce_setup_regs_skcipher(async_req, totallen, offset);
+ return qce_setup_regs_skcipher(async_req);
#endif
#ifdef CONFIG_CRYPTO_DEV_QCE_SHA
case CRYPTO_ALG_TYPE_AHASH:
- return qce_setup_regs_ahash(async_req, totallen, offset);
+ return qce_setup_regs_ahash(async_req);
#endif
default:
return -EINVAL;
void qce_cpu_to_be32p_array(__be32 *dst, const u8 *src, unsigned int len);
int qce_check_status(struct qce_device *qce, u32 *status);
void qce_get_version(struct qce_device *qce, u32 *major, u32 *minor, u32 *step);
-int qce_start(struct crypto_async_request *async_req, u32 type, u32 totallen,
- u32 offset);
+int qce_start(struct crypto_async_request *async_req, u32 type);
#endif /* _COMMON_H_ */
#include "core.h"
#include "sha.h"
-/* crypto hw padding constant for first operation */
-#define SHA_PADDING 64
-#define SHA_PADDING_MASK (SHA_PADDING - 1)
+struct qce_sha_saved_state {
+ u8 pending_buf[QCE_SHA_MAX_BLOCKSIZE];
+ u8 partial_digest[QCE_SHA_MAX_DIGESTSIZE];
+ __be32 byte_count[2];
+ unsigned int pending_buflen;
+ unsigned int flags;
+ u64 count;
+ bool first_blk;
+};
static LIST_HEAD(ahash_algs);
qce_dma_issue_pending(&qce->dma);
- ret = qce_start(async_req, tmpl->crypto_alg_type, 0, 0);
+ ret = qce_start(async_req, tmpl->crypto_alg_type);
if (ret)
goto error_terminate;
static int qce_ahash_export(struct ahash_request *req, void *out)
{
- struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
struct qce_sha_reqctx *rctx = ahash_request_ctx(req);
- unsigned long flags = rctx->flags;
- unsigned int digestsize = crypto_ahash_digestsize(ahash);
- unsigned int blocksize =
- crypto_tfm_alg_blocksize(crypto_ahash_tfm(ahash));
-
- if (IS_SHA1(flags) || IS_SHA1_HMAC(flags)) {
- struct sha1_state *out_state = out;
-
- out_state->count = rctx->count;
- qce_cpu_to_be32p_array((__be32 *)out_state->state,
- rctx->digest, digestsize);
- memcpy(out_state->buffer, rctx->buf, blocksize);
- } else if (IS_SHA256(flags) || IS_SHA256_HMAC(flags)) {
- struct sha256_state *out_state = out;
-
- out_state->count = rctx->count;
- qce_cpu_to_be32p_array((__be32 *)out_state->state,
- rctx->digest, digestsize);
- memcpy(out_state->buf, rctx->buf, blocksize);
- } else {
- return -EINVAL;
- }
+ struct qce_sha_saved_state *export_state = out;
- return 0;
-}
-
-static int qce_import_common(struct ahash_request *req, u64 in_count,
- const u32 *state, const u8 *buffer, bool hmac)
-{
- struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
- struct qce_sha_reqctx *rctx = ahash_request_ctx(req);
- unsigned int digestsize = crypto_ahash_digestsize(ahash);
- unsigned int blocksize;
- u64 count = in_count;
-
- blocksize = crypto_tfm_alg_blocksize(crypto_ahash_tfm(ahash));
- rctx->count = in_count;
- memcpy(rctx->buf, buffer, blocksize);
-
- if (in_count <= blocksize) {
- rctx->first_blk = 1;
- } else {
- rctx->first_blk = 0;
- /*
- * For HMAC, there is a hardware padding done when first block
- * is set. Therefore the byte_count must be incremened by 64
- * after the first block operation.
- */
- if (hmac)
- count += SHA_PADDING;
- }
-
- rctx->byte_count[0] = (__force __be32)(count & ~SHA_PADDING_MASK);
- rctx->byte_count[1] = (__force __be32)(count >> 32);
- qce_cpu_to_be32p_array((__be32 *)rctx->digest, (const u8 *)state,
- digestsize);
- rctx->buflen = (unsigned int)(in_count & (blocksize - 1));
+ memcpy(export_state->pending_buf, rctx->buf, rctx->buflen);
+ memcpy(export_state->partial_digest, rctx->digest, sizeof(rctx->digest));
+ export_state->byte_count[0] = rctx->byte_count[0];
+ export_state->byte_count[1] = rctx->byte_count[1];
+ export_state->pending_buflen = rctx->buflen;
+ export_state->count = rctx->count;
+ export_state->first_blk = rctx->first_blk;
+ export_state->flags = rctx->flags;
return 0;
}
static int qce_ahash_import(struct ahash_request *req, const void *in)
{
- struct qce_sha_reqctx *rctx;
- unsigned long flags;
- bool hmac;
- int ret;
-
- ret = qce_ahash_init(req);
- if (ret)
- return ret;
-
- rctx = ahash_request_ctx(req);
- flags = rctx->flags;
- hmac = IS_SHA_HMAC(flags);
-
- if (IS_SHA1(flags) || IS_SHA1_HMAC(flags)) {
- const struct sha1_state *state = in;
-
- ret = qce_import_common(req, state->count, state->state,
- state->buffer, hmac);
- } else if (IS_SHA256(flags) || IS_SHA256_HMAC(flags)) {
- const struct sha256_state *state = in;
+ struct qce_sha_reqctx *rctx = ahash_request_ctx(req);
+ const struct qce_sha_saved_state *import_state = in;
- ret = qce_import_common(req, state->count, state->state,
- state->buf, hmac);
- }
+ memset(rctx, 0, sizeof(*rctx));
+ rctx->count = import_state->count;
+ rctx->buflen = import_state->pending_buflen;
+ rctx->first_blk = import_state->first_blk;
+ rctx->flags = import_state->flags;
+ rctx->byte_count[0] = import_state->byte_count[0];
+ rctx->byte_count[1] = import_state->byte_count[1];
+ memcpy(rctx->buf, import_state->pending_buf, rctx->buflen);
+ memcpy(rctx->digest, import_state->partial_digest, sizeof(rctx->digest));
- return ret;
+ return 0;
}
static int qce_ahash_update(struct ahash_request *req)
/* calculate how many bytes will be hashed later */
hash_later = total % blocksize;
+
+ /*
+ * At this point, there is more than one block size of data. If
+ * the available data to transfer is exactly a multiple of block
+ * size, save the last block to be transferred in qce_ahash_final
+ * (with the last block bit set) if this is indeed the end of data
+ * stream. If not this saved block will be transferred as part of
+ * next update. If this block is not held back and if this is
+ * indeed the end of data stream, the digest obtained will be wrong
+ * since qce_ahash_final will see that rctx->buflen is 0 and return
+ * doing nothing which in turn means that a digest will not be
+ * copied to the destination result buffer. qce_ahash_final cannot
+ * be made to alter this behavior and allowed to proceed if
+ * rctx->buflen is 0 because the crypto engine BAM does not allow
+ * for zero length transfers.
+ */
+ if (!hash_later)
+ hash_later = blocksize;
+
if (hash_later) {
unsigned int src_offset = req->nbytes - hash_later;
scatterwalk_map_and_copy(rctx->buf, req->src, src_offset,
.drv_name = "sha1-qce",
.digestsize = SHA1_DIGEST_SIZE,
.blocksize = SHA1_BLOCK_SIZE,
- .statesize = sizeof(struct sha1_state),
+ .statesize = sizeof(struct qce_sha_saved_state),
.std_iv = std_iv_sha1,
},
{
.drv_name = "sha256-qce",
.digestsize = SHA256_DIGEST_SIZE,
.blocksize = SHA256_BLOCK_SIZE,
- .statesize = sizeof(struct sha256_state),
+ .statesize = sizeof(struct qce_sha_saved_state),
.std_iv = std_iv_sha256,
},
{
.drv_name = "hmac-sha1-qce",
.digestsize = SHA1_DIGEST_SIZE,
.blocksize = SHA1_BLOCK_SIZE,
- .statesize = sizeof(struct sha1_state),
+ .statesize = sizeof(struct qce_sha_saved_state),
.std_iv = std_iv_sha1,
},
{
.drv_name = "hmac-sha256-qce",
.digestsize = SHA256_DIGEST_SIZE,
.blocksize = SHA256_BLOCK_SIZE,
- .statesize = sizeof(struct sha256_state),
+ .statesize = sizeof(struct qce_sha_saved_state),
.std_iv = std_iv_sha256,
},
};
#include <linux/interrupt.h>
#include <linux/moduleparam.h>
#include <linux/types.h>
+#include <linux/errno.h>
#include <crypto/aes.h>
#include <crypto/internal/des.h>
#include <crypto/internal/skcipher.h>
qce_dma_issue_pending(&qce->dma);
- ret = qce_start(async_req, tmpl->crypto_alg_type, req->cryptlen, 0);
+ ret = qce_start(async_req, tmpl->crypto_alg_type);
if (ret)
goto error_terminate;
struct crypto_tfm *tfm = crypto_skcipher_tfm(ablk);
struct qce_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
unsigned long flags = to_cipher_tmpl(ablk)->alg_flags;
+ unsigned int __keylen;
int ret;
if (!key || !keylen)
return -EINVAL;
- switch (IS_XTS(flags) ? keylen >> 1 : keylen) {
+ /*
+ * AES XTS key1 = key2 not supported by crypto engine.
+ * Revisit to request a fallback cipher in this case.
+ */
+ if (IS_XTS(flags)) {
+ __keylen = keylen >> 1;
+ if (!memcmp(key, key + __keylen, __keylen))
+ return -ENOKEY;
+ } else {
+ __keylen = keylen;
+ }
+
+ switch (__keylen) {
case AES_KEYSIZE_128:
case AES_KEYSIZE_256:
memcpy(ctx->enc_key, key, keylen);
break;
+ case AES_KEYSIZE_192:
+ break;
+ default:
+ return -EINVAL;
}
ret = crypto_skcipher_setkey(ctx->fallback, key, keylen);
unsigned int keylen)
{
struct qce_cipher_ctx *ctx = crypto_skcipher_ctx(ablk);
+ u32 _key[6];
int err;
err = verify_skcipher_des3_key(ablk, key);
if (err)
return err;
+ /*
+ * The crypto engine does not support any two keys
+ * being the same for triple des algorithms. The
+ * verify_skcipher_des3_key does not check for all the
+ * below conditions. Return -ENOKEY in case any two keys
+ * are the same. Revisit to see if a fallback cipher
+ * is needed to handle this condition.
+ */
+ memcpy(_key, key, DES3_EDE_KEY_SIZE);
+ if (!((_key[0] ^ _key[2]) | (_key[1] ^ _key[3])) ||
+ !((_key[2] ^ _key[4]) | (_key[3] ^ _key[5])) ||
+ !((_key[0] ^ _key[4]) | (_key[1] ^ _key[5])))
+ return -ENOKEY;
+
ctx->enc_keylen = keylen;
memcpy(ctx->enc_key, key, keylen);
return 0;
struct qce_cipher_ctx *ctx = crypto_skcipher_ctx(tfm);
struct qce_cipher_reqctx *rctx = skcipher_request_ctx(req);
struct qce_alg_template *tmpl = to_cipher_tmpl(tfm);
+ unsigned int blocksize = crypto_skcipher_blocksize(tfm);
int keylen;
int ret;
rctx->flags |= encrypt ? QCE_ENCRYPT : QCE_DECRYPT;
keylen = IS_XTS(rctx->flags) ? ctx->enc_keylen >> 1 : ctx->enc_keylen;
- /* qce is hanging when AES-XTS request len > QCE_SECTOR_SIZE and
- * is not a multiple of it; pass such requests to the fallback
+ /* CE does not handle 0 length messages */
+ if (!req->cryptlen)
+ return 0;
+
+ /*
+ * ECB and CBC algorithms require message lengths to be
+ * multiples of block size.
+ */
+ if (IS_ECB(rctx->flags) || IS_CBC(rctx->flags))
+ if (!IS_ALIGNED(req->cryptlen, blocksize))
+ return -EINVAL;
+
+ /*
+ * Conditions for requesting a fallback cipher
+ * AES-192 (not supported by crypto engine (CE))
+ * AES-XTS request with len <= 512 byte (not recommended to use CE)
+ * AES-XTS request with len > QCE_SECTOR_SIZE and
+ * is not a multiple of it.(Revisit this condition to check if it is
+ * needed in all versions of CE)
*/
if (IS_AES(rctx->flags) &&
- (((keylen != AES_KEYSIZE_128 && keylen != AES_KEYSIZE_256) ||
- req->cryptlen <= aes_sw_max_len) ||
- (IS_XTS(rctx->flags) && req->cryptlen > QCE_SECTOR_SIZE &&
- req->cryptlen % QCE_SECTOR_SIZE))) {
+ ((keylen != AES_KEYSIZE_128 && keylen != AES_KEYSIZE_256) ||
+ (IS_XTS(rctx->flags) && ((req->cryptlen <= aes_sw_max_len) ||
+ (req->cryptlen > QCE_SECTOR_SIZE &&
+ req->cryptlen % QCE_SECTOR_SIZE))))) {
skcipher_request_set_tfm(&rctx->fallback_req, ctx->fallback);
skcipher_request_set_callback(&rctx->fallback_req,
req->base.flags,
.name = "ecb(aes)",
.drv_name = "ecb-aes-qce",
.blocksize = AES_BLOCK_SIZE,
- .ivsize = AES_BLOCK_SIZE,
+ .ivsize = 0,
.min_keysize = AES_MIN_KEY_SIZE,
.max_keysize = AES_MAX_KEY_SIZE,
},
{
struct ahash_request *req = ahash_request_cast(dev->async_req);
struct rk_ahash_rctx *rctx = ahash_request_ctx(req);
- int reg_status = 0;
+ int reg_status;
reg_status = CRYPTO_READ(dev, RK_CRYPTO_CTRL) |
RK_CRYPTO_HASH_FLUSH | _SBF(0xffff, 16);
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/of.h>
+#include <linux/of_device.h>
#include <linux/platform_device.h>
#include <linux/scatterlist.h>
static const struct samsung_aes_variant exynos5433_slim_aes_data = {
.aes_offset = 0x400,
.hash_offset = 0x800,
- .clk_names = { "pclk", "aclk", },
+ .clk_names = { "aclk", "pclk", },
};
static const struct of_device_id s5p_sss_dt_match[] = {
static inline const struct samsung_aes_variant *find_s5p_sss_version
(const struct platform_device *pdev)
{
- if (IS_ENABLED(CONFIG_OF) && (pdev->dev.of_node)) {
- const struct of_device_id *match;
+ if (IS_ENABLED(CONFIG_OF) && (pdev->dev.of_node))
+ return of_device_get_match_data(&pdev->dev);
- match = of_match_node(s5p_sss_dt_match,
- pdev->dev.of_node);
- return (const struct samsung_aes_variant *)match->data;
- }
return (const struct samsung_aes_variant *)
platform_get_device_id(pdev)->driver_data;
}
static int s5p_aes_probe(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
- int i, j, err = -ENODEV;
+ int i, j, err;
const struct samsung_aes_variant *variant;
struct s5p_aes_dev *pdata;
struct resource *res;
}
pdata->res = res;
- pdata->ioaddr = devm_ioremap_resource(&pdev->dev, res);
+ pdata->ioaddr = devm_ioremap_resource(dev, res);
if (IS_ERR(pdata->ioaddr)) {
if (!pdata->use_hash)
return PTR_ERR(pdata->ioaddr);
/* try AES without HASH */
res->end -= 0x300;
pdata->use_hash = false;
- pdata->ioaddr = devm_ioremap_resource(&pdev->dev, res);
+ pdata->ioaddr = devm_ioremap_resource(dev, res);
if (IS_ERR(pdata->ioaddr))
return PTR_ERR(pdata->ioaddr);
}
/* Max Authentication tag size */
#define SA_MAX_AUTH_TAG_SZ 64
-#define PRIV_ID 0x1
-#define PRIV 0x1
+enum sa_algo_id {
+ SA_ALG_CBC_AES = 0,
+ SA_ALG_EBC_AES,
+ SA_ALG_CBC_DES3,
+ SA_ALG_ECB_DES3,
+ SA_ALG_SHA1,
+ SA_ALG_SHA256,
+ SA_ALG_SHA512,
+ SA_ALG_AUTHENC_SHA1_AES,
+ SA_ALG_AUTHENC_SHA256_AES,
+};
+
+struct sa_match_data {
+ u8 priv;
+ u8 priv_id;
+ u32 supported_algos;
+ bool skip_engine_control;
+};
static struct device *sa_k3_dev;
}
static
-int sa_init_sc(struct sa_ctx_info *ctx, const u8 *enc_key,
- u16 enc_key_sz, const u8 *auth_key, u16 auth_key_sz,
+int sa_init_sc(struct sa_ctx_info *ctx, const struct sa_match_data *match_data,
+ const u8 *enc_key, u16 enc_key_sz,
+ const u8 *auth_key, u16 auth_key_sz,
struct algo_data *ad, u8 enc, u32 *swinfo)
{
int enc_sc_offset = 0;
sc_buf[SA_CTX_SCCTL_OWNER_OFFSET] = 0;
memcpy(&sc_buf[2], &sc_id, 2);
sc_buf[4] = 0x0;
- sc_buf[5] = PRIV_ID;
- sc_buf[6] = PRIV;
+ sc_buf[5] = match_data->priv_id;
+ sc_buf[6] = match_data->priv;
sc_buf[7] = 0x0;
/* Prepare context for encryption engine */
return ret;
/* Setup Encryption Security Context & Command label template */
- if (sa_init_sc(&ctx->enc, key, keylen, NULL, 0, ad, 1,
- &ctx->enc.epib[1]))
+ if (sa_init_sc(&ctx->enc, ctx->dev_data->match_data, key, keylen, NULL, 0,
+ ad, 1, &ctx->enc.epib[1]))
goto badkey;
cmdl_len = sa_format_cmdl_gen(&cfg,
ctx->enc.cmdl_size = cmdl_len;
/* Setup Decryption Security Context & Command label template */
- if (sa_init_sc(&ctx->dec, key, keylen, NULL, 0, ad, 0,
- &ctx->dec.epib[1]))
+ if (sa_init_sc(&ctx->dec, ctx->dev_data->match_data, key, keylen, NULL, 0,
+ ad, 0, &ctx->dec.epib[1]))
goto badkey;
cfg.enc_eng_id = ad->enc_eng.eng_id;
else
dma_rx = pdata->dma_rx1;
- ddev = dma_rx->device->dev;
+ ddev = dmaengine_get_dma_device(pdata->dma_tx);
rxd->ddev = ddev;
memcpy(cmdl, sa_ctx->cmdl, sa_ctx->cmdl_size);
mapped_sg->sgt.sgl = src;
mapped_sg->sgt.orig_nents = src_nents;
ret = dma_map_sgtable(ddev, &mapped_sg->sgt, dir_src, 0);
- if (ret)
+ if (ret) {
+ kfree(rxd);
return ret;
+ }
mapped_sg->dir = dir_src;
mapped_sg->mapped = true;
mapped_sg->sgt.sgl = req->src;
mapped_sg->sgt.orig_nents = sg_nents;
ret = dma_map_sgtable(ddev, &mapped_sg->sgt, dir_src, 0);
- if (ret)
+ if (ret) {
+ kfree(rxd);
return ret;
+ }
mapped_sg->dir = dir_src;
mapped_sg->mapped = true;
cfg.akey = NULL;
cfg.akey_len = 0;
+ ctx->dev_data = dev_get_drvdata(sa_k3_dev);
/* Setup Encryption Security Context & Command label template */
- if (sa_init_sc(&ctx->enc, NULL, 0, NULL, 0, ad, 0,
- &ctx->enc.epib[1]))
+ if (sa_init_sc(&ctx->enc, ctx->dev_data->match_data, NULL, 0, NULL, 0,
+ ad, 0, &ctx->enc.epib[1]))
goto badkey;
cmdl_len = sa_format_cmdl_gen(&cfg,
int ret;
memzero_explicit(ctx, sizeof(*ctx));
+ ctx->dev_data = data;
ctx->shash = crypto_alloc_shash(hash, 0, CRYPTO_ALG_NEED_FALLBACK);
if (IS_ERR(ctx->shash)) {
cfg.akey_len = keys.authkeylen;
/* Setup Encryption Security Context & Command label template */
- if (sa_init_sc(&ctx->enc, keys.enckey, keys.enckeylen,
- keys.authkey, keys.authkeylen,
+ if (sa_init_sc(&ctx->enc, ctx->dev_data->match_data, keys.enckey,
+ keys.enckeylen, keys.authkey, keys.authkeylen,
ad, 1, &ctx->enc.epib[1]))
return -EINVAL;
ctx->enc.cmdl_size = cmdl_len;
/* Setup Decryption Security Context & Command label template */
- if (sa_init_sc(&ctx->dec, keys.enckey, keys.enckeylen,
- keys.authkey, keys.authkeylen,
+ if (sa_init_sc(&ctx->dec, ctx->dev_data->match_data, keys.enckey,
+ keys.enckeylen, keys.authkey, keys.authkeylen,
ad, 0, &ctx->dec.epib[1]))
return -EINVAL;
}
static struct sa_alg_tmpl sa_algs[] = {
- {
+ [SA_ALG_CBC_AES] = {
.type = CRYPTO_ALG_TYPE_SKCIPHER,
.alg.skcipher = {
.base.cra_name = "cbc(aes)",
.decrypt = sa_decrypt,
}
},
- {
+ [SA_ALG_EBC_AES] = {
.type = CRYPTO_ALG_TYPE_SKCIPHER,
.alg.skcipher = {
.base.cra_name = "ecb(aes)",
.decrypt = sa_decrypt,
}
},
- {
+ [SA_ALG_CBC_DES3] = {
.type = CRYPTO_ALG_TYPE_SKCIPHER,
.alg.skcipher = {
.base.cra_name = "cbc(des3_ede)",
.decrypt = sa_decrypt,
}
},
- {
+ [SA_ALG_ECB_DES3] = {
.type = CRYPTO_ALG_TYPE_SKCIPHER,
.alg.skcipher = {
.base.cra_name = "ecb(des3_ede)",
.decrypt = sa_decrypt,
}
},
- {
+ [SA_ALG_SHA1] = {
.type = CRYPTO_ALG_TYPE_AHASH,
.alg.ahash = {
.halg.base = {
.import = sa_sha_import,
},
},
- {
+ [SA_ALG_SHA256] = {
.type = CRYPTO_ALG_TYPE_AHASH,
.alg.ahash = {
.halg.base = {
.import = sa_sha_import,
},
},
- {
+ [SA_ALG_SHA512] = {
.type = CRYPTO_ALG_TYPE_AHASH,
.alg.ahash = {
.halg.base = {
.import = sa_sha_import,
},
},
- {
+ [SA_ALG_AUTHENC_SHA1_AES] = {
.type = CRYPTO_ALG_TYPE_AEAD,
.alg.aead = {
.base = {
.decrypt = sa_aead_decrypt,
},
},
- {
+ [SA_ALG_AUTHENC_SHA256_AES] = {
.type = CRYPTO_ALG_TYPE_AEAD,
.alg.aead = {
.base = {
};
/* Register the algorithms in crypto framework */
-static void sa_register_algos(const struct device *dev)
+static void sa_register_algos(struct sa_crypto_data *dev_data)
{
+ const struct sa_match_data *match_data = dev_data->match_data;
+ struct device *dev = dev_data->dev;
char *alg_name;
u32 type;
int i, err;
for (i = 0; i < ARRAY_SIZE(sa_algs); i++) {
+ /* Skip unsupported algos */
+ if (!(match_data->supported_algos & BIT(i)))
+ continue;
+
type = sa_algs[i].type;
if (type == CRYPTO_ALG_TYPE_SKCIPHER) {
alg_name = sa_algs[i].alg.skcipher.base.cra_name;
return 0;
}
+static struct sa_match_data am654_match_data = {
+ .priv = 1,
+ .priv_id = 1,
+ .supported_algos = GENMASK(SA_ALG_AUTHENC_SHA256_AES, 0),
+};
+
+static struct sa_match_data am64_match_data = {
+ .priv = 0,
+ .priv_id = 0,
+ .supported_algos = BIT(SA_ALG_CBC_AES) |
+ BIT(SA_ALG_EBC_AES) |
+ BIT(SA_ALG_SHA256) |
+ BIT(SA_ALG_SHA512) |
+ BIT(SA_ALG_AUTHENC_SHA256_AES),
+ .skip_engine_control = true,
+};
+
+static const struct of_device_id of_match[] = {
+ { .compatible = "ti,j721e-sa2ul", .data = &am654_match_data, },
+ { .compatible = "ti,am654-sa2ul", .data = &am654_match_data, },
+ { .compatible = "ti,am64-sa2ul", .data = &am64_match_data, },
+ {},
+};
+MODULE_DEVICE_TABLE(of, of_match);
+
static int sa_ul_probe(struct platform_device *pdev)
{
+ const struct of_device_id *match;
struct device *dev = &pdev->dev;
struct device_node *node = dev->of_node;
struct resource *res;
static void __iomem *saul_base;
struct sa_crypto_data *dev_data;
- u32 val;
int ret;
dev_data = devm_kzalloc(dev, sizeof(*dev_data), GFP_KERNEL);
dev_set_drvdata(sa_k3_dev, dev_data);
pm_runtime_enable(dev);
- ret = pm_runtime_get_sync(dev);
+ ret = pm_runtime_resume_and_get(dev);
if (ret < 0) {
dev_err(&pdev->dev, "%s: failed to get sync: %d\n", __func__,
ret);
if (ret)
goto disable_pm_runtime;
+ match = of_match_node(of_match, dev->of_node);
+ if (!match) {
+ dev_err(dev, "No compatible match found\n");
+ return -ENODEV;
+ }
+ dev_data->match_data = match->data;
+
spin_lock_init(&dev_data->scid_lock);
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
saul_base = devm_ioremap_resource(dev, res);
dev_data->base = saul_base;
- val = SA_EEC_ENCSS_EN | SA_EEC_AUTHSS_EN | SA_EEC_CTXCACH_EN |
- SA_EEC_CPPI_PORT_IN_EN | SA_EEC_CPPI_PORT_OUT_EN |
- SA_EEC_TRNG_EN;
- writel_relaxed(val, saul_base + SA_ENGINE_ENABLE_CONTROL);
+ if (!dev_data->match_data->skip_engine_control) {
+ u32 val = SA_EEC_ENCSS_EN | SA_EEC_AUTHSS_EN | SA_EEC_CTXCACH_EN |
+ SA_EEC_CPPI_PORT_IN_EN | SA_EEC_CPPI_PORT_OUT_EN |
+ SA_EEC_TRNG_EN;
- sa_register_algos(dev);
+ writel_relaxed(val, saul_base + SA_ENGINE_ENABLE_CONTROL);
+ }
+
+ sa_register_algos(dev_data);
ret = of_platform_populate(node, NULL, NULL, &pdev->dev);
if (ret)
return 0;
}
-static const struct of_device_id of_match[] = {
- {.compatible = "ti,j721e-sa2ul",},
- {.compatible = "ti,am654-sa2ul",},
- {},
-};
-MODULE_DEVICE_TABLE(of, of_match);
-
static struct platform_driver sa_ul_driver = {
.probe = sa_ul_probe,
.remove = sa_ul_remove,
#define SA_UNSAFE_DATA_SZ_MIN 240
#define SA_UNSAFE_DATA_SZ_MAX 256
+struct sa_match_data;
+
/**
* struct sa_crypto_data - Crypto driver instance data
* @base: Base address of the register space
+ * @soc_data: Pointer to SoC specific data
* @pdev: Platform device pointer
* @sc_pool: security context pool
* @dev: Device pointer
*/
struct sa_crypto_data {
void __iomem *base;
+ const struct sa_match_data *match_data;
struct platform_device *pdev;
struct dma_pool *sc_pool;
struct device *dev;
int ret;
u32 cfg, hw_mode;
- pm_runtime_get_sync(cryp->dev);
+ pm_runtime_resume_and_get(cryp->dev);
/* Disable interrupt */
stm32_cryp_write(cryp, CRYP_IMSCR, 0);
if (!cryp)
return -ENODEV;
- ret = pm_runtime_get_sync(cryp->dev);
+ ret = pm_runtime_resume_and_get(cryp->dev);
if (ret < 0)
return ret;
static int stm32_hash_hw_init(struct stm32_hash_dev *hdev,
struct stm32_hash_request_ctx *rctx)
{
- pm_runtime_get_sync(hdev->dev);
+ pm_runtime_resume_and_get(hdev->dev);
if (!(HASH_FLAGS_INIT & hdev->flags)) {
stm32_hash_write(hdev, HASH_CR, HASH_CR_INIT);
u32 *preg;
unsigned int i;
- pm_runtime_get_sync(hdev->dev);
+ pm_runtime_resume_and_get(hdev->dev);
while ((stm32_hash_read(hdev, HASH_SR) & HASH_SR_BUSY))
cpu_relax();
preg = rctx->hw_context;
- pm_runtime_get_sync(hdev->dev);
+ pm_runtime_resume_and_get(hdev->dev);
stm32_hash_write(hdev, HASH_IMR, *preg++);
stm32_hash_write(hdev, HASH_STR, *preg++);
if (!hdev)
return -ENODEV;
- ret = pm_runtime_get_sync(hdev->dev);
+ ret = pm_runtime_resume_and_get(hdev->dev);
if (ret < 0)
return ret;
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* Copyright (C) ST-Ericsson SA 2010
* Author: Shujuan Chen <shujuan.chen@stericsson.com> for ST-Ericsson.
* Author: Jonas Linde <jonas.linde@stericsson.com> for ST-Ericsson.
#include "cryp_p.h"
#include "cryp.h"
-/**
+/*
* cryp_wait_until_done - wait until the device logic is not busy
*/
void cryp_wait_until_done(struct cryp_device_data *device_data)
* other device context parameter
* @device_data: Pointer to the device data struct for base address.
* @ctx: Crypto device context
+ * @cryp_mode: Mode: Polling, Interrupt or DMA
*/
void cryp_save_device_context(struct cryp_device_data *device_data,
struct cryp_device_context *ctx,
/* SPDX-License-Identifier: GPL-2.0-only */
-/**
+/*
* Copyright (C) ST-Ericsson SA 2010
* Author: Shujuan Chen <shujuan.chen@stericsson.com> for ST-Ericsson.
* Author: Jonas Linde <jonas.linde@stericsson.com> for ST-Ericsson.
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* Copyright (C) ST-Ericsson SA 2010
* Author: Shujuan Chen <shujuan.chen@stericsson.com> for ST-Ericsson.
* Author: Joakim Bech <joakim.xx.bech@stericsson.com> for ST-Ericsson.
/**
* struct cryp_ctx - Crypto context
* @config: Crypto mode.
- * @key[CRYP_MAX_KEY_SIZE]: Key.
+ * @key: Key array.
* @keylen: Length of key.
* @iv: Pointer to initialization vector.
* @indata: Pointer to indata.
* @updated: Updated flag.
* @dev_ctx: Device dependent context.
* @device: Pointer to the device.
+ * @session_id: Atomic session ID.
*/
struct cryp_ctx {
struct cryp_config config;
chan = ctx->device->dma.chan_mem2cryp;
dmaengine_terminate_all(chan);
dma_unmap_sg(chan->device->dev, ctx->device->dma.sg_src,
- ctx->device->dma.sg_src_len, DMA_TO_DEVICE);
+ ctx->device->dma.nents_src, DMA_TO_DEVICE);
chan = ctx->device->dma.chan_cryp2mem;
dmaengine_terminate_all(chan);
dma_unmap_sg(chan->device->dev, ctx->device->dma.sg_dst,
- ctx->device->dma.sg_dst_len, DMA_FROM_DEVICE);
+ ctx->device->dma.nents_dst, DMA_FROM_DEVICE);
}
static int cryp_dma_write(struct cryp_ctx *ctx, struct scatterlist *sg,
device_data->phybase = res->start;
device_data->base = devm_ioremap_resource(dev, res);
if (IS_ERR(device_data->base)) {
- dev_err(dev, "[%s]: ioremap failed!", __func__);
ret = PTR_ERR(device_data->base);
goto out;
}
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* Copyright (C) ST-Ericsson SA 2010
* Author: Shujuan Chen <shujuan.chen@stericsson.com> for ST-Ericsson.
* Author: Jonas Linde <jonas.linde@stericsson.com> for ST-Ericsson.
/* SPDX-License-Identifier: GPL-2.0-only */
-/**
+/*
* Copyright (C) ST-Ericsson SA 2010
* Author: Shujuan Chen <shujuan.chen@stericsson.com> for ST-Ericsson.
* Author: Jonas Linde <jonas.linde@stericsson.com> for ST-Ericsson.
CRYP_IRQ_SRC_ALL = 0x3
};
-/**
+/*
* M0 Funtions
*/
void cryp_enable_irq_src(struct cryp_device_data *device_data, u32 irq_src);
/* SPDX-License-Identifier: GPL-2.0-only */
-/**
+/*
* Copyright (C) ST-Ericsson SA 2010
* Author: Shujuan Chen <shujuan.chen@stericsson.com> for ST-Ericsson.
* Author: Jonas Linde <jonas.linde@stericsson.com> for ST-Ericsson.
#include "cryp_irq.h"
-/**
+/*
*
* CRYP Registers - Offset mapping
* +-----------------+
/* SPDX-License-Identifier: GPL-2.0-only */
-/**
+/*
* Copyright (C) ST-Ericsson SA 2010
* Author: Shujuan Chen <shujuan.chen@stericsson.com> for ST-Ericsson.
* Author: Jonas Linde <jonas.linde@stericsson.com> for ST-Ericsson.
#include "cryp.h"
#include "cryp_irqp.h"
-/**
+/*
* Generic Macros
*/
#define CRYP_SET_BITS(reg_name, mask) \
writel_relaxed(((readl_relaxed(reg) & ~(mask)) | \
(((u32)val << shift) & (mask))), reg)
-/**
+/*
* CRYP specific Macros
*/
#define CRYP_PERIPHERAL_ID0 0xE3
#define CRYP_PCELL_ID2 0x05
#define CRYP_PCELL_ID3 0xB1
-/**
+/*
* CRYP register default values
*/
#define MAX_DEVICE_SUPPORT 2
#define CRYP_KEY_DEFAULT 0x0
#define CRYP_INIT_VECT_DEFAULT 0x0
-/**
+/*
* CRYP Control register specific mask
*/
#define CRYP_CR_SECURE_MASK BIT(0)
CRYP_CR_PRLG_MASK |\
CRYP_CR_ALGODIR_MASK |\
CRYP_CR_ALGOMODE_MASK |\
- CRYP_CR_DATATYPE_MASK |\
CRYP_CR_KEYSIZE_MASK |\
CRYP_CR_KEYRDEN_MASK |\
CRYP_CR_DATATYPE_MASK)
#define CRYP_SR_IFEM_MASK BIT(0)
#define CRYP_SR_BUSY_MASK BIT(4)
-/**
+/*
* Bit position used while setting bits in register
*/
#define CRYP_CR_PRLG_POS 1
#define CRYP_SR_BUSY_POS 4
-/**
+/*
* CRYP PCRs------PC_NAND control register
* BIT_MASK
*/
chan = ctx->device->dma.chan_mem2hash;
dmaengine_terminate_all(chan);
dma_unmap_sg(chan->device->dev, ctx->device->dma.sg,
- ctx->device->dma.sg_len, DMA_TO_DEVICE);
+ ctx->device->dma.nents, DMA_TO_DEVICE);
}
static int hash_dma_write(struct hash_ctx *ctx,
/**
* hash_get_device_data - Checks for an available hash device and return it.
- * @hash_ctx: Structure for the hash context.
+ * @ctx: Structure for the hash context.
* @device_data: Structure for the hash device.
*
* This function check for an available hash device and return it to
}
/**
- * hash_init - Common hash init function for SHA1/SHA2 (SHA256).
+ * ux500_hash_init - Common hash init function for SHA1/SHA2 (SHA256).
* @req: The hash request for the job.
*
* Initialize structures.
* @device_data: Structure for the hash device.
* @message: Block (512 bits) of message to be written to
* the HASH hardware.
+ * @length: Message length
*
*/
static void hash_processblock(struct hash_device_data *device_data,
}
/**
- * hash_update - The hash update function for SHA1/SHA2 (SHA256).
+ * ahash_update - The hash update function for SHA1/SHA2 (SHA256).
* @req: The hash request for the job.
*/
static int ahash_update(struct ahash_request *req)
}
/**
- * hash_final - The hash final function for SHA1/SHA2 (SHA256).
+ * ahash_final - The hash final function for SHA1/SHA2 (SHA256).
* @req: The hash request for the job.
*/
static int ahash_final(struct ahash_request *req)
}
};
-/**
- * hash_algs_register_all -
- */
static int ahash_algs_register_all(struct hash_device_data *device_data)
{
int ret;
return ret;
}
-/**
- * hash_algs_unregister_all -
- */
static void ahash_algs_unregister_all(struct hash_device_data *device_data)
{
int i;
device_data->phybase = res->start;
device_data->base = devm_ioremap_resource(dev, res);
if (IS_ERR(device_data->base)) {
- dev_err(dev, "%s: ioremap() failed!\n", __func__);
ret = PTR_ERR(device_data->base);
goto out;
}
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* AES routines supporting VMX instructions on the Power 8
*
* Copyright (C) 2015 International Business Machines Inc.
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* AES CBC routines supporting VMX instructions on the Power 8
*
* Copyright (C) 2015 International Business Machines Inc.
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* AES CTR routines supporting VMX instructions on the Power 8
*
* Copyright (C) 2015 International Business Machines Inc.
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* AES XTS routines supporting VMX In-core instructions on Power 8
*
* Copyright (C) 2015 International Business Machines Inc.
// SPDX-License-Identifier: GPL-2.0
-/**
+/*
* GHASH routines supporting VMX instructions on the Power 8
*
* Copyright (C) 2015, 2019 International Business Machines Inc.
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* Routines supporting VMX instructions on the Power 8
*
* Copyright (C) 2015 International Business Machines Inc.
#include <linux/security.h>
#include <linux/debugfs.h>
#include <linux/module.h>
+#include <linux/sizes.h>
#include <linux/mutex.h>
#include <linux/cdev.h>
#include <linux/idr.h>
* @dev: driver core device object
* @cdev: char dev core object for ioctl operations
* @cxlm: pointer to the parent device driver data
- * @ops_active: active user of @cxlm in ops handlers
- * @ops_dead: completion when all @cxlm ops users have exited
* @id: id number of this memdev instance.
*/
struct cxl_memdev {
struct device dev;
struct cdev cdev;
struct cxl_mem *cxlm;
- struct percpu_ref ops_active;
- struct completion ops_dead;
int id;
};
static int cxl_mem_major;
static DEFINE_IDA(cxl_memdev_ida);
+static DECLARE_RWSEM(cxl_memdev_rwsem);
static struct dentry *cxl_debugfs;
static bool cxl_raw_allow_all;
* table will be validated against the user's input. For example, if size_in is
* 0, and the user passed in 1, it is an error.
*/
-static struct cxl_mem_command mem_commands[] = {
+static struct cxl_mem_command mem_commands[CXL_MEM_COMMAND_ID_MAX] = {
CXL_CMD(IDENTIFY, 0, 0x43, CXL_CMD_FLAG_FORCE_ENABLE),
#ifdef CONFIG_CXL_MEM_RAW_COMMANDS
CXL_CMD(RAW, ~0, ~0, 0),
static long cxl_memdev_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
- struct cxl_memdev *cxlmd;
- struct inode *inode;
- int rc = -ENOTTY;
+ struct cxl_memdev *cxlmd = file->private_data;
+ int rc = -ENXIO;
- inode = file_inode(file);
- cxlmd = container_of(inode->i_cdev, typeof(*cxlmd), cdev);
+ down_read(&cxl_memdev_rwsem);
+ if (cxlmd->cxlm)
+ rc = __cxl_memdev_ioctl(cxlmd, cmd, arg);
+ up_read(&cxl_memdev_rwsem);
- if (!percpu_ref_tryget_live(&cxlmd->ops_active))
- return -ENXIO;
+ return rc;
+}
- rc = __cxl_memdev_ioctl(cxlmd, cmd, arg);
+static int cxl_memdev_open(struct inode *inode, struct file *file)
+{
+ struct cxl_memdev *cxlmd =
+ container_of(inode->i_cdev, typeof(*cxlmd), cdev);
- percpu_ref_put(&cxlmd->ops_active);
+ get_device(&cxlmd->dev);
+ file->private_data = cxlmd;
- return rc;
+ return 0;
+}
+
+static int cxl_memdev_release_file(struct inode *inode, struct file *file)
+{
+ struct cxl_memdev *cxlmd =
+ container_of(inode->i_cdev, typeof(*cxlmd), cdev);
+
+ put_device(&cxlmd->dev);
+
+ return 0;
}
static const struct file_operations cxl_memdev_fops = {
.owner = THIS_MODULE,
.unlocked_ioctl = cxl_memdev_ioctl,
+ .open = cxl_memdev_open,
+ .release = cxl_memdev_release_file,
.compat_ioctl = compat_ptr_ioctl,
.llseek = noop_llseek,
};
return NULL;
}
- offset = ((u64)reg_hi << 32) | FIELD_GET(CXL_REGLOC_ADDR_MASK, reg_lo);
+ offset = ((u64)reg_hi << 32) | (reg_lo & CXL_REGLOC_ADDR_MASK);
bar = FIELD_GET(CXL_REGLOC_BIR_MASK, reg_lo);
/* Basic sanity check that BAR is big enough */
{
struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
- percpu_ref_exit(&cxlmd->ops_active);
ida_free(&cxl_memdev_ida, cxlmd->id);
kfree(cxlmd);
}
struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
struct cxl_mem *cxlm = cxlmd->cxlm;
- return sprintf(buf, "%.16s\n", cxlm->firmware_version);
+ return sysfs_emit(buf, "%.16s\n", cxlm->firmware_version);
}
static DEVICE_ATTR_RO(firmware_version);
struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
struct cxl_mem *cxlm = cxlmd->cxlm;
- return sprintf(buf, "%zu\n", cxlm->payload_size);
+ return sysfs_emit(buf, "%zu\n", cxlm->payload_size);
}
static DEVICE_ATTR_RO(payload_max);
struct cxl_mem *cxlm = cxlmd->cxlm;
unsigned long long len = range_len(&cxlm->ram_range);
- return sprintf(buf, "%#llx\n", len);
+ return sysfs_emit(buf, "%#llx\n", len);
}
static struct device_attribute dev_attr_ram_size =
struct cxl_mem *cxlm = cxlmd->cxlm;
unsigned long long len = range_len(&cxlm->pmem_range);
- return sprintf(buf, "%#llx\n", len);
+ return sysfs_emit(buf, "%#llx\n", len);
}
static struct device_attribute dev_attr_pmem_size =
.groups = cxl_memdev_attribute_groups,
};
-static void cxlmdev_unregister(void *_cxlmd)
+static void cxl_memdev_shutdown(struct cxl_memdev *cxlmd)
{
- struct cxl_memdev *cxlmd = _cxlmd;
- struct device *dev = &cxlmd->dev;
-
- percpu_ref_kill(&cxlmd->ops_active);
- cdev_device_del(&cxlmd->cdev, dev);
- wait_for_completion(&cxlmd->ops_dead);
+ down_write(&cxl_memdev_rwsem);
cxlmd->cxlm = NULL;
- put_device(dev);
+ up_write(&cxl_memdev_rwsem);
}
-static void cxlmdev_ops_active_release(struct percpu_ref *ref)
+static void cxl_memdev_unregister(void *_cxlmd)
{
- struct cxl_memdev *cxlmd =
- container_of(ref, typeof(*cxlmd), ops_active);
+ struct cxl_memdev *cxlmd = _cxlmd;
+ struct device *dev = &cxlmd->dev;
- complete(&cxlmd->ops_dead);
+ cdev_device_del(&cxlmd->cdev, dev);
+ cxl_memdev_shutdown(cxlmd);
+ put_device(dev);
}
-static int cxl_mem_add_memdev(struct cxl_mem *cxlm)
+static struct cxl_memdev *cxl_memdev_alloc(struct cxl_mem *cxlm)
{
struct pci_dev *pdev = cxlm->pdev;
struct cxl_memdev *cxlmd;
cxlmd = kzalloc(sizeof(*cxlmd), GFP_KERNEL);
if (!cxlmd)
- return -ENOMEM;
- init_completion(&cxlmd->ops_dead);
-
- /*
- * @cxlm is deallocated when the driver unbinds so operations
- * that are using it need to hold a live reference.
- */
- cxlmd->cxlm = cxlm;
- rc = percpu_ref_init(&cxlmd->ops_active, cxlmdev_ops_active_release, 0,
- GFP_KERNEL);
- if (rc)
- goto err_ref;
+ return ERR_PTR(-ENOMEM);
rc = ida_alloc_range(&cxl_memdev_ida, 0, CXL_MEM_MAX_DEVS, GFP_KERNEL);
if (rc < 0)
- goto err_id;
+ goto err;
cxlmd->id = rc;
dev = &cxlmd->dev;
dev->bus = &cxl_bus_type;
dev->devt = MKDEV(cxl_mem_major, cxlmd->id);
dev->type = &cxl_memdev_type;
- dev_set_name(dev, "mem%d", cxlmd->id);
+ device_set_pm_not_required(dev);
cdev = &cxlmd->cdev;
cdev_init(cdev, &cxl_memdev_fops);
+ return cxlmd;
+
+err:
+ kfree(cxlmd);
+ return ERR_PTR(rc);
+}
+
+static int cxl_mem_add_memdev(struct cxl_mem *cxlm)
+{
+ struct cxl_memdev *cxlmd;
+ struct device *dev;
+ struct cdev *cdev;
+ int rc;
+
+ cxlmd = cxl_memdev_alloc(cxlm);
+ if (IS_ERR(cxlmd))
+ return PTR_ERR(cxlmd);
+
+ dev = &cxlmd->dev;
+ rc = dev_set_name(dev, "mem%d", cxlmd->id);
+ if (rc)
+ goto err;
+
+ /*
+ * Activate ioctl operations, no cxl_memdev_rwsem manipulation
+ * needed as this is ordered with cdev_add() publishing the device.
+ */
+ cxlmd->cxlm = cxlm;
+ cdev = &cxlmd->cdev;
rc = cdev_device_add(cdev, dev);
if (rc)
- goto err_add;
+ goto err;
- return devm_add_action_or_reset(dev->parent, cxlmdev_unregister, cxlmd);
+ return devm_add_action_or_reset(dev->parent, cxl_memdev_unregister,
+ cxlmd);
-err_add:
- ida_free(&cxl_memdev_ida, cxlmd->id);
-err_id:
+err:
/*
- * Theoretically userspace could have already entered the fops,
- * so flush ops_active.
+ * The cdev was briefly live, shutdown any ioctl operations that
+ * saw that state.
*/
- percpu_ref_kill(&cxlmd->ops_active);
- wait_for_completion(&cxlmd->ops_dead);
- percpu_ref_exit(&cxlmd->ops_active);
-err_ref:
- kfree(cxlmd);
-
+ cxl_memdev_shutdown(cxlmd);
+ put_device(dev);
return rc;
}
*/
static int cxl_mem_identify(struct cxl_mem *cxlm)
{
+ /* See CXL 2.0 Table 175 Identify Memory Device Output Payload */
struct cxl_mbox_identify {
char fw_revision[0x10];
__le64 total_capacity;
* For now, only the capacity is exported in sysfs
*/
cxlm->ram_range.start = 0;
- cxlm->ram_range.end = le64_to_cpu(id.volatile_capacity) - 1;
+ cxlm->ram_range.end = le64_to_cpu(id.volatile_capacity) * SZ_256M - 1;
cxlm->pmem_range.start = 0;
- cxlm->pmem_range.end = le64_to_cpu(id.persistent_capacity) - 1;
+ cxlm->pmem_range.end =
+ le64_to_cpu(id.persistent_capacity) * SZ_256M - 1;
memcpy(cxlm->firmware_version, id.fw_revision, sizeof(id.fw_revision));
list_add(&dax_id->list, &dax_drv->ids);
} else
rc = -ENOMEM;
- } else
- /* nothing to remove */;
+ }
} else if (action == ID_REMOVE) {
list_del(&dax_id->list);
kfree(dax_id);
- } else
- /* dax_id already added */;
+ }
mutex_unlock(&dax_bus_lock);
if (rc < 0)
kfree(chan->dev);
err_free_local:
free_percpu(chan->local);
+ chan->local = NULL;
return rc;
}
config DW_DMAC
tristate "Synopsys DesignWare AHB DMA platform driver"
+ depends on HAS_IOMEM
select DW_DMAC_CORE
help
Support the Synopsys DesignWare AHB DMA controller. This
config DW_DMAC_PCI
tristate "Synopsys DesignWare AHB DMA PCI driver"
depends on PCI
+ depends on HAS_IOMEM
select DW_DMAC_CORE
help
Support the Synopsys DesignWare AHB DMA controller on the
idxd_cmd_exec(idxd, IDXD_CMD_DRAIN_WQ, operand, NULL);
}
+void idxd_wq_reset(struct idxd_wq *wq)
+{
+ struct idxd_device *idxd = wq->idxd;
+ struct device *dev = &idxd->pdev->dev;
+ u32 operand;
+
+ if (wq->state != IDXD_WQ_ENABLED) {
+ dev_dbg(dev, "WQ %d in wrong state: %d\n", wq->id, wq->state);
+ return;
+ }
+
+ operand = BIT(wq->id % 16) | ((wq->id / 16) << 16);
+ idxd_cmd_exec(idxd, IDXD_CMD_RESET_WQ, operand, NULL);
+ wq->state = IDXD_WQ_DISABLED;
+}
+
int idxd_wq_map_portal(struct idxd_wq *wq)
{
struct idxd_device *idxd = wq->idxd;
void idxd_wq_disable_cleanup(struct idxd_wq *wq)
{
struct idxd_device *idxd = wq->idxd;
- struct device *dev = &idxd->pdev->dev;
- int i, wq_offset;
lockdep_assert_held(&idxd->dev_lock);
memset(wq->wqcfg, 0, idxd->wqcfg_size);
wq->ats_dis = 0;
clear_bit(WQ_FLAG_DEDICATED, &wq->flags);
memset(wq->name, 0, WQ_NAME_SIZE);
-
- for (i = 0; i < WQCFG_STRIDES(idxd); i++) {
- wq_offset = WQCFG_OFFSET(idxd, wq->id, i);
- iowrite32(0, idxd->reg_base + wq_offset);
- dev_dbg(dev, "WQ[%d][%d][%#x]: %#x\n",
- wq->id, i, wq_offset,
- ioread32(idxd->reg_base + wq_offset));
- }
}
/* Device control bits */
}
/* Device configuration bits */
+void idxd_msix_perm_setup(struct idxd_device *idxd)
+{
+ union msix_perm mperm;
+ int i, msixcnt;
+
+ msixcnt = pci_msix_vec_count(idxd->pdev);
+ if (msixcnt < 0)
+ return;
+
+ mperm.bits = 0;
+ mperm.pasid = idxd->pasid;
+ mperm.pasid_en = device_pasid_enabled(idxd);
+ for (i = 1; i < msixcnt; i++)
+ iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + i * 8);
+}
+
+void idxd_msix_perm_clear(struct idxd_device *idxd)
+{
+ union msix_perm mperm;
+ int i, msixcnt;
+
+ msixcnt = pci_msix_vec_count(idxd->pdev);
+ if (msixcnt < 0)
+ return;
+
+ mperm.bits = 0;
+ for (i = 1; i < msixcnt; i++)
+ iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + i * 8);
+}
+
static void idxd_group_config_write(struct idxd_group *group)
{
struct idxd_device *idxd = group->idxd;
if (!wq->group)
return 0;
- memset(wq->wqcfg, 0, idxd->wqcfg_size);
+ /*
+ * Instead of memset the entire shadow copy of WQCFG, copy from the hardware after
+ * wq reset. This will copy back the sticky values that are present on some devices.
+ */
+ for (i = 0; i < WQCFG_STRIDES(idxd); i++) {
+ wq_offset = WQCFG_OFFSET(idxd, wq->id, i);
+ wq->wqcfg->bits[i] = ioread32(idxd->reg_base + wq_offset);
+ }
/* byte 0-3 */
wq->wqcfg->wq_size = wq->size;
struct bus_type *idxd_get_bus_type(struct idxd_device *idxd);
/* device interrupt control */
+void idxd_msix_perm_setup(struct idxd_device *idxd);
+void idxd_msix_perm_clear(struct idxd_device *idxd);
irqreturn_t idxd_irq_handler(int vec, void *data);
irqreturn_t idxd_misc_thread(int vec, void *data);
irqreturn_t idxd_wq_thread(int irq, void *data);
int idxd_wq_enable(struct idxd_wq *wq);
int idxd_wq_disable(struct idxd_wq *wq);
void idxd_wq_drain(struct idxd_wq *wq);
+void idxd_wq_reset(struct idxd_wq *wq);
int idxd_wq_map_portal(struct idxd_wq *wq);
void idxd_wq_unmap_portal(struct idxd_wq *wq);
void idxd_wq_disable_cleanup(struct idxd_wq *wq);
struct idxd_irq_entry *irq_entry;
int i, msixcnt;
int rc = 0;
- union msix_perm mperm;
msixcnt = pci_msix_vec_count(pdev);
if (msixcnt < 0) {
}
idxd_unmask_error_interrupts(idxd);
-
- /* Setup MSIX permission table */
- mperm.bits = 0;
- mperm.pasid = idxd->pasid;
- mperm.pasid_en = device_pasid_enabled(idxd);
- for (i = 1; i < msixcnt; i++)
- iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + i * 8);
-
+ idxd_msix_perm_setup(idxd);
return 0;
err_no_irq:
idxd_flush_work_list(irq_entry);
}
+ idxd_msix_perm_clear(idxd);
destroy_workqueue(idxd->wq);
}
for (i = 0; i < 4; i++)
idxd->sw_err.bits[i] = ioread64(idxd->reg_base +
IDXD_SWERR_OFFSET + i * sizeof(u64));
- iowrite64(IDXD_SWERR_ACK, idxd->reg_base + IDXD_SWERR_OFFSET);
+
+ iowrite64(idxd->sw_err.bits[0] & IDXD_SWERR_ACK,
+ idxd->reg_base + IDXD_SWERR_OFFSET);
if (idxd->sw_err.valid && idxd->sw_err.wq_idx_valid) {
int id = idxd->sw_err.wq_idx;
{
struct idxd_device *idxd = wq->idxd;
struct device *dev = &idxd->pdev->dev;
- int rc;
mutex_lock(&wq->wq_lock);
dev_dbg(dev, "%s removing WQ %s\n", __func__, dev_name(&wq->conf_dev));
idxd_wq_unmap_portal(wq);
idxd_wq_drain(wq);
- rc = idxd_wq_disable(wq);
+ idxd_wq_reset(wq);
idxd_wq_free_resources(wq);
wq->client_count = 0;
mutex_unlock(&wq->wq_lock);
- if (rc < 0)
- dev_warn(dev, "Failed to disable %s: %d\n",
- dev_name(&wq->conf_dev), rc);
- else
- dev_info(dev, "wq %s disabled\n", dev_name(&wq->conf_dev));
+ dev_info(dev, "wq %s disabled\n", dev_name(&wq->conf_dev));
}
static int idxd_config_bus_remove(struct device *dev)
if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags))
return -EPERM;
- if (wq->state != IDXD_WQ_DISABLED)
+ if (idxd->state == IDXD_DEV_ENABLED)
return -EPERM;
if (size + total_claimed_wq_size(idxd) - wq->size > idxd->max_wq_size)
{
struct idxd_device *idxd =
container_of(dev, struct idxd_device, conf_dev);
+ int i, rc = 0;
+
+ for (i = 0; i < 4; i++)
+ rc += sysfs_emit_at(buf, rc, "%#llx ", idxd->hw.opcap.bits[i]);
- return sprintf(buf, "%#llx\n", idxd->hw.opcap.bits[0]);
+ rc--;
+ rc += sysfs_emit_at(buf, rc, "\n");
+ return rc;
}
static DEVICE_ATTR_RO(op_cap);
rc = request_irq(pci_irq_vector(pdev, 0), plx_dma_isr, 0,
KBUILD_MODNAME, plxdev);
- if (rc) {
- kfree(plxdev);
- return rc;
- }
+ if (rc)
+ goto free_plx;
spin_lock_init(&plxdev->ring_lock);
tasklet_setup(&plxdev->desc_task, plx_dma_desc_task);
rc = dma_async_device_register(dma);
if (rc) {
pci_err(pdev, "Failed to register dma device: %d\n", rc);
- free_irq(pci_irq_vector(pdev, 0), plxdev);
- kfree(plxdev);
- return rc;
+ goto put_device;
}
pci_set_drvdata(pdev, plxdev);
return 0;
+
+put_device:
+ put_device(&pdev->dev);
+ free_irq(pci_irq_vector(pdev, 0), plxdev);
+free_plx:
+ kfree(plxdev);
+
+ return rc;
}
static int plx_dma_probe(struct pci_dev *pdev,
goto end;
}
if (!tdc->busy) {
- err = pm_runtime_get_sync(tdc->tdma->dev);
+ err = pm_runtime_resume_and_get(tdc->tdma->dev);
if (err < 0) {
dev_err(tdc2dev(tdc), "Failed to enable DMA\n");
goto end;
struct tegra_dma_channel *tdc = to_tegra_dma_chan(dc);
int err;
- err = pm_runtime_get_sync(tdc->tdma->dev);
+ err = pm_runtime_resume_and_get(tdc->tdma->dev);
if (err < 0) {
dev_err(tdc2dev(tdc), "Failed to synchronize DMA: %d\n", err);
return;
struct xilinx_dpdma_tx_desc *desc;
struct virt_dma_desc *vdesc;
u32 reg, channels;
+ bool first_frame;
lockdep_assert_held(&chan->lock);
chan->running = true;
}
- if (chan->video_group)
- channels = xilinx_dpdma_chan_video_group_ready(chan);
- else
- channels = BIT(chan->id);
-
- if (!channels)
- return;
-
vdesc = vchan_next_desc(&chan->vchan);
if (!vdesc)
return;
FIELD_PREP(XILINX_DPDMA_CH_DESC_START_ADDRE_MASK,
upper_32_bits(sw_desc->dma_addr)));
- if (chan->first_frame)
+ first_frame = chan->first_frame;
+ chan->first_frame = false;
+
+ if (chan->video_group) {
+ channels = xilinx_dpdma_chan_video_group_ready(chan);
+ /*
+ * Trigger the transfer only when all channels in the group are
+ * ready.
+ */
+ if (!channels)
+ return;
+ } else {
+ channels = BIT(chan->id);
+ }
+
+ if (first_frame)
reg = XILINX_DPDMA_GBL_TRIG_MASK(channels);
else
reg = XILINX_DPDMA_GBL_RETRIG_MASK(channels);
- chan->first_frame = false;
-
dpdma_write(xdev->reg, XILINX_DPDMA_GBL, reg);
}
*/
static void xilinx_dpdma_chan_done_irq(struct xilinx_dpdma_chan *chan)
{
- struct xilinx_dpdma_tx_desc *active = chan->desc.active;
+ struct xilinx_dpdma_tx_desc *active;
unsigned long flags;
spin_lock_irqsave(&chan->lock, flags);
xilinx_dpdma_debugfs_desc_done_irq(chan);
+ active = chan->desc.active;
if (active)
vchan_cyclic_callback(&active->vdesc);
else
sizeof(*edev->nh), GFP_KERNEL);
if (!edev->nh) {
ret = -ENOMEM;
+ device_unregister(&edev->dev);
goto err_dev;
}
struct client *client = file->private_data;
spinlock_t *client_list_lock = &client->lynx->client_list_lock;
struct nosy_stats stats;
+ int ret;
switch (cmd) {
case NOSY_IOC_GET_STATS:
return 0;
case NOSY_IOC_START:
+ ret = -EBUSY;
spin_lock_irq(client_list_lock);
- list_add_tail(&client->link, &client->lynx->client_list);
+ if (list_empty(&client->link)) {
+ list_add_tail(&client->link, &client->lynx->client_list);
+ ret = 0;
+ }
spin_unlock_irq(client_list_lock);
- return 0;
+ return ret;
case NOSY_IOC_STOP:
spin_lock_irq(client_list_lock);
struct driver_data *driver_data = packet->driver_data;
int ret = -ENOENT;
- tasklet_disable(&ctx->tasklet);
+ tasklet_disable_in_atomic(&ctx->tasklet);
if (packet->ack != 0)
goto out;
struct iso_context *ctx = container_of(base, struct iso_context, base);
int ret = 0;
- tasklet_disable(&ctx->context.tasklet);
+ tasklet_disable_in_atomic(&ctx->context.tasklet);
if (!test_and_set_bit_lock(0, &ctx->flushing_completions)) {
context_tasklet((unsigned long)&ctx->context);
}
/* first try to find a slot in an existing linked list entry */
- for (prsv = efi_memreserve_root->next; prsv; prsv = rsv->next) {
+ for (prsv = efi_memreserve_root->next; prsv; ) {
rsv = memremap(prsv, sizeof(*rsv), MEMREMAP_WB);
index = atomic_fetch_add_unless(&rsv->count, 1, rsv->size);
if (index < rsv->size) {
memunmap(rsv);
return efi_mem_reserve_iomem(addr, size);
}
+ prsv = rsv->next;
memunmap(rsv);
}
-Wno-pointer-sign \
$(call cc-disable-warning, address-of-packed-member) \
$(call cc-disable-warning, gnu) \
- -fno-asynchronous-unwind-tables
+ -fno-asynchronous-unwind-tables \
+ $(CLANG_FLAGS)
# arm64 uses the full KBUILD_CFLAGS so it's necessary to explicitly
# disable the stackleak plugin
return EFI_SUCCESS;
tg = (read_cpuid(ID_AA64MMFR0_EL1) >> ID_AA64MMFR0_TGRAN_SHIFT) & 0xf;
- if (tg != ID_AA64MMFR0_TGRAN_SUPPORTED) {
+ if (tg < ID_AA64MMFR0_TGRAN_SUPPORTED_MIN || tg > ID_AA64MMFR0_TGRAN_SUPPORTED_MAX) {
if (IS_ENABLED(CONFIG_ARM64_64K_PAGES))
efi_err("This 64 KB granular kernel is not supported by your CPU\n");
else
efi_err("Failed to install memreserve config table!\n");
}
+static u32 get_supported_rt_services(void)
+{
+ const efi_rt_properties_table_t *rt_prop_table;
+ u32 supported = EFI_RT_SUPPORTED_ALL;
+
+ rt_prop_table = get_efi_config_table(EFI_RT_PROPERTIES_TABLE_GUID);
+ if (rt_prop_table)
+ supported &= rt_prop_table->runtime_services_supported;
+
+ return supported;
+}
+
/*
* EFI entry point for the arm/arm64 EFI stubs. This is the entrypoint
* that is described in the PE/COFF header. Most of the code is the same
(prop_tbl->memory_protection_attribute &
EFI_PROPERTIES_RUNTIME_MEMORY_PROTECTION_NON_EXECUTABLE_PE_DATA);
+ /* force efi_novamap if SetVirtualAddressMap() is unsupported */
+ efi_novamap |= !(get_supported_rt_services() &
+ EFI_RT_SUPPORTED_SET_VIRTUAL_ADDRESS_MAP);
+
/* hibernation expects the runtime regions to stay in the same place */
if (!IS_ENABLED(CONFIG_HIBERNATION) && !efi_nokaslr && !flat_va_mapping) {
/*
}
break;
+ case EFI_UNSUPPORTED:
+ err = -EOPNOTSUPP;
+ status = EFI_NOT_FOUND;
+ break;
case EFI_NOT_FOUND:
break;
default:
/*
* Turris Mox rWTM firmware driver
*
- * Copyright (C) 2019 Marek Behun <marek.behun@nic.cz>
+ * Copyright (C) 2019 Marek Behún <kabel@kernel.org>
*/
#include <linux/armada-37xx-rwtm-mailbox.h>
MODULE_LICENSE("GPL v2");
MODULE_DESCRIPTION("Turris Mox rWTM firmware driver");
-MODULE_AUTHOR("Marek Behun <marek.behun@nic.cz>");
+MODULE_AUTHOR("Marek Behun <kabel@kernel.org>");
/*
* Turris Mox Moxtet GPIO expander
*
- * Copyright (C) 2018 Marek Behun <marek.behun@nic.cz>
+ * Copyright (C) 2018 Marek Behún <kabel@kernel.org>
*/
#include <linux/bitops.h>
};
module_moxtet_driver(moxtet_gpio_driver);
-MODULE_AUTHOR("Marek Behun <marek.behun@nic.cz>");
+MODULE_AUTHOR("Marek Behun <kabel@kernel.org>");
MODULE_DESCRIPTION("Turris Mox Moxtet GPIO expander");
MODULE_LICENSE("GPL v2");
#define OMAP4_GPIO_DEBOUNCINGTIME_MASK 0xFF
struct gpio_regs {
+ u32 sysconfig;
u32 irqenable1;
u32 irqenable2;
u32 wake_en;
const struct omap_gpio_reg_offs *regs = p->regs;
void __iomem *base = p->base;
+ p->context.sysconfig = readl_relaxed(base + regs->sysconfig);
p->context.ctrl = readl_relaxed(base + regs->ctrl);
p->context.oe = readl_relaxed(base + regs->direction);
p->context.wake_en = readl_relaxed(base + regs->wkup_en);
const struct omap_gpio_reg_offs *regs = bank->regs;
void __iomem *base = bank->base;
+ writel_relaxed(bank->context.sysconfig, base + regs->sysconfig);
writel_relaxed(bank->context.wake_en, base + regs->wkup_en);
writel_relaxed(bank->context.ctrl, base + regs->ctrl);
writel_relaxed(bank->context.leveldetect0, base + regs->leveldetect0);
bank->saved_datain = readl_relaxed(base + bank->regs->datain);
+ /* Save syconfig, it's runtime value can be different from init value */
+ if (bank->loses_context)
+ bank->context.sysconfig = readl_relaxed(base + bank->regs->sysconfig);
+
if (!bank->enabled_non_wakeup_gpios)
goto update_gpio_context_count;
static const struct omap_gpio_reg_offs omap2_gpio_regs = {
.revision = OMAP24XX_GPIO_REVISION,
+ .sysconfig = OMAP24XX_GPIO_SYSCONFIG,
.direction = OMAP24XX_GPIO_OE,
.datain = OMAP24XX_GPIO_DATAIN,
.dataout = OMAP24XX_GPIO_DATAOUT,
static const struct omap_gpio_reg_offs omap4_gpio_regs = {
.revision = OMAP4_GPIO_REVISION,
+ .sysconfig = OMAP4_GPIO_SYSCONFIG,
.direction = OMAP4_GPIO_OE,
.datain = OMAP4_GPIO_DATAIN,
.dataout = OMAP4_GPIO_DATAOUT,
#ifdef CONFIG_GPIO_PCA953X_IRQ
#include <linux/dmi.h>
-#include <linux/gpio.h>
-#include <linux/list.h>
+
+static const struct acpi_gpio_params pca953x_irq_gpios = { 0, 0, true };
+
+static const struct acpi_gpio_mapping pca953x_acpi_irq_gpios[] = {
+ { "irq-gpios", &pca953x_irq_gpios, 1, ACPI_GPIO_QUIRK_ABSOLUTE_NUMBER },
+ { }
+};
+
+static int pca953x_acpi_get_irq(struct device *dev)
+{
+ int ret;
+
+ ret = devm_acpi_dev_add_driver_gpios(dev, pca953x_acpi_irq_gpios);
+ if (ret)
+ dev_warn(dev, "can't add GPIO ACPI mapping\n");
+
+ ret = acpi_dev_gpio_irq_get_by(ACPI_COMPANION(dev), "irq-gpios", 0);
+ if (ret < 0)
+ return ret;
+
+ dev_info(dev, "ACPI interrupt quirk (IRQ %d)\n", ret);
+ return ret;
+}
static const struct dmi_system_id pca953x_dmi_acpi_irq_info[] = {
{
},
{}
};
-
-#ifdef CONFIG_ACPI
-static int pca953x_acpi_get_pin(struct acpi_resource *ares, void *data)
-{
- struct acpi_resource_gpio *agpio;
- int *pin = data;
-
- if (acpi_gpio_get_irq_resource(ares, &agpio))
- *pin = agpio->pin_table[0];
- return 1;
-}
-
-static int pca953x_acpi_find_pin(struct device *dev)
-{
- struct acpi_device *adev = ACPI_COMPANION(dev);
- int pin = -ENOENT, ret;
- LIST_HEAD(r);
-
- ret = acpi_dev_get_resources(adev, &r, pca953x_acpi_get_pin, &pin);
- acpi_dev_free_resource_list(&r);
- if (ret < 0)
- return ret;
-
- return pin;
-}
-#else
-static inline int pca953x_acpi_find_pin(struct device *dev) { return -ENXIO; }
-#endif
-
-static int pca953x_acpi_get_irq(struct device *dev)
-{
- int pin, ret;
-
- pin = pca953x_acpi_find_pin(dev);
- if (pin < 0)
- return pin;
-
- dev_info(dev, "Applying ACPI interrupt quirk (GPIO %d)\n", pin);
-
- if (!gpio_is_valid(pin))
- return -EINVAL;
-
- ret = gpio_request(pin, "pca953x interrupt");
- if (ret)
- return ret;
-
- ret = gpio_to_irq(pin);
-
- /* When pin is used as an IRQ, no need to keep it requested */
- gpio_free(pin);
-
- return ret;
-}
#endif
static const struct acpi_device_id pca953x_acpi_ids[] = {
int ret, value;
ret = request_threaded_irq(event->irq, NULL, event->handler,
- event->irqflags, "ACPI:Event", event);
+ event->irqflags | IRQF_ONESHOT, "ACPI:Event", event);
if (ret) {
dev_err(acpi_gpio->chip->parent,
"Failed to setup interrupt handler for %d\n",
if (!lookup->desc) {
const struct acpi_resource_gpio *agpio = &ares->data.gpio;
bool gpioint = agpio->connection_type == ACPI_RESOURCE_GPIO_TYPE_INT;
+ struct gpio_desc *desc;
u16 pin_index;
if (lookup->info.quirks & ACPI_GPIO_QUIRK_ONLY_GPIOIO && gpioint)
if (pin_index >= agpio->pin_table_length)
return 1;
- lookup->desc = acpi_get_gpiod(agpio->resource_source.string_ptr,
+ if (lookup->info.quirks & ACPI_GPIO_QUIRK_ABSOLUTE_NUMBER)
+ desc = gpio_to_desc(agpio->pin_table[pin_index]);
+ else
+ desc = acpi_get_gpiod(agpio->resource_source.string_ptr,
agpio->pin_table[pin_index]);
+ lookup->desc = desc;
lookup->info.pin_config = agpio->pin_config;
lookup->info.debounce = agpio->debounce_timeout;
lookup->info.gpioint = gpioint;
}
/**
- * acpi_dev_gpio_irq_get() - Find GpioInt and translate it to Linux IRQ number
+ * acpi_dev_gpio_irq_get_by() - Find GpioInt and translate it to Linux IRQ number
* @adev: pointer to a ACPI device to get IRQ from
+ * @name: optional name of GpioInt resource
* @index: index of GpioInt resource (starting from %0)
*
* If the device has one or more GpioInt resources, this function can be
* The function is idempotent, though each time it runs it will configure GPIO
* pin direction according to the flags in GpioInt resource.
*
+ * The function takes optional @name parameter. If the resource has a property
+ * name, then only those will be taken into account.
+ *
* Return: Linux IRQ number (> %0) on success, negative errno on failure.
*/
-int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index)
+int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *name, int index)
{
int idx, i;
unsigned int irq_flags;
struct acpi_gpio_info info;
struct gpio_desc *desc;
- desc = acpi_get_gpiod_by_index(adev, NULL, i, &info);
+ desc = acpi_get_gpiod_by_index(adev, name, i, &info);
/* Ignore -EPROBE_DEFER, it only matters if idx matches */
if (IS_ERR(desc) && PTR_ERR(desc) != -EPROBE_DEFER)
}
return -ENOENT;
}
-EXPORT_SYMBOL_GPL(acpi_dev_gpio_irq_get);
+EXPORT_SYMBOL_GPL(acpi_dev_gpio_irq_get_by);
static acpi_status
acpi_gpio_adr_space_handler(u32 function, acpi_physical_address address,
long gpio;
struct gpio_desc *desc;
int status;
+ struct gpio_chip *gc;
+ int offset;
status = kstrtol(buf, 0, &gpio);
if (status < 0)
pr_warn("%s: invalid GPIO %ld\n", __func__, gpio);
return -EINVAL;
}
+ gc = desc->gdev->chip;
+ offset = gpio_chip_hwgpio(desc);
+ if (!gpiochip_line_is_valid(gc, offset)) {
+ pr_warn("%s: GPIO %ld masked\n", __func__, gpio);
+ return -EINVAL;
+ }
/* No extra locking here; FLAG_SYSFS just signifies that the
* request and export were done by on behalf of userspace, so
*
* Looks for device property "gpio-line-names" and if it exists assigns
* GPIO line names for the chip. The memory allocated for the assigned
- * names belong to the underlying software node and should not be released
+ * names belong to the underlying firmware node and should not be released
* by the caller.
*/
static int devprop_gpiochip_set_names(struct gpio_chip *chip)
{
struct gpio_device *gdev = chip->gpiodev;
- struct device *dev = chip->parent;
+ struct fwnode_handle *fwnode = dev_fwnode(&gdev->dev);
const char **names;
int ret, i;
int count;
- /* GPIO chip may not have a parent device whose properties we inspect. */
- if (!dev)
- return 0;
-
- count = device_property_string_array_count(dev, "gpio-line-names");
+ count = fwnode_property_string_array_count(fwnode, "gpio-line-names");
if (count < 0)
return 0;
if (!names)
return -ENOMEM;
- ret = device_property_read_string_array(dev, "gpio-line-names",
+ ret = fwnode_property_read_string_array(fwnode, "gpio-line-names",
names, count);
if (ret < 0) {
dev_warn(&gdev->dev, "failed to read GPIO line names\n");
static void gpiodevice_release(struct device *dev)
{
- struct gpio_device *gdev = dev_get_drvdata(dev);
+ struct gpio_device *gdev = container_of(dev, struct gpio_device, dev);
+ unsigned long flags;
+ spin_lock_irqsave(&gpio_lock, flags);
list_del(&gdev->list);
+ spin_unlock_irqrestore(&gpio_lock, flags);
+
ida_free(&gpio_ida, gdev->id);
kfree_const(gdev->label);
kfree(gdev->descs);
struct lock_class_key *lock_key,
struct lock_class_key *request_key)
{
+ struct fwnode_handle *fwnode = gc->parent ? dev_fwnode(gc->parent) : NULL;
unsigned long flags;
int ret = 0;
unsigned i;
of_gpio_dev_init(gc, gdev);
+ /*
+ * Assign fwnode depending on the result of the previous calls,
+ * if none of them succeed, assign it to the parent's one.
+ */
+ gdev->dev.fwnode = dev_fwnode(&gdev->dev) ?: fwnode;
+
gdev->id = ida_alloc(&gpio_ida, GFP_KERNEL);
if (gdev->id < 0) {
ret = gdev->id;
goto err_free_ida;
device_initialize(&gdev->dev);
- dev_set_drvdata(&gdev->dev, gdev);
if (gc->parent && gc->parent->driver)
gdev->owner = gc->parent->driver->owner;
else if (gc->owner)
return ret;
}
- if (driver_register(&gpio_stub_drv) < 0) {
+ ret = driver_register(&gpio_stub_drv);
+ if (ret < 0) {
pr_err("gpiolib: could not register GPIO stub driver\n");
bus_unregister(&gpio_bus_type);
return ret;
config DRM_RADEON
tristate "ATI Radeon"
depends on DRM && PCI && MMU
+ depends on AGP || !AGP
select FW_LOADER
select DRM_KMS_HELPER
select DRM_TTM
extern uint amdgpu_dc_feature_mask;
extern uint amdgpu_dc_debug_mask;
extern uint amdgpu_dm_abm_level;
+extern int amdgpu_backlight;
extern struct amdgpu_mgpu_info mgpu_info;
extern int amdgpu_ras_enable;
extern uint amdgpu_ras_mask;
/* s3/s4 mask */
bool in_suspend;
- bool in_hibernate;
-
- /*
- * The combination flag in_poweroff_reboot_com used to identify the poweroff
- * and reboot opt in the s0i3 system-wide suspend.
- */
- bool in_poweroff_reboot_com;
+ bool in_s3;
+ bool in_s4;
+ bool in_s0ix;
atomic_t in_gpu_reset;
enum pp_mp1_state mp1_state;
*/
bool amdgpu_acpi_is_s0ix_supported(struct amdgpu_device *adev)
{
-#if defined(CONFIG_AMD_PMC)
+#if defined(CONFIG_AMD_PMC) || defined(CONFIG_AMD_PMC_MODULE)
if (acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0) {
if (adev->flags & AMD_IS_APU)
return true;
i = state == AMD_CG_STATE_GATE ? j : adev->num_ip_blocks - j - 1;
if (!adev->ip_blocks[i].status.late_initialized)
continue;
+ /* skip CG for GFX on S0ix */
+ if (adev->in_s0ix &&
+ adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX)
+ continue;
/* skip CG for VCE/UVD, it's handled specially */
if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD &&
adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE &&
i = state == AMD_PG_STATE_GATE ? j : adev->num_ip_blocks - j - 1;
if (!adev->ip_blocks[i].status.late_initialized)
continue;
+ /* skip PG for GFX on S0ix */
+ if (adev->in_s0ix &&
+ adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX)
+ continue;
/* skip CG for VCE/UVD, it's handled specially */
if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD &&
adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE &&
{
int i, r;
- if (adev->in_poweroff_reboot_com ||
- !amdgpu_acpi_is_s0ix_supported(adev) || amdgpu_in_reset(adev)) {
- amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE);
- amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE);
- }
+ amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE);
+ amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE);
for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
if (!adev->ip_blocks[i].status.valid)
{
int i, r;
+ if (adev->in_s0ix)
+ amdgpu_gfx_state_change_set(adev, sGpuChangeState_D3Entry);
+
for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
if (!adev->ip_blocks[i].status.valid)
continue;
adev->ip_blocks[i].status.hw = false;
continue;
}
+
+ /* skip suspend of gfx and psp for S0ix
+ * gfx is in gfxoff state, so on resume it will exit gfxoff just
+ * like at runtime. PSP is also part of the always on hardware
+ * so no need to suspend it.
+ */
+ if (adev->in_s0ix &&
+ (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP ||
+ adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX))
+ continue;
+
/* XXX handle errors */
r = adev->ip_blocks[i].version->funcs->suspend(adev);
/* XXX handle errors */
*/
int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
{
- struct amdgpu_device *adev;
- struct drm_crtc *crtc;
- struct drm_connector *connector;
- struct drm_connector_list_iter iter;
+ struct amdgpu_device *adev = drm_to_adev(dev);
int r;
- adev = drm_to_adev(dev);
-
if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
return 0;
cancel_delayed_work_sync(&adev->delayed_init_work);
- if (!amdgpu_device_has_dc_support(adev)) {
- /* turn off display hw */
- drm_modeset_lock_all(dev);
- drm_connector_list_iter_begin(dev, &iter);
- drm_for_each_connector_iter(connector, &iter)
- drm_helper_connector_dpms(connector,
- DRM_MODE_DPMS_OFF);
- drm_connector_list_iter_end(&iter);
- drm_modeset_unlock_all(dev);
- /* unpin the front buffers and cursors */
- list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
- struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
- struct drm_framebuffer *fb = crtc->primary->fb;
- struct amdgpu_bo *robj;
-
- if (amdgpu_crtc->cursor_bo && !adev->enable_virtual_display) {
- struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
- r = amdgpu_bo_reserve(aobj, true);
- if (r == 0) {
- amdgpu_bo_unpin(aobj);
- amdgpu_bo_unreserve(aobj);
- }
- }
-
- if (fb == NULL || fb->obj[0] == NULL) {
- continue;
- }
- robj = gem_to_amdgpu_bo(fb->obj[0]);
- /* don't unpin kernel fb objects */
- if (!amdgpu_fbdev_robj_is_fb(adev, robj)) {
- r = amdgpu_bo_reserve(robj, true);
- if (r == 0) {
- amdgpu_bo_unpin(robj);
- amdgpu_bo_unreserve(robj);
- }
- }
- }
- }
-
amdgpu_ras_suspend(adev);
r = amdgpu_device_ip_suspend_phase1(adev);
- amdgpu_amdkfd_suspend(adev, adev->in_runpm);
+ if (!adev->in_s0ix)
+ amdgpu_amdkfd_suspend(adev, adev->in_runpm);
/* evict vram memory */
amdgpu_bo_evict_vram(adev);
amdgpu_fence_driver_suspend(adev);
- if (adev->in_poweroff_reboot_com ||
- !amdgpu_acpi_is_s0ix_supported(adev) || amdgpu_in_reset(adev))
- r = amdgpu_device_ip_suspend_phase2(adev);
- else
- amdgpu_gfx_state_change_set(adev, sGpuChangeState_D3Entry);
+ r = amdgpu_device_ip_suspend_phase2(adev);
/* evict remaining vram memory
* This second call to evict vram is to evict the gart page table
* using the CPU.
*/
int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
{
- struct drm_connector *connector;
- struct drm_connector_list_iter iter;
struct amdgpu_device *adev = drm_to_adev(dev);
- struct drm_crtc *crtc;
int r = 0;
if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
return 0;
- if (amdgpu_acpi_is_s0ix_supported(adev))
+ if (adev->in_s0ix)
amdgpu_gfx_state_change_set(adev, sGpuChangeState_D0Entry);
/* post card */
queue_delayed_work(system_wq, &adev->delayed_init_work,
msecs_to_jiffies(AMDGPU_RESUME_MS));
- if (!amdgpu_device_has_dc_support(adev)) {
- /* pin cursors */
- list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
- struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-
- if (amdgpu_crtc->cursor_bo && !adev->enable_virtual_display) {
- struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
- r = amdgpu_bo_reserve(aobj, true);
- if (r == 0) {
- r = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM);
- if (r != 0)
- dev_err(adev->dev, "Failed to pin cursor BO (%d)\n", r);
- amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj);
- amdgpu_bo_unreserve(aobj);
- }
- }
- }
+ if (!adev->in_s0ix) {
+ r = amdgpu_amdkfd_resume(adev, adev->in_runpm);
+ if (r)
+ return r;
}
- r = amdgpu_amdkfd_resume(adev, adev->in_runpm);
- if (r)
- return r;
/* Make sure IB tests flushed */
flush_delayed_work(&adev->delayed_init_work);
- /* blat the mode back in */
- if (fbcon) {
- if (!amdgpu_device_has_dc_support(adev)) {
- /* pre DCE11 */
- drm_helper_resume_force_mode(dev);
-
- /* turn on display hw */
- drm_modeset_lock_all(dev);
-
- drm_connector_list_iter_begin(dev, &iter);
- drm_for_each_connector_iter(connector, &iter)
- drm_helper_connector_dpms(connector,
- DRM_MODE_DPMS_ON);
- drm_connector_list_iter_end(&iter);
-
- drm_modeset_unlock_all(dev);
- }
+ if (fbcon)
amdgpu_fbdev_set_suspend(adev, 0);
- }
drm_kms_helper_poll_enable(dev);
return amdgpu_display_get_crtc_scanoutpos(dev, pipe, 0, vpos, hpos,
stime, etime, mode);
}
+
+int amdgpu_display_suspend_helper(struct amdgpu_device *adev)
+{
+ struct drm_device *dev = adev_to_drm(adev);
+ struct drm_crtc *crtc;
+ struct drm_connector *connector;
+ struct drm_connector_list_iter iter;
+ int r;
+
+ /* turn off display hw */
+ drm_modeset_lock_all(dev);
+ drm_connector_list_iter_begin(dev, &iter);
+ drm_for_each_connector_iter(connector, &iter)
+ drm_helper_connector_dpms(connector,
+ DRM_MODE_DPMS_OFF);
+ drm_connector_list_iter_end(&iter);
+ drm_modeset_unlock_all(dev);
+ /* unpin the front buffers and cursors */
+ list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+ struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
+ struct drm_framebuffer *fb = crtc->primary->fb;
+ struct amdgpu_bo *robj;
+
+ if (amdgpu_crtc->cursor_bo && !adev->enable_virtual_display) {
+ struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
+ r = amdgpu_bo_reserve(aobj, true);
+ if (r == 0) {
+ amdgpu_bo_unpin(aobj);
+ amdgpu_bo_unreserve(aobj);
+ }
+ }
+
+ if (fb == NULL || fb->obj[0] == NULL) {
+ continue;
+ }
+ robj = gem_to_amdgpu_bo(fb->obj[0]);
+ /* don't unpin kernel fb objects */
+ if (!amdgpu_fbdev_robj_is_fb(adev, robj)) {
+ r = amdgpu_bo_reserve(robj, true);
+ if (r == 0) {
+ amdgpu_bo_unpin(robj);
+ amdgpu_bo_unreserve(robj);
+ }
+ }
+ }
+ return r;
+}
+
+int amdgpu_display_resume_helper(struct amdgpu_device *adev)
+{
+ struct drm_device *dev = adev_to_drm(adev);
+ struct drm_connector *connector;
+ struct drm_connector_list_iter iter;
+ struct drm_crtc *crtc;
+ int r;
+
+ /* pin cursors */
+ list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+ struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
+
+ if (amdgpu_crtc->cursor_bo && !adev->enable_virtual_display) {
+ struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
+ r = amdgpu_bo_reserve(aobj, true);
+ if (r == 0) {
+ r = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM);
+ if (r != 0)
+ dev_err(adev->dev, "Failed to pin cursor BO (%d)\n", r);
+ amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj);
+ amdgpu_bo_unreserve(aobj);
+ }
+ }
+ }
+
+ drm_helper_resume_force_mode(dev);
+
+ /* turn on display hw */
+ drm_modeset_lock_all(dev);
+
+ drm_connector_list_iter_begin(dev, &iter);
+ drm_for_each_connector_iter(connector, &iter)
+ drm_helper_connector_dpms(connector,
+ DRM_MODE_DPMS_ON);
+ drm_connector_list_iter_end(&iter);
+
+ drm_modeset_unlock_all(dev);
+
+ return 0;
+}
+
const struct drm_format_info *
amdgpu_lookup_format_info(u32 format, uint64_t modifier);
+int amdgpu_display_suspend_helper(struct amdgpu_device *adev);
+int amdgpu_display_resume_helper(struct amdgpu_device *adev);
+
#endif
MODULE_PARM_DESC(abmlevel, "ABM level (0 = off (default), 1-4 = backlight reduction level) ");
module_param_named(abmlevel, amdgpu_dm_abm_level, uint, 0444);
+int amdgpu_backlight = -1;
+MODULE_PARM_DESC(backlight, "Backlight control (0 = pwm, 1 = aux, -1 auto (default))");
+module_param_named(backlight, amdgpu_backlight, bint, 0444);
+
/**
* DOC: tmz (int)
* Trusted Memory Zone (TMZ) is a method to protect data being written
{0x1002, 0x73A3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
{0x1002, 0x73AB, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
{0x1002, 0x73AE, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
+ {0x1002, 0x73AF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
{0x1002, 0x73BF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
/* Van Gogh */
*/
if (!amdgpu_passthrough(adev))
adev->mp1_state = PP_MP1_STATE_UNLOAD;
- adev->in_poweroff_reboot_com = true;
amdgpu_device_ip_suspend(adev);
- adev->in_poweroff_reboot_com = false;
adev->mp1_state = PP_MP1_STATE_NONE;
}
static int amdgpu_pmops_suspend(struct device *dev)
{
struct drm_device *drm_dev = dev_get_drvdata(dev);
+ struct amdgpu_device *adev = drm_to_adev(drm_dev);
+ int r;
- return amdgpu_device_suspend(drm_dev, true);
+ if (amdgpu_acpi_is_s0ix_supported(adev))
+ adev->in_s0ix = true;
+ adev->in_s3 = true;
+ r = amdgpu_device_suspend(drm_dev, true);
+ adev->in_s3 = false;
+
+ return r;
}
static int amdgpu_pmops_resume(struct device *dev)
{
struct drm_device *drm_dev = dev_get_drvdata(dev);
+ struct amdgpu_device *adev = drm_to_adev(drm_dev);
+ int r;
- return amdgpu_device_resume(drm_dev, true);
+ r = amdgpu_device_resume(drm_dev, true);
+ if (amdgpu_acpi_is_s0ix_supported(adev))
+ adev->in_s0ix = false;
+ return r;
}
static int amdgpu_pmops_freeze(struct device *dev)
struct amdgpu_device *adev = drm_to_adev(drm_dev);
int r;
- adev->in_hibernate = true;
+ adev->in_s4 = true;
r = amdgpu_device_suspend(drm_dev, true);
- adev->in_hibernate = false;
+ adev->in_s4 = false;
if (r)
return r;
return amdgpu_asic_reset(adev);
static int amdgpu_pmops_poweroff(struct device *dev)
{
struct drm_device *drm_dev = dev_get_drvdata(dev);
- struct amdgpu_device *adev = drm_to_adev(drm_dev);
- int r;
- adev->in_poweroff_reboot_com = true;
- r = amdgpu_device_suspend(drm_dev, true);
- adev->in_poweroff_reboot_com = false;
- return r;
+ return amdgpu_device_suspend(drm_dev, true);
}
static int amdgpu_pmops_restore(struct device *dev)
size = mode_cmd->pitches[0] * height;
aligned_size = ALIGN(size, PAGE_SIZE);
ret = amdgpu_gem_object_create(adev, aligned_size, 0, domain, flags,
- ttm_bo_type_kernel, NULL, &gobj);
+ ttm_bo_type_device, NULL, &gobj);
if (ret) {
pr_err("failed to allocate framebuffer (%d)\n", aligned_size);
return -ENOMEM;
dev_info->high_va_offset = AMDGPU_GMC_HOLE_END;
dev_info->high_va_max = AMDGPU_GMC_HOLE_END | vm_size;
}
- dev_info->virtual_address_alignment = max((int)PAGE_SIZE, AMDGPU_GPU_PAGE_SIZE);
+ dev_info->virtual_address_alignment = max_t(u32, PAGE_SIZE, AMDGPU_GPU_PAGE_SIZE);
dev_info->pte_fragment_size = (1 << adev->vm_manager.fragment_size) * AMDGPU_GPU_PAGE_SIZE;
- dev_info->gart_page_size = AMDGPU_GPU_PAGE_SIZE;
+ dev_info->gart_page_size = max_t(u32, PAGE_SIZE, AMDGPU_GPU_PAGE_SIZE);
dev_info->cu_active_number = adev->gfx.cu_info.number;
dev_info->cu_ao_mask = adev->gfx.cu_info.ao_cu_mask;
dev_info->ce_ram_size = adev->gfx.ce_ram_size;
{
struct ttm_resource_manager *man;
- /* late 2.6.33 fix IGP hibernate - we need pm ops to do this correct */
-#ifndef CONFIG_HIBERNATION
- if (adev->flags & AMD_IS_APU) {
- /* Useless to evict on IGP chips */
+ if (adev->in_s3 && (adev->flags & AMD_IS_APU)) {
+ /* No need to evict vram on APUs for suspend to ram */
return 0;
}
-#endif
man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM);
return ttm_resource_manager_evict_all(&adev->mman.bdev, man);
/* Allocate an SG array and squash pages into it */
r = sg_alloc_table_from_pages(ttm->sg, ttm->pages, ttm->num_pages, 0,
- ttm->num_pages << PAGE_SHIFT,
+ (u64)ttm->num_pages << PAGE_SHIFT,
GFP_KERNEL);
if (r)
goto release_sg;
uint64_t eaddr;
/* validate the parameters */
- if (saddr & AMDGPU_GPU_PAGE_MASK || offset & AMDGPU_GPU_PAGE_MASK ||
- size == 0 || size & AMDGPU_GPU_PAGE_MASK)
+ if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK ||
+ size == 0 || size & ~PAGE_MASK)
return -EINVAL;
/* make sure object fit at this offset */
int r;
/* validate the parameters */
- if (saddr & AMDGPU_GPU_PAGE_MASK || offset & AMDGPU_GPU_PAGE_MASK ||
- size == 0 || size & AMDGPU_GPU_PAGE_MASK)
+ if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK ||
+ size == 0 || size & ~PAGE_MASK)
return -EINVAL;
/* make sure object fit at this offset */
after->start = eaddr + 1;
after->last = tmp->last;
after->offset = tmp->offset;
- after->offset += after->start - tmp->start;
+ after->offset += (after->start - tmp->start) << PAGE_SHIFT;
after->flags = tmp->flags;
after->bo_va = tmp->bo_va;
list_add(&after->list, &tmp->bo_va->invalids);
struct amdgpu_bo *root;
uint64_t value, flags;
struct amdgpu_vm *vm;
- long r;
+ int r;
spin_lock(&adev->vm_manager.pasid_lock);
vm = idr_find(&adev->vm_manager.pasid_idr, pasid);
value = 0;
}
+ r = dma_resv_reserve_shared(root->tbo.base.resv, 1);
+ if (r) {
+ pr_debug("failed %d to reserve fence slot\n", r);
+ goto error_unlock;
+ }
+
r = amdgpu_vm_bo_update_mapping(adev, adev, vm, true, false, NULL, addr,
addr, flags, value, NULL, NULL,
NULL);
error_unlock:
amdgpu_bo_unreserve(root);
if (r < 0)
- DRM_ERROR("Can't handle page fault (%ld)\n", r);
+ DRM_ERROR("Can't handle page fault (%d)\n", r);
error_unref:
amdgpu_bo_unref(&root);
static int dce_v10_0_suspend(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ int r;
+
+ r = amdgpu_display_suspend_helper(adev);
+ if (r)
+ return r;
adev->mode_info.bl_level =
amdgpu_atombios_encoder_get_backlight_level_from_reg(adev);
amdgpu_display_backlight_set_level(adev, adev->mode_info.bl_encoder,
bl_level);
}
+ if (ret)
+ return ret;
- return ret;
+ return amdgpu_display_resume_helper(adev);
}
static bool dce_v10_0_is_idle(void *handle)
static int dce_v11_0_suspend(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ int r;
+
+ r = amdgpu_display_suspend_helper(adev);
+ if (r)
+ return r;
adev->mode_info.bl_level =
amdgpu_atombios_encoder_get_backlight_level_from_reg(adev);
amdgpu_display_backlight_set_level(adev, adev->mode_info.bl_encoder,
bl_level);
}
+ if (ret)
+ return ret;
- return ret;
+ return amdgpu_display_resume_helper(adev);
}
static bool dce_v11_0_is_idle(void *handle)
static int dce_v6_0_suspend(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ int r;
+ r = amdgpu_display_suspend_helper(adev);
+ if (r)
+ return r;
adev->mode_info.bl_level =
amdgpu_atombios_encoder_get_backlight_level_from_reg(adev);
amdgpu_display_backlight_set_level(adev, adev->mode_info.bl_encoder,
bl_level);
}
+ if (ret)
+ return ret;
- return ret;
+ return amdgpu_display_resume_helper(adev);
}
static bool dce_v6_0_is_idle(void *handle)
static int dce_v8_0_suspend(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ int r;
+
+ r = amdgpu_display_suspend_helper(adev);
+ if (r)
+ return r;
adev->mode_info.bl_level =
amdgpu_atombios_encoder_get_backlight_level_from_reg(adev);
amdgpu_display_backlight_set_level(adev, adev->mode_info.bl_encoder,
bl_level);
}
+ if (ret)
+ return ret;
- return ret;
+ return amdgpu_display_resume_helper(adev);
}
static bool dce_v8_0_is_idle(void *handle)
#include "dce_v11_0.h"
#include "dce_virtual.h"
#include "ivsrcid/ivsrcid_vislands30.h"
+#include "amdgpu_display.h"
#define DCE_VIRTUAL_VBLANK_PERIOD 16666666
static int dce_virtual_suspend(void *handle)
{
+ struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ int r;
+
+ r = amdgpu_display_suspend_helper(adev);
+ if (r)
+ return r;
return dce_virtual_hw_fini(handle);
}
static int dce_virtual_resume(void *handle)
{
- return dce_virtual_hw_init(handle);
+ struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ int r;
+
+ r = dce_virtual_hw_init(handle);
+ if (r)
+ return r;
+ return amdgpu_display_resume_helper(adev);
}
static bool dce_virtual_is_idle(void *handle)
SOC15_REG_GOLDEN_VALUE(GC, 0, mmCPF_GCR_CNTL, 0x0007ffff, 0x0000c000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0x00000280, 0x00000280),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0x07800000, 0x00800000),
- SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x00001d00, 0x00000500),
+ SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Sienna_Cichlid, 0x00001d00, 0x00000500),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmGE_PC_CNTL, 0x003c0000, 0x00280400),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2A_ADDR_MATCH_MASK, 0xffffffff, 0xffffffcf),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_ADDR_MATCH_MASK, 0xffffffff, 0xffffffcf),
/* Wait till CP writes sync code: */
status = amdkfd_fence_wait_timeout(
- (unsigned int *) rm_state,
+ rm_state,
QUEUESTATE__ACTIVE, 1500);
kfd_gtt_sa_free(dbgdev->dev, mem_obj);
if (retval)
goto fail_allocate_vidmem;
- dqm->fence_addr = dqm->fence_mem->cpu_ptr;
+ dqm->fence_addr = (uint64_t *)dqm->fence_mem->cpu_ptr;
dqm->fence_gpu_addr = dqm->fence_mem->gpu_addr;
init_interrupts(dqm);
return retval;
}
-int amdkfd_fence_wait_timeout(unsigned int *fence_addr,
- unsigned int fence_value,
+int amdkfd_fence_wait_timeout(uint64_t *fence_addr,
+ uint64_t fence_value,
unsigned int timeout_ms)
{
unsigned long end_jiffies = msecs_to_jiffies(timeout_ms) + jiffies;
uint16_t vmid_pasid[VMID_NUM];
uint64_t pipelines_addr;
uint64_t fence_gpu_addr;
- unsigned int *fence_addr;
+ uint64_t *fence_addr;
struct kfd_mem_obj *fence_mem;
bool active_runlist;
int sched_policy;
}
int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address,
- uint32_t fence_value)
+ uint64_t fence_value)
{
uint32_t *buffer, size;
int retval = 0;
}
static int pm_query_status_v9(struct packet_manager *pm, uint32_t *buffer,
- uint64_t fence_address, uint32_t fence_value)
+ uint64_t fence_address, uint64_t fence_value)
{
struct pm4_mes_query_status *packet;
}
static int pm_query_status_vi(struct packet_manager *pm, uint32_t *buffer,
- uint64_t fence_address, uint32_t fence_value)
+ uint64_t fence_address, uint64_t fence_value)
{
struct pm4_mes_query_status *packet;
u32 *ctl_stack_used_size,
u32 *save_area_used_size);
-int amdkfd_fence_wait_timeout(unsigned int *fence_addr,
- unsigned int fence_value,
+int amdkfd_fence_wait_timeout(uint64_t *fence_addr,
+ uint64_t fence_value,
unsigned int timeout_ms);
/* Packet Manager */
uint32_t filter_param, bool reset,
unsigned int sdma_engine);
int (*query_status)(struct packet_manager *pm, uint32_t *buffer,
- uint64_t fence_address, uint32_t fence_value);
+ uint64_t fence_address, uint64_t fence_value);
int (*release_mem)(uint64_t gpu_addr, uint32_t *buffer);
/* Packet sizes */
struct scheduling_resources *res);
int pm_send_runlist(struct packet_manager *pm, struct list_head *dqm_queues);
int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address,
- uint32_t fence_value);
+ uint64_t fence_value);
int pm_send_unmap_queue(struct packet_manager *pm, enum kfd_queue_type type,
enum kfd_unmap_queues_filter mode,
caps->ext_caps->bits.hdr_aux_backlight_control == 1)
caps->aux_support = true;
+ if (amdgpu_backlight == 0)
+ caps->aux_support = false;
+ else if (amdgpu_backlight == 1)
+ caps->aux_support = true;
+
/* From the specification (CTA-861-G), for calculating the maximum
* luminance we need to use:
* Luminance = 50*2**(CV/32)
#endif
}
-static int set_backlight_via_aux(struct dc_link *link, uint32_t brightness)
-{
- bool rc;
-
- if (!link)
- return 1;
-
- rc = dc_link_set_backlight_level_nits(link, true, brightness,
- AUX_BL_DEFAULT_TRANSITION_TIME_MS);
-
- return rc ? 0 : 1;
-}
-
static int get_brightness_range(const struct amdgpu_dm_backlight_caps *caps,
unsigned *min, unsigned *max)
{
brightness = convert_brightness_from_user(&caps, bd->props.brightness);
// Change brightness based on AUX property
if (caps.aux_support)
- return set_backlight_via_aux(link, brightness);
-
- rc = dc_link_set_backlight_level(dm->backlight_link, brightness, 0);
+ rc = dc_link_set_backlight_level_nits(link, true, brightness,
+ AUX_BL_DEFAULT_TRANSITION_TIME_MS);
+ else
+ rc = dc_link_set_backlight_level(dm->backlight_link, brightness, 0);
return rc ? 0 : 1;
}
static int amdgpu_dm_backlight_get_brightness(struct backlight_device *bd)
{
struct amdgpu_display_manager *dm = bl_get_data(bd);
- int ret = dc_link_get_backlight_level(dm->backlight_link);
+ struct amdgpu_dm_backlight_caps caps;
- if (ret == DC_ERROR_UNEXPECTED)
- return bd->props.brightness;
- return convert_brightness_to_user(&dm->backlight_caps, ret);
+ amdgpu_dm_update_backlight_caps(dm);
+ caps = dm->backlight_caps;
+
+ if (caps.aux_support) {
+ struct dc_link *link = (struct dc_link *)dm->backlight_link;
+ u32 avg, peak;
+ bool rc;
+
+ rc = dc_link_get_backlight_level_nits(link, &avg, &peak);
+ if (!rc)
+ return bd->props.brightness;
+ return convert_brightness_to_user(&caps, avg);
+ } else {
+ int ret = dc_link_get_backlight_level(dm->backlight_link);
+
+ if (ret == DC_ERROR_UNEXPECTED)
+ return bd->props.brightness;
+ return convert_brightness_to_user(&caps, ret);
+ }
}
static const struct backlight_ops amdgpu_dm_backlight_ops = {
return true;
/*
- * The arbitrary tiling support for multiplane formats has not been hooked
- * up.
- */
- if (info->num_planes > 1)
- return false;
-
- /*
* For D swizzle the canonical modifier depends on the bpp, so check
* it here.
*/
/* Per radeonsi comments 16/64 bpp are more complicated. */
if (info->cpp[0] != 4)
return false;
+ /* We support multi-planar formats, but not when combined with
+ * additional DCC metadata planes. */
+ if (info->num_planes > 1)
+ return false;
}
return true;
AMD_FMT_MOD_SET(DCC_CONSTANT_ENCODE, 1) |
AMD_FMT_MOD_SET(DCC_INDEPENDENT_64B, 1) |
AMD_FMT_MOD_SET(DCC_INDEPENDENT_128B, 1) |
- AMD_FMT_MOD_SET(DCC_MAX_COMPRESSED_BLOCK, AMD_FMT_MOD_DCC_BLOCK_128B));
+ AMD_FMT_MOD_SET(DCC_MAX_COMPRESSED_BLOCK, AMD_FMT_MOD_DCC_BLOCK_64B));
add_modifier(mods, size, capacity, AMD_FMT_MOD |
AMD_FMT_MOD_SET(TILE, AMD_FMT_MOD_TILE_GFX9_64K_R_X) |
AMD_FMT_MOD_SET(DCC_CONSTANT_ENCODE, 1) |
AMD_FMT_MOD_SET(DCC_INDEPENDENT_64B, 1) |
AMD_FMT_MOD_SET(DCC_INDEPENDENT_128B, 1) |
- AMD_FMT_MOD_SET(DCC_MAX_COMPRESSED_BLOCK, AMD_FMT_MOD_DCC_BLOCK_128B));
+ AMD_FMT_MOD_SET(DCC_MAX_COMPRESSED_BLOCK, AMD_FMT_MOD_DCC_BLOCK_64B));
add_modifier(mods, size, capacity, AMD_FMT_MOD |
AMD_FMT_MOD_SET(TILE, AMD_FMT_MOD_TILE_GFX9_64K_R_X) |
dc_plane_state->global_alpha_value = plane_info.global_alpha_value;
dc_plane_state->dcc = plane_info.dcc;
dc_plane_state->layer_index = plane_info.layer_index; // Always returns 0
+ dc_plane_state->flip_int_enabled = true;
/*
* Always set input transfer function, since plane state is refreshed
if (pipe_ctx->plane_state == NULL)
frame_ramp = 0;
} else {
- ASSERT(false);
return false;
}
int layer_index;
union surface_update_flags update_flags;
+ bool flip_int_enabled;
/* private to DC core */
struct dc_plane_status status;
struct dc_context *ctx;
REG_UPDATE(DCHUBP_CNTL, HUBP_DISABLE, reset ? 1 : 0);
}
+void hubp1_set_flip_int(struct hubp *hubp)
+{
+ struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
+
+ REG_UPDATE(DCSURF_SURFACE_FLIP_INTERRUPT,
+ SURFACE_FLIP_INT_MASK, 1);
+
+ return;
+}
+
void hubp1_init(struct hubp *hubp)
{
//do nothing
.dmdata_load = NULL,
.hubp_soft_reset = hubp1_soft_reset,
.hubp_in_blank = hubp1_in_blank,
+ .hubp_set_flip_int = hubp1_set_flip_int,
};
/*****************************************/
SRI(DCSURF_SURFACE_EARLIEST_INUSE_C, HUBPREQ, id),\
SRI(DCSURF_SURFACE_EARLIEST_INUSE_HIGH_C, HUBPREQ, id),\
SRI(DCSURF_SURFACE_CONTROL, HUBPREQ, id),\
+ SRI(DCSURF_SURFACE_FLIP_INTERRUPT, HUBPREQ, id),\
SRI(HUBPRET_CONTROL, HUBPRET, id),\
SRI(DCN_EXPANSION_MODE, HUBPREQ, id),\
SRI(DCHUBP_REQ_SIZE_CONFIG, HUBP, id),\
uint32_t DCSURF_SURFACE_EARLIEST_INUSE_C; \
uint32_t DCSURF_SURFACE_EARLIEST_INUSE_HIGH_C; \
uint32_t DCSURF_SURFACE_CONTROL; \
+ uint32_t DCSURF_SURFACE_FLIP_INTERRUPT; \
uint32_t HUBPRET_CONTROL; \
uint32_t DCN_EXPANSION_MODE; \
uint32_t DCHUBP_REQ_SIZE_CONFIG; \
HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_META_SURFACE_TMZ_C, mask_sh),\
HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_EN, mask_sh),\
HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_IND_64B_BLK, mask_sh),\
+ HUBP_SF(HUBPREQ0_DCSURF_SURFACE_FLIP_INTERRUPT, SURFACE_FLIP_INT_MASK, mask_sh),\
HUBP_SF(HUBPRET0_HUBPRET_CONTROL, DET_BUF_PLANE1_BASE_ADDRESS, mask_sh),\
HUBP_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CB_B, mask_sh),\
HUBP_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CR_R, mask_sh),\
type PRIMARY_SURFACE_DCC_IND_64B_BLK;\
type SECONDARY_SURFACE_DCC_EN;\
type SECONDARY_SURFACE_DCC_IND_64B_BLK;\
+ type SURFACE_FLIP_INT_MASK;\
type DET_BUF_PLANE1_BASE_ADDRESS;\
type CROSSBAR_SRC_CB_B;\
type CROSSBAR_SRC_CR_R;\
bool hubp1_in_blank(struct hubp *hubp);
void hubp1_soft_reset(struct hubp *hubp, bool reset);
+void hubp1_set_flip_int(struct hubp *hubp);
+
#endif
if (dc->debug.sanity_checks) {
hws->funcs.verify_allow_pstate_change_high(dc);
}
+
+ if (!pipe_ctx->top_pipe
+ && pipe_ctx->plane_state
+ && pipe_ctx->plane_state->flip_int_enabled
+ && pipe_ctx->plane_res.hubp->funcs->hubp_set_flip_int)
+ pipe_ctx->plane_res.hubp->funcs->hubp_set_flip_int(pipe_ctx->plane_res.hubp);
+
}
void dcn10_program_gamut_remap(struct pipe_ctx *pipe_ctx)
.validate_dml_output = hubp2_validate_dml_output,
.hubp_in_blank = hubp1_in_blank,
.hubp_soft_reset = hubp1_soft_reset,
+ .hubp_set_flip_int = hubp1_set_flip_int,
};
pipe_ctx->plane_res.hubp->funcs->hubp_set_vm_system_aperture_settings(pipe_ctx->plane_res.hubp, &apt);
}
+ if (!pipe_ctx->top_pipe
+ && pipe_ctx->plane_state
+ && pipe_ctx->plane_state->flip_int_enabled
+ && pipe_ctx->plane_res.hubp->funcs->hubp_set_flip_int)
+ pipe_ctx->plane_res.hubp->funcs->hubp_set_flip_int(pipe_ctx->plane_res.hubp);
+
// if (dc->debug.sanity_checks) {
// dcn10_verify_allow_pstate_change_high(dc);
// }
if (pipe_ctx->update_flags.bits.enable || pipe_ctx->update_flags.bits.opp_changed
|| pipe_ctx->stream->update_flags.bits.gamut_remap
|| pipe_ctx->stream->update_flags.bits.out_csc) {
- struct mpc *mpc = pipe_ctx->stream_res.opp->ctx->dc->res_pool->mpc;
-
- if (mpc->funcs->set_gamut_remap) {
- int i;
- int mpcc_id = hubp->inst;
- struct mpc_grph_gamut_adjustment adjust;
- bool enable_remap_dpp = false;
-
- memset(&adjust, 0, sizeof(adjust));
- adjust.gamut_adjust_type = GRAPHICS_GAMUT_ADJUST_TYPE_BYPASS;
-
- /* save the enablement of gamut remap for dpp */
- enable_remap_dpp = pipe_ctx->stream->gamut_remap_matrix.enable_remap;
-
- /* force bypass gamut remap for dpp/cm */
- pipe_ctx->stream->gamut_remap_matrix.enable_remap = false;
- dc->hwss.program_gamut_remap(pipe_ctx);
-
- /* restore gamut remap flag and use this remap into mpc */
- pipe_ctx->stream->gamut_remap_matrix.enable_remap = enable_remap_dpp;
-
- /* build remap matrix for top plane if enabled */
- if (enable_remap_dpp && pipe_ctx->top_pipe == NULL) {
- adjust.gamut_adjust_type = GRAPHICS_GAMUT_ADJUST_TYPE_SW;
- for (i = 0; i < CSC_TEMPERATURE_MATRIX_SIZE; i++)
- adjust.temperature_matrix[i] =
- pipe_ctx->stream->gamut_remap_matrix.matrix[i];
- }
- mpc->funcs->set_gamut_remap(mpc, mpcc_id, &adjust);
- } else
- /* dpp/cm gamut remap*/
- dc->hwss.program_gamut_remap(pipe_ctx);
+ /* dpp/cm gamut remap*/
+ dc->hwss.program_gamut_remap(pipe_ctx);
/*call the dcn2 method which uses mpc csc*/
dc->hwss.program_output_csc(dc,
} else {
AUX_REG_WRITE(AUX_DPHY_RX_CONTROL0, 0x103d1110);
- AUX_REG_WRITE(AUX_DPHY_TX_CONTROL, 0x21c4d);
-
+ AUX_REG_WRITE(AUX_DPHY_TX_CONTROL, 0x21c7a);
}
//AUX_DPHY_TX_REF_CONTROL'AUX_TX_REF_DIV HW default is 0x32;
.hubp_set_flip_control_surface_gsl = hubp2_set_flip_control_surface_gsl,
.hubp_init = hubp21_init,
.validate_dml_output = hubp21_validate_dml_output,
+ .hubp_set_flip_int = hubp1_set_flip_int,
};
bool hubp21_construct(
.num_banks = 8,
.num_chans = 4,
.vmm_page_size_bytes = 4096,
- .dram_clock_change_latency_us = 11.72,
+ .dram_clock_change_latency_us = 23.84,
.return_bus_width_bytes = 64,
.dispclk_dppclk_vco_speed_mhz = 3600,
.xfc_bus_transport_time_us = 4,
{
int i;
- DC_FP_START();
-
if (dc->bb_overrides.sr_exit_time_ns) {
for (i = 0; i < WM_SET_COUNT; i++) {
dc->clk_mgr->bw_params->wm_table.entries[i].sr_exit_time_us =
dc->bb_overrides.dram_clock_change_latency_ns / 1000.0;
}
}
-
- DC_FP_END();
}
void dcn21_calculate_wm(
int vlevel = 0;
int pipe_split_from[MAX_PIPES];
int pipe_cnt = 0;
- display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_KERNEL);
+ display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_ATOMIC);
DC_LOGGER_INIT(dc->ctx->logger);
BW_VAL_TRACE_COUNT();
dcn2_1_soc.num_chans = bw_params->num_channels;
ASSERT(clk_table->num_entries);
+ /* Copy dcn2_1_soc.clock_limits to clock_limits to avoid copying over null states later */
+ for (i = 0; i < dcn2_1_soc.num_states + 1; i++) {
+ clock_limits[i] = dcn2_1_soc.clock_limits[i];
+ }
+
for (i = 0; i < clk_table->num_entries; i++) {
/* loop backwards*/
for (closest_clk_lvl = 0, j = dcn2_1_soc.num_states - 1; j >= 0; j--) {
struct pwl_result_data *rgb_resulted;
struct pwl_result_data *rgb;
struct pwl_result_data *rgb_plus_1;
+ struct pwl_result_data *rgb_minus_1;
struct fixed31_32 end_value;
int32_t region_start, region_end;
region_start = -MAX_LOW_POINT;
region_end = NUMBER_REGIONS - MAX_LOW_POINT;
} else {
- /* 10 segments
+ /* 11 segments
* segment is from 2^-10 to 2^0
* There are less than 256 points, for optimization
*/
seg_distr[7] = 4;
seg_distr[8] = 4;
seg_distr[9] = 4;
+ seg_distr[10] = 1;
region_start = -10;
- region_end = 0;
+ region_end = 1;
}
for (i = region_end - region_start; i < MAX_REGIONS_NUMBER ; i++)
rgb_resulted[hw_points - 1].green = output_tf->tf_pts.green[start_index];
rgb_resulted[hw_points - 1].blue = output_tf->tf_pts.blue[start_index];
+ rgb_resulted[hw_points].red = rgb_resulted[hw_points - 1].red;
+ rgb_resulted[hw_points].green = rgb_resulted[hw_points - 1].green;
+ rgb_resulted[hw_points].blue = rgb_resulted[hw_points - 1].blue;
+
// All 3 color channels have same x
corner_points[0].red.x = dc_fixpt_pow(dc_fixpt_from_int(2),
dc_fixpt_from_int(region_start));
rgb = rgb_resulted;
rgb_plus_1 = rgb_resulted + 1;
+ rgb_minus_1 = rgb;
i = 1;
while (i != hw_points + 1) {
- if (dc_fixpt_lt(rgb_plus_1->red, rgb->red))
- rgb_plus_1->red = rgb->red;
- if (dc_fixpt_lt(rgb_plus_1->green, rgb->green))
- rgb_plus_1->green = rgb->green;
- if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue))
- rgb_plus_1->blue = rgb->blue;
+ if (i >= hw_points - 1) {
+ if (dc_fixpt_lt(rgb_plus_1->red, rgb->red))
+ rgb_plus_1->red = dc_fixpt_add(rgb->red, rgb_minus_1->delta_red);
+ if (dc_fixpt_lt(rgb_plus_1->green, rgb->green))
+ rgb_plus_1->green = dc_fixpt_add(rgb->green, rgb_minus_1->delta_green);
+ if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue))
+ rgb_plus_1->blue = dc_fixpt_add(rgb->blue, rgb_minus_1->delta_blue);
+ }
rgb->delta_red = dc_fixpt_sub(rgb_plus_1->red, rgb->red);
rgb->delta_green = dc_fixpt_sub(rgb_plus_1->green, rgb->green);
}
++rgb_plus_1;
+ rgb_minus_1 = rgb;
++rgb;
++i;
}
.hubp_init = hubp3_init,
.hubp_in_blank = hubp1_in_blank,
.hubp_soft_reset = hubp1_soft_reset,
+ .hubp_set_flip_int = hubp1_set_flip_int,
};
bool hubp3_construct(
HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_EN, mask_sh),\
HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_IND_BLK, mask_sh),\
HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_IND_BLK_C, mask_sh),\
+ HUBP_SF(HUBPREQ0_DCSURF_SURFACE_FLIP_INTERRUPT, SURFACE_FLIP_INT_MASK, mask_sh),\
HUBP_SF(HUBPRET0_HUBPRET_CONTROL, DET_BUF_PLANE1_BASE_ADDRESS, mask_sh),\
HUBP_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CB_B, mask_sh),\
HUBP_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CR_R, mask_sh),\
.patch_unknown_plane_state = dcn20_patch_unknown_plane_state,
};
+#define CTX ctx
+
+#define REG(reg_name) \
+ (DCN_BASE.instance[0].segment[mm ## reg_name ## _BASE_IDX] + mm ## reg_name)
+
+static uint32_t read_pipe_fuses(struct dc_context *ctx)
+{
+ uint32_t value = REG_READ(CC_DC_PIPE_DIS);
+ /* Support for max 6 pipes */
+ value = value & 0x3f;
+ return value;
+}
+
static bool dcn30_resource_construct(
uint8_t num_virtual_links,
struct dc *dc,
struct dc_context *ctx = dc->ctx;
struct irq_service_init_data init_data;
struct ddc_service_init_data ddc_init_data;
+ uint32_t pipe_fuses = read_pipe_fuses(ctx);
+ uint32_t num_pipes = 0;
+
+ if (!(pipe_fuses == 0 || pipe_fuses == 0x3e)) {
+ BREAK_TO_DEBUGGER();
+ dm_error("DC: Unexpected fuse recipe for navi2x !\n");
+ /* fault to single pipe */
+ pipe_fuses = 0x3e;
+ }
DC_FP_START();
/* PP Lib and SMU interfaces */
init_soc_bounding_box(dc, pool);
+ num_pipes = dcn3_0_ip.max_num_dpp;
+
+ for (i = 0; i < dcn3_0_ip.max_num_dpp; i++)
+ if (pipe_fuses & 1 << i)
+ num_pipes--;
+
+ dcn3_0_ip.max_num_dpp = num_pipes;
+ dcn3_0_ip.max_num_otg = num_pipes;
+
dml_init_instance(&dc->dml, &dcn3_0_soc, &dcn3_0_ip, DML_PROJECT_DCN30);
/* IRQ */
dml_init_instance(&dc->dml, &dcn3_01_soc, &dcn3_01_ip, DML_PROJECT_DCN30);
}
+static void calculate_wm_set_for_vlevel(
+ int vlevel,
+ struct wm_range_table_entry *table_entry,
+ struct dcn_watermarks *wm_set,
+ struct display_mode_lib *dml,
+ display_e2e_pipe_params_st *pipes,
+ int pipe_cnt)
+{
+ double dram_clock_change_latency_cached = dml->soc.dram_clock_change_latency_us;
+
+ ASSERT(vlevel < dml->soc.num_states);
+ /* only pipe 0 is read for voltage and dcf/soc clocks */
+ pipes[0].clks_cfg.voltage = vlevel;
+ pipes[0].clks_cfg.dcfclk_mhz = dml->soc.clock_limits[vlevel].dcfclk_mhz;
+ pipes[0].clks_cfg.socclk_mhz = dml->soc.clock_limits[vlevel].socclk_mhz;
+
+ dml->soc.dram_clock_change_latency_us = table_entry->pstate_latency_us;
+ dml->soc.sr_exit_time_us = table_entry->sr_exit_time_us;
+ dml->soc.sr_enter_plus_exit_time_us = table_entry->sr_enter_plus_exit_time_us;
+
+ wm_set->urgent_ns = get_wm_urgent(dml, pipes, pipe_cnt) * 1000;
+ wm_set->cstate_pstate.cstate_enter_plus_exit_ns = get_wm_stutter_enter_exit(dml, pipes, pipe_cnt) * 1000;
+ wm_set->cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(dml, pipes, pipe_cnt) * 1000;
+ wm_set->cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(dml, pipes, pipe_cnt) * 1000;
+ wm_set->pte_meta_urgent_ns = get_wm_memory_trip(dml, pipes, pipe_cnt) * 1000;
+ wm_set->frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(dml, pipes, pipe_cnt) * 1000;
+ wm_set->frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(dml, pipes, pipe_cnt) * 1000;
+ wm_set->urgent_latency_ns = get_urgent_latency(dml, pipes, pipe_cnt) * 1000;
+ dml->soc.dram_clock_change_latency_us = dram_clock_change_latency_cached;
+
+}
+
+static void dcn301_calculate_wm_and_dlg(
+ struct dc *dc, struct dc_state *context,
+ display_e2e_pipe_params_st *pipes,
+ int pipe_cnt,
+ int vlevel_req)
+{
+ int i, pipe_idx;
+ int vlevel, vlevel_max;
+ struct wm_range_table_entry *table_entry;
+ struct clk_bw_params *bw_params = dc->clk_mgr->bw_params;
+
+ ASSERT(bw_params);
+
+ vlevel_max = bw_params->clk_table.num_entries - 1;
+
+ /* WM Set D */
+ table_entry = &bw_params->wm_table.entries[WM_D];
+ if (table_entry->wm_type == WM_TYPE_RETRAINING)
+ vlevel = 0;
+ else
+ vlevel = vlevel_max;
+ calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.d,
+ &context->bw_ctx.dml, pipes, pipe_cnt);
+ /* WM Set C */
+ table_entry = &bw_params->wm_table.entries[WM_C];
+ vlevel = min(max(vlevel_req, 2), vlevel_max);
+ calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.c,
+ &context->bw_ctx.dml, pipes, pipe_cnt);
+ /* WM Set B */
+ table_entry = &bw_params->wm_table.entries[WM_B];
+ vlevel = min(max(vlevel_req, 1), vlevel_max);
+ calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.b,
+ &context->bw_ctx.dml, pipes, pipe_cnt);
+
+ /* WM Set A */
+ table_entry = &bw_params->wm_table.entries[WM_A];
+ vlevel = min(vlevel_req, vlevel_max);
+ calculate_wm_set_for_vlevel(vlevel, table_entry, &context->bw_ctx.bw.dcn.watermarks.a,
+ &context->bw_ctx.dml, pipes, pipe_cnt);
+
+ for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) {
+ if (!context->res_ctx.pipe_ctx[i].stream)
+ continue;
+
+ pipes[pipe_idx].clks_cfg.dispclk_mhz = get_dispclk_calculated(&context->bw_ctx.dml, pipes, pipe_cnt);
+ pipes[pipe_idx].clks_cfg.dppclk_mhz = get_dppclk_calculated(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx);
+
+ if (dc->config.forced_clocks) {
+ pipes[pipe_idx].clks_cfg.dispclk_mhz = context->bw_ctx.dml.soc.clock_limits[0].dispclk_mhz;
+ pipes[pipe_idx].clks_cfg.dppclk_mhz = context->bw_ctx.dml.soc.clock_limits[0].dppclk_mhz;
+ }
+ if (dc->debug.min_disp_clk_khz > pipes[pipe_idx].clks_cfg.dispclk_mhz * 1000)
+ pipes[pipe_idx].clks_cfg.dispclk_mhz = dc->debug.min_disp_clk_khz / 1000.0;
+ if (dc->debug.min_dpp_clk_khz > pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000)
+ pipes[pipe_idx].clks_cfg.dppclk_mhz = dc->debug.min_dpp_clk_khz / 1000.0;
+
+ pipe_idx++;
+ }
+
+ dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel);
+}
+
static struct resource_funcs dcn301_res_pool_funcs = {
.destroy = dcn301_destroy_resource_pool,
.link_enc_create = dcn301_link_encoder_create,
.panel_cntl_create = dcn301_panel_cntl_create,
.validate_bandwidth = dcn30_validate_bandwidth,
- .calculate_wm_and_dlg = dcn30_calculate_wm_and_dlg,
+ .calculate_wm_and_dlg = dcn301_calculate_wm_and_dlg,
.populate_dml_pipes = dcn30_populate_dml_pipes_from_context,
.acquire_idle_pipe_for_layer = dcn20_acquire_idle_pipe_for_layer,
.add_stream_to_ctx = dcn30_add_stream_to_ctx,
bool (*hubp_in_blank)(struct hubp *hubp);
void (*hubp_soft_reset)(struct hubp *hubp, bool reset);
+ void (*hubp_set_flip_int)(struct hubp *hubp);
+
};
#endif
tmp, MC_CG_ARB_FREQ_F0);
}
+static uint16_t smu7_override_pcie_speed(struct pp_hwmgr *hwmgr)
+{
+ struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev);
+ uint16_t pcie_gen = 0;
+
+ if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4 &&
+ adev->pm.pcie_gen_mask & CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN4)
+ pcie_gen = 3;
+ else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3 &&
+ adev->pm.pcie_gen_mask & CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3)
+ pcie_gen = 2;
+ else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2 &&
+ adev->pm.pcie_gen_mask & CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2)
+ pcie_gen = 1;
+ else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1 &&
+ adev->pm.pcie_gen_mask & CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1)
+ pcie_gen = 0;
+
+ return pcie_gen;
+}
+
+static uint16_t smu7_override_pcie_width(struct pp_hwmgr *hwmgr)
+{
+ struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev);
+ uint16_t pcie_width = 0;
+
+ if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X16)
+ pcie_width = 16;
+ else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X12)
+ pcie_width = 12;
+ else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X8)
+ pcie_width = 8;
+ else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X4)
+ pcie_width = 4;
+ else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X2)
+ pcie_width = 2;
+ else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X1)
+ pcie_width = 1;
+
+ return pcie_width;
+}
+
static int smu7_setup_default_pcie_table(struct pp_hwmgr *hwmgr)
{
struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
PP_Min_PCIEGen),
get_pcie_lane_support(data->pcie_lane_cap,
PP_Max_PCIELane));
+
+ if (data->pcie_dpm_key_disabled)
+ phm_setup_pcie_table_entry(&data->dpm_table.pcie_speed_table,
+ data->dpm_table.pcie_speed_table.count,
+ smu7_override_pcie_speed(hwmgr), smu7_override_pcie_width(hwmgr));
}
return 0;
}
(hwmgr->chip_id == CHIP_POLARIS10) ||
(hwmgr->chip_id == CHIP_POLARIS11) ||
(hwmgr->chip_id == CHIP_POLARIS12) ||
- (hwmgr->chip_id == CHIP_TONGA))
+ (hwmgr->chip_id == CHIP_TONGA) ||
+ (hwmgr->chip_id == CHIP_TOPAZ))
PHM_WRITE_FIELD(hwmgr->device, MC_SEQ_CNTL_3, CAC_EN, 0x1);
NULL)),
"Failed to enable pcie DPM during DPM Start Function!",
return -EINVAL);
+ } else {
+ PP_ASSERT_WITH_CODE(
+ (0 == smum_send_msg_to_smc(hwmgr,
+ PPSMC_MSG_PCIeDPM_Disable,
+ NULL)),
+ "Failed to disble pcie DPM during DPM Start Function!",
+ return -EINVAL);
}
if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
disable_mclk_switching_for_display = ((1 < hwmgr->display_config->num_display) &&
!hwmgr->display_config->multi_monitor_in_sync) ||
- smu7_vblank_too_short(hwmgr, hwmgr->display_config->min_vblank_time);
+ (hwmgr->display_config->num_display &&
+ smu7_vblank_too_short(hwmgr, hwmgr->display_config->min_vblank_time));
disable_mclk_switching = disable_mclk_switching_for_frame_lock ||
disable_mclk_switching_for_display;
for (j = 0; j < dep_sclk_table->count; j++) {
valid_entry = false;
for (k = 0; k < watermarks->num_wm_sets; k++) {
- if (dep_sclk_table->entries[i].clk / 10 >= watermarks->wm_clk_ranges[k].wm_min_eng_clk_in_khz &&
- dep_sclk_table->entries[i].clk / 10 < watermarks->wm_clk_ranges[k].wm_max_eng_clk_in_khz &&
- dep_mclk_table->entries[i].clk / 10 >= watermarks->wm_clk_ranges[k].wm_min_mem_clk_in_khz &&
- dep_mclk_table->entries[i].clk / 10 < watermarks->wm_clk_ranges[k].wm_max_mem_clk_in_khz) {
+ if (dep_sclk_table->entries[i].clk >= watermarks->wm_clk_ranges[k].wm_min_eng_clk_in_khz / 10 &&
+ dep_sclk_table->entries[i].clk < watermarks->wm_clk_ranges[k].wm_max_eng_clk_in_khz / 10 &&
+ dep_mclk_table->entries[i].clk >= watermarks->wm_clk_ranges[k].wm_min_mem_clk_in_khz / 10 &&
+ dep_mclk_table->entries[i].clk < watermarks->wm_clk_ranges[k].wm_max_mem_clk_in_khz / 10) {
valid_entry = true;
table->DisplayWatermark[i][j] = watermarks->wm_clk_ranges[k].wm_set_id;
break;
#include "smuio/smuio_9_0_offset.h"
#include "smuio/smuio_9_0_sh_mask.h"
+#define smnPCIE_LC_SPEED_CNTL 0x11140290
+#define smnPCIE_LC_LINK_WIDTH_CNTL 0x11140288
+
#define HBM_MEMORY_CHANNEL_WIDTH 128
static const uint32_t channel_number[] = {1, 2, 0, 4, 0, 8, 0, 16, 2};
if (PP_CAP(PHM_PlatformCaps_VCEDPM))
data->smu_features[GNLD_DPM_VCE].supported = true;
- if (!data->registry_data.pcie_dpm_key_disabled)
- data->smu_features[GNLD_DPM_LINK].supported = true;
+ data->smu_features[GNLD_DPM_LINK].supported = true;
if (!data->registry_data.dcefclk_dpm_key_disabled)
data->smu_features[GNLD_DPM_DCEFCLK].supported = true;
return 0;
}
+static int vega10_override_pcie_parameters(struct pp_hwmgr *hwmgr)
+{
+ struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev);
+ struct vega10_hwmgr *data =
+ (struct vega10_hwmgr *)(hwmgr->backend);
+ uint32_t pcie_gen = 0, pcie_width = 0;
+ PPTable_t *pp_table = &(data->smc_state_table.pp_table);
+ int i;
+
+ if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4)
+ pcie_gen = 3;
+ else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3)
+ pcie_gen = 2;
+ else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2)
+ pcie_gen = 1;
+ else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1)
+ pcie_gen = 0;
+
+ if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X16)
+ pcie_width = 6;
+ else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X12)
+ pcie_width = 5;
+ else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X8)
+ pcie_width = 4;
+ else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X4)
+ pcie_width = 3;
+ else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X2)
+ pcie_width = 2;
+ else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X1)
+ pcie_width = 1;
+
+ for (i = 0; i < NUM_LINK_LEVELS; i++) {
+ if (pp_table->PcieGenSpeed[i] > pcie_gen)
+ pp_table->PcieGenSpeed[i] = pcie_gen;
+
+ if (pp_table->PcieLaneCount[i] > pcie_width)
+ pp_table->PcieLaneCount[i] = pcie_width;
+ }
+
+ if (data->registry_data.pcie_dpm_key_disabled) {
+ for (i = 0; i < NUM_LINK_LEVELS; i++) {
+ pp_table->PcieGenSpeed[i] = pcie_gen;
+ pp_table->PcieLaneCount[i] = pcie_width;
+ }
+ }
+
+ return 0;
+}
+
static int vega10_populate_smc_link_levels(struct pp_hwmgr *hwmgr)
{
int result = -1;
"Failed to initialize Link Level!",
return result);
+ result = vega10_override_pcie_parameters(hwmgr);
+ PP_ASSERT_WITH_CODE(!result,
+ "Failed to override pcie parameters!",
+ return result);
+
result = vega10_populate_all_graphic_levels(hwmgr);
PP_ASSERT_WITH_CODE(!result,
"Failed to initialize Graphics Level!",
}
}
+ if (data->registry_data.pcie_dpm_key_disabled) {
+ PP_ASSERT_WITH_CODE(!vega10_enable_smc_features(hwmgr,
+ false, data->smu_features[GNLD_DPM_LINK].smu_feature_bitmap),
+ "Attempt to Disable Link DPM feature Failed!", return -EINVAL);
+ data->smu_features[GNLD_DPM_LINK].enabled = false;
+ data->smu_features[GNLD_DPM_LINK].supported = false;
+ }
+
return 0;
}
+
static int vega10_enable_disable_PCC_limit_feature(struct pp_hwmgr *hwmgr, bool enable)
{
struct vega10_hwmgr *data = hwmgr->backend;
return 0;
}
+static int vega10_get_current_pcie_link_width_level(struct pp_hwmgr *hwmgr)
+{
+ struct amdgpu_device *adev = hwmgr->adev;
+
+ return (RREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL) &
+ PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD_MASK)
+ >> PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD__SHIFT;
+}
+
+static int vega10_get_current_pcie_link_speed_level(struct pp_hwmgr *hwmgr)
+{
+ struct amdgpu_device *adev = hwmgr->adev;
+
+ return (RREG32_PCIE(smnPCIE_LC_SPEED_CNTL) &
+ PSWUSP0_PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK)
+ >> PSWUSP0_PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE__SHIFT;
+}
+
static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
enum pp_clock_type type, char *buf)
{
struct vega10_single_dpm_table *mclk_table = &(data->dpm_table.mem_table);
struct vega10_single_dpm_table *soc_table = &(data->dpm_table.soc_table);
struct vega10_single_dpm_table *dcef_table = &(data->dpm_table.dcef_table);
- struct vega10_pcie_table *pcie_table = &(data->dpm_table.pcie_table);
struct vega10_odn_clock_voltage_dependency_table *podn_vdd_dep = NULL;
+ uint32_t gen_speed, lane_width, current_gen_speed, current_lane_width;
+ PPTable_t *pptable = &(data->smc_state_table.pp_table);
int i, now, size = 0, count = 0;
"*" : "");
break;
case PP_PCIE:
- smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentLinkIndex, &now);
-
- for (i = 0; i < pcie_table->count; i++)
- size += sprintf(buf + size, "%d: %s %s\n", i,
- (pcie_table->pcie_gen[i] == 0) ? "2.5GT/s, x1" :
- (pcie_table->pcie_gen[i] == 1) ? "5.0GT/s, x16" :
- (pcie_table->pcie_gen[i] == 2) ? "8.0GT/s, x16" : "",
- (i == now) ? "*" : "");
+ current_gen_speed =
+ vega10_get_current_pcie_link_speed_level(hwmgr);
+ current_lane_width =
+ vega10_get_current_pcie_link_width_level(hwmgr);
+ for (i = 0; i < NUM_LINK_LEVELS; i++) {
+ gen_speed = pptable->PcieGenSpeed[i];
+ lane_width = pptable->PcieLaneCount[i];
+
+ size += sprintf(buf + size, "%d: %s %s %s\n", i,
+ (gen_speed == 0) ? "2.5GT/s," :
+ (gen_speed == 1) ? "5.0GT/s," :
+ (gen_speed == 2) ? "8.0GT/s," :
+ (gen_speed == 3) ? "16.0GT/s," : "",
+ (lane_width == 1) ? "x1" :
+ (lane_width == 2) ? "x2" :
+ (lane_width == 3) ? "x4" :
+ (lane_width == 4) ? "x8" :
+ (lane_width == 5) ? "x12" :
+ (lane_width == 6) ? "x16" : "",
+ (current_gen_speed == gen_speed) &&
+ (current_lane_width == lane_width) ?
+ "*" : "");
+ }
break;
+
case OD_SCLK:
if (hwmgr->od_enabled) {
size = sprintf(buf, "%s:\n", "OD_SCLK");
data->registry_data.auto_wattman_debug = 0;
data->registry_data.auto_wattman_sample_period = 100;
data->registry_data.auto_wattman_threshold = 50;
+ data->registry_data.pcie_dpm_key_disabled = !(hwmgr->feature_mask & PP_PCIE_DPM_MASK);
}
static int vega12_set_features_platform_caps(struct pp_hwmgr *hwmgr)
dpm_state->hard_max_level = 0xffff;
}
+static int vega12_override_pcie_parameters(struct pp_hwmgr *hwmgr)
+{
+ struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev);
+ struct vega12_hwmgr *data =
+ (struct vega12_hwmgr *)(hwmgr->backend);
+ uint32_t pcie_gen = 0, pcie_width = 0, smu_pcie_arg, pcie_gen_arg, pcie_width_arg;
+ PPTable_t *pp_table = &(data->smc_state_table.pp_table);
+ int i;
+ int ret;
+
+ if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4)
+ pcie_gen = 3;
+ else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3)
+ pcie_gen = 2;
+ else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2)
+ pcie_gen = 1;
+ else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1)
+ pcie_gen = 0;
+
+ if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X16)
+ pcie_width = 6;
+ else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X12)
+ pcie_width = 5;
+ else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X8)
+ pcie_width = 4;
+ else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X4)
+ pcie_width = 3;
+ else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X2)
+ pcie_width = 2;
+ else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X1)
+ pcie_width = 1;
+
+ /* Bit 31:16: LCLK DPM level. 0 is DPM0, and 1 is DPM1
+ * Bit 15:8: PCIE GEN, 0 to 3 corresponds to GEN1 to GEN4
+ * Bit 7:0: PCIE lane width, 1 to 7 corresponds is x1 to x32
+ */
+ for (i = 0; i < NUM_LINK_LEVELS; i++) {
+ pcie_gen_arg = (pp_table->PcieGenSpeed[i] > pcie_gen) ? pcie_gen :
+ pp_table->PcieGenSpeed[i];
+ pcie_width_arg = (pp_table->PcieLaneCount[i] > pcie_width) ? pcie_width :
+ pp_table->PcieLaneCount[i];
+
+ if (pcie_gen_arg != pp_table->PcieGenSpeed[i] || pcie_width_arg !=
+ pp_table->PcieLaneCount[i]) {
+ smu_pcie_arg = (i << 16) | (pcie_gen_arg << 8) | pcie_width_arg;
+ ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+ PPSMC_MSG_OverridePcieParameters, smu_pcie_arg,
+ NULL);
+ PP_ASSERT_WITH_CODE(!ret,
+ "[OverridePcieParameters] Attempt to override pcie params failed!",
+ return ret);
+ }
+
+ /* update the pptable */
+ pp_table->PcieGenSpeed[i] = pcie_gen_arg;
+ pp_table->PcieLaneCount[i] = pcie_width_arg;
+ }
+
+ /* override to the highest if it's disabled from ppfeaturmask */
+ if (data->registry_data.pcie_dpm_key_disabled) {
+ for (i = 0; i < NUM_LINK_LEVELS; i++) {
+ smu_pcie_arg = (i << 16) | (pcie_gen << 8) | pcie_width;
+ ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+ PPSMC_MSG_OverridePcieParameters, smu_pcie_arg,
+ NULL);
+ PP_ASSERT_WITH_CODE(!ret,
+ "[OverridePcieParameters] Attempt to override pcie params failed!",
+ return ret);
+
+ pp_table->PcieGenSpeed[i] = pcie_gen;
+ pp_table->PcieLaneCount[i] = pcie_width;
+ }
+ ret = vega12_enable_smc_features(hwmgr,
+ false,
+ data->smu_features[GNLD_DPM_LINK].smu_feature_bitmap);
+ PP_ASSERT_WITH_CODE(!ret,
+ "Attempt to Disable DPM LINK Failed!",
+ return ret);
+ data->smu_features[GNLD_DPM_LINK].enabled = false;
+ data->smu_features[GNLD_DPM_LINK].supported = false;
+ }
+ return 0;
+}
+
static int vega12_get_number_of_dpm_level(struct pp_hwmgr *hwmgr,
PPCLK_e clk_id, uint32_t *num_of_levels)
{
"Failed to enable all smu features!",
return result);
+ result = vega12_override_pcie_parameters(hwmgr);
+ PP_ASSERT_WITH_CODE(!result,
+ "[EnableDPMTasks] Failed to override pcie parameters!",
+ return result);
+
tmp_result = vega12_power_control_set_level(hwmgr);
PP_ASSERT_WITH_CODE(!tmp_result,
"Failed to power control set level!",
data->registry_data.gfxoff_controlled_by_driver = 1;
data->gfxoff_allowed = false;
data->counter_gfxoff = 0;
+ data->registry_data.pcie_dpm_key_disabled = !(hwmgr->feature_mask & PP_PCIE_DPM_MASK);
}
static int vega20_set_features_platform_caps(struct pp_hwmgr *hwmgr)
struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev);
struct vega20_hwmgr *data =
(struct vega20_hwmgr *)(hwmgr->backend);
- uint32_t pcie_gen = 0, pcie_width = 0, smu_pcie_arg;
+ uint32_t pcie_gen = 0, pcie_width = 0, smu_pcie_arg, pcie_gen_arg, pcie_width_arg;
+ PPTable_t *pp_table = &(data->smc_state_table.pp_table);
+ int i;
int ret;
if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4)
* Bit 15:8: PCIE GEN, 0 to 3 corresponds to GEN1 to GEN4
* Bit 7:0: PCIE lane width, 1 to 7 corresponds is x1 to x32
*/
- smu_pcie_arg = (1 << 16) | (pcie_gen << 8) | pcie_width;
- ret = smum_send_msg_to_smc_with_parameter(hwmgr,
- PPSMC_MSG_OverridePcieParameters, smu_pcie_arg,
- NULL);
- PP_ASSERT_WITH_CODE(!ret,
- "[OverridePcieParameters] Attempt to override pcie params failed!",
- return ret);
+ for (i = 0; i < NUM_LINK_LEVELS; i++) {
+ pcie_gen_arg = (pp_table->PcieGenSpeed[i] > pcie_gen) ? pcie_gen :
+ pp_table->PcieGenSpeed[i];
+ pcie_width_arg = (pp_table->PcieLaneCount[i] > pcie_width) ? pcie_width :
+ pp_table->PcieLaneCount[i];
+
+ if (pcie_gen_arg != pp_table->PcieGenSpeed[i] || pcie_width_arg !=
+ pp_table->PcieLaneCount[i]) {
+ smu_pcie_arg = (i << 16) | (pcie_gen_arg << 8) | pcie_width_arg;
+ ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+ PPSMC_MSG_OverridePcieParameters, smu_pcie_arg,
+ NULL);
+ PP_ASSERT_WITH_CODE(!ret,
+ "[OverridePcieParameters] Attempt to override pcie params failed!",
+ return ret);
+ }
+
+ /* update the pptable */
+ pp_table->PcieGenSpeed[i] = pcie_gen_arg;
+ pp_table->PcieLaneCount[i] = pcie_width_arg;
+ }
+
+ /* override to the highest if it's disabled from ppfeaturmask */
+ if (data->registry_data.pcie_dpm_key_disabled) {
+ for (i = 0; i < NUM_LINK_LEVELS; i++) {
+ smu_pcie_arg = (i << 16) | (pcie_gen << 8) | pcie_width;
+ ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+ PPSMC_MSG_OverridePcieParameters, smu_pcie_arg,
+ NULL);
+ PP_ASSERT_WITH_CODE(!ret,
+ "[OverridePcieParameters] Attempt to override pcie params failed!",
+ return ret);
- data->pcie_parameters_override = true;
- data->pcie_gen_level1 = pcie_gen;
- data->pcie_width_level1 = pcie_width;
+ pp_table->PcieGenSpeed[i] = pcie_gen;
+ pp_table->PcieLaneCount[i] = pcie_width;
+ }
+ ret = vega20_enable_smc_features(hwmgr,
+ false,
+ data->smu_features[GNLD_DPM_LINK].smu_feature_bitmap);
+ PP_ASSERT_WITH_CODE(!ret,
+ "Attempt to Disable DPM LINK Failed!",
+ return ret);
+ data->smu_features[GNLD_DPM_LINK].enabled = false;
+ data->smu_features[GNLD_DPM_LINK].supported = false;
+ }
return 0;
}
data->od8_settings.od8_settings_array;
OverDriveTable_t *od_table =
&(data->smc_state_table.overdrive_table);
- struct phm_ppt_v3_information *pptable_information =
- (struct phm_ppt_v3_information *)hwmgr->pptable;
- PPTable_t *pptable = (PPTable_t *)pptable_information->smc_pptable;
+ PPTable_t *pptable = &(data->smc_state_table.pp_table);
struct pp_clock_levels_with_latency clocks;
struct vega20_single_dpm_table *fclk_dpm_table =
&(data->dpm_table.fclk_table);
current_lane_width =
vega20_get_current_pcie_link_width_level(hwmgr);
for (i = 0; i < NUM_LINK_LEVELS; i++) {
- if (i == 1 && data->pcie_parameters_override) {
- gen_speed = data->pcie_gen_level1;
- lane_width = data->pcie_width_level1;
- } else {
- gen_speed = pptable->PcieGenSpeed[i];
- lane_width = pptable->PcieLaneCount[i];
- }
+ gen_speed = pptable->PcieGenSpeed[i];
+ lane_width = pptable->PcieLaneCount[i];
+
size += sprintf(buf + size, "%d: %s %s %dMhz %s\n", i,
(gen_speed == 0) ? "2.5GT/s," :
(gen_speed == 1) ? "5.0GT/s," :
bool use_baco = !smu->is_apu &&
((amdgpu_in_reset(adev) &&
(amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_BACO)) ||
- ((adev->in_runpm || adev->in_hibernate) && amdgpu_asic_supports_baco(adev)));
+ ((adev->in_runpm || adev->in_s4) && amdgpu_asic_supports_baco(adev)));
/*
* For custom pptable uploading, skip the DPM features
smu->watermarks_bitmap &= ~(WATERMARKS_LOADED);
- if (smu->is_apu)
+ /* skip CGPG when in S0ix */
+ if (smu->is_apu && !adev->in_s0ix)
smu_set_gfx_cgpg(&adev->smu, false);
return 0;
static bool vangogh_is_dpm_running(struct smu_context *smu)
{
+ struct amdgpu_device *adev = smu->adev;
int ret = 0;
uint32_t feature_mask[2];
uint64_t feature_enabled;
+ /* we need to re-init after suspend so return false */
+ if (adev->in_suspend)
+ return false;
+
ret = smu_cmn_get_enabled_32_bits_mask(smu, feature_mask, 2);
if (ret)
if (shadow)
vfree(shadow);
- else
+ else if (fb_helper->buffer)
drm_client_buffer_vunmap(fb_helper->buffer);
drm_client_framebuffer_delete(fb_helper->buffer);
if (--shmem->vmap_use_count > 0)
return;
- if (obj->import_attach)
+ if (obj->import_attach) {
dma_buf_vunmap(obj->import_attach->dmabuf, map);
- else
+ } else {
vunmap(shmem->vaddr);
+ drm_gem_shmem_put_pages(shmem);
+ }
shmem->vaddr = NULL;
- drm_gem_shmem_put_pages(shmem);
}
/*
struct drm_gem_object *obj = vma->vm_private_data;
struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
loff_t num_pages = obj->size >> PAGE_SHIFT;
+ vm_fault_t ret;
struct page *page;
+ pgoff_t page_offset;
- if (vmf->pgoff >= num_pages || WARN_ON_ONCE(!shmem->pages))
- return VM_FAULT_SIGBUS;
+ /* We don't use vmf->pgoff since that has the fake offset */
+ page_offset = (vmf->address - vma->vm_start) >> PAGE_SHIFT;
- page = shmem->pages[vmf->pgoff];
+ mutex_lock(&shmem->pages_lock);
- return vmf_insert_page(vma, vmf->address, page);
+ if (page_offset >= num_pages ||
+ WARN_ON_ONCE(!shmem->pages) ||
+ shmem->madv < 0) {
+ ret = VM_FAULT_SIGBUS;
+ } else {
+ page = shmem->pages[page_offset];
+
+ ret = vmf_insert_page(vma, vmf->address, page);
+ }
+
+ mutex_unlock(&shmem->pages_lock);
+
+ return ret;
}
static void drm_gem_shmem_vm_open(struct vm_area_struct *vma)
struct drm_gem_shmem_object *shmem;
int ret;
- /* Remove the fake offset */
- vma->vm_pgoff -= drm_vma_node_start(&obj->vma_node);
-
if (obj->import_attach) {
/* Drop the reference drm_gem_mmap_obj() acquired.*/
drm_gem_object_put(obj);
if (copy_from_user(&v32, (void __user *)arg, sizeof(v32)))
return -EFAULT;
+ memset(&v, 0, sizeof(v));
+
v = (struct drm_version) {
.name_len = v32.name_len,
.name = compat_ptr(v32.name),
if (copy_from_user(&uq32, (void __user *)arg, sizeof(uq32)))
return -EFAULT;
+
+ memset(&uq, 0, sizeof(uq));
+
uq = (struct drm_unique){
.unique_len = uq32.unique_len,
.unique = compat_ptr(uq32.unique),
if (copy_from_user(&c32, argp, sizeof(c32)))
return -EFAULT;
+ memset(&client, 0, sizeof(client));
+
client.idx = c32.idx;
err = drm_ioctl_kernel(file, drm_getclient, &client, 0);
if (copy_from_user(&req32, argp, sizeof(req32)))
return -EFAULT;
+ memset(&req, 0, sizeof(req));
+
req.request.type = req32.request.type;
req.request.sequence = req32.request.sequence;
req.request.signal = req32.request.signal;
struct drm_mode_fb_cmd2 req64;
int err;
+ memset(&req64, 0, sizeof(req64));
+
if (copy_from_user(&req64, argp,
offsetof(drm_mode_fb_cmd232_t, modifier)))
return -EFAULT;
struct page **pages = pvec + pinned;
ret = pin_user_pages_fast(ptr, num_pages,
- !userptr->ro ? FOLL_WRITE : 0, pages);
+ FOLL_WRITE | FOLL_FORCE | FOLL_LONGTERM,
+ pages);
if (ret < 0) {
unpin_user_pages(pvec, pinned);
kvfree(pvec);
#include <linux/irq.h>
#include <linux/mfd/syscon.h>
#include <linux/of_device.h>
-#include <linux/of_gpio.h>
#include <linux/platform_device.h>
#include <linux/pm_runtime.h>
#include <linux/regmap.h>
return;
}
+ if (!pkg->package.count) {
+ DRM_DEBUG_DRIVER("no connection in _DSM\n");
+ return;
+ }
+
connector_count = &pkg->package.elements[0];
DRM_DEBUG_DRIVER("MUX info connectors: %lld\n",
(unsigned long long)connector_count->integer.value);
for (i = 1; i < pkg->package.count; i++) {
union acpi_object *obj = &pkg->package.elements[i];
- union acpi_object *connector_id = &obj->package.elements[0];
- union acpi_object *info = &obj->package.elements[1];
+ union acpi_object *connector_id;
+ union acpi_object *info;
+
+ if (obj->type != ACPI_TYPE_PACKAGE || obj->package.count < 2) {
+ DRM_DEBUG_DRIVER("Invalid object for MUX #%d\n", i);
+ continue;
+ }
+
+ connector_id = &obj->package.elements[0];
+ info = &obj->package.elements[1];
+ if (info->type != ACPI_TYPE_BUFFER || info->buffer.length < 4) {
+ DRM_DEBUG_DRIVER("Invalid info for MUX obj #%d\n", i);
+ continue;
+ }
+
DRM_DEBUG_DRIVER("Connector id: 0x%016llx\n",
(unsigned long long)connector_id->integer.value);
DRM_DEBUG_DRIVER(" port id: %s\n",
if (!new_plane_state->hw.crtc && !old_plane_state->hw.crtc)
return 0;
- new_crtc_state->enabled_planes |= BIT(plane->id);
-
ret = plane->check_plane(new_crtc_state, new_plane_state);
if (ret)
return ret;
+ if (fb)
+ new_crtc_state->enabled_planes |= BIT(plane->id);
+
/* FIXME pre-g4x don't work like this */
if (new_plane_state->uapi.visible)
new_crtc_state->active_planes |= BIT(plane->id);
{
int ret;
- intel_dp_lttpr_init(intel_dp);
-
- if (drm_dp_read_dpcd_caps(&intel_dp->aux, intel_dp->dpcd))
+ if (intel_dp_init_lttpr_and_dprx_caps(intel_dp) < 0)
return false;
/*
else
precharge = 5;
+ /* Max timeout value on G4x-BDW: 1.6ms */
if (IS_BROADWELL(dev_priv))
timeout = DP_AUX_CH_CTL_TIME_OUT_600us;
else
enum phy phy = intel_port_to_phy(i915, dig_port->base.port);
u32 ret;
+ /*
+ * Max timeout values:
+ * SKL-GLK: 1.6ms
+ * CNL: 3.2ms
+ * ICL+: 4ms
+ */
ret = DP_AUX_CH_CTL_SEND_BUSY |
DP_AUX_CH_CTL_DONE |
DP_AUX_CH_CTL_INTERRUPT |
break;
case INTEL_BACKLIGHT_DISPLAY_DDI:
try_intel_interface = true;
- try_vesa_interface = true;
break;
default:
return -ENODEV;
link_status[3], link_status[4], link_status[5]);
}
+static void intel_dp_reset_lttpr_common_caps(struct intel_dp *intel_dp)
+{
+ memset(&intel_dp->lttpr_common_caps, 0, sizeof(intel_dp->lttpr_common_caps));
+}
+
static void intel_dp_reset_lttpr_count(struct intel_dp *intel_dp)
{
intel_dp->lttpr_common_caps[DP_PHY_REPEATER_CNT -
static bool intel_dp_read_lttpr_common_caps(struct intel_dp *intel_dp)
{
- if (drm_dp_read_lttpr_common_caps(&intel_dp->aux,
- intel_dp->lttpr_common_caps) < 0) {
- memset(intel_dp->lttpr_common_caps, 0,
- sizeof(intel_dp->lttpr_common_caps));
+ struct drm_i915_private *i915 = dp_to_i915(intel_dp);
+
+ if (intel_dp_is_edp(intel_dp))
return false;
- }
+
+ /*
+ * Detecting LTTPRs must be avoided on platforms with an AUX timeout
+ * period < 3.2ms. (see DP Standard v2.0, 2.11.2, 3.6.6.1).
+ */
+ if (INTEL_GEN(i915) < 10)
+ return false;
+
+ if (drm_dp_read_lttpr_common_caps(&intel_dp->aux,
+ intel_dp->lttpr_common_caps) < 0)
+ goto reset_caps;
drm_dbg_kms(&dp_to_i915(intel_dp)->drm,
"LTTPR common capabilities: %*ph\n",
(int)sizeof(intel_dp->lttpr_common_caps),
intel_dp->lttpr_common_caps);
+ /* The minimum value of LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV is 1.4 */
+ if (intel_dp->lttpr_common_caps[0] < 0x14)
+ goto reset_caps;
+
return true;
+
+reset_caps:
+ intel_dp_reset_lttpr_common_caps(intel_dp);
+ return false;
}
static bool
}
/**
- * intel_dp_lttpr_init - detect LTTPRs and init the LTTPR link training mode
+ * intel_dp_init_lttpr_and_dprx_caps - detect LTTPR and DPRX caps, init the LTTPR link training mode
* @intel_dp: Intel DP struct
*
- * Read the LTTPR common capabilities, switch to non-transparent link training
- * mode if any is detected and read the PHY capabilities for all detected
- * LTTPRs. In case of an LTTPR detection error or if the number of
+ * Read the LTTPR common and DPRX capabilities and switch to non-transparent
+ * link training mode if any is detected and read the PHY capabilities for all
+ * detected LTTPRs. In case of an LTTPR detection error or if the number of
* LTTPRs is more than is supported (8), fall back to the no-LTTPR,
* transparent mode link training mode.
*
* Returns:
- * >0 if LTTPRs were detected and the non-transparent LT mode was set
+ * >0 if LTTPRs were detected and the non-transparent LT mode was set. The
+ * DPRX capabilities are read out.
* 0 if no LTTPRs or more than 8 LTTPRs were detected or in case of a
- * detection failure and the transparent LT mode was set
+ * detection failure and the transparent LT mode was set. The DPRX
+ * capabilities are read out.
+ * <0 Reading out the DPRX capabilities failed.
*/
-int intel_dp_lttpr_init(struct intel_dp *intel_dp)
+int intel_dp_init_lttpr_and_dprx_caps(struct intel_dp *intel_dp)
{
int lttpr_count;
bool ret;
int i;
- if (intel_dp_is_edp(intel_dp))
- return 0;
-
ret = intel_dp_read_lttpr_common_caps(intel_dp);
+
+ /* The DPTX shall read the DPRX caps after LTTPR detection. */
+ if (drm_dp_read_dpcd_caps(&intel_dp->aux, intel_dp->dpcd)) {
+ intel_dp_reset_lttpr_common_caps(intel_dp);
+ return -EIO;
+ }
+
if (!ret)
return 0;
+ /*
+ * The 0xF0000-0xF02FF range is only valid if the DPCD revision is
+ * at least 1.4.
+ */
+ if (intel_dp->dpcd[DP_DPCD_REV] < 0x14) {
+ intel_dp_reset_lttpr_common_caps(intel_dp);
+ return 0;
+ }
+
lttpr_count = drm_dp_lttpr_count(intel_dp->lttpr_common_caps);
/*
* Prevent setting LTTPR transparent mode explicitly if no LTTPRs are
return lttpr_count;
}
-EXPORT_SYMBOL(intel_dp_lttpr_init);
+EXPORT_SYMBOL(intel_dp_init_lttpr_and_dprx_caps);
static u8 dp_voltage_max(u8 preemph)
{
* TODO: Reiniting LTTPRs here won't be needed once proper connector
* HW state readout is added.
*/
- int lttpr_count = intel_dp_lttpr_init(intel_dp);
+ int lttpr_count = intel_dp_init_lttpr_and_dprx_caps(intel_dp);
+
+ if (lttpr_count < 0)
+ /* Still continue with enabling the port and link training. */
+ lttpr_count = 0;
if (!intel_dp_link_train_all_phys(intel_dp, crtc_state, lttpr_count))
intel_dp_schedule_fallback_link_training(intel_dp, crtc_state);
struct intel_crtc_state;
struct intel_dp;
-int intel_dp_lttpr_init(struct intel_dp *intel_dp);
+int intel_dp_init_lttpr_and_dprx_caps(struct intel_dp *intel_dp);
void intel_dp_get_adjust_train(struct intel_dp *intel_dp,
const struct intel_crtc_state *crtc_state,
{
enum pipe pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe;
- if (crtc_state->cpu_transcoder == TRANSCODER_EDP)
- return DSS_CTL1;
-
- return ICL_PIPE_DSS_CTL1(pipe);
+ return is_pipe_dsc(crtc_state) ? ICL_PIPE_DSS_CTL1(pipe) : DSS_CTL1;
}
static i915_reg_t dss_ctl2_reg(const struct intel_crtc_state *crtc_state)
{
enum pipe pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe;
- if (crtc_state->cpu_transcoder == TRANSCODER_EDP)
- return DSS_CTL2;
-
- return ICL_PIPE_DSS_CTL2(pipe);
+ return is_pipe_dsc(crtc_state) ? ICL_PIPE_DSS_CTL2(pipe) : DSS_CTL2;
}
void intel_dsc_enable(struct intel_encoder *encoder,
* FIXME As we do with eDP, just make a note of the time here
* and perform the wait before the next panel power on.
*/
- intel_dsi_msleep(intel_dsi, intel_dsi->panel_pwr_cycle_delay);
+ msleep(intel_dsi->panel_pwr_cycle_delay);
}
static void intel_dsi_shutdown(struct intel_encoder *encoder)
{
struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
- intel_dsi_msleep(intel_dsi, intel_dsi->panel_pwr_cycle_delay);
+ msleep(intel_dsi->panel_pwr_cycle_delay);
}
static bool intel_dsi_get_hw_state(struct intel_encoder *encoder,
goto err_status;
}
+ err = intel_engine_init_cmd_parser(engine);
+ if (err)
+ goto err_cmd_parser;
+
intel_engine_init_active(engine, ENGINE_PHYSICAL);
intel_engine_init_execlists(engine);
- intel_engine_init_cmd_parser(engine);
intel_engine_init__pm(engine);
intel_engine_init_retire(engine);
return 0;
+err_cmd_parser:
+ intel_breadcrumbs_free(engine->breadcrumbs);
err_status:
cleanup_status_page(engine);
return err;
WRITE_ONCE(fence->vma, NULL);
vma->fence = NULL;
- with_intel_runtime_pm_if_in_use(fence_to_uncore(fence)->rpm, wakeref)
+ /*
+ * Skip the write to HW if and only if the device is currently
+ * suspended.
+ *
+ * If the driver does not currently hold a wakeref (if_in_use == 0),
+ * the device may currently be runtime suspended, or it may be woken
+ * up before the suspend takes place. If the device is not suspended
+ * (powered down) and we skip clearing the fence register, the HW is
+ * left in an undefined state where we may end up with multiple
+ * registers overlapping.
+ */
+ with_intel_runtime_pm_if_active(fence_to_uncore(fence)->rpm, wakeref)
fence_write(fence);
}
if (!strncmp(cmd, "srm", 3) ||
!strncmp(cmd, "lrm", 3)) {
- if (offset != i915_mmio_reg_offset(GEN8_L3SQCREG4) &&
- offset != 0x21f0) {
+ if (offset == i915_mmio_reg_offset(GEN8_L3SQCREG4) ||
+ offset == 0x21f0 ||
+ (IS_BROADWELL(gvt->gt->i915) &&
+ offset == i915_mmio_reg_offset(INSTPM)))
+ return 0;
+ else {
gvt_vgpu_err("%s access to register (%x)\n",
cmd, offset);
return -EPERM;
- } else
- return 0;
+ }
}
if (!strncmp(cmd, "lrr-src", 7) ||
!strncmp(cmd, "lrr-dst", 7)) {
- gvt_vgpu_err("not allowed cmd %s\n", cmd);
- return -EPERM;
+ if (IS_BROADWELL(gvt->gt->i915) && offset == 0x215c)
+ return 0;
+ else {
+ gvt_vgpu_err("not allowed cmd %s reg (%x)\n", cmd, offset);
+ return -EPERM;
+ }
}
if (!strncmp(cmd, "pipe_ctrl", 9)) {
* struct intel_engine_cs based on whether the platform requires software
* command parsing.
*/
-void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
+int intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
{
const struct drm_i915_cmd_table *cmd_tables;
int cmd_table_count;
if (!IS_GEN(engine->i915, 7) && !(IS_GEN(engine->i915, 9) &&
engine->class == COPY_ENGINE_CLASS))
- return;
+ return 0;
switch (engine->class) {
case RENDER_CLASS:
break;
default:
MISSING_CASE(engine->class);
- return;
+ goto out;
}
if (!validate_cmds_sorted(engine, cmd_tables, cmd_table_count)) {
drm_err(&engine->i915->drm,
"%s: command descriptions are not sorted\n",
engine->name);
- return;
+ goto out;
}
if (!validate_regs_sorted(engine)) {
drm_err(&engine->i915->drm,
"%s: registers are not sorted\n", engine->name);
- return;
+ goto out;
}
ret = init_hash_table(engine, cmd_tables, cmd_table_count);
drm_err(&engine->i915->drm,
"%s: initialised failed!\n", engine->name);
fini_hash_table(engine);
- return;
+ goto out;
}
engine->flags |= I915_ENGINE_USING_CMD_PARSER;
+
+out:
+ if (intel_engine_requires_cmd_parser(engine) &&
+ !intel_engine_using_cmd_parser(engine))
+ return -EINVAL;
+
+ return 0;
}
/**
/* i915_cmd_parser.c */
int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv);
-void intel_engine_init_cmd_parser(struct intel_engine_cs *engine);
+int intel_engine_init_cmd_parser(struct intel_engine_cs *engine);
void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine);
int intel_engine_cmd_parser(struct intel_engine_cs *engine,
struct i915_vma *batch,
static inline void __tasklet_disable_sync_once(struct tasklet_struct *t)
{
if (!atomic_fetch_inc(&t->count))
- tasklet_unlock_wait(t);
+ tasklet_unlock_spin_wait(t);
}
static inline bool __tasklet_is_enabled(const struct tasklet_struct *t)
{
int report_size = stream->oa_buffer.format_size;
struct drm_i915_perf_record_header header;
- u32 sample_flags = stream->sample_flags;
header.type = DRM_I915_PERF_RECORD_SAMPLE;
header.pad = 0;
return -EFAULT;
buf += sizeof(header);
- if (sample_flags & SAMPLE_OA_REPORT) {
- if (copy_to_user(buf, report, report_size))
- return -EFAULT;
- }
+ if (copy_to_user(buf, report, report_size))
+ return -EFAULT;
(*offset) += header.size;
stream->perf->ops.oa_enable(stream);
- if (stream->periodic)
+ if (stream->sample_flags & SAMPLE_OA_REPORT)
hrtimer_start(&stream->poll_check_timer,
ns_to_ktime(stream->poll_oa_period),
HRTIMER_MODE_REL_PINNED);
{
stream->perf->ops.oa_disable(stream);
- if (stream->periodic)
+ if (stream->sample_flags & SAMPLE_OA_REPORT)
hrtimer_cancel(&stream->poll_check_timer);
}
* disabled stream as an error. In particular it might otherwise lead
* to a deadlock for blocking file descriptors...
*/
- if (!stream->enabled)
+ if (!stream->enabled || !(stream->sample_flags & SAMPLE_OA_REPORT))
return -EIO;
if (!(file->f_flags & O_NONBLOCK)) {
#define ILK_DISPLAY_CHICKEN1 _MMIO(0x42000)
#define ILK_FBCQ_DIS (1 << 22)
-#define ILK_PABSTRETCH_DIS (1 << 21)
+#define ILK_PABSTRETCH_DIS REG_BIT(21)
+#define ILK_SABSTRETCH_DIS REG_BIT(20)
+#define IVB_PRI_STRETCH_MAX_MASK REG_GENMASK(21, 20)
+#define IVB_PRI_STRETCH_MAX_X8 REG_FIELD_PREP(IVB_PRI_STRETCH_MAX_MASK, 0)
+#define IVB_PRI_STRETCH_MAX_X4 REG_FIELD_PREP(IVB_PRI_STRETCH_MAX_MASK, 1)
+#define IVB_PRI_STRETCH_MAX_X2 REG_FIELD_PREP(IVB_PRI_STRETCH_MAX_MASK, 2)
+#define IVB_PRI_STRETCH_MAX_X1 REG_FIELD_PREP(IVB_PRI_STRETCH_MAX_MASK, 3)
+#define IVB_SPR_STRETCH_MAX_MASK REG_GENMASK(19, 18)
+#define IVB_SPR_STRETCH_MAX_X8 REG_FIELD_PREP(IVB_SPR_STRETCH_MAX_MASK, 0)
+#define IVB_SPR_STRETCH_MAX_X4 REG_FIELD_PREP(IVB_SPR_STRETCH_MAX_MASK, 1)
+#define IVB_SPR_STRETCH_MAX_X2 REG_FIELD_PREP(IVB_SPR_STRETCH_MAX_MASK, 2)
+#define IVB_SPR_STRETCH_MAX_X1 REG_FIELD_PREP(IVB_SPR_STRETCH_MAX_MASK, 3)
/*
#define _CHICKEN_PIPESL_1_A 0x420b0
#define _CHICKEN_PIPESL_1_B 0x420b4
+#define HSW_PRI_STRETCH_MAX_MASK REG_GENMASK(28, 27)
+#define HSW_PRI_STRETCH_MAX_X8 REG_FIELD_PREP(HSW_PRI_STRETCH_MAX_MASK, 0)
+#define HSW_PRI_STRETCH_MAX_X4 REG_FIELD_PREP(HSW_PRI_STRETCH_MAX_MASK, 1)
+#define HSW_PRI_STRETCH_MAX_X2 REG_FIELD_PREP(HSW_PRI_STRETCH_MAX_MASK, 2)
+#define HSW_PRI_STRETCH_MAX_X1 REG_FIELD_PREP(HSW_PRI_STRETCH_MAX_MASK, 3)
+#define HSW_SPR_STRETCH_MAX_MASK REG_GENMASK(26, 25)
+#define HSW_SPR_STRETCH_MAX_X8 REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 0)
+#define HSW_SPR_STRETCH_MAX_X4 REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 1)
+#define HSW_SPR_STRETCH_MAX_X2 REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 2)
+#define HSW_SPR_STRETCH_MAX_X1 REG_FIELD_PREP(HSW_SPR_STRETCH_MAX_MASK, 3)
#define HSW_FBCQ_DIS (1 << 22)
#define BDW_DPRS_MASK_VBLANK_SRD (1 << 0)
#define CHICKEN_PIPESL_1(pipe) _MMIO_PIPE(pipe, _CHICKEN_PIPESL_1_A, _CHICKEN_PIPESL_1_B)
struct skl_plane_wm *wm = &crtc_state->wm.skl.raw.planes[plane_id];
int ret;
- memset(wm, 0, sizeof(*wm));
-
/* Watermarks calculated in master */
if (plane_state->planar_slave)
return 0;
+ memset(wm, 0, sizeof(*wm));
+
if (plane_state->planar_linked_plane) {
const struct drm_framebuffer *fb = plane_state->hw.fb;
enum plane_id y_plane_id = plane_state->planar_linked_plane->id;
intel_uncore_write(&dev_priv->uncore, CHICKEN_PAR1_1,
intel_uncore_read(&dev_priv->uncore, CHICKEN_PAR1_1) | DPA_MASK_VBLANK_SRD);
- /* WaPsrDPRSUnmaskVBlankInSRD:bdw */
for_each_pipe(dev_priv, pipe) {
+ /* WaPsrDPRSUnmaskVBlankInSRD:bdw */
intel_uncore_write(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe),
intel_uncore_read(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe)) |
BDW_DPRS_MASK_VBLANK_SRD);
+
+ /* Undocumented but fixes async flip + VT-d corruption */
+ if (intel_vtd_active())
+ intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe),
+ HSW_PRI_STRETCH_MAX_MASK, HSW_PRI_STRETCH_MAX_X1);
}
/* WaVSRefCountFullforceMissDisable:bdw */
static void hsw_init_clock_gating(struct drm_i915_private *dev_priv)
{
+ enum pipe pipe;
+
/* WaFbcAsynchFlipDisableFbcQueue:hsw,bdw */
intel_uncore_write(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A),
intel_uncore_read(&dev_priv->uncore, CHICKEN_PIPESL_1(PIPE_A)) |
HSW_FBCQ_DIS);
+ for_each_pipe(dev_priv, pipe) {
+ /* Undocumented but fixes async flip + VT-d corruption */
+ if (intel_vtd_active())
+ intel_uncore_rmw(&dev_priv->uncore, CHICKEN_PIPESL_1(pipe),
+ HSW_PRI_STRETCH_MAX_MASK, HSW_PRI_STRETCH_MAX_X1);
+ }
+
/* This is required by WaCatErrorRejectionIssue:hsw */
intel_uncore_write(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG,
intel_uncore_read(&dev_priv->uncore, GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
}
/**
- * intel_runtime_pm_get_if_in_use - grab a runtime pm reference if device in use
+ * __intel_runtime_pm_get_if_active - grab a runtime pm reference if device is active
* @rpm: the intel_runtime_pm structure
+ * @ignore_usecount: get a ref even if dev->power.usage_count is 0
*
* This function grabs a device-level runtime pm reference if the device is
- * already in use and ensures that it is powered up. It is illegal to try
- * and access the HW should intel_runtime_pm_get_if_in_use() report failure.
+ * already active and ensures that it is powered up. It is illegal to try
+ * and access the HW should intel_runtime_pm_get_if_active() report failure.
+ *
+ * If @ignore_usecount=true, a reference will be acquired even if there is no
+ * user requiring the device to be powered up (dev->power.usage_count == 0).
+ * If the function returns false in this case then it's guaranteed that the
+ * device's runtime suspend hook has been called already or that it will be
+ * called (and hence it's also guaranteed that the device's runtime resume
+ * hook will be called eventually).
*
* Any runtime pm reference obtained by this function must have a symmetric
* call to intel_runtime_pm_put() to release the reference again.
* Returns: the wakeref cookie to pass to intel_runtime_pm_put(), evaluates
* as True if the wakeref was acquired, or False otherwise.
*/
-intel_wakeref_t intel_runtime_pm_get_if_in_use(struct intel_runtime_pm *rpm)
+static intel_wakeref_t __intel_runtime_pm_get_if_active(struct intel_runtime_pm *rpm,
+ bool ignore_usecount)
{
if (IS_ENABLED(CONFIG_PM)) {
/*
* function, since the power state is undefined. This applies
* atm to the late/early system suspend/resume handlers.
*/
- if (pm_runtime_get_if_in_use(rpm->kdev) <= 0)
+ if (pm_runtime_get_if_active(rpm->kdev, ignore_usecount) <= 0)
return 0;
}
return track_intel_runtime_pm_wakeref(rpm);
}
+intel_wakeref_t intel_runtime_pm_get_if_in_use(struct intel_runtime_pm *rpm)
+{
+ return __intel_runtime_pm_get_if_active(rpm, false);
+}
+
+intel_wakeref_t intel_runtime_pm_get_if_active(struct intel_runtime_pm *rpm)
+{
+ return __intel_runtime_pm_get_if_active(rpm, true);
+}
+
/**
* intel_runtime_pm_get_noresume - grab a runtime pm reference
* @rpm: the intel_runtime_pm structure
intel_wakeref_t intel_runtime_pm_get(struct intel_runtime_pm *rpm);
intel_wakeref_t intel_runtime_pm_get_if_in_use(struct intel_runtime_pm *rpm);
+intel_wakeref_t intel_runtime_pm_get_if_active(struct intel_runtime_pm *rpm);
intel_wakeref_t intel_runtime_pm_get_noresume(struct intel_runtime_pm *rpm);
intel_wakeref_t intel_runtime_pm_get_raw(struct intel_runtime_pm *rpm);
for ((wf) = intel_runtime_pm_get_if_in_use(rpm); (wf); \
intel_runtime_pm_put((rpm), (wf)), (wf) = 0)
+#define with_intel_runtime_pm_if_active(rpm, wf) \
+ for ((wf) = intel_runtime_pm_get_if_active(rpm); (wf); \
+ intel_runtime_pm_put((rpm), (wf)), (wf) = 0)
+
void intel_runtime_pm_put_unchecked(struct intel_runtime_pm *rpm);
#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)
void intel_runtime_pm_put(struct intel_runtime_pm *rpm, intel_wakeref_t wref);
ret = drmm_mode_config_init(drm);
if (ret)
- return ret;
+ goto err_kms;
ret = drm_vblank_init(drm, MAX_CRTC);
if (ret)
int dual = ldb->ldb_ctrl & LDB_SPLIT_MODE_EN;
int mux = drm_of_encoder_active_port_id(imx_ldb_ch->child, encoder);
+ if (mux < 0 || mux >= ARRAY_SIZE(ldb->clk_sel)) {
+ dev_warn(ldb->dev, "%s: invalid mux %d\n", __func__, mux);
+ return;
+ }
+
drm_panel_prepare(imx_ldb_ch->panel);
if (dual) {
int mux = drm_of_encoder_active_port_id(imx_ldb_ch->child, encoder);
u32 bus_format = imx_ldb_ch->bus_format;
+ if (mux < 0 || mux >= ARRAY_SIZE(ldb->clk_sel)) {
+ dev_warn(ldb->dev, "%s: invalid mux %d\n", __func__, mux);
+ return;
+ }
+
if (mode->clock > 170000) {
dev_warn(ldb->dev,
"%s: mode exceeds 170 MHz pixel clock\n", __func__);
struct imx_ldb_channel *channel = &imx_ldb->channel[i];
if (!channel->ldb)
- break;
+ continue;
ret = imx_ldb_register(drm, channel);
if (ret)
return count;
}
+static void meson_drv_shutdown(struct platform_device *pdev)
+{
+ struct meson_drm *priv = dev_get_drvdata(&pdev->dev);
+ struct drm_device *drm = priv->drm;
+
+ DRM_DEBUG_DRIVER("\n");
+ drm_kms_helper_poll_fini(drm);
+ drm_atomic_helper_shutdown(drm);
+}
+
static int meson_drv_probe(struct platform_device *pdev)
{
struct component_match *match = NULL;
static struct platform_driver meson_drm_platform_driver = {
.probe = meson_drv_probe,
+ .shutdown = meson_drv_shutdown,
.driver = {
.name = "meson-drm",
.of_match_table = dt_match,
static int a5xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value)
{
- *value = gpu_read64(gpu, REG_A5XX_RBBM_PERFCTR_CP_0_LO,
- REG_A5XX_RBBM_PERFCTR_CP_0_HI);
+ *value = gpu_read64(gpu, REG_A5XX_RBBM_ALWAYSON_COUNTER_LO,
+ REG_A5XX_RBBM_ALWAYSON_COUNTER_HI);
return 0;
}
/* Set up the limits management */
if (adreno_is_a530(adreno_gpu))
a530_lm_setup(gpu);
- else
+ else if (adreno_is_a540(adreno_gpu))
a540_lm_setup(gpu);
/* Set up SP/TP power collpase */
else
bit = a6xx_gmu_oob_bits[state].ack_new;
- gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET, bit);
+ gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET, 1 << bit);
}
/* Enable CPU control of SPTP power power collapse */
return a6xx_idle(gpu, ring) ? 0 : -EINVAL;
}
-static void a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
+/*
+ * Check that the microcode version is new enough to include several key
+ * security fixes. Return true if the ucode is safe.
+ */
+static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu,
struct drm_gem_object *obj)
{
+ struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
+ struct msm_gpu *gpu = &adreno_gpu->base;
u32 *buf = msm_gem_get_vaddr(obj);
+ bool ret = false;
if (IS_ERR(buf))
- return;
+ return false;
/*
- * If the lowest nibble is 0xa that is an indication that this microcode
- * has been patched. The actual version is in dword [3] but we only care
- * about the patchlevel which is the lowest nibble of dword [3]
- *
- * Otherwise check that the firmware is greater than or equal to 1.90
- * which was the first version that had this fix built in
+ * Targets up to a640 (a618, a630 and a640) need to check for a
+ * microcode version that is patched to support the whereami opcode or
+ * one that is new enough to include it by default.
*/
- if (((buf[0] & 0xf) == 0xa) && (buf[2] & 0xf) >= 1)
- a6xx_gpu->has_whereami = true;
- else if ((buf[0] & 0xfff) > 0x190)
- a6xx_gpu->has_whereami = true;
+ if (adreno_is_a618(adreno_gpu) || adreno_is_a630(adreno_gpu) ||
+ adreno_is_a640(adreno_gpu)) {
+ /*
+ * If the lowest nibble is 0xa that is an indication that this
+ * microcode has been patched. The actual version is in dword
+ * [3] but we only care about the patchlevel which is the lowest
+ * nibble of dword [3]
+ *
+ * Otherwise check that the firmware is greater than or equal
+ * to 1.90 which was the first version that had this fix built
+ * in
+ */
+ if ((((buf[0] & 0xf) == 0xa) && (buf[2] & 0xf) >= 1) ||
+ (buf[0] & 0xfff) >= 0x190) {
+ a6xx_gpu->has_whereami = true;
+ ret = true;
+ goto out;
+ }
+ DRM_DEV_ERROR(&gpu->pdev->dev,
+ "a630 SQE ucode is too old. Have version %x need at least %x\n",
+ buf[0] & 0xfff, 0x190);
+ } else {
+ /*
+ * a650 tier targets don't need whereami but still need to be
+ * equal to or newer than 0.95 for other security fixes
+ */
+ if (adreno_is_a650(adreno_gpu)) {
+ if ((buf[0] & 0xfff) >= 0x095) {
+ ret = true;
+ goto out;
+ }
+
+ DRM_DEV_ERROR(&gpu->pdev->dev,
+ "a650 SQE ucode is too old. Have version %x need at least %x\n",
+ buf[0] & 0xfff, 0x095);
+ }
+
+ /*
+ * When a660 is added those targets should return true here
+ * since those have all the critical security fixes built in
+ * from the start
+ */
+ }
+out:
msm_gem_put_vaddr(obj);
+ return ret;
}
static int a6xx_ucode_init(struct msm_gpu *gpu)
}
msm_gem_object_set_name(a6xx_gpu->sqe_bo, "sqefw");
- a6xx_ucode_check_version(a6xx_gpu, a6xx_gpu->sqe_bo);
+ if (!a6xx_ucode_check_version(a6xx_gpu, a6xx_gpu->sqe_bo)) {
+ msm_gem_unpin_iova(a6xx_gpu->sqe_bo, gpu->aspace);
+ drm_gem_object_put(a6xx_gpu->sqe_bo);
+
+ a6xx_gpu->sqe_bo = NULL;
+ return -EPERM;
+ }
}
gpu_write64(gpu, REG_A6XX_CP_SQE_INSTR_BASE_LO,
/* Force the GPU power on so we can read this register */
a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET);
- *value = gpu_read64(gpu, REG_A6XX_RBBM_PERFCTR_CP_0_LO,
- REG_A6XX_RBBM_PERFCTR_CP_0_HI);
+ *value = gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO,
+ REG_A6XX_CP_ALWAYS_ON_COUNTER_HI);
a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET);
mutex_unlock(&perfcounter_oob);
u32 revn)
{
struct opp_table *opp_table;
- struct nvmem_cell *cell;
u32 supp_hw = UINT_MAX;
- void *buf;
+ u16 speedbin;
+ int ret;
- cell = nvmem_cell_get(dev, "speed_bin");
+ ret = nvmem_cell_read_u16(dev, "speed_bin", &speedbin);
/*
* -ENOENT means that the platform doesn't support speedbin which is
* fine
*/
- if (PTR_ERR(cell) == -ENOENT)
+ if (ret == -ENOENT) {
return 0;
- else if (IS_ERR(cell)) {
- DRM_DEV_ERROR(dev,
- "failed to read speed-bin. Some OPPs may not be supported by hardware");
- goto done;
- }
-
- buf = nvmem_cell_read(cell, NULL);
- if (IS_ERR(buf)) {
- nvmem_cell_put(cell);
+ } else if (ret) {
DRM_DEV_ERROR(dev,
- "failed to read speed-bin. Some OPPs may not be supported by hardware");
+ "failed to read speed-bin (%d). Some OPPs may not be supported by hardware",
+ ret);
goto done;
}
+ speedbin = le16_to_cpu(speedbin);
- supp_hw = fuse_to_supp_hw(dev, revn, *((u32 *) buf));
-
- kfree(buf);
- nvmem_cell_put(cell);
+ supp_hw = fuse_to_supp_hw(dev, revn, speedbin);
done:
opp_table = dev_pm_opp_set_supported_hw(dev, &supp_hw, 1);
DPU_REG_WRITE(c, CTL_TOP, mode_sel);
DPU_REG_WRITE(c, CTL_INTF_ACTIVE, intf_active);
- DPU_REG_WRITE(c, CTL_MERGE_3D_ACTIVE, BIT(cfg->merge_3d - MERGE_3D_0));
+ if (cfg->merge_3d)
+ DPU_REG_WRITE(c, CTL_MERGE_3D_ACTIVE,
+ BIT(cfg->merge_3d - MERGE_3D_0));
}
static void dpu_hw_ctl_intf_cfg(struct dpu_hw_ctl *ctx,
#define DPU_DEBUGFS_DIR "msm_dpu"
#define DPU_DEBUGFS_HWMASKNAME "hw_log_mask"
+#define MIN_IB_BW 400000000ULL /* Min ib vote 400MB */
+
static int dpu_kms_hw_init(struct msm_kms *kms);
static void _dpu_kms_mmu_destroy(struct dpu_kms *dpu_kms);
DPU_DEBUG("REG_DMA is not defined");
}
+ if (of_device_is_compatible(dev->dev->of_node, "qcom,sc7180-mdss"))
+ dpu_kms_parse_data_bus_icc_path(dpu_kms);
+
pm_runtime_get_sync(&dpu_kms->pdev->dev);
dpu_kms->core_rev = readl_relaxed(dpu_kms->mmio + 0x0);
dpu_vbif_init_memtypes(dpu_kms);
- if (of_device_is_compatible(dev->dev->of_node, "qcom,sc7180-mdss"))
- dpu_kms_parse_data_bus_icc_path(dpu_kms);
-
pm_runtime_put_sync(&dpu_kms->pdev->dev);
return 0;
ddev = dpu_kms->dev;
+ WARN_ON(!(dpu_kms->num_paths));
/* Min vote of BW is required before turning on AXI clk */
for (i = 0; i < dpu_kms->num_paths; i++)
- icc_set_bw(dpu_kms->path[i], 0,
- dpu_kms->catalog->perf.min_dram_ib);
+ icc_set_bw(dpu_kms->path[i], 0, Bps_to_icc(MIN_IB_BW));
rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true);
if (rc) {
struct drm_dp_aux dp_aux;
};
+#define MAX_AUX_RETRIES 5
+
static const char *dp_aux_get_error(u32 aux_error)
{
switch (aux_error) {
ret = dp_aux_cmd_fifo_tx(aux, msg);
if (ret < 0) {
+ if (aux->native) {
+ aux->retry_cnt++;
+ if (!(aux->retry_cnt % MAX_AUX_RETRIES))
+ dp_catalog_aux_update_cfg(aux->catalog);
+ }
usleep_range(400, 500); /* at least 400us to next try */
goto unlock_exit;
}
break;
case MSM_DSI_PHY_7NM:
case MSM_DSI_PHY_7NM_V4_1:
- pll = msm_dsi_pll_7nm_init(pdev, id);
+ pll = msm_dsi_pll_7nm_init(pdev, type, id);
break;
default:
pll = ERR_PTR(-ENXIO);
}
#endif
#ifdef CONFIG_DRM_MSM_DSI_7NM_PHY
-struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev, int id);
+struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev,
+ enum msm_dsi_phy_type type, int id);
#else
static inline struct msm_dsi_pll *
-msm_dsi_pll_7nm_init(struct platform_device *pdev, int id)
+msm_dsi_pll_7nm_init(struct platform_device *pdev,
+ enum msm_dsi_phy_type type, int id)
{
return ERR_PTR(-ENODEV);
}
pll_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_LOW_1, reg->frac_div_start_low);
pll_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_MID_1, reg->frac_div_start_mid);
pll_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_HIGH_1, reg->frac_div_start_high);
- pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCKDET_RATE_1, 0x40);
+ pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCKDET_RATE_1, reg->pll_lockdet_rate);
pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCK_DELAY, 0x06);
pll_write(base + REG_DSI_7nm_PHY_PLL_CMODE_1, 0x10); /* TODO: 0x00 for CPHY */
pll_write(base + REG_DSI_7nm_PHY_PLL_CLOCK_INVERTERS, reg->pll_clock_inverters);
{
struct msm_dsi_pll *pll = hw_clk_to_pll(hw);
struct dsi_pll_7nm *pll_7nm = to_pll_7nm(pll);
+ struct dsi_pll_config *config = &pll_7nm->pll_configuration;
void __iomem *base = pll_7nm->mmio;
u64 ref_clk = pll_7nm->vco_ref_clk_rate;
u64 vco_rate = 0x0;
/*
* TODO:
* 1. Assumes prescaler is disabled
- * 2. Multiplier is 2^18. it should be 2^(num_of_frac_bits)
*/
- multiplier = 1 << 18;
+ multiplier = 1 << config->frac_bits;
pll_freq = dec * (ref_clk * 2);
tmp64 = (ref_clk * 2 * frac);
pll_freq += div_u64(tmp64, multiplier);
return ret;
}
-struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev, int id)
+struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev,
+ enum msm_dsi_phy_type type, int id)
{
struct dsi_pll_7nm *pll_7nm;
struct msm_dsi_pll *pll;
pll = &pll_7nm->base;
pll->min_rate = 1000000000UL;
pll->max_rate = 3500000000UL;
- if (pll->type == MSM_DSI_PHY_7NM_V4_1) {
+ if (type == MSM_DSI_PHY_7NM_V4_1) {
pll->min_rate = 600000000UL;
pll->max_rate = (unsigned long)5000000000ULL;
/* workaround for max rate overflowing on 32-bit builds: */
static void lock_crtcs(struct msm_kms *kms, unsigned int crtc_mask)
{
+ int crtc_index;
struct drm_crtc *crtc;
- for_each_crtc_mask(kms->dev, crtc, crtc_mask)
- mutex_lock(&kms->commit_lock[drm_crtc_index(crtc)]);
+ for_each_crtc_mask(kms->dev, crtc, crtc_mask) {
+ crtc_index = drm_crtc_index(crtc);
+ mutex_lock_nested(&kms->commit_lock[crtc_index], crtc_index);
+ }
}
static void unlock_crtcs(struct msm_kms *kms, unsigned int crtc_mask)
kfree(priv);
err_put_drm_dev:
drm_dev_put(ddev);
+ platform_set_drvdata(pdev, NULL);
return ret;
}
static int __maybe_unused msm_pm_prepare(struct device *dev)
{
struct drm_device *ddev = dev_get_drvdata(dev);
+ struct msm_drm_private *priv = ddev ? ddev->dev_private : NULL;
+
+ if (!priv || !priv->kms)
+ return 0;
return drm_mode_config_helper_suspend(ddev);
}
static void __maybe_unused msm_pm_complete(struct device *dev)
{
struct drm_device *ddev = dev_get_drvdata(dev);
+ struct msm_drm_private *priv = ddev ? ddev->dev_private : NULL;
+
+ if (!priv || !priv->kms)
+ return;
drm_mode_config_helper_resume(ddev);
}
static void msm_pdev_shutdown(struct platform_device *pdev)
{
struct drm_device *drm = platform_get_drvdata(pdev);
+ struct msm_drm_private *priv = drm ? drm->dev_private : NULL;
+
+ if (!priv || !priv->kms)
+ return;
drm_atomic_helper_shutdown(drm);
}
int ret;
if (fence > fctx->last_fence) {
- DRM_ERROR("%s: waiting on invalid fence: %u (of %u)\n",
+ DRM_ERROR_RATELIMITED("%s: waiting on invalid fence: %u (of %u)\n",
fctx->name, fence, fctx->last_fence);
return -EINVAL;
}
* from the crtc's pending_timer close to end of the frame:
*/
struct mutex commit_lock[MAX_CRTCS];
- struct lock_class_key commit_lock_keys[MAX_CRTCS];
unsigned pending_crtc_mask;
struct msm_pending_timer pending_timers[MAX_CRTCS];
};
{
unsigned i, ret;
- for (i = 0; i < ARRAY_SIZE(kms->commit_lock); i++) {
- lockdep_register_key(&kms->commit_lock_keys[i]);
- __mutex_init(&kms->commit_lock[i], "&kms->commit_lock[i]",
- &kms->commit_lock_keys[i]);
- }
+ for (i = 0; i < ARRAY_SIZE(kms->commit_lock); i++)
+ mutex_init(&kms->commit_lock[i]);
kms->funcs = funcs;
else
nouveau_display(dev)->format_modifiers = disp50xx_modifiers;
- if (disp->disp->object.oclass >= GK104_DISP) {
+ /* FIXME: 256x256 cursors are supported on Kepler, however unlike Maxwell and later
+ * generations Kepler requires that we use small pages (4K) for cursor scanout surfaces. The
+ * proper fix for this is to teach nouveau to migrate fbs being used for the cursor plane to
+ * small page allocations in prepare_fb(). When this is implemented, we should also force
+ * large pages (128K) for ovly fbs in order to fix Kepler ovlys.
+ * But until then, just limit cursors to 128x128 - which is small enough to avoid ever using
+ * large pages.
+ */
+ if (disp->disp->object.oclass >= GM107_DISP) {
dev->mode_config.cursor_width = 256;
dev->mode_config.cursor_height = 256;
+ } else if (disp->disp->object.oclass >= GK104_DISP) {
+ dev->mode_config.cursor_width = 128;
+ dev->mode_config.cursor_height = 128;
} else {
dev->mode_config.cursor_width = 64;
dev->mode_config.cursor_height = 64;
if (!ttm_dma)
return;
+ if (!ttm_dma->pages) {
+ NV_DEBUG(drm, "ttm_dma 0x%p: pages NULL\n", ttm_dma);
+ return;
+ }
/* Don't waste time looping if the object is coherent */
if (nvbo->force_coherent)
return;
- for (i = 0; i < ttm_dma->num_pages; ++i) {
+ i = 0;
+ while (i < ttm_dma->num_pages) {
struct page *p = ttm_dma->pages[i];
size_t num_pages = 1;
if (!ttm_dma)
return;
+ if (!ttm_dma->pages) {
+ NV_DEBUG(drm, "ttm_dma 0x%p: pages NULL\n", ttm_dma);
+ return;
+ }
/* Don't waste time looping if the object is coherent */
if (nvbo->force_coherent)
return;
- for (i = 0; i < ttm_dma->num_pages; ++i) {
+ i = 0;
+ while (i < ttm_dma->num_pages) {
struct page *p = ttm_dma->pages[i];
size_t num_pages = 1;
const struct mipi_dsi_msg *msg)
{
struct mipi_dsi_packet pkt;
+ int ret;
u32 r;
- r = mipi_dsi_create_packet(&pkt, msg);
- if (r < 0)
- return r;
+ ret = mipi_dsi_create_packet(&pkt, msg);
+ if (ret < 0)
+ return ret;
WARN_ON(!dsi_bus_is_locked(dsi));
u32 height_mm;
u32 max_hs_rate;
u32 max_lp_rate;
+ bool te_support;
};
struct panel_drv_data {
if (r)
goto err;
- r = mipi_dsi_dcs_set_tear_on(ddata->dsi, MIPI_DSI_DCS_TEAR_MODE_VBLANK);
- if (r)
- goto err;
+ if (ddata->panel_data->te_support) {
+ r = mipi_dsi_dcs_set_tear_on(ddata->dsi, MIPI_DSI_DCS_TEAR_MODE_VBLANK);
+ if (r)
+ goto err;
+ }
/* possible panel bug */
msleep(100);
.height_mm = 0,
.max_hs_rate = 300000000,
.max_lp_rate = 10000000,
+ .te_support = true,
};
static const struct dsic_panel_data himalaya_data = {
.height_mm = 88,
.max_hs_rate = 300000000,
.max_lp_rate = 10000000,
+ .te_support = false,
};
static const struct dsic_panel_data droid4_data = {
.height_mm = 89,
.max_hs_rate = 300000000,
.max_lp_rate = 10000000,
+ .te_support = false,
};
static const struct of_device_id dsicm_of_match[] = {
head.id = i;
head.flags = 0;
+ head.surface_id = 0;
oldcount = qdev->monitors_config->count;
if (crtc->state->active) {
struct drm_display_mode *mode = &crtc->mode;
int type, struct qxl_release **release,
struct qxl_bo **rbo)
{
- struct qxl_bo *bo;
+ struct qxl_bo *bo, *free_bo = NULL;
int idr_ret;
int ret = 0;
union qxl_release_info *info;
mutex_lock(&qdev->release_mutex);
if (qdev->current_release_bo_offset[cur_idx] + 1 >= releases_per_bo[cur_idx]) {
- qxl_bo_unref(&qdev->current_release_bo[cur_idx]);
+ free_bo = qdev->current_release_bo[cur_idx];
qdev->current_release_bo_offset[cur_idx] = 0;
qdev->current_release_bo[cur_idx] = NULL;
}
ret = qxl_release_bo_alloc(qdev, &qdev->current_release_bo[cur_idx]);
if (ret) {
mutex_unlock(&qdev->release_mutex);
+ if (free_bo) {
+ qxl_bo_unpin(free_bo);
+ qxl_bo_unref(&free_bo);
+ }
qxl_release_free(qdev, *release);
return ret;
}
*rbo = bo;
mutex_unlock(&qdev->release_mutex);
+ if (free_bo) {
+ qxl_bo_unpin(free_bo);
+ qxl_bo_unref(&free_bo);
+ }
ret = qxl_release_list_add(*release, bo);
qxl_bo_unref(&bo);
struct list_head objects;
};
+extern const struct drm_gem_object_funcs radeon_gem_object_funcs;
+
int radeon_gem_init(struct radeon_device *rdev);
void radeon_gem_fini(struct radeon_device *rdev);
int radeon_gem_object_create(struct radeon_device *rdev, unsigned long size,
int radeon_gem_prime_pin(struct drm_gem_object *obj);
void radeon_gem_prime_unpin(struct drm_gem_object *obj);
-static const struct drm_gem_object_funcs radeon_gem_object_funcs;
+const struct drm_gem_object_funcs radeon_gem_object_funcs;
static void radeon_gem_object_free(struct drm_gem_object *gobj)
{
return r;
}
-static const struct drm_gem_object_funcs radeon_gem_object_funcs = {
+const struct drm_gem_object_funcs radeon_gem_object_funcs = {
.free = radeon_gem_object_free,
.open = radeon_gem_object_open,
.close = radeon_gem_object_close,
if (ret)
return ERR_PTR(ret);
+ bo->tbo.base.funcs = &radeon_gem_object_funcs;
+
mutex_lock(&rdev->gem.mutex);
list_add_tail(&bo->list, &rdev->gem.objects);
mutex_unlock(&rdev->gem.mutex);
if (gtt->userflags & RADEON_GEM_USERPTR_ANONONLY) {
/* check that we only pin down anonymous memory
to prevent problems with writeback */
- unsigned long end = gtt->userptr + ttm->num_pages * PAGE_SIZE;
+ unsigned long end = gtt->userptr + (u64)ttm->num_pages * PAGE_SIZE;
struct vm_area_struct *vma;
vma = find_vma(gtt->usermm, gtt->userptr);
if (!vma || vma->vm_file || vma->vm_end < end)
} while (pinned < ttm->num_pages);
r = sg_alloc_table_from_pages(ttm->sg, ttm->pages, ttm->num_pages, 0,
- ttm->num_pages << PAGE_SHIFT,
+ (u64)ttm->num_pages << PAGE_SHIFT,
GFP_KERNEL);
if (r)
goto release_sg;
static const struct drm_encoder_funcs rcar_du_encoder_funcs = {
};
-static void rcar_du_encoder_release(struct drm_device *dev, void *res)
-{
- struct rcar_du_encoder *renc = res;
-
- drm_encoder_cleanup(&renc->base);
- kfree(renc);
-}
-
int rcar_du_encoder_init(struct rcar_du_device *rcdu,
enum rcar_du_output output,
struct device_node *enc_node)
{
struct rcar_du_encoder *renc;
struct drm_bridge *bridge;
- int ret;
/*
* Locate the DRM bridge from the DT node. For the DPAD outputs, if the
return -ENOLINK;
}
- renc = kzalloc(sizeof(*renc), GFP_KERNEL);
- if (renc == NULL)
- return -ENOMEM;
-
- renc->output = output;
-
dev_dbg(rcdu->dev, "initializing encoder %pOF for output %u\n",
enc_node, output);
- ret = drm_encoder_init(&rcdu->ddev, &renc->base, &rcar_du_encoder_funcs,
- DRM_MODE_ENCODER_NONE, NULL);
- if (ret < 0) {
- kfree(renc);
- return ret;
- }
+ renc = drmm_encoder_alloc(&rcdu->ddev, struct rcar_du_encoder, base,
+ &rcar_du_encoder_funcs, DRM_MODE_ENCODER_NONE,
+ NULL);
+ if (!renc)
+ return -ENOMEM;
- ret = drmm_add_action_or_reset(&rcdu->ddev, rcar_du_encoder_release,
- renc);
- if (ret)
- return ret;
+ renc->output = output;
/*
* Attach the bridge to the encoder. The bridge will create the
dev_err(dc->dev,
"failed to set clock rate to %lu Hz\n",
state->pclk);
+
+ err = clk_set_rate(dc->clk, state->pclk);
+ if (err < 0)
+ dev_err(dc->dev, "failed to set clock %pC to %lu Hz: %d\n",
+ dc->clk, state->pclk, err);
}
DRM_DEBUG_KMS("rate: %lu, div: %u\n", clk_get_rate(dc->clk),
value = SHIFT_CLK_DIVIDER(state->div) | PIXEL_CLK_DIVIDER_PCD1;
tegra_dc_writel(dc, value, DC_DISP_DISP_CLOCK_CONTROL);
}
-
- err = clk_set_rate(dc->clk, state->pclk);
- if (err < 0)
- dev_err(dc->dev, "failed to set clock %pC to %lu Hz: %d\n",
- dc->clk, state->pclk, err);
}
static void tegra_dc_stop(struct tegra_dc *dc)
* POWER_CONTROL registers during CRTC enabling.
*/
if (dc->soc->coupled_pm && dc->pipe == 1) {
- u32 flags = DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE_CONSUMER;
- struct device_link *link;
- struct device *partner;
+ struct device *companion;
+ struct tegra_dc *parent;
- partner = driver_find_device(dc->dev->driver, NULL, NULL,
- tegra_dc_match_by_pipe);
- if (!partner)
+ companion = driver_find_device(dc->dev->driver, NULL, (const void *)0,
+ tegra_dc_match_by_pipe);
+ if (!companion)
return -EPROBE_DEFER;
- link = device_link_add(dc->dev, partner, flags);
- if (!link) {
- dev_err(dc->dev, "failed to link controllers\n");
- return -EINVAL;
- }
+ parent = dev_get_drvdata(companion);
+ dc->client.parent = &parent->client;
- dev_dbg(dc->dev, "coupled to %s\n", dev_name(partner));
+ dev_dbg(dc->dev, "coupled to %s\n", dev_name(companion));
}
return 0;
* kernel is possible.
*/
if (sor->rst) {
+ err = pm_runtime_resume_and_get(sor->dev);
+ if (err < 0) {
+ dev_err(sor->dev, "failed to get runtime PM: %d\n", err);
+ return err;
+ }
+
err = reset_control_acquire(sor->rst);
if (err < 0) {
dev_err(sor->dev, "failed to acquire SOR reset: %d\n",
}
reset_control_release(sor->rst);
+ pm_runtime_put(sor->dev);
}
err = clk_prepare_enable(sor->clk_safe);
struct gm12u320_device {
struct drm_device dev;
+ struct device *dmadev;
struct drm_simple_display_pipe pipe;
struct drm_connector conn;
unsigned char *cmd_buf;
DRM_FORMAT_MOD_INVALID
};
+/*
+ * FIXME: Dma-buf sharing requires DMA support by the importing device.
+ * This function is a workaround to make USB devices work as well.
+ * See todo.rst for how to fix the issue in the dma-buf framework.
+ */
+static struct drm_gem_object *gm12u320_gem_prime_import(struct drm_device *dev,
+ struct dma_buf *dma_buf)
+{
+ struct gm12u320_device *gm12u320 = to_gm12u320(dev);
+
+ if (!gm12u320->dmadev)
+ return ERR_PTR(-ENODEV);
+
+ return drm_gem_prime_import_dev(dev, dma_buf, gm12u320->dmadev);
+}
+
DEFINE_DRM_GEM_FOPS(gm12u320_fops);
static const struct drm_driver gm12u320_drm_driver = {
.fops = &gm12u320_fops,
DRM_GEM_SHMEM_DRIVER_OPS,
+ .gem_prime_import = gm12u320_gem_prime_import,
};
static const struct drm_mode_config_funcs gm12u320_mode_config_funcs = {
struct gm12u320_device, dev);
if (IS_ERR(gm12u320))
return PTR_ERR(gm12u320);
+ dev = &gm12u320->dev;
+
+ gm12u320->dmadev = usb_intf_get_dma_device(to_usb_interface(dev->dev));
+ if (!gm12u320->dmadev)
+ drm_warn(dev, "buffer sharing not supported"); /* not an error */
INIT_DELAYED_WORK(&gm12u320->fb_update.work, gm12u320_fb_update_work);
mutex_init(&gm12u320->fb_update.lock);
- dev = &gm12u320->dev;
-
ret = drmm_mode_config_init(dev);
if (ret)
- return ret;
+ goto err_put_device;
dev->mode_config.min_width = GM12U320_USER_WIDTH;
dev->mode_config.max_width = GM12U320_USER_WIDTH;
ret = gm12u320_usb_alloc(gm12u320);
if (ret)
- return ret;
+ goto err_put_device;
ret = gm12u320_set_ecomode(gm12u320);
if (ret)
- return ret;
+ goto err_put_device;
ret = gm12u320_conn_init(gm12u320);
if (ret)
- return ret;
+ goto err_put_device;
ret = drm_simple_display_pipe_init(&gm12u320->dev,
&gm12u320->pipe,
gm12u320_pipe_modifiers,
&gm12u320->conn);
if (ret)
- return ret;
+ goto err_put_device;
drm_mode_config_reset(dev);
usb_set_intfdata(interface, dev);
ret = drm_dev_register(dev, 0);
if (ret)
- return ret;
+ goto err_put_device;
drm_fbdev_generic_setup(dev, 0);
return 0;
+
+err_put_device:
+ put_device(gm12u320->dmadev);
+ return ret;
}
static void gm12u320_usb_disconnect(struct usb_interface *interface)
{
struct drm_device *dev = usb_get_intfdata(interface);
+ struct gm12u320_device *gm12u320 = to_gm12u320(dev);
+ put_device(gm12u320->dmadev);
+ gm12u320->dmadev = NULL;
drm_dev_unplug(dev);
drm_atomic_helper_shutdown(dev);
}
struct ttm_bo_device *bdev = bo->bdev;
struct ttm_resource_manager *man;
- dma_resv_assert_held(bo->base.resv);
+ if (!bo->deleted)
+ dma_resv_assert_held(bo->base.resv);
if (bo->pin_count) {
ttm_bo_del_from_lru(bo);
* Make pinned bos immediately available to
* shrinkers, now that they are queued for
* destruction.
+ *
+ * FIXME: QXL is triggering this. Can be removed when the
+ * driver is fixed.
*/
- if (WARN_ON(bo->pin_count)) {
+ if (WARN_ON_ONCE(bo->pin_count)) {
bo->pin_count = 0;
ttm_bo_move_to_lru_tail(bo, &bo->mem, NULL);
}
/* Remove a pool_type from the global shrinker list and free all pages */
static void ttm_pool_type_fini(struct ttm_pool_type *pt)
{
- struct page *p, *tmp;
+ struct page *p;
mutex_lock(&shrinker_lock);
list_del(&pt->shrinker_list);
mutex_unlock(&shrinker_lock);
- list_for_each_entry_safe(p, tmp, &pt->pages, lru)
+ while ((p = ttm_pool_type_take(pt)))
ttm_pool_free_page(pt->pool, pt->caching, pt->order, p);
}
return drm_mode_config_helper_resume(dev);
}
+/*
+ * FIXME: Dma-buf sharing requires DMA support by the importing device.
+ * This function is a workaround to make USB devices work as well.
+ * See todo.rst for how to fix the issue in the dma-buf framework.
+ */
+static struct drm_gem_object *udl_driver_gem_prime_import(struct drm_device *dev,
+ struct dma_buf *dma_buf)
+{
+ struct udl_device *udl = to_udl(dev);
+
+ if (!udl->dmadev)
+ return ERR_PTR(-ENODEV);
+
+ return drm_gem_prime_import_dev(dev, dma_buf, udl->dmadev);
+}
+
DEFINE_DRM_GEM_FOPS(udl_driver_fops);
static const struct drm_driver driver = {
/* GEM hooks */
.fops = &udl_driver_fops,
DRM_GEM_SHMEM_DRIVER_OPS,
+ .gem_prime_import = udl_driver_gem_prime_import,
.name = DRIVER_NAME,
.desc = DRIVER_DESC,
struct udl_device {
struct drm_device drm;
struct device *dev;
+ struct device *dmadev;
struct drm_simple_display_pipe display_pipe;
DRM_DEBUG("\n");
+ udl->dmadev = usb_intf_get_dma_device(to_usb_interface(dev->dev));
+ if (!udl->dmadev)
+ drm_warn(dev, "buffer sharing not supported"); /* not an error */
+
mutex_init(&udl->gem_lock);
if (!udl_parse_vendor_descriptor(udl)) {
err:
if (udl->urbs.count)
udl_free_urb_list(dev);
+ put_device(udl->dmadev);
DRM_ERROR("%d\n", ret);
return ret;
}
int udl_drop_usb(struct drm_device *dev)
{
+ struct udl_device *udl = to_udl(dev);
+
udl_free_urb_list(dev);
+ put_device(udl->dmadev);
+ udl->dmadev = NULL;
+
return 0;
}
{
const struct vc4_crtc_data *crtc_data = vc4_crtc_to_vc4_crtc_data(vc4_crtc);
const struct vc4_pv_data *pv_data = vc4_crtc_to_vc4_pv_data(vc4_crtc);
+ struct vc4_dev *vc4 = to_vc4_dev(vc4_crtc->base.dev);
u32 fifo_len_bytes = pv_data->fifo_depth;
/*
if (crtc_data->hvs_output == 5)
return 32;
+ /*
+ * It looks like in some situations, we will overflow
+ * the PixelValve FIFO (with the bit 10 of PV stat being
+ * set) and stall the HVS / PV, eventually resulting in
+ * a page flip timeout.
+ *
+ * Displaying the video overlay during a playback with
+ * Kodi on an RPi3 seems to be a great solution with a
+ * failure rate around 50%.
+ *
+ * Removing 1 from the FIFO full level however
+ * seems to completely remove that issue.
+ */
+ if (!vc4->hvs->hvs5)
+ return fifo_len_bytes - 3 * HVS_FIFO_LATENCY_PIX - 1;
+
return fifo_len_bytes - 3 * HVS_FIFO_LATENCY_PIX;
}
}
plane->state->src_y = state->src_y;
plane->state->src_w = state->src_w;
plane->state->src_h = state->src_h;
- plane->state->src_h = state->src_h;
plane->state->alpha = state->alpha;
plane->state->pixel_blend_mode = state->pixel_blend_mode;
plane->state->rotation = state->rotation;
vmw_bo_unreference(&old_buf);
res->id = vcotbl->type;
+ /* Release the pin acquired in vmw_bo_init */
+ ttm_bo_unpin(bo);
+
return 0;
out_map_new:
ttm_bo_kunmap(&old_map);
out_wait:
+ ttm_bo_unpin(bo);
ttm_bo_unreserve(bo);
vmw_bo_unreference(&buf);
dev_priv->last_read_seqno = (uint32_t) -100;
dev_priv->drm.dev_private = dev_priv;
- ret = vmw_setup_pci_resources(dev_priv, pci_id);
- if (ret)
- return ret;
- ret = vmw_detect_version(dev_priv);
- if (ret)
- goto out_no_pci_or_version;
-
mutex_init(&dev_priv->cmdbuf_mutex);
- mutex_init(&dev_priv->release_mutex);
mutex_init(&dev_priv->binding_mutex);
- mutex_init(&dev_priv->global_kms_state_mutex);
ttm_lock_init(&dev_priv->reservation_sem);
spin_lock_init(&dev_priv->resource_lock);
spin_lock_init(&dev_priv->hw_lock);
spin_lock_init(&dev_priv->cap_lock);
spin_lock_init(&dev_priv->cursor_lock);
+ ret = vmw_setup_pci_resources(dev_priv, pci_id);
+ if (ret)
+ return ret;
+ ret = vmw_detect_version(dev_priv);
+ if (ret)
+ goto out_no_pci_or_version;
+
+
for (i = vmw_res_context; i < vmw_res_max; ++i) {
idr_init(&dev_priv->res_idr[i]);
INIT_LIST_HEAD(&dev_priv->res_lru[i]);
struct vmw_overlay *overlay_priv;
struct drm_property *hotplug_mode_update_property;
struct drm_property *implicit_placement_property;
- struct mutex global_kms_state_mutex;
spinlock_t cursor_lock;
struct drm_atomic_state *suspend_state;
bool refuse_hibernation;
bool suspend_locked;
- struct mutex release_mutex;
atomic_t num_fifo_resources;
/*
struct vmw_buffer_object *tmp_buf = *buf;
*buf = NULL;
- if (tmp_buf != NULL) {
+ if (tmp_buf != NULL)
ttm_bo_put(&tmp_buf->base);
- }
}
static inline struct vmw_buffer_object *
struct vmw_piter data_iter,
unsigned long num_data_pages);
+
+static inline void vmw_bo_unpin_unlocked(struct ttm_buffer_object *bo)
+{
+ int ret = ttm_bo_reserve(bo, false, true, NULL);
+ BUG_ON(ret != 0);
+ ttm_bo_unpin(bo);
+ ttm_bo_unreserve(bo);
+}
+
+
/*
* vmw_setup_otable_base - Issue an object table base setup command to
* the device
&batch->otables[i]);
}
+ vmw_bo_unpin_unlocked(batch->otable_bo);
ttm_bo_put(batch->otable_bo);
batch->otable_bo = NULL;
return ret;
BUG_ON(ret != 0);
vmw_bo_fence_single(bo, NULL);
+ ttm_bo_unpin(bo);
ttm_bo_unreserve(bo);
ttm_bo_put(batch->otable_bo);
void vmw_mob_destroy(struct vmw_mob *mob)
{
if (mob->pt_bo) {
+ vmw_bo_unpin_unlocked(mob->pt_bo);
ttm_bo_put(mob->pt_bo);
mob->pt_bo = NULL;
}
out_no_cmd_space:
vmw_fifo_resource_dec(dev_priv);
if (pt_set_up) {
+ vmw_bo_unpin_unlocked(mob->pt_bo);
ttm_bo_put(mob->pt_bo);
mob->pt_bo = NULL;
}
vm_fault_t ret;
pgoff_t fault_page_size;
bool write = vmf->flags & FAULT_FLAG_WRITE;
- bool is_cow_mapping =
- (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
switch (pe_size) {
case PE_SIZE_PMD:
}
/* Always do write dirty-tracking and COW on PTE level. */
- if (write && (READ_ONCE(vbo->dirty) || is_cow_mapping))
+ if (write && (READ_ONCE(vbo->dirty) || is_cow_mapping(vma->vm_flags)))
return VM_FAULT_FALLBACK;
ret = ttm_bo_vm_reserve(bo, vmf);
vma->vm_ops = &vmw_vm_ops;
/* Use VM_PFNMAP rather than VM_MIXEDMAP if not a COW mapping */
- if ((vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) != VM_MAYWRITE)
+ if (!is_cow_mapping(vma->vm_flags))
vma->vm_flags = (vma->vm_flags & ~VM_MIXEDMAP) | VM_PFNMAP;
return 0;
drm_dev = drm_dev_alloc(&xen_drm_driver, dev);
if (IS_ERR(drm_dev)) {
ret = PTR_ERR(drm_dev);
- goto fail;
+ goto fail_dev;
}
drm_info->drm_dev = drm_dev;
drm_kms_helper_poll_fini(drm_dev);
drm_mode_config_cleanup(drm_dev);
drm_dev_put(drm_dev);
-fail:
+fail_dev:
kfree(drm_info);
+ front_info->drm_info = NULL;
+fail:
return ret;
}
struct drm_connector;
struct xen_drm_front_drm_info;
-struct xen_drm_front_drm_info;
int xen_drm_front_conn_init(struct xen_drm_front_drm_info *drm_info,
struct drm_connector *connector);
EXPORT_SYMBOL(host1x_driver_unregister);
/**
- * host1x_client_register() - register a host1x client
+ * __host1x_client_register() - register a host1x client
* @client: host1x client
+ * @key: lock class key for the client-specific mutex
*
* Registers a host1x client with each host1x controller instance. Note that
* each client will only match their parent host1x controller and will only be
* device and call host1x_device_init(), which will in turn call each client's
* &host1x_client_ops.init implementation.
*/
-int host1x_client_register(struct host1x_client *client)
+int __host1x_client_register(struct host1x_client *client,
+ struct lock_class_key *key)
{
struct host1x *host1x;
int err;
INIT_LIST_HEAD(&client->list);
- mutex_init(&client->lock);
+ __mutex_init(&client->lock, "host1x client lock", key);
client->usecount = 0;
mutex_lock(&devices_lock);
return 0;
}
-EXPORT_SYMBOL(host1x_client_register);
+EXPORT_SYMBOL(__host1x_client_register);
/**
* host1x_client_unregister() - unregister a host1x client
#include <linux/bitops.h>
#include <linux/delay.h>
#include <linux/dma-mapping.h>
+#include <linux/dmi.h>
#include <linux/interrupt.h>
#include <linux/io-64-nonatomic-lo-hi.h>
#include <linux/module.h>
#define ACEL_EN BIT(0)
#define GYRO_EN BIT(1)
-#define MAGNO_EN BIT(2)
+#define MAGNO_EN BIT(2)
#define ALS_EN BIT(19)
+static int sensor_mask_override = -1;
+module_param_named(sensor_mask, sensor_mask_override, int, 0444);
+MODULE_PARM_DESC(sensor_mask, "override the detected sensors mask");
+
void amd_start_sensor(struct amd_mp2_dev *privdata, struct amd_mp2_sensor_info info)
{
union sfh_cmd_param cmd_param;
writel(cmd_base.ul, privdata->mmio + AMD_C2P_MSG0);
}
+static const struct dmi_system_id dmi_sensor_mask_overrides[] = {
+ {
+ .matches = {
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP ENVY x360 Convertible 13-ag0xxx"),
+ },
+ .driver_data = (void *)(ACEL_EN | MAGNO_EN),
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP ENVY x360 Convertible 15-cp0xxx"),
+ },
+ .driver_data = (void *)(ACEL_EN | MAGNO_EN),
+ },
+ { }
+};
+
int amd_mp2_get_sensor_num(struct amd_mp2_dev *privdata, u8 *sensor_id)
{
int activestatus, num_of_sensors = 0;
+ const struct dmi_system_id *dmi_id;
+ u32 activecontrolstatus;
+
+ if (sensor_mask_override == -1) {
+ dmi_id = dmi_first_match(dmi_sensor_mask_overrides);
+ if (dmi_id)
+ sensor_mask_override = (long)dmi_id->driver_data;
+ }
+
+ if (sensor_mask_override >= 0) {
+ activestatus = sensor_mask_override;
+ } else {
+ activecontrolstatus = readl(privdata->mmio + AMD_P2C_MSG3);
+ activestatus = activecontrolstatus >> 4;
+ }
- privdata->activecontrolstatus = readl(privdata->mmio + AMD_P2C_MSG3);
- activestatus = privdata->activecontrolstatus >> 4;
if (ACEL_EN & activestatus)
sensor_id[num_of_sensors++] = accel_idx;
struct pci_dev *pdev;
struct amdtp_cl_data *cl_data;
void __iomem *mmio;
- u32 activecontrolstatus;
};
struct amd_mp2_sensor_info {
if (input_register_device(data->input2)) {
input_free_device(input2);
+ ret = -ENOENT;
goto exit;
}
}
USB_DEVICE_ID_ASUSTEK_ROG_NKEY_KEYBOARD),
QUIRK_USE_KBD_BACKLIGHT | QUIRK_ROG_NKEY_KEYBOARD },
{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
+ USB_DEVICE_ID_ASUSTEK_ROG_NKEY_KEYBOARD2),
+ QUIRK_USE_KBD_BACKLIGHT | QUIRK_ROG_NKEY_KEYBOARD },
+ { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
USB_DEVICE_ID_ASUSTEK_T100TA_KEYBOARD),
QUIRK_T100_KEYBOARD | QUIRK_NO_CONSUMER_USAGES },
{ HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
atomic_t read_avail;
atomic_t xfer_avail;
struct gpio_chip gc;
+ struct irq_chip irq;
u8 *in_out_buffer;
struct mutex lock;
return 0;
}
-static struct irq_chip cp2112_gpio_irqchip = {
- .name = "cp2112-gpio",
- .irq_startup = cp2112_gpio_irq_startup,
- .irq_shutdown = cp2112_gpio_irq_shutdown,
- .irq_ack = cp2112_gpio_irq_ack,
- .irq_mask = cp2112_gpio_irq_mask,
- .irq_unmask = cp2112_gpio_irq_unmask,
- .irq_set_type = cp2112_gpio_irq_type,
-};
-
static int __maybe_unused cp2112_allocate_irq(struct cp2112_device *dev,
int pin)
{
dev->gc.can_sleep = 1;
dev->gc.parent = &hdev->dev;
+ dev->irq.name = "cp2112-gpio";
+ dev->irq.irq_startup = cp2112_gpio_irq_startup;
+ dev->irq.irq_shutdown = cp2112_gpio_irq_shutdown;
+ dev->irq.irq_ack = cp2112_gpio_irq_ack;
+ dev->irq.irq_mask = cp2112_gpio_irq_mask;
+ dev->irq.irq_unmask = cp2112_gpio_irq_unmask;
+ dev->irq.irq_set_type = cp2112_gpio_irq_type;
+ dev->irq.flags = IRQCHIP_MASK_ON_SUSPEND;
+
girq = &dev->gc.irq;
- girq->chip = &cp2112_gpio_irqchip;
+ girq->chip = &dev->irq;
/* The event comes from the outside so no parent handler */
girq->parent_handler = NULL;
girq->num_parents = 0;
static const struct hid_device_id hammer_devices[] = {
{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
+ USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_DON) },
+ { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_HAMMER) },
{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_MAGNEMITE) },
#define USB_DEVICE_ID_ASUSTEK_ROG_KEYBOARD2 0x1837
#define USB_DEVICE_ID_ASUSTEK_ROG_KEYBOARD3 0x1822
#define USB_DEVICE_ID_ASUSTEK_ROG_NKEY_KEYBOARD 0x1866
+#define USB_DEVICE_ID_ASUSTEK_ROG_NKEY_KEYBOARD2 0x19b6
#define USB_DEVICE_ID_ASUSTEK_FX503VD_KEYBOARD 0x1869
#define USB_VENDOR_ID_ATEN 0x0557
#define USB_DEVICE_ID_GOOGLE_MASTERBALL 0x503c
#define USB_DEVICE_ID_GOOGLE_MAGNEMITE 0x503d
#define USB_DEVICE_ID_GOOGLE_MOONBALL 0x5044
+#define USB_DEVICE_ID_GOOGLE_DON 0x5050
#define USB_VENDOR_ID_GOTOP 0x08f2
#define USB_DEVICE_ID_SUPER_Q2 0x007f
!wacom_wac->shared->is_touch_on) {
if (!wacom_wac->shared->touch_down)
return;
- prox = 0;
+ prox = false;
}
wacom_wac->hid_data.num_received++;
{
struct wacom_features *features = &wacom_wac->features;
- input_dev->evbit[0] |= BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS);
-
if (!(features->device_type & WACOM_DEVICETYPE_PEN))
return -ENODEV;
return 0;
}
+ input_dev->evbit[0] |= BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS);
__set_bit(BTN_TOUCH, input_dev->keybit);
__set_bit(ABS_MISC, input_dev->absbit);
{
struct wacom_features *features = &wacom_wac->features;
- input_dev->evbit[0] |= BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS);
-
if (!(features->device_type & WACOM_DEVICETYPE_TOUCH))
return -ENODEV;
/* setup has already been done */
return 0;
+ input_dev->evbit[0] |= BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS);
__set_bit(BTN_TOUCH, input_dev->keybit);
if (features->touch_max == 1) {
if ((comp_param1 & DW_IC_COMP_PARAM_1_SPEED_MODE_MASK)
!= DW_IC_COMP_PARAM_1_SPEED_MODE_HIGH) {
dev_err(dev->dev, "High Speed not supported!\n");
+ t->bus_freq_hz = I2C_MAX_FAST_MODE_FREQ;
dev->master_cfg &= ~DW_IC_CON_SPEED_MASK;
dev->master_cfg |= DW_IC_CON_SPEED_FAST;
dev->hs_hcnt = 0;
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* i2c-exynos5.c - Samsung Exynos5 I2C Controller Driver
*
* Copyright (C) 2013 Samsung Electronics Co., Ltd.
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright (c) 2014 Linaro Ltd.
- * Copyright (c) 2014 Hisilicon Limited.
+ * Copyright (c) 2014 HiSilicon Limited.
*
* Now only support 7 bit address.
*/
i2c_sta = jz4780_i2c_readw(i2c, JZ4780_I2C_STA);
data = *i2c->wbuf;
data &= ~JZ4780_I2C_DC_READ;
- if ((!i2c->stop_hold) && (i2c->cdata->version >=
- ID_X1000))
+ if ((i2c->wt_len == 1) && (!i2c->stop_hold) &&
+ (i2c->cdata->version >= ID_X1000))
data |= X1000_I2C_DC_STOP;
jz4780_i2c_writew(i2c, JZ4780_I2C_DC, data);
i2c->wbuf++;
writel(0, drv_data->reg_base + drv_data->reg_offsets.ext_addr);
writel(MV64XXX_I2C_REG_CONTROL_TWSIEN | MV64XXX_I2C_REG_CONTROL_STOP,
drv_data->reg_base + drv_data->reg_offsets.control);
+
+ if (drv_data->errata_delay)
+ udelay(5);
+
drv_data->state = MV64XXX_I2C_STATE_IDLE;
}
default:
/*
* N-byte reception:
- * Enable ACK, reset POS (ACK postion) and clear ADDR flag.
+ * Enable ACK, reset POS (ACK position) and clear ADDR flag.
* In that way, ACK will be sent as soon as the current byte
* will be received in the shift register
*/
static int i2c_init_recovery(struct i2c_adapter *adap)
{
struct i2c_bus_recovery_info *bri = adap->bus_recovery_info;
- char *err_str;
+ char *err_str, *err_level = KERN_ERR;
if (!bri)
return 0;
return -EPROBE_DEFER;
if (!bri->recover_bus) {
- err_str = "no recover_bus() found";
+ err_str = "no suitable method provided";
+ err_level = KERN_DEBUG;
goto err;
}
return 0;
err:
- dev_err(&adap->dev, "Not using recovery: %s\n", err_str);
+ dev_printk(err_level, &adap->dev, "Not using recovery: %s\n", err_str);
adap->bus_recovery_info = NULL;
return -EINVAL;
select IIO_BUFFER
select IIO_BUFFER_HW_CONSUMER
select IIO_BUFFER_DMAENGINE
+ depends on HAS_IOMEM
+ depends on OF
help
Say yes here to build support for Analog Devices Generic
AXI ADC IP core. The IP core is used for interfacing with
depends on ARCH_STM32 || COMPILE_TEST
depends on OF
depends on REGULATOR
+ depends on HAS_IOMEM
select IIO_BUFFER
select MFD_STM32_TIMERS
select IIO_STM32_TIMER_TRIGGER
return processed;
/* Return millivolt or milliamps or millicentigrades */
- *val = processed * 1000;
+ *val = processed;
return IIO_VAL_INT;
}
int ret;
int i;
int bits_per_word = ad7949_adc->resolution;
- int mask = GENMASK(ad7949_adc->resolution, 0);
+ int mask = GENMASK(ad7949_adc->resolution - 1, 0);
struct spi_message msg;
struct spi_transfer tx[] = {
{
VADC_CHAN_NO_SCALE(P_MUX16_1_3, 1)
VADC_CHAN_NO_SCALE(LR_MUX1_BAT_THERM, 0)
- VADC_CHAN_NO_SCALE(LR_MUX2_BAT_ID, 0)
+ VADC_CHAN_VOLT(LR_MUX2_BAT_ID, 0, SCALE_DEFAULT)
VADC_CHAN_NO_SCALE(LR_MUX3_XO_THERM, 0)
VADC_CHAN_NO_SCALE(LR_MUX4_AMUX_THM1, 0)
VADC_CHAN_NO_SCALE(LR_MUX5_AMUX_THM2, 0)
MPU3050_FIFO_R,
&fifo_values[offset],
toread);
+ if (ret)
+ goto out_trigger_unlock;
dev_dbg(mpu3050->dev,
"%04x %04x %04x %04x %04x\n",
struct hid_humidity_state {
struct hid_sensor_common common_attributes;
struct hid_sensor_hub_attribute_info humidity_attr;
- s32 humidity_data;
+ struct {
+ s32 humidity_data;
+ u64 timestamp __aligned(8);
+ } scan;
int scale_pre_decml;
int scale_post_decml;
int scale_precision;
struct hid_humidity_state *humid_st = iio_priv(indio_dev);
if (atomic_read(&humid_st->common_attributes.data_ready))
- iio_push_to_buffers_with_timestamp(indio_dev,
- &humid_st->humidity_data,
- iio_get_time_ns(indio_dev));
+ iio_push_to_buffers_with_timestamp(indio_dev, &humid_st->scan,
+ iio_get_time_ns(indio_dev));
return 0;
}
switch (usage_id) {
case HID_USAGE_SENSOR_ATMOSPHERIC_HUMIDITY:
- humid_st->humidity_data = *(s32 *)raw_data;
+ humid_st->scan.humidity_data = *(s32 *)raw_data;
return 0;
default:
if (ret)
goto err_ret;
- ret = sscanf(indio_dev->name, "adis%u\n", &device_id);
- if (ret != 1) {
+ if (sscanf(indio_dev->name, "adis%u\n", &device_id) != 1) {
ret = -EINVAL;
goto err_ret;
}
struct hid_sensor_common common_attributes;
struct hid_sensor_hub_attribute_info prox_attr;
u32 human_presence;
+ int scale_pre_decml;
+ int scale_post_decml;
+ int scale_precision;
};
/* Channel definitions */
ret_type = IIO_VAL_INT;
break;
case IIO_CHAN_INFO_SCALE:
- *val = prox_state->prox_attr.units;
- ret_type = IIO_VAL_INT;
+ *val = prox_state->scale_pre_decml;
+ *val2 = prox_state->scale_post_decml;
+ ret_type = prox_state->scale_precision;
break;
case IIO_CHAN_INFO_OFFSET:
*val = hid_sensor_convert_exponent(
HID_USAGE_SENSOR_HUMAN_PRESENCE,
&st->common_attributes.sensitivity);
+ st->scale_precision = hid_sensor_format_scale(
+ hsdev->usage,
+ &st->prox_attr,
+ &st->scale_pre_decml, &st->scale_post_decml);
+
return ret;
}
struct temperature_state {
struct hid_sensor_common common_attributes;
struct hid_sensor_hub_attribute_info temperature_attr;
- s32 temperature_data;
+ struct {
+ s32 temperature_data;
+ u64 timestamp __aligned(8);
+ } scan;
int scale_pre_decml;
int scale_post_decml;
int scale_precision;
BIT(IIO_CHAN_INFO_SAMP_FREQ) |
BIT(IIO_CHAN_INFO_HYSTERESIS),
},
- IIO_CHAN_SOFT_TIMESTAMP(3),
+ IIO_CHAN_SOFT_TIMESTAMP(1),
};
/* Adjust channel real bits based on report descriptor */
struct temperature_state *temp_st = iio_priv(indio_dev);
if (atomic_read(&temp_st->common_attributes.data_ready))
- iio_push_to_buffers_with_timestamp(indio_dev,
- &temp_st->temperature_data,
- iio_get_time_ns(indio_dev));
+ iio_push_to_buffers_with_timestamp(indio_dev, &temp_st->scan,
+ iio_get_time_ns(indio_dev));
return 0;
}
switch (usage_id) {
case HID_USAGE_SENSOR_DATA_ENVIRONMENTAL_TEMPERATURE:
- temp_st->temperature_data = *(s32 *)raw_data;
+ temp_st->scan.temperature_data = *(s32 *)raw_data;
return 0;
default:
return -EINVAL;
static const struct nla_policy ib_nl_addr_policy[LS_NLA_TYPE_MAX] = {
[LS_NLA_TYPE_DGID] = {.type = NLA_BINARY,
- .len = sizeof(struct rdma_nla_ls_gid)},
+ .len = sizeof(struct rdma_nla_ls_gid),
+ .validation_type = NLA_VALIDATE_MIN,
+ .min = sizeof(struct rdma_nla_ls_gid)},
};
static inline bool ib_nl_is_good_ip_resp(const struct nlmsghdr *nlh)
ep->com.local_addr.ss_family == AF_INET) {
err = cxgb4_remove_server_filter(
ep->com.dev->rdev.lldi.ports[0], ep->stid,
- ep->com.dev->rdev.lldi.rxq_ids[0], 0);
+ ep->com.dev->rdev.lldi.rxq_ids[0], false);
} else {
struct sockaddr_in6 *sin6;
c4iw_init_wr_wait(ep->com.wr_waitp);
err = cxgb4_remove_server(
ep->com.dev->rdev.lldi.ports[0], ep->stid,
- ep->com.dev->rdev.lldi.rxq_ids[0], 0);
+ ep->com.dev->rdev.lldi.rxq_ids[0],
+ ep->com.local_addr.ss_family == AF_INET6);
if (err)
goto done;
err = c4iw_wait_for_reply(&ep->com.dev->rdev, ep->com.wr_waitp,
*/
int hfi1_dev_affinity_init(struct hfi1_devdata *dd)
{
- int node = pcibus_to_node(dd->pcidev->bus);
struct hfi1_affinity_node *entry;
const struct cpumask *local_mask;
int curr_cpu, possible, i, ret;
bool new_entry = false;
- /*
- * If the BIOS does not have the NUMA node information set, select
- * NUMA 0 so we get consistent performance.
- */
- if (node < 0) {
- dd_dev_err(dd, "Invalid PCI NUMA node. Performance may be affected\n");
- node = 0;
- }
- dd->node = node;
-
local_mask = cpumask_of_node(dd->node);
if (cpumask_first(local_mask) >= nr_cpu_ids)
local_mask = topology_core_cpumask(0);
* create an entry in the global affinity structure and initialize it.
*/
if (!entry) {
- entry = node_affinity_allocate(node);
+ entry = node_affinity_allocate(dd->node);
if (!entry) {
dd_dev_err(dd,
"Unable to allocate global affinity node\n");
if (new_entry)
node_affinity_add_tail(entry);
+ dd->affinity_entry = entry;
mutex_unlock(&node_affinity.lock);
return 0;
{
struct hfi1_affinity_node *entry;
- if (dd->node < 0)
- return;
-
mutex_lock(&node_affinity.lock);
+ if (!dd->affinity_entry)
+ goto unlock;
entry = node_affinity_lookup(dd->node);
if (!entry)
goto unlock;
*/
_dev_comp_vect_cpu_mask_clean_up(dd, entry);
unlock:
+ dd->affinity_entry = NULL;
mutex_unlock(&node_affinity.lock);
- dd->node = NUMA_NO_NODE;
}
/*
spinlock_t irq_src_lock;
int vnic_num_vports;
struct net_device *dummy_netdev;
+ struct hfi1_affinity_node *affinity_entry;
/* Keeps track of IPoIB RSM rule users */
atomic_t ipoib_rsm_usr_num;
dd->pport = (struct hfi1_pportdata *)(dd + 1);
dd->pcidev = pdev;
pci_set_drvdata(pdev, dd);
- dd->node = NUMA_NO_NODE;
ret = xa_alloc_irq(&hfi1_dev_table, &dd->unit, dd, xa_limit_32b,
GFP_KERNEL);
goto bail;
}
rvt_set_ibdev_name(&dd->verbs_dev.rdi, "%s_%d", class_name(), dd->unit);
+ /*
+ * If the BIOS does not have the NUMA node information set, select
+ * NUMA 0 so we get consistent performance.
+ */
+ dd->node = pcibus_to_node(pdev->bus);
+ if (dd->node == NUMA_NO_NODE) {
+ dd_dev_err(dd, "Invalid PCI NUMA node. Performance may be affected\n");
+ dd->node = 0;
+ }
/*
* Initialize all locks for the device. This needs to be as early as
return 0;
}
- cpumask_and(node_cpu_mask, cpu_mask,
- cpumask_of_node(pcibus_to_node(dd->pcidev->bus)));
+ cpumask_and(node_cpu_mask, cpu_mask, cpumask_of_node(dd->node));
available_cpus = cpumask_weight(node_cpu_mask);
upper_32_bits(dma));
roce_write(hr_dev, ROCEE_TX_CMQ_DEPTH_REG,
(u32)ring->desc_num >> HNS_ROCE_CMQ_DESC_NUM_S);
- roce_write(hr_dev, ROCEE_TX_CMQ_HEAD_REG, 0);
+
+ /* Make sure to write tail first and then head */
roce_write(hr_dev, ROCEE_TX_CMQ_TAIL_REG, 0);
+ roce_write(hr_dev, ROCEE_TX_CMQ_HEAD_REG, 0);
} else {
roce_write(hr_dev, ROCEE_RX_CMQ_BASEADDR_L_REG, (u32)dma);
roce_write(hr_dev, ROCEE_RX_CMQ_BASEADDR_H_REG,
case MLX5_CMD_OP_CREATE_MKEY:
MLX5_SET(destroy_mkey_in, din, opcode,
MLX5_CMD_OP_DESTROY_MKEY);
- MLX5_SET(destroy_mkey_in, in, mkey_index, *obj_id);
+ MLX5_SET(destroy_mkey_in, din, mkey_index, *obj_id);
break;
case MLX5_CMD_OP_CREATE_CQ:
MLX5_SET(destroy_cq_in, din, opcode, MLX5_CMD_OP_DESTROY_CQ);
qpc = MLX5_ADDR_OF(create_qp_in, *in, qpc);
MLX5_SET(qpc, qpc, uar_page, uar_index);
- MLX5_SET(qpc, qpc, ts_format, MLX5_QPC_TIMESTAMP_FORMAT_DEFAULT);
+ MLX5_SET(qpc, qpc, ts_format, mlx5_get_qp_default_ts(dev->mdev));
MLX5_SET(qpc, qpc, log_page_size, qp->buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT);
/* Set "fast registration enabled" for all kernel QPs */
}
return MLX5_RQC_TIMESTAMP_FORMAT_FREE_RUNNING;
}
- return MLX5_RQC_TIMESTAMP_FORMAT_DEFAULT;
+ return fr_supported ? MLX5_RQC_TIMESTAMP_FORMAT_FREE_RUNNING :
+ MLX5_RQC_TIMESTAMP_FORMAT_DEFAULT;
}
static int get_sq_ts_format(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *send_cq)
}
return MLX5_SQC_TIMESTAMP_FORMAT_FREE_RUNNING;
}
- return MLX5_SQC_TIMESTAMP_FORMAT_DEFAULT;
+ return fr_supported ? MLX5_SQC_TIMESTAMP_FORMAT_FREE_RUNNING :
+ MLX5_SQC_TIMESTAMP_FORMAT_DEFAULT;
}
static int get_qp_ts_format(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *send_cq,
MLX5_QP_TIMESTAMP_FORMAT_CAP_FREE_RUNNING ||
MLX5_CAP_ROCE(dev->mdev, qp_ts_format) ==
MLX5_QP_TIMESTAMP_FORMAT_CAP_FREE_RUNNING_AND_REAL_TIME;
- int ts_format = MLX5_QPC_TIMESTAMP_FORMAT_DEFAULT;
+ int ts_format = fr_supported ? MLX5_QPC_TIMESTAMP_FORMAT_FREE_RUNNING :
+ MLX5_QPC_TIMESTAMP_FORMAT_DEFAULT;
if (recv_cq &&
recv_cq->create_flags & IB_UVERBS_CQ_FLAGS_TIMESTAMP_COMPLETION)
if (qp->flags & IB_QP_CREATE_MANAGED_RECV)
MLX5_SET(qpc, qpc, cd_slave_receive, 1);
+ MLX5_SET(qpc, qpc, ts_format, mlx5_get_qp_default_ts(dev->mdev));
MLX5_SET(qpc, qpc, rq_type, MLX5_SRQ_RQ);
MLX5_SET(qpc, qpc, no_sq, 1);
MLX5_SET(qpc, qpc, cqn_rcv, to_mcq(devr->c0)->mcq.cqn);
struct mlx5_ib_dev *dev;
int has_net_offloads;
__be64 *rq_pas0;
+ int ts_format;
void *in;
void *rqc;
void *wq;
dev = to_mdev(pd->device);
+ ts_format = get_rq_ts_format(dev, to_mcq(init_attr->cq));
+ if (ts_format < 0)
+ return ts_format;
+
inlen = MLX5_ST_SZ_BYTES(create_rq_in) + sizeof(u64) * rwq->rq_num_pas;
in = kvzalloc(inlen, GFP_KERNEL);
if (!in)
rqc = MLX5_ADDR_OF(create_rq_in, in, ctx);
MLX5_SET(rqc, rqc, mem_rq_type,
MLX5_RQC_MEM_RQ_TYPE_MEMORY_RQ_INLINE);
+ MLX5_SET(rqc, rqc, ts_format, ts_format);
MLX5_SET(rqc, rqc, user_index, rwq->user_index);
MLX5_SET(rqc, rqc, cqn, to_mcq(init_attr->cq)->mcq.cqn);
MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RST);
* TGT QP isn't associated with RQ/SQ
*/
if ((attrs->qp_type != IB_QPT_GSI) && (dev->gsi_qp_created) &&
- (attrs->qp_type != IB_QPT_XRC_TGT)) {
+ (attrs->qp_type != IB_QPT_XRC_TGT) &&
+ (attrs->qp_type != IB_QPT_XRC_INI)) {
struct qedr_cq *send_cq = get_qedr_cq(attrs->send_cq);
struct qedr_cq *recv_cq = get_qedr_cq(attrs->recv_cq);
/* Now it is safe to iterate over all paths without locks */
list_for_each_entry_safe(sess, tmp, &clt->paths_list, s.entry) {
- rtrs_clt_destroy_sess_files(sess, NULL);
rtrs_clt_close_conns(sess, true);
+ rtrs_clt_destroy_sess_files(sess, NULL);
kobject_put(&sess->kobj);
}
free_clt(clt);
MODULE_AUTHOR("Vojtech Pavlik <vojtech@ucw.cz>");
MODULE_DESCRIPTION("Joystick device interfaces");
-MODULE_SUPPORTED_DEVICE("input/js");
MODULE_LICENSE("GPL");
#define JOYDEV_MINOR_BASE 0
mutex_init(&priv->n64joy_mutex);
priv->reg_base = devm_platform_ioremap_resource(pdev, 0);
- if (!priv->reg_base) {
- err = -EINVAL;
+ if (IS_ERR(priv->reg_base)) {
+ err = PTR_ERR(priv->reg_base);
goto fail;
}
return IRQ_HANDLED;
}
-static int nspire_keypad_chip_init(struct nspire_keypad *keypad)
+static int nspire_keypad_open(struct input_dev *input)
{
+ struct nspire_keypad *keypad = input_get_drvdata(input);
unsigned long val = 0, cycles_per_us, delay_cycles, row_delay_cycles;
+ int error;
+
+ error = clk_prepare_enable(keypad->clk);
+ if (error)
+ return error;
cycles_per_us = (clk_get_rate(keypad->clk) / 1000000);
if (cycles_per_us == 0)
keypad->int_mask = 1 << 1;
writel(keypad->int_mask, keypad->reg_base + KEYPAD_INTMSK);
- /* Disable GPIO interrupts to prevent hanging on touchpad */
- /* Possibly used to detect touchpad events */
- writel(0, keypad->reg_base + KEYPAD_UNKNOWN_INT);
- /* Acknowledge existing interrupts */
- writel(~0, keypad->reg_base + KEYPAD_UNKNOWN_INT_STS);
-
- return 0;
-}
-
-static int nspire_keypad_open(struct input_dev *input)
-{
- struct nspire_keypad *keypad = input_get_drvdata(input);
- int error;
-
- error = clk_prepare_enable(keypad->clk);
- if (error)
- return error;
-
- error = nspire_keypad_chip_init(keypad);
- if (error) {
- clk_disable_unprepare(keypad->clk);
- return error;
- }
-
return 0;
}
{
struct nspire_keypad *keypad = input_get_drvdata(input);
+ /* Disable interrupts */
+ writel(0, keypad->reg_base + KEYPAD_INTMSK);
+ /* Acknowledge existing interrupts */
+ writel(~0, keypad->reg_base + KEYPAD_INT);
+
clk_disable_unprepare(keypad->clk);
}
return -ENOMEM;
}
+ error = clk_prepare_enable(keypad->clk);
+ if (error) {
+ dev_err(&pdev->dev, "failed to enable clock\n");
+ return error;
+ }
+
+ /* Disable interrupts */
+ writel(0, keypad->reg_base + KEYPAD_INTMSK);
+ /* Acknowledge existing interrupts */
+ writel(~0, keypad->reg_base + KEYPAD_INT);
+
+ /* Disable GPIO interrupts to prevent hanging on touchpad */
+ /* Possibly used to detect touchpad events */
+ writel(0, keypad->reg_base + KEYPAD_UNKNOWN_INT);
+ /* Acknowledge existing GPIO interrupts */
+ writel(~0, keypad->reg_base + KEYPAD_UNKNOWN_INT_STS);
+
+ clk_disable_unprepare(keypad->clk);
+
input_set_drvdata(input, keypad);
input->id.bustype = BUS_HOST;
DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
DMI_MATCH(DMI_CHASSIS_TYPE, "10"), /* Notebook */
},
+ }, {
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
DMI_MATCH(DMI_CHASSIS_TYPE, "31"), /* Convertible Notebook */
touchscreen_parse_properties(ts->input, true, &ts->prop);
- if (ts->chip_id == EKTF3624) {
+ if (ts->chip_id == EKTF3624 && ts->phy_x && ts->phy_y) {
/* calculate resolution from size */
ts->x_res = DIV_ROUND_CLOSEST(ts->prop.max_x, ts->phy_x);
ts->y_res = DIV_ROUND_CLOSEST(ts->prop.max_y, ts->phy_y);
input_abs_set_res(ts->input, ABS_MT_POSITION_X, ts->x_res);
input_abs_set_res(ts->input, ABS_MT_POSITION_Y, ts->y_res);
- if (ts->major_res > 0)
- input_abs_set_res(ts->input, ABS_MT_TOUCH_MAJOR, ts->major_res);
+ input_abs_set_res(ts->input, ABS_MT_TOUCH_MAJOR, ts->major_res);
error = input_mt_init_slots(ts->input, MAX_CONTACT_NUM,
INPUT_MT_DIRECT | INPUT_MT_DROP_UNUSED);
u8 major = event[4];
u8 minor = event[5];
u8 z = event[6] & S6SY761_MASK_Z;
- u16 x = (event[1] << 3) | ((event[3] & S6SY761_MASK_X) >> 4);
- u16 y = (event[2] << 3) | (event[3] & S6SY761_MASK_Y);
+ u16 x = (event[1] << 4) | ((event[3] & S6SY761_MASK_X) >> 4);
+ u16 y = (event[2] << 4) | (event[3] & S6SY761_MASK_Y);
input_mt_slot(sdata->input, tid);
EXPORT_SYMBOL_GPL(icc_bulk_put);
/**
- * icc_bulk_set() - set bandwidth to a set of paths
+ * icc_bulk_set_bw() - set bandwidth to a set of paths
* @num_paths: the number of icc_bulk_data
* @paths: the icc_bulk_data table containing the paths and bandwidth
*
GFP_KERNEL);
if (new)
src->links = new;
+ else
+ ret = -ENOMEM;
out:
mutex_unlock(&icc_lock);
DEFINE_QNODE(mas_pcnoc_sdcc_2, MSM8939_MASTER_SDCC_2, 8, -1, -1, MSM8939_PNOC_INT_1);
DEFINE_QNODE(mas_qdss_bam, MSM8939_MASTER_QDSS_BAM, 8, -1, -1, MSM8939_SNOC_QDSS_INT);
DEFINE_QNODE(mas_qdss_etr, MSM8939_MASTER_QDSS_ETR, 8, -1, -1, MSM8939_SNOC_QDSS_INT);
-DEFINE_QNODE(mas_snoc_cfg, MSM8939_MASTER_SNOC_CFG, 4, 20, -1, MSM8939_SLAVE_SRVC_SNOC);
+DEFINE_QNODE(mas_snoc_cfg, MSM8939_MASTER_SNOC_CFG, 4, -1, -1, MSM8939_SLAVE_SRVC_SNOC);
DEFINE_QNODE(mas_spdm, MSM8939_MASTER_SPDM, 4, -1, -1, MSM8939_PNOC_MAS_0);
DEFINE_QNODE(mas_tcu0, MSM8939_MASTER_TCU0, 16, -1, -1, MSM8939_SLAVE_EBI_CH0, MSM8939_BIMC_SNOC_MAS, MSM8939_SLAVE_AMPSS_L2);
DEFINE_QNODE(mas_usb_hs1, MSM8939_MASTER_USB_HS1, 4, -1, -1, MSM8939_PNOC_MAS_1);
DEFINE_QNODE(pcnoc_snoc_slv, MSM8939_PNOC_SNOC_SLV, 8, -1, 45, MSM8939_SNOC_INT_0, MSM8939_SNOC_INT_BIMC, MSM8939_SNOC_INT_1);
DEFINE_QNODE(qdss_int, MSM8939_SNOC_QDSS_INT, 8, -1, -1, MSM8939_SNOC_INT_0, MSM8939_SNOC_INT_BIMC);
DEFINE_QNODE(slv_apps_l2, MSM8939_SLAVE_AMPSS_L2, 16, -1, -1, 0);
-DEFINE_QNODE(slv_apss, MSM8939_SLAVE_APSS, 4, -1, 20, 0);
+DEFINE_QNODE(slv_apss, MSM8939_SLAVE_APSS, 4, -1, -1, 0);
DEFINE_QNODE(slv_audio, MSM8939_SLAVE_LPASS, 4, -1, -1, 0);
DEFINE_QNODE(slv_bimc_cfg, MSM8939_SLAVE_BIMC_CFG, 4, -1, -1, 0);
DEFINE_QNODE(slv_blsp_1, MSM8939_SLAVE_BLSP_1, 4, -1, -1, 0);
DEFINE_QNODE(slv_boot_rom, MSM8939_SLAVE_BOOT_ROM, 4, -1, -1, 0);
DEFINE_QNODE(slv_camera_cfg, MSM8939_SLAVE_CAMERA_CFG, 4, -1, -1, 0);
-DEFINE_QNODE(slv_cats_0, MSM8939_SLAVE_CATS_128, 16, -1, 106, 0);
-DEFINE_QNODE(slv_cats_1, MSM8939_SLAVE_OCMEM_64, 8, -1, 107, 0);
+DEFINE_QNODE(slv_cats_0, MSM8939_SLAVE_CATS_128, 16, -1, -1, 0);
+DEFINE_QNODE(slv_cats_1, MSM8939_SLAVE_OCMEM_64, 8, -1, -1, 0);
DEFINE_QNODE(slv_clk_ctl, MSM8939_SLAVE_CLK_CTL, 4, -1, -1, 0);
DEFINE_QNODE(slv_crypto_0_cfg, MSM8939_SLAVE_CRYPTO_0_CFG, 4, -1, -1, 0);
DEFINE_QNODE(slv_dehr_cfg, MSM8939_SLAVE_DEHR_CFG, 4, -1, -1, 0);
DEFINE_QNODE(slv_security, MSM8939_SLAVE_SECURITY, 4, -1, -1, 0);
DEFINE_QNODE(slv_snoc_cfg, MSM8939_SLAVE_SNOC_CFG, 4, -1, -1, 0);
DEFINE_QNODE(slv_spdm, MSM8939_SLAVE_SPDM, 4, -1, -1, 0);
-DEFINE_QNODE(slv_srvc_snoc, MSM8939_SLAVE_SRVC_SNOC, 8, -1, 29, 0);
+DEFINE_QNODE(slv_srvc_snoc, MSM8939_SLAVE_SRVC_SNOC, 8, -1, -1, 0);
DEFINE_QNODE(slv_tcsr, MSM8939_SLAVE_TCSR, 4, -1, -1, 0);
DEFINE_QNODE(slv_tlmm, MSM8939_SLAVE_TLMM, 4, -1, -1, 0);
DEFINE_QNODE(slv_usb_hs1, MSM8939_SLAVE_USB_HS1, 4, -1, -1, 0);
DEFINE_QNODE(slv_usb_hs2, MSM8939_SLAVE_USB_HS2, 4, -1, -1, 0);
DEFINE_QNODE(slv_venus_cfg, MSM8939_SLAVE_VENUS_CFG, 4, -1, -1, 0);
-DEFINE_QNODE(snoc_bimc_0_mas, MSM8939_SNOC_BIMC_0_MAS, 16, 3, -1, MSM8939_SNOC_BIMC_0_SLV);
-DEFINE_QNODE(snoc_bimc_0_slv, MSM8939_SNOC_BIMC_0_SLV, 16, -1, 24, MSM8939_SLAVE_EBI_CH0);
+DEFINE_QNODE(snoc_bimc_0_mas, MSM8939_SNOC_BIMC_0_MAS, 16, -1, -1, MSM8939_SNOC_BIMC_0_SLV);
+DEFINE_QNODE(snoc_bimc_0_slv, MSM8939_SNOC_BIMC_0_SLV, 16, -1, -1, MSM8939_SLAVE_EBI_CH0);
DEFINE_QNODE(snoc_bimc_1_mas, MSM8939_SNOC_BIMC_1_MAS, 16, 76, -1, MSM8939_SNOC_BIMC_1_SLV);
DEFINE_QNODE(snoc_bimc_1_slv, MSM8939_SNOC_BIMC_1_SLV, 16, -1, 104, MSM8939_SLAVE_EBI_CH0);
DEFINE_QNODE(snoc_bimc_2_mas, MSM8939_SNOC_BIMC_2_MAS, 16, -1, -1, MSM8939_SNOC_BIMC_2_SLV);
DEFINE_QNODE(snoc_bimc_2_slv, MSM8939_SNOC_BIMC_2_SLV, 16, -1, -1, MSM8939_SLAVE_EBI_CH0);
DEFINE_QNODE(snoc_int_0, MSM8939_SNOC_INT_0, 8, 99, 130, MSM8939_SLAVE_QDSS_STM, MSM8939_SLAVE_IMEM, MSM8939_SNOC_PNOC_MAS);
-DEFINE_QNODE(snoc_int_1, MSM8939_SNOC_INT_1, 8, 100, 131, MSM8939_SLAVE_APSS, MSM8939_SLAVE_CATS_128, MSM8939_SLAVE_OCMEM_64);
+DEFINE_QNODE(snoc_int_1, MSM8939_SNOC_INT_1, 8, -1, -1, MSM8939_SLAVE_APSS, MSM8939_SLAVE_CATS_128, MSM8939_SLAVE_OCMEM_64);
DEFINE_QNODE(snoc_int_bimc, MSM8939_SNOC_INT_BIMC, 8, 101, 132, MSM8939_SNOC_BIMC_1_MAS);
DEFINE_QNODE(snoc_pcnoc_mas, MSM8939_SNOC_PNOC_MAS, 8, -1, -1, MSM8939_SNOC_PNOC_SLV);
DEFINE_QNODE(snoc_pcnoc_slv, MSM8939_SNOC_PNOC_SLV, 8, -1, -1, MSM8939_PNOC_INT_0);
struct acpi_table_header *ivrs_base;
int i, remap_cache_sz, ret;
acpi_status status;
- u32 pci_id;
if (!amd_iommu_detected)
return -ENODEV;
if (ret)
goto out;
- /* Disable IOMMU if there's Stoney Ridge graphics */
- for (i = 0; i < 32; i++) {
- pci_id = read_pci_config(0, i, 0, 0);
- if ((pci_id & 0xffff) == 0x1002 && (pci_id >> 16) == 0x98e4) {
- pr_info("Disable IOMMU on Stoney Ridge\n");
- amd_iommu_disabled = true;
- break;
- }
- }
-
/* Disable any previously enabled IOMMUs */
if (!is_kdump_kernel() || amd_iommu_disabled)
disable_iommus();
{
struct acpi_table_header *ivrs_base;
acpi_status status;
+ int i;
status = acpi_get_table("IVRS", 0, &ivrs_base);
if (status == AE_NOT_FOUND)
acpi_put_table(ivrs_base);
+ /* Don't use IOMMU if there is Stoney Ridge graphics */
+ for (i = 0; i < 32; i++) {
+ u32 pci_id;
+
+ pci_id = read_pci_config(0, i, 0, 0);
+ if ((pci_id & 0xffff) == 0x1002 && (pci_id >> 16) == 0x98e4) {
+ pr_info("Disable IOMMU on Stoney Ridge\n");
+ return false;
+ }
+ }
+
/* Make sure ACS will be enabled during PCI probe */
pci_request_acs();
}
break;
case IOMMU_IVRS_DETECTED:
- ret = early_amd_iommu_init();
- init_state = ret ? IOMMU_INIT_ERROR : IOMMU_ACPI_FINISHED;
- if (init_state == IOMMU_ACPI_FINISHED && amd_iommu_disabled) {
- pr_info("AMD IOMMU disabled\n");
+ if (amd_iommu_disabled) {
init_state = IOMMU_CMDLINE_DISABLED;
ret = -EINVAL;
+ } else {
+ ret = early_amd_iommu_init();
+ init_state = ret ? IOMMU_INIT_ERROR : IOMMU_ACPI_FINISHED;
}
break;
case IOMMU_ACPI_FINISHED:
amd_iommu_irq_remap = true;
ret = iommu_go_to_state(IOMMU_ACPI_FINISHED);
- if (ret)
+ if (ret) {
+ amd_iommu_irq_remap = false;
return ret;
+ }
+
return amd_iommu_irq_remap ? 0 : -ENODEV;
}
smmu = tegra_smmu_find(args.np);
if (smmu) {
err = tegra_smmu_configure(smmu, dev, &args);
- of_node_put(args.np);
- if (err < 0)
+ if (err < 0) {
+ of_node_put(args.np);
return ERR_PTR(err);
-
- break;
+ }
}
of_node_put(args.np);
config ARM_GIC
bool
select IRQ_DOMAIN_HIERARCHY
- select GENERIC_IRQ_MULTI_HANDLER
select GENERIC_IRQ_EFFECTIVE_AFF_MASK
config ARM_GIC_PM
config ARM_GIC_V3
bool
- select GENERIC_IRQ_MULTI_HANDLER
select IRQ_DOMAIN_HIERARCHY
select PARTITION_PERCPU
select GENERIC_IRQ_EFFECTIVE_AFF_MASK
config ARM_VIC
bool
select IRQ_DOMAIN
- select GENERIC_IRQ_MULTI_HANDLER
config ARM_VIC_NR
int
bool
select GENERIC_IRQ_CHIP
select IRQ_DOMAIN
- select GENERIC_IRQ_MULTI_HANDLER
select SPARSE_IRQ
config ATMEL_AIC5_IRQ
bool
select GENERIC_IRQ_CHIP
select IRQ_DOMAIN
- select GENERIC_IRQ_MULTI_HANDLER
select SPARSE_IRQ
config I8259
config FARADAY_FTINTC010
bool
select IRQ_DOMAIN
- select GENERIC_IRQ_MULTI_HANDLER
select SPARSE_IRQ
config HISILICON_IRQ_MBIGEN
config IXP4XX_IRQ
bool
select IRQ_DOMAIN
- select GENERIC_IRQ_MULTI_HANDLER
select SPARSE_IRQ
config MADERA_IRQ
bool
depends on ARCH_CLPS711X
select IRQ_DOMAIN
- select GENERIC_IRQ_MULTI_HANDLER
select SPARSE_IRQ
default y
config ORION_IRQCHIP
bool
select IRQ_DOMAIN
- select GENERIC_IRQ_MULTI_HANDLER
config PIC32_EVIC
bool
select GENERIC_IRQ_EFFECTIVE_AFF_MASK
config XILINX_INTC
- bool
+ bool "Xilinx Interrupt Controller IP"
+ depends on MICROBLAZE || ARCH_ZYNQ || ARCH_ZYNQMP
select IRQ_DOMAIN
+ help
+ Support for the Xilinx Interrupt Controller IP core.
+ This is used as a primary controller with MicroBlaze and can also
+ be used as a secondary chained controller on other platforms.
config IRQ_CROSSBAR
bool
help
Support MStar Interrupt Controller.
+config WPCM450_AIC
+ bool "Nuvoton WPCM450 Advanced Interrupt Controller"
+ depends on ARCH_WPCM450
+ help
+ Support for the interrupt controller in the Nuvoton WPCM450 BMC SoC.
+
+config IRQ_IDT3243X
+ bool
+ select GENERIC_IRQ_CHIP
+ select IRQ_DOMAIN
+
endmenu
obj-$(CONFIG_MST_IRQ) += irq-mst-intc.o
obj-$(CONFIG_SL28CPLD_INTC) += irq-sl28cpld.o
obj-$(CONFIG_MACH_REALTEK_RTL) += irq-realtek-rtl.o
+obj-$(CONFIG_WPCM450_AIC) += irq-wpcm450-aic.o
+obj-$(CONFIG_IRQ_IDT3243X) += irq-idt3243x.o
writel(0, vic->base + AVIC_INT_SELECT);
writel(0, vic->base + AVIC_INT_SELECT + 4);
- /* Some interrupts have a programable high/low level trigger
+ /* Some interrupts have a programmable high/low level trigger
* (4 GPIO direct inputs), for now we assume this was configured
* by firmware. We read which ones are edge now.
*/
}
vic->base = regs;
- /* Initialize soures, all masked */
+ /* Initialize sources, all masked */
vic_init_hw(vic);
/* Ready to receive interrupts */
if (data->can_wake) {
/* This IRQ chip can wake the system, set all
- * relevant child interupts in wake_enabled mask
+ * relevant child interrupts in wake_enabled mask
*/
gc->wake_enabled = 0xffffffff;
gc->wake_enabled &= ~gc->unused;
writel(0x0, reg_base + GX_INTC_NEN63_32);
/*
- * Initial mask reg with all unmasked, because we only use enalbe reg
+ * Initial mask reg with all unmasked, because we only use enable reg
*/
writel(0x0, reg_base + GX_INTC_NMASK31_00);
writel(0x0, reg_base + GX_INTC_NMASK63_32);
* the MSI data is the absolute value within the range from
* spi_start to (spi_start + num_spis).
*
- * Broadom NS2 GICv2m implementation has an erratum where the MSI data
+ * Broadcom NS2 GICv2m implementation has an erratum where the MSI data
* is 'spi_number - 32'
*
* Reading that register fails on the Graviton implementation
*
* Ideally, we'd issue a VMAPTI to set the doorbell to its LPI
* value or to 1023, depending on the enable bit. But that
- * would be issueing a mapping for an /existing/ DevID+EventID
+ * would be issuing a mapping for an /existing/ DevID+EventID
* pair, which is UNPREDICTABLE. Instead, let's issue a VMOVI
* to the /same/ vPE, using this opportunity to adjust the
* doorbell. Mouahahahaha. We loves it, Precious.
/*
* It's possible for CPU to receive VLPIs before it is
- * sheduled as a vPE, especially for the first CPU, and the
+ * scheduled as a vPE, especially for the first CPU, and the
* VLPI with INTID larger than 2^(IDbits+1) will be considered
* as out of range and dropped by GIC.
* So we initialize IDbits to known value to avoid VLPI drop.
/*
* If all interrupts have been freed, start mopping the
- * floor. This is conditionned on the device not being shared.
+ * floor. This is conditioned on the device not being shared.
*/
if (!its_dev->shared &&
bitmap_empty(its_dev->event_map.lpi_map,
{
/*
* There is no notion of affinity for virtual SGIs, at least
- * not on the host (since they can only be targetting a vPE).
+ * not on the host (since they can only be targeting a vPE).
* Tell the kernel we've done whatever it asked for.
*/
irq_data_update_effective_affinity(d, mask_val);
/*
* Locking galore! We can race against two different events:
*
- * - Concurent vPE affinity change: we must make sure it cannot
+ * - Concurrent vPE affinity change: we must make sure it cannot
* happen, or we'll talk to the wrong redistributor. This is
* identical to what happens with vLPIs.
*
reg = of_get_property(np, "mbi-alias", NULL);
if (reg) {
mbi_phys_base = of_translate_address(np, reg);
- if (mbi_phys_base == OF_BAD_ADDR) {
+ if (mbi_phys_base == (phys_addr_t)OF_BAD_ADDR) {
ret = -ENXIO;
goto err_free_mbi;
}
irqnr = gic_read_iar();
+ /* Check for special IDs first */
+ if ((irqnr >= 1020 && irqnr <= 1023))
+ return;
+
if (gic_supports_nmi() &&
unlikely(gic_read_rpr() == GICD_INT_NMI_PRI)) {
gic_handle_nmi(irqnr, regs);
gic_arch_enable_irqs();
}
- /* Check for special IDs first */
- if ((irqnr >= 1020 && irqnr <= 1023))
- return;
-
if (static_branch_likely(&supports_deactivate_key))
gic_write_eoir(irqnr);
else
/*
* Make it clear that broken DTs are... broken.
- * Partitionned PPIs are an unfortunate exception.
+ * Partitioned PPIs are an unfortunate exception.
*/
WARN_ON(*type == IRQ_TYPE_NONE &&
fwspec->param[0] != GIC_IRQ_TYPE_PARTITION);
static const struct irq_domain_ops *vpe_domain_ops;
static const struct irq_domain_ops *sgi_domain_ops;
+#ifdef CONFIG_ARM64
+#include <asm/cpufeature.h>
+
+bool gic_cpuif_has_vsgi(void)
+{
+ unsigned long fld, reg = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
+
+ fld = cpuid_feature_extract_unsigned_field(reg, ID_AA64PFR0_GIC_SHIFT);
+
+ return fld >= 0x3;
+}
+#else
+bool gic_cpuif_has_vsgi(void)
+{
+ return false;
+}
+#endif
+
static bool has_v4_1(void)
{
return !!sgi_domain_ops;
}
+static bool has_v4_1_sgi(void)
+{
+ return has_v4_1() && gic_cpuif_has_vsgi();
+}
+
static int its_alloc_vcpu_sgis(struct its_vpe *vpe, int idx)
{
char *name;
int sgi_base;
- if (!has_v4_1())
+ if (!has_v4_1_sgi())
return 0;
name = kasprintf(GFP_KERNEL, "GICv4-sgi-%d", task_pid_nr(current));
{
int i;
- if (!has_v4_1())
+ if (!has_v4_1_sgi())
return;
for (i = 0; i < vm->nr_vpes; i++) {
// SPDX-License-Identifier: GPL-2.0-only
/*
- * Hisilicon HiP04 INTC
+ * HiSilicon HiP04 INTC
*
* Copyright (C) 2002-2014 ARM Limited.
- * Copyright (c) 2013-2014 Hisilicon Ltd.
+ * Copyright (c) 2013-2014 HiSilicon Ltd.
* Copyright (c) 2013-2014 Linaro Ltd.
*
* Interrupt architecture for the HIP04 INTC:
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Driver for IDT/Renesas 79RC3243x Interrupt Controller.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+
+#define IDT_PIC_NR_IRQS 32
+
+#define IDT_PIC_IRQ_PEND 0x00
+#define IDT_PIC_IRQ_MASK 0x08
+
+struct idt_pic_data {
+ void __iomem *base;
+ struct irq_domain *irq_domain;
+ struct irq_chip_generic *gc;
+};
+
+static void idt_irq_dispatch(struct irq_desc *desc)
+{
+ struct idt_pic_data *idtpic = irq_desc_get_handler_data(desc);
+ struct irq_chip *host_chip = irq_desc_get_chip(desc);
+ u32 pending, hwirq, virq;
+
+ chained_irq_enter(host_chip, desc);
+
+ pending = irq_reg_readl(idtpic->gc, IDT_PIC_IRQ_PEND);
+ pending &= ~idtpic->gc->mask_cache;
+ while (pending) {
+ hwirq = __fls(pending);
+ virq = irq_linear_revmap(idtpic->irq_domain, hwirq);
+ if (virq)
+ generic_handle_irq(virq);
+ pending &= ~(1 << hwirq);
+ }
+
+ chained_irq_exit(host_chip, desc);
+}
+
+static int idt_pic_init(struct device_node *of_node, struct device_node *parent)
+{
+ struct irq_domain *domain;
+ struct idt_pic_data *idtpic;
+ struct irq_chip_generic *gc;
+ struct irq_chip_type *ct;
+ unsigned int parent_irq;
+ int ret = 0;
+
+ idtpic = kzalloc(sizeof(*idtpic), GFP_KERNEL);
+ if (!idtpic) {
+ ret = -ENOMEM;
+ goto out_err;
+ }
+
+ parent_irq = irq_of_parse_and_map(of_node, 0);
+ if (!parent_irq) {
+ pr_err("Failed to map parent IRQ!\n");
+ ret = -EINVAL;
+ goto out_free;
+ }
+
+ idtpic->base = of_iomap(of_node, 0);
+ if (!idtpic->base) {
+ pr_err("Failed to map base address!\n");
+ ret = -ENOMEM;
+ goto out_unmap_irq;
+ }
+
+ domain = irq_domain_add_linear(of_node, IDT_PIC_NR_IRQS,
+ &irq_generic_chip_ops, NULL);
+ if (!domain) {
+ pr_err("Failed to add irqdomain!\n");
+ ret = -ENOMEM;
+ goto out_iounmap;
+ }
+ idtpic->irq_domain = domain;
+
+ ret = irq_alloc_domain_generic_chips(domain, 32, 1, "IDTPIC",
+ handle_level_irq, 0,
+ IRQ_NOPROBE | IRQ_LEVEL, 0);
+ if (ret)
+ goto out_domain_remove;
+
+ gc = irq_get_domain_generic_chip(domain, 0);
+ gc->reg_base = idtpic->base;
+ gc->private = idtpic;
+
+ ct = gc->chip_types;
+ ct->regs.mask = IDT_PIC_IRQ_MASK;
+ ct->chip.irq_mask = irq_gc_mask_set_bit;
+ ct->chip.irq_unmask = irq_gc_mask_clr_bit;
+ idtpic->gc = gc;
+
+ /* Mask interrupts. */
+ writel(0xffffffff, idtpic->base + IDT_PIC_IRQ_MASK);
+ gc->mask_cache = 0xffffffff;
+
+ irq_set_chained_handler_and_data(parent_irq,
+ idt_irq_dispatch, idtpic);
+
+ return 0;
+
+out_domain_remove:
+ irq_domain_remove(domain);
+out_iounmap:
+ iounmap(idtpic->base);
+out_unmap_irq:
+ irq_dispose_mapping(parent_irq);
+out_free:
+ kfree(idtpic);
+out_err:
+ pr_err("Failed to initialize! (errno = %d)\n", ret);
+ return ret;
+}
+
+IRQCHIP_DECLARE(idt_pic, "idt,32434-pic", idt_pic_init);
}
IRQCHIP_DECLARE(jz4740_tcu_irq, "ingenic,jz4740-tcu", ingenic_tcu_irq_init);
IRQCHIP_DECLARE(jz4725b_tcu_irq, "ingenic,jz4725b-tcu", ingenic_tcu_irq_init);
+IRQCHIP_DECLARE(jz4760_tcu_irq, "ingenic,jz4760-tcu", ingenic_tcu_irq_init);
IRQCHIP_DECLARE(jz4770_tcu_irq, "ingenic,jz4770-tcu", ingenic_tcu_irq_init);
IRQCHIP_DECLARE(x1000_tcu_irq, "ingenic,x1000-tcu", ingenic_tcu_irq_init);
{
return ingenic_intc_of_init(node, 2);
}
+IRQCHIP_DECLARE(jz4760_intc, "ingenic,jz4760-intc", intc_2chip_of_init);
IRQCHIP_DECLARE(jz4770_intc, "ingenic,jz4770-intc", intc_2chip_of_init);
IRQCHIP_DECLARE(jz4775_intc, "ingenic,jz4775-intc", intc_2chip_of_init);
IRQCHIP_DECLARE(jz4780_intc, "ingenic,jz4780-intc", intc_2chip_of_init);
jcore_aic.irq_unmask = noop;
jcore_aic.name = "AIC";
- domain = irq_domain_add_linear(node, dom_sz, &jcore_aic_irqdomain_ops,
+ domain = irq_domain_add_legacy(node, dom_sz - min_irq, min_irq, min_irq,
+ &jcore_aic_irqdomain_ops,
&jcore_aic);
if (!domain)
return -ENOMEM;
- irq_create_strict_mappings(domain, min_irq, min_irq, dom_sz - min_irq);
return 0;
}
int i;
for (i = 0; i < PIC_COUNT; i++) {
- /* Write vectore ID */
+ /* Write vectored ID */
writeb(priv->ht_vec_base + i, priv->base + PCH_INT_HTVEC(i));
/* Hardcode route to HT0 Lo */
writeb(1, priv->base + PCH_INT_ROUTE(i));
// SPDX-License-Identifier: GPL-2.0-only
/*
- * Copyright (C) 2015 Hisilicon Limited, All Rights Reserved.
+ * Copyright (C) 2015 HiSilicon Limited, All Rights Reserved.
* Author: Jun Ma <majun258@huawei.com>
* Author: Yun Wu <wuyun.wu@huawei.com>
*/
MODULE_AUTHOR("Jun Ma <majun258@huawei.com>");
MODULE_AUTHOR("Yun Wu <wuyun.wu@huawei.com>");
MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Hisilicon MBI Generator driver");
+MODULE_DESCRIPTION("HiSilicon MBI Generator driver");
/*
* Get the hwirq number assigned to this channel through
- * a pointer the channel_irq table. The added benifit of this
+ * a pointer the channel_irq table. The added benefit of this
* method is that we can also retrieve the channel index with
* it, using the table base.
*/
#include <linux/of_irq.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
+#include <linux/syscore_ops.h>
-#define INTC_MASK 0x0
-#define INTC_EOI 0x20
+#define MST_INTC_MAX_IRQS 64
+
+#define INTC_MASK 0x0
+#define INTC_REV_POLARITY 0x10
+#define INTC_EOI 0x20
+
+#ifdef CONFIG_PM_SLEEP
+static LIST_HEAD(mst_intc_list);
+#endif
struct mst_intc_chip_data {
raw_spinlock_t lock;
unsigned int irq_start, nr_irqs;
void __iomem *base;
bool no_eoi;
+#ifdef CONFIG_PM_SLEEP
+ struct list_head entry;
+ u16 saved_polarity_conf[DIV_ROUND_UP(MST_INTC_MAX_IRQS, 16)];
+#endif
};
static void mst_set_irq(struct irq_data *d, u32 offset)
irq_chip_eoi_parent(d);
}
+static int mst_irq_chip_set_type(struct irq_data *data, unsigned int type)
+{
+ switch (type) {
+ case IRQ_TYPE_LEVEL_LOW:
+ case IRQ_TYPE_EDGE_FALLING:
+ mst_set_irq(data, INTC_REV_POLARITY);
+ break;
+ case IRQ_TYPE_LEVEL_HIGH:
+ case IRQ_TYPE_EDGE_RISING:
+ mst_clear_irq(data, INTC_REV_POLARITY);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return irq_chip_set_type_parent(data, IRQ_TYPE_LEVEL_HIGH);
+}
+
static struct irq_chip mst_intc_chip = {
.name = "mst-intc",
.irq_mask = mst_intc_mask_irq,
.irq_set_irqchip_state = irq_chip_set_parent_state,
.irq_set_affinity = irq_chip_set_affinity_parent,
.irq_set_vcpu_affinity = irq_chip_set_vcpu_affinity_parent,
- .irq_set_type = irq_chip_set_type_parent,
+ .irq_set_type = mst_irq_chip_set_type,
.irq_retrigger = irq_chip_retrigger_hierarchy,
.flags = IRQCHIP_SET_TYPE_MASKED |
IRQCHIP_SKIP_SET_WAKE |
IRQCHIP_MASK_ON_SUSPEND,
};
+#ifdef CONFIG_PM_SLEEP
+static void mst_intc_polarity_save(struct mst_intc_chip_data *cd)
+{
+ int i;
+ void __iomem *addr = cd->base + INTC_REV_POLARITY;
+
+ for (i = 0; i < DIV_ROUND_UP(cd->nr_irqs, 16); i++)
+ cd->saved_polarity_conf[i] = readw_relaxed(addr + i * 4);
+}
+
+static void mst_intc_polarity_restore(struct mst_intc_chip_data *cd)
+{
+ int i;
+ void __iomem *addr = cd->base + INTC_REV_POLARITY;
+
+ for (i = 0; i < DIV_ROUND_UP(cd->nr_irqs, 16); i++)
+ writew_relaxed(cd->saved_polarity_conf[i], addr + i * 4);
+}
+
+static void mst_irq_resume(void)
+{
+ struct mst_intc_chip_data *cd;
+
+ list_for_each_entry(cd, &mst_intc_list, entry)
+ mst_intc_polarity_restore(cd);
+}
+
+static int mst_irq_suspend(void)
+{
+ struct mst_intc_chip_data *cd;
+
+ list_for_each_entry(cd, &mst_intc_list, entry)
+ mst_intc_polarity_save(cd);
+ return 0;
+}
+
+static struct syscore_ops mst_irq_syscore_ops = {
+ .suspend = mst_irq_suspend,
+ .resume = mst_irq_resume,
+};
+
+static int __init mst_irq_pm_init(void)
+{
+ register_syscore_ops(&mst_irq_syscore_ops);
+ return 0;
+}
+late_initcall(mst_irq_pm_init);
+#endif
+
static int mst_intc_domain_translate(struct irq_domain *d,
struct irq_fwspec *fwspec,
unsigned long *hwirq,
parent_fwspec = *fwspec;
parent_fwspec.fwnode = domain->parent->fwnode;
parent_fwspec.param[1] = cd->irq_start + hwirq;
+
+ /*
+ * mst-intc latch the interrupt request if it's edge triggered,
+ * so the output signal to parent GIC is always level sensitive.
+ * And if the irq signal is active low, configure it to active high
+ * to meet GIC SPI spec in mst_irq_chip_set_type via REV_POLARITY bit.
+ */
+ parent_fwspec.param[2] = IRQ_TYPE_LEVEL_HIGH;
+
return irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, &parent_fwspec);
}
return -ENOMEM;
}
+#ifdef CONFIG_PM_SLEEP
+ INIT_LIST_HEAD(&cd->entry);
+ list_add_tail(&cd->entry, &mst_intc_list);
+#endif
return 0;
}
{
u32 value;
- /* flush recored interrupts, will send signals to parent controller */
+ /* flush recorded interrupts, will send signals to parent controller */
value = readl_relaxed(cirq_data->base + CIRQ_CONTROL);
writel_relaxed(value | CIRQ_FLUSH, cirq_data->base + CIRQ_CONTROL);
static struct icoll_priv icoll_priv;
static struct irq_domain *icoll_domain;
-/* calculate bit offset depending on number of intterupt per register */
+/* calculate bit offset depending on number of interrupt per register */
static u32 icoll_intr_bitshift(struct irq_data *d, u32 bit)
{
/*
return bit << ((d->hwirq & 3) << 3);
}
-/* calculate mem offset depending on number of intterupt per register */
+/* calculate mem offset depending on number of interrupt per register */
static void __iomem *icoll_intr_reg(struct irq_data *d)
{
/* offset = hwirq / intr_per_reg * 0x10 */
void __iomem *enable_base;
struct plic_priv *priv;
};
-static int plic_parent_irq;
-static bool plic_cpuhp_setup_done;
+static int plic_parent_irq __ro_after_init;
+static bool plic_cpuhp_setup_done __ro_after_init;
static DEFINE_PER_CPU(struct plic_handler, plic_handlers);
static inline void plic_toggle(struct plic_handler *handler,
{ .exti = 23, .irq_parent = 72, .chip = &stm32_exti_h_chip_direct },
{ .exti = 24, .irq_parent = 95, .chip = &stm32_exti_h_chip_direct },
{ .exti = 25, .irq_parent = 107, .chip = &stm32_exti_h_chip_direct },
+ { .exti = 26, .irq_parent = 37, .chip = &stm32_exti_h_chip_direct },
+ { .exti = 27, .irq_parent = 38, .chip = &stm32_exti_h_chip_direct },
+ { .exti = 28, .irq_parent = 39, .chip = &stm32_exti_h_chip_direct },
+ { .exti = 29, .irq_parent = 71, .chip = &stm32_exti_h_chip_direct },
{ .exti = 30, .irq_parent = 52, .chip = &stm32_exti_h_chip_direct },
+ { .exti = 31, .irq_parent = 53, .chip = &stm32_exti_h_chip_direct },
+ { .exti = 32, .irq_parent = 82, .chip = &stm32_exti_h_chip_direct },
+ { .exti = 33, .irq_parent = 83, .chip = &stm32_exti_h_chip_direct },
{ .exti = 47, .irq_parent = 93, .chip = &stm32_exti_h_chip_direct },
{ .exti = 48, .irq_parent = 138, .chip = &stm32_exti_h_chip_direct },
{ .exti = 50, .irq_parent = 139, .chip = &stm32_exti_h_chip_direct },
* 3) spurious irq
* So if we immediately get a reading of 0, check the irq-pending reg
* to differentiate between 2 and 3. We only do this once to avoid
- * the extra check in the common case of 1 hapening after having
+ * the extra check in the common case of 1 happening after having
* read the vector-reg once.
*/
hwirq = readl(irq_ic_data->irq_base + SUN4I_IRQ_VECTOR_REG) >> 2;
break;
case IRQ_TYPE_NONE:
flow_type = IRQ_TYPE_LEVEL_LOW;
+ fallthrough;
case IRQ_TYPE_LEVEL_LOW:
mod ^= im;
pol ^= im;
* struct ti_sci_inta_irq_domain - Structure representing a TISCI based
* Interrupt Aggregator IRQ domain.
* @sci: Pointer to TISCI handle
- * @vint: TISCI resource pointer representing IA inerrupts.
+ * @vint: TISCI resource pointer representing IA interrupts.
* @global_event: TISCI resource pointer representing global events.
* @vint_list: List of the vints active in the system
* @vint_mutex: Mutex to protect vint_list
};
/**
- * vic_pm_init - initicall to register VIC pm
+ * vic_pm_init - initcall to register VIC pm
*
* This is called via late_initcall() to register
* the resources for the VICs due to the early
/*
* The PL190 cell from ARM has been modified by ST to handle 64 interrupts.
* The original cell has 32 interrupts, while the modified one has 64,
- * replocating two blocks 0x00..0x1f in 0x20..0x3f. In that case
+ * replicating two blocks 0x00..0x1f in 0x20..0x3f. In that case
* the probe function is called twice, with base set to offset 000
* and 020 within the page. We call this "second block".
*/
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright 2021 Jonathan Neuschäfer
+
+#include <linux/irqchip.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/printk.h>
+
+#include <asm/exception.h>
+
+#define AIC_SCR(x) ((x)*4) /* Source control registers */
+#define AIC_GEN 0x84 /* Interrupt group enable control register */
+#define AIC_GRSR 0x88 /* Interrupt group raw status register */
+#define AIC_IRSR 0x100 /* Interrupt raw status register */
+#define AIC_IASR 0x104 /* Interrupt active status register */
+#define AIC_ISR 0x108 /* Interrupt status register */
+#define AIC_IPER 0x10c /* Interrupt priority encoding register */
+#define AIC_ISNR 0x110 /* Interrupt source number register */
+#define AIC_IMR 0x114 /* Interrupt mask register */
+#define AIC_OISR 0x118 /* Output interrupt status register */
+#define AIC_MECR 0x120 /* Mask enable command register */
+#define AIC_MDCR 0x124 /* Mask disable command register */
+#define AIC_SSCR 0x128 /* Source set command register */
+#define AIC_SCCR 0x12c /* Source clear command register */
+#define AIC_EOSCR 0x130 /* End of service command register */
+
+#define AIC_SCR_SRCTYPE_LOW_LEVEL (0 << 6)
+#define AIC_SCR_SRCTYPE_HIGH_LEVEL (1 << 6)
+#define AIC_SCR_SRCTYPE_NEG_EDGE (2 << 6)
+#define AIC_SCR_SRCTYPE_POS_EDGE (3 << 6)
+#define AIC_SCR_PRIORITY(x) (x)
+#define AIC_SCR_PRIORITY_MASK 0x7
+
+#define AIC_NUM_IRQS 32
+
+struct wpcm450_aic {
+ void __iomem *regs;
+ struct irq_domain *domain;
+};
+
+static struct wpcm450_aic *aic;
+
+static void wpcm450_aic_init_hw(void)
+{
+ int i;
+
+ /* Disable (mask) all interrupts */
+ writel(0xffffffff, aic->regs + AIC_MDCR);
+
+ /*
+ * Make sure the interrupt controller is ready to serve new interrupts.
+ * Reading from IPER indicates that the nIRQ signal may be deasserted,
+ * and writing to EOSCR indicates that interrupt handling has finished.
+ */
+ readl(aic->regs + AIC_IPER);
+ writel(0, aic->regs + AIC_EOSCR);
+
+ /* Initialize trigger mode and priority of each interrupt source */
+ for (i = 0; i < AIC_NUM_IRQS; i++)
+ writel(AIC_SCR_SRCTYPE_HIGH_LEVEL | AIC_SCR_PRIORITY(7),
+ aic->regs + AIC_SCR(i));
+}
+
+static void __exception_irq_entry wpcm450_aic_handle_irq(struct pt_regs *regs)
+{
+ int hwirq;
+
+ /* Determine the interrupt source */
+ /* Read IPER to signal that nIRQ can be de-asserted */
+ hwirq = readl(aic->regs + AIC_IPER) / 4;
+
+ handle_domain_irq(aic->domain, hwirq, regs);
+}
+
+static void wpcm450_aic_eoi(struct irq_data *d)
+{
+ /* Signal end-of-service */
+ writel(0, aic->regs + AIC_EOSCR);
+}
+
+static void wpcm450_aic_mask(struct irq_data *d)
+{
+ unsigned int mask = BIT(d->hwirq);
+
+ /* Disable (mask) the interrupt */
+ writel(mask, aic->regs + AIC_MDCR);
+}
+
+static void wpcm450_aic_unmask(struct irq_data *d)
+{
+ unsigned int mask = BIT(d->hwirq);
+
+ /* Enable (unmask) the interrupt */
+ writel(mask, aic->regs + AIC_MECR);
+}
+
+static int wpcm450_aic_set_type(struct irq_data *d, unsigned int flow_type)
+{
+ /*
+ * The hardware supports high/low level, as well as rising/falling edge
+ * modes, and the DT binding accommodates for that, but as long as
+ * other modes than high level mode are not used and can't be tested,
+ * they are rejected in this driver.
+ */
+ if ((flow_type & IRQ_TYPE_SENSE_MASK) != IRQ_TYPE_LEVEL_HIGH)
+ return -EINVAL;
+
+ return 0;
+}
+
+static struct irq_chip wpcm450_aic_chip = {
+ .name = "wpcm450-aic",
+ .irq_eoi = wpcm450_aic_eoi,
+ .irq_mask = wpcm450_aic_mask,
+ .irq_unmask = wpcm450_aic_unmask,
+ .irq_set_type = wpcm450_aic_set_type,
+};
+
+static int wpcm450_aic_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hwirq)
+{
+ if (hwirq >= AIC_NUM_IRQS)
+ return -EPERM;
+
+ irq_set_chip_and_handler(irq, &wpcm450_aic_chip, handle_fasteoi_irq);
+ irq_set_chip_data(irq, aic);
+ irq_set_probe(irq);
+
+ return 0;
+}
+
+static const struct irq_domain_ops wpcm450_aic_ops = {
+ .map = wpcm450_aic_map,
+ .xlate = irq_domain_xlate_twocell,
+};
+
+static int __init wpcm450_aic_of_init(struct device_node *node,
+ struct device_node *parent)
+{
+ if (parent)
+ return -EINVAL;
+
+ aic = kzalloc(sizeof(*aic), GFP_KERNEL);
+ if (!aic)
+ return -ENOMEM;
+
+ aic->regs = of_iomap(node, 0);
+ if (!aic->regs) {
+ pr_err("Failed to map WPCM450 AIC registers\n");
+ return -ENOMEM;
+ }
+
+ wpcm450_aic_init_hw();
+
+ set_handle_irq(wpcm450_aic_handle_irq);
+
+ aic->domain = irq_domain_add_linear(node, AIC_NUM_IRQS, &wpcm450_aic_ops, aic);
+
+ return 0;
+}
+
+IRQCHIP_DECLARE(wpcm450_aic, "nuvoton,wpcm450-aic", wpcm450_aic_of_init);
/*
* Disable all external interrupts until they are
- * explicity requested.
+ * explicitly requested.
*/
xintc_write(irqc, IER, 0);
* Return value: CAPI result code
*/
-u16 capi20_get_manufacturer(u32 contr, u8 *buf)
+u16 capi20_get_manufacturer(u32 contr, u8 buf[CAPI_MANUFACTURER_LEN])
{
struct capi_ctr *ctr;
u16 ret;
* Return value: CAPI result code
*/
-u16 capi20_get_serial(u32 contr, u8 *serial)
+u16 capi20_get_serial(u32 contr, u8 serial[CAPI_SERIAL_LEN])
{
struct capi_ctr *ctr;
u16 ret;
{
if (isac->type & IPAC_TYPE_ISACX)
WriteISAC(isac, ISACX_MASK, 0xff);
- else
+ else if (isac->type != 0)
WriteISAC(isac, ISAC_MASK, 0xff);
if (isac->dch.timer.function != NULL) {
del_timer(&isac->dch.timer);
/*
* CZ.NIC's Turris Omnia LEDs driver
*
- * 2020 by Marek Behun <marek.behun@nic.cz>
+ * 2020 by Marek Behún <kabel@kernel.org>
*/
#include <linux/i2c.h>
module_i2c_driver(omnia_leds_driver);
-MODULE_AUTHOR("Marek Behun <marek.behun@nic.cz>");
+MODULE_AUTHOR("Marek Behun <kabel@kernel.org>");
MODULE_DESCRIPTION("CZ.NIC's Turris Omnia LEDs");
MODULE_LICENSE("GPL v2");
if (size) {
ttyname = kmemdup_nul(buf, size, GFP_KERNEL);
- if (!ttyname) {
- ret = -ENOMEM;
- goto out_unlock;
- }
+ if (!ttyname)
+ return -ENOMEM;
} else {
ttyname = NULL;
}
trigger_data->ttyname = ttyname;
-out_unlock:
mutex_unlock(&trigger_data->mutex);
if (ttyname && !running)
if (icount.rx != trigger_data->rx ||
icount.tx != trigger_data->tx) {
- led_set_brightness(trigger_data->led_cdev, LED_ON);
+ led_set_brightness_sync(trigger_data->led_cdev, LED_ON);
trigger_data->rx = icount.rx;
trigger_data->tx = icount.tx;
} else {
- led_set_brightness(trigger_data->led_cdev, LED_OFF);
+ led_set_brightness_sync(trigger_data->led_cdev, LED_OFF);
}
out:
/*
* rWTM BIU Mailbox driver for Armada 37xx
*
- * Author: Marek Behun <marek.behun@nic.cz>
+ * Author: Marek Behún <kabel@kernel.org>
*/
#include <linux/device.h>
MODULE_LICENSE("GPL v2");
MODULE_DESCRIPTION("rWTM BIU Mailbox driver for Armada 37xx");
-MODULE_AUTHOR("Marek Behun <marek.behun@nic.cz>");
+MODULE_AUTHOR("Marek Behun <kabel@kernel.org>");
q->limits.max_hw_sectors = UINT_MAX;
q->limits.max_sectors = UINT_MAX;
q->limits.max_segment_size = UINT_MAX;
- q->limits.max_segments = BIO_MAX_PAGES;
+ q->limits.max_segments = BIO_MAX_VECS;
blk_queue_max_discard_sectors(q, UINT_MAX);
q->limits.discard_granularity = 512;
q->limits.io_min = block_size;
static unsigned dm_crypt_clients_n = 0;
static volatile unsigned long dm_crypt_pages_per_client;
#define DM_CRYPT_MEMORY_PERCENT 2
-#define DM_CRYPT_MIN_PAGES_PER_CLIENT (BIO_MAX_PAGES * 16)
+#define DM_CRYPT_MIN_PAGES_PER_CLIENT (BIO_MAX_VECS * 16)
static void clone_init(struct dm_crypt_io *, struct bio *);
static void kcryptd_queue_crypt(struct dm_crypt_io *io);
ALIGN(sizeof(struct dm_crypt_io) + cc->dmreq_start + additional_req_size,
ARCH_KMALLOC_MINALIGN);
- ret = mempool_init(&cc->page_pool, BIO_MAX_PAGES, crypt_page_alloc, crypt_page_free, cc);
+ ret = mempool_init(&cc->page_pool, BIO_MAX_VECS, crypt_page_alloc, crypt_page_free, cc);
if (ret) {
ti->error = "Cannot allocate page mempool";
goto bad;
/*
* Check if bio is too large, split as needed.
*/
- if (unlikely(bio->bi_iter.bi_size > (BIO_MAX_PAGES << PAGE_SHIFT)) &&
+ if (unlikely(bio->bi_iter.bi_size > (BIO_MAX_VECS << PAGE_SHIFT)) &&
(bio_data_dir(bio) == WRITE || cc->on_disk_tag_size))
- dm_accept_partial_bio(bio, ((BIO_MAX_PAGES << PAGE_SHIFT) >> SECTOR_SHIFT));
+ dm_accept_partial_bio(bio, ((BIO_MAX_VECS << PAGE_SHIFT) >> SECTOR_SHIFT));
/*
* Ensure that bio is a multiple of internal sector encryption size
* Grab our output buffer.
*/
nl = orig_nl = get_result_buffer(param, param_size, &len);
- if (len < needed) {
+ if (len < needed || len < sizeof(nl->dev)) {
param->flags |= DM_BUFFER_FULL_FLAG;
goto out;
}
return blk_queue_zoned_model(q) != *zoned_model;
}
+/*
+ * Check the device zoned model based on the target feature flag. If the target
+ * has the DM_TARGET_ZONED_HM feature flag set, host-managed zoned devices are
+ * also accepted but all devices must have the same zoned model. If the target
+ * has the DM_TARGET_MIXED_ZONED_MODEL feature set, the devices can have any
+ * zoned model with all zoned devices having the same zone size.
+ */
static bool dm_table_supports_zoned_model(struct dm_table *t,
enum blk_zoned_model zoned_model)
{
for (i = 0; i < dm_table_get_num_targets(t); i++) {
ti = dm_table_get_target(t, i);
- if (zoned_model == BLK_ZONED_HM &&
- !dm_target_supports_zoned_hm(ti->type))
- return false;
-
- if (!ti->type->iterate_devices ||
- ti->type->iterate_devices(ti, device_not_zoned_model, &zoned_model))
- return false;
+ if (dm_target_supports_zoned_hm(ti->type)) {
+ if (!ti->type->iterate_devices ||
+ ti->type->iterate_devices(ti, device_not_zoned_model,
+ &zoned_model))
+ return false;
+ } else if (!dm_target_supports_mixed_zoned_model(ti->type)) {
+ if (zoned_model == BLK_ZONED_HM)
+ return false;
+ }
}
return true;
struct request_queue *q = bdev_get_queue(dev->bdev);
unsigned int *zone_sectors = data;
+ if (!blk_queue_is_zoned(q))
+ return 0;
+
return blk_queue_zone_sectors(q) != *zone_sectors;
}
+/*
+ * Check consistency of zoned model and zone sectors across all targets. For
+ * zone sectors, if the destination device is a zoned block device, it shall
+ * have the specified zone_sectors.
+ */
static int validate_hardware_zoned_model(struct dm_table *table,
enum blk_zoned_model zoned_model,
unsigned int zone_sectors)
return -EINVAL;
if (dm_table_any_dev_attr(table, device_not_matches_zone_sectors, &zone_sectors)) {
- DMERR("%s: zone sectors is not consistent across all devices",
+ DMERR("%s: zone sectors is not consistent across all zoned devices",
dm_device_name(table->md));
return -EINVAL;
}
u8 *res;
position = (index + rsb) * v->fec->roots;
- block = div64_u64_rem(position, v->fec->roots << SECTOR_SHIFT, &rem);
+ block = div64_u64_rem(position, v->fec->io_size, &rem);
*offset = (unsigned)rem;
res = dm_bufio_read(v->fec->bufio, block, buf);
/* read the next block when we run out of parity bytes */
offset += v->fec->roots;
- if (offset >= v->fec->roots << SECTOR_SHIFT) {
+ if (offset >= v->fec->io_size) {
dm_bufio_release(buf);
par = fec_read_parity(v, rsb, block_offset, &offset, &buf);
return -E2BIG;
}
+ if ((f->roots << SECTOR_SHIFT) & ((1 << v->data_dev_block_bits) - 1))
+ f->io_size = 1 << v->data_dev_block_bits;
+ else
+ f->io_size = v->fec->roots << SECTOR_SHIFT;
+
f->bufio = dm_bufio_client_create(f->dev->bdev,
- f->roots << SECTOR_SHIFT,
+ f->io_size,
1, 0, NULL, NULL);
if (IS_ERR(f->bufio)) {
ti->error = "Cannot initialize FEC bufio client";
struct dm_dev *dev; /* parity data device */
struct dm_bufio_client *data_bufio; /* for data dev access */
struct dm_bufio_client *bufio; /* for parity data access */
+ size_t io_size; /* IO size for roots */
sector_t start; /* parity data start in blocks */
sector_t blocks; /* number of blocks covered */
sector_t rounds; /* number of interleaving rounds */
#define DM_VERITY_OPT_IGN_ZEROES "ignore_zero_blocks"
#define DM_VERITY_OPT_AT_MOST_ONCE "check_at_most_once"
-#define DM_VERITY_OPTS_MAX (2 + DM_VERITY_OPTS_FEC + \
+#define DM_VERITY_OPTS_MAX (3 + DM_VERITY_OPTS_FEC + \
DM_VERITY_ROOT_HASH_VERIFICATION_OPTS)
static unsigned dm_verity_prefetch_cluster = DM_VERITY_DEFAULT_PREFETCH_SIZE;
list_add(&g->lru, &wbl.list);
wbl.size++;
g->write_in_progress = true;
- g->wc_list_contiguous = BIO_MAX_PAGES;
+ g->wc_list_contiguous = BIO_MAX_VECS;
f = g;
e->wc_list_contiguous++;
- if (unlikely(e->wc_list_contiguous == BIO_MAX_PAGES)) {
+ if (unlikely(e->wc_list_contiguous == BIO_MAX_VECS)) {
if (unlikely(wc->writeback_all)) {
next_node = rb_next(&f->rb_node);
if (likely(next_node))
static struct target_type dmz_type = {
.name = "zoned",
.version = {2, 0, 0},
- .features = DM_TARGET_SINGLETON | DM_TARGET_ZONED_HM,
+ .features = DM_TARGET_SINGLETON | DM_TARGET_MIXED_ZONED_MODEL,
.module = THIS_MODULE,
.ctr = dmz_ctr,
.dtr = dmz_dtr,
if (size != dm_get_size(md))
memset(&md->geometry, 0, sizeof(md->geometry));
- set_capacity_and_notify(md->disk, size);
+ if (!get_capacity(md->disk))
+ set_capacity(md->disk, size);
+ else
+ set_capacity_and_notify(md->disk, size);
dm_table_event_callback(t, event_callback, md);
static struct bio *r5l_bio_alloc(struct r5l_log *log)
{
- struct bio *bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_PAGES, &log->bs);
+ struct bio *bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_VECS, &log->bs);
bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
bio_set_dev(bio, log->rdev->bdev);
{
struct page *page;
- ctx->ra_bio = bio_alloc_bioset(GFP_KERNEL, BIO_MAX_PAGES, &log->bs);
+ ctx->ra_bio = bio_alloc_bioset(GFP_KERNEL, BIO_MAX_VECS, &log->bs);
if (!ctx->ra_bio)
return -ENOMEM;
if (!bio_add_page(bio, sh->ppl_page, PAGE_SIZE, 0)) {
struct bio *prev = bio;
- bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_PAGES,
+ bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_VECS,
&ppl_conf->bs);
bio->bi_opf = prev->bi_opf;
bio->bi_write_hint = prev->bi_write_hint;
MODULE_AUTHOR("Ben Backx <ben@bbackx.com>");
MODULE_DESCRIPTION("FireDTV DVB Driver");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("FireDTV DVB");
MODULE_AUTHOR("Andy Walls");
MODULE_DESCRIPTION("CX23418 ALSA Interface");
-MODULE_SUPPORTED_DEVICE("CX23418 MPEG2 encoder");
MODULE_LICENSE("GPL");
MODULE_VERSION(CX18_VERSION);
MODULE_AUTHOR("Hans Verkuil");
MODULE_DESCRIPTION("CX23418 driver");
-MODULE_SUPPORTED_DEVICE("CX23418 MPEG2 encoder");
MODULE_LICENSE("GPL");
MODULE_VERSION(CX18_VERSION);
MODULE_DESCRIPTION("ALSA driver module for cx25821 based capture cards");
MODULE_AUTHOR("Hiep Huynh");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Conexant,25821}"); /* "{{Conexant,23881}," */
static unsigned int debug;
module_param(debug, int, 0644);
MODULE_LICENSE("GPL v2");
MODULE_VERSION(CX88_VERSION);
-MODULE_SUPPORTED_DEVICE("{{Conexant,23881},{{Conexant,23882},{{Conexant,23883}");
static unsigned int debug;
module_param(debug, int, 0644);
MODULE_PARM_DESC(debug, "enable debug messages");
MODULE_AUTHOR("Andy Walls");
MODULE_DESCRIPTION("CX23415/CX23416 ALSA Interface");
-MODULE_SUPPORTED_DEVICE("CX23415/CX23416 MPEG2 encoder");
MODULE_LICENSE("GPL");
MODULE_VERSION(IVTV_VERSION);
MODULE_AUTHOR("Kevin Thayer, Chris Kennedy, Hans Verkuil");
MODULE_DESCRIPTION("CX23415/CX23416 driver");
-MODULE_SUPPORTED_DEVICE
- ("CX23415/CX23416 MPEG2 encoder (WinTV PVR-150/250/350/500,\n"
- "\t\t\tYuan MPG series and similar)");
MODULE_LICENSE("GPL");
MODULE_VERSION(IVTV_VERSION);
MODULE_DESCRIPTION("STA2X11 Video Input Port driver");
MODULE_AUTHOR("Wind River");
MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("sta2x11 video input");
MODULE_VERSION(DRV_VERSION);
MODULE_DEVICE_TABLE(pci, sta2x11_vip_pci_tbl);
MODULE_AUTHOR("Josh Wu <josh.wu@atmel.com>");
MODULE_DESCRIPTION("The V4L2 driver for Atmel Linux");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("video");
MODULE_AUTHOR("Songjun Wu");
MODULE_DESCRIPTION("The V4L2 driver for Atmel-ISC");
MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("video");
MODULE_AUTHOR("Jonathan Corbet <corbet@lwn.net>");
MODULE_DESCRIPTION("Marvell 88ALP01 CMOS Camera Controller driver");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("Video");
-
-
-
struct cafe_camera {
int registered; /* Fully initialized? */
memset(hst.hist_weight, 0x01, sizeof(hst.hist_weight));
rkisp1_hst_config(params, &hst);
rkisp1_param_set_bits(params, RKISP1_CIF_ISP_HIST_PROP,
- ~RKISP1_CIF_ISP_HIST_PROP_MODE_MASK |
rkisp1_hst_params_default_config.mode);
/* set the range */
MODULE_AUTHOR("Hugues Fruchet <hugues.fruchet@st.com>");
MODULE_DESCRIPTION("STMicroelectronics STM32 Digital Camera Memory Interface driver");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("video");
brx = &vsp1->bru->entity;
else if (pipe->brx && !drm_pipe->force_brx_release)
brx = pipe->brx;
- else if (!vsp1->bru->entity.pipe)
+ else if (vsp1_feature(vsp1, VSP1_HAS_BRU) && !vsp1->bru->entity.pipe)
brx = &vsp1->bru->entity;
else
brx = &vsp1->brs->entity;
* make sure it is present in the pipeline's list of entities if it
* wasn't already.
*/
- if (!use_uif) {
+ if (drm_pipe->uif && !use_uif) {
drm_pipe->uif->pipe = NULL;
- } else if (!drm_pipe->uif->pipe) {
+ } else if (drm_pipe->uif && !drm_pipe->uif->pipe) {
drm_pipe->uif->pipe = pipe;
list_add_tail(&drm_pipe->uif->list_pipe, &pipe->entities);
}
obj-$(CONFIG_RC_CORE) += rc-core.o
rc-core-y := rc-main.o rc-ir-raw.o
rc-core-$(CONFIG_LIRC) += lirc_dev.o
+rc-core-$(CONFIG_MEDIA_CEC_RC) += keymaps/rc-cec.o
rc-core-$(CONFIG_BPF_LIRC_MODE2) += bpf-lirc.o
obj-$(CONFIG_IR_NEC_DECODER) += ir-nec-decoder.o
obj-$(CONFIG_IR_RC5_DECODER) += ir-rc5-decoder.o
rc-behold.o \
rc-behold-columbus.o \
rc-budget-ci-old.o \
- rc-cec.o \
rc-cinergy-1400.o \
rc-cinergy.o \
rc-d680-dmb.o \
// SPDX-License-Identifier: GPL-2.0-or-later
/* Keytable for the CEC remote control
*
+ * This keymap is unusual in that it can't be built as a module,
+ * instead it is registered directly in rc-main.c if CONFIG_MEDIA_CEC_RC
+ * is set. This is because it can be called from drm_dp_cec_set_edid() via
+ * cec_register_adapter() in an asynchronous context, and it is not
+ * allowed to use request_module() to load rc-cec.ko in that case.
+ *
+ * Since this keymap is only used if CONFIG_MEDIA_CEC_RC is set, we
+ * just compile this keymap into the rc-core module and never as a
+ * separate module.
+ *
* Copyright (c) 2015 by Kamil Debski
*/
/* 0x77-0xff: Reserved */
};
-static struct rc_map_list cec_map = {
+struct rc_map_list cec_map = {
.map = {
.scan = cec,
.size = ARRAY_SIZE(cec),
.name = RC_MAP_CEC,
}
};
-
-static int __init init_rc_map_cec(void)
-{
- return rc_map_register(&cec_map);
-}
-
-static void __exit exit_rc_map_cec(void)
-{
- rc_map_unregister(&cec_map);
-}
-
-module_init(init_rc_map_cec);
-module_exit(exit_rc_map_cec);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Kamil Debski");
led_trigger_register_simple("rc-feedback", &led_feedback);
rc_map_register(&empty_map);
+#ifdef CONFIG_MEDIA_CEC_RC
+ rc_map_register(&cec_map);
+#endif
return 0;
}
lirc_dev_exit();
class_unregister(&rc_class);
led_trigger_unregister_simple(led_feedback);
+#ifdef CONFIG_MEDIA_CEC_RC
+ rc_map_unregister(&cec_map);
+#endif
rc_map_unregister(&empty_map);
}
MODULE_AUTHOR("Steve Miller (STMicroelectronics) <steve.miller@st.com>");
MODULE_DESCRIPTION("V4L-driver for STMicroelectronics CPiA2 based cameras");
-MODULE_SUPPORTED_DEVICE("video");
MODULE_LICENSE("GPL");
MODULE_VERSION(CPIA_VERSION);
MODULE_DESCRIPTION("ALSA driver module for tm5600/tm6000/tm6010 based TV cards");
MODULE_AUTHOR("Mauro Carvalho Chehab");
MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("{{Trident,tm5600},{{Trident,tm6000},{{Trident,tm6010}");
static unsigned int debug;
module_param(debug, int, 0644);
MODULE_PARM_DESC(debug, "enable debug messages");
MODULE_AUTHOR("Mauro Carvalho Chehab");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Trident, tm5600},{{Trident, tm6000},{{Trident, tm6010}");
-
static int debug;
module_param(debug, int, 0644);
cancel_work_sync(&usbtv->snd_trigger);
if (usbtv->snd && usbtv->udev) {
- snd_card_free(usbtv->snd);
+ snd_card_free_when_closed(usbtv->snd);
usbtv->snd = NULL;
}
}
{}
};
-static const struct resource intel_quark_i2c_res[] = {
+/* This is used as a place holder and will be modified at run-time */
+static struct resource intel_quark_i2c_res[] = {
[INTEL_QUARK_IORES_MEM] = {
.flags = IORESOURCE_MEM,
},
.adr = MFD_ACPI_MATCH_I2C,
};
-static const struct resource intel_quark_gpio_res[] = {
+/* This is used as a place holder and will be modified at run-time */
+static struct resource intel_quark_gpio_res[] = {
[INTEL_QUARK_IORES_MEM] = {
.flags = IORESOURCE_MEM,
},
if (!fl->cctx->rpdev)
return -EPIPE;
+ if (handle == FASTRPC_INIT_HANDLE && !kernel) {
+ dev_warn_ratelimited(fl->sctx->dev, "user app trying to send a kernel RPC message (%d)\n", handle);
+ return -EPERM;
+ }
+
ctx = fastrpc_context_alloc(fl, kernel, sc, args);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
struct hl_dbg_device_entry *dev_entry = &hdev->hl_debugfs;
int count = ARRAY_SIZE(hl_debugfs_list);
struct hl_debugfs_entry *entry;
- struct dentry *ent;
int i;
dev_entry->hdev = hdev;
&hl_security_violations_fops);
for (i = 0, entry = dev_entry->entry_arr ; i < count ; i++, entry++) {
-
- ent = debugfs_create_file(hl_debugfs_list[i].name,
+ debugfs_create_file(hl_debugfs_list[i].name,
0444,
dev_entry->root,
entry,
&hl_debugfs_fops);
- entry->dent = ent;
entry->info_ent = &hl_debugfs_list[i];
entry->dev_entry = dev_entry;
}
static int hl_device_release(struct inode *inode, struct file *filp)
{
struct hl_fpriv *hpriv = filp->private_data;
+ struct hl_device *hdev = hpriv->hdev;
+
+ filp->private_data = NULL;
+
+ if (!hdev) {
+ pr_crit("Closing FD after device was removed. Memory leak will occur and it is advised to reboot.\n");
+ put_pid(hpriv->taskpid);
+ return 0;
+ }
hl_cb_mgr_fini(hpriv->hdev, &hpriv->cb_mgr);
hl_ctx_mgr_fini(hpriv->hdev, &hpriv->ctx_mgr);
- filp->private_data = NULL;
-
hl_hpriv_put(hpriv);
return 0;
static int hl_device_release_ctrl(struct inode *inode, struct file *filp)
{
struct hl_fpriv *hpriv = filp->private_data;
- struct hl_device *hdev;
+ struct hl_device *hdev = hpriv->hdev;
filp->private_data = NULL;
- hdev = hpriv->hdev;
+ if (!hdev) {
+ pr_err("Closing FD after device was removed\n");
+ goto out;
+ }
mutex_lock(&hdev->fpriv_list_lock);
list_del(&hpriv->dev_node);
mutex_unlock(&hdev->fpriv_list_lock);
+out:
+ put_pid(hpriv->taskpid);
kfree(hpriv);
static int hl_mmap(struct file *filp, struct vm_area_struct *vma)
{
struct hl_fpriv *hpriv = filp->private_data;
+ struct hl_device *hdev = hpriv->hdev;
unsigned long vm_pgoff;
+ if (!hdev) {
+ pr_err_ratelimited("Trying to mmap after device was removed! Please close FD\n");
+ return -ENODEV;
+ }
+
vm_pgoff = vma->vm_pgoff;
vma->vm_pgoff = HL_MMAP_OFFSET_VALUE_GET(vm_pgoff);
return -EBUSY;
}
+static void device_disable_open_processes(struct hl_device *hdev)
+{
+ struct hl_fpriv *hpriv;
+
+ mutex_lock(&hdev->fpriv_list_lock);
+ list_for_each_entry(hpriv, &hdev->fpriv_list, dev_node)
+ hpriv->hdev = NULL;
+ mutex_unlock(&hdev->fpriv_list_lock);
+}
+
/*
* hl_device_reset - reset the device
*
HL_PENDING_RESET_LONG_SEC);
rc = device_kill_open_processes(hdev, HL_PENDING_RESET_LONG_SEC);
- if (rc)
+ if (rc) {
dev_crit(hdev->dev, "Failed to kill all open processes\n");
+ device_disable_open_processes(hdev);
+ }
hl_cb_pool_fini(hdev);
/**
* struct hl_debugfs_entry - debugfs dentry wrapper.
- * @dent: base debugfs entry structure.
* @info_ent: dentry realted ops.
* @dev_entry: ASIC specific debugfs manager.
*/
struct hl_debugfs_entry {
- struct dentry *dent;
const struct hl_info_list *info_ent;
struct hl_dbg_device_entry *dev_entry;
};
* All Rights Reserved.
*/
+#define pr_fmt(fmt) "habanalabs: " fmt
+
#include <uapi/misc/habanalabs.h>
#include "habanalabs.h"
const struct hl_ioctl_desc *ioctl = NULL;
unsigned int nr = _IOC_NR(cmd);
+ if (!hdev) {
+ pr_err_ratelimited("Sending ioctl after device was removed! Please close FD\n");
+ return -ENODEV;
+ }
+
if ((nr >= HL_COMMAND_START) && (nr < HL_COMMAND_END)) {
ioctl = &hl_ioctls[nr];
} else {
const struct hl_ioctl_desc *ioctl = NULL;
unsigned int nr = _IOC_NR(cmd);
+ if (!hdev) {
+ pr_err_ratelimited("Sending ioctl after device was removed! Please close FD\n");
+ return -ENODEV;
+ }
+
if (nr == _IOC_NR(HL_IOCTL_INFO)) {
ioctl = &hl_ioctls_control[nr];
} else {
* Increment ptr by 1. If it reaches the number of event queue
* entries, set it to 0
*/
-inline u32 hl_eq_inc_ptr(u32 ptr)
+static inline u32 hl_eq_inc_ptr(u32 ptr)
{
ptr++;
if (unlikely(ptr == HL_EQ_LENGTH))
else /* HL_VA_RANGE_TYPE_DRAM */
p = &prop->dmmu;
- /*
- * find the correct hop shift field in hl_mmu_properties structure
- * in order to determine the right maks for the page offset.
- */
- hop0_shift_off = offsetof(struct hl_mmu_properties, hop0_shift);
- p = (char *)p + hop0_shift_off;
- p = (char *)p + ((hops->used_hops - 1) * sizeof(u64));
- hop_shift = *(u64 *)p;
- offset_mask = (1ull << hop_shift) - 1;
- addr_mask = ~(offset_mask);
- *phys_addr = (tmp_phys_addr & addr_mask) |
- (virt_addr & offset_mask);
+ if ((hops->range_type == HL_VA_RANGE_TYPE_DRAM) &&
+ !is_power_of_2(prop->dram_page_size)) {
+ u32 bit;
+ u64 page_offset_mask;
+ u64 phys_addr_mask;
+
+ bit = __ffs64((u64)prop->dram_page_size);
+ page_offset_mask = ((1ull << bit) - 1);
+ phys_addr_mask = ~page_offset_mask;
+ *phys_addr = (tmp_phys_addr & phys_addr_mask) |
+ (virt_addr & page_offset_mask);
+ } else {
+ /*
+ * find the correct hop shift field in hl_mmu_properties
+ * structure in order to determine the right masks
+ * for the page offset.
+ */
+ hop0_shift_off = offsetof(struct hl_mmu_properties, hop0_shift);
+ p = (char *)p + hop0_shift_off;
+ p = (char *)p + ((hops->used_hops - 1) * sizeof(u64));
+ hop_shift = *(u64 *)p;
+ offset_mask = (1ull << hop_shift) - 1;
+ addr_mask = ~(offset_mask);
+ *phys_addr = (tmp_phys_addr & addr_mask) |
+ (virt_addr & offset_mask);
+ }
}
int hl_mmu_va_to_pa(struct hl_ctx *ctx, u64 virt_addr, u64 *phys_addr)
return -EPERM;
}
-static int ibmvmc_remove(struct vio_dev *vdev)
+static void ibmvmc_remove(struct vio_dev *vdev)
{
struct crq_server_adapter *adapter = dev_get_drvdata(&vdev->dev);
dev_info(adapter->dev, "Entering remove for UA 0x%x\n",
vdev->unit_address);
ibmvmc_release_crq_queue(adapter);
-
- return 0;
}
static struct vio_device_id ibmvmc_device_table[] = {
__lkdtm_CORRUPT_STACK((void *)&data);
}
+static pid_t stack_pid;
+static unsigned long stack_addr;
+
+void lkdtm_REPORT_STACK(void)
+{
+ volatile uintptr_t magic;
+ pid_t pid = task_pid_nr(current);
+
+ if (pid != stack_pid) {
+ pr_info("Starting stack offset tracking for pid %d\n", pid);
+ stack_pid = pid;
+ stack_addr = (uintptr_t)&magic;
+ }
+
+ pr_info("Stack offset: %d\n", (int)(stack_addr - (uintptr_t)&magic));
+}
+
void lkdtm_UNALIGNED_LOAD_STORE_WRITE(void)
{
static u8 data[5] __attribute__((aligned(4))) = {1, 2, 3, 4, 5};
CRASHTYPE(EXHAUST_STACK),
CRASHTYPE(CORRUPT_STACK),
CRASHTYPE(CORRUPT_STACK_STRONG),
+ CRASHTYPE(REPORT_STACK),
CRASHTYPE(CORRUPT_LIST_ADD),
CRASHTYPE(CORRUPT_LIST_DEL),
CRASHTYPE(STACK_GUARD_PAGE_LEADING),
void lkdtm_EXHAUST_STACK(void);
void lkdtm_CORRUPT_STACK(void);
void lkdtm_CORRUPT_STACK_STRONG(void);
+void lkdtm_REPORT_STACK(void);
void lkdtm_UNALIGNED_LOAD_STORE_WRITE(void);
void lkdtm_SOFTLOCKUP(void);
void lkdtm_HARDLOCKUP(void);
if (buffer_id == 0)
return -EINVAL;
- if (!mei_cl_is_connected(cl))
- return -ENODEV;
+ if (mei_cl_is_connected(cl))
+ return -EPROTO;
if (cl->dma_mapped)
return -EPROTO;
mutex_unlock(&dev->device_lock);
wait_event_timeout(cl->wait,
- cl->dma_mapped ||
- cl->status ||
- !mei_cl_is_connected(cl),
+ cl->dma_mapped || cl->status,
mei_secs_to_jiffies(MEI_CL_CONNECT_TIMEOUT));
mutex_lock(&dev->device_lock);
return -EOPNOTSUPP;
}
- if (!mei_cl_is_connected(cl))
- return -ENODEV;
+ /* do not allow unmap for connected client */
+ if (mei_cl_is_connected(cl))
+ return -EPROTO;
if (!cl->dma_mapped)
return -EPROTO;
mutex_unlock(&dev->device_lock);
wait_event_timeout(cl->wait,
- !cl->dma_mapped ||
- cl->status ||
- !mei_cl_is_connected(cl),
+ !cl->dma_mapped || cl->status,
mei_secs_to_jiffies(MEI_CL_CONNECT_TIMEOUT));
mutex_lock(&dev->device_lock);
{ .compatible = "qemu,pvpanic-mmio", },
{}
};
+MODULE_DEVICE_TABLE(of, pvpanic_mmio_match);
static const struct acpi_device_id pvpanic_device_ids[] = {
{ "QEMU0001", 0 },
mmc_remove_card_debugfs(card);
#endif
- if (host->cqe_enabled) {
- host->cqe_ops->cqe_disable(host);
- host->cqe_enabled = false;
- }
-
if (mmc_card_present(card)) {
if (mmc_host_is_spi(card->host)) {
pr_info("%s: SPI card removed\n",
of_node_put(card->dev.of_node);
}
+ if (host->cqe_enabled) {
+ host->cqe_ops->cqe_disable(host);
+ host->cqe_enabled = false;
+ }
+
put_device(&card->dev);
}
-
/* EXT_CSD value is in units of 10ms, but we store in ms */
card->ext_csd.part_time = 10 * ext_csd[EXT_CSD_PART_SWITCH_TIME];
- /* Some eMMC set the value too low so set a minimum */
- if (card->ext_csd.part_time &&
- card->ext_csd.part_time < MMC_MIN_PART_SWITCH_TIME)
- card->ext_csd.part_time = MMC_MIN_PART_SWITCH_TIME;
/* Sleep / awake timeout in 100ns units */
if (sa_shift > 0 && sa_shift <= 0x17)
card->ext_csd.data_sector_size = 512;
}
+ /*
+ * GENERIC_CMD6_TIME is to be used "unless a specific timeout is defined
+ * when accessing a specific field", so use it here if there is no
+ * PARTITION_SWITCH_TIME.
+ */
+ if (!card->ext_csd.part_time)
+ card->ext_csd.part_time = card->ext_csd.generic_cmd6_time;
+ /* Some eMMC set the value too low so set a minimum */
+ if (card->ext_csd.part_time < MMC_MIN_PART_SWITCH_TIME)
+ card->ext_csd.part_time = MMC_MIN_PART_SWITCH_TIME;
+
/* eMMC v5 or later */
if (card->ext_csd.rev >= 7) {
memcpy(card->ext_csd.fwrev, &ext_csd[EXT_CSD_FIRMWARE_VERSION],
*/
for_each_sg(data->sg, sg, data->sg_len, i) {
if (sg->length % data->blksz) {
- WARN_ONCE(1, "unaligned sg len %u blksize %u\n",
- sg->length, data->blksz);
+ dev_warn_once(mmc_dev(mmc),
+ "unaligned sg len %u blksize %u, disabling descriptor DMA for transfer\n",
+ sg->length, data->blksz);
return;
}
}
if (!cmd->busy_timeout)
cmd->busy_timeout = 10 * MSEC_PER_SEC;
- clks = (unsigned long long)cmd->busy_timeout * host->cclk;
+ if (cmd->busy_timeout > host->mmc->max_busy_timeout)
+ clks = (unsigned long long)host->mmc->max_busy_timeout * host->cclk;
+ else
+ clks = (unsigned long long)cmd->busy_timeout * host->cclk;
+
do_div(clks, MSEC_PER_SEC);
writel_relaxed(clks, host->base + MMCIDATATIMER);
}
mmc->caps |= MMC_CAP_WAIT_WHILE_BUSY;
}
+ /* Variants with mandatory busy timeout in HW needs R1B responses. */
+ if (variant->busy_timeout)
+ mmc->caps |= MMC_CAP_NEED_RSP_BUSY;
+
/* Prepare a CMD12 - needed to clear the DPSM on some variants. */
host->stop_abort.opcode = MMC_STOP_TRANSMISSION;
host->stop_abort.arg = 0;
MODULE_AUTHOR("Eric Brower <ebrower@usa.net>");
MODULE_DESCRIPTION("User-programmable flash device on Sun Microsystems boardsets");
-MODULE_SUPPORTED_DEVICE(DRIVER_NAME);
MODULE_LICENSE("GPL");
MODULE_VERSION("2.1");
return 0;
case NAND_OP_WAITRDY_INSTR:
return readl_poll_timeout(nfc->regs + NFI_STA, status,
- status & STA_BUSY, 20,
- instr->ctx.waitrdy.timeout_ms);
+ !(status & STA_BUSY), 20,
+ instr->ctx.waitrdy.timeout_ms * 1000);
default:
break;
}
select CRYPTO_BLAKE2S_ARM if ARM
select CRYPTO_CURVE25519_NEON if ARM && KERNEL_MODE_NEON
select CRYPTO_CHACHA_MIPS if CPU_MIPS32_R2
- select CRYPTO_POLY1305_MIPS if CPU_MIPS32 || (CPU_MIPS64 && 64BIT)
+ select CRYPTO_POLY1305_MIPS if MIPS
help
WireGuard is a secure, fast, and easy to use replacement for IPSec
that uses modern cryptography and clever networking tricks. It's
int i, ioaddr, ret;
struct resource *r;
+ ret = 0;
+
if (pci_enable_device(pdev))
return -EIO;
priv->ci = ci;
mm = &ci->misc_map;
+ pci_set_drvdata(pdev, priv);
+
INIT_LIST_HEAD(&priv->list_dev);
if (mm->size) {
dev = alloc_arcdev(device);
if (!dev) {
ret = -ENOMEM;
- goto out_port;
+ break;
}
dev->dev_port = i;
pr_err("IO region %xh-%xh already allocated\n",
ioaddr, ioaddr + cm->size - 1);
ret = -EBUSY;
- goto out_port;
+ goto err_free_arcdev;
}
/* Dummy access after Reset
if (arcnet_inb(ioaddr, COM20020_REG_R_STATUS) == 0xFF) {
pr_err("IO address %Xh is empty!\n", ioaddr);
ret = -EIO;
- goto out_port;
+ goto err_free_arcdev;
}
if (com20020_check(dev)) {
ret = -EIO;
- goto out_port;
+ goto err_free_arcdev;
}
card = devm_kzalloc(&pdev->dev, sizeof(struct com20020_dev),
GFP_KERNEL);
if (!card) {
ret = -ENOMEM;
- goto out_port;
+ goto err_free_arcdev;
}
card->index = i;
ret = devm_led_classdev_register(&pdev->dev, &card->tx_led);
if (ret)
- goto out_port;
+ goto err_free_arcdev;
ret = devm_led_classdev_register(&pdev->dev, &card->recon_led);
if (ret)
- goto out_port;
+ goto err_free_arcdev;
dev_set_drvdata(&dev->dev, card);
ret = com20020_found(dev, IRQF_SHARED);
if (ret)
- goto out_port;
+ goto err_free_arcdev;
devm_arcnet_led_init(dev, dev->dev_id, i);
list_add(&card->list, &priv->list_dev);
- }
+ continue;
- pci_set_drvdata(pdev, priv);
-
- return 0;
-
-out_port:
- com20020pci_remove(pdev);
+err_free_arcdev:
+ free_arcdev(dev);
+ break;
+ }
+ if (ret)
+ com20020pci_remove(pdev);
return ret;
}
.brp_inc = 1,
};
-static inline void c_can_pm_runtime_enable(const struct c_can_priv *priv)
-{
- if (priv->device)
- pm_runtime_enable(priv->device);
-}
-
-static inline void c_can_pm_runtime_disable(const struct c_can_priv *priv)
-{
- if (priv->device)
- pm_runtime_disable(priv->device);
-}
-
static inline void c_can_pm_runtime_get_sync(const struct c_can_priv *priv)
{
if (priv->device)
int register_c_can_dev(struct net_device *dev)
{
- struct c_can_priv *priv = netdev_priv(dev);
int err;
/* Deactivate pins to prevent DRA7 DCAN IP from being
*/
pinctrl_pm_select_sleep_state(dev->dev.parent);
- c_can_pm_runtime_enable(priv);
-
dev->flags |= IFF_ECHO; /* we support local echo */
dev->netdev_ops = &c_can_netdev_ops;
err = register_candev(dev);
- if (err)
- c_can_pm_runtime_disable(priv);
- else
+ if (!err)
devm_can_led_init(dev);
-
return err;
}
EXPORT_SYMBOL_GPL(register_c_can_dev);
void unregister_c_can_dev(struct net_device *dev)
{
- struct c_can_priv *priv = netdev_priv(dev);
-
unregister_candev(dev);
-
- c_can_pm_runtime_disable(priv);
}
EXPORT_SYMBOL_GPL(unregister_c_can_dev);
{
struct net_device *dev = pci_get_drvdata(pdev);
struct c_can_priv *priv = netdev_priv(dev);
+ void __iomem *addr = priv->base;
unregister_c_can_dev(dev);
free_c_can_dev(dev);
- pci_iounmap(pdev, priv->base);
+ pci_iounmap(pdev, addr);
pci_disable_msi(pdev);
pci_clear_master(pdev);
pci_release_regions(pdev);
#include <linux/list.h>
#include <linux/io.h>
#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
#include <linux/clk.h>
#include <linux/of.h>
#include <linux/of_device.h>
platform_set_drvdata(pdev, dev);
SET_NETDEV_DEV(dev, &pdev->dev);
+ pm_runtime_enable(priv->device);
ret = register_c_can_dev(dev);
if (ret) {
dev_err(&pdev->dev, "registering %s failed (err=%d)\n",
return 0;
exit_free_device:
+ pm_runtime_disable(priv->device);
free_c_can_dev(dev);
exit:
dev_err(&pdev->dev, "probe failed\n");
static int c_can_plat_remove(struct platform_device *pdev)
{
struct net_device *dev = platform_get_drvdata(pdev);
+ struct c_can_priv *priv = netdev_priv(dev);
unregister_c_can_dev(dev);
-
+ pm_runtime_disable(priv->device);
free_c_can_dev(dev);
return 0;
struct rtnl_link_ops can_link_ops __read_mostly = {
.kind = "can",
+ .netns_refund = true,
.maxtype = IFLA_CAN_MAX,
.policy = can_policy,
.setup = can_setup,
static int flexcan_chip_freeze(struct flexcan_priv *priv)
{
struct flexcan_regs __iomem *regs = priv->regs;
- unsigned int timeout = 1000 * 1000 * 10 / priv->can.bittiming.bitrate;
+ unsigned int timeout;
+ u32 bitrate = priv->can.bittiming.bitrate;
u32 reg;
+ if (bitrate)
+ timeout = 1000 * 1000 * 10 / bitrate;
+ else
+ timeout = FLEXCAN_TIMEOUT_US / 10;
+
reg = priv->read(®s->mcr);
- reg |= FLEXCAN_MCR_HALT;
+ reg |= FLEXCAN_MCR_FRZ | FLEXCAN_MCR_HALT;
priv->write(reg, ®s->mcr);
while (timeout-- && !(priv->read(®s->mcr) & FLEXCAN_MCR_FRZ_ACK))
flexcan_set_bittiming(dev);
+ /* set freeze, halt */
+ err = flexcan_chip_freeze(priv);
+ if (err)
+ goto out_chip_disable;
+
/* MCR
*
- * enable freeze
- * halt now
* only supervisor access
* enable warning int
* enable individual RX masking
*/
reg_mcr = priv->read(®s->mcr);
reg_mcr &= ~FLEXCAN_MCR_MAXMB(0xff);
- reg_mcr |= FLEXCAN_MCR_FRZ | FLEXCAN_MCR_HALT | FLEXCAN_MCR_SUPV |
- FLEXCAN_MCR_WRN_EN | FLEXCAN_MCR_IRMQ | FLEXCAN_MCR_IDAM_C |
- FLEXCAN_MCR_MAXMB(priv->tx_mb_idx);
+ reg_mcr |= FLEXCAN_MCR_SUPV | FLEXCAN_MCR_WRN_EN | FLEXCAN_MCR_IRMQ |
+ FLEXCAN_MCR_IDAM_C | FLEXCAN_MCR_MAXMB(priv->tx_mb_idx);
/* MCR
*
if (err)
goto out_chip_disable;
- /* set freeze, halt and activate FIFO, restrict register access */
+ /* set freeze, halt */
+ err = flexcan_chip_freeze(priv);
+ if (err)
+ goto out_chip_disable;
+
+ /* activate FIFO, restrict register access */
reg = priv->read(®s->mcr);
- reg |= FLEXCAN_MCR_FRZ | FLEXCAN_MCR_HALT |
- FLEXCAN_MCR_FEN | FLEXCAN_MCR_SUPV;
+ reg |= FLEXCAN_MCR_FEN | FLEXCAN_MCR_SUPV;
priv->write(reg, ®s->mcr);
/* Currently we only support newer versions of this core
#define KVASER_PCIEFD_KCAN_STAT_REG 0x418
#define KVASER_PCIEFD_KCAN_MODE_REG 0x41c
#define KVASER_PCIEFD_KCAN_BTRN_REG 0x420
+#define KVASER_PCIEFD_KCAN_BUS_LOAD_REG 0x424
#define KVASER_PCIEFD_KCAN_BTRD_REG 0x428
#define KVASER_PCIEFD_KCAN_PWM_REG 0x430
/* Loopback control register */
timer_setup(&can->bec_poll_timer, kvaser_pciefd_bec_poll_timer,
0);
+ /* Disable Bus load reporting */
+ iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_BUS_LOAD_REG);
+
tx_npackets = ioread32(can->reg_base +
KVASER_PCIEFD_KCAN_TX_NPACKETS_REG);
if (((tx_npackets >> KVASER_PCIEFD_KCAN_TX_NPACKETS_MAX_SHIFT) &
}
while ((rxfs & RXFS_FFL_MASK) && (quota > 0)) {
- if (rxfs & RXFS_RFL)
- netdev_warn(dev, "Rx FIFO 0 Message Lost\n");
-
m_can_read_fifo(dev, rxfs);
quota--;
{
struct m_can_classdev *cdev = netdev_priv(dev);
- m_can_rx_handler(dev, 1);
+ m_can_rx_handler(dev, M_CAN_NAPI_WEIGHT);
m_can_enable_all_interrupts(cdev);
if (ret)
return ret;
+ /* Zero out the MCAN buffers */
+ m_can_init_ram(cdev);
+
ret = regmap_update_bits(tcan4x5x->regmap, TCAN4X5X_CONFIG,
TCAN4X5X_MODE_SEL_MASK, TCAN4X5X_MODE_NORMAL);
if (ret)
return ret;
- /* Zero out the MCAN buffers */
- m_can_init_ram(cdev);
-
return ret;
}
MODULE_AUTHOR("Stephane Grosjean <s.grosjean@peak-system.com>");
MODULE_DESCRIPTION("Socket-CAN driver for PEAK PCAN PCIe/M.2 FD family cards");
-MODULE_SUPPORTED_DEVICE("PEAK PCAN PCIe/M.2 FD CAN cards");
MODULE_LICENSE("GPL v2");
#define PCIEFD_DRV_NAME "peak_pciefd"
MODULE_AUTHOR("Sebastian Haas <haas@ems-wuenche.com>");
MODULE_DESCRIPTION("Socket-CAN driver for EMS CPC-PCI/PCIe/104P CAN cards");
-MODULE_SUPPORTED_DEVICE("EMS CPC-PCI/PCIe/104P CAN card");
MODULE_LICENSE("GPL v2");
#define EMS_PCI_V1_MAX_CHAN 2
MODULE_AUTHOR("Markus Plessing <plessing@ems-wuensche.com>");
MODULE_DESCRIPTION("Socket-CAN driver for EMS CPC-CARD cards");
-MODULE_SUPPORTED_DEVICE("EMS CPC-CARD CAN card");
MODULE_LICENSE("GPL v2");
#define EMS_PCMCIA_MAX_CHAN 2
MODULE_AUTHOR("Per Dalen <per.dalen@cnw.se>");
MODULE_DESCRIPTION("Socket-CAN driver for KVASER PCAN PCI cards");
-MODULE_SUPPORTED_DEVICE("KVASER PCAN PCI CAN card");
MODULE_LICENSE("GPL v2");
#define MAX_NO_OF_CHANNELS 4 /* max no of channels on a single card */
MODULE_AUTHOR("Stephane Grosjean <s.grosjean@peak-system.com>");
MODULE_DESCRIPTION("Socket-CAN driver for PEAK PCAN PCI family cards");
-MODULE_SUPPORTED_DEVICE("PEAK PCAN PCI/PCIe/PCIeC miniPCI CAN cards");
-MODULE_SUPPORTED_DEVICE("PEAK PCAN miniPCIe/cPCI PC/104+ PCI/104e CAN Cards");
MODULE_LICENSE("GPL v2");
#define DRV_NAME "peak_pci"
MODULE_AUTHOR("Stephane Grosjean <s.grosjean@peak-system.com>");
MODULE_DESCRIPTION("CAN driver for PEAK-System PCAN-PC Cards");
MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("PEAK PCAN-PC Card");
/* PEAK-System PCMCIA driver name */
#define PCC_NAME "peak_pcmcia"
MODULE_AUTHOR("Pavel Cheblakov <P.B.Cheblakov@inp.nsk.su>");
MODULE_DESCRIPTION("Socket-CAN driver for PLX90xx PCI-bridge cards with "
"the SJA1000 chips");
-MODULE_SUPPORTED_DEVICE("Adlink PCI-7841/cPCI-7841, "
- "Adlink PCI-7841/cPCI-7841 SE, "
- "Marathon CAN-bus-PCI, "
- "Marathon CAN-bus-PCIe, "
- "TEWS TECHNOLOGIES TPMC810, "
- "esd CAN-PCI/CPCI/PCI104/200, "
- "esd CAN-PCI/PMC/266, "
- "esd CAN-PCIe/2000, "
- "Connect Tech Inc. CANpro/104-Plus Opto (CRG001), "
- "IXXAT PC-I 04/PCI, "
- "ELCUS CAN-200-PCI, "
- "ASEM DUAL CAN-RAW")
MODULE_LICENSE("GPL v2");
#define PLX_PCI_MAX_CHAN 2
return ret;
}
+static int mcp251x_spi_write(struct spi_device *spi, int len)
+{
+ struct mcp251x_priv *priv = spi_get_drvdata(spi);
+ int ret;
+
+ ret = spi_write(spi, priv->spi_tx_buf, len);
+ if (ret)
+ dev_err(&spi->dev, "spi write failed: ret = %d\n", ret);
+
+ return ret;
+}
+
static u8 mcp251x_read_reg(struct spi_device *spi, u8 reg)
{
struct mcp251x_priv *priv = spi_get_drvdata(spi);
priv->spi_tx_buf[1] = reg;
priv->spi_tx_buf[2] = val;
- mcp251x_spi_trans(spi, 3);
+ mcp251x_spi_write(spi, 3);
}
static void mcp251x_write_2regs(struct spi_device *spi, u8 reg, u8 v1, u8 v2)
priv->spi_tx_buf[2] = v1;
priv->spi_tx_buf[3] = v2;
- mcp251x_spi_trans(spi, 4);
+ mcp251x_spi_write(spi, 4);
}
static void mcp251x_write_bits(struct spi_device *spi, u8 reg,
priv->spi_tx_buf[2] = mask;
priv->spi_tx_buf[3] = val;
- mcp251x_spi_trans(spi, 4);
+ mcp251x_spi_write(spi, 4);
}
static u8 mcp251x_read_stat(struct spi_device *spi)
buf[i]);
} else {
memcpy(priv->spi_tx_buf, buf, TXBDAT_OFF + len);
- mcp251x_spi_trans(spi, TXBDAT_OFF + len);
+ mcp251x_spi_write(spi, TXBDAT_OFF + len);
}
}
/* use INSTRUCTION_RTS, to avoid "repeated frame problem" */
priv->spi_tx_buf[0] = INSTRUCTION_RTS(1 << tx_buf_idx);
- mcp251x_spi_trans(priv->spi, 1);
+ mcp251x_spi_write(priv->spi, 1);
}
static void mcp251x_hw_rx_frame(struct spi_device *spi, u8 *buf,
mdelay(MCP251X_OST_DELAY_MS);
priv->spi_tx_buf[0] = INSTRUCTION_RESET;
- ret = mcp251x_spi_trans(spi, 1);
+ ret = mcp251x_spi_write(spi, 1);
if (ret)
return ret;
u8 len;
int i, j;
- netdev_reset_queue(priv->ndev);
-
/* TEF */
tef_ring = priv->tef;
tef_ring->head = 0;
static int
mcp251xfd_handle_tefif_one(struct mcp251xfd_priv *priv,
- const struct mcp251xfd_hw_tef_obj *hw_tef_obj,
- unsigned int *frame_len_ptr)
+ const struct mcp251xfd_hw_tef_obj *hw_tef_obj)
{
struct net_device_stats *stats = &priv->ndev->stats;
u32 seq, seq_masked, tef_tail_masked;
stats->tx_bytes +=
can_rx_offload_get_echo_skb(&priv->offload,
mcp251xfd_get_tef_tail(priv),
- hw_tef_obj->ts,
- frame_len_ptr);
+ hw_tef_obj->ts, NULL);
stats->tx_packets++;
priv->tef->tail++;
static int mcp251xfd_handle_tefif(struct mcp251xfd_priv *priv)
{
struct mcp251xfd_hw_tef_obj hw_tef_obj[MCP251XFD_TX_OBJ_NUM_MAX];
- unsigned int total_frame_len = 0;
u8 tef_tail, len, l;
int err, i;
}
for (i = 0; i < len; i++) {
- unsigned int frame_len;
-
- err = mcp251xfd_handle_tefif_one(priv, &hw_tef_obj[i], &frame_len);
+ err = mcp251xfd_handle_tefif_one(priv, &hw_tef_obj[i]);
/* -EAGAIN means the Sequence Number in the TEF
* doesn't match our tef_tail. This can happen if we
* read the TEF objects too early. Leave loop let the
goto out_netif_wake_queue;
if (err)
return err;
-
- total_frame_len += frame_len;
}
out_netif_wake_queue:
return err;
tx_ring->tail += len;
- netdev_completed_queue(priv->ndev, len, total_frame_len);
err = mcp251xfd_check_tef_tail(priv);
if (err)
struct mcp251xfd_priv *priv = netdev_priv(ndev);
struct mcp251xfd_tx_ring *tx_ring = priv->tx;
struct mcp251xfd_tx_obj *tx_obj;
- unsigned int frame_len;
u8 tx_head;
int err;
if (mcp251xfd_get_tx_free(tx_ring) == 0)
netif_stop_queue(ndev);
- frame_len = can_skb_get_frame_len(skb);
- can_put_echo_skb(skb, ndev, tx_head, frame_len);
- netdev_sent_queue(priv->ndev, frame_len);
+ can_put_echo_skb(skb, ndev, tx_head, 0);
err = mcp251xfd_tx_obj_write(priv, tx_obj);
if (err)
- Kvaser Memorator Pro 5xHS
- Kvaser USBcan Light 4xHS
- Kvaser USBcan Pro 2xHS v2
+ - Kvaser USBcan Pro 4xHS
- Kvaser USBcan Pro 5xHS
- Kvaser U100
- Kvaser U100P
#define USB_U100_PRODUCT_ID 273
#define USB_U100P_PRODUCT_ID 274
#define USB_U100S_PRODUCT_ID 275
+#define USB_USBCAN_PRO_4HS_PRODUCT_ID 276
#define USB_HYDRA_PRODUCT_ID_END \
- USB_U100S_PRODUCT_ID
+ USB_USBCAN_PRO_4HS_PRODUCT_ID
static inline bool kvaser_is_leaf(const struct usb_device_id *id)
{
{ USB_DEVICE(KVASER_VENDOR_ID, USB_U100_PRODUCT_ID) },
{ USB_DEVICE(KVASER_VENDOR_ID, USB_U100P_PRODUCT_ID) },
{ USB_DEVICE(KVASER_VENDOR_ID, USB_U100S_PRODUCT_ID) },
+ { USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_PRO_4HS_PRODUCT_ID) },
{ }
};
MODULE_DEVICE_TABLE(usb, kvaser_usb_table);
#include "pcan_usb_core.h"
-MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB adapter");
-
/* PCAN-USB Endpoints */
#define PCAN_USB_EP_CMDOUT 1
#define PCAN_USB_EP_CMDIN (PCAN_USB_EP_CMDOUT | USB_DIR_IN)
if (dev->adapter->dev_set_bus) {
err = dev->adapter->dev_set_bus(dev, 0);
if (err)
- goto lbl_unregister_candev;
+ goto adap_dev_free;
}
/* get device number early */
return 0;
+adap_dev_free:
+ if (dev->adapter->dev_free)
+ dev->adapter->dev_free(dev);
+
lbl_unregister_candev:
unregister_candev(netdev);
#include "pcan_usb_core.h"
#include "pcan_usb_pro.h"
-MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB FD adapter");
-MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB Pro FD adapter");
-
#define PCAN_USBPROFD_CHANNEL_COUNT 2
#define PCAN_USBFD_CHANNEL_COUNT 1
#include "pcan_usb_core.h"
#include "pcan_usb_pro.h"
-MODULE_SUPPORTED_DEVICE("PEAK-System PCAN-USB Pro adapter");
-
#define PCAN_USBPRO_CHANNEL_COUNT 2
/* PCAN-USB Pro adapter internal clock (MHz) */
b53_disable_port(ds, port);
}
- /* Let DSA handle the case were multiple bridges span the same switch
- * device and different VLAN awareness settings are requested, which
- * would be breaking filtering semantics for any of the other bridge
- * devices. (not hardware supported)
- */
- ds->vlan_filtering_is_global = true;
-
return b53_setup_devlink_resources(ds);
}
ds->ops = &b53_switch_ops;
ds->untag_bridge_pvid = true;
dev->vlan_enabled = true;
+ /* Let DSA handle the case were multiple bridges span the same switch
+ * device and different VLAN awareness settings are requested, which
+ * would be breaking filtering semantics for any of the other bridge
+ * devices. (not hardware supported)
+ */
+ ds->vlan_filtering_is_global = true;
+
mutex_init(&dev->reg_mutex);
mutex_init(&dev->stats_mutex);
/* Force link status for IMP port */
reg = core_readl(priv, offset);
reg |= (MII_SW_OR | LINK_STS);
- reg &= ~GMII_SPEED_UP_2G;
+ if (priv->type == BCM4908_DEVICE_ID)
+ reg |= GMII_SPEED_UP_2G;
+ else
+ reg &= ~GMII_SPEED_UP_2G;
core_writel(priv, reg, offset);
/* Enable Broadcast, Multicast, Unicast forwarding to IMP port */
/* The watchdog reset does not work on 7278, we need to hit the
* "external" reset line through the reset controller.
*/
- if (priv->type == BCM7278_DEVICE_ID && !IS_ERR(priv->rcdev)) {
+ if (priv->type == BCM7278_DEVICE_ID) {
ret = reset_control_assert(priv->rcdev);
if (ret)
return ret;
* in bits 15:8 and the patch level in bits 7:0 which is exactly what
* the REG_PHY_REVISION register layout is.
*/
-
- return priv->hw_params.gphy_rev;
+ if (priv->int_phy_mask & BIT(port))
+ return priv->hw_params.gphy_rev;
+ else
+ return 0;
}
static void bcm_sf2_sw_validate(struct dsa_switch *ds, int port,
priv->rcdev = devm_reset_control_get_optional_exclusive(&pdev->dev,
"switch");
- if (PTR_ERR(priv->rcdev) == -EPROBE_DEFER)
+ if (IS_ERR(priv->rcdev))
return PTR_ERR(priv->rcdev);
/* Auto-detection using standard registers will not work, so
bcm_sf2_mdio_unregister(priv);
clk_disable_unprepare(priv->clk_mdiv);
clk_disable_unprepare(priv->clk);
- if (priv->type == BCM7278_DEVICE_ID && !IS_ERR(priv->rcdev))
+ if (priv->type == BCM7278_DEVICE_ID)
reset_control_assert(priv->rcdev);
return 0;
/* GSWIP MII Registers */
#define GSWIP_MII_CFGp(p) (0x2 * (p))
+#define GSWIP_MII_CFG_RESET BIT(15)
#define GSWIP_MII_CFG_EN BIT(14)
+#define GSWIP_MII_CFG_ISOLATE BIT(13)
#define GSWIP_MII_CFG_LDCLKDIS BIT(12)
+#define GSWIP_MII_CFG_RGMII_IBS BIT(8)
+#define GSWIP_MII_CFG_RMII_CLK BIT(7)
#define GSWIP_MII_CFG_MODE_MIIP 0x0
#define GSWIP_MII_CFG_MODE_MIIM 0x1
#define GSWIP_MII_CFG_MODE_RMIIP 0x2
#define GSWIP_PCE_DEFPVID(p) (0x486 + ((p) * 0xA))
#define GSWIP_MAC_FLEN 0x8C5
+#define GSWIP_MAC_CTRL_0p(p) (0x903 + ((p) * 0xC))
+#define GSWIP_MAC_CTRL_0_PADEN BIT(8)
+#define GSWIP_MAC_CTRL_0_FCS_EN BIT(7)
+#define GSWIP_MAC_CTRL_0_FCON_MASK 0x0070
+#define GSWIP_MAC_CTRL_0_FCON_AUTO 0x0000
+#define GSWIP_MAC_CTRL_0_FCON_RX 0x0010
+#define GSWIP_MAC_CTRL_0_FCON_TX 0x0020
+#define GSWIP_MAC_CTRL_0_FCON_RXTX 0x0030
+#define GSWIP_MAC_CTRL_0_FCON_NONE 0x0040
+#define GSWIP_MAC_CTRL_0_FDUP_MASK 0x000C
+#define GSWIP_MAC_CTRL_0_FDUP_AUTO 0x0000
+#define GSWIP_MAC_CTRL_0_FDUP_EN 0x0004
+#define GSWIP_MAC_CTRL_0_FDUP_DIS 0x000C
+#define GSWIP_MAC_CTRL_0_GMII_MASK 0x0003
+#define GSWIP_MAC_CTRL_0_GMII_AUTO 0x0000
+#define GSWIP_MAC_CTRL_0_GMII_MII 0x0001
+#define GSWIP_MAC_CTRL_0_GMII_RGMII 0x0002
#define GSWIP_MAC_CTRL_2p(p) (0x905 + ((p) * 0xC))
#define GSWIP_MAC_CTRL_2_MLEN BIT(3) /* Maximum Untagged Frame Lnegth */
GSWIP_SDMA_PCTRLp(port));
if (!dsa_is_cpu_port(ds, port)) {
- u32 macconf = GSWIP_MDIO_PHY_LINK_AUTO |
- GSWIP_MDIO_PHY_SPEED_AUTO |
- GSWIP_MDIO_PHY_FDUP_AUTO |
- GSWIP_MDIO_PHY_FCONTX_AUTO |
- GSWIP_MDIO_PHY_FCONRX_AUTO |
- (phydev->mdio.addr & GSWIP_MDIO_PHY_ADDR_MASK);
-
- gswip_mdio_w(priv, macconf, GSWIP_MDIO_PHYp(port));
- /* Activate MDIO auto polling */
- gswip_mdio_mask(priv, 0, BIT(port), GSWIP_MDIO_MDC_CFG0);
+ u32 mdio_phy = 0;
+
+ if (phydev)
+ mdio_phy = phydev->mdio.addr & GSWIP_MDIO_PHY_ADDR_MASK;
+
+ gswip_mdio_mask(priv, GSWIP_MDIO_PHY_ADDR_MASK, mdio_phy,
+ GSWIP_MDIO_PHYp(port));
}
return 0;
if (!dsa_is_user_port(ds, port))
return;
- if (!dsa_is_cpu_port(ds, port)) {
- gswip_mdio_mask(priv, GSWIP_MDIO_PHY_LINK_DOWN,
- GSWIP_MDIO_PHY_LINK_MASK,
- GSWIP_MDIO_PHYp(port));
- /* Deactivate MDIO auto polling */
- gswip_mdio_mask(priv, BIT(port), 0, GSWIP_MDIO_MDC_CFG0);
- }
-
gswip_switch_mask(priv, GSWIP_FDMA_PCTRL_EN, 0,
GSWIP_FDMA_PCTRLp(port));
gswip_switch_mask(priv, GSWIP_SDMA_PCTRL_EN, 0,
gswip_switch_w(priv, BIT(cpu_port), GSWIP_PCE_PMAP2);
gswip_switch_w(priv, BIT(cpu_port), GSWIP_PCE_PMAP3);
- /* disable PHY auto polling */
+ /* Deactivate MDIO PHY auto polling. Some PHYs as the AR8030 have an
+ * interoperability problem with this auto polling mechanism because
+ * their status registers think that the link is in a different state
+ * than it actually is. For the AR8030 it has the BMSR_ESTATEN bit set
+ * as well as ESTATUS_1000_TFULL and ESTATUS_1000_XFULL. This makes the
+ * auto polling state machine consider the link being negotiated with
+ * 1Gbit/s. Since the PHY itself is a Fast Ethernet RMII PHY this leads
+ * to the switch port being completely dead (RX and TX are both not
+ * working).
+ * Also with various other PHY / port combinations (PHY11G GPHY, PHY22F
+ * GPHY, external RGMII PEF7071/7072) any traffic would stop. Sometimes
+ * it would work fine for a few minutes to hours and then stop, on
+ * other device it would no traffic could be sent or received at all.
+ * Testing shows that when PHY auto polling is disabled these problems
+ * go away.
+ */
gswip_mdio_w(priv, 0x0, GSWIP_MDIO_MDC_CFG0);
+
/* Configure the MDIO Clock 2.5 MHz */
gswip_mdio_mask(priv, 0xff, 0x09, GSWIP_MDIO_MDC_CFG1);
- /* Disable the xMII link */
+ /* Disable the xMII interface and clear it's isolation bit */
for (i = 0; i < priv->hw_info->max_ports; i++)
- gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, i);
+ gswip_mii_mask_cfg(priv,
+ GSWIP_MII_CFG_EN | GSWIP_MII_CFG_ISOLATE,
+ 0, i);
/* enable special tag insertion on cpu port */
gswip_switch_mask(priv, 0, GSWIP_FDMA_PCTRL_STEN,
return;
}
+static void gswip_port_set_link(struct gswip_priv *priv, int port, bool link)
+{
+ u32 mdio_phy;
+
+ if (link)
+ mdio_phy = GSWIP_MDIO_PHY_LINK_UP;
+ else
+ mdio_phy = GSWIP_MDIO_PHY_LINK_DOWN;
+
+ gswip_mdio_mask(priv, GSWIP_MDIO_PHY_LINK_MASK, mdio_phy,
+ GSWIP_MDIO_PHYp(port));
+}
+
+static void gswip_port_set_speed(struct gswip_priv *priv, int port, int speed,
+ phy_interface_t interface)
+{
+ u32 mdio_phy = 0, mii_cfg = 0, mac_ctrl_0 = 0;
+
+ switch (speed) {
+ case SPEED_10:
+ mdio_phy = GSWIP_MDIO_PHY_SPEED_M10;
+
+ if (interface == PHY_INTERFACE_MODE_RMII)
+ mii_cfg = GSWIP_MII_CFG_RATE_M50;
+ else
+ mii_cfg = GSWIP_MII_CFG_RATE_M2P5;
+
+ mac_ctrl_0 = GSWIP_MAC_CTRL_0_GMII_MII;
+ break;
+
+ case SPEED_100:
+ mdio_phy = GSWIP_MDIO_PHY_SPEED_M100;
+
+ if (interface == PHY_INTERFACE_MODE_RMII)
+ mii_cfg = GSWIP_MII_CFG_RATE_M50;
+ else
+ mii_cfg = GSWIP_MII_CFG_RATE_M25;
+
+ mac_ctrl_0 = GSWIP_MAC_CTRL_0_GMII_MII;
+ break;
+
+ case SPEED_1000:
+ mdio_phy = GSWIP_MDIO_PHY_SPEED_G1;
+
+ mii_cfg = GSWIP_MII_CFG_RATE_M125;
+
+ mac_ctrl_0 = GSWIP_MAC_CTRL_0_GMII_RGMII;
+ break;
+ }
+
+ gswip_mdio_mask(priv, GSWIP_MDIO_PHY_SPEED_MASK, mdio_phy,
+ GSWIP_MDIO_PHYp(port));
+ gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_RATE_MASK, mii_cfg, port);
+ gswip_switch_mask(priv, GSWIP_MAC_CTRL_0_GMII_MASK, mac_ctrl_0,
+ GSWIP_MAC_CTRL_0p(port));
+}
+
+static void gswip_port_set_duplex(struct gswip_priv *priv, int port, int duplex)
+{
+ u32 mac_ctrl_0, mdio_phy;
+
+ if (duplex == DUPLEX_FULL) {
+ mac_ctrl_0 = GSWIP_MAC_CTRL_0_FDUP_EN;
+ mdio_phy = GSWIP_MDIO_PHY_FDUP_EN;
+ } else {
+ mac_ctrl_0 = GSWIP_MAC_CTRL_0_FDUP_DIS;
+ mdio_phy = GSWIP_MDIO_PHY_FDUP_DIS;
+ }
+
+ gswip_switch_mask(priv, GSWIP_MAC_CTRL_0_FDUP_MASK, mac_ctrl_0,
+ GSWIP_MAC_CTRL_0p(port));
+ gswip_mdio_mask(priv, GSWIP_MDIO_PHY_FDUP_MASK, mdio_phy,
+ GSWIP_MDIO_PHYp(port));
+}
+
+static void gswip_port_set_pause(struct gswip_priv *priv, int port,
+ bool tx_pause, bool rx_pause)
+{
+ u32 mac_ctrl_0, mdio_phy;
+
+ if (tx_pause && rx_pause) {
+ mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_RXTX;
+ mdio_phy = GSWIP_MDIO_PHY_FCONTX_EN |
+ GSWIP_MDIO_PHY_FCONRX_EN;
+ } else if (tx_pause) {
+ mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_TX;
+ mdio_phy = GSWIP_MDIO_PHY_FCONTX_EN |
+ GSWIP_MDIO_PHY_FCONRX_DIS;
+ } else if (rx_pause) {
+ mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_RX;
+ mdio_phy = GSWIP_MDIO_PHY_FCONTX_DIS |
+ GSWIP_MDIO_PHY_FCONRX_EN;
+ } else {
+ mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_NONE;
+ mdio_phy = GSWIP_MDIO_PHY_FCONTX_DIS |
+ GSWIP_MDIO_PHY_FCONRX_DIS;
+ }
+
+ gswip_switch_mask(priv, GSWIP_MAC_CTRL_0_FCON_MASK,
+ mac_ctrl_0, GSWIP_MAC_CTRL_0p(port));
+ gswip_mdio_mask(priv,
+ GSWIP_MDIO_PHY_FCONTX_MASK |
+ GSWIP_MDIO_PHY_FCONRX_MASK,
+ mdio_phy, GSWIP_MDIO_PHYp(port));
+}
+
static void gswip_phylink_mac_config(struct dsa_switch *ds, int port,
unsigned int mode,
const struct phylink_link_state *state)
break;
case PHY_INTERFACE_MODE_RMII:
miicfg |= GSWIP_MII_CFG_MODE_RMIIM;
+
+ /* Configure the RMII clock as output: */
+ miicfg |= GSWIP_MII_CFG_RMII_CLK;
break;
case PHY_INTERFACE_MODE_RGMII:
case PHY_INTERFACE_MODE_RGMII_ID:
"Unsupported interface: %d\n", state->interface);
return;
}
- gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_MODE_MASK, miicfg, port);
+
+ gswip_mii_mask_cfg(priv,
+ GSWIP_MII_CFG_MODE_MASK | GSWIP_MII_CFG_RMII_CLK |
+ GSWIP_MII_CFG_RGMII_IBS | GSWIP_MII_CFG_LDCLKDIS,
+ miicfg, port);
switch (state->interface) {
case PHY_INTERFACE_MODE_RGMII_ID:
struct gswip_priv *priv = ds->priv;
gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, port);
+
+ if (!dsa_is_cpu_port(ds, port))
+ gswip_port_set_link(priv, port, false);
}
static void gswip_phylink_mac_link_up(struct dsa_switch *ds, int port,
{
struct gswip_priv *priv = ds->priv;
+ if (!dsa_is_cpu_port(ds, port)) {
+ gswip_port_set_link(priv, port, true);
+ gswip_port_set_speed(priv, port, speed, interface);
+ gswip_port_set_duplex(priv, port, duplex);
+ gswip_port_set_pause(priv, port, tx_pause, rx_pause);
+ }
+
gswip_mii_mask_cfg(priv, 0, GSWIP_MII_CFG_EN, port);
}
TD_DM_DRVP(8) | TD_DM_DRVN(8));
/* Setup core clock for MT7530 */
- if (!trgint) {
- /* Disable MT7530 core clock */
- core_clear(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN);
-
- /* Disable PLL, since phy_device has not yet been created
- * provided for phy_[read,write]_mmd_indirect is called, we
- * provide our own core_write_mmd_indirect to complete this
- * function.
- */
- core_write_mmd_indirect(priv,
- CORE_GSWPLL_GRP1,
- MDIO_MMD_VEND2,
- 0);
-
- /* Set core clock into 500Mhz */
- core_write(priv, CORE_GSWPLL_GRP2,
- RG_GSWPLL_POSDIV_500M(1) |
- RG_GSWPLL_FBKDIV_500M(25));
+ /* Disable MT7530 core clock */
+ core_clear(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN);
- /* Enable PLL */
- core_write(priv, CORE_GSWPLL_GRP1,
- RG_GSWPLL_EN_PRE |
- RG_GSWPLL_POSDIV_200M(2) |
- RG_GSWPLL_FBKDIV_200M(32));
-
- /* Enable MT7530 core clock */
- core_set(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN);
- }
+ /* Disable PLL, since phy_device has not yet been created
+ * provided for phy_[read,write]_mmd_indirect is called, we
+ * provide our own core_write_mmd_indirect to complete this
+ * function.
+ */
+ core_write_mmd_indirect(priv,
+ CORE_GSWPLL_GRP1,
+ MDIO_MMD_VEND2,
+ 0);
+
+ /* Set core clock into 500Mhz */
+ core_write(priv, CORE_GSWPLL_GRP2,
+ RG_GSWPLL_POSDIV_500M(1) |
+ RG_GSWPLL_FBKDIV_500M(25));
+
+ /* Enable PLL */
+ core_write(priv, CORE_GSWPLL_GRP1,
+ RG_GSWPLL_EN_PRE |
+ RG_GSWPLL_POSDIV_200M(2) |
+ RG_GSWPLL_FBKDIV_200M(32));
+
+ /* Enable MT7530 core clock */
+ core_set(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN);
/* Setup the MT7530 TRGMII Tx Clock */
core_set(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN);
}
}
+#ifdef CONFIG_GPIOLIB
static inline u32
mt7530_gpio_to_bit(unsigned int offset)
{
return devm_gpiochip_add_data(dev, gc, priv);
}
+#endif /* CONFIG_GPIOLIB */
static int
mt7530_setup(struct dsa_switch *ds)
}
}
+#ifdef CONFIG_GPIOLIB
if (of_property_read_bool(priv->dev->of_node, "gpio-controller")) {
ret = mt7530_setup_gpio(priv);
if (ret)
return ret;
}
+#endif /* CONFIG_GPIOLIB */
mt7530_setup_port5(ds, interface);
return err;
}
+/* prod_id for switch families which do not have a PHY model number */
+static const u16 family_prod_id_table[] = {
+ [MV88E6XXX_FAMILY_6341] = MV88E6XXX_PORT_SWITCH_ID_PROD_6341,
+ [MV88E6XXX_FAMILY_6390] = MV88E6XXX_PORT_SWITCH_ID_PROD_6390,
+};
+
static int mv88e6xxx_mdio_read(struct mii_bus *bus, int phy, int reg)
{
struct mv88e6xxx_mdio_bus *mdio_bus = bus->priv;
struct mv88e6xxx_chip *chip = mdio_bus->chip;
+ u16 prod_id;
u16 val;
int err;
err = chip->info->ops->phy_read(chip, bus, phy, reg, &val);
mv88e6xxx_reg_unlock(chip);
- if (reg == MII_PHYSID2) {
- /* Some internal PHYs don't have a model number. */
- if (chip->info->family != MV88E6XXX_FAMILY_6165)
- /* Then there is the 6165 family. It gets is
- * PHYs correct. But it can also have two
- * SERDES interfaces in the PHY address
- * space. And these don't have a model
- * number. But they are not PHYs, so we don't
- * want to give them something a PHY driver
- * will recognise.
- *
- * Use the mv88e6390 family model number
- * instead, for anything which really could be
- * a PHY,
- */
- if (!(val & 0x3f0))
- val |= MV88E6XXX_PORT_SWITCH_ID_PROD_6390 >> 4;
+ /* Some internal PHYs don't have a model number. */
+ if (reg == MII_PHYSID2 && !(val & 0x3f0) &&
+ chip->info->family < ARRAY_SIZE(family_prod_id_table)) {
+ prod_id = family_prod_id_table[chip->info->family];
+ if (prod_id)
+ val |= prod_id >> 4;
}
return err ? err : val;
speed = SPEED_1000;
else if (bmcr & BMCR_SPEED100)
speed = SPEED_100;
- else if (bmcr & BMCR_SPEED10)
+ else
speed = SPEED_10;
sja1105_sgmii_pcs_force_speed(priv, speed);
if (flags.val & BR_FLOOD)
priv->ucast_egress_floods |= BIT(to);
else
- priv->ucast_egress_floods |= BIT(to);
+ priv->ucast_egress_floods &= ~BIT(to);
}
if (flags.mask & BR_BCAST_FLOOD) {
if (flags.val & BR_BCAST_FLOOD)
priv->bcast_egress_floods |= BIT(to);
else
- priv->bcast_egress_floods |= BIT(to);
+ priv->bcast_egress_floods &= ~BIT(to);
}
return sja1105_manage_flood_domains(priv);
return -EOPNOTSUPP;
dsa_hsr_foreach_port(dp, ds, hsr) {
- partner = dp;
+ if (dp->index != port) {
+ partner = dp;
+ break;
+ }
}
/* We can't enable redundancy on the switch until both
unsigned int val;
dsa_hsr_foreach_port(dp, ds, hsr) {
- partner = dp;
+ if (dp->index != port) {
+ partner = dp;
+ break;
+ }
}
if (!partner)
}
pci_set_master(pdev);
- ioaddr = pci_resource_start(pdev, 0);
- if (!ioaddr) {
+ if (!pci_resource_len(pdev, 0)) {
if (pcnet32_debug & NETIF_MSG_PROBE)
pr_err("card has no PCI IO resources, aborting\n");
err = -ENODEV;
pr_err("architecture does not support 32bit PCI busmaster DMA\n");
goto err_disable_dev;
}
+
+ ioaddr = pci_resource_start(pdev, 0);
if (!request_region(ioaddr, PCNET32_TOTAL_SIZE, "pcnet32_probe_pci")) {
if (pcnet32_debug & NETIF_MSG_PROBE)
pr_err("io address range already allocated\n");
#define XGBE_DMA_SYS_AWCR 0x30303030
/* DMA cache settings - PCI device */
-#define XGBE_DMA_PCI_ARCR 0x00000003
-#define XGBE_DMA_PCI_AWCR 0x13131313
-#define XGBE_DMA_PCI_AWARCR 0x00000313
+#define XGBE_DMA_PCI_ARCR 0x000f0f0f
+#define XGBE_DMA_PCI_AWCR 0x0f0f0f0f
+#define XGBE_DMA_PCI_AWARCR 0x00000f0f
/* DMA channel interrupt modes */
#define XGBE_IRQ_MODE_EDGE 0
if (!netif_running(alx->dev))
return 0;
- netif_device_attach(alx->dev);
rtnl_lock();
err = __alx_open(alx, true);
rtnl_unlock();
+ if (err)
+ return err;
- return err;
+ netif_device_attach(alx->dev);
+
+ return 0;
}
static SIMPLE_DEV_PM_OPS(alx_pm_ops, alx_suspend, alx_resume);
config BCM4908_ENET
tristate "Broadcom BCM4908 internal mac support"
depends on ARCH_BCM4908 || COMPILE_TEST
- default y
+ default y if ARCH_BCM4908
help
This driver supports Ethernet controller integrated into Broadcom
BCM4908 family SoCs.
err_free_buf_descs:
dma_free_coherent(dev, size, ring->cpu_addr, ring->dma_addr);
+ ring->cpu_addr = NULL;
return -ENOMEM;
}
bcm4908_enet_intrs_on(enet);
}
+ /* Hardware could disable ring if it run out of descriptors */
+ bcm4908_enet_dma_rx_ring_enable(enet, &enet->rx_ring);
+
return handled;
}
bp->irq_tbl[0].handler = bnxt_inta;
}
+static int bnxt_init_int_mode(struct bnxt *bp);
+
static int bnxt_setup_int_mode(struct bnxt *bp)
{
int rc;
+ if (!bp->irq_tbl) {
+ rc = bnxt_init_int_mode(bp);
+ if (rc || !bp->irq_tbl)
+ return rc ?: -ENODEV;
+ }
+
if (bp->flags & BNXT_FLAG_USING_MSIX)
bnxt_setup_msix(bp);
else
static int bnxt_init_int_mode(struct bnxt *bp)
{
- int rc = 0;
+ int rc = -ENODEV;
if (bp->flags & BNXT_FLAG_MSIX_CAP)
rc = bnxt_init_msix(bp);
{
struct hwrm_func_drv_if_change_output *resp = bp->hwrm_cmd_resp_addr;
struct hwrm_func_drv_if_change_input req = {0};
- bool resc_reinit = false, fw_reset = false;
+ bool fw_reset = !bp->irq_tbl;
+ bool resc_reinit = false;
int rc, retry = 0;
u32 flags = 0;
if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state) && !fw_reset) {
netdev_err(bp->dev, "RESET_DONE not set during FW reset.\n");
+ set_bit(BNXT_STATE_ABORT_ERR, &bp->state);
return -ENODEV;
}
if (resc_reinit || fw_reset) {
if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
return -EBUSY;
+ if (bp->dev->reg_state == NETREG_UNREGISTERED)
+ return -ENODEV;
+
rc = bnxt_fw_init_one(bp);
if (!rc) {
bnxt_clear_int_mode(bp);
bool cmp_b = false;
bool cmp_c = false;
+ if (!macb_is_gem(bp))
+ return;
+
tp4sp_v = &(fs->h_u.tcp_ip4_spec);
tp4sp_m = &(fs->m_u.tcp_ip4_spec);
{
struct net_device *netdev = bp->dev;
netdev_features_t features = netdev->features;
+ struct ethtool_rx_fs_item *item;
/* TX checksum offload */
macb_set_txcsum_feature(bp, features);
macb_set_rxcsum_feature(bp, features);
/* RX Flow Filters */
+ list_for_each_entry(item, &bp->rx_fs_list.list, list)
+ gem_prog_cmp_regs(bp, &item->fs);
+
macb_set_rxflow_feature(bp, features);
}
reg = gem_readl(bp, DCFG8);
bp->max_tuples = min((GEM_BFEXT(SCR2CMP, reg) / 3),
GEM_BFEXT(T2SCR, reg));
+ INIT_LIST_HEAD(&bp->rx_fs_list.list);
if (bp->max_tuples > 0) {
/* also needs one ethtype match to check IPv4 */
if (GEM_BFEXT(SCR2ETH, reg) > 0) {
/* Filtering is supported in hw but don't enable it in kernel now */
dev->hw_features |= NETIF_F_NTUPLE;
/* init Rx flow definitions */
- INIT_LIST_HEAD(&bp->rx_fs_list.list);
bp->rx_fs_list.count = 0;
spin_lock_init(&bp->rx_fs_lock);
} else
return 0;
}
+static const struct macb_usrio_config macb_default_usrio = {
+ .mii = MACB_BIT(MII),
+ .rmii = MACB_BIT(RMII),
+ .rgmii = GEM_BIT(RGMII),
+ .refclk = MACB_BIT(CLKEN),
+};
+
#if defined(CONFIG_OF)
/* 1518 rounded up */
#define AT91ETHER_MAX_RBUFF_SZ 0x600
return macb_init(pdev);
}
-static const struct macb_usrio_config macb_default_usrio = {
- .mii = MACB_BIT(MII),
- .rmii = MACB_BIT(RMII),
- .rgmii = GEM_BIT(RGMII),
- .refclk = MACB_BIT(CLKEN),
-};
-
static const struct macb_usrio_config sama7g5_usrio = {
.mii = 0,
.rmii = 1,
.dma_burst_length = 16,
.clk_init = macb_clk_init,
.init = macb_init,
+ .usrio = &macb_default_usrio,
.jumbo_max_len = 10240,
};
| CN6XXX_INTR_M0UNWI_ERR \
| CN6XXX_INTR_M1UPB0_ERR \
| CN6XXX_INTR_M1UPWI_ERR \
- | CN6XXX_INTR_M1UPB0_ERR \
+ | CN6XXX_INTR_M1UNB0_ERR \
| CN6XXX_INTR_M1UNWI_ERR \
| CN6XXX_INTR_INSTR_DB_OF_ERR \
| CN6XXX_INTR_SLIST_DB_OF_ERR \
struct cudbg_buffer temp_buff = { 0 };
struct sge_qbase_reg_field *sge_qbase;
struct ireg_buf *ch_sge_dbg;
+ u8 padap_running = 0;
int i, rc;
+ u32 size;
- rc = cudbg_get_buff(pdbg_init, dbg_buff,
- sizeof(*ch_sge_dbg) * 2 + sizeof(*sge_qbase),
- &temp_buff);
+ /* Accessing SGE_QBASE_MAP[0-3] and SGE_QBASE_INDEX regs can
+ * lead to SGE missing doorbells under heavy traffic. So, only
+ * collect them when adapter is idle.
+ */
+ for_each_port(padap, i) {
+ padap_running = netif_running(padap->port[i]);
+ if (padap_running)
+ break;
+ }
+
+ size = sizeof(*ch_sge_dbg) * 2;
+ if (!padap_running)
+ size += sizeof(*sge_qbase);
+
+ rc = cudbg_get_buff(pdbg_init, dbg_buff, size, &temp_buff);
if (rc)
return rc;
ch_sge_dbg++;
}
- if (CHELSIO_CHIP_VERSION(padap->params.chip) > CHELSIO_T5) {
+ if (CHELSIO_CHIP_VERSION(padap->params.chip) > CHELSIO_T5 &&
+ !padap_running) {
sge_qbase = (struct sge_qbase_reg_field *)ch_sge_dbg;
/* 1 addr reg SGE_QBASE_INDEX and 4 data reg
* SGE_QBASE_MAP[0-3]
0x1190, 0x1194,
0x11a0, 0x11a4,
0x11b0, 0x11b4,
- 0x11fc, 0x1274,
+ 0x11fc, 0x123c,
+ 0x1254, 0x1274,
0x1280, 0x133c,
0x1800, 0x18fc,
0x3000, 0x302c,
}
/*
- * chcr_ktls_mark_tcb_close: mark tcb state to CLOSE
- * @tx_info - driver specific tls info.
- * return: NET_TX_OK/NET_XMIT_DROP.
- */
-static int chcr_ktls_mark_tcb_close(struct chcr_ktls_info *tx_info)
-{
- return chcr_set_tcb_field(tx_info, TCB_T_STATE_W,
- TCB_T_STATE_V(TCB_T_STATE_M),
- CHCR_TCB_STATE_CLOSED, 1);
-}
-
-/*
* chcr_ktls_dev_del: call back for tls_dev_del.
* Remove the tid and l2t entry and close the connection.
* it per connection basis.
/* clear tid */
if (tx_info->tid != -1) {
- /* clear tcb state and then release tid */
- chcr_ktls_mark_tcb_close(tx_info);
cxgb4_remove_tid(&tx_info->adap->tids, tx_info->tx_chan,
tx_info->tid, tx_info->ip_family);
}
return 0;
free_tid:
- chcr_ktls_mark_tcb_close(tx_info);
#if IS_ENABLED(CONFIG_IPV6)
/* clear clip entry */
if (tx_info->ip_family == AF_INET6)
if (tx_info->pending_close) {
spin_unlock(&tx_info->lock);
if (!status) {
- /* it's a late success, tcb status is establised,
- * mark it close.
- */
- chcr_ktls_mark_tcb_close(tx_info);
cxgb4_remove_tid(&tx_info->adap->tids, tx_info->tx_chan,
tid, tx_info->ip_family);
}
kvfree(tx_info);
return 0;
}
- tx_info->open_state = false;
+ tx_info->open_state = CH_KTLS_OPEN_SUCCESS;
spin_unlock(&tx_info->lock);
complete(&tx_info->completion);
}
/*
- * chcr_ktls_check_tcp_options: To check if there is any TCP option availbale
+ * chcr_ktls_check_tcp_options: To check if there is any TCP option available
* other than timestamp.
* @skb - skb contains partial record..
* return: 1 / 0
}
if (unlikely(credits < ETHTXQ_STOP_THRES)) {
- /* Credits are below the threshold vaues, stop the queue after
+ /* Credits are below the threshold values, stop the queue after
* injecting the Work Request for this packet.
*/
chcr_eth_txq_stop(q);
}
/*
- * chcr_ktls_update_snd_una: Reset the SEND_UNA. It will be done to avoid
- * sending the same segment again. It will discard the segment which is before
- * the current tx max.
- * @tx_info - driver specific tls info.
- * @q - TX queue.
- * return: NET_TX_OK/NET_XMIT_DROP.
- */
-static int chcr_ktls_update_snd_una(struct chcr_ktls_info *tx_info,
- struct sge_eth_txq *q)
-{
- struct fw_ulptx_wr *wr;
- unsigned int ndesc;
- int credits;
- void *pos;
- u32 len;
-
- len = sizeof(*wr) + roundup(CHCR_SET_TCB_FIELD_LEN, 16);
- ndesc = DIV_ROUND_UP(len, 64);
-
- credits = chcr_txq_avail(&q->q) - ndesc;
- if (unlikely(credits < 0)) {
- chcr_eth_txq_stop(q);
- return NETDEV_TX_BUSY;
- }
-
- pos = &q->q.desc[q->q.pidx];
-
- wr = pos;
- /* ULPTX wr */
- wr->op_to_compl = htonl(FW_WR_OP_V(FW_ULPTX_WR));
- wr->cookie = 0;
- /* fill len in wr field */
- wr->flowid_len16 = htonl(FW_WR_LEN16_V(DIV_ROUND_UP(len, 16)));
-
- pos += sizeof(*wr);
-
- pos = chcr_write_cpl_set_tcb_ulp(tx_info, q, tx_info->tid, pos,
- TCB_SND_UNA_RAW_W,
- TCB_SND_UNA_RAW_V(TCB_SND_UNA_RAW_M),
- TCB_SND_UNA_RAW_V(0), 0);
-
- chcr_txq_advance(&q->q, ndesc);
- cxgb4_ring_tx_db(tx_info->adap, &q->q, ndesc);
-
- return 0;
-}
-
-/*
* chcr_end_part_handler: This handler will handle the record which
* is complete or if record's end part is received. T6 adapter has a issue that
* it can't send out TAG with partial record so if its an end part then we have
struct sge_eth_txq *q, u32 skb_offset,
u32 tls_end_offset, bool last_wr)
{
+ bool free_skb_if_tx_fails = false;
struct sk_buff *nskb = NULL;
+
/* check if it is a complete record */
if (tls_end_offset == record->len) {
nskb = skb;
if (last_wr)
dev_kfree_skb_any(skb);
+ else
+ free_skb_if_tx_fails = true;
last_wr = true;
record->num_frags,
(last_wr && tcp_push_no_fin),
mss)) {
+ if (free_skb_if_tx_fails)
+ dev_kfree_skb_any(skb);
goto out;
}
tx_info->prev_seq = record->end_seq;
/* reset tcp_seq as per the prior_data_required len */
tcp_seq -= prior_data_len;
}
- /* reset snd una, so the middle record won't send the already
- * sent part.
- */
- if (chcr_ktls_update_snd_una(tx_info, q))
- goto out;
atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_middle_pkts);
} else {
atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_start_pkts);
/* TCP segments can be in received either complete or partial.
* chcr_end_part_handler will handle cases if complete record or end
- * part of the record is received. Incase of partial end part of record,
+ * part of the record is received. In case of partial end part of record,
* we will send the complete record again.
*/
+ spin_lock_irqsave(&tx_ctx->base.lock, flags);
+
do {
- int i;
cxgb4_reclaim_completed_tx(adap, &q->q, true);
- /* lock taken */
- spin_lock_irqsave(&tx_ctx->base.lock, flags);
/* fetch the tls record */
record = tls_get_record(&tx_ctx->base, tcp_seq,
&tx_info->record_no);
tls_end_offset, skb_offset,
0);
- spin_unlock_irqrestore(&tx_ctx->base.lock, flags);
if (ret) {
/* free the refcount taken earlier */
if (tls_end_offset < data_len)
dev_kfree_skb_any(skb);
+ spin_unlock_irqrestore(&tx_ctx->base.lock, flags);
goto out;
}
continue;
}
- /* increase page reference count of the record, so that there
- * won't be any chance of page free in middle if in case stack
- * receives ACK and try to delete the record.
- */
- for (i = 0; i < record->num_frags; i++)
- __skb_frag_ref(&record->frags[i]);
- /* lock cleared */
- spin_unlock_irqrestore(&tx_ctx->base.lock, flags);
-
-
/* if a tls record is finishing in this SKB */
if (tls_end_offset <= data_len) {
ret = chcr_end_part_handler(tx_info, skb, record,
data_len = 0;
}
- /* clear the frag ref count which increased locally before */
- for (i = 0; i < record->num_frags; i++) {
- /* clear the frag ref count */
- __skb_frag_unref(&record->frags[i]);
- }
/* if any failure, come out from the loop. */
if (ret) {
+ spin_unlock_irqrestore(&tx_ctx->base.lock, flags);
if (th->fin)
dev_kfree_skb_any(skb);
} while (data_len > 0);
+ spin_unlock_irqrestore(&tx_ctx->base.lock, flags);
atomic64_inc(&port_stats->ktls_tx_encrypted_packets);
atomic64_add(skb_data_len, &port_stats->ktls_tx_encrypted_bytes);
u32 wake_state;
int ip_summed;
+
+ struct regulator *power_supply;
};
/* debug code */
if (ret) {
dev_err(dev, "failed to request reset gpio %d: %d\n",
reset_gpios, ret);
- return -ENODEV;
+ goto out_regulator_disable;
}
/* According to manual PWRST# Low Period Min 1ms */
if (!pdata) {
pdata = dm9000_parse_dt(&pdev->dev);
- if (IS_ERR(pdata))
- return PTR_ERR(pdata);
+ if (IS_ERR(pdata)) {
+ ret = PTR_ERR(pdata);
+ goto out_regulator_disable;
+ }
}
/* Init network device */
ndev = alloc_etherdev(sizeof(struct board_info));
- if (!ndev)
- return -ENOMEM;
+ if (!ndev) {
+ ret = -ENOMEM;
+ goto out_regulator_disable;
+ }
SET_NETDEV_DEV(ndev, &pdev->dev);
db->dev = &pdev->dev;
db->ndev = ndev;
+ if (!IS_ERR(power))
+ db->power_supply = power;
spin_lock_init(&db->lock);
mutex_init(&db->addr_lock);
goto out;
}
- db->irq_wake = platform_get_irq(pdev, 1);
+ db->irq_wake = platform_get_irq_optional(pdev, 1);
if (db->irq_wake >= 0) {
dev_dbg(db->dev, "wakeup irq %d\n", db->irq_wake);
dm9000_release_board(pdev, db);
free_netdev(ndev);
+out_regulator_disable:
+ if (!IS_ERR(power))
+ regulator_disable(power);
+
return ret;
}
dm9000_drv_remove(struct platform_device *pdev)
{
struct net_device *ndev = platform_get_drvdata(pdev);
+ struct board_info *dm = to_dm9000_board(ndev);
unregister_netdev(ndev);
- dm9000_release_board(pdev, netdev_priv(ndev));
+ dm9000_release_board(pdev, dm);
free_netdev(ndev); /* free device structure */
+ if (dm->power_supply)
+ regulator_disable(dm->power_supply);
dev_dbg(&pdev->dev, "released and freed device\n");
return 0;
unsigned long flag;
netif_stop_queue(dev);
- tasklet_disable(&np->tx_tasklet);
+ tasklet_disable_in_atomic(&np->tx_tasklet);
iowrite16(0, ioaddr + IntrEnable);
printk(KERN_WARNING "%s: Transmit timed out, TxStatus %2.2x "
"TxFrameId %2.2x,"
*/
if (unlikely(priv->need_mac_restart)) {
ftgmac100_start_hw(priv);
+ priv->need_mac_restart = false;
/* Re-enable "bad" interrupts */
iowrite32(FTGMAC100_INT_BAD,
int work_done;
int i;
+ enetc_lock_mdio();
+
for (i = 0; i < v->count_tx_rings; i++)
if (!enetc_clean_tx_ring(&v->tx_ring[i], budget))
complete = false;
if (work_done)
v->rx_napi_work = true;
- if (!complete)
+ if (!complete) {
+ enetc_unlock_mdio();
return budget;
+ }
napi_complete_done(napi, work_done);
v->rx_napi_work = false;
- enetc_lock_mdio();
-
/* enable interrupts */
enetc_wr_reg_hot(v->rbier, ENETC_RBIER_RXTIE);
{
u32 lo, hi, tstamp_lo;
- lo = enetc_rd(hw, ENETC_SICTR0);
- hi = enetc_rd(hw, ENETC_SICTR1);
+ lo = enetc_rd_hot(hw, ENETC_SICTR0);
+ hi = enetc_rd_hot(hw, ENETC_SICTR1);
tstamp_lo = le32_to_cpu(txbd->wb.tstamp);
if (lo <= tstamp_lo)
hi -= 1;
if (skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS) {
memset(&shhwtstamps, 0, sizeof(shhwtstamps));
shhwtstamps.hwtstamp = ns_to_ktime(tstamp);
+ /* Ensure skb_mstamp_ns, which might have been populated with
+ * the txtime, is not mistaken for a software timestamp,
+ * because this will prevent the dispatch of our hardware
+ * timestamp to the socket.
+ */
+ skb->tstamp = ktime_set(0, 0);
skb_tstamp_tx(skb, &shhwtstamps);
}
}
i = tx_ring->next_to_clean;
tx_swbd = &tx_ring->tx_swbd[i];
- enetc_lock_mdio();
bds_to_clean = enetc_bd_ready_count(tx_ring, i);
- enetc_unlock_mdio();
do_tstamp = false;
tx_swbd = tx_ring->tx_swbd;
}
- enetc_lock_mdio();
-
/* BD iteration loop end */
if (is_eof) {
tx_frm_cnt++;
if (unlikely(!bds_to_clean))
bds_to_clean = enetc_bd_ready_count(tx_ring, i);
-
- enetc_unlock_mdio();
}
tx_ring->next_to_clean = i;
static void enetc_get_offloads(struct enetc_bdr *rx_ring,
union enetc_rx_bd *rxbd, struct sk_buff *skb)
{
-#ifdef CONFIG_FSL_ENETC_PTP_CLOCK
struct enetc_ndev_priv *priv = netdev_priv(rx_ring->ndev);
-#endif
+
/* TODO: hashing */
if (rx_ring->ndev->features & NETIF_F_RXCSUM) {
u16 inet_csum = le16_to_cpu(rxbd->r.inet_csum);
skb->ip_summed = CHECKSUM_COMPLETE;
}
- /* copy VLAN to skb, if one is extracted, for now we assume it's a
- * standard TPID, but HW also supports custom values
- */
- if (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_VLAN)
- __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
- le16_to_cpu(rxbd->r.vlan_opt));
+ if (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_VLAN) {
+ __be16 tpid = 0;
+
+ switch (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_TPID) {
+ case 0:
+ tpid = htons(ETH_P_8021Q);
+ break;
+ case 1:
+ tpid = htons(ETH_P_8021AD);
+ break;
+ case 2:
+ tpid = htons(enetc_port_rd(&priv->si->hw,
+ ENETC_PCVLANR1));
+ break;
+ case 3:
+ tpid = htons(enetc_port_rd(&priv->si->hw,
+ ENETC_PCVLANR2));
+ break;
+ default:
+ break;
+ }
+
+ __vlan_hwaccel_put_tag(skb, tpid, le16_to_cpu(rxbd->r.vlan_opt));
+ }
+
#ifdef CONFIG_FSL_ENETC_PTP_CLOCK
if (priv->active_offloads & ENETC_F_RX_TSTAMP)
enetc_get_rx_tstamp(rx_ring->ndev, rxbd, skb);
u32 bd_status;
u16 size;
- enetc_lock_mdio();
-
if (cleaned_cnt >= ENETC_RXBD_BUNDLE) {
int count = enetc_refill_rx_ring(rx_ring, cleaned_cnt);
rxbd = enetc_rxbd(rx_ring, i);
bd_status = le32_to_cpu(rxbd->r.lstatus);
- if (!bd_status) {
- enetc_unlock_mdio();
+ if (!bd_status)
break;
- }
enetc_wr_reg_hot(rx_ring->idr, BIT(rx_ring->index));
dma_rmb(); /* for reading other rxbd fields */
size = le16_to_cpu(rxbd->r.buf_len);
skb = enetc_map_rx_buff_to_skb(rx_ring, i, size);
- if (!skb) {
- enetc_unlock_mdio();
+ if (!skb)
break;
- }
enetc_get_offloads(rx_ring, rxbd, skb);
if (unlikely(bd_status &
ENETC_RXBD_LSTATUS(ENETC_RXBD_ERR_MASK))) {
- enetc_unlock_mdio();
dev_kfree_skb(skb);
while (!(bd_status & ENETC_RXBD_LSTATUS_F)) {
dma_rmb();
enetc_process_skb(rx_ring, skb);
- enetc_unlock_mdio();
-
napi_gro_receive(napi, skb);
rx_frm_cnt++;
enetc_free_tx_ring(priv->tx_ring[i]);
}
-static int enetc_alloc_cbdr(struct device *dev, struct enetc_cbdr *cbdr)
+int enetc_alloc_cbdr(struct device *dev, struct enetc_cbdr *cbdr)
{
int size = cbdr->bd_count * sizeof(struct enetc_cbd);
return 0;
}
-static void enetc_free_cbdr(struct device *dev, struct enetc_cbdr *cbdr)
+void enetc_free_cbdr(struct device *dev, struct enetc_cbdr *cbdr)
{
int size = cbdr->bd_count * sizeof(struct enetc_cbd);
cbdr->bd_base = NULL;
}
-static void enetc_setup_cbdr(struct enetc_hw *hw, struct enetc_cbdr *cbdr)
+void enetc_setup_cbdr(struct enetc_hw *hw, struct enetc_cbdr *cbdr)
{
/* set CBDR cache attributes */
enetc_wr(hw, ENETC_SICAR2,
cbdr->cir = hw->reg + ENETC_SICBDRCIR;
}
-static void enetc_clear_cbdr(struct enetc_hw *hw)
+void enetc_clear_cbdr(struct enetc_hw *hw)
{
enetc_wr(hw, ENETC_SICBDRMR, 0);
}
return 0;
}
-static int enetc_configure_si(struct enetc_ndev_priv *priv)
+int enetc_configure_si(struct enetc_ndev_priv *priv)
{
struct enetc_si *si = priv->si;
struct enetc_hw *hw = &si->hw;
int err;
- enetc_setup_cbdr(hw, &si->cbd_ring);
/* set SI cache attributes */
enetc_wr(hw, ENETC_SICAR0,
ENETC_SICAR_RD_COHERENT | ENETC_SICAR_WR_COHERENT);
if (err)
return err;
+ enetc_setup_cbdr(&si->hw, &si->cbd_ring);
+
priv->cls_rules = kcalloc(si->num_fs_entries, sizeof(*priv->cls_rules),
GFP_KERNEL);
if (!priv->cls_rules) {
goto err_alloc_cls;
}
- err = enetc_configure_si(priv);
- if (err)
- goto err_config_si;
-
return 0;
-err_config_si:
- kfree(priv->cls_rules);
err_alloc_cls:
enetc_clear_cbdr(&si->hw);
enetc_free_cbdr(priv->dev, &si->cbd_ring);
rx_ring->idr = hw->reg + ENETC_SIRXIDR;
enetc_refill_rx_ring(rx_ring, enetc_bd_unused(rx_ring));
- enetc_wr(hw, ENETC_SIRXIDR, rx_ring->next_to_use);
+ /* update ENETC's consumer index */
+ enetc_rxbdr_wr(hw, idx, ENETC_RBCIR, rx_ring->next_to_use);
/* enable ring */
enetc_rxbdr_wr(hw, idx, ENETC_RBMR, rbmr);
void enetc_init_si_rings_params(struct enetc_ndev_priv *priv);
int enetc_alloc_si_resources(struct enetc_ndev_priv *priv);
void enetc_free_si_resources(struct enetc_ndev_priv *priv);
+int enetc_configure_si(struct enetc_ndev_priv *priv);
int enetc_open(struct net_device *ndev);
int enetc_close(struct net_device *ndev);
void enetc_set_ethtool_ops(struct net_device *ndev);
/* control buffer descriptor ring (CBDR) */
+int enetc_alloc_cbdr(struct device *dev, struct enetc_cbdr *cbdr);
+void enetc_free_cbdr(struct device *dev, struct enetc_cbdr *cbdr);
+void enetc_setup_cbdr(struct enetc_hw *hw, struct enetc_cbdr *cbdr);
+void enetc_clear_cbdr(struct enetc_hw *hw);
int enetc_set_mac_flt_entry(struct enetc_si *si, int index,
char *mac_addr, int si_map);
int enetc_clear_mac_flt_entry(struct enetc_si *si, int index);
#define ENETC_PSIPMAR0(n) (0x0100 + (n) * 0x8) /* n = SI index */
#define ENETC_PSIPMAR1(n) (0x0104 + (n) * 0x8)
#define ENETC_PVCLCTR 0x0208
+#define ENETC_PCVLANR1 0x0210
+#define ENETC_PCVLANR2 0x0214
#define ENETC_VLAN_TYPE_C BIT(0)
#define ENETC_VLAN_TYPE_S BIT(1)
#define ENETC_PVCLCTR_OVTPIDL(bmp) ((bmp) & 0xff) /* VLAN_TYPE */
#define ENETC_PM0_MAXFRM 0x8014
#define ENETC_SET_TX_MTU(val) ((val) << 16)
#define ENETC_SET_MAXFRM(val) ((val) & 0xffff)
+#define ENETC_PM0_RX_FIFO 0x801c
+#define ENETC_PM0_RX_FIFO_VAL 1
#define ENETC_PM_IMDIO_BASE 0x8030
#define ENETC_PM0_IF_MODE 0x8300
-#define ENETC_PMO_IFM_RG BIT(2)
+#define ENETC_PM0_IFM_RG BIT(2)
#define ENETC_PM0_IFM_RLP (BIT(5) | BIT(11))
-#define ENETC_PM0_IFM_RGAUTO (BIT(15) | ENETC_PMO_IFM_RG | BIT(1))
-#define ENETC_PM0_IFM_XGMII BIT(12)
+#define ENETC_PM0_IFM_EN_AUTO BIT(15)
+#define ENETC_PM0_IFM_SSP_MASK GENMASK(14, 13)
+#define ENETC_PM0_IFM_SSP_1000 (2 << 13)
+#define ENETC_PM0_IFM_SSP_100 (0 << 13)
+#define ENETC_PM0_IFM_SSP_10 (1 << 13)
+#define ENETC_PM0_IFM_FULL_DPX BIT(12)
+#define ENETC_PM0_IFM_IFMODE_MASK GENMASK(1, 0)
+#define ENETC_PM0_IFM_IFMODE_XGMII 0
+#define ENETC_PM0_IFM_IFMODE_GMII 2
#define ENETC_PSIDCAPR 0x1b08
#define ENETC_PSIDCAPR_MSK GENMASK(15, 0)
#define ENETC_PSFCAPR 0x1b18
#define enetc_wr_reg(reg, val) _enetc_wr_reg_wa((reg), (val))
#define enetc_rd(hw, off) enetc_rd_reg((hw)->reg + (off))
#define enetc_wr(hw, off, val) enetc_wr_reg((hw)->reg + (off), val)
+#define enetc_rd_hot(hw, off) enetc_rd_reg_hot((hw)->reg + (off))
+#define enetc_wr_hot(hw, off, val) enetc_wr_reg_hot((hw)->reg + (off), val)
#define enetc_rd64(hw, off) _enetc_rd_reg64_wa((hw)->reg + (off))
/* port register accessors - PF only */
#define enetc_port_rd(hw, off) enetc_rd_reg((hw)->port + (off))
#define ENETC_RXBD_LSTATUS(flags) ((flags) << 16)
#define ENETC_RXBD_FLAG_VLAN BIT(9)
#define ENETC_RXBD_FLAG_TSTMP BIT(10)
+#define ENETC_RXBD_FLAG_TPID GENMASK(1, 0)
#define ENETC_MAC_ADDR_FILT_CNT 8 /* # of supported entries per port */
#define EMETC_MAC_ADDR_FILT_RES 3 /* # of reserved entries at the beginning */
{
struct enetc_ndev_priv *priv = netdev_priv(ndev);
struct enetc_pf *pf = enetc_si_priv(priv->si);
- char vlan_promisc_simap = pf->vlan_promisc_simap;
struct enetc_hw *hw = &priv->si->hw;
bool uprom = false, mprom = false;
struct enetc_mac_filter *filter;
psipmr = ENETC_PSIPMR_SET_UP(0) | ENETC_PSIPMR_SET_MP(0);
uprom = true;
mprom = true;
- /* Enable VLAN promiscuous mode for SI0 (PF) */
- vlan_promisc_simap |= BIT(0);
} else if (ndev->flags & IFF_ALLMULTI) {
/* enable multi cast promisc mode for SI0 (PF) */
psipmr = ENETC_PSIPMR_SET_MP(0);
mprom = true;
}
- enetc_set_vlan_promisc(&pf->si->hw, vlan_promisc_simap);
-
/* first 2 filter entries belong to PF */
if (!uprom) {
/* Update unicast filters */
u32 reg;
reg = enetc_port_rd(hw, ENETC_PM0_IF_MODE);
- if (reg & ENETC_PMO_IFM_RG) {
+ if (reg & ENETC_PM0_IFM_RG) {
/* RGMII mode */
reg = (reg & ~ENETC_PM0_IFM_RLP) |
(en ? ENETC_PM0_IFM_RLP : 0);
enetc_port_wr(hw, ENETC_PM1_CMD_CFG, ENETC_PM0_CMD_PHY_TX_EN |
ENETC_PM0_CMD_TXP | ENETC_PM0_PROMISC);
+
+ /* On LS1028A, the MAC RX FIFO defaults to 2, which is too high
+ * and may lead to RX lock-up under traffic. Set it to 1 instead,
+ * as recommended by the hardware team.
+ */
+ enetc_port_wr(hw, ENETC_PM0_RX_FIFO, ENETC_PM0_RX_FIFO_VAL);
}
static void enetc_mac_config(struct enetc_hw *hw, phy_interface_t phy_mode)
{
- /* set auto-speed for RGMII */
- if (enetc_port_rd(hw, ENETC_PM0_IF_MODE) & ENETC_PMO_IFM_RG ||
- phy_interface_mode_is_rgmii(phy_mode))
- enetc_port_wr(hw, ENETC_PM0_IF_MODE, ENETC_PM0_IFM_RGAUTO);
+ u32 val;
+
+ if (phy_interface_mode_is_rgmii(phy_mode)) {
+ val = enetc_port_rd(hw, ENETC_PM0_IF_MODE);
+ val &= ~ENETC_PM0_IFM_EN_AUTO;
+ val &= ENETC_PM0_IFM_IFMODE_MASK;
+ val |= ENETC_PM0_IFM_IFMODE_GMII | ENETC_PM0_IFM_RG;
+ enetc_port_wr(hw, ENETC_PM0_IF_MODE, val);
+ }
- if (phy_mode == PHY_INTERFACE_MODE_USXGMII)
- enetc_port_wr(hw, ENETC_PM0_IF_MODE, ENETC_PM0_IFM_XGMII);
+ if (phy_mode == PHY_INTERFACE_MODE_USXGMII) {
+ val = ENETC_PM0_IFM_FULL_DPX | ENETC_PM0_IFM_IFMODE_XGMII;
+ enetc_port_wr(hw, ENETC_PM0_IF_MODE, val);
+ }
}
static void enetc_mac_enable(struct enetc_hw *hw, bool en)
phylink_set_pcs(priv->phylink, &pf->pcs->pcs);
}
+static void enetc_force_rgmii_mac(struct enetc_hw *hw, int speed, int duplex)
+{
+ u32 old_val, val;
+
+ old_val = val = enetc_port_rd(hw, ENETC_PM0_IF_MODE);
+
+ if (speed == SPEED_1000) {
+ val &= ~ENETC_PM0_IFM_SSP_MASK;
+ val |= ENETC_PM0_IFM_SSP_1000;
+ } else if (speed == SPEED_100) {
+ val &= ~ENETC_PM0_IFM_SSP_MASK;
+ val |= ENETC_PM0_IFM_SSP_100;
+ } else if (speed == SPEED_10) {
+ val &= ~ENETC_PM0_IFM_SSP_MASK;
+ val |= ENETC_PM0_IFM_SSP_10;
+ }
+
+ if (duplex == DUPLEX_FULL)
+ val |= ENETC_PM0_IFM_FULL_DPX;
+ else
+ val &= ~ENETC_PM0_IFM_FULL_DPX;
+
+ if (val == old_val)
+ return;
+
+ enetc_port_wr(hw, ENETC_PM0_IF_MODE, val);
+}
+
static void enetc_pl_mac_link_up(struct phylink_config *config,
struct phy_device *phy, unsigned int mode,
phy_interface_t interface, int speed,
if (priv->active_offloads & ENETC_F_QBV)
enetc_sched_speed_set(priv, speed);
+ if (!phylink_autoneg_inband(mode) &&
+ phy_interface_mode_is_rgmii(interface))
+ enetc_force_rgmii_mac(&pf->si->hw, speed, duplex);
+
enetc_mac_enable(&pf->si->hw, true);
}
return err;
}
+static void enetc_init_unused_port(struct enetc_si *si)
+{
+ struct device *dev = &si->pdev->dev;
+ struct enetc_hw *hw = &si->hw;
+ int err;
+
+ si->cbd_ring.bd_count = ENETC_CBDR_DEFAULT_SIZE;
+ err = enetc_alloc_cbdr(dev, &si->cbd_ring);
+ if (err)
+ return;
+
+ enetc_setup_cbdr(hw, &si->cbd_ring);
+
+ enetc_init_port_rfs_memory(si);
+ enetc_init_port_rss_memory(si);
+
+ enetc_clear_cbdr(hw);
+ enetc_free_cbdr(dev, &si->cbd_ring);
+}
+
static int enetc_pf_probe(struct pci_dev *pdev,
const struct pci_device_id *ent)
{
struct enetc_pf *pf;
int err;
- if (node && !of_device_is_available(node)) {
- dev_info(&pdev->dev, "device is disabled, skipping\n");
- return -ENODEV;
- }
-
err = enetc_pci_probe(pdev, KBUILD_MODNAME, sizeof(*pf));
if (err) {
dev_err(&pdev->dev, "PCI probing failed\n");
goto err_map_pf_space;
}
+ if (node && !of_device_is_available(node)) {
+ enetc_init_unused_port(si);
+ dev_info(&pdev->dev, "device is disabled, skipping\n");
+ err = -ENODEV;
+ goto err_device_disabled;
+ }
+
pf = enetc_si_priv(si);
pf->si = si;
pf->total_vfs = pci_sriov_get_totalvfs(pdev);
goto err_init_port_rss;
}
+ err = enetc_configure_si(priv);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to configure SI\n");
+ goto err_config_si;
+ }
+
err = enetc_alloc_msix(priv);
if (err) {
dev_err(&pdev->dev, "MSIX alloc failed\n");
enetc_mdiobus_destroy(pf);
err_mdiobus_create:
enetc_free_msix(priv);
+err_config_si:
err_init_port_rss:
err_init_port_rfs:
err_alloc_msix:
si->ndev = NULL;
free_netdev(ndev);
err_alloc_netdev:
+err_device_disabled:
err_map_pf_space:
enetc_pci_remove(pdev);
goto err_alloc_si_res;
}
+ err = enetc_configure_si(priv);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to configure SI\n");
+ goto err_config_si;
+ }
+
err = enetc_alloc_msix(priv);
if (err) {
dev_err(&pdev->dev, "MSIX alloc failed\n");
err_reg_netdev:
enetc_free_msix(priv);
+err_config_si:
err_alloc_msix:
enetc_free_si_resources(priv);
err_alloc_si_res:
u64 ns;
unsigned long flags;
+ mutex_lock(&adapter->ptp_clk_mutex);
+ /* Check the ptp clock */
+ if (!adapter->ptp_clk_on) {
+ mutex_unlock(&adapter->ptp_clk_mutex);
+ return -EINVAL;
+ }
spin_lock_irqsave(&adapter->tmreg_lock, flags);
ns = timecounter_read(&adapter->tc);
spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
+ mutex_unlock(&adapter->ptp_clk_mutex);
*ts = ns_to_timespec64(ns);
static int gfar_set_mac_addr(struct net_device *dev, void *p)
{
- eth_mac_addr(dev, p);
+ int ret;
+
+ ret = eth_mac_addr(dev, p);
+ if (ret)
+ return ret;
gfar_set_mac_for_addr(dev, 0, dev->dev_addr);
if (lstatus & BD_LFLAG(RXBD_LAST))
size -= skb->len;
+ WARN(size < 0, "gianfar: rx fragment size underflow");
+ if (size < 0)
+ return false;
+
skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
rxb->page_offset + RXBUF_ALIGNMENT,
size, GFAR_RXB_TRUESIZE);
if (lstatus & BD_LFLAG(RXBD_EMPTY))
break;
+ /* lost RXBD_LAST descriptor due to overrun */
+ if (skb &&
+ (lstatus & BD_LFLAG(RXBD_FIRST))) {
+ /* discard faulty buffer */
+ dev_kfree_skb(skb);
+ skb = NULL;
+ rx_queue->stats.rx_dropped++;
+
+ /* can continue normally */
+ }
+
/* order rx buffer descriptor reads */
rmb();
for (j = 0; j < fetch_num; j++) {
/* alloc one skb and init */
skb = hns_assemble_skb(ndev);
- if (!skb)
+ if (!skb) {
+ ret = -ENOMEM;
goto out;
+ }
rd = &tx_ring_data(priv, skb->queue_mapping);
hns_nic_net_xmit_hw(ndev, skb, rd);
#define HCLGE_FD_AD_DROP_B 0
#define HCLGE_FD_AD_DIRECT_QID_B 1
#define HCLGE_FD_AD_QID_S 2
-#define HCLGE_FD_AD_QID_M GENMASK(12, 2)
+#define HCLGE_FD_AD_QID_M GENMASK(11, 2)
#define HCLGE_FD_AD_USE_COUNTER_B 12
#define HCLGE_FD_AD_COUNTER_NUM_S 13
#define HCLGE_FD_AD_COUNTER_NUM_M GENMASK(20, 13)
#define HCLGE_FD_AD_NXT_STEP_B 20
#define HCLGE_FD_AD_NXT_KEY_S 21
-#define HCLGE_FD_AD_NXT_KEY_M GENMASK(26, 21)
+#define HCLGE_FD_AD_NXT_KEY_M GENMASK(25, 21)
#define HCLGE_FD_AD_WR_RULE_ID_B 0
#define HCLGE_FD_AD_RULE_ID_S 1
-#define HCLGE_FD_AD_RULE_ID_M GENMASK(13, 1)
+#define HCLGE_FD_AD_RULE_ID_M GENMASK(12, 1)
#define HCLGE_FD_AD_TC_OVRD_B 16
#define HCLGE_FD_AD_TC_SIZE_S 17
#define HCLGE_FD_AD_TC_SIZE_M GENMASK(20, 17)
* normalcy is to reset.
* 2. A new reset request from the stack due to timeout
*
- * For the first case,error event might not have ae handle available.
* check if this is a new reset request and we are not here just because
* last reset attempt did not succeed and watchdog hit us again. We will
* know this if last reset request did not occur very recently (watchdog
* want to make sure we throttle the reset request. Therefore, we will
* not allow it again before 3*HZ times.
*/
- if (!handle)
- handle = &hdev->vport[0].nic;
if (time_before(jiffies, (hdev->last_reset_time +
HCLGE_RESET_INTERVAL))) {
mod_timer(&hdev->reset_timer, jiffies + HCLGE_RESET_INTERVAL);
return;
- } else if (hdev->default_reset_request) {
+ }
+
+ if (hdev->default_reset_request) {
hdev->reset_level =
hclge_get_reset_level(ae_dev,
&hdev->default_reset_request);
case BIT(INNER_SRC_MAC):
for (i = 0; i < ETH_ALEN; i++) {
calc_x(key_x[ETH_ALEN - 1 - i], rule->tuples.src_mac[i],
- rule->tuples.src_mac[i]);
+ rule->tuples_mask.src_mac[i]);
calc_y(key_y[ETH_ALEN - 1 - i], rule->tuples.src_mac[i],
- rule->tuples.src_mac[i]);
+ rule->tuples_mask.src_mac[i]);
}
return true;
fs->h_ext.vlan_tci = cpu_to_be16(rule->tuples.vlan_tag1);
fs->m_ext.vlan_tci =
rule->unused_tuple & BIT(INNER_VLAN_TAG_FST) ?
- cpu_to_be16(VLAN_VID_MASK) :
- cpu_to_be16(rule->tuples_mask.vlan_tag1);
+ 0 : cpu_to_be16(rule->tuples_mask.vlan_tag1);
}
if (fs->flow_type & FLOW_MAC_EXT) {
if (ret)
return ret;
- /* RSS indirection table has been configuared by user */
+ /* RSS indirection table has been configured by user */
if (rxfh_configured)
goto out;
if (test_and_clear_bit(HCLGEVF_RESET_PENDING,
&hdev->reset_state)) {
- /* PF has initmated that it is about to reset the hardware.
+ /* PF has intimated that it is about to reset the hardware.
* We now have to poll & check if hardware has actually
* completed the reset sequence. On hardware reset completion,
* VF needs to reset the client and ae device.
{
struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+ clear_bit(HCLGEVF_STATE_DOWN, &hdev->state);
+
hclgevf_reset_tqp_stats(handle);
hclgevf_request_link_info(hdev);
hclgevf_update_link_mode(hdev);
- clear_bit(HCLGEVF_STATE_DOWN, &hdev->state);
-
return 0;
}
if (ret)
return ret;
- /* RSS indirection table has been configuared by user */
+ /* RSS indirection table has been configured by user */
if (rxfh_configured)
goto out;
return 0;
}
-static int ibmveth_remove(struct vio_dev *dev)
+static void ibmveth_remove(struct vio_dev *dev)
{
struct net_device *netdev = dev_get_drvdata(&dev->dev);
struct ibmveth_adapter *adapter = netdev_priv(netdev);
free_netdev(netdev);
dev_set_drvdata(&dev->dev, NULL);
-
- return 0;
}
static struct attribute veth_active_attr;
MODULE_VERSION(IBMVNIC_DRIVER_VERSION);
static int ibmvnic_version = IBMVNIC_INITIAL_VERSION;
-static int ibmvnic_remove(struct vio_dev *);
static void release_sub_crqs(struct ibmvnic_adapter *, bool);
static int ibmvnic_reset_crq(struct ibmvnic_adapter *);
static int ibmvnic_send_crq_init(struct ibmvnic_adapter *);
rc = set_link_state(adapter, IBMVNIC_LOGICAL_LNK_UP);
if (rc) {
- for (i = 0; i < adapter->req_rx_queues; i++)
- napi_disable(&adapter->napi[i]);
+ ibmvnic_napi_disable(adapter);
release_resources(adapter);
return rc;
}
netif_tx_start_all_queues(netdev);
- if (prev_state == VNIC_CLOSED) {
- for (i = 0; i < adapter->req_rx_queues; i++)
- napi_schedule(&adapter->napi[i]);
- }
-
adapter->state = VNIC_OPEN;
return rc;
}
if (!is_valid_ether_addr(addr->sa_data))
return -EADDRNOTAVAIL;
- if (adapter->state != VNIC_PROBED) {
- ether_addr_copy(adapter->mac_addr, addr->sa_data);
+ ether_addr_copy(adapter->mac_addr, addr->sa_data);
+ if (adapter->state != VNIC_PROBED)
rc = __ibmvnic_set_mac(netdev, addr->sa_data);
- }
return rc;
}
u64 old_num_rx_queues, old_num_tx_queues;
u64 old_num_rx_slots, old_num_tx_slots;
struct net_device *netdev = adapter->netdev;
- int i, rc;
+ int rc;
netdev_dbg(adapter->netdev,
"[S:%d FOP:%d] Reset reason %d, reset_state %d\n",
/* refresh device's multicast list */
ibmvnic_set_multi(netdev);
- /* kick napi */
- for (i = 0; i < adapter->req_rx_queues; i++)
- napi_schedule(&adapter->napi[i]);
-
if (adapter->reset_reason == VNIC_RESET_FAILOVER ||
adapter->reset_reason == VNIC_RESET_MOBILITY)
__netdev_notify_peers(netdev);
next = ibmvnic_next_scrq(adapter, scrq);
for (i = 0; i < next->tx_comp.num_comps; i++) {
- if (next->tx_comp.rcs[i])
- dev_err(dev, "tx error %x\n",
- next->tx_comp.rcs[i]);
index = be32_to_cpu(next->tx_comp.correlators[i]);
if (index & IBMVNIC_TSO_POOL_MASK) {
tx_pool = &adapter->tso_pool[pool];
num_entries += txbuff->num_entries;
if (txbuff->skb) {
total_bytes += txbuff->skb->len;
- dev_consume_skb_irq(txbuff->skb);
+ if (next->tx_comp.rcs[i]) {
+ dev_err(dev, "tx error %x\n",
+ next->tx_comp.rcs[i]);
+ dev_kfree_skb_irq(txbuff->skb);
+ } else {
+ dev_consume_skb_irq(txbuff->skb);
+ }
txbuff->skb = NULL;
} else {
netdev_warn(adapter->netdev,
{
struct device *dev = &adapter->vdev->dev;
unsigned long timeout = msecs_to_jiffies(20000);
- u64 old_num_rx_queues, old_num_tx_queues;
+ u64 old_num_rx_queues = adapter->req_rx_queues;
+ u64 old_num_tx_queues = adapter->req_tx_queues;
int rc;
adapter->from_passive_init = false;
- if (reset) {
- old_num_rx_queues = adapter->req_rx_queues;
- old_num_tx_queues = adapter->req_tx_queues;
+ if (reset)
reinit_completion(&adapter->init_done);
- }
adapter->init_done_rc = 0;
rc = ibmvnic_send_crq_init(adapter);
return rc;
}
-static int ibmvnic_remove(struct vio_dev *dev)
+static void ibmvnic_remove(struct vio_dev *dev)
{
struct net_device *netdev = dev_get_drvdata(&dev->dev);
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
* after setting state, so __ibmvnic_reset() which is called
* from the flush_work() below, can make progress.
*/
- spin_lock_irqsave(&adapter->rwi_lock, flags);
+ spin_lock(&adapter->rwi_lock);
adapter->state = VNIC_REMOVING;
- spin_unlock_irqrestore(&adapter->rwi_lock, flags);
+ spin_unlock(&adapter->rwi_lock);
spin_unlock_irqrestore(&adapter->state_lock, flags);
device_remove_file(&dev->dev, &dev_attr_failover);
free_netdev(netdev);
dev_set_drvdata(&dev->dev, NULL);
-
- return 0;
}
static ssize_t failover_store(struct device *dev, struct device_attribute *attr,
} else {
data &= ~IGP02E1000_PM_D0_LPLU;
ret_val = e1e_wphy(hw, IGP02E1000_PHY_POWER_MGMT, data);
+ if (ret_val)
+ return ret_val;
/* LPLU and SmartSpeed are mutually exclusive. LPLU is used
* during Dx states where the power conservation is most
* important. During driver activity we should enable
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright(c) 1999 - 2018 Intel Corporation. */
-#ifndef _E1000_HW_H_
-#define _E1000_HW_H_
+#ifndef _E1000E_HW_H_
+#define _E1000E_HW_H_
#include "regs.h"
#include "defines.h"
#include "80003es2lan.h"
#include "ich8lan.h"
-#endif
+#endif /* _E1000E_HW_H_ */
struct e1000_adapter *adapter;
adapter = container_of(work, struct e1000_adapter, reset_task);
+ rtnl_lock();
/* don't run the task if already down */
- if (test_bit(__E1000_DOWN, &adapter->state))
+ if (test_bit(__E1000_DOWN, &adapter->state)) {
+ rtnl_unlock();
return;
+ }
if (!(adapter->flags & FLAG_RESTART_NOW)) {
e1000e_dump(adapter);
e_err("Reset adapter unexpectedly\n");
}
e1000e_reinit_locked(adapter);
+ rtnl_unlock();
}
/**
__I40E_VIRTCHNL_OP_PENDING,
__I40E_RECOVERY_MODE,
__I40E_VF_RESETS_DISABLED, /* disable resets during i40e_remove */
+ __I40E_VFS_RELEASING,
/* This must be last as it determines the size of the BITMAP */
__I40E_STATE_SIZE__,
};
case RING_TYPE_XDP:
ring = kmemdup(vsi->xdp_rings[ring_id], sizeof(*ring), GFP_KERNEL);
break;
+ default:
+ ring = NULL;
+ break;
}
if (!ring)
return;
I40E_STAT(struct i40e_vsi, _name, _stat)
#define I40E_VEB_STAT(_name, _stat) \
I40E_STAT(struct i40e_veb, _name, _stat)
+#define I40E_VEB_TC_STAT(_name, _stat) \
+ I40E_STAT(struct i40e_cp_veb_tc_stats, _name, _stat)
#define I40E_PFC_STAT(_name, _stat) \
I40E_STAT(struct i40e_pfc_stats, _name, _stat)
#define I40E_QUEUE_STAT(_name, _stat) \
I40E_VEB_STAT("veb.rx_unknown_protocol", stats.rx_unknown_protocol),
};
+struct i40e_cp_veb_tc_stats {
+ u64 tc_rx_packets;
+ u64 tc_rx_bytes;
+ u64 tc_tx_packets;
+ u64 tc_tx_bytes;
+};
+
static const struct i40e_stats i40e_gstrings_veb_tc_stats[] = {
- I40E_VEB_STAT("veb.tc_%u_tx_packets", tc_stats.tc_tx_packets),
- I40E_VEB_STAT("veb.tc_%u_tx_bytes", tc_stats.tc_tx_bytes),
- I40E_VEB_STAT("veb.tc_%u_rx_packets", tc_stats.tc_rx_packets),
- I40E_VEB_STAT("veb.tc_%u_rx_bytes", tc_stats.tc_rx_bytes),
+ I40E_VEB_TC_STAT("veb.tc_%u_tx_packets", tc_tx_packets),
+ I40E_VEB_TC_STAT("veb.tc_%u_tx_bytes", tc_tx_bytes),
+ I40E_VEB_TC_STAT("veb.tc_%u_rx_packets", tc_rx_packets),
+ I40E_VEB_TC_STAT("veb.tc_%u_rx_bytes", tc_rx_bytes),
};
static const struct i40e_stats i40e_gstrings_misc_stats[] = {
/* Set flow control settings */
ethtool_link_ksettings_add_link_mode(ks, supported, Pause);
+ ethtool_link_ksettings_add_link_mode(ks, supported, Asym_Pause);
switch (hw->fc.requested_mode) {
case I40E_FC_FULL:
}
/**
+ * i40e_get_veb_tc_stats - copy VEB TC statistics to formatted structure
+ * @tc: the TC statistics in VEB structure (veb->tc_stats)
+ * @i: the index of traffic class in (veb->tc_stats) structure to copy
+ *
+ * Copy VEB TC statistics from structure of arrays (veb->tc_stats) to
+ * one dimensional structure i40e_cp_veb_tc_stats.
+ * Produce formatted i40e_cp_veb_tc_stats structure of the VEB TC
+ * statistics for the given TC.
+ **/
+static struct i40e_cp_veb_tc_stats
+i40e_get_veb_tc_stats(struct i40e_veb_tc_stats *tc, unsigned int i)
+{
+ struct i40e_cp_veb_tc_stats veb_tc = {
+ .tc_rx_packets = tc->tc_rx_packets[i],
+ .tc_rx_bytes = tc->tc_rx_bytes[i],
+ .tc_tx_packets = tc->tc_tx_packets[i],
+ .tc_tx_bytes = tc->tc_tx_bytes[i],
+ };
+
+ return veb_tc;
+}
+
+/**
* i40e_get_pfc_stats - copy HW PFC statistics to formatted structure
* @pf: the PF device structure
* @i: the priority value to copy
i40e_gstrings_veb_stats);
for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++)
- i40e_add_ethtool_stats(&data, veb_stats ? veb : NULL,
- i40e_gstrings_veb_tc_stats);
+ if (veb_stats) {
+ struct i40e_cp_veb_tc_stats veb_tc =
+ i40e_get_veb_tc_stats(&veb->tc_stats, i);
+
+ i40e_add_ethtool_stats(&data, &veb_tc,
+ i40e_gstrings_veb_tc_stats);
+ } else {
+ i40e_add_ethtool_stats(&data, NULL,
+ i40e_gstrings_veb_tc_stats);
+ }
i40e_add_ethtool_stats(&data, pf, i40e_gstrings_stats);
status = i40e_aq_get_phy_register(hw,
I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE,
- true, addr, offset, &value, NULL);
+ addr, true, offset, &value, NULL);
if (status)
return -EIO;
data[i] = value;
i40e_stat_str(hw, aq_ret),
i40e_aq_str(hw, hw->aq.asq_last_status));
} else {
- dev_info(&pf->pdev->dev, "%s is %s allmulti mode.\n",
- vsi->netdev->name,
+ dev_info(&pf->pdev->dev, "%s allmulti mode.\n",
cur_multipromisc ? "entering" : "leaving");
}
}
}
/**
+ * i40e_rx_offset - Return expected offset into page to access data
+ * @rx_ring: Ring we are requesting offset of
+ *
+ * Returns the offset value for ring into the data buffer.
+ */
+static unsigned int i40e_rx_offset(struct i40e_ring *rx_ring)
+{
+ return ring_uses_build_skb(rx_ring) ? I40E_SKB_PAD : 0;
+}
+
+/**
* i40e_configure_rx_ring - Configure a receive ring context
* @ring: The Rx ring to configure
*
else
set_ring_build_skb_enabled(ring);
+ ring->rx_offset = i40e_rx_offset(ring);
+
/* cache tail for quicker writes, and clear the reg before use */
ring->tail = hw->hw_addr + I40E_QRX_TAIL(pf_q);
writel(0, ring->tail);
set_bit(__I40E_CLIENT_SERVICE_REQUESTED, pf->state);
set_bit(__I40E_CLIENT_L2_CHANGE, pf->state);
}
- /* registers are set, lets apply */
- if (pf->hw_features & I40E_HW_USE_SET_LLDP_MIB)
- ret = i40e_hw_set_dcb_config(pf, new_cfg);
+ /* registers are set, lets apply */
+ if (pf->hw_features & I40E_HW_USE_SET_LLDP_MIB)
+ ret = i40e_hw_set_dcb_config(pf, new_cfg);
}
err:
goto end_core_reset;
}
- if (!lock_acquired)
- rtnl_lock();
- ret = i40e_setup_pf_switch(pf, reinit);
- if (ret)
- goto end_unlock;
-
#ifdef CONFIG_I40E_DCB
/* Enable FW to write a default DCB config on link-up
* unless I40E_FLAG_TC_MQPRIO was enabled or DCB
i40e_aq_set_dcb_parameters(hw, false, NULL);
dev_warn(&pf->pdev->dev,
"DCB is not supported for X710-T*L 2.5/5G speeds\n");
- pf->flags &= ~I40E_FLAG_DCB_CAPABLE;
+ pf->flags &= ~I40E_FLAG_DCB_CAPABLE;
} else {
i40e_aq_set_dcb_parameters(hw, true, NULL);
ret = i40e_init_pf_dcb(pf);
}
#endif /* CONFIG_I40E_DCB */
+ if (!lock_acquired)
+ rtnl_lock();
+ ret = i40e_setup_pf_switch(pf, reinit);
+ if (ret)
+ goto end_unlock;
/* The driver only wants link up/down and module qualification
* reports from firmware. Note the negative logic.
{
int err = 0;
int size;
+ u16 pow;
/* Set default capability flags */
pf->flags = I40E_FLAG_RX_CSUM_ENABLED |
pf->rss_table_size = pf->hw.func_caps.rss_table_size;
pf->rss_size_max = min_t(int, pf->rss_size_max,
pf->hw.func_caps.num_tx_qp);
+
+ /* find the next higher power-of-2 of num cpus */
+ pow = roundup_pow_of_two(num_online_cpus());
+ pf->rss_size_max = min_t(int, pf->rss_size_max, pow);
+
if (pf->hw.func_caps.rss) {
pf->flags |= I40E_FLAG_RSS_ENABLED;
pf->alloc_rss_size = min_t(int, pf->rss_size_max,
* in order to register the netdev
*/
v_idx = i40e_vsi_mem_alloc(pf, I40E_VSI_MAIN);
- if (v_idx < 0)
+ if (v_idx < 0) {
+ err = v_idx;
goto err_switch_setup;
+ }
pf->lan_vsi = v_idx;
vsi = pf->vsi[v_idx];
- if (!vsi)
+ if (!vsi) {
+ err = -EFAULT;
goto err_switch_setup;
+ }
vsi->alloc_queue_pairs = 1;
err = i40e_config_netdev(vsi);
if (err)
}
/**
- * i40e_rx_offset - Return expected offset into page to access data
- * @rx_ring: Ring we are requesting offset of
- *
- * Returns the offset value for ring into the data buffer.
- */
-static unsigned int i40e_rx_offset(struct i40e_ring *rx_ring)
-{
- return ring_uses_build_skb(rx_ring) ? I40E_SKB_PAD : 0;
-}
-
-/**
* i40e_setup_rx_descriptors - Allocate Rx descriptors
* @rx_ring: Rx descriptor ring (for a specific queue) to setup
*
rx_ring->next_to_alloc = 0;
rx_ring->next_to_clean = 0;
rx_ring->next_to_use = 0;
- rx_ring->rx_offset = i40e_rx_offset(rx_ring);
/* XDP RX-queue info only needed for RX rings exposed to XDP */
if (rx_ring->vsi->type == I40E_VSI_MAIN) {
* @rx_ring: Rx ring being processed
* @xdp: XDP buffer containing the frame
**/
-static struct sk_buff *i40e_run_xdp(struct i40e_ring *rx_ring,
- struct xdp_buff *xdp)
+static int i40e_run_xdp(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
{
int err, result = I40E_XDP_PASS;
struct i40e_ring *xdp_ring;
}
xdp_out:
rcu_read_unlock();
- return ERR_PTR(-result);
+ return result;
}
/**
unsigned int xdp_xmit = 0;
bool failure = false;
struct xdp_buff xdp;
+ int xdp_res = 0;
#if (PAGE_SIZE < 8192)
frame_sz = i40e_rx_frame_truesize(rx_ring, 0);
/* At larger PAGE_SIZE, frame_sz depend on len size */
xdp.frame_sz = i40e_rx_frame_truesize(rx_ring, size);
#endif
- skb = i40e_run_xdp(rx_ring, &xdp);
+ xdp_res = i40e_run_xdp(rx_ring, &xdp);
}
- if (IS_ERR(skb)) {
- unsigned int xdp_res = -PTR_ERR(skb);
-
+ if (xdp_res) {
if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR)) {
xdp_xmit |= xdp_res;
i40e_rx_buffer_flip(rx_ring, rx_buffer, size);
**/
static inline void i40e_vc_disable_vf(struct i40e_vf *vf)
{
+ struct i40e_pf *pf = vf->pf;
int i;
i40e_vc_notify_vf_reset(vf);
* ensure a reset.
*/
for (i = 0; i < 20; i++) {
+ /* If PF is in VFs releasing state reset VF is impossible,
+ * so leave it.
+ */
+ if (test_bit(__I40E_VFS_RELEASING, pf->state))
+ return;
if (i40e_reset_vf(vf, false))
return;
usleep_range(10000, 20000);
if (!pf->vf)
return;
+
+ set_bit(__I40E_VFS_RELEASING, pf->state);
while (test_and_set_bit(__I40E_VF_DISABLE, pf->state))
usleep_range(1000, 2000);
}
}
clear_bit(__I40E_VF_DISABLE, pf->state);
+ clear_bit(__I40E_VFS_RELEASING, pf->state);
}
#ifdef CONFIG_PCI_IOV
nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, descs, budget);
if (!nb_pkts)
- return false;
+ return true;
if (xdp_ring->next_to_use + nb_pkts >= xdp_ring->count) {
nb_processed = xdp_ring->count - xdp_ring->next_to_use;
i40e_update_tx_stats(xdp_ring, nb_pkts, total_bytes);
- return true;
+ return nb_pkts < budget;
}
/**
goto err_alloc;
}
- if (iavf_process_config(adapter))
+ err = iavf_process_config(adapter);
+ if (err)
goto err_alloc;
adapter->current_op = VIRTCHNL_OP_UNKNOWN;
__ICE_NEEDS_RESTART,
__ICE_PREPARED_FOR_RESET, /* set by driver when prepared */
__ICE_RESET_OICR_RECV, /* set by driver after rcv reset OICR */
- __ICE_DCBNL_DEVRESET, /* set by dcbnl devreset */
__ICE_PFR_REQ, /* set by driver and peers */
__ICE_CORER_REQ, /* set by driver and peers */
__ICE_GLOBR_REQ, /* set by driver and peers */
void ice_print_link_msg(struct ice_vsi *vsi, bool isup);
const char *ice_stat_str(enum ice_status stat_err);
const char *ice_aq_str(enum ice_aq_err aq_err);
-bool ice_is_wol_supported(struct ice_pf *pf);
+bool ice_is_wol_supported(struct ice_hw *hw);
int
ice_fdir_write_fltr(struct ice_pf *pf, struct ice_fdir_fltr *input, bool add,
bool is_tun);
int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout,
struct ice_rq_event_info *event);
int ice_open(struct net_device *netdev);
+int ice_open_internal(struct net_device *netdev);
int ice_stop(struct net_device *netdev);
void ice_service_task_schedule(struct ice_pf *pf);
}
/**
+ * ice_rx_offset - Return expected offset into page to access data
+ * @rx_ring: Ring we are requesting offset of
+ *
+ * Returns the offset value for ring into the data buffer.
+ */
+static unsigned int ice_rx_offset(struct ice_ring *rx_ring)
+{
+ if (ice_ring_uses_build_skb(rx_ring))
+ return ICE_SKB_PAD;
+ else if (ice_is_xdp_ena_vsi(rx_ring->vsi))
+ return XDP_PACKET_HEADROOM;
+
+ return 0;
+}
+
+/**
* ice_setup_rx_ctx - Configure a receive ring context
* @ring: The Rx ring to configure
*
else
ice_set_ring_build_skb_ena(ring);
+ ring->rx_offset = ice_rx_offset(ring);
+
/* init queue specific tail register */
ring->tail = hw->hw_addr + QRX_TAIL(pf_q);
writel(0, ring->tail);
if (ring->xsk_pool) {
+ bool ok;
+
if (!xsk_buff_can_alloc(ring->xsk_pool, num_bufs)) {
dev_warn(dev, "XSK buffer pool does not provide enough addresses to fill %d buffers on Rx ring %d\n",
num_bufs, ring->q_index);
return 0;
}
- err = ice_alloc_rx_bufs_zc(ring, num_bufs);
- if (err)
+ ok = ice_alloc_rx_bufs_zc(ring, num_bufs);
+ if (!ok)
dev_info(dev, "Failed to allocate some buffers on XSK buffer pool enabled Rx ring %d (pf_q %d)\n",
ring->q_index, pf_q);
return 0;
if (!data) {
data = devm_kcalloc(ice_hw_to_dev(hw),
- sizeof(*data),
ICE_AQC_FW_LOG_ID_MAX,
+ sizeof(*data),
GFP_KERNEL);
if (!data)
return ICE_ERR_NO_MEMORY;
ICE_CTL_Q_MAILBOX,
};
-/* Control Queue timeout settings - max delay 250ms */
-#define ICE_CTL_Q_SQ_CMD_TIMEOUT 2500 /* Count 2500 times */
+/* Control Queue timeout settings - max delay 1s */
+#define ICE_CTL_Q_SQ_CMD_TIMEOUT 10000 /* Count 10000 times */
#define ICE_CTL_Q_SQ_CMD_USEC 100 /* Check every 100usec */
#define ICE_CTL_Q_ADMIN_INIT_TIMEOUT 10 /* Count 10 times */
#define ICE_CTL_Q_ADMIN_INIT_MSEC 100 /* Check every 100msec */
/**
* ice_cee_to_dcb_cfg
* @cee_cfg: pointer to CEE configuration struct
- * @dcbcfg: DCB configuration struct
+ * @pi: port information structure
*
* Convert CEE configuration from firmware to DCB configuration
*/
static void
ice_cee_to_dcb_cfg(struct ice_aqc_get_cee_dcb_cfg_resp *cee_cfg,
- struct ice_dcbx_cfg *dcbcfg)
+ struct ice_port_info *pi)
{
u32 status, tlv_status = le32_to_cpu(cee_cfg->tlv_status);
- u32 ice_aqc_cee_status_mask, ice_aqc_cee_status_shift;
- u16 app_prio = le16_to_cpu(cee_cfg->oper_app_prio);
+ u32 ice_aqc_cee_status_mask, ice_aqc_cee_status_shift, j;
u8 i, err, sync, oper, app_index, ice_app_sel_type;
+ u16 app_prio = le16_to_cpu(cee_cfg->oper_app_prio);
u16 ice_aqc_cee_app_mask, ice_aqc_cee_app_shift;
+ struct ice_dcbx_cfg *cmp_dcbcfg, *dcbcfg;
u16 ice_app_prot_id_type;
- /* CEE PG data to ETS config */
+ dcbcfg = &pi->qos_cfg.local_dcbx_cfg;
+ dcbcfg->dcbx_mode = ICE_DCBX_MODE_CEE;
+ dcbcfg->tlv_status = tlv_status;
+
+ /* CEE PG data */
dcbcfg->etscfg.maxtcs = cee_cfg->oper_num_tc;
/* Note that the FW creates the oper_prio_tc nibbles reversed
}
}
- /* CEE PFC data to ETS config */
+ /* CEE PFC data */
dcbcfg->pfc.pfcena = cee_cfg->oper_pfc_en;
dcbcfg->pfc.pfccap = ICE_MAX_TRAFFIC_CLASS;
+ /* CEE APP TLV data */
+ if (dcbcfg->app_mode == ICE_DCBX_APPS_NON_WILLING)
+ cmp_dcbcfg = &pi->qos_cfg.desired_dcbx_cfg;
+ else
+ cmp_dcbcfg = &pi->qos_cfg.remote_dcbx_cfg;
+
app_index = 0;
for (i = 0; i < 3; i++) {
if (i == 0) {
ice_aqc_cee_app_shift = ICE_AQC_CEE_APP_ISCSI_S;
ice_app_sel_type = ICE_APP_SEL_TCPIP;
ice_app_prot_id_type = ICE_APP_PROT_ID_ISCSI;
+
+ for (j = 0; j < cmp_dcbcfg->numapps; j++) {
+ u16 prot_id = cmp_dcbcfg->app[j].prot_id;
+ u8 sel = cmp_dcbcfg->app[j].selector;
+
+ if (sel == ICE_APP_SEL_TCPIP &&
+ (prot_id == ICE_APP_PROT_ID_ISCSI ||
+ prot_id == ICE_APP_PROT_ID_ISCSI_860)) {
+ ice_app_prot_id_type = prot_id;
+ break;
+ }
+ }
} else {
/* FIP APP */
ice_aqc_cee_status_mask = ICE_AQC_CEE_FIP_STATUS_M;
ret = ice_aq_get_cee_dcb_cfg(pi->hw, &cee_cfg, NULL);
if (!ret) {
/* CEE mode */
- dcbx_cfg = &pi->qos_cfg.local_dcbx_cfg;
- dcbx_cfg->dcbx_mode = ICE_DCBX_MODE_CEE;
- dcbx_cfg->tlv_status = le32_to_cpu(cee_cfg.tlv_status);
- ice_cee_to_dcb_cfg(&cee_cfg, dcbx_cfg);
ret = ice_get_ieee_or_cee_dcb_cfg(pi, ICE_DCBX_MODE_CEE);
+ ice_cee_to_dcb_cfg(&cee_cfg, pi);
} else if (pi->hw->adminq.sq_last_status == ICE_AQ_RC_ENOENT) {
/* CEE mode not enabled try querying IEEE data */
dcbx_cfg = &pi->qos_cfg.local_dcbx_cfg;
while (ice_is_reset_in_progress(pf->state))
usleep_range(1000, 2000);
- set_bit(__ICE_DCBNL_DEVRESET, pf->state);
dev_close(netdev);
netdev_state_change(netdev);
dev_open(netdev, NULL);
netdev_state_change(netdev);
- clear_bit(__ICE_DCBNL_DEVRESET, pf->state);
}
/**
netdev_warn(netdev, "Wake on LAN is not supported on this interface!\n");
/* Get WoL settings based on the HW capability */
- if (ice_is_wol_supported(pf)) {
+ if (ice_is_wol_supported(&pf->hw)) {
wol->supported = WAKE_MAGIC;
wol->wolopts = pf->wol_ena ? WAKE_MAGIC : 0;
} else {
struct ice_vsi *vsi = np->vsi;
struct ice_pf *pf = vsi->back;
- if (vsi->type != ICE_VSI_PF || !ice_is_wol_supported(pf))
+ if (vsi->type != ICE_VSI_PF || !ice_is_wol_supported(&pf->hw))
return -EOPNOTSUPP;
/* only magic packet is supported */
if (!locked)
rtnl_lock();
- err = ice_open(vsi->netdev);
+ err = ice_open_internal(vsi->netdev);
if (!locked)
rtnl_unlock();
if (!locked)
rtnl_lock();
- ice_stop(vsi->netdev);
+ ice_vsi_close(vsi);
if (!locked)
rtnl_unlock();
bool ice_is_reset_in_progress(unsigned long *state)
{
return test_bit(__ICE_RESET_OICR_RECV, state) ||
- test_bit(__ICE_DCBNL_DEVRESET, state) ||
test_bit(__ICE_PFR_REQ, state) ||
test_bit(__ICE_CORER_REQ, state) ||
test_bit(__ICE_GLOBR_REQ, state);
}
/**
- * ice_is_wol_supported - get NVM state of WoL
- * @pf: board private structure
+ * ice_is_wol_supported - check if WoL is supported
+ * @hw: pointer to hardware info
*
* Check if WoL is supported based on the HW configuration.
* Returns true if NVM supports and enables WoL for this port, false otherwise
*/
-bool ice_is_wol_supported(struct ice_pf *pf)
+bool ice_is_wol_supported(struct ice_hw *hw)
{
- struct ice_hw *hw = &pf->hw;
u16 wol_ctrl;
/* A bit set to 1 in the NVM Software Reserved Word 2 (WoL control
if (ice_read_sr_word(hw, ICE_SR_NVM_WOL_CFG, &wol_ctrl))
return false;
- return !(BIT(hw->pf_id) & wol_ctrl);
+ return !(BIT(hw->port_info->lport) & wol_ctrl);
}
/**
goto err_send_version_unroll;
}
+ /* not a fatal error if this fails */
err = ice_init_nvm_phy_type(pf->hw.port_info);
- if (err) {
+ if (err)
dev_err(dev, "ice_init_nvm_phy_type failed: %d\n", err);
- goto err_send_version_unroll;
- }
+ /* not a fatal error if this fails */
err = ice_update_link_info(pf->hw.port_info);
- if (err) {
+ if (err)
dev_err(dev, "ice_update_link_info failed: %d\n", err);
- goto err_send_version_unroll;
- }
ice_init_link_dflt_override(pf->hw.port_info);
/* if media available, initialize PHY settings */
if (pf->hw.port_info->phy.link_info.link_info &
ICE_AQ_MEDIA_AVAILABLE) {
+ /* not a fatal error if this fails */
err = ice_init_phy_user_cfg(pf->hw.port_info);
- if (err) {
+ if (err)
dev_err(dev, "ice_init_phy_user_cfg failed: %d\n", err);
- goto err_send_version_unroll;
- }
if (!test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, pf->flags)) {
struct ice_vsi *vsi = ice_get_main_vsi(pf);
continue;
ice_vsi_free_q_vectors(pf->vsi[v]);
}
+ ice_free_cpu_rx_rmap(ice_get_main_vsi(pf));
ice_clear_interrupt_scheme(pf);
pci_save_state(pdev);
int ice_open(struct net_device *netdev)
{
struct ice_netdev_priv *np = netdev_priv(netdev);
+ struct ice_pf *pf = np->vsi->back;
+
+ if (ice_is_reset_in_progress(pf->state)) {
+ netdev_err(netdev, "can't open net device while reset is in progress");
+ return -EBUSY;
+ }
+
+ return ice_open_internal(netdev);
+}
+
+/**
+ * ice_open_internal - Called when a network interface becomes active
+ * @netdev: network interface device structure
+ *
+ * Internal ice_open implementation. Should not be used directly except for ice_open and reset
+ * handling routine
+ *
+ * Returns 0 on success, negative value on failure
+ */
+int ice_open_internal(struct net_device *netdev)
+{
+ struct ice_netdev_priv *np = netdev_priv(netdev);
struct ice_vsi *vsi = np->vsi;
struct ice_pf *pf = vsi->back;
struct ice_port_info *pi;
{
struct ice_netdev_priv *np = netdev_priv(netdev);
struct ice_vsi *vsi = np->vsi;
+ struct ice_pf *pf = vsi->back;
+
+ if (ice_is_reset_in_progress(pf->state)) {
+ netdev_err(netdev, "can't stop net device while reset is in progress");
+ return -EBUSY;
+ }
ice_vsi_close(vsi);
ice_create_vsi_list_map(hw, &vsi_handle_arr[0], 2,
vsi_list_id);
+ if (!m_entry->vsi_list_info)
+ return ICE_ERR_NO_MEMORY;
+
/* If this entry was large action then the large action needs
* to be updated to point to FWD to VSI list
*/
return ((fm_entry->fltr_info.fltr_act == ICE_FWD_TO_VSI &&
fm_entry->fltr_info.vsi_handle == vsi_handle) ||
(fm_entry->fltr_info.fltr_act == ICE_FWD_TO_VSI_LIST &&
+ fm_entry->vsi_list_info &&
(test_bit(vsi_handle, fm_entry->vsi_list_info->vsi_map))));
}
return ICE_ERR_PARAM;
list_for_each_entry(fm_entry, lkup_list_head, list_entry) {
- struct ice_fltr_info *fi;
-
- fi = &fm_entry->fltr_info;
- if (!fi || !ice_vsi_uses_fltr(fm_entry, vsi_handle))
+ if (!ice_vsi_uses_fltr(fm_entry, vsi_handle))
continue;
status = ice_add_entry_to_vsi_fltr_list(hw, vsi_handle,
- vsi_list_head, fi);
+ vsi_list_head,
+ &fm_entry->fltr_info);
if (status)
return status;
}
&remove_list_head);
mutex_unlock(rule_lock);
if (status)
- return;
+ goto free_fltr_list;
switch (lkup) {
case ICE_SW_LKUP_MAC:
break;
}
+free_fltr_list:
list_for_each_entry_safe(fm_entry, tmp, &remove_list_head, list_entry) {
list_del(&fm_entry->list_entry);
devm_kfree(ice_hw_to_dev(hw), fm_entry);
}
/**
- * ice_rx_offset - Return expected offset into page to access data
- * @rx_ring: Ring we are requesting offset of
- *
- * Returns the offset value for ring into the data buffer.
- */
-static unsigned int ice_rx_offset(struct ice_ring *rx_ring)
-{
- if (ice_ring_uses_build_skb(rx_ring))
- return ICE_SKB_PAD;
- else if (ice_is_xdp_ena_vsi(rx_ring->vsi))
- return XDP_PACKET_HEADROOM;
-
- return 0;
-}
-
-/**
* ice_setup_rx_ring - Allocate the Rx descriptors
* @rx_ring: the Rx ring to set up
*
rx_ring->next_to_use = 0;
rx_ring->next_to_clean = 0;
- rx_ring->rx_offset = ice_rx_offset(rx_ring);
if (ice_is_xdp_ena_vsi(rx_ring->vsi))
WRITE_ONCE(rx_ring->xdp_prog, rx_ring->vsi->xdp_prog);
#define ICE_TLV_STATUS_ERR 0x4
#define ICE_APP_PROT_ID_FCOE 0x8906
#define ICE_APP_PROT_ID_ISCSI 0x0cbc
+#define ICE_APP_PROT_ID_ISCSI_860 0x035c
#define ICE_APP_PROT_ID_FIP 0x8914
#define ICE_APP_SEL_ETHTYPE 0x1
#define ICE_APP_SEL_TCPIP 0x2
* This function allocates a number of Rx buffers from the fill ring
* or the internal recycle mechanism and places them on the Rx ring.
*
- * Returns false if all allocations were successful, true if any fail.
+ * Returns true if all allocations were successful, false if any fail.
*/
bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count)
{
union ice_32b_rx_flex_desc *rx_desc;
u16 ntu = rx_ring->next_to_use;
struct ice_rx_buf *rx_buf;
- bool ret = false;
+ bool ok = true;
dma_addr_t dma;
if (!count)
- return false;
+ return true;
rx_desc = ICE_RX_DESC(rx_ring, ntu);
rx_buf = &rx_ring->rx_buf[ntu];
do {
rx_buf->xdp = xsk_buff_alloc(rx_ring->xsk_pool);
if (!rx_buf->xdp) {
- ret = true;
+ ok = false;
break;
}
ice_release_rx_desc(rx_ring, ntu);
}
- return ret;
+ return ok;
}
/**
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright(c) 2007 - 2018 Intel Corporation. */
-#ifndef _E1000_HW_H_
-#define _E1000_HW_H_
+#ifndef _E1000_IGB_HW_H_
+#define _E1000_IGB_HW_H_
#include <linux/types.h>
#include <linux/delay.h>
void igb_read_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value);
void igb_write_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value);
-#endif /* _E1000_HW_H_ */
+#endif /* _E1000_IGB_HW_H_ */
void igb_ptp_rx_hang(struct igb_adapter *adapter);
void igb_ptp_tx_hang(struct igb_adapter *adapter);
void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb);
-void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
- struct sk_buff *skb);
+int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
+ struct sk_buff *skb);
int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr);
int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr);
void igb_set_flag_queue_pairs(struct igb_adapter *, const u32);
new_buff->pagecnt_bias = old_buff->pagecnt_bias;
}
-static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer)
+static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
+ int rx_buf_pgcnt)
{
unsigned int pagecnt_bias = rx_buffer->pagecnt_bias;
struct page *page = rx_buffer->page;
#if (PAGE_SIZE < 8192)
/* if we are only owner of page we can reuse it */
- if (unlikely((page_ref_count(page) - pagecnt_bias) > 1))
+ if (unlikely((rx_buf_pgcnt - pagecnt_bias) > 1))
return false;
#else
#define IGB_LAST_OFFSET \
return NULL;
if (unlikely(igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP))) {
- igb_ptp_rx_pktstamp(rx_ring->q_vector, xdp->data, skb);
- xdp->data += IGB_TS_HDR_LEN;
- size -= IGB_TS_HDR_LEN;
+ if (!igb_ptp_rx_pktstamp(rx_ring->q_vector, xdp->data, skb)) {
+ xdp->data += IGB_TS_HDR_LEN;
+ size -= IGB_TS_HDR_LEN;
+ }
}
/* Determine available headroom for copy */
/* pull timestamp out of packet data */
if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
- igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb);
- __skb_pull(skb, IGB_TS_HDR_LEN);
+ if (!igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb))
+ __skb_pull(skb, IGB_TS_HDR_LEN);
}
/* update buffer offset */
}
static struct igb_rx_buffer *igb_get_rx_buffer(struct igb_ring *rx_ring,
- const unsigned int size)
+ const unsigned int size, int *rx_buf_pgcnt)
{
struct igb_rx_buffer *rx_buffer;
rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
+ *rx_buf_pgcnt =
+#if (PAGE_SIZE < 8192)
+ page_count(rx_buffer->page);
+#else
+ 0;
+#endif
prefetchw(rx_buffer->page);
/* we are reusing so sync this buffer for CPU use */
}
static void igb_put_rx_buffer(struct igb_ring *rx_ring,
- struct igb_rx_buffer *rx_buffer)
+ struct igb_rx_buffer *rx_buffer, int rx_buf_pgcnt)
{
- if (igb_can_reuse_rx_page(rx_buffer)) {
+ if (igb_can_reuse_rx_page(rx_buffer, rx_buf_pgcnt)) {
/* hand second half of page back to the ring */
igb_reuse_rx_page(rx_ring, rx_buffer);
} else {
unsigned int xdp_xmit = 0;
struct xdp_buff xdp;
u32 frame_sz = 0;
+ int rx_buf_pgcnt;
/* Frame size depend on rx_ring setup when PAGE_SIZE=4K */
#if (PAGE_SIZE < 8192)
*/
dma_rmb();
- rx_buffer = igb_get_rx_buffer(rx_ring, size);
+ rx_buffer = igb_get_rx_buffer(rx_ring, size, &rx_buf_pgcnt);
/* retrieve a buffer from the ring */
if (!skb) {
break;
}
- igb_put_rx_buffer(rx_ring, rx_buffer);
+ igb_put_rx_buffer(rx_ring, rx_buffer, rx_buf_pgcnt);
cleaned_count++;
/* fetch next buffer in frame if non-eop */
dev_kfree_skb_any(skb);
}
+#define IGB_RET_PTP_DISABLED 1
+#define IGB_RET_PTP_INVALID 2
+
/**
* igb_ptp_rx_pktstamp - retrieve Rx per packet timestamp
* @q_vector: Pointer to interrupt specific structure
*
* This function is meant to retrieve a timestamp from the first buffer of an
* incoming frame. The value is stored in little endian format starting on
- * byte 8.
+ * byte 8
+ *
+ * Returns: 0 if success, nonzero if failure
**/
-void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
- struct sk_buff *skb)
+int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va,
+ struct sk_buff *skb)
{
- __le64 *regval = (__le64 *)va;
struct igb_adapter *adapter = q_vector->adapter;
+ __le64 *regval = (__le64 *)va;
int adjust = 0;
+ if (!(adapter->ptp_flags & IGB_PTP_ENABLED))
+ return IGB_RET_PTP_DISABLED;
+
/* The timestamp is recorded in little endian format.
* DWORD: 0 1 2 3
* Field: Reserved Reserved SYSTIML SYSTIMH
*/
+
+ /* check reserved dwords are zero, be/le doesn't matter for zero */
+ if (regval[0])
+ return IGB_RET_PTP_INVALID;
+
igb_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb),
le64_to_cpu(regval[1]));
}
skb_hwtstamps(skb)->hwtstamp =
ktime_sub_ns(skb_hwtstamps(skb)->hwtstamp, adjust);
+
+ return 0;
}
/**
* This function is meant to retrieve a timestamp from the internal registers
* of the adapter and store it in the skb.
**/
-void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector,
- struct sk_buff *skb)
+void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb)
{
struct igb_adapter *adapter = q_vector->adapter;
struct e1000_hw *hw = &adapter->hw;
- u64 regval;
int adjust = 0;
+ u64 regval;
+
+ if (!(adapter->ptp_flags & IGB_PTP_ENABLED))
+ return;
/* If this bit is set, then the RX registers contain the time stamp. No
* other packet will be time stamped until we read these registers, so
void igc_ptp_reset(struct igc_adapter *adapter);
void igc_ptp_suspend(struct igc_adapter *adapter);
void igc_ptp_stop(struct igc_adapter *adapter);
-void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, void *va,
+void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, __le32 *va,
struct sk_buff *skb);
int igc_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr);
int igc_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr);
Autoneg);
}
+ /* Set pause flow control settings */
+ ethtool_link_ksettings_add_link_mode(cmd, supported, Pause);
+
switch (hw->fc.requested_mode) {
case igc_fc_full:
ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause);
Asym_Pause);
break;
default:
- ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause);
- ethtool_link_ksettings_add_link_mode(cmd, advertising,
- Asym_Pause);
+ break;
}
status = pm_runtime_suspended(&adapter->pdev->dev) ?
adapter = container_of(work, struct igc_adapter, reset_task);
+ rtnl_lock();
+ /* If we're already down or resetting, just bail */
+ if (test_bit(__IGC_DOWN, &adapter->state) ||
+ test_bit(__IGC_RESETTING, &adapter->state)) {
+ rtnl_unlock();
+ return;
+ }
+
igc_rings_dump(adapter);
igc_regs_dump(adapter);
netdev_err(adapter->netdev, "Reset adapter\n");
igc_reinit_locked(adapter);
+ rtnl_unlock();
}
/**
}
/**
- * igc_ptp_rx_pktstamp - retrieve Rx per packet timestamp
+ * igc_ptp_rx_pktstamp - Retrieve timestamp from Rx packet buffer
* @q_vector: Pointer to interrupt specific structure
* @va: Pointer to address containing Rx buffer
* @skb: Buffer containing timestamp and packet
*
- * This function is meant to retrieve the first timestamp from the
- * first buffer of an incoming frame. The value is stored in little
- * endian format starting on byte 0. There's a second timestamp
- * starting on byte 8.
- **/
-void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, void *va,
+ * This function retrieves the timestamp saved in the beginning of packet
+ * buffer. While two timestamps are available, one in timer0 reference and the
+ * other in timer1 reference, this function considers only the timestamp in
+ * timer0 reference.
+ */
+void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, __le32 *va,
struct sk_buff *skb)
{
struct igc_adapter *adapter = q_vector->adapter;
- __le64 *regval = (__le64 *)va;
- int adjust = 0;
-
- /* The timestamp is recorded in little endian format.
- * DWORD: | 0 | 1 | 2 | 3
- * Field: | Timer0 Low | Timer0 High | Timer1 Low | Timer1 High
+ u64 regval;
+ int adjust;
+
+ /* Timestamps are saved in little endian at the beginning of the packet
+ * buffer following the layout:
+ *
+ * DWORD: | 0 | 1 | 2 | 3 |
+ * Field: | Timer1 SYSTIML | Timer1 SYSTIMH | Timer0 SYSTIML | Timer0 SYSTIMH |
+ *
+ * SYSTIML holds the nanoseconds part while SYSTIMH holds the seconds
+ * part of the timestamp.
*/
- igc_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb),
- le64_to_cpu(regval[0]));
-
- /* adjust timestamp for the RX latency based on link speed */
- if (adapter->hw.mac.type == igc_i225) {
- switch (adapter->link_speed) {
- case SPEED_10:
- adjust = IGC_I225_RX_LATENCY_10;
- break;
- case SPEED_100:
- adjust = IGC_I225_RX_LATENCY_100;
- break;
- case SPEED_1000:
- adjust = IGC_I225_RX_LATENCY_1000;
- break;
- case SPEED_2500:
- adjust = IGC_I225_RX_LATENCY_2500;
- break;
- }
+ regval = le32_to_cpu(va[2]);
+ regval |= (u64)le32_to_cpu(va[3]) << 32;
+ igc_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), regval);
+
+ /* Adjust timestamp for the RX latency based on link speed */
+ switch (adapter->link_speed) {
+ case SPEED_10:
+ adjust = IGC_I225_RX_LATENCY_10;
+ break;
+ case SPEED_100:
+ adjust = IGC_I225_RX_LATENCY_100;
+ break;
+ case SPEED_1000:
+ adjust = IGC_I225_RX_LATENCY_1000;
+ break;
+ case SPEED_2500:
+ adjust = IGC_I225_RX_LATENCY_2500;
+ break;
+ default:
+ adjust = 0;
+ netdev_warn_once(adapter->netdev, "Imprecise timestamp\n");
+ break;
}
skb_hwtstamps(skb)->hwtstamp =
ktime_sub_ns(skb_hwtstamps(skb)->hwtstamp, adjust);
return -EINVAL;
}
+ if (xs->props.mode != XFRM_MODE_TRANSPORT) {
+ netdev_err(dev, "Unsupported mode for ipsec offload\n");
+ return -EINVAL;
+ }
+
if (ixgbe_ipsec_check_mgmt_ip(xs)) {
netdev_err(dev, "IPsec IP addr clash with mgmt filters\n");
return -EINVAL;
#endif
}
+ ring->rx_offset = ixgbe_rx_offset(ring);
+
if (ring->xsk_pool && hw->mac.type != ixgbe_mac_82599EB) {
u32 xsk_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool);
return err;
}
+static int ixgbe_rx_napi_id(struct ixgbe_ring *rx_ring)
+{
+ struct ixgbe_q_vector *q_vector = rx_ring->q_vector;
+
+ return q_vector ? q_vector->napi.napi_id : 0;
+}
+
/**
* ixgbe_setup_rx_resources - allocate Rx resources (Descriptors)
* @adapter: pointer to ixgbe_adapter
rx_ring->next_to_clean = 0;
rx_ring->next_to_use = 0;
- rx_ring->rx_offset = ixgbe_rx_offset(rx_ring);
/* XDP RX-queue info */
if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, adapter->netdev,
- rx_ring->queue_index, rx_ring->q_vector->napi.napi_id) < 0)
+ rx_ring->queue_index, ixgbe_rx_napi_id(rx_ring)) < 0)
goto err;
rx_ring->xdp_prog = adapter->xdp_prog;
adapter->hw.hw_addr = adapter->io_addr;
+ err = pci_enable_device_mem(pdev);
+ if (err) {
+ e_dev_err("Cannot enable PCI device from suspend\n");
+ return err;
+ }
smp_mb__before_atomic();
clear_bit(__IXGBE_DISABLED, &adapter->state);
pci_set_master(pdev);
ixgbe_atr_compute_perfect_hash_82599(&input->filter, mask);
err = ixgbe_fdir_write_perfect_filter_82599(hw, &input->filter,
input->sw_idx, queue);
- if (!err)
- ixgbe_update_ethtool_fdir_entry(adapter, input, input->sw_idx);
+ if (err)
+ goto err_out_w_lock;
+
+ ixgbe_update_ethtool_fdir_entry(adapter, input, input->sw_idx);
spin_unlock(&adapter->fdir_perfect_lock);
if ((uhtid != 0x800) && (adapter->jump_tables[uhtid]))
return -EINVAL;
}
+ if (xs->props.mode != XFRM_MODE_TRANSPORT) {
+ netdev_err(dev, "Unsupported mode for ipsec offload\n");
+ return -EINVAL;
+ }
+
if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) {
struct rx_sa rsa;
jwrite32f(jme, JME_APMC, apmc);
}
-static void jme_link_change_tasklet(struct tasklet_struct *t)
+static void jme_link_change_work(struct work_struct *work)
{
- struct jme_adapter *jme = from_tasklet(jme, t, linkch_task);
+ struct jme_adapter *jme = container_of(work, struct jme_adapter, linkch_task);
struct net_device *netdev = jme->dev;
int rc;
* all other events are ignored
*/
jwrite32(jme, JME_IEVE, intrstat);
- tasklet_schedule(&jme->linkch_task);
+ schedule_work(&jme->linkch_task);
goto out_reenable;
}
jme_clear_pm_disable_wol(jme);
JME_NAPI_ENABLE(jme);
- tasklet_setup(&jme->linkch_task, jme_link_change_tasklet);
tasklet_setup(&jme->txclean_task, jme_tx_clean_tasklet);
tasklet_setup(&jme->rxclean_task, jme_rx_clean_tasklet);
tasklet_setup(&jme->rxempty_task, jme_rx_empty_tasklet);
JME_NAPI_DISABLE(jme);
- tasklet_kill(&jme->linkch_task);
+ cancel_work_sync(&jme->linkch_task);
tasklet_kill(&jme->txclean_task);
tasklet_kill(&jme->rxclean_task);
tasklet_kill(&jme->rxempty_task);
atomic_set(&jme->rx_empty, 1);
tasklet_setup(&jme->pcc_task, jme_pcc_tasklet);
+ INIT_WORK(&jme->linkch_task, jme_link_change_work);
jme->dpi.cur = PCC_P1;
jme->reg_ghc = 0;
struct tasklet_struct rxempty_task;
struct tasklet_struct rxclean_task;
struct tasklet_struct txclean_task;
- struct tasklet_struct linkch_task;
+ struct work_struct linkch_task;
struct tasklet_struct pcc_task;
unsigned long flags;
u32 reg_txcs;
config NET_VENDOR_MARVELL
bool "Marvell devices"
default y
- depends on PCI || CPU_PXA168 || MV64X60 || PPC32 || PLAT_ORION || INET || COMPILE_TEST
+ depends on PCI || CPU_PXA168 || PPC32 || PLAT_ORION || INET || COMPILE_TEST
help
If you have a network (Ethernet) card belonging to this class, say Y.
config MV643XX_ETH
tristate "Marvell Discovery (643XX) and Orion ethernet support"
- depends on MV64X60 || PPC32 || PLAT_ORION || COMPILE_TEST
+ depends on PPC32 || PLAT_ORION || COMPILE_TEST
depends on INET
select PHYLIB
select MVMDIO
MODULE_DEVICE_TABLE(of, mv643xx_eth_shared_ids);
#endif
-#if defined(CONFIG_OF_IRQ) && !defined(CONFIG_MV64X60)
+#ifdef CONFIG_OF_IRQ
#define mv643xx_eth_property(_np, _name, _v) \
do { \
u32 tmp; \
bool is_lmac_valid(struct cgx *cgx, int lmac_id)
{
- return cgx && test_bit(lmac_id, &cgx->lmac_bmap);
+ if (!cgx || lmac_id < 0 || lmac_id >= MAX_LMAC_PER_CGX)
+ return false;
+ return test_bit(lmac_id, &cgx->lmac_bmap);
}
struct mac_ops *get_mac_ops(void *cgxd)
[NPC_LT_LC_IP] = {
/* SIP+DIP: 8 bytes, KW2[63:0] */
KEX_LD_CFG(0x07, 0xc, 0x1, 0x0, 0x10),
- /* TOS: 1 byte, KW1[63:56] */
- KEX_LD_CFG(0x0, 0x1, 0x1, 0x0, 0xf),
},
/* Layer C: IPv6 */
[NPC_LT_LC_IP6] = {
INTR_MASK(rvu->hw->total_pfs) & ~1ULL);
for (irq = 0; irq < rvu->num_vec; irq++) {
- if (rvu->irq_allocated[irq])
+ if (rvu->irq_allocated[irq]) {
free_irq(pci_irq_vector(rvu->pdev, irq), rvu);
+ rvu->irq_allocated[irq] = false;
+ }
}
pci_free_irq_vectors(rvu->pdev);
struct rvu *rvu = pci_get_drvdata(pdev);
rvu_dbg_exit(rvu);
- rvu_unregister_interrupts(rvu);
rvu_unregister_dl(rvu);
+ rvu_unregister_interrupts(rvu);
rvu_flr_wq_destroy(rvu);
rvu_cgx_exit(rvu);
rvu_fwdata_exit(rvu);
u8 *intf, u8 *ena);
bool is_mac_feature_supported(struct rvu *rvu, int pf, int feature);
u32 rvu_cgx_get_fifolen(struct rvu *rvu);
+void *rvu_first_cgx_pdata(struct rvu *rvu);
/* CPT APIs */
int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int lf, int slot);
return rvu->cgx_idmap[cgx_id];
}
+/* Return first enabled CGX instance if none are enabled then return NULL */
+void *rvu_first_cgx_pdata(struct rvu *rvu)
+{
+ int first_enabled_cgx = 0;
+ void *cgxd = NULL;
+
+ for (; first_enabled_cgx < rvu->cgx_cnt_max; first_enabled_cgx++) {
+ cgxd = rvu_cgx_pdata(first_enabled_cgx, rvu);
+ if (cgxd)
+ break;
+ }
+
+ return cgxd;
+}
+
/* Based on P2X connectivity find mapped NIX block for a PF */
static void rvu_map_cgx_nix_block(struct rvu *rvu, int pf,
int cgx_id, int lmac_id)
u32 rvu_cgx_get_fifolen(struct rvu *rvu)
{
struct mac_ops *mac_ops;
- int rvu_def_cgx_id = 0;
u32 fifo_len;
- mac_ops = get_mac_ops(rvu_cgx_pdata(rvu_def_cgx_id, rvu));
+ mac_ops = get_mac_ops(rvu_first_cgx_pdata(rvu));
fifo_len = mac_ops ? mac_ops->fifo_len : 0;
return fifo_len;
char __user *buffer,
size_t count, loff_t *ppos)
{
- int index, off = 0, flag = 0, go_back = 0, off_prev;
+ int index, off = 0, flag = 0, go_back = 0, len = 0;
struct rvu *rvu = filp->private_data;
int lf, pf, vf, pcifunc;
struct rvu_block block;
int bytes_not_copied;
+ int lf_str_size = 12;
int buf_size = 2048;
+ char *lfs;
char *buf;
/* don't allow partial reads */
buf = kzalloc(buf_size, GFP_KERNEL);
if (!buf)
return -ENOSPC;
- off += scnprintf(&buf[off], buf_size - 1 - off, "\npcifunc\t\t");
+
+ lfs = kzalloc(lf_str_size, GFP_KERNEL);
+ if (!lfs) {
+ kfree(buf);
+ return -ENOMEM;
+ }
+ off += scnprintf(&buf[off], buf_size - 1 - off, "%-*s", lf_str_size,
+ "pcifunc");
for (index = 0; index < BLK_COUNT; index++)
- if (strlen(rvu->hw->block[index].name))
- off += scnprintf(&buf[off], buf_size - 1 - off,
- "%*s\t", (index - 1) * 2,
- rvu->hw->block[index].name);
+ if (strlen(rvu->hw->block[index].name)) {
+ off += scnprintf(&buf[off], buf_size - 1 - off,
+ "%-*s", lf_str_size,
+ rvu->hw->block[index].name);
+ }
off += scnprintf(&buf[off], buf_size - 1 - off, "\n");
for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
for (vf = 0; vf <= rvu->hw->total_vfs; vf++) {
continue;
if (vf) {
+ sprintf(lfs, "PF%d:VF%d", pf, vf - 1);
go_back = scnprintf(&buf[off],
buf_size - 1 - off,
- "PF%d:VF%d\t\t", pf,
- vf - 1);
+ "%-*s", lf_str_size, lfs);
} else {
+ sprintf(lfs, "PF%d", pf);
go_back = scnprintf(&buf[off],
buf_size - 1 - off,
- "PF%d\t\t", pf);
+ "%-*s", lf_str_size, lfs);
}
off += go_back;
block = rvu->hw->block[index];
if (!strlen(block.name))
continue;
- off_prev = off;
+ len = 0;
+ lfs[len] = '\0';
for (lf = 0; lf < block.lf.max; lf++) {
if (block.fn_map[lf] != pcifunc)
continue;
flag = 1;
- off += scnprintf(&buf[off], buf_size - 1
- - off, "%3d,", lf);
+ len += sprintf(&lfs[len], "%d,", lf);
}
- if (flag && off_prev != off)
- off--;
- else
- go_back++;
+
+ if (flag)
+ len--;
+ lfs[len] = '\0';
off += scnprintf(&buf[off], buf_size - 1 - off,
- "\t");
+ "%-*s", lf_str_size, lfs);
+ if (!strlen(lfs))
+ go_back += lf_str_size;
}
if (!flag)
off -= go_back;
}
bytes_not_copied = copy_to_user(buffer, buf, off);
+ kfree(lfs);
kfree(buf);
if (bytes_not_copied)
struct rvu *rvu = filp->private;
struct pci_dev *pdev = NULL;
struct mac_ops *mac_ops;
- int rvu_def_cgx_id = 0;
char cgx[10], lmac[10];
struct rvu_pfvf *pfvf;
int pf, domain, blkid;
u16 pcifunc;
domain = 2;
- mac_ops = get_mac_ops(rvu_cgx_pdata(rvu_def_cgx_id, rvu));
+ mac_ops = get_mac_ops(rvu_first_cgx_pdata(rvu));
+ /* There can be no CGX devices at all */
+ if (!mac_ops)
+ return 0;
seq_printf(filp, "PCI dev\t\tRVU PF Func\tNIX block\t%s\tLMAC\n",
mac_ops->name);
for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
{
struct mac_ops *mac_ops;
unsigned long lmac_bmap;
- int rvu_def_cgx_id = 0;
int i, lmac_id;
char dname[20];
void *cgx;
if (!cgx_get_cgxcnt_max())
return;
- mac_ops = get_mac_ops(rvu_cgx_pdata(rvu_def_cgx_id, rvu));
+ mac_ops = get_mac_ops(rvu_first_cgx_pdata(rvu));
if (!mac_ops)
return;
struct nix_rx_flowkey_alg *field;
struct nix_rx_flowkey_alg tmp;
u32 key_type, valid_key;
- int l4_key_offset;
+ int l4_key_offset = 0;
if (!alg)
return -EINVAL;
index = find_next_bit(mcam->bmap, mcam->bmap_entries, entry);
if (index >= mcam->bmap_entries)
break;
+ entry = index + 1;
if (mcam->entry2cntr_map[index] != req->cntr)
continue;
- entry = index + 1;
npc_unmap_mcam_entry_and_cntr(rvu, mcam, blkaddr,
index, req->cntr);
}
int otx2_get_all_flows(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc,
u32 *rule_locs)
{
+ u32 rule_cnt = nfc->rule_cnt;
u32 location = 0;
int idx = 0;
int err = 0;
nfc->data = pfvf->flow_cfg->ntuple_max_flows;
- while ((!err || err == -ENOENT) && idx < nfc->rule_cnt) {
+ while ((!err || err == -ENOENT) && idx < rule_cnt) {
err = otx2_get_flow(pfvf, nfc, location);
if (!err)
rule_locs[idx++] = location;
location++;
}
+ nfc->rule_cnt = rule_cnt;
return err;
}
struct otx2_nic *pf = netdev_priv(netdev);
struct otx2_cq_poll *cq_poll = NULL;
struct otx2_qset *qset = &pf->qset;
+ struct otx2_rss_info *rss;
int qidx, vec, wrk;
netif_carrier_off(netdev);
/* First stop packet Rx/Tx */
otx2_rxtx_enable(pf, false);
+ /* Clear RSS enable flag */
+ rss = &pf->hw.rss_info;
+ rss->enable = false;
+
/* Cleanup Queue IRQ */
vec = pci_irq_vector(pf->pdev,
pf->hw.nix_msixoff + NIX_LF_QINT_VEC_START);
clk_disable_unprepare(pep->clk);
mdiobus_unregister(pep->smi_bus);
mdiobus_free(pep->smi_bus);
- unregister_netdev(dev);
cancel_work_sync(&pep->tx_timeout_task);
+ unregister_netdev(dev);
free_netdev(dev);
return 0;
}
goto push_new_skb;
}
- desc_data.dma_addr = new_dma_addr;
-
/* We can't fail anymore at this point: it's safe to unmap the skb. */
mtk_star_dma_unmap_rx(priv, &desc_data);
desc_data.skb->dev = ndev;
netif_receive_skb(desc_data.skb);
+ /* update dma_addr for new skb */
+ desc_data.dma_addr = new_dma_addr;
+
push_new_skb:
desc_data.len = skb_tailroom(new_skb);
desc_data.skb = new_skb;
#define EN_ETHTOOL_SHORT_MASK cpu_to_be16(0xffff)
#define EN_ETHTOOL_WORD_MASK cpu_to_be32(0xffffffff)
-static int mlx4_en_moderation_update(struct mlx4_en_priv *priv)
+int mlx4_en_moderation_update(struct mlx4_en_priv *priv)
{
int i, t;
int err = 0;
en_err(priv, "Failed starting port\n");
}
+ if (!err)
+ err = mlx4_en_moderation_update(priv);
out:
mutex_unlock(&mdev->state_lock);
kfree(tmp);
#define DEV_FEATURE_CHANGED(dev, new_features, feature) \
((dev->features & feature) ^ (new_features & feature))
+int mlx4_en_moderation_update(struct mlx4_en_priv *priv);
int mlx4_en_reset_config(struct net_device *dev,
struct hwtstamp_config ts_config,
netdev_features_t new_features);
}
enum {
- MLX5_INTERFACE_PROTOCOL_ETH_REP,
MLX5_INTERFACE_PROTOCOL_ETH,
+ MLX5_INTERFACE_PROTOCOL_ETH_REP,
+ MLX5_INTERFACE_PROTOCOL_IB,
MLX5_INTERFACE_PROTOCOL_IB_REP,
MLX5_INTERFACE_PROTOCOL_MPIB,
- MLX5_INTERFACE_PROTOCOL_IB,
MLX5_INTERFACE_PROTOCOL_VNET,
};
struct mlx5_devlink_trap *dl_trap;
int err = 0;
+ if (is_mdev_switchdev_mode(dev)) {
+ NL_SET_ERR_MSG_MOD(extack, "Devlink traps can't be set in switchdev mode");
+ return -EOPNOTSUPP;
+ }
+
dl_trap = mlx5_find_trap_by_id(dev, trap->id);
if (!dl_trap) {
mlx5_core_err(dev, "Devlink trap: Set action on invalid trap id 0x%x", trap->id);
MLX5_MPWRQ_LOG_WQE_SZ - PAGE_SHIFT : 0)
#define MLX5_MPWRQ_PAGES_PER_WQE BIT(MLX5_MPWRQ_WQE_PAGE_ORDER)
-#define MLX5_MTT_OCTW(npages) (ALIGN(npages, 8) / 2)
+#define MLX5_ALIGN_MTTS(mtts) (ALIGN(mtts, 8))
+#define MLX5_ALIGNED_MTTS_OCTW(mtts) ((mtts) / 2)
+#define MLX5_MTT_OCTW(mtts) (MLX5_ALIGNED_MTTS_OCTW(MLX5_ALIGN_MTTS(mtts)))
/* Add another page to MLX5E_REQUIRED_WQE_MTTS as a buffer between
* WQEs, This page will absorb write overflow by the hardware, when
* receiving packets larger than MTU. These oversize packets are
* dropped by the driver at a later stage.
*/
-#define MLX5E_REQUIRED_WQE_MTTS (ALIGN(MLX5_MPWRQ_PAGES_PER_WQE + 1, 8))
-#define MLX5E_LOG_ALIGNED_MPWQE_PPW (ilog2(MLX5E_REQUIRED_WQE_MTTS))
+#define MLX5E_REQUIRED_WQE_MTTS (MLX5_ALIGN_MTTS(MLX5_MPWRQ_PAGES_PER_WQE + 1))
#define MLX5E_REQUIRED_MTTS(wqes) (wqes * MLX5E_REQUIRED_WQE_MTTS)
#define MLX5E_MAX_RQ_NUM_MTTS \
((1 << 16) * 2) /* So that MLX5_MTT_OCTW(num_mtts) fits into u16 */
struct mlx5_wq_cyc wq;
void __iomem *uar_map;
u32 sqn;
+ u16 reserved_room;
unsigned long state;
/* control path */
*_policy = MLX5_GET(pplm_reg, _buf, fec_override_admin_##link); \
} while (0)
-#define MLX5E_FEC_OVERRIDE_ADMIN_50G_POLICY(buf, policy, write, link) \
- do { \
- unsigned long policy_long; \
- u16 *__policy = &(policy); \
- bool _write = (write); \
- \
- policy_long = *__policy; \
- if (_write && *__policy) \
- *__policy = find_first_bit(&policy_long, \
- sizeof(policy_long) * BITS_PER_BYTE);\
- MLX5E_FEC_OVERRIDE_ADMIN_POLICY(buf, *__policy, _write, link); \
- if (!_write && *__policy) \
- *__policy = 1 << *__policy; \
- } while (0)
-
/* get/set FEC admin field for a given speed */
static int mlx5e_fec_admin_field(u32 *pplm, u16 *fec_policy, bool write,
enum mlx5e_fec_supported_link_mode link_mode)
MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 100g);
break;
case MLX5E_FEC_SUPPORTED_LINK_MODE_50G_1X:
- MLX5E_FEC_OVERRIDE_ADMIN_50G_POLICY(pplm, *fec_policy, write, 50g_1x);
+ MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 50g_1x);
break;
case MLX5E_FEC_SUPPORTED_LINK_MODE_100G_2X:
- MLX5E_FEC_OVERRIDE_ADMIN_50G_POLICY(pplm, *fec_policy, write, 100g_2x);
+ MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 100g_2x);
break;
case MLX5E_FEC_SUPPORTED_LINK_MODE_200G_4X:
- MLX5E_FEC_OVERRIDE_ADMIN_50G_POLICY(pplm, *fec_policy, write, 200g_4x);
+ MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 200g_4x);
break;
case MLX5E_FEC_SUPPORTED_LINK_MODE_400G_8X:
- MLX5E_FEC_OVERRIDE_ADMIN_50G_POLICY(pplm, *fec_policy, write, 400g_8x);
+ MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 400g_8x);
break;
default:
return -EINVAL;
}
static int
+mlx5_get_label_mapping(struct mlx5_tc_ct_priv *ct_priv,
+ u32 *labels, u32 *id)
+{
+ if (!memchr_inv(labels, 0, sizeof(u32) * 4)) {
+ *id = 0;
+ return 0;
+ }
+
+ if (mapping_add(ct_priv->labels_mapping, labels, id))
+ return -EOPNOTSUPP;
+
+ return 0;
+}
+
+static void
+mlx5_put_label_mapping(struct mlx5_tc_ct_priv *ct_priv, u32 id)
+{
+ if (id)
+ mapping_remove(ct_priv->labels_mapping, id);
+}
+
+static int
mlx5_tc_ct_rule_to_tuple(struct mlx5_ct_tuple *tuple, struct flow_rule *rule)
{
struct flow_match_control control;
mlx5_tc_rule_delete(netdev_priv(ct_priv->netdev), zone_rule->rule, attr);
mlx5e_mod_hdr_detach(ct_priv->dev,
ct_priv->mod_hdr_tbl, zone_rule->mh);
- mapping_remove(ct_priv->labels_mapping, attr->ct_attr.ct_labels_id);
+ mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id);
kfree(attr);
}
if (!meta)
return -EOPNOTSUPP;
- err = mapping_add(ct_priv->labels_mapping, meta->ct_metadata.labels,
- &attr->ct_attr.ct_labels_id);
+ err = mlx5_get_label_mapping(ct_priv, meta->ct_metadata.labels,
+ &attr->ct_attr.ct_labels_id);
if (err)
return -EOPNOTSUPP;
if (nat) {
err_mapping:
dealloc_mod_hdr_actions(&mod_acts);
- mapping_remove(ct_priv->labels_mapping, attr->ct_attr.ct_labels_id);
+ mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id);
return err;
}
err_rule:
mlx5e_mod_hdr_detach(ct_priv->dev,
ct_priv->mod_hdr_tbl, zone_rule->mh);
- mapping_remove(ct_priv->labels_mapping, attr->ct_attr.ct_labels_id);
+ mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id);
err_mod_hdr:
kfree(attr);
err_attr:
mlx5e_tc_match_to_reg_get_match(spec, CTSTATE_TO_REG,
&ctstate, &ctstate_mask);
- if (ctstate_mask)
+
+ if ((ctstate & ctstate_mask) == MLX5_CT_STATE_TRK_BIT)
return -EOPNOTSUPP;
ctstate_mask |= MLX5_CT_STATE_TRK_BIT;
if (!priv || !ct_attr->ct_labels_id)
return;
- mapping_remove(priv->labels_mapping, ct_attr->ct_labels_id);
+ mlx5_put_label_mapping(priv, ct_attr->ct_labels_id);
}
int
ct_labels[1] = key->ct_labels[1] & mask->ct_labels[1];
ct_labels[2] = key->ct_labels[2] & mask->ct_labels[2];
ct_labels[3] = key->ct_labels[3] & mask->ct_labels[3];
- if (mapping_add(priv->labels_mapping, ct_labels, &ct_attr->ct_labels_id))
+ if (mlx5_get_label_mapping(priv, ct_labels, &ct_attr->ct_labels_id))
return -EOPNOTSUPP;
mlx5e_tc_match_to_reg_match(spec, LABELS_TO_REG, ct_attr->ct_labels_id,
MLX5_CT_LABELS_MASK);
u16 vport_num;
int err = 0;
- if (flow_attr->ip_version == 4) {
+ if (flow_attr->tun_ip_version == 4) {
/* Addresses are swapped for decap */
attr.fl.fl4.saddr = esw_attr->rx_tun_attr->dst_ip.v4;
attr.fl.fl4.daddr = esw_attr->rx_tun_attr->src_ip.v4;
err = mlx5e_route_lookup_ipv4_get(priv, priv->netdev, &attr);
}
#if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6)
- else if (flow_attr->ip_version == 6) {
+ else if (flow_attr->tun_ip_version == 6) {
/* Addresses are swapped for decap */
attr.fl.fl6.saddr = esw_attr->rx_tun_attr->dst_ip.v6;
attr.fl.fl6.daddr = esw_attr->rx_tun_attr->src_ip.v6;
esw_attr->rx_tun_attr->decap_vport = vport_num;
out:
- if (flow_attr->ip_version == 4)
+ if (flow_attr->tun_ip_version == 4)
mlx5e_route_lookup_ipv4_put(&attr);
#if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6)
- else if (flow_attr->ip_version == 6)
+ else if (flow_attr->tun_ip_version == 6)
mlx5e_route_lookup_ipv6_put(&attr);
#endif
return err;
MLX5E_TC_TUNNEL_TYPE_MPLSOUDP,
};
+struct mlx5e_encap_key {
+ const struct ip_tunnel_key *ip_tun_key;
+ struct mlx5e_tc_tunnel *tc_tunnel;
+};
+
struct mlx5e_tc_tunnel {
int tunnel_type;
enum mlx5_flow_match_level match_level;
struct flow_cls_offload *f,
void *headers_c,
void *headers_v);
+ bool (*encap_info_equal)(struct mlx5e_encap_key *a,
+ struct mlx5e_encap_key *b);
};
extern struct mlx5e_tc_tunnel vxlan_tunnel;
void *headers_c,
void *headers_v);
+bool mlx5e_tc_tun_encap_info_equal_generic(struct mlx5e_encap_key *a,
+ struct mlx5e_encap_key *b);
+
#endif /* CONFIG_MLX5_ESWITCH */
#endif //__MLX5_EN_TC_TUNNEL_H__
* required to establish routing.
*/
flow_flag_set(flow, TUN_RX);
+ flow->attr->tun_ip_version = ip_version;
return 0;
}
mlx5e_decap_dealloc(priv, d);
}
-struct encap_key {
- const struct ip_tunnel_key *ip_tun_key;
- struct mlx5e_tc_tunnel *tc_tunnel;
-};
-
-static int cmp_encap_info(struct encap_key *a,
- struct encap_key *b)
+bool mlx5e_tc_tun_encap_info_equal_generic(struct mlx5e_encap_key *a,
+ struct mlx5e_encap_key *b)
{
- return memcmp(a->ip_tun_key, b->ip_tun_key, sizeof(*a->ip_tun_key)) ||
- a->tc_tunnel->tunnel_type != b->tc_tunnel->tunnel_type;
+ return memcmp(a->ip_tun_key, b->ip_tun_key, sizeof(*a->ip_tun_key)) == 0 &&
+ a->tc_tunnel->tunnel_type == b->tc_tunnel->tunnel_type;
}
static int cmp_decap_info(struct mlx5e_decap_key *a,
return memcmp(&a->key, &b->key, sizeof(b->key));
}
-static int hash_encap_info(struct encap_key *key)
+static int hash_encap_info(struct mlx5e_encap_key *key)
{
return jhash(key->ip_tun_key, sizeof(*key->ip_tun_key),
key->tc_tunnel->tunnel_type);
}
static struct mlx5e_encap_entry *
-mlx5e_encap_get(struct mlx5e_priv *priv, struct encap_key *key,
+mlx5e_encap_get(struct mlx5e_priv *priv, struct mlx5e_encap_key *key,
uintptr_t hash_key)
{
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+ struct mlx5e_encap_key e_key;
struct mlx5e_encap_entry *e;
- struct encap_key e_key;
hash_for_each_possible_rcu(esw->offloads.encap_tbl, e,
encap_hlist, hash_key) {
e_key.ip_tun_key = &e->tun_info->key;
e_key.tc_tunnel = e->tunnel;
- if (!cmp_encap_info(&e_key, key) &&
+ if (e->tunnel->encap_info_equal(&e_key, key) &&
mlx5e_encap_take(e))
return e;
}
struct mlx5_flow_attr *attr = flow->attr;
const struct ip_tunnel_info *tun_info;
unsigned long tbl_time_before = 0;
- struct encap_key key;
struct mlx5e_encap_entry *e;
+ struct mlx5e_encap_key key;
bool entry_created = false;
unsigned short family;
uintptr_t hash_key;
if (err || !esw_attr->rx_tun_attr->decap_vport)
goto out;
- key.ip_version = attr->ip_version;
+ key.ip_version = attr->tun_ip_version;
if (key.ip_version == 4)
key.endpoint_ip.v4 = esw_attr->rx_tun_attr->dst_ip.v4;
else
option_key = (struct geneve_opt *)&enc_opts.key->data[0];
option_mask = (struct geneve_opt *)&enc_opts.mask->data[0];
+ if (option_mask->opt_class == 0 && option_mask->type == 0 &&
+ !memchr_inv(option_mask->opt_data, 0, option_mask->length * 4))
+ return 0;
+
if (option_key->length > max_tlv_option_data_len) {
NL_SET_ERR_MSG_MOD(extack,
"Matching on GENEVE options: unsupported option len");
return mlx5e_tc_tun_parse_geneve_options(priv, spec, f);
}
+static bool mlx5e_tc_tun_encap_info_equal_geneve(struct mlx5e_encap_key *a,
+ struct mlx5e_encap_key *b)
+{
+ struct ip_tunnel_info *a_info;
+ struct ip_tunnel_info *b_info;
+ bool a_has_opts, b_has_opts;
+
+ if (!mlx5e_tc_tun_encap_info_equal_generic(a, b))
+ return false;
+
+ a_has_opts = !!(a->ip_tun_key->tun_flags & TUNNEL_GENEVE_OPT);
+ b_has_opts = !!(b->ip_tun_key->tun_flags & TUNNEL_GENEVE_OPT);
+
+ /* keys are equal when both don't have any options attached */
+ if (!a_has_opts && !b_has_opts)
+ return true;
+
+ if (a_has_opts != b_has_opts)
+ return false;
+
+ /* geneve options stored in memory next to ip_tunnel_info struct */
+ a_info = container_of(a->ip_tun_key, struct ip_tunnel_info, key);
+ b_info = container_of(b->ip_tun_key, struct ip_tunnel_info, key);
+
+ return a_info->options_len == b_info->options_len &&
+ memcmp(a_info + 1, b_info + 1, a_info->options_len) == 0;
+}
+
struct mlx5e_tc_tunnel geneve_tunnel = {
.tunnel_type = MLX5E_TC_TUNNEL_TYPE_GENEVE,
.match_level = MLX5_MATCH_L4,
.generate_ip_tun_hdr = mlx5e_gen_ip_tunnel_header_geneve,
.parse_udp_ports = mlx5e_tc_tun_parse_udp_ports_geneve,
.parse_tunnel = mlx5e_tc_tun_parse_geneve,
+ .encap_info_equal = mlx5e_tc_tun_encap_info_equal_geneve,
};
.generate_ip_tun_hdr = mlx5e_gen_ip_tunnel_header_gretap,
.parse_udp_ports = NULL,
.parse_tunnel = mlx5e_tc_tun_parse_gretap,
+ .encap_info_equal = mlx5e_tc_tun_encap_info_equal_generic,
};
.generate_ip_tun_hdr = generate_ip_tun_hdr,
.parse_udp_ports = parse_udp_ports,
.parse_tunnel = parse_tunnel,
+ .encap_info_equal = mlx5e_tc_tun_encap_info_equal_generic,
};
.generate_ip_tun_hdr = mlx5e_gen_ip_tunnel_header_vxlan,
.parse_udp_ports = mlx5e_tc_tun_parse_udp_ports_vxlan,
.parse_tunnel = mlx5e_tc_tun_parse_vxlan,
+ .encap_info_equal = mlx5e_tc_tun_encap_info_equal_generic,
};
return wqe_size * 2 - 1;
}
+static inline bool mlx5e_icosq_can_post_wqe(struct mlx5e_icosq *sq, u16 wqe_size)
+{
+ u16 room = sq->reserved_room + mlx5e_stop_room_for_wqe(wqe_size);
+
+ return mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, room);
+}
#endif
struct tls12_crypto_info_aes_gcm_128 crypto_info;
struct accel_rule rule;
struct sock *sk;
- struct mlx5e_rq_stats *stats;
+ struct mlx5e_rq_stats *rq_stats;
+ struct mlx5e_tls_sw_stats *sw_stats;
struct completion add_ctx;
u32 tirn;
u32 key_id;
{
struct mlx5e_set_tls_static_params_wqe *wqe;
struct mlx5e_icosq_wqe_info wi;
- u16 pi, num_wqebbs, room;
+ u16 pi, num_wqebbs;
num_wqebbs = MLX5E_TLS_SET_STATIC_PARAMS_WQEBBS;
- room = mlx5e_stop_room_for_wqe(num_wqebbs);
- if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, room)))
+ if (unlikely(!mlx5e_icosq_can_post_wqe(sq, num_wqebbs)))
return ERR_PTR(-ENOSPC);
pi = mlx5e_icosq_get_next_pi(sq, num_wqebbs);
{
struct mlx5e_set_tls_progress_params_wqe *wqe;
struct mlx5e_icosq_wqe_info wi;
- u16 pi, num_wqebbs, room;
+ u16 pi, num_wqebbs;
num_wqebbs = MLX5E_TLS_SET_PROGRESS_PARAMS_WQEBBS;
- room = mlx5e_stop_room_for_wqe(num_wqebbs);
- if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, room)))
+ if (unlikely(!mlx5e_icosq_can_post_wqe(sq, num_wqebbs)))
return ERR_PTR(-ENOSPC);
pi = mlx5e_icosq_get_next_pi(sq, num_wqebbs);
return err;
err_out:
- priv_rx->stats->tls_resync_req_skip++;
+ priv_rx->rq_stats->tls_resync_req_skip++;
err = PTR_ERR(cseg);
complete(&priv_rx->add_ctx);
goto unlock;
buf->priv_rx = priv_rx;
- BUILD_BUG_ON(MLX5E_KTLS_GET_PROGRESS_WQEBBS != 1);
-
spin_lock_bh(&sq->channel->async_icosq_lock);
- if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1))) {
+ if (unlikely(!mlx5e_icosq_can_post_wqe(sq, MLX5E_KTLS_GET_PROGRESS_WQEBBS))) {
spin_unlock_bh(&sq->channel->async_icosq_lock);
err = -ENOSPC;
goto err_dma_unmap;
}
- pi = mlx5e_icosq_get_next_pi(sq, 1);
+ pi = mlx5e_icosq_get_next_pi(sq, MLX5E_KTLS_GET_PROGRESS_WQEBBS);
wqe = MLX5E_TLS_FETCH_GET_PROGRESS_PARAMS_WQE(sq, pi);
#define GET_PSV_DS_CNT (DIV_ROUND_UP(sizeof(*wqe), MLX5_SEND_WQE_DS))
wi = (struct mlx5e_icosq_wqe_info) {
.wqe_type = MLX5E_ICOSQ_WQE_GET_PSV_TLS,
- .num_wqebbs = 1,
+ .num_wqebbs = MLX5E_KTLS_GET_PROGRESS_WQEBBS,
.tls_get_params.buf = buf,
};
icosq_fill_wi(sq, pi, &wi);
err_free:
kfree(buf);
err_out:
- priv_rx->stats->tls_resync_req_skip++;
+ priv_rx->rq_stats->tls_resync_req_skip++;
return err;
}
cseg = post_static_params(sq, priv_rx);
if (IS_ERR(cseg)) {
- priv_rx->stats->tls_resync_res_skip++;
+ priv_rx->rq_stats->tls_resync_res_skip++;
err = PTR_ERR(cseg);
goto unlock;
}
/* Do not increment priv_rx refcnt, CQE handling is empty */
mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg);
- priv_rx->stats->tls_resync_res_ok++;
+ priv_rx->rq_stats->tls_resync_res_ok++;
unlock:
spin_unlock_bh(&c->async_icosq_lock);
auth_state = MLX5_GET(tls_progress_params, ctx, auth_state);
if (tracker_state != MLX5E_TLS_PROGRESS_PARAMS_RECORD_TRACKER_STATE_TRACKING ||
auth_state != MLX5E_TLS_PROGRESS_PARAMS_AUTH_STATE_NO_OFFLOAD) {
- priv_rx->stats->tls_resync_req_skip++;
+ priv_rx->rq_stats->tls_resync_req_skip++;
goto out;
}
hw_seq = MLX5_GET(tls_progress_params, ctx, hw_resync_tcp_sn);
tls_offload_rx_resync_async_request_end(priv_rx->sk, cpu_to_be32(hw_seq));
- priv_rx->stats->tls_resync_req_end++;
+ priv_rx->rq_stats->tls_resync_req_end++;
out:
mlx5e_ktls_priv_rx_put(priv_rx);
dma_unmap_single(dev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE);
priv_rx->rxq = rxq;
priv_rx->sk = sk;
- priv_rx->stats = &priv->channel_stats[rxq].rq;
+ priv_rx->rq_stats = &priv->channel_stats[rxq].rq;
+ priv_rx->sw_stats = &priv->tls->sw_stats;
mlx5e_set_ktls_rx_priv_ctx(tls_ctx, priv_rx);
rqtn = priv->direct_tir[rxq].rqt.rqtn;
if (err)
goto err_post_wqes;
- priv_rx->stats->tls_ctx++;
+ atomic64_inc(&priv_rx->sw_stats->rx_tls_ctx);
return 0;
if (cancel_work_sync(&resync->work))
mlx5e_ktls_priv_rx_put(priv_rx);
- priv_rx->stats->tls_del++;
+ atomic64_inc(&priv_rx->sw_stats->rx_tls_del);
if (priv_rx->rule.rule)
mlx5e_accel_fs_del_sk(priv_rx->rule.rule);
// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
// Copyright (c) 2019 Mellanox Technologies.
+#include "en_accel/tls.h"
#include "en_accel/ktls_txrx.h"
#include "en_accel/ktls_utils.h"
struct mlx5e_ktls_offload_context_tx {
struct tls_offload_context_tx *tx_ctx;
struct tls12_crypto_info_aes_gcm_128 crypto_info;
+ struct mlx5e_tls_sw_stats *sw_stats;
u32 expected_seq;
u32 tisn;
u32 key_id;
if (err)
goto err_create_key;
+ priv_tx->sw_stats = &priv->tls->sw_stats;
priv_tx->expected_seq = start_offload_tcp_sn;
priv_tx->crypto_info =
*(struct tls12_crypto_info_aes_gcm_128 *)crypto_info;
goto err_create_tis;
priv_tx->ctx_post_pending = true;
+ atomic64_inc(&priv_tx->sw_stats->tx_tls_ctx);
return 0;
if (unlikely(mlx5e_ktls_tx_offload_test_and_clear_pending(priv_tx))) {
mlx5e_ktls_tx_post_param_wqes(sq, priv_tx, false, false);
- stats->tls_ctx++;
}
seq = ntohl(tcp_hdr(skb)->seq);
#include "en.h"
struct mlx5e_tls_sw_stats {
+ atomic64_t tx_tls_ctx;
atomic64_t tx_tls_drop_metadata;
atomic64_t tx_tls_drop_resync_alloc;
atomic64_t tx_tls_drop_no_sync_data;
atomic64_t tx_tls_drop_bypass_required;
+ atomic64_t rx_tls_ctx;
+ atomic64_t rx_tls_del;
atomic64_t rx_tls_drop_resync_request;
atomic64_t rx_tls_resync_request;
atomic64_t rx_tls_resync_reply;
{ MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_drop_bypass_required) },
};
+static const struct counter_desc mlx5e_ktls_sw_stats_desc[] = {
+ { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_ctx) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, rx_tls_ctx) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, rx_tls_del) },
+};
+
#define MLX5E_READ_CTR_ATOMIC64(ptr, dsc, i) \
atomic64_read((atomic64_t *)((char *)(ptr) + (dsc)[i].offset))
-#define NUM_TLS_SW_COUNTERS ARRAY_SIZE(mlx5e_tls_sw_stats_desc)
-
-static bool is_tls_atomic_stats(struct mlx5e_priv *priv)
+static const struct counter_desc *get_tls_atomic_stats(struct mlx5e_priv *priv)
{
- return priv->tls && !mlx5_accel_is_ktls_device(priv->mdev);
+ if (!priv->tls)
+ return NULL;
+ if (mlx5_accel_is_ktls_device(priv->mdev))
+ return mlx5e_ktls_sw_stats_desc;
+ return mlx5e_tls_sw_stats_desc;
}
int mlx5e_tls_get_count(struct mlx5e_priv *priv)
{
- if (!is_tls_atomic_stats(priv))
+ if (!priv->tls)
return 0;
-
- return NUM_TLS_SW_COUNTERS;
+ if (mlx5_accel_is_ktls_device(priv->mdev))
+ return ARRAY_SIZE(mlx5e_ktls_sw_stats_desc);
+ return ARRAY_SIZE(mlx5e_tls_sw_stats_desc);
}
int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data)
{
- unsigned int i, idx = 0;
+ const struct counter_desc *stats_desc;
+ unsigned int i, n, idx = 0;
- if (!is_tls_atomic_stats(priv))
- return 0;
+ stats_desc = get_tls_atomic_stats(priv);
+ n = mlx5e_tls_get_count(priv);
- for (i = 0; i < NUM_TLS_SW_COUNTERS; i++)
+ for (i = 0; i < n; i++)
strcpy(data + (idx++) * ETH_GSTRING_LEN,
- mlx5e_tls_sw_stats_desc[i].format);
+ stats_desc[i].format);
- return NUM_TLS_SW_COUNTERS;
+ return n;
}
int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data)
{
- int i, idx = 0;
+ const struct counter_desc *stats_desc;
+ unsigned int i, n, idx = 0;
- if (!is_tls_atomic_stats(priv))
- return 0;
+ stats_desc = get_tls_atomic_stats(priv);
+ n = mlx5e_tls_get_count(priv);
- for (i = 0; i < NUM_TLS_SW_COUNTERS; i++)
+ for (i = 0; i < n; i++)
data[idx++] =
MLX5E_READ_CTR_ATOMIC64(&priv->tls->sw_stats,
- mlx5e_tls_sw_stats_desc, i);
+ stats_desc, i);
- return NUM_TLS_SW_COUNTERS;
+ return n;
}
return 0;
}
-static void ptys2ethtool_supported_advertised_port(struct ethtool_link_ksettings *link_ksettings,
- u32 eth_proto_cap,
- u8 connector_type, bool ext)
+static void ptys2ethtool_supported_advertised_port(struct mlx5_core_dev *mdev,
+ struct ethtool_link_ksettings *link_ksettings,
+ u32 eth_proto_cap, u8 connector_type)
{
- if ((!connector_type && !ext) || connector_type >= MLX5E_CONNECTOR_TYPE_NUMBER) {
+ if (!MLX5_CAP_PCAM_FEATURE(mdev, ptys_connector_type)) {
if (eth_proto_cap & (MLX5E_PROT_MASK(MLX5E_10GBASE_CR)
| MLX5E_PROT_MASK(MLX5E_10GBASE_SR)
| MLX5E_PROT_MASK(MLX5E_40GBASE_CR4)
[MLX5E_PORT_OTHER] = PORT_OTHER,
};
-static u8 get_connector_port(u32 eth_proto, u8 connector_type, bool ext)
+static u8 get_connector_port(struct mlx5_core_dev *mdev, u32 eth_proto, u8 connector_type)
{
- if ((connector_type || ext) && connector_type < MLX5E_CONNECTOR_TYPE_NUMBER)
+ if (MLX5_CAP_PCAM_FEATURE(mdev, ptys_connector_type))
return ptys2connector_type[connector_type];
if (eth_proto &
data_rate_oper, link_ksettings);
eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap;
-
- link_ksettings->base.port = get_connector_port(eth_proto_oper,
- connector_type, ext);
- ptys2ethtool_supported_advertised_port(link_ksettings, eth_proto_admin,
- connector_type, ext);
+ connector_type = connector_type < MLX5E_CONNECTOR_TYPE_NUMBER ?
+ connector_type : MLX5E_PORT_UNKNOWN;
+ link_ksettings->base.port = get_connector_port(mdev, eth_proto_oper, connector_type);
+ ptys2ethtool_supported_advertised_port(mdev, link_ksettings, eth_proto_admin,
+ connector_type);
get_lp_advertising(mdev, eth_proto_lp, link_ksettings);
if (an_status == MLX5_AN_COMPLETE)
{
struct mlx5e_priv *priv = netdev_priv(netdev);
struct mlx5_core_dev *mdev = priv->mdev;
+ int err;
if (!MLX5_CAP_GEN(mdev, cqe_compression))
return -EOPNOTSUPP;
return -EINVAL;
}
- mlx5e_modify_rx_cqe_compression_locked(priv, enable);
+ err = mlx5e_modify_rx_cqe_compression_locked(priv, enable);
+ if (err)
+ return err;
+
priv->channels.params.rx_cqe_compress_def = enable;
return 0;
*/
if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+ struct mlx5e_params old_params;
+
+ old_params = priv->channels.params;
priv->channels.params = new_channels.params;
err = mlx5e_num_channels_changed(priv);
+ if (err)
+ priv->channels.params = old_params;
goto out;
}
rq->wqe_overflow.addr);
}
-static inline u64 mlx5e_get_mpwqe_offset(struct mlx5e_rq *rq, u16 wqe_ix)
+static u64 mlx5e_get_mpwqe_offset(u16 wqe_ix)
{
- return (wqe_ix << MLX5E_LOG_ALIGNED_MPWQE_PPW) << PAGE_SHIFT;
+ return MLX5E_REQUIRED_MTTS(wqe_ix) << PAGE_SHIFT;
}
static void mlx5e_init_frags_partition(struct mlx5e_rq *rq)
mlx5_wq_ll_get_wqe(&rq->mpwqe.wq, i);
u32 byte_count =
rq->mpwqe.num_strides << rq->mpwqe.log_stride_sz;
- u64 dma_offset = mlx5e_get_mpwqe_offset(rq, i);
+ u64 dma_offset = mlx5e_get_mpwqe_offset(i);
wqe->data[0].addr = cpu_to_be64(dma_offset + rq->buff.headroom);
wqe->data[0].byte_count = cpu_to_be32(byte_count);
sq->channel = c;
sq->uar_map = mdev->mlx5e_res.bfreg.map;
+ sq->reserved_room = param->stop_room;
param->wq.db_numa_node = cpu_to_node(c->cpu);
err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, wq, &sq->wq_ctrl);
mlx5e_build_ico_cq_param(priv, log_wq_size, ¶m->cqp);
}
+static void mlx5e_build_async_icosq_param(struct mlx5e_priv *priv,
+ struct mlx5e_params *params,
+ u8 log_wq_size,
+ struct mlx5e_sq_param *param)
+{
+ void *sqc = param->sqc;
+ void *wq = MLX5_ADDR_OF(sqc, sqc, wq);
+
+ mlx5e_build_sq_param_common(priv, param);
+
+ /* async_icosq is used by XSK only if xdp_prog is active */
+ if (params->xdp_prog)
+ param->stop_room = mlx5e_stop_room_for_wqe(1); /* for XSK NOP */
+ MLX5_SET(sqc, sqc, reg_umr, MLX5_CAP_ETH(priv->mdev, reg_umr_sq));
+ MLX5_SET(wq, wq, log_wq_sz, log_wq_size);
+ mlx5e_build_ico_cq_param(priv, log_wq_size, ¶m->cqp);
+}
+
void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv,
struct mlx5e_params *params,
struct mlx5e_sq_param *param)
{
switch (params->rq_wq_type) {
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
- return order_base_2(MLX5E_UMR_WQEBBS) +
- mlx5e_get_rq_log_wq_sz(rqp->rqc);
+ return max_t(u8, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE,
+ order_base_2(MLX5E_UMR_WQEBBS) +
+ mlx5e_get_rq_log_wq_sz(rqp->rqc));
default: /* MLX5_WQ_TYPE_CYCLIC */
return MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE;
}
mlx5e_build_sq_param(priv, params, &cparam->txq_sq);
mlx5e_build_xdpsq_param(priv, params, &cparam->xdp_sq);
mlx5e_build_icosq_param(priv, icosq_log_wq_sz, &cparam->icosq);
- mlx5e_build_icosq_param(priv, async_icosq_log_wq_sz, &cparam->async_icosq);
+ mlx5e_build_async_icosq_param(priv, params, async_icosq_log_wq_sz, &cparam->async_icosq);
}
int mlx5e_open_channels(struct mlx5e_priv *priv,
{
int i;
- if (chs->port_ptp)
+ if (chs->port_ptp) {
mlx5e_port_ptp_close(chs->port_ptp);
+ chs->port_ptp = NULL;
+ }
for (i = 0; i < chs->num; i++)
mlx5e_close_channel(chs->c[i]);
s->tx_dropped += sq_stats->dropped;
}
}
+ if (priv->port_ptp_opened) {
+ for (i = 0; i < priv->max_opened_tc; i++) {
+ struct mlx5e_sq_stats *sq_stats = &priv->port_ptp_stats.sq[i];
+
+ s->tx_packets += sq_stats->packets;
+ s->tx_bytes += sq_stats->bytes;
+ s->tx_dropped += sq_stats->dropped;
+ }
+ }
}
void
}
if (mlx5e_is_uplink_rep(priv)) {
+ struct mlx5e_vport_stats *vstats = &priv->stats.vport;
+
stats->rx_packets = PPORT_802_3_GET(pstats, a_frames_received_ok);
stats->rx_bytes = PPORT_802_3_GET(pstats, a_octets_received_ok);
stats->tx_packets = PPORT_802_3_GET(pstats, a_frames_transmitted_ok);
stats->tx_bytes = PPORT_802_3_GET(pstats, a_octets_transmitted_ok);
+
+ /* vport multicast also counts packets that are dropped due to steering
+ * or rx out of buffer
+ */
+ stats->multicast = VPORT_COUNTER_GET(vstats, received_eth_multicast.packets);
} else {
mlx5e_fold_sw_stats64(priv, stats);
}
struct mlx5e_channel *c = priv->channels.c[i];
mlx5e_rq_replace_xdp_prog(&c->rq, prog);
- if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state))
+ if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)) {
+ bpf_prog_inc(prog);
mlx5e_rq_replace_xdp_prog(&c->xskrq, prog);
+ }
}
unlock:
priv->max_nch);
params->num_tc = 1;
+ /* Set an initial non-zero value, so that mlx5e_select_queue won't
+ * divide by zero if called before first activating channels.
+ */
+ priv->num_tc_x_num_ch = params->num_channels * params->num_tc;
+
/* SQ */
params->log_sq_size = is_kdump_kernel() ?
MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE :
struct net_device *netdev,
struct mlx5_core_dev *mdev)
{
- memset(priv, 0, sizeof(*priv));
-
/* priv init */
priv->mdev = mdev;
priv->netdev = netdev;
{
int i;
+ /* bail if change profile failed and also rollback failed */
+ if (!priv->mdev)
+ return;
+
destroy_workqueue(priv->wq);
free_cpumask_var(priv->scratchpad.cpumask);
for (i = 0; i < priv->htb.max_qos_sqs; i++)
kfree(priv->htb.qos_sq_stats[i]);
kvfree(priv->htb.qos_sq_stats);
+
+ memset(priv, 0, sizeof(*priv));
}
struct net_device *
}
static int
-mlx5e_netdev_attach_profile(struct mlx5e_priv *priv,
+mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mdev,
const struct mlx5e_profile *new_profile, void *new_ppriv)
{
- struct net_device *netdev = priv->netdev;
- struct mlx5_core_dev *mdev = priv->mdev;
+ struct mlx5e_priv *priv = netdev_priv(netdev);
int err;
err = mlx5e_priv_init(priv, netdev, mdev);
priv->ppriv = new_ppriv;
err = new_profile->init(priv->mdev, priv->netdev);
if (err)
- return err;
+ goto priv_cleanup;
err = mlx5e_attach_netdev(priv);
if (err)
- new_profile->cleanup(priv);
+ goto profile_cleanup;
+ return err;
+
+profile_cleanup:
+ new_profile->cleanup(priv);
+priv_cleanup:
+ mlx5e_priv_cleanup(priv);
return err;
}
{
unsigned int new_max_nch = mlx5e_calc_max_nch(priv, new_profile);
const struct mlx5e_profile *orig_profile = priv->profile;
+ struct net_device *netdev = priv->netdev;
+ struct mlx5_core_dev *mdev = priv->mdev;
void *orig_ppriv = priv->ppriv;
int err, rollback_err;
/* sanity */
if (new_max_nch != priv->max_nch) {
- netdev_warn(priv->netdev,
- "%s: Replacing profile with different max channels\n",
+ netdev_warn(netdev, "%s: Replacing profile with different max channels\n",
__func__);
return -EINVAL;
}
priv->profile->cleanup(priv);
mlx5e_priv_cleanup(priv);
- err = mlx5e_netdev_attach_profile(priv, new_profile, new_ppriv);
+ err = mlx5e_netdev_attach_profile(netdev, mdev, new_profile, new_ppriv);
if (err) { /* roll back to original profile */
- netdev_warn(priv->netdev, "%s: new profile init failed, %d\n",
- __func__, err);
+ netdev_warn(netdev, "%s: new profile init failed, %d\n", __func__, err);
goto rollback;
}
return 0;
rollback:
- rollback_err = mlx5e_netdev_attach_profile(priv, orig_profile, orig_ppriv);
- if (rollback_err) {
- netdev_err(priv->netdev,
- "%s: failed to rollback to orig profile, %d\n",
+ rollback_err = mlx5e_netdev_attach_profile(netdev, mdev, orig_profile, orig_ppriv);
+ if (rollback_err)
+ netdev_err(netdev, "%s: failed to rollback to orig profile, %d\n",
__func__, rollback_err);
- }
return err;
}
mlx5e_rep_tc_enable(priv);
- mlx5_modify_vport_admin_state(mdev, MLX5_VPORT_STATE_OP_MOD_UPLINK,
- 0, 0, MLX5_VPORT_ADMIN_STATE_AUTO);
+ if (MLX5_CAP_GEN(mdev, uplink_follow))
+ mlx5_modify_vport_admin_state(mdev, MLX5_VPORT_STATE_OP_MOD_UPLINK,
+ 0, 0, MLX5_VPORT_ADMIN_STATE_AUTO);
mlx5_lag_add(mdev, netdev);
priv->events_nb.notifier_call = uplink_rep_async_event;
mlx5_notifier_register(mdev, &priv->events_nb);
struct mlx5e_icosq *sq = rq->icosq;
struct mlx5_wq_cyc *wq = &sq->wq;
struct mlx5e_umr_wqe *umr_wqe;
- u16 xlt_offset = ix << (MLX5E_LOG_ALIGNED_MPWQE_PPW - 1);
u16 pi;
int err;
int i;
umr_wqe->ctrl.opmod_idx_opcode =
cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) |
MLX5_OPCODE_UMR);
- umr_wqe->uctrl.xlt_offset = cpu_to_be16(xlt_offset);
+ umr_wqe->uctrl.xlt_offset =
+ cpu_to_be16(MLX5_ALIGNED_MTTS_OCTW(MLX5E_REQUIRED_MTTS(ix)));
sq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) {
.wqe_type = MLX5E_ICOSQ_WQE_UMR_RX,
#ifdef CONFIG_MLX5_EN_TLS
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_encrypted_packets) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_encrypted_bytes) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ctx) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ooo) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_dump_packets) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_dump_bytes) },
#ifdef CONFIG_MLX5_EN_TLS
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_decrypted_packets) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_decrypted_bytes) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_ctx) },
- { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_del) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_resync_req_pkt) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_resync_req_start) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_resync_req_end) },
#ifdef CONFIG_MLX5_EN_TLS
s->rx_tls_decrypted_packets += rq_stats->tls_decrypted_packets;
s->rx_tls_decrypted_bytes += rq_stats->tls_decrypted_bytes;
- s->rx_tls_ctx += rq_stats->tls_ctx;
- s->rx_tls_del += rq_stats->tls_del;
s->rx_tls_resync_req_pkt += rq_stats->tls_resync_req_pkt;
s->rx_tls_resync_req_start += rq_stats->tls_resync_req_start;
s->rx_tls_resync_req_end += rq_stats->tls_resync_req_end;
#ifdef CONFIG_MLX5_EN_TLS
s->tx_tls_encrypted_packets += sq_stats->tls_encrypted_packets;
s->tx_tls_encrypted_bytes += sq_stats->tls_encrypted_bytes;
- s->tx_tls_ctx += sq_stats->tls_ctx;
s->tx_tls_ooo += sq_stats->tls_ooo;
s->tx_tls_dump_bytes += sq_stats->tls_dump_bytes;
s->tx_tls_dump_packets += sq_stats->tls_dump_packets;
#ifdef CONFIG_MLX5_EN_TLS
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_decrypted_packets) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_decrypted_bytes) },
- { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_ctx) },
- { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_del) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_resync_req_pkt) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_resync_req_start) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_resync_req_end) },
#ifdef CONFIG_MLX5_EN_TLS
{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_encrypted_packets) },
{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_encrypted_bytes) },
- { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_ctx) },
{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_ooo) },
{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_dump_packets) },
{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_dump_bytes) },
#ifdef CONFIG_MLX5_EN_TLS
{ MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, tls_encrypted_packets) },
{ MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, tls_encrypted_bytes) },
- { MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, tls_ctx) },
{ MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, tls_ooo) },
{ MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, tls_dump_packets) },
{ MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, tls_dump_bytes) },
#ifdef CONFIG_MLX5_EN_TLS
u64 tx_tls_encrypted_packets;
u64 tx_tls_encrypted_bytes;
- u64 tx_tls_ctx;
u64 tx_tls_ooo;
u64 tx_tls_dump_packets;
u64 tx_tls_dump_bytes;
u64 rx_tls_decrypted_packets;
u64 rx_tls_decrypted_bytes;
- u64 rx_tls_ctx;
- u64 rx_tls_del;
u64 rx_tls_resync_req_pkt;
u64 rx_tls_resync_req_start;
u64 rx_tls_resync_req_end;
#ifdef CONFIG_MLX5_EN_TLS
u64 tls_decrypted_packets;
u64 tls_decrypted_bytes;
- u64 tls_ctx;
- u64 tls_del;
u64 tls_resync_req_pkt;
u64 tls_resync_req_start;
u64 tls_resync_req_end;
#ifdef CONFIG_MLX5_EN_TLS
u64 tls_encrypted_packets;
u64 tls_encrypted_bytes;
- u64 tls_ctx;
u64 tls_ooo;
u64 tls_dump_packets;
u64 tls_dump_bytes;
return 0;
flow_rule_match_meta(rule, &match);
+ if (!match.mask->ingress_ifindex)
+ return 0;
+
if (match.mask->ingress_ifindex != 0xFFFFFFFF) {
NL_SET_ERR_MSG_MOD(extack, "Unsupported ingress ifindex mask");
return -EOPNOTSUPP;
*match_level = MLX5_MATCH_L4;
}
+ /* Currenlty supported only for MPLS over UDP */
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_MPLS) &&
+ !netif_is_bareudp(filter_dev)) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Matching on MPLS is supported only for MPLS over UDP");
+ netdev_err(priv->netdev,
+ "Matching on MPLS is supported only for MPLS over UDP\n");
+ return -EOPNOTSUPP;
+ }
+
return 0;
}
return 0;
}
+static bool modify_tuple_supported(bool modify_tuple, bool ct_clear,
+ bool ct_flow, struct netlink_ext_ack *extack,
+ struct mlx5e_priv *priv,
+ struct mlx5_flow_spec *spec)
+{
+ if (!modify_tuple || ct_clear)
+ return true;
+
+ if (ct_flow) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "can't offload tuple modification with non-clear ct()");
+ netdev_info(priv->netdev,
+ "can't offload tuple modification with non-clear ct()");
+ return false;
+ }
+
+ /* Add ct_state=-trk match so it will be offloaded for non ct flows
+ * (or after clear action), as otherwise, since the tuple is changed,
+ * we can't restore ct state
+ */
+ if (mlx5_tc_ct_add_no_trk_match(spec)) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "can't offload tuple modification with ct matches and no ct(clear) action");
+ netdev_info(priv->netdev,
+ "can't offload tuple modification with ct matches and no ct(clear) action");
+ return false;
+ }
+
+ return true;
+}
+
static bool modify_header_match_supported(struct mlx5e_priv *priv,
struct mlx5_flow_spec *spec,
struct flow_action *flow_action,
return err;
}
- /* Add ct_state=-trk match so it will be offloaded for non ct flows
- * (or after clear action), as otherwise, since the tuple is changed,
- * we can't restore ct state
- */
- if (!ct_clear && modify_tuple &&
- mlx5_tc_ct_add_no_trk_match(spec)) {
- NL_SET_ERR_MSG_MOD(extack,
- "can't offload tuple modify header with ct matches");
- netdev_info(priv->netdev,
- "can't offload tuple modify header with ct matches");
+ if (!modify_tuple_supported(modify_tuple, ct_clear, ct_flow, extack,
+ priv, spec))
return false;
- }
ip_proto = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ip_protocol);
if (modify_ip_header && ip_proto != IPPROTO_TCP &&
*/
if (rate) {
rate = (rate * BITS_PER_BYTE) + 500000;
- rate_mbps = max_t(u64, do_div(rate, 1000000), 1);
+ do_div(rate, 1000000);
+ rate_mbps = max_t(u32, rate, 1);
}
err = mlx5_esw_modify_vport_rate(esw, vport_num, rate_mbps);
u8 inner_match_level;
u8 outer_match_level;
u8 ip_version;
+ u8 tun_ip_version;
u32 flags;
union {
struct mlx5_esw_flow_attr esw_attr[0];
mutex_unlock(&table->lock);
}
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#define MLX5_MAX_ASYNC_EQS 4
+#else
+#define MLX5_MAX_ASYNC_EQS 3
+#endif
+
int mlx5_eq_table_create(struct mlx5_core_dev *dev)
{
struct mlx5_eq_table *eq_table = dev->priv.eq_table;
+ int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ?
+ MLX5_CAP_GEN(dev, max_num_eqs) :
+ 1 << MLX5_CAP_GEN(dev, log_max_eq);
int err;
eq_table->num_comp_eqs =
- mlx5_irq_get_num_comp(eq_table->irq_table);
+ min_t(int,
+ mlx5_irq_get_num_comp(eq_table->irq_table),
+ num_eqs - MLX5_MAX_ASYNC_EQS);
err = create_async_eqs(dev);
if (err) {
err_ethertype:
kfree(rule);
out:
- kfree(rule_spec);
+ kvfree(rule_spec);
return err;
}
e->recirc_cnt = 0;
out:
- kfree(in);
+ kvfree(in);
return err;
}
spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
if (!spec) {
- kfree(in);
+ kvfree(in);
return -ENOMEM;
}
}
err_out:
- kfree(spec);
- kfree(in);
+ kvfree(spec);
+ kvfree(in);
return err;
}
return i;
}
+static bool
+esw_src_port_rewrite_supported(struct mlx5_eswitch *esw)
+{
+ return MLX5_CAP_GEN(esw->dev, reg_c_preserve) &&
+ mlx5_eswitch_vport_match_metadata_enabled(esw) &&
+ MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ignore_flow_level);
+}
+
static int
esw_setup_dests(struct mlx5_flow_destination *dest,
struct mlx5_flow_act *flow_act,
int err = 0;
if (!mlx5_eswitch_termtbl_required(esw, attr, flow_act, spec) &&
- MLX5_CAP_GEN(esw_attr->in_mdev, reg_c_preserve) &&
- mlx5_eswitch_vport_match_metadata_enabled(esw))
+ esw_src_port_rewrite_supported(esw))
attr->flags |= MLX5_ESW_ATTR_FLAG_SRC_REWRITE;
if (attr->dest_ft) {
}
esw->fdb_table.offloads.send_to_vport_grp = g;
- /* meta send to vport */
- memset(flow_group_in, 0, inlen);
- MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
- MLX5_MATCH_MISC_PARAMETERS_2);
-
- match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria);
+ if (esw_src_port_rewrite_supported(esw)) {
+ /* meta send to vport */
+ memset(flow_group_in, 0, inlen);
+ MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
+ MLX5_MATCH_MISC_PARAMETERS_2);
- MLX5_SET(fte_match_param, match_criteria,
- misc_parameters_2.metadata_reg_c_0, mlx5_eswitch_get_vport_metadata_mask());
- MLX5_SET(fte_match_param, match_criteria,
- misc_parameters_2.metadata_reg_c_1, ESW_TUN_MASK);
+ match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria);
- num_vfs = esw->esw_funcs.num_vfs;
- if (num_vfs) {
- MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
- MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ix + num_vfs - 1);
- ix += num_vfs;
+ MLX5_SET(fte_match_param, match_criteria,
+ misc_parameters_2.metadata_reg_c_0,
+ mlx5_eswitch_get_vport_metadata_mask());
+ MLX5_SET(fte_match_param, match_criteria,
+ misc_parameters_2.metadata_reg_c_1, ESW_TUN_MASK);
- g = mlx5_create_flow_group(fdb, flow_group_in);
- if (IS_ERR(g)) {
- err = PTR_ERR(g);
- esw_warn(dev, "Failed to create send-to-vport meta flow group err(%d)\n",
- err);
- goto send_vport_meta_err;
+ num_vfs = esw->esw_funcs.num_vfs;
+ if (num_vfs) {
+ MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
+ MLX5_SET(create_flow_group_in, flow_group_in,
+ end_flow_index, ix + num_vfs - 1);
+ ix += num_vfs;
+
+ g = mlx5_create_flow_group(fdb, flow_group_in);
+ if (IS_ERR(g)) {
+ err = PTR_ERR(g);
+ esw_warn(dev, "Failed to create send-to-vport meta flow group err(%d)\n",
+ err);
+ goto send_vport_meta_err;
+ }
+ esw->fdb_table.offloads.send_to_vport_meta_grp = g;
+
+ err = mlx5_eswitch_add_send_to_vport_meta_rules(esw);
+ if (err)
+ goto meta_rule_err;
}
- esw->fdb_table.offloads.send_to_vport_meta_grp = g;
-
- err = mlx5_eswitch_add_send_to_vport_meta_rules(esw);
- if (err)
- goto meta_rule_err;
}
if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) {
MLX5_SET(qpc, qpc, log_sq_size, ilog2(conn->qp.sq.size));
MLX5_SET(qpc, qpc, cqn_snd, conn->cq.mcq.cqn);
MLX5_SET(qpc, qpc, cqn_rcv, conn->cq.mcq.cqn);
+ MLX5_SET(qpc, qpc, ts_format, mlx5_get_qp_default_ts(mdev));
MLX5_SET64(qpc, qpc, dbr_addr, conn->qp.wq_ctrl.db.dma);
if (MLX5_CAP_GEN(mdev, cqe_version) == 1)
MLX5_SET(qpc, qpc, user_index, 0xFFFFFF);
}
qpc = MLX5_ADDR_OF(create_qp_in, in, qpc);
+ MLX5_SET(qpc, qpc, ts_format, mlx5_get_qp_default_ts(priv->mdev));
MLX5_SET(qpc, qpc, st, MLX5_QP_ST_UD);
MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED);
MLX5_SET(qpc, qpc, ulp_stateless_offload_mode,
static void mlx5_rdma_netdev_free(struct net_device *netdev)
{
struct mlx5e_priv *priv = mlx5i_epriv(netdev);
+ struct mlx5_core_dev *mdev = priv->mdev;
struct mlx5i_priv *ipriv = priv->ppriv;
const struct mlx5e_profile *profile = priv->profile;
if (!ipriv->sub_interface) {
mlx5i_pkey_qpn_ht_cleanup(netdev);
- mlx5e_destroy_mdev_resources(priv->mdev);
+ mlx5e_destroy_mdev_resources(mdev);
}
}
return -EINVAL;
field_select = MLX5_MTPPS_FS_ENABLE;
+ pin = ptp_find_pin(clock->ptp, PTP_PF_PEROUT, rq->perout.index);
+ if (pin < 0)
+ return -EBUSY;
+
if (on) {
bool rt_mode = mlx5_real_time_mode(mdev);
u32 nsec;
s64 sec;
- pin = ptp_find_pin(clock->ptp, PTP_PF_PEROUT, rq->perout.index);
- if (pin < 0)
- return -EBUSY;
-
pin_mode = MLX5_PIN_MODE_OUT;
pattern = MLX5_OUT_PATTERN_PERIODIC;
ts.tv_sec = rq->perout.period.sec;
u16 max_functions;
u16 function_id;
int err = 0;
- bool ecpu;
int i;
max_functions = mlx5_sf_max_functions(dev);
function_id = MLX5_CAP_GEN(dev, sf_base_id);
- ecpu = mlx5_read_embedded_cpu(dev);
/* Arm the vhca context as the vhca event notifier */
for (i = 0; i < max_functions; i++) {
- err = mlx5_vhca_event_arm(dev, function_id, ecpu);
+ err = mlx5_vhca_event_arm(dev, function_id);
if (err)
return err;
#include "sf.h"
#include "mlx5_ifc_vhca_event.h"
#include "vhca_event.h"
-#include "ecpf.h"
+#include "mlx5_core.h"
struct mlx5_sf_hw {
u32 usr_sfnum;
struct mlx5_core_dev *dev;
struct mlx5_sf_hw *sfs;
int max_local_functions;
- u8 ecpu: 1;
struct mutex table_lock; /* Serializes sf deletion and vhca state change handler. */
struct notifier_block vhca_nb;
};
}
if (sw_id == -ENOSPC) {
err = -ENOSPC;
- goto err;
+ goto exist_err;
}
hw_fn_id = mlx5_sf_sw_to_hw_id(table->dev, sw_id);
if (err)
goto err;
- err = mlx5_modify_vhca_sw_id(dev, hw_fn_id, table->ecpu, usr_sfnum);
+ err = mlx5_modify_vhca_sw_id(dev, hw_fn_id, usr_sfnum);
if (err)
goto vhca_err;
hw_fn_id = mlx5_sf_sw_to_hw_id(dev, id);
mutex_lock(&table->table_lock);
- err = mlx5_cmd_query_vhca_state(dev, hw_fn_id, table->ecpu, out, sizeof(out));
+ err = mlx5_cmd_query_vhca_state(dev, hw_fn_id, out, sizeof(out));
if (err)
goto err;
state = MLX5_GET(query_vhca_state_out, out, vhca_state_context.vhca_state);
table->dev = dev;
table->sfs = sfs;
table->max_local_functions = max_functions;
- table->ecpu = mlx5_read_embedded_cpu(dev);
dev->priv.sf_hw_table = table;
mlx5_core_dbg(dev, "SF HW table: max sfs = %d\n", max_functions);
return 0;
u8 sw_function_id[0x20];
- u8 reserved_at_40[0x80];
+ u8 reserved_at_40[0x40];
};
struct mlx5_ifc_query_vhca_state_out_bits {
struct mlx5_vhca_state_event event;
};
-int mlx5_cmd_query_vhca_state(struct mlx5_core_dev *dev, u16 function_id,
- bool ecpu, u32 *out, u32 outlen)
+int mlx5_cmd_query_vhca_state(struct mlx5_core_dev *dev, u16 function_id, u32 *out, u32 outlen)
{
u32 in[MLX5_ST_SZ_DW(query_vhca_state_in)] = {};
MLX5_SET(query_vhca_state_in, in, opcode, MLX5_CMD_OP_QUERY_VHCA_STATE);
MLX5_SET(query_vhca_state_in, in, function_id, function_id);
- MLX5_SET(query_vhca_state_in, in, embedded_cpu_function, ecpu);
+ MLX5_SET(query_vhca_state_in, in, embedded_cpu_function, 0);
return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
}
static int mlx5_cmd_modify_vhca_state(struct mlx5_core_dev *dev, u16 function_id,
- bool ecpu, u32 *in, u32 inlen)
+ u32 *in, u32 inlen)
{
u32 out[MLX5_ST_SZ_DW(modify_vhca_state_out)] = {};
MLX5_SET(modify_vhca_state_in, in, opcode, MLX5_CMD_OP_MODIFY_VHCA_STATE);
MLX5_SET(modify_vhca_state_in, in, function_id, function_id);
- MLX5_SET(modify_vhca_state_in, in, embedded_cpu_function, ecpu);
+ MLX5_SET(modify_vhca_state_in, in, embedded_cpu_function, 0);
return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
}
-int mlx5_modify_vhca_sw_id(struct mlx5_core_dev *dev, u16 function_id, bool ecpu, u32 sw_fn_id)
+int mlx5_modify_vhca_sw_id(struct mlx5_core_dev *dev, u16 function_id, u32 sw_fn_id)
{
u32 out[MLX5_ST_SZ_DW(modify_vhca_state_out)] = {};
u32 in[MLX5_ST_SZ_DW(modify_vhca_state_in)] = {};
MLX5_SET(modify_vhca_state_in, in, opcode, MLX5_CMD_OP_MODIFY_VHCA_STATE);
MLX5_SET(modify_vhca_state_in, in, function_id, function_id);
- MLX5_SET(modify_vhca_state_in, in, embedded_cpu_function, ecpu);
+ MLX5_SET(modify_vhca_state_in, in, embedded_cpu_function, 0);
MLX5_SET(modify_vhca_state_in, in, vhca_state_field_select.sw_function_id, 1);
MLX5_SET(modify_vhca_state_in, in, vhca_state_context.sw_function_id, sw_fn_id);
return mlx5_cmd_exec_inout(dev, modify_vhca_state, in, out);
}
-int mlx5_vhca_event_arm(struct mlx5_core_dev *dev, u16 function_id, bool ecpu)
+int mlx5_vhca_event_arm(struct mlx5_core_dev *dev, u16 function_id)
{
u32 in[MLX5_ST_SZ_DW(modify_vhca_state_in)] = {};
MLX5_SET(modify_vhca_state_in, in, vhca_state_context.arm_change_event, 1);
MLX5_SET(modify_vhca_state_in, in, vhca_state_field_select.arm_change_event, 1);
- return mlx5_cmd_modify_vhca_state(dev, function_id, ecpu, in, sizeof(in));
+ return mlx5_cmd_modify_vhca_state(dev, function_id, in, sizeof(in));
}
static void
u32 out[MLX5_ST_SZ_DW(query_vhca_state_out)] = {};
int err;
- err = mlx5_cmd_query_vhca_state(dev, event->function_id, event->ecpu, out, sizeof(out));
+ err = mlx5_cmd_query_vhca_state(dev, event->function_id, out, sizeof(out));
if (err)
return;
event->new_vhca_state = MLX5_GET(query_vhca_state_out, out,
vhca_state_context.vhca_state);
- mlx5_vhca_event_arm(dev, event->function_id, event->ecpu);
+ mlx5_vhca_event_arm(dev, event->function_id);
blocking_notifier_call_chain(&dev->priv.vhca_state_notifier->n_head, 0, event);
}
struct mlx5_core_dev *dev = notifier->dev;
mlx5_vhca_event_notify(dev, &work->event);
+ kfree(work);
}
static int
INIT_WORK(&work->work, &mlx5_vhca_state_work_handler);
work->notifier = notifier;
work->event.function_id = be16_to_cpu(eqe->data.vhca_state.function_id);
- work->event.ecpu = be16_to_cpu(eqe->data.vhca_state.ec_function);
mlx5_events_work_enqueue(notifier->dev, &work->work);
return NOTIFY_OK;
}
u16 function_id;
u16 sw_function_id;
u8 new_vhca_state;
- bool ecpu;
};
static inline bool mlx5_vhca_event_supported(const struct mlx5_core_dev *dev)
void mlx5_vhca_event_stop(struct mlx5_core_dev *dev);
int mlx5_vhca_event_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb);
void mlx5_vhca_event_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb);
-int mlx5_modify_vhca_sw_id(struct mlx5_core_dev *dev, u16 function_id, bool ecpu, u32 sw_fn_id);
-int mlx5_vhca_event_arm(struct mlx5_core_dev *dev, u16 function_id, bool ecpu);
+int mlx5_modify_vhca_sw_id(struct mlx5_core_dev *dev, u16 function_id, u32 sw_fn_id);
+int mlx5_vhca_event_arm(struct mlx5_core_dev *dev, u16 function_id);
int mlx5_cmd_query_vhca_state(struct mlx5_core_dev *dev, u16 function_id,
- bool ecpu, u32 *out, u32 outlen);
+ u32 *out, u32 outlen);
#else
static inline void mlx5_vhca_state_cap_handle(struct mlx5_core_dev *dev, void *set_hca_cap)
MLX5_SET(qpc, qpc, log_rq_size, ilog2(dr_qp->rq.wqe_cnt));
MLX5_SET(qpc, qpc, rq_type, MLX5_NON_ZERO_RQ);
MLX5_SET(qpc, qpc, log_sq_size, ilog2(dr_qp->sq.wqe_cnt));
+ MLX5_SET(qpc, qpc, ts_format, mlx5_get_qp_default_ts(mdev));
MLX5_SET64(qpc, qpc, dbr_addr, dr_qp->wq_ctrl.db.dma);
if (MLX5_CAP_GEN(mdev, cqe_version) == 1)
MLX5_SET(qpc, qpc, user_index, 0xFFFFFF);
static u64 dr_ste_v1_get_miss_addr(u8 *hw_ste_p)
{
u64 index =
- (MLX5_GET(ste_match_bwc_v1, hw_ste_p, miss_address_31_6) |
- MLX5_GET(ste_match_bwc_v1, hw_ste_p, miss_address_39_32) << 26);
+ ((u64)MLX5_GET(ste_match_bwc_v1, hw_ste_p, miss_address_31_6) |
+ ((u64)MLX5_GET(ste_match_bwc_v1, hw_ste_p, miss_address_39_32)) << 26);
return index << 6;
}
#define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_CR4 BIT(20)
#define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 BIT(21)
#define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4 BIT(22)
+#define MLXSW_REG_PTYS_ETH_SPEED_100GBASE_LR4_ER4 BIT(23)
#define MLXSW_REG_PTYS_ETH_SPEED_25GBASE_CR BIT(27)
#define MLXSW_REG_PTYS_ETH_SPEED_25GBASE_KR BIT(28)
#define MLXSW_REG_PTYS_ETH_SPEED_25GBASE_SR BIT(29)
#include <net/red.h>
#include <net/vxlan.h>
#include <net/flow_offload.h>
+#include <net/inet_ecn.h>
#include "port.h"
#include "core.h"
u32 (*ptys_proto_cap_masked_get)(u32 eth_proto_cap);
};
+static inline u8 mlxsw_sp_tunnel_ecn_decap(u8 outer_ecn, u8 inner_ecn,
+ bool *trap_en)
+{
+ bool set_ce = false;
+
+ *trap_en = !!__INET_ECN_decapsulate(outer_ecn, inner_ecn, &set_ce);
+ if (set_ce)
+ return INET_ECN_CE;
+ else if (outer_ecn == INET_ECN_ECT_1 && inner_ecn == INET_ECN_ECT_0)
+ return INET_ECN_ECT_1;
+ else
+ return inner_ecn;
+}
+
static inline struct net_device *
mlxsw_sp_bridge_vxlan_dev_find(struct net_device *br_dev)
{
.mask_ethtool = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT,
.speed = SPEED_100000,
},
+ {
+ .mask = MLXSW_REG_PTYS_ETH_SPEED_100GBASE_LR4_ER4,
+ .mask_ethtool = ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT,
+ .speed = SPEED_100000,
+ },
};
#define MLXSW_SP1_PORT_LINK_MODE_LEN ARRAY_SIZE(mlxsw_sp1_port_link_mode)
u32 ptys_eth_proto,
struct ethtool_link_ksettings *cmd)
{
+ struct mlxsw_sp1_port_link_mode link;
int i;
- cmd->link_mode = -1;
+ cmd->base.speed = SPEED_UNKNOWN;
+ cmd->base.duplex = DUPLEX_UNKNOWN;
+ cmd->lanes = 0;
if (!carrier_ok)
return;
for (i = 0; i < MLXSW_SP1_PORT_LINK_MODE_LEN; i++) {
- if (ptys_eth_proto & mlxsw_sp1_port_link_mode[i].mask)
- cmd->link_mode = mlxsw_sp1_port_link_mode[i].mask_ethtool;
+ if (ptys_eth_proto & mlxsw_sp1_port_link_mode[i].mask) {
+ link = mlxsw_sp1_port_link_mode[i];
+ ethtool_params_from_link_mode(cmd,
+ link.mask_ethtool);
+ }
}
}
struct mlxsw_sp2_port_link_mode link;
int i;
- cmd->link_mode = -1;
+ cmd->base.speed = SPEED_UNKNOWN;
+ cmd->base.duplex = DUPLEX_UNKNOWN;
+ cmd->lanes = 0;
if (!carrier_ok)
return;
for (i = 0; i < MLXSW_SP2_PORT_LINK_MODE_LEN; i++) {
if (ptys_eth_proto & mlxsw_sp2_port_link_mode[i].mask) {
link = mlxsw_sp2_port_link_mode[i];
- cmd->link_mode = link.mask_ethtool[1];
+ ethtool_params_from_link_mode(cmd,
+ link.mask_ethtool[1]);
}
}
}
u8 inner_ecn, u8 outer_ecn)
{
char tidem_pl[MLXSW_REG_TIDEM_LEN];
- bool trap_en, set_ce = false;
u8 new_inner_ecn;
+ bool trap_en;
- trap_en = __INET_ECN_decapsulate(outer_ecn, inner_ecn, &set_ce);
- new_inner_ecn = set_ce ? INET_ECN_CE : inner_ecn;
-
+ new_inner_ecn = mlxsw_sp_tunnel_ecn_decap(outer_ecn, inner_ecn,
+ &trap_en);
mlxsw_reg_tidem_pack(tidem_pl, outer_ecn, inner_ecn, new_inner_ecn,
trap_en, trap_en ? MLXSW_TRAP_ID_DECAP_ECN0 : 0);
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(tidem), tidem_pl);
u8 inner_ecn, u8 outer_ecn)
{
char tndem_pl[MLXSW_REG_TNDEM_LEN];
- bool trap_en, set_ce = false;
u8 new_inner_ecn;
+ bool trap_en;
- trap_en = !!__INET_ECN_decapsulate(outer_ecn, inner_ecn, &set_ce);
- new_inner_ecn = set_ce ? INET_ECN_CE : inner_ecn;
-
+ new_inner_ecn = mlxsw_sp_tunnel_ecn_decap(outer_ecn, inner_ecn,
+ &trap_en);
mlxsw_reg_tndem_pack(tndem_pl, outer_ecn, inner_ecn, new_inner_ecn,
trap_en, trap_en ? MLXSW_TRAP_ID_DECAP_ECN0 : 0);
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(tndem), tndem_pl);
if (mlxsw_sp->router->aborted)
return 0;
+ if (fen_info->fi->nh &&
+ !mlxsw_sp_nexthop_obj_group_lookup(mlxsw_sp, fen_info->fi->nh->id))
+ return 0;
+
fib_node = mlxsw_sp_fib_node_get(mlxsw_sp, fen_info->tb_id,
&fen_info->dst, sizeof(fen_info->dst),
fen_info->dst_len,
if (mlxsw_sp_fib6_rt_should_ignore(rt))
return 0;
+ if (rt->nh && !mlxsw_sp_nexthop_obj_group_lookup(mlxsw_sp, rt->nh->id))
+ return 0;
+
fib_node = mlxsw_sp_fib_node_get(mlxsw_sp, rt->fib6_table->tb6_id,
&rt->fib6_dst.addr,
sizeof(rt->fib6_dst.addr),
{
.mask = MLXSW_REG_PTYS_ETH_SPEED_100GBASE_CR4 |
MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 |
- MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4,
+ MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4 |
+ MLXSW_REG_PTYS_ETH_SPEED_100GBASE_LR4_ER4,
.speed = 100000,
},
};
}
mac_rx &= ~(MAC_RX_MAX_SIZE_MASK_);
- mac_rx |= (((new_mtu + ETH_HLEN + 4) << MAC_RX_MAX_SIZE_SHIFT_) &
- MAC_RX_MAX_SIZE_MASK_);
+ mac_rx |= (((new_mtu + ETH_HLEN + ETH_FCS_LEN)
+ << MAC_RX_MAX_SIZE_SHIFT_) & MAC_RX_MAX_SIZE_MASK_);
lan743x_csr_write(adapter, MAC_RX, mac_rx);
if (enabled) {
struct sk_buff *skb;
dma_addr_t dma_ptr;
- buffer_length = netdev->mtu + ETH_HLEN + 4 + RX_HEAD_PADDING;
+ buffer_length = netdev->mtu + ETH_HLEN + ETH_FCS_LEN + RX_HEAD_PADDING;
descriptor = &rx->ring_cpu_ptr[index];
buffer_info = &rx->buffer_info[index];
dev_kfree_skb_irq(skb);
return NULL;
}
- frame_length = max_t(int, 0, frame_length - RX_HEAD_PADDING - 2);
+ frame_length = max_t(int, 0, frame_length - ETH_FCS_LEN);
if (skb->len > frame_length) {
skb->tail -= skb->len - frame_length;
skb->len = frame_length;
# Users should depend on NET_SWITCHDEV, HAS_IOMEM
config MSCC_OCELOT_SWITCH_LIB
+ select NET_DEVLINK
select REGMAP_MMIO
select PACKING
select PHYLIB
return -EOPNOTSUPP;
}
+ flow_rule_match_ipv4_addrs(rule, &match);
+
if (filter->block_id == VCAP_IS1 && *(u32 *)&match.mask->dst) {
NL_SET_ERR_MSG_MOD(extack,
"Key type S1_NORMAL cannot match on destination IP");
return -EOPNOTSUPP;
}
- flow_rule_match_ipv4_addrs(rule, &match);
tmp = &filter->key.ipv4.sip.value.addr[0];
memcpy(tmp, &match.key->src, 4);
dev_kfree_skb_any(curr);
if (segs != NULL) {
curr = segs;
- segs = segs->next;
+ segs = next;
curr->next = NULL;
dev_kfree_skb_any(segs);
}
dev_consume_skb_any(skb);
else
dev_kfree_skb_any(skb);
+ return;
}
nfp_ccm_rx(&bpf->ccm, skb);
* @qos_rate_limiters: Current active qos rate limiters
* @qos_stats_lock: Lock on qos stats updates
* @pre_tun_rule_cnt: Number of pre-tunnel rules offloaded
+ * @merge_table: Hash table to store merged flows
*/
struct nfp_flower_priv {
struct nfp_app *app;
unsigned int qos_rate_limiters;
spinlock_t qos_stats_lock; /* Protect the qos stats */
int pre_tun_rule_cnt;
+ struct rhashtable merge_table;
};
/**
};
extern const struct rhashtable_params nfp_flower_table_params;
+extern const struct rhashtable_params merge_table_params;
+
+struct nfp_merge_info {
+ u64 parent_ctx;
+ struct rhash_head ht_node;
+};
struct nfp_fl_stats_frame {
__be32 stats_con_id;
goto err_free_ctx_entry;
}
+ /* Do net allocate a mask-id for pre_tun_rules. These flows are used to
+ * configure the pre_tun table and are never actually send to the
+ * firmware as an add-flow message. This causes the mask-id allocation
+ * on the firmware to get out of sync if allocated here.
+ */
new_mask_id = 0;
- if (!nfp_check_mask_add(app, nfp_flow->mask_data,
+ if (!nfp_flow->pre_tun_rule.dev &&
+ !nfp_check_mask_add(app, nfp_flow->mask_data,
nfp_flow->meta.mask_len,
&nfp_flow->meta.flags, &new_mask_id)) {
NL_SET_ERR_MSG_MOD(extack, "invalid entry: cannot allocate a new mask id");
goto err_remove_mask;
}
- if (!nfp_check_mask_remove(app, nfp_flow->mask_data,
+ if (!nfp_flow->pre_tun_rule.dev &&
+ !nfp_check_mask_remove(app, nfp_flow->mask_data,
nfp_flow->meta.mask_len,
NULL, &new_mask_id)) {
NL_SET_ERR_MSG_MOD(extack, "invalid entry: cannot release mask id");
return 0;
err_remove_mask:
- nfp_check_mask_remove(app, nfp_flow->mask_data, nfp_flow->meta.mask_len,
- NULL, &new_mask_id);
+ if (!nfp_flow->pre_tun_rule.dev)
+ nfp_check_mask_remove(app, nfp_flow->mask_data,
+ nfp_flow->meta.mask_len,
+ NULL, &new_mask_id);
err_remove_rhash:
WARN_ON_ONCE(rhashtable_remove_fast(&priv->stats_ctx_table,
&ctx_entry->ht_node,
__nfp_modify_flow_metadata(priv, nfp_flow);
- nfp_check_mask_remove(app, nfp_flow->mask_data,
- nfp_flow->meta.mask_len, &nfp_flow->meta.flags,
- &new_mask_id);
+ if (!nfp_flow->pre_tun_rule.dev)
+ nfp_check_mask_remove(app, nfp_flow->mask_data,
+ nfp_flow->meta.mask_len, &nfp_flow->meta.flags,
+ &new_mask_id);
/* Update flow payload with mask ids. */
nfp_flow->unmasked_data[NFP_FL_MASK_ID_LOCATION] = new_mask_id;
.automatic_shrinking = true,
};
+const struct rhashtable_params merge_table_params = {
+ .key_offset = offsetof(struct nfp_merge_info, parent_ctx),
+ .head_offset = offsetof(struct nfp_merge_info, ht_node),
+ .key_len = sizeof(u64),
+};
+
int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count,
unsigned int host_num_mems)
{
if (err)
goto err_free_flow_table;
+ err = rhashtable_init(&priv->merge_table, &merge_table_params);
+ if (err)
+ goto err_free_stats_ctx_table;
+
get_random_bytes(&priv->mask_id_seed, sizeof(priv->mask_id_seed));
/* Init ring buffer and unallocated mask_ids. */
kmalloc_array(NFP_FLOWER_MASK_ENTRY_RS,
NFP_FLOWER_MASK_ELEMENT_RS, GFP_KERNEL);
if (!priv->mask_ids.mask_id_free_list.buf)
- goto err_free_stats_ctx_table;
+ goto err_free_merge_table;
priv->mask_ids.init_unallocated = NFP_FLOWER_MASK_ENTRY_RS - 1;
kfree(priv->mask_ids.last_used);
err_free_mask_id:
kfree(priv->mask_ids.mask_id_free_list.buf);
+err_free_merge_table:
+ rhashtable_destroy(&priv->merge_table);
err_free_stats_ctx_table:
rhashtable_destroy(&priv->stats_ctx_table);
err_free_flow_table:
nfp_check_rhashtable_empty, NULL);
rhashtable_free_and_destroy(&priv->stats_ctx_table,
nfp_check_rhashtable_empty, NULL);
+ rhashtable_free_and_destroy(&priv->merge_table,
+ nfp_check_rhashtable_empty, NULL);
kvfree(priv->stats);
kfree(priv->mask_ids.mask_id_free_list.buf);
kfree(priv->mask_ids.last_used);
struct netlink_ext_ack *extack = NULL;
struct nfp_fl_payload *merge_flow;
struct nfp_fl_key_ls merge_key_ls;
+ struct nfp_merge_info *merge_info;
+ u64 parent_ctx = 0;
int err;
ASSERT_RTNL();
nfp_flower_is_merge_flow(sub_flow2))
return -EINVAL;
+ /* check if the two flows are already merged */
+ parent_ctx = (u64)(be32_to_cpu(sub_flow1->meta.host_ctx_id)) << 32;
+ parent_ctx |= (u64)(be32_to_cpu(sub_flow2->meta.host_ctx_id));
+ if (rhashtable_lookup_fast(&priv->merge_table,
+ &parent_ctx, merge_table_params)) {
+ nfp_flower_cmsg_warn(app, "The two flows are already merged.\n");
+ return 0;
+ }
+
err = nfp_flower_can_merge(sub_flow1, sub_flow2);
if (err)
return err;
if (err)
goto err_release_metadata;
+ merge_info = kmalloc(sizeof(*merge_info), GFP_KERNEL);
+ if (!merge_info) {
+ err = -ENOMEM;
+ goto err_remove_rhash;
+ }
+ merge_info->parent_ctx = parent_ctx;
+ err = rhashtable_insert_fast(&priv->merge_table, &merge_info->ht_node,
+ merge_table_params);
+ if (err)
+ goto err_destroy_merge_info;
+
err = nfp_flower_xmit_flow(app, merge_flow,
NFP_FLOWER_CMSG_TYPE_FLOW_MOD);
if (err)
- goto err_remove_rhash;
+ goto err_remove_merge_info;
merge_flow->in_hw = true;
sub_flow1->in_hw = false;
return 0;
+err_remove_merge_info:
+ WARN_ON_ONCE(rhashtable_remove_fast(&priv->merge_table,
+ &merge_info->ht_node,
+ merge_table_params));
+err_destroy_merge_info:
+ kfree(merge_info);
err_remove_rhash:
WARN_ON_ONCE(rhashtable_remove_fast(&priv->flow_table,
&merge_flow->fl_node,
return -EOPNOTSUPP;
}
+ if (!(key_layer & NFP_FLOWER_LAYER_IPV4) &&
+ !(key_layer & NFP_FLOWER_LAYER_IPV6)) {
+ NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: match on ipv4/ipv6 eth_type must be present");
+ return -EOPNOTSUPP;
+ }
+
/* Skip fields known to exist. */
mask += sizeof(struct nfp_flower_meta_tci);
ext += sizeof(struct nfp_flower_meta_tci);
mask += sizeof(struct nfp_flower_in_port);
ext += sizeof(struct nfp_flower_in_port);
+ /* Ensure destination MAC address matches pre_tun_dev. */
+ mac = (struct nfp_flower_mac_mpls *)ext;
+ if (memcmp(&mac->mac_dst[0], flow->pre_tun_rule.dev->dev_addr, 6)) {
+ NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: dest MAC must match output dev MAC");
+ return -EOPNOTSUPP;
+ }
+
/* Ensure destination MAC address is fully matched. */
mac = (struct nfp_flower_mac_mpls *)mask;
if (!is_broadcast_ether_addr(&mac->mac_dst[0])) {
return -EOPNOTSUPP;
}
+ if (mac->mpls_lse) {
+ NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: MPLS not supported");
+ return -EOPNOTSUPP;
+ }
+
mask += sizeof(struct nfp_flower_mac_mpls);
ext += sizeof(struct nfp_flower_mac_mpls);
if (key_layer & NFP_FLOWER_LAYER_IPV4 ||
{
struct nfp_flower_priv *priv = app->priv;
struct nfp_fl_payload_link *link, *temp;
+ struct nfp_merge_info *merge_info;
struct nfp_fl_payload *origin;
+ u64 parent_ctx = 0;
bool mod = false;
int err;
err_free_links:
/* Clean any links connected with the merged flow. */
list_for_each_entry_safe(link, temp, &merge_flow->linked_flows,
- merge_flow.list)
+ merge_flow.list) {
+ u32 ctx_id = be32_to_cpu(link->sub_flow.flow->meta.host_ctx_id);
+
+ parent_ctx = (parent_ctx << 32) | (u64)(ctx_id);
nfp_flower_unlink_flow(link);
+ }
+
+ merge_info = rhashtable_lookup_fast(&priv->merge_table,
+ &parent_ctx,
+ merge_table_params);
+ if (merge_info) {
+ WARN_ON_ONCE(rhashtable_remove_fast(&priv->merge_table,
+ &merge_info->ht_node,
+ merge_table_params));
+ kfree(merge_info);
+ }
kfree(merge_flow->action_data);
kfree(merge_flow->mask_data);
#define NFP_FL_MAX_ROUTES 32
#define NFP_TUN_PRE_TUN_RULE_LIMIT 32
-#define NFP_TUN_PRE_TUN_RULE_DEL 0x1
-#define NFP_TUN_PRE_TUN_IDX_BIT 0x8
+#define NFP_TUN_PRE_TUN_RULE_DEL BIT(0)
+#define NFP_TUN_PRE_TUN_IDX_BIT BIT(3)
+#define NFP_TUN_PRE_TUN_IPV6_BIT BIT(7)
/**
* struct nfp_tun_pre_run_rule - rule matched before decap
{
struct nfp_flower_priv *app_priv = app->priv;
struct nfp_tun_offloaded_mac *mac_entry;
+ struct nfp_flower_meta_tci *key_meta;
struct nfp_tun_pre_tun_rule payload;
struct net_device *internal_dev;
int err;
if (!mac_entry)
return -ENOENT;
+ /* Set/clear IPV6 bit. cpu_to_be16() swap will lead to MSB being
+ * set/clear for port_idx.
+ */
+ key_meta = (struct nfp_flower_meta_tci *)flow->unmasked_data;
+ if (key_meta->nfp_flow_key_layer & NFP_FLOWER_LAYER_IPV6)
+ mac_entry->index |= NFP_TUN_PRE_TUN_IPV6_BIT;
+ else
+ mac_entry->index &= ~NFP_TUN_PRE_TUN_IPV6_BIT;
+
payload.port_idx = cpu_to_be16(mac_entry->index);
/* Copy mac id and vlan to flow - dev may not exist at delete time. */
{
int sg_elems = q->lif->qtype_info[IONIC_QTYPE_TXQ].max_sg_elems;
struct ionic_tx_stats *stats = q_to_tx_stats(q);
+ int ndescs;
int err;
- /* If TSO, need roundup(skb->len/mss) descs */
+ /* Each desc is mss long max, so a descriptor for each gso_seg */
if (skb_is_gso(skb))
- return (skb->len / skb_shinfo(skb)->gso_size) + 1;
+ ndescs = skb_shinfo(skb)->gso_segs;
+ else
+ ndescs = 1;
- /* If non-TSO, just need 1 desc and nr_frags sg elems */
if (skb_shinfo(skb)->nr_frags <= sg_elems)
- return 1;
+ return ndescs;
/* Too many frags, so linearize */
err = skb_linearize(skb);
stats->linearize++;
- /* Need 1 desc and zero sg elems */
- return 1;
+ return ndescs;
}
static int ionic_maybe_stop_tx(struct ionic_queue *q, int ndescs)
if (fw_dump->tmpl_hdr == NULL || current_version > prev_version) {
vfree(fw_dump->tmpl_hdr);
+ fw_dump->tmpl_hdr = NULL;
if (qlcnic_83xx_md_check_extended_dump_capability(adapter))
extended = !qlcnic_83xx_extend_md_capab(adapter);
struct qlcnic_83xx_dump_template_hdr *hdr;
hdr = fw_dump->tmpl_hdr;
+ if (!hdr)
+ return;
hdr->drv_cap_mask = 0x1f;
fw_dump->cap_mask = 0x1f;
dev_info(&pdev->dev,
if (type == ERIAR_OOB &&
(tp->mac_version == RTL_GIGA_MAC_VER_52 ||
tp->mac_version == RTL_GIGA_MAC_VER_53))
- *cmd |= 0x7f0 << 18;
+ *cmd |= 0xf70 << 18;
}
DECLARE_RTL_COND(rtl_eriar_cond)
if (pci_is_pcie(tp->pci_dev) && tp->supports_gmii)
pcie_set_readrq(tp->pci_dev, readrq);
+
+ /* Chip doesn't support pause in jumbo mode */
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+ tp->phydev->advertising, !jumbo);
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+ tp->phydev->advertising, !jumbo);
+ phy_start_aneg(tp->phydev);
}
DECLARE_RTL_COND(rtl_chipcmd_cond)
if (!tp->supports_gmii)
phy_set_max_speed(phydev, SPEED_100);
- phy_support_asym_pause(phydev);
-
phy_attached_info(phydev);
return 0;
rtl8169_update_counters(tp);
+ pci_clear_master(tp->pci_dev);
+ rtl_pci_commit(tp);
+
rtl8169_cleanup(tp, true);
rtl_prepare_power_down(tp);
static void rtl8169_up(struct rtl8169_private *tp)
{
+ pci_set_master(tp->pci_dev);
phy_resume(tp->phydev);
rtl8169_init_phy(tp);
napi_enable(&tp->napi);
rtl_hw_reset(tp);
- pci_set_master(pdev);
-
rc = rtl_alloc_irq(tp);
if (rc < 0) {
dev_err(&pdev->dev, "Can't allocate interrupt\n");
EESR_TDE,
.fdr_value = 0x0000070f,
+ .trscer_err_mask = DESC_I_RINT8 | DESC_I_RINT5,
+
.no_psr = 1,
.apr = 1,
.mpr = 1,
.fdr_value = 0x0000070f,
+ .trscer_err_mask = DESC_I_RINT8 | DESC_I_RINT5,
+
.apr = 1,
.mpr = 1,
.tpauser = 1,
EESIPR_CEEFIP | EESIPR_CELFIP |
EESIPR_RRFIP | EESIPR_RTLFIP | EESIPR_RTSFIP |
EESIPR_PREIP | EESIPR_CERFIP,
+
+ .trscer_err_mask = DESC_I_RINT8,
+
.tsu = 1,
.dual_port = 1,
};
goto err1;
/* set phy power down */
- data = netsec_phy_read(priv->mii_bus, priv->phy_addr, MII_BMCR) |
- BMCR_PDOWN;
- netsec_phy_write(priv->mii_bus, priv->phy_addr, MII_BMCR, data);
+ data = netsec_phy_read(priv->mii_bus, priv->phy_addr, MII_BMCR);
+ netsec_phy_write(priv->mii_bus, priv->phy_addr, MII_BMCR,
+ data | BMCR_PDOWN);
ret = netsec_reset_hardware(priv, true);
if (ret)
goto err2;
+ /* Restore phy power state */
+ netsec_phy_write(priv->mii_bus, priv->phy_addr, MII_BMCR, data);
+
spin_lock_init(&priv->desc_ring[NETSEC_RING_TX].lock);
spin_lock_init(&priv->desc_ring[NETSEC_RING_RX].lock);
static int intel_mgbe_common_data(struct pci_dev *pdev,
struct plat_stmmacenet_data *plat)
{
+ char clk_name[20];
int ret;
int i;
plat->eee_usecs_rate = plat->clk_ptp_rate;
/* Set system clock */
+ sprintf(clk_name, "%s-%s", "stmmac", pci_name(pdev));
+
plat->stmmac_clk = clk_register_fixed_rate(&pdev->dev,
- "stmmac-clk", NULL, 0,
+ clk_name, NULL, 0,
plat->clk_ptp_rate);
if (IS_ERR(plat->stmmac_clk)) {
return intel_mgbe_common_data(pdev, plat);
}
-static int tgl_sgmii_data(struct pci_dev *pdev,
- struct plat_stmmacenet_data *plat)
+static int tgl_sgmii_phy0_data(struct pci_dev *pdev,
+ struct plat_stmmacenet_data *plat)
{
plat->bus_id = 1;
plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
return tgl_common_data(pdev, plat);
}
-static struct stmmac_pci_info tgl_sgmii1g_info = {
- .setup = tgl_sgmii_data,
+static struct stmmac_pci_info tgl_sgmii1g_phy0_info = {
+ .setup = tgl_sgmii_phy0_data,
};
-static int adls_sgmii_data(struct pci_dev *pdev,
- struct plat_stmmacenet_data *plat)
+static int tgl_sgmii_phy1_data(struct pci_dev *pdev,
+ struct plat_stmmacenet_data *plat)
+{
+ plat->bus_id = 2;
+ plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
+ plat->serdes_powerup = intel_serdes_powerup;
+ plat->serdes_powerdown = intel_serdes_powerdown;
+ return tgl_common_data(pdev, plat);
+}
+
+static struct stmmac_pci_info tgl_sgmii1g_phy1_info = {
+ .setup = tgl_sgmii_phy1_data,
+};
+
+static int adls_sgmii_phy0_data(struct pci_dev *pdev,
+ struct plat_stmmacenet_data *plat)
{
plat->bus_id = 1;
plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
return tgl_common_data(pdev, plat);
}
-static struct stmmac_pci_info adls_sgmii1g_info = {
- .setup = adls_sgmii_data,
+static struct stmmac_pci_info adls_sgmii1g_phy0_info = {
+ .setup = adls_sgmii_phy0_data,
};
+static int adls_sgmii_phy1_data(struct pci_dev *pdev,
+ struct plat_stmmacenet_data *plat)
+{
+ plat->bus_id = 2;
+ plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
+
+ /* SerDes power up and power down are done in BIOS for ADL */
+
+ return tgl_common_data(pdev, plat);
+}
+
+static struct stmmac_pci_info adls_sgmii1g_phy1_info = {
+ .setup = adls_sgmii_phy1_data,
+};
static const struct stmmac_pci_func_data galileo_stmmac_func_data[] = {
{
.func = 6,
{ PCI_DEVICE_DATA(INTEL, EHL_PSE1_RGMII1G_ID, &ehl_pse1_rgmii1g_info) },
{ PCI_DEVICE_DATA(INTEL, EHL_PSE1_SGMII1G_ID, &ehl_pse1_sgmii1g_info) },
{ PCI_DEVICE_DATA(INTEL, EHL_PSE1_SGMII2G5_ID, &ehl_pse1_sgmii1g_info) },
- { PCI_DEVICE_DATA(INTEL, TGL_SGMII1G_ID, &tgl_sgmii1g_info) },
- { PCI_DEVICE_DATA(INTEL, TGLH_SGMII1G_0_ID, &tgl_sgmii1g_info) },
- { PCI_DEVICE_DATA(INTEL, TGLH_SGMII1G_1_ID, &tgl_sgmii1g_info) },
- { PCI_DEVICE_DATA(INTEL, ADLS_SGMII1G_0_ID, &adls_sgmii1g_info) },
- { PCI_DEVICE_DATA(INTEL, ADLS_SGMII1G_1_ID, &adls_sgmii1g_info) },
+ { PCI_DEVICE_DATA(INTEL, TGL_SGMII1G_ID, &tgl_sgmii1g_phy0_info) },
+ { PCI_DEVICE_DATA(INTEL, TGLH_SGMII1G_0_ID, &tgl_sgmii1g_phy0_info) },
+ { PCI_DEVICE_DATA(INTEL, TGLH_SGMII1G_1_ID, &tgl_sgmii1g_phy1_info) },
+ { PCI_DEVICE_DATA(INTEL, ADLS_SGMII1G_0_ID, &adls_sgmii1g_phy0_info) },
+ { PCI_DEVICE_DATA(INTEL, ADLS_SGMII1G_1_ID, &adls_sgmii1g_phy1_info) },
{}
};
MODULE_DEVICE_TABLE(pci, intel_eth_pci_id_table);
plat_dat->init = sun8i_dwmac_init;
plat_dat->exit = sun8i_dwmac_exit;
plat_dat->setup = sun8i_dwmac_setup;
+ plat_dat->tx_fifo_size = 4096;
+ plat_dat->rx_fifo_size = 16384;
ret = sun8i_dwmac_set_syscon(&pdev->dev, plat_dat);
if (ret)
p->des2 |= cpu_to_le32(TDES2_INTERRUPT_ON_COMPLETION);
}
-static void dwmac4_display_ring(void *head, unsigned int size, bool rx)
+static void dwmac4_display_ring(void *head, unsigned int size, bool rx,
+ dma_addr_t dma_rx_phy, unsigned int desc_size)
{
- struct dma_desc *p = (struct dma_desc *)head;
+ dma_addr_t dma_addr;
int i;
pr_info("%s descriptor ring:\n", rx ? "RX" : "TX");
- for (i = 0; i < size; i++) {
- pr_info("%03d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
- i, (unsigned int)virt_to_phys(p),
- le32_to_cpu(p->des0), le32_to_cpu(p->des1),
- le32_to_cpu(p->des2), le32_to_cpu(p->des3));
- p++;
+ if (desc_size == sizeof(struct dma_desc)) {
+ struct dma_desc *p = (struct dma_desc *)head;
+
+ for (i = 0; i < size; i++) {
+ dma_addr = dma_rx_phy + i * sizeof(*p);
+ pr_info("%03d [%pad]: 0x%x 0x%x 0x%x 0x%x\n",
+ i, &dma_addr,
+ le32_to_cpu(p->des0), le32_to_cpu(p->des1),
+ le32_to_cpu(p->des2), le32_to_cpu(p->des3));
+ p++;
+ }
+ } else if (desc_size == sizeof(struct dma_extended_desc)) {
+ struct dma_extended_desc *extp = (struct dma_extended_desc *)head;
+
+ for (i = 0; i < size; i++) {
+ dma_addr = dma_rx_phy + i * sizeof(*extp);
+ pr_info("%03d [%pad]: 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x\n",
+ i, &dma_addr,
+ le32_to_cpu(extp->basic.des0), le32_to_cpu(extp->basic.des1),
+ le32_to_cpu(extp->basic.des2), le32_to_cpu(extp->basic.des3),
+ le32_to_cpu(extp->des4), le32_to_cpu(extp->des5),
+ le32_to_cpu(extp->des6), le32_to_cpu(extp->des7));
+ extp++;
+ }
+ } else if (desc_size == sizeof(struct dma_edesc)) {
+ struct dma_edesc *ep = (struct dma_edesc *)head;
+
+ for (i = 0; i < size; i++) {
+ dma_addr = dma_rx_phy + i * sizeof(*ep);
+ pr_info("%03d [%pad]: 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x\n",
+ i, &dma_addr,
+ le32_to_cpu(ep->des4), le32_to_cpu(ep->des5),
+ le32_to_cpu(ep->des6), le32_to_cpu(ep->des7),
+ le32_to_cpu(ep->basic.des0), le32_to_cpu(ep->basic.des1),
+ le32_to_cpu(ep->basic.des2), le32_to_cpu(ep->basic.des3));
+ ep++;
+ }
+ } else {
+ pr_err("unsupported descriptor!");
}
}
*len = le32_to_cpu(p->des2) & RDES2_HL;
}
-static void dwmac4_set_sec_addr(struct dma_desc *p, dma_addr_t addr)
+static void dwmac4_set_sec_addr(struct dma_desc *p, dma_addr_t addr, bool buf2_valid)
{
p->des2 = cpu_to_le32(lower_32_bits(addr));
- p->des3 = cpu_to_le32(upper_32_bits(addr) | RDES3_BUFFER2_VALID_ADDR);
+ p->des3 = cpu_to_le32(upper_32_bits(addr));
+
+ if (buf2_valid)
+ p->des3 |= cpu_to_le32(RDES3_BUFFER2_VALID_ADDR);
+ else
+ p->des3 &= cpu_to_le32(~RDES3_BUFFER2_VALID_ADDR);
}
static void dwmac4_set_tbs(struct dma_edesc *p, u32 sec, u32 nsec)
ioaddr + DMA_CHAN_INTR_ENA(chan));
}
+static void dwmac410_dma_init_channel(void __iomem *ioaddr,
+ struct stmmac_dma_cfg *dma_cfg, u32 chan)
+{
+ u32 value;
+
+ /* common channel control register config */
+ value = readl(ioaddr + DMA_CHAN_CONTROL(chan));
+ if (dma_cfg->pblx8)
+ value = value | DMA_BUS_MODE_PBL;
+
+ writel(value, ioaddr + DMA_CHAN_CONTROL(chan));
+
+ /* Mask interrupts by writing to CSR7 */
+ writel(DMA_CHAN_INTR_DEFAULT_MASK_4_10,
+ ioaddr + DMA_CHAN_INTR_ENA(chan));
+}
+
static void dwmac4_dma_init(void __iomem *ioaddr,
struct stmmac_dma_cfg *dma_cfg, int atds)
{
const struct stmmac_dma_ops dwmac410_dma_ops = {
.reset = dwmac4_dma_reset,
.init = dwmac4_dma_init,
- .init_chan = dwmac4_dma_init_channel,
+ .init_chan = dwmac410_dma_init_channel,
.init_rx_chan = dwmac4_dma_init_rx_chan,
.init_tx_chan = dwmac4_dma_init_tx_chan,
.axi = dwmac4_dma_axi,
value &= ~DMA_CONTROL_ST;
writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan));
-
- value = readl(ioaddr + GMAC_CONFIG);
- value &= ~GMAC_CONFIG_TE;
- writel(value, ioaddr + GMAC_CONFIG);
}
void dwmac4_dma_start_rx(void __iomem *ioaddr, u32 chan)
*len = le32_to_cpu(p->des2) & XGMAC_RDES2_HL;
}
-static void dwxgmac2_set_sec_addr(struct dma_desc *p, dma_addr_t addr)
+static void dwxgmac2_set_sec_addr(struct dma_desc *p, dma_addr_t addr, bool is_valid)
{
p->des2 = cpu_to_le32(lower_32_bits(addr));
p->des3 = cpu_to_le32(upper_32_bits(addr));
}
}
-static void enh_desc_display_ring(void *head, unsigned int size, bool rx)
+static void enh_desc_display_ring(void *head, unsigned int size, bool rx,
+ dma_addr_t dma_rx_phy, unsigned int desc_size)
{
struct dma_extended_desc *ep = (struct dma_extended_desc *)head;
+ dma_addr_t dma_addr;
int i;
pr_info("Extended %s descriptor ring:\n", rx ? "RX" : "TX");
for (i = 0; i < size; i++) {
u64 x;
+ dma_addr = dma_rx_phy + i * sizeof(*ep);
x = *(u64 *)ep;
- pr_info("%03d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
- i, (unsigned int)virt_to_phys(ep),
+ pr_info("%03d [%pad]: 0x%x 0x%x 0x%x 0x%x\n",
+ i, &dma_addr,
(unsigned int)x, (unsigned int)(x >> 32),
ep->basic.des2, ep->basic.des3);
ep++;
/* get rx timestamp status */
int (*get_rx_timestamp_status)(void *desc, void *next_desc, u32 ats);
/* Display ring */
- void (*display_ring)(void *head, unsigned int size, bool rx);
+ void (*display_ring)(void *head, unsigned int size, bool rx,
+ dma_addr_t dma_rx_phy, unsigned int desc_size);
/* set MSS via context descriptor */
void (*set_mss)(struct dma_desc *p, unsigned int mss);
/* get descriptor skbuff address */
int (*get_rx_hash)(struct dma_desc *p, u32 *hash,
enum pkt_hash_types *type);
void (*get_rx_header_len)(struct dma_desc *p, unsigned int *len);
- void (*set_sec_addr)(struct dma_desc *p, dma_addr_t addr);
+ void (*set_sec_addr)(struct dma_desc *p, dma_addr_t addr, bool buf2_valid);
void (*set_sarc)(struct dma_desc *p, u32 sarc_type);
void (*set_vlan_tag)(struct dma_desc *p, u16 tag, u16 inner_tag,
u32 inner_type);
return 1;
}
-static void ndesc_display_ring(void *head, unsigned int size, bool rx)
+static void ndesc_display_ring(void *head, unsigned int size, bool rx,
+ dma_addr_t dma_rx_phy, unsigned int desc_size)
{
struct dma_desc *p = (struct dma_desc *)head;
+ dma_addr_t dma_addr;
int i;
pr_info("%s descriptor ring:\n", rx ? "RX" : "TX");
for (i = 0; i < size; i++) {
u64 x;
+ dma_addr = dma_rx_phy + i * sizeof(*p);
x = *(u64 *)p;
- pr_info("%03d [0x%x]: 0x%x 0x%x 0x%x 0x%x",
- i, (unsigned int)virt_to_phys(p),
+ pr_info("%03d [%pad]: 0x%x 0x%x 0x%x 0x%x",
+ i, &dma_addr,
(unsigned int)x, (unsigned int)(x >> 32),
p->des2, p->des3);
p++;
static void stmmac_display_rx_rings(struct stmmac_priv *priv)
{
u32 rx_cnt = priv->plat->rx_queues_to_use;
+ unsigned int desc_size;
void *head_rx;
u32 queue;
pr_info("\tRX Queue %u rings\n", queue);
- if (priv->extend_desc)
+ if (priv->extend_desc) {
head_rx = (void *)rx_q->dma_erx;
- else
+ desc_size = sizeof(struct dma_extended_desc);
+ } else {
head_rx = (void *)rx_q->dma_rx;
+ desc_size = sizeof(struct dma_desc);
+ }
/* Display RX ring */
- stmmac_display_ring(priv, head_rx, priv->dma_rx_size, true);
+ stmmac_display_ring(priv, head_rx, priv->dma_rx_size, true,
+ rx_q->dma_rx_phy, desc_size);
}
}
static void stmmac_display_tx_rings(struct stmmac_priv *priv)
{
u32 tx_cnt = priv->plat->tx_queues_to_use;
+ unsigned int desc_size;
void *head_tx;
u32 queue;
pr_info("\tTX Queue %d rings\n", queue);
- if (priv->extend_desc)
+ if (priv->extend_desc) {
head_tx = (void *)tx_q->dma_etx;
- else if (tx_q->tbs & STMMAC_TBS_AVAIL)
+ desc_size = sizeof(struct dma_extended_desc);
+ } else if (tx_q->tbs & STMMAC_TBS_AVAIL) {
head_tx = (void *)tx_q->dma_entx;
- else
+ desc_size = sizeof(struct dma_edesc);
+ } else {
head_tx = (void *)tx_q->dma_tx;
+ desc_size = sizeof(struct dma_desc);
+ }
- stmmac_display_ring(priv, head_tx, priv->dma_tx_size, false);
+ stmmac_display_ring(priv, head_tx, priv->dma_tx_size, false,
+ tx_q->dma_tx_phy, desc_size);
}
}
return -ENOMEM;
buf->sec_addr = page_pool_get_dma_addr(buf->sec_page);
- stmmac_set_desc_sec_addr(priv, p, buf->sec_addr);
+ stmmac_set_desc_sec_addr(priv, p, buf->sec_addr, true);
} else {
buf->sec_page = NULL;
+ stmmac_set_desc_sec_addr(priv, p, buf->sec_addr, false);
}
buf->addr = page_pool_get_dma_addr(buf->page);
DMA_FROM_DEVICE);
stmmac_set_desc_addr(priv, p, buf->addr);
- stmmac_set_desc_sec_addr(priv, p, buf->sec_addr);
+ if (priv->sph)
+ stmmac_set_desc_sec_addr(priv, p, buf->sec_addr, true);
+ else
+ stmmac_set_desc_sec_addr(priv, p, buf->sec_addr, false);
stmmac_refill_desc3(priv, rx_q, p);
rx_q->rx_count_frames++;
unsigned int count = 0, error = 0, len = 0;
int status = 0, coe = priv->hw->rx_csum;
unsigned int next_entry = rx_q->cur_rx;
+ unsigned int desc_size;
struct sk_buff *skb = NULL;
if (netif_msg_rx_status(priv)) {
void *rx_head;
netdev_dbg(priv->dev, "%s: descriptor ring:\n", __func__);
- if (priv->extend_desc)
+ if (priv->extend_desc) {
rx_head = (void *)rx_q->dma_erx;
- else
+ desc_size = sizeof(struct dma_extended_desc);
+ } else {
rx_head = (void *)rx_q->dma_rx;
+ desc_size = sizeof(struct dma_desc);
+ }
- stmmac_display_ring(priv, rx_head, priv->dma_rx_size, true);
+ stmmac_display_ring(priv, rx_head, priv->dma_rx_size, true,
+ rx_q->dma_rx_phy, desc_size);
}
while (count < limit) {
unsigned int buf1_len = 0, buf2_len = 0;
static struct dentry *stmmac_fs_dir;
static void sysfs_display_ring(void *head, int size, int extend_desc,
- struct seq_file *seq)
+ struct seq_file *seq, dma_addr_t dma_phy_addr)
{
int i;
struct dma_extended_desc *ep = (struct dma_extended_desc *)head;
struct dma_desc *p = (struct dma_desc *)head;
+ dma_addr_t dma_addr;
for (i = 0; i < size; i++) {
if (extend_desc) {
- seq_printf(seq, "%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
- i, (unsigned int)virt_to_phys(ep),
+ dma_addr = dma_phy_addr + i * sizeof(*ep);
+ seq_printf(seq, "%d [%pad]: 0x%x 0x%x 0x%x 0x%x\n",
+ i, &dma_addr,
le32_to_cpu(ep->basic.des0),
le32_to_cpu(ep->basic.des1),
le32_to_cpu(ep->basic.des2),
le32_to_cpu(ep->basic.des3));
ep++;
} else {
- seq_printf(seq, "%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
- i, (unsigned int)virt_to_phys(p),
+ dma_addr = dma_phy_addr + i * sizeof(*p);
+ seq_printf(seq, "%d [%pad]: 0x%x 0x%x 0x%x 0x%x\n",
+ i, &dma_addr,
le32_to_cpu(p->des0), le32_to_cpu(p->des1),
le32_to_cpu(p->des2), le32_to_cpu(p->des3));
p++;
if (priv->extend_desc) {
seq_printf(seq, "Extended descriptor ring:\n");
sysfs_display_ring((void *)rx_q->dma_erx,
- priv->dma_rx_size, 1, seq);
+ priv->dma_rx_size, 1, seq, rx_q->dma_rx_phy);
} else {
seq_printf(seq, "Descriptor ring:\n");
sysfs_display_ring((void *)rx_q->dma_rx,
- priv->dma_rx_size, 0, seq);
+ priv->dma_rx_size, 0, seq, rx_q->dma_rx_phy);
}
}
if (priv->extend_desc) {
seq_printf(seq, "Extended descriptor ring:\n");
sysfs_display_ring((void *)tx_q->dma_etx,
- priv->dma_tx_size, 1, seq);
+ priv->dma_tx_size, 1, seq, tx_q->dma_tx_phy);
} else if (!(tx_q->tbs & STMMAC_TBS_AVAIL)) {
seq_printf(seq, "Descriptor ring:\n");
sysfs_display_ring((void *)tx_q->dma_tx,
- priv->dma_tx_size, 0, seq);
+ priv->dma_tx_size, 0, seq, tx_q->dma_tx_phy);
}
}
netdev_info(priv->dev, "%s: removing driver", __func__);
stmmac_stop_all_dma(priv);
+ stmmac_mac_set(priv, priv->ioaddr, false);
+ netif_carrier_off(ndev);
+ unregister_netdev(ndev);
+ /* Serdes power down needs to happen after VLAN filter
+ * is deleted that is triggered by unregister_netdev().
+ */
if (priv->plat->serdes_powerdown)
priv->plat->serdes_powerdown(ndev, priv->plat->bsp_priv);
- stmmac_mac_set(priv, priv->ioaddr, false);
- netif_carrier_off(ndev);
- unregister_netdev(ndev);
#ifdef CONFIG_DEBUG_FS
stmmac_exit_fs(ndev);
#endif
tx_q->cur_tx = 0;
tx_q->dirty_tx = 0;
tx_q->mss = 0;
+
+ netdev_tx_reset_queue(netdev_get_tx_queue(priv->dev, queue));
}
}
mp->rx_mcasts += RXMAC_MC_FRM_CNT_COUNT;
if (val & XRXMAC_STATUS_RXBCAST_CNT_EXP)
mp->rx_bcasts += RXMAC_BC_FRM_CNT_COUNT;
- if (val & XRXMAC_STATUS_RXBCAST_CNT_EXP)
- mp->rx_bcasts += RXMAC_BC_FRM_CNT_COUNT;
if (val & XRXMAC_STATUS_RXHIST1_CNT_EXP)
mp->rx_hist_cnt1 += RXMAC_HIST_CNT1_COUNT;
if (val & XRXMAC_STATUS_RXHIST2_CNT_EXP)
/*bdx_hw_reset(priv); */
if (bdx_read_mac(priv)) {
pr_err("load MAC address failed\n");
+ err = -EFAULT;
goto err_out_iomap;
}
SET_NETDEV_DEV(ndev, &pdev->dev);
return axienet_ior(lp, XAE_MDIO_MCR_OFFSET);
}
+static inline void axienet_lock_mii(struct axienet_local *lp)
+{
+ if (lp->mii_bus)
+ mutex_lock(&lp->mii_bus->mdio_lock);
+}
+
+static inline void axienet_unlock_mii(struct axienet_local *lp)
+{
+ if (lp->mii_bus)
+ mutex_unlock(&lp->mii_bus->mdio_lock);
+}
+
/**
* axienet_iow - Memory mapped Axi Ethernet register write
* @lp: Pointer to axienet local structure
* including the MDIO. MDIO must be disabled before resetting.
* Hold MDIO bus lock to avoid MDIO accesses during the reset.
*/
- mutex_lock(&lp->mii_bus->mdio_lock);
+ axienet_lock_mii(lp);
ret = axienet_device_reset(ndev);
- mutex_unlock(&lp->mii_bus->mdio_lock);
+ axienet_unlock_mii(lp);
ret = phylink_of_phy_connect(lp->phylink, lp->dev->of_node, 0);
if (ret) {
}
/* Do a reset to ensure DMA is really stopped */
- mutex_lock(&lp->mii_bus->mdio_lock);
+ axienet_lock_mii(lp);
__axienet_device_reset(lp);
- mutex_unlock(&lp->mii_bus->mdio_lock);
+ axienet_unlock_mii(lp);
cancel_work_sync(&lp->dma_err_task);
* including the MDIO. MDIO must be disabled before resetting.
* Hold MDIO bus lock to avoid MDIO accesses during the reset.
*/
- mutex_lock(&lp->mii_bus->mdio_lock);
+ axienet_lock_mii(lp);
__axienet_device_reset(lp);
- mutex_unlock(&lp->mii_bus->mdio_lock);
+ axienet_unlock_mii(lp);
for (i = 0; i < lp->tx_bd_num; i++) {
cur_p = &lp->tx_bd_v[i];
if (IS_ERR(lp->regs)) {
dev_err(&pdev->dev, "could not map Axi Ethernet regs.\n");
ret = PTR_ERR(lp->regs);
- goto free_netdev;
+ goto cleanup_clk;
}
lp->regs_start = ethres->start;
break;
default:
ret = -EINVAL;
- goto free_netdev;
+ goto cleanup_clk;
}
} else {
ret = of_get_phy_mode(pdev->dev.of_node, &lp->phy_mode);
if (ret)
- goto free_netdev;
+ goto cleanup_clk;
}
if (lp->switch_x_sgmii && lp->phy_mode != PHY_INTERFACE_MODE_SGMII &&
lp->phy_mode != PHY_INTERFACE_MODE_1000BASEX) {
dev_err(&pdev->dev, "xlnx,switch-x-sgmii only supported with SGMII or 1000BaseX\n");
ret = -EINVAL;
- goto free_netdev;
+ goto cleanup_clk;
}
/* Find the DMA node, map the DMA registers, and decode the DMA IRQs */
dev_err(&pdev->dev,
"unable to get DMA resource\n");
of_node_put(np);
- goto free_netdev;
+ goto cleanup_clk;
}
lp->dma_regs = devm_ioremap_resource(&pdev->dev,
&dmares);
if (IS_ERR(lp->dma_regs)) {
dev_err(&pdev->dev, "could not map DMA regs\n");
ret = PTR_ERR(lp->dma_regs);
- goto free_netdev;
+ goto cleanup_clk;
}
if ((lp->rx_irq <= 0) || (lp->tx_irq <= 0)) {
dev_err(&pdev->dev, "could not determine irqs\n");
ret = -ENOMEM;
- goto free_netdev;
+ goto cleanup_clk;
}
/* Autodetect the need for 64-bit DMA pointers.
ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(addr_width));
if (ret) {
dev_err(&pdev->dev, "No suitable DMA available\n");
- goto free_netdev;
+ goto cleanup_clk;
}
/* Check for Ethernet core IRQ (optional) */
if (!lp->phy_node) {
dev_err(&pdev->dev, "phy-handle required for 1000BaseX/SGMII\n");
ret = -EINVAL;
- goto free_netdev;
+ goto cleanup_mdio;
}
lp->pcs_phy = of_mdio_find_device(lp->phy_node);
if (!lp->pcs_phy) {
ret = -EPROBE_DEFER;
- goto free_netdev;
+ goto cleanup_mdio;
}
lp->phylink_config.pcs_poll = true;
}
if (IS_ERR(lp->phylink)) {
ret = PTR_ERR(lp->phylink);
dev_err(&pdev->dev, "phylink_create error (%i)\n", ret);
- goto free_netdev;
+ goto cleanup_mdio;
}
ret = register_netdev(lp->ndev);
if (ret) {
dev_err(lp->dev, "register_netdev() error (%i)\n", ret);
- goto free_netdev;
+ goto cleanup_phylink;
}
return 0;
+cleanup_phylink:
+ phylink_destroy(lp->phylink);
+
+cleanup_mdio:
+ if (lp->pcs_phy)
+ put_device(&lp->pcs_phy->dev);
+ if (lp->mii_bus)
+ axienet_mdio_teardown(lp);
+ of_node_put(lp->phy_node);
+
+cleanup_clk:
+ clk_disable_unprepare(lp->clk);
+
free_netdev:
free_netdev(ndev);
__be16 sport;
int err;
+ if (!pskb_network_may_pull(skb, sizeof(struct iphdr)))
+ return -EINVAL;
+
sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info,
geneve->cfg.info.key.tp_dst, sport);
info = skb_tunnel_info(skb);
if (info) {
- info->key.u.ipv4.dst = fl4.saddr;
- info->key.u.ipv4.src = fl4.daddr;
+ struct ip_tunnel_info *unclone;
+
+ unclone = skb_tunnel_info_unclone(skb);
+ if (unlikely(!unclone)) {
+ dst_release(&rt->dst);
+ return -ENOMEM;
+ }
+
+ unclone->key.u.ipv4.dst = fl4.saddr;
+ unclone->key.u.ipv4.src = fl4.daddr;
}
if (!pskb_may_pull(skb, ETH_HLEN)) {
__be16 sport;
int err;
+ if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr)))
+ return -EINVAL;
+
sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info,
geneve->cfg.info.key.tp_dst, sport);
struct ip_tunnel_info *info = skb_tunnel_info(skb);
if (info) {
- info->key.u.ipv6.dst = fl6.saddr;
- info->key.u.ipv6.src = fl6.daddr;
+ struct ip_tunnel_info *unclone;
+
+ unclone = skb_tunnel_info_unclone(skb);
+ if (unlikely(!unclone)) {
+ dst_release(dst);
+ return -ENOMEM;
+ }
+
+ unclone->key.u.ipv6.dst = fl6.saddr;
+ unclone->key.u.ipv6.src = fl6.daddr;
}
if (!pskb_may_pull(skb, ETH_HLEN)) {
goto out_drop;
}
- if (len > sp->mtu) { /* sp->mtu = AX25_MTU = max. PACLEN = 256 */
- msg = "oversized transmit packet!";
- goto out_drop;
- }
-
if (p[0] > 5) {
msg = "invalid KISS command";
goto out_drop;
MODULE_AUTHOR("Joerg Reuter <jreuter@yaina.de>");
MODULE_DESCRIPTION("AX.25 Device Driver for Z8530 based HDLC cards");
-MODULE_SUPPORTED_DEVICE("Z8530 based SCC cards for Amateur Radio");
MODULE_LICENSE("GPL");
module_init(scc_init_driver);
module_exit(scc_cleanup_driver);
bool xdp_tx);
void netvsc_linkstatus_callback(struct net_device *net,
struct rndis_message *resp,
- void *data);
+ void *data, u32 data_buflen);
int netvsc_recv_callback(struct net_device *net,
struct netvsc_device *nvdev,
struct netvsc_channel *nvchan);
*/
void netvsc_linkstatus_callback(struct net_device *net,
struct rndis_message *resp,
- void *data)
+ void *data, u32 data_buflen)
{
struct rndis_indicate_status *indicate = &resp->msg.indicate_status;
struct net_device_context *ndev_ctx = netdev_priv(net);
if (indicate->status == RNDIS_STATUS_LINK_SPEED_CHANGE) {
u32 speed;
- /* Validate status_buf_offset */
+ /* Validate status_buf_offset and status_buflen.
+ *
+ * Certain (pre-Fe) implementations of Hyper-V's vSwitch didn't account
+ * for the status buffer field in resp->msg_len; perform the validation
+ * using data_buflen (>= resp->msg_len).
+ */
if (indicate->status_buflen < sizeof(speed) ||
indicate->status_buf_offset < sizeof(*indicate) ||
- resp->msg_len - RNDIS_HEADER_SIZE < indicate->status_buf_offset ||
- resp->msg_len - RNDIS_HEADER_SIZE - indicate->status_buf_offset
+ data_buflen - RNDIS_HEADER_SIZE < indicate->status_buf_offset ||
+ data_buflen - RNDIS_HEADER_SIZE - indicate->status_buf_offset
< indicate->status_buflen) {
netdev_err(net, "invalid rndis_indicate_status packet\n");
return;
case RNDIS_MSG_INDICATE:
/* notification msgs */
- netvsc_linkstatus_callback(ndev, rndis_msg, data);
+ netvsc_linkstatus_callback(ndev, rndis_msg, data, buflen);
break;
default:
netdev_err(ndev,
return -ENOMEM;
}
usb_anchor_urb(urb, &atusb->idle_urbs);
+ usb_free_urb(urb);
n--;
}
return 0;
: field_max(IP_FLTRT_FLAGS_NHASH_ADDR_FMASK);
if (mem->offset > offset_max ||
ipa->mem_offset > offset_max - mem->offset) {
- dev_err(dev, "IPv%c %s%s table region offset too large "
- "(0x%04x + 0x%04x > 0x%04x)\n",
- ipv6 ? '6' : '4', hashed ? "hashed " : "",
- route ? "route" : "filter",
- ipa->mem_offset, mem->offset, offset_max);
+ dev_err(dev, "IPv%c %s%s table region offset too large\n",
+ ipv6 ? '6' : '4', hashed ? "hashed " : "",
+ route ? "route" : "filter");
+ dev_err(dev, " (0x%04x + 0x%04x > 0x%04x)\n",
+ ipa->mem_offset, mem->offset, offset_max);
+
return false;
}
if (mem->offset > ipa->mem_size ||
mem->size > ipa->mem_size - mem->offset) {
- dev_err(dev, "IPv%c %s%s table region out of range "
- "(0x%04x + 0x%04x > 0x%04x)\n",
- ipv6 ? '6' : '4', hashed ? "hashed " : "",
- route ? "route" : "filter",
- mem->offset, mem->size, ipa->mem_size);
+ dev_err(dev, "IPv%c %s%s table region out of range\n",
+ ipv6 ? '6' : '4', hashed ? "hashed " : "",
+ route ? "route" : "filter");
+ dev_err(dev, " (0x%04x + 0x%04x > 0x%04x)\n",
+ mem->offset, mem->size, ipa->mem_size);
+
return false;
}
u32 size_max;
u32 size;
+ /* In ipa_cmd_hdr_init_local_add() we record the offset and size
+ * of the header table memory area. Make sure the offset and size
+ * fit in the fields that need to hold them, and that the entire
+ * range is within the overall IPA memory range.
+ */
offset_max = field_max(HDR_INIT_LOCAL_FLAGS_HDR_ADDR_FMASK);
if (mem->offset > offset_max ||
ipa->mem_offset > offset_max - mem->offset) {
- dev_err(dev, "header table region offset too large "
- "(0x%04x + 0x%04x > 0x%04x)\n",
- ipa->mem_offset + mem->offset, offset_max);
+ dev_err(dev, "header table region offset too large\n");
+ dev_err(dev, " (0x%04x + 0x%04x > 0x%04x)\n",
+ ipa->mem_offset, mem->offset, offset_max);
+
return false;
}
size_max = field_max(HDR_INIT_LOCAL_FLAGS_TABLE_SIZE_FMASK);
size = ipa->mem[IPA_MEM_MODEM_HEADER].size;
size += ipa->mem[IPA_MEM_AP_HEADER].size;
- if (mem->offset > ipa->mem_size || size > ipa->mem_size - mem->offset) {
- dev_err(dev, "header table region out of range "
- "(0x%04x + 0x%04x > 0x%04x)\n",
- mem->offset, size, ipa->mem_size);
+
+ if (size > size_max) {
+ dev_err(dev, "header table region size too large\n");
+ dev_err(dev, " (0x%04x > 0x%08x)\n", size, size_max);
+
+ return false;
+ }
+ if (size > ipa->mem_size || mem->offset > ipa->mem_size - size) {
+ dev_err(dev, "header table region out of range\n");
+ dev_err(dev, " (0x%04x + 0x%04x > 0x%04x)\n",
+ mem->offset, size, ipa->mem_size);
+
return false;
}
.decoded_size = IPA_QMI_DRIVER_INIT_COMPLETE_REQ_SZ,
.fn = ipa_server_driver_init_complete,
},
+ { },
};
/* Handle an INIT_DRIVER response message from the modem. */
.decoded_size = IPA_QMI_INIT_DRIVER_RSP_SZ,
.fn = ipa_client_init_driver,
},
+ { },
};
/* Return a pointer to an init modem driver request structure, which contains
dev_net_set(dev, nsim_dev_net(nsim_dev));
ns = netdev_priv(dev);
ns->netdev = dev;
+ u64_stats_init(&ns->syncp);
ns->nsim_dev = nsim_dev;
ns->nsim_dev_port = nsim_dev_port;
ns->nsim_bus_dev = nsim_dev->nsim_bus_dev;
int bcm_phy_set_eee(struct phy_device *phydev, bool enable)
{
- int val;
+ int val, mask = 0;
/* Enable EEE at PHY level */
val = phy_read_mmd(phydev, MDIO_MMD_AN, BRCM_CL45VEN_EEE_CONTROL);
if (val < 0)
return val;
+ if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+ phydev->supported))
+ mask |= MDIO_EEE_1000T;
+ if (linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+ phydev->supported))
+ mask |= MDIO_EEE_100TX;
+
if (enable)
- val |= (MDIO_EEE_100TX | MDIO_EEE_1000T);
+ val |= mask;
else
- val &= ~(MDIO_EEE_100TX | MDIO_EEE_1000T);
+ val &= ~mask;
phy_write_mmd(phydev, MDIO_MMD_AN, BCM_CL45VEN_EEE_ADV, (u32)val);
bcm54xx_adjust_rxrefclk(phydev);
switch (BRCM_PHY_MODEL(phydev)) {
+ case PHY_ID_BCM50610:
+ case PHY_ID_BCM50610M:
+ err = bcm54xx_config_clock_delay(phydev);
+ break;
case PHY_ID_BCM54210E:
err = bcm54210e_config_init(phydev);
break;
if (ret < 0)
return ret;
+ /* Upon exiting power down, the PHY remains in an internal reset state
+ * for 40us
+ */
+ fsleep(40);
+
return bcm54xx_config_init(phydev);
}
static irqreturn_t dp83822_handle_interrupt(struct phy_device *phydev)
{
+ bool trigger_machine = false;
int irq_status;
/* The MISR1 and MISR2 registers are holding the interrupt status in
return IRQ_NONE;
}
if (irq_status & ((irq_status & GENMASK(7, 0)) << 8))
- goto trigger_machine;
+ trigger_machine = true;
irq_status = phy_read(phydev, MII_DP83822_MISR2);
if (irq_status < 0) {
return IRQ_NONE;
}
if (irq_status & ((irq_status & GENMASK(7, 0)) << 8))
- goto trigger_machine;
+ trigger_machine = true;
- return IRQ_NONE;
+ if (!trigger_machine)
+ return IRQ_NONE;
-trigger_machine:
phy_trigger_machine(phydev);
return IRQ_HANDLED;
static irqreturn_t dp83811_handle_interrupt(struct phy_device *phydev)
{
+ bool trigger_machine = false;
int irq_status;
/* The INT_STAT registers 1, 2 and 3 are holding the interrupt status
return IRQ_NONE;
}
if (irq_status & ((irq_status & GENMASK(7, 0)) << 8))
- goto trigger_machine;
+ trigger_machine = true;
irq_status = phy_read(phydev, MII_DP83811_INT_STAT2);
if (irq_status < 0) {
return IRQ_NONE;
}
if (irq_status & ((irq_status & GENMASK(7, 0)) << 8))
- goto trigger_machine;
+ trigger_machine = true;
irq_status = phy_read(phydev, MII_DP83811_INT_STAT3);
if (irq_status < 0) {
return IRQ_NONE;
}
if (irq_status & ((irq_status & GENMASK(7, 0)) << 8))
- goto trigger_machine;
+ trigger_machine = true;
- return IRQ_NONE;
+ if (!trigger_machine)
+ return IRQ_NONE;
-trigger_machine:
phy_trigger_machine(phydev);
return IRQ_HANDLED;
.get_stats = marvell_get_stats,
},
{
- .phy_id = MARVELL_PHY_ID_88E6390,
+ .phy_id = MARVELL_PHY_ID_88E6341_FAMILY,
.phy_id_mask = MARVELL_PHY_ID_MASK,
- .name = "Marvell 88E6390",
+ .name = "Marvell 88E6341 Family",
+ /* PHY_GBIT_FEATURES */
+ .flags = PHY_POLL_CABLE_TEST,
+ .probe = m88e1510_probe,
+ .config_init = marvell_config_init,
+ .config_aneg = m88e6390_config_aneg,
+ .read_status = marvell_read_status,
+ .config_intr = marvell_config_intr,
+ .handle_interrupt = marvell_handle_interrupt,
+ .resume = genphy_resume,
+ .suspend = genphy_suspend,
+ .read_page = marvell_read_page,
+ .write_page = marvell_write_page,
+ .get_sset_count = marvell_get_sset_count,
+ .get_strings = marvell_get_strings,
+ .get_stats = marvell_get_stats,
+ .get_tunable = m88e1540_get_tunable,
+ .set_tunable = m88e1540_set_tunable,
+ .cable_test_start = marvell_vct7_cable_test_start,
+ .cable_test_tdr_start = marvell_vct5_cable_test_tdr_start,
+ .cable_test_get_status = marvell_vct7_cable_test_get_status,
+ },
+ {
+ .phy_id = MARVELL_PHY_ID_88E6390_FAMILY,
+ .phy_id_mask = MARVELL_PHY_ID_MASK,
+ .name = "Marvell 88E6390 Family",
/* PHY_GBIT_FEATURES */
.flags = PHY_POLL_CABLE_TEST,
.probe = m88e6390_probe,
{ MARVELL_PHY_ID_88E1540, MARVELL_PHY_ID_MASK },
{ MARVELL_PHY_ID_88E1545, MARVELL_PHY_ID_MASK },
{ MARVELL_PHY_ID_88E3016, MARVELL_PHY_ID_MASK },
- { MARVELL_PHY_ID_88E6390, MARVELL_PHY_ID_MASK },
+ { MARVELL_PHY_ID_88E6341_FAMILY, MARVELL_PHY_ID_MASK },
+ { MARVELL_PHY_ID_88E6390_FAMILY, MARVELL_PHY_ID_MASK },
{ MARVELL_PHY_ID_88E1340S, MARVELL_PHY_ID_MASK },
{ MARVELL_PHY_ID_88E1548P, MARVELL_PHY_ID_MASK },
{ }
phydev->autoneg = autoneg;
- phydev->speed = speed;
+ if (autoneg == AUTONEG_DISABLE) {
+ phydev->speed = speed;
+ phydev->duplex = duplex;
+ }
linkmode_copy(phydev->advertising, advertising);
linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
phydev->advertising, autoneg == AUTONEG_ENABLE);
- phydev->duplex = duplex;
phydev->master_slave_set = cmd->base.master_slave_cfg;
phydev->mdix_ctrl = cmd->base.eth_tp_mdix_ctrl;
static LIST_HEAD(phy_fixup_list);
static DEFINE_MUTEX(phy_fixup_lock);
-#ifdef CONFIG_PM
static bool mdio_bus_phy_may_suspend(struct phy_device *phydev)
{
struct device_driver *drv = phydev->mdio.dev.driver;
return !phydev->suspended;
}
-static int mdio_bus_phy_suspend(struct device *dev)
+static __maybe_unused int mdio_bus_phy_suspend(struct device *dev)
{
struct phy_device *phydev = to_phy_device(dev);
return phy_suspend(phydev);
}
-static int mdio_bus_phy_resume(struct device *dev)
+static __maybe_unused int mdio_bus_phy_resume(struct device *dev)
{
struct phy_device *phydev = to_phy_device(dev);
int ret;
static SIMPLE_DEV_PM_OPS(mdio_bus_phy_pm_ops, mdio_bus_phy_suspend,
mdio_bus_phy_resume);
-#endif /* CONFIG_PM */
/**
* phy_register_fixup - creates a new phy_fixup and adds it to the list
err = pl->mac_ops->mac_finish(pl->config, pl->cur_link_an_mode,
state->interface);
if (err < 0)
- phylink_err(pl, "mac_prepare failed: %pe\n",
+ phylink_err(pl, "mac_finish failed: %pe\n",
ERR_PTR(err));
}
}
#include <linux/bpf.h>
#include <linux/bpf_trace.h>
#include <linux/mutex.h>
+#include <linux/ieee802154.h>
+#include <linux/if_ltalk.h>
+#include <uapi/linux/if_fddi.h>
+#include <uapi/linux/if_hippi.h>
+#include <uapi/linux/if_fc.h>
+#include <net/ax25.h>
+#include <net/rose.h>
+#include <net/6lowpan.h>
#include <linux/uaccess.h>
#include <linux/proc_fs.h>
return __tun_set_ebpf(tun, prog_p, prog);
}
+/* Return correct value for tun->dev->addr_len based on tun->dev->type. */
+static unsigned char tun_get_addr_len(unsigned short type)
+{
+ switch (type) {
+ case ARPHRD_IP6GRE:
+ case ARPHRD_TUNNEL6:
+ return sizeof(struct in6_addr);
+ case ARPHRD_IPGRE:
+ case ARPHRD_TUNNEL:
+ case ARPHRD_SIT:
+ return 4;
+ case ARPHRD_ETHER:
+ return ETH_ALEN;
+ case ARPHRD_IEEE802154:
+ case ARPHRD_IEEE802154_MONITOR:
+ return IEEE802154_EXTENDED_ADDR_LEN;
+ case ARPHRD_PHONET_PIPE:
+ case ARPHRD_PPP:
+ case ARPHRD_NONE:
+ return 0;
+ case ARPHRD_6LOWPAN:
+ return EUI64_ADDR_LEN;
+ case ARPHRD_FDDI:
+ return FDDI_K_ALEN;
+ case ARPHRD_HIPPI:
+ return HIPPI_ALEN;
+ case ARPHRD_IEEE802:
+ return FC_ALEN;
+ case ARPHRD_ROSE:
+ return ROSE_ADDR_LEN;
+ case ARPHRD_NETROM:
+ return AX25_ADDR_LEN;
+ case ARPHRD_LOCALTLK:
+ return LTALK_ALEN;
+ default:
+ return 0;
+ }
+}
+
static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
unsigned long arg, int ifreq_len)
{
break;
}
tun->dev->type = (int) arg;
+ tun->dev->addr_len = tun_get_addr_len(tun->dev->type);
netif_info(tun, drv, tun->dev, "linktype set to %d\n",
tun->dev->type);
call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE,
err = register_netdev(dev);
if (err) {
+ /* Set disconnected flag so that disconnect() returns early. */
+ pnd->disconnected = 1;
usb_driver_release_interface(&usbpn_driver, data_intf);
goto out;
}
/* check if we got everything */
if (!ctx->data) {
- dev_dbg(&intf->dev, "CDC Union missing and no IAD found\n");
+ dev_err(&intf->dev, "CDC Union missing and no IAD found\n");
goto error;
}
if (cdc_ncm_comm_intf_is_mbim(intf->cur_altsetting)) {
if (!ctx->mbim_desc) {
- dev_dbg(&intf->dev, "MBIM functional descriptor missing\n");
+ dev_err(&intf->dev, "MBIM functional descriptor missing\n");
goto error;
}
} else {
if (!ctx->ether_desc || !ctx->func_desc) {
- dev_dbg(&intf->dev, "NCM or ECM functional descriptors missing\n");
+ dev_err(&intf->dev, "NCM or ECM functional descriptors missing\n");
goto error;
}
}
if (ctx->data != ctx->control) {
temp = usb_driver_claim_interface(driver, ctx->data, dev);
if (temp) {
- dev_dbg(&intf->dev, "failed to claim data intf\n");
+ dev_err(&intf->dev, "failed to claim data intf\n");
goto error;
}
}
if (ctx->ether_desc) {
temp = usbnet_get_ethernet_addr(dev, ctx->ether_desc->iMACAddress);
if (temp) {
- dev_dbg(&intf->dev, "failed to get mac address\n");
+ dev_err(&intf->dev, "failed to get mac address\n");
goto error2;
}
dev_info(&intf->dev, "MAC-Address: %pM\n", dev->net->dev_addr);
return serial;
}
-static int get_free_serial_index(void)
+static int obtain_minor(struct hso_serial *serial)
{
int index;
unsigned long flags;
spin_lock_irqsave(&serial_table_lock, flags);
for (index = 0; index < HSO_SERIAL_TTY_MINORS; index++) {
if (serial_table[index] == NULL) {
+ serial_table[index] = serial->parent;
+ serial->minor = index;
spin_unlock_irqrestore(&serial_table_lock, flags);
- return index;
+ return 0;
}
}
spin_unlock_irqrestore(&serial_table_lock, flags);
return -1;
}
-static void set_serial_by_index(unsigned index, struct hso_serial *serial)
+static void release_minor(struct hso_serial *serial)
{
unsigned long flags;
spin_lock_irqsave(&serial_table_lock, flags);
- if (serial)
- serial_table[index] = serial->parent;
- else
- serial_table[index] = NULL;
+ serial_table[serial->minor] = NULL;
spin_unlock_irqrestore(&serial_table_lock, flags);
}
static void hso_serial_tty_unregister(struct hso_serial *serial)
{
tty_unregister_device(tty_drv, serial->minor);
+ release_minor(serial);
}
static void hso_serial_common_free(struct hso_serial *serial)
static int hso_serial_common_create(struct hso_serial *serial, int num_urbs,
int rx_size, int tx_size)
{
- int minor;
int i;
tty_port_init(&serial->port);
- minor = get_free_serial_index();
- if (minor < 0)
+ if (obtain_minor(serial))
goto exit2;
/* register our minor number */
serial->parent->dev = tty_port_register_device_attr(&serial->port,
- tty_drv, minor, &serial->parent->interface->dev,
+ tty_drv, serial->minor, &serial->parent->interface->dev,
serial->parent, hso_serial_dev_groups);
- if (IS_ERR(serial->parent->dev))
+ if (IS_ERR(serial->parent->dev)) {
+ release_minor(serial);
goto exit2;
+ }
- /* fill in specific data for later use */
- serial->minor = minor;
serial->magic = HSO_SERIAL_MAGIC;
spin_lock_init(&serial->serial_lock);
serial->num_rx_urbs = num_urbs;
serial->write_data = hso_std_serial_write_data;
- /* and record this serial */
- set_serial_by_index(serial->minor, serial);
-
/* setup the proc dirs and files if needed */
hso_log_port(hso_dev);
serial->shared_int->ref_count++;
mutex_unlock(&serial->shared_int->shared_int_lock);
- /* and record this serial */
- set_serial_by_index(serial->minor, serial);
-
/* setup the proc dirs and files if needed */
hso_log_port(hso_dev);
cancel_work_sync(&serial_table[i]->async_get_intf);
hso_serial_tty_unregister(serial);
kref_put(&serial_table[i]->ref, hso_serial_ref_free);
- set_serial_by_index(i, NULL);
}
}
goto err;
}
- /* we don't want to modify a running netdev */
- if (netif_running(dev->net)) {
- netdev_err(dev->net, "Cannot change a running device\n");
- ret = -EBUSY;
- goto err;
- }
-
ret = qmimux_register_device(dev->net, mux_id);
if (!ret) {
info->flags |= QMI_WWAN_FLAG_MUX;
if (!rtnl_trylock())
return restart_syscall();
- /* we don't want to modify a running netdev */
- if (netif_running(dev->net)) {
- netdev_err(dev->net, "Cannot change a running device\n");
- ret = -EBUSY;
- goto err;
- }
-
del_dev = qmimux_find_dev(dev, mux_id);
if (!del_dev) {
netdev_err(dev->net, "mux_id not present\n");
device_set_wakeup_enable(&tp->udev->dev, false);
}
-static void r8153_mac_clk_spd(struct r8152 *tp, bool enable)
-{
- /* MAC clock speed down */
- if (enable) {
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL,
- ALDPS_SPDWN_RATIO);
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL2,
- EEE_SPDWN_RATIO);
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3,
- PKT_AVAIL_SPDWN_EN | SUSPEND_SPDWN_EN |
- U1U2_SPDWN_EN | L1_SPDWN_EN);
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL4,
- PWRSAVE_SPDWN_EN | RXDV_SPDWN_EN | TX10MIDLE_EN |
- TP100_SPDWN_EN | TP500_SPDWN_EN | EEE_SPDWN_EN |
- TP1000_SPDWN_EN);
- } else {
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL, 0);
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL2, 0);
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, 0);
- ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL4, 0);
- }
-}
-
static void r8153_u1u2en(struct r8152 *tp, bool enable)
{
u8 u1u2[8];
if (enable) {
r8153_u1u2en(tp, false);
r8153_u2p3en(tp, false);
- r8153_mac_clk_spd(tp, true);
rtl_runtime_suspend_enable(tp, true);
} else {
rtl_runtime_suspend_enable(tp, false);
- r8153_mac_clk_spd(tp, false);
switch (tp->version) {
case RTL_VER_03:
{
u32 ocp_data;
- r8153_mac_clk_spd(tp, false);
rxdy_gated_en(tp, true);
r8153_teredo_off(tp);
{
u32 ocp_data;
- r8153_mac_clk_spd(tp, true);
-
ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL);
ocp_data &= ~NOW_IS_OOB;
ocp_write_byte(tp, MCU_TYPE_PLA, PLA_OOB_CTRL, ocp_data);
ocp_write_word(tp, MCU_TYPE_USB, USB_CONNECT_TIMER, 0x0001);
+ /* MAC clock speed down */
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL, 0);
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL2, 0);
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL3, 0);
+ ocp_write_word(tp, MCU_TYPE_PLA, PLA_MAC_PWR_CTRL4, 0);
+
r8153_power_cut_en(tp, false);
rtl_runtime_suspend_enable(tp, false);
r8153_u1u2en(tp, true);
- r8153_mac_clk_spd(tp, false);
usb_enable_lpm(tp->udev);
ocp_data = ocp_read_byte(tp, MCU_TYPE_PLA, PLA_CONFIG6);
ops->in_nway = rtl8153_in_nway;
ops->hw_phy_cfg = r8153_hw_phy_cfg;
ops->autosuspend_en = rtl8153_runtime_enable;
- tp->rx_buf_sz = 32 * 1024;
+ if (tp->udev->speed < USB_SPEED_SUPER)
+ tp->rx_buf_sz = 16 * 1024;
+ else
+ tp->rx_buf_sz = 32 * 1024;
tp->eee_en = true;
tp->eee_adv = MDIO_EEE_1000T | MDIO_EEE_100TX;
break;
// insist peer be connected
if (info->check_connect && (retval = info->check_connect (dev)) < 0) {
- netif_dbg(dev, ifup, dev->net, "can't open; %d\n", retval);
+ netif_err(dev, ifup, dev->net, "can't open; %d\n", retval);
goto done;
}
if (rxq < rcv->real_num_rx_queues) {
rq = &rcv_priv->rq[rxq];
rcv_xdp = rcu_access_pointer(rq->xdp_prog);
- if (rcv_xdp)
- skb_record_rx_queue(skb, rxq);
+ skb_record_rx_queue(skb, rxq);
}
skb_tx_timestamp(skb);
offset += hdr_padded_len;
p += hdr_padded_len;
- copy = len;
- if (copy > skb_tailroom(skb))
- copy = skb_tailroom(skb);
+ /* Copy all frame if it fits skb->head, otherwise
+ * we let virtio_net_hdr_to_skb() and GRO pull headers as needed.
+ */
+ if (len <= skb_tailroom(skb))
+ copy = len;
+ else
+ copy = ETH_HLEN + metasize;
skb_put_data(skb, p, copy);
if (metasize) {
skb_dst_drop(skb);
- /* if dst.dev is loopback or the VRF device again this is locally
- * originated traffic destined to a local address. Short circuit
- * to Rx path
+ /* if dst.dev is the VRF device again this is locally originated traffic
+ * destined to a local address. Short circuit to Rx path.
*/
if (dst->dev == dev)
return vrf_local_xmit(skb, dev, dst);
skb_dst_drop(skb);
- /* if dst.dev is loopback or the VRF device again this is locally
- * originated traffic destined to a local address. Short circuit
- * to Rx path
+ /* if dst.dev is the VRF device again this is locally originated traffic
+ * destined to a local address. Short circuit to Rx path.
*/
if (rt->dst.dev == vrf_dev)
return vrf_local_xmit(skb, vrf_dev, &rt->dst);
goto tx_error;
} else if (err) {
if (info) {
+ struct ip_tunnel_info *unclone;
struct in_addr src, dst;
+ unclone = skb_tunnel_info_unclone(skb);
+ if (unlikely(!unclone))
+ goto tx_error;
+
src = remote_ip.sin.sin_addr;
dst = local_ip.sin.sin_addr;
- info->key.u.ipv4.src = src.s_addr;
- info->key.u.ipv4.dst = dst.s_addr;
+ unclone->key.u.ipv4.src = src.s_addr;
+ unclone->key.u.ipv4.dst = dst.s_addr;
}
vxlan_encap_bypass(skb, vxlan, vxlan, vni, false);
dst_release(ndst);
goto tx_error;
} else if (err) {
if (info) {
+ struct ip_tunnel_info *unclone;
struct in6_addr src, dst;
+ unclone = skb_tunnel_info_unclone(skb);
+ if (unlikely(!unclone))
+ goto tx_error;
+
src = remote_ip.sin6.sin6_addr;
dst = local_ip.sin6.sin6_addr;
- info->key.u.ipv6.src = src;
- info->key.u.ipv6.dst = dst;
+ unclone->key.u.ipv6.src = src;
+ unclone->key.u.ipv6.dst = dst;
}
vxlan_encap_bypass(skb, vxlan, vxlan, vni, false);
priv->rx_skbuff = kcalloc(priv->rx_ring_size,
sizeof(*priv->rx_skbuff),
GFP_KERNEL);
- if (!priv->rx_skbuff)
+ if (!priv->rx_skbuff) {
+ ret = -ENOMEM;
goto free_ucc_pram;
+ }
priv->tx_skbuff = kcalloc(priv->tx_ring_size,
sizeof(*priv->tx_skbuff),
GFP_KERNEL);
- if (!priv->tx_skbuff)
+ if (!priv->tx_skbuff) {
+ ret = -ENOMEM;
goto free_rx_skbuff;
+ }
priv->skb_curtx = 0;
priv->skb_dirtytx = 0;
if (pad > 0) { /* Pad the frame with zeros */
if (__skb_pad(skb, pad, false))
- goto drop;
+ goto out;
skb_put(skb, pad);
}
}
return NETDEV_TX_OK;
drop:
- dev->stats.tx_dropped++;
kfree_skb(skb);
+out:
+ dev->stats.tx_dropped++;
return NETDEV_TX_OK;
}
struct x25_state {
x25_hdlc_proto settings;
+ bool up;
+ spinlock_t up_lock; /* Protects "up" */
};
static int x25_ioctl(struct net_device *dev, struct ifreq *ifr);
static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev)
{
+ hdlc_device *hdlc = dev_to_hdlc(dev);
+ struct x25_state *x25st = state(hdlc);
int result;
/* There should be a pseudo header of 1 byte added by upper layers.
return NETDEV_TX_OK;
}
+ spin_lock_bh(&x25st->up_lock);
+ if (!x25st->up) {
+ spin_unlock_bh(&x25st->up_lock);
+ kfree_skb(skb);
+ return NETDEV_TX_OK;
+ }
+
switch (skb->data[0]) {
case X25_IFACE_DATA: /* Data to be transmitted */
skb_pull(skb, 1);
if ((result = lapb_data_request(dev, skb)) != LAPB_OK)
dev_kfree_skb(skb);
+ spin_unlock_bh(&x25st->up_lock);
return NETDEV_TX_OK;
case X25_IFACE_CONNECT:
break;
}
+ spin_unlock_bh(&x25st->up_lock);
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
.data_transmit = x25_data_transmit,
};
hdlc_device *hdlc = dev_to_hdlc(dev);
+ struct x25_state *x25st = state(hdlc);
struct lapb_parms_struct params;
int result;
if (result != LAPB_OK)
return -EINVAL;
+ spin_lock_bh(&x25st->up_lock);
+ x25st->up = true;
+ spin_unlock_bh(&x25st->up_lock);
+
return 0;
}
static void x25_close(struct net_device *dev)
{
+ hdlc_device *hdlc = dev_to_hdlc(dev);
+ struct x25_state *x25st = state(hdlc);
+
+ spin_lock_bh(&x25st->up_lock);
+ x25st->up = false;
+ spin_unlock_bh(&x25st->up_lock);
+
lapb_unregister(dev);
}
static int x25_rx(struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
+ hdlc_device *hdlc = dev_to_hdlc(dev);
+ struct x25_state *x25st = state(hdlc);
if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) {
dev->stats.rx_dropped++;
return NET_RX_DROP;
}
- if (lapb_data_received(dev, skb) == LAPB_OK)
+ spin_lock_bh(&x25st->up_lock);
+ if (!x25st->up) {
+ spin_unlock_bh(&x25st->up_lock);
+ kfree_skb(skb);
+ dev->stats.rx_dropped++;
+ return NET_RX_DROP;
+ }
+
+ if (lapb_data_received(dev, skb) == LAPB_OK) {
+ spin_unlock_bh(&x25st->up_lock);
return NET_RX_SUCCESS;
+ }
+ spin_unlock_bh(&x25st->up_lock);
dev->stats.rx_errors++;
dev_kfree_skb_any(skb);
return NET_RX_DROP;
return result;
memcpy(&state(hdlc)->settings, &new_settings, size);
+ state(hdlc)->up = false;
+ spin_lock_init(&state(hdlc)->up_lock);
/* There's no header_ops so hard_header_len should be 0. */
dev->hard_header_len = 0;
return -ENODEV;
}
- netif_start_queue(dev);
return 0;
}
{
int err;
- netif_stop_queue(dev);
-
if ((err = lapb_unregister(dev)) != LAPB_OK)
pr_err("lapb_unregister error: %d\n", err);
MODULE_AUTHOR("Michael Wu <flamingice@sourmilk.net>");
MODULE_AUTHOR("Jouni Malinen <j@w1.fi>");
MODULE_DESCRIPTION("Driver for IEEE 802.11b wireless cards based on ADMtek ADM8211");
-MODULE_SUPPORTED_DEVICE("ADM8211");
MODULE_LICENSE("GPL");
static unsigned int tx_ring_size __read_mostly = 16;
}
if (ab->hw_params.vdev_start_delay &&
- (arvif->vdev_type == WMI_VDEV_TYPE_AP ||
- arvif->vdev_type == WMI_VDEV_TYPE_MONITOR)) {
+ arvif->vdev_type != WMI_VDEV_TYPE_AP &&
+ arvif->vdev_type != WMI_VDEV_TYPE_MONITOR) {
param.vdev_id = arvif->vdev_id;
param.peer_type = WMI_PEER_TYPE_DEFAULT;
param.peer_addr = ar->mac_addr;
req->mem_seg[i].size = ab->qmi.target_mem[i].size;
req->mem_seg[i].type = ab->qmi.target_mem[i].type;
ath11k_dbg(ab, ATH11K_DBG_QMI,
- "qmi req mem_seg[%d] 0x%llx %u %u\n", i,
- ab->qmi.target_mem[i].paddr,
+ "qmi req mem_seg[%d] %pad %u %u\n", i,
+ &ab->qmi.target_mem[i].paddr,
ab->qmi.target_mem[i].size,
ab->qmi.target_mem[i].type);
}
MODULE_AUTHOR("Jiri Slaby");
MODULE_AUTHOR("Nick Kossifidis");
MODULE_DESCRIPTION("Support for 5xxx series of Atheros 802.11 wireless LAN cards.");
-MODULE_SUPPORTED_DEVICE("Atheros 5xxx WLAN cards");
MODULE_LICENSE("Dual BSD/GPL");
static int ath5k_init(struct ieee80211_hw *hw);
s8 txq;
u8 keyix;
u8 rtscts_rate;
- u8 retries : 7;
+ u8 retries : 6;
+ u8 dyn_smps : 1;
u8 baw_tracked : 1;
u8 tx_power;
enum ath9k_key_type keytype:2;
int first_slot = ATH_BCBUF;
int slot;
- tasklet_disable(&sc->bcon_tasklet);
+ tasklet_disable_in_atomic(&sc->bcon_tasklet);
/* Find first taken slot. */
for (slot = 0; slot < ATH_BCBUF; slot++) {
MODULE_AUTHOR("Atheros Communications");
MODULE_DESCRIPTION("Support for Atheros 802.11n wireless LAN cards.");
-MODULE_SUPPORTED_DEVICE("Atheros 802.11n WLAN cards");
MODULE_LICENSE("Dual BSD/GPL");
static void ath9k_hw_set_clockrate(struct ath_hw *ah)
MODULE_AUTHOR("Atheros Communications");
MODULE_DESCRIPTION("Support for Atheros 802.11n wireless LAN cards.");
-MODULE_SUPPORTED_DEVICE("Atheros 802.11n WLAN cards");
MODULE_LICENSE("Dual BSD/GPL");
static unsigned int ath9k_debug = ATH_DBG_DEFAULT;
is_40, is_sgi, is_sp);
if (rix < 8 && (tx_info->flags & IEEE80211_TX_CTL_STBC))
info->rates[i].RateFlags |= ATH9K_RATESERIES_STBC;
+ if (rix >= 8 && fi->dyn_smps) {
+ info->rates[i].RateFlags |=
+ ATH9K_RATESERIES_RTS_CTS;
+ info->flags |= ATH9K_TXDESC_CTSENA;
+ }
info->txpower[i] = ath_get_rate_txpower(sc, bf, rix,
is_40, false);
fi->keyix = an->ps_key;
else
fi->keyix = ATH9K_TXKEYIX_INVALID;
+ fi->dyn_smps = sta && sta->smps_mode == IEEE80211_SMPS_DYNAMIC;
fi->keytype = keytype;
fi->framelen = framelen;
fi->tx_power = txpower;
MODULE_AUTHOR("Simon Kelley");
MODULE_DESCRIPTION("Support for Atmel at76c50x 802.11 wireless ethernet cards.");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("Atmel at76c50x wireless cards");
/* The name of the firmware file to be loaded
over-rides any automatic selection */
MODULE_AUTHOR("Simon Kelley");
MODULE_DESCRIPTION("Support for Atmel at76c50x 802.11 wireless ethernet cards.");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("Atmel at76c50x PCMCIA cards");
/*====================================================================*/
MODULE_AUTHOR("Simon Kelley");
MODULE_DESCRIPTION("Support for Atmel at76c50x 802.11 wireless ethernet cards.");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("Atmel at76c506 PCI wireless cards");
static const struct pci_device_id card_ids[] = {
{ 0x1114, 0x0506, PCI_ANY_ID, PCI_ANY_ID },
vif = ifp->vif;
cfg = wdev_to_cfg(&vif->wdev);
cfg->p2p.bss_idx[P2PAPI_BSSCFG_DEVICE].vif = NULL;
- if (locked) {
+ if (!locked) {
rtnl_lock();
wiphy_lock(cfg->wiphy);
cfg80211_unregister_wdev(&vif->wdev);
MODULE_AUTHOR("Broadcom Corporation");
MODULE_DESCRIPTION("Broadcom 802.11n wireless LAN driver.");
-MODULE_SUPPORTED_DEVICE("Broadcom 802.11n WLAN cards");
MODULE_LICENSE("Dual BSD/GPL");
/* This needs to be adjusted when brcms_firmwares changes */
MODULE_FIRMWARE("brcm/bcm43xx-0.fw");
MODULE_AUTHOR("Broadcom Corporation");
MODULE_DESCRIPTION("Broadcom 802.11n wireless LAN driver utilities.");
-MODULE_SUPPORTED_DEVICE("Broadcom 802.11n WLAN cards");
MODULE_LICENSE("Dual BSD/GPL");
struct sk_buff *brcmu_pkt_buf_get_skb(uint len)
MODULE_DESCRIPTION("Support for Cisco/Aironet 802.11 wireless ethernet cards. "
"Direct support for ISA/PCI/MPI cards and support for PCMCIA when used with airo_cs.");
MODULE_LICENSE("Dual BSD/GPL");
-MODULE_SUPPORTED_DEVICE("Aironet 4500, 4800 and Cisco 340/350");
module_param_hw_array(io, int, ioport, NULL, 0);
module_param_hw_array(irq, int, irq, NULL, 0);
module_param_array(rates, int, NULL, 0);
"cards. This is the module that links the PCMCIA card "
"with the airo module.");
MODULE_LICENSE("Dual BSD/GPL");
-MODULE_SUPPORTED_DEVICE("Aironet 4500, 4800 and Cisco 340 PCMCIA cards");
/*====================================================================*/
// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
/*
- * Copyright (C) 2005-2014 Intel Corporation
+ * Copyright (C) 2005-2014, 2021 Intel Corporation
* Copyright (C) 2015-2017 Intel Deutschland GmbH
*/
#include <linux/sched.h>
if (!list_empty(¬if_wait->notif_waits)) {
struct iwl_notification_wait *w;
- spin_lock(¬if_wait->notif_wait_lock);
+ spin_lock_bh(¬if_wait->notif_wait_lock);
list_for_each_entry(w, ¬if_wait->notif_waits, list) {
int i;
bool found = false;
triggered = true;
}
}
- spin_unlock(¬if_wait->notif_wait_lock);
+ spin_unlock_bh(¬if_wait->notif_wait_lock);
}
return triggered;
{
struct iwl_notification_wait *wait_entry;
- spin_lock(¬if_wait->notif_wait_lock);
+ spin_lock_bh(¬if_wait->notif_wait_lock);
list_for_each_entry(wait_entry, ¬if_wait->notif_waits, list)
wait_entry->aborted = true;
- spin_unlock(¬if_wait->notif_wait_lock);
+ spin_unlock_bh(¬if_wait->notif_wait_lock);
wake_up_all(¬if_wait->notif_waitq);
}
err = efivar_entry_get(pnvm_efivar, NULL, &package_size, package);
if (err) {
IWL_DEBUG_FW(trans,
- "PNVM UEFI variable not found %d (len %zd)\n",
+ "PNVM UEFI variable not found %d (len %lu)\n",
err, package_size);
goto out;
}
- IWL_DEBUG_FW(trans, "Read PNVM fro UEFI with size %zd\n", package_size);
+ IWL_DEBUG_FW(trans, "Read PNVM fro UEFI with size %lu\n", package_size);
*data = kmemdup(package->data, *len, GFP_KERNEL);
if (!*data)
#define IWL_CFG_MAC_TYPE_QNJ 0x36
#define IWL_CFG_MAC_TYPE_SO 0x37
#define IWL_CFG_MAC_TYPE_SNJ 0x42
+#define IWL_CFG_MAC_TYPE_SOF 0x43
#define IWL_CFG_MAC_TYPE_MA 0x44
#define IWL_CFG_RF_TYPE_TH 0x105
REG_CAPA_V2_MCS_9_ALLOWED = BIT(6),
REG_CAPA_V2_WEATHER_DISABLED = BIT(7),
REG_CAPA_V2_40MHZ_ALLOWED = BIT(8),
- REG_CAPA_V2_11AX_DISABLED = BIT(13),
+ REG_CAPA_V2_11AX_DISABLED = BIT(10),
};
/*
enum iwl_fw_ini_time_point tp_id,
union iwl_dbg_tlv_tp_data *tp_data)
{
+ if (!op_mode || !op_mode->ops || !op_mode->ops->time_point)
+ return;
op_mode->ops->time_point(op_mode, tp_id, tp_data);
}
return -EINVAL;
/* value zero triggers re-sending the default table to the device */
- if (!op_id)
+ if (!op_id) {
+ mutex_lock(&mvm->mutex);
ret = iwl_rfi_send_config_cmd(mvm, NULL);
- else
+ mutex_unlock(&mvm->mutex);
+ } else {
ret = -EOPNOTSUPP; /* in the future a new table will be added */
+ }
return ret ?: count;
}
DMI_MATCH(DMI_SYS_VENDOR, "ASUSTek COMPUTER INC."),
},
},
+ {}
};
static int iwl_mvm_ppag_init(struct iwl_mvm *mvm)
// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
/*
- * Copyright (C) 2020 Intel Corporation
+ * Copyright (C) 2020 - 2021 Intel Corporation
*/
#include "mvm.h"
if (!fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_RFIM_SUPPORT))
return -EOPNOTSUPP;
+ lockdep_assert_held(&mvm->mutex);
+
/* in case no table is passed, use the default one */
if (!rfi_table) {
memcpy(cmd.table, iwl_rfi_table, sizeof(cmd.table));
cmd.oem = 1;
}
- mutex_lock(&mvm->mutex);
ret = iwl_mvm_send_cmd(mvm, &hcmd);
- mutex_unlock(&mvm->mutex);
if (ret)
IWL_ERR(mvm, "Failed to send RFI config cmd %d\n", ret);
rx_status->chain_signal[2] = S8_MIN;
}
-static int iwl_mvm_rx_mgmt_crypto(struct ieee80211_sta *sta,
- struct ieee80211_hdr *hdr,
- struct iwl_rx_mpdu_desc *desc,
- u32 status)
+static int iwl_mvm_rx_mgmt_prot(struct ieee80211_sta *sta,
+ struct ieee80211_hdr *hdr,
+ struct iwl_rx_mpdu_desc *desc,
+ u32 status)
{
struct iwl_mvm_sta *mvmsta;
struct iwl_mvm_vif *mvmvif;
u32 len = le16_to_cpu(desc->mpdu_len);
const u8 *frame = (void *)hdr;
+ if ((status & IWL_RX_MPDU_STATUS_SEC_MASK) == IWL_RX_MPDU_STATUS_SEC_NONE)
+ return 0;
+
/*
* For non-beacon, we don't really care. But beacons may
* be filtered out, and we thus need the firmware's replay
IWL_RX_MPDU_STATUS_SEC_UNKNOWN && !mvm->monitor_on)
return -1;
+ if (unlikely(ieee80211_is_mgmt(hdr->frame_control) &&
+ !ieee80211_has_protected(hdr->frame_control)))
+ return iwl_mvm_rx_mgmt_prot(sta, hdr, desc, status);
+
if (!ieee80211_has_protected(hdr->frame_control) ||
(status & IWL_RX_MPDU_STATUS_SEC_MASK) ==
IWL_RX_MPDU_STATUS_SEC_NONE)
stats->flag |= RX_FLAG_DECRYPTED;
return 0;
case RX_MPDU_RES_STATUS_SEC_CMAC_GMAC_ENC:
- return iwl_mvm_rx_mgmt_crypto(sta, hdr, desc, status);
+ break;
default:
/*
* Sometimes we can get frames that were not decrypted
// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
/*
- * Copyright (C) 2018-2020 Intel Corporation
+ * Copyright (C) 2018-2021 Intel Corporation
*/
#include "iwl-trans.h"
#include "iwl-fh.h"
const struct fw_img *fw)
{
struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
- u32 ltr_val = CSR_LTR_LONG_VAL_AD_NO_SNOOP_REQ |
- u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC,
- CSR_LTR_LONG_VAL_AD_NO_SNOOP_SCALE) |
- u32_encode_bits(250,
- CSR_LTR_LONG_VAL_AD_NO_SNOOP_VAL) |
- CSR_LTR_LONG_VAL_AD_SNOOP_REQ |
- u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC,
- CSR_LTR_LONG_VAL_AD_SNOOP_SCALE) |
- u32_encode_bits(250, CSR_LTR_LONG_VAL_AD_SNOOP_VAL);
struct iwl_context_info_gen3 *ctxt_info_gen3;
struct iwl_prph_scratch *prph_scratch;
struct iwl_prph_scratch_ctrl_cfg *prph_sc_ctrl;
iwl_set_bit(trans, CSR_CTXT_INFO_BOOT_CTRL,
CSR_AUTO_FUNC_BOOT_ENA);
- /*
- * To workaround hardware latency issues during the boot process,
- * initialize the LTR to ~250 usec (see ltr_val above).
- * The firmware initializes this again later (to a smaller value).
- */
- if ((trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_AX210 ||
- trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000) &&
- !trans->trans_cfg->integrated) {
- iwl_write32(trans, CSR_LTR_LONG_VAL_AD, ltr_val);
- } else if (trans->trans_cfg->integrated &&
- trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000) {
- iwl_write_prph(trans, HPM_MAC_LTR_CSR, HPM_MAC_LRT_ENABLE_ALL);
- iwl_write_prph(trans, HPM_UMAC_LTR, ltr_val);
- }
-
- if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
- iwl_write_umac_prph(trans, UREG_CPU_INIT_RUN, 1);
- else
- iwl_set_bit(trans, CSR_GP_CNTRL, CSR_AUTO_FUNC_INIT);
-
return 0;
err_free_ctxt_info:
// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
/*
* Copyright (C) 2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2020 Intel Corporation
+ * Copyright (C) 2018-2021 Intel Corporation
*/
#include "iwl-trans.h"
#include "iwl-fh.h"
/* kick FW self load */
iwl_write64(trans, CSR_CTXT_INFO_BA, trans_pcie->ctxt_info_dma_addr);
- iwl_write_prph(trans, UREG_CPU_INIT_RUN, 1);
/* Context info will be released upon alive or failure to get one */
IWL_DEV_INFO(0x4DF0, 0x1652, killer1650i_2ax_cfg_qu_b0_hr_b0, NULL),
IWL_DEV_INFO(0x4DF0, 0x2074, iwl_ax201_cfg_qu_hr, NULL),
IWL_DEV_INFO(0x4DF0, 0x4070, iwl_ax201_cfg_qu_hr, NULL),
+ IWL_DEV_INFO(0x4DF0, 0x6074, iwl_ax201_cfg_qu_hr, NULL),
/* So with HR */
IWL_DEV_INFO(0x2725, 0x0090, iwlax211_2ax_cfg_so_gf_a0, NULL),
IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY,
IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
- iwl_cfg_so_a0_hr_a0, iwl_ax201_name)
+ iwl_cfg_so_a0_hr_a0, iwl_ax201_name),
+
+/* So-F with Hr */
+ _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
+ IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY,
+ IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ iwl_cfg_so_a0_hr_a0, iwl_ax203_name),
+ _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
+ IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY,
+ IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ iwl_cfg_so_a0_hr_a0, iwl_ax101_name),
+ _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
+ IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY,
+ IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ iwl_cfg_so_a0_hr_a0, iwl_ax201_name),
+
+/* So-F with Gf */
+ _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+ IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
+ IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY,
+ IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+ iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_name),
#endif /* CONFIG_IWLMVM */
};
}
}
+#if IS_ENABLED(CONFIG_IWLMVM)
+
/*
* Workaround for problematic SnJ device: sometimes when
* certain RF modules are connected to SnJ, the device ID
if (CSR_HW_REV_TYPE(iwl_trans->hw_rev) == IWL_CFG_MAC_TYPE_SNJ)
iwl_trans->trans_cfg = &iwl_so_trans_cfg;
-#if IS_ENABLED(CONFIG_IWLMVM)
/*
* special-case 7265D, it has the same PCI IDs.
*
iwl_pcie_rx_init_rxb_lists(rxq);
+ spin_unlock_bh(&rxq->lock);
+
if (!rxq->napi.poll) {
int (*poll)(struct napi_struct *, int) = iwl_pcie_napi_poll;
napi_enable(&rxq->napi);
}
- spin_unlock_bh(&rxq->lock);
}
/* move the pool to the default queue and allocator ownerships */
mutex_unlock(&trans_pcie->mutex);
}
+static void iwl_pcie_set_ltr(struct iwl_trans *trans)
+{
+ u32 ltr_val = CSR_LTR_LONG_VAL_AD_NO_SNOOP_REQ |
+ u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC,
+ CSR_LTR_LONG_VAL_AD_NO_SNOOP_SCALE) |
+ u32_encode_bits(250,
+ CSR_LTR_LONG_VAL_AD_NO_SNOOP_VAL) |
+ CSR_LTR_LONG_VAL_AD_SNOOP_REQ |
+ u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC,
+ CSR_LTR_LONG_VAL_AD_SNOOP_SCALE) |
+ u32_encode_bits(250, CSR_LTR_LONG_VAL_AD_SNOOP_VAL);
+
+ /*
+ * To workaround hardware latency issues during the boot process,
+ * initialize the LTR to ~250 usec (see ltr_val above).
+ * The firmware initializes this again later (to a smaller value).
+ */
+ if ((trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_AX210 ||
+ trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000) &&
+ !trans->trans_cfg->integrated) {
+ iwl_write32(trans, CSR_LTR_LONG_VAL_AD, ltr_val);
+ } else if (trans->trans_cfg->integrated &&
+ trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000) {
+ iwl_write_prph(trans, HPM_MAC_LTR_CSR, HPM_MAC_LRT_ENABLE_ALL);
+ iwl_write_prph(trans, HPM_UMAC_LTR, ltr_val);
+ }
+}
+
int iwl_trans_pcie_gen2_start_fw(struct iwl_trans *trans,
const struct fw_img *fw, bool run_in_rfkill)
{
if (ret)
goto out;
+ iwl_pcie_set_ltr(trans);
+
+ if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210)
+ iwl_write_umac_prph(trans, UREG_CPU_INIT_RUN, 1);
+ else
+ iwl_write_prph(trans, UREG_CPU_INIT_RUN, 1);
+
/* re-check RF-Kill state since we may have missed the interrupt */
hw_rfkill = iwl_pcie_check_hw_rf_kill(trans);
if (hw_rfkill && !run_in_rfkill)
u32 cmd_pos;
const u8 *cmddata[IWL_MAX_CMD_TBS_PER_TFD];
u16 cmdlen[IWL_MAX_CMD_TBS_PER_TFD];
+ unsigned long flags;
if (WARN(!trans->wide_cmd_header &&
group_id > IWL_ALWAYS_LONG_GROUP,
goto free_dup_buf;
}
- spin_lock_bh(&txq->lock);
+ spin_lock_irqsave(&txq->lock, flags);
if (iwl_txq_space(trans, txq) < ((cmd->flags & CMD_ASYNC) ? 2 : 1)) {
- spin_unlock_bh(&txq->lock);
+ spin_unlock_irqrestore(&txq->lock, flags);
IWL_ERR(trans, "No space in command queue\n");
iwl_op_mode_cmd_queue_full(trans->op_mode);
unlock_reg:
spin_unlock(&trans_pcie->reg_lock);
out:
- spin_unlock_bh(&txq->lock);
+ spin_unlock_irqrestore(&txq->lock, flags);
free_dup_buf:
if (idx < 0)
kfree(dup_buf);
MODULE_AUTHOR("Jouni Malinen");
MODULE_DESCRIPTION("Support for Intersil Prism2-based 802.11 wireless LAN "
"cards (PC Card).");
-MODULE_SUPPORTED_DEVICE("Intersil Prism2-based WLAN cards (PC Card)");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jouni Malinen");
MODULE_DESCRIPTION("Support for Intersil Prism2.5-based 802.11 wireless LAN "
"PCI cards.");
-MODULE_SUPPORTED_DEVICE("Intersil Prism2.5-based WLAN PCI cards");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Jouni Malinen");
MODULE_DESCRIPTION("Support for Intersil Prism2-based 802.11 wireless LAN "
"cards (PLX).");
-MODULE_SUPPORTED_DEVICE("Intersil Prism2-based WLAN cards (PLX)");
MODULE_LICENSE("GPL");
};
struct ieee80211_hw *hw;
int len, n = 0, ret = -ENOMEM;
- struct mt76_queue_entry e;
struct mt76_txwi_cache *t;
struct sk_buff *iter;
dma_addr_t addr;
}
tx_info.nbuf = n;
+ if (q->queued + (tx_info.nbuf + 1) / 2 >= q->ndesc - 1) {
+ ret = -ENOMEM;
+ goto unmap;
+ }
+
dma_sync_single_for_cpu(dev->dev, t->dma_addr, dev->drv->txwi_size,
DMA_TO_DEVICE);
ret = dev->drv->tx_prepare_skb(dev, txwi, q->qid, wcid, sta, &tx_info);
if (ret < 0)
goto unmap;
- if (q->queued + (tx_info.nbuf + 1) / 2 >= q->ndesc - 1) {
- ret = -ENOMEM;
- goto unmap;
- }
-
return mt76_dma_add_buf(dev, q, tx_info.buf, tx_info.nbuf,
tx_info.info, tx_info.skb, t);
}
#endif
- e.skb = tx_info.skb;
- e.txwi = t;
- dev->drv->tx_complete_skb(dev, &e);
+ dev_kfree_skb(tx_info.skb);
mt76_put_txwi(dev, t);
return ret;
}
{
struct sk_buff *skb = q->rx_head;
struct skb_shared_info *shinfo = skb_shinfo(skb);
+ int nr_frags = shinfo->nr_frags;
- if (shinfo->nr_frags < ARRAY_SIZE(shinfo->frags)) {
+ if (nr_frags < ARRAY_SIZE(shinfo->frags)) {
struct page *page = virt_to_head_page(data);
int offset = data - page_address(page) + q->buf_offset;
- skb_add_rx_frag(skb, shinfo->nr_frags, page, offset, len,
- q->buf_size);
+ skb_add_rx_frag(skb, nr_frags, page, offset, len, q->buf_size);
} else {
skb_free_frag(data);
}
return;
q->rx_head = NULL;
- dev->drv->rx_skb(dev, q - dev->q_rx, skb);
+ if (nr_frags < ARRAY_SIZE(shinfo->frags))
+ dev->drv->rx_skb(dev, q - dev->q_rx, skb);
+ else
+ dev_kfree_skb(skb);
}
static int
}
txp->nbuf = nbuf;
- /* pass partial skb header to fw */
- tx_info->buf[1].len = MT_CT_PARSE_LEN;
- tx_info->buf[1].skip_unmap = true;
- tx_info->nbuf = MT_CT_DMA_BUF_NUM;
-
txp->flags = cpu_to_le16(MT_CT_INFO_APPLY_TXD | MT_CT_INFO_FROM_HOST);
if (!key)
txp->rept_wds_wcid = cpu_to_le16(0x3ff);
tx_info->skb = DMA_DUMMY_DATA;
+ /* pass partial skb header to fw */
+ tx_info->buf[1].len = MT_CT_PARSE_LEN;
+ tx_info->buf[1].skip_unmap = true;
+ tx_info->nbuf = MT_CT_DMA_BUF_NUM;
+
return 0;
}
tx_cont->bw = CMD_CBW_20MHZ;
break;
default:
- break;
+ return -EINVAL;
}
if (!en) {
mode = MT_PHY_TYPE_HE_MU;
break;
default:
- break;
+ return -EINVAL;
}
rateval = mode << 6 | rate_idx;
if (wlan_idx >= MT76_N_WCIDS)
return;
wcid = rcu_dereference(dev->mt76.wcid[wlan_idx]);
- if (!wcid) {
- stats->tx_rate = rate;
+ if (!wcid)
return;
- }
msta = container_of(wcid, struct mt7921_sta, wcid);
stats = &msta->stats;
#define MT_WTBLON_TOP_BASE 0x34000
#define MT_WTBLON_TOP(ofs) (MT_WTBLON_TOP_BASE + (ofs))
-#define MT_WTBLON_TOP_WDUCR MT_WTBLON_TOP(0x0)
+#define MT_WTBLON_TOP_WDUCR MT_WTBLON_TOP(0x200)
#define MT_WTBLON_TOP_WDUCR_GROUP GENMASK(2, 0)
-#define MT_WTBL_UPDATE MT_WTBLON_TOP(0x030)
+#define MT_WTBL_UPDATE MT_WTBLON_TOP(0x230)
#define MT_WTBL_UPDATE_WLAN_IDX GENMASK(9, 0)
#define MT_WTBL_UPDATE_ADM_COUNT_CLEAR BIT(12)
#define MT_WTBL_UPDATE_BUSY BIT(31)
MODULE_AUTHOR(DRV_PROJECT);
MODULE_VERSION(DRV_VERSION);
MODULE_DESCRIPTION("Ralink RT2400 PCI & PCMCIA Wireless LAN driver.");
-MODULE_SUPPORTED_DEVICE("Ralink RT2460 PCI & PCMCIA chipset based cards");
MODULE_DEVICE_TABLE(pci, rt2400pci_device_table);
MODULE_LICENSE("GPL");
MODULE_AUTHOR(DRV_PROJECT);
MODULE_VERSION(DRV_VERSION);
MODULE_DESCRIPTION("Ralink RT2500 PCI & PCMCIA Wireless LAN driver.");
-MODULE_SUPPORTED_DEVICE("Ralink RT2560 PCI & PCMCIA chipset based cards");
MODULE_DEVICE_TABLE(pci, rt2500pci_device_table);
MODULE_LICENSE("GPL");
MODULE_AUTHOR(DRV_PROJECT);
MODULE_VERSION(DRV_VERSION);
MODULE_DESCRIPTION("Ralink RT2500 USB Wireless LAN driver.");
-MODULE_SUPPORTED_DEVICE("Ralink RT2570 USB chipset based cards");
MODULE_DEVICE_TABLE(usb, rt2500usb_device_table);
MODULE_LICENSE("GPL");
MODULE_AUTHOR(DRV_PROJECT);
MODULE_VERSION(DRV_VERSION);
MODULE_DESCRIPTION("Ralink RT2800 PCI & PCMCIA Wireless LAN driver.");
-MODULE_SUPPORTED_DEVICE("Ralink RT2860 PCI & PCMCIA chipset based cards");
MODULE_FIRMWARE(FIRMWARE_RT2860);
MODULE_DEVICE_TABLE(pci, rt2800pci_device_table);
MODULE_LICENSE("GPL");
MODULE_AUTHOR(DRV_PROJECT);
MODULE_VERSION(DRV_VERSION);
MODULE_DESCRIPTION("Ralink RT2800 USB Wireless LAN driver.");
-MODULE_SUPPORTED_DEVICE("Ralink RT2870 USB chipset based cards");
MODULE_DEVICE_TABLE(usb, rt2800usb_device_table);
MODULE_FIRMWARE(FIRMWARE_RT2870);
MODULE_LICENSE("GPL");
MODULE_AUTHOR(DRV_PROJECT);
MODULE_VERSION(DRV_VERSION);
MODULE_DESCRIPTION("Ralink RT61 PCI & PCMCIA Wireless LAN driver.");
-MODULE_SUPPORTED_DEVICE("Ralink RT2561, RT2561s & RT2661 "
- "PCI & PCMCIA chipset based cards");
MODULE_DEVICE_TABLE(pci, rt61pci_device_table);
MODULE_FIRMWARE(FIRMWARE_RT2561);
MODULE_FIRMWARE(FIRMWARE_RT2561s);
MODULE_AUTHOR(DRV_PROJECT);
MODULE_VERSION(DRV_VERSION);
MODULE_DESCRIPTION("Ralink RT73 USB Wireless LAN driver.");
-MODULE_SUPPORTED_DEVICE("Ralink RT2571W & RT2671 USB chipset based cards");
MODULE_DEVICE_TABLE(usb, rt73usb_device_table);
MODULE_FIRMWARE(FIRMWARE_RT2571);
MODULE_LICENSE("GPL");
module_exit(rsi_91x_hal_module_exit);
MODULE_AUTHOR("Redpine Signals Inc");
MODULE_DESCRIPTION("Station driver for RSI 91x devices");
-MODULE_SUPPORTED_DEVICE("RSI-91x");
MODULE_VERSION("0.1");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_AUTHOR("Redpine Signals Inc");
MODULE_DESCRIPTION("Common SDIO layer for RSI drivers");
-MODULE_SUPPORTED_DEVICE("RSI-91x");
MODULE_DEVICE_TABLE(sdio, rsi_dev_table);
MODULE_FIRMWARE(FIRMWARE_RSI9113);
MODULE_VERSION("0.1");
MODULE_AUTHOR("Redpine Signals Inc");
MODULE_DESCRIPTION("Common USB layer for RSI drivers");
-MODULE_SUPPORTED_DEVICE("RSI-91x");
MODULE_DEVICE_TABLE(usb, rsi_dev_table);
MODULE_FIRMWARE(FIRMWARE_RSI9113);
MODULE_VERSION("0.1");
#include <net/cfg80211.h>
#include <net/rtnetlink.h>
#include <linux/etherdevice.h>
+#include <linux/math64.h>
#include <linux/module.h>
static struct wiphy *common_wiphy;
scan_result.work);
struct wiphy *wiphy = priv_to_wiphy(priv);
struct cfg80211_scan_info scan_info = { .aborted = false };
+ u64 tsf = div_u64(ktime_get_boottime_ns(), 1000);
informed_bss = cfg80211_inform_bss(wiphy, &channel_5ghz,
CFG80211_BSS_FTYPE_PRESP,
- fake_router_bssid,
- ktime_get_boottime_ns(),
+ fake_router_bssid, tsf,
WLAN_CAPABILITY_ESS, 0,
(void *)&ssid, sizeof(ssid),
DBM_TO_MBM(-50), GFP_KERNEL);
}
if (skb_has_frag_list(skb) && !first_shinfo) {
- first_shinfo = skb_shinfo(skb);
- shinfo = skb_shinfo(skb_shinfo(skb)->frag_list);
+ first_shinfo = shinfo;
+ shinfo = skb_shinfo(shinfo->frag_list);
nr_frags = shinfo->nr_frags;
goto check_frags;
xenvif_carrier_on(be->vif);
unregister_hotplug_status_watch(be);
- err = xenbus_watch_pathfmt(dev, &be->hotplug_status_watch, NULL,
- hotplug_status_changed,
- "%s/%s", dev->nodename, "hotplug-status");
- if (!err)
+ if (xenbus_exists(XBT_NIL, dev->nodename, "hotplug-status")) {
+ err = xenbus_watch_pathfmt(dev, &be->hotplug_status_watch,
+ NULL, hotplug_status_changed,
+ "%s/%s", dev->nodename,
+ "hotplug-status");
+ if (err)
+ goto err;
be->have_hotplug_status_watch = 1;
+ }
netif_tx_wake_all_queues(be->vif->dev);
struct nd_region *nd_region = to_nd_region(dev->parent);
int disk_ro = get_disk_ro(disk);
- /*
- * Upgrade to read-only if the region is read-only preserve as
- * read-only if the disk is already read-only.
- */
- if (disk_ro || nd_region->ro == disk_ro)
+ /* catch the disk up with the region ro state */
+ if (disk_ro == nd_region->ro)
return;
- dev_info(dev, "%s read-only, marking %s read-only\n",
- dev_name(&nd_region->dev), disk->disk_name);
- set_disk_ro(disk, 1);
+ dev_info(dev, "%s read-%s, marking %s read-%s\n",
+ dev_name(&nd_region->dev), nd_region->ro ? "only" : "write",
+ disk->disk_name, nd_region->ro ? "only" : "write");
+ set_disk_ro(disk, nd_region->ro);
}
EXPORT_SYMBOL(nvdimm_check_and_set_ro);
#include <linux/mm.h>
#include <asm/cacheflush.h>
#include "pmem.h"
+#include "btt.h"
#include "pfn.h"
#include "nd.h"
nvdimm_flush(to_nd_region(dev->parent), NULL);
}
-static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)
+static void pmem_revalidate_poison(struct device *dev)
{
struct nd_region *nd_region;
resource_size_t offset = 0, end_trunc = 0;
struct range range;
struct kernfs_node *bb_state;
- if (event != NVDIMM_REVALIDATE_POISON)
- return;
-
if (is_nd_btt(dev)) {
struct nd_btt *nd_btt = to_nd_btt(dev);
sysfs_notify_dirent(bb_state);
}
+static void pmem_revalidate_region(struct device *dev)
+{
+ struct pmem_device *pmem;
+
+ if (is_nd_btt(dev)) {
+ struct nd_btt *nd_btt = to_nd_btt(dev);
+ struct btt *btt = nd_btt->btt;
+
+ nvdimm_check_and_set_ro(btt->btt_disk);
+ return;
+ }
+
+ pmem = dev_get_drvdata(dev);
+ nvdimm_check_and_set_ro(pmem->disk);
+}
+
+static void nd_pmem_notify(struct device *dev, enum nvdimm_event event)
+{
+ switch (event) {
+ case NVDIMM_REVALIDATE_POISON:
+ pmem_revalidate_poison(dev);
+ break;
+ case NVDIMM_REVALIDATE_REGION:
+ pmem_revalidate_region(dev);
+ break;
+ default:
+ dev_WARN_ONCE(dev, 1, "notify: unknown event: %d\n", event);
+ break;
+ }
+}
+
MODULE_ALIAS("pmem");
MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_IO);
MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_PMEM);
return sprintf(buf, "%d\n", nd_region->ro);
}
+static int revalidate_read_only(struct device *dev, void *data)
+{
+ nd_device_notify(dev, NVDIMM_REVALIDATE_REGION);
+ return 0;
+}
+
static ssize_t read_only_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
return rc;
nd_region->ro = ro;
+ device_for_each_child(dev, NULL, revalidate_read_only);
return len;
}
static DEVICE_ATTR_RW(read_only);
|| !IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API))
return -ENXIO;
+ /* Test if an explicit flush function is defined */
+ if (test_bit(ND_REGION_ASYNC, &nd_region->flags) && nd_region->flush)
+ return 1;
+
+ /* Test if any flush hints for the region are available */
for (i = 0; i < nd_region->ndr_mappings; i++) {
struct nd_mapping *nd_mapping = &nd_region->mapping[i];
struct nvdimm *nvdimm = nd_mapping->nvdimm;
}
/*
- * The platform defines dimm devices without hints, assume
- * platform persistence mechanism like ADR
+ * The platform defines dimm devices without hints nor explicit flush,
+ * assume platform persistence mechanism like ADR
*/
return 0;
}
return true;
nvme_req(req)->status = NVME_SC_HOST_ABORTED_CMD;
+ nvme_req(req)->flags |= NVME_REQ_CANCELLED;
blk_mq_complete_request(req);
return true;
}
queue_delayed_work(nvme_wq, &ctrl->ka_work, ctrl->kato * HZ);
}
-static int nvme_keep_alive(struct nvme_ctrl *ctrl)
-{
- struct request *rq;
-
- rq = nvme_alloc_request(ctrl->admin_q, &ctrl->ka_cmd,
- BLK_MQ_REQ_RESERVED);
- if (IS_ERR(rq))
- return PTR_ERR(rq);
-
- rq->timeout = ctrl->kato * HZ;
- rq->end_io_data = ctrl;
-
- blk_execute_rq_nowait(NULL, rq, 0, nvme_keep_alive_end_io);
-
- return 0;
-}
-
static void nvme_keep_alive_work(struct work_struct *work)
{
struct nvme_ctrl *ctrl = container_of(to_delayed_work(work),
struct nvme_ctrl, ka_work);
bool comp_seen = ctrl->comp_seen;
+ struct request *rq;
if ((ctrl->ctratt & NVME_CTRL_ATTR_TBKAS) && comp_seen) {
dev_dbg(ctrl->device,
return;
}
- if (nvme_keep_alive(ctrl)) {
+ rq = nvme_alloc_request(ctrl->admin_q, &ctrl->ka_cmd,
+ BLK_MQ_REQ_RESERVED | BLK_MQ_REQ_NOWAIT);
+ if (IS_ERR(rq)) {
/* allocation failure, reset the controller */
- dev_err(ctrl->device, "keep-alive failed\n");
+ dev_err(ctrl->device, "keep-alive failed: %ld\n", PTR_ERR(rq));
nvme_reset_ctrl(ctrl);
return;
}
+
+ rq->timeout = ctrl->kato * HZ;
+ rq->end_io_data = ctrl;
+ blk_execute_rq_nowait(NULL, rq, 0, nvme_keep_alive_end_io);
}
static void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
goto out_free_id;
}
- error = -ENODEV;
+ error = NVME_SC_INVALID_NS | NVME_SC_DNR;
if ((*id)->ncap == 0) /* namespace not allocated or attached */
goto out_free_id;
blk_queue_max_write_zeroes_sectors(queue, UINT_MAX);
}
-static void nvme_config_write_zeroes(struct gendisk *disk, struct nvme_ns *ns)
+/*
+ * Even though NVMe spec explicitly states that MDTS is not applicable to the
+ * write-zeroes, we are cautious and limit the size to the controllers
+ * max_hw_sectors value, which is based on the MDTS field and possibly other
+ * limiting factors.
+ */
+static void nvme_config_write_zeroes(struct request_queue *q,
+ struct nvme_ctrl *ctrl)
{
- u64 max_blocks;
-
- if (!(ns->ctrl->oncs & NVME_CTRL_ONCS_WRITE_ZEROES) ||
- (ns->ctrl->quirks & NVME_QUIRK_DISABLE_WRITE_ZEROES))
- return;
- /*
- * Even though NVMe spec explicitly states that MDTS is not
- * applicable to the write-zeroes:- "The restriction does not apply to
- * commands that do not transfer data between the host and the
- * controller (e.g., Write Uncorrectable ro Write Zeroes command).".
- * In order to be more cautious use controller's max_hw_sectors value
- * to configure the maximum sectors for the write-zeroes which is
- * configured based on the controller's MDTS field in the
- * nvme_init_identify() if available.
- */
- if (ns->ctrl->max_hw_sectors == UINT_MAX)
- max_blocks = (u64)USHRT_MAX + 1;
- else
- max_blocks = ns->ctrl->max_hw_sectors + 1;
-
- blk_queue_max_write_zeroes_sectors(disk->queue,
- nvme_lba_to_sect(ns, max_blocks));
+ if ((ctrl->oncs & NVME_CTRL_ONCS_WRITE_ZEROES) &&
+ !(ctrl->quirks & NVME_QUIRK_DISABLE_WRITE_ZEROES))
+ blk_queue_max_write_zeroes_sectors(q, ctrl->max_hw_sectors);
}
static bool nvme_ns_ids_valid(struct nvme_ns_ids *ids)
set_capacity_and_notify(disk, capacity);
nvme_config_discard(disk, ns);
- nvme_config_write_zeroes(disk, ns);
+ nvme_config_write_zeroes(disk->queue, ns->ctrl);
set_disk_ro(disk, (id->nsattr & NVME_NS_ATTR_RO) ||
test_bit(NVME_NS_FORCE_RO, &ns->flags));
static void nvme_validate_ns(struct nvme_ns *ns, struct nvme_ns_ids *ids)
{
struct nvme_id_ns *id;
- int ret = -ENODEV;
+ int ret = NVME_SC_INVALID_NS | NVME_SC_DNR;
if (test_bit(NVME_NS_DEAD, &ns->flags))
goto out;
if (ret)
goto out;
- ret = -ENODEV;
+ ret = NVME_SC_INVALID_NS | NVME_SC_DNR;
if (!nvme_ns_ids_equal(&ns->head->ids, ids)) {
dev_err(ns->ctrl->device,
"identifiers changed for nsid %d\n", ns->head->ns_id);
*
* TODO: we should probably schedule a delayed retry here.
*/
- if (ret && ret != -ENOMEM && !(ret > 0 && !(ret & NVME_SC_DNR)))
+ if (ret > 0 && (ret & NVME_SC_DNR))
nvme_ns_remove(ns);
}
nsid);
break;
}
+ if (!nvme_multi_css(ctrl)) {
+ dev_warn(ctrl->device,
+ "command set not reported for nsid: %d\n",
+ nsid);
+ break;
+ }
nvme_alloc_ns(ctrl, nsid, &ids);
break;
default:
#define NVMF_DEF_FAIL_FAST_TMO -1
/*
+ * Reserved one command for internal usage. This command is used for sending
+ * the connect command, as well as for the keep alive command on the admin
+ * queue once live.
+ */
+#define NVMF_RESERVED_TAGS 1
+
+/*
* Define a host as seen by the target. We allocate one at boot, but also
* allow the override it when creating controllers. This is both to provide
* persistence of the Host NQN over multiple boots, and to allow using
sizeof(op->rsp_iu), DMA_FROM_DEVICE);
if (opstate == FCPOP_STATE_ABORTED)
- status = cpu_to_le16(NVME_SC_HOST_PATH_ERROR << 1);
+ status = cpu_to_le16(NVME_SC_HOST_ABORTED_CMD << 1);
else if (freq->status) {
status = cpu_to_le16(NVME_SC_HOST_PATH_ERROR << 1);
dev_info(ctrl->ctrl.device,
nvme_fc_complete_rq(rq);
check_error:
- if (terminate_assoc)
+ if (terminate_assoc && ctrl->ctrl.state != NVME_CTRL_RESETTING)
queue_work(nvme_reset_wq, &ctrl->ioerr_work);
}
struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(req);
+ op->nreq.flags |= NVME_REQ_CANCELLED;
__nvme_fc_abort_op(ctrl, op);
return true;
}
memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set));
ctrl->tag_set.ops = &nvme_fc_mq_ops;
ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size;
- ctrl->tag_set.reserved_tags = 1; /* fabric connect */
+ ctrl->tag_set.reserved_tags = NVMF_RESERVED_TAGS;
ctrl->tag_set.numa_node = ctrl->ctrl.numa_node;
ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
ctrl->tag_set.cmd_size =
memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set));
ctrl->admin_tag_set.ops = &nvme_fc_admin_mq_ops;
ctrl->admin_tag_set.queue_depth = NVME_AQ_MQ_TAG_DEPTH;
- ctrl->admin_tag_set.reserved_tags = 2; /* fabric connect + Keep-Alive */
+ ctrl->admin_tag_set.reserved_tags = NVMF_RESERVED_TAGS;
ctrl->admin_tag_set.numa_node = ctrl->ctrl.numa_node;
ctrl->admin_tag_set.cmd_size =
struct_size((struct nvme_fcp_op_w_sgl *)NULL, priv,
.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, },
{ PCI_DEVICE(0x144d, 0xa822), /* Samsung PM1725a */
.driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY |
+ NVME_QUIRK_DISABLE_WRITE_ZEROES|
NVME_QUIRK_IGNORE_DEV_SUBNQN, },
{ PCI_DEVICE(0x1987, 0x5016), /* Phison E16 */
.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, },
return ret;
ctrl->ctrl.queue_count = nr_io_queues + 1;
- if (ctrl->ctrl.queue_count < 2)
- return 0;
+ if (ctrl->ctrl.queue_count < 2) {
+ dev_err(ctrl->ctrl.device,
+ "unable to set any I/O queues\n");
+ return -ENOMEM;
+ }
dev_info(ctrl->ctrl.device,
"creating %d I/O queues.\n", nr_io_queues);
memset(set, 0, sizeof(*set));
set->ops = &nvme_rdma_admin_mq_ops;
set->queue_depth = NVME_AQ_MQ_TAG_DEPTH;
- set->reserved_tags = 2; /* connect + keep-alive */
+ set->reserved_tags = NVMF_RESERVED_TAGS;
set->numa_node = nctrl->numa_node;
set->cmd_size = sizeof(struct nvme_rdma_request) +
NVME_RDMA_DATA_SGL_SIZE;
memset(set, 0, sizeof(*set));
set->ops = &nvme_rdma_mq_ops;
set->queue_depth = nctrl->sqsize + 1;
- set->reserved_tags = 1; /* fabric connect */
+ set->reserved_tags = NVMF_RESERVED_TAGS;
set->numa_node = nctrl->numa_node;
set->flags = BLK_MQ_F_SHOULD_MERGE;
set->cmd_size = sizeof(struct nvme_rdma_request) +
* directly, otherwise queue io_work. Also, only do that if we
* are on the same cpu, so we don't introduce contention.
*/
- if (queue->io_cpu == __smp_processor_id() &&
+ if (queue->io_cpu == raw_smp_processor_id() &&
sync && empty && mutex_trylock(&queue->send_mutex)) {
queue->more_requests = !last;
nvme_tcp_send_all(queue);
req->pdu_len = le32_to_cpu(pdu->r2t_length);
req->pdu_sent = 0;
+ if (unlikely(!req->pdu_len)) {
+ dev_err(queue->ctrl->ctrl.device,
+ "req %d r2t len is %u, probably a bug...\n",
+ rq->tag, req->pdu_len);
+ return -EPROTO;
+ }
+
if (unlikely(req->data_sent + req->pdu_len > req->data_len)) {
dev_err(queue->ctrl->ctrl.device,
"req %d r2t len %u exceeded data len %u (%zu sent)\n",
memset(set, 0, sizeof(*set));
set->ops = &nvme_tcp_admin_mq_ops;
set->queue_depth = NVME_AQ_MQ_TAG_DEPTH;
- set->reserved_tags = 2; /* connect + keep-alive */
+ set->reserved_tags = NVMF_RESERVED_TAGS;
set->numa_node = nctrl->numa_node;
set->flags = BLK_MQ_F_BLOCKING;
set->cmd_size = sizeof(struct nvme_tcp_request);
memset(set, 0, sizeof(*set));
set->ops = &nvme_tcp_mq_ops;
set->queue_depth = nctrl->sqsize + 1;
- set->reserved_tags = 1; /* fabric connect */
+ set->reserved_tags = NVMF_RESERVED_TAGS;
set->numa_node = nctrl->numa_node;
set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING;
set->cmd_size = sizeof(struct nvme_tcp_request);
return ret;
ctrl->queue_count = nr_io_queues + 1;
- if (ctrl->queue_count < 2)
- return 0;
+ if (ctrl->queue_count < 2) {
+ dev_err(ctrl->device,
+ "unable to set any I/O queues\n");
+ return -ENOMEM;
+ }
dev_info(ctrl->device,
"creating %d I/O queues.\n", nr_io_queues);
int nvme_revalidate_zones(struct nvme_ns *ns)
{
- return blk_revalidate_disk_zones(ns->disk, NULL);
+ struct request_queue *q = ns->queue;
+ int ret;
+
+ ret = blk_revalidate_disk_zones(ns->disk, NULL);
+ if (!ret)
+ blk_queue_max_zone_append_sectors(q, ns->ctrl->max_zone_append);
+ return ret;
}
static int nvme_set_max_append(struct nvme_ctrl *ctrl)
blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
blk_queue_max_open_zones(q, le32_to_cpu(id->mor) + 1);
blk_queue_max_active_zones(q, le32_to_cpu(id->mar) + 1);
- blk_queue_max_zone_append_sectors(q, ns->ctrl->max_zone_append);
free_data:
kfree(id);
return status;
{
lockdep_assert_held(&ctrl->lock);
- if (nvmet_cc_iosqes(ctrl->cc) != NVME_NVM_IOSQES ||
- nvmet_cc_iocqes(ctrl->cc) != NVME_NVM_IOCQES ||
- nvmet_cc_mps(ctrl->cc) != 0 ||
+ /*
+ * Only I/O controllers should verify iosqes,iocqes.
+ * Strictly speaking, the spec says a discovery controller
+ * should verify iosqes,iocqes are zeroed, however that
+ * would break backwards compatibility, so don't enforce it.
+ */
+ if (ctrl->subsys->type != NVME_NQN_DISC &&
+ (nvmet_cc_iosqes(ctrl->cc) != NVME_NVM_IOSQES ||
+ nvmet_cc_iocqes(ctrl->cc) != NVME_NVM_IOCQES)) {
+ ctrl->csts = NVME_CSTS_CFS;
+ return;
+ }
+
+ if (nvmet_cc_mps(ctrl->cc) != 0 ||
nvmet_cc_ams(ctrl->cc) != 0 ||
nvmet_cc_css(ctrl->cc) != 0) {
ctrl->csts = NVME_CSTS_CFS;
memset(&ctrl->admin_tag_set, 0, sizeof(ctrl->admin_tag_set));
ctrl->admin_tag_set.ops = &nvme_loop_admin_mq_ops;
ctrl->admin_tag_set.queue_depth = NVME_AQ_MQ_TAG_DEPTH;
- ctrl->admin_tag_set.reserved_tags = 2; /* connect + keep-alive */
+ ctrl->admin_tag_set.reserved_tags = NVMF_RESERVED_TAGS;
ctrl->admin_tag_set.numa_node = ctrl->ctrl.numa_node;
ctrl->admin_tag_set.cmd_size = sizeof(struct nvme_loop_iod) +
NVME_INLINE_SG_CNT * sizeof(struct scatterlist);
memset(&ctrl->tag_set, 0, sizeof(ctrl->tag_set));
ctrl->tag_set.ops = &nvme_loop_mq_ops;
ctrl->tag_set.queue_depth = ctrl->ctrl.opts->queue_size;
- ctrl->tag_set.reserved_tags = 1; /* fabric connect */
+ ctrl->tag_set.reserved_tags = NVMF_RESERVED_TAGS;
ctrl->tag_set.numa_node = ctrl->ctrl.numa_node;
ctrl->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
ctrl->tag_set.cmd_size = sizeof(struct nvme_loop_iod) +
/*
* nvmet_passthru_map_sg is limitted to using a single bio so limit
- * the mdts based on BIO_MAX_PAGES as well
+ * the mdts based on BIO_MAX_VECS as well
*/
- max_hw_sectors = min_not_zero(BIO_MAX_PAGES << (PAGE_SHIFT - 9),
+ max_hw_sectors = min_not_zero(BIO_MAX_VECS << (PAGE_SHIFT - 9),
max_hw_sectors);
page_shift = NVME_CAP_MPSMIN(ctrl->cap) + 12;
struct bio *bio;
int i;
- if (req->sg_cnt > BIO_MAX_PAGES)
+ if (req->sg_cnt > BIO_MAX_VECS)
return -EINVAL;
if (req->transfer_len <= NVMET_MAX_INLINE_DATA_LEN) {
nvmet_req_uninit(&rsp->req);
nvmet_rdma_release_rsp(rsp);
if (wc->status != IB_WC_WR_FLUSH_ERR) {
- pr_info("RDMA WRITE for CQE 0x%p failed with status %s (%d).\n",
- wc->wr_cqe, ib_wc_status_msg(wc->status),
- wc->status);
+ pr_info("RDMA WRITE for CQE failed with status %s (%d).\n",
+ ib_wc_status_msg(wc->status), wc->status);
nvmet_rdma_error_comp(queue);
}
return;
cmd->rbytes_done += ret;
}
+ nvmet_tcp_unmap_pdu_iovec(cmd);
if (queue->data_digest) {
nvmet_tcp_prep_recv_ddgst(cmd);
return 0;
}
- nvmet_tcp_unmap_pdu_iovec(cmd);
if (!(cmd->flags & NVMET_TCP_F_INIT_FAILED) &&
cmd->rbytes_done == cmd->req.transfer_len) {
*pprev = NULL;
}
-static bool populate_node(const void *blob,
+static int populate_node(const void *blob,
int offset,
void **mem,
struct device_node *dad,
{
struct device_node *np;
const char *pathp;
- unsigned int l, allocl;
+ int len;
- pathp = fdt_get_name(blob, offset, &l);
+ pathp = fdt_get_name(blob, offset, &len);
if (!pathp) {
*pnp = NULL;
- return false;
+ return len;
}
- allocl = ++l;
+ len++;
- np = unflatten_dt_alloc(mem, sizeof(struct device_node) + allocl,
+ np = unflatten_dt_alloc(mem, sizeof(struct device_node) + len,
__alignof__(struct device_node));
if (!dryrun) {
char *fn;
of_node_init(np);
np->full_name = fn = ((char *)np) + sizeof(*np);
- memcpy(fn, pathp, l);
+ memcpy(fn, pathp, len);
if (dad != NULL) {
np->parent = dad;
struct device_node *nps[FDT_MAX_DEPTH];
void *base = mem;
bool dryrun = !base;
+ int ret;
if (nodepp)
*nodepp = NULL;
!of_fdt_device_is_available(blob, offset))
continue;
- if (!populate_node(blob, offset, &mem, nps[depth],
- &nps[depth+1], dryrun))
- return mem - base;
+ ret = populate_node(blob, offset, &mem, nps[depth],
+ &nps[depth+1], dryrun);
+ if (ret < 0)
+ return ret;
if (!dryrun && nodepp && !*nodepp)
*nodepp = nps[depth+1];
{
int size;
void *mem;
+ int ret;
+
+ if (mynodes)
+ *mynodes = NULL;
pr_debug(" -> unflatten_device_tree()\n");
/* First pass, scan for size */
size = unflatten_dt_nodes(blob, NULL, dad, NULL);
- if (size < 0)
+ if (size <= 0)
return NULL;
size = ALIGN(size, 4);
pr_debug(" unflattening %p...\n", mem);
/* Second pass, do actual unflattening */
- unflatten_dt_nodes(blob, mem, dad, mynodes);
+ ret = unflatten_dt_nodes(blob, mem, dad, mynodes);
+
if (be32_to_cpup(mem + size) != 0xdeadbeef)
pr_warn("End of tree marker overwritten: %08x\n",
be32_to_cpup(mem + size));
- if (detached && mynodes) {
+ if (ret <= 0)
+ return NULL;
+
+ if (detached && mynodes && *mynodes) {
of_node_set_flag(*mynodes, OF_DETACHED);
pr_debug("unflattened tree is detached\n");
}
* Copyright (C) 1996-2005 Paul Mackerras.
*/
+#define FDT_ALIGN_SIZE 8
+
/**
* struct alias_prop - Alias property in 'aliases' node
* @link: List node to link the structure in aliases_lookup list
* struct overlay_changeset
* @id: changeset identifier
* @ovcs_list: list on which we are located
- * @fdt: FDT that was unflattened to create @overlay_tree
+ * @fdt: base of memory allocated to hold aligned FDT that was unflattened to create @overlay_tree
* @overlay_tree: expanded device tree that contains the fragment nodes
* @count: count of fragment structures
* @fragments: fragment nodes in the overlay expanded device tree
/**
* init_overlay_changeset() - initialize overlay changeset from overlay tree
* @ovcs: Overlay changeset to build
- * @fdt: the FDT that was unflattened to create @tree
- * @tree: Contains all the overlay fragments and overlay fixup nodes
+ * @fdt: base of memory allocated to hold aligned FDT that was unflattened to create @tree
+ * @tree: Contains the overlay fragments and overlay fixup nodes
*
* Initialize @ovcs. Populate @ovcs->fragments with node information from
* the top level of @tree. The relevant top level nodes are the fragment
* internal documentation
*
* of_overlay_apply() - Create and apply an overlay changeset
- * @fdt: the FDT that was unflattened to create @tree
+ * @fdt: base of memory allocated to hold the aligned FDT
* @tree: Expanded overlay device tree
* @ovcs_id: Pointer to overlay changeset id
*
/*
* after overlay_notify(), ovcs->overlay_tree related pointers may have
* leaked to drivers, so can not kfree() tree, aka ovcs->overlay_tree;
- * and can not free fdt, aka ovcs->fdt
+ * and can not free memory containing aligned fdt. The aligned fdt
+ * is contained within the memory at ovcs->fdt, possibly at an offset
+ * from ovcs->fdt.
*/
ret = overlay_notify(ovcs, OF_OVERLAY_PRE_APPLY);
if (ret) {
int of_overlay_fdt_apply(const void *overlay_fdt, u32 overlay_fdt_size,
int *ovcs_id)
{
- const void *new_fdt;
+ void *new_fdt;
+ void *new_fdt_align;
int ret;
u32 size;
- struct device_node *overlay_root;
+ struct device_node *overlay_root = NULL;
*ovcs_id = 0;
ret = 0;
* Must create permanent copy of FDT because of_fdt_unflatten_tree()
* will create pointers to the passed in FDT in the unflattened tree.
*/
- new_fdt = kmemdup(overlay_fdt, size, GFP_KERNEL);
+ new_fdt = kmalloc(size + FDT_ALIGN_SIZE, GFP_KERNEL);
if (!new_fdt)
return -ENOMEM;
- of_fdt_unflatten_tree(new_fdt, NULL, &overlay_root);
+ new_fdt_align = PTR_ALIGN(new_fdt, FDT_ALIGN_SIZE);
+ memcpy(new_fdt_align, overlay_fdt, size);
+
+ of_fdt_unflatten_tree(new_fdt_align, NULL, &overlay_root);
if (!overlay_root) {
pr_err("unable to unflatten overlay_fdt\n");
ret = -EINVAL;
DEFINE_SIMPLE_PROP(pinctrl8, "pinctrl-8", NULL)
DEFINE_SUFFIX_PROP(regulators, "-supply", NULL)
DEFINE_SUFFIX_PROP(gpio, "-gpio", "#gpio-cells")
-DEFINE_SUFFIX_PROP(gpios, "-gpios", "#gpio-cells")
+
+static struct device_node *parse_gpios(struct device_node *np,
+ const char *prop_name, int index)
+{
+ if (!strcmp_suffix(prop_name, ",nr-gpios"))
+ return NULL;
+
+ return parse_suffix_prop_cells(np, prop_name, index, "-gpios",
+ "#gpio-cells");
+}
static struct device_node *parse_iommu_maps(struct device_node *np,
const char *prop_name, int index)
#include <linux/slab.h>
#include <linux/device.h>
#include <linux/platform_device.h>
+#include <linux/kernel.h>
#include <linux/i2c.h>
#include <linux/i2c-mux.h>
static int __init unittest_data_add(void)
{
void *unittest_data;
- struct device_node *unittest_data_node, *np;
+ void *unittest_data_align;
+ struct device_node *unittest_data_node = NULL, *np;
/*
* __dtb_testcases_begin[] and __dtb_testcases_end[] are magically
* created by cmd_dt_S_dtb in scripts/Makefile.lib
extern uint8_t __dtb_testcases_end[];
const int size = __dtb_testcases_end - __dtb_testcases_begin;
int rc;
+ void *ret;
if (!size) {
- pr_warn("%s: No testcase data to attach; not running tests\n",
- __func__);
+ pr_warn("%s: testcases is empty\n", __func__);
return -ENODATA;
}
/* creating copy */
- unittest_data = kmemdup(__dtb_testcases_begin, size, GFP_KERNEL);
+ unittest_data = kmalloc(size + FDT_ALIGN_SIZE, GFP_KERNEL);
if (!unittest_data)
return -ENOMEM;
- of_fdt_unflatten_tree(unittest_data, NULL, &unittest_data_node);
+ unittest_data_align = PTR_ALIGN(unittest_data, FDT_ALIGN_SIZE);
+ memcpy(unittest_data_align, __dtb_testcases_begin, size);
+
+ ret = of_fdt_unflatten_tree(unittest_data_align, NULL, &unittest_data_node);
+ if (!ret) {
+ pr_warn("%s: unflatten testcases tree failed\n", __func__);
+ kfree(unittest_data);
+ return -ENODATA;
+ }
if (!unittest_data_node) {
- pr_warn("%s: No tree to attach; not running tests\n", __func__);
+ pr_warn("%s: testcases tree is empty\n", __func__);
kfree(unittest_data);
return -ENODATA;
}
mutex_lock(&opp_table->lock);
list_for_each_entry(temp, &opp_table->opp_list, node) {
- if (dynamic == temp->dynamic) {
+ /*
+ * Refcount must be dropped only once for each OPP by OPP core,
+ * do that with help of "removed" flag.
+ */
+ if (!temp->removed && dynamic == temp->dynamic) {
opp = temp;
break;
}
return opp;
}
-bool _opp_remove_all_static(struct opp_table *opp_table)
+/*
+ * Can't call dev_pm_opp_put() from under the lock as debugfs removal needs to
+ * happen lock less to avoid circular dependency issues. This routine must be
+ * called without the opp_table->lock held.
+ */
+static void _opp_remove_all(struct opp_table *opp_table, bool dynamic)
{
struct dev_pm_opp *opp;
+ while ((opp = _opp_get_next(opp_table, dynamic))) {
+ opp->removed = true;
+ dev_pm_opp_put(opp);
+
+ /* Drop the references taken by dev_pm_opp_add() */
+ if (dynamic)
+ dev_pm_opp_put_opp_table(opp_table);
+ }
+}
+
+bool _opp_remove_all_static(struct opp_table *opp_table)
+{
mutex_lock(&opp_table->lock);
if (!opp_table->parsed_static_opps) {
mutex_unlock(&opp_table->lock);
- /*
- * Can't remove the OPP from under the lock, debugfs removal needs to
- * happen lock less to avoid circular dependency issues.
- */
- while ((opp = _opp_get_next(opp_table, false)))
- dev_pm_opp_put(opp);
-
+ _opp_remove_all(opp_table, false);
return true;
}
void dev_pm_opp_remove_all_dynamic(struct device *dev)
{
struct opp_table *opp_table;
- struct dev_pm_opp *opp;
- int count = 0;
opp_table = _find_opp_table(dev);
if (IS_ERR(opp_table))
return;
- /*
- * Can't remove the OPP from under the lock, debugfs removal needs to
- * happen lock less to avoid circular dependency issues.
- */
- while ((opp = _opp_get_next(opp_table, true))) {
- dev_pm_opp_put(opp);
- count++;
- }
-
- /* Drop the references taken by dev_pm_opp_add() */
- while (count--)
- dev_pm_opp_put_opp_table(opp_table);
+ _opp_remove_all(opp_table, true);
/* Drop the reference taken by _find_opp_table() */
dev_pm_opp_put_opp_table(opp_table);
* @dynamic: not-created from static DT entries.
* @turbo: true if turbo (boost) OPP
* @suspend: true if suspend OPP
+ * @removed: flag indicating that OPP's reference is dropped by OPP core.
* @pstate: Device's power domain's performance state.
* @rate: Frequency in hertz
* @level: Performance level
bool dynamic;
bool turbo;
bool suspend;
+ bool removed;
unsigned int pstate;
unsigned long rate;
unsigned int level;
MODULE_AUTHOR("Joerg Dorchain <joerg@dorchain.net>");
MODULE_DESCRIPTION("Parport Driver for Amiga builtin Port");
-MODULE_SUPPORTED_DEVICE("Amiga builtin Parallel Port");
MODULE_LICENSE("GPL");
MODULE_ALIAS("platform:amiga-parallel");
MODULE_AUTHOR("Andreas Schwab");
MODULE_DESCRIPTION("Parport Driver for Atari builtin Port");
-MODULE_SUPPORTED_DEVICE("Atari builtin Parallel Port");
MODULE_LICENSE("GPL");
module_init(parport_atari_init)
MODULE_AUTHOR("Helge Deller <deller@gmx.de>");
MODULE_DESCRIPTION("HP-PARISC PC-style parallel port driver");
-MODULE_SUPPORTED_DEVICE("integrated PC-style parallel port");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Joerg Dorchain <joerg@dorchain.net>");
MODULE_DESCRIPTION("Parport Driver for Multiface 3 expansion cards Parallel Port");
-MODULE_SUPPORTED_DEVICE("Multiface 3 Parallel Port");
MODULE_LICENSE("GPL");
module_init(parport_mfc3_init)
MODULE_AUTHOR("Derrick J Brashear");
MODULE_DESCRIPTION("Parport Driver for Sparc bidirectional Port");
-MODULE_SUPPORTED_DEVICE("Sparc Bidirectional Parallel Port");
MODULE_VERSION("2.0");
MODULE_LICENSE("GPL");
* Prevents hv_pci_onchannelcallback() from running concurrently
* in the tasklet.
*/
- tasklet_disable(&channel->callback_event);
+ tasklet_disable_in_atomic(&channel->callback_event);
/*
* Since this function is called with IRQ locks held, can't
if (nbytes >= MAX_DRC_NAME_LEN)
return 0;
- memcpy(drc_name, buf, nbytes);
+ strscpy(drc_name, buf, nbytes + 1);
end = strchr(drc_name, '\n');
- if (!end)
- end = &drc_name[nbytes];
- *end = '\0';
+ if (end)
+ *end = '\0';
rc = dlpar_add_slot(drc_name);
if (rc)
if (nbytes >= MAX_DRC_NAME_LEN)
return 0;
- memcpy(drc_name, buf, nbytes);
+ strscpy(drc_name, buf, nbytes + 1);
end = strchr(drc_name, '\n');
- if (!end)
- end = &drc_name[nbytes];
- *end = '\0';
+ if (end)
+ *end = '\0';
rc = dlpar_remove_slot(drc_name);
if (rc)
pci_dev_put(pdev);
return -EBUSY;
}
+ pci_dev_put(pdev);
- zpci_remove_device(zdev);
+ zpci_remove_device(zdev, false);
rc = zpci_disable_device(zdev);
if (rc)
#include <xen/platform_pci.h>
#include <asm/xen/swiotlb-xen.h>
-#define INVALID_GRANT_REF (0)
+
#define INVALID_EVTCHN (-1)
struct pci_bus_entry {
struct list_head root_buses;
int evtchn;
- int gnt_ref;
+ grant_ref_t gnt_ref;
int irq;
{
struct dev_ext_attribute *eattr = container_of(attr,
struct dev_ext_attribute, attr);
- return snprintf(buf, PAGE_SIZE, "config=0x%lx\n", (unsigned long)eattr->var);
+ return sysfs_emit(buf, "config=0x%lx\n", (unsigned long)eattr->var);
}
static int cci400_get_event_idx(struct cci_pmu *cci_pmu,
struct dev_ext_attribute *eattr = container_of(attr,
struct dev_ext_attribute, attr);
/* Global events have single fixed source code */
- return snprintf(buf, PAGE_SIZE, "event=0x%lx,source=0x%x\n",
- (unsigned long)eattr->var, CCI5xx_PORT_GLOBAL);
+ return sysfs_emit(buf, "event=0x%lx,source=0x%x\n",
+ (unsigned long)eattr->var, CCI5xx_PORT_GLOBAL);
}
/*
{
struct dev_ext_attribute *eattr = container_of(attr,
struct dev_ext_attribute, attr);
- return snprintf(buf, PAGE_SIZE, "%s\n", (char *)eattr->var);
+ return sysfs_emit(buf, "%s\n", (char *)eattr->var);
}
static ssize_t cci_pmu_event_show(struct device *dev,
struct dev_ext_attribute *eattr = container_of(attr,
struct dev_ext_attribute, attr);
/* source parameter is mandatory for normal PMU events */
- return snprintf(buf, PAGE_SIZE, "source=?,event=0x%lx\n",
- (unsigned long)eattr->var);
+ return sysfs_emit(buf, "source=?,event=0x%lx\n",
+ (unsigned long)eattr->var);
}
static int pmu_is_valid_counter(struct cci_pmu *cci_pmu, int idx)
struct dev_ext_attribute *ea = container_of(attr,
struct dev_ext_attribute, attr);
- return snprintf(buf, PAGE_SIZE, "%s\n", (char *)ea->var);
+ return sysfs_emit(buf, "%s\n", (char *)ea->var);
}
#define CCN_FORMAT_ATTR(_name, _config) \
struct arm_ccn *ccn = pmu_to_arm_ccn(dev_get_drvdata(dev));
struct arm_ccn_pmu_event *event = container_of(attr,
struct arm_ccn_pmu_event, attr);
- ssize_t res;
+ int res;
- res = scnprintf(buf, PAGE_SIZE, "type=0x%x", event->type);
+ res = sysfs_emit(buf, "type=0x%x", event->type);
if (event->event)
- res += scnprintf(buf + res, PAGE_SIZE - res, ",event=0x%x",
- event->event);
+ res += sysfs_emit_at(buf, res, ",event=0x%x", event->event);
if (event->def)
- res += scnprintf(buf + res, PAGE_SIZE - res, ",%s",
- event->def);
+ res += sysfs_emit_at(buf, res, ",%s", event->def);
if (event->mask)
- res += scnprintf(buf + res, PAGE_SIZE - res, ",mask=0x%x",
- event->mask);
+ res += sysfs_emit_at(buf, res, ",mask=0x%x", event->mask);
/* Arguments required by an event */
switch (event->type) {
case CCN_TYPE_CYCLES:
break;
case CCN_TYPE_XP:
- res += scnprintf(buf + res, PAGE_SIZE - res,
- ",xp=?,vc=?");
+ res += sysfs_emit_at(buf, res, ",xp=?,vc=?");
if (event->event == CCN_EVENT_WATCHPOINT)
- res += scnprintf(buf + res, PAGE_SIZE - res,
+ res += sysfs_emit_at(buf, res,
",port=?,dir=?,cmp_l=?,cmp_h=?,mask=?");
else
- res += scnprintf(buf + res, PAGE_SIZE - res,
- ",bus=?");
+ res += sysfs_emit_at(buf, res, ",bus=?");
break;
case CCN_TYPE_MN:
- res += scnprintf(buf + res, PAGE_SIZE - res, ",node=%d", ccn->mn_id);
+ res += sysfs_emit_at(buf, res, ",node=%d", ccn->mn_id);
break;
default:
- res += scnprintf(buf + res, PAGE_SIZE - res, ",node=?");
+ res += sysfs_emit_at(buf, res, ",node=?");
break;
}
- res += scnprintf(buf + res, PAGE_SIZE - res, "\n");
+ res += sysfs_emit_at(buf, res, "\n");
return res;
}
struct arm_ccn *ccn = pmu_to_arm_ccn(dev_get_drvdata(dev));
u64 *mask = arm_ccn_pmu_get_cmp_mask(ccn, attr->attr.name);
- return mask ? snprintf(buf, PAGE_SIZE, "0x%016llx\n", *mask) : -EINVAL;
+ return mask ? sysfs_emit(buf, "0x%016llx\n", *mask) : -EINVAL;
}
static ssize_t arm_ccn_pmu_cmp_mask_store(struct device *dev,
eattr = container_of(attr, typeof(*eattr), attr);
if (eattr->type == CMN_TYPE_DTC)
- return snprintf(buf, PAGE_SIZE, "type=0x%x\n", eattr->type);
+ return sysfs_emit(buf, "type=0x%x\n", eattr->type);
if (eattr->type == CMN_TYPE_WP)
- return snprintf(buf, PAGE_SIZE,
- "type=0x%x,eventid=0x%x,wp_dev_sel=?,wp_chn_sel=?,wp_grp=?,wp_val=?,wp_mask=?\n",
- eattr->type, eattr->eventid);
+ return sysfs_emit(buf,
+ "type=0x%x,eventid=0x%x,wp_dev_sel=?,wp_chn_sel=?,wp_grp=?,wp_val=?,wp_mask=?\n",
+ eattr->type, eattr->eventid);
if (arm_cmn_is_occup_event(eattr->type, eattr->eventid))
- return snprintf(buf, PAGE_SIZE, "type=0x%x,eventid=0x%x,occupid=0x%x\n",
- eattr->type, eattr->eventid, eattr->occupid);
+ return sysfs_emit(buf, "type=0x%x,eventid=0x%x,occupid=0x%x\n",
+ eattr->type, eattr->eventid, eattr->occupid);
- return snprintf(buf, PAGE_SIZE, "type=0x%x,eventid=0x%x\n",
- eattr->type, eattr->eventid);
+ return sysfs_emit(buf, "type=0x%x,eventid=0x%x\n", eattr->type,
+ eattr->eventid);
}
static umode_t arm_cmn_event_attr_is_visible(struct kobject *kobj,
int lo = __ffs(fmt->field), hi = __fls(fmt->field);
if (lo == hi)
- return snprintf(buf, PAGE_SIZE, "config:%d\n", lo);
+ return sysfs_emit(buf, "config:%d\n", lo);
if (!fmt->config)
- return snprintf(buf, PAGE_SIZE, "config:%d-%d\n", lo, hi);
+ return sysfs_emit(buf, "config:%d-%d\n", lo, hi);
- return snprintf(buf, PAGE_SIZE, "config%d:%d-%d\n", fmt->config, lo, hi);
+ return sysfs_emit(buf, "config%d:%d-%d\n", fmt->config, lo, hi);
}
#define _CMN_FORMAT_ATTR(_name, _cfg, _fld) \
eattr = container_of(attr, typeof(*eattr), attr);
- return sprintf(page, "event=0x%x,clkdiv2=0x%x\n", eattr->eventid, eattr->clkdiv2);
+ return sysfs_emit(page, "event=0x%x,clkdiv2=0x%x\n", eattr->eventid, eattr->clkdiv2);
}
#define DMC620_PMU_EVENT_ATTR(_name, _eventid, _clkdiv2) \
if (!name) {
dev_err(&pdev->dev,
"Create name failed, PMU @%pa\n", &res->start);
+ ret = -ENOMEM;
goto out_teardown_dev;
}
{
struct dev_ext_attribute *eattr = container_of(attr,
struct dev_ext_attribute, attr);
- return snprintf(buf, PAGE_SIZE, "event=0x%lx\n",
- (unsigned long)eattr->var);
+ return sysfs_emit(buf, "event=0x%lx\n", (unsigned long)eattr->var);
}
static ssize_t dsu_pmu_sysfs_format_show(struct device *dev,
{
struct dev_ext_attribute *eattr = container_of(attr,
struct dev_ext_attribute, attr);
- return snprintf(buf, PAGE_SIZE, "%s\n", (char *)eattr->var);
+ return sysfs_emit(buf, "%s\n", (char *)eattr->var);
}
static ssize_t dsu_pmu_cpumask_show(struct device *dev,
* Copyright (C) 2010 ARM Ltd., Will Deacon <will.deacon@arm.com>
*/
#define pr_fmt(fmt) "hw perfevents: " fmt
+#define dev_fmt pr_fmt
#include <linux/bug.h>
#include <linux/cpumask.h>
return !!of_find_property(node, "interrupt-affinity", NULL);
}
-static int pmu_parse_irq_affinity(struct device_node *node, int i)
+static int pmu_parse_irq_affinity(struct device *dev, int i)
{
struct device_node *dn;
int cpu;
* affinity matches our logical CPU order, as we used to assume.
* This is fragile, so we'll warn in pmu_parse_irqs().
*/
- if (!pmu_has_irq_affinity(node))
+ if (!pmu_has_irq_affinity(dev->of_node))
return i;
- dn = of_parse_phandle(node, "interrupt-affinity", i);
+ dn = of_parse_phandle(dev->of_node, "interrupt-affinity", i);
if (!dn) {
- pr_warn("failed to parse interrupt-affinity[%d] for %pOFn\n",
- i, node);
+ dev_warn(dev, "failed to parse interrupt-affinity[%d]\n", i);
return -EINVAL;
}
cpu = of_cpu_node_to_id(dn);
if (cpu < 0) {
- pr_warn("failed to find logical CPU for %pOFn\n", dn);
+ dev_warn(dev, "failed to find logical CPU for %pOFn\n", dn);
cpu = nr_cpu_ids;
}
int i = 0, num_irqs;
struct platform_device *pdev = pmu->plat_device;
struct pmu_hw_events __percpu *hw_events = pmu->hw_events;
+ struct device *dev = &pdev->dev;
num_irqs = platform_irq_count(pdev);
- if (num_irqs < 0) {
- pr_err("unable to count PMU IRQs\n");
- return num_irqs;
- }
+ if (num_irqs < 0)
+ return dev_err_probe(dev, num_irqs, "unable to count PMU IRQs\n");
/*
* In this case we have no idea which CPUs are covered by the PMU.
* To match our prior behaviour, we assume all CPUs in this case.
*/
if (num_irqs == 0) {
- pr_warn("no irqs for PMU, sampling events not supported\n");
+ dev_warn(dev, "no irqs for PMU, sampling events not supported\n");
pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
cpumask_setall(&pmu->supported_cpus);
return 0;
return pmu_parse_percpu_irq(pmu, irq);
}
- if (nr_cpu_ids != 1 && !pmu_has_irq_affinity(pdev->dev.of_node)) {
- pr_warn("no interrupt-affinity property for %pOF, guessing.\n",
- pdev->dev.of_node);
- }
+ if (nr_cpu_ids != 1 && !pmu_has_irq_affinity(dev->of_node))
+ dev_warn(dev, "no interrupt-affinity property, guessing.\n");
for (i = 0; i < num_irqs; i++) {
int cpu, irq;
continue;
if (irq_is_percpu_devid(irq)) {
- pr_warn("multiple PPIs or mismatched SPI/PPI detected\n");
+ dev_warn(dev, "multiple PPIs or mismatched SPI/PPI detected\n");
return -EINVAL;
}
- cpu = pmu_parse_irq_affinity(pdev->dev.of_node, i);
+ cpu = pmu_parse_irq_affinity(dev, i);
if (cpu < 0)
return cpu;
if (cpu >= nr_cpu_ids)
continue;
if (per_cpu(hw_events->irq, cpu)) {
- pr_warn("multiple PMU IRQs for the same CPU detected\n");
+ dev_warn(dev, "multiple PMU IRQs for the same CPU detected\n");
return -EINVAL;
}
const struct of_device_id *of_table,
const struct pmu_probe_info *probe_table)
{
- const struct of_device_id *of_id;
armpmu_init_fn init_fn;
- struct device_node *node = pdev->dev.of_node;
+ struct device *dev = &pdev->dev;
struct arm_pmu *pmu;
int ret = -ENODEV;
if (ret)
goto out_free;
- if (node && (of_id = of_match_node(of_table, pdev->dev.of_node))) {
- init_fn = of_id->data;
-
- pmu->secure_access = of_property_read_bool(pdev->dev.of_node,
+ init_fn = of_device_get_match_data(dev);
+ if (init_fn) {
+ pmu->secure_access = of_property_read_bool(dev->of_node,
"secure-reg-access");
/* arm64 systems boot only as non-secure */
if (IS_ENABLED(CONFIG_ARM64) && pmu->secure_access) {
- pr_warn("ignoring \"secure-reg-access\" property for arm64\n");
+ dev_warn(dev, "ignoring \"secure-reg-access\" property for arm64\n");
pmu->secure_access = false;
}
}
if (ret) {
- pr_info("%pOF: failed to probe PMU!\n", node);
+ dev_err(dev, "failed to probe PMU!\n");
goto out_free;
}
goto out_free_irqs;
ret = armpmu_register(pmu);
- if (ret)
- goto out_free;
+ if (ret) {
+ dev_err(dev, "failed to register PMU devices!\n");
+ goto out_free_irqs;
+ }
return 0;
out_free_irqs:
armpmu_free_irqs(pmu);
out_free:
- pr_info("%pOF: failed to register PMU devices!\n", node);
armpmu_free(pmu);
return ret;
}
pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
- return sprintf(page, "event=0x%02llx\n", pmu_attr->id);
+ return sysfs_emit(page, "event=0x%02llx\n", pmu_attr->id);
}
-#define SMMU_EVENT_ATTR(name, config) \
- PMU_EVENT_ATTR(name, smmu_event_attr_##name, \
- config, smmu_pmu_event_show)
-SMMU_EVENT_ATTR(cycles, 0);
-SMMU_EVENT_ATTR(transaction, 1);
-SMMU_EVENT_ATTR(tlb_miss, 2);
-SMMU_EVENT_ATTR(config_cache_miss, 3);
-SMMU_EVENT_ATTR(trans_table_walk_access, 4);
-SMMU_EVENT_ATTR(config_struct_access, 5);
-SMMU_EVENT_ATTR(pcie_ats_trans_rq, 6);
-SMMU_EVENT_ATTR(pcie_ats_trans_passed, 7);
+#define SMMU_EVENT_ATTR(name, config) \
+ (&((struct perf_pmu_events_attr) { \
+ .attr = __ATTR(name, 0444, smmu_pmu_event_show, NULL), \
+ .id = config, \
+ }).attr.attr)
static struct attribute *smmu_pmu_events[] = {
- &smmu_event_attr_cycles.attr.attr,
- &smmu_event_attr_transaction.attr.attr,
- &smmu_event_attr_tlb_miss.attr.attr,
- &smmu_event_attr_config_cache_miss.attr.attr,
- &smmu_event_attr_trans_table_walk_access.attr.attr,
- &smmu_event_attr_config_struct_access.attr.attr,
- &smmu_event_attr_pcie_ats_trans_rq.attr.attr,
- &smmu_event_attr_pcie_ats_trans_passed.attr.attr,
+ SMMU_EVENT_ATTR(cycles, 0),
+ SMMU_EVENT_ATTR(transaction, 1),
+ SMMU_EVENT_ATTR(tlb_miss, 2),
+ SMMU_EVENT_ATTR(config_cache_miss, 3),
+ SMMU_EVENT_ATTR(trans_table_walk_access, 4),
+ SMMU_EVENT_ATTR(config_struct_access, 5),
+ SMMU_EVENT_ATTR(pcie_ats_trans_rq, 6),
+ SMMU_EVENT_ATTR(pcie_ats_trans_passed, 7),
NULL
};
{
struct smmu_pmu *smmu_pmu = to_smmu_pmu(dev_get_drvdata(dev));
- return snprintf(page, PAGE_SIZE, "0x%08x\n", smmu_pmu->iidr);
+ return sysfs_emit(page, "0x%08x\n", smmu_pmu->iidr);
}
static umode_t smmu_pmu_identifier_attr_visible(struct kobject *kobj,
container_of(attr, struct dev_ext_attribute, attr);
int cap = (long)ea->var;
- return snprintf(buf, PAGE_SIZE, "%u\n",
- arm_spe_pmu_cap_get(spe_pmu, cap));
+ return sysfs_emit(buf, "%u\n", arm_spe_pmu_cap_get(spe_pmu, cap));
}
#define SPE_EXT_ATTR_ENTRY(_name, _func, _var) \
{
struct ddr_pmu *pmu = dev_get_drvdata(dev);
- return sprintf(page, "%s\n", pmu->devtype_data->identifier);
+ return sysfs_emit(page, "%s\n", pmu->devtype_data->identifier);
}
static umode_t ddr_perf_identifier_attr_visible(struct kobject *kobj,
container_of(attr, struct dev_ext_attribute, attr);
int cap = (long)ea->var;
- return snprintf(buf, PAGE_SIZE, "%u\n",
- ddr_perf_filter_cap_get(pmu, cap));
+ return sysfs_emit(buf, "%u\n", ddr_perf_filter_cap_get(pmu, cap));
}
#define PERF_EXT_ATTR_ENTRY(_name, _func, _var) \
struct perf_pmu_events_attr *pmu_attr;
pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
- return sprintf(page, "event=0x%02llx\n", pmu_attr->id);
+ return sysfs_emit(page, "event=0x%02llx\n", pmu_attr->id);
}
#define IMX8_DDR_PMU_EVENT_ATTR(_name, _id) \
# SPDX-License-Identifier: GPL-2.0-only
obj-$(CONFIG_HISI_PMU) += hisi_uncore_pmu.o hisi_uncore_l3c_pmu.o \
- hisi_uncore_hha_pmu.o hisi_uncore_ddrc_pmu.o
+ hisi_uncore_hha_pmu.o hisi_uncore_ddrc_pmu.o hisi_uncore_sllc_pmu.o \
+ hisi_uncore_pa_pmu.o
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/list.h>
-#include <linux/platform_device.h>
#include <linux/smp.h>
#include "hisi_uncore_pmu.h"
-/* DDRC register definition */
+/* DDRC register definition in v1 */
#define DDRC_PERF_CTRL 0x010
#define DDRC_FLUX_WR 0x380
#define DDRC_FLUX_RD 0x384
#define DDRC_INT_CLEAR 0x6d0
#define DDRC_VERSION 0x710
+/* DDRC register definition in v2 */
+#define DDRC_V2_INT_MASK 0x528
+#define DDRC_V2_INT_STATUS 0x52c
+#define DDRC_V2_INT_CLEAR 0x530
+#define DDRC_V2_EVENT_CNT 0xe00
+#define DDRC_V2_EVENT_CTRL 0xe70
+#define DDRC_V2_EVENT_TYPE 0xe74
+#define DDRC_V2_PERF_CTRL 0xeA0
+
/* DDRC has 8-counters */
#define DDRC_NR_COUNTERS 0x8
-#define DDRC_PERF_CTRL_EN 0x2
+#define DDRC_V1_PERF_CTRL_EN 0x2
+#define DDRC_V2_PERF_CTRL_EN 0x1
+#define DDRC_V1_NR_EVENTS 0x7
+#define DDRC_V2_NR_EVENTS 0x90
/*
- * For DDRC PMU, there are eight-events and every event has been mapped
+ * For PMU v1, there are eight-events and every event has been mapped
* to fixed-purpose counters which register offset is not consistent.
* Therefore there is no write event type and we assume that event
* code (0 to 7) is equal to counter index in PMU driver.
/*
* Select the counter register offset using the counter index.
- * In DDRC there are no programmable counter, the count
- * is readed form the statistics counter register itself.
+ * In PMU v1, there are no programmable counter, the count
+ * is read form the statistics counter register itself.
*/
-static u32 hisi_ddrc_pmu_get_counter_offset(int cntr_idx)
+static u32 hisi_ddrc_pmu_v1_get_counter_offset(int cntr_idx)
{
return ddrc_reg_off[cntr_idx];
}
-static u64 hisi_ddrc_pmu_read_counter(struct hisi_pmu *ddrc_pmu,
- struct hw_perf_event *hwc)
+static u32 hisi_ddrc_pmu_v2_get_counter_offset(int cntr_idx)
{
- /* Use event code as counter index */
- u32 idx = GET_DDRC_EVENTID(hwc);
-
- if (!hisi_uncore_pmu_counter_valid(ddrc_pmu, idx)) {
- dev_err(ddrc_pmu->dev, "Unsupported event index:%d!\n", idx);
- return 0;
- }
+ return DDRC_V2_EVENT_CNT + cntr_idx * 8;
+}
- return readl(ddrc_pmu->base + hisi_ddrc_pmu_get_counter_offset(idx));
+static u64 hisi_ddrc_pmu_v1_read_counter(struct hisi_pmu *ddrc_pmu,
+ struct hw_perf_event *hwc)
+{
+ return readl(ddrc_pmu->base +
+ hisi_ddrc_pmu_v1_get_counter_offset(hwc->idx));
}
-static void hisi_ddrc_pmu_write_counter(struct hisi_pmu *ddrc_pmu,
+static void hisi_ddrc_pmu_v1_write_counter(struct hisi_pmu *ddrc_pmu,
struct hw_perf_event *hwc, u64 val)
{
- u32 idx = GET_DDRC_EVENTID(hwc);
+ writel((u32)val,
+ ddrc_pmu->base + hisi_ddrc_pmu_v1_get_counter_offset(hwc->idx));
+}
- if (!hisi_uncore_pmu_counter_valid(ddrc_pmu, idx)) {
- dev_err(ddrc_pmu->dev, "Unsupported event index:%d!\n", idx);
- return;
- }
+static u64 hisi_ddrc_pmu_v2_read_counter(struct hisi_pmu *ddrc_pmu,
+ struct hw_perf_event *hwc)
+{
+ return readq(ddrc_pmu->base +
+ hisi_ddrc_pmu_v2_get_counter_offset(hwc->idx));
+}
- writel((u32)val,
- ddrc_pmu->base + hisi_ddrc_pmu_get_counter_offset(idx));
+static void hisi_ddrc_pmu_v2_write_counter(struct hisi_pmu *ddrc_pmu,
+ struct hw_perf_event *hwc, u64 val)
+{
+ writeq(val,
+ ddrc_pmu->base + hisi_ddrc_pmu_v2_get_counter_offset(hwc->idx));
}
/*
- * For DDRC PMU, event has been mapped to fixed-purpose counter by hardware,
- * so there is no need to write event type.
+ * For DDRC PMU v1, event has been mapped to fixed-purpose counter by hardware,
+ * so there is no need to write event type, while it is programmable counter in
+ * PMU v2.
*/
static void hisi_ddrc_pmu_write_evtype(struct hisi_pmu *hha_pmu, int idx,
u32 type)
{
+ u32 offset;
+
+ if (hha_pmu->identifier >= HISI_PMU_V2) {
+ offset = DDRC_V2_EVENT_TYPE + 4 * idx;
+ writel(type, hha_pmu->base + offset);
+ }
}
-static void hisi_ddrc_pmu_start_counters(struct hisi_pmu *ddrc_pmu)
+static void hisi_ddrc_pmu_v1_start_counters(struct hisi_pmu *ddrc_pmu)
{
u32 val;
/* Set perf_enable in DDRC_PERF_CTRL to start event counting */
val = readl(ddrc_pmu->base + DDRC_PERF_CTRL);
- val |= DDRC_PERF_CTRL_EN;
+ val |= DDRC_V1_PERF_CTRL_EN;
writel(val, ddrc_pmu->base + DDRC_PERF_CTRL);
}
-static void hisi_ddrc_pmu_stop_counters(struct hisi_pmu *ddrc_pmu)
+static void hisi_ddrc_pmu_v1_stop_counters(struct hisi_pmu *ddrc_pmu)
{
u32 val;
/* Clear perf_enable in DDRC_PERF_CTRL to stop event counting */
val = readl(ddrc_pmu->base + DDRC_PERF_CTRL);
- val &= ~DDRC_PERF_CTRL_EN;
+ val &= ~DDRC_V1_PERF_CTRL_EN;
writel(val, ddrc_pmu->base + DDRC_PERF_CTRL);
}
-static void hisi_ddrc_pmu_enable_counter(struct hisi_pmu *ddrc_pmu,
- struct hw_perf_event *hwc)
+static void hisi_ddrc_pmu_v1_enable_counter(struct hisi_pmu *ddrc_pmu,
+ struct hw_perf_event *hwc)
{
u32 val;
writel(val, ddrc_pmu->base + DDRC_EVENT_CTRL);
}
-static void hisi_ddrc_pmu_disable_counter(struct hisi_pmu *ddrc_pmu,
- struct hw_perf_event *hwc)
+static void hisi_ddrc_pmu_v1_disable_counter(struct hisi_pmu *ddrc_pmu,
+ struct hw_perf_event *hwc)
{
u32 val;
writel(val, ddrc_pmu->base + DDRC_EVENT_CTRL);
}
-static int hisi_ddrc_pmu_get_event_idx(struct perf_event *event)
+static int hisi_ddrc_pmu_v1_get_event_idx(struct perf_event *event)
{
struct hisi_pmu *ddrc_pmu = to_hisi_pmu(event->pmu);
unsigned long *used_mask = ddrc_pmu->pmu_events.used_mask;
return idx;
}
-static void hisi_ddrc_pmu_enable_counter_int(struct hisi_pmu *ddrc_pmu,
+static int hisi_ddrc_pmu_v2_get_event_idx(struct perf_event *event)
+{
+ return hisi_uncore_pmu_get_event_idx(event);
+}
+
+static void hisi_ddrc_pmu_v2_start_counters(struct hisi_pmu *ddrc_pmu)
+{
+ u32 val;
+
+ val = readl(ddrc_pmu->base + DDRC_V2_PERF_CTRL);
+ val |= DDRC_V2_PERF_CTRL_EN;
+ writel(val, ddrc_pmu->base + DDRC_V2_PERF_CTRL);
+}
+
+static void hisi_ddrc_pmu_v2_stop_counters(struct hisi_pmu *ddrc_pmu)
+{
+ u32 val;
+
+ val = readl(ddrc_pmu->base + DDRC_V2_PERF_CTRL);
+ val &= ~DDRC_V2_PERF_CTRL_EN;
+ writel(val, ddrc_pmu->base + DDRC_V2_PERF_CTRL);
+}
+
+static void hisi_ddrc_pmu_v2_enable_counter(struct hisi_pmu *ddrc_pmu,
+ struct hw_perf_event *hwc)
+{
+ u32 val;
+
+ val = readl(ddrc_pmu->base + DDRC_V2_EVENT_CTRL);
+ val |= 1 << hwc->idx;
+ writel(val, ddrc_pmu->base + DDRC_V2_EVENT_CTRL);
+}
+
+static void hisi_ddrc_pmu_v2_disable_counter(struct hisi_pmu *ddrc_pmu,
struct hw_perf_event *hwc)
{
u32 val;
+ val = readl(ddrc_pmu->base + DDRC_V2_EVENT_CTRL);
+ val &= ~(1 << hwc->idx);
+ writel(val, ddrc_pmu->base + DDRC_V2_EVENT_CTRL);
+}
+
+static void hisi_ddrc_pmu_v1_enable_counter_int(struct hisi_pmu *ddrc_pmu,
+ struct hw_perf_event *hwc)
+{
+ u32 val;
+
/* Write 0 to enable interrupt */
val = readl(ddrc_pmu->base + DDRC_INT_MASK);
- val &= ~(1 << GET_DDRC_EVENTID(hwc));
+ val &= ~(1 << hwc->idx);
writel(val, ddrc_pmu->base + DDRC_INT_MASK);
}
-static void hisi_ddrc_pmu_disable_counter_int(struct hisi_pmu *ddrc_pmu,
- struct hw_perf_event *hwc)
+static void hisi_ddrc_pmu_v1_disable_counter_int(struct hisi_pmu *ddrc_pmu,
+ struct hw_perf_event *hwc)
{
u32 val;
/* Write 1 to mask interrupt */
val = readl(ddrc_pmu->base + DDRC_INT_MASK);
- val |= (1 << GET_DDRC_EVENTID(hwc));
+ val |= 1 << hwc->idx;
writel(val, ddrc_pmu->base + DDRC_INT_MASK);
}
-static irqreturn_t hisi_ddrc_pmu_isr(int irq, void *dev_id)
+static void hisi_ddrc_pmu_v2_enable_counter_int(struct hisi_pmu *ddrc_pmu,
+ struct hw_perf_event *hwc)
{
- struct hisi_pmu *ddrc_pmu = dev_id;
- struct perf_event *event;
- unsigned long overflown;
- int idx;
-
- /* Read the DDRC_INT_STATUS register */
- overflown = readl(ddrc_pmu->base + DDRC_INT_STATUS);
- if (!overflown)
- return IRQ_NONE;
+ u32 val;
- /*
- * Find the counter index which overflowed if the bit was set
- * and handle it
- */
- for_each_set_bit(idx, &overflown, DDRC_NR_COUNTERS) {
- /* Write 1 to clear the IRQ status flag */
- writel((1 << idx), ddrc_pmu->base + DDRC_INT_CLEAR);
+ val = readl(ddrc_pmu->base + DDRC_V2_INT_MASK);
+ val &= ~(1 << hwc->idx);
+ writel(val, ddrc_pmu->base + DDRC_V2_INT_MASK);
+}
- /* Get the corresponding event struct */
- event = ddrc_pmu->pmu_events.hw_events[idx];
- if (!event)
- continue;
+static void hisi_ddrc_pmu_v2_disable_counter_int(struct hisi_pmu *ddrc_pmu,
+ struct hw_perf_event *hwc)
+{
+ u32 val;
- hisi_uncore_pmu_event_update(event);
- hisi_uncore_pmu_set_event_period(event);
- }
+ val = readl(ddrc_pmu->base + DDRC_V2_INT_MASK);
+ val |= 1 << hwc->idx;
+ writel(val, ddrc_pmu->base + DDRC_V2_INT_MASK);
+}
- return IRQ_HANDLED;
+static u32 hisi_ddrc_pmu_v1_get_int_status(struct hisi_pmu *ddrc_pmu)
+{
+ return readl(ddrc_pmu->base + DDRC_INT_STATUS);
}
-static int hisi_ddrc_pmu_init_irq(struct hisi_pmu *ddrc_pmu,
- struct platform_device *pdev)
+static void hisi_ddrc_pmu_v1_clear_int_status(struct hisi_pmu *ddrc_pmu,
+ int idx)
{
- int irq, ret;
-
- /* Read and init IRQ */
- irq = platform_get_irq(pdev, 0);
- if (irq < 0)
- return irq;
-
- ret = devm_request_irq(&pdev->dev, irq, hisi_ddrc_pmu_isr,
- IRQF_NOBALANCING | IRQF_NO_THREAD,
- dev_name(&pdev->dev), ddrc_pmu);
- if (ret < 0) {
- dev_err(&pdev->dev,
- "Fail to request IRQ:%d ret:%d\n", irq, ret);
- return ret;
- }
+ writel(1 << idx, ddrc_pmu->base + DDRC_INT_CLEAR);
+}
- ddrc_pmu->irq = irq;
+static u32 hisi_ddrc_pmu_v2_get_int_status(struct hisi_pmu *ddrc_pmu)
+{
+ return readl(ddrc_pmu->base + DDRC_V2_INT_STATUS);
+}
- return 0;
+static void hisi_ddrc_pmu_v2_clear_int_status(struct hisi_pmu *ddrc_pmu,
+ int idx)
+{
+ writel(1 << idx, ddrc_pmu->base + DDRC_V2_INT_CLEAR);
}
static const struct acpi_device_id hisi_ddrc_pmu_acpi_match[] = {
{ "HISI0233", },
- {},
+ { "HISI0234", },
+ {}
};
MODULE_DEVICE_TABLE(acpi, hisi_ddrc_pmu_acpi_match);
}
ddrc_pmu->identifier = readl(ddrc_pmu->base + DDRC_VERSION);
+ if (ddrc_pmu->identifier >= HISI_PMU_V2) {
+ if (device_property_read_u32(&pdev->dev, "hisilicon,sub-id",
+ &ddrc_pmu->sub_id)) {
+ dev_err(&pdev->dev, "Can not read sub-id!\n");
+ return -EINVAL;
+ }
+ }
return 0;
}
-static struct attribute *hisi_ddrc_pmu_format_attr[] = {
+static struct attribute *hisi_ddrc_pmu_v1_format_attr[] = {
HISI_PMU_FORMAT_ATTR(event, "config:0-4"),
NULL,
};
-static const struct attribute_group hisi_ddrc_pmu_format_group = {
+static const struct attribute_group hisi_ddrc_pmu_v1_format_group = {
+ .name = "format",
+ .attrs = hisi_ddrc_pmu_v1_format_attr,
+};
+
+static struct attribute *hisi_ddrc_pmu_v2_format_attr[] = {
+ HISI_PMU_FORMAT_ATTR(event, "config:0-7"),
+ NULL
+};
+
+static const struct attribute_group hisi_ddrc_pmu_v2_format_group = {
.name = "format",
- .attrs = hisi_ddrc_pmu_format_attr,
+ .attrs = hisi_ddrc_pmu_v2_format_attr,
};
-static struct attribute *hisi_ddrc_pmu_events_attr[] = {
+static struct attribute *hisi_ddrc_pmu_v1_events_attr[] = {
HISI_PMU_EVENT_ATTR(flux_wr, 0x00),
HISI_PMU_EVENT_ATTR(flux_rd, 0x01),
HISI_PMU_EVENT_ATTR(flux_wcmd, 0x02),
NULL,
};
-static const struct attribute_group hisi_ddrc_pmu_events_group = {
+static const struct attribute_group hisi_ddrc_pmu_v1_events_group = {
.name = "events",
- .attrs = hisi_ddrc_pmu_events_attr,
+ .attrs = hisi_ddrc_pmu_v1_events_attr,
+};
+
+static struct attribute *hisi_ddrc_pmu_v2_events_attr[] = {
+ HISI_PMU_EVENT_ATTR(cycles, 0x00),
+ HISI_PMU_EVENT_ATTR(flux_wr, 0x83),
+ HISI_PMU_EVENT_ATTR(flux_rd, 0x84),
+ NULL
+};
+
+static const struct attribute_group hisi_ddrc_pmu_v2_events_group = {
+ .name = "events",
+ .attrs = hisi_ddrc_pmu_v2_events_attr,
};
static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL);
.attrs = hisi_ddrc_pmu_identifier_attrs,
};
-static const struct attribute_group *hisi_ddrc_pmu_attr_groups[] = {
- &hisi_ddrc_pmu_format_group,
- &hisi_ddrc_pmu_events_group,
+static const struct attribute_group *hisi_ddrc_pmu_v1_attr_groups[] = {
+ &hisi_ddrc_pmu_v1_format_group,
+ &hisi_ddrc_pmu_v1_events_group,
&hisi_ddrc_pmu_cpumask_attr_group,
&hisi_ddrc_pmu_identifier_group,
NULL,
};
-static const struct hisi_uncore_ops hisi_uncore_ddrc_ops = {
+static const struct attribute_group *hisi_ddrc_pmu_v2_attr_groups[] = {
+ &hisi_ddrc_pmu_v2_format_group,
+ &hisi_ddrc_pmu_v2_events_group,
+ &hisi_ddrc_pmu_cpumask_attr_group,
+ &hisi_ddrc_pmu_identifier_group,
+ NULL
+};
+
+static const struct hisi_uncore_ops hisi_uncore_ddrc_v1_ops = {
+ .write_evtype = hisi_ddrc_pmu_write_evtype,
+ .get_event_idx = hisi_ddrc_pmu_v1_get_event_idx,
+ .start_counters = hisi_ddrc_pmu_v1_start_counters,
+ .stop_counters = hisi_ddrc_pmu_v1_stop_counters,
+ .enable_counter = hisi_ddrc_pmu_v1_enable_counter,
+ .disable_counter = hisi_ddrc_pmu_v1_disable_counter,
+ .enable_counter_int = hisi_ddrc_pmu_v1_enable_counter_int,
+ .disable_counter_int = hisi_ddrc_pmu_v1_disable_counter_int,
+ .write_counter = hisi_ddrc_pmu_v1_write_counter,
+ .read_counter = hisi_ddrc_pmu_v1_read_counter,
+ .get_int_status = hisi_ddrc_pmu_v1_get_int_status,
+ .clear_int_status = hisi_ddrc_pmu_v1_clear_int_status,
+};
+
+static const struct hisi_uncore_ops hisi_uncore_ddrc_v2_ops = {
.write_evtype = hisi_ddrc_pmu_write_evtype,
- .get_event_idx = hisi_ddrc_pmu_get_event_idx,
- .start_counters = hisi_ddrc_pmu_start_counters,
- .stop_counters = hisi_ddrc_pmu_stop_counters,
- .enable_counter = hisi_ddrc_pmu_enable_counter,
- .disable_counter = hisi_ddrc_pmu_disable_counter,
- .enable_counter_int = hisi_ddrc_pmu_enable_counter_int,
- .disable_counter_int = hisi_ddrc_pmu_disable_counter_int,
- .write_counter = hisi_ddrc_pmu_write_counter,
- .read_counter = hisi_ddrc_pmu_read_counter,
+ .get_event_idx = hisi_ddrc_pmu_v2_get_event_idx,
+ .start_counters = hisi_ddrc_pmu_v2_start_counters,
+ .stop_counters = hisi_ddrc_pmu_v2_stop_counters,
+ .enable_counter = hisi_ddrc_pmu_v2_enable_counter,
+ .disable_counter = hisi_ddrc_pmu_v2_disable_counter,
+ .enable_counter_int = hisi_ddrc_pmu_v2_enable_counter_int,
+ .disable_counter_int = hisi_ddrc_pmu_v2_disable_counter_int,
+ .write_counter = hisi_ddrc_pmu_v2_write_counter,
+ .read_counter = hisi_ddrc_pmu_v2_read_counter,
+ .get_int_status = hisi_ddrc_pmu_v2_get_int_status,
+ .clear_int_status = hisi_ddrc_pmu_v2_clear_int_status,
};
static int hisi_ddrc_pmu_dev_probe(struct platform_device *pdev,
if (ret)
return ret;
- ret = hisi_ddrc_pmu_init_irq(ddrc_pmu, pdev);
+ ret = hisi_uncore_pmu_init_irq(ddrc_pmu, pdev);
if (ret)
return ret;
+ if (ddrc_pmu->identifier >= HISI_PMU_V2) {
+ ddrc_pmu->counter_bits = 48;
+ ddrc_pmu->check_event = DDRC_V2_NR_EVENTS;
+ ddrc_pmu->pmu_events.attr_groups = hisi_ddrc_pmu_v2_attr_groups;
+ ddrc_pmu->ops = &hisi_uncore_ddrc_v2_ops;
+ } else {
+ ddrc_pmu->counter_bits = 32;
+ ddrc_pmu->check_event = DDRC_V1_NR_EVENTS;
+ ddrc_pmu->pmu_events.attr_groups = hisi_ddrc_pmu_v1_attr_groups;
+ ddrc_pmu->ops = &hisi_uncore_ddrc_v1_ops;
+ }
+
ddrc_pmu->num_counters = DDRC_NR_COUNTERS;
- ddrc_pmu->counter_bits = 32;
- ddrc_pmu->ops = &hisi_uncore_ddrc_ops;
ddrc_pmu->dev = &pdev->dev;
ddrc_pmu->on_cpu = -1;
- ddrc_pmu->check_event = 7;
return 0;
}
return ret;
}
- name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_ddrc%u",
- ddrc_pmu->sccl_id, ddrc_pmu->index_id);
+ if (ddrc_pmu->identifier >= HISI_PMU_V2)
+ name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+ "hisi_sccl%u_ddrc%u_%u",
+ ddrc_pmu->sccl_id, ddrc_pmu->index_id,
+ ddrc_pmu->sub_id);
+ else
+ name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+ "hisi_sccl%u_ddrc%u", ddrc_pmu->sccl_id,
+ ddrc_pmu->index_id);
+
ddrc_pmu->pmu = (struct pmu) {
.name = name,
.module = THIS_MODULE,
.start = hisi_uncore_pmu_start,
.stop = hisi_uncore_pmu_stop,
.read = hisi_uncore_pmu_read,
- .attr_groups = hisi_ddrc_pmu_attr_groups,
+ .attr_groups = ddrc_pmu->pmu_events.attr_groups,
.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
};
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/list.h>
-#include <linux/platform_device.h>
#include <linux/smp.h>
#include "hisi_uncore_pmu.h"
#define HHA_VERSION 0x1cf0
#define HHA_PERF_CTRL 0x1E00
#define HHA_EVENT_CTRL 0x1E04
+#define HHA_SRCID_CTRL 0x1E08
+#define HHA_DATSRC_CTRL 0x1BF0
#define HHA_EVENT_TYPE0 0x1E80
/*
- * Each counter is 48-bits and [48:63] are reserved
- * which are Read-As-Zero and Writes-Ignored.
+ * If the HW version only supports a 48-bit counter, then
+ * bits [63:48] are reserved, which are Read-As-Zero and
+ * Writes-Ignored.
*/
#define HHA_CNT0_LOWER 0x1F00
-/* HHA has 16-counters */
-#define HHA_NR_COUNTERS 0x10
+/* HHA PMU v1 has 16 counters and v2 only has 8 counters */
+#define HHA_V1_NR_COUNTERS 0x10
+#define HHA_V2_NR_COUNTERS 0x8
#define HHA_PERF_CTRL_EN 0x1
+#define HHA_TRACETAG_EN BIT(31)
+#define HHA_SRCID_EN BIT(2)
+#define HHA_SRCID_CMD_SHIFT 6
+#define HHA_SRCID_MSK_SHIFT 20
+#define HHA_SRCID_CMD GENMASK(16, 6)
+#define HHA_SRCID_MSK GENMASK(30, 20)
+#define HHA_DATSRC_SKT_EN BIT(23)
#define HHA_EVTYPE_NONE 0xff
+#define HHA_V1_NR_EVENT 0x65
+#define HHA_V2_NR_EVENT 0xCE
+
+HISI_PMU_EVENT_ATTR_EXTRACTOR(srcid_cmd, config1, 10, 0);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(srcid_msk, config1, 21, 11);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(tracetag_en, config1, 22, 22);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(datasrc_skt, config1, 23, 23);
+
+static void hisi_hha_pmu_enable_tracetag(struct perf_event *event)
+{
+ struct hisi_pmu *hha_pmu = to_hisi_pmu(event->pmu);
+ u32 tt_en = hisi_get_tracetag_en(event);
+
+ if (tt_en) {
+ u32 val;
+
+ val = readl(hha_pmu->base + HHA_SRCID_CTRL);
+ val |= HHA_TRACETAG_EN;
+ writel(val, hha_pmu->base + HHA_SRCID_CTRL);
+ }
+}
+
+static void hisi_hha_pmu_clear_tracetag(struct perf_event *event)
+{
+ struct hisi_pmu *hha_pmu = to_hisi_pmu(event->pmu);
+ u32 val;
+
+ val = readl(hha_pmu->base + HHA_SRCID_CTRL);
+ val &= ~HHA_TRACETAG_EN;
+ writel(val, hha_pmu->base + HHA_SRCID_CTRL);
+}
+
+static void hisi_hha_pmu_config_ds(struct perf_event *event)
+{
+ struct hisi_pmu *hha_pmu = to_hisi_pmu(event->pmu);
+ u32 ds_skt = hisi_get_datasrc_skt(event);
+
+ if (ds_skt) {
+ u32 val;
+
+ val = readl(hha_pmu->base + HHA_DATSRC_CTRL);
+ val |= HHA_DATSRC_SKT_EN;
+ writel(ds_skt, hha_pmu->base + HHA_DATSRC_CTRL);
+ }
+}
+
+static void hisi_hha_pmu_clear_ds(struct perf_event *event)
+{
+ struct hisi_pmu *hha_pmu = to_hisi_pmu(event->pmu);
+ u32 ds_skt = hisi_get_datasrc_skt(event);
+
+ if (ds_skt) {
+ u32 val;
+
+ val = readl(hha_pmu->base + HHA_DATSRC_CTRL);
+ val &= ~HHA_DATSRC_SKT_EN;
+ writel(ds_skt, hha_pmu->base + HHA_DATSRC_CTRL);
+ }
+}
+
+static void hisi_hha_pmu_config_srcid(struct perf_event *event)
+{
+ struct hisi_pmu *hha_pmu = to_hisi_pmu(event->pmu);
+ u32 cmd = hisi_get_srcid_cmd(event);
+
+ if (cmd) {
+ u32 val, msk;
+
+ msk = hisi_get_srcid_msk(event);
+ val = readl(hha_pmu->base + HHA_SRCID_CTRL);
+ val |= HHA_SRCID_EN | (cmd << HHA_SRCID_CMD_SHIFT) |
+ (msk << HHA_SRCID_MSK_SHIFT);
+ writel(val, hha_pmu->base + HHA_SRCID_CTRL);
+ }
+}
+
+static void hisi_hha_pmu_disable_srcid(struct perf_event *event)
+{
+ struct hisi_pmu *hha_pmu = to_hisi_pmu(event->pmu);
+ u32 cmd = hisi_get_srcid_cmd(event);
+
+ if (cmd) {
+ u32 val;
+
+ val = readl(hha_pmu->base + HHA_SRCID_CTRL);
+ val &= ~(HHA_SRCID_EN | HHA_SRCID_MSK | HHA_SRCID_CMD);
+ writel(val, hha_pmu->base + HHA_SRCID_CTRL);
+ }
+}
+
+static void hisi_hha_pmu_enable_filter(struct perf_event *event)
+{
+ if (event->attr.config1 != 0x0) {
+ hisi_hha_pmu_enable_tracetag(event);
+ hisi_hha_pmu_config_ds(event);
+ hisi_hha_pmu_config_srcid(event);
+ }
+}
+
+static void hisi_hha_pmu_disable_filter(struct perf_event *event)
+{
+ if (event->attr.config1 != 0x0) {
+ hisi_hha_pmu_disable_srcid(event);
+ hisi_hha_pmu_clear_ds(event);
+ hisi_hha_pmu_clear_tracetag(event);
+ }
+}
/*
* Select the counter register offset using the counter index
static u64 hisi_hha_pmu_read_counter(struct hisi_pmu *hha_pmu,
struct hw_perf_event *hwc)
{
- u32 idx = hwc->idx;
-
- if (!hisi_uncore_pmu_counter_valid(hha_pmu, idx)) {
- dev_err(hha_pmu->dev, "Unsupported event index:%d!\n", idx);
- return 0;
- }
-
/* Read 64 bits and like L3C, top 16 bits are RAZ */
- return readq(hha_pmu->base + hisi_hha_pmu_get_counter_offset(idx));
+ return readq(hha_pmu->base + hisi_hha_pmu_get_counter_offset(hwc->idx));
}
static void hisi_hha_pmu_write_counter(struct hisi_pmu *hha_pmu,
struct hw_perf_event *hwc, u64 val)
{
- u32 idx = hwc->idx;
-
- if (!hisi_uncore_pmu_counter_valid(hha_pmu, idx)) {
- dev_err(hha_pmu->dev, "Unsupported event index:%d!\n", idx);
- return;
- }
-
/* Write 64 bits and like L3C, top 16 bits are WI */
- writeq(val, hha_pmu->base + hisi_hha_pmu_get_counter_offset(idx));
+ writeq(val, hha_pmu->base + hisi_hha_pmu_get_counter_offset(hwc->idx));
}
static void hisi_hha_pmu_write_evtype(struct hisi_pmu *hha_pmu, int idx,
writel(val, hha_pmu->base + HHA_INT_MASK);
}
-static irqreturn_t hisi_hha_pmu_isr(int irq, void *dev_id)
+static u32 hisi_hha_pmu_get_int_status(struct hisi_pmu *hha_pmu)
{
- struct hisi_pmu *hha_pmu = dev_id;
- struct perf_event *event;
- unsigned long overflown;
- int idx;
-
- /* Read HHA_INT_STATUS register */
- overflown = readl(hha_pmu->base + HHA_INT_STATUS);
- if (!overflown)
- return IRQ_NONE;
-
- /*
- * Find the counter index which overflowed if the bit was set
- * and handle it
- */
- for_each_set_bit(idx, &overflown, HHA_NR_COUNTERS) {
- /* Write 1 to clear the IRQ status flag */
- writel((1 << idx), hha_pmu->base + HHA_INT_CLEAR);
-
- /* Get the corresponding event struct */
- event = hha_pmu->pmu_events.hw_events[idx];
- if (!event)
- continue;
-
- hisi_uncore_pmu_event_update(event);
- hisi_uncore_pmu_set_event_period(event);
- }
-
- return IRQ_HANDLED;
+ return readl(hha_pmu->base + HHA_INT_STATUS);
}
-static int hisi_hha_pmu_init_irq(struct hisi_pmu *hha_pmu,
- struct platform_device *pdev)
+static void hisi_hha_pmu_clear_int_status(struct hisi_pmu *hha_pmu, int idx)
{
- int irq, ret;
-
- /* Read and init IRQ */
- irq = platform_get_irq(pdev, 0);
- if (irq < 0)
- return irq;
-
- ret = devm_request_irq(&pdev->dev, irq, hisi_hha_pmu_isr,
- IRQF_NOBALANCING | IRQF_NO_THREAD,
- dev_name(&pdev->dev), hha_pmu);
- if (ret < 0) {
- dev_err(&pdev->dev,
- "Fail to request IRQ:%d ret:%d\n", irq, ret);
- return ret;
- }
-
- hha_pmu->irq = irq;
-
- return 0;
+ writel(1 << idx, hha_pmu->base + HHA_INT_CLEAR);
}
static const struct acpi_device_id hisi_hha_pmu_acpi_match[] = {
{ "HISI0243", },
- {},
+ { "HISI0244", },
+ {}
};
MODULE_DEVICE_TABLE(acpi, hisi_hha_pmu_acpi_match);
unsigned long long id;
acpi_status status;
- status = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev),
- "_UID", NULL, &id);
- if (ACPI_FAILURE(status))
- return -EINVAL;
-
- hha_pmu->index_id = id;
-
/*
* Use SCCL_ID and UID to identify the HHA PMU, while
* SCCL_ID is in MPIDR[aff2].
dev_err(&pdev->dev, "Can not read hha sccl-id!\n");
return -EINVAL;
}
+
+ /*
+ * Early versions of BIOS support _UID by mistake, so we support
+ * both "hisilicon, idx-id" as preference, if available.
+ */
+ if (device_property_read_u32(&pdev->dev, "hisilicon,idx-id",
+ &hha_pmu->index_id)) {
+ status = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev),
+ "_UID", NULL, &id);
+ if (ACPI_FAILURE(status)) {
+ dev_err(&pdev->dev, "Cannot read idx-id!\n");
+ return -EINVAL;
+ }
+
+ hha_pmu->index_id = id;
+ }
/* HHA PMUs only share the same SCCL */
hha_pmu->ccl_id = -1;
return 0;
}
-static struct attribute *hisi_hha_pmu_format_attr[] = {
+static struct attribute *hisi_hha_pmu_v1_format_attr[] = {
HISI_PMU_FORMAT_ATTR(event, "config:0-7"),
NULL,
};
-static const struct attribute_group hisi_hha_pmu_format_group = {
+static const struct attribute_group hisi_hha_pmu_v1_format_group = {
+ .name = "format",
+ .attrs = hisi_hha_pmu_v1_format_attr,
+};
+
+static struct attribute *hisi_hha_pmu_v2_format_attr[] = {
+ HISI_PMU_FORMAT_ATTR(event, "config:0-7"),
+ HISI_PMU_FORMAT_ATTR(srcid_cmd, "config1:0-10"),
+ HISI_PMU_FORMAT_ATTR(srcid_msk, "config1:11-21"),
+ HISI_PMU_FORMAT_ATTR(tracetag_en, "config1:22"),
+ HISI_PMU_FORMAT_ATTR(datasrc_skt, "config1:23"),
+ NULL
+};
+
+static const struct attribute_group hisi_hha_pmu_v2_format_group = {
.name = "format",
- .attrs = hisi_hha_pmu_format_attr,
+ .attrs = hisi_hha_pmu_v2_format_attr,
};
-static struct attribute *hisi_hha_pmu_events_attr[] = {
+static struct attribute *hisi_hha_pmu_v1_events_attr[] = {
HISI_PMU_EVENT_ATTR(rx_ops_num, 0x00),
HISI_PMU_EVENT_ATTR(rx_outer, 0x01),
HISI_PMU_EVENT_ATTR(rx_sccl, 0x02),
NULL,
};
-static const struct attribute_group hisi_hha_pmu_events_group = {
+static const struct attribute_group hisi_hha_pmu_v1_events_group = {
.name = "events",
- .attrs = hisi_hha_pmu_events_attr,
+ .attrs = hisi_hha_pmu_v1_events_attr,
+};
+
+static struct attribute *hisi_hha_pmu_v2_events_attr[] = {
+ HISI_PMU_EVENT_ATTR(rx_ops_num, 0x00),
+ HISI_PMU_EVENT_ATTR(rx_outer, 0x01),
+ HISI_PMU_EVENT_ATTR(rx_sccl, 0x02),
+ HISI_PMU_EVENT_ATTR(hha_retry, 0x2e),
+ HISI_PMU_EVENT_ATTR(cycles, 0x55),
+ NULL
+};
+
+static const struct attribute_group hisi_hha_pmu_v2_events_group = {
+ .name = "events",
+ .attrs = hisi_hha_pmu_v2_events_attr,
};
static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL);
.attrs = hisi_hha_pmu_identifier_attrs,
};
-static const struct attribute_group *hisi_hha_pmu_attr_groups[] = {
- &hisi_hha_pmu_format_group,
- &hisi_hha_pmu_events_group,
+static const struct attribute_group *hisi_hha_pmu_v1_attr_groups[] = {
+ &hisi_hha_pmu_v1_format_group,
+ &hisi_hha_pmu_v1_events_group,
&hisi_hha_pmu_cpumask_attr_group,
&hisi_hha_pmu_identifier_group,
NULL,
};
+static const struct attribute_group *hisi_hha_pmu_v2_attr_groups[] = {
+ &hisi_hha_pmu_v2_format_group,
+ &hisi_hha_pmu_v2_events_group,
+ &hisi_hha_pmu_cpumask_attr_group,
+ &hisi_hha_pmu_identifier_group,
+ NULL
+};
+
static const struct hisi_uncore_ops hisi_uncore_hha_ops = {
.write_evtype = hisi_hha_pmu_write_evtype,
.get_event_idx = hisi_uncore_pmu_get_event_idx,
.disable_counter_int = hisi_hha_pmu_disable_counter_int,
.write_counter = hisi_hha_pmu_write_counter,
.read_counter = hisi_hha_pmu_read_counter,
+ .get_int_status = hisi_hha_pmu_get_int_status,
+ .clear_int_status = hisi_hha_pmu_clear_int_status,
+ .enable_filter = hisi_hha_pmu_enable_filter,
+ .disable_filter = hisi_hha_pmu_disable_filter,
};
static int hisi_hha_pmu_dev_probe(struct platform_device *pdev,
if (ret)
return ret;
- ret = hisi_hha_pmu_init_irq(hha_pmu, pdev);
+ ret = hisi_uncore_pmu_init_irq(hha_pmu, pdev);
if (ret)
return ret;
- hha_pmu->num_counters = HHA_NR_COUNTERS;
- hha_pmu->counter_bits = 48;
+ if (hha_pmu->identifier >= HISI_PMU_V2) {
+ hha_pmu->counter_bits = 64;
+ hha_pmu->check_event = HHA_V2_NR_EVENT;
+ hha_pmu->pmu_events.attr_groups = hisi_hha_pmu_v2_attr_groups;
+ hha_pmu->num_counters = HHA_V2_NR_COUNTERS;
+ } else {
+ hha_pmu->counter_bits = 48;
+ hha_pmu->check_event = HHA_V1_NR_EVENT;
+ hha_pmu->pmu_events.attr_groups = hisi_hha_pmu_v1_attr_groups;
+ hha_pmu->num_counters = HHA_V1_NR_COUNTERS;
+ }
hha_pmu->ops = &hisi_uncore_hha_ops;
hha_pmu->dev = &pdev->dev;
hha_pmu->on_cpu = -1;
- hha_pmu->check_event = 0x65;
return 0;
}
.start = hisi_uncore_pmu_start,
.stop = hisi_uncore_pmu_stop,
.read = hisi_uncore_pmu_read,
- .attr_groups = hisi_hha_pmu_attr_groups,
+ .attr_groups = hha_pmu->pmu_events.attr_groups,
.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
};
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/list.h>
-#include <linux/platform_device.h>
#include <linux/smp.h>
#include "hisi_uncore_pmu.h"
#define L3C_INT_MASK 0x0800
#define L3C_INT_STATUS 0x0808
#define L3C_INT_CLEAR 0x080c
+#define L3C_CORE_CTRL 0x1b04
+#define L3C_TRACETAG_CTRL 0x1b20
+#define L3C_DATSRC_TYPE 0x1b48
+#define L3C_DATSRC_CTRL 0x1bf0
#define L3C_EVENT_CTRL 0x1c00
#define L3C_VERSION 0x1cf0
#define L3C_EVENT_TYPE0 0x1d00
/*
- * Each counter is 48-bits and [48:63] are reserved
- * which are Read-As-Zero and Writes-Ignored.
+ * If the HW version only supports a 48-bit counter, then
+ * bits [63:48] are reserved, which are Read-As-Zero and
+ * Writes-Ignored.
*/
#define L3C_CNTR0_LOWER 0x1e00
#define L3C_NR_COUNTERS 0x8
#define L3C_PERF_CTRL_EN 0x10000
+#define L3C_TRACETAG_EN BIT(31)
+#define L3C_TRACETAG_REQ_SHIFT 7
+#define L3C_TRACETAG_MARK_EN BIT(0)
+#define L3C_TRACETAG_REQ_EN (L3C_TRACETAG_MARK_EN | BIT(2))
+#define L3C_TRACETAG_CORE_EN (L3C_TRACETAG_MARK_EN | BIT(3))
+#define L3C_CORE_EN BIT(20)
+#define L3C_COER_NONE 0x0
+#define L3C_DATSRC_MASK 0xFF
+#define L3C_DATSRC_SKT_EN BIT(23)
+#define L3C_DATSRC_NONE 0x0
#define L3C_EVTYPE_NONE 0xff
+#define L3C_V1_NR_EVENTS 0x59
+#define L3C_V2_NR_EVENTS 0xFF
+
+HISI_PMU_EVENT_ATTR_EXTRACTOR(tt_core, config1, 7, 0);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(tt_req, config1, 10, 8);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(datasrc_cfg, config1, 15, 11);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(datasrc_skt, config1, 16, 16);
+
+static void hisi_l3c_pmu_config_req_tracetag(struct perf_event *event)
+{
+ struct hisi_pmu *l3c_pmu = to_hisi_pmu(event->pmu);
+ u32 tt_req = hisi_get_tt_req(event);
+
+ if (tt_req) {
+ u32 val;
+
+ /* Set request-type for tracetag */
+ val = readl(l3c_pmu->base + L3C_TRACETAG_CTRL);
+ val |= tt_req << L3C_TRACETAG_REQ_SHIFT;
+ val |= L3C_TRACETAG_REQ_EN;
+ writel(val, l3c_pmu->base + L3C_TRACETAG_CTRL);
+
+ /* Enable request-tracetag statistics */
+ val = readl(l3c_pmu->base + L3C_PERF_CTRL);
+ val |= L3C_TRACETAG_EN;
+ writel(val, l3c_pmu->base + L3C_PERF_CTRL);
+ }
+}
+
+static void hisi_l3c_pmu_clear_req_tracetag(struct perf_event *event)
+{
+ struct hisi_pmu *l3c_pmu = to_hisi_pmu(event->pmu);
+ u32 tt_req = hisi_get_tt_req(event);
+
+ if (tt_req) {
+ u32 val;
+
+ /* Clear request-type */
+ val = readl(l3c_pmu->base + L3C_TRACETAG_CTRL);
+ val &= ~(tt_req << L3C_TRACETAG_REQ_SHIFT);
+ val &= ~L3C_TRACETAG_REQ_EN;
+ writel(val, l3c_pmu->base + L3C_TRACETAG_CTRL);
+
+ /* Disable request-tracetag statistics */
+ val = readl(l3c_pmu->base + L3C_PERF_CTRL);
+ val &= ~L3C_TRACETAG_EN;
+ writel(val, l3c_pmu->base + L3C_PERF_CTRL);
+ }
+}
+
+static void hisi_l3c_pmu_write_ds(struct perf_event *event, u32 ds_cfg)
+{
+ struct hisi_pmu *l3c_pmu = to_hisi_pmu(event->pmu);
+ struct hw_perf_event *hwc = &event->hw;
+ u32 reg, reg_idx, shift, val;
+ int idx = hwc->idx;
+
+ /*
+ * Select the appropriate datasource register(L3C_DATSRC_TYPE0/1).
+ * There are 2 datasource ctrl register for the 8 hardware counters.
+ * Datasrc is 8-bits and for the former 4 hardware counters,
+ * L3C_DATSRC_TYPE0 is chosen. For the latter 4 hardware counters,
+ * L3C_DATSRC_TYPE1 is chosen.
+ */
+ reg = L3C_DATSRC_TYPE + (idx / 4) * 4;
+ reg_idx = idx % 4;
+ shift = 8 * reg_idx;
+
+ val = readl(l3c_pmu->base + reg);
+ val &= ~(L3C_DATSRC_MASK << shift);
+ val |= ds_cfg << shift;
+ writel(val, l3c_pmu->base + reg);
+}
+
+static void hisi_l3c_pmu_config_ds(struct perf_event *event)
+{
+ struct hisi_pmu *l3c_pmu = to_hisi_pmu(event->pmu);
+ u32 ds_cfg = hisi_get_datasrc_cfg(event);
+ u32 ds_skt = hisi_get_datasrc_skt(event);
+
+ if (ds_cfg)
+ hisi_l3c_pmu_write_ds(event, ds_cfg);
+
+ if (ds_skt) {
+ u32 val;
+
+ val = readl(l3c_pmu->base + L3C_DATSRC_CTRL);
+ val |= L3C_DATSRC_SKT_EN;
+ writel(val, l3c_pmu->base + L3C_DATSRC_CTRL);
+ }
+}
+
+static void hisi_l3c_pmu_clear_ds(struct perf_event *event)
+{
+ struct hisi_pmu *l3c_pmu = to_hisi_pmu(event->pmu);
+ u32 ds_cfg = hisi_get_datasrc_cfg(event);
+ u32 ds_skt = hisi_get_datasrc_skt(event);
+
+ if (ds_cfg)
+ hisi_l3c_pmu_write_ds(event, L3C_DATSRC_NONE);
+
+ if (ds_skt) {
+ u32 val;
+
+ val = readl(l3c_pmu->base + L3C_DATSRC_CTRL);
+ val &= ~L3C_DATSRC_SKT_EN;
+ writel(val, l3c_pmu->base + L3C_DATSRC_CTRL);
+ }
+}
+
+static void hisi_l3c_pmu_config_core_tracetag(struct perf_event *event)
+{
+ struct hisi_pmu *l3c_pmu = to_hisi_pmu(event->pmu);
+ u32 core = hisi_get_tt_core(event);
+
+ if (core) {
+ u32 val;
+
+ /* Config and enable core information */
+ writel(core, l3c_pmu->base + L3C_CORE_CTRL);
+ val = readl(l3c_pmu->base + L3C_PERF_CTRL);
+ val |= L3C_CORE_EN;
+ writel(val, l3c_pmu->base + L3C_PERF_CTRL);
+
+ /* Enable core-tracetag statistics */
+ val = readl(l3c_pmu->base + L3C_TRACETAG_CTRL);
+ val |= L3C_TRACETAG_CORE_EN;
+ writel(val, l3c_pmu->base + L3C_TRACETAG_CTRL);
+ }
+}
+
+static void hisi_l3c_pmu_clear_core_tracetag(struct perf_event *event)
+{
+ struct hisi_pmu *l3c_pmu = to_hisi_pmu(event->pmu);
+ u32 core = hisi_get_tt_core(event);
+
+ if (core) {
+ u32 val;
+
+ /* Clear core information */
+ writel(L3C_COER_NONE, l3c_pmu->base + L3C_CORE_CTRL);
+ val = readl(l3c_pmu->base + L3C_PERF_CTRL);
+ val &= ~L3C_CORE_EN;
+ writel(val, l3c_pmu->base + L3C_PERF_CTRL);
+
+ /* Disable core-tracetag statistics */
+ val = readl(l3c_pmu->base + L3C_TRACETAG_CTRL);
+ val &= ~L3C_TRACETAG_CORE_EN;
+ writel(val, l3c_pmu->base + L3C_TRACETAG_CTRL);
+ }
+}
+
+static void hisi_l3c_pmu_enable_filter(struct perf_event *event)
+{
+ if (event->attr.config1 != 0x0) {
+ hisi_l3c_pmu_config_req_tracetag(event);
+ hisi_l3c_pmu_config_core_tracetag(event);
+ hisi_l3c_pmu_config_ds(event);
+ }
+}
+
+static void hisi_l3c_pmu_disable_filter(struct perf_event *event)
+{
+ if (event->attr.config1 != 0x0) {
+ hisi_l3c_pmu_clear_ds(event);
+ hisi_l3c_pmu_clear_core_tracetag(event);
+ hisi_l3c_pmu_clear_req_tracetag(event);
+ }
+}
/*
* Select the counter register offset using the counter index
static u64 hisi_l3c_pmu_read_counter(struct hisi_pmu *l3c_pmu,
struct hw_perf_event *hwc)
{
- u32 idx = hwc->idx;
-
- if (!hisi_uncore_pmu_counter_valid(l3c_pmu, idx)) {
- dev_err(l3c_pmu->dev, "Unsupported event index:%d!\n", idx);
- return 0;
- }
-
- /* Read 64-bits and the upper 16 bits are RAZ */
- return readq(l3c_pmu->base + hisi_l3c_pmu_get_counter_offset(idx));
+ return readq(l3c_pmu->base + hisi_l3c_pmu_get_counter_offset(hwc->idx));
}
static void hisi_l3c_pmu_write_counter(struct hisi_pmu *l3c_pmu,
struct hw_perf_event *hwc, u64 val)
{
- u32 idx = hwc->idx;
-
- if (!hisi_uncore_pmu_counter_valid(l3c_pmu, idx)) {
- dev_err(l3c_pmu->dev, "Unsupported event index:%d!\n", idx);
- return;
- }
-
- /* Write 64-bits and the upper 16 bits are WI */
- writeq(val, l3c_pmu->base + hisi_l3c_pmu_get_counter_offset(idx));
+ writeq(val, l3c_pmu->base + hisi_l3c_pmu_get_counter_offset(hwc->idx));
}
static void hisi_l3c_pmu_write_evtype(struct hisi_pmu *l3c_pmu, int idx,
writel(val, l3c_pmu->base + L3C_INT_MASK);
}
-static irqreturn_t hisi_l3c_pmu_isr(int irq, void *dev_id)
+static u32 hisi_l3c_pmu_get_int_status(struct hisi_pmu *l3c_pmu)
{
- struct hisi_pmu *l3c_pmu = dev_id;
- struct perf_event *event;
- unsigned long overflown;
- int idx;
-
- /* Read L3C_INT_STATUS register */
- overflown = readl(l3c_pmu->base + L3C_INT_STATUS);
- if (!overflown)
- return IRQ_NONE;
-
- /*
- * Find the counter index which overflowed if the bit was set
- * and handle it.
- */
- for_each_set_bit(idx, &overflown, L3C_NR_COUNTERS) {
- /* Write 1 to clear the IRQ status flag */
- writel((1 << idx), l3c_pmu->base + L3C_INT_CLEAR);
-
- /* Get the corresponding event struct */
- event = l3c_pmu->pmu_events.hw_events[idx];
- if (!event)
- continue;
-
- hisi_uncore_pmu_event_update(event);
- hisi_uncore_pmu_set_event_period(event);
- }
-
- return IRQ_HANDLED;
+ return readl(l3c_pmu->base + L3C_INT_STATUS);
}
-static int hisi_l3c_pmu_init_irq(struct hisi_pmu *l3c_pmu,
- struct platform_device *pdev)
+static void hisi_l3c_pmu_clear_int_status(struct hisi_pmu *l3c_pmu, int idx)
{
- int irq, ret;
-
- /* Read and init IRQ */
- irq = platform_get_irq(pdev, 0);
- if (irq < 0)
- return irq;
-
- ret = devm_request_irq(&pdev->dev, irq, hisi_l3c_pmu_isr,
- IRQF_NOBALANCING | IRQF_NO_THREAD,
- dev_name(&pdev->dev), l3c_pmu);
- if (ret < 0) {
- dev_err(&pdev->dev,
- "Fail to request IRQ:%d ret:%d\n", irq, ret);
- return ret;
- }
-
- l3c_pmu->irq = irq;
-
- return 0;
+ writel(1 << idx, l3c_pmu->base + L3C_INT_CLEAR);
}
static const struct acpi_device_id hisi_l3c_pmu_acpi_match[] = {
{ "HISI0213", },
- {},
+ { "HISI0214", },
+ {}
};
MODULE_DEVICE_TABLE(acpi, hisi_l3c_pmu_acpi_match);
static int hisi_l3c_pmu_init_data(struct platform_device *pdev,
struct hisi_pmu *l3c_pmu)
{
- unsigned long long id;
- acpi_status status;
-
- status = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev),
- "_UID", NULL, &id);
- if (ACPI_FAILURE(status))
- return -EINVAL;
-
- l3c_pmu->index_id = id;
-
/*
* Use the SCCL_ID and CCL_ID to identify the L3C PMU, while
* SCCL_ID is in MPIDR[aff2] and CCL_ID is in MPIDR[aff1].
return 0;
}
-static struct attribute *hisi_l3c_pmu_format_attr[] = {
+static struct attribute *hisi_l3c_pmu_v1_format_attr[] = {
HISI_PMU_FORMAT_ATTR(event, "config:0-7"),
NULL,
};
-static const struct attribute_group hisi_l3c_pmu_format_group = {
+static const struct attribute_group hisi_l3c_pmu_v1_format_group = {
+ .name = "format",
+ .attrs = hisi_l3c_pmu_v1_format_attr,
+};
+
+static struct attribute *hisi_l3c_pmu_v2_format_attr[] = {
+ HISI_PMU_FORMAT_ATTR(event, "config:0-7"),
+ HISI_PMU_FORMAT_ATTR(tt_core, "config1:0-7"),
+ HISI_PMU_FORMAT_ATTR(tt_req, "config1:8-10"),
+ HISI_PMU_FORMAT_ATTR(datasrc_cfg, "config1:11-15"),
+ HISI_PMU_FORMAT_ATTR(datasrc_skt, "config1:16"),
+ NULL
+};
+
+static const struct attribute_group hisi_l3c_pmu_v2_format_group = {
.name = "format",
- .attrs = hisi_l3c_pmu_format_attr,
+ .attrs = hisi_l3c_pmu_v2_format_attr,
};
-static struct attribute *hisi_l3c_pmu_events_attr[] = {
+static struct attribute *hisi_l3c_pmu_v1_events_attr[] = {
HISI_PMU_EVENT_ATTR(rd_cpipe, 0x00),
HISI_PMU_EVENT_ATTR(wr_cpipe, 0x01),
HISI_PMU_EVENT_ATTR(rd_hit_cpipe, 0x02),
NULL,
};
-static const struct attribute_group hisi_l3c_pmu_events_group = {
+static const struct attribute_group hisi_l3c_pmu_v1_events_group = {
+ .name = "events",
+ .attrs = hisi_l3c_pmu_v1_events_attr,
+};
+
+static struct attribute *hisi_l3c_pmu_v2_events_attr[] = {
+ HISI_PMU_EVENT_ATTR(l3c_hit, 0x48),
+ HISI_PMU_EVENT_ATTR(cycles, 0x7f),
+ HISI_PMU_EVENT_ATTR(l3c_ref, 0xb8),
+ HISI_PMU_EVENT_ATTR(dat_access, 0xb9),
+ NULL
+};
+
+static const struct attribute_group hisi_l3c_pmu_v2_events_group = {
.name = "events",
- .attrs = hisi_l3c_pmu_events_attr,
+ .attrs = hisi_l3c_pmu_v2_events_attr,
};
static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL);
.attrs = hisi_l3c_pmu_identifier_attrs,
};
-static const struct attribute_group *hisi_l3c_pmu_attr_groups[] = {
- &hisi_l3c_pmu_format_group,
- &hisi_l3c_pmu_events_group,
+static const struct attribute_group *hisi_l3c_pmu_v1_attr_groups[] = {
+ &hisi_l3c_pmu_v1_format_group,
+ &hisi_l3c_pmu_v1_events_group,
&hisi_l3c_pmu_cpumask_attr_group,
&hisi_l3c_pmu_identifier_group,
NULL,
};
+static const struct attribute_group *hisi_l3c_pmu_v2_attr_groups[] = {
+ &hisi_l3c_pmu_v2_format_group,
+ &hisi_l3c_pmu_v2_events_group,
+ &hisi_l3c_pmu_cpumask_attr_group,
+ &hisi_l3c_pmu_identifier_group,
+ NULL
+};
+
static const struct hisi_uncore_ops hisi_uncore_l3c_ops = {
.write_evtype = hisi_l3c_pmu_write_evtype,
.get_event_idx = hisi_uncore_pmu_get_event_idx,
.disable_counter_int = hisi_l3c_pmu_disable_counter_int,
.write_counter = hisi_l3c_pmu_write_counter,
.read_counter = hisi_l3c_pmu_read_counter,
+ .get_int_status = hisi_l3c_pmu_get_int_status,
+ .clear_int_status = hisi_l3c_pmu_clear_int_status,
+ .enable_filter = hisi_l3c_pmu_enable_filter,
+ .disable_filter = hisi_l3c_pmu_disable_filter,
};
static int hisi_l3c_pmu_dev_probe(struct platform_device *pdev,
if (ret)
return ret;
- ret = hisi_l3c_pmu_init_irq(l3c_pmu, pdev);
+ ret = hisi_uncore_pmu_init_irq(l3c_pmu, pdev);
if (ret)
return ret;
+ if (l3c_pmu->identifier >= HISI_PMU_V2) {
+ l3c_pmu->counter_bits = 64;
+ l3c_pmu->check_event = L3C_V2_NR_EVENTS;
+ l3c_pmu->pmu_events.attr_groups = hisi_l3c_pmu_v2_attr_groups;
+ } else {
+ l3c_pmu->counter_bits = 48;
+ l3c_pmu->check_event = L3C_V1_NR_EVENTS;
+ l3c_pmu->pmu_events.attr_groups = hisi_l3c_pmu_v1_attr_groups;
+ }
+
l3c_pmu->num_counters = L3C_NR_COUNTERS;
- l3c_pmu->counter_bits = 48;
l3c_pmu->ops = &hisi_uncore_l3c_ops;
l3c_pmu->dev = &pdev->dev;
l3c_pmu->on_cpu = -1;
- l3c_pmu->check_event = 0x59;
return 0;
}
return ret;
}
+ /*
+ * CCL_ID is used to identify the L3C in the same SCCL which was
+ * used _UID by mistake.
+ */
name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_l3c%u",
- l3c_pmu->sccl_id, l3c_pmu->index_id);
+ l3c_pmu->sccl_id, l3c_pmu->ccl_id);
l3c_pmu->pmu = (struct pmu) {
.name = name,
.module = THIS_MODULE,
.start = hisi_uncore_pmu_start,
.stop = hisi_uncore_pmu_stop,
.read = hisi_uncore_pmu_read,
- .attr_groups = hisi_l3c_pmu_attr_groups,
+ .attr_groups = l3c_pmu->pmu_events.attr_groups,
.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
};
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * HiSilicon PA uncore Hardware event counters support
+ *
+ * Copyright (C) 2020 HiSilicon Limited
+ * Author: Shaokun Zhang <zhangshaokun@hisilicon.com>
+ *
+ * This code is based on the uncore PMUs like arm-cci and arm-ccn.
+ */
+#include <linux/acpi.h>
+#include <linux/cpuhotplug.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/list.h>
+#include <linux/smp.h>
+
+#include "hisi_uncore_pmu.h"
+
+/* PA register definition */
+#define PA_PERF_CTRL 0x1c00
+#define PA_EVENT_CTRL 0x1c04
+#define PA_TT_CTRL 0x1c08
+#define PA_TGTID_CTRL 0x1c14
+#define PA_SRCID_CTRL 0x1c18
+#define PA_INT_MASK 0x1c70
+#define PA_INT_STATUS 0x1c78
+#define PA_INT_CLEAR 0x1c7c
+#define PA_EVENT_TYPE0 0x1c80
+#define PA_PMU_VERSION 0x1cf0
+#define PA_EVENT_CNT0_L 0x1f00
+
+#define PA_EVTYPE_MASK 0xff
+#define PA_NR_COUNTERS 0x8
+#define PA_PERF_CTRL_EN BIT(0)
+#define PA_TRACETAG_EN BIT(4)
+#define PA_TGTID_EN BIT(11)
+#define PA_SRCID_EN BIT(11)
+#define PA_TGTID_NONE 0
+#define PA_SRCID_NONE 0
+#define PA_TGTID_MSK_SHIFT 12
+#define PA_SRCID_MSK_SHIFT 12
+
+HISI_PMU_EVENT_ATTR_EXTRACTOR(tgtid_cmd, config1, 10, 0);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(tgtid_msk, config1, 21, 11);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(srcid_cmd, config1, 32, 22);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(srcid_msk, config1, 43, 33);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(tracetag_en, config1, 44, 44);
+
+static void hisi_pa_pmu_enable_tracetag(struct perf_event *event)
+{
+ struct hisi_pmu *pa_pmu = to_hisi_pmu(event->pmu);
+ u32 tt_en = hisi_get_tracetag_en(event);
+
+ if (tt_en) {
+ u32 val;
+
+ val = readl(pa_pmu->base + PA_TT_CTRL);
+ val |= PA_TRACETAG_EN;
+ writel(val, pa_pmu->base + PA_TT_CTRL);
+ }
+}
+
+static void hisi_pa_pmu_clear_tracetag(struct perf_event *event)
+{
+ struct hisi_pmu *pa_pmu = to_hisi_pmu(event->pmu);
+ u32 tt_en = hisi_get_tracetag_en(event);
+
+ if (tt_en) {
+ u32 val;
+
+ val = readl(pa_pmu->base + PA_TT_CTRL);
+ val &= ~PA_TRACETAG_EN;
+ writel(val, pa_pmu->base + PA_TT_CTRL);
+ }
+}
+
+static void hisi_pa_pmu_config_tgtid(struct perf_event *event)
+{
+ struct hisi_pmu *pa_pmu = to_hisi_pmu(event->pmu);
+ u32 cmd = hisi_get_tgtid_cmd(event);
+
+ if (cmd) {
+ u32 msk = hisi_get_tgtid_msk(event);
+ u32 val = cmd | PA_TGTID_EN | (msk << PA_TGTID_MSK_SHIFT);
+
+ writel(val, pa_pmu->base + PA_TGTID_CTRL);
+ }
+}
+
+static void hisi_pa_pmu_clear_tgtid(struct perf_event *event)
+{
+ struct hisi_pmu *pa_pmu = to_hisi_pmu(event->pmu);
+ u32 cmd = hisi_get_tgtid_cmd(event);
+
+ if (cmd)
+ writel(PA_TGTID_NONE, pa_pmu->base + PA_TGTID_CTRL);
+}
+
+static void hisi_pa_pmu_config_srcid(struct perf_event *event)
+{
+ struct hisi_pmu *pa_pmu = to_hisi_pmu(event->pmu);
+ u32 cmd = hisi_get_srcid_cmd(event);
+
+ if (cmd) {
+ u32 msk = hisi_get_srcid_msk(event);
+ u32 val = cmd | PA_SRCID_EN | (msk << PA_SRCID_MSK_SHIFT);
+
+ writel(val, pa_pmu->base + PA_SRCID_CTRL);
+ }
+}
+
+static void hisi_pa_pmu_clear_srcid(struct perf_event *event)
+{
+ struct hisi_pmu *pa_pmu = to_hisi_pmu(event->pmu);
+ u32 cmd = hisi_get_srcid_cmd(event);
+
+ if (cmd)
+ writel(PA_SRCID_NONE, pa_pmu->base + PA_SRCID_CTRL);
+}
+
+static void hisi_pa_pmu_enable_filter(struct perf_event *event)
+{
+ if (event->attr.config1 != 0x0) {
+ hisi_pa_pmu_enable_tracetag(event);
+ hisi_pa_pmu_config_srcid(event);
+ hisi_pa_pmu_config_tgtid(event);
+ }
+}
+
+static void hisi_pa_pmu_disable_filter(struct perf_event *event)
+{
+ if (event->attr.config1 != 0x0) {
+ hisi_pa_pmu_clear_tgtid(event);
+ hisi_pa_pmu_clear_srcid(event);
+ hisi_pa_pmu_clear_tracetag(event);
+ }
+}
+
+static u32 hisi_pa_pmu_get_counter_offset(int idx)
+{
+ return (PA_EVENT_CNT0_L + idx * 8);
+}
+
+static u64 hisi_pa_pmu_read_counter(struct hisi_pmu *pa_pmu,
+ struct hw_perf_event *hwc)
+{
+ return readq(pa_pmu->base + hisi_pa_pmu_get_counter_offset(hwc->idx));
+}
+
+static void hisi_pa_pmu_write_counter(struct hisi_pmu *pa_pmu,
+ struct hw_perf_event *hwc, u64 val)
+{
+ writeq(val, pa_pmu->base + hisi_pa_pmu_get_counter_offset(hwc->idx));
+}
+
+static void hisi_pa_pmu_write_evtype(struct hisi_pmu *pa_pmu, int idx,
+ u32 type)
+{
+ u32 reg, reg_idx, shift, val;
+
+ /*
+ * Select the appropriate event select register(PA_EVENT_TYPE0/1).
+ * There are 2 event select registers for the 8 hardware counters.
+ * Event code is 8-bits and for the former 4 hardware counters,
+ * PA_EVENT_TYPE0 is chosen. For the latter 4 hardware counters,
+ * PA_EVENT_TYPE1 is chosen.
+ */
+ reg = PA_EVENT_TYPE0 + (idx / 4) * 4;
+ reg_idx = idx % 4;
+ shift = 8 * reg_idx;
+
+ /* Write event code to pa_EVENT_TYPEx Register */
+ val = readl(pa_pmu->base + reg);
+ val &= ~(PA_EVTYPE_MASK << shift);
+ val |= (type << shift);
+ writel(val, pa_pmu->base + reg);
+}
+
+static void hisi_pa_pmu_start_counters(struct hisi_pmu *pa_pmu)
+{
+ u32 val;
+
+ val = readl(pa_pmu->base + PA_PERF_CTRL);
+ val |= PA_PERF_CTRL_EN;
+ writel(val, pa_pmu->base + PA_PERF_CTRL);
+}
+
+static void hisi_pa_pmu_stop_counters(struct hisi_pmu *pa_pmu)
+{
+ u32 val;
+
+ val = readl(pa_pmu->base + PA_PERF_CTRL);
+ val &= ~(PA_PERF_CTRL_EN);
+ writel(val, pa_pmu->base + PA_PERF_CTRL);
+}
+
+static void hisi_pa_pmu_enable_counter(struct hisi_pmu *pa_pmu,
+ struct hw_perf_event *hwc)
+{
+ u32 val;
+
+ /* Enable counter index in PA_EVENT_CTRL register */
+ val = readl(pa_pmu->base + PA_EVENT_CTRL);
+ val |= 1 << hwc->idx;
+ writel(val, pa_pmu->base + PA_EVENT_CTRL);
+}
+
+static void hisi_pa_pmu_disable_counter(struct hisi_pmu *pa_pmu,
+ struct hw_perf_event *hwc)
+{
+ u32 val;
+
+ /* Clear counter index in PA_EVENT_CTRL register */
+ val = readl(pa_pmu->base + PA_EVENT_CTRL);
+ val &= ~(1 << hwc->idx);
+ writel(val, pa_pmu->base + PA_EVENT_CTRL);
+}
+
+static void hisi_pa_pmu_enable_counter_int(struct hisi_pmu *pa_pmu,
+ struct hw_perf_event *hwc)
+{
+ u32 val;
+
+ /* Write 0 to enable interrupt */
+ val = readl(pa_pmu->base + PA_INT_MASK);
+ val &= ~(1 << hwc->idx);
+ writel(val, pa_pmu->base + PA_INT_MASK);
+}
+
+static void hisi_pa_pmu_disable_counter_int(struct hisi_pmu *pa_pmu,
+ struct hw_perf_event *hwc)
+{
+ u32 val;
+
+ /* Write 1 to mask interrupt */
+ val = readl(pa_pmu->base + PA_INT_MASK);
+ val |= 1 << hwc->idx;
+ writel(val, pa_pmu->base + PA_INT_MASK);
+}
+
+static u32 hisi_pa_pmu_get_int_status(struct hisi_pmu *pa_pmu)
+{
+ return readl(pa_pmu->base + PA_INT_STATUS);
+}
+
+static void hisi_pa_pmu_clear_int_status(struct hisi_pmu *pa_pmu, int idx)
+{
+ writel(1 << idx, pa_pmu->base + PA_INT_CLEAR);
+}
+
+static const struct acpi_device_id hisi_pa_pmu_acpi_match[] = {
+ { "HISI0273", },
+ {}
+};
+MODULE_DEVICE_TABLE(acpi, hisi_pa_pmu_acpi_match);
+
+static int hisi_pa_pmu_init_data(struct platform_device *pdev,
+ struct hisi_pmu *pa_pmu)
+{
+ /*
+ * Use the SCCL_ID and the index ID to identify the PA PMU,
+ * while SCCL_ID is the nearst SCCL_ID from this SICL and
+ * CPU core is chosen from this SCCL to manage this PMU.
+ */
+ if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id",
+ &pa_pmu->sccl_id)) {
+ dev_err(&pdev->dev, "Cannot read sccl-id!\n");
+ return -EINVAL;
+ }
+
+ if (device_property_read_u32(&pdev->dev, "hisilicon,idx-id",
+ &pa_pmu->index_id)) {
+ dev_err(&pdev->dev, "Cannot read idx-id!\n");
+ return -EINVAL;
+ }
+
+ pa_pmu->ccl_id = -1;
+
+ pa_pmu->base = devm_platform_ioremap_resource(pdev, 0);
+ if (IS_ERR(pa_pmu->base)) {
+ dev_err(&pdev->dev, "ioremap failed for pa_pmu resource.\n");
+ return PTR_ERR(pa_pmu->base);
+ }
+
+ pa_pmu->identifier = readl(pa_pmu->base + PA_PMU_VERSION);
+
+ return 0;
+}
+
+static struct attribute *hisi_pa_pmu_v2_format_attr[] = {
+ HISI_PMU_FORMAT_ATTR(event, "config:0-7"),
+ HISI_PMU_FORMAT_ATTR(tgtid_cmd, "config1:0-10"),
+ HISI_PMU_FORMAT_ATTR(tgtid_msk, "config1:11-21"),
+ HISI_PMU_FORMAT_ATTR(srcid_cmd, "config1:22-32"),
+ HISI_PMU_FORMAT_ATTR(srcid_msk, "config1:33-43"),
+ HISI_PMU_FORMAT_ATTR(tracetag_en, "config1:44"),
+ NULL,
+};
+
+static const struct attribute_group hisi_pa_pmu_v2_format_group = {
+ .name = "format",
+ .attrs = hisi_pa_pmu_v2_format_attr,
+};
+
+static struct attribute *hisi_pa_pmu_v2_events_attr[] = {
+ HISI_PMU_EVENT_ATTR(rx_req, 0x40),
+ HISI_PMU_EVENT_ATTR(tx_req, 0x5c),
+ HISI_PMU_EVENT_ATTR(cycle, 0x78),
+ NULL
+};
+
+static const struct attribute_group hisi_pa_pmu_v2_events_group = {
+ .name = "events",
+ .attrs = hisi_pa_pmu_v2_events_attr,
+};
+
+static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL);
+
+static struct attribute *hisi_pa_pmu_cpumask_attrs[] = {
+ &dev_attr_cpumask.attr,
+ NULL
+};
+
+static const struct attribute_group hisi_pa_pmu_cpumask_attr_group = {
+ .attrs = hisi_pa_pmu_cpumask_attrs,
+};
+
+static struct device_attribute hisi_pa_pmu_identifier_attr =
+ __ATTR(identifier, 0444, hisi_uncore_pmu_identifier_attr_show, NULL);
+
+static struct attribute *hisi_pa_pmu_identifier_attrs[] = {
+ &hisi_pa_pmu_identifier_attr.attr,
+ NULL
+};
+
+static struct attribute_group hisi_pa_pmu_identifier_group = {
+ .attrs = hisi_pa_pmu_identifier_attrs,
+};
+
+static const struct attribute_group *hisi_pa_pmu_v2_attr_groups[] = {
+ &hisi_pa_pmu_v2_format_group,
+ &hisi_pa_pmu_v2_events_group,
+ &hisi_pa_pmu_cpumask_attr_group,
+ &hisi_pa_pmu_identifier_group,
+ NULL
+};
+
+static const struct hisi_uncore_ops hisi_uncore_pa_ops = {
+ .write_evtype = hisi_pa_pmu_write_evtype,
+ .get_event_idx = hisi_uncore_pmu_get_event_idx,
+ .start_counters = hisi_pa_pmu_start_counters,
+ .stop_counters = hisi_pa_pmu_stop_counters,
+ .enable_counter = hisi_pa_pmu_enable_counter,
+ .disable_counter = hisi_pa_pmu_disable_counter,
+ .enable_counter_int = hisi_pa_pmu_enable_counter_int,
+ .disable_counter_int = hisi_pa_pmu_disable_counter_int,
+ .write_counter = hisi_pa_pmu_write_counter,
+ .read_counter = hisi_pa_pmu_read_counter,
+ .get_int_status = hisi_pa_pmu_get_int_status,
+ .clear_int_status = hisi_pa_pmu_clear_int_status,
+ .enable_filter = hisi_pa_pmu_enable_filter,
+ .disable_filter = hisi_pa_pmu_disable_filter,
+};
+
+static int hisi_pa_pmu_dev_probe(struct platform_device *pdev,
+ struct hisi_pmu *pa_pmu)
+{
+ int ret;
+
+ ret = hisi_pa_pmu_init_data(pdev, pa_pmu);
+ if (ret)
+ return ret;
+
+ ret = hisi_uncore_pmu_init_irq(pa_pmu, pdev);
+ if (ret)
+ return ret;
+
+ pa_pmu->pmu_events.attr_groups = hisi_pa_pmu_v2_attr_groups;
+ pa_pmu->num_counters = PA_NR_COUNTERS;
+ pa_pmu->ops = &hisi_uncore_pa_ops;
+ pa_pmu->check_event = 0xB0;
+ pa_pmu->counter_bits = 64;
+ pa_pmu->dev = &pdev->dev;
+ pa_pmu->on_cpu = -1;
+
+ return 0;
+}
+
+static int hisi_pa_pmu_probe(struct platform_device *pdev)
+{
+ struct hisi_pmu *pa_pmu;
+ char *name;
+ int ret;
+
+ pa_pmu = devm_kzalloc(&pdev->dev, sizeof(*pa_pmu), GFP_KERNEL);
+ if (!pa_pmu)
+ return -ENOMEM;
+
+ ret = hisi_pa_pmu_dev_probe(pdev, pa_pmu);
+ if (ret)
+ return ret;
+ /*
+ * PA is attached in SICL and the CPU core is chosen to manage this
+ * PMU which is the nearest SCCL, while its SCCL_ID is greater than
+ * one with the SICL_ID.
+ */
+ name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sicl%u_pa%u",
+ pa_pmu->sccl_id - 1, pa_pmu->index_id);
+ if (!name)
+ return -ENOMEM;
+
+ ret = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_HISI_PA_ONLINE,
+ &pa_pmu->node);
+ if (ret) {
+ dev_err(&pdev->dev, "Error %d registering hotplug\n", ret);
+ return ret;
+ }
+
+ pa_pmu->pmu = (struct pmu) {
+ .module = THIS_MODULE,
+ .task_ctx_nr = perf_invalid_context,
+ .event_init = hisi_uncore_pmu_event_init,
+ .pmu_enable = hisi_uncore_pmu_enable,
+ .pmu_disable = hisi_uncore_pmu_disable,
+ .add = hisi_uncore_pmu_add,
+ .del = hisi_uncore_pmu_del,
+ .start = hisi_uncore_pmu_start,
+ .stop = hisi_uncore_pmu_stop,
+ .read = hisi_uncore_pmu_read,
+ .attr_groups = pa_pmu->pmu_events.attr_groups,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
+ };
+
+ ret = perf_pmu_register(&pa_pmu->pmu, name, -1);
+ if (ret) {
+ dev_err(pa_pmu->dev, "PMU register failed, ret = %d\n", ret);
+ cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_PA_ONLINE,
+ &pa_pmu->node);
+ irq_set_affinity_hint(pa_pmu->irq, NULL);
+ return ret;
+ }
+
+ platform_set_drvdata(pdev, pa_pmu);
+ return ret;
+}
+
+static int hisi_pa_pmu_remove(struct platform_device *pdev)
+{
+ struct hisi_pmu *pa_pmu = platform_get_drvdata(pdev);
+
+ perf_pmu_unregister(&pa_pmu->pmu);
+ cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_PA_ONLINE,
+ &pa_pmu->node);
+ irq_set_affinity_hint(pa_pmu->irq, NULL);
+
+ return 0;
+}
+
+static struct platform_driver hisi_pa_pmu_driver = {
+ .driver = {
+ .name = "hisi_pa_pmu",
+ .acpi_match_table = hisi_pa_pmu_acpi_match,
+ .suppress_bind_attrs = true,
+ },
+ .probe = hisi_pa_pmu_probe,
+ .remove = hisi_pa_pmu_remove,
+};
+
+static int __init hisi_pa_pmu_module_init(void)
+{
+ int ret;
+
+ ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_HISI_PA_ONLINE,
+ "AP_PERF_ARM_HISI_PA_ONLINE",
+ hisi_uncore_pmu_online_cpu,
+ hisi_uncore_pmu_offline_cpu);
+ if (ret) {
+ pr_err("PA PMU: cpuhp state setup failed, ret = %d\n", ret);
+ return ret;
+ }
+
+ ret = platform_driver_register(&hisi_pa_pmu_driver);
+ if (ret)
+ cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_PA_ONLINE);
+
+ return ret;
+}
+module_init(hisi_pa_pmu_module_init);
+
+static void __exit hisi_pa_pmu_module_exit(void)
+{
+ platform_driver_unregister(&hisi_pa_pmu_driver);
+ cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_PA_ONLINE);
+}
+module_exit(hisi_pa_pmu_module_exit);
+
+MODULE_DESCRIPTION("HiSilicon Protocol Adapter uncore PMU driver");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Shaokun Zhang <zhangshaokun@hisilicon.com>");
+MODULE_AUTHOR("Qi Liu <liuqi115@huawei.com>");
#include "hisi_uncore_pmu.h"
#define HISI_GET_EVENTID(ev) (ev->hw.config_base & 0xff)
-#define HISI_MAX_PERIOD(nr) (BIT_ULL(nr) - 1)
+#define HISI_MAX_PERIOD(nr) (GENMASK_ULL((nr) - 1, 0))
/*
* PMU format attributes
eattr = container_of(attr, struct dev_ext_attribute, attr);
- return sprintf(buf, "%s\n", (char *)eattr->var);
+ return sysfs_emit(buf, "%s\n", (char *)eattr->var);
}
EXPORT_SYMBOL_GPL(hisi_format_sysfs_show);
eattr = container_of(attr, struct dev_ext_attribute, attr);
- return sprintf(page, "config=0x%lx\n", (unsigned long)eattr->var);
+ return sysfs_emit(page, "config=0x%lx\n", (unsigned long)eattr->var);
}
EXPORT_SYMBOL_GPL(hisi_event_sysfs_show);
{
struct hisi_pmu *hisi_pmu = to_hisi_pmu(dev_get_drvdata(dev));
- return sprintf(buf, "%d\n", hisi_pmu->on_cpu);
+ return sysfs_emit(buf, "%d\n", hisi_pmu->on_cpu);
}
EXPORT_SYMBOL_GPL(hisi_cpumask_sysfs_show);
return counters <= hisi_pmu->num_counters;
}
-int hisi_uncore_pmu_counter_valid(struct hisi_pmu *hisi_pmu, int idx)
-{
- return idx >= 0 && idx < hisi_pmu->num_counters;
-}
-EXPORT_SYMBOL_GPL(hisi_uncore_pmu_counter_valid);
-
int hisi_uncore_pmu_get_event_idx(struct perf_event *event)
{
struct hisi_pmu *hisi_pmu = to_hisi_pmu(event->pmu);
{
struct hisi_pmu *hisi_pmu = to_hisi_pmu(dev_get_drvdata(dev));
- return snprintf(page, PAGE_SIZE, "0x%08x\n", hisi_pmu->identifier);
+ return sysfs_emit(page, "0x%08x\n", hisi_pmu->identifier);
}
EXPORT_SYMBOL_GPL(hisi_uncore_pmu_identifier_attr_show);
static void hisi_uncore_pmu_clear_event_idx(struct hisi_pmu *hisi_pmu, int idx)
{
- if (!hisi_uncore_pmu_counter_valid(hisi_pmu, idx)) {
- dev_err(hisi_pmu->dev, "Unsupported event index:%d!\n", idx);
- return;
+ clear_bit(idx, hisi_pmu->pmu_events.used_mask);
+}
+
+static irqreturn_t hisi_uncore_pmu_isr(int irq, void *data)
+{
+ struct hisi_pmu *hisi_pmu = data;
+ struct perf_event *event;
+ unsigned long overflown;
+ int idx;
+
+ overflown = hisi_pmu->ops->get_int_status(hisi_pmu);
+ if (!overflown)
+ return IRQ_NONE;
+
+ /*
+ * Find the counter index which overflowed if the bit was set
+ * and handle it.
+ */
+ for_each_set_bit(idx, &overflown, hisi_pmu->num_counters) {
+ /* Write 1 to clear the IRQ status flag */
+ hisi_pmu->ops->clear_int_status(hisi_pmu, idx);
+ /* Get the corresponding event struct */
+ event = hisi_pmu->pmu_events.hw_events[idx];
+ if (!event)
+ continue;
+
+ hisi_uncore_pmu_event_update(event);
+ hisi_uncore_pmu_set_event_period(event);
}
- clear_bit(idx, hisi_pmu->pmu_events.used_mask);
+ return IRQ_HANDLED;
+}
+
+int hisi_uncore_pmu_init_irq(struct hisi_pmu *hisi_pmu,
+ struct platform_device *pdev)
+{
+ int irq, ret;
+
+ irq = platform_get_irq(pdev, 0);
+ if (irq < 0)
+ return irq;
+
+ ret = devm_request_irq(&pdev->dev, irq, hisi_uncore_pmu_isr,
+ IRQF_NOBALANCING | IRQF_NO_THREAD,
+ dev_name(&pdev->dev), hisi_pmu);
+ if (ret < 0) {
+ dev_err(&pdev->dev,
+ "Fail to request IRQ: %d ret: %d.\n", irq, ret);
+ return ret;
+ }
+
+ hisi_pmu->irq = irq;
+
+ return 0;
}
+EXPORT_SYMBOL_GPL(hisi_uncore_pmu_init_irq);
int hisi_uncore_pmu_event_init(struct perf_event *event)
{
hisi_pmu->ops->write_evtype(hisi_pmu, hwc->idx,
HISI_GET_EVENTID(event));
+ if (hisi_pmu->ops->enable_filter)
+ hisi_pmu->ops->enable_filter(event);
+
hisi_pmu->ops->enable_counter_int(hisi_pmu, hwc);
hisi_pmu->ops->enable_counter(hisi_pmu, hwc);
}
hisi_pmu->ops->disable_counter(hisi_pmu, hwc);
hisi_pmu->ops->disable_counter_int(hisi_pmu, hwc);
+
+ if (hisi_pmu->ops->disable_filter)
+ hisi_pmu->ops->disable_filter(event);
}
void hisi_uncore_pmu_set_event_period(struct perf_event *event)
#ifndef __HISI_UNCORE_PMU_H__
#define __HISI_UNCORE_PMU_H__
+#include <linux/bitfield.h>
#include <linux/cpumask.h>
#include <linux/device.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/perf_event.h>
+#include <linux/platform_device.h>
#include <linux/types.h>
#undef pr_fmt
#define pr_fmt(fmt) "hisi_pmu: " fmt
+#define HISI_PMU_V2 0x30
#define HISI_MAX_COUNTERS 0x10
#define to_hisi_pmu(p) (container_of(p, struct hisi_pmu, pmu))
#define HISI_PMU_EVENT_ATTR(_name, _config) \
HISI_PMU_ATTR(_name, hisi_event_sysfs_show, (unsigned long)_config)
+#define HISI_PMU_EVENT_ATTR_EXTRACTOR(name, config, hi, lo) \
+ static inline u32 hisi_get_##name(struct perf_event *event) \
+ { \
+ return FIELD_GET(GENMASK_ULL(hi, lo), event->attr.config); \
+ }
+
struct hisi_pmu;
struct hisi_uncore_ops {
void (*disable_counter_int)(struct hisi_pmu *, struct hw_perf_event *);
void (*start_counters)(struct hisi_pmu *);
void (*stop_counters)(struct hisi_pmu *);
+ u32 (*get_int_status)(struct hisi_pmu *hisi_pmu);
+ void (*clear_int_status)(struct hisi_pmu *hisi_pmu, int idx);
+ void (*enable_filter)(struct perf_event *event);
+ void (*disable_filter)(struct perf_event *event);
};
struct hisi_pmu_hwevents {
struct perf_event *hw_events[HISI_MAX_COUNTERS];
DECLARE_BITMAP(used_mask, HISI_MAX_COUNTERS);
+ const struct attribute_group **attr_groups;
};
/* Generic pmu struct for different pmu types */
void __iomem *base;
/* the ID of the PMU modules */
u32 index_id;
+ /* For DDRC PMU v2: each DDRC has more than one DMC */
+ u32 sub_id;
int num_counters;
int counter_bits;
/* check event code range */
u32 identifier;
};
-int hisi_uncore_pmu_counter_valid(struct hisi_pmu *hisi_pmu, int idx);
int hisi_uncore_pmu_get_event_idx(struct perf_event *event);
void hisi_uncore_pmu_read(struct perf_event *event);
int hisi_uncore_pmu_add(struct perf_event *event, int flags);
ssize_t hisi_uncore_pmu_identifier_attr_show(struct device *dev,
struct device_attribute *attr,
char *page);
-
+int hisi_uncore_pmu_init_irq(struct hisi_pmu *hisi_pmu,
+ struct platform_device *pdev);
#endif /* __HISI_UNCORE_PMU_H__ */
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * HiSilicon SLLC uncore Hardware event counters support
+ *
+ * Copyright (C) 2020 Hisilicon Limited
+ * Author: Shaokun Zhang <zhangshaokun@hisilicon.com>
+ *
+ * This code is based on the uncore PMUs like arm-cci and arm-ccn.
+ */
+#include <linux/acpi.h>
+#include <linux/cpuhotplug.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/list.h>
+#include <linux/smp.h>
+
+#include "hisi_uncore_pmu.h"
+
+/* SLLC register definition */
+#define SLLC_INT_MASK 0x0814
+#define SLLC_INT_STATUS 0x0818
+#define SLLC_INT_CLEAR 0x081c
+#define SLLC_PERF_CTRL 0x1c00
+#define SLLC_SRCID_CTRL 0x1c04
+#define SLLC_TGTID_CTRL 0x1c08
+#define SLLC_EVENT_CTRL 0x1c14
+#define SLLC_EVENT_TYPE0 0x1c18
+#define SLLC_VERSION 0x1cf0
+#define SLLC_EVENT_CNT0_L 0x1d00
+
+#define SLLC_EVTYPE_MASK 0xff
+#define SLLC_PERF_CTRL_EN BIT(0)
+#define SLLC_FILT_EN BIT(1)
+#define SLLC_TRACETAG_EN BIT(2)
+#define SLLC_SRCID_EN BIT(4)
+#define SLLC_SRCID_NONE 0x0
+#define SLLC_TGTID_EN BIT(5)
+#define SLLC_TGTID_NONE 0x0
+#define SLLC_TGTID_MIN_SHIFT 1
+#define SLLC_TGTID_MAX_SHIFT 12
+#define SLLC_SRCID_CMD_SHIFT 1
+#define SLLC_SRCID_MSK_SHIFT 12
+#define SLLC_NR_EVENTS 0x80
+
+HISI_PMU_EVENT_ATTR_EXTRACTOR(tgtid_min, config1, 10, 0);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(tgtid_max, config1, 21, 11);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(srcid_cmd, config1, 32, 22);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(srcid_msk, config1, 43, 33);
+HISI_PMU_EVENT_ATTR_EXTRACTOR(tracetag_en, config1, 44, 44);
+
+static bool tgtid_is_valid(u32 max, u32 min)
+{
+ return max > 0 && max >= min;
+}
+
+static void hisi_sllc_pmu_enable_tracetag(struct perf_event *event)
+{
+ struct hisi_pmu *sllc_pmu = to_hisi_pmu(event->pmu);
+ u32 tt_en = hisi_get_tracetag_en(event);
+
+ if (tt_en) {
+ u32 val;
+
+ val = readl(sllc_pmu->base + SLLC_PERF_CTRL);
+ val |= SLLC_TRACETAG_EN | SLLC_FILT_EN;
+ writel(val, sllc_pmu->base + SLLC_PERF_CTRL);
+ }
+}
+
+static void hisi_sllc_pmu_disable_tracetag(struct perf_event *event)
+{
+ struct hisi_pmu *sllc_pmu = to_hisi_pmu(event->pmu);
+ u32 tt_en = hisi_get_tracetag_en(event);
+
+ if (tt_en) {
+ u32 val;
+
+ val = readl(sllc_pmu->base + SLLC_PERF_CTRL);
+ val &= ~(SLLC_TRACETAG_EN | SLLC_FILT_EN);
+ writel(val, sllc_pmu->base + SLLC_PERF_CTRL);
+ }
+}
+
+static void hisi_sllc_pmu_config_tgtid(struct perf_event *event)
+{
+ struct hisi_pmu *sllc_pmu = to_hisi_pmu(event->pmu);
+ u32 min = hisi_get_tgtid_min(event);
+ u32 max = hisi_get_tgtid_max(event);
+
+ if (tgtid_is_valid(max, min)) {
+ u32 val = (max << SLLC_TGTID_MAX_SHIFT) | (min << SLLC_TGTID_MIN_SHIFT);
+
+ writel(val, sllc_pmu->base + SLLC_TGTID_CTRL);
+ /* Enable the tgtid */
+ val = readl(sllc_pmu->base + SLLC_PERF_CTRL);
+ val |= SLLC_TGTID_EN | SLLC_FILT_EN;
+ writel(val, sllc_pmu->base + SLLC_PERF_CTRL);
+ }
+}
+
+static void hisi_sllc_pmu_clear_tgtid(struct perf_event *event)
+{
+ struct hisi_pmu *sllc_pmu = to_hisi_pmu(event->pmu);
+ u32 min = hisi_get_tgtid_min(event);
+ u32 max = hisi_get_tgtid_max(event);
+
+ if (tgtid_is_valid(max, min)) {
+ u32 val;
+
+ writel(SLLC_TGTID_NONE, sllc_pmu->base + SLLC_TGTID_CTRL);
+ /* Disable the tgtid */
+ val = readl(sllc_pmu->base + SLLC_PERF_CTRL);
+ val &= ~(SLLC_TGTID_EN | SLLC_FILT_EN);
+ writel(val, sllc_pmu->base + SLLC_PERF_CTRL);
+ }
+}
+
+static void hisi_sllc_pmu_config_srcid(struct perf_event *event)
+{
+ struct hisi_pmu *sllc_pmu = to_hisi_pmu(event->pmu);
+ u32 cmd = hisi_get_srcid_cmd(event);
+
+ if (cmd) {
+ u32 val, msk;
+
+ msk = hisi_get_srcid_msk(event);
+ val = (cmd << SLLC_SRCID_CMD_SHIFT) | (msk << SLLC_SRCID_MSK_SHIFT);
+ writel(val, sllc_pmu->base + SLLC_SRCID_CTRL);
+ /* Enable the srcid */
+ val = readl(sllc_pmu->base + SLLC_PERF_CTRL);
+ val |= SLLC_SRCID_EN | SLLC_FILT_EN;
+ writel(val, sllc_pmu->base + SLLC_PERF_CTRL);
+ }
+}
+
+static void hisi_sllc_pmu_clear_srcid(struct perf_event *event)
+{
+ struct hisi_pmu *sllc_pmu = to_hisi_pmu(event->pmu);
+ u32 cmd = hisi_get_srcid_cmd(event);
+
+ if (cmd) {
+ u32 val;
+
+ writel(SLLC_SRCID_NONE, sllc_pmu->base + SLLC_SRCID_CTRL);
+ /* Disable the srcid */
+ val = readl(sllc_pmu->base + SLLC_PERF_CTRL);
+ val &= ~(SLLC_SRCID_EN | SLLC_FILT_EN);
+ writel(val, sllc_pmu->base + SLLC_PERF_CTRL);
+ }
+}
+
+static void hisi_sllc_pmu_enable_filter(struct perf_event *event)
+{
+ if (event->attr.config1 != 0x0) {
+ hisi_sllc_pmu_enable_tracetag(event);
+ hisi_sllc_pmu_config_srcid(event);
+ hisi_sllc_pmu_config_tgtid(event);
+ }
+}
+
+static void hisi_sllc_pmu_clear_filter(struct perf_event *event)
+{
+ if (event->attr.config1 != 0x0) {
+ hisi_sllc_pmu_disable_tracetag(event);
+ hisi_sllc_pmu_clear_srcid(event);
+ hisi_sllc_pmu_clear_tgtid(event);
+ }
+}
+
+static u32 hisi_sllc_pmu_get_counter_offset(int idx)
+{
+ return (SLLC_EVENT_CNT0_L + idx * 8);
+}
+
+static u64 hisi_sllc_pmu_read_counter(struct hisi_pmu *sllc_pmu,
+ struct hw_perf_event *hwc)
+{
+ return readq(sllc_pmu->base +
+ hisi_sllc_pmu_get_counter_offset(hwc->idx));
+}
+
+static void hisi_sllc_pmu_write_counter(struct hisi_pmu *sllc_pmu,
+ struct hw_perf_event *hwc, u64 val)
+{
+ writeq(val, sllc_pmu->base +
+ hisi_sllc_pmu_get_counter_offset(hwc->idx));
+}
+
+static void hisi_sllc_pmu_write_evtype(struct hisi_pmu *sllc_pmu, int idx,
+ u32 type)
+{
+ u32 reg, reg_idx, shift, val;
+
+ /*
+ * Select the appropriate event select register(SLLC_EVENT_TYPE0/1).
+ * There are 2 event select registers for the 8 hardware counters.
+ * Event code is 8-bits and for the former 4 hardware counters,
+ * SLLC_EVENT_TYPE0 is chosen. For the latter 4 hardware counters,
+ * SLLC_EVENT_TYPE1 is chosen.
+ */
+ reg = SLLC_EVENT_TYPE0 + (idx / 4) * 4;
+ reg_idx = idx % 4;
+ shift = 8 * reg_idx;
+
+ /* Write event code to SLLC_EVENT_TYPEx Register */
+ val = readl(sllc_pmu->base + reg);
+ val &= ~(SLLC_EVTYPE_MASK << shift);
+ val |= (type << shift);
+ writel(val, sllc_pmu->base + reg);
+}
+
+static void hisi_sllc_pmu_start_counters(struct hisi_pmu *sllc_pmu)
+{
+ u32 val;
+
+ val = readl(sllc_pmu->base + SLLC_PERF_CTRL);
+ val |= SLLC_PERF_CTRL_EN;
+ writel(val, sllc_pmu->base + SLLC_PERF_CTRL);
+}
+
+static void hisi_sllc_pmu_stop_counters(struct hisi_pmu *sllc_pmu)
+{
+ u32 val;
+
+ val = readl(sllc_pmu->base + SLLC_PERF_CTRL);
+ val &= ~(SLLC_PERF_CTRL_EN);
+ writel(val, sllc_pmu->base + SLLC_PERF_CTRL);
+}
+
+static void hisi_sllc_pmu_enable_counter(struct hisi_pmu *sllc_pmu,
+ struct hw_perf_event *hwc)
+{
+ u32 val;
+
+ val = readl(sllc_pmu->base + SLLC_EVENT_CTRL);
+ val |= 1 << hwc->idx;
+ writel(val, sllc_pmu->base + SLLC_EVENT_CTRL);
+}
+
+static void hisi_sllc_pmu_disable_counter(struct hisi_pmu *sllc_pmu,
+ struct hw_perf_event *hwc)
+{
+ u32 val;
+
+ val = readl(sllc_pmu->base + SLLC_EVENT_CTRL);
+ val &= ~(1 << hwc->idx);
+ writel(val, sllc_pmu->base + SLLC_EVENT_CTRL);
+}
+
+static void hisi_sllc_pmu_enable_counter_int(struct hisi_pmu *sllc_pmu,
+ struct hw_perf_event *hwc)
+{
+ u32 val;
+
+ val = readl(sllc_pmu->base + SLLC_INT_MASK);
+ /* Write 0 to enable interrupt */
+ val &= ~(1 << hwc->idx);
+ writel(val, sllc_pmu->base + SLLC_INT_MASK);
+}
+
+static void hisi_sllc_pmu_disable_counter_int(struct hisi_pmu *sllc_pmu,
+ struct hw_perf_event *hwc)
+{
+ u32 val;
+
+ val = readl(sllc_pmu->base + SLLC_INT_MASK);
+ /* Write 1 to mask interrupt */
+ val |= 1 << hwc->idx;
+ writel(val, sllc_pmu->base + SLLC_INT_MASK);
+}
+
+static u32 hisi_sllc_pmu_get_int_status(struct hisi_pmu *sllc_pmu)
+{
+ return readl(sllc_pmu->base + SLLC_INT_STATUS);
+}
+
+static void hisi_sllc_pmu_clear_int_status(struct hisi_pmu *sllc_pmu, int idx)
+{
+ writel(1 << idx, sllc_pmu->base + SLLC_INT_CLEAR);
+}
+
+static const struct acpi_device_id hisi_sllc_pmu_acpi_match[] = {
+ { "HISI0263", },
+ {}
+};
+MODULE_DEVICE_TABLE(acpi, hisi_sllc_pmu_acpi_match);
+
+static int hisi_sllc_pmu_init_data(struct platform_device *pdev,
+ struct hisi_pmu *sllc_pmu)
+{
+ /*
+ * Use the SCCL_ID and the index ID to identify the SLLC PMU,
+ * while SCCL_ID is from MPIDR_EL1 by CPU.
+ */
+ if (device_property_read_u32(&pdev->dev, "hisilicon,scl-id",
+ &sllc_pmu->sccl_id)) {
+ dev_err(&pdev->dev, "Cannot read sccl-id!\n");
+ return -EINVAL;
+ }
+
+ if (device_property_read_u32(&pdev->dev, "hisilicon,idx-id",
+ &sllc_pmu->index_id)) {
+ dev_err(&pdev->dev, "Cannot read idx-id!\n");
+ return -EINVAL;
+ }
+
+ /* SLLC PMUs only share the same SCCL */
+ sllc_pmu->ccl_id = -1;
+
+ sllc_pmu->base = devm_platform_ioremap_resource(pdev, 0);
+ if (IS_ERR(sllc_pmu->base)) {
+ dev_err(&pdev->dev, "ioremap failed for sllc_pmu resource.\n");
+ return PTR_ERR(sllc_pmu->base);
+ }
+
+ sllc_pmu->identifier = readl(sllc_pmu->base + SLLC_VERSION);
+
+ return 0;
+}
+
+static struct attribute *hisi_sllc_pmu_v2_format_attr[] = {
+ HISI_PMU_FORMAT_ATTR(event, "config:0-7"),
+ HISI_PMU_FORMAT_ATTR(tgtid_min, "config1:0-10"),
+ HISI_PMU_FORMAT_ATTR(tgtid_max, "config1:11-21"),
+ HISI_PMU_FORMAT_ATTR(srcid_cmd, "config1:22-32"),
+ HISI_PMU_FORMAT_ATTR(srcid_msk, "config1:33-43"),
+ HISI_PMU_FORMAT_ATTR(tracetag_en, "config1:44"),
+ NULL
+};
+
+static const struct attribute_group hisi_sllc_pmu_v2_format_group = {
+ .name = "format",
+ .attrs = hisi_sllc_pmu_v2_format_attr,
+};
+
+static struct attribute *hisi_sllc_pmu_v2_events_attr[] = {
+ HISI_PMU_EVENT_ATTR(rx_req, 0x30),
+ HISI_PMU_EVENT_ATTR(rx_data, 0x31),
+ HISI_PMU_EVENT_ATTR(tx_req, 0x34),
+ HISI_PMU_EVENT_ATTR(tx_data, 0x35),
+ HISI_PMU_EVENT_ATTR(cycles, 0x09),
+ NULL
+};
+
+static const struct attribute_group hisi_sllc_pmu_v2_events_group = {
+ .name = "events",
+ .attrs = hisi_sllc_pmu_v2_events_attr,
+};
+
+static DEVICE_ATTR(cpumask, 0444, hisi_cpumask_sysfs_show, NULL);
+
+static struct attribute *hisi_sllc_pmu_cpumask_attrs[] = {
+ &dev_attr_cpumask.attr,
+ NULL
+};
+
+static const struct attribute_group hisi_sllc_pmu_cpumask_attr_group = {
+ .attrs = hisi_sllc_pmu_cpumask_attrs,
+};
+
+static struct device_attribute hisi_sllc_pmu_identifier_attr =
+ __ATTR(identifier, 0444, hisi_uncore_pmu_identifier_attr_show, NULL);
+
+static struct attribute *hisi_sllc_pmu_identifier_attrs[] = {
+ &hisi_sllc_pmu_identifier_attr.attr,
+ NULL
+};
+
+static struct attribute_group hisi_sllc_pmu_identifier_group = {
+ .attrs = hisi_sllc_pmu_identifier_attrs,
+};
+
+static const struct attribute_group *hisi_sllc_pmu_v2_attr_groups[] = {
+ &hisi_sllc_pmu_v2_format_group,
+ &hisi_sllc_pmu_v2_events_group,
+ &hisi_sllc_pmu_cpumask_attr_group,
+ &hisi_sllc_pmu_identifier_group,
+ NULL
+};
+
+static const struct hisi_uncore_ops hisi_uncore_sllc_ops = {
+ .write_evtype = hisi_sllc_pmu_write_evtype,
+ .get_event_idx = hisi_uncore_pmu_get_event_idx,
+ .start_counters = hisi_sllc_pmu_start_counters,
+ .stop_counters = hisi_sllc_pmu_stop_counters,
+ .enable_counter = hisi_sllc_pmu_enable_counter,
+ .disable_counter = hisi_sllc_pmu_disable_counter,
+ .enable_counter_int = hisi_sllc_pmu_enable_counter_int,
+ .disable_counter_int = hisi_sllc_pmu_disable_counter_int,
+ .write_counter = hisi_sllc_pmu_write_counter,
+ .read_counter = hisi_sllc_pmu_read_counter,
+ .get_int_status = hisi_sllc_pmu_get_int_status,
+ .clear_int_status = hisi_sllc_pmu_clear_int_status,
+ .enable_filter = hisi_sllc_pmu_enable_filter,
+ .disable_filter = hisi_sllc_pmu_clear_filter,
+};
+
+static int hisi_sllc_pmu_dev_probe(struct platform_device *pdev,
+ struct hisi_pmu *sllc_pmu)
+{
+ int ret;
+
+ ret = hisi_sllc_pmu_init_data(pdev, sllc_pmu);
+ if (ret)
+ return ret;
+
+ ret = hisi_uncore_pmu_init_irq(sllc_pmu, pdev);
+ if (ret)
+ return ret;
+
+ sllc_pmu->pmu_events.attr_groups = hisi_sllc_pmu_v2_attr_groups;
+ sllc_pmu->ops = &hisi_uncore_sllc_ops;
+ sllc_pmu->check_event = SLLC_NR_EVENTS;
+ sllc_pmu->counter_bits = 64;
+ sllc_pmu->num_counters = 8;
+ sllc_pmu->dev = &pdev->dev;
+ sllc_pmu->on_cpu = -1;
+
+ return 0;
+}
+
+static int hisi_sllc_pmu_probe(struct platform_device *pdev)
+{
+ struct hisi_pmu *sllc_pmu;
+ char *name;
+ int ret;
+
+ sllc_pmu = devm_kzalloc(&pdev->dev, sizeof(*sllc_pmu), GFP_KERNEL);
+ if (!sllc_pmu)
+ return -ENOMEM;
+
+ ret = hisi_sllc_pmu_dev_probe(pdev, sllc_pmu);
+ if (ret)
+ return ret;
+
+ name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_sllc%u",
+ sllc_pmu->sccl_id, sllc_pmu->index_id);
+ if (!name)
+ return -ENOMEM;
+
+ ret = cpuhp_state_add_instance(CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE,
+ &sllc_pmu->node);
+ if (ret) {
+ dev_err(&pdev->dev, "Error %d registering hotplug\n", ret);
+ return ret;
+ }
+
+ sllc_pmu->pmu = (struct pmu) {
+ .module = THIS_MODULE,
+ .task_ctx_nr = perf_invalid_context,
+ .event_init = hisi_uncore_pmu_event_init,
+ .pmu_enable = hisi_uncore_pmu_enable,
+ .pmu_disable = hisi_uncore_pmu_disable,
+ .add = hisi_uncore_pmu_add,
+ .del = hisi_uncore_pmu_del,
+ .start = hisi_uncore_pmu_start,
+ .stop = hisi_uncore_pmu_stop,
+ .read = hisi_uncore_pmu_read,
+ .attr_groups = sllc_pmu->pmu_events.attr_groups,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
+ };
+
+ ret = perf_pmu_register(&sllc_pmu->pmu, name, -1);
+ if (ret) {
+ dev_err(sllc_pmu->dev, "PMU register failed, ret = %d\n", ret);
+ cpuhp_state_remove_instance(CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE,
+ &sllc_pmu->node);
+ irq_set_affinity_hint(sllc_pmu->irq, NULL);
+ return ret;
+ }
+
+ platform_set_drvdata(pdev, sllc_pmu);
+
+ return ret;
+}
+
+static int hisi_sllc_pmu_remove(struct platform_device *pdev)
+{
+ struct hisi_pmu *sllc_pmu = platform_get_drvdata(pdev);
+
+ perf_pmu_unregister(&sllc_pmu->pmu);
+ cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE,
+ &sllc_pmu->node);
+ irq_set_affinity_hint(sllc_pmu->irq, NULL);
+
+ return 0;
+}
+
+static struct platform_driver hisi_sllc_pmu_driver = {
+ .driver = {
+ .name = "hisi_sllc_pmu",
+ .acpi_match_table = hisi_sllc_pmu_acpi_match,
+ .suppress_bind_attrs = true,
+ },
+ .probe = hisi_sllc_pmu_probe,
+ .remove = hisi_sllc_pmu_remove,
+};
+
+static int __init hisi_sllc_pmu_module_init(void)
+{
+ int ret;
+
+ ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE,
+ "AP_PERF_ARM_HISI_SLLC_ONLINE",
+ hisi_uncore_pmu_online_cpu,
+ hisi_uncore_pmu_offline_cpu);
+ if (ret) {
+ pr_err("SLLC PMU: cpuhp state setup failed, ret = %d\n", ret);
+ return ret;
+ }
+
+ ret = platform_driver_register(&hisi_sllc_pmu_driver);
+ if (ret)
+ cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE);
+
+ return ret;
+}
+module_init(hisi_sllc_pmu_module_init);
+
+static void __exit hisi_sllc_pmu_module_exit(void)
+{
+ platform_driver_unregister(&hisi_sllc_pmu_driver);
+ cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE);
+}
+module_exit(hisi_sllc_pmu_module_exit);
+
+MODULE_DESCRIPTION("HiSilicon SLLC uncore PMU driver");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Shaokun Zhang <zhangshaokun@hisilicon.com>");
+MODULE_AUTHOR("Qi Liu <liuqi115@huawei.com>");
struct perf_pmu_events_attr *pmu_attr;
pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
- return sprintf(page, "event=0x%02llx\n", pmu_attr->id);
+ return sysfs_emit(page, "event=0x%02llx\n", pmu_attr->id);
}
#define L2CACHE_EVENT_ATTR(_name, _id) \
struct dev_ext_attribute *eattr;
eattr = container_of(attr, struct dev_ext_attribute, attr);
- return sprintf(buf, "%s\n", (char *) eattr->var);
+ return sysfs_emit(buf, "%s\n", (char *) eattr->var);
}
#define L3CACHE_PMU_FORMAT_ATTR(_name, _config) \
struct perf_pmu_events_attr *pmu_attr;
pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
- return sprintf(page, "event=0x%02llx\n", pmu_attr->id);
+ return sysfs_emit(page, "event=0x%02llx\n", pmu_attr->id);
}
#define L3CACHE_EVENT_ATTR(_name, _id) \
char *page) \
{ \
BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \
- return sprintf(page, _format "\n"); \
+ return sysfs_emit(page, _format "\n"); \
} \
\
static struct device_attribute format_attr_##_var = \
struct dev_ext_attribute *eattr;
eattr = container_of(attr, struct dev_ext_attribute, attr);
- return sprintf(buf, "event=0x%lx\n", (unsigned long) eattr->var);
+ return sysfs_emit(buf, "event=0x%lx\n", (unsigned long) eattr->var);
}
#define TX2_EVENT_ATTR(name, config) \
struct dev_ext_attribute *eattr;
eattr = container_of(attr, struct dev_ext_attribute, attr);
- return sprintf(buf, "%s\n", (char *) eattr->var);
+ return sysfs_emit(buf, "%s\n", (char *) eattr->var);
}
#define XGENE_PMU_FORMAT_ATTR(_name, _config) \
struct dev_ext_attribute *eattr;
eattr = container_of(attr, struct dev_ext_attribute, attr);
- return sprintf(buf, "config=0x%lx\n", (unsigned long) eattr->var);
+ return sysfs_emit(buf, "config=0x%lx\n", (unsigned long) eattr->var);
}
#define XGENE_PMU_EVENT_ATTR(_name, _config) \
unsigned i, pin;
#ifdef CONFIG_GPIOLIB
struct pinctrl_gpio_range *range;
- unsigned int gpio_num;
struct gpio_chip *chip;
+ int gpio_num;
#endif
seq_printf(s, "registered pins: %d\n", pctldev->desc->npins);
seq_printf(s, "pin %d (%s) ", pin, desc->name);
#ifdef CONFIG_GPIOLIB
- gpio_num = 0;
+ gpio_num = -1;
list_for_each_entry(range, &pctldev->gpio_ranges, node) {
if ((pin >= range->pin_base) &&
(pin < (range->pin_base + range->npins))) {
break;
}
}
- chip = gpio_to_chip(gpio_num);
- if (chip && chip->gpiodev && chip->gpiodev->base)
- seq_printf(s, "%u:%s ", gpio_num -
- chip->gpiodev->base, chip->label);
+ if (gpio_num >= 0)
+ chip = gpio_to_chip(gpio_num);
+ else
+ chip = NULL;
+ if (chip)
+ seq_printf(s, "%u:%s ", gpio_num - chip->gpiodev->base, chip->label);
else
seq_puts(s, "0:? ");
#endif
gpps[i].gpio_base = 0;
break;
case INTEL_GPIO_BASE_NOMAP:
+ break;
default:
break;
}
gpps[i].size = min(gpp_size, npins);
npins -= gpps[i].size;
+ gpps[i].gpio_base = gpps[i].base;
gpps[i].padown_num = padown_num;
/*
if (IS_ERR(regs))
return PTR_ERR(regs);
- /* Determine community features based on the revision */
+ /*
+ * Determine community features based on the revision.
+ * A value of all ones means the device is not present.
+ */
value = readl(regs + REVID);
+ if (value == ~0u)
+ return -ENODEV;
if (((value & REVID_MASK) >> REVID_SHIFT) >= 0x94) {
community->features |= PINCTRL_FEATURE_DEBOUNCE;
community->features |= PINCTRL_FEATURE_1K_PD;
static const struct intel_community lbg_communities[] = {
LBG_COMMUNITY(0, 0, 71),
LBG_COMMUNITY(1, 72, 132),
- LBG_COMMUNITY(3, 133, 144),
- LBG_COMMUNITY(4, 145, 180),
- LBG_COMMUNITY(5, 181, 246),
+ LBG_COMMUNITY(3, 133, 143),
+ LBG_COMMUNITY(4, 144, 178),
+ LBG_COMMUNITY(5, 179, 246),
};
static const struct intel_pinctrl_soc_data lbg_soc_data = {
/* Type value spread over 2 registers sets: low, high bit */
sgpio_clrsetbits(bank->priv, REG_INT_TRIGGER, addr.bit,
BIT(addr.port), (!!(type & 0x1)) << addr.port);
- sgpio_clrsetbits(bank->priv, REG_INT_TRIGGER + SGPIO_MAX_BITS, addr.bit,
+ sgpio_clrsetbits(bank->priv, REG_INT_TRIGGER, SGPIO_MAX_BITS + addr.bit,
BIT(addr.port), (!!(type & 0x2)) << addr.port);
if (type == SGPIO_INT_TRG_LEVEL)
static int __maybe_unused rockchip_pinctrl_resume(struct device *dev)
{
struct rockchip_pinctrl *info = dev_get_drvdata(dev);
- int ret = regmap_write(info->regmap_base, RK3288_GRF_GPIO6C_IOMUX,
- rk3288_grf_gpio6c_iomux |
- GPIO6C6_SEL_WRITE_ENABLE);
+ int ret;
- if (ret)
- return ret;
+ if (info->ctrl->type == RK3288) {
+ ret = regmap_write(info->regmap_base, RK3288_GRF_GPIO6C_IOMUX,
+ rk3288_grf_gpio6c_iomux |
+ GPIO6C6_SEL_WRITE_ENABLE);
+ if (ret)
+ return ret;
+ }
return pinctrl_force_default(info->pctl_dev);
}
unsigned long *configs, unsigned int nconfs)
{
struct lpi_pinctrl *pctrl = dev_get_drvdata(pctldev->dev);
- unsigned int param, arg, pullup, strength;
+ unsigned int param, arg, pullup = LPI_GPIO_BIAS_DISABLE, strength = 2;
bool value, output_enabled = false;
const struct lpi_pingroup *g;
unsigned long sval;
[172] = PINGROUP(172, qdss, _, _, _, _, _, _, _, _),
[173] = PINGROUP(173, qdss, _, _, _, _, _, _, _, _),
[174] = PINGROUP(174, qdss, _, _, _, _, _, _, _, _),
- [175] = UFS_RESET(ufs_reset, 0x1be000),
- [176] = SDC_QDSD_PINGROUP(sdc1_rclk, 0x1b3000, 15, 0),
- [177] = SDC_QDSD_PINGROUP(sdc1_clk, 0x1b3000, 13, 6),
- [178] = SDC_QDSD_PINGROUP(sdc1_cmd, 0x1b3000, 11, 3),
- [179] = SDC_QDSD_PINGROUP(sdc1_data, 0x1b3000, 9, 0),
- [180] = SDC_QDSD_PINGROUP(sdc2_clk, 0x1b4000, 14, 6),
- [181] = SDC_QDSD_PINGROUP(sdc2_cmd, 0x1b4000, 11, 3),
- [182] = SDC_QDSD_PINGROUP(sdc2_data, 0x1b4000, 9, 0),
+ [175] = UFS_RESET(ufs_reset, 0xbe000),
+ [176] = SDC_QDSD_PINGROUP(sdc1_rclk, 0xb3004, 0, 6),
+ [177] = SDC_QDSD_PINGROUP(sdc1_clk, 0xb3000, 13, 6),
+ [178] = SDC_QDSD_PINGROUP(sdc1_cmd, 0xb3000, 11, 3),
+ [179] = SDC_QDSD_PINGROUP(sdc1_data, 0xb3000, 9, 0),
+ [180] = SDC_QDSD_PINGROUP(sdc2_clk, 0xb4000, 14, 6),
+ [181] = SDC_QDSD_PINGROUP(sdc2_cmd, 0xb4000, 11, 3),
+ [182] = SDC_QDSD_PINGROUP(sdc2_data, 0xb4000, 9, 0),
};
static const struct msm_pinctrl_soc_data sc7280_pinctrl = {
static const char * const qdss_stm_groups[] = {
"gpio0", "gpio1", "gpio2", "gpio3", "gpio4", "gpio5", "gpio6", "gpio7", "gpio12", "gpio13",
- "gpio14", "gpio15", "gpio16", "gpio17", "gpio18", "gpio19" "gpio20", "gpio21", "gpio22",
+ "gpio14", "gpio15", "gpio16", "gpio17", "gpio18", "gpio19", "gpio20", "gpio21", "gpio22",
"gpio23", "gpio44", "gpio45", "gpio52", "gpio53", "gpio56", "gpio57", "gpio61", "gpio62",
"gpio63", "gpio64", "gpio65", "gpio66",
};
depends on PCI
help
The Intel Platform Controller Hub for Intel Core SoCs provides access
- to Power Management Controller registers via a PCI interface. This
+ to Power Management Controller registers via various interfaces. This
driver can utilize debugging capabilities and supported features as
- exposed by the Power Management Controller.
+ exposed by the Power Management Controller. It also may perform some
+ tasks in the PMC in order to enable transition into the SLPS0 state.
+ It should be selected on all Intel platforms supported by the driver.
Supported features:
- SLP_S0_RESIDENCY counter
- PCH IP Power Gating status
- - LTR Ignore
+ - LTR Ignore / LTR Show
- MPHY/PLL gating status (Sunrisepoint PCH only)
+ - SLPS0 Debug registers (Cannonlake/Icelake PCH)
+ - Low Power Mode registers (Tigerlake and beyond)
+ - PMC quirks as needed to enable SLPS0/S0ix
config INTEL_PMT_CLASS
tristate
sysfs_remove_group(wmi_priv.enumeration_data[instance_id].attr_name_kobj,
&enumeration_attr_group);
}
+ wmi_priv.enumeration_instances_count = 0;
+
kfree(wmi_priv.enumeration_data);
+ wmi_priv.enumeration_data = NULL;
}
sysfs_remove_group(wmi_priv.integer_data[instance_id].attr_name_kobj,
&integer_attr_group);
}
+ wmi_priv.integer_instances_count = 0;
+
kfree(wmi_priv.integer_data);
+ wmi_priv.integer_data = NULL;
}
sysfs_remove_group(wmi_priv.po_data[instance_id].attr_name_kobj,
&po_attr_group);
}
+ wmi_priv.po_instances_count = 0;
+
kfree(wmi_priv.po_data);
+ wmi_priv.po_data = NULL;
}
sysfs_remove_group(wmi_priv.str_data[instance_id].attr_name_kobj,
&str_attr_group);
}
+ wmi_priv.str_instances_count = 0;
+
kfree(wmi_priv.str_data);
+ wmi_priv.str_data = NULL;
}
*/
static int create_attributes_level_sysfs_files(void)
{
- int ret = sysfs_create_file(&wmi_priv.main_dir_kset->kobj, &reset_bios.attr);
+ int ret;
- if (ret) {
- pr_debug("could not create reset_bios file\n");
+ ret = sysfs_create_file(&wmi_priv.main_dir_kset->kobj, &reset_bios.attr);
+ if (ret)
return ret;
- }
ret = sysfs_create_file(&wmi_priv.main_dir_kset->kobj, &pending_reboot.attr);
- if (ret) {
- pr_debug("could not create changing_pending_reboot file\n");
- sysfs_remove_file(&wmi_priv.main_dir_kset->kobj, &reset_bios.attr);
- }
- return ret;
-}
+ if (ret)
+ return ret;
-static void release_reset_bios_data(void)
-{
- sysfs_remove_file(&wmi_priv.main_dir_kset->kobj, &reset_bios.attr);
- sysfs_remove_file(&wmi_priv.main_dir_kset->kobj, &pending_reboot.attr);
+ return 0;
}
static ssize_t wmi_sysman_attr_show(struct kobject *kobj, struct attribute *attr,
*/
static void release_attributes_data(void)
{
- release_reset_bios_data();
-
mutex_lock(&wmi_priv.mutex);
exit_enum_attributes();
exit_int_attributes();
wmi_priv.authentication_dir_kset = NULL;
}
if (wmi_priv.main_dir_kset) {
+ sysfs_remove_file(&wmi_priv.main_dir_kset->kobj, &reset_bios.attr);
+ sysfs_remove_file(&wmi_priv.main_dir_kset->kobj, &pending_reboot.attr);
destroy_attribute_objs(wmi_priv.main_dir_kset);
kset_unregister(wmi_priv.main_dir_kset);
+ wmi_priv.main_dir_kset = NULL;
}
mutex_unlock(&wmi_priv.mutex);
-
}
/**
err_attr_init:
mutex_unlock(&wmi_priv.mutex);
- release_attributes_data();
kfree(obj);
return retval;
}
}
ret = init_bios_attr_set_interface();
- if (ret || !wmi_priv.bios_attr_wdev) {
- pr_debug("failed to initialize set interface\n");
- goto fail_set_interface;
- }
+ if (ret)
+ return ret;
ret = init_bios_attr_pass_interface();
- if (ret || !wmi_priv.password_attr_wdev) {
- pr_debug("failed to initialize pass interface\n");
- goto fail_pass_interface;
+ if (ret)
+ goto err_exit_bios_attr_set_interface;
+
+ if (!wmi_priv.bios_attr_wdev || !wmi_priv.password_attr_wdev) {
+ pr_debug("failed to find set or pass interface\n");
+ ret = -ENODEV;
+ goto err_exit_bios_attr_pass_interface;
}
ret = class_register(&firmware_attributes_class);
if (ret)
- goto fail_class;
+ goto err_exit_bios_attr_pass_interface;
wmi_priv.class_dev = device_create(&firmware_attributes_class, NULL, MKDEV(0, 0),
NULL, "%s", DRIVER_NAME);
if (IS_ERR(wmi_priv.class_dev)) {
ret = PTR_ERR(wmi_priv.class_dev);
- goto fail_classdev;
+ goto err_unregister_class;
}
wmi_priv.main_dir_kset = kset_create_and_add("attributes", NULL,
&wmi_priv.class_dev->kobj);
if (!wmi_priv.main_dir_kset) {
ret = -ENOMEM;
- goto fail_main_kset;
+ goto err_destroy_classdev;
}
wmi_priv.authentication_dir_kset = kset_create_and_add("authentication", NULL,
&wmi_priv.class_dev->kobj);
if (!wmi_priv.authentication_dir_kset) {
ret = -ENOMEM;
- goto fail_authentication_kset;
+ goto err_release_attributes_data;
}
ret = create_attributes_level_sysfs_files();
if (ret) {
pr_debug("could not create reset BIOS attribute\n");
- goto fail_reset_bios;
+ goto err_release_attributes_data;
}
ret = init_bios_attributes(ENUM, DELL_WMI_BIOS_ENUMERATION_ATTRIBUTE_GUID);
if (ret) {
pr_debug("failed to populate enumeration type attributes\n");
- goto fail_create_group;
+ goto err_release_attributes_data;
}
ret = init_bios_attributes(INT, DELL_WMI_BIOS_INTEGER_ATTRIBUTE_GUID);
if (ret) {
pr_debug("failed to populate integer type attributes\n");
- goto fail_create_group;
+ goto err_release_attributes_data;
}
ret = init_bios_attributes(STR, DELL_WMI_BIOS_STRING_ATTRIBUTE_GUID);
if (ret) {
pr_debug("failed to populate string type attributes\n");
- goto fail_create_group;
+ goto err_release_attributes_data;
}
ret = init_bios_attributes(PO, DELL_WMI_BIOS_PASSOBJ_ATTRIBUTE_GUID);
if (ret) {
pr_debug("failed to populate pass object type attributes\n");
- goto fail_create_group;
+ goto err_release_attributes_data;
}
return 0;
-fail_create_group:
+err_release_attributes_data:
release_attributes_data();
-fail_reset_bios:
- if (wmi_priv.authentication_dir_kset) {
- kset_unregister(wmi_priv.authentication_dir_kset);
- wmi_priv.authentication_dir_kset = NULL;
- }
-
-fail_authentication_kset:
- if (wmi_priv.main_dir_kset) {
- kset_unregister(wmi_priv.main_dir_kset);
- wmi_priv.main_dir_kset = NULL;
- }
-
-fail_main_kset:
+err_destroy_classdev:
device_destroy(&firmware_attributes_class, MKDEV(0, 0));
-fail_classdev:
+err_unregister_class:
class_unregister(&firmware_attributes_class);
-fail_class:
+err_exit_bios_attr_pass_interface:
exit_bios_attr_pass_interface();
-fail_pass_interface:
+err_exit_bios_attr_set_interface:
exit_bios_attr_set_interface();
-fail_set_interface:
return ret;
}
DMI_MATCH(DMI_PRODUCT_NAME, "HP Spectre x2 Detachable"),
},
},
+ {
+ .ident = "Lenovo ThinkPad X1 Tablet Gen 2",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_FAMILY, "ThinkPad X1 Tablet Gen 2"),
+ },
+ },
{ }
};
goto wakeup;
/*
- * Switch events will wake the device and report the new switch
- * position to the input subsystem.
+ * Some devices send (duplicate) tablet-mode events when moved
+ * around even though the mode has not changed; and they do this
+ * even when suspended.
+ * Update the switch state in case it changed and then return
+ * without waking up to avoid spurious wakeups.
*/
- if (priv->switches && (event == 0xcc || event == 0xcd))
- goto wakeup;
+ if (event == 0xcc || event == 0xcd) {
+ report_tablet_mode_event(priv->switches, event);
+ return;
+ }
/* Wake up on 5-button array events only. */
if (event == 0xc0 || !priv->array)
wakeup:
pm_wakeup_hard_event(&device->dev);
- if (report_tablet_mode_event(priv->switches, event))
- return;
-
return;
}
};
static const struct key_entry intel_vbtn_switchmap[] = {
- { KE_SW, 0xCA, { .sw = { SW_DOCK, 1 } } }, /* Docked */
- { KE_SW, 0xCB, { .sw = { SW_DOCK, 0 } } }, /* Undocked */
+ /*
+ * SW_DOCK should only be reported for docking stations, but DSDTs using the
+ * intel-vbtn code, always seem to use this for 2-in-1s / convertibles and set
+ * SW_DOCK=1 when in laptop-mode (in tandem with setting SW_TABLET_MODE=0).
+ * This causes userspace to think the laptop is docked to a port-replicator
+ * and to disable suspend-on-lid-close, which is undesirable.
+ * Map the dock events to KEY_IGNORE to avoid this broken SW_DOCK reporting.
+ */
+ { KE_IGNORE, 0xCA, { .sw = { SW_DOCK, 1 } } }, /* Docked */
+ { KE_IGNORE, 0xCB, { .sw = { SW_DOCK, 0 } } }, /* Undocked */
{ KE_SW, 0xCC, { .sw = { SW_TABLET_MODE, 1 } } }, /* Tablet */
{ KE_SW, 0xCD, { .sw = { SW_TABLET_MODE, 0 } } }, /* Laptop */
{ KE_END }
}
DEFINE_SHOW_ATTRIBUTE(pmc_core_pll);
-static ssize_t pmc_core_ltr_ignore_write(struct file *file,
- const char __user *userbuf,
- size_t count, loff_t *ppos)
+static int pmc_core_send_ltr_ignore(u32 value)
{
struct pmc_dev *pmcdev = &pmc;
const struct pmc_reg_map *map = pmcdev->map;
- u32 val, buf_size, fd;
- int err;
-
- buf_size = count < 64 ? count : 64;
-
- err = kstrtou32_from_user(userbuf, buf_size, 10, &val);
- if (err)
- return err;
+ u32 reg;
+ int err = 0;
mutex_lock(&pmcdev->lock);
- if (val > map->ltr_ignore_max) {
+ if (value > map->ltr_ignore_max) {
err = -EINVAL;
goto out_unlock;
}
- fd = pmc_core_reg_read(pmcdev, map->ltr_ignore_offset);
- fd |= (1U << val);
- pmc_core_reg_write(pmcdev, map->ltr_ignore_offset, fd);
+ reg = pmc_core_reg_read(pmcdev, map->ltr_ignore_offset);
+ reg |= BIT(value);
+ pmc_core_reg_write(pmcdev, map->ltr_ignore_offset, reg);
out_unlock:
mutex_unlock(&pmcdev->lock);
+
+ return err;
+}
+
+static ssize_t pmc_core_ltr_ignore_write(struct file *file,
+ const char __user *userbuf,
+ size_t count, loff_t *ppos)
+{
+ u32 buf_size, value;
+ int err;
+
+ buf_size = min_t(u32, count, 64);
+
+ err = kstrtou32_from_user(userbuf, buf_size, 10, &value);
+ if (err)
+ return err;
+
+ err = pmc_core_send_ltr_ignore(value);
+
return err == 0 ? count : err;
}
pmcdev->pmc_xram_read_bit = pmc_core_check_read_lock_bit();
dmi_check_system(pmc_core_dmi_table);
+ /*
+ * On TGL, due to a hardware limitation, the GBE LTR blocks PC10 when
+ * a cable is attached. Tell the PMC to ignore it.
+ */
+ if (pmcdev->map == &tgl_reg_map) {
+ dev_dbg(&pdev->dev, "ignoring GBE LTR\n");
+ pmc_core_send_ltr_ignore(3);
+ }
+
pmc_core_dbgfs_register(pmcdev);
device_initialized = true;
struct intel_pmt_namespace *ns,
struct device *parent)
{
- struct resource res;
+ struct resource res = {0};
struct device *dev;
int ret;
#define CRASH_TYPE_OOBMSM 1
/* Control Flags */
-#define CRASHLOG_FLAG_DISABLE BIT(27)
+#define CRASHLOG_FLAG_DISABLE BIT(28)
/*
- * Bits 28 and 29 control the state of bit 31.
+ * Bits 29 and 30 control the state of bit 31.
*
- * Bit 28 will clear bit 31, if set, allowing a new crashlog to be captured.
- * Bit 29 will immediately trigger a crashlog to be generated, setting bit 31.
- * Bit 30 is read-only and reserved as 0.
+ * Bit 29 will clear bit 31, if set, allowing a new crashlog to be captured.
+ * Bit 30 will immediately trigger a crashlog to be generated, setting bit 31.
* Bit 31 is the read-only status with a 1 indicating log is complete.
*/
-#define CRASHLOG_FLAG_TRIGGER_CLEAR BIT(28)
-#define CRASHLOG_FLAG_TRIGGER_EXECUTE BIT(29)
+#define CRASHLOG_FLAG_TRIGGER_CLEAR BIT(29)
+#define CRASHLOG_FLAG_TRIGGER_EXECUTE BIT(30)
#define CRASHLOG_FLAG_TRIGGER_COMPLETE BIT(31)
#define CRASHLOG_FLAG_TRIGGER_MASK GENMASK(31, 28)
case TP_HKEY_EV_KEY_NUMLOCK:
case TP_HKEY_EV_KEY_FN:
- case TP_HKEY_EV_KEY_FN_ESC:
/* key press events, we just ignore them as long as the EC
* is still reporting them in the normal keyboard stream */
*send_acpi_ev = false;
*ignore_acpi_ev = true;
return true;
+ case TP_HKEY_EV_KEY_FN_ESC:
+ /* Get the media key status to foce the status LED to update */
+ acpi_evalf(hkey_handle, NULL, "GMKS", "v");
+ *send_acpi_ev = false;
+ *ignore_acpi_ev = true;
+ return true;
+
case TP_HKEY_EV_TABLET_CHANGED:
tpacpi_input_send_tabletsw();
hotkey_tablet_mode_notify_change();
* Thinkpad sensor interfaces
*/
+#define DYTC_CMD_QUERY 0 /* To get DYTC status - enable/revision */
+#define DYTC_QUERY_ENABLE_BIT 8 /* Bit 8 - 0 = disabled, 1 = enabled */
+#define DYTC_QUERY_SUBREV_BIT 16 /* Bits 16 - 27 - sub revision */
+#define DYTC_QUERY_REV_BIT 28 /* Bits 28 - 31 - revision */
+
#define DYTC_CMD_GET 2 /* To get current IC function and mode */
#define DYTC_GET_LAPMODE_BIT 17 /* Set when in lapmode */
static bool has_lapsensor;
static bool palm_state;
static bool lap_state;
+static int dytc_version;
static int dytc_command(int command, int *output)
{
return 0;
}
+static int dytc_get_version(void)
+{
+ int err, output;
+
+ /* Check if we've been called before - and just return cached value */
+ if (dytc_version)
+ return dytc_version;
+
+ /* Otherwise query DYTC and extract version information */
+ err = dytc_command(DYTC_CMD_QUERY, &output);
+ /*
+ * If support isn't available (ENODEV) then don't return an error
+ * and don't create the sysfs group
+ */
+ if (err == -ENODEV)
+ return 0;
+ /* For all other errors we can flag the failure */
+ if (err)
+ return err;
+
+ /* Check DYTC is enabled and supports mode setting */
+ if (output & BIT(DYTC_QUERY_ENABLE_BIT))
+ dytc_version = (output >> DYTC_QUERY_REV_BIT) & 0xF;
+
+ return 0;
+}
+
static int lapsensor_get(bool *present, bool *state)
{
int output, err;
if (err)
return err;
}
- if (has_lapsensor) {
+
+ /* Check if we know the DYTC version, if we don't then get it */
+ if (!dytc_version) {
+ err = dytc_get_version();
+ if (err)
+ return err;
+ }
+ /*
+ * Platforms before DYTC version 5 claim to have a lap sensor, but it doesn't work, so we
+ * ignore them
+ */
+ if (has_lapsensor && (dytc_version >= 5)) {
err = sysfs_create_file(&tpacpi_pdev->dev.kobj, &dev_attr_dytc_lapmode.attr);
if (err)
return err;
* DYTC Platform Profile interface
*/
-#define DYTC_CMD_QUERY 0 /* To get DYTC status - enable/revision */
#define DYTC_CMD_SET 1 /* To enable/disable IC function mode */
#define DYTC_CMD_RESET 0x1ff /* To reset back to default */
-#define DYTC_QUERY_ENABLE_BIT 8 /* Bit 8 - 0 = disabled, 1 = enabled */
-#define DYTC_QUERY_SUBREV_BIT 16 /* Bits 16 - 27 - sub revision */
-#define DYTC_QUERY_REV_BIT 28 /* Bits 28 - 31 - revision */
-
#define DYTC_GET_FUNCTION_BIT 8 /* Bits 8-11 - function setting */
#define DYTC_GET_MODE_BIT 12 /* Bits 12-15 - mode setting */
return err;
if (profile == PLATFORM_PROFILE_BALANCED) {
- /* To get back to balanced mode we just issue a reset command */
- err = dytc_command(DYTC_CMD_RESET, &output);
+ /*
+ * To get back to balanced mode we need to issue a reset command.
+ * Note we still need to disable CQL mode before hand and re-enable
+ * it afterwards, otherwise dytc_lapmode gets reset to 0 and stays
+ * stuck at 0 for aprox. 30 minutes.
+ */
+ err = dytc_cql_command(DYTC_CMD_RESET, &output);
if (err)
goto unlock;
} else {
if (err)
return err;
+ /* Check if we know the DYTC version, if we don't then get it */
+ if (!dytc_version) {
+ err = dytc_get_version();
+ if (err)
+ return err;
+ }
/* Check DYTC is enabled and supports mode setting */
- if (output & BIT(DYTC_QUERY_ENABLE_BIT)) {
- /* Only DYTC v5.0 and later has this feature. */
- int dytc_version;
-
- dytc_version = (output >> DYTC_QUERY_REV_BIT) & 0xF;
- if (dytc_version >= 5) {
- dbg_printk(TPACPI_DBG_INIT,
- "DYTC version %d: thermal mode available\n", dytc_version);
- /* Create platform_profile structure and register */
- err = platform_profile_register(&dytc_profile);
- /*
- * If for some reason platform_profiles aren't enabled
- * don't quit terminally.
- */
- if (err)
- return 0;
+ if (dytc_version >= 5) {
+ dbg_printk(TPACPI_DBG_INIT,
+ "DYTC version %d: thermal mode available\n", dytc_version);
+ /* Create platform_profile structure and register */
+ err = platform_profile_register(&dytc_profile);
+ /*
+ * If for some reason platform_profiles aren't enabled
+ * don't quit terminally.
+ */
+ if (err)
+ return 0;
- dytc_profile_available = true;
- /* Ensure initial values are correct */
- dytc_profile_refresh();
- }
+ dytc_profile_available = true;
+ /* Ensure initial values are correct */
+ dytc_profile_refresh();
}
return 0;
}
tmr_add = ptp_qoriq->tmr_add;
adj = tmr_add;
- /* calculate diff as adj*(scaled_ppm/65536)/1000000
- * and round() to the nearest integer
+ /*
+ * Calculate diff and round() to the nearest integer
+ *
+ * diff = adj * (ppb / 1000000000)
+ * = adj * scaled_ppm / 65536000000
*/
- adj *= scaled_ppm;
- diff = div_u64(adj, 8000000);
- diff = (diff >> 13) + ((diff >> 12) & 1);
+ diff = mul_u64_u64_div_u64(adj, scaled_ppm, 32768000000);
+ diff = DIV64_U64_ROUND_UP(diff, 2);
tmr_add = neg_adj ? tmr_add - diff : tmr_add + diff;
-
ptp_qoriq->write(®s->ctrl_regs->tmr_add, tmr_add);
return 0;
return ret;
}
+/**
+ * cec_add_elem - Add an element to the CEC array.
+ * @pfn: page frame number to insert
+ *
+ * Return values:
+ * - <0: on error
+ * - 0: on success
+ * - >0: when the inserted pfn was offlined
+ */
static int cec_add_elem(u64 pfn)
{
struct ce_array *ca = &ce_arr;
+ int count, err, ret = 0;
unsigned int to = 0;
- int count, ret = 0;
/*
* We can be called very early on the identify_cpu() path where we are
if (ca->n == MAX_ELEMS)
WARN_ON(!del_lru_elem_unlocked(ca));
- ret = find_elem(ca, pfn, &to);
- if (ret < 0) {
+ err = find_elem(ca, pfn, &to);
+ if (err < 0) {
/*
* Shift range [to-end] to make room for one more element.
*/
static const struct regulator_desc regulators[] = {
BD9571MWV_REG("VD09", "vd09", VD09, avs_ops, 0, 0x7f,
- 0x80, 600000, 10000, 0x3c),
+ 0x6f, 600000, 10000, 0x3c),
BD9571MWV_REG("VD18", "vd18", VD18, vid_ops, BD9571MWV_VD18_VID, 0xf,
16, 1625000, 25000, 0),
BD9571MWV_REG("VD25", "vd25", VD25, vid_ops, BD9571MWV_VD25_VID, 0xf,
11, 2800000, 100000, 0),
BD9571MWV_REG("DVFS", "dvfs", DVFS, reg_ops,
BD9571MWV_DVFS_MONIVDAC, 0x7f,
- 0x80, 600000, 10000, 0x3c),
+ 0x6f, 600000, 10000, 0x3c),
};
#ifdef CONFIG_PM_SLEEP
{
struct bd9571mwv_reg *bdreg = dev_get_drvdata(dev);
- return sprintf(buf, "%s\n", bdreg->bkup_mode_enabled ? "on" : "off");
+ return sysfs_emit(buf, "%s\n", bdreg->bkup_mode_enabled ? "on" : "off");
}
static ssize_t backup_mode_store(struct device *dev,
&config);
if (IS_ERR(rdev)) {
dev_err(&pdev->dev, "failed to register %s regulator\n",
- pdev->name);
+ regulators[i].name);
return PTR_ERR(rdev);
}
}
.type = REGULATOR_VOLTAGE, \
.id = _bid, \
.owner = THIS_MODULE, \
- .n_voltages = 0xbf, \
+ .n_voltages = 0xc0, \
.linear_ranges = mt_volt_range1, \
.n_linear_ranges = ARRAY_SIZE(mt_volt_range1), \
.vsel_reg = _vsel, \
case MT6315_BUCK_MODE_LP:
return REGULATOR_MODE_IDLE;
default:
- return -EINVAL;
+ return REGULATOR_MODE_INVALID;
}
}
return ret;
}
+ /* Clear PRESET_EN bit in BUCK123_DVS to use DVS registers */
+ ret = regmap_clear_bits(pca9450->regmap, PCA9450_REG_BUCK123_DVS,
+ BUCK123_PRESET_EN);
+ if (ret) {
+ dev_err(&i2c->dev, "Failed to clear PRESET_EN bit: %d\n", ret);
+ return ret;
+ }
+
/* Set reset behavior on assertion of WDOG_B signal */
ret = regmap_update_bits(pca9450->regmap, PCA9450_REG_RESET_CTRL,
WDOG_B_CFG_MASK, WDOG_B_CFG_COLD_LDO12);
if (IS_ERR(pca9450->sd_vsel_gpio)) {
dev_err(&i2c->dev, "Failed to get SD_VSEL GPIO\n");
- return ret;
+ return PTR_ERR(pca9450->sd_vsel_gpio);
}
dev_info(&i2c->dev, "%s probed.\n",
static const struct rpmh_vreg_hw_data pmic5_hfsmps515 = {
.regulator_type = VRM,
.ops = &rpmh_regulator_vrm_ops,
- .voltage_range = REGULATOR_LINEAR_RANGE(2800000, 0, 4, 16000),
- .n_voltages = 5,
+ .voltage_range = REGULATOR_LINEAR_RANGE(320000, 0, 235, 16000),
+ .n_voltages = 236,
.pmic_mode_map = pmic_mode_map_pmic5_smps,
.of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode,
};
};
static const struct rpmh_vreg_init_data pm8350c_vreg_data[] = {
- RPMH_VREG("smps1", "smp%s1", &pmic5_hfsmps510, "vdd-s1"),
+ RPMH_VREG("smps1", "smp%s1", &pmic5_hfsmps515, "vdd-s1"),
RPMH_VREG("smps2", "smp%s2", &pmic5_ftsmps510, "vdd-s2"),
RPMH_VREG("smps3", "smp%s3", &pmic5_ftsmps510, "vdd-s3"),
RPMH_VREG("smps4", "smp%s4", &pmic5_ftsmps510, "vdd-s4"),
int i, ret;
regmap = dev_get_regmap(pdev->dev.parent, NULL);
- if (IS_ERR(regmap)) {
+ if (!regmap) {
dev_err(&pdev->dev, "Failed to init regmap\n");
- return PTR_ERR(regmap);
+ return -ENODEV;
}
/* Configure DSV mode to normal by default */
if (len == 0)
return NULL;
+ /*
+ * GNU binutils do not support multiple address spaces. The GNU
+ * linker's default linker script places IRAM at an arbitrary high
+ * offset, in order to differentiate it from DRAM. Hence we need to
+ * strip the artificial offset in the IRAM addresses coming from the
+ * ELF file.
+ *
+ * The TI proprietary linker would never set those higher IRAM address
+ * bits anyway. PRU architecture limits the program counter to 16-bit
+ * word-address range. This in turn corresponds to 18-bit IRAM
+ * byte-address range for ELF.
+ *
+ * Two more bits are added just in case to make the final 20-bit mask.
+ * Idea is to have a safeguard in case TI decides to add banking
+ * in future SoCs.
+ */
+ da &= 0xfffff;
+
if (da >= PRU_IRAM_DA &&
da + len <= PRU_IRAM_DA + pru->mem_regions[PRU_IOMEM_IRAM].size) {
offset = da - PRU_IRAM_DA;
break;
}
- if (pru->data->is_k3 && is_iram) {
+ if (pru->data->is_k3) {
ret = pru_rproc_memcpy(ptr, elf_data + phdr->p_offset,
filesz);
if (ret) {
memset_io(base, 0, resource_size(&imem));
_reloc.base = base;
- _reloc.num_entries = resource_size(&imem) / PIL_RELOC_ENTRY_SIZE;
+ _reloc.num_entries = (u32)resource_size(&imem) / PIL_RELOC_ENTRY_SIZE;
return 0;
}
MODULE_AUTHOR("Holger Smolinski <Holger.Smolinski@de.ibm.com>");
MODULE_DESCRIPTION("Linux on S/390 DASD device driver,"
" Copyright IBM Corp. 2000");
-MODULE_SUPPORTED_DEVICE("dasd");
MODULE_LICENSE("GPL");
/*
basedev = block->base;
spin_lock_irq(&dq->lock);
- if (basedev->state < DASD_STATE_READY) {
+ if (basedev->state < DASD_STATE_READY ||
+ test_bit(DASD_FLAG_OFFLINE, &basedev->flags)) {
DBF_DEV_EVENT(DBF_ERR, basedev,
"device not ready for request %p", req);
rc = BLK_STS_IOERR;
struct dasd_device *device;
struct dasd_block *block;
- cdev->handler = NULL;
-
device = dasd_device_from_cdev(cdev);
if (IS_ERR(device)) {
dasd_remove_sysfs_files(cdev);
* no quite down yet.
*/
dasd_set_target_state(device, DASD_STATE_NEW);
+ cdev->handler = NULL;
/* dasd_delete_device destroys the device reference. */
block = device->block;
dasd_delete_device(device);
* last output position matches the start address
* of this line.
*/
- if (s->string[1] == sba[0] && s->string[2] == sba[1])
- str += 3, len -= 3;
+ if (s->string[1] == sba[0] && s->string[2] == sba[1]) {
+ str += 3;
+ len -= 3;
+ }
if (raw3270_request_add_data(wrq, str, len) != 0)
break;
list_del_init(&s->update);
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/debugfs.h>
+#include <linux/reboot.h>
#include <asm/asm-offsets.h>
#include <asm/ipl.h>
return 0;
}
+static int zcore_reboot_and_on_panic_handler(struct notifier_block *self,
+ unsigned long event,
+ void *data)
+{
+ if (hsa_available)
+ release_hsa();
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block zcore_reboot_notifier = {
+ .notifier_call = zcore_reboot_and_on_panic_handler,
+ /* we need to be notified before reipl and kdump */
+ .priority = INT_MAX,
+};
+
+static struct notifier_block zcore_on_panic_notifier = {
+ .notifier_call = zcore_reboot_and_on_panic_handler,
+ /* we need to be notified before reipl and kdump */
+ .priority = INT_MAX,
+};
+
static int __init zcore_init(void)
{
unsigned char arch;
goto fail;
zcore_dir = debugfs_create_dir("zcore" , NULL);
- if (!zcore_dir) {
- rc = -ENOMEM;
- goto fail;
- }
zcore_reipl_file = debugfs_create_file("reipl", S_IRUSR, zcore_dir,
NULL, &zcore_reipl_fops);
- if (!zcore_reipl_file) {
- rc = -ENOMEM;
- goto fail_dir;
- }
zcore_hsa_file = debugfs_create_file("hsa", S_IRUSR|S_IWUSR, zcore_dir,
NULL, &zcore_hsa_fops);
- if (!zcore_hsa_file) {
- rc = -ENOMEM;
- goto fail_reipl_file;
- }
- return 0;
-fail_reipl_file:
- debugfs_remove(zcore_reipl_file);
-fail_dir:
- debugfs_remove(zcore_dir);
+ register_reboot_notifier(&zcore_reboot_notifier);
+ atomic_notifier_chain_register(&panic_notifier_list, &zcore_on_panic_notifier);
+
+ return 0;
fail:
diag308(DIAG308_REL_HSA, NULL);
return rc;
orb = &private->orb;
cc = stsch(sch->schid, &schib);
- printk(KERN_WARNING "cio: ccw device timeout occurred at %llx, "
+ printk(KERN_WARNING "cio: ccw device timeout occurred at %lx, "
"device information:\n", get_tod_clock());
printk(KERN_WARNING "cio: orb:\n");
print_hex_dump(KERN_WARNING, "cio: ", DUMP_PREFIX_NONE, 16, 1,
if (ret)
return ret;
- return copy_to_user((void __user *)arg, &info, minsz);
+ return copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0;
}
case VFIO_DEVICE_GET_REGION_INFO:
{
if (ret)
return ret;
- return copy_to_user((void __user *)arg, &info, minsz);
+ return copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0;
}
case VFIO_DEVICE_GET_IRQ_INFO:
{
if (info.count == -1)
return -EINVAL;
- return copy_to_user((void __user *)arg, &info, minsz);
+ return copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0;
}
case VFIO_DEVICE_SET_IRQS:
{
info.num_regions = 0;
info.num_irqs = 0;
- return copy_to_user((void __user *)arg, &info, minsz);
+ return copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0;
}
static ssize_t vfio_ap_mdev_ioctl(struct mdev_device *mdev,
int is_header[QDIO_MAX_ELEMENTS_PER_BUFFER];
struct qeth_qdio_out_q *q;
- struct qeth_qdio_out_buffer *next_pending;
+ struct list_head list_entry;
};
struct qeth_card;
struct qdio_buffer *qdio_bufs[QDIO_MAX_BUFFERS_PER_Q];
struct qeth_qdio_out_buffer *bufs[QDIO_MAX_BUFFERS_PER_Q];
struct qdio_outbuf_state *bufstates; /* convenience pointer */
+ struct list_head pending_bufs;
struct qeth_out_q_stats stats;
spinlock_t lock;
unsigned int priority;
static void qeth_notify_skbs(struct qeth_qdio_out_q *queue,
struct qeth_qdio_out_buffer *buf,
enum iucv_tx_notify notification);
-static void qeth_tx_complete_buf(struct qeth_qdio_out_buffer *buf, bool error,
- int budget);
static void qeth_close_dev_handler(struct work_struct *work)
{
return n;
}
-static void qeth_cleanup_handled_pending(struct qeth_qdio_out_q *q, int bidx,
- int forced_cleanup)
-{
- if (q->card->options.cq != QETH_CQ_ENABLED)
- return;
-
- if (q->bufs[bidx]->next_pending != NULL) {
- struct qeth_qdio_out_buffer *head = q->bufs[bidx];
- struct qeth_qdio_out_buffer *c = q->bufs[bidx]->next_pending;
-
- while (c) {
- if (forced_cleanup ||
- atomic_read(&c->state) == QETH_QDIO_BUF_EMPTY) {
- struct qeth_qdio_out_buffer *f = c;
-
- QETH_CARD_TEXT(f->q->card, 5, "fp");
- QETH_CARD_TEXT_(f->q->card, 5, "%lx", (long) f);
- /* release here to avoid interleaving between
- outbound tasklet and inbound tasklet
- regarding notifications and lifecycle */
- qeth_tx_complete_buf(c, forced_cleanup, 0);
-
- c = f->next_pending;
- WARN_ON_ONCE(head->next_pending != f);
- head->next_pending = c;
- kmem_cache_free(qeth_qdio_outbuf_cache, f);
- } else {
- head = c;
- c = c->next_pending;
- }
-
- }
- }
-}
-
static void qeth_qdio_handle_aob(struct qeth_card *card,
unsigned long phys_aob_addr)
{
struct qaob *aob;
struct qeth_qdio_out_buffer *buffer;
enum iucv_tx_notify notification;
+ struct qeth_qdio_out_q *queue;
unsigned int i;
aob = (struct qaob *) phys_to_virt(phys_aob_addr);
qeth_notify_skbs(buffer->q, buffer, notification);
/* Free dangling allocations. The attached skbs are handled by
- * qeth_cleanup_handled_pending().
+ * qeth_tx_complete_pending_bufs().
*/
for (i = 0;
i < aob->sb_count && i < QETH_MAX_BUFFER_ELEMENTS(card);
buffer->is_header[i] = 0;
}
+ queue = buffer->q;
atomic_set(&buffer->state, QETH_QDIO_BUF_EMPTY);
+ napi_schedule(&queue->napi);
break;
default:
WARN_ON_ONCE(1);
struct qeth_qdio_out_q *queue = buf->q;
struct sk_buff *skb;
- if (atomic_read(&buf->state) == QETH_QDIO_BUF_PENDING)
- qeth_notify_skbs(queue, buf, TX_NOTIFY_GENERALERROR);
-
/* Empty buffer? */
if (buf->next_element_to_fill == 0)
return;
atomic_set(&buf->state, QETH_QDIO_BUF_EMPTY);
}
+static void qeth_tx_complete_pending_bufs(struct qeth_card *card,
+ struct qeth_qdio_out_q *queue,
+ bool drain)
+{
+ struct qeth_qdio_out_buffer *buf, *tmp;
+
+ list_for_each_entry_safe(buf, tmp, &queue->pending_bufs, list_entry) {
+ if (drain || atomic_read(&buf->state) == QETH_QDIO_BUF_EMPTY) {
+ QETH_CARD_TEXT(card, 5, "fp");
+ QETH_CARD_TEXT_(card, 5, "%lx", (long) buf);
+
+ if (drain)
+ qeth_notify_skbs(queue, buf,
+ TX_NOTIFY_GENERALERROR);
+ qeth_tx_complete_buf(buf, drain, 0);
+
+ list_del(&buf->list_entry);
+ kmem_cache_free(qeth_qdio_outbuf_cache, buf);
+ }
+ }
+}
+
static void qeth_drain_output_queue(struct qeth_qdio_out_q *q, bool free)
{
int j;
+ qeth_tx_complete_pending_bufs(q->card, q, true);
+
for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; ++j) {
if (!q->bufs[j])
continue;
- qeth_cleanup_handled_pending(q, j, 1);
+
qeth_clear_output_buffer(q, q->bufs[j], true, 0);
if (free) {
kmem_cache_free(qeth_qdio_outbuf_cache, q->bufs[j]);
skb_queue_head_init(&newbuf->skb_list);
lockdep_set_class(&newbuf->skb_list.lock, &qdio_out_skb_queue_key);
newbuf->q = q;
- newbuf->next_pending = q->bufs[bidx];
atomic_set(&newbuf->state, QETH_QDIO_BUF_EMPTY);
q->bufs[bidx] = newbuf;
return 0;
static struct qeth_qdio_out_q *qeth_alloc_output_queue(void)
{
struct qeth_qdio_out_q *q = kzalloc(sizeof(*q), GFP_KERNEL);
+ unsigned int i;
if (!q)
return NULL;
- if (qdio_alloc_buffers(q->qdio_bufs, QDIO_MAX_BUFFERS_PER_Q)) {
- kfree(q);
- return NULL;
+ if (qdio_alloc_buffers(q->qdio_bufs, QDIO_MAX_BUFFERS_PER_Q))
+ goto err_qdio_bufs;
+
+ for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; i++) {
+ if (qeth_init_qdio_out_buf(q, i))
+ goto err_out_bufs;
}
+
return q;
+
+err_out_bufs:
+ while (i > 0)
+ kmem_cache_free(qeth_qdio_outbuf_cache, q->bufs[--i]);
+ qdio_free_buffers(q->qdio_bufs, QDIO_MAX_BUFFERS_PER_Q);
+err_qdio_bufs:
+ kfree(q);
+ return NULL;
}
static void qeth_tx_completion_timer(struct timer_list *timer)
static int qeth_alloc_qdio_queues(struct qeth_card *card)
{
- int i, j;
+ unsigned int i;
QETH_CARD_TEXT(card, 2, "allcqdbf");
card->qdio.out_qs[i] = queue;
queue->card = card;
queue->queue_no = i;
+ INIT_LIST_HEAD(&queue->pending_bufs);
spin_lock_init(&queue->lock);
timer_setup(&queue->timer, qeth_tx_completion_timer, 0);
queue->coalesce_usecs = QETH_TX_COALESCE_USECS;
queue->max_coalesced_frames = QETH_TX_MAX_COALESCED_FRAMES;
queue->priority = QETH_QIB_PQUE_PRIO_DEFAULT;
-
- /* give outbound qeth_qdio_buffers their qdio_buffers */
- for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; ++j) {
- WARN_ON(queue->bufs[j]);
- if (qeth_init_qdio_out_buf(queue, j))
- goto out_freeoutqbufs;
- }
}
/* completion */
return 0;
-out_freeoutqbufs:
- while (j > 0) {
- --j;
- kmem_cache_free(qeth_qdio_outbuf_cache,
- card->qdio.out_qs[i]->bufs[j]);
- card->qdio.out_qs[i]->bufs[j] = NULL;
- }
out_freeoutq:
while (i > 0) {
qeth_free_output_queue(card->qdio.out_qs[--i]);
qeth_schedule_recovery(card);
}
+ list_add(&buffer->list_entry,
+ &queue->pending_bufs);
/* Skip clearing the buffer: */
return;
case QETH_QDIO_BUF_QAOB_OK:
unsigned int bytes = 0;
int completed;
+ qeth_tx_complete_pending_bufs(card, queue, false);
+
if (qeth_out_queue_is_empty(queue)) {
napi_complete(napi);
return 0;
qeth_handle_send_error(card, buffer, error);
qeth_iqd_tx_complete(queue, bidx, error, budget);
- qeth_cleanup_handled_pending(queue, bidx, false);
}
netdev_tx_completed_queue(txq, packets, bytes);
card->data.state = CH_STATE_UP;
netif_tx_start_all_queues(dev);
- napi_enable(&card->napi);
local_bh_disable();
- napi_schedule(&card->napi);
if (IS_IQD(card)) {
struct qeth_qdio_out_q *queue;
unsigned int i;
napi_schedule(&queue->napi);
}
}
+
+ napi_enable(&card->napi);
+ napi_schedule(&card->napi);
/* kick-start the NAPI softirq: */
local_bh_enable();
+
return 0;
}
EXPORT_SYMBOL_GPL(qeth_open);
struct qeth_card *card = dev->ml_priv;
QETH_CARD_TEXT(card, 4, "qethstop");
+
+ napi_disable(&card->napi);
+ cancel_delayed_work_sync(&card->buffer_reclaim_work);
+ qdio_stop_irq(CARD_DDEV(card));
+
if (IS_IQD(card)) {
struct qeth_qdio_out_q *queue;
unsigned int i;
netif_tx_disable(dev);
}
- napi_disable(&card->napi);
- cancel_delayed_work_sync(&card->buffer_reclaim_work);
- qdio_stop_irq(CARD_DDEV(card));
-
return 0;
}
EXPORT_SYMBOL_GPL(qeth_stop);
MODULE_AUTHOR("Eric Brower <ebrower@usa.net>");
MODULE_DESCRIPTION("7-Segment Display driver for Sun Microsystems CP1400/1500");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("d7s");
struct d7s {
void __iomem *regs;
MODULE_AUTHOR("Hewlett-Packard Company");
MODULE_DESCRIPTION("Driver for HP Smart Array Controller version " \
HPSA_DRIVER_VERSION);
-MODULE_SUPPORTED_DEVICE("HP Smart Array Controllers");
MODULE_VERSION(HPSA_DRIVER_VERSION);
MODULE_LICENSE("GPL");
MODULE_ALIAS("cciss");
#ifndef HPSA_CMD_H
#define HPSA_CMD_H
+#include <linux/compiler.h>
+
+#include <linux/build_bug.h> /* static_assert */
+#include <linux/stddef.h> /* offsetof */
+
/* general boundary defintions */
#define SENSEINFOBYTES 32 /* may vary between hbas */
#define SG_ENTRIES_IN_CMD 32 /* Max SG entries excluding chain blocks */
MAX_EXT_TARGETS + 1) /* + 1 is for the controller itself */
/* SCSI-3 Commands */
-#pragma pack(1)
-
#define HPSA_INQUIRY 0x12
struct InquiryData {
u8 data_byte[36];
-};
+} __packed;
#define HPSA_REPORT_LOG 0xc2 /* Report Logical LUNs */
#define HPSA_REPORT_PHYS 0xc3 /* Report Physical LUNs */
u8 xor_mult[2]; /**< XOR multipliers for this position,
* valid for data disks only */
u8 reserved[2];
-};
+} __packed;
struct raid_map_data {
__le32 structure_size; /* Size of entire structure in bytes */
__le16 dekindex; /* Data encryption key index. */
u8 reserved[16];
struct raid_map_disk_data data[RAID_MAP_MAX_ENTRIES];
-};
+} __packed;
struct ReportLUNdata {
u8 LUNListLength[4];
u8 extended_response_flag;
u8 reserved[3];
u8 LUN[HPSA_MAX_LUN][8];
-};
+} __packed;
struct ext_report_lun_entry {
u8 lunid[8];
u8 lun_count; /* multi-lun device, how many luns */
u8 redundant_paths;
u32 ioaccel_handle; /* ioaccel1 only uses lower 16 bits */
-};
+} __packed;
struct ReportExtendedLUNdata {
u8 LUNListLength[4];
u8 extended_response_flag;
u8 reserved[3];
struct ext_report_lun_entry LUN[HPSA_MAX_PHYS_LUN];
-};
+} __packed;
struct SenseSubsystem_info {
u8 reserved[36];
u8 portname[8];
u8 reserved1[1108];
-};
+} __packed;
/* BMIC commands */
#define BMIC_READ 0x26
u8 Targ:6;
u8 Mode:2; /* b10 */
} LogUnit;
-};
+} __packed;
struct PhysDevAddr {
u32 TargetId:24;
u32 Mode:2;
/* 2 level target device addr */
union SCSI3Addr Target[2];
-};
+} __packed;
struct LogDevAddr {
u32 VolId:30;
u32 Mode:2;
u8 reserved[4];
-};
+} __packed;
union LUNAddr {
u8 LunAddrBytes[8];
union SCSI3Addr SCSI3Lun[4];
struct PhysDevAddr PhysDev;
struct LogDevAddr LogDev;
-};
+} __packed;
struct CommandListHeader {
u8 ReplyQueue;
__le16 SGTotal;
__le64 tag;
union LUNAddr LUN;
-};
+} __packed;
struct RequestBlock {
u8 CDBLen;
#define GET_DIR(tad) (((tad) >> 6) & 0x03)
u16 Timeout;
u8 CDB[16];
-};
+} __packed;
struct ErrDescriptor {
__le64 Addr;
__le32 Len;
-};
+} __packed;
struct SGDescriptor {
__le64 Addr;
__le32 Len;
__le32 Ext;
-};
+} __packed;
union MoreErrInfo {
struct {
u8 offense_num; /* byte # of offense 0-base */
u32 offense_value;
} Invalid_Cmd;
-};
+} __packed;
+
struct ErrorInfo {
u8 ScsiStatus;
u8 SenseLen;
u32 ResidualCnt;
union MoreErrInfo MoreErrInfo;
u8 SenseInfo[SENSEINFOBYTES];
-};
+} __packed;
/* Command types */
#define CMD_IOCTL_PEND 0x01
#define CMD_SCSI 0x03
atomic_t refcount; /* Must be last to avoid memset in hpsa_cmd_init() */
} __aligned(COMMANDLIST_ALIGNMENT);
+/*
+ * Make sure our embedded atomic variable is aligned. Otherwise we break atomic
+ * operations on architectures that don't support unaligned atomics like IA64.
+ *
+ * The assert guards against reintroductin against unwanted __packed to
+ * the struct CommandList.
+ */
+static_assert(offsetof(struct CommandList, refcount) % __alignof__(atomic_t) == 0);
+
/* Max S/G elements in I/O accelerator command */
#define IOACCEL1_MAXSGENTRIES 24
#define IOACCEL2_MAXSGENTRIES 28
__le64 host_addr; /* 0x70 - 0x77 */
u8 CISS_LUN[8]; /* 0x78 - 0x7F */
struct SGDescriptor SG[IOACCEL1_MAXSGENTRIES];
-} __aligned(IOACCEL1_COMMANDLIST_ALIGNMENT);
+} __packed __aligned(IOACCEL1_COMMANDLIST_ALIGNMENT);
#define IOACCEL1_FUNCTION_SCSIIO 0x00
#define IOACCEL1_SGLOFFSET 32
u8 chain_indicator;
#define IOACCEL2_CHAIN 0x80
#define IOACCEL2_LAST_SG 0x40
-};
+} __packed;
/*
* SCSI Response Format structure for IO Accelerator Mode 2
u8 sense_data_len; /* sense/response data length */
u8 resid_cnt[4]; /* residual count */
u8 sense_data_buff[32]; /* sense/response data buffer */
-};
+} __packed;
/*
* Structure for I/O accelerator (mode 2 or m2) commands.
__le32 tweak_upper; /* Encryption tweak, upper 4 bytes */
struct ioaccel2_sg_element sg[IOACCEL2_MAXSGENTRIES];
struct io_accel2_scsi_response error_data;
-} __aligned(IOACCEL2_COMMANDLIST_ALIGNMENT);
+} __packed __aligned(IOACCEL2_COMMANDLIST_ALIGNMENT);
/*
* defines for Mode 2 command struct
__le64 abort_tag; /* cciss tag of SCSI cmd or TMF to abort */
__le64 error_ptr; /* Error Pointer */
__le32 error_len; /* Error Length */
-} __aligned(IOACCEL2_COMMANDLIST_ALIGNMENT);
+} __packed __aligned(IOACCEL2_COMMANDLIST_ALIGNMENT);
/* Configuration Table Structure */
struct HostWrite {
__le32 command_pool_addr_hi;
__le32 CoalIntDelay;
__le32 CoalIntCount;
-};
+} __packed;
#define SIMPLE_MODE 0x02
#define PERFORMANT_MODE 0x04
#define HPSA_EVENT_NOTIFY_ACCEL_IO_PATH_STATE_CHANGE (1 << 30)
#define HPSA_EVENT_NOTIFY_ACCEL_IO_PATH_CONFIG_CHANGE (1 << 31)
__le32 clear_event_notify;
-};
+} __packed;
#define NUM_BLOCKFETCH_ENTRIES 8
struct TransTable_struct {
__le32 RepQCtrAddrHigh32;
#define MAX_REPLY_QUEUES 64
struct vals32 RepQAddr[MAX_REPLY_QUEUES];
-};
+} __packed;
struct hpsa_pci_info {
unsigned char bus;
unsigned char dev_fn;
unsigned short domain;
u32 board_id;
-};
+} __packed;
struct bmic_identify_controller {
u8 configured_logical_drive_count; /* offset 0 */
u8 pad2[136];
u8 controller_mode; /* offset 292 */
u8 pad3[32];
-};
+} __packed;
struct bmic_identify_physical_device {
u8 max_link_rate[256];
u8 neg_phys_link_rate[256];
u8 box_conn_name[8];
-} __attribute((aligned(512)));
+} __packed __attribute((aligned(512)));
struct bmic_sense_subsystem_info {
u8 primary_slot_number;
u8 secondary_array_serial_number[32];
u8 secondary_cache_serial_number[32];
u8 pad[332];
-};
+} __packed;
struct bmic_sense_storage_box_params {
u8 reserved[36];
u8 reserver_3[84];
u8 phys_connector[2];
u8 reserved_4[296];
-};
+} __packed;
-#pragma pack()
#endif /* HPSA_CMD_H */
#include <linux/bsg-lib.h>
#include <asm/firmware.h>
#include <asm/irq.h>
+#include <asm/rtas.h>
#include <asm/vio.h>
#include <scsi/scsi.h>
#include <scsi/scsi_cmnd.h>
static void ibmvfc_tgt_implicit_logout_and_del(struct ibmvfc_target *);
static void ibmvfc_tgt_move_login(struct ibmvfc_target *);
+static void ibmvfc_release_sub_crqs(struct ibmvfc_host *);
+static void ibmvfc_init_sub_crqs(struct ibmvfc_host *);
+
static const char *unknown_error = "unknown error";
static long h_reg_sub_crq(unsigned long unit_address, unsigned long ioba,
{
int rc = 0;
struct vio_dev *vdev = to_vio_dev(vhost->dev);
+ unsigned long flags;
+
+ ibmvfc_release_sub_crqs(vhost);
/* Re-enable the CRQ */
do {
if (rc)
dev_err(vhost->dev, "Error enabling adapter (rc=%d)\n", rc);
+ spin_lock_irqsave(vhost->host->host_lock, flags);
+ spin_lock(vhost->crq.q_lock);
+ vhost->do_enquiry = 1;
+ vhost->using_channels = 0;
+ spin_unlock(vhost->crq.q_lock);
+ spin_unlock_irqrestore(vhost->host->host_lock, flags);
+
+ ibmvfc_init_sub_crqs(vhost);
+
return rc;
}
unsigned long flags;
struct vio_dev *vdev = to_vio_dev(vhost->dev);
struct ibmvfc_queue *crq = &vhost->crq;
- struct ibmvfc_queue *scrq;
- int i;
+
+ ibmvfc_release_sub_crqs(vhost);
/* Close the CRQ */
do {
memset(crq->msgs.crq, 0, PAGE_SIZE);
crq->cur = 0;
- if (vhost->scsi_scrqs.scrqs) {
- for (i = 0; i < nr_scsi_hw_queues; i++) {
- scrq = &vhost->scsi_scrqs.scrqs[i];
- spin_lock(scrq->q_lock);
- memset(scrq->msgs.scrq, 0, PAGE_SIZE);
- scrq->cur = 0;
- spin_unlock(scrq->q_lock);
- }
- }
-
/* And re-open it again */
rc = plpar_hcall_norets(H_REG_CRQ, vdev->unit_address,
crq->msg_token, PAGE_SIZE);
dev_warn(vhost->dev, "Partner adapter not ready\n");
else if (rc != 0)
dev_warn(vhost->dev, "Couldn't register crq (rc=%d)\n", rc);
+
spin_unlock(vhost->crq.q_lock);
spin_unlock_irqrestore(vhost->host->host_lock, flags);
+ ibmvfc_init_sub_crqs(vhost);
+
return rc;
}
}
/**
+ * ibmvfc_event_is_free - Check if event is free or not
+ * @evt: ibmvfc event struct
+ *
+ * Returns:
+ * true / false
+ **/
+static bool ibmvfc_event_is_free(struct ibmvfc_event *evt)
+{
+ struct ibmvfc_event *loop_evt;
+
+ list_for_each_entry(loop_evt, &evt->queue->free, queue_list)
+ if (loop_evt == evt)
+ return true;
+
+ return false;
+}
+
+/**
* ibmvfc_wait_for_ops - Wait for ops to complete
* @vhost: ibmvfc host struct
* @device: device to match (starget or sdev)
{
struct ibmvfc_event *evt;
DECLARE_COMPLETION_ONSTACK(comp);
- int wait;
+ int wait, i, q_index, q_size;
unsigned long flags;
signed long timeout = IBMVFC_ABORT_WAIT_TIMEOUT * HZ;
+ struct ibmvfc_queue *queues;
ENTER;
+ if (vhost->mq_enabled && vhost->using_channels) {
+ queues = vhost->scsi_scrqs.scrqs;
+ q_size = vhost->scsi_scrqs.active_queues;
+ } else {
+ queues = &vhost->crq;
+ q_size = 1;
+ }
+
do {
wait = 0;
- spin_lock_irqsave(&vhost->crq.l_lock, flags);
- list_for_each_entry(evt, &vhost->crq.sent, queue_list) {
- if (match(evt, device)) {
- evt->eh_comp = ∁
- wait++;
+ spin_lock_irqsave(vhost->host->host_lock, flags);
+ for (q_index = 0; q_index < q_size; q_index++) {
+ spin_lock(&queues[q_index].l_lock);
+ for (i = 0; i < queues[q_index].evt_pool.size; i++) {
+ evt = &queues[q_index].evt_pool.events[i];
+ if (!ibmvfc_event_is_free(evt)) {
+ if (match(evt, device)) {
+ evt->eh_comp = ∁
+ wait++;
+ }
+ }
}
+ spin_unlock(&queues[q_index].l_lock);
}
- spin_unlock_irqrestore(&vhost->crq.l_lock, flags);
+ spin_unlock_irqrestore(vhost->host->host_lock, flags);
if (wait) {
timeout = wait_for_completion_timeout(&comp, timeout);
if (!timeout) {
wait = 0;
- spin_lock_irqsave(&vhost->crq.l_lock, flags);
- list_for_each_entry(evt, &vhost->crq.sent, queue_list) {
- if (match(evt, device)) {
- evt->eh_comp = NULL;
- wait++;
+ spin_lock_irqsave(vhost->host->host_lock, flags);
+ for (q_index = 0; q_index < q_size; q_index++) {
+ spin_lock(&queues[q_index].l_lock);
+ for (i = 0; i < queues[q_index].evt_pool.size; i++) {
+ evt = &queues[q_index].evt_pool.events[i];
+ if (!ibmvfc_event_is_free(evt)) {
+ if (match(evt, device)) {
+ evt->eh_comp = NULL;
+ wait++;
+ }
+ }
}
+ spin_unlock(&queues[q_index].l_lock);
}
- spin_unlock_irqrestore(&vhost->crq.l_lock, flags);
+ spin_unlock_irqrestore(vhost->host->host_lock, flags);
if (wait)
dev_err(vhost->dev, "Timed out waiting for aborted commands\n");
LEAVE;
rc = h_reg_sub_crq(vdev->unit_address, scrq->msg_token, PAGE_SIZE,
&scrq->cookie, &scrq->hw_irq);
- if (rc) {
+ /* H_CLOSED indicates successful register, but no CRQ partner */
+ if (rc && rc != H_CLOSED) {
dev_warn(dev, "Error registering sub-crq: %d\n", rc);
if (rc == H_PARAMETER)
dev_warn_once(dev, "Firmware may not support MQ\n");
irq_failed:
do {
- plpar_hcall_norets(H_FREE_SUB_CRQ, vdev->unit_address, scrq->cookie);
- } while (rc == H_BUSY || H_IS_LONG_BUSY(rc));
+ rc = plpar_hcall_norets(H_FREE_SUB_CRQ, vdev->unit_address, scrq->cookie);
+ } while (rtas_busy_delay(rc));
reg_failed:
ibmvfc_free_queue(vhost, scrq);
LEAVE;
free_irq(scrq->irq, scrq);
irq_dispose_mapping(scrq->irq);
+ scrq->irq = 0;
do {
rc = plpar_hcall_norets(H_FREE_SUB_CRQ, vdev->unit_address,
LEAVE;
}
-static int ibmvfc_init_sub_crqs(struct ibmvfc_host *vhost)
+static void ibmvfc_init_sub_crqs(struct ibmvfc_host *vhost)
{
int i, j;
ENTER;
+ if (!vhost->mq_enabled)
+ return;
vhost->scsi_scrqs.scrqs = kcalloc(nr_scsi_hw_queues,
sizeof(*vhost->scsi_scrqs.scrqs),
GFP_KERNEL);
- if (!vhost->scsi_scrqs.scrqs)
- return -1;
+ if (!vhost->scsi_scrqs.scrqs) {
+ vhost->do_enquiry = 0;
+ return;
+ }
for (i = 0; i < nr_scsi_hw_queues; i++) {
if (ibmvfc_register_scsi_channel(vhost, i)) {
kfree(vhost->scsi_scrqs.scrqs);
vhost->scsi_scrqs.scrqs = NULL;
vhost->scsi_scrqs.active_queues = 0;
- LEAVE;
- return -1;
+ vhost->do_enquiry = 0;
+ break;
}
}
LEAVE;
- return 0;
}
static void ibmvfc_release_sub_crqs(struct ibmvfc_host *vhost)
vhost->disc_buf_dma);
dma_free_coherent(vhost->dev, sizeof(*vhost->login_buf),
vhost->login_buf, vhost->login_buf_dma);
+ dma_free_coherent(vhost->dev, sizeof(*vhost->channel_setup_buf),
+ vhost->channel_setup_buf, vhost->channel_setup_dma);
dma_pool_destroy(vhost->sg_pool);
ibmvfc_free_queue(vhost, async_q);
LEAVE;
goto remove_shost;
}
- if (vhost->mq_enabled) {
- rc = ibmvfc_init_sub_crqs(vhost);
- if (rc)
- dev_warn(dev, "Failed to allocate Sub-CRQs. rc=%d\n", rc);
- }
+ ibmvfc_init_sub_crqs(vhost);
if (shost_to_fc_host(shost)->rqst_q)
blk_queue_max_segments(shost_to_fc_host(shost)->rqst_q, 1);
* Return value:
* 0
**/
-static int ibmvfc_remove(struct vio_dev *vdev)
+static void ibmvfc_remove(struct vio_dev *vdev)
{
struct ibmvfc_host *vhost = dev_get_drvdata(&vdev->dev);
LIST_HEAD(purge);
spin_unlock(&ibmvfc_driver_lock);
scsi_host_put(vhost->host);
LEAVE;
- return 0;
}
/**
return -1;
}
-static int ibmvscsi_remove(struct vio_dev *vdev)
+static void ibmvscsi_remove(struct vio_dev *vdev)
{
struct ibmvscsi_host_data *hostdata = dev_get_drvdata(&vdev->dev);
spin_unlock(&ibmvscsi_driver_lock);
scsi_host_put(hostdata->host);
-
- return 0;
}
/**
return rc;
}
-static int ibmvscsis_remove(struct vio_dev *vdev)
+static void ibmvscsis_remove(struct vio_dev *vdev)
{
struct scsi_info *vscsi = dev_get_drvdata(&vdev->dev);
list_del(&vscsi->list);
spin_unlock_bh(&ibmvscsis_dev_lock);
kfree(vscsi);
-
- return 0;
}
static ssize_t system_id_show(struct device *dev,
}
}
-static void iscsi_start_session_recovery(struct iscsi_session *session,
- struct iscsi_conn *conn, int flag)
+void iscsi_conn_stop(struct iscsi_cls_conn *cls_conn, int flag)
{
+ struct iscsi_conn *conn = cls_conn->dd_data;
+ struct iscsi_session *session = conn->session;
int old_stop_stage;
mutex_lock(&session->eh_mutex);
spin_unlock_bh(&session->frwd_lock);
mutex_unlock(&session->eh_mutex);
}
-
-void iscsi_conn_stop(struct iscsi_cls_conn *cls_conn, int flag)
-{
- struct iscsi_conn *conn = cls_conn->dd_data;
- struct iscsi_session *session = conn->session;
-
- switch (flag) {
- case STOP_CONN_RECOVER:
- cls_conn->state = ISCSI_CONN_FAILED;
- break;
- case STOP_CONN_TERM:
- cls_conn->state = ISCSI_CONN_DOWN;
- break;
- default:
- iscsi_conn_printk(KERN_ERR, conn,
- "invalid stop flag %d\n", flag);
- return;
- }
-
- iscsi_start_session_recovery(session, conn, flag);
-}
EXPORT_SYMBOL_GPL(iscsi_conn_stop);
int iscsi_conn_bind(struct iscsi_cls_session *cls_session,
memcpy(task->ata_task.atapi_packet, qc->cdb, qc->dev->cdb_len);
task->total_xfer_len = qc->nbytes;
task->num_scatter = qc->n_elem;
+ task->data_dir = qc->dma_dir;
+ } else if (qc->tf.protocol == ATA_PROT_NODATA) {
+ task->data_dir = DMA_NONE;
} else {
for_each_sg(qc->sg, sg, qc->n_elem, si)
xfer += sg_dma_len(sg);
task->total_xfer_len = xfer;
task->num_scatter = si;
- }
-
- if (qc->tf.protocol == ATA_PROT_NODATA)
- task->data_dir = DMA_NONE;
- else
task->data_dir = qc->dma_dir;
+ }
task->scatter = qc->sg;
task->ata_task.retry_count = 1;
task->task_state_flags = SAS_TASK_STATE_PENDING;
memset(dstbuf, 0, 33);
size = (nbytes < 32) ? nbytes : 32;
if (copy_from_user(dstbuf, buf, size))
- return 0;
+ return -EFAULT;
if (dent == phba->debug_InjErrLBA) {
if ((dstbuf[0] == 'o') && (dstbuf[1] == 'f') &&
}
if ((tmp == 0) && (kstrtoull(dstbuf, 0, &tmp)))
- return 0;
+ return -EINVAL;
if (dent == phba->debug_writeGuard)
phba->lpfc_injerr_wgrd_cnt = (uint32_t)tmp;
ioc->pend_os_device_add_sz++;
ioc->pend_os_device_add = kzalloc(ioc->pend_os_device_add_sz,
GFP_KERNEL);
- if (!ioc->pend_os_device_add)
+ if (!ioc->pend_os_device_add) {
+ r = -ENOMEM;
goto out_free_resources;
+ }
ioc->device_remove_in_progress_sz = ioc->pend_os_device_add_sz;
ioc->device_remove_in_progress =
kzalloc(ioc->device_remove_in_progress_sz, GFP_KERNEL);
- if (!ioc->device_remove_in_progress)
+ if (!ioc->device_remove_in_progress) {
+ r = -ENOMEM;
goto out_free_resources;
+ }
ioc->fwfault_debug = mpt3sas_fwfault_debug;
* And add this object to port_table_list.
*/
if (!ioc->multipath_on_hba) {
- port = kzalloc(sizeof(struct hba_port), GFP_KERNEL);
+ port = kzalloc(sizeof(struct hba_port), GFP_ATOMIC);
if (!port)
return NULL;
if (cs->mmio_base) {
cs->disable_intr(cs);
iounmap(cs->mmio_base);
+ cs->mmio_base = NULL;
}
if (cs->irq)
free_irq(cs->irq, cs);
if (cs->io_addr)
release_region(cs->io_addr, 0x80);
- iounmap(cs->mmio_base);
pci_set_drvdata(pdev, NULL);
pci_disable_device(pdev);
scsi_host_put(cs->host);
MODULE_AUTHOR("YOKOTA Hiroshi <yokota@netlab.is.tsukuba.ac.jp>");
MODULE_DESCRIPTION("WorkBit NinjaSCSI-3 / NinjaSCSI-32Bi(16bit) PCMCIA SCSI host adapter module");
-MODULE_SUPPORTED_DEVICE("sd,sr,sg,st");
MODULE_LICENSE("GPL");
#include "nsp_io.h"
PM8001_EVENT_LOG_SIZE;
pm8001_ha->main_cfg_tbl.pm8001_tbl.iop_event_log_option = 0x01;
pm8001_ha->main_cfg_tbl.pm8001_tbl.fatal_err_interrupt = 0x01;
- for (i = 0; i < PM8001_MAX_INB_NUM; i++) {
+ for (i = 0; i < pm8001_ha->max_q_num; i++) {
pm8001_ha->inbnd_q_tbl[i].element_pri_size_cnt =
PM8001_MPI_QUEUE | (pm8001_ha->iomb_size << 16) | (0x00<<30);
pm8001_ha->inbnd_q_tbl[i].upper_base_addr =
pm8001_ha->inbnd_q_tbl[i].producer_idx = 0;
pm8001_ha->inbnd_q_tbl[i].consumer_index = 0;
}
- for (i = 0; i < PM8001_MAX_OUTB_NUM; i++) {
+ for (i = 0; i < pm8001_ha->max_q_num; i++) {
pm8001_ha->outbnd_q_tbl[i].element_size_cnt =
PM8001_MPI_QUEUE | (pm8001_ha->iomb_size << 16) | (0x01<<30);
pm8001_ha->outbnd_q_tbl[i].upper_base_addr =
read_outbnd_queue_table(pm8001_ha);
/* update main config table ,inbound table and outbound table */
update_main_config_table(pm8001_ha);
- for (i = 0; i < PM8001_MAX_INB_NUM; i++)
+ for (i = 0; i < pm8001_ha->max_q_num; i++)
update_inbnd_queue_table(pm8001_ha, i);
- for (i = 0; i < PM8001_MAX_OUTB_NUM; i++)
+ for (i = 0; i < pm8001_ha->max_q_num; i++)
update_outbnd_queue_table(pm8001_ha, i);
/* 8081 controller donot require these operations */
if (deviceid != 0x8081 && deviceid != 0x0042) {
if (!qedi->global_queues[i]) {
QEDI_ERR(&qedi->dbg_ctx,
"Unable to allocation global queue %d.\n", i);
+ status = -ENOMEM;
goto mem_alloc_failure;
}
if (!qpair->fw_started || (cmd->reset_count != qpair->chip_reset) ||
(cmd->sess && cmd->sess->deleted)) {
cmd->state = QLA_TGT_STATE_PROCESSED;
- res = 0;
- goto free;
+ return 0;
}
ql_dbg_qp(ql_dbg_tgt, qpair, 0xe018,
res = qlt_pre_xmit_response(cmd, &prm, xmit_type, scsi_status,
&full_req_cnt);
- if (unlikely(res != 0))
- goto free;
+ if (unlikely(res != 0)) {
+ return res;
+ }
spin_lock_irqsave(qpair->qp_lock_ptr, flags);
vha->flags.online, qla2x00_reset_active(vha),
cmd->reset_count, qpair->chip_reset);
spin_unlock_irqrestore(qpair->qp_lock_ptr, flags);
- res = 0;
- goto free;
+ return 0;
}
/* Does F/W have an IOCBs for this request */
qlt_unmap_sg(vha, cmd);
spin_unlock_irqrestore(qpair->qp_lock_ptr, flags);
-free:
- vha->hw->tgt.tgt_ops->free_cmd(cmd);
return res;
}
EXPORT_SYMBOL(qlt_xmit_response);
(min(1270, ((ql) > 0) ? (QLA_TGT_DATASEGS_PER_CMD_24XX + \
QLA_TGT_DATASEGS_PER_CONT_24XX*((ql) - 1)) : 0))
#endif
-#endif
#define GET_TARGET_ID(ha, iocb) ((HAS_EXTENDED_IDS(ha)) \
? le16_to_cpu((iocb)->u.isp2x.target.extended) \
#ifndef CTIO_RET_TYPE
#define CTIO_RET_TYPE 0x17 /* CTIO return entry */
#define ATIO_TYPE7 0x06 /* Accept target I/O entry for 24xx */
+#endif
struct fcp_hdr {
uint8_t r_ctl;
{
struct qla_tgt_cmd *cmd = container_of(se_cmd,
struct qla_tgt_cmd, se_cmd);
- struct scsi_qla_host *vha = cmd->vha;
if (cmd->aborted) {
/* Cmd can loop during Q-full. tcm_qla2xxx_aborted_task
cmd->se_cmd.transport_state,
cmd->se_cmd.t_state,
cmd->se_cmd.se_cmd_flags);
- vha->hw->tgt.tgt_ops->free_cmd(cmd);
return 0;
}
{
struct qla_tgt_cmd *cmd = container_of(se_cmd,
struct qla_tgt_cmd, se_cmd);
- struct scsi_qla_host *vha = cmd->vha;
int xmit_type = QLA_TGT_XMIT_STATUS;
if (cmd->aborted) {
cmd, kref_read(&cmd->se_cmd.cmd_kref),
cmd->se_cmd.transport_state, cmd->se_cmd.t_state,
cmd->se_cmd.se_cmd_flags);
- vha->hw->tgt.tgt_ops->free_cmd(cmd);
return 0;
}
cmd->bufflen = se_cmd->data_length;
* it works.
*/
mutex_lock(&conn_mutex);
+ switch (flag) {
+ case STOP_CONN_RECOVER:
+ conn->state = ISCSI_CONN_FAILED;
+ break;
+ case STOP_CONN_TERM:
+ conn->state = ISCSI_CONN_DOWN;
+ break;
+ default:
+ iscsi_cls_conn_printk(KERN_ERR, conn,
+ "invalid stop flag %d\n", flag);
+ goto unlock;
+ }
+
conn->transport->stop_conn(conn, flag);
+unlock:
mutex_unlock(&conn_mutex);
-
}
static void stop_conn_work_fn(struct work_struct *work)
default:
err = transport->set_param(conn, ev->u.set_param.param,
data, ev->u.set_param.len);
+ if ((conn->state == ISCSI_CONN_BOUND) ||
+ (conn->state == ISCSI_CONN_UP)) {
+ err = transport->set_param(conn, ev->u.set_param.param,
+ data, ev->u.set_param.len);
+ } else {
+ return -ENOTCONN;
+ }
}
return err;
mutex_lock(&conn->ep_mutex);
conn->ep = NULL;
mutex_unlock(&conn->ep_mutex);
+ conn->state = ISCSI_CONN_FAILED;
}
transport->ep_disconnect(ep);
ev->r.retcode = transport->bind_conn(session, conn,
ev->u.b_conn.transport_eph,
ev->u.b_conn.is_leading);
+ if (!ev->r.retcode)
+ conn->state = ISCSI_CONN_BOUND;
mutex_unlock(&conn_mutex);
if (ev->r.retcode || !transport->ep_connect)
static const char *const connection_state_names[] = {
[ISCSI_CONN_UP] = "up",
[ISCSI_CONN_DOWN] = "down",
- [ISCSI_CONN_FAILED] = "failed"
+ [ISCSI_CONN_FAILED] = "failed",
+ [ISCSI_CONN_BOUND] = "bound"
};
static ssize_t show_conn_state(struct device *dev,
res = mutex_lock_interruptible(&rport->mutex);
if (res)
goto out;
- if (rport->state != SRP_RPORT_FAIL_FAST)
+ if (rport->state != SRP_RPORT_FAIL_FAST && rport->state != SRP_RPORT_LOST)
/*
* sdev state must be SDEV_TRANSPORT_OFFLINE, transition
* to SDEV_BLOCK is illegal. Calling scsi_target_unblock()
static void sd_zbc_update_wp_offset_workfn(struct work_struct *work)
{
struct scsi_disk *sdkp;
+ unsigned long flags;
unsigned int zno;
int ret;
sdkp = container_of(work, struct scsi_disk, zone_wp_offset_work);
- spin_lock_bh(&sdkp->zones_wp_offset_lock);
+ spin_lock_irqsave(&sdkp->zones_wp_offset_lock, flags);
for (zno = 0; zno < sdkp->nr_zones; zno++) {
if (sdkp->zones_wp_offset[zno] != SD_ZBC_UPDATING_WP_OFST)
continue;
- spin_unlock_bh(&sdkp->zones_wp_offset_lock);
+ spin_unlock_irqrestore(&sdkp->zones_wp_offset_lock, flags);
ret = sd_zbc_do_report_zones(sdkp, sdkp->zone_wp_update_buf,
SD_BUF_SIZE,
zno * sdkp->zone_blocks, true);
- spin_lock_bh(&sdkp->zones_wp_offset_lock);
+ spin_lock_irqsave(&sdkp->zones_wp_offset_lock, flags);
if (!ret)
sd_zbc_parse_report(sdkp, sdkp->zone_wp_update_buf + 64,
zno, sd_zbc_update_wp_offset_cb,
sdkp);
}
- spin_unlock_bh(&sdkp->zones_wp_offset_lock);
+ spin_unlock_irqrestore(&sdkp->zones_wp_offset_lock, flags);
scsi_device_put(sdkp->device);
}
struct request *rq = cmd->request;
struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
unsigned int wp_offset, zno = blk_rq_zone_no(rq);
+ unsigned long flags;
blk_status_t ret;
ret = sd_zbc_cmnd_checks(cmd);
if (!blk_req_zone_write_trylock(rq))
return BLK_STS_ZONE_RESOURCE;
- spin_lock_bh(&sdkp->zones_wp_offset_lock);
+ spin_lock_irqsave(&sdkp->zones_wp_offset_lock, flags);
wp_offset = sdkp->zones_wp_offset[zno];
switch (wp_offset) {
case SD_ZBC_INVALID_WP_OFST:
*lba += wp_offset;
}
- spin_unlock_bh(&sdkp->zones_wp_offset_lock);
+ spin_unlock_irqrestore(&sdkp->zones_wp_offset_lock, flags);
if (ret)
blk_req_zone_write_unlock(rq);
return ret;
struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
unsigned int zno = blk_rq_zone_no(rq);
enum req_opf op = req_op(rq);
+ unsigned long flags;
/*
* If we got an error for a command that needs updating the write
* invalid to force an update from disk the next time a zone append
* command is issued.
*/
- spin_lock_bh(&sdkp->zones_wp_offset_lock);
+ spin_lock_irqsave(&sdkp->zones_wp_offset_lock, flags);
if (result && op != REQ_OP_ZONE_RESET_ALL) {
if (op == REQ_OP_ZONE_APPEND) {
}
unlock_wp_offset:
- spin_unlock_bh(&sdkp->zones_wp_offset_lock);
+ spin_unlock_irqrestore(&sdkp->zones_wp_offset_lock, flags);
return good_bytes;
}
MODULE_AUTHOR("Microsemi");
MODULE_DESCRIPTION("Driver for Microsemi Smart Family Controller version "
DRIVER_VERSION);
-MODULE_SUPPORTED_DEVICE("Microsemi Smart Family Controllers");
MODULE_VERSION(DRIVER_VERSION);
MODULE_LICENSE("GPL");
spin_lock(&st_use_lock);
if (STp->in_use) {
spin_unlock(&st_use_lock);
- scsi_tape_put(STp);
DEBC_printk(STp, "Device already in use.\n");
+ scsi_tape_put(STp);
return (-EBUSY);
}
if (!hba->vreg_info.vccq2 || !hba->vreg_info.vcc)
return;
- if (lpm & !hba->vreg_info.vcc->enabled)
+ if (lpm && !hba->vreg_info.vcc->enabled)
regulator_set_mode(hba->vreg_info.vccq2->reg,
REGULATOR_MODE_IDLE);
else if (!lpm)
{
int ret = 0;
struct ufs_qcom_host *host = ufshcd_get_variant(hba);
+ bool reenable_intr = false;
if (!host->core_reset) {
dev_warn(hba->dev, "%s: reset control not set\n", __func__);
goto out;
}
+ reenable_intr = hba->is_irq_enabled;
+ disable_irq(hba->irq);
+ hba->is_irq_enabled = false;
+
ret = reset_control_assert(host->core_reset);
if (ret) {
dev_err(hba->dev, "%s: core_reset assert failed, err = %d\n",
usleep_range(1000, 1100);
+ if (reenable_intr) {
+ enable_irq(hba->irq);
+ hba->is_irq_enabled = true;
+ }
+
out:
return ret;
}
16, 4, buf, __len, false); \
} while (0)
-static bool early_suspend;
-
int ufshcd_dump_regs(struct ufs_hba *hba, size_t offset, size_t len,
const char *prefix)
{
{
struct ufs_hba *hba = dev_get_drvdata(dev);
- return snprintf(buf, PAGE_SIZE, "%d\n", hba->clk_scaling.is_enabled);
+ return sysfs_emit(buf, "%d\n", hba->clk_scaling.is_enabled);
}
static ssize_t ufshcd_clkscale_enable_store(struct device *dev,
* UFS device needs urgent BKOPs.
*/
if (!hba->pm_op_in_progress &&
+ !ufshcd_eh_in_progress(hba) &&
ufshcd_is_exception_event(lrbp->ucd_rsp_ptr) &&
schedule_work(&hba->eeh_work)) {
/*
ufshcd_suspend_clkscaling(hba);
ufshcd_clk_scaling_allow(hba, false);
}
+ ufshcd_scsi_block_requests(hba);
+ /* Drain ufshcd_queuecommand() */
+ down_write(&hba->clk_scaling_lock);
+ up_write(&hba->clk_scaling_lock);
+ cancel_work_sync(&hba->eeh_work);
}
static void ufshcd_err_handling_unprepare(struct ufs_hba *hba)
{
+ ufshcd_scsi_unblock_requests(hba);
ufshcd_release(hba);
if (ufshcd_is_clkscaling_supported(hba))
ufshcd_clk_scaling_suspend(hba, false);
+ ufshcd_clear_ua_wluns(hba);
pm_runtime_put(hba->dev);
}
spin_unlock_irqrestore(hba->host->host_lock, flags);
ufshcd_err_handling_prepare(hba);
spin_lock_irqsave(hba->host->host_lock, flags);
- ufshcd_scsi_block_requests(hba);
- hba->ufshcd_state = UFSHCD_STATE_RESET;
+ if (hba->ufshcd_state != UFSHCD_STATE_ERROR)
+ hba->ufshcd_state = UFSHCD_STATE_RESET;
/* Complete requests that have door-bell cleared by h/w */
ufshcd_complete_requests(hba);
}
ufshcd_clear_eh_in_progress(hba);
spin_unlock_irqrestore(hba->host->host_lock, flags);
- ufshcd_scsi_unblock_requests(hba);
ufshcd_err_handling_unprepare(hba);
up(&hba->host_sem);
-
- if (!err && needs_reset)
- ufshcd_clear_ua_wluns(hba);
}
/**
DECLARE_COMPLETION_ONSTACK(wait);
struct request *req;
unsigned long flags;
- int free_slot, task_tag, err;
+ int task_tag, err;
/*
- * Get free slot, sleep if slots are unavailable.
- * Even though we use wait_event() which sleeps indefinitely,
- * the maximum wait time is bounded by %TM_CMD_TIMEOUT.
+ * blk_get_request() is used here only to get a free tag.
*/
req = blk_get_request(q, REQ_OP_DRV_OUT, 0);
if (IS_ERR(req))
return PTR_ERR(req);
req->end_io_data = &wait;
- free_slot = req->tag;
- WARN_ON_ONCE(free_slot < 0 || free_slot >= hba->nutmrs);
ufshcd_hold(hba, false);
spin_lock_irqsave(host->host_lock, flags);
- task_tag = hba->nutrs + free_slot;
+ blk_mq_start_request(req);
+ task_tag = req->tag;
treq->req_header.dword_0 |= cpu_to_be32(task_tag);
- memcpy(hba->utmrdl_base_addr + free_slot, treq, sizeof(*treq));
- ufshcd_vops_setup_task_mgmt(hba, free_slot, tm_function);
+ memcpy(hba->utmrdl_base_addr + task_tag, treq, sizeof(*treq));
+ ufshcd_vops_setup_task_mgmt(hba, task_tag, tm_function);
/* send command to the controller */
- __set_bit(free_slot, &hba->outstanding_tasks);
+ __set_bit(task_tag, &hba->outstanding_tasks);
/* Make sure descriptors are ready before ringing the task doorbell */
wmb();
- ufshcd_writel(hba, 1 << free_slot, REG_UTP_TASK_REQ_DOOR_BELL);
+ ufshcd_writel(hba, 1 << task_tag, REG_UTP_TASK_REQ_DOOR_BELL);
/* Make sure that doorbell is committed immediately */
wmb();
ufshcd_add_tm_upiu_trace(hba, task_tag, UFS_TM_ERR);
dev_err(hba->dev, "%s: task management cmd 0x%.2x timed-out\n",
__func__, tm_function);
- if (ufshcd_clear_tm_cmd(hba, free_slot))
- dev_WARN(hba->dev, "%s: unable clear tm cmd (slot %d) after timeout\n",
- __func__, free_slot);
+ if (ufshcd_clear_tm_cmd(hba, task_tag))
+ dev_WARN(hba->dev, "%s: unable to clear tm cmd (slot %d) after timeout\n",
+ __func__, task_tag);
err = -ETIMEDOUT;
} else {
err = 0;
- memcpy(treq, hba->utmrdl_base_addr + free_slot, sizeof(*treq));
+ memcpy(treq, hba->utmrdl_base_addr + task_tag, sizeof(*treq));
ufshcd_add_tm_upiu_trace(hba, task_tag, UFS_TM_COMP);
}
spin_lock_irqsave(hba->host->host_lock, flags);
- __clear_bit(free_slot, &hba->outstanding_tasks);
+ __clear_bit(task_tag, &hba->outstanding_tasks);
spin_unlock_irqrestore(hba->host->host_lock, flags);
+ ufshcd_release(hba);
blk_put_request(req);
- ufshcd_release(hba);
return err;
}
unsigned long flags;
ktime_t start = ktime_get();
+ hba->ufshcd_state = UFSHCD_STATE_RESET;
+
ret = ufshcd_link_startup(hba);
if (ret)
goto out;
int ret = 0;
ktime_t start = ktime_get();
- if (!hba) {
- early_suspend = true;
- return 0;
- }
-
down(&hba->host_sem);
if (!hba->is_powered)
int ret = 0;
ktime_t start = ktime_get();
- if (!hba)
- return -EINVAL;
-
- if (unlikely(early_suspend)) {
- early_suspend = false;
- down(&hba->host_sem);
- }
-
if (!hba->is_powered || pm_runtime_suspended(hba->dev))
/*
* Let the runtime resume take care of resuming
int ret = 0;
ktime_t start = ktime_get();
- if (!hba)
- return -EINVAL;
-
if (!hba->is_powered)
goto out;
else
int ret = 0;
ktime_t start = ktime_get();
- if (!hba)
- return -EINVAL;
-
if (!hba->is_powered)
goto out;
else
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
*
- * Maintained by: Jim Gill <jgill@vmware.com>
- *
*/
#include <linux/kernel.h>
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
*
- * Maintained by: Jim Gill <jgill@vmware.com>
- *
*/
#ifndef _VMW_PVSCSI_H_
return 0;
}
+static bool __init intc_map(struct irq_domain *domain, int irq)
+{
+ if (!irq_to_desc(irq) && irq_alloc_desc_at(irq, NUMA_NO_NODE) != irq) {
+ pr_err("uname to allocate IRQ %d\n", irq);
+ return false;
+ }
+
+ if (irq_domain_associate(domain, irq, irq)) {
+ pr_err("domain association failure\n");
+ return false;
+ }
+
+ return true;
+}
+
int __init register_intc_controller(struct intc_desc *desc)
{
unsigned int i, k, smp;
for (i = 0; i < hw->nr_vectors; i++) {
struct intc_vect *vect = hw->vectors + i;
unsigned int irq = evt2irq(vect->vect);
- int res;
if (!vect->enum_id)
continue;
- res = irq_create_identity_mapping(d->domain, irq);
- if (unlikely(res)) {
- if (res == -EEXIST) {
- res = irq_domain_associate(d->domain, irq, irq);
- if (unlikely(res)) {
- pr_err("domain association failure\n");
- continue;
- }
- } else {
- pr_err("can't identity map IRQ %d\n", irq);
- continue;
- }
- }
+ if (!intc_map(d->domain, irq))
+ continue;
intc_irq_xlate_set(irq, vect->enum_id, d);
intc_register_irq(desc, d, vect->enum_id, irq);
* IRQ support, each vector still needs to have
* its own backing irq_desc.
*/
- res = irq_create_identity_mapping(d->domain, irq2);
- if (unlikely(res)) {
- if (res == -EEXIST) {
- res = irq_domain_associate(d->domain,
- irq2, irq2);
- if (unlikely(res)) {
- pr_err("domain association "
- "failure\n");
- continue;
- }
- } else {
- pr_err("can't identity map IRQ %d\n",
- irq);
- continue;
- }
- }
+ if (!intc_map(d->domain, irq2))
+ continue;
vect2->enum_id = 0;
MODULE_AUTHOR("Adrian McMenamin <adrian@mcmen.demon.co.uk>");
MODULE_DESCRIPTION("Maple bus driver for Dreamcast");
MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("{{SEGA, Dreamcast/Maple}}");
static void maple_dma_handler(struct work_struct *work);
static void maple_vblank_handler(struct work_struct *work);
__be32 tag;
struct qm_fd fd;
u8 __reserved3[32];
-} __packed;
+} __packed __aligned(8);
#define QM_EQCR_VERB_VBIT 0x80
#define QM_EQCR_VERB_CMD_MASK 0x61 /* but only one value; */
#define QM_EQCR_VERB_CMD_ENQUEUE 0x01
#include <linux/platform_device.h>
#include <linux/printk.h>
#include <linux/module.h>
-#include <linux/errno.h>
#include <linux/io.h>
#include <linux/reboot.h>
#include <linux/acpi.h>
#include <linux/clk.h>
-#include <linux/console.h>
#include <linux/slab.h>
#include <linux/dma-mapping.h>
#include <linux/io.h>
struct device *dev;
void __iomem *base;
struct clk_bulk_data ahb_clks[NUM_AHB_CLKS];
- struct geni_icc_path to_core;
};
static const char * const icc_path_names[] = {"qup-core", "qup-config",
"qup-memory"};
-static struct geni_wrapper *earlycon_wrapper;
-
#define QUP_HW_VER_REG 0x4
/* Common SE registers */
int i, err;
const char *icc_names[] = {"qup-core", "qup-config", icc_ddr};
+ if (has_acpi_companion(se->dev))
+ return 0;
+
for (i = 0; i < ARRAY_SIZE(se->icc_paths); i++) {
if (!icc_names[i])
continue;
}
EXPORT_SYMBOL(geni_icc_disable);
-void geni_remove_earlycon_icc_vote(void)
-{
- struct platform_device *pdev;
- struct geni_wrapper *wrapper;
- struct device_node *parent;
- struct device_node *child;
-
- if (!earlycon_wrapper)
- return;
-
- wrapper = earlycon_wrapper;
- parent = of_get_next_parent(wrapper->dev->of_node);
- for_each_child_of_node(parent, child) {
- if (!of_device_is_compatible(child, "qcom,geni-se-qup"))
- continue;
-
- pdev = of_find_device_by_node(child);
- if (!pdev)
- continue;
-
- wrapper = platform_get_drvdata(pdev);
- icc_put(wrapper->to_core.path);
- wrapper->to_core.path = NULL;
-
- }
- of_node_put(parent);
-
- earlycon_wrapper = NULL;
-}
-EXPORT_SYMBOL(geni_remove_earlycon_icc_vote);
-
static int geni_se_probe(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
struct resource *res;
struct geni_wrapper *wrapper;
- struct console __maybe_unused *bcon;
- bool __maybe_unused has_earlycon = false;
int ret;
wrapper = devm_kzalloc(dev, sizeof(*wrapper), GFP_KERNEL);
}
}
-#ifdef CONFIG_SERIAL_EARLYCON
- for_each_console(bcon) {
- if (!strcmp(bcon->name, "qcom_geni")) {
- has_earlycon = true;
- break;
- }
- }
- if (!has_earlycon)
- goto exit;
-
- wrapper->to_core.path = devm_of_icc_get(dev, "qup-core");
- if (IS_ERR(wrapper->to_core.path))
- return PTR_ERR(wrapper->to_core.path);
- /*
- * Put minmal BW request on core clocks on behalf of early console.
- * The vote will be removed earlycon exit function.
- *
- * Note: We are putting vote on each QUP wrapper instead only to which
- * earlycon is connected because QUP core clock of different wrapper
- * share same voltage domain. If core1 is put to 0, then core2 will
- * also run at 0, if not voted. Default ICC vote will be removed ASA
- * we touch any of the core clock.
- * core1 = core2 = max(core1, core2)
- */
- ret = icc_set_bw(wrapper->to_core.path, GENI_DEFAULT_BW,
- GENI_DEFAULT_BW);
- if (ret) {
- dev_err(&pdev->dev, "%s: ICC BW voting failed for core: %d\n",
- __func__, ret);
- return ret;
- }
-
- if (of_get_compatible_child(pdev->dev.of_node, "qcom,geni-debug-uart"))
- earlycon_wrapper = wrapper;
- of_node_put(pdev->dev.of_node);
-exit:
-#endif
dev_set_drvdata(dev, wrapper);
dev_dbg(dev, "GENI SE Driver probed\n");
return devm_of_platform_populate(dev);
{
.name = "l3init", .base = 0x4ae07300,
.pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_alwon,
- .rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_012,
+ .rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_01,
.clkdm_name = "pcie"
},
{
reset->prm->data->name, id);
exit:
- if (reset->clkdm)
+ if (reset->clkdm) {
+ /* At least dra7 iva needs a delay before clkdm idle */
+ if (has_rstst)
+ udelay(1);
pdata->clkdm_allow_idle(reset->clkdm);
+ }
return ret;
}
cqspi = spi_master_get_devdata(master);
cqspi->pdev = pdev;
+ platform_set_drvdata(pdev, cqspi);
/* Obtain configuration from OF. */
ret = cqspi_of_get_pdata(cqspi);
struct apci1032_private *devpriv = dev->private;
struct comedi_subdevice *s = dev->read_subdev;
unsigned int ctrl;
+ unsigned short val;
/* check interrupt is from this device */
if ((inl(devpriv->amcc_iobase + AMCC_OP_REG_INTCSR) &
outl(ctrl & ~APCI1032_CTRL_INT_ENA, dev->iobase + APCI1032_CTRL_REG);
s->state = inl(dev->iobase + APCI1032_STATUS_REG) & 0xffff;
- comedi_buf_write_samples(s, &s->state, 1);
+ val = s->state;
+ comedi_buf_write_samples(s, &val, 1);
comedi_handle_events(dev, s);
/* enable the interrupt */
struct comedi_device *dev = d;
struct apci1500_private *devpriv = dev->private;
struct comedi_subdevice *s = dev->read_subdev;
- unsigned int status = 0;
+ unsigned short status = 0;
unsigned int val;
val = inl(devpriv->amcc + AMCC_OP_REG_INTCSR);
*
* Mask Meaning
* ---------- ------------------------------------------
- * 0x00000001 Event 1 has occurred
- * 0x00000010 Event 2 has occurred
- * 0x00000100 Counter/timer 1 has run down (not implemented)
- * 0x00001000 Counter/timer 2 has run down (not implemented)
- * 0x00010000 Counter 3 has run down (not implemented)
- * 0x00100000 Watchdog has run down (not implemented)
- * 0x01000000 Voltage error
- * 0x10000000 Short-circuit error
+ * 0b00000001 Event 1 has occurred
+ * 0b00000010 Event 2 has occurred
+ * 0b00000100 Counter/timer 1 has run down (not implemented)
+ * 0b00001000 Counter/timer 2 has run down (not implemented)
+ * 0b00010000 Counter 3 has run down (not implemented)
+ * 0b00100000 Watchdog has run down (not implemented)
+ * 0b01000000 Voltage error
+ * 0b10000000 Short-circuit error
*/
comedi_buf_write_samples(s, &status, 1);
comedi_handle_events(dev, s);
static int pci1710_ai_read_sample(struct comedi_device *dev,
struct comedi_subdevice *s,
unsigned int cur_chan,
- unsigned int *val)
+ unsigned short *val)
{
const struct boardtype *board = dev->board_ptr;
struct pci1710_private *devpriv = dev->private;
- unsigned int sample;
+ unsigned short sample;
unsigned int chan;
sample = inw(dev->iobase + PCI171X_AD_DATA_REG);
pci1710_ai_setup_chanlist(dev, s, &insn->chanspec, 1, 1);
for (i = 0; i < insn->n; i++) {
- unsigned int val;
+ unsigned short val;
/* start conversion */
outw(0, dev->iobase + PCI171X_SOFTTRG_REG);
{
struct comedi_cmd *cmd = &s->async->cmd;
unsigned int status;
- unsigned int val;
+ unsigned short val;
int ret;
status = inw(dev->iobase + PCI171X_STATUS_REG);
}
for (i = 0; i < devpriv->max_samples; i++) {
- unsigned int val;
+ unsigned short val;
int ret;
ret = pci1710_ai_read_sample(dev, s, s->async->cur_chan, &val);
handled = pc236_intr_check(dev);
if (dev->attached && handled) {
- comedi_buf_write_samples(s, &s->state, 1);
+ unsigned short val = 0;
+
+ comedi_buf_write_samples(s, &val, 1);
comedi_handle_events(dev, s);
}
return IRQ_RETVAL(handled);
devpriv->amcc + AMCC_OP_REG_INTCSR);
ret = request_irq(pcidev->irq, cb_pcidas_interrupt, IRQF_SHARED,
- dev->board_name, dev);
+ "cb_pcidas", dev);
if (ret) {
dev_dbg(dev->class_dev, "unable to allocate irq %d\n",
pcidev->irq);
init_stc_registers(dev);
retval = request_irq(pcidev->irq, handle_interrupt, IRQF_SHARED,
- dev->board_name, dev);
+ "cb_pcidas64", dev);
if (retval) {
dev_dbg(dev->class_dev, "unable to allocate irq %u\n",
pcidev->irq);
struct comedi_device *dev = d;
struct comedi_subdevice *s = dev->read_subdev;
unsigned int ctrl;
+ unsigned short val = 0;
ctrl = inb(dev->iobase + PARPORT_CTRL_REG);
if (!(ctrl & PARPORT_CTRL_IRQ_ENA))
return IRQ_NONE;
- comedi_buf_write_samples(s, &s->state, 1);
+ comedi_buf_write_samples(s, &val, 1);
comedi_handle_events(dev, s);
return IRQ_HANDLED;
if (status & DAS6402_STATUS_FFULL) {
async->events |= COMEDI_CB_OVERFLOW;
} else if (status & DAS6402_STATUS_FFNE) {
- unsigned int val;
+ unsigned short val;
val = das6402_ai_read_sample(dev, s);
comedi_buf_write_samples(s, &val, 1);
struct comedi_cmd *cmd;
unsigned long irq_flags;
unsigned int status;
- unsigned int val;
+ unsigned short val;
bool fifo_empty;
bool fifo_overflow;
int i;
{
struct comedi_device *dev = d;
unsigned char intstat;
- unsigned int val;
+ unsigned short val;
int i;
if (!dev->attached) {
struct comedi_subdevice *s = dev->read_subdev;
int i;
int c = 0;
- unsigned int lval;
+ unsigned short lval;
if (!dev->attached)
return IRQ_NONE;
return IRQ_NONE;
if (status & NI6527_STATUS_EDGE) {
- comedi_buf_write_samples(s, &s->state, 1);
+ unsigned short val = 0;
+
+ comedi_buf_write_samples(s, &val, 1);
comedi_handle_events(dev, s);
}
struct comedi_device *dev = d;
struct comedi_subdevice *s = dev->read_subdev;
unsigned int status;
+ unsigned short val = 0;
status = readb(dev->mmio + NI_65XX_STATUS_REG);
if ((status & NI_65XX_STATUS_INT) == 0)
writeb(NI_65XX_CLR_EDGE_INT | NI_65XX_CLR_OVERFLOW_INT,
dev->mmio + NI_65XX_CLR_REG);
- comedi_buf_write_samples(s, &s->state, 1);
+ comedi_buf_write_samples(s, &val, 1);
comedi_handle_events(dev, s);
return IRQ_HANDLED;
struct comedi_device *dev = d;
struct comedi_subdevice *s = dev->read_subdev;
struct comedi_cmd *cmd = &s->async->cmd;
- unsigned int data;
+ unsigned short data;
if (!dev->attached) {
dev_err(dev->class_dev, "spurious interrupt\n");
struct pcl726_private *devpriv = dev->private;
if (devpriv->cmd_running) {
+ unsigned short val = 0;
+
pcl726_intr_cancel(dev, s);
- comedi_buf_write_samples(s, &s->state, 1);
+ comedi_buf_write_samples(s, &val, 1);
comedi_handle_events(dev, s);
}
static bool pcl818_ai_write_sample(struct comedi_device *dev,
struct comedi_subdevice *s,
- unsigned int chan, unsigned int val)
+ unsigned int chan, unsigned short val)
{
struct pcl818_private *devpriv = dev->private;
struct comedi_cmd *cmd = &s->async->cmd;
MODULE_AUTHOR("Manuel Gebele <forensixs@gmx.de>");
MODULE_DESCRIPTION("Velleman USB Board Low-Level Driver");
-MODULE_SUPPORTED_DEVICE("K8055/K8061 aka VM110/VM140");
MODULE_LICENSE("GPL");
{
struct ks_wlan_private *priv = netdev_priv(dev);
struct iw_scan_req *req = NULL;
+ int len;
if (priv->sleep_mode == SLP_SLEEP)
return -EPERM;
if (wrqu->data.length == sizeof(struct iw_scan_req) &&
wrqu->data.flags & IW_SCAN_THIS_ESSID) {
req = (struct iw_scan_req *)extra;
- priv->scan_ssid_len = req->essid_len;
- memcpy(priv->scan_ssid, req->essid, priv->scan_ssid_len);
+ len = min_t(int, req->essid_len, IW_ESSID_MAX_SIZE);
+ priv->scan_ssid_len = len;
+ memcpy(priv->scan_ssid, req->essid, len);
} else {
priv->scan_ssid_len = 0;
}
p = rtw_get_ie(ie + _BEACON_IE_OFFSET_, WLAN_EID_SSID, &ie_len,
pbss_network->ie_length - _BEACON_IE_OFFSET_);
if (p && ie_len > 0) {
+ ie_len = min_t(int, ie_len, sizeof(pbss_network->ssid.ssid));
memset(&pbss_network->ssid, 0, sizeof(struct ndis_802_11_ssid));
memcpy(pbss_network->ssid.ssid, p + 2, ie_len);
pbss_network->ssid.ssid_length = ie_len;
p = rtw_get_ie(ie + _BEACON_IE_OFFSET_, WLAN_EID_SUPP_RATES, &ie_len,
pbss_network->ie_length - _BEACON_IE_OFFSET_);
if (p) {
+ ie_len = min_t(int, ie_len, NDIS_802_11_LENGTH_RATES_EX);
memcpy(supportRate, p + 2, ie_len);
supportRateNum = ie_len;
}
p = rtw_get_ie(ie + _BEACON_IE_OFFSET_, WLAN_EID_EXT_SUPP_RATES,
&ie_len, pbss_network->ie_length - _BEACON_IE_OFFSET_);
if (p) {
+ ie_len = min_t(int, ie_len,
+ NDIS_802_11_LENGTH_RATES_EX - supportRateNum);
memcpy(supportRate + supportRateNum, p + 2, ie_len);
supportRateNum += ie_len;
}
pht_cap->mcs.rx_mask[0] = 0xff;
pht_cap->mcs.rx_mask[1] = 0x0;
+ ie_len = min_t(int, ie_len, sizeof(pmlmepriv->htpriv.ht_cap));
memcpy(&pmlmepriv->htpriv.ht_cap, p + 2, ie_len);
}
break;
}
sec_len = *(pos++); len -= 1;
- if (sec_len > 0 && sec_len <= len) {
+ if (sec_len > 0 &&
+ sec_len <= len &&
+ sec_len <= 32) {
ssid[ssid_index].ssid_length = sec_len;
- memcpy(ssid[ssid_index].ssid, pos, ssid[ssid_index].ssid_length);
+ memcpy(ssid[ssid_index].ssid, pos, sec_len);
ssid_index++;
}
pos += sec_len;
config RTLLIB_CRYPTO_TKIP
tristate "Support for rtllib TKIP crypto"
depends on RTLLIB
+ select CRYPTO
select CRYPTO_LIB_ARC4
select CRYPTO_MICHAEL_MIC
default y
struct iw_scan_req *req = (struct iw_scan_req *)b;
if (req->essid_len) {
- ieee->current_network.ssid_len = req->essid_len;
- memcpy(ieee->current_network.ssid, req->essid,
- req->essid_len);
+ int len = min_t(int, req->essid_len, IW_ESSID_MAX_SIZE);
+
+ ieee->current_network.ssid_len = len;
+ memcpy(ieee->current_network.ssid, req->essid, len);
}
}
bool bWithAironetIE;
bool bCkipSupported;
bool bCcxRmEnable;
- u16 CcxRmState[2];
+ u8 CcxRmState[2];
bool bMBssidValid;
u8 MBssidMask;
u8 MBssid[ETH_ALEN];
info_element->data[2] == 0x96 &&
info_element->data[3] == 0x01) {
if (info_element->len == 6) {
- memcpy(network->CcxRmState, &info_element[4], 2);
+ memcpy(network->CcxRmState, &info_element->data[4], 2);
if (network->CcxRmState[0] != 0)
network->bCcxRmEnable = true;
else
struct iw_scan_req *req = (struct iw_scan_req *)b;
if (req->essid_len) {
- ieee->current_network.ssid_len = req->essid_len;
- memcpy(ieee->current_network.ssid, req->essid, req->essid_len);
+ int len = min_t(int, req->essid_len, IW_ESSID_MAX_SIZE);
+
+ ieee->current_network.ssid_len = len;
+ memcpy(ieee->current_network.ssid, req->essid, len);
}
}
psurveyPara->ss_ssidlen = 0;
memset(psurveyPara->ss_ssid, 0, IW_ESSID_MAX_SIZE + 1);
if (pssid && pssid->SsidLength) {
- memcpy(psurveyPara->ss_ssid, pssid->Ssid, pssid->SsidLength);
- psurveyPara->ss_ssidlen = cpu_to_le32(pssid->SsidLength);
+ int len = min_t(int, pssid->SsidLength, IW_ESSID_MAX_SIZE);
+
+ memcpy(psurveyPara->ss_ssid, pssid->Ssid, len);
+ psurveyPara->ss_ssidlen = cpu_to_le32(len);
}
set_fwstate(pmlmepriv, _FW_UNDER_SURVEY);
r8712_enqueue_cmd(pcmdpriv, ph2c);
struct iw_point *dwrq = (struct iw_point *)awrq;
len = dwrq->length;
- ext = memdup_user(dwrq->pointer, len);
+ ext = strndup_user(dwrq->pointer, len);
if (IS_ERR(ext))
return PTR_ERR(ext);
u16 reserved;
struct ieee80211_cts data;
u16 reserved2;
-} __packed;
+} __packed __aligned(2);
struct vnt_cts_fb {
struct vnt_phy_field b;
__le16 cts_duration_ba_f1;
struct ieee80211_cts data;
u16 reserved2;
-} __packed;
+} __packed __aligned(2);
struct vnt_tx_fifo_head {
u8 tx_key[WLAN_KEY_LEN_CCMP];
* Copyright (c) 2017-2020, Silicon Laboratories, Inc.
* Copyright (c) 2010, ST-Ericsson
*/
+#include <linux/gpio/consumer.h>
#include <net/mac80211.h>
#include "bh.h"
#ifndef WFX_BH_H
#define WFX_BH_H
+#include <linux/atomic.h>
+#include <linux/wait.h>
+#include <linux/workqueue.h>
+
struct wfx_dev;
struct wfx_hif {
#ifndef WFX_BUS_H
#define WFX_BUS_H
+#include <linux/mmc/sdio_func.h>
+#include <linux/spi/spi.h>
+
#define WFX_REG_CONFIG 0x0
#define WFX_REG_CONTROL 0x1
#define WFX_REG_IN_OUT_QUEUE 0x2
* Copyright (c) 2017-2020, Silicon Laboratories, Inc.
* Copyright (c) 2010, ST-Ericsson
*/
+#include <linux/module.h>
#include <linux/mmc/sdio.h>
#include <linux/mmc/sdio_func.h>
#include <linux/mmc/card.h>
+#include <linux/interrupt.h>
#include <linux/of_irq.h>
+#include <linux/irq.h>
#include "bus.h"
#include "wfx.h"
+#include "hwio.h"
+#include "main.h"
+#include "bh.h"
static const struct wfx_platform_data wfx_sdio_pdata = {
.file_fw = "wfm_wf200",
* Copyright (c) 2011, Sagrad Inc.
* Copyright (c) 2010, ST-Ericsson
*/
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
#include <linux/spi/spi.h>
+#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/of.h>
#include "bus.h"
#include "wfx.h"
+#include "hwio.h"
+#include "main.h"
+#include "bh.h"
#define SET_WRITE 0x7FFF /* usage: and operation */
#define SET_READ 0x8000 /* usage: or operation */
* Copyright (c) 2017-2020, Silicon Laboratories, Inc.
* Copyright (c) 2010, ST-Ericsson
*/
+#include <linux/etherdevice.h>
+#include <net/mac80211.h>
+
#include "data_rx.h"
#include "wfx.h"
+#include "bh.h"
+#include "sta.h"
static void wfx_rx_handle_ba(struct wfx_vif *wvif, struct ieee80211_mgmt *mgmt)
{
* Copyright (c) 2010, ST-Ericsson
*/
#include <net/mac80211.h>
+#include <linux/etherdevice.h>
+#include "data_tx.h"
#include "wfx.h"
+#include "bh.h"
#include "sta.h"
+#include "queue.h"
+#include "debug.h"
#include "traces.h"
#include "hif_tx_mib.h"
#ifndef WFX_DATA_TX_H
#define WFX_DATA_TX_H
+#include <linux/list.h>
+#include <net/mac80211.h>
+
#include "hif_api_cmd.h"
#include "hif_api_mib.h"
* Copyright (c) 2017-2020, Silicon Laboratories, Inc.
* Copyright (c) 2010, ST-Ericsson
*/
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/crc32.h>
+
#include "debug.h"
#include "wfx.h"
#include "sta.h"
+#include "main.h"
+#include "hif_tx.h"
#include "hif_tx_mib.h"
#define CREATE_TRACE_POINTS
* Copyright (c) 2010, ST-Ericsson
*/
#include <linux/firmware.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
#include <linux/bitfield.h>
#include "fwio.h"
#ifndef WFX_HIF_API_CMD_H
#define WFX_HIF_API_CMD_H
+#include <linux/ieee80211.h>
+
+#include "hif_api_general.h"
+
enum hif_requests_ids {
HIF_REQ_ID_RESET = 0x0a,
HIF_REQ_ID_READ_MIB = 0x05,
#ifndef WFX_HIF_API_GENERAL_H
#define WFX_HIF_API_GENERAL_H
+#ifdef __KERNEL__
+#include <linux/types.h>
+#include <linux/if_ether.h>
+#else
+#include <net/ethernet.h>
+#include <stdint.h>
+#define __packed __attribute__((__packed__))
+#endif
+
#define HIF_ID_IS_INDICATION 0x80
#define HIF_COUNTER_MAX 7
* Copyright (c) 2017-2020, Silicon Laboratories, Inc.
* Copyright (c) 2010, ST-Ericsson
*/
+#include <linux/etherdevice.h>
+
+#include "hif_tx.h"
#include "wfx.h"
+#include "bh.h"
#include "hwio.h"
#include "debug.h"
#include "sta.h"
* Copyright (c) 2010, ST-Ericsson
* Copyright (C) 2010, ST-Ericsson SA
*/
+
+#include <linux/etherdevice.h>
+
#include "wfx.h"
+#include "hif_tx.h"
#include "hif_tx_mib.h"
+#include "hif_api_mib.h"
int hif_set_output_power(struct wfx_vif *wvif, int val)
{
* Copyright (c) 2017-2020, Silicon Laboratories, Inc.
* Copyright (c) 2010, ST-Ericsson
*/
+#include <linux/kernel.h>
+#include <linux/delay.h>
#include <linux/slab.h>
#include "hwio.h"
#include "wfx.h"
+#include "bus.h"
#include "traces.h"
/*
#ifndef WFX_HWIO_H
#define WFX_HWIO_H
+#include <linux/types.h>
+
struct wfx_dev;
int wfx_data_read(struct wfx_dev *wdev, void *buf, size_t buf_len);
* Copyright (c) 2017-2020, Silicon Laboratories, Inc.
* Copyright (c) 2010, ST-Ericsson
*/
+#include <linux/etherdevice.h>
#include <net/mac80211.h>
#include "key.h"
#include "wfx.h"
+#include "hif_tx_mib.h"
static int wfx_alloc_key(struct wfx_dev *wdev)
{
#ifndef WFX_KEY_H
#define WFX_KEY_H
+#include <net/mac80211.h>
+
struct wfx_dev;
struct wfx_vif;
* Copyright (c) 2006, Michael Wu <flamingice@sourmilk.net>
* Copyright (c) 2004-2006 Jean-Baptiste Note <jbnote@gmail.com>, et al.
*/
+#include <linux/module.h>
#include <linux/of.h>
#include <linux/of_net.h>
+#include <linux/gpio/consumer.h>
#include <linux/mmc/sdio_func.h>
#include <linux/spi/spi.h>
+#include <linux/etherdevice.h>
#include <linux/firmware.h>
+#include "main.h"
#include "wfx.h"
#include "fwio.h"
#include "hwio.h"
#include "bus.h"
+#include "bh.h"
#include "sta.h"
#include "key.h"
#include "scan.h"
#include "debug.h"
+#include "data_tx.h"
#include "hif_tx_mib.h"
+#include "hif_api_cmd.h"
#define WFX_PDS_MAX_SIZE 1500
#ifndef WFX_MAIN_H
#define WFX_MAIN_H
+#include <linux/device.h>
#include <linux/gpio/consumer.h>
+#include "hif_api_general.h"
+
struct wfx_dev;
struct hwbus_ops;
* Copyright (c) 2017-2020, Silicon Laboratories, Inc.
* Copyright (c) 2010, ST-Ericsson
*/
+#include <linux/sched.h>
#include <net/mac80211.h>
+#include "queue.h"
#include "wfx.h"
+#include "sta.h"
+#include "data_tx.h"
#include "traces.h"
void wfx_tx_lock(struct wfx_dev *wdev)
#ifndef WFX_QUEUE_H
#define WFX_QUEUE_H
+#include <linux/skbuff.h>
+#include <linux/atomic.h>
+
struct wfx_dev;
struct wfx_vif;
#ifndef WFX_SCAN_H
#define WFX_SCAN_H
+#include <net/mac80211.h>
+
struct wfx_dev;
struct wfx_vif;
* Copyright (c) 2017-2020, Silicon Laboratories, Inc.
* Copyright (c) 2010, ST-Ericsson
*/
+#include <linux/etherdevice.h>
#include <net/mac80211.h>
#include "sta.h"
#include "wfx.h"
+#include "fwio.h"
+#include "bh.h"
+#include "key.h"
#include "scan.h"
+#include "debug.h"
+#include "hif_tx.h"
#include "hif_tx_mib.h"
#define HIF_MAX_ARP_IP_ADDRTABLE_ENTRIES 2
#ifndef WFX_STA_H
#define WFX_STA_H
+#include <net/mac80211.h>
+
struct wfx_dev;
struct wfx_vif;
#define _WFX_TRACE_H
#include <linux/tracepoint.h>
+#include <net/mac80211.h>
#include "bus.h"
+#include "hif_api_cmd.h"
+#include "hif_api_mib.h"
/* The hell below need some explanations. For each symbolic number, we need to
* define it with TRACE_DEFINE_ENUM() and in a list for __print_symbolic.
#ifndef WFX_H
#define WFX_H
+#include <linux/completion.h>
+#include <linux/workqueue.h>
+#include <linux/mutex.h>
#include <linux/nospec.h>
#include <net/mac80211.h>
target_get_sess_cmd(&cmd->se_cmd, true);
+ cmd->se_cmd.tag = (__force u32)cmd->init_task_tag;
cmd->sense_reason = target_cmd_init_cdb(&cmd->se_cmd, hdr->cdb);
if (cmd->sense_reason) {
if (cmd->sense_reason == TCM_OUT_OF_RESOURCES) {
if (cmd->sense_reason)
goto attach_cmd;
- /* only used for printks or comparing with ->ref_task_tag */
- cmd->se_cmd.tag = (__force u32)cmd->init_task_tag;
cmd->sense_reason = target_cmd_parse_cdb(&cmd->se_cmd);
if (cmd->sense_reason)
goto attach_cmd;
if (!bio) {
new_bio:
nr_vecs = bio_max_segs(nr_pages);
- nr_pages -= nr_vecs;
/*
* Calls bio_kmalloc() and sets bio->bi_end_io()
*/
return 0;
fail:
+ if (bio)
+ bio_put(bio);
+ while (req->bio) {
+ bio = req->bio;
+ req->bio = bio->bi_next;
+ bio_put(bio);
+ }
+ req->biotail = NULL;
return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
}
MODULE_AUTHOR("Linaro");
MODULE_DESCRIPTION("OP-TEE driver");
-MODULE_SUPPORTED_DEVICE("");
MODULE_VERSION("1.0");
MODULE_LICENSE("GPL v2");
MODULE_ALIAS("platform:optee");
{
struct cooling_dev_stats *stats = cdev->stats;
+ if (!stats)
+ return;
+
spin_lock(&stats->lock);
if (stats->state == new_state)
ret = tb_retimer_nvm_add(rt);
if (ret) {
dev_err(&rt->dev, "failed to add NVM devices: %d\n", ret);
- device_del(&rt->dev);
+ device_unregister(&rt->dev);
return ret;
}
*/
int tb_retimer_scan(struct tb_port *port)
{
- u32 status[TB_MAX_RETIMER_INDEX] = {};
+ u32 status[TB_MAX_RETIMER_INDEX + 1] = {};
int ret, i, last_idx = 0;
if (!port->cap_usb4)
tb_dump_port(port->sw->tb, &port->config);
- /* Control port does not need HopID allocation */
- if (port->port) {
- ida_init(&port->in_hopids);
- ida_init(&port->out_hopids);
- }
-
INIT_LIST_HEAD(&port->list);
return 0;
dma_port_free(sw->dma_port);
tb_switch_for_each_port(sw, port) {
- if (!port->disabled) {
- ida_destroy(&port->in_hopids);
- ida_destroy(&port->out_hopids);
- }
+ ida_destroy(&port->in_hopids);
+ ida_destroy(&port->out_hopids);
}
kfree(sw->uuid);
/* minimum setup for tb_find_cap and tb_drom_read to work */
sw->ports[i].sw = sw;
sw->ports[i].port = i;
+
+ /* Control port does not need HopID allocation */
+ if (i) {
+ ida_init(&sw->ports[i].in_hopids);
+ ida_init(&sw->ports[i].out_hopids);
+ }
}
ret = tb_switch_find_vse_cap(sw, TB_VSE_CAP_PLUG_EVENTS);
parent->boot = true;
parent = tb_switch_parent(parent);
}
+ } else if (tb_tunnel_is_dp(tunnel)) {
+ /* Keep the domain from powering down */
+ pm_runtime_get_sync(&tunnel->src_port->sw->dev);
+ pm_runtime_get_sync(&tunnel->dst_port->sw->dev);
}
list_add_tail(&tunnel->list, &tcm->tunnel_list);
static int hvcs_probe(struct vio_dev *dev,
const struct vio_device_id *id);
-static int hvcs_remove(struct vio_dev *dev);
static int __init hvcs_module_init(void);
static void __exit hvcs_module_exit(void);
static int hvcs_initialize(void);
return 0;
}
-static int hvcs_remove(struct vio_dev *dev)
+static void hvcs_remove(struct vio_dev *dev)
{
struct hvcs_struct *hvcsd = dev_get_drvdata(&dev->dev);
unsigned long flags;
printk(KERN_INFO "HVCS: vty-server@%X removed from the"
" vio bus.\n", dev->unit_address);
- return 0;
};
static struct vio_driver hvcs_vio_driver = {
wake_up_interruptible(&tty->link->read_wait);
wake_up_interruptible(&tty->link->write_wait);
if (tty->driver->subtype == PTY_TYPE_MASTER) {
- struct file *f;
-
+ set_bit(TTY_OTHER_CLOSED, &tty->flags);
#ifdef CONFIG_UNIX98_PTYS
if (tty->driver == ptm_driver) {
mutex_lock(&devpts_mutex);
mutex_unlock(&devpts_mutex);
}
#endif
-
- /*
- * This hack is required because a program can open a
- * pty and redirect a console to it, but if the pty is
- * closed and the console is not released, then the
- * slave side will never close. So release the
- * redirect when the master closes.
- */
- f = tty_release_redirect(tty->link);
- if (f)
- fput(f);
+ tty_vhangup(tty->link);
}
}
MODULE_AUTHOR("Michael Anderson <mjanders@us.ibm.com>");
MODULE_DESCRIPTION("IBM iSeries Serial IOA driver");
-MODULE_SUPPORTED_DEVICE
- ("IBM iSeries 2745, 2771, 2772, 2742, 2793 and 2805 Communications adapters");
MODULE_LICENSE("GPL");
MODULE_FIRMWARE("icom_call_setup.bin");
MODULE_FIRMWARE("icom_res_dce.bin");
MODULE_AUTHOR("Digi International, https://www.digi.com");
MODULE_DESCRIPTION("Driver for the Digi International Neo and Classic PCI based product line");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("jsm");
#define JSM_DRIVER_NAME "jsm"
#define NR_PORTS 32
max310x_port_update(port, MAX310X_MODE1_REG,
MAX310X_MODE1_TRNSCVCTRL_BIT, 0);
- /* Reset FIFOs */
- max310x_port_write(port, MAX310X_MODE2_REG,
- MAX310X_MODE2_FIFORST_BIT);
+ /* Configure MODE2 register & Reset FIFOs*/
+ val = MAX310X_MODE2_RXEMPTINV_BIT | MAX310X_MODE2_FIFORST_BIT;
+ max310x_port_write(port, MAX310X_MODE2_REG, val);
max310x_port_update(port, MAX310X_MODE2_REG,
MAX310X_MODE2_FIFORST_BIT, 0);
/* Clear IRQ status register */
max310x_port_read(port, MAX310X_IRQSTS_REG);
- /*
- * Let's ask for an interrupt after a timeout equivalent to
- * the receiving time of 4 characters after the last character
- * has been received.
- */
- max310x_port_write(port, MAX310X_RXTO_REG, 4);
-
- /*
- * Make sure we also get RX interrupts when the RX FIFO is
- * filling up quickly, so get an interrupt when half of the RX
- * FIFO has been filled in.
- */
- max310x_port_write(port, MAX310X_FIFOTRIGLVL_REG,
- MAX310X_FIFOTRIGLVL_RX(MAX310X_FIFO_SIZE / 2));
-
- /* Enable RX timeout interrupt in LSR */
- max310x_port_write(port, MAX310X_LSR_IRQEN_REG,
- MAX310X_LSR_RXTO_BIT);
-
- /* Enable LSR, RX FIFO trigger, CTS change interrupts */
- val = MAX310X_IRQ_LSR_BIT | MAX310X_IRQ_RXFIFO_BIT | MAX310X_IRQ_TXEMPTY_BIT;
+ /* Enable RX, TX, CTS change interrupts */
+ val = MAX310X_IRQ_RXEMPTY_BIT | MAX310X_IRQ_TXEMPTY_BIT;
max310x_port_write(port, MAX310X_IRQEN_REG, val | MAX310X_IRQ_CTS_BIT);
return 0;
struct console *con) { }
#endif
-static int qcom_geni_serial_earlycon_exit(struct console *con)
-{
- geni_remove_earlycon_icc_vote();
- return 0;
-}
-
static struct qcom_geni_private_data earlycon_private_data;
static int __init qcom_geni_serial_earlycon_setup(struct earlycon_device *dev,
writel(stop_bit_len, uport->membase + SE_UART_TX_STOP_BIT_LEN);
dev->con->write = qcom_geni_serial_earlycon_write;
- dev->con->exit = qcom_geni_serial_earlycon_exit;
dev->con->setup = NULL;
qcom_geni_serial_enable_early_read(&se, dev->con);
* @tty: tty device
*
* This is available to the pty code so if the master closes, if the
- * slave is a redirect it can release the redirect. It returns the
- * filp for the redirect, which must be fput when the operations on
- * the tty are completed.
+ * slave is a redirect it can release the redirect.
*/
struct file *tty_release_redirect(struct tty_struct *tty)
{
return f;
}
+EXPORT_SYMBOL_GPL(tty_release_redirect);
/**
* __tty_hangup - actual handler for hangup events
return -ESHUTDOWN;
}
+ /* Requests has been dequeued during disabling endpoint. */
+ if (!(pep->ep_state & EP_ENABLED))
+ return 0;
+
spin_lock_irqsave(&pdev->lock, flags);
ret = cdnsp_ep_dequeue(pep, to_cdnsp_request(request));
spin_unlock_irqrestore(&pdev->lock, flags);
* inverted in the first TDs isoc TRB.
*/
field = TRB_TYPE(TRB_ISOC) | TRB_TLBPC(last_burst_pkt) |
- start_cycle ? 0 : 1 | TRB_SIA | TRB_TBC(burst_count);
+ TRB_SIA | TRB_TBC(burst_count);
+
+ if (!start_cycle)
+ field |= TRB_CYCLE;
/* Fill the rest of the TRB fields, and remaining normal TRBs. */
for (i = 0; i < trbs_per_td; i++) {
#define acm_send_break(acm, ms) \
acm_ctrl_msg(acm, USB_CDC_REQ_SEND_BREAK, ms, NULL, 0)
-static void acm_kill_urbs(struct acm *acm)
+static void acm_poison_urbs(struct acm *acm)
{
int i;
- usb_kill_urb(acm->ctrlurb);
+ usb_poison_urb(acm->ctrlurb);
for (i = 0; i < ACM_NW; i++)
- usb_kill_urb(acm->wb[i].urb);
+ usb_poison_urb(acm->wb[i].urb);
for (i = 0; i < acm->rx_buflimit; i++)
- usb_kill_urb(acm->read_urbs[i]);
+ usb_poison_urb(acm->read_urbs[i]);
+}
+
+static void acm_unpoison_urbs(struct acm *acm)
+{
+ int i;
+
+ for (i = 0; i < acm->rx_buflimit; i++)
+ usb_unpoison_urb(acm->read_urbs[i]);
+ for (i = 0; i < ACM_NW; i++)
+ usb_unpoison_urb(acm->wb[i].urb);
+ usb_unpoison_urb(acm->ctrlurb);
}
+
/*
* Write buffer management.
* All of these assume proper locks taken by the caller.
rc = usb_submit_urb(wb->urb, GFP_ATOMIC);
if (rc < 0) {
- dev_err(&acm->data->dev,
- "%s - usb_submit_urb(write bulk) failed: %d\n",
- __func__, rc);
+ if (rc != -EPERM)
+ dev_err(&acm->data->dev,
+ "%s - usb_submit_urb(write bulk) failed: %d\n",
+ __func__, rc);
acm_write_done(acm, wb);
}
return rc;
acm->iocount.dsr++;
if (difference & ACM_CTRL_DCD)
acm->iocount.dcd++;
- if (newctrl & ACM_CTRL_BRK)
+ if (newctrl & ACM_CTRL_BRK) {
acm->iocount.brk++;
+ tty_insert_flip_char(&acm->port, 0, TTY_BREAK);
+ }
if (newctrl & ACM_CTRL_RI)
acm->iocount.rng++;
if (newctrl & ACM_CTRL_FRAMING)
dev_vdbg(&acm->data->dev, "got urb %d, len %d, status %d\n",
rb->index, urb->actual_length, status);
- if (!acm->dev) {
- dev_dbg(&acm->data->dev, "%s - disconnected\n", __func__);
- return;
- }
-
switch (status) {
case 0:
usb_mark_last_busy(acm->dev);
res = acm_set_control(acm, val);
if (res && (acm->ctrl_caps & USB_CDC_CAP_LINE))
- dev_err(&acm->control->dev, "failed to set dtr/rts\n");
+ /* This is broken in too many devices to spam the logs */
+ dev_dbg(&acm->control->dev, "failed to set dtr/rts\n");
}
static int acm_port_activate(struct tty_port *port, struct tty_struct *tty)
* Need to grab write_lock to prevent race with resume, but no need to
* hold it due to the tty-port initialised flag.
*/
+ acm_poison_urbs(acm);
spin_lock_irq(&acm->write_lock);
spin_unlock_irq(&acm->write_lock);
usb_autopm_put_interface_async(acm->control);
}
- acm_kill_urbs(acm);
+ acm_unpoison_urbs(acm);
+
}
static void acm_tty_cleanup(struct tty_struct *tty)
if (!combined_interfaces && intf != control_interface)
return -ENODEV;
- if (!combined_interfaces && usb_interface_claimed(data_interface)) {
- /* valid in this context */
- dev_dbg(&intf->dev, "The data interface isn't available\n");
- return -EBUSY;
- }
-
-
if (data_interface->cur_altsetting->desc.bNumEndpoints < 2 ||
control_interface->cur_altsetting->desc.bNumEndpoints == 0)
return -EINVAL;
dev_dbg(&intf->dev, "interfaces are valid\n");
acm = kzalloc(sizeof(struct acm), GFP_KERNEL);
- if (acm == NULL)
- goto alloc_fail;
+ if (!acm)
+ return -ENOMEM;
tty_port_init(&acm->port);
acm->port.ops = &acm_port_ops;
minor = acm_alloc_minor(acm);
if (minor < 0)
- goto alloc_fail1;
+ goto err_put_port;
acm->minor = minor;
acm->dev = usb_dev;
buf = usb_alloc_coherent(usb_dev, ctrlsize, GFP_KERNEL, &acm->ctrl_dma);
if (!buf)
- goto alloc_fail1;
+ goto err_put_port;
acm->ctrl_buffer = buf;
if (acm_write_buffers_alloc(acm) < 0)
- goto alloc_fail2;
+ goto err_free_ctrl_buffer;
acm->ctrlurb = usb_alloc_urb(0, GFP_KERNEL);
if (!acm->ctrlurb)
- goto alloc_fail3;
+ goto err_free_write_buffers;
for (i = 0; i < num_rx_buf; i++) {
struct acm_rb *rb = &(acm->read_buffers[i]);
rb->base = usb_alloc_coherent(acm->dev, readsize, GFP_KERNEL,
&rb->dma);
if (!rb->base)
- goto alloc_fail4;
+ goto err_free_read_urbs;
rb->index = i;
rb->instance = acm;
urb = usb_alloc_urb(0, GFP_KERNEL);
if (!urb)
- goto alloc_fail4;
+ goto err_free_read_urbs;
urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
urb->transfer_dma = rb->dma;
struct acm_wb *snd = &(acm->wb[i]);
snd->urb = usb_alloc_urb(0, GFP_KERNEL);
- if (snd->urb == NULL)
- goto alloc_fail5;
+ if (!snd->urb)
+ goto err_free_write_urbs;
if (usb_endpoint_xfer_int(epwrite))
usb_fill_int_urb(snd->urb, usb_dev, acm->out,
i = device_create_file(&intf->dev, &dev_attr_bmCapabilities);
if (i < 0)
- goto alloc_fail5;
+ goto err_free_write_urbs;
if (h.usb_cdc_country_functional_desc) { /* export the country data */
struct usb_cdc_country_functional_desc * cfd =
acm->nb_index = 0;
acm->nb_size = 0;
- dev_info(&intf->dev, "ttyACM%d: USB ACM device\n", minor);
-
acm->line.dwDTERate = cpu_to_le32(9600);
acm->line.bDataBits = 8;
acm_set_line(acm, &acm->line);
- usb_driver_claim_interface(&acm_driver, data_interface, acm);
- usb_set_intfdata(data_interface, acm);
+ if (!acm->combined_interfaces) {
+ rv = usb_driver_claim_interface(&acm_driver, data_interface, acm);
+ if (rv)
+ goto err_remove_files;
+ }
tty_dev = tty_port_register_device(&acm->port, acm_tty_driver, minor,
&control_interface->dev);
if (IS_ERR(tty_dev)) {
rv = PTR_ERR(tty_dev);
- goto alloc_fail6;
+ goto err_release_data_interface;
}
if (quirks & CLEAR_HALT_CONDITIONS) {
usb_clear_halt(usb_dev, acm->out);
}
+ dev_info(&intf->dev, "ttyACM%d: USB ACM device\n", minor);
+
return 0;
-alloc_fail6:
+
+err_release_data_interface:
+ if (!acm->combined_interfaces) {
+ /* Clear driver data so that disconnect() returns early. */
+ usb_set_intfdata(data_interface, NULL);
+ usb_driver_release_interface(&acm_driver, data_interface);
+ }
+err_remove_files:
if (acm->country_codes) {
device_remove_file(&acm->control->dev,
&dev_attr_wCountryCodes);
device_remove_file(&acm->control->dev,
&dev_attr_iCountryCodeRelDate);
- kfree(acm->country_codes);
}
device_remove_file(&acm->control->dev, &dev_attr_bmCapabilities);
-alloc_fail5:
- usb_set_intfdata(intf, NULL);
+err_free_write_urbs:
for (i = 0; i < ACM_NW; i++)
usb_free_urb(acm->wb[i].urb);
-alloc_fail4:
+err_free_read_urbs:
for (i = 0; i < num_rx_buf; i++)
usb_free_urb(acm->read_urbs[i]);
acm_read_buffers_free(acm);
usb_free_urb(acm->ctrlurb);
-alloc_fail3:
+err_free_write_buffers:
acm_write_buffers_free(acm);
-alloc_fail2:
+err_free_ctrl_buffer:
usb_free_coherent(usb_dev, ctrlsize, acm->ctrl_buffer, acm->ctrl_dma);
-alloc_fail1:
+err_put_port:
tty_port_put(&acm->port);
-alloc_fail:
+
return rv;
}
if (!acm)
return;
- mutex_lock(&acm->mutex);
acm->disconnected = true;
+ /*
+ * there is a circular dependency. acm_softint() can resubmit
+ * the URBs in error handling so we need to block any
+ * submission right away
+ */
+ acm_poison_urbs(acm);
+ mutex_lock(&acm->mutex);
if (acm->country_codes) {
device_remove_file(&acm->control->dev,
&dev_attr_wCountryCodes);
tty_kref_put(tty);
}
- acm_kill_urbs(acm);
cancel_delayed_work_sync(&acm->dwork);
tty_unregister_device(acm_tty_driver, acm->minor);
if (cnt)
return 0;
- acm_kill_urbs(acm);
+ acm_poison_urbs(acm);
cancel_delayed_work_sync(&acm->dwork);
acm->urbs_in_error_delay = 0;
struct urb *urb;
int rv = 0;
+ acm_unpoison_urbs(acm);
spin_lock_irq(&acm->write_lock);
if (--acm->susp_count)
.driver_info = SEND_ZERO_PACKET,
},
+ /* Exclude Goodix Fingerprint Reader */
+ { USB_DEVICE(0x27c6, 0x5395),
+ .driver_info = IGNORE_DEVICE,
+ },
+
/* control interfaces without any protocol set */
{ USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_ACM,
USB_CDC_PROTO_NONE) },
/* No kernel lock - fine */
static __poll_t usblp_poll(struct file *file, struct poll_table_struct *wait)
{
- __poll_t ret;
+ struct usblp *usblp = file->private_data;
+ __poll_t ret = 0;
unsigned long flags;
- struct usblp *usblp = file->private_data;
/* Should we check file->f_mode & FMODE_WRITE before poll_wait()? */
poll_wait(file, &usblp->rwait, wait);
poll_wait(file, &usblp->wwait, wait);
+
+ mutex_lock(&usblp->mut);
+ if (!usblp->present)
+ ret |= EPOLLHUP;
+ mutex_unlock(&usblp->mut);
+
spin_lock_irqsave(&usblp->lock, flags);
- ret = ((usblp->bidir && usblp->rcomplete) ? EPOLLIN | EPOLLRDNORM : 0) |
- ((usblp->no_paper || usblp->wcomplete) ? EPOLLOUT | EPOLLWRNORM : 0);
+ if (usblp->bidir && usblp->rcomplete)
+ ret |= EPOLLIN | EPOLLRDNORM;
+ if (usblp->no_paper || usblp->wcomplete)
+ ret |= EPOLLOUT | EPOLLWRNORM;
spin_unlock_irqrestore(&usblp->lock, flags);
return ret;
}
/* DJI CineSSD */
{ USB_DEVICE(0x2ca3, 0x0031), .driver_info = USB_QUIRK_NO_LPM },
+ /* Fibocom L850-GL LTE Modem */
+ { USB_DEVICE(0x2cb7, 0x0007), .driver_info =
+ USB_QUIRK_IGNORE_REMOTE_WAKEUP },
+
/* INTEL VALUE SSD */
{ USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME },
}
EXPORT_SYMBOL_GPL(usb_put_intf);
+/**
+ * usb_intf_get_dma_device - acquire a reference on the usb interface's DMA endpoint
+ * @intf: the usb interface
+ *
+ * While a USB device cannot perform DMA operations by itself, many USB
+ * controllers can. A call to usb_intf_get_dma_device() returns the DMA endpoint
+ * for the given USB interface, if any. The returned device structure must be
+ * released with put_device().
+ *
+ * See also usb_get_dma_device().
+ *
+ * Returns: A reference to the usb interface's DMA endpoint; or NULL if none
+ * exists.
+ */
+struct device *usb_intf_get_dma_device(struct usb_interface *intf)
+{
+ struct usb_device *udev = interface_to_usbdev(intf);
+ struct device *dmadev;
+
+ if (!udev->bus)
+ return NULL;
+
+ dmadev = get_device(udev->bus->sysdev);
+ if (!dmadev || !dmadev->dma_mask) {
+ put_device(dmadev);
+ return NULL;
+ }
+
+ return dmadev;
+}
+EXPORT_SYMBOL_GPL(usb_intf_get_dma_device);
+
/* USB device locking
*
* USB devices and interfaces are locked using the semaphore in their
if (hsotg->op_state == OTG_STATE_B_PERIPHERAL)
goto unlock;
- if (hsotg->params.power_down > DWC2_POWER_DOWN_PARAM_PARTIAL)
+ if (hsotg->params.power_down != DWC2_POWER_DOWN_PARAM_PARTIAL ||
+ hsotg->flags.b.port_connect_status == 0)
goto skip_power_saving;
/*
dwc2_writel(hsotg, hprt0, HPRT0);
/* Wait for the HPRT0.PrtSusp register field to be set */
- if (dwc2_hsotg_wait_bit_set(hsotg, HPRT0, HPRT0_SUSP, 3000))
+ if (dwc2_hsotg_wait_bit_set(hsotg, HPRT0, HPRT0_SUSP, 5000))
dev_warn(hsotg->dev, "Suspend wasn't generated\n");
/*
static const struct property_entry dwc3_pci_mrfld_properties[] = {
PROPERTY_ENTRY_STRING("dr_mode", "otg"),
PROPERTY_ENTRY_STRING("linux,extcon-name", "mrfld_bcove_pwrsrc"),
+ PROPERTY_ENTRY_BOOL("snps,dis_u3_susphy_quirk"),
+ PROPERTY_ENTRY_BOOL("snps,dis_u2_susphy_quirk"),
PROPERTY_ENTRY_BOOL("linux,sysdev_is_parent"),
{}
};
struct device *dev = qcom->dev;
int ret;
+ if (has_acpi_companion(dev))
+ return 0;
+
qcom->icc_path_ddr = of_icc_get(dev, "usb-ddr");
if (IS_ERR(qcom->icc_path_ddr)) {
dev_err(dev, "failed to get usb-ddr path: %ld\n",
if (ret)
dev_warn(qcom->dev, "failed to disable interconnect: %d\n", ret);
+ if (device_may_wakeup(qcom->dev))
+ dwc3_qcom_enable_interrupts(qcom);
+
qcom->is_suspended = true;
- dwc3_qcom_enable_interrupts(qcom);
return 0;
}
if (!qcom->is_suspended)
return 0;
- dwc3_qcom_disable_interrupts(qcom);
+ if (device_may_wakeup(qcom->dev))
+ dwc3_qcom_disable_interrupts(qcom);
for (i = 0; i < qcom->num_clocks; i++) {
ret = clk_prepare_enable(qcom->clks[i]);
ret = of_platform_populate(np, NULL, NULL, dev);
if (ret) {
dev_err(dev, "failed to register dwc3 core - %d\n", ret);
- return ret;
+ goto node_put;
}
qcom->dwc3 = of_find_device_by_node(dwc3_np);
if (!qcom->dwc3) {
+ ret = -ENODEV;
dev_err(dev, "failed to get dwc3 platform device\n");
- return -ENODEV;
}
- return 0;
+node_put:
+ of_node_put(dwc3_np);
+
+ return ret;
}
static struct platform_device *
static const struct acpi_device_id dwc3_qcom_acpi_match[] = {
{ "QCOM2430", (unsigned long)&sdm845_acpi_pdata },
{ "QCOM0304", (unsigned long)&sdm845_acpi_urs_pdata },
+ { "QCOM0497", (unsigned long)&sdm845_acpi_urs_pdata },
+ { "QCOM04A6", (unsigned long)&sdm845_acpi_pdata },
{ },
};
MODULE_DEVICE_TABLE(acpi, dwc3_qcom_acpi_match);
trace_dwc3_gadget_ep_disable(dep);
- dwc3_remove_requests(dwc, dep);
-
/* make sure HW endpoint isn't stalled */
if (dep->flags & DWC3_EP_STALL)
__dwc3_gadget_ep_set_halt(dep, 0, false);
reg &= ~DWC3_DALEPENA_EP(dep->number);
dwc3_writel(dwc->regs, DWC3_DALEPENA, reg);
- dep->stream_capable = false;
- dep->type = 0;
- dep->flags = 0;
-
/* Clear out the ep descriptors for non-ep0 */
if (dep->number > 1) {
dep->endpoint.comp_desc = NULL;
dep->endpoint.desc = NULL;
}
+ dwc3_remove_requests(dwc, dep);
+
+ dep->stream_capable = false;
+ dep->type = 0;
+ dep->flags = 0;
+
return 0;
}
{
struct dwc3 *dwc = dep->dwc;
- if (!dep->endpoint.desc || !dwc->pullups_connected) {
+ if (!dep->endpoint.desc || !dwc->pullups_connected || !dwc->connected) {
dev_err(dwc->dev, "%s: can't queue to disabled endpoint\n",
dep->name);
return -ESHUTDOWN;
u32 reg;
speed = dwc->gadget_max_speed;
- if (speed > dwc->maximum_speed)
+ if (speed == USB_SPEED_UNKNOWN || speed > dwc->maximum_speed)
speed = dwc->maximum_speed;
if (speed == USB_SPEED_SUPER_PLUS &&
if (!is_on) {
u32 count;
+ dwc->connected = false;
/*
* In the Synopsis DesignWare Cores USB3 Databook Rev. 3.30a
* Section 4.1.8 Table 4-7, it states that for a device-initiated
dwc->ev_buf->lpos = (dwc->ev_buf->lpos + count) %
dwc->ev_buf->length;
}
- dwc->connected = false;
} else {
__dwc3_gadget_start(dwc);
}
unsigned long flags;
spin_lock_irqsave(&dwc->lock, flags);
+ dwc->gadget_max_speed = USB_SPEED_SUPER_PLUS;
dwc->gadget_ssp_rate = rate;
spin_unlock_irqrestore(&dwc->lock, flags);
}
{
u32 reg;
- dwc->connected = true;
-
/*
* WORKAROUND: DWC3 revisions <1.88a have an issue which
* would cause a missing Disconnect Event if there's a
* transfers."
*/
dwc3_stop_active_transfers(dwc);
+ dwc->connected = true;
reg = dwc3_readl(dwc->regs, DWC3_DCTL);
reg &= ~DWC3_DCTL_TSTCTRL_MASK;
struct list_head list;
};
+#define USB_MAX_STRING_WITH_NULL_LEN (USB_MAX_STRING_LEN+1)
+
static int usb_string_copy(const char *s, char **s_copy)
{
int ret;
if (ret > USB_MAX_STRING_LEN)
return -EOVERFLOW;
- str = kstrdup(s, GFP_KERNEL);
- if (!str)
- return -ENOMEM;
+ if (copy) {
+ str = copy;
+ } else {
+ str = kmalloc(USB_MAX_STRING_WITH_NULL_LEN, GFP_KERNEL);
+ if (!str)
+ return -ENOMEM;
+ }
+ strcpy(str, s);
if (str[ret - 1] == '\n')
str[ret - 1] = '\0';
- kfree(copy);
*s_copy = str;
return 0;
}
uac1->as_out_alt = 0;
uac1->as_in_alt = 0;
+ u_audio_stop_playback(&uac1->g_audio);
u_audio_stop_capture(&uac1->g_audio);
}
}
max_size_bw = num_channels(chmask) * ssize *
- DIV_ROUND_UP(srate, factor / (1 << (ep_desc->bInterval - 1)));
+ ((srate / (factor / (1 << (ep_desc->bInterval - 1)))) + 1);
ep_desc->wMaxPacketSize = cpu_to_le16(min_t(u16, max_size_bw,
max_size_ep));
size_t len) \
{ \
struct f_##_f_##_opts *opts = to_f_##_f_##_opts(item); \
- int ret; \
+ int ret = -EINVAL; \
u8 val; \
\
mutex_lock(&opts->lock); \
- ret = sscanf(page, "%02hhx", &val); \
- if (ret > 0) { \
+ if (sscanf(page, "%02hhx", &val) > 0) { \
opts->_n_ = val; \
ret = len; \
} \
pci_set_master(pdev);
pci_try_set_mwi(pdev);
+ dev->phys_addr = resource;
+ dev->irq = pdev->irq;
+ dev->pdev = pdev;
+ dev->dev = &pdev->dev;
+
/* init dma pools */
if (use_dma) {
retval = init_dma_pools(dev);
goto err_dma;
}
- dev->phys_addr = resource;
- dev->irq = pdev->irq;
- dev->pdev = pdev;
- dev->dev = &pdev->dev;
-
/* general probing */
if (udc_probe(dev)) {
retval = -ENODEV;
udc_info = dev_get_platdata(&pdev->dev);
base_addr = devm_platform_ioremap_resource(pdev, 0);
- if (!base_addr) {
- retval = -ENOMEM;
+ if (IS_ERR(base_addr)) {
+ retval = PTR_ERR(base_addr);
goto err_mem;
}
xhci->quirks |= XHCI_SPURIOUS_SUCCESS;
if (mtk->lpm_support)
xhci->quirks |= XHCI_LPM_SUPPORT;
+
+ /*
+ * MTK xHCI 0.96: PSA is 1 by default even if doesn't support stream,
+ * and it's 3 when support it.
+ */
+ if (xhci->hci_version < 0x100 && HCC_MAX_PSA(xhci->hcc_params) == 4)
+ xhci->quirks |= XHCI_BROKEN_STREAMS;
}
/* called during probe() after chip reset completes */
if (ret)
goto put_usb3_hcd;
- if (HCC_MAX_PSA(xhci->hcc_params) >= 4)
+ if (HCC_MAX_PSA(xhci->hcc_params) >= 4 &&
+ !(xhci->quirks & XHCI_BROKEN_STREAMS))
xhci->shared_hcd->can_do_streams = 1;
ret = usb_add_hcd(xhci->shared_hcd, irq, IRQF_SHARED);
#define PCI_DEVICE_ID_ASMEDIA_1042A_XHCI 0x1142
#define PCI_DEVICE_ID_ASMEDIA_1142_XHCI 0x1242
#define PCI_DEVICE_ID_ASMEDIA_2142_XHCI 0x2142
+#define PCI_DEVICE_ID_ASMEDIA_3242_XHCI 0x3242
static const char hcd_name[] = "xhci_hcd";
pdev->device == PCI_DEVICE_ID_ASMEDIA_1042_XHCI)
xhci->quirks |= XHCI_BROKEN_STREAMS;
if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA &&
- pdev->device == PCI_DEVICE_ID_ASMEDIA_1042A_XHCI)
+ pdev->device == PCI_DEVICE_ID_ASMEDIA_1042A_XHCI) {
xhci->quirks |= XHCI_TRUST_TX_LENGTH;
+ xhci->quirks |= XHCI_NO_64BIT_SUPPORT;
+ }
if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA &&
(pdev->device == PCI_DEVICE_ID_ASMEDIA_1142_XHCI ||
- pdev->device == PCI_DEVICE_ID_ASMEDIA_2142_XHCI))
+ pdev->device == PCI_DEVICE_ID_ASMEDIA_2142_XHCI ||
+ pdev->device == PCI_DEVICE_ID_ASMEDIA_3242_XHCI))
xhci->quirks |= XHCI_NO_64BIT_SUPPORT;
if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA &&
pdev->device == 0x9026)
xhci->quirks |= XHCI_RESET_PLL_ON_DISCONNECT;
+ if (pdev->vendor == PCI_VENDOR_ID_AMD &&
+ (pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_2 ||
+ pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_4))
+ xhci->quirks |= XHCI_NO_SOFT_RETRY;
+
if (xhci->quirks & XHCI_RESET_ON_RESUME)
xhci_dbg_trace(xhci, trace_xhci_dbg_quirks,
"QUIRK: Resetting on resume");
remaining = 0;
break;
case COMP_USB_TRANSACTION_ERROR:
- if ((ep_ring->err_count++ > MAX_SOFT_RETRY) ||
+ if (xhci->quirks & XHCI_NO_SOFT_RETRY ||
+ (ep_ring->err_count++ > MAX_SOFT_RETRY) ||
le32_to_cpu(slot_ctx->tt_info) & TT_SLOT)
break;
xhci_set_cmd_ring_deq(xhci);
}
-static void xhci_disable_port_wake_on_bits(struct xhci_hcd *xhci)
+/*
+ * Disable port wake bits if do_wakeup is not set.
+ *
+ * Also clear a possible internal port wake state left hanging for ports that
+ * detected termination but never successfully enumerated (trained to 0U).
+ * Internal wake causes immediate xHCI wake after suspend. PORT_CSC write done
+ * at enumeration clears this wake, force one here as well for unconnected ports
+ */
+
+static void xhci_disable_hub_port_wake(struct xhci_hcd *xhci,
+ struct xhci_hub *rhub,
+ bool do_wakeup)
{
- struct xhci_port **ports;
- int port_index;
unsigned long flags;
u32 t1, t2, portsc;
+ int i;
spin_lock_irqsave(&xhci->lock, flags);
- /* disable usb3 ports Wake bits */
- port_index = xhci->usb3_rhub.num_ports;
- ports = xhci->usb3_rhub.ports;
- while (port_index--) {
- t1 = readl(ports[port_index]->addr);
- portsc = t1;
- t1 = xhci_port_state_to_neutral(t1);
- t2 = t1 & ~PORT_WAKE_BITS;
- if (t1 != t2) {
- writel(t2, ports[port_index]->addr);
- xhci_dbg(xhci, "disable wake bits port %d-%d, portsc: 0x%x, write: 0x%x\n",
- xhci->usb3_rhub.hcd->self.busnum,
- port_index + 1, portsc, t2);
- }
- }
+ for (i = 0; i < rhub->num_ports; i++) {
+ portsc = readl(rhub->ports[i]->addr);
+ t1 = xhci_port_state_to_neutral(portsc);
+ t2 = t1;
+
+ /* clear wake bits if do_wake is not set */
+ if (!do_wakeup)
+ t2 &= ~PORT_WAKE_BITS;
+
+ /* Don't touch csc bit if connected or connect change is set */
+ if (!(portsc & (PORT_CSC | PORT_CONNECT)))
+ t2 |= PORT_CSC;
- /* disable usb2 ports Wake bits */
- port_index = xhci->usb2_rhub.num_ports;
- ports = xhci->usb2_rhub.ports;
- while (port_index--) {
- t1 = readl(ports[port_index]->addr);
- portsc = t1;
- t1 = xhci_port_state_to_neutral(t1);
- t2 = t1 & ~PORT_WAKE_BITS;
if (t1 != t2) {
- writel(t2, ports[port_index]->addr);
- xhci_dbg(xhci, "disable wake bits port %d-%d, portsc: 0x%x, write: 0x%x\n",
- xhci->usb2_rhub.hcd->self.busnum,
- port_index + 1, portsc, t2);
+ writel(t2, rhub->ports[i]->addr);
+ xhci_dbg(xhci, "config port %d-%d wake bits, portsc: 0x%x, write: 0x%x\n",
+ rhub->hcd->self.busnum, i + 1, portsc, t2);
}
}
spin_unlock_irqrestore(&xhci->lock, flags);
return -EINVAL;
/* Clear root port wake on bits if wakeup not allowed. */
- if (!do_wakeup)
- xhci_disable_port_wake_on_bits(xhci);
+ xhci_disable_hub_port_wake(xhci, &xhci->usb3_rhub, do_wakeup);
+ xhci_disable_hub_port_wake(xhci, &xhci->usb2_rhub, do_wakeup);
if (!HCD_HW_ACCESSIBLE(hcd))
return 0;
struct usb_hcd *secondary_hcd;
int retval = 0;
bool comp_timer_running = false;
+ bool pending_portevent = false;
if (!hcd->state)
return 0;
done:
if (retval == 0) {
- /* Resume root hubs only when have pending events. */
- if (xhci_pending_portevent(xhci)) {
+ /*
+ * Resume roothubs only if there are pending events.
+ * USB 3 devices resend U3 LFPS wake after a 100ms delay if
+ * the first wake signalling failed, give it that chance.
+ */
+ pending_portevent = xhci_pending_portevent(xhci);
+ if (!pending_portevent) {
+ msleep(120);
+ pending_portevent = xhci_pending_portevent(xhci);
+ }
+
+ if (pending_portevent) {
usb_hcd_resume_root_hub(xhci->shared_hcd);
usb_hcd_resume_root_hub(hcd);
}
}
-
/*
* If system is subject to the Quirk, Compliance Mode Timer needs to
* be re-initialized Always after a system resume. Ports are subject
#define XHCI_SKIP_PHY_INIT BIT_ULL(37)
#define XHCI_DISABLE_SPARSE BIT_ULL(38)
#define XHCI_SG_TRB_CACHE_SIZE_QUIRK BIT_ULL(39)
+#define XHCI_NO_SOFT_RETRY BIT_ULL(40)
unsigned int num_active_eps;
unsigned int limit_active_eps;
MODULE_AUTHOR("Michael Hund <mhund@ld-didactic.de>");
MODULE_DESCRIPTION("LD USB Driver");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("LD USB Devices");
/* All interrupt in transfers are collected in a ring buffer to
* avoid racing conditions and get better performance of the driver.
MUSB_DEVCTL_HR;
switch (devctl & ~s) {
case MUSB_QUIRK_B_DISCONNECT_99:
- musb_dbg(musb, "Poll devctl in case of suspend after disconnect\n");
- schedule_delayed_work(&musb->irq_work,
- msecs_to_jiffies(1000));
- break;
+ if (musb->quirk_retries && !musb->flush_irq_work) {
+ musb_dbg(musb, "Poll devctl in case of suspend after disconnect\n");
+ schedule_delayed_work(&musb->irq_work,
+ msecs_to_jiffies(1000));
+ musb->quirk_retries--;
+ break;
+ }
+ fallthrough;
case MUSB_QUIRK_B_INVALID_VBUS_91:
if (musb->quirk_retries && !musb->flush_irq_work) {
musb_dbg(musb,
void usbhs_pipe_free(struct usbhs_pipe *pipe)
{
+ usbhsp_pipe_select(pipe);
+ usbhsp_pipe_cfg_set(pipe, 0xFFFF, 0);
usbhsp_put_pipe(pipe);
}
{ USB_DEVICE(0x1a86, 0x7522) },
{ USB_DEVICE(0x1a86, 0x7523) },
{ USB_DEVICE(0x4348, 0x5523) },
+ { USB_DEVICE(0x9986, 0x7523) },
{ },
};
MODULE_DEVICE_TABLE(usb, id_table);
{ USB_DEVICE(0x10C4, 0x8857) }, /* CEL EM357 ZigBee USB Stick */
{ USB_DEVICE(0x10C4, 0x88A4) }, /* MMB Networks ZigBee USB Device */
{ USB_DEVICE(0x10C4, 0x88A5) }, /* Planet Innovation Ingeni ZigBee USB Device */
+ { USB_DEVICE(0x10C4, 0x88D8) }, /* Acuity Brands nLight Air Adapter */
{ USB_DEVICE(0x10C4, 0x88FB) }, /* CESINEL MEDCAL STII Network Analyzer */
{ USB_DEVICE(0x10C4, 0x8938) }, /* CESINEL MEDCAL S II Network Analyzer */
{ USB_DEVICE(0x10C4, 0x8946) }, /* Ketra N1 Wireless Interface */
{ USB_DEVICE(0x1901, 0x0194) }, /* GE Healthcare Remote Alarm Box */
{ USB_DEVICE(0x1901, 0x0195) }, /* GE B850/B650/B450 CP2104 DP UART interface */
{ USB_DEVICE(0x1901, 0x0196) }, /* GE B850 CP2105 DP UART interface */
+ { USB_DEVICE(0x1901, 0x0197) }, /* GE CS1000 Display serial interface */
+ { USB_DEVICE(0x1901, 0x0198) }, /* GE CS1000 M.2 Key E serial interface */
{ USB_DEVICE(0x199B, 0xBA30) }, /* LORD WSDA-200-USB */
{ USB_DEVICE(0x19CF, 0x3000) }, /* Parrot NMEA GPS Flight Recorder */
{ USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */
response = -ENODEV;
}
- usb_free_urb(edge_serial->interrupt_read_urb);
- kfree(edge_serial->interrupt_in_buffer);
-
- usb_free_urb(edge_serial->read_urb);
- kfree(edge_serial->bulk_in_buffer);
-
- kfree(edge_serial);
-
- return response;
+ goto error;
}
/* start interrupt read for this edgeport this interrupt will
* continue as long as the edgeport is connected */
response = usb_submit_urb(edge_serial->interrupt_read_urb,
GFP_KERNEL);
- if (response)
+ if (response) {
dev_err(ddev, "%s - Error %d submitting control urb\n",
__func__, response);
+
+ goto error;
+ }
}
return response;
+
+error:
+ usb_free_urb(edge_serial->interrupt_read_urb);
+ kfree(edge_serial->interrupt_in_buffer);
+
+ usb_free_urb(edge_serial->read_urb);
+ kfree(edge_serial->bulk_in_buffer);
+
+ kfree(edge_serial);
+
+ return response;
}
static int xr_probe(struct usb_serial *serial, const struct usb_device_id *id)
{
- struct usb_driver *driver = serial->type->usb_driver;
- struct usb_interface *control_interface;
- int ret;
-
/* Don't bind to control interface */
if (serial->interface->cur_altsetting->desc.bInterfaceNumber == 0)
return -ENODEV;
- /* But claim the control interface during data interface probe */
- control_interface = usb_ifnum_to_if(serial->dev, 0);
- if (!control_interface)
- return -ENODEV;
-
- ret = usb_driver_claim_interface(driver, control_interface, NULL);
- if (ret) {
- dev_err(&serial->interface->dev, "Failed to claim control interface\n");
- return ret;
- }
-
return 0;
}
-static void xr_disconnect(struct usb_serial *serial)
-{
- struct usb_driver *driver = serial->type->usb_driver;
- struct usb_interface *control_interface;
-
- control_interface = usb_ifnum_to_if(serial->dev, 0);
- usb_driver_release_interface(driver, control_interface);
-}
-
static const struct usb_device_id id_table[] = {
{ USB_DEVICE(0x04e2, 0x1410) }, /* XR21V141X */
{ }
.id_table = id_table,
.num_ports = 1,
.probe = xr_probe,
- .disconnect = xr_disconnect,
.open = xr_open,
.close = xr_close,
.break_ctl = xr_break_ctl,
need_auto_sense = 1;
}
+ /* Some devices (Kindle) require another command after SYNC CACHE */
+ if ((us->fflags & US_FL_SENSE_AFTER_SYNC) &&
+ srb->cmnd[0] == SYNCHRONIZE_CACHE) {
+ usb_stor_dbg(us, "-- sense after SYNC CACHE\n");
+ need_auto_sense = 1;
+ }
+
/*
* If we have a failure, we're going to do a REQUEST_SENSE
* automatically. Note that we differentiate between a command
US_FL_NO_READ_DISC_INFO ),
/*
+ * Reported by Matthias Schwarzott <zzam@gentoo.org>
+ * The Amazon Kindle treats SYNCHRONIZE CACHE as an indication that
+ * the host may be finished with it, and automatically ejects its
+ * emulated media unless it receives another command within one second.
+ */
+UNUSUAL_DEV( 0x1949, 0x0004, 0x0000, 0x9999,
+ "Amazon",
+ "Kindle",
+ USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+ US_FL_SENSE_AFTER_SYNC ),
+
+/*
* Reported by Oliver Neukum <oneukum@suse.com>
* This device morphes spontaneously into another device if the access
* pattern of Windows isn't followed. Thus writable media would be dirty
port->supply_voltage = mv;
port->current_limit = max_ma;
+ power_supply_changed(port->psy);
if (port->tcpc->set_current_limit)
ret = port->tcpc->set_current_limit(port->tcpc, max_ma, mv);
port->pps_data.supported = false;
port->usb_type = POWER_SUPPLY_USB_TYPE_PD;
+ power_supply_changed(port->psy);
/*
* Select the source PDO providing the most power which has a
port->pps_data.supported = true;
port->usb_type =
POWER_SUPPLY_USB_TYPE_PD_PPS;
+ power_supply_changed(port->psy);
}
continue;
default:
port->pps_data.out_volt));
port->pps_data.op_curr = min(port->pps_data.max_curr,
port->pps_data.op_curr);
+ power_supply_changed(port->psy);
}
return src_pdo;
return ret;
}
port->vbus_charge = charge;
+ power_supply_changed(port->psy);
return 0;
}
port->try_src_count = 0;
port->try_snk_count = 0;
port->usb_type = POWER_SUPPLY_USB_TYPE_C;
+ power_supply_changed(port->psy);
port->nr_sink_caps = 0;
port->sink_cap_done = false;
if (port->tcpc->enable_frs)
goto unlock;
/* Send when the state machine is idle */
- if (port->state != SNK_READY || port->vdm_state != VDM_STATE_DONE || port->send_discover)
+ if (port->state != SNK_READY || port->vdm_sm_running || port->send_discover)
goto resched;
port->upcoming_state = GET_SINK_CAP;
ret = -EINVAL;
break;
}
-
+ power_supply_changed(port->psy);
return ret;
}
err = devm_tcpm_psy_register(port);
if (err)
goto out_role_sw_put;
+ power_supply_changed(port->psy);
port->typec_port = typec_register_port(port->dev, &port->typec_caps);
if (IS_ERR(port->typec_port)) {
struct tps6598x_rx_identity_reg {
u8 status;
struct usb_pd_identity identity;
- u32 vdo[3];
} __packed;
/* Standard Task return codes */
int sockfd = 0;
struct socket *socket;
int rv;
+ struct task_struct *tcp_rx = NULL;
+ struct task_struct *tcp_tx = NULL;
if (!sdev) {
dev_err(dev, "sdev is null\n");
dev_info(dev, "stub up\n");
+ mutex_lock(&sdev->ud.sysfs_lock);
spin_lock_irq(&sdev->ud.lock);
if (sdev->ud.status != SDEV_ST_AVAILABLE) {
}
socket = sockfd_lookup(sockfd, &err);
- if (!socket)
+ if (!socket) {
+ dev_err(dev, "failed to lookup sock");
goto err;
+ }
- sdev->ud.tcp_socket = socket;
- sdev->ud.sockfd = sockfd;
+ if (socket->type != SOCK_STREAM) {
+ dev_err(dev, "Expecting SOCK_STREAM - found %d",
+ socket->type);
+ goto sock_err;
+ }
+ /* unlock and create threads and get tasks */
spin_unlock_irq(&sdev->ud.lock);
+ tcp_rx = kthread_create(stub_rx_loop, &sdev->ud, "stub_rx");
+ if (IS_ERR(tcp_rx)) {
+ sockfd_put(socket);
+ goto unlock_mutex;
+ }
+ tcp_tx = kthread_create(stub_tx_loop, &sdev->ud, "stub_tx");
+ if (IS_ERR(tcp_tx)) {
+ kthread_stop(tcp_rx);
+ sockfd_put(socket);
+ goto unlock_mutex;
+ }
- sdev->ud.tcp_rx = kthread_get_run(stub_rx_loop, &sdev->ud,
- "stub_rx");
- sdev->ud.tcp_tx = kthread_get_run(stub_tx_loop, &sdev->ud,
- "stub_tx");
+ /* get task structs now */
+ get_task_struct(tcp_rx);
+ get_task_struct(tcp_tx);
+ /* lock and update sdev->ud state */
spin_lock_irq(&sdev->ud.lock);
+ sdev->ud.tcp_socket = socket;
+ sdev->ud.sockfd = sockfd;
+ sdev->ud.tcp_rx = tcp_rx;
+ sdev->ud.tcp_tx = tcp_tx;
sdev->ud.status = SDEV_ST_USED;
spin_unlock_irq(&sdev->ud.lock);
+ wake_up_process(sdev->ud.tcp_rx);
+ wake_up_process(sdev->ud.tcp_tx);
+
+ mutex_unlock(&sdev->ud.sysfs_lock);
+
} else {
dev_info(dev, "stub down\n");
spin_unlock_irq(&sdev->ud.lock);
usbip_event_add(&sdev->ud, SDEV_EVENT_DOWN);
+ mutex_unlock(&sdev->ud.sysfs_lock);
}
return count;
+sock_err:
+ sockfd_put(socket);
err:
spin_unlock_irq(&sdev->ud.lock);
+unlock_mutex:
+ mutex_unlock(&sdev->ud.sysfs_lock);
return -EINVAL;
}
static DEVICE_ATTR_WO(usbip_sockfd);
sdev->ud.side = USBIP_STUB;
sdev->ud.status = SDEV_ST_AVAILABLE;
spin_lock_init(&sdev->ud.lock);
+ mutex_init(&sdev->ud.sysfs_lock);
sdev->ud.tcp_socket = NULL;
sdev->ud.sockfd = -1;
/* lock for status */
spinlock_t lock;
+ /* mutex for synchronizing sysfs store paths */
+ struct mutex sysfs_lock;
+
int sockfd;
struct socket *tcp_socket;
while ((ud = get_event()) != NULL) {
usbip_dbg_eh("pending event %lx\n", ud->event);
+ mutex_lock(&ud->sysfs_lock);
/*
* NOTE: shutdown must come first.
* Shutdown the device.
ud->eh_ops.unusable(ud);
unset_event(ud, USBIP_EH_UNUSABLE);
}
+ mutex_unlock(&ud->sysfs_lock);
wake_up(&ud->eh_waitq);
}
pr_err("invalid port number %d\n", wIndex);
goto error;
}
+ if (wValue >= 32)
+ goto error;
if (hcd->speed == HCD_USB3) {
if ((vhci_hcd->port_status[rhport] &
USB_SS_PORT_STAT_POWER) != 0) {
vdev->ud.side = USBIP_VHCI;
vdev->ud.status = VDEV_ST_NULL;
spin_lock_init(&vdev->ud.lock);
+ mutex_init(&vdev->ud.sysfs_lock);
INIT_LIST_HEAD(&vdev->priv_rx);
INIT_LIST_HEAD(&vdev->priv_tx);
usbip_dbg_vhci_sysfs("enter\n");
+ mutex_lock(&vdev->ud.sysfs_lock);
+
/* lock */
spin_lock_irqsave(&vhci->lock, flags);
spin_lock(&vdev->ud.lock);
/* unlock */
spin_unlock(&vdev->ud.lock);
spin_unlock_irqrestore(&vhci->lock, flags);
+ mutex_unlock(&vdev->ud.sysfs_lock);
return -EINVAL;
}
usbip_event_add(&vdev->ud, VDEV_EVENT_DOWN);
+ mutex_unlock(&vdev->ud.sysfs_lock);
+
return 0;
}
struct vhci *vhci;
int err;
unsigned long flags;
+ struct task_struct *tcp_rx = NULL;
+ struct task_struct *tcp_tx = NULL;
/*
* @rhport: port number of vhci_hcd
else
vdev = &vhci->vhci_hcd_hs->vdev[rhport];
+ mutex_lock(&vdev->ud.sysfs_lock);
+
/* Extract socket from fd. */
socket = sockfd_lookup(sockfd, &err);
- if (!socket)
- return -EINVAL;
+ if (!socket) {
+ dev_err(dev, "failed to lookup sock");
+ err = -EINVAL;
+ goto unlock_mutex;
+ }
+ if (socket->type != SOCK_STREAM) {
+ dev_err(dev, "Expecting SOCK_STREAM - found %d",
+ socket->type);
+ sockfd_put(socket);
+ err = -EINVAL;
+ goto unlock_mutex;
+ }
- /* now need lock until setting vdev status as used */
+ /* create threads before locking */
+ tcp_rx = kthread_create(vhci_rx_loop, &vdev->ud, "vhci_rx");
+ if (IS_ERR(tcp_rx)) {
+ sockfd_put(socket);
+ err = -EINVAL;
+ goto unlock_mutex;
+ }
+ tcp_tx = kthread_create(vhci_tx_loop, &vdev->ud, "vhci_tx");
+ if (IS_ERR(tcp_tx)) {
+ kthread_stop(tcp_rx);
+ sockfd_put(socket);
+ err = -EINVAL;
+ goto unlock_mutex;
+ }
+
+ /* get task structs now */
+ get_task_struct(tcp_rx);
+ get_task_struct(tcp_tx);
- /* begin a lock */
+ /* now begin lock until setting vdev status set */
spin_lock_irqsave(&vhci->lock, flags);
spin_lock(&vdev->ud.lock);
spin_unlock_irqrestore(&vhci->lock, flags);
sockfd_put(socket);
+ kthread_stop_put(tcp_rx);
+ kthread_stop_put(tcp_tx);
dev_err(dev, "port %d already used\n", rhport);
/*
* Will be retried from userspace
* if there's another free port.
*/
- return -EBUSY;
+ err = -EBUSY;
+ goto unlock_mutex;
}
dev_info(dev, "pdev(%u) rhport(%u) sockfd(%d)\n",
vdev->speed = speed;
vdev->ud.sockfd = sockfd;
vdev->ud.tcp_socket = socket;
+ vdev->ud.tcp_rx = tcp_rx;
+ vdev->ud.tcp_tx = tcp_tx;
vdev->ud.status = VDEV_ST_NOTASSIGNED;
usbip_kcov_handle_init(&vdev->ud);
spin_unlock_irqrestore(&vhci->lock, flags);
/* end the lock */
- vdev->ud.tcp_rx = kthread_get_run(vhci_rx_loop, &vdev->ud, "vhci_rx");
- vdev->ud.tcp_tx = kthread_get_run(vhci_tx_loop, &vdev->ud, "vhci_tx");
+ wake_up_process(vdev->ud.tcp_rx);
+ wake_up_process(vdev->ud.tcp_tx);
rh_port_connect(vdev, speed);
+ dev_info(dev, "Device attached\n");
+
+ mutex_unlock(&vdev->ud.sysfs_lock);
+
return count;
+
+unlock_mutex:
+ mutex_unlock(&vdev->ud.sysfs_lock);
+ return err;
}
static DEVICE_ATTR_WO(attach);
init_waitqueue_head(&udc->tx_waitq);
spin_lock_init(&ud->lock);
+ mutex_init(&ud->sysfs_lock);
ud->status = SDEV_ST_AVAILABLE;
ud->side = USBIP_VUDC;
}
static BIN_ATTR_RO(dev_desc, sizeof(struct usb_device_descriptor));
-static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *attr,
- const char *in, size_t count)
+static ssize_t usbip_sockfd_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *in, size_t count)
{
struct vudc *udc = (struct vudc *) dev_get_drvdata(dev);
int rv;
struct socket *socket;
unsigned long flags;
int ret;
+ struct task_struct *tcp_rx = NULL;
+ struct task_struct *tcp_tx = NULL;
rv = kstrtoint(in, 0, &sockfd);
if (rv != 0)
dev_err(dev, "no device");
return -ENODEV;
}
+ mutex_lock(&udc->ud.sysfs_lock);
spin_lock_irqsave(&udc->lock, flags);
/* Don't export what we don't have */
if (!udc->driver || !udc->pullup) {
goto unlock_ud;
}
- udc->ud.tcp_socket = socket;
+ if (socket->type != SOCK_STREAM) {
+ dev_err(dev, "Expecting SOCK_STREAM - found %d",
+ socket->type);
+ ret = -EINVAL;
+ goto sock_err;
+ }
+ /* unlock and create threads and get tasks */
spin_unlock_irq(&udc->ud.lock);
spin_unlock_irqrestore(&udc->lock, flags);
- udc->ud.tcp_rx = kthread_get_run(&v_rx_loop,
- &udc->ud, "vudc_rx");
- udc->ud.tcp_tx = kthread_get_run(&v_tx_loop,
- &udc->ud, "vudc_tx");
+ tcp_rx = kthread_create(&v_rx_loop, &udc->ud, "vudc_rx");
+ if (IS_ERR(tcp_rx)) {
+ sockfd_put(socket);
+ return -EINVAL;
+ }
+ tcp_tx = kthread_create(&v_tx_loop, &udc->ud, "vudc_tx");
+ if (IS_ERR(tcp_tx)) {
+ kthread_stop(tcp_rx);
+ sockfd_put(socket);
+ return -EINVAL;
+ }
+
+ /* get task structs now */
+ get_task_struct(tcp_rx);
+ get_task_struct(tcp_tx);
+ /* lock and update udc->ud state */
spin_lock_irqsave(&udc->lock, flags);
spin_lock_irq(&udc->ud.lock);
+
+ udc->ud.tcp_socket = socket;
+ udc->ud.tcp_rx = tcp_rx;
+ udc->ud.tcp_tx = tcp_tx;
udc->ud.status = SDEV_ST_USED;
+
spin_unlock_irq(&udc->ud.lock);
ktime_get_ts64(&udc->start_time);
v_start_timer(udc);
udc->connected = 1;
+
+ spin_unlock_irqrestore(&udc->lock, flags);
+
+ wake_up_process(udc->ud.tcp_rx);
+ wake_up_process(udc->ud.tcp_tx);
+
+ mutex_unlock(&udc->ud.sysfs_lock);
+ return count;
+
} else {
if (!udc->connected) {
dev_err(dev, "Device not connected");
}
spin_unlock_irqrestore(&udc->lock, flags);
+ mutex_unlock(&udc->ud.sysfs_lock);
return count;
+sock_err:
+ sockfd_put(socket);
unlock_ud:
spin_unlock_irq(&udc->ud.lock);
unlock:
spin_unlock_irqrestore(&udc->lock, flags);
+ mutex_unlock(&udc->ud.sysfs_lock);
return ret;
}
}
adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa,
- dev, &ifc_vdpa_ops,
- IFCVF_MAX_QUEUE_PAIRS * 2, NULL);
+ dev, &ifc_vdpa_ops, NULL);
if (adapter == NULL) {
IFCVF_ERR(pdev, "Failed to allocate vDPA structure");
return -ENOMEM;
for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++)
vf->vring[i].irq = -EINVAL;
- ret = vdpa_register_device(&adapter->vdpa);
+ ret = vdpa_register_device(&adapter->vdpa, IFCVF_MAX_QUEUE_PAIRS * 2);
if (ret) {
IFCVF_ERR(pdev, "Failed to register ifcvf to vdpa bus");
goto err;
#ifndef __MLX5_VDPA_H__
#define __MLX5_VDPA_H__
+#include <linux/etherdevice.h>
+#include <linux/if_vlan.h>
#include <linux/vdpa.h>
#include <linux/mlx5/driver.h>
+#define MLX5V_ETH_HARD_MTU (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN)
+
struct mlx5_vdpa_direct_mr {
u64 start;
u64 end;
mlx5_vdpa_destroy_mkey(mvdev, &mkey->mkey);
}
+static struct device *get_dma_device(struct mlx5_vdpa_dev *mvdev)
+{
+ return &mvdev->mdev->pdev->dev;
+}
+
static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr,
struct vhost_iotlb *iotlb)
{
u64 pa;
u64 paend;
struct scatterlist *sg;
- struct device *dma = mvdev->mdev->device;
+ struct device *dma = get_dma_device(mvdev);
for (map = vhost_iotlb_itree_first(iotlb, mr->start, mr->end - 1);
map; map = vhost_iotlb_itree_next(map, start, mr->end - 1)) {
mr->log_size = log_entity_size;
mr->nsg = nsg;
mr->nent = dma_map_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0);
- if (!mr->nent)
+ if (!mr->nent) {
+ err = -ENOMEM;
goto err_map;
+ }
err = create_direct_mr(mvdev, mr);
if (err)
static void unmap_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr)
{
- struct device *dma = mvdev->mdev->device;
+ struct device *dma = get_dma_device(mvdev);
destroy_direct_mr(mvdev, mr);
dma_unmap_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0);
if (err)
goto err_key;
- kick_addr = pci_resource_start(mdev->pdev, 0) + offset;
+ kick_addr = mdev->bar_addr + offset;
+
res->kick_addr = ioremap(kick_addr, PAGE_SIZE);
if (!res->kick_addr) {
err = -ENOMEM;
MLX5_SET(virtio_q, vq_ctx, event_qpn_or_msix, mvq->fwqp.mqp.qpn);
MLX5_SET(virtio_q, vq_ctx, queue_size, mvq->num_ent);
MLX5_SET(virtio_q, vq_ctx, virtio_version_1_0,
- !!(ndev->mvdev.actual_features & VIRTIO_F_VERSION_1));
+ !!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_F_VERSION_1)));
MLX5_SET64(virtio_q, vq_ctx, desc_addr, mvq->desc_addr);
MLX5_SET64(virtio_q, vq_ctx, used_addr, mvq->device_addr);
MLX5_SET64(virtio_q, vq_ctx, available_addr, mvq->driver_addr);
return;
}
mvq->avail_idx = attr.available_index;
+ mvq->used_idx = attr.used_index;
}
static void suspend_vqs(struct mlx5_vdpa_net *ndev)
return -EINVAL;
}
+ mvq->used_idx = state->avail_index;
mvq->avail_idx = state->avail_index;
return 0;
}
* that cares about emulating the index after vq is stopped.
*/
if (!mvq->initialized) {
- state->avail_index = mvq->avail_idx;
+ /* Firmware returns a wrong value for the available index.
+ * Since both values should be identical, we take the value of
+ * used_idx which is reported correctly.
+ */
+ state->avail_index = mvq->used_idx;
return 0;
}
mlx5_vdpa_warn(mvdev, "failed to query virtqueue\n");
return err;
}
- state->avail_index = attr.available_index;
+ state->avail_index = attr.used_index;
return 0;
}
}
}
-static void clear_virtqueues(struct mlx5_vdpa_net *ndev)
-{
- int i;
-
- for (i = ndev->mvdev.max_vqs - 1; i >= 0; i--) {
- ndev->vqs[i].avail_idx = 0;
- ndev->vqs[i].used_idx = 0;
- }
-}
-
/* TODO: cross-endian support */
static inline bool mlx5_vdpa_is_little_endian(struct mlx5_vdpa_dev *mvdev)
{
return virtio_legacy_is_little_endian() ||
- (mvdev->actual_features & (1ULL << VIRTIO_F_VERSION_1));
+ (mvdev->actual_features & BIT_ULL(VIRTIO_F_VERSION_1));
}
static __virtio16 cpu_to_mlx5vdpa16(struct mlx5_vdpa_dev *mvdev, u16 val)
if (!status) {
mlx5_vdpa_info(mvdev, "performing device reset\n");
teardown_driver(ndev);
- clear_virtqueues(ndev);
mlx5_vdpa_destroy_mr(&ndev->mvdev);
ndev->mvdev.status = 0;
ndev->mvdev.mlx_features = 0;
.free = mlx5_vdpa_free,
};
+static int query_mtu(struct mlx5_core_dev *mdev, u16 *mtu)
+{
+ u16 hw_mtu;
+ int err;
+
+ err = mlx5_query_nic_vport_mtu(mdev, &hw_mtu);
+ if (err)
+ return err;
+
+ *mtu = hw_mtu - MLX5V_ETH_HARD_MTU;
+ return 0;
+}
+
static int alloc_resources(struct mlx5_vdpa_net *ndev)
{
struct mlx5_vdpa_net_resources *res = &ndev->res;
max_vqs = min_t(u32, max_vqs, MLX5_MAX_SUPPORTED_VQS);
ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops,
- 2 * mlx5_vdpa_max_qps(max_vqs), NULL);
+ NULL);
if (IS_ERR(ndev))
return PTR_ERR(ndev);
init_mvqs(ndev);
mutex_init(&ndev->reslock);
config = &ndev->config;
- err = mlx5_query_nic_vport_mtu(mdev, &ndev->mtu);
+ err = query_mtu(mdev, &ndev->mtu);
if (err)
goto err_mtu;
if (err)
goto err_res;
- err = vdpa_register_device(&mvdev->vdev);
+ err = vdpa_register_device(&mvdev->vdev, 2 * mlx5_vdpa_max_qps(max_vqs));
if (err)
goto err_reg;
* initialized but before registered.
* @parent: the parent device
* @config: the bus operations that is supported by this device
- * @nvqs: number of virtqueues supported by this device
* @size: size of the parent structure that contains private data
* @name: name of the vdpa device; optional.
*
*/
struct vdpa_device *__vdpa_alloc_device(struct device *parent,
const struct vdpa_config_ops *config,
- int nvqs, size_t size, const char *name)
+ size_t size, const char *name)
{
struct vdpa_device *vdev;
int err = -EINVAL;
vdev->index = err;
vdev->config = config;
vdev->features_valid = false;
- vdev->nvqs = nvqs;
if (name)
err = dev_set_name(&vdev->dev, "%s", name);
return (strcmp(dev_name(&vdev->dev), data) == 0);
}
-static int __vdpa_register_device(struct vdpa_device *vdev)
+static int __vdpa_register_device(struct vdpa_device *vdev, int nvqs)
{
struct device *dev;
+ vdev->nvqs = nvqs;
+
lockdep_assert_held(&vdpa_dev_mutex);
dev = bus_find_device(&vdpa_bus, NULL, dev_name(&vdev->dev), vdpa_name_match);
if (dev) {
* Caller must invoke this routine in the management device dev_add()
* callback after setting up valid mgmtdev for this vdpa device.
* @vdev: the vdpa device to be registered to vDPA bus
+ * @nvqs: number of virtqueues supported by this device
*
* Returns an error when fail to add device to vDPA bus
*/
-int _vdpa_register_device(struct vdpa_device *vdev)
+int _vdpa_register_device(struct vdpa_device *vdev, int nvqs)
{
if (!vdev->mdev)
return -EINVAL;
- return __vdpa_register_device(vdev);
+ return __vdpa_register_device(vdev, nvqs);
}
EXPORT_SYMBOL_GPL(_vdpa_register_device);
* vdpa_register_device - register a vDPA device
* Callers must have a succeed call of vdpa_alloc_device() before.
* @vdev: the vdpa device to be registered to vDPA bus
+ * @nvqs: number of virtqueues supported by this device
*
* Returns an error when fail to add to vDPA bus
*/
-int vdpa_register_device(struct vdpa_device *vdev)
+int vdpa_register_device(struct vdpa_device *vdev, int nvqs)
{
int err;
mutex_lock(&vdpa_dev_mutex);
- err = __vdpa_register_device(vdev);
+ err = __vdpa_register_device(vdev, nvqs);
mutex_unlock(&vdpa_dev_mutex);
return err;
}
ops = &vdpasim_config_ops;
vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops,
- dev_attr->nvqs, dev_attr->name);
+ dev_attr->name);
if (!vdpasim)
goto err_alloc;
static void vdpasim_net_get_config(struct vdpasim *vdpasim, void *config)
{
- struct virtio_net_config *net_config =
- (struct virtio_net_config *)config;
+ struct virtio_net_config *net_config = config;
net_config->mtu = cpu_to_vdpasim16(vdpasim, 1500);
net_config->status = cpu_to_vdpasim16(vdpasim, VIRTIO_NET_S_LINK_UP);
if (IS_ERR(simdev))
return PTR_ERR(simdev);
- ret = _vdpa_register_device(&simdev->vdpa);
+ ret = _vdpa_register_device(&simdev->vdpa, VDPASIM_NET_VQ_NUM);
if (ret)
goto reg_err;
menuconfig VFIO
tristate "VFIO Non-Privileged userspace driver framework"
- depends on IOMMU_API
- select VFIO_IOMMU_TYPE1 if (X86 || S390 || ARM || ARM64)
+ select IOMMU_API
+ select VFIO_IOMMU_TYPE1 if MMU && (X86 || S390 || ARM || ARM64)
help
VFIO provides a framework for secure userspace device drivers.
See Documentation/driver-api/vfio.rst for more details.
config VFIO_PCI_NVLINK2
def_bool y
- depends on VFIO_PCI && PPC_POWERNV
+ depends on VFIO_PCI && PPC_POWERNV && SPAPR_TCE_IOMMU
help
VFIO PCI support for P9 Witherspoon machine with NVIDIA V100 GPUs
index = vma->vm_pgoff >> (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT);
+ if (index >= VFIO_PCI_NUM_REGIONS + vdev->num_regions)
+ return -EINVAL;
if (vma->vm_end < vma->vm_start)
return -EINVAL;
if ((vma->vm_flags & VM_SHARED) == 0)
int regnum = index - VFIO_PCI_NUM_REGIONS;
struct vfio_pci_region *region = vdev->region + regnum;
- if (region && region->ops && region->ops->mmap &&
+ if (region->ops && region->ops->mmap &&
(region->flags & VFIO_REGION_INFO_FLAG_MMAP))
return region->ops->mmap(vdev, region, vma);
return -EINVAL;
# SPDX-License-Identifier: GPL-2.0-only
config VFIO_PLATFORM
tristate "VFIO support for platform devices"
- depends on VFIO && EVENTFD && (ARM || ARM64)
+ depends on VFIO && EVENTFD && (ARM || ARM64 || COMPILE_TEST)
select VFIO_VIRQFD
help
Support for platform devices with VFIO. This is required to make
config VFIO_AMBA
tristate "VFIO support for AMBA devices"
- depends on VFIO_PLATFORM && ARM_AMBA
+ depends on VFIO_PLATFORM && (ARM_AMBA || COMPILE_TEST)
help
Support for ARM AMBA devices with VFIO. This is required to make
use of ARM AMBA devices present on the system using the VFIO
}
static struct rb_node *vfio_find_dma_first_node(struct vfio_iommu *iommu,
- dma_addr_t start, size_t size)
+ dma_addr_t start, u64 size)
{
struct rb_node *res = NULL;
struct rb_node *node = iommu->dma_list.rb_node;
ret = vfio_lock_acct(dma, lock_acct, false);
unpin_out:
+ if (batch->size == 1 && !batch->offset) {
+ /* May be a VM_PFNMAP pfn, which the batch can't remember. */
+ put_pfn(pfn, dma->prot);
+ batch->size = 0;
+ }
+
if (ret < 0) {
if (pinned && !rsvd) {
for (pfn = *pfn_base ; pinned ; pfn++, pinned--)
return -ENODEV;
ret = vaddr_get_pfns(mm, vaddr, 1, dma->prot, pfn_base, pages);
- if (ret == 1 && do_accounting && !is_invalid_reserved_pfn(*pfn_base)) {
+ if (ret != 1)
+ goto out;
+
+ ret = 0;
+
+ if (do_accounting && !is_invalid_reserved_pfn(*pfn_base)) {
ret = vfio_lock_acct(dma, 1, true);
if (ret) {
put_pfn(*pfn_base, dma->prot);
}
}
+out:
mmput(mm);
return ret;
}
int ret = -EINVAL, retries = 0;
unsigned long pgshift;
dma_addr_t iova = unmap->iova;
- unsigned long size = unmap->size;
+ u64 size = unmap->size;
bool unmap_all = unmap->flags & VFIO_DMA_UNMAP_FLAG_ALL;
bool invalidate_vaddr = unmap->flags & VFIO_DMA_UNMAP_FLAG_VADDR;
struct rb_node *n, *first_n;
if (unmap_all) {
if (iova || size)
goto unlock;
- size = SIZE_MAX;
- } else if (!size || size & (pgsize - 1)) {
+ size = U64_MAX;
+ } else if (!size || size & (pgsize - 1) ||
+ iova + size - 1 < iova || size > SIZE_MAX) {
goto unlock;
}
- if (iova + size - 1 < iova || size > SIZE_MAX)
- goto unlock;
-
/* When dirty tracking is enabled, allow only min supported pgsize */
if ((unmap->flags & VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) &&
(!iommu->dirty_page_tracking || (bitmap->pgsize != pgsize))) {
static void vhost_vdpa_config_put(struct vhost_vdpa *v)
{
- if (v->config_ctx)
+ if (v->config_ctx) {
eventfd_ctx_put(v->config_ctx);
+ v->config_ctx = NULL;
+ }
}
static long vhost_vdpa_set_config_call(struct vhost_vdpa *v, u32 __user *argp)
if (!IS_ERR_OR_NULL(ctx))
eventfd_ctx_put(ctx);
- if (IS_ERR(v->config_ctx))
- return PTR_ERR(v->config_ctx);
+ if (IS_ERR(v->config_ctx)) {
+ long ret = PTR_ERR(v->config_ctx);
+
+ v->config_ctx = NULL;
+ return ret;
+ }
v->vdpa->config->set_config_cb(v->vdpa, &cb);
const struct vdpa_config_ops *ops = vdpa->config;
int r = 0;
+ mutex_lock(&dev->mutex);
+
r = vhost_dev_check_owner(dev);
if (r)
- return r;
+ goto unlock;
switch (msg->type) {
case VHOST_IOTLB_UPDATE:
r = -EINVAL;
break;
}
+unlock:
+ mutex_unlock(&dev->mutex);
return r;
}
static void vhost_vdpa_clean_irq(struct vhost_vdpa *v)
{
- struct vhost_virtqueue *vq;
int i;
- for (i = 0; i < v->nvqs; i++) {
- vq = &v->vqs[i];
- if (vq->call_ctx.producer.irq)
- irq_bypass_unregister_producer(&vq->call_ctx.producer);
- }
+ for (i = 0; i < v->nvqs; i++)
+ vhost_vdpa_unsetup_vq_irq(v, i);
}
static int vhost_vdpa_release(struct inode *inode, struct file *filep)
vq->error_ctx = NULL;
vq->kick = NULL;
vq->log_ctx = NULL;
- vhost_reset_is_le(vq);
vhost_disable_cross_endian(vq);
+ vhost_reset_is_le(vq);
vq->busyloop_timeout = 0;
vq->umem = NULL;
vq->iotlb = NULL;
#endif
}
-#if defined(CONFIG_PMAC_BACKLIGHT) || defined (CONFIG_FB_ATY_GENERIC_LCD) || \
-defined (CONFIG_FB_ATY_BACKLIGHT)
extern void aty_st_lcd(int index, u32 val, const struct atyfb_par *par);
extern u32 aty_ld_lcd(int index, const struct atyfb_par *par);
-#endif
/*
* DAC operations
#define PRINTKE(fmt, args...) printk(KERN_ERR "atyfb: " fmt, ## args)
#if defined(CONFIG_PMAC_BACKLIGHT) || defined(CONFIG_FB_ATY_GENERIC_LCD) || \
-defined(CONFIG_FB_ATY_BACKLIGHT)
+defined(CONFIG_FB_ATY_BACKLIGHT) || defined (CONFIG_PPC_PMAC)
static const u32 lt_lcd_regs[] = {
CNFG_PANEL_LG,
LCD_GEN_CNTL_LG,
return aty_ld_le32(LCD_DATA, par);
}
}
-#else /* defined(CONFIG_PMAC_BACKLIGHT) || defined(CONFIG_FB_ATY_BACKLIGHT) \
- defined(CONFIG_FB_ATY_GENERIC_LCD) */
+#else /* defined(CONFIG_PMAC_BACKLIGHT) || defined(CONFIG_FB_ATY_BACKLIGHT) ||
+ defined(CONFIG_FB_ATY_GENERIC_LCD) || defined(CONFIG_PPC_PMAC) */
void aty_st_lcd(int index, u32 val, const struct atyfb_par *par)
{ }
{
return 0;
}
-#endif /* defined(CONFIG_PMAC_BACKLIGHT) || defined (CONFIG_FB_ATY_GENERIC_LCD) */
+#endif /* defined(CONFIG_PMAC_BACKLIGHT) || defined(CONFIG_FB_ATY_BACKLIGHT) ||
+ defined (CONFIG_FB_ATY_GENERIC_LCD) || defined(CONFIG_PPC_PMAC) */
#ifdef CONFIG_FB_ATY_GENERIC_LCD
/*
ops->cursor_flash = (mode == CM_ERASE) ? 0 : 1;
+ if (!ops->cursor)
+ return;
+
ops->cursor(vc, info, mode, get_color(vc, info, c, 1),
get_color(vc, info, c, 0));
}
PCI_DEVICE_ID_HYPERV_VIDEO, NULL);
if (!pdev) {
pr_err("Unable to find PCI Hyper-V video\n");
- kfree(info->apertures);
return -ENODEV;
}
} else {
pci_dev_put(pdev);
}
- kfree(info->apertures);
return 0;
err1:
if (!gen2vm)
pci_dev_put(pdev);
- kfree(info->apertures);
return -ENOMEM;
}
acrn_ioreq_request_clear(vm);
break;
case ACRN_IOCTL_PM_GET_CPU_STATE:
- if (copy_from_user(&cstate_cmd, (void *)ioctl_param,
+ if (copy_from_user(&cstate_cmd, (void __user *)ioctl_param,
sizeof(cstate_cmd)))
return -EFAULT;
}
static DEVICE_ATTR_WO(remove_cpu);
+static umode_t acrn_attr_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+ if (a == &dev_attr_remove_cpu.attr)
+ return IS_ENABLED(CONFIG_HOTPLUG_CPU) ? a->mode : 0;
+
+ return a->mode;
+}
+
static struct attribute *acrn_attrs[] = {
&dev_attr_remove_cpu.attr,
NULL
static struct attribute_group acrn_attr_group = {
.attrs = acrn_attrs,
+ .is_visible = acrn_attr_visible,
};
static const struct attribute_group *acrn_attr_groups[] = {
{
struct eventfd_ctx *eventfd = NULL;
struct hsm_irqfd *irqfd, *tmp;
- unsigned int events;
+ __poll_t events;
struct fd f;
int ret = 0;
mutex_unlock(&vm->irqfds_lock);
/* Check the pending event in this stage */
- events = f.file->f_op->poll(f.file, &irqfd->pt);
+ events = vfs_poll(f.file, &irqfd->pt);
- if (events & POLLIN)
+ if (events & EPOLLIN)
acrn_irqfd_inject(irqfd);
fdput(f);
}
EXPORT_SYMBOL_GPL(virtio_config_changed);
-void virtio_config_disable(struct virtio_device *dev)
+static void virtio_config_disable(struct virtio_device *dev)
{
spin_lock_irq(&dev->config_lock);
dev->config_enabled = false;
spin_unlock_irq(&dev->config_lock);
}
-EXPORT_SYMBOL_GPL(virtio_config_disable);
-void virtio_config_enable(struct virtio_device *dev)
+static void virtio_config_enable(struct virtio_device *dev)
{
spin_lock_irq(&dev->config_lock);
dev->config_enabled = true;
dev->config_change_pending = false;
spin_unlock_irq(&dev->config_lock);
}
-EXPORT_SYMBOL_GPL(virtio_config_enable);
void virtio_add_status(struct virtio_device *dev, unsigned int status)
{
{
struct virtio_device *vdev =
container_of(_d, struct virtio_device, dev);
- struct virtio_mmio_device *vm_dev =
- container_of(vdev, struct virtio_mmio_device, vdev);
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
struct platform_device *pdev = vm_dev->pdev;
devm_kfree(&pdev->dev, vm_dev);
/*
* Watchdog driver for Marvell Armada 37xx SoCs
*
- * Author: Marek Behun <marek.behun@nic.cz>
+ * Author: Marek Behún <kabel@kernel.org>
*/
#include <linux/clk.h>
module_platform_driver(armada_37xx_wdt_driver);
-MODULE_AUTHOR("Marek Behun <marek.behun@nic.cz>");
+MODULE_AUTHOR("Marek Behun <kabel@kernel.org>");
MODULE_DESCRIPTION("Armada 37xx CPU Watchdog");
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Heiko Ronsdorf <hero@ihg.uni-duisburg.de>");
MODULE_DESCRIPTION("sma cpu5 watchdog driver");
-MODULE_SUPPORTED_DEVICE("sma cpu5 watchdog");
MODULE_LICENSE("GPL");
module_param_hw(port, int, ioport, 0);
MODULE_AUTHOR("Eric Brower <ebrower@usa.net>");
MODULE_DESCRIPTION("Hardware watchdog driver for Sun Microsystems CP1400/1500");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("watchdog");
static void cpwd_writew(u16 val, void __iomem *addr)
{
MODULE_AUTHOR("David S. Miller <davem@davemloft.net>");
MODULE_DESCRIPTION("Hardware watchdog driver for Sun RIO");
-MODULE_SUPPORTED_DEVICE("watchdog");
MODULE_LICENSE("GPL");
#define DRIVER_NAME "riowd"
SUBSYSTEM=="memory", ACTION=="add", RUN+="/bin/sh -c '[ -f /sys$devpath/state ] && echo online > /sys$devpath/state'"
-config XEN_BALLOON_MEMORY_HOTPLUG_LIMIT
+config XEN_MEMORY_HOTPLUG_LIMIT
int "Hotplugged memory limit (in GiB) for a PV guest"
default 512
depends on XEN_HAVE_PVMMU
- depends on XEN_BALLOON_MEMORY_HOTPLUG
+ depends on MEMORY_HOTPLUG
help
Maxmium amount of memory (in GiB) that a PV guest can be
expanded to when using memory hotplug.
depends on XEN
default m
-config XEN_STUB
- bool "Xen stub drivers"
- depends on XEN && X86_64 && BROKEN
- help
- Allow kernel to install stub drivers, to reserve space for Xen drivers,
- i.e. memory hotplug and cpu hotplug, and to block native drivers loaded,
- so that real Xen drivers can be modular.
-
- To enable Xen features like cpu and memory hotplug, select Y here.
-
-config XEN_ACPI_HOTPLUG_MEMORY
- tristate "Xen ACPI memory hotplug"
- depends on XEN_DOM0 && XEN_STUB && ACPI
- help
- This is Xen ACPI memory hotplug.
-
- Currently Xen only support ACPI memory hot-add. If you want
- to hot-add memory at runtime (the hot-added memory cannot be
- removed until machine stop), select Y/M here, otherwise select N.
-
-config XEN_ACPI_HOTPLUG_CPU
- tristate "Xen ACPI cpu hotplug"
- depends on XEN_DOM0 && XEN_STUB && ACPI
- select ACPI_CONTAINER
- help
- Xen ACPI cpu enumerating and hotplugging
-
- For hotplugging, currently Xen only support ACPI cpu hotadd.
- If you want to hotadd cpu at runtime (the hotadded cpu cannot
- be removed until machine stop), select Y/M here.
-
config XEN_ACPI_PROCESSOR
tristate "Xen ACPI processor"
depends on XEN && XEN_DOM0 && X86 && ACPI_PROCESSOR && CPU_FREQ
obj-$(CONFIG_XEN_MCE_LOG) += mcelog.o
obj-$(CONFIG_XEN_PCIDEV_BACKEND) += xen-pciback/
obj-$(CONFIG_XEN_PRIVCMD) += xen-privcmd.o
-obj-$(CONFIG_XEN_STUB) += xen-stub.o
-obj-$(CONFIG_XEN_ACPI_HOTPLUG_MEMORY) += xen-acpi-memhotplug.o
-obj-$(CONFIG_XEN_ACPI_HOTPLUG_CPU) += xen-acpi-cpuhotplug.o
obj-$(CONFIG_XEN_ACPI_PROCESSOR) += xen-acpi-processor.o
obj-$(CONFIG_XEN_EFI) += efi.o
obj-$(CONFIG_XEN_SCSI_BACKEND) += xen-scsiback.o
return EVTCHN_2L_NR_CHANNELS;
}
+static void evtchn_2l_remove(evtchn_port_t evtchn, unsigned int cpu)
+{
+ clear_bit(evtchn, BM(per_cpu(cpu_evtchn_mask, cpu)));
+}
+
static void evtchn_2l_bind_to_cpu(evtchn_port_t evtchn, unsigned int cpu,
unsigned int old_cpu)
{
return sync_test_bit(port, BM(&s->evtchn_pending[0]));
}
-static bool evtchn_2l_test_and_set_mask(evtchn_port_t port)
-{
- struct shared_info *s = HYPERVISOR_shared_info;
- return sync_test_and_set_bit(port, BM(&s->evtchn_mask[0]));
-}
-
static void evtchn_2l_mask(evtchn_port_t port)
{
struct shared_info *s = HYPERVISOR_shared_info;
EVTCHN_2L_NR_CHANNELS/BITS_PER_EVTCHN_WORD);
}
+static int evtchn_2l_percpu_deinit(unsigned int cpu)
+{
+ memset(per_cpu(cpu_evtchn_mask, cpu), 0, sizeof(xen_ulong_t) *
+ EVTCHN_2L_NR_CHANNELS/BITS_PER_EVTCHN_WORD);
+
+ return 0;
+}
+
static const struct evtchn_ops evtchn_ops_2l = {
.max_channels = evtchn_2l_max_channels,
.nr_channels = evtchn_2l_max_channels,
+ .remove = evtchn_2l_remove,
.bind_to_cpu = evtchn_2l_bind_to_cpu,
.clear_pending = evtchn_2l_clear_pending,
.set_pending = evtchn_2l_set_pending,
.is_pending = evtchn_2l_is_pending,
- .test_and_set_mask = evtchn_2l_test_and_set_mask,
.mask = evtchn_2l_mask,
.unmask = evtchn_2l_unmask,
.handle_events = evtchn_2l_handle_events,
.resume = evtchn_2l_resume,
+ .percpu_deinit = evtchn_2l_percpu_deinit,
};
void __init xen_evtchn_2l_init(void)
short refcnt;
u8 spurious_cnt;
u8 is_accounted;
- enum xen_irq_type type; /* type */
+ short type; /* type: IRQT_* */
+ u8 mask_reason; /* Why is event channel masked */
+#define EVT_MASK_REASON_EXPLICIT 0x01
+#define EVT_MASK_REASON_TEMPORARY 0x02
+#define EVT_MASK_REASON_EOI_PENDING 0x04
+ u8 is_active; /* Is event just being handled? */
unsigned irq;
evtchn_port_t evtchn; /* event channel */
unsigned short cpu; /* cpu bound */
unsigned short eoi_cpu; /* EOI must happen on this cpu-1 */
unsigned int irq_epoch; /* If eoi_cpu valid: irq_epoch of event */
u64 eoi_time; /* Time in jiffies when to EOI. */
+ raw_spinlock_t lock;
union {
unsigned short virq;
* evtchn_rwlock
* IRQ-desc lock
* percpu eoi_list_lock
+ * irq_info->lock
*/
static LIST_HEAD(xen_irq_list_head);
info->irq = irq;
info->evtchn = evtchn;
info->cpu = cpu;
+ info->mask_reason = EVT_MASK_REASON_EXPLICIT;
+ raw_spin_lock_init(&info->lock);
ret = set_evtchn_to_irq(evtchn, irq);
if (ret < 0)
static void xen_irq_info_cleanup(struct irq_info *info)
{
set_evtchn_to_irq(info->evtchn, -1);
+ xen_evtchn_port_remove(info->evtchn, info->cpu);
info->evtchn = 0;
channels_on_cpu_dec(info);
}
return ret;
}
+static void do_mask(struct irq_info *info, u8 reason)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&info->lock, flags);
+
+ if (!info->mask_reason)
+ mask_evtchn(info->evtchn);
+
+ info->mask_reason |= reason;
+
+ raw_spin_unlock_irqrestore(&info->lock, flags);
+}
+
+static void do_unmask(struct irq_info *info, u8 reason)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&info->lock, flags);
+
+ info->mask_reason &= ~reason;
+
+ if (!info->mask_reason)
+ unmask_evtchn(info->evtchn);
+
+ raw_spin_unlock_irqrestore(&info->lock, flags);
+}
+
#ifdef CONFIG_X86
static bool pirq_check_eoi_map(unsigned irq)
{
}
info->eoi_time = 0;
- unmask_evtchn(evtchn);
+ do_unmask(info, EVT_MASK_REASON_EOI_PENDING);
}
static void xen_irq_lateeoi_worker(struct work_struct *work)
BUG();
}
+static void event_handler_exit(struct irq_info *info)
+{
+ smp_store_release(&info->is_active, 0);
+ clear_evtchn(info->evtchn);
+}
+
static void pirq_query_unmask(int irq)
{
struct physdev_irq_status_query irq_status;
static void eoi_pirq(struct irq_data *data)
{
- evtchn_port_t evtchn = evtchn_from_irq(data->irq);
+ struct irq_info *info = info_for_irq(data->irq);
+ evtchn_port_t evtchn = info ? info->evtchn : 0;
struct physdev_eoi eoi = { .irq = pirq_from_irq(data->irq) };
int rc = 0;
if (!VALID_EVTCHN(evtchn))
return;
- clear_evtchn(evtchn);
+ event_handler_exit(info);
if (pirq_needs_eoi(data->irq)) {
rc = HYPERVISOR_physdev_op(PHYSDEVOP_eoi, &eoi);
goto err;
out:
- unmask_evtchn(evtchn);
+ do_unmask(info, EVT_MASK_REASON_EXPLICIT);
+
eoi_pirq(irq_get_irq_data(irq));
return 0;
if (!VALID_EVTCHN(evtchn))
return;
- mask_evtchn(evtchn);
+ do_mask(info, EVT_MASK_REASON_EXPLICIT);
xen_evtchn_close(evtchn);
xen_irq_info_cleanup(info);
}
}
info = info_for_irq(irq);
+ if (xchg_acquire(&info->is_active, 1))
+ return;
dev = (info->type == IRQT_EVTCHN) ? info->u.interdomain : NULL;
if (dev)
}
/* Rebind an evtchn so that it gets delivered to a specific cpu */
-static int xen_rebind_evtchn_to_cpu(evtchn_port_t evtchn, unsigned int tcpu)
+static int xen_rebind_evtchn_to_cpu(struct irq_info *info, unsigned int tcpu)
{
struct evtchn_bind_vcpu bind_vcpu;
- int masked;
+ evtchn_port_t evtchn = info ? info->evtchn : 0;
if (!VALID_EVTCHN(evtchn))
return -1;
* Mask the event while changing the VCPU binding to prevent
* it being delivered on an unexpected VCPU.
*/
- masked = test_and_set_mask(evtchn);
+ do_mask(info, EVT_MASK_REASON_TEMPORARY);
/*
* If this fails, it usually just indicates that we're dealing with a
if (HYPERVISOR_event_channel_op(EVTCHNOP_bind_vcpu, &bind_vcpu) >= 0)
bind_evtchn_to_cpu(evtchn, tcpu, false);
- if (!masked)
- unmask_evtchn(evtchn);
+ do_unmask(info, EVT_MASK_REASON_TEMPORARY);
return 0;
}
unsigned int tcpu = select_target_cpu(dest);
int ret;
- ret = xen_rebind_evtchn_to_cpu(evtchn_from_irq(data->irq), tcpu);
+ ret = xen_rebind_evtchn_to_cpu(info_for_irq(data->irq), tcpu);
if (!ret)
irq_data_update_effective_affinity(data, cpumask_of(tcpu));
static void enable_dynirq(struct irq_data *data)
{
- evtchn_port_t evtchn = evtchn_from_irq(data->irq);
+ struct irq_info *info = info_for_irq(data->irq);
+ evtchn_port_t evtchn = info ? info->evtchn : 0;
if (VALID_EVTCHN(evtchn))
- unmask_evtchn(evtchn);
+ do_unmask(info, EVT_MASK_REASON_EXPLICIT);
}
static void disable_dynirq(struct irq_data *data)
{
- evtchn_port_t evtchn = evtchn_from_irq(data->irq);
+ struct irq_info *info = info_for_irq(data->irq);
+ evtchn_port_t evtchn = info ? info->evtchn : 0;
if (VALID_EVTCHN(evtchn))
- mask_evtchn(evtchn);
+ do_mask(info, EVT_MASK_REASON_EXPLICIT);
}
static void ack_dynirq(struct irq_data *data)
{
- evtchn_port_t evtchn = evtchn_from_irq(data->irq);
+ struct irq_info *info = info_for_irq(data->irq);
+ evtchn_port_t evtchn = info ? info->evtchn : 0;
- if (!VALID_EVTCHN(evtchn))
- return;
-
- clear_evtchn(evtchn);
+ if (VALID_EVTCHN(evtchn))
+ event_handler_exit(info);
}
static void mask_ack_dynirq(struct irq_data *data)
ack_dynirq(data);
}
+static void lateeoi_ack_dynirq(struct irq_data *data)
+{
+ struct irq_info *info = info_for_irq(data->irq);
+ evtchn_port_t evtchn = info ? info->evtchn : 0;
+
+ if (VALID_EVTCHN(evtchn)) {
+ do_mask(info, EVT_MASK_REASON_EOI_PENDING);
+ event_handler_exit(info);
+ }
+}
+
+static void lateeoi_mask_ack_dynirq(struct irq_data *data)
+{
+ struct irq_info *info = info_for_irq(data->irq);
+ evtchn_port_t evtchn = info ? info->evtchn : 0;
+
+ if (VALID_EVTCHN(evtchn)) {
+ do_mask(info, EVT_MASK_REASON_EXPLICIT);
+ event_handler_exit(info);
+ }
+}
+
static int retrigger_dynirq(struct irq_data *data)
{
- evtchn_port_t evtchn = evtchn_from_irq(data->irq);
- int masked;
+ struct irq_info *info = info_for_irq(data->irq);
+ evtchn_port_t evtchn = info ? info->evtchn : 0;
if (!VALID_EVTCHN(evtchn))
return 0;
- masked = test_and_set_mask(evtchn);
+ do_mask(info, EVT_MASK_REASON_TEMPORARY);
set_evtchn(evtchn);
- if (!masked)
- unmask_evtchn(evtchn);
+ do_unmask(info, EVT_MASK_REASON_TEMPORARY);
return 1;
}
/* Clear an irq's pending state, in preparation for polling on it */
void xen_clear_irq_pending(int irq)
{
- evtchn_port_t evtchn = evtchn_from_irq(irq);
+ struct irq_info *info = info_for_irq(irq);
+ evtchn_port_t evtchn = info ? info->evtchn : 0;
if (VALID_EVTCHN(evtchn))
- clear_evtchn(evtchn);
+ event_handler_exit(info);
}
EXPORT_SYMBOL(xen_clear_irq_pending);
void xen_set_irq_pending(int irq)
.irq_mask = disable_dynirq,
.irq_unmask = enable_dynirq,
- .irq_ack = mask_ack_dynirq,
- .irq_mask_ack = mask_ack_dynirq,
+ .irq_ack = lateeoi_ack_dynirq,
+ .irq_mask_ack = lateeoi_mask_ack_dynirq,
.irq_set_affinity = set_affinity_irq,
.irq_retrigger = retrigger_dynirq,
return sync_test_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word));
}
-static bool evtchn_fifo_test_and_set_mask(evtchn_port_t port)
-{
- event_word_t *word = event_word_from_port(port);
- return sync_test_and_set_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word));
-}
-
static void evtchn_fifo_mask(evtchn_port_t port)
{
event_word_t *word = event_word_from_port(port);
.clear_pending = evtchn_fifo_clear_pending,
.set_pending = evtchn_fifo_set_pending,
.is_pending = evtchn_fifo_is_pending,
- .test_and_set_mask = evtchn_fifo_test_and_set_mask,
.mask = evtchn_fifo_mask,
.unmask = evtchn_fifo_unmask,
.handle_events = evtchn_fifo_handle_events,
unsigned (*nr_channels)(void);
int (*setup)(evtchn_port_t port);
+ void (*remove)(evtchn_port_t port, unsigned int cpu);
void (*bind_to_cpu)(evtchn_port_t evtchn, unsigned int cpu,
unsigned int old_cpu);
void (*clear_pending)(evtchn_port_t port);
void (*set_pending)(evtchn_port_t port);
bool (*is_pending)(evtchn_port_t port);
- bool (*test_and_set_mask)(evtchn_port_t port);
void (*mask)(evtchn_port_t port);
void (*unmask)(evtchn_port_t port);
return 0;
}
+static inline void xen_evtchn_port_remove(evtchn_port_t evtchn,
+ unsigned int cpu)
+{
+ if (evtchn_ops->remove)
+ evtchn_ops->remove(evtchn, cpu);
+}
+
static inline void xen_evtchn_port_bind_to_cpu(evtchn_port_t evtchn,
unsigned int cpu,
unsigned int old_cpu)
return evtchn_ops->is_pending(port);
}
-static inline bool test_and_set_mask(evtchn_port_t port)
-{
- return evtchn_ops->test_and_set_mask(port);
-}
-
static inline void mask_evtchn(evtchn_port_t port)
{
return evtchn_ops->mask(port);
if (NULL == add)
return NULL;
- add->grants = kvcalloc(count, sizeof(add->grants[0]), GFP_KERNEL);
- add->map_ops = kvcalloc(count, sizeof(add->map_ops[0]), GFP_KERNEL);
- add->unmap_ops = kvcalloc(count, sizeof(add->unmap_ops[0]), GFP_KERNEL);
- add->kmap_ops = kvcalloc(count, sizeof(add->kmap_ops[0]), GFP_KERNEL);
- add->kunmap_ops = kvcalloc(count,
- sizeof(add->kunmap_ops[0]), GFP_KERNEL);
+ add->grants = kvmalloc_array(count, sizeof(add->grants[0]),
+ GFP_KERNEL);
+ add->map_ops = kvmalloc_array(count, sizeof(add->map_ops[0]),
+ GFP_KERNEL);
+ add->unmap_ops = kvmalloc_array(count, sizeof(add->unmap_ops[0]),
+ GFP_KERNEL);
add->pages = kvcalloc(count, sizeof(add->pages[0]), GFP_KERNEL);
if (NULL == add->grants ||
NULL == add->map_ops ||
NULL == add->unmap_ops ||
- NULL == add->kmap_ops ||
- NULL == add->kunmap_ops ||
NULL == add->pages)
goto err;
+ if (use_ptemod) {
+ add->kmap_ops = kvmalloc_array(count, sizeof(add->kmap_ops[0]),
+ GFP_KERNEL);
+ add->kunmap_ops = kvmalloc_array(count, sizeof(add->kunmap_ops[0]),
+ GFP_KERNEL);
+ if (NULL == add->kmap_ops || NULL == add->kunmap_ops)
+ goto err;
+ }
#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
add->dma_flags = dma_flags;
goto err;
for (i = 0; i < count; i++) {
- add->map_ops[i].handle = -1;
- add->unmap_ops[i].handle = -1;
- add->kmap_ops[i].handle = -1;
- add->kunmap_ops[i].handle = -1;
+ add->grants[i].domid = DOMID_INVALID;
+ add->grants[i].ref = INVALID_GRANT_REF;
+ add->map_ops[i].handle = INVALID_GRANT_HANDLE;
+ add->unmap_ops[i].handle = INVALID_GRANT_HANDLE;
+ if (use_ptemod) {
+ add->kmap_ops[i].handle = INVALID_GRANT_HANDLE;
+ add->kunmap_ops[i].handle = INVALID_GRANT_HANDLE;
+ }
}
add->index = 0;
map->grants[pgnr].ref,
map->grants[pgnr].domid);
gnttab_set_unmap_op(&map->unmap_ops[pgnr], pte_maddr, flags,
- -1 /* handle */);
+ INVALID_GRANT_HANDLE);
return 0;
}
if (!use_ptemod) {
/* Note: it could already be mapped */
- if (map->map_ops[0].handle != -1)
+ if (map->map_ops[0].handle != INVALID_GRANT_HANDLE)
return 0;
for (i = 0; i < map->count; i++) {
unsigned long addr = (unsigned long)
map->grants[i].ref,
map->grants[i].domid);
gnttab_set_unmap_op(&map->unmap_ops[i], addr,
- map->flags, -1 /* handle */);
+ map->flags, INVALID_GRANT_HANDLE);
}
} else {
/*
map->grants[i].ref,
map->grants[i].domid);
gnttab_set_unmap_op(&map->kunmap_ops[i], address,
- flags, -1);
+ flags, INVALID_GRANT_HANDLE);
}
}
pr_debug("map %d+%d\n", map->index, map->count);
- err = gnttab_map_refs(map->map_ops, use_ptemod ? map->kmap_ops : NULL,
- map->pages, map->count);
+ err = gnttab_map_refs(map->map_ops, map->kmap_ops, map->pages,
+ map->count);
for (i = 0; i < map->count; i++) {
if (map->map_ops[i].status == GNTST_okay)
pr_debug("unmap handle=%d st=%d\n",
map->unmap_ops[offset+i].handle,
map->unmap_ops[offset+i].status);
- map->unmap_ops[offset+i].handle = -1;
+ map->unmap_ops[offset+i].handle = INVALID_GRANT_HANDLE;
}
return err;
}
* already unmapped some of the grants. Only unmap valid ranges.
*/
while (pages && !err) {
- while (pages && map->unmap_ops[offset].handle == -1) {
+ while (pages &&
+ map->unmap_ops[offset].handle == INVALID_GRANT_HANDLE) {
offset++;
pages--;
}
range = 0;
while (range < pages) {
- if (map->unmap_ops[offset+range].handle == -1)
+ if (map->unmap_ops[offset + range].handle ==
+ INVALID_GRANT_HANDLE)
break;
range++;
}
return IRQ_HANDLED;
}
-/* Sync with Xen hypervisor after cpu hotadded */
-void xen_pcpu_hotplug_sync(void)
-{
- schedule_work(&xen_pcpu_work);
-}
-EXPORT_SYMBOL_GPL(xen_pcpu_hotplug_sync);
-
-/*
- * For hypervisor presented cpu, return logic cpu id;
- * For hypervisor non-presented cpu, return -ENODEV.
- */
-int xen_pcpu_id(uint32_t acpi_id)
-{
- int cpu_id = 0, max_id = 0;
- struct xen_platform_op op;
-
- op.cmd = XENPF_get_cpuinfo;
- while (cpu_id <= max_id) {
- op.u.pcpu_info.xen_cpuid = cpu_id;
- if (HYPERVISOR_platform_op(&op)) {
- cpu_id++;
- continue;
- }
-
- if (acpi_id == op.u.pcpu_info.acpi_id)
- return cpu_id;
- if (op.u.pcpu_info.max_present > max_id)
- max_id = op.u.pcpu_info.max_present;
- cpu_id++;
- }
-
- return -ENODEV;
-}
-EXPORT_SYMBOL_GPL(xen_pcpu_id);
-
static int __init xen_pcpu_init(void)
{
int irq, ret;
#include <linux/math64.h>
#include <linux/gfp.h>
#include <linux/slab.h>
+#include <linux/static_call.h>
#include <asm/paravirt.h>
#include <asm/xen/hypervisor.h>
xen_runstate_remote = !HYPERVISOR_vm_assist(VMASST_CMD_enable,
VMASST_TYPE_runstate_update_flag);
- pv_ops.time.steal_clock = xen_steal_clock;
+ static_call_update(pv_steal_clock, xen_steal_clock);
static_key_slow_inc(¶virt_steal_enabled);
if (xen_runstate_remote)
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright (C) 2012 Intel Corporation
- * Author: Liu Jinsong <jinsong.liu@intel.com>
- * Author: Jiang Yunhong <yunhong.jiang@intel.com>
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/cpu.h>
-#include <linux/acpi.h>
-#include <linux/uaccess.h>
-#include <acpi/processor.h>
-#include <xen/acpi.h>
-#include <xen/interface/platform.h>
-#include <asm/xen/hypercall.h>
-
-#define PREFIX "ACPI:xen_cpu_hotplug:"
-
-#define INSTALL_NOTIFY_HANDLER 0
-#define UNINSTALL_NOTIFY_HANDLER 1
-
-static acpi_status xen_acpi_cpu_hotadd(struct acpi_processor *pr);
-
-/* --------------------------------------------------------------------------
- Driver Interface
--------------------------------------------------------------------------- */
-
-static int xen_acpi_processor_enable(struct acpi_device *device)
-{
- acpi_status status = 0;
- unsigned long long value;
- union acpi_object object = { 0 };
- struct acpi_buffer buffer = { sizeof(union acpi_object), &object };
- struct acpi_processor *pr = acpi_driver_data(device);
-
- if (!strcmp(acpi_device_hid(device), ACPI_PROCESSOR_OBJECT_HID)) {
- /* Declared with "Processor" statement; match ProcessorID */
- status = acpi_evaluate_object(pr->handle, NULL, NULL, &buffer);
- if (ACPI_FAILURE(status)) {
- pr_err(PREFIX "Evaluating processor object\n");
- return -ENODEV;
- }
-
- pr->acpi_id = object.processor.proc_id;
- } else {
- /* Declared with "Device" statement; match _UID */
- status = acpi_evaluate_integer(pr->handle, METHOD_NAME__UID,
- NULL, &value);
- if (ACPI_FAILURE(status)) {
- pr_err(PREFIX "Evaluating processor _UID\n");
- return -ENODEV;
- }
-
- pr->acpi_id = value;
- }
-
- pr->id = xen_pcpu_id(pr->acpi_id);
-
- if (invalid_logical_cpuid(pr->id))
- /* This cpu is not presented at hypervisor, try to hotadd it */
- if (ACPI_FAILURE(xen_acpi_cpu_hotadd(pr))) {
- pr_err(PREFIX "Hotadd CPU (acpi_id = %d) failed.\n",
- pr->acpi_id);
- return -ENODEV;
- }
-
- return 0;
-}
-
-static int xen_acpi_processor_add(struct acpi_device *device)
-{
- int ret;
- struct acpi_processor *pr;
-
- if (!device)
- return -EINVAL;
-
- pr = kzalloc(sizeof(struct acpi_processor), GFP_KERNEL);
- if (!pr)
- return -ENOMEM;
-
- pr->handle = device->handle;
- strcpy(acpi_device_name(device), ACPI_PROCESSOR_DEVICE_NAME);
- strcpy(acpi_device_class(device), ACPI_PROCESSOR_CLASS);
- device->driver_data = pr;
-
- ret = xen_acpi_processor_enable(device);
- if (ret)
- pr_err(PREFIX "Error when enabling Xen processor\n");
-
- return ret;
-}
-
-static int xen_acpi_processor_remove(struct acpi_device *device)
-{
- struct acpi_processor *pr;
-
- if (!device)
- return -EINVAL;
-
- pr = acpi_driver_data(device);
- if (!pr)
- return -EINVAL;
-
- kfree(pr);
- return 0;
-}
-
-/*--------------------------------------------------------------
- Acpi processor hotplug support
---------------------------------------------------------------*/
-
-static int is_processor_present(acpi_handle handle)
-{
- acpi_status status;
- unsigned long long sta = 0;
-
-
- status = acpi_evaluate_integer(handle, "_STA", NULL, &sta);
-
- if (ACPI_SUCCESS(status) && (sta & ACPI_STA_DEVICE_PRESENT))
- return 1;
-
- /*
- * _STA is mandatory for a processor that supports hot plug
- */
- if (status == AE_NOT_FOUND)
- pr_info(PREFIX "Processor does not support hot plug\n");
- else
- pr_info(PREFIX "Processor Device is not present");
- return 0;
-}
-
-static int xen_apic_id(acpi_handle handle)
-{
- struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
- union acpi_object *obj;
- struct acpi_madt_local_apic *lapic;
- int apic_id;
-
- if (ACPI_FAILURE(acpi_evaluate_object(handle, "_MAT", NULL, &buffer)))
- return -EINVAL;
-
- if (!buffer.length || !buffer.pointer)
- return -EINVAL;
-
- obj = buffer.pointer;
- if (obj->type != ACPI_TYPE_BUFFER ||
- obj->buffer.length < sizeof(*lapic)) {
- kfree(buffer.pointer);
- return -EINVAL;
- }
-
- lapic = (struct acpi_madt_local_apic *)obj->buffer.pointer;
-
- if (lapic->header.type != ACPI_MADT_TYPE_LOCAL_APIC ||
- !(lapic->lapic_flags & ACPI_MADT_ENABLED)) {
- kfree(buffer.pointer);
- return -EINVAL;
- }
-
- apic_id = (uint32_t)lapic->id;
- kfree(buffer.pointer);
- buffer.length = ACPI_ALLOCATE_BUFFER;
- buffer.pointer = NULL;
-
- return apic_id;
-}
-
-static int xen_hotadd_cpu(struct acpi_processor *pr)
-{
- int cpu_id, apic_id, pxm;
- struct xen_platform_op op;
-
- apic_id = xen_apic_id(pr->handle);
- if (apic_id < 0) {
- pr_err(PREFIX "Failed to get apic_id for acpi_id %d\n",
- pr->acpi_id);
- return -ENODEV;
- }
-
- pxm = xen_acpi_get_pxm(pr->handle);
- if (pxm < 0) {
- pr_err(PREFIX "Failed to get _PXM for acpi_id %d\n",
- pr->acpi_id);
- return pxm;
- }
-
- op.cmd = XENPF_cpu_hotadd;
- op.u.cpu_add.apic_id = apic_id;
- op.u.cpu_add.acpi_id = pr->acpi_id;
- op.u.cpu_add.pxm = pxm;
-
- cpu_id = HYPERVISOR_platform_op(&op);
- if (cpu_id < 0)
- pr_err(PREFIX "Failed to hotadd CPU for acpi_id %d\n",
- pr->acpi_id);
-
- return cpu_id;
-}
-
-static acpi_status xen_acpi_cpu_hotadd(struct acpi_processor *pr)
-{
- if (!is_processor_present(pr->handle))
- return AE_ERROR;
-
- pr->id = xen_hotadd_cpu(pr);
- if (invalid_logical_cpuid(pr->id))
- return AE_ERROR;
-
- /*
- * Sync with Xen hypervisor, providing new /sys/.../xen_cpuX
- * interface after cpu hotadded.
- */
- xen_pcpu_hotplug_sync();
-
- return AE_OK;
-}
-
-static int acpi_processor_device_remove(struct acpi_device *device)
-{
- pr_debug(PREFIX "Xen does not support CPU hotremove\n");
-
- return -ENOSYS;
-}
-
-static void acpi_processor_hotplug_notify(acpi_handle handle,
- u32 event, void *data)
-{
- struct acpi_processor *pr;
- struct acpi_device *device = NULL;
- u32 ost_code = ACPI_OST_SC_NON_SPECIFIC_FAILURE; /* default */
- int result;
-
- acpi_scan_lock_acquire();
-
- switch (event) {
- case ACPI_NOTIFY_BUS_CHECK:
- case ACPI_NOTIFY_DEVICE_CHECK:
- ACPI_DEBUG_PRINT((ACPI_DB_INFO,
- "Processor driver received %s event\n",
- (event == ACPI_NOTIFY_BUS_CHECK) ?
- "ACPI_NOTIFY_BUS_CHECK" : "ACPI_NOTIFY_DEVICE_CHECK"));
-
- if (!is_processor_present(handle))
- break;
-
- acpi_bus_get_device(handle, &device);
- if (acpi_device_enumerated(device))
- break;
-
- result = acpi_bus_scan(handle);
- if (result) {
- pr_err(PREFIX "Unable to add the device\n");
- break;
- }
- device = NULL;
- acpi_bus_get_device(handle, &device);
- if (!acpi_device_enumerated(device)) {
- pr_err(PREFIX "Missing device object\n");
- break;
- }
- ost_code = ACPI_OST_SC_SUCCESS;
- break;
-
- case ACPI_NOTIFY_EJECT_REQUEST:
- ACPI_DEBUG_PRINT((ACPI_DB_INFO,
- "received ACPI_NOTIFY_EJECT_REQUEST\n"));
-
- if (acpi_bus_get_device(handle, &device)) {
- pr_err(PREFIX "Device don't exist, dropping EJECT\n");
- break;
- }
- pr = acpi_driver_data(device);
- if (!pr) {
- pr_err(PREFIX "Driver data is NULL, dropping EJECT\n");
- break;
- }
-
- /*
- * TBD: implement acpi_processor_device_remove if Xen support
- * CPU hotremove in the future.
- */
- acpi_processor_device_remove(device);
- break;
-
- default:
- ACPI_DEBUG_PRINT((ACPI_DB_INFO,
- "Unsupported event [0x%x]\n", event));
-
- /* non-hotplug event; possibly handled by other handler */
- goto out;
- }
-
- (void) acpi_evaluate_ost(handle, event, ost_code, NULL);
-
-out:
- acpi_scan_lock_release();
-}
-
-static acpi_status is_processor_device(acpi_handle handle)
-{
- struct acpi_device_info *info;
- char *hid;
- acpi_status status;
-
- status = acpi_get_object_info(handle, &info);
- if (ACPI_FAILURE(status))
- return status;
-
- if (info->type == ACPI_TYPE_PROCESSOR) {
- kfree(info);
- return AE_OK; /* found a processor object */
- }
-
- if (!(info->valid & ACPI_VALID_HID)) {
- kfree(info);
- return AE_ERROR;
- }
-
- hid = info->hardware_id.string;
- if ((hid == NULL) || strcmp(hid, ACPI_PROCESSOR_DEVICE_HID)) {
- kfree(info);
- return AE_ERROR;
- }
-
- kfree(info);
- return AE_OK; /* found a processor device object */
-}
-
-static acpi_status
-processor_walk_namespace_cb(acpi_handle handle,
- u32 lvl, void *context, void **rv)
-{
- acpi_status status;
- int *action = context;
-
- status = is_processor_device(handle);
- if (ACPI_FAILURE(status))
- return AE_OK; /* not a processor; continue to walk */
-
- switch (*action) {
- case INSTALL_NOTIFY_HANDLER:
- acpi_install_notify_handler(handle,
- ACPI_SYSTEM_NOTIFY,
- acpi_processor_hotplug_notify,
- NULL);
- break;
- case UNINSTALL_NOTIFY_HANDLER:
- acpi_remove_notify_handler(handle,
- ACPI_SYSTEM_NOTIFY,
- acpi_processor_hotplug_notify);
- break;
- default:
- break;
- }
-
- /* found a processor; skip walking underneath */
- return AE_CTRL_DEPTH;
-}
-
-static
-void acpi_processor_install_hotplug_notify(void)
-{
- int action = INSTALL_NOTIFY_HANDLER;
- acpi_walk_namespace(ACPI_TYPE_ANY,
- ACPI_ROOT_OBJECT,
- ACPI_UINT32_MAX,
- processor_walk_namespace_cb, NULL, &action, NULL);
-}
-
-static
-void acpi_processor_uninstall_hotplug_notify(void)
-{
- int action = UNINSTALL_NOTIFY_HANDLER;
- acpi_walk_namespace(ACPI_TYPE_ANY,
- ACPI_ROOT_OBJECT,
- ACPI_UINT32_MAX,
- processor_walk_namespace_cb, NULL, &action, NULL);
-}
-
-static const struct acpi_device_id processor_device_ids[] = {
- {ACPI_PROCESSOR_OBJECT_HID, 0},
- {ACPI_PROCESSOR_DEVICE_HID, 0},
- {"", 0},
-};
-MODULE_DEVICE_TABLE(acpi, processor_device_ids);
-
-static struct acpi_driver xen_acpi_processor_driver = {
- .name = "processor",
- .class = ACPI_PROCESSOR_CLASS,
- .ids = processor_device_ids,
- .ops = {
- .add = xen_acpi_processor_add,
- .remove = xen_acpi_processor_remove,
- },
-};
-
-static int __init xen_acpi_processor_init(void)
-{
- int result = 0;
-
- if (!xen_initial_domain())
- return -ENODEV;
-
- /* unregister the stub which only used to reserve driver space */
- xen_stub_processor_exit();
-
- result = acpi_bus_register_driver(&xen_acpi_processor_driver);
- if (result < 0) {
- xen_stub_processor_init();
- return result;
- }
-
- acpi_processor_install_hotplug_notify();
- return 0;
-}
-
-static void __exit xen_acpi_processor_exit(void)
-{
- if (!xen_initial_domain())
- return;
-
- acpi_processor_uninstall_hotplug_notify();
-
- acpi_bus_unregister_driver(&xen_acpi_processor_driver);
-
- /*
- * stub reserve space again to prevent any chance of native
- * driver loading.
- */
- xen_stub_processor_init();
- return;
-}
-
-module_init(xen_acpi_processor_init);
-module_exit(xen_acpi_processor_exit);
-ACPI_MODULE_NAME("xen-acpi-cpuhotplug");
-MODULE_AUTHOR("Liu Jinsong <jinsong.liu@intel.com>");
-MODULE_DESCRIPTION("Xen Hotplug CPU Driver");
-MODULE_LICENSE("GPL");
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright (C) 2012 Intel Corporation
- * Author: Liu Jinsong <jinsong.liu@intel.com>
- * Author: Jiang Yunhong <yunhong.jiang@intel.com>
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/acpi.h>
-#include <xen/acpi.h>
-#include <xen/interface/platform.h>
-#include <asm/xen/hypercall.h>
-
-#define PREFIX "ACPI:xen_memory_hotplug:"
-
-struct acpi_memory_info {
- struct list_head list;
- u64 start_addr; /* Memory Range start physical addr */
- u64 length; /* Memory Range length */
- unsigned short caching; /* memory cache attribute */
- unsigned short write_protect; /* memory read/write attribute */
- /* copied from buffer getting from _CRS */
- unsigned int enabled:1;
-};
-
-struct acpi_memory_device {
- struct acpi_device *device;
- struct list_head res_list;
-};
-
-static bool acpi_hotmem_initialized __read_mostly;
-
-static int xen_hotadd_memory(int pxm, struct acpi_memory_info *info)
-{
- int rc;
- struct xen_platform_op op;
-
- op.cmd = XENPF_mem_hotadd;
- op.u.mem_add.spfn = info->start_addr >> PAGE_SHIFT;
- op.u.mem_add.epfn = (info->start_addr + info->length) >> PAGE_SHIFT;
- op.u.mem_add.pxm = pxm;
-
- rc = HYPERVISOR_dom0_op(&op);
- if (rc)
- pr_err(PREFIX "Xen Hotplug Memory Add failed on "
- "0x%lx -> 0x%lx, _PXM: %d, error: %d\n",
- (unsigned long)info->start_addr,
- (unsigned long)(info->start_addr + info->length),
- pxm, rc);
-
- return rc;
-}
-
-static int xen_acpi_memory_enable_device(struct acpi_memory_device *mem_device)
-{
- int pxm, result;
- int num_enabled = 0;
- struct acpi_memory_info *info;
-
- if (!mem_device)
- return -EINVAL;
-
- pxm = xen_acpi_get_pxm(mem_device->device->handle);
- if (pxm < 0)
- return pxm;
-
- list_for_each_entry(info, &mem_device->res_list, list) {
- if (info->enabled) { /* just sanity check...*/
- num_enabled++;
- continue;
- }
-
- if (!info->length)
- continue;
-
- result = xen_hotadd_memory(pxm, info);
- if (result)
- continue;
- info->enabled = 1;
- num_enabled++;
- }
-
- if (!num_enabled)
- return -ENODEV;
-
- return 0;
-}
-
-static acpi_status
-acpi_memory_get_resource(struct acpi_resource *resource, void *context)
-{
- struct acpi_memory_device *mem_device = context;
- struct acpi_resource_address64 address64;
- struct acpi_memory_info *info, *new;
- acpi_status status;
-
- status = acpi_resource_to_address64(resource, &address64);
- if (ACPI_FAILURE(status) ||
- (address64.resource_type != ACPI_MEMORY_RANGE))
- return AE_OK;
-
- list_for_each_entry(info, &mem_device->res_list, list) {
- if ((info->caching == address64.info.mem.caching) &&
- (info->write_protect == address64.info.mem.write_protect) &&
- (info->start_addr + info->length == address64.address.minimum)) {
- info->length += address64.address.address_length;
- return AE_OK;
- }
- }
-
- new = kzalloc(sizeof(struct acpi_memory_info), GFP_KERNEL);
- if (!new)
- return AE_ERROR;
-
- INIT_LIST_HEAD(&new->list);
- new->caching = address64.info.mem.caching;
- new->write_protect = address64.info.mem.write_protect;
- new->start_addr = address64.address.minimum;
- new->length = address64.address.address_length;
- list_add_tail(&new->list, &mem_device->res_list);
-
- return AE_OK;
-}
-
-static int
-acpi_memory_get_device_resources(struct acpi_memory_device *mem_device)
-{
- acpi_status status;
- struct acpi_memory_info *info, *n;
-
- if (!list_empty(&mem_device->res_list))
- return 0;
-
- status = acpi_walk_resources(mem_device->device->handle,
- METHOD_NAME__CRS, acpi_memory_get_resource, mem_device);
-
- if (ACPI_FAILURE(status)) {
- list_for_each_entry_safe(info, n, &mem_device->res_list, list)
- kfree(info);
- INIT_LIST_HEAD(&mem_device->res_list);
- return -EINVAL;
- }
-
- return 0;
-}
-
-static int acpi_memory_get_device(acpi_handle handle,
- struct acpi_memory_device **mem_device)
-{
- struct acpi_device *device = NULL;
- int result = 0;
-
- acpi_scan_lock_acquire();
-
- acpi_bus_get_device(handle, &device);
- if (acpi_device_enumerated(device))
- goto end;
-
- /*
- * Now add the notified device. This creates the acpi_device
- * and invokes .add function
- */
- result = acpi_bus_scan(handle);
- if (result) {
- pr_warn(PREFIX "ACPI namespace scan failed\n");
- result = -EINVAL;
- goto out;
- }
- device = NULL;
- acpi_bus_get_device(handle, &device);
- if (!acpi_device_enumerated(device)) {
- pr_warn(PREFIX "Missing device object\n");
- result = -EINVAL;
- goto out;
- }
-
-end:
- *mem_device = acpi_driver_data(device);
- if (!(*mem_device)) {
- pr_err(PREFIX "driver data not found\n");
- result = -ENODEV;
- goto out;
- }
-
-out:
- acpi_scan_lock_release();
- return result;
-}
-
-static int acpi_memory_check_device(struct acpi_memory_device *mem_device)
-{
- unsigned long long current_status;
-
- /* Get device present/absent information from the _STA */
- if (ACPI_FAILURE(acpi_evaluate_integer(mem_device->device->handle,
- "_STA", NULL, ¤t_status)))
- return -ENODEV;
- /*
- * Check for device status. Device should be
- * present/enabled/functioning.
- */
- if (!((current_status & ACPI_STA_DEVICE_PRESENT)
- && (current_status & ACPI_STA_DEVICE_ENABLED)
- && (current_status & ACPI_STA_DEVICE_FUNCTIONING)))
- return -ENODEV;
-
- return 0;
-}
-
-static int acpi_memory_disable_device(struct acpi_memory_device *mem_device)
-{
- pr_debug(PREFIX "Xen does not support memory hotremove\n");
-
- return -ENOSYS;
-}
-
-static void acpi_memory_device_notify(acpi_handle handle, u32 event, void *data)
-{
- struct acpi_memory_device *mem_device;
- struct acpi_device *device;
- u32 ost_code = ACPI_OST_SC_NON_SPECIFIC_FAILURE; /* default */
-
- switch (event) {
- case ACPI_NOTIFY_BUS_CHECK:
- ACPI_DEBUG_PRINT((ACPI_DB_INFO,
- "\nReceived BUS CHECK notification for device\n"));
- fallthrough;
- case ACPI_NOTIFY_DEVICE_CHECK:
- if (event == ACPI_NOTIFY_DEVICE_CHECK)
- ACPI_DEBUG_PRINT((ACPI_DB_INFO,
- "\nReceived DEVICE CHECK notification for device\n"));
-
- if (acpi_memory_get_device(handle, &mem_device)) {
- pr_err(PREFIX "Cannot find driver data\n");
- break;
- }
-
- ost_code = ACPI_OST_SC_SUCCESS;
- break;
-
- case ACPI_NOTIFY_EJECT_REQUEST:
- ACPI_DEBUG_PRINT((ACPI_DB_INFO,
- "\nReceived EJECT REQUEST notification for device\n"));
-
- acpi_scan_lock_acquire();
- if (acpi_bus_get_device(handle, &device)) {
- acpi_scan_lock_release();
- pr_err(PREFIX "Device doesn't exist\n");
- break;
- }
- mem_device = acpi_driver_data(device);
- if (!mem_device) {
- acpi_scan_lock_release();
- pr_err(PREFIX "Driver Data is NULL\n");
- break;
- }
-
- /*
- * TBD: implement acpi_memory_disable_device and invoke
- * acpi_bus_remove if Xen support hotremove in the future
- */
- acpi_memory_disable_device(mem_device);
- acpi_scan_lock_release();
- break;
-
- default:
- ACPI_DEBUG_PRINT((ACPI_DB_INFO,
- "Unsupported event [0x%x]\n", event));
- /* non-hotplug event; possibly handled by other handler */
- return;
- }
-
- (void) acpi_evaluate_ost(handle, event, ost_code, NULL);
- return;
-}
-
-static int xen_acpi_memory_device_add(struct acpi_device *device)
-{
- int result;
- struct acpi_memory_device *mem_device = NULL;
-
-
- if (!device)
- return -EINVAL;
-
- mem_device = kzalloc(sizeof(struct acpi_memory_device), GFP_KERNEL);
- if (!mem_device)
- return -ENOMEM;
-
- INIT_LIST_HEAD(&mem_device->res_list);
- mem_device->device = device;
- sprintf(acpi_device_name(device), "%s", ACPI_MEMORY_DEVICE_NAME);
- sprintf(acpi_device_class(device), "%s", ACPI_MEMORY_DEVICE_CLASS);
- device->driver_data = mem_device;
-
- /* Get the range from the _CRS */
- result = acpi_memory_get_device_resources(mem_device);
- if (result) {
- kfree(mem_device);
- return result;
- }
-
- /*
- * For booting existed memory devices, early boot code has recognized
- * memory area by EFI/E820. If DSDT shows these memory devices on boot,
- * hotplug is not necessary for them.
- * For hot-added memory devices during runtime, it need hypercall to
- * Xen hypervisor to add memory.
- */
- if (!acpi_hotmem_initialized)
- return 0;
-
- if (!acpi_memory_check_device(mem_device))
- result = xen_acpi_memory_enable_device(mem_device);
-
- return result;
-}
-
-static int xen_acpi_memory_device_remove(struct acpi_device *device)
-{
- struct acpi_memory_device *mem_device = NULL;
-
- if (!device || !acpi_driver_data(device))
- return -EINVAL;
-
- mem_device = acpi_driver_data(device);
- kfree(mem_device);
-
- return 0;
-}
-
-/*
- * Helper function to check for memory device
- */
-static acpi_status is_memory_device(acpi_handle handle)
-{
- char *hardware_id;
- acpi_status status;
- struct acpi_device_info *info;
-
- status = acpi_get_object_info(handle, &info);
- if (ACPI_FAILURE(status))
- return status;
-
- if (!(info->valid & ACPI_VALID_HID)) {
- kfree(info);
- return AE_ERROR;
- }
-
- hardware_id = info->hardware_id.string;
- if ((hardware_id == NULL) ||
- (strcmp(hardware_id, ACPI_MEMORY_DEVICE_HID)))
- status = AE_ERROR;
-
- kfree(info);
- return status;
-}
-
-static acpi_status
-acpi_memory_register_notify_handler(acpi_handle handle,
- u32 level, void *ctxt, void **retv)
-{
- acpi_status status;
-
- status = is_memory_device(handle);
- if (ACPI_FAILURE(status))
- return AE_OK; /* continue */
-
- status = acpi_install_notify_handler(handle, ACPI_SYSTEM_NOTIFY,
- acpi_memory_device_notify, NULL);
- /* continue */
- return AE_OK;
-}
-
-static acpi_status
-acpi_memory_deregister_notify_handler(acpi_handle handle,
- u32 level, void *ctxt, void **retv)
-{
- acpi_status status;
-
- status = is_memory_device(handle);
- if (ACPI_FAILURE(status))
- return AE_OK; /* continue */
-
- status = acpi_remove_notify_handler(handle,
- ACPI_SYSTEM_NOTIFY,
- acpi_memory_device_notify);
-
- return AE_OK; /* continue */
-}
-
-static const struct acpi_device_id memory_device_ids[] = {
- {ACPI_MEMORY_DEVICE_HID, 0},
- {"", 0},
-};
-MODULE_DEVICE_TABLE(acpi, memory_device_ids);
-
-static struct acpi_driver xen_acpi_memory_device_driver = {
- .name = "acpi_memhotplug",
- .class = ACPI_MEMORY_DEVICE_CLASS,
- .ids = memory_device_ids,
- .ops = {
- .add = xen_acpi_memory_device_add,
- .remove = xen_acpi_memory_device_remove,
- },
-};
-
-static int __init xen_acpi_memory_device_init(void)
-{
- int result;
- acpi_status status;
-
- if (!xen_initial_domain())
- return -ENODEV;
-
- /* unregister the stub which only used to reserve driver space */
- xen_stub_memory_device_exit();
-
- result = acpi_bus_register_driver(&xen_acpi_memory_device_driver);
- if (result < 0) {
- xen_stub_memory_device_init();
- return -ENODEV;
- }
-
- status = acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT,
- ACPI_UINT32_MAX,
- acpi_memory_register_notify_handler,
- NULL, NULL, NULL);
-
- if (ACPI_FAILURE(status)) {
- pr_warn(PREFIX "walk_namespace failed\n");
- acpi_bus_unregister_driver(&xen_acpi_memory_device_driver);
- xen_stub_memory_device_init();
- return -ENODEV;
- }
-
- acpi_hotmem_initialized = true;
- return 0;
-}
-
-static void __exit xen_acpi_memory_device_exit(void)
-{
- acpi_status status;
-
- if (!xen_initial_domain())
- return;
-
- status = acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT,
- ACPI_UINT32_MAX,
- acpi_memory_deregister_notify_handler,
- NULL, NULL, NULL);
- if (ACPI_FAILURE(status))
- pr_warn(PREFIX "walk_namespace failed\n");
-
- acpi_bus_unregister_driver(&xen_acpi_memory_device_driver);
-
- /*
- * stub reserve space again to prevent any chance of native
- * driver loading.
- */
- xen_stub_memory_device_init();
- return;
-}
-
-module_init(xen_acpi_memory_device_init);
-module_exit(xen_acpi_memory_device_exit);
-ACPI_MODULE_NAME("xen-acpi-memhotplug");
-MODULE_AUTHOR("Liu Jinsong <jinsong.liu@intel.com>");
-MODULE_DESCRIPTION("Xen Hotplug Mem Driver");
-MODULE_LICENSE("GPL");
"guest with no AER driver should have been killed\n");
goto end;
}
- result = common_process(psdev, 1, XEN_PCI_OP_aer_slotreset, result);
+ result = common_process(psdev, pci_channel_io_normal, XEN_PCI_OP_aer_slotreset, result);
if (result == PCI_ERS_RESULT_NONE ||
result == PCI_ERS_RESULT_DISCONNECT) {
"guest with no AER driver should have been killed\n");
goto end;
}
- result = common_process(psdev, 1, XEN_PCI_OP_aer_mmio, result);
+ result = common_process(psdev, pci_channel_io_normal, XEN_PCI_OP_aer_mmio, result);
if (result == PCI_ERS_RESULT_NONE ||
result == PCI_ERS_RESULT_DISCONNECT) {
kill_domain_by_device(psdev);
goto end;
}
- common_process(psdev, 1, XEN_PCI_OP_aer_resume,
+ common_process(psdev, pci_channel_io_normal, XEN_PCI_OP_aer_resume,
PCI_ERS_RESULT_RECOVERED);
end:
if (psdev)
unsigned int *devfn)
{
struct pci_dev_entry *entry;
- struct pci_dev *dev = NULL;
struct vpci_dev_data *vpci_dev = pdev->pci_dev_data;
int found = 0, slot;
list_for_each_entry(entry,
&vpci_dev->dev_list[slot],
list) {
- dev = entry->dev;
- if (dev && dev->bus->number == pcidev->bus->number
- && pci_domain_nr(dev->bus) ==
- pci_domain_nr(pcidev->bus)
- && dev->devfn == pcidev->devfn) {
+ if (entry->dev == pcidev) {
found = 1;
*domain = 0;
*bus = 0;
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * xen-stub.c - stub drivers to reserve space for Xen
- *
- * Copyright (C) 2012 Intel Corporation
- * Author: Liu Jinsong <jinsong.liu@intel.com>
- * Author: Jiang Yunhong <yunhong.jiang@intel.com>
- *
- * Copyright (C) 2012 Oracle Inc
- * Author: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/export.h>
-#include <linux/types.h>
-#include <linux/acpi.h>
-#include <xen/acpi.h>
-
-#ifdef CONFIG_ACPI
-
-/*--------------------------------------------
- stub driver for Xen memory hotplug
---------------------------------------------*/
-
-static const struct acpi_device_id memory_device_ids[] = {
- {ACPI_MEMORY_DEVICE_HID, 0},
- {"", 0},
-};
-
-static struct acpi_driver xen_stub_memory_device_driver = {
- /* same name as native memory driver to block native loaded */
- .name = "acpi_memhotplug",
- .class = ACPI_MEMORY_DEVICE_CLASS,
- .ids = memory_device_ids,
-};
-
-int xen_stub_memory_device_init(void)
-{
- if (!xen_initial_domain())
- return -ENODEV;
-
- /* just reserve space for Xen, block native driver loaded */
- return acpi_bus_register_driver(&xen_stub_memory_device_driver);
-}
-EXPORT_SYMBOL_GPL(xen_stub_memory_device_init);
-subsys_initcall(xen_stub_memory_device_init);
-
-void xen_stub_memory_device_exit(void)
-{
- acpi_bus_unregister_driver(&xen_stub_memory_device_driver);
-}
-EXPORT_SYMBOL_GPL(xen_stub_memory_device_exit);
-
-
-/*--------------------------------------------
- stub driver for Xen cpu hotplug
---------------------------------------------*/
-
-static const struct acpi_device_id processor_device_ids[] = {
- {ACPI_PROCESSOR_OBJECT_HID, 0},
- {ACPI_PROCESSOR_DEVICE_HID, 0},
- {"", 0},
-};
-
-static struct acpi_driver xen_stub_processor_driver = {
- /* same name as native processor driver to block native loaded */
- .name = "processor",
- .class = ACPI_PROCESSOR_CLASS,
- .ids = processor_device_ids,
-};
-
-int xen_stub_processor_init(void)
-{
- if (!xen_initial_domain())
- return -ENODEV;
-
- /* just reserve space for Xen, block native driver loaded */
- return acpi_bus_register_driver(&xen_stub_processor_driver);
-}
-EXPORT_SYMBOL_GPL(xen_stub_processor_init);
-subsys_initcall(xen_stub_processor_init);
-
-void xen_stub_processor_exit(void)
-{
- acpi_bus_unregister_driver(&xen_stub_processor_driver);
-}
-EXPORT_SYMBOL_GPL(xen_stub_processor_exit);
-
-#endif
config TMPFS_INODE64
bool "Use 64-bit ino_t by default in tmpfs"
- depends on TMPFS && 64BIT && !(S390 || ALPHA)
+ depends on TMPFS && 64BIT
default n
help
tmpfs has historically used only inode numbers as wide as an unsigned
.permission = afs_permission,
.getattr = afs_getattr,
.setattr = afs_setattr,
- .listxattr = afs_listxattr,
};
const struct address_space_operations afs_dir_aops = {
.getattr = afs_getattr,
.setattr = afs_setattr,
.permission = afs_permission,
- .listxattr = afs_listxattr,
};
const struct address_space_operations afs_fs_aops = {
if (test_bit(AFS_SERVER_FL_IS_YFS, &op->server->flags) &&
op->ops->issue_yfs_rpc)
op->ops->issue_yfs_rpc(op);
- else
+ else if (op->ops->issue_afs_rpc)
op->ops->issue_afs_rpc(op);
+ else
+ op->ac.error = -ENOTSUPP;
- op->error = afs_wait_for_call_to_complete(op->call, &op->ac);
+ if (op->call)
+ op->error = afs_wait_for_call_to_complete(op->call, &op->ac);
}
switch (op->error) {
static const struct inode_operations afs_symlink_inode_operations = {
.get_link = page_get_link,
- .listxattr = afs_listxattr,
};
static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *parent_vnode)
* xattr.c
*/
extern const struct xattr_handler *afs_xattr_handlers[];
-extern ssize_t afs_listxattr(struct dentry *, char *, size_t);
/*
* yfsclient.c
.lookup = afs_mntpt_lookup,
.readlink = page_readlink,
.getattr = afs_getattr,
- .listxattr = afs_listxattr,
};
const struct inode_operations afs_autocell_inode_operations = {
fscache_wait_on_page_write(vnode->cache, vmf->page);
#endif
- if (PageWriteback(vmf->page) &&
- wait_on_page_bit_killable(vmf->page, PG_writeback) < 0)
+ if (wait_on_page_writeback_killable(vmf->page))
return VM_FAULT_RETRY;
if (lock_page_killable(vmf->page) < 0)
#include <linux/xattr.h>
#include "internal.h"
-static const char afs_xattr_list[] =
- "afs.acl\0"
- "afs.cell\0"
- "afs.fid\0"
- "afs.volume\0"
- "afs.yfs.acl\0"
- "afs.yfs.acl_inherited\0"
- "afs.yfs.acl_num_cleaned\0"
- "afs.yfs.vol_acl";
-
-/*
- * Retrieve a list of the supported xattrs.
- */
-ssize_t afs_listxattr(struct dentry *dentry, char *buffer, size_t size)
-{
- if (size == 0)
- return sizeof(afs_xattr_list);
- if (size < sizeof(afs_xattr_list))
- return -ERANGE;
- memcpy(buffer, afs_xattr_list, sizeof(afs_xattr_list));
- return sizeof(afs_xattr_list);
-}
-
/*
* Deal with the result of a successful fetch ACL operation.
*/
else
ret = -ERANGE;
}
+ } else if (ret == -ENOTSUPP) {
+ ret = -ENODATA;
}
error_yacl:
{
struct afs_operation *op;
struct afs_vnode *vnode = AFS_FS_I(inode);
+ int ret;
if (flags == XATTR_CREATE ||
strcmp(name, "acl") != 0)
return afs_put_operation(op);
op->ops = &yfs_store_opaque_acl2_operation;
- return afs_do_sync_operation(op);
+ ret = afs_do_sync_operation(op);
+ if (ret == -ENOTSUPP)
+ ret = -ENODATA;
+ return ret;
}
static const struct xattr_handler afs_xattr_yfs_handler = {
struct super_block *sb = file_inode(file)->i_sb;
struct dentry *root = sb->s_root, *dentry;
int err = 0;
+ struct file *f = NULL;
e = create_entry(buffer, count);
if (IS_ERR(e))
return PTR_ERR(e);
+ if (e->flags & MISC_FMT_OPEN_FILE) {
+ f = open_exec(e->interpreter);
+ if (IS_ERR(f)) {
+ pr_notice("register: failed to install interpreter file %s\n",
+ e->interpreter);
+ kfree(e);
+ return PTR_ERR(f);
+ }
+ e->interp_file = f;
+ }
+
inode_lock(d_inode(root));
dentry = lookup_one_len(e->name, root, strlen(e->name));
err = PTR_ERR(dentry);
goto out2;
}
- if (e->flags & MISC_FMT_OPEN_FILE) {
- struct file *f;
-
- f = open_exec(e->interpreter);
- if (IS_ERR(f)) {
- err = PTR_ERR(f);
- pr_notice("register: failed to install interpreter file %s\n", e->interpreter);
- simple_release_fs(&bm_mnt, &entry_count);
- iput(inode);
- inode = NULL;
- goto out2;
- }
- e->interp_file = f;
- }
-
e->dentry = dget(dentry);
inode->i_private = e;
inode->i_fop = &bm_entry_operations;
inode_unlock(d_inode(root));
if (err) {
+ if (f)
+ filp_close(f, NULL);
kfree(e);
return err;
}
if (!(mode & FMODE_EXCL)) {
int err = bd_prepare_to_claim(bdev, truncate_bdev_range);
if (err)
- return err;
+ goto invalidate;
}
truncate_inode_pages_range(bdev->bd_inode->i_mapping, lstart, lend);
if (!(mode & FMODE_EXCL))
bd_abort_claiming(bdev, truncate_bdev_range);
return 0;
+
+invalidate:
+ /*
+ * Someone else has handle exclusively open. Try invalidating instead.
+ * The 'end' argument is inclusive so the rounding is safe.
+ */
+ return invalidate_inode_pages2_range(bdev->bd_inode->i_mapping,
+ lstart >> PAGE_SHIFT,
+ lend >> PAGE_SHIFT);
}
static void set_init_blocksize(struct block_device *bdev)
bio.bi_opf = dio_bio_write_op(iocb);
task_io_account_write(ret);
}
+ if (iocb->ki_flags & IOCB_NOWAIT)
+ bio.bi_opf |= REQ_NOWAIT;
if (iocb->ki_flags & IOCB_HIPRI)
bio_set_polled(&bio, iocb);
bio->bi_opf = dio_bio_write_op(iocb);
task_io_account_write(bio->bi_iter.bi_size);
}
+ if (iocb->ki_flags & IOCB_NOWAIT)
+ bio->bi_opf |= REQ_NOWAIT;
dio->size += bio->bi_iter.bi_size;
pos += bio->bi_iter.bi_size;
- nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_PAGES);
+ nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS);
if (!nr_pages) {
bool polled = false;
if (!iov_iter_count(iter))
return 0;
- nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_PAGES + 1);
- if (is_sync_kiocb(iocb) && nr_pages <= BIO_MAX_PAGES)
+ nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1);
+ if (is_sync_kiocb(iocb) && nr_pages <= BIO_MAX_VECS)
return __blkdev_direct_IO_simple(iocb, iter, nr_pages);
return __blkdev_direct_IO(iocb, iter, bio_max_segs(nr_pages));
lockdep_assert_held(&bdev->bd_mutex);
- clear_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state);
-
rescan:
ret = blk_drop_partitions(bdev);
if (ret)
return ret;
+ clear_bit(GD_NEED_PART_SCAN, &disk->state);
+
/*
* Historically we only set the capacity to zero for devices that
* support partitions (independ of actually having partitions created).
subdir-ccflags-y += -Wmissing-prototypes
subdir-ccflags-y += -Wold-style-definition
subdir-ccflags-y += -Wmissing-include-dirs
-subdir-ccflags-y += $(call cc-option, -Wunused-but-set-variable)
-subdir-ccflags-y += $(call cc-option, -Wunused-const-variable)
-subdir-ccflags-y += $(call cc-option, -Wpacked-not-aligned)
-subdir-ccflags-y += $(call cc-option, -Wstringop-truncation)
+condflags := \
+ $(call cc-option, -Wunused-but-set-variable) \
+ $(call cc-option, -Wunused-const-variable) \
+ $(call cc-option, -Wpacked-not-aligned) \
+ $(call cc-option, -Wstringop-truncation)
+subdir-ccflags-y += $(condflags)
# The following turn off the warnings enabled by -Wextra
subdir-ccflags-y += -Wno-missing-field-initializers
subdir-ccflags-y += -Wno-sign-compare
"failed to read tree block %llu from get_old_root",
logical);
} else {
+ btrfs_tree_read_lock(old);
eb = btrfs_clone_extent_buffer(old);
+ btrfs_tree_read_unlock(old);
free_extent_buffer(old);
}
} else if (old_root) {
struct btrfs_dev_replace_item *ptr;
u64 src_devid;
+ if (!dev_root)
+ return 0;
+
path = btrfs_alloc_path();
if (!path) {
ret = -ENOMEM;
} else {
set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
fs_info->dev_root = root;
- btrfs_init_devices_late(fs_info);
}
+ /* Initialize fs_info for all devices in any case */
+ btrfs_init_devices_late(fs_info);
/* If IGNOREDATACSUMS is set don't bother reading the csum root. */
if (!btrfs_test_opt(fs_info, IGNOREDATACSUMS)) {
}
}
+ /*
+ * btrfs_find_orphan_roots() is responsible for finding all the dead
+ * roots (with 0 refs), flag them with BTRFS_ROOT_DEAD_TREE and load
+ * them into the fs_info->fs_roots_radix tree. This must be done before
+ * calling btrfs_orphan_cleanup() on the tree root. If we don't do it
+ * first, then btrfs_orphan_cleanup() will delete a dead root's orphan
+ * item before the root's tree is deleted - this means that if we unmount
+ * or crash before the deletion completes, on the next mount we will not
+ * delete what remains of the tree because the orphan item does not
+ * exists anymore, which is what tells us we have a pending deletion.
+ */
+ ret = btrfs_find_orphan_roots(fs_info);
+ if (ret)
+ goto out;
+
ret = btrfs_cleanup_fs_roots(fs_info);
if (ret)
goto out;
}
}
- ret = btrfs_find_orphan_roots(fs_info);
out:
return ret;
}
if (last_ref && btrfs_header_generation(buf) == trans->transid) {
struct btrfs_block_group *cache;
+ bool must_pin = false;
if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
ret = check_ref_cleanup(trans, buf->start);
goto out;
}
- if (btrfs_is_zoned(fs_info)) {
+ /*
+ * If this is a leaf and there are tree mod log users, we may
+ * have recorded mod log operations that point to this leaf.
+ * So we must make sure no one reuses this leaf's extent before
+ * mod log operations are applied to a node, otherwise after
+ * rewinding a node using the mod log operations we get an
+ * inconsistent btree, as the leaf's extent may now be used as
+ * a node or leaf for another different btree.
+ * We are safe from races here because at this point no other
+ * node or root points to this extent buffer, so if after this
+ * check a new tree mod log user joins, it will not be able to
+ * find a node pointing to this leaf and record operations that
+ * point to this leaf.
+ */
+ if (btrfs_header_level(buf) == 0) {
+ read_lock(&fs_info->tree_mod_log_lock);
+ must_pin = !list_empty(&fs_info->tree_mod_seq_list);
+ read_unlock(&fs_info->tree_mod_log_lock);
+ }
+
+ if (must_pin || btrfs_is_zoned(fs_info)) {
btrfs_redirty_list_add(trans->transaction, buf);
pin_down_extent(trans, cache, buf->start, buf->len, 1);
btrfs_put_block_group(cache);
}
/*
+ * Find extent buffer for a givne bytenr.
+ *
+ * This is for end_bio_extent_readpage(), thus we can't do any unsafe locking
+ * in endio context.
+ */
+static struct extent_buffer *find_extent_buffer_readpage(
+ struct btrfs_fs_info *fs_info, struct page *page, u64 bytenr)
+{
+ struct extent_buffer *eb;
+
+ /*
+ * For regular sectorsize, we can use page->private to grab extent
+ * buffer
+ */
+ if (fs_info->sectorsize == PAGE_SIZE) {
+ ASSERT(PagePrivate(page) && page->private);
+ return (struct extent_buffer *)page->private;
+ }
+
+ /* For subpage case, we need to lookup buffer radix tree */
+ rcu_read_lock();
+ eb = radix_tree_lookup(&fs_info->buffer_radix,
+ bytenr >> fs_info->sectorsize_bits);
+ rcu_read_unlock();
+ ASSERT(eb);
+ return eb;
+}
+
+/*
* after a readpage IO is done, we need to:
* clear the uptodate bits on error
* set the uptodate bits if things worked
} else {
struct extent_buffer *eb;
- eb = (struct extent_buffer *)page->private;
+ eb = find_extent_buffer_readpage(fs_info, page, start);
set_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
eb->read_mirror = mirror;
atomic_dec(&eb->io_pages);
*/
if (page->index == end_index && i_size <= end) {
u32 zero_start = max(offset_in_page(i_size),
- offset_in_page(end));
+ offset_in_page(start));
zero_user_segment(page, zero_start,
offset_in_page(end) + 1);
{
struct bio *bio;
- bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &btrfs_bioset);
+ bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_VECS, &btrfs_bioset);
bio->bi_iter.bi_sector = first_byte >> 9;
btrfs_io_bio_init(btrfs_io_bio(bio));
return bio;
* @bio_offset: offset to the beginning of the bio (in bytes)
* @page: page where is the data to be verified
* @pgoff: offset inside the page
+ * @start: logical offset in the file
*
* The length of such check is always one sector size.
*/
static int check_data_csum(struct inode *inode, struct btrfs_io_bio *io_bio,
- u32 bio_offset, struct page *page, u32 pgoff)
+ u32 bio_offset, struct page *page, u32 pgoff,
+ u64 start)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
kunmap_atomic(kaddr);
return 0;
zeroit:
- btrfs_print_data_csum_error(BTRFS_I(inode), page_offset(page) + pgoff,
- csum, csum_expected, io_bio->mirror_num);
+ btrfs_print_data_csum_error(BTRFS_I(inode), start, csum, csum_expected,
+ io_bio->mirror_num);
if (io_bio->device)
btrfs_dev_stat_inc_and_print(io_bio->device,
BTRFS_DEV_STAT_CORRUPTION_ERRS);
pg_off += sectorsize, bio_offset += sectorsize) {
int ret;
- ret = check_data_csum(inode, io_bio, bio_offset, page, pg_off);
+ ret = check_data_csum(inode, io_bio, bio_offset, page, pg_off,
+ page_offset(page) + pg_off);
if (ret < 0)
return -EIO;
}
ASSERT(pgoff < PAGE_SIZE);
if (uptodate &&
(!csum || !check_data_csum(inode, io_bio,
- bio_offset, bvec.bv_page, pgoff))) {
+ bio_offset, bvec.bv_page,
+ pgoff, start))) {
clean_io_failure(fs_info, failure_tree, io_tree,
start, bvec.bv_page,
btrfs_ino(BTRFS_I(inode)),
bio->bi_end_io = btrfs_end_dio_bio;
btrfs_io_bio(bio)->logical = file_offset;
- WARN_ON_ONCE(write && btrfs_is_zoned(fs_info) &&
- fs_info->max_zone_append_size &&
- bio_op(bio) != REQ_OP_ZONE_APPEND);
-
if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
status = extract_ordered_extent(BTRFS_I(inode), bio,
file_offset);
btrfs_free_space_bitmap_cachep = kmem_cache_create("btrfs_free_space_bitmap",
PAGE_SIZE, PAGE_SIZE,
- SLAB_RED_ZONE, NULL);
+ SLAB_MEM_SPREAD, NULL);
if (!btrfs_free_space_bitmap_cachep)
goto fail;
struct btrfs_path *path;
u64 start = ins->objectid;
u64 len = ins->offset;
+ int qgroup_released;
int ret;
memset(&stack_fi, 0, sizeof(stack_fi));
btrfs_set_stack_file_extent_compression(&stack_fi, BTRFS_COMPRESS_NONE);
/* Encryption and other encoding is reserved and all 0 */
- ret = btrfs_qgroup_release_data(inode, file_offset, len);
- if (ret < 0)
- return ERR_PTR(ret);
+ qgroup_released = btrfs_qgroup_release_data(inode, file_offset, len);
+ if (qgroup_released < 0)
+ return ERR_PTR(qgroup_released);
if (trans) {
ret = insert_reserved_file_extent(trans, inode,
file_offset, &stack_fi,
- true, ret);
+ true, qgroup_released);
if (ret)
- return ERR_PTR(ret);
+ goto free_qgroup;
return trans;
}
extent_info.file_offset = file_offset;
extent_info.extent_buf = (char *)&stack_fi;
extent_info.is_new_extent = true;
- extent_info.qgroup_reserved = ret;
+ extent_info.qgroup_reserved = qgroup_released;
extent_info.insertions = 0;
path = btrfs_alloc_path();
- if (!path)
- return ERR_PTR(-ENOMEM);
+ if (!path) {
+ ret = -ENOMEM;
+ goto free_qgroup;
+ }
ret = btrfs_replace_file_extents(&inode->vfs_inode, path, file_offset,
file_offset + len - 1, &extent_info,
&trans);
btrfs_free_path(path);
if (ret)
- return ERR_PTR(ret);
-
+ goto free_qgroup;
return trans;
+
+free_qgroup:
+ /*
+ * We have released qgroup data range at the beginning of the function,
+ * and normally qgroup_released bytes will be freed when committing
+ * transaction.
+ * But if we error out early, we have to free what we have released
+ * or we leak qgroup data reservation.
+ */
+ btrfs_qgroup_free_refroot(inode->root->fs_info,
+ inode->root->root_key.objectid, qgroup_released,
+ BTRFS_QGROUP_RSV_DATA);
+ return ERR_PTR(ret);
}
static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
{
struct btrfs_qgroup_list *list;
- btrfs_sysfs_del_one_qgroup(fs_info, qgroup);
list_del(&qgroup->dirty);
while (!list_empty(&qgroup->groups)) {
list = list_first_entry(&qgroup->groups,
list_del(&list->next_member);
kfree(list);
}
- kfree(qgroup);
}
/* must be called with qgroup_lock held */
qgroup = rb_entry(n, struct btrfs_qgroup, node);
rb_erase(n, &fs_info->qgroup_tree);
__del_qgroup_rb(fs_info, qgroup);
+ btrfs_sysfs_del_one_qgroup(fs_info, qgroup);
+ kfree(qgroup);
}
/*
* We call btrfs_free_qgroup_config() when unmounting
spin_lock(&fs_info->qgroup_lock);
del_qgroup_rb(fs_info, qgroupid);
spin_unlock(&fs_info->qgroup_lock);
+
+ /*
+ * Remove the qgroup from sysfs now without holding the qgroup_lock
+ * spinlock, since the sysfs_remove_group() function needs to take
+ * the mutex kernfs_mutex through kernfs_remove_by_name_ns().
+ */
+ btrfs_sysfs_del_one_qgroup(fs_info, qgroup);
+ kfree(qgroup);
out:
mutex_unlock(&fs_info->qgroup_ioctl_lock);
return ret;
/* find extent */
spin_lock(&fs_info->reada_lock);
re = radix_tree_lookup(&fs_info->reada_tree,
- eb->start >> PAGE_SHIFT);
+ eb->start >> fs_info->sectorsize_bits);
if (re)
re->refcnt++;
spin_unlock(&fs_info->reada_lock);
zone = NULL;
spin_lock(&fs_info->reada_lock);
ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone,
- logical >> PAGE_SHIFT, 1);
+ logical >> fs_info->sectorsize_bits, 1);
if (ret == 1 && logical >= zone->start && logical <= zone->end) {
kref_get(&zone->refcnt);
spin_unlock(&fs_info->reada_lock);
spin_lock(&fs_info->reada_lock);
ret = radix_tree_insert(&dev->reada_zones,
- (unsigned long)(zone->end >> PAGE_SHIFT),
- zone);
+ (unsigned long)(zone->end >> fs_info->sectorsize_bits),
+ zone);
if (ret == -EEXIST) {
kfree(zone);
ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone,
- logical >> PAGE_SHIFT, 1);
+ logical >> fs_info->sectorsize_bits, 1);
if (ret == 1 && logical >= zone->start && logical <= zone->end)
kref_get(&zone->refcnt);
else
u64 length;
int real_stripes;
int nzones = 0;
- unsigned long index = logical >> PAGE_SHIFT;
+ unsigned long index = logical >> fs_info->sectorsize_bits;
int dev_replace_is_ongoing;
int have_zone = 0;
struct reada_extent *re)
{
int i;
- unsigned long index = re->logical >> PAGE_SHIFT;
+ unsigned long index = re->logical >> fs_info->sectorsize_bits;
spin_lock(&fs_info->reada_lock);
if (--re->refcnt) {
static void reada_zone_release(struct kref *kref)
{
struct reada_zone *zone = container_of(kref, struct reada_zone, refcnt);
+ struct btrfs_fs_info *fs_info = zone->device->fs_info;
- lockdep_assert_held(&zone->device->fs_info->reada_lock);
+ lockdep_assert_held(&fs_info->reada_lock);
radix_tree_delete(&zone->device->reada_zones,
- zone->end >> PAGE_SHIFT);
+ zone->end >> fs_info->sectorsize_bits);
kfree(zone);
}
static void reada_peer_zones_set_lock(struct reada_zone *zone, int lock)
{
int i;
- unsigned long index = zone->end >> PAGE_SHIFT;
+ unsigned long index = zone->end >> zone->device->fs_info->sectorsize_bits;
for (i = 0; i < zone->ndevs; ++i) {
struct reada_zone *peer;
(void **)&zone, index, 1);
if (ret == 0)
break;
- index = (zone->end >> PAGE_SHIFT) + 1;
+ index = (zone->end >> dev->fs_info->sectorsize_bits) + 1;
if (zone->locked) {
if (zone->elems > top_locked_elems) {
top_locked_elems = zone->elems;
* plugging to speed things up
*/
ret = radix_tree_gang_lookup(&dev->reada_extents, (void **)&re,
- dev->reada_next >> PAGE_SHIFT, 1);
+ dev->reada_next >> fs_info->sectorsize_bits, 1);
if (ret == 0 || re->logical > dev->reada_curr_zone->end) {
ret = reada_pick_zone(dev);
if (!ret) {
}
re = NULL;
ret = radix_tree_gang_lookup(&dev->reada_extents, (void **)&re,
- dev->reada_next >> PAGE_SHIFT, 1);
+ dev->reada_next >> fs_info->sectorsize_bits, 1);
}
if (ret == 0) {
spin_unlock(&fs_info->reada_lock);
pr_cont(" curr off %llu",
device->reada_next - zone->start);
pr_cont("\n");
- index = (zone->end >> PAGE_SHIFT) + 1;
+ index = (zone->end >> fs_info->sectorsize_bits) + 1;
}
cnt = 0;
index = 0;
}
}
pr_cont("\n");
- index = (re->logical >> PAGE_SHIFT) + 1;
+ index = (re->logical >> fs_info->sectorsize_bits) + 1;
if (++cnt > 15)
break;
}
if (ret == 0)
break;
if (!re->scheduled) {
- index = (re->logical >> PAGE_SHIFT) + 1;
+ index = (re->logical >> fs_info->sectorsize_bits) + 1;
continue;
}
pr_debug("re: logical %llu size %u list empty %d scheduled %d",
}
}
pr_cont("\n");
- index = (re->logical >> PAGE_SHIFT) + 1;
+ index = (re->logical >> fs_info->sectorsize_bits) + 1;
}
spin_unlock(&fs_info->reada_lock);
}
if (!first_page->dev->bdev)
goto out;
- bio = btrfs_io_bio_alloc(BIO_MAX_PAGES);
+ bio = btrfs_io_bio_alloc(BIO_MAX_VECS);
bio_set_dev(bio, first_page->dev->bdev);
for (page_num = 0; page_num < sblock->page_count; page_num++) {
mutex_lock(&log_root_tree->log_mutex);
- index2 = log_root_tree->log_transid % 2;
- list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]);
- root_log_ctx.log_transid = log_root_tree->log_transid;
-
if (btrfs_is_zoned(fs_info)) {
if (!log_root_tree->node) {
ret = btrfs_alloc_log_tree_node(trans, log_root_tree);
}
}
+ index2 = log_root_tree->log_transid % 2;
+ list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]);
+ root_log_ctx.log_transid = log_root_tree->log_transid;
+
/*
* Now we are safe to update the log_root_tree because we're under the
* log_mutex, and we're a current writer so we're holding the commit
int item_size;
int i, ret, slot;
+ if (!device->fs_info->dev_root)
+ return 0;
+
key.objectid = BTRFS_DEV_STATS_OBJECTID;
key.type = BTRFS_PERSISTENT_ITEM_KEY;
key.offset = device->devid;
/* Pseudo write pointer value for conventional zone */
#define WP_CONVENTIONAL ((u64)-2)
+/*
+ * Location of the first zone of superblock logging zone pairs.
+ *
+ * - primary superblock: 0B (zone 0)
+ * - first copy: 512G (zone starting at that offset)
+ * - second copy: 4T (zone starting at that offset)
+ */
+#define BTRFS_SB_LOG_PRIMARY_OFFSET (0ULL)
+#define BTRFS_SB_LOG_FIRST_OFFSET (512ULL * SZ_1G)
+#define BTRFS_SB_LOG_SECOND_OFFSET (4096ULL * SZ_1G)
+
+#define BTRFS_SB_LOG_FIRST_SHIFT const_ilog2(BTRFS_SB_LOG_FIRST_OFFSET)
+#define BTRFS_SB_LOG_SECOND_SHIFT const_ilog2(BTRFS_SB_LOG_SECOND_OFFSET)
+
/* Number of superblock log zones */
#define BTRFS_NR_SB_LOG_ZONES 2
+/*
+ * Maximum supported zone size. Currently, SMR disks have a zone size of
+ * 256MiB, and we are expecting ZNS drives to be in the 1-4GiB range. We do not
+ * expect the zone size to become larger than 8GiB in the near future.
+ */
+#define BTRFS_MAX_ZONE_SIZE SZ_8G
+
static int copy_zone_info_cb(struct blk_zone *zone, unsigned int idx, void *data)
{
struct blk_zone *zones = data;
}
/*
- * The following zones are reserved as the circular buffer on ZONED btrfs.
- * - The primary superblock: zones 0 and 1
- * - The first copy: zones 16 and 17
- * - The second copy: zones 1024 or zone at 256GB which is minimum, and
- * the following one
+ * Get the first zone number of the superblock mirror
*/
static inline u32 sb_zone_number(int shift, int mirror)
{
- ASSERT(mirror < BTRFS_SUPER_MIRROR_MAX);
+ u64 zone;
+ ASSERT(mirror < BTRFS_SUPER_MIRROR_MAX);
switch (mirror) {
- case 0: return 0;
- case 1: return 16;
- case 2: return min_t(u64, btrfs_sb_offset(mirror) >> shift, 1024);
+ case 0: zone = 0; break;
+ case 1: zone = 1ULL << (BTRFS_SB_LOG_FIRST_SHIFT - shift); break;
+ case 2: zone = 1ULL << (BTRFS_SB_LOG_SECOND_SHIFT - shift); break;
}
- return 0;
+ ASSERT(zone <= U32_MAX);
+
+ return (u32)zone;
}
/*
zone_sectors = bdev_zone_sectors(bdev);
}
- nr_sectors = bdev_nr_sectors(bdev);
/* Check if it's power of 2 (see is_power_of_2) */
ASSERT(zone_sectors != 0 && (zone_sectors & (zone_sectors - 1)) == 0);
zone_info->zone_size = zone_sectors << SECTOR_SHIFT;
+
+ /* We reject devices with a zone size larger than 8GB */
+ if (zone_info->zone_size > BTRFS_MAX_ZONE_SIZE) {
+ btrfs_err_in_rcu(fs_info,
+ "zoned: %s: zone size %llu larger than supported maximum %llu",
+ rcu_str_deref(device->name),
+ zone_info->zone_size, BTRFS_MAX_ZONE_SIZE);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ nr_sectors = bdev_nr_sectors(bdev);
zone_info->zone_size_shift = ilog2(zone_info->zone_size);
zone_info->max_zone_append_size =
(u64)queue_max_zone_append_sectors(queue) << SECTOR_SHIFT;
cache->mnt = path.mnt;
root = path.dentry;
+ ret = -EINVAL;
+ if (mnt_user_ns(path.mnt) != &init_user_ns) {
+ pr_warn("File cache on idmapped mounts not supported");
+ goto error_unsupported;
+ }
+
/* check parameters */
ret = -EOPNOTSUPP;
if (d_is_negative(root) ||
container_of(wait, struct cachefiles_one_read, monitor);
struct cachefiles_object *object;
struct fscache_retrieval *op = monitor->op;
- struct wait_bit_key *key = _key;
+ struct wait_page_key *key = _key;
struct page *page = wait->private;
ASSERT(key);
_enter("{%lu},%u,%d,{%p,%u}",
monitor->netfs_page->index, mode, sync,
- key->flags, key->bit_nr);
+ key->page, key->bit_nr);
- if (key->flags != &page->flags ||
- key->bit_nr != PG_locked)
+ if (key->page != page || key->bit_nr != PG_locked)
return 0;
_debug("--- monitor %p %lx ---", page, page->flags);
select CRYPTO_AES
select CRYPTO_LIB_DES
select KEYS
+ select DNS_RESOLVER
help
This is the client VFS module for the SMB3 family of NAS protocols,
(including support for the most recent, most secure dialect SMB3.1.1)
config CIFS_UPCALL
bool "Kerberos/SPNEGO advanced session setup"
depends on CIFS
- select DNS_RESOLVER
help
Enables an upcall mechanism for CIFS which accesses userspace helper
utilities to provide SPNEGO packaged (RFC 4178) Kerberos tickets
config CIFS_DFS_UPCALL
bool "DFS feature support"
depends on CIFS
- select DNS_RESOLVER
help
Distributed File System (DFS) support is used to access shares
transparently in an enterprise name space, even if the share
cifs_unicode.o nterr.o cifsencrypt.o \
readdir.o ioctl.o sess.o export.o smb1ops.o unc.o winucase.o \
smb2ops.o smb2maperror.o smb2transport.o \
- smb2misc.o smb2pdu.o smb2inode.o smb2file.o cifsacl.o fs_context.o
+ smb2misc.o smb2pdu.o smb2inode.o smb2file.o cifsacl.o fs_context.o \
+ dns_resolve.o
cifs-$(CONFIG_CIFS_XATTR) += xattr.o
cifs-$(CONFIG_CIFS_UPCALL) += cifs_spnego.o
-cifs-$(CONFIG_CIFS_DFS_UPCALL) += dns_resolve.o cifs_dfs_ref.o dfs_cache.o
+cifs-$(CONFIG_CIFS_DFS_UPCALL) += cifs_dfs_ref.o dfs_cache.o
cifs-$(CONFIG_CIFS_SWN_UPCALL) += netlink.o cifs_swn.o
from_kuid(&init_user_ns, cfile->uid),
cfile->dentry);
#ifdef CONFIG_CIFS_DEBUG2
- seq_printf(m, " 0x%llx\n", cfile->fid.mid);
+ seq_printf(m, " %llu\n", cfile->fid.mid);
#else
seq_printf(m, "\n");
#endif /* CIFS_DEBUG2 */
/*
* Try to find a matching registration for the tcon's server name and share name.
- * Calls to this funciton must be protected by cifs_swnreg_idr_mutex.
+ * Calls to this function must be protected by cifs_swnreg_idr_mutex.
* TODO Try to avoid memory allocations
*/
static struct cifs_swn_reg *cifs_find_swn_reg(struct cifs_tcon *tcon)
/* Retain old ACEs which we can retain */
for (i = 0; i < src_num_aces; ++i) {
pntace = (struct cifs_ace *) (acl_base + size);
- pnntace = (struct cifs_ace *) (nacl_base + nsize);
if (!new_aces_set && (pntace->flags & INHERITED_ACE)) {
/* Place the new ACEs in between existing explicit and inherited */
}
/* If it's any one of the ACE we're replacing, skip! */
- if ((compare_sids(&pntace->sid, &sid_unix_NFS_mode) == 0) ||
+ if (((compare_sids(&pntace->sid, &sid_unix_NFS_mode) == 0) ||
(compare_sids(&pntace->sid, pownersid) == 0) ||
(compare_sids(&pntace->sid, pgrpsid) == 0) ||
(compare_sids(&pntace->sid, &sid_everyone) == 0) ||
- (compare_sids(&pntace->sid, &sid_authusers) == 0)) {
+ (compare_sids(&pntace->sid, &sid_authusers) == 0))) {
goto next_ace;
}
+ /* update the pointer to the next ACE to populate*/
+ pnntace = (struct cifs_ace *) (nacl_base + nsize);
+
nsize += cifs_copy_ace(pnntace, pntace, NULL);
num_aces++;
rc = server->ops->queryfs(xid, tcon, cifs_sb, buf);
free_xid(xid);
- return 0;
+ return rc;
}
static long cifs_fallocate(struct file *file, int mode, loff_t off, loff_t len)
seq_puts(m, "none");
else {
convert_delimiter(devname, '/');
- seq_puts(m, devname);
+ /* escape all spaces in share names */
+ seq_escape(m, devname, " \t");
kfree(devname);
}
return 0;
/* verify the message */
int (*check_message)(char *, unsigned int, struct TCP_Server_Info *);
bool (*is_oplock_break)(char *, struct TCP_Server_Info *);
- int (*handle_cancelled_mid)(char *, struct TCP_Server_Info *);
+ int (*handle_cancelled_mid)(struct mid_q_entry *, struct TCP_Server_Info *);
void (*downgrade_oplock)(struct TCP_Server_Info *server,
struct cifsInodeInfo *cinode, __u32 oplock,
unsigned int epoch, bool *purge_cache);
bool binding:1; /* are we binding the session? */
__u16 session_flags;
__u8 smb3signingkey[SMB3_SIGN_KEY_SIZE];
- __u8 smb3encryptionkey[SMB3_SIGN_KEY_SIZE];
- __u8 smb3decryptionkey[SMB3_SIGN_KEY_SIZE];
+ __u8 smb3encryptionkey[SMB3_ENC_DEC_KEY_SIZE];
+ __u8 smb3decryptionkey[SMB3_ENC_DEC_KEY_SIZE];
__u8 preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE];
__u8 binding_preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE];
bool direct_io;
};
-struct cifs_readdata;
-
/* asynchronous read support */
struct cifs_readdata {
struct kref refcount;
#define CIFS_NO_RSP_BUF 0x040 /* no response buffer required */
/* Type of request operation */
-#define CIFS_ECHO_OP 0x080 /* echo request */
-#define CIFS_OBREAK_OP 0x0100 /* oplock break request */
-#define CIFS_NEG_OP 0x0200 /* negotiate request */
+#define CIFS_ECHO_OP 0x080 /* echo request */
+#define CIFS_OBREAK_OP 0x0100 /* oplock break request */
+#define CIFS_NEG_OP 0x0200 /* negotiate request */
+#define CIFS_CP_CREATE_CLOSE_OP 0x0400 /* compound create+close request */
/* Lower bitmask values are reserved by others below. */
-#define CIFS_SESS_OP 0x2000 /* session setup request */
-#define CIFS_OP_MASK 0x2380 /* mask request type */
+#define CIFS_SESS_OP 0x2000 /* session setup request */
+#define CIFS_OP_MASK 0x2780 /* mask request type */
-#define CIFS_HAS_CREDITS 0x0400 /* already has credits */
-#define CIFS_TRANSFORM_REQ 0x0800 /* transform request before sending */
-#define CIFS_NO_SRV_RSP 0x1000 /* there is no server response */
+#define CIFS_HAS_CREDITS 0x0400 /* already has credits */
+#define CIFS_TRANSFORM_REQ 0x0800 /* transform request before sending */
+#define CIFS_NO_SRV_RSP 0x1000 /* there is no server response */
/* Security Flags: indicate type of session setup needed */
#define CIFSSEC_MAY_SIGN 0x00001
*/
#define SMB3_SIGN_KEY_SIZE (16)
+/*
+ * Size of the smb3 encryption/decryption keys
+ */
+#define SMB3_ENC_DEC_KEY_SIZE (32)
+
#define CIFS_CLIENT_CHALLENGE_SIZE (8)
#define CIFS_SERVER_CHALLENGE_SIZE (8)
#define CIFS_HMAC_MD5_HASH_SIZE (16)
*
* This should be called with server->srv_mutex held.
*/
-#ifdef CONFIG_CIFS_DFS_UPCALL
static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server)
{
int rc;
return !rc ? -1 : 0;
}
+#ifdef CONFIG_CIFS_DFS_UPCALL
/* These functions must be called with server->srv_mutex held */
static void reconn_set_next_dfs_target(struct TCP_Server_Info *server,
struct cifs_sb_info *cifs_sb,
#endif
#ifdef CONFIG_CIFS_DFS_UPCALL
+ if (cifs_sb && cifs_sb->origin_fullpath)
/*
* Set up next DFS target server (if any) for reconnect. If DFS
* feature is disabled, then we will retry last server we
* connected to before.
*/
reconn_set_next_dfs_target(server, cifs_sb, &tgt_list, &tgt_it);
+ else {
+#endif
+ /*
+ * Resolve the hostname again to make sure that IP address is up-to-date.
+ */
+ rc = reconn_set_ipaddr_from_hostname(server);
+ if (rc) {
+ cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n",
+ __func__, rc);
+ }
+
+#ifdef CONFIG_CIFS_DFS_UPCALL
+ }
#endif
+
#ifdef CONFIG_CIFS_SWN_UPCALL
}
#endif
spin_lock(&GlobalMid_Lock);
list_for_each_safe(tmp, tmp2, &server->pending_mid_q) {
mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
- cifs_dbg(FYI, "Clearing mid 0x%llx\n", mid_entry->mid);
+ cifs_dbg(FYI, "Clearing mid %llu\n", mid_entry->mid);
kref_get(&mid_entry->refcount);
mid_entry->mid_state = MID_SHUTDOWN;
list_move(&mid_entry->qhead, &dispose_list);
/* now walk dispose list and issue callbacks */
list_for_each_safe(tmp, tmp2, &dispose_list) {
mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
- cifs_dbg(FYI, "Callback mid 0x%llx\n", mid_entry->mid);
+ cifs_dbg(FYI, "Callback mid %llu\n", mid_entry->mid);
list_del_init(&mid_entry->qhead);
mid_entry->callback(mid_entry);
cifs_mid_q_entry_release(mid_entry);
tcp_ses->min_offload = ctx->min_offload;
tcp_ses->tcpStatus = CifsNeedNegotiate;
+ if ((ctx->max_credits < 20) || (ctx->max_credits > 60000))
+ tcp_ses->max_credits = SMB2_MAX_CREDITS_AVAILABLE;
+ else
+ tcp_ses->max_credits = ctx->max_credits;
+
tcp_ses->nr_targets = 1;
tcp_ses->ignore_signature = ctx->ignore_signature;
/* thread spawned, put it on the list */
*nserver = server;
- if ((ctx->max_credits < 20) || (ctx->max_credits > 60000))
- server->max_credits = SMB2_MAX_CREDITS_AVAILABLE;
- else
- server->max_credits = ctx->max_credits;
-
/* get a reference to a SMB session */
ses = cifs_get_smb_ses(server, ctx);
if (IS_ERR(ses)) {
goto posix_open_ret;
}
} else {
+ cifs_revalidate_mapping(*pinode);
cifs_fattr_to_inode(*pinode, &fattr);
}
pr_warn_once("Witness protocol support is experimental\n");
break;
case Opt_rootfs:
-#ifdef CONFIG_CIFS_ROOT
- ctx->rootfs = true;
+#ifndef CONFIG_CIFS_ROOT
+ cifs_dbg(VFS, "rootfs support requires CONFIG_CIFS_ROOT config option\n");
+ goto cifs_parse_mount_err;
#endif
+ ctx->rootfs = true;
break;
case Opt_posixpaths:
if (result.negated)
* We need to be sure that all dirty pages are written and the server
* has actual ctime, mtime and file length.
*/
- if ((request_mask & (STATX_CTIME | STATX_MTIME | STATX_SIZE)) &&
+ if ((request_mask & (STATX_CTIME | STATX_MTIME | STATX_SIZE | STATX_BLOCKS)) &&
!CIFS_CACHE_READ(CIFS_I(inode)) &&
inode->i_mapping && inode->i_mapping->nrpages != 0) {
rc = filemap_fdatawait(inode->i_mapping);
if (rc == 0) {
cifsInode->server_eof = attrs->ia_size;
cifs_setsize(inode, attrs->ia_size);
+ /*
+ * i_blocks is not related to (i_size / i_blksize), but instead
+ * 512 byte (2**9) size is required for calculating num blocks.
+ * Until we can query the server for actual allocation size,
+ * this is best estimate we have for blocks allocated for a file
+ * Number of blocks must be rounded up so size 1 is not 0 blocks
+ */
+ inode->i_blocks = (512 - 1 + attrs->ia_size) >> 9;
/*
* The man page of truncate says if the size changed,
ctx.noautotune = ses->server->noautotune;
ctx.sockopt_tcp_nodelay = ses->server->tcp_nodelay;
ctx.echo_interval = ses->server->echo_interval / HZ;
+ ctx.max_credits = ses->server->max_credits;
/*
* This will be used for encoding/decoding user/domain/pw
#define SMB2_HMACSHA256_SIZE (32)
#define SMB2_CMACAES_SIZE (16)
#define SMB3_SIGNKEY_SIZE (16)
+#define SMB3_GCM128_CRYPTKEY_SIZE (16)
#define SMB3_GCM256_CRYPTKEY_SIZE (32)
/* Maximum buffer size value we can send with 1 credit */
if (cfile)
goto after_close;
/* Close */
+ flags |= CIFS_CP_CREATE_CLOSE_OP;
rqst[num_rqst].rq_iov = &vars->close_iov[0];
rqst[num_rqst].rq_nvec = 1;
rc = SMB2_close_init(tcon, server,
}
}
spin_unlock(&cifs_tcp_ses_lock);
- cifs_dbg(FYI, "Can not process oplock break for non-existent connection\n");
- return false;
+ cifs_dbg(FYI, "No file id matched, oplock break ignored\n");
+ return true;
}
void
int rc;
if (cancelled->mid)
- cifs_tcon_dbg(VFS, "Close unmatched open for MID:%llx\n",
+ cifs_tcon_dbg(VFS, "Close unmatched open for MID:%llu\n",
cancelled->mid);
else
cifs_tcon_dbg(VFS, "Close interrupted close\n");
}
int
-smb2_handle_cancelled_mid(char *buffer, struct TCP_Server_Info *server)
+smb2_handle_cancelled_mid(struct mid_q_entry *mid, struct TCP_Server_Info *server)
{
- struct smb2_sync_hdr *sync_hdr = (struct smb2_sync_hdr *)buffer;
- struct smb2_create_rsp *rsp = (struct smb2_create_rsp *)buffer;
+ struct smb2_sync_hdr *sync_hdr = mid->resp_buf;
+ struct smb2_create_rsp *rsp = mid->resp_buf;
struct cifs_tcon *tcon;
int rc;
- if (sync_hdr->Command != SMB2_CREATE ||
+ if ((mid->optype & CIFS_CP_CREATE_CLOSE_OP) || sync_hdr->Command != SMB2_CREATE ||
sync_hdr->Status != STATUS_SUCCESS)
return 0;
struct TCP_Server_Info *server = cifs_pick_channel(ses);
__le16 *utf16_path = NULL;
int ea_name_len = strlen(ea_name);
- int flags = 0;
+ int flags = CIFS_CP_CREATE_CLOSE_OP;
int len;
struct smb_rqst rqst[3];
int resp_buftype[3];
struct smb_query_info qi;
struct smb_query_info __user *pqi;
int rc = 0;
- int flags = 0;
+ int flags = CIFS_CP_CREATE_CLOSE_OP;
struct smb2_query_info_rsp *qi_rsp = NULL;
struct smb2_ioctl_rsp *io_rsp = NULL;
void *buffer = NULL;
{
int rc;
unsigned int ret_data_len;
+ struct inode *inode;
struct duplicate_extents_to_file dup_ext_buf;
struct cifs_tcon *tcon = tlink_tcon(trgtfile->tlink);
cifs_dbg(FYI, "Duplicate extents: src off %lld dst off %lld len %lld\n",
src_off, dest_off, len);
- rc = smb2_set_file_size(xid, tcon, trgtfile, dest_off + len, false);
- if (rc)
- goto duplicate_extents_out;
+ inode = d_inode(trgtfile->dentry);
+ if (inode->i_size < dest_off + len) {
+ rc = smb2_set_file_size(xid, tcon, trgtfile, dest_off + len, false);
+ if (rc)
+ goto duplicate_extents_out;
+ /*
+ * Although also could set plausible allocation size (i_blocks)
+ * here in addition to setting the file size, in reflink
+ * it is likely that the target file is sparse. Its allocation
+ * size will be queried on next revalidate, but it is important
+ * to make sure that file's cached size is updated immediately
+ */
+ cifs_setsize(inode, dest_off + len);
+ }
rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid,
trgtfile->fid.volatile_fid,
FSCTL_DUPLICATE_EXTENTS_TO_FILE,
{
struct cifs_ses *ses = tcon->ses;
struct TCP_Server_Info *server = cifs_pick_channel(ses);
- int flags = 0;
+ int flags = CIFS_CP_CREATE_CLOSE_OP;
struct smb_rqst rqst[3];
int resp_buftype[3];
struct kvec rsp_iov[3];
unsigned int sub_offset;
unsigned int print_len;
unsigned int print_offset;
- int flags = 0;
+ int flags = CIFS_CP_CREATE_CLOSE_OP;
struct smb_rqst rqst[3];
int resp_buftype[3];
struct kvec rsp_iov[3];
struct cifs_open_parms oparms;
struct cifs_fid fid;
struct TCP_Server_Info *server = cifs_pick_channel(tcon->ses);
- int flags = 0;
+ int flags = CIFS_CP_CREATE_CLOSE_OP;
struct smb_rqst rqst[3];
int resp_buftype[3];
struct kvec rsp_iov[3];
if (ses->Suid == ses_id) {
ses_enc_key = enc ? ses->smb3encryptionkey :
ses->smb3decryptionkey;
- memcpy(key, ses_enc_key, SMB3_SIGN_KEY_SIZE);
+ memcpy(key, ses_enc_key, SMB3_ENC_DEC_KEY_SIZE);
spin_unlock(&cifs_tcp_ses_lock);
return 0;
}
int rc = 0;
struct scatterlist *sg;
u8 sign[SMB2_SIGNATURE_SIZE] = {};
- u8 key[SMB3_SIGN_KEY_SIZE];
+ u8 key[SMB3_ENC_DEC_KEY_SIZE];
struct aead_request *req;
char *iv;
unsigned int iv_len;
tfm = enc ? server->secmech.ccmaesencrypt :
server->secmech.ccmaesdecrypt;
- if (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)
+ if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) ||
+ (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM))
rc = crypto_aead_setkey(tfm, key, SMB3_GCM256_CRYPTKEY_SIZE);
else
- rc = crypto_aead_setkey(tfm, key, SMB3_SIGN_KEY_SIZE);
+ rc = crypto_aead_setkey(tfm, key, SMB3_GCM128_CRYPTKEY_SIZE);
if (rc) {
cifs_server_dbg(VFS, "%s: Failed to set aead key %d\n", __func__, rc);
if (rdata->credits.value > 0) {
shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->bytes,
SMB2_MAX_BUFFER_SIZE));
- shdr->CreditRequest =
- cpu_to_le16(le16_to_cpu(shdr->CreditCharge) + 1);
+ shdr->CreditRequest = cpu_to_le16(le16_to_cpu(shdr->CreditCharge) + 8);
rc = adjust_credits(server, &rdata->credits, rdata->bytes);
if (rc)
if (wdata->credits.value > 0) {
shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(wdata->bytes,
SMB2_MAX_BUFFER_SIZE));
- shdr->CreditRequest =
- cpu_to_le16(le16_to_cpu(shdr->CreditCharge) + 1);
+ shdr->CreditRequest = cpu_to_le16(le16_to_cpu(shdr->CreditCharge) + 8);
rc = adjust_credits(server, &wdata->credits, wdata->bytes);
if (rc)
extern int smb2_handle_cancelled_close(struct cifs_tcon *tcon,
__u64 persistent_fid,
__u64 volatile_fid);
-extern int smb2_handle_cancelled_mid(char *buffer,
- struct TCP_Server_Info *server);
+extern int smb2_handle_cancelled_mid(struct mid_q_entry *mid, struct TCP_Server_Info *server);
void smb2_cancelled_close_fid(struct work_struct *work);
extern int SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
u64 persistent_file_id, u64 volatile_file_id,
{
unsigned char zero = 0x0;
__u8 i[4] = {0, 0, 0, 1};
- __u8 L[4] = {0, 0, 0, 128};
+ __u8 L128[4] = {0, 0, 0, 128};
+ __u8 L256[4] = {0, 0, 1, 0};
int rc = 0;
unsigned char prfhash[SMB2_HMACSHA256_SIZE];
unsigned char *hashptr = prfhash;
goto smb3signkey_ret;
}
- rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash,
- L, 4);
+ if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) ||
+ (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) {
+ rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash,
+ L256, 4);
+ } else {
+ rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash,
+ L128, 4);
+ }
if (rc) {
cifs_server_dbg(VFS, "%s: Could not update with L\n", __func__);
goto smb3signkey_ret;
const struct derivation_triplet *ptriplet)
{
int rc;
+#ifdef CONFIG_CIFS_DEBUG_DUMP_KEYS
+ struct TCP_Server_Info *server = ses->server;
+#endif
/*
* All channels use the same encryption/decryption keys but
rc = generate_key(ses, ptriplet->encryption.label,
ptriplet->encryption.context,
ses->smb3encryptionkey,
- SMB3_SIGN_KEY_SIZE);
+ SMB3_ENC_DEC_KEY_SIZE);
rc = generate_key(ses, ptriplet->decryption.label,
ptriplet->decryption.context,
ses->smb3decryptionkey,
- SMB3_SIGN_KEY_SIZE);
+ SMB3_ENC_DEC_KEY_SIZE);
if (rc)
return rc;
}
*/
cifs_dbg(VFS, "Session Id %*ph\n", (int)sizeof(ses->Suid),
&ses->Suid);
+ cifs_dbg(VFS, "Cipher type %d\n", server->cipher_type);
cifs_dbg(VFS, "Session Key %*ph\n",
SMB2_NTLMV2_SESSKEY_SIZE, ses->auth_key.response);
cifs_dbg(VFS, "Signing Key %*ph\n",
SMB3_SIGN_KEY_SIZE, ses->smb3signingkey);
- cifs_dbg(VFS, "ServerIn Key %*ph\n",
- SMB3_SIGN_KEY_SIZE, ses->smb3encryptionkey);
- cifs_dbg(VFS, "ServerOut Key %*ph\n",
- SMB3_SIGN_KEY_SIZE, ses->smb3decryptionkey);
+ if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) ||
+ (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) {
+ cifs_dbg(VFS, "ServerIn Key %*ph\n",
+ SMB3_GCM256_CRYPTKEY_SIZE, ses->smb3encryptionkey);
+ cifs_dbg(VFS, "ServerOut Key %*ph\n",
+ SMB3_GCM256_CRYPTKEY_SIZE, ses->smb3decryptionkey);
+ } else {
+ cifs_dbg(VFS, "ServerIn Key %*ph\n",
+ SMB3_GCM128_CRYPTKEY_SIZE, ses->smb3encryptionkey);
+ cifs_dbg(VFS, "ServerOut Key %*ph\n",
+ SMB3_GCM128_CRYPTKEY_SIZE, ses->smb3decryptionkey);
+ }
#endif
return rc;
}
if (midEntry->resp_buf && (midEntry->mid_flags & MID_WAIT_CANCELLED) &&
midEntry->mid_state == MID_RESPONSE_RECEIVED &&
server->ops->handle_cancelled_mid)
- server->ops->handle_cancelled_mid(midEntry->resp_buf, server);
+ server->ops->handle_cancelled_mid(midEntry, server);
midEntry->mid_state = MID_FREE;
atomic_dec(&midCount);
/*
* Compounding is never used during session establish.
*/
- if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP) || (optype & CIFS_SESS_OP))
+ if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP) || (optype & CIFS_SESS_OP)) {
+ mutex_lock(&server->srv_mutex);
smb311_update_preauth_hash(ses, rqst[0].rq_iov,
rqst[0].rq_nvec);
+ mutex_unlock(&server->srv_mutex);
+ }
for (i = 0; i < num_rqst; i++) {
rc = wait_for_response(server, midQ[i]);
}
if (rc != 0) {
for (; i < num_rqst; i++) {
- cifs_server_dbg(VFS, "Cancelling wait for mid %llu cmd: %d\n",
+ cifs_server_dbg(FYI, "Cancelling wait for mid %llu cmd: %d\n",
midQ[i]->mid, le16_to_cpu(midQ[i]->command));
send_cancel(server, &rqst[i], midQ[i]);
spin_lock(&GlobalMid_Lock);
.iov_base = resp_iov[0].iov_base,
.iov_len = resp_iov[0].iov_len
};
+ mutex_lock(&server->srv_mutex);
smb311_update_preauth_hash(ses, &iov, 1);
+ mutex_unlock(&server->srv_mutex);
}
out:
ret = call_mmap(vma->vm_file, vma);
if (ret) {
- /* if call_mmap fails, our caller will put coda_file so we
- * should drop the reference to the host_file that we got.
+ /* if call_mmap fails, our caller will put host_file so we
+ * should drop the reference to the coda_file that we got.
*/
- fput(host_file);
+ fput(coda_file);
kfree(cvm_ops);
} else {
/* here we add redirects for the open/close vm_operations */
attr = to_attr(dentry);
if (!attr)
- goto out_put_item;
+ goto out_free_buffer;
if (type & CONFIGFS_ITEM_BIN_ATTR) {
buffer->bin_attr = to_bin_attr(dentry);
/* Grab the module reference for this attribute if we have one */
error = -ENODEV;
if (!try_module_get(buffer->owner))
- goto out_put_item;
+ goto out_free_buffer;
error = -EACCES;
if (!buffer->item->ci_type)
out_put_module:
module_put(buffer->owner);
-out_put_item:
- config_item_put(buffer->item);
out_free_buffer:
up_read(&frag->frag_sem);
kfree(buffer);
F2FS and UBIFS make use of this feature.
# Filesystems supporting encryption must select this if FS_ENCRYPTION. This
-# allows the algorithms to be built as modules when all the filesystems are.
+# allows the algorithms to be built as modules when all the filesystems are,
+# whereas selecting them from FS_ENCRYPTION would force them to be built-in.
+#
+# Note: this option only pulls in the algorithms that filesystem encryption
+# needs "by default". If userspace will use "non-default" encryption modes such
+# as Adiantum encryption, then those other modes need to be explicitly enabled
+# in the crypto API; see Documentation/filesystems/fscrypt.rst for details.
+#
+# Also note that this option only pulls in the generic implementations of the
+# algorithms, not any per-architecture optimized implementations. It is
+# strongly recommended to enable optimized implementations too. It is safe to
+# disable these generic implementations if corresponding optimized
+# implementations will always be available too; for this reason, these are soft
+# dependencies ('imply' rather than 'select'). Only disable these generic
+# implementations if you're sure they will never be needed, though.
config FS_ENCRYPTION_ALGS
tristate
- select CRYPTO_AES
- select CRYPTO_CBC
- select CRYPTO_CTS
- select CRYPTO_ECB
- select CRYPTO_HMAC
- select CRYPTO_SHA512
- select CRYPTO_XTS
+ imply CRYPTO_AES
+ imply CRYPTO_CBC
+ imply CRYPTO_CTS
+ imply CRYPTO_ECB
+ imply CRYPTO_HMAC
+ imply CRYPTO_SHA512
+ imply CRYPTO_XTS
config FS_ENCRYPTION_INLINE_CRYPT
bool "Enable fscrypt to use inline crypto"
int num_pages = 0;
/* This always succeeds since __GFP_DIRECT_RECLAIM is set. */
- bio = bio_alloc(GFP_NOFS, BIO_MAX_PAGES);
+ bio = bio_alloc(GFP_NOFS, BIO_MAX_VECS);
while (len) {
unsigned int blocks_this_page = min(len, blocks_per_page);
len -= blocks_this_page;
lblk += blocks_this_page;
pblk += blocks_this_page;
- if (num_pages == BIO_MAX_PAGES || !len ||
+ if (num_pages == BIO_MAX_VECS || !len ||
!fscrypt_mergeable_bio(bio, inode, lblk)) {
err = submit_bio_wait(bio);
if (err)
return fscrypt_zeroout_range_inline_crypt(inode, lblk, pblk,
len);
- BUILD_BUG_ON(ARRAY_SIZE(pages) > BIO_MAX_PAGES);
+ BUILD_BUG_ON(ARRAY_SIZE(pages) > BIO_MAX_VECS);
nr_pages = min_t(unsigned int, ARRAY_SIZE(pages),
(len + blocks_per_page - 1) >> blocks_per_page_bits);
struct buffer_head *map_bh)
{
int ret = 0;
+ int boundary = sdio->boundary; /* dio_send_cur_page may clear it */
if (dio->op == REQ_OP_WRITE) {
/*
sdio->cur_page_fs_offset = sdio->block_in_file << sdio->blkbits;
out:
/*
- * If sdio->boundary then we want to schedule the IO now to
+ * If boundary then we want to schedule the IO now to
* avoid metadata seeks.
*/
- if (sdio->boundary) {
+ if (boundary) {
ret = dio_send_cur_page(dio, sdio, map_bh);
if (sdio->bio)
dio_bio_submit(dio, sdio);
struct page *page,
erofs_off_t *last_block,
unsigned int nblocks,
+ unsigned int *eblks,
bool ra)
{
struct inode *const inode = mapping->host;
/* note that for readpage case, bio also equals to NULL */
if (bio &&
- /* not continuous */
- *last_block + 1 != current_block) {
+ (*last_block + 1 != current_block || !*eblks)) {
submit_bio_retry:
submit_bio(bio);
bio = NULL;
if (nblocks > DIV_ROUND_UP(map.m_plen, PAGE_SIZE))
nblocks = DIV_ROUND_UP(map.m_plen, PAGE_SIZE);
- bio = bio_alloc(GFP_NOIO, bio_max_segs(nblocks));
+ *eblks = bio_max_segs(nblocks);
+ bio = bio_alloc(GFP_NOIO, *eblks);
bio->bi_end_io = erofs_readendio;
bio_set_dev(bio, sb->s_bdev);
/* out of the extent or bio is full */
if (err < PAGE_SIZE)
goto submit_bio_retry;
-
+ --*eblks;
*last_block = current_block;
-
- /* shift in advance in case of it followed by too many gaps */
- if (bio->bi_iter.bi_size >= bio->bi_max_vecs * PAGE_SIZE) {
- /* err should reassign to 0 after submitting */
- err = 0;
- goto submit_bio_out;
- }
-
return bio;
err_out:
/* if updated manually, continuous pages has a gap */
if (bio)
-submit_bio_out:
submit_bio(bio);
return err ? ERR_PTR(err) : NULL;
}
static int erofs_raw_access_readpage(struct file *file, struct page *page)
{
erofs_off_t last_block;
+ unsigned int eblks;
struct bio *bio;
trace_erofs_readpage(page, true);
bio = erofs_read_raw_page(NULL, page->mapping,
- page, &last_block, 1, false);
+ page, &last_block, 1, &eblks, false);
if (IS_ERR(bio))
return PTR_ERR(bio);
- DBG_BUGON(bio); /* since we have only one bio -- must be NULL */
+ if (bio)
+ submit_bio(bio);
return 0;
}
static void erofs_raw_access_readahead(struct readahead_control *rac)
{
erofs_off_t last_block;
+ unsigned int eblks;
struct bio *bio = NULL;
struct page *page;
prefetchw(&page->flags);
bio = erofs_read_raw_page(bio, rac->mapping, page, &last_block,
- readahead_count(rac), true);
+ readahead_count(rac), &eblks, true);
/* all the page errors are ignored when readahead */
if (IS_ERR(bio)) {
put_page(page);
}
- /* the rare case (end in gaps) */
if (bio)
submit_bio(bio);
}
}
if (!bio) {
- bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
+ bio = bio_alloc(GFP_NOIO, BIO_MAX_VECS);
bio->bi_end_io = z_erofs_decompressqueue_endio;
bio_set_dev(bio, sb->s_bdev);
/**
* ext4_should_retry_alloc() - check if a block allocation should be retried
- * @sb: super block
- * @retries: number of attemps has been made
+ * @sb: superblock
+ * @retries: number of retry attempts made so far
*
- * ext4_should_retry_alloc() is called when ENOSPC is returned, and if
- * it is profitable to retry the operation, this function will wait
- * for the current or committing transaction to complete, and then
- * return TRUE. We will only retry once.
+ * ext4_should_retry_alloc() is called when ENOSPC is returned while
+ * attempting to allocate blocks. If there's an indication that a pending
+ * journal transaction might free some space and allow another attempt to
+ * succeed, this function will wait for the current or committing transaction
+ * to complete and then return TRUE.
*/
int ext4_should_retry_alloc(struct super_block *sb, int *retries)
{
- if (!ext4_has_free_clusters(EXT4_SB(sb), 1, 0) ||
- (*retries)++ > 1 ||
- !EXT4_SB(sb)->s_journal)
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+
+ if (!sbi->s_journal)
return 0;
- smp_mb();
- if (EXT4_SB(sb)->s_mb_free_pending == 0)
+ if (++(*retries) > 3) {
+ percpu_counter_inc(&sbi->s_sra_exceeded_retry_limit);
return 0;
+ }
+ /*
+ * if there's no indication that blocks are about to be freed it's
+ * possible we just missed a transaction commit that did so
+ */
+ smp_mb();
+ if (sbi->s_mb_free_pending == 0)
+ return ext4_has_free_clusters(sbi, 1, 0);
+
+ /*
+ * it's possible we've just missed a transaction commit here,
+ * so ignore the returned status
+ */
jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id);
- jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal);
+ (void) jbd2_journal_force_commit_nested(sbi->s_journal);
return 1;
}
struct percpu_counter s_freeinodes_counter;
struct percpu_counter s_dirs_counter;
struct percpu_counter s_dirtyclusters_counter;
+ struct percpu_counter s_sra_exceeded_retry_limit;
struct blockgroup_lock *s_blockgroup_lock;
struct proc_dir_entry *s_proc;
struct kobject s_kobj;
struct dentry *dentry);
void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry);
void ext4_fc_track_link(handle_t *handle, struct dentry *dentry);
+void __ext4_fc_track_create(handle_t *handle, struct inode *inode,
+ struct dentry *dentry);
void ext4_fc_track_create(handle_t *handle, struct dentry *dentry);
void ext4_fc_track_inode(handle_t *handle, struct inode *inode);
void ext4_fc_mark_ineligible(struct super_block *sb, int reason);
{
struct inode *inode = file_inode(file);
handle_t *handle;
- int ret, ret2 = 0, ret3 = 0;
+ int ret = 0, ret2 = 0, ret3 = 0;
int retries = 0;
int depth = 0;
struct ext4_map_blocks map;
__ext4_fc_track_link(handle, d_inode(dentry), dentry);
}
-void ext4_fc_track_create(handle_t *handle, struct dentry *dentry)
+void __ext4_fc_track_create(handle_t *handle, struct inode *inode,
+ struct dentry *dentry)
{
struct __track_dentry_update_args args;
- struct inode *inode = d_inode(dentry);
int ret;
args.dentry = dentry;
trace_ext4_fc_track_create(inode, dentry, ret);
}
+void ext4_fc_track_create(handle_t *handle, struct dentry *dentry)
+{
+ __ext4_fc_track_create(handle, d_inode(dentry), dentry);
+}
+
/* __track_fn for inode tracking */
static int __track_inode(struct inode *inode, void *arg, bool update)
{
if (!ret)
ret = err;
- if (!ext4_has_inline_data(inode))
- ext4_walk_page_buffers(NULL, page_bufs, 0, len,
- NULL, bput_one);
ext4_set_inode_state(inode, EXT4_STATE_JDATA);
out:
unlock_page(page);
out_no_pagelock:
+ if (!inline_data && page_bufs)
+ ext4_walk_page_buffers(NULL, page_bufs, 0, len,
+ NULL, bput_one);
brelse(inode_bh);
return ret;
}
struct ext4_inode_info *ei = EXT4_I(inode);
struct buffer_head *bh = iloc->bh;
struct super_block *sb = inode->i_sb;
- int err = 0, rc, block;
+ int err = 0, block;
int need_datasync = 0, set_large_file = 0;
uid_t i_uid;
gid_t i_gid;
bh->b_data);
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
- rc = ext4_handle_dirty_metadata(handle, NULL, bh);
- if (!err)
- err = rc;
+ err = ext4_handle_dirty_metadata(handle, NULL, bh);
+ if (err)
+ goto out_brelse;
ext4_clear_inode_state(inode, EXT4_STATE_NEW);
if (set_large_file) {
BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get write access");
inode->i_gid = attr->ia_gid;
error = ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
- if (unlikely(error))
+ if (unlikely(error)) {
+ ext4_fc_stop_update(inode);
return error;
+ }
}
if (attr->ia_valid & ATTR_SIZE) {
}
if (ext4_has_feature_flex_bg(sb)) {
- /* a single flex group is supposed to be read by a single IO */
- sbi->s_mb_prefetch = min(1 << sbi->s_es->s_log_groups_per_flex,
+ /* a single flex group is supposed to be read by a single IO.
+ * 2 ^ s_log_groups_per_flex != UINT_MAX as s_mb_prefetch is
+ * unsigned integer, so the maximum shift is 32.
+ */
+ if (sbi->s_es->s_log_groups_per_flex >= 32) {
+ ext4_msg(sb, KERN_ERR, "too many log groups per flexible block group");
+ goto err_freesgi;
+ }
+ sbi->s_mb_prefetch = min_t(uint, 1 << sbi->s_es->s_log_groups_per_flex,
BLK_MAX_SEGMENT_SIZE >> (sb->s_blocksize_bits - 9));
sbi->s_mb_prefetch *= 8; /* 8 prefetch IOs in flight at most */
} else {
return retval;
}
+static void ext4_resetent(handle_t *handle, struct ext4_renament *ent,
+ unsigned ino, unsigned file_type)
+{
+ struct ext4_renament old = *ent;
+ int retval = 0;
+
+ /*
+ * old->de could have moved from under us during make indexed dir,
+ * so the old->de may no longer valid and need to find it again
+ * before reset old inode info.
+ */
+ old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL);
+ if (IS_ERR(old.bh))
+ retval = PTR_ERR(old.bh);
+ if (!old.bh)
+ retval = -ENOENT;
+ if (retval) {
+ ext4_std_error(old.dir->i_sb, retval);
+ return;
+ }
+
+ ext4_setent(handle, &old, ino, file_type);
+ brelse(old.bh);
+}
+
static int ext4_find_delete_entry(handle_t *handle, struct inode *dir,
const struct qstr *d_name)
{
*/
retval = -ENOENT;
if (!old.bh || le32_to_cpu(old.de->inode) != old.inode->i_ino)
- goto end_rename;
+ goto release_bh;
new.bh = ext4_find_entry(new.dir, &new.dentry->d_name,
&new.de, &new.inlined);
if (IS_ERR(new.bh)) {
retval = PTR_ERR(new.bh);
new.bh = NULL;
- goto end_rename;
+ goto release_bh;
}
if (new.bh) {
if (!new.inode) {
handle = ext4_journal_start(old.dir, EXT4_HT_DIR, credits);
if (IS_ERR(handle)) {
retval = PTR_ERR(handle);
- handle = NULL;
- goto end_rename;
+ goto release_bh;
}
} else {
whiteout = ext4_whiteout_for_rename(mnt_userns, &old, credits, &handle);
if (IS_ERR(whiteout)) {
retval = PTR_ERR(whiteout);
- whiteout = NULL;
- goto end_rename;
+ goto release_bh;
}
}
retval = ext4_mark_inode_dirty(handle, whiteout);
if (unlikely(retval))
goto end_rename;
+
}
if (!new.bh) {
retval = ext4_add_entry(handle, new.dentry, old.inode);
ext4_fc_track_unlink(handle, new.dentry);
__ext4_fc_track_link(handle, old.inode, new.dentry);
__ext4_fc_track_unlink(handle, old.inode, old.dentry);
+ if (whiteout)
+ __ext4_fc_track_create(handle, whiteout, old.dentry);
}
if (new.inode) {
end_rename:
if (whiteout) {
if (retval) {
- ext4_setent(handle, &old,
- old.inode->i_ino, old_file_type);
+ ext4_resetent(handle, &old,
+ old.inode->i_ino, old_file_type);
drop_nlink(whiteout);
+ ext4_orphan_add(handle, whiteout);
}
unlock_new_inode(whiteout);
+ ext4_journal_stop(handle);
iput(whiteout);
-
+ } else {
+ ext4_journal_stop(handle);
}
+release_bh:
brelse(old.dir_bh);
brelse(old.bh);
brelse(new.bh);
- if (handle)
- ext4_journal_stop(handle);
return retval;
}
* bio_alloc will _always_ be able to allocate a bio if
* __GFP_DIRECT_RECLAIM is set, see comments for bio_alloc_bioset().
*/
- bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
+ bio = bio_alloc(GFP_NOIO, BIO_MAX_VECS);
fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO);
bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
bio_set_dev(bio, bh->b_bdev);
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
+ percpu_counter_destroy(&sbi->s_sra_exceeded_retry_limit);
percpu_free_rwsem(&sbi->s_writepages_rwsem);
#ifdef CONFIG_QUOTA
for (i = 0; i < EXT4_MAXQUOTAS; i++)
err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0,
GFP_KERNEL);
if (!err)
+ err = percpu_counter_init(&sbi->s_sra_exceeded_retry_limit, 0,
+ GFP_KERNEL);
+ if (!err)
err = percpu_init_rwsem(&sbi->s_writepages_rwsem);
if (err) {
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
+ percpu_counter_destroy(&sbi->s_sra_exceeded_retry_limit);
percpu_free_rwsem(&sbi->s_writepages_rwsem);
failed_mount5:
ext4_ext_release(sb);
failed_mount3a:
ext4_es_unregister_shrinker(sbi);
failed_mount3:
- del_timer_sync(&sbi->s_err_report);
flush_work(&sbi->s_error_work);
+ del_timer_sync(&sbi->s_err_report);
if (sbi->s_mmp_tsk)
kthread_stop(sbi->s_mmp_tsk);
failed_mount2:
attr_session_write_kbytes,
attr_lifetime_write_kbytes,
attr_reserved_clusters,
+ attr_sra_exceeded_retry_limit,
attr_inode_readahead,
attr_trigger_test_error,
attr_first_error_time,
EXT4_ATTR_FUNC(session_write_kbytes, 0444);
EXT4_ATTR_FUNC(lifetime_write_kbytes, 0444);
EXT4_ATTR_FUNC(reserved_clusters, 0644);
+EXT4_ATTR_FUNC(sra_exceeded_retry_limit, 0444);
EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, inode_readahead,
ext4_sb_info, s_inode_readahead_blks);
ATTR_LIST(session_write_kbytes),
ATTR_LIST(lifetime_write_kbytes),
ATTR_LIST(reserved_clusters),
+ ATTR_LIST(sra_exceeded_retry_limit),
ATTR_LIST(inode_readahead_blks),
ATTR_LIST(inode_goal),
ATTR_LIST(mb_stats),
return snprintf(buf, PAGE_SIZE, "%llu\n",
(unsigned long long)
atomic64_read(&sbi->s_resv_clusters));
+ case attr_sra_exceeded_retry_limit:
+ return snprintf(buf, PAGE_SIZE, "%llu\n",
+ (unsigned long long)
+ percpu_counter_sum(&sbi->s_sra_exceeded_retry_limit));
case attr_inode_readahead:
case attr_pointer_ui:
if (!ptr)
struct inode *inode = file_inode(filp);
const int credits = 2; /* superblock and inode for ext4_orphan_del() */
handle_t *handle;
+ struct ext4_iloc iloc;
int err = 0;
- int err2;
- if (desc != NULL) {
- /* Succeeded; write the verity descriptor. */
- err = ext4_write_verity_descriptor(inode, desc, desc_size,
- merkle_tree_size);
-
- /* Write all pages before clearing VERITY_IN_PROGRESS. */
- if (!err)
- err = filemap_write_and_wait(inode->i_mapping);
- }
+ /*
+ * If an error already occurred (which fs/verity/ signals by passing
+ * desc == NULL), then only clean-up is needed.
+ */
+ if (desc == NULL)
+ goto cleanup;
- /* If we failed, truncate anything we wrote past i_size. */
- if (desc == NULL || err)
- ext4_truncate(inode);
+ /* Append the verity descriptor. */
+ err = ext4_write_verity_descriptor(inode, desc, desc_size,
+ merkle_tree_size);
+ if (err)
+ goto cleanup;
/*
- * We must always clean up by clearing EXT4_STATE_VERITY_IN_PROGRESS and
- * deleting the inode from the orphan list, even if something failed.
- * If everything succeeded, we'll also set the verity bit in the same
- * transaction.
+ * Write all pages (both data and verity metadata). Note that this must
+ * happen before clearing EXT4_STATE_VERITY_IN_PROGRESS; otherwise pages
+ * beyond i_size won't be written properly. For crash consistency, this
+ * also must happen before the verity inode flag gets persisted.
*/
+ err = filemap_write_and_wait(inode->i_mapping);
+ if (err)
+ goto cleanup;
- ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS);
+ /*
+ * Finally, set the verity inode flag and remove the inode from the
+ * orphan list (in a single transaction).
+ */
handle = ext4_journal_start(inode, EXT4_HT_INODE, credits);
if (IS_ERR(handle)) {
- ext4_orphan_del(NULL, inode);
- return PTR_ERR(handle);
+ err = PTR_ERR(handle);
+ goto cleanup;
}
- err2 = ext4_orphan_del(handle, inode);
- if (err2)
- goto out_stop;
+ err = ext4_orphan_del(handle, inode);
+ if (err)
+ goto stop_and_cleanup;
- if (desc != NULL && !err) {
- struct ext4_iloc iloc;
+ err = ext4_reserve_inode_write(handle, inode, &iloc);
+ if (err)
+ goto stop_and_cleanup;
- err = ext4_reserve_inode_write(handle, inode, &iloc);
- if (err)
- goto out_stop;
- ext4_set_inode_flag(inode, EXT4_INODE_VERITY);
- ext4_set_inode_flags(inode, false);
- err = ext4_mark_iloc_dirty(handle, inode, &iloc);
- }
-out_stop:
+ ext4_set_inode_flag(inode, EXT4_INODE_VERITY);
+ ext4_set_inode_flags(inode, false);
+ err = ext4_mark_iloc_dirty(handle, inode, &iloc);
+ if (err)
+ goto stop_and_cleanup;
+
+ ext4_journal_stop(handle);
+
+ ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS);
+ return 0;
+
+stop_and_cleanup:
ext4_journal_stop(handle);
- return err ?: err2;
+cleanup:
+ /*
+ * Verity failed to be enabled, so clean up by truncating any verity
+ * metadata that was written beyond i_size (both from cache and from
+ * disk), removing the inode from the orphan list (if it wasn't done
+ * already), and clearing EXT4_STATE_VERITY_IN_PROGRESS.
+ */
+ truncate_inode_pages(inode->i_mapping, inode->i_size);
+ ext4_truncate(inode);
+ ext4_orphan_del(NULL, inode);
+ ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS);
+ return err;
}
static int ext4_get_verity_descriptor_location(struct inode *inode,
if (!ce)
return NULL;
+ WARN_ON_ONCE(ext4_handle_valid(journal_current_handle()) &&
+ !(current->flags & PF_MEMALLOC_NOFS));
+
ea_data = kvmalloc(value_len, GFP_KERNEL);
if (!ea_data) {
mb_cache_entry_put(ea_inode_cache, ce);
error = -ENOSPC;
goto cleanup;
}
+ WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS));
}
error = ext4_reserve_inode_write(handle, inode, &is.iloc);
* external inode if possible.
*/
if (ext4_has_feature_ea_inode(inode->i_sb) &&
- !i.in_inode) {
+ i.value_len && !i.in_inode) {
i.in_inode = 1;
goto retry_inode;
}
f2fs_put_page(page, 0);
if (readahead)
- f2fs_ra_meta_pages(sbi, index, BIO_MAX_PAGES, META_POR, true);
+ f2fs_ra_meta_pages(sbi, index, BIO_MAX_VECS, META_POR, true);
}
static int __f2fs_write_meta_page(struct page *page,
f2fs_submit_merged_ipu_write(fio->sbi, &bio, NULL);
alloc_new:
if (!bio) {
- bio = __bio_alloc(fio, BIO_MAX_PAGES);
+ bio = __bio_alloc(fio, BIO_MAX_VECS);
__attach_io_flag(fio);
f2fs_set_bio_crypt_ctx(bio, fio->page->mapping->host,
fio->page->index, fio, GFP_NOIO);
fio->retry = true;
goto skip;
}
- io->bio = __bio_alloc(fio, BIO_MAX_PAGES);
+ io->bio = __bio_alloc(fio, BIO_MAX_VECS);
f2fs_set_bio_crypt_ctx(io->bio, fio->page->mapping->host,
bio_page->index, fio, GFP_NOIO);
io->fio = *fio;
block_t total_node_blocks = 0;
do {
- readed = f2fs_ra_meta_pages(sbi, start_blk, BIO_MAX_PAGES,
+ readed = f2fs_ra_meta_pages(sbi, start_blk, BIO_MAX_VECS,
META_SIT, true);
start = start_blk * sit_i->sents_per_block;
else if (type == NODE)
return 8 * sbi->blocks_per_seg;
else if (type == META)
- return 8 * BIO_MAX_PAGES;
+ return 8 * BIO_MAX_VECS;
else
return 0;
}
return 0;
nr_to_write = wbc->nr_to_write;
- desired = BIO_MAX_PAGES;
+ desired = BIO_MAX_VECS;
if (type == NODE)
desired <<= 1;
case Opt_io_size_bits:
if (args->from && match_int(args, &arg))
return -EINVAL;
- if (arg <= 0 || arg > __ilog2_u32(BIO_MAX_PAGES)) {
+ if (arg <= 0 || arg > __ilog2_u32(BIO_MAX_VECS)) {
f2fs_warn(sbi, "Not support %d, larger than %d",
- 1 << arg, BIO_MAX_PAGES);
+ 1 << arg, BIO_MAX_VECS);
return -EINVAL;
}
F2FS_OPTION(sbi).write_io_size_bits = arg;
}
EXPORT_SYMBOL(close_fd); /* for ksys_close() */
+/**
+ * last_fd - return last valid index into fd table
+ * @cur_fds: files struct
+ *
+ * Context: Either rcu read lock or files_lock must be held.
+ *
+ * Returns: Last valid index into fdtable.
+ */
+static inline unsigned last_fd(struct fdtable *fdt)
+{
+ return fdt->max_fds - 1;
+}
+
static inline void __range_cloexec(struct files_struct *cur_fds,
unsigned int fd, unsigned int max_fd)
{
struct fdtable *fdt;
- if (fd > max_fd)
- return;
-
+ /* make sure we're using the correct maximum value */
spin_lock(&cur_fds->file_lock);
fdt = files_fdtable(cur_fds);
- bitmap_set(fdt->close_on_exec, fd, max_fd - fd + 1);
+ max_fd = min(last_fd(fdt), max_fd);
+ if (fd <= max_fd)
+ bitmap_set(fdt->close_on_exec, fd, max_fd - fd + 1);
spin_unlock(&cur_fds->file_lock);
}
static long fuse_dev_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
- int err = -ENOTTY;
+ int res;
+ int oldfd;
+ struct fuse_dev *fud = NULL;
- if (cmd == FUSE_DEV_IOC_CLONE) {
- int oldfd;
+ if (_IOC_TYPE(cmd) != FUSE_DEV_IOC_MAGIC)
+ return -ENOTTY;
- err = -EFAULT;
- if (!get_user(oldfd, (__u32 __user *) arg)) {
+ switch (_IOC_NR(cmd)) {
+ case _IOC_NR(FUSE_DEV_IOC_CLONE):
+ res = -EFAULT;
+ if (!get_user(oldfd, (__u32 __user *)arg)) {
struct file *old = fget(oldfd);
- err = -EINVAL;
+ res = -EINVAL;
if (old) {
- struct fuse_dev *fud = NULL;
-
/*
* Check against file->f_op because CUSE
* uses the same ioctl handler.
if (fud) {
mutex_lock(&fuse_mutex);
- err = fuse_device_clone(fud->fc, file);
+ res = fuse_device_clone(fud->fc, file);
mutex_unlock(&fuse_mutex);
}
fput(old);
}
}
+ break;
+ default:
+ res = -ENOTTY;
+ break;
}
- return err;
+ return res;
}
const struct file_operations fuse_dev_operations = {
static inline void fuse_make_bad(struct inode *inode)
{
+ remove_inode_hash(inode);
set_bit(FUSE_I_BAD, &get_fuse_inode(inode)->state);
}
/* virtiofs allocates and installs its own fuse devices */
ctx->fudptr = NULL;
- if (ctx->dax)
+ if (ctx->dax) {
+ if (!fs->dax_dev) {
+ err = -EINVAL;
+ pr_err("virtio-fs: dax can't be enabled as filesystem"
+ " device does not support it.\n");
+ goto err_free_fuse_devs;
+ }
ctx->dax_dev = fs->dax_dev;
+ }
err = fuse_fill_super_common(sb, ctx);
if (err < 0)
goto err_free_fuse_devs;
while (!list_empty(head)) {
bd = list_first_entry(head, struct gfs2_bufdata, bd_list);
list_del_init(&bd->bd_list);
+ if (!list_empty(&bd->bd_ail_st_list))
+ gfs2_remove_from_ail(bd);
kmem_cache_free(gfs2_bufdata_cachep, bd);
}
head = &tr->tr_databuf;
while (!list_empty(head)) {
bd = list_first_entry(head, struct gfs2_bufdata, bd_list);
list_del_init(&bd->bd_list);
+ if (!list_empty(&bd->bd_ail_st_list))
+ gfs2_remove_from_ail(bd);
kmem_cache_free(gfs2_bufdata_cachep, bd);
}
}
* Do this check while holding the log_flush_lock to prevent new
* buffers from being added to the ail via gfs2_pin()
*/
- if (gfs2_withdrawn(sdp))
+ if (gfs2_withdrawn(sdp) || !test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
goto out;
/* Log might have been flushed while we waited for the flush lock */
bio_end_io_t *end_io)
{
struct super_block *sb = sdp->sd_vfs;
- struct bio *bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES);
+ struct bio *bio = bio_alloc(GFP_NOIO, BIO_MAX_VECS);
bio->bi_iter.bi_sector = blkno << sdp->sd_fsb2bb_shift;
bio_set_dev(bio, sb->s_bdev);
return -EINVAL;
if (fc->sb_flags & SB_RDONLY) {
- error = gfs2_make_fs_ro(sdp);
- if (error)
- errorfc(fc, "unable to remount read-only");
+ gfs2_make_fs_ro(sdp);
} else {
error = gfs2_make_fs_rw(sdp);
if (error)
int error;
error = init_threads(sdp);
- if (error)
+ if (error) {
+ gfs2_withdraw_delayed(sdp);
return error;
+ }
j_gl->gl_ops->go_inval(j_gl, DIO_METADATA);
if (gfs2_withdrawn(sdp)) {
* Returns: errno
*/
-int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
+void gfs2_make_fs_ro(struct gfs2_sbd *sdp)
{
- int error = 0;
int log_write_allowed = test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
gfs2_flush_delete_work(sdp);
if (!log_write_allowed)
sdp->sd_vfs->s_flags |= SB_RDONLY;
-
- return error;
}
/**
static void gfs2_put_super(struct super_block *sb)
{
struct gfs2_sbd *sdp = sb->s_fs_info;
- int error;
struct gfs2_jdesc *jd;
/* No more recovery requests */
spin_unlock(&sdp->sd_jindex_spin);
if (!sb_rdonly(sb)) {
- error = gfs2_make_fs_ro(sdp);
- if (error)
- gfs2_io_error(sdp);
+ gfs2_make_fs_ro(sdp);
}
WARN_ON(gfs2_withdrawing(sdp));
static int gfs2_freeze(struct super_block *sb)
{
struct gfs2_sbd *sdp = sb->s_fs_info;
- int error = 0;
+ int error;
mutex_lock(&sdp->sd_freeze_mutex);
- if (atomic_read(&sdp->sd_freeze_state) != SFS_UNFROZEN)
+ if (atomic_read(&sdp->sd_freeze_state) != SFS_UNFROZEN) {
+ error = -EBUSY;
goto out;
+ }
for (;;) {
if (gfs2_withdrawn(sdp)) {
struct gfs2_sbd *sdp = sb->s_fs_info;
mutex_lock(&sdp->sd_freeze_mutex);
- if (atomic_read(&sdp->sd_freeze_state) != SFS_FROZEN ||
+ if (atomic_read(&sdp->sd_freeze_state) != SFS_FROZEN ||
!gfs2_holder_initialized(&sdp->sd_freeze_gh)) {
mutex_unlock(&sdp->sd_freeze_mutex);
- return 0;
+ return -EINVAL;
}
gfs2_freeze_unlock(&sdp->sd_freeze_gh);
struct gfs2_inode **ipp);
extern int gfs2_make_fs_rw(struct gfs2_sbd *sdp);
-extern int gfs2_make_fs_ro(struct gfs2_sbd *sdp);
+extern void gfs2_make_fs_ro(struct gfs2_sbd *sdp);
extern void gfs2_online_uevent(struct gfs2_sbd *sdp);
extern int gfs2_statfs_init(struct gfs2_sbd *sdp);
extern void gfs2_statfs_change(struct gfs2_sbd *sdp, s64 total, s64 free,
bd->bd_bh = bh;
bd->bd_gl = gl;
INIT_LIST_HEAD(&bd->bd_list);
+ INIT_LIST_HEAD(&bd->bd_ail_st_list);
+ INIT_LIST_HEAD(&bd->bd_ail_gl_list);
bh->b_private = bd;
return bd;
}
static void signal_our_withdraw(struct gfs2_sbd *sdp)
{
struct gfs2_glock *live_gl = sdp->sd_live_gh.gh_gl;
- struct inode *inode = sdp->sd_jdesc->jd_inode;
- struct gfs2_inode *ip = GFS2_I(inode);
- struct gfs2_glock *i_gl = ip->i_gl;
- u64 no_formal_ino = ip->i_no_formal_ino;
+ struct inode *inode;
+ struct gfs2_inode *ip;
+ struct gfs2_glock *i_gl;
+ u64 no_formal_ino;
int log_write_allowed = test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
int ret = 0;
int tries;
- if (test_bit(SDF_NORECOVERY, &sdp->sd_flags))
+ if (test_bit(SDF_NORECOVERY, &sdp->sd_flags) || !sdp->sd_jdesc)
return;
+ inode = sdp->sd_jdesc->jd_inode;
+ ip = GFS2_I(inode);
+ i_gl = ip->i_gl;
+ no_formal_ino = ip->i_no_formal_ino;
+
/* Prevent any glock dq until withdraw recovery is complete */
set_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags);
/*
ret = 0;
}
if (!ret)
- ret = gfs2_make_fs_ro(sdp);
+ gfs2_make_fs_ro(sdp);
gfs2_freeze_unlock(&freeze_gh);
}
char *name, *resolved, *end;
int n;
- name = __getname();
+ name = kmalloc(PATH_MAX, GFP_KERNEL);
if (!name) {
n = -ENOMEM;
goto out_free;
goto out_free;
}
- __putname(name);
- kfree(link);
+ kfree(name);
return resolved;
out_free:
- __putname(name);
+ kfree(name);
return ERR_PTR(n);
}
#include <linux/rculist_nulls.h>
#include <linux/cpu.h>
#include <linux/tracehook.h>
-#include <linux/freezer.h>
#include "../kernel/sched/sched.h"
#include "io-wq.h"
io_wq_work_fn *do_work;
struct task_struct *manager;
- struct user_struct *user;
struct io_wq_hash *hash;
return NULL;
}
-static void io_flush_signals(void)
+static bool io_flush_signals(void)
{
- if (unlikely(test_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL))) {
- if (current->task_works)
- task_work_run();
- clear_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL);
+ if (unlikely(test_thread_flag(TIF_NOTIFY_SIGNAL))) {
+ __set_current_state(TASK_RUNNING);
+ tracehook_notify_signal();
+ return true;
}
+ return false;
}
static void io_assign_current_work(struct io_worker *worker,
{
struct io_wqe *wqe = worker->wqe;
struct io_wq *wq = wqe->wq;
+ bool do_kill = test_bit(IO_WQ_BIT_EXIT, &wq->state);
do {
struct io_wq_work *work;
unsigned int hash = io_get_work_hash(work);
next_hashed = wq_next_work(work);
+
+ if (unlikely(do_kill) && (work->flags & IO_WQ_WORK_UNBOUND))
+ work->flags |= IO_WQ_WORK_CANCEL;
wq->do_work(work);
io_assign_current_work(worker, NULL);
worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING);
io_wqe_inc_running(worker);
- sprintf(buf, "iou-wrk-%d", wq->task_pid);
+ snprintf(buf, sizeof(buf), "iou-wrk-%d", wq->task_pid);
set_task_comm(current, buf);
while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) {
+ long ret;
+
set_current_state(TASK_INTERRUPTIBLE);
loop:
raw_spin_lock_irq(&wqe->lock);
}
__io_worker_idle(wqe, worker);
raw_spin_unlock_irq(&wqe->lock);
- io_flush_signals();
- if (schedule_timeout(WORKER_IDLE_TIMEOUT))
+ if (io_flush_signals())
continue;
- if (fatal_signal_pending(current))
+ ret = schedule_timeout(WORKER_IDLE_TIMEOUT);
+ if (signal_pending(current)) {
+ struct ksignal ksig;
+
+ if (!get_signal(&ksig))
+ continue;
break;
+ }
+ if (ret)
+ continue;
/* timed out, exit unless we're the fixed worker */
if (test_bit(IO_WQ_BIT_EXIT, &wq->state) ||
!(worker->flags & IO_WORKER_F_FIXED))
tsk->pf_io_worker = worker;
worker->task = tsk;
set_cpus_allowed_ptr(tsk, cpumask_of_node(wqe->node));
- tsk->flags |= PF_NOFREEZE | PF_NO_SETAFFINITY;
+ tsk->flags |= PF_NO_SETAFFINITY;
raw_spin_lock_irq(&wqe->lock);
hlist_nulls_add_head_rcu(&worker->nulls_node, &wqe->free_list);
char buf[TASK_COMM_LEN];
int node;
- sprintf(buf, "iou-mgr-%d", wq->task_pid);
+ snprintf(buf, sizeof(buf), "iou-mgr-%d", wq->task_pid);
set_task_comm(current, buf);
do {
set_current_state(TASK_INTERRUPTIBLE);
io_wq_check_workers(wq);
schedule_timeout(HZ);
- try_to_freeze();
- if (fatal_signal_pending(current))
+ if (signal_pending(current)) {
+ struct ksignal ksig;
+
+ if (!get_signal(&ksig))
+ continue;
set_bit(IO_WQ_BIT_EXIT, &wq->state);
+ }
} while (!test_bit(IO_WQ_BIT_EXIT, &wq->state));
io_wq_check_workers(wq);
io_wq_for_each_worker(wq->wqes[node], io_wq_worker_wake, NULL);
rcu_read_unlock();
- /* we might not ever have created any workers */
- if (atomic_read(&wq->worker_refs))
- wait_for_completion(&wq->worker_done);
+ if (atomic_dec_and_test(&wq->worker_refs))
+ complete(&wq->worker_done);
+ wait_for_completion(&wq->worker_done);
spin_lock_irq(&wq->hash->wait.lock);
for_each_node(node)
if (wq->manager)
return 0;
- reinit_completion(&wq->worker_done);
+ WARN_ON_ONCE(test_bit(IO_WQ_BIT_EXIT, &wq->state));
+
+ init_completion(&wq->worker_done);
+ atomic_set(&wq->worker_refs, 1);
tsk = create_io_thread(io_wq_manager, wq, NUMA_NO_NODE);
if (!IS_ERR(tsk)) {
wq->manager = get_task_struct(tsk);
return 0;
}
+ if (atomic_dec_and_test(&wq->worker_refs))
+ complete(&wq->worker_done);
+
return PTR_ERR(tsk);
}
/* Can only happen if manager creation fails after exec */
if (io_wq_fork_manager(wqe->wq) ||
test_bit(IO_WQ_BIT_EXIT, &wqe->wq->state)) {
- work->flags |= IO_WQ_WORK_CANCEL;
- wqe->wq->do_work(work);
+ io_run_cancel(work, wqe);
return;
}
init_completion(&wq->exited);
refcount_set(&wq->refs, 1);
- init_completion(&wq->worker_done);
- atomic_set(&wq->worker_refs, 0);
-
ret = io_wq_fork_manager(wq);
if (!ret)
return wq;
-
err:
io_wq_put_hash(data->hash);
cpuhp_state_remove_instance_nocalls(io_wq_online, &wq->cpuhp_node);
for_each_node(node) {
struct io_wqe *wqe = wq->wqes[node];
- WARN_ON_ONCE(!wq_list_empty(&wqe->work_list));
+ struct io_cb_cancel_data match = {
+ .fn = io_wq_work_match_all,
+ .cancel_all = true,
+ };
+ io_wqe_cancel_pending_work(wqe, &match);
kfree(wqe);
}
io_wq_put_hash(wq->hash);
#define INTERNAL_IO_WQ_H
#include <linux/refcount.h>
-#include <linux/io_uring.h>
struct io_wq;
IO_WQ_CANCEL_NOTFOUND, /* work not found */
};
+struct io_wq_work_node {
+ struct io_wq_work_node *next;
+};
+
+struct io_wq_work_list {
+ struct io_wq_work_node *first;
+ struct io_wq_work_node *last;
+};
+
static inline void wq_list_add_after(struct io_wq_work_node *node,
struct io_wq_work_node *pos,
struct io_wq_work_list *list)
struct io_wq_work {
struct io_wq_work_node list;
+ const struct cred *creds;
unsigned flags;
- unsigned short personality;
};
static inline struct io_wq_work *wq_next_work(struct io_wq_work *work)
#include <linux/task_work.h>
#include <linux/pagemap.h>
#include <linux/io_uring.h>
-#include <linux/freezer.h>
#define CREATE_TRACE_POINTS
#include <trace/events/io_uring.h>
struct io_sq_data {
refcount_t refs;
+ atomic_t park_pending;
struct mutex lock;
/* ctx's that are using this sqd */
struct list_head ctx_list;
- struct list_head ctx_new_list;
- struct mutex ctx_lock;
struct task_struct *thread;
struct wait_queue_head wait;
unsigned sq_thread_idle;
int sq_cpu;
pid_t task_pid;
+ pid_t task_tgid;
unsigned long state;
- struct completion startup;
- struct completion parked;
struct completion exited;
+ struct callback_head *park_task_work;
};
#define IO_IOPOLL_BATCH 8
unsigned int drain_next: 1;
unsigned int eventfd_async: 1;
unsigned int restricted: 1;
- unsigned int sqo_exec: 1;
/*
* Ring buffer of indices into array of io_uring_sqe, which is
/* Only used for accounting purposes */
struct mm_struct *mm_account;
+ const struct cred *sq_creds; /* cred used for __io_sq_thread() */
struct io_sq_data *sq_data; /* if using sq thread polling */
struct wait_queue_head sqo_sq_wait;
struct user_struct *user;
struct completion ref_comp;
- struct completion sq_thread_comp;
#if defined(CONFIG_UNIX)
struct socket *ring_sock;
#endif
- struct idr io_buffer_idr;
+ struct xarray io_buffers;
- struct idr personality_idr;
+ struct xarray personalities;
+ u32 pers_next;
struct {
unsigned cached_cq_tail;
/* Keep this last, we don't need it for the fast path */
struct work_struct exit_work;
+ struct list_head tctx_list;
+};
+
+struct io_uring_task {
+ /* submission side */
+ struct xarray xa;
+ struct wait_queue_head wait;
+ const struct io_ring_ctx *last;
+ struct io_wq *io_wq;
+ struct percpu_counter inflight;
+ atomic_t in_idle;
+ bool sqpoll;
+
+ spinlock_t task_lock;
+ struct io_wq_work_list task_list;
+ unsigned long task_state;
+ struct callback_head task_work;
};
/*
REQ_F_NO_FILE_TABLE_BIT,
REQ_F_LTIMEOUT_ACTIVE_BIT,
REQ_F_COMPLETE_INLINE_BIT,
+ REQ_F_REISSUE_BIT,
/* not a real bit, just to check we're not overflowing the space */
__REQ_F_LAST_BIT,
REQ_F_LTIMEOUT_ACTIVE = BIT(REQ_F_LTIMEOUT_ACTIVE_BIT),
/* completion is deferred through io_comp_state */
REQ_F_COMPLETE_INLINE = BIT(REQ_F_COMPLETE_INLINE_BIT),
+ /* caller should reissue async */
+ REQ_F_REISSUE = BIT(REQ_F_REISSUE_BIT),
};
struct async_poll {
struct io_wq_work work;
};
+struct io_tctx_node {
+ struct list_head ctx_node;
+ struct task_struct *task;
+ struct io_ring_ctx *ctx;
+};
+
struct io_defer_entry {
struct list_head list;
struct io_kiocb *req;
[IORING_OP_UNLINKAT] = {},
};
+static bool io_disarm_next(struct io_kiocb *req);
+static void io_uring_del_task_file(unsigned long index);
static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
struct task_struct *task,
struct files_struct *files);
io_for_each_link(req, head) {
if (req->flags & REQ_F_INFLIGHT)
return true;
- if (req->task->files == files)
- return true;
}
return false;
}
init_waitqueue_head(&ctx->cq_wait);
INIT_LIST_HEAD(&ctx->cq_overflow_list);
init_completion(&ctx->ref_comp);
- init_completion(&ctx->sq_thread_comp);
- idr_init(&ctx->io_buffer_idr);
- idr_init(&ctx->personality_idr);
+ xa_init_flags(&ctx->io_buffers, XA_FLAGS_ALLOC1);
+ xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1);
mutex_init(&ctx->uring_lock);
init_waitqueue_head(&ctx->wait);
spin_lock_init(&ctx->completion_lock);
INIT_LIST_HEAD(&ctx->rsrc_ref_list);
INIT_DELAYED_WORK(&ctx->rsrc_put_work, io_rsrc_put_work);
init_llist_head(&ctx->rsrc_put_llist);
+ INIT_LIST_HEAD(&ctx->tctx_list);
INIT_LIST_HEAD(&ctx->submit_state.comp.free_list);
INIT_LIST_HEAD(&ctx->submit_state.comp.locked_free_list);
return ctx;
const struct io_op_def *def = &io_op_defs[req->opcode];
struct io_ring_ctx *ctx = req->ctx;
+ if (!req->work.creds)
+ req->work.creds = get_current_cred();
+
if (req->flags & REQ_F_FORCE_ASYNC)
req->work.flags |= IO_WQ_WORK_CONCURRENT;
if (req->flags & REQ_F_ISREG) {
if (def->hash_reg_file || (ctx->flags & IORING_SETUP_IOPOLL))
io_wq_hash_work(&req->work, file_inode(req->file));
- } else {
+ } else if (!req->file || !S_ISBLK(file_inode(req->file)->i_mode)) {
if (def->unbound_nonreg_file)
req->work.flags |= IO_WQ_WORK_UNBOUND;
}
BUG_ON(!tctx);
BUG_ON(!tctx->io_wq);
- trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req,
- &req->work, req->flags);
/* init ->work of the whole link before punting */
io_prep_async_link(req);
+ trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req,
+ &req->work, req->flags);
io_wq_enqueue(tctx->io_wq, &req->work);
if (link)
io_queue_linked_timeout(link);
}
-static void io_kill_timeout(struct io_kiocb *req)
+static void io_kill_timeout(struct io_kiocb *req, int status)
{
struct io_timeout_data *io = req->async_data;
int ret;
atomic_set(&req->ctx->cq_timeouts,
atomic_read(&req->ctx->cq_timeouts) + 1);
list_del_init(&req->timeout.list);
- io_cqring_fill_event(req, 0);
+ io_cqring_fill_event(req, status);
io_put_req_deferred(req, 1);
}
}
-/*
- * Returns true if we found and killed one or more timeouts
- */
-static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk,
- struct files_struct *files)
-{
- struct io_kiocb *req, *tmp;
- int canceled = 0;
-
- spin_lock_irq(&ctx->completion_lock);
- list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) {
- if (io_match_task(req, tsk, files)) {
- io_kill_timeout(req);
- canceled++;
- }
- }
- spin_unlock_irq(&ctx->completion_lock);
- return canceled != 0;
-}
-
static void __io_queue_deferred(struct io_ring_ctx *ctx)
{
do {
break;
list_del_init(&req->timeout.list);
- io_kill_timeout(req);
+ io_kill_timeout(req, 0);
} while (!list_empty(&ctx->timeout_list));
ctx->cq_last_tm_flush = seq;
__io_cqring_fill_event(req, res, 0);
}
-static inline void io_req_complete_post(struct io_kiocb *req, long res,
- unsigned int cflags)
+static void io_req_complete_post(struct io_kiocb *req, long res,
+ unsigned int cflags)
{
struct io_ring_ctx *ctx = req->ctx;
unsigned long flags;
spin_lock_irqsave(&ctx->completion_lock, flags);
__io_cqring_fill_event(req, res, cflags);
- io_commit_cqring(ctx);
/*
* If we're the last reference to this request, add to our locked
* free_list cache.
if (refcount_dec_and_test(&req->refs)) {
struct io_comp_state *cs = &ctx->submit_state.comp;
+ if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) {
+ if (req->flags & (REQ_F_LINK_TIMEOUT | REQ_F_FAIL_LINK))
+ io_disarm_next(req);
+ if (req->link) {
+ io_req_task_queue(req->link);
+ req->link = NULL;
+ }
+ }
io_dismantle_req(req);
io_put_task(req->task, 1);
list_add(&req->compl.list, &cs->locked_free_list);
cs->locked_free_nr++;
- } else
- req = NULL;
+ } else {
+ if (!percpu_ref_tryget(&ctx->refs))
+ req = NULL;
+ }
+ io_commit_cqring(ctx);
spin_unlock_irqrestore(&ctx->completion_lock, flags);
- io_cqring_ev_posted(ctx);
if (req) {
- io_queue_next(req);
+ io_cqring_ev_posted(ctx);
percpu_ref_put(&ctx->refs);
}
}
io_put_file(req, req->file, (req->flags & REQ_F_FIXED_FILE));
if (req->fixed_rsrc_refs)
percpu_ref_put(req->fixed_rsrc_refs);
+ if (req->work.creds) {
+ put_cred(req->work.creds);
+ req->work.creds = NULL;
+ }
if (req->flags & REQ_F_INFLIGHT) {
struct io_ring_ctx *ctx = req->ctx;
nxt->link = NULL;
}
-static void io_kill_linked_timeout(struct io_kiocb *req)
+static bool io_kill_linked_timeout(struct io_kiocb *req)
+ __must_hold(&req->ctx->completion_lock)
{
- struct io_ring_ctx *ctx = req->ctx;
- struct io_kiocb *link;
+ struct io_kiocb *link = req->link;
bool cancelled = false;
- unsigned long flags;
-
- spin_lock_irqsave(&ctx->completion_lock, flags);
- link = req->link;
/*
* Can happen if a linked timeout fired and link had been like
ret = hrtimer_try_to_cancel(&io->timer);
if (ret != -1) {
io_cqring_fill_event(link, -ECANCELED);
- io_commit_cqring(ctx);
+ io_put_req_deferred(link, 1);
cancelled = true;
}
}
req->flags &= ~REQ_F_LINK_TIMEOUT;
- spin_unlock_irqrestore(&ctx->completion_lock, flags);
-
- if (cancelled) {
- io_cqring_ev_posted(ctx);
- io_put_req(link);
- }
+ return cancelled;
}
-
static void io_fail_links(struct io_kiocb *req)
+ __must_hold(&req->ctx->completion_lock)
{
- struct io_kiocb *link, *nxt;
- struct io_ring_ctx *ctx = req->ctx;
- unsigned long flags;
+ struct io_kiocb *nxt, *link = req->link;
- spin_lock_irqsave(&ctx->completion_lock, flags);
- link = req->link;
req->link = NULL;
-
while (link) {
nxt = link->link;
link->link = NULL;
trace_io_uring_fail_link(req, link);
io_cqring_fill_event(link, -ECANCELED);
-
io_put_req_deferred(link, 2);
link = nxt;
}
- io_commit_cqring(ctx);
- spin_unlock_irqrestore(&ctx->completion_lock, flags);
+}
- io_cqring_ev_posted(ctx);
+static bool io_disarm_next(struct io_kiocb *req)
+ __must_hold(&req->ctx->completion_lock)
+{
+ bool posted = false;
+
+ if (likely(req->flags & REQ_F_LINK_TIMEOUT))
+ posted = io_kill_linked_timeout(req);
+ if (unlikely(req->flags & REQ_F_FAIL_LINK)) {
+ posted |= (req->link != NULL);
+ io_fail_links(req);
+ }
+ return posted;
}
static struct io_kiocb *__io_req_find_next(struct io_kiocb *req)
{
- if (req->flags & REQ_F_LINK_TIMEOUT)
- io_kill_linked_timeout(req);
+ struct io_kiocb *nxt;
/*
* If LINK is set, we have dependent requests in this chain. If we
* dependencies to the next request. In case of failure, fail the rest
* of the chain.
*/
- if (likely(!(req->flags & REQ_F_FAIL_LINK))) {
- struct io_kiocb *nxt = req->link;
+ if (req->flags & (REQ_F_LINK_TIMEOUT | REQ_F_FAIL_LINK)) {
+ struct io_ring_ctx *ctx = req->ctx;
+ unsigned long flags;
+ bool posted;
- req->link = NULL;
- return nxt;
+ spin_lock_irqsave(&ctx->completion_lock, flags);
+ posted = io_disarm_next(req);
+ if (posted)
+ io_commit_cqring(req->ctx);
+ spin_unlock_irqrestore(&ctx->completion_lock, flags);
+ if (posted)
+ io_cqring_ev_posted(ctx);
}
- io_fail_links(req);
- return NULL;
+ nxt = req->link;
+ req->link = NULL;
+ return nxt;
}
static inline struct io_kiocb *io_req_find_next(struct io_kiocb *req)
return ret;
}
-static void io_req_task_work_add_fallback(struct io_kiocb *req,
- task_work_func_t cb)
+static bool io_run_task_work_head(struct callback_head **work_head)
+{
+ struct callback_head *work, *next;
+ bool executed = false;
+
+ do {
+ work = xchg(work_head, NULL);
+ if (!work)
+ break;
+
+ do {
+ next = work->next;
+ work->func(work);
+ work = next;
+ cond_resched();
+ } while (work);
+ executed = true;
+ } while (1);
+
+ return executed;
+}
+
+static void io_task_work_add_head(struct callback_head **work_head,
+ struct callback_head *task_work)
{
- struct io_ring_ctx *ctx = req->ctx;
struct callback_head *head;
- init_task_work(&req->task_work, cb);
do {
- head = READ_ONCE(ctx->exit_task_work);
- req->task_work.next = head;
- } while (cmpxchg(&ctx->exit_task_work, head, &req->task_work) != head);
+ head = READ_ONCE(*work_head);
+ task_work->next = head;
+ } while (cmpxchg(work_head, head, task_work) != head);
+}
+
+static void io_req_task_work_add_fallback(struct io_kiocb *req,
+ task_work_func_t cb)
+{
+ init_task_work(&req->task_work, cb);
+ io_task_work_add_head(&req->ctx->exit_task_work, &req->task_work);
}
static void __io_req_task_cancel(struct io_kiocb *req, int error)
return false;
return true;
}
+#else
+static bool io_rw_should_reissue(struct io_kiocb *req)
+{
+ return false;
+}
#endif
static bool io_rw_reissue(struct io_kiocb *req)
{
int cflags = 0;
- if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_reissue(req))
+ if (req->rw.kiocb.ki_flags & IOCB_WRITE)
+ kiocb_end_write(req);
+ if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_should_reissue(req)) {
+ req->flags |= REQ_F_REISSUE;
return;
+ }
if (res != req->result)
req_set_fail_links(req);
-
- if (req->rw.kiocb.ki_flags & IOCB_WRITE)
- kiocb_end_write(req);
if (req->flags & REQ_F_BUFFER_SELECTED)
cflags = io_put_rw_kbuf(req);
__io_req_complete(req, issue_flags, res, cflags);
{
struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb);
struct io_async_rw *io = req->async_data;
+ bool check_reissue = kiocb->ki_complete == io_complete_rw;
/* add previously done IO, if any */
if (io && io->bytes_done > 0) {
__io_complete_rw(req, ret, 0, issue_flags);
else
io_rw_done(kiocb, ret);
+
+ if (check_reissue && req->flags & REQ_F_REISSUE) {
+ req->flags &= ~REQ_F_REISSUE;
+ if (!io_rw_reissue(req)) {
+ int cflags = 0;
+
+ req_set_fail_links(req);
+ if (req->flags & REQ_F_BUFFER_SELECTED)
+ cflags = io_put_rw_kbuf(req);
+ __io_req_complete(req, issue_flags, ret, cflags);
+ }
+ }
}
static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter)
lockdep_assert_held(&req->ctx->uring_lock);
- head = idr_find(&req->ctx->io_buffer_idr, bgid);
+ head = xa_load(&req->ctx->io_buffers, bgid);
if (head) {
if (!list_empty(&head->list)) {
kbuf = list_last_entry(&head->list, struct io_buffer,
list_del(&kbuf->list);
} else {
kbuf = head;
- idr_remove(&req->ctx->io_buffer_idr, bgid);
+ xa_erase(&req->ctx->io_buffers, bgid);
}
if (*len > kbuf->len)
*len = kbuf->len;
ret = io_iter_do_read(req, iter);
- if (ret == -EIOCBQUEUED) {
- if (req->async_data)
- iov_iter_revert(iter, io_size - iov_iter_count(iter));
- goto out_free;
- } else if (ret == -EAGAIN) {
+ if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) {
+ req->flags &= ~REQ_F_REISSUE;
/* IOPOLL retry should happen for io-wq threads */
if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL))
goto done;
/* some cases will consume bytes even on error returns */
iov_iter_revert(iter, io_size - iov_iter_count(iter));
ret = 0;
+ } else if (ret == -EIOCBQUEUED) {
+ goto out_free;
} else if (ret <= 0 || ret == io_size || !force_nonblock ||
(req->flags & REQ_F_NOWAIT) || !(req->flags & REQ_F_ISREG)) {
/* read all, failed, already did sync or don't want to retry */
else
ret2 = -EINVAL;
+ if (req->flags & REQ_F_REISSUE) {
+ req->flags &= ~REQ_F_REISSUE;
+ ret2 = -EAGAIN;
+ }
+
/*
* Raw bdev writes will return -EOPNOTSUPP for IOCB_NOWAIT. Just
* retry them without IOCB_NOWAIT.
/* no retry on NONBLOCK nor RWF_NOWAIT */
if (ret2 == -EAGAIN && (req->flags & REQ_F_NOWAIT))
goto done;
- if (ret2 == -EIOCBQUEUED && req->async_data)
- iov_iter_revert(iter, io_size - iov_iter_count(iter));
if (!force_nonblock || ret2 != -EAGAIN) {
/* IOPOLL retry should happen for io-wq threads */
if ((req->ctx->flags & IORING_SETUP_IOPOLL) && ret2 == -EAGAIN)
}
i++;
kfree(buf);
- idr_remove(&ctx->io_buffer_idr, bgid);
+ xa_erase(&ctx->io_buffers, bgid);
return i;
}
lockdep_assert_held(&ctx->uring_lock);
ret = -ENOENT;
- head = idr_find(&ctx->io_buffer_idr, p->bgid);
+ head = xa_load(&ctx->io_buffers, p->bgid);
if (head)
ret = __io_remove_buffers(ctx, head, p->bgid, p->nbufs);
if (ret < 0)
static int io_provide_buffers_prep(struct io_kiocb *req,
const struct io_uring_sqe *sqe)
{
+ unsigned long size;
struct io_provide_buf *p = &req->pbuf;
u64 tmp;
p->addr = READ_ONCE(sqe->addr);
p->len = READ_ONCE(sqe->len);
- if (!access_ok(u64_to_user_ptr(p->addr), (p->len * p->nbufs)))
+ size = (unsigned long)p->len * p->nbufs;
+ if (!access_ok(u64_to_user_ptr(p->addr), size))
return -EFAULT;
p->bgid = READ_ONCE(sqe->buf_group);
lockdep_assert_held(&ctx->uring_lock);
- list = head = idr_find(&ctx->io_buffer_idr, p->bgid);
+ list = head = xa_load(&ctx->io_buffers, p->bgid);
ret = io_add_buffers(p, &head);
- if (ret < 0)
- goto out;
-
- if (!list) {
- ret = idr_alloc(&ctx->io_buffer_idr, head, p->bgid, p->bgid + 1,
- GFP_KERNEL);
- if (ret < 0) {
+ if (ret >= 0 && !list) {
+ ret = xa_insert(&ctx->io_buffers, p->bgid, head, GFP_KERNEL);
+ if (ret < 0)
__io_remove_buffers(ctx, head, p->bgid, -1U);
- goto out;
- }
}
-out:
if (ret < 0)
req_set_fail_links(req);
struct io_async_msghdr iomsg, *kmsg;
struct socket *sock;
unsigned flags;
+ int min_ret = 0;
int ret;
sock = sock_from_file(req->file);
kmsg = &iomsg;
}
- flags = req->sr_msg.msg_flags;
+ flags = req->sr_msg.msg_flags | MSG_NOSIGNAL;
if (flags & MSG_DONTWAIT)
req->flags |= REQ_F_NOWAIT;
else if (issue_flags & IO_URING_F_NONBLOCK)
flags |= MSG_DONTWAIT;
+ if (flags & MSG_WAITALL)
+ min_ret = iov_iter_count(&kmsg->msg.msg_iter);
+
ret = __sys_sendmsg_sock(sock, &kmsg->msg, flags);
if ((issue_flags & IO_URING_F_NONBLOCK) && ret == -EAGAIN)
return io_setup_async_msg(req, kmsg);
if (kmsg->free_iov)
kfree(kmsg->free_iov);
req->flags &= ~REQ_F_NEED_CLEANUP;
- if (ret < 0)
+ if (ret < min_ret)
req_set_fail_links(req);
__io_req_complete(req, issue_flags, ret, 0);
return 0;
struct iovec iov;
struct socket *sock;
unsigned flags;
+ int min_ret = 0;
int ret;
sock = sock_from_file(req->file);
msg.msg_controllen = 0;
msg.msg_namelen = 0;
- flags = req->sr_msg.msg_flags;
+ flags = req->sr_msg.msg_flags | MSG_NOSIGNAL;
if (flags & MSG_DONTWAIT)
req->flags |= REQ_F_NOWAIT;
else if (issue_flags & IO_URING_F_NONBLOCK)
flags |= MSG_DONTWAIT;
+ if (flags & MSG_WAITALL)
+ min_ret = iov_iter_count(&msg.msg_iter);
+
msg.msg_flags = flags;
ret = sock_sendmsg(sock, &msg);
if ((issue_flags & IO_URING_F_NONBLOCK) && ret == -EAGAIN)
if (ret == -ERESTARTSYS)
ret = -EINTR;
- if (ret < 0)
+ if (ret < min_ret)
req_set_fail_links(req);
__io_req_complete(req, issue_flags, ret, 0);
return 0;
struct socket *sock;
struct io_buffer *kbuf;
unsigned flags;
+ int min_ret = 0;
int ret, cflags = 0;
bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
1, req->sr_msg.len);
}
- flags = req->sr_msg.msg_flags;
+ flags = req->sr_msg.msg_flags | MSG_NOSIGNAL;
if (flags & MSG_DONTWAIT)
req->flags |= REQ_F_NOWAIT;
else if (force_nonblock)
flags |= MSG_DONTWAIT;
+ if (flags & MSG_WAITALL)
+ min_ret = iov_iter_count(&kmsg->msg.msg_iter);
+
ret = __sys_recvmsg_sock(sock, &kmsg->msg, req->sr_msg.umsg,
kmsg->uaddr, flags);
if (force_nonblock && ret == -EAGAIN)
if (kmsg->free_iov)
kfree(kmsg->free_iov);
req->flags &= ~REQ_F_NEED_CLEANUP;
- if (ret < 0)
+ if (ret < min_ret || ((flags & MSG_WAITALL) && (kmsg->msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))))
req_set_fail_links(req);
__io_req_complete(req, issue_flags, ret, cflags);
return 0;
struct socket *sock;
struct iovec iov;
unsigned flags;
+ int min_ret = 0;
int ret, cflags = 0;
bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
msg.msg_iocb = NULL;
msg.msg_flags = 0;
- flags = req->sr_msg.msg_flags;
+ flags = req->sr_msg.msg_flags | MSG_NOSIGNAL;
if (flags & MSG_DONTWAIT)
req->flags |= REQ_F_NOWAIT;
else if (force_nonblock)
flags |= MSG_DONTWAIT;
+ if (flags & MSG_WAITALL)
+ min_ret = iov_iter_count(&msg.msg_iter);
+
ret = sock_recvmsg(sock, &msg, flags);
if (force_nonblock && ret == -EAGAIN)
return -EAGAIN;
out_free:
if (req->flags & REQ_F_BUFFER_SELECTED)
cflags = io_put_recv_kbuf(req);
- if (ret < 0)
+ if (ret < min_ret || ((flags & MSG_WAITALL) && (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC))))
req_set_fail_links(req);
__io_req_complete(req, issue_flags, ret, cflags);
return 0;
ret = -ENOMEM;
goto out;
}
- io = req->async_data;
memcpy(req->async_data, &__io, sizeof(__io));
return -EAGAIN;
}
data->mode = io_translate_timeout_mode(flags);
hrtimer_init(&data->timer, CLOCK_MONOTONIC, data->mode);
- io_req_track_inflight(req);
+ if (is_timeout_link)
+ io_req_track_inflight(req);
return 0;
}
return 0;
}
+struct io_cancel_data {
+ struct io_ring_ctx *ctx;
+ u64 user_data;
+};
+
static bool io_cancel_cb(struct io_wq_work *work, void *data)
{
struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+ struct io_cancel_data *cd = data;
- return req->user_data == (unsigned long) data;
+ return req->ctx == cd->ctx && req->user_data == cd->user_data;
}
-static int io_async_cancel_one(struct io_uring_task *tctx, void *sqe_addr)
+static int io_async_cancel_one(struct io_uring_task *tctx, u64 user_data,
+ struct io_ring_ctx *ctx)
{
+ struct io_cancel_data data = { .ctx = ctx, .user_data = user_data, };
enum io_wq_cancel cancel_ret;
int ret = 0;
- if (!tctx->io_wq)
+ if (!tctx || !tctx->io_wq)
return -ENOENT;
- cancel_ret = io_wq_cancel_cb(tctx->io_wq, io_cancel_cb, sqe_addr, false);
+ cancel_ret = io_wq_cancel_cb(tctx->io_wq, io_cancel_cb, &data, false);
switch (cancel_ret) {
case IO_WQ_CANCEL_OK:
ret = 0;
unsigned long flags;
int ret;
- ret = io_async_cancel_one(req->task->io_uring,
- (void *) (unsigned long) sqe_addr);
+ ret = io_async_cancel_one(req->task->io_uring, sqe_addr, ctx);
if (ret != -ENOENT) {
spin_lock_irqsave(&ctx->completion_lock, flags);
goto done;
static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_ring_ctx *ctx = req->ctx;
+ u64 sqe_addr = req->cancel.addr;
+ struct io_tctx_node *node;
+ int ret;
- io_async_find_and_cancel(ctx, req, req->cancel.addr, 0);
+ /* tasks should wait for their io-wq threads, so safe w/o sync */
+ ret = io_async_cancel_one(req->task->io_uring, sqe_addr, ctx);
+ spin_lock_irq(&ctx->completion_lock);
+ if (ret != -ENOENT)
+ goto done;
+ ret = io_timeout_cancel(ctx, sqe_addr);
+ if (ret != -ENOENT)
+ goto done;
+ ret = io_poll_cancel(ctx, sqe_addr);
+ if (ret != -ENOENT)
+ goto done;
+ spin_unlock_irq(&ctx->completion_lock);
+
+ /* slow path, try all io-wq's */
+ io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK));
+ ret = -ENOENT;
+ list_for_each_entry(node, &ctx->tctx_list, ctx_node) {
+ struct io_uring_task *tctx = node->task->io_uring;
+
+ if (!tctx || !tctx->io_wq)
+ continue;
+ ret = io_async_cancel_one(tctx, req->cancel.addr, ctx);
+ if (ret != -ENOENT)
+ break;
+ }
+ io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK));
+
+ spin_lock_irq(&ctx->completion_lock);
+done:
+ io_cqring_fill_event(req, ret);
+ io_commit_cqring(ctx);
+ spin_unlock_irq(&ctx->completion_lock);
+ io_cqring_ev_posted(ctx);
+
+ if (ret < 0)
+ req_set_fail_links(req);
+ io_put_req(req);
return 0;
}
const struct cred *creds = NULL;
int ret;
- if (req->work.personality) {
- const struct cred *new_creds;
-
- if (!(issue_flags & IO_URING_F_NONBLOCK))
- mutex_lock(&ctx->uring_lock);
- new_creds = idr_find(&ctx->personality_idr, req->work.personality);
- if (!(issue_flags & IO_URING_F_NONBLOCK))
- mutex_unlock(&ctx->uring_lock);
- if (!new_creds)
- return -EINVAL;
- creds = override_creds(new_creds);
- }
+ if (req->work.creds && req->work.creds != current_cred())
+ creds = override_creds(req->work.creds);
switch (req->opcode) {
case IORING_OP_NOP:
spin_unlock_irqrestore(&ctx->completion_lock, flags);
if (prev) {
- req_set_fail_links(prev);
io_async_find_and_cancel(ctx, req, prev->user_data, -ETIME);
io_put_req_deferred(prev, 1);
} else {
{
struct io_submit_state *state;
unsigned int sqe_flags;
- int ret = 0;
+ int personality, ret = 0;
req->opcode = READ_ONCE(sqe->opcode);
/* same numerical values with corresponding REQ_F_*, safe to copy */
refcount_set(&req->refs, 2);
req->task = current;
req->result = 0;
+ req->work.list.next = NULL;
+ req->work.creds = NULL;
+ req->work.flags = 0;
/* enforce forwards compatibility on users */
if (unlikely(sqe_flags & ~SQE_VALID_FLAGS)) {
!io_op_defs[req->opcode].buffer_select)
return -EOPNOTSUPP;
- req->work.list.next = NULL;
- req->work.flags = 0;
- req->work.personality = READ_ONCE(sqe->personality);
+ personality = READ_ONCE(sqe->personality);
+ if (personality) {
+ req->work.creds = xa_load(&ctx->personalities, personality);
+ if (!req->work.creds)
+ return -EINVAL;
+ get_cred(req->work.creds);
+ }
state = &ctx->submit_state;
/*
ret = io_init_req(ctx, req, sqe);
if (unlikely(ret)) {
fail_req:
- io_put_req(req);
- io_req_complete(req, ret);
if (link->head) {
/* fail even hard links since we don't submit */
link->head->flags |= REQ_F_FAIL_LINK;
io_req_complete(link->head, -ECANCELED);
link->head = NULL;
}
+ io_put_req(req);
+ io_req_complete(req, ret);
return ret;
}
ret = io_req_prep(req, sqe);
if (!list_empty(&ctx->iopoll_list))
io_do_iopoll(ctx, &nr_events, 0);
- if (to_submit && likely(!percpu_ref_is_dying(&ctx->refs)))
+ if (to_submit && likely(!percpu_ref_is_dying(&ctx->refs)) &&
+ !(ctx->flags & IORING_SETUP_R_DISABLED))
ret = io_submit_sqes(ctx, to_submit);
mutex_unlock(&ctx->uring_lock);
}
sqd->sq_thread_idle = sq_thread_idle;
}
-static void io_sqd_init_new(struct io_sq_data *sqd)
-{
- struct io_ring_ctx *ctx;
-
- while (!list_empty(&sqd->ctx_new_list)) {
- ctx = list_first_entry(&sqd->ctx_new_list, struct io_ring_ctx, sqd_list);
- list_move_tail(&ctx->sqd_list, &sqd->ctx_list);
- complete(&ctx->sq_thread_comp);
- }
-
- io_sqd_update_thread_idle(sqd);
-}
-
-static bool io_sq_thread_should_stop(struct io_sq_data *sqd)
-{
- return test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
-}
-
-static bool io_sq_thread_should_park(struct io_sq_data *sqd)
-{
- return test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
-}
-
-static void io_sq_thread_parkme(struct io_sq_data *sqd)
-{
- for (;;) {
- /*
- * TASK_PARKED is a special state; we must serialize against
- * possible pending wakeups to avoid store-store collisions on
- * task->state.
- *
- * Such a collision might possibly result in the task state
- * changin from TASK_PARKED and us failing the
- * wait_task_inactive() in kthread_park().
- */
- set_special_state(TASK_PARKED);
- if (!test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state))
- break;
-
- /*
- * Thread is going to call schedule(), do not preempt it,
- * or the caller of kthread_park() may spend more time in
- * wait_task_inactive().
- */
- preempt_disable();
- complete(&sqd->parked);
- schedule_preempt_disabled();
- preempt_enable();
- }
- __set_current_state(TASK_RUNNING);
-}
-
static int io_sq_thread(void *data)
{
struct io_sq_data *sqd = data;
char buf[TASK_COMM_LEN];
DEFINE_WAIT(wait);
- sprintf(buf, "iou-sqp-%d", sqd->task_pid);
+ snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid);
set_task_comm(current, buf);
current->pf_io_worker = NULL;
set_cpus_allowed_ptr(current, cpu_online_mask);
current->flags |= PF_NO_SETAFFINITY;
- wait_for_completion(&sqd->startup);
+ mutex_lock(&sqd->lock);
+ /* a user may had exited before the thread started */
+ io_run_task_work_head(&sqd->park_task_work);
- while (!io_sq_thread_should_stop(sqd)) {
+ while (!test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state)) {
int ret;
bool cap_entries, sqt_spin, needs_sched;
- /*
- * Any changes to the sqd lists are synchronized through the
- * thread parking. This synchronizes the thread vs users,
- * the users are synchronized on the sqd->ctx_lock.
- */
- if (io_sq_thread_should_park(sqd)) {
- io_sq_thread_parkme(sqd);
- continue;
- }
- if (unlikely(!list_empty(&sqd->ctx_new_list))) {
- io_sqd_init_new(sqd);
+ if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state) ||
+ signal_pending(current)) {
+ bool did_sig = false;
+
+ mutex_unlock(&sqd->lock);
+ if (signal_pending(current)) {
+ struct ksignal ksig;
+
+ did_sig = get_signal(&ksig);
+ }
+ cond_resched();
+ mutex_lock(&sqd->lock);
+ io_run_task_work();
+ io_run_task_work_head(&sqd->park_task_work);
+ if (did_sig)
+ break;
timeout = jiffies + sqd->sq_thread_idle;
+ continue;
}
- if (fatal_signal_pending(current))
- break;
sqt_spin = false;
cap_entries = !list_is_singular(&sqd->ctx_list);
list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
+ const struct cred *creds = NULL;
+
+ if (ctx->sq_creds != current_cred())
+ creds = override_creds(ctx->sq_creds);
ret = __io_sq_thread(ctx, cap_entries);
+ if (creds)
+ revert_creds(creds);
if (!sqt_spin && (ret > 0 || !list_empty(&ctx->iopoll_list)))
sqt_spin = true;
}
}
}
- if (needs_sched && !io_sq_thread_should_park(sqd)) {
+ if (needs_sched && !test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state)) {
list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
io_ring_set_wakeup_flag(ctx);
+ mutex_unlock(&sqd->lock);
schedule();
- try_to_freeze();
+ mutex_lock(&sqd->lock);
list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
io_ring_clear_wakeup_flag(ctx);
}
finish_wait(&sqd->wait, &wait);
+ io_run_task_work_head(&sqd->park_task_work);
timeout = jiffies + sqd->sq_thread_idle;
}
list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
io_uring_cancel_sqpoll(ctx);
-
- io_run_task_work();
-
- /*
- * Ensure that we park properly if racing with someone trying to park
- * while we're exiting. If we fail to grab the lock, check park and
- * park if necessary. The ordering with the park bit and the lock
- * ensures that we catch this reliably.
- */
- if (!mutex_trylock(&sqd->lock)) {
- if (io_sq_thread_should_park(sqd))
- io_sq_thread_parkme(sqd);
- mutex_lock(&sqd->lock);
- }
-
sqd->thread = NULL;
- list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
- ctx->sqo_exec = 1;
+ list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
io_ring_set_wakeup_flag(ctx);
- }
+ mutex_unlock(&sqd->lock);
+ io_run_task_work();
+ io_run_task_work_head(&sqd->park_task_work);
complete(&sqd->exited);
- mutex_unlock(&sqd->lock);
do_exit(0);
}
return 1;
if (!signal_pending(current))
return 0;
- if (test_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL))
+ if (test_thread_flag(TIF_NOTIFY_SIGNAL))
return -ERESTARTSYS;
return -EINTR;
}
static void io_sq_thread_unpark(struct io_sq_data *sqd)
__releases(&sqd->lock)
{
- if (sqd->thread == current)
- return;
+ WARN_ON_ONCE(sqd->thread == current);
+
+ /*
+ * Do the dance but not conditional clear_bit() because it'd race with
+ * other threads incrementing park_pending and setting the bit.
+ */
clear_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
- if (sqd->thread)
- wake_up_state(sqd->thread, TASK_PARKED);
+ if (atomic_dec_return(&sqd->park_pending))
+ set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
mutex_unlock(&sqd->lock);
}
static void io_sq_thread_park(struct io_sq_data *sqd)
__acquires(&sqd->lock)
{
- if (sqd->thread == current)
- return;
+ WARN_ON_ONCE(sqd->thread == current);
+
+ atomic_inc(&sqd->park_pending);
set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
mutex_lock(&sqd->lock);
- if (sqd->thread) {
+ if (sqd->thread)
wake_up_process(sqd->thread);
- wait_for_completion(&sqd->parked);
- }
}
static void io_sq_thread_stop(struct io_sq_data *sqd)
{
- if (test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state))
- return;
+ WARN_ON_ONCE(sqd->thread == current);
+
mutex_lock(&sqd->lock);
- if (sqd->thread) {
- set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
- WARN_ON_ONCE(test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state));
+ set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
+ if (sqd->thread)
wake_up_process(sqd->thread);
- mutex_unlock(&sqd->lock);
- wait_for_completion(&sqd->exited);
- WARN_ON_ONCE(sqd->thread);
- } else {
- mutex_unlock(&sqd->lock);
- }
+ mutex_unlock(&sqd->lock);
+ wait_for_completion(&sqd->exited);
}
static void io_put_sq_data(struct io_sq_data *sqd)
{
if (refcount_dec_and_test(&sqd->refs)) {
+ WARN_ON_ONCE(atomic_read(&sqd->park_pending));
+
io_sq_thread_stop(sqd);
kfree(sqd);
}
struct io_sq_data *sqd = ctx->sq_data;
if (sqd) {
- complete(&sqd->startup);
- if (sqd->thread) {
- wait_for_completion(&ctx->sq_thread_comp);
- io_sq_thread_park(sqd);
- }
-
- mutex_lock(&sqd->ctx_lock);
- list_del(&ctx->sqd_list);
+ io_sq_thread_park(sqd);
+ list_del_init(&ctx->sqd_list);
io_sqd_update_thread_idle(sqd);
- mutex_unlock(&sqd->ctx_lock);
-
- if (sqd->thread)
- io_sq_thread_unpark(sqd);
+ io_sq_thread_unpark(sqd);
io_put_sq_data(sqd);
ctx->sq_data = NULL;
+ if (ctx->sq_creds)
+ put_cred(ctx->sq_creds);
}
}
fdput(f);
return ERR_PTR(-EINVAL);
}
+ if (sqd->task_tgid != current->tgid) {
+ fdput(f);
+ return ERR_PTR(-EPERM);
+ }
refcount_inc(&sqd->refs);
fdput(f);
return sqd;
}
-static struct io_sq_data *io_get_sq_data(struct io_uring_params *p)
+static struct io_sq_data *io_get_sq_data(struct io_uring_params *p,
+ bool *attached)
{
struct io_sq_data *sqd;
- if (p->flags & IORING_SETUP_ATTACH_WQ)
- return io_attach_sq_data(p);
+ *attached = false;
+ if (p->flags & IORING_SETUP_ATTACH_WQ) {
+ sqd = io_attach_sq_data(p);
+ if (!IS_ERR(sqd)) {
+ *attached = true;
+ return sqd;
+ }
+ /* fall through for EPERM case, setup new sqd/task */
+ if (PTR_ERR(sqd) != -EPERM)
+ return sqd;
+ }
sqd = kzalloc(sizeof(*sqd), GFP_KERNEL);
if (!sqd)
return ERR_PTR(-ENOMEM);
+ atomic_set(&sqd->park_pending, 0);
refcount_set(&sqd->refs, 1);
INIT_LIST_HEAD(&sqd->ctx_list);
- INIT_LIST_HEAD(&sqd->ctx_new_list);
- mutex_init(&sqd->ctx_lock);
mutex_init(&sqd->lock);
init_waitqueue_head(&sqd->wait);
- init_completion(&sqd->startup);
- init_completion(&sqd->parked);
init_completion(&sqd->exited);
return sqd;
}
init_waitqueue_head(&tctx->wait);
tctx->last = NULL;
atomic_set(&tctx->in_idle, 0);
- tctx->sqpoll = false;
task->io_uring = tctx;
spin_lock_init(&tctx->task_lock);
INIT_WQ_LIST(&tctx->task_list);
tsk->io_uring = NULL;
}
-static int io_sq_thread_fork(struct io_sq_data *sqd, struct io_ring_ctx *ctx)
-{
- struct task_struct *tsk;
- int ret;
-
- clear_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
- reinit_completion(&sqd->parked);
- ctx->sqo_exec = 0;
- sqd->task_pid = current->pid;
- tsk = create_io_thread(io_sq_thread, sqd, NUMA_NO_NODE);
- if (IS_ERR(tsk))
- return PTR_ERR(tsk);
- ret = io_uring_alloc_task_context(tsk, ctx);
- if (ret)
- set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
- sqd->thread = tsk;
- wake_up_new_task(tsk);
- return ret;
-}
-
static int io_sq_offload_create(struct io_ring_ctx *ctx,
struct io_uring_params *p)
{
if (ctx->flags & IORING_SETUP_SQPOLL) {
struct task_struct *tsk;
struct io_sq_data *sqd;
+ bool attached;
ret = -EPERM;
if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_NICE))
goto err;
- sqd = io_get_sq_data(p);
+ sqd = io_get_sq_data(p, &attached);
if (IS_ERR(sqd)) {
ret = PTR_ERR(sqd);
goto err;
}
+ ctx->sq_creds = get_current_cred();
ctx->sq_data = sqd;
- io_sq_thread_park(sqd);
- mutex_lock(&sqd->ctx_lock);
- list_add(&ctx->sqd_list, &sqd->ctx_new_list);
- mutex_unlock(&sqd->ctx_lock);
- io_sq_thread_unpark(sqd);
-
ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle);
if (!ctx->sq_thread_idle)
ctx->sq_thread_idle = HZ;
- if (sqd->thread)
+ ret = 0;
+ io_sq_thread_park(sqd);
+ list_add(&ctx->sqd_list, &sqd->ctx_list);
+ io_sqd_update_thread_idle(sqd);
+ /* don't attach to a dying SQPOLL thread, would be racy */
+ if (attached && !sqd->thread)
+ ret = -ENXIO;
+ io_sq_thread_unpark(sqd);
+
+ if (ret < 0)
+ goto err;
+ if (attached)
return 0;
if (p->flags & IORING_SETUP_SQ_AFF) {
ret = -EINVAL;
if (cpu >= nr_cpu_ids)
- goto err;
+ goto err_sqpoll;
if (!cpu_online(cpu))
- goto err;
+ goto err_sqpoll;
sqd->sq_cpu = cpu;
} else {
}
sqd->task_pid = current->pid;
+ sqd->task_tgid = current->tgid;
tsk = create_io_thread(io_sq_thread, sqd, NUMA_NO_NODE);
if (IS_ERR(tsk)) {
ret = PTR_ERR(tsk);
- goto err;
+ goto err_sqpoll;
}
- ret = io_uring_alloc_task_context(tsk, ctx);
- if (ret)
- set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
+
sqd->thread = tsk;
+ ret = io_uring_alloc_task_context(tsk, ctx);
wake_up_new_task(tsk);
if (ret)
goto err;
err:
io_sq_thread_finish(ctx);
return ret;
-}
-
-static void io_sq_offload_start(struct io_ring_ctx *ctx)
-{
- struct io_sq_data *sqd = ctx->sq_data;
-
- ctx->flags &= ~IORING_SETUP_R_DISABLED;
- if (ctx->flags & IORING_SETUP_SQPOLL)
- complete(&sqd->startup);
+err_sqpoll:
+ complete(&ctx->sq_data->exited);
+ goto err;
}
static inline void __io_unaccount_mem(struct user_struct *user,
return -ENXIO;
}
-static int __io_destroy_buffers(int id, void *p, void *data)
-{
- struct io_ring_ctx *ctx = data;
- struct io_buffer *buf = p;
-
- __io_remove_buffers(ctx, buf, id, -1U);
- return 0;
-}
-
static void io_destroy_buffers(struct io_ring_ctx *ctx)
{
- idr_for_each(&ctx->io_buffer_idr, __io_destroy_buffers, ctx);
- idr_destroy(&ctx->io_buffer_idr);
+ struct io_buffer *buf;
+ unsigned long index;
+
+ xa_for_each(&ctx->io_buffers, index, buf)
+ __io_remove_buffers(ctx, buf, index, -1U);
}
static void io_req_cache_free(struct list_head *list, struct task_struct *tsk)
{
/*
* Some may use context even when all refs and requests have been put,
- * and they are free to do so while still holding uring_lock, see
- * __io_req_task_submit(). Wait for them to finish.
+ * and they are free to do so while still holding uring_lock or
+ * completion_lock, see __io_req_task_submit(). Wait for them to finish.
*/
mutex_lock(&ctx->uring_lock);
mutex_unlock(&ctx->uring_lock);
+ spin_lock_irq(&ctx->completion_lock);
+ spin_unlock_irq(&ctx->completion_lock);
io_sq_thread_finish(ctx);
io_sqe_buffers_unregister(ctx);
mutex_unlock(&ctx->uring_lock);
io_eventfd_unregister(ctx);
io_destroy_buffers(ctx);
- idr_destroy(&ctx->personality_idr);
#if defined(CONFIG_UNIX)
if (ctx->ring_sock) {
{
const struct cred *creds;
- creds = idr_remove(&ctx->personality_idr, id);
+ creds = xa_erase(&ctx->personalities, id);
if (creds) {
put_cred(creds);
return 0;
return -EINVAL;
}
-static int io_remove_personalities(int id, void *p, void *data)
+static inline bool io_run_ctx_fallback(struct io_ring_ctx *ctx)
{
- struct io_ring_ctx *ctx = data;
-
- io_unregister_personality(ctx, id);
- return 0;
+ return io_run_task_work_head(&ctx->exit_task_work);
}
-static bool io_run_ctx_fallback(struct io_ring_ctx *ctx)
-{
- struct callback_head *work, *next;
- bool executed = false;
-
- do {
- work = xchg(&ctx->exit_task_work, NULL);
- if (!work)
- break;
+struct io_tctx_exit {
+ struct callback_head task_work;
+ struct completion completion;
+ struct io_ring_ctx *ctx;
+};
- do {
- next = work->next;
- work->func(work);
- work = next;
- cond_resched();
- } while (work);
- executed = true;
- } while (1);
+static void io_tctx_exit_cb(struct callback_head *cb)
+{
+ struct io_uring_task *tctx = current->io_uring;
+ struct io_tctx_exit *work;
- return executed;
+ work = container_of(cb, struct io_tctx_exit, task_work);
+ /*
+ * When @in_idle, we're in cancellation and it's racy to remove the
+ * node. It'll be removed by the end of cancellation, just ignore it.
+ */
+ if (!atomic_read(&tctx->in_idle))
+ io_uring_del_task_file((unsigned long)work->ctx);
+ complete(&work->completion);
}
static void io_ring_exit_work(struct work_struct *work)
{
- struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx,
- exit_work);
+ struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, exit_work);
+ unsigned long timeout = jiffies + HZ * 60 * 5;
+ struct io_tctx_exit exit;
+ struct io_tctx_node *node;
+ int ret;
+
+ /* prevent SQPOLL from submitting new requests */
+ if (ctx->sq_data) {
+ io_sq_thread_park(ctx->sq_data);
+ list_del_init(&ctx->sqd_list);
+ io_sqd_update_thread_idle(ctx->sq_data);
+ io_sq_thread_unpark(ctx->sq_data);
+ }
/*
* If we're doing polled IO and end up having requests being
*/
do {
io_uring_try_cancel_requests(ctx, NULL, NULL);
+
+ WARN_ON_ONCE(time_after(jiffies, timeout));
} while (!wait_for_completion_timeout(&ctx->ref_comp, HZ/20));
+
+ mutex_lock(&ctx->uring_lock);
+ while (!list_empty(&ctx->tctx_list)) {
+ WARN_ON_ONCE(time_after(jiffies, timeout));
+
+ node = list_first_entry(&ctx->tctx_list, struct io_tctx_node,
+ ctx_node);
+ exit.ctx = ctx;
+ init_completion(&exit.completion);
+ init_task_work(&exit.task_work, io_tctx_exit_cb);
+ ret = task_work_add(node->task, &exit.task_work, TWA_SIGNAL);
+ if (WARN_ON_ONCE(ret))
+ continue;
+ wake_up_process(node->task);
+
+ mutex_unlock(&ctx->uring_lock);
+ wait_for_completion(&exit.completion);
+ cond_resched();
+ mutex_lock(&ctx->uring_lock);
+ }
+ mutex_unlock(&ctx->uring_lock);
+
io_ring_ctx_free(ctx);
}
+/* Returns true if we found and killed one or more timeouts */
+static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk,
+ struct files_struct *files)
+{
+ struct io_kiocb *req, *tmp;
+ int canceled = 0;
+
+ spin_lock_irq(&ctx->completion_lock);
+ list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) {
+ if (io_match_task(req, tsk, files)) {
+ io_kill_timeout(req, -ECANCELED);
+ canceled++;
+ }
+ }
+ if (canceled != 0)
+ io_commit_cqring(ctx);
+ spin_unlock_irq(&ctx->completion_lock);
+ if (canceled != 0)
+ io_cqring_ev_posted(ctx);
+ return canceled != 0;
+}
+
static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
{
+ unsigned long index;
+ struct creds *creds;
+
mutex_lock(&ctx->uring_lock);
percpu_ref_kill(&ctx->refs);
/* if force is set, the ring is going away. always drop after that */
ctx->cq_overflow_flushed = 1;
if (ctx->rings)
__io_cqring_overflow_flush(ctx, true, NULL, NULL);
- idr_for_each(&ctx->personality_idr, io_remove_personalities, ctx);
+ xa_for_each(&ctx->personalities, index, creds)
+ io_unregister_personality(ctx, index);
mutex_unlock(&ctx->uring_lock);
io_kill_timeouts(ctx, NULL, NULL);
return ret;
}
-static void io_cancel_defer_files(struct io_ring_ctx *ctx,
+static bool io_cancel_defer_files(struct io_ring_ctx *ctx,
struct task_struct *task,
struct files_struct *files)
{
- struct io_defer_entry *de = NULL;
+ struct io_defer_entry *de;
LIST_HEAD(list);
spin_lock_irq(&ctx->completion_lock);
}
}
spin_unlock_irq(&ctx->completion_lock);
+ if (list_empty(&list))
+ return false;
while (!list_empty(&list)) {
de = list_first_entry(&list, struct io_defer_entry, list);
io_req_complete(de->req, -ECANCELED);
kfree(de);
}
+ return true;
+}
+
+static bool io_cancel_ctx_cb(struct io_wq_work *work, void *data)
+{
+ struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+
+ return req->ctx == data;
+}
+
+static bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx)
+{
+ struct io_tctx_node *node;
+ enum io_wq_cancel cret;
+ bool ret = false;
+
+ mutex_lock(&ctx->uring_lock);
+ list_for_each_entry(node, &ctx->tctx_list, ctx_node) {
+ struct io_uring_task *tctx = node->task->io_uring;
+
+ /*
+ * io_wq will stay alive while we hold uring_lock, because it's
+ * killed after ctx nodes, which requires to take the lock.
+ */
+ if (!tctx || !tctx->io_wq)
+ continue;
+ cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_ctx_cb, ctx, true);
+ ret |= (cret != IO_WQ_CANCEL_NOTFOUND);
+ }
+ mutex_unlock(&ctx->uring_lock);
+
+ return ret;
}
static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
struct files_struct *files)
{
struct io_task_cancel cancel = { .task = task, .files = files, };
- struct task_struct *tctx_task = task ?: current;
- struct io_uring_task *tctx = tctx_task->io_uring;
+ struct io_uring_task *tctx = task ? task->io_uring : NULL;
while (1) {
enum io_wq_cancel cret;
bool ret = false;
- if (tctx && tctx->io_wq) {
+ if (!task) {
+ ret |= io_uring_try_cancel_iowq(ctx);
+ } else if (tctx && tctx->io_wq) {
+ /*
+ * Cancels requests of all rings, not only @ctx, but
+ * it's fine as the task is in exit/exec.
+ */
cret = io_wq_cancel_cb(tctx->io_wq, io_cancel_task_cb,
&cancel, true);
ret |= (cret != IO_WQ_CANCEL_NOTFOUND);
}
/* SQPOLL thread does its own polling */
- if (!(ctx->flags & IORING_SETUP_SQPOLL) && !files) {
+ if ((!(ctx->flags & IORING_SETUP_SQPOLL) && !files) ||
+ (ctx->sq_data && ctx->sq_data->thread == current)) {
while (!list_empty_careful(&ctx->iopoll_list)) {
io_iopoll_try_reap_events(ctx);
ret = true;
}
}
+ ret |= io_cancel_defer_files(ctx, task, files);
ret |= io_poll_remove_all(ctx, task, files);
ret |= io_kill_timeouts(ctx, task, files);
ret |= io_run_task_work();
io_uring_try_cancel_requests(ctx, task, files);
- if (ctx->sq_data)
- io_sq_thread_unpark(ctx->sq_data);
prepare_to_wait(&task->io_uring->wait, &wait,
TASK_UNINTERRUPTIBLE);
if (inflight == io_uring_count_inflight(ctx, task, files))
schedule();
finish_wait(&task->io_uring->wait, &wait);
- if (ctx->sq_data)
- io_sq_thread_park(ctx->sq_data);
}
}
/*
- * We need to iteratively cancel requests, in case a request has dependent
- * hard links. These persist even for failure of cancelations, hence keep
- * looping until none are found.
- */
-static void io_uring_cancel_task_requests(struct io_ring_ctx *ctx,
- struct files_struct *files)
-{
- struct task_struct *task = current;
-
- if ((ctx->flags & IORING_SETUP_SQPOLL) && ctx->sq_data) {
- /* never started, nothing to cancel */
- if (ctx->flags & IORING_SETUP_R_DISABLED) {
- io_sq_offload_start(ctx);
- return;
- }
- io_sq_thread_park(ctx->sq_data);
- task = ctx->sq_data->thread;
- if (task)
- atomic_inc(&task->io_uring->in_idle);
- }
-
- io_cancel_defer_files(ctx, task, files);
-
- io_uring_cancel_files(ctx, task, files);
- if (!files)
- io_uring_try_cancel_requests(ctx, task, NULL);
-
- if (task)
- atomic_dec(&task->io_uring->in_idle);
- if (ctx->sq_data)
- io_sq_thread_unpark(ctx->sq_data);
-}
-
-/*
* Note that this task has used io_uring. We use it for cancelation purposes.
*/
-static int io_uring_add_task_file(struct io_ring_ctx *ctx, struct file *file)
+static int io_uring_add_task_file(struct io_ring_ctx *ctx)
{
struct io_uring_task *tctx = current->io_uring;
+ struct io_tctx_node *node;
int ret;
if (unlikely(!tctx)) {
return ret;
tctx = current->io_uring;
}
- if (tctx->last != file) {
- void *old = xa_load(&tctx->xa, (unsigned long)file);
+ if (tctx->last != ctx) {
+ void *old = xa_load(&tctx->xa, (unsigned long)ctx);
if (!old) {
- get_file(file);
- ret = xa_err(xa_store(&tctx->xa, (unsigned long)file,
- file, GFP_KERNEL));
+ node = kmalloc(sizeof(*node), GFP_KERNEL);
+ if (!node)
+ return -ENOMEM;
+ node->ctx = ctx;
+ node->task = current;
+
+ ret = xa_err(xa_store(&tctx->xa, (unsigned long)ctx,
+ node, GFP_KERNEL));
if (ret) {
- fput(file);
+ kfree(node);
return ret;
}
+
+ mutex_lock(&ctx->uring_lock);
+ list_add(&node->ctx_node, &ctx->tctx_list);
+ mutex_unlock(&ctx->uring_lock);
}
- tctx->last = file;
+ tctx->last = ctx;
}
-
- /*
- * This is race safe in that the task itself is doing this, hence it
- * cannot be going through the exit/cancel paths at the same time.
- * This cannot be modified while exit/cancel is running.
- */
- if (!tctx->sqpoll && (ctx->flags & IORING_SETUP_SQPOLL))
- tctx->sqpoll = true;
-
return 0;
}
/*
* Remove this io_uring_file -> task mapping.
*/
-static void io_uring_del_task_file(struct file *file)
+static void io_uring_del_task_file(unsigned long index)
{
struct io_uring_task *tctx = current->io_uring;
+ struct io_tctx_node *node;
+
+ if (!tctx)
+ return;
+ node = xa_erase(&tctx->xa, index);
+ if (!node)
+ return;
+
+ WARN_ON_ONCE(current != node->task);
+ WARN_ON_ONCE(list_empty(&node->ctx_node));
- if (tctx->last == file)
+ mutex_lock(&node->ctx->uring_lock);
+ list_del(&node->ctx_node);
+ mutex_unlock(&node->ctx->uring_lock);
+
+ if (tctx->last == node->ctx)
tctx->last = NULL;
- file = xa_erase(&tctx->xa, (unsigned long)file);
- if (file)
- fput(file);
+ kfree(node);
}
static void io_uring_clean_tctx(struct io_uring_task *tctx)
{
- struct file *file;
+ struct io_tctx_node *node;
unsigned long index;
- xa_for_each(&tctx->xa, index, file)
- io_uring_del_task_file(file);
+ xa_for_each(&tctx->xa, index, node)
+ io_uring_del_task_file(index);
if (tctx->io_wq) {
io_wq_put_and_exit(tctx->io_wq);
tctx->io_wq = NULL;
}
}
+static s64 tctx_inflight(struct io_uring_task *tctx)
+{
+ return percpu_counter_sum(&tctx->inflight);
+}
+
+static void io_sqpoll_cancel_cb(struct callback_head *cb)
+{
+ struct io_tctx_exit *work = container_of(cb, struct io_tctx_exit, task_work);
+ struct io_ring_ctx *ctx = work->ctx;
+ struct io_sq_data *sqd = ctx->sq_data;
+
+ if (sqd->thread)
+ io_uring_cancel_sqpoll(ctx);
+ complete(&work->completion);
+}
+
+static void io_sqpoll_cancel_sync(struct io_ring_ctx *ctx)
+{
+ struct io_sq_data *sqd = ctx->sq_data;
+ struct io_tctx_exit work = { .ctx = ctx, };
+ struct task_struct *task;
+
+ io_sq_thread_park(sqd);
+ list_del_init(&ctx->sqd_list);
+ io_sqd_update_thread_idle(sqd);
+ task = sqd->thread;
+ if (task) {
+ init_completion(&work.completion);
+ init_task_work(&work.task_work, io_sqpoll_cancel_cb);
+ io_task_work_add_head(&sqd->park_task_work, &work.task_work);
+ wake_up_process(task);
+ }
+ io_sq_thread_unpark(sqd);
+
+ if (task)
+ wait_for_completion(&work.completion);
+}
+
void __io_uring_files_cancel(struct files_struct *files)
{
struct io_uring_task *tctx = current->io_uring;
- struct file *file;
+ struct io_tctx_node *node;
unsigned long index;
/* make sure overflow events are dropped */
atomic_inc(&tctx->in_idle);
- xa_for_each(&tctx->xa, index, file)
- io_uring_cancel_task_requests(file->private_data, files);
+ xa_for_each(&tctx->xa, index, node) {
+ struct io_ring_ctx *ctx = node->ctx;
+
+ if (ctx->sq_data) {
+ io_sqpoll_cancel_sync(ctx);
+ continue;
+ }
+ io_uring_cancel_files(ctx, current, files);
+ if (!files)
+ io_uring_try_cancel_requests(ctx, current, NULL);
+ }
atomic_dec(&tctx->in_idle);
if (files)
io_uring_clean_tctx(tctx);
}
-static s64 tctx_inflight(struct io_uring_task *tctx)
-{
- return percpu_counter_sum(&tctx->inflight);
-}
-
+/* should only be called by SQPOLL task */
static void io_uring_cancel_sqpoll(struct io_ring_ctx *ctx)
{
struct io_sq_data *sqd = ctx->sq_data;
- struct io_uring_task *tctx;
+ struct io_uring_task *tctx = current->io_uring;
s64 inflight;
DEFINE_WAIT(wait);
- if (!sqd)
- return;
- io_sq_thread_park(sqd);
- if (!sqd->thread || !sqd->thread->io_uring) {
- io_sq_thread_unpark(sqd);
- return;
- }
- tctx = ctx->sq_data->thread->io_uring;
+ WARN_ON_ONCE(!sqd || ctx->sq_data->thread != current);
+
atomic_inc(&tctx->in_idle);
do {
/* read completions before cancelations */
inflight = tctx_inflight(tctx);
if (!inflight)
break;
- io_uring_cancel_task_requests(ctx, NULL);
+ io_uring_try_cancel_requests(ctx, current, NULL);
prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE);
/*
finish_wait(&tctx->wait, &wait);
} while (1);
atomic_dec(&tctx->in_idle);
- io_sq_thread_unpark(sqd);
}
/*
/* make sure overflow events are dropped */
atomic_inc(&tctx->in_idle);
-
- if (tctx->sqpoll) {
- struct file *file;
- unsigned long index;
-
- xa_for_each(&tctx->xa, index, file)
- io_uring_cancel_sqpoll(file->private_data);
- }
+ __io_uring_files_cancel(NULL);
do {
/* read completions before cancelations */
static int io_sqpoll_wait_sq(struct io_ring_ctx *ctx)
{
- int ret = 0;
DEFINE_WAIT(wait);
do {
} while (!signal_pending(current));
finish_wait(&ctx->sqo_sq_wait, &wait);
- return ret;
+ return 0;
}
static int io_get_ext_arg(unsigned flags, const void __user *argp, size_t *argsz,
if (ctx->flags & IORING_SETUP_SQPOLL) {
io_cqring_overflow_flush(ctx, false, NULL, NULL);
- if (unlikely(ctx->sqo_exec)) {
- ret = io_sq_thread_fork(ctx->sq_data, ctx);
- if (ret)
- goto out;
- ctx->sqo_exec = 0;
- }
ret = -EOWNERDEAD;
+ if (unlikely(ctx->sq_data->thread == NULL)) {
+ goto out;
+ }
if (flags & IORING_ENTER_SQ_WAKEUP)
wake_up(&ctx->sq_data->wait);
if (flags & IORING_ENTER_SQ_WAIT) {
}
submitted = to_submit;
} else if (to_submit) {
- ret = io_uring_add_task_file(ctx, f.file);
+ ret = io_uring_add_task_file(ctx);
if (unlikely(ret))
goto out;
mutex_lock(&ctx->uring_lock);
}
#ifdef CONFIG_PROC_FS
-static int io_uring_show_cred(int id, void *p, void *data)
+static int io_uring_show_cred(struct seq_file *m, unsigned int id,
+ const struct cred *cred)
{
- const struct cred *cred = p;
- struct seq_file *m = data;
struct user_namespace *uns = seq_user_ns(m);
struct group_info *gi;
kernel_cap_t cap;
seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf,
(unsigned int) buf->len);
}
- if (has_lock && !idr_is_empty(&ctx->personality_idr)) {
+ if (has_lock && !xa_empty(&ctx->personalities)) {
+ unsigned long index;
+ const struct cred *cred;
+
seq_printf(m, "Personalities:\n");
- idr_for_each(&ctx->personality_idr, io_uring_show_cred, m);
+ xa_for_each(&ctx->personalities, index, cred)
+ io_uring_show_cred(m, index, cred);
}
seq_printf(m, "PollList:\n");
spin_lock_irq(&ctx->completion_lock);
if (fd < 0)
return fd;
- ret = io_uring_add_task_file(ctx, file);
+ ret = io_uring_add_task_file(ctx);
if (ret) {
put_unused_fd(fd);
return ret;
if (ret)
goto err;
- if (!(p->flags & IORING_SETUP_R_DISABLED))
- io_sq_offload_start(ctx);
-
memset(&p->sq_off, 0, sizeof(p->sq_off));
p->sq_off.head = offsetof(struct io_rings, sq.head);
p->sq_off.tail = offsetof(struct io_rings, sq.tail);
static int io_register_personality(struct io_ring_ctx *ctx)
{
const struct cred *creds;
+ u32 id;
int ret;
creds = get_current_cred();
- ret = idr_alloc_cyclic(&ctx->personality_idr, (void *) creds, 1,
- USHRT_MAX, GFP_KERNEL);
- if (ret < 0)
- put_cred(creds);
+ ret = xa_alloc_cyclic(&ctx->personalities, &id, (void *)creds,
+ XA_LIMIT(0, USHRT_MAX), &ctx->pers_next, GFP_KERNEL);
+ if (!ret)
+ return id;
+ put_cred(creds);
return ret;
}
if (ctx->restrictions.registered)
ctx->restricted = 1;
- io_sq_offload_start(ctx);
+ ctx->flags &= ~IORING_SETUP_R_DISABLED;
+ if (ctx->sq_data && wq_has_sleeper(&ctx->sq_data->wait))
+ wake_up(&ctx->sq_data->wait);
return 0;
}
struct iomap_ioend *ioend;
struct bio *bio;
- bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &iomap_ioend_bioset);
+ bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_VECS, &iomap_ioend_bioset);
bio_set_dev(bio, wpc->iomap.bdev);
bio->bi_iter.bi_sector = sector;
bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc);
{
struct bio *new;
- new = bio_alloc(GFP_NOFS, BIO_MAX_PAGES);
+ new = bio_alloc(GFP_NOFS, BIO_MAX_VECS);
bio_copy_dev(new, prev);/* also copies over blkcg information */
new->bi_iter.bi_sector = bio_end_sector(prev);
new->bi_opf = prev->bi_opf;
*/
bio_opf = iomap_dio_bio_opflags(dio, iomap, use_fua);
- nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter, BIO_MAX_PAGES);
+ nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter, BIO_MAX_VECS);
do {
size_t n;
if (dio->error) {
copied += n;
nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter,
- BIO_MAX_PAGES);
+ BIO_MAX_VECS);
iomap_dio_submit_bio(dio, iomap, bio, pos);
pos += n;
} while (nr_pages);
return ret;
}
+ /*
+ * If this swapfile doesn't contain even a single page-aligned
+ * contiguous range of blocks, reject this useless swapfile to
+ * prevent confusion later on.
+ */
+ if (isi.nr_pages == 0) {
+ pr_warn("swapon: Cannot find a single usable page in file.\n");
+ return -EINVAL;
+ }
+
*pagespan = 1 + isi.highest_ppage - isi.lowest_ppage;
sis->max = isi.nr_pages;
sis->pages = isi.nr_pages - 1;
if (flags & FL_LAYOUT)
return 0;
- if (flags & FL_DELEG)
- /* We leave these checks to the caller. */
- return 0;
if (arg == F_RDLCK)
return inode_is_open_for_write(inode) ? -EAGAIN : 0;
goto out;
}
bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9),
- BIO_MAX_PAGES, GFP_NOFS|__GFP_HIGH);
+ BIO_MAX_VECS, GFP_NOFS|__GFP_HIGH);
if (bio == NULL)
goto confused;
p->stack = p->internal;
p->dfd = dfd;
p->name = name;
+ p->path.mnt = NULL;
+ p->path.dentry = NULL;
p->total_link_count = old ? old->total_link_count : 0;
p->saved = old;
current->nameidata = p;
rcu_read_unlock();
}
nd->depth = 0;
+ nd->path.mnt = NULL;
+ nd->path.dentry = NULL;
}
/* path_put is needed afterwards regardless of success or failure */
}
nd->root.mnt = NULL;
- nd->path.mnt = NULL;
- nd->path.dentry = NULL;
/* Absolute pathname -- fetch the root (LOOKUP_IN_ROOT uses nd->dfd). */
if (*s == '/' && !(flags & LOOKUP_IN_ROOT)) {
while (!(err = link_path_walk(s, nd)) &&
(s = lookup_last(nd)) != NULL)
;
+ if (!err && unlikely(nd->flags & LOOKUP_MOUNTPOINT)) {
+ err = handle_lookup_down(nd);
+ nd->flags &= ~LOOKUP_JUMPED; // no d_weak_revalidate(), please...
+ }
if (!err)
err = complete_walk(nd);
if (!err && nd->flags & LOOKUP_DIRECTORY)
if (!d_can_lookup(nd->path.dentry))
err = -ENOTDIR;
- if (!err && unlikely(nd->flags & LOOKUP_MOUNTPOINT)) {
- err = handle_lookup_down(nd);
- nd->flags &= ~LOOKUP_JUMPED; // no d_weak_revalidate(), please...
- }
if (!err) {
*path = nd->path;
nd->path.mnt = NULL;
config PNFS_FLEXFILE_LAYOUT
tristate
depends on NFS_V4_1 && NFS_V3
- default m
+ default NFS_V4
config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN
string "NFSv4.1 Implementation ID Domain"
spin_lock(&dir->i_lock);
if (list_empty(&nfsi->open_files) &&
(nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER))
- nfsi->cache_validity |= NFS_INO_INVALID_DATA |
- NFS_INO_REVAL_FORCED;
+ nfs_set_cache_invalid(dir,
+ NFS_INO_INVALID_DATA |
+ NFS_INO_REVAL_FORCED);
list_add(&ctx->list, &nfsi->open_files);
spin_unlock(&dir->i_lock);
return ctx;
goto out;
}
+static void nfs_mark_dir_for_revalidate(struct inode *inode)
+{
+ spin_lock(&inode->i_lock);
+ nfs_set_cache_invalid(inode, NFS_INO_REVAL_PAGECACHE);
+ spin_unlock(&inode->i_lock);
+}
+
/*
* We judge how long we want to trust negative
* dentries by looking at the parent inode mtime.
__func__, dentry);
return 1;
case 0:
- nfs_mark_for_revalidate(dir);
- if (inode && S_ISDIR(inode->i_mode)) {
- /* Purge readdir caches. */
- nfs_zap_caches(inode);
- /*
- * We can't d_drop the root of a disconnected tree:
- * its d_hash is on the s_anon list and d_drop() would hide
- * it from shrink_dcache_for_unmount(), leading to busy
- * inodes on unmount and further oopses.
- */
- if (IS_ROOT(dentry))
- return 1;
- }
+ /*
+ * We can't d_drop the root of a disconnected tree:
+ * its d_hash is on the s_anon list and d_drop() would hide
+ * it from shrink_dcache_for_unmount(), leading to busy
+ * inodes on unmount and further oopses.
+ */
+ if (inode && IS_ROOT(dentry))
+ return 1;
dfprintk(LOOKUPCACHE, "NFS: %s(%pd2) is invalid\n",
__func__, dentry);
return 0;
nfs_free_fattr(fattr);
nfs_free_fhandle(fhandle);
nfs4_label_free(label);
+
+ /*
+ * If the lookup failed despite the dentry change attribute being
+ * a match, then we should revalidate the directory cache.
+ */
+ if (!ret && nfs_verify_change_attribute(dir, dentry->d_time))
+ nfs_mark_dir_for_revalidate(dir);
return nfs_lookup_revalidate_done(dir, dentry, inode, ret);
}
error = nfs_lookup_verify_inode(inode, flags);
if (error) {
if (error == -ESTALE)
- nfs_zap_caches(dir);
+ nfs_mark_dir_for_revalidate(dir);
goto out_bad;
}
nfs_advise_use_readdirplus(dir);
if (inode->i_nlink > 0)
drop_nlink(inode);
NFS_I(inode)->attr_gencount = nfs_inc_attr_generation_counter();
- NFS_I(inode)->cache_validity |= NFS_INO_INVALID_CHANGE
- | NFS_INO_INVALID_CTIME
- | NFS_INO_INVALID_OTHER
- | NFS_INO_REVAL_FORCED;
+ nfs_set_cache_invalid(
+ inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME |
+ NFS_INO_INVALID_OTHER | NFS_INO_REVAL_FORCED);
spin_unlock(&inode->i_lock);
}
{
if (S_ISDIR(inode->i_mode))
/* drop any readdir cache as it could easily be old */
- NFS_I(inode)->cache_validity |= NFS_INO_INVALID_DATA;
+ nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA);
if (dentry->d_flags & DCACHE_NFSFS_RENAMED) {
nfs_complete_unlink(dentry, inode);
dput(parent);
return d;
out_error:
- nfs_mark_for_revalidate(dir);
d = ERR_PTR(error);
goto out;
}
if (error == 0) {
spin_lock(&old_inode->i_lock);
NFS_I(old_inode)->attr_gencount = nfs_inc_attr_generation_counter();
- NFS_I(old_inode)->cache_validity |= NFS_INO_INVALID_CHANGE
- | NFS_INO_INVALID_CTIME
- | NFS_INO_REVAL_FORCED;
+ nfs_set_cache_invalid(old_inode, NFS_INO_INVALID_CHANGE |
+ NFS_INO_INVALID_CTIME |
+ NFS_INO_REVAL_FORCED);
spin_unlock(&old_inode->i_lock);
}
out:
}
#endif
-static void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
+void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
{
struct nfs_inode *nfsi = NFS_I(inode);
bool have_delegation = NFS_PROTO(inode)->have_delegation(inode, FMODE_READ);
if (flags & NFS_INO_INVALID_DATA)
nfs_fscache_invalidate(inode);
}
+EXPORT_SYMBOL_GPL(nfs_set_cache_invalid);
/*
* Invalidate the local caches
spin_lock(&inode->i_lock);
if (list_empty(&nfsi->open_files) &&
(nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER))
- nfsi->cache_validity |= NFS_INO_INVALID_DATA |
- NFS_INO_REVAL_FORCED;
+ nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA |
+ NFS_INO_REVAL_FORCED);
list_add_tail_rcu(&ctx->list, &nfsi->open_files);
spin_unlock(&inode->i_lock);
}
extern int nfs_drop_inode(struct inode *);
extern void nfs_clear_inode(struct inode *);
extern void nfs_evict_inode(struct inode *);
-void nfs_zap_acl_cache(struct inode *inode);
+extern void nfs_zap_acl_cache(struct inode *inode);
+extern void nfs_set_cache_invalid(struct inode *inode, unsigned long flags);
extern bool nfs_check_cache_invalid(struct inode *, unsigned long);
extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode);
extern int nfs_wait_atomic_killable(atomic_t *p, unsigned int mode);
#define NFS3_pagepad_sz (1) /* Page padding */
#define NFS3_fhandle_sz (1+16)
#define NFS3_fh_sz (NFS3_fhandle_sz) /* shorthand */
+#define NFS3_post_op_fh_sz (1+NFS3_fh_sz)
#define NFS3_sattr_sz (15)
#define NFS3_filename_sz (1+(NFS3_MAXNAMLEN>>2))
#define NFS3_path_sz (1+(NFS3_MAXPATHLEN>>2))
#define NFS3_readlinkres_sz (1+NFS3_post_op_attr_sz+1+NFS3_pagepad_sz)
#define NFS3_readres_sz (1+NFS3_post_op_attr_sz+3+NFS3_pagepad_sz)
#define NFS3_writeres_sz (1+NFS3_wcc_data_sz+4)
-#define NFS3_createres_sz (1+NFS3_fh_sz+NFS3_post_op_attr_sz+NFS3_wcc_data_sz)
+#define NFS3_createres_sz (1+NFS3_post_op_fh_sz+NFS3_post_op_attr_sz+NFS3_wcc_data_sz)
#define NFS3_renameres_sz (1+(2 * NFS3_wcc_data_sz))
#define NFS3_linkres_sz (1+NFS3_post_op_attr_sz+NFS3_wcc_data_sz)
#define NFS3_readdirres_sz (1+NFS3_post_op_attr_sz+2+NFS3_pagepad_sz)
truncate_pagecache_range(dst_inode, pos_dst,
pos_dst + res->write_res.count);
spin_lock(&dst_inode->i_lock);
- NFS_I(dst_inode)->cache_validity |= (NFS_INO_REVAL_PAGECACHE |
- NFS_INO_REVAL_FORCED | NFS_INO_INVALID_SIZE |
- NFS_INO_INVALID_ATTR | NFS_INO_INVALID_DATA);
+ nfs_set_cache_invalid(
+ dst_inode, NFS_INO_REVAL_PAGECACHE | NFS_INO_REVAL_FORCED |
+ NFS_INO_INVALID_SIZE | NFS_INO_INVALID_ATTR |
+ NFS_INO_INVALID_DATA);
spin_unlock(&dst_inode->i_lock);
spin_lock(&src_inode->i_lock);
- NFS_I(src_inode)->cache_validity |= (NFS_INO_REVAL_PAGECACHE |
- NFS_INO_REVAL_FORCED | NFS_INO_INVALID_ATIME);
+ nfs_set_cache_invalid(src_inode, NFS_INO_REVAL_PAGECACHE |
+ NFS_INO_REVAL_FORCED |
+ NFS_INO_INVALID_ATIME);
spin_unlock(&src_inode->i_lock);
status = res->write_res.count;
out:
static void
nfs4_inc_nlink_locked(struct inode *inode)
{
- NFS_I(inode)->cache_validity |= NFS_INO_INVALID_OTHER;
+ nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
inc_nlink(inode);
}
static void
nfs4_dec_nlink_locked(struct inode *inode)
{
- NFS_I(inode)->cache_validity |= NFS_INO_INVALID_OTHER;
+ nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
drop_nlink(inode);
}
{
struct nfs_inode *nfsi = NFS_I(inode);
- nfsi->cache_validity |= NFS_INO_INVALID_CTIME
- | NFS_INO_INVALID_MTIME
- | cache_validity;
+ cache_validity |= NFS_INO_INVALID_CTIME | NFS_INO_INVALID_MTIME;
if (cinfo->atomic && cinfo->before == inode_peek_iversion_raw(inode)) {
nfsi->cache_validity &= ~NFS_INO_REVAL_PAGECACHE;
nfsi->attrtimeo_timestamp = jiffies;
} else {
if (S_ISDIR(inode->i_mode)) {
- nfsi->cache_validity |= NFS_INO_INVALID_DATA;
+ cache_validity |= NFS_INO_INVALID_DATA;
nfs_force_lookup_revalidate(inode);
} else {
if (!NFS_PROTO(inode)->have_delegation(inode,
FMODE_READ))
- nfsi->cache_validity |= NFS_INO_REVAL_PAGECACHE;
+ cache_validity |= NFS_INO_REVAL_PAGECACHE;
}
if (cinfo->before != inode_peek_iversion_raw(inode))
- nfsi->cache_validity |= NFS_INO_INVALID_ACCESS |
- NFS_INO_INVALID_ACL |
- NFS_INO_INVALID_XATTR;
+ cache_validity |= NFS_INO_INVALID_ACCESS |
+ NFS_INO_INVALID_ACL |
+ NFS_INO_INVALID_XATTR;
}
inode_set_iversion_raw(inode, cinfo->after);
nfsi->read_cache_jiffies = timestamp;
nfsi->attr_gencount = nfs_inc_attr_generation_counter();
+ nfs_set_cache_invalid(inode, cache_validity);
nfsi->cache_validity &= ~NFS_INO_INVALID_CHANGE;
-
- if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
- nfs_fscache_invalidate(inode);
}
void
unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE);
int ret, i;
+ /* You can't remove system.nfs4_acl: */
+ if (buflen == 0)
+ return -EINVAL;
if (!nfs4_server_supports_acls(server))
return -EOPNOTSUPP;
if (npages > ARRAY_SIZE(pages))
* so mark the attribute cache invalid.
*/
spin_lock(&inode->i_lock);
- NFS_I(inode)->cache_validity |= NFS_INO_INVALID_CHANGE
- | NFS_INO_INVALID_CTIME
- | NFS_INO_REVAL_FORCED;
+ nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE |
+ NFS_INO_INVALID_CTIME |
+ NFS_INO_REVAL_FORCED);
spin_unlock(&inode->i_lock);
nfs_access_zap_cache(inode);
nfs_zap_acl_cache(inode);
return ret;
if (!(fattr.valid & NFS_ATTR_FATTR_V4_SECURITY_LABEL))
return -ENOENT;
- return 0;
+ return label.len;
}
static int nfs4_get_security_label(struct inode *inode, void *buf,
nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
spin_lock(&inode->i_lock);
NFS_I(inode)->attr_gencount = nfs_inc_attr_generation_counter();
- NFS_I(inode)->cache_validity |= NFS_INO_INVALID_CHANGE
- | NFS_INO_INVALID_CTIME
- | NFS_INO_REVAL_FORCED;
+ nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE |
+ NFS_INO_INVALID_CTIME |
+ NFS_INO_REVAL_FORCED);
spin_unlock(&inode->i_lock);
d_move(dentry, sdentry);
break;
nfs_zap_mapping(mapping->host, mapping);
/* Force file size revalidation */
spin_lock(&inode->i_lock);
- NFS_I(inode)->cache_validity |= NFS_INO_REVAL_FORCED |
- NFS_INO_REVAL_PAGECACHE |
- NFS_INO_INVALID_SIZE;
+ nfs_set_cache_invalid(inode, NFS_INO_REVAL_FORCED |
+ NFS_INO_REVAL_PAGECACHE |
+ NFS_INO_INVALID_SIZE);
spin_unlock(&inode->i_lock);
}
/* Deal with the suid/sgid bit corner case */
if (nfs_should_remove_suid(inode)) {
spin_lock(&inode->i_lock);
- NFS_I(inode)->cache_validity |= NFS_INO_INVALID_OTHER;
+ nfs_set_cache_invalid(inode, NFS_INO_INVALID_OTHER);
spin_unlock(&inode->i_lock);
}
return 0;
select NFSD_V3
select FS_POSIX_ACL
select SUNRPC_GSS
+ select CRYPTO
select CRYPTO_MD5
select CRYPTO_SHA256
select GRACE_PERIOD
continue;
if (!nfsd_match_cred(nf->nf_cred, current_cred()))
continue;
+ if (!test_bit(NFSD_FILE_HASHED, &nf->nf_flags))
+ continue;
if (nfsd_file_get(nf) != NULL)
return nf;
}
switch (task->tk_status) {
case -EIO:
case -ETIMEDOUT:
+ case -EACCES:
nfsd4_mark_cb_down(clp, task->tk_status);
}
break;
struct nfsd_file *dst)
{
nfs42_ssc_close(src->nf_file);
- /* 'src' is freed by nfsd4_do_async_copy */
+ fput(src->nf_file);
nfsd_file_put(dst);
mntput(ss_mnt);
}
return fl;
}
-static int nfsd4_check_conflicting_opens(struct nfs4_client *clp,
- struct nfs4_file *fp)
-{
- struct nfs4_clnt_odstate *co;
- struct file *f = fp->fi_deleg_file->nf_file;
- struct inode *ino = locks_inode(f);
- int writes = atomic_read(&ino->i_writecount);
-
- if (fp->fi_fds[O_WRONLY])
- writes--;
- if (fp->fi_fds[O_RDWR])
- writes--;
- if (writes > 0)
- return -EAGAIN;
- spin_lock(&fp->fi_lock);
- list_for_each_entry(co, &fp->fi_clnt_odstate, co_perfile) {
- if (co->co_client != clp) {
- spin_unlock(&fp->fi_lock);
- return -EAGAIN;
- }
- }
- spin_unlock(&fp->fi_lock);
- return 0;
-}
-
static struct nfs4_delegation *
nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh,
struct nfs4_file *fp, struct nfs4_clnt_odstate *odstate)
nf = find_readable_file(fp);
if (!nf) {
- /*
- * We probably could attempt another open and get a read
- * delegation, but for now, don't bother until the
- * client actually sends us one.
- */
- return ERR_PTR(-EAGAIN);
+ /* We should always have a readable file here */
+ WARN_ON_ONCE(1);
+ return ERR_PTR(-EBADF);
}
spin_lock(&state_lock);
spin_lock(&fp->fi_lock);
if (!fl)
goto out_clnt_odstate;
- status = nfsd4_check_conflicting_opens(clp, fp);
- if (status) {
- locks_free_lock(fl);
- goto out_clnt_odstate;
- }
status = vfs_setlease(fp->fi_deleg_file->nf_file, fl->fl_type, &fl, NULL);
if (fl)
locks_free_lock(fl);
if (status)
goto out_clnt_odstate;
- status = nfsd4_check_conflicting_opens(clp, fp);
- if (status)
- goto out_clnt_odstate;
spin_lock(&state_lock);
spin_lock(&fp->fi_lock);
goto out_no_deleg;
if (!cb_up || !(oo->oo_flags & NFS4_OO_CONFIRMED))
goto out_no_deleg;
+ /*
+ * Also, if the file was opened for write or
+ * create, there's a good chance the client's
+ * about to write to it, resulting in an
+ * immediate recall (since we don't support
+ * write delegations):
+ */
+ if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE)
+ goto out_no_deleg;
+ if (open->op_create == NFS4_OPEN_CREATE)
+ goto out_no_deleg;
break;
default:
goto out_no_deleg;
idr_for_each_entry(&nn->s2s_cp_stateids, cps_t, i) {
cps = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid);
if (cps->cp_stateid.sc_type == NFS4_COPYNOTIFY_STID &&
- cps->cpntf_time > cutoff)
+ cps->cpntf_time < cutoff)
_free_cpntf_state_locked(nn, cps);
}
spin_unlock(&nn->s2s_cp_lock);
{
wi->bio = NULL;
wi->rest_blocks = segbuf->sb_sum.nblocks;
- wi->max_pages = BIO_MAX_PAGES;
+ wi->max_pages = BIO_MAX_VECS;
wi->nr_vecs = min(wi->max_pages, wi->rest_blocks);
wi->start = wi->end = 0;
wi->blocknr = segbuf->sb_pseg_start;
struct ocfs2_alloc_context *meta_ac = NULL;
handle_t *handle = NULL;
loff_t end = offset + bytes;
- int ret = 0, credits = 0, locked = 0;
+ int ret = 0, credits = 0;
ocfs2_init_dealloc_ctxt(&dealloc);
!dwc->dw_orphaned)
goto out;
- /* ocfs2_file_write_iter will get i_mutex, so we need not lock if we
- * are in that context. */
- if (dwc->dw_writer_pid != task_pid_nr(current)) {
- inode_lock(inode);
- locked = 1;
- }
-
ret = ocfs2_inode_lock(inode, &di_bh, 1);
if (ret < 0) {
mlog_errno(ret);
if (meta_ac)
ocfs2_free_alloc_context(meta_ac);
ocfs2_run_deallocs(osb, &dealloc);
- if (locked)
- inode_unlock(inode);
ocfs2_dio_free_write_ctx(inode, dwc);
return ret;
goto bail_unlock;
}
}
+ down_write(&OCFS2_I(inode)->ip_alloc_sem);
handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS +
2 * ocfs2_quota_trans_credits(sb));
if (IS_ERR(handle)) {
status = PTR_ERR(handle);
mlog_errno(status);
- goto bail_unlock;
+ goto bail_unlock_alloc;
}
status = __dquot_transfer(inode, transfer_to);
if (status < 0)
goto bail_commit;
} else {
+ down_write(&OCFS2_I(inode)->ip_alloc_sem);
handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
if (IS_ERR(handle)) {
status = PTR_ERR(handle);
mlog_errno(status);
- goto bail_unlock;
+ goto bail_unlock_alloc;
}
}
bail_commit:
ocfs2_commit_trans(osb, handle);
+bail_unlock_alloc:
+ up_write(&OCFS2_I(inode)->ip_alloc_sem);
bail_unlock:
if (status && inode_locked) {
ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock);
if (WARN_ON(file != vma->vm_file))
return -EIO;
- vma->vm_file = get_file(realfile);
+ vma_set_file(vma, realfile);
old_cred = ovl_override_creds(file_inode(file)->i_sb);
ret = call_mmap(vma->vm_file, vma);
revert_creds(old_cred);
-
- if (ret) {
- /* Drop reference count from new vm_file value */
- fput(realfile);
- } else {
- /* Drop reference count from previous vm_file value */
- fput(file);
- }
-
ovl_file_accessed(file);
return ret;
#define IS_MNT_SHARED(m) ((m)->mnt.mnt_flags & MNT_SHARED)
#define IS_MNT_SLAVE(m) ((m)->mnt_master)
-#define IS_MNT_NEW(m) (!(m)->mnt_ns)
+#define IS_MNT_NEW(m) (!(m)->mnt_ns || is_anon_ns((m)->mnt_ns))
#define CLEAR_MNT_SHARED(m) ((m)->mnt.mnt_flags &= ~MNT_SHARED)
#define IS_MNT_UNBINDABLE(m) ((m)->mnt.mnt_flags & MNT_UNBINDABLE)
#define IS_MNT_MARKED(m) ((m)->mnt.mnt_flags & MNT_MARKED)
#ifdef CONFIG_MEM_SOFT_DIRTY
-#define is_cow_mapping(flags) (((flags) & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE)
-
static inline bool pte_is_pinned(struct vm_area_struct *vma, unsigned long addr, pte_t pte)
{
struct page *page;
if (buf->result)
return -EINVAL;
+ buf->result = verify_dirent_name(name, namlen);
+ if (buf->result < 0)
+ return buf->result;
d_ino = ino;
if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) {
buf->result = -EOVERFLOW;
if (buf->result)
return -EINVAL;
+ buf->result = verify_dirent_name(name, namlen);
+ if (buf->result < 0)
+ return buf->result;
d_ino = ino;
if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) {
buf->result = -EOVERFLOW;
static inline int reiserfs_xattrs_initialized(struct super_block *sb)
{
- return REISERFS_SB(sb)->priv_root != NULL;
+ return REISERFS_SB(sb)->priv_root && REISERFS_SB(sb)->xattr_root;
}
#define xattr_size(size) ((size) + sizeof(struct reiserfs_xattr_header))
ret = do_sys_poll(ufds, nfds, to);
- if (ret == -ERESTARTNOHAND) {
- restart_block->fn = do_restart_poll;
- ret = -ERESTART_RESTARTBLOCK;
- }
+ if (ret == -ERESTARTNOHAND)
+ ret = set_restart_fn(restart_block, do_restart_poll);
+
return ret;
}
struct restart_block *restart_block;
restart_block = ¤t->restart_block;
- restart_block->fn = do_restart_poll;
restart_block->poll.ufds = ufds;
restart_block->poll.nfds = nfds;
} else
restart_block->poll.has_timeout = 0;
- ret = -ERESTART_RESTARTBLOCK;
+ ret = set_restart_fn(restart_block, do_restart_poll);
}
return ret;
}
int error, i;
struct bio *bio;
- if (page_count <= BIO_MAX_PAGES)
+ if (page_count <= BIO_MAX_VECS)
bio = bio_alloc(GFP_NOIO, page_count);
else
bio = bio_kmalloc(GFP_NOIO, page_count);
start = le64_to_cpu(table[n]);
end = le64_to_cpu(table[n + 1]);
- if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) {
+ if (start >= end
+ || (end - start) >
+ (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
kfree(table);
return ERR_PTR(-EINVAL);
}
}
start = le64_to_cpu(table[indexes - 1]);
- if (start >= lookup_table_start || (lookup_table_start - start) > SQUASHFS_METADATA_SIZE) {
+ if (start >= lookup_table_start ||
+ (lookup_table_start - start) >
+ (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
kfree(table);
return ERR_PTR(-EINVAL);
}
start = le64_to_cpu(table[n]);
end = le64_to_cpu(table[n + 1]);
- if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) {
+ if (start >= end || (end - start) >
+ (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
kfree(table);
return ERR_PTR(-EINVAL);
}
}
start = le64_to_cpu(table[indexes - 1]);
- if (start >= id_table_start || (id_table_start - start) > SQUASHFS_METADATA_SIZE) {
+ if (start >= id_table_start || (id_table_start - start) >
+ (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
kfree(table);
return ERR_PTR(-EINVAL);
}
/* size of metadata (inode and directory) blocks */
#define SQUASHFS_METADATA_SIZE 8192
+#define SQUASHFS_BLOCK_OFFSET 2
/* default size of block device I/O */
#ifdef CONFIG_SQUASHFS_4K_DEVBLK_SIZE
start = le64_to_cpu(table[n]);
end = le64_to_cpu(table[n + 1]);
- if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) {
+ if (start >= end || (end - start) >
+ (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
kfree(table);
return ERR_PTR(-EINVAL);
}
}
start = le64_to_cpu(table[indexes - 1]);
- if (start >= table_start || (table_start - start) > SQUASHFS_METADATA_SIZE) {
+ if (start >= table_start || (table_start - start) >
+ (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) {
kfree(table);
return ERR_PTR(-EINVAL);
}
config FS_VERITY
bool "FS Verity (read-only file-based authenticity protection)"
select CRYPTO
- # SHA-256 is selected as it's intended to be the default hash algorithm.
+ # SHA-256 is implied as it's intended to be the default hash algorithm.
# To avoid bloat, other wanted algorithms must be selected explicitly.
- select CRYPTO_SHA256
+ # Note that CRYPTO_SHA256 denotes the generic C implementation, but
+ # some architectures provided optimized implementations of the same
+ # algorithm that may be used instead. In this case, CRYPTO_SHA256 may
+ # be omitted even if SHA-256 is being used.
+ imply CRYPTO_SHA256
help
This option enables fs-verity. fs-verity is the dm-verity
mechanism implemented at the file level. On supported
/*
* Make sure that we have allocated dquot(s) on disk.
*/
- error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid,
- XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
- &udqp, &gdqp, &pdqp);
+ error = xfs_qm_vop_dqalloc(dp, fsuid_into_mnt(mnt_userns),
+ fsgid_into_mnt(mnt_userns), prid,
+ XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
+ &udqp, &gdqp, &pdqp);
if (error)
return error;
/*
* Make sure that we have allocated dquot(s) on disk.
*/
- error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid,
- XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
- &udqp, &gdqp, &pdqp);
+ error = xfs_qm_vop_dqalloc(dp, fsuid_into_mnt(mnt_userns),
+ fsgid_into_mnt(mnt_userns), prid,
+ XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
+ &udqp, &gdqp, &pdqp);
if (error)
return error;
};
int error;
+ if (breq->mnt_userns != &init_user_ns) {
+ xfs_warn_ratelimited(breq->mp,
+ "bulkstat not supported inside of idmapped mounts.");
+ return -EINVAL;
+ }
+
ASSERT(breq->icount == 1);
bc.buf = kmem_zalloc(sizeof(struct xfs_bulkstat),
}
/*
+ * Flush and reclaim dirty inodes in preparation for unmount. Inodes and
+ * internal inode structures can be sitting in the CIL and AIL at this point,
+ * so we need to unpin them, write them back and/or reclaim them before unmount
+ * can proceed.
+ *
+ * An inode cluster that has been freed can have its buffer still pinned in
+ * memory because the transaction is still sitting in a iclog. The stale inodes
+ * on that buffer will be pinned to the buffer until the transaction hits the
+ * disk and the callbacks run. Pushing the AIL will skip the stale inodes and
+ * may never see the pinned buffer, so nothing will push out the iclog and
+ * unpin the buffer.
+ *
+ * Hence we need to force the log to unpin everything first. However, log
+ * forces don't wait for the discards they issue to complete, so we have to
+ * explicitly wait for them to complete here as well.
+ *
+ * Then we can tell the world we are unmounting so that error handling knows
+ * that the filesystem is going away and we should error out anything that we
+ * have been retrying in the background. This will prevent never-ending
+ * retries in AIL pushing from hanging the unmount.
+ *
+ * Finally, we can push the AIL to clean all the remaining dirty objects, then
+ * reclaim the remaining inodes that are still in memory at this point in time.
+ */
+static void
+xfs_unmount_flush_inodes(
+ struct xfs_mount *mp)
+{
+ xfs_log_force(mp, XFS_LOG_SYNC);
+ xfs_extent_busy_wait_all(mp);
+ flush_workqueue(xfs_discard_wq);
+
+ mp->m_flags |= XFS_MOUNT_UNMOUNTING;
+
+ xfs_ail_push_all_sync(mp->m_ail);
+ cancel_delayed_work_sync(&mp->m_reclaim_work);
+ xfs_reclaim_inodes(mp);
+ xfs_health_unmount(mp);
+}
+
+/*
* This function does the following on an initial mount of a file system:
* - reads the superblock from disk and init the mount struct
* - if we're a 32-bit kernel, do a size check on the superblock
/* Clean out dquots that might be in memory after quotacheck. */
xfs_qm_unmount(mp);
/*
- * Cancel all delayed reclaim work and reclaim the inodes directly.
+ * Flush all inode reclamation work and flush the log.
* We have to do this /after/ rtunmount and qm_unmount because those
* two will have scheduled delayed reclaim for the rt/quota inodes.
*
* qm_unmount_quotas and therefore rely on qm_unmount to release the
* quota inodes.
*/
- cancel_delayed_work_sync(&mp->m_reclaim_work);
- xfs_reclaim_inodes(mp);
- xfs_health_unmount(mp);
+ xfs_unmount_flush_inodes(mp);
out_log_dealloc:
- mp->m_flags |= XFS_MOUNT_UNMOUNTING;
xfs_log_mount_cancel(mp);
out_fail_wait:
if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp)
xfs_rtunmount_inodes(mp);
xfs_irele(mp->m_rootip);
- /*
- * We can potentially deadlock here if we have an inode cluster
- * that has been freed has its buffer still pinned in memory because
- * the transaction is still sitting in a iclog. The stale inodes
- * on that buffer will be pinned to the buffer until the
- * transaction hits the disk and the callbacks run. Pushing the AIL will
- * skip the stale inodes and may never see the pinned buffer, so
- * nothing will push out the iclog and unpin the buffer. Hence we
- * need to force the log here to ensure all items are flushed into the
- * AIL before we go any further.
- */
- xfs_log_force(mp, XFS_LOG_SYNC);
-
- /*
- * Wait for all busy extents to be freed, including completion of
- * any discard operation.
- */
- xfs_extent_busy_wait_all(mp);
- flush_workqueue(xfs_discard_wq);
-
- /*
- * We now need to tell the world we are unmounting. This will allow
- * us to detect that the filesystem is going away and we should error
- * out anything that we have been retrying in the background. This will
- * prevent neverending retries in AIL pushing from hanging the unmount.
- */
- mp->m_flags |= XFS_MOUNT_UNMOUNTING;
-
- /*
- * Flush all pending changes from the AIL.
- */
- xfs_ail_push_all_sync(mp->m_ail);
-
- /*
- * Reclaim all inodes. At this point there should be no dirty inodes and
- * none should be pinned or locked. Stop background inode reclaim here
- * if it is still running.
- */
- cancel_delayed_work_sync(&mp->m_reclaim_work);
- xfs_reclaim_inodes(mp);
- xfs_health_unmount(mp);
+ xfs_unmount_flush_inodes(mp);
xfs_qm_unmount(mp);
/*
* Make sure that we have allocated dquot(s) on disk.
*/
- error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid,
+ error = xfs_qm_vop_dqalloc(dp, fsuid_into_mnt(mnt_userns),
+ fsgid_into_mnt(mnt_userns), prid,
XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
&udqp, &gdqp, &pdqp);
if (error)
return iomap_writepages(mapping, wbc, &wpc, &zonefs_writeback_ops);
}
+static int zonefs_swap_activate(struct swap_info_struct *sis,
+ struct file *swap_file, sector_t *span)
+{
+ struct inode *inode = file_inode(swap_file);
+ struct zonefs_inode_info *zi = ZONEFS_I(inode);
+
+ if (zi->i_ztype != ZONEFS_ZTYPE_CNV) {
+ zonefs_err(inode->i_sb,
+ "swap file: not a conventional zone file\n");
+ return -EINVAL;
+ }
+
+ return iomap_swapfile_activate(sis, swap_file, span, &zonefs_iomap_ops);
+}
+
static const struct address_space_operations zonefs_file_aops = {
.readpage = zonefs_readpage,
.readahead = zonefs_readahead,
.is_partially_uptodate = iomap_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
.direct_IO = noop_direct_IO,
+ .swap_activate = zonefs_swap_activate,
};
static void zonefs_update_stats(struct inode *inode, loff_t new_isize)
max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize);
iov_iter_truncate(from, max);
- nr_pages = iov_iter_npages(from, BIO_MAX_PAGES);
+ nr_pages = iov_iter_npages(from, BIO_MAX_VECS);
if (!nr_pages)
return 0;
}
/*
+ * Do not exceed the LFS limits nor the file zone size. If pos is under the
+ * limit it becomes a short access. If it exceeds the limit, return -EFBIG.
+ */
+static loff_t zonefs_write_check_limits(struct file *file, loff_t pos,
+ loff_t count)
+{
+ struct inode *inode = file_inode(file);
+ struct zonefs_inode_info *zi = ZONEFS_I(inode);
+ loff_t limit = rlimit(RLIMIT_FSIZE);
+ loff_t max_size = zi->i_max_size;
+
+ if (limit != RLIM_INFINITY) {
+ if (pos >= limit) {
+ send_sig(SIGXFSZ, current, 0);
+ return -EFBIG;
+ }
+ count = min(count, limit - pos);
+ }
+
+ if (!(file->f_flags & O_LARGEFILE))
+ max_size = min_t(loff_t, MAX_NON_LFS, max_size);
+
+ if (unlikely(pos >= max_size))
+ return -EFBIG;
+
+ return min(count, max_size - pos);
+}
+
+static ssize_t zonefs_write_checks(struct kiocb *iocb, struct iov_iter *from)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file_inode(file);
+ struct zonefs_inode_info *zi = ZONEFS_I(inode);
+ loff_t count;
+
+ if (IS_SWAPFILE(inode))
+ return -ETXTBSY;
+
+ if (!iov_iter_count(from))
+ return 0;
+
+ if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
+ return -EINVAL;
+
+ if (iocb->ki_flags & IOCB_APPEND) {
+ if (zi->i_ztype != ZONEFS_ZTYPE_SEQ)
+ return -EINVAL;
+ mutex_lock(&zi->i_truncate_mutex);
+ iocb->ki_pos = zi->i_wpoffset;
+ mutex_unlock(&zi->i_truncate_mutex);
+ }
+
+ count = zonefs_write_check_limits(file, iocb->ki_pos,
+ iov_iter_count(from));
+ if (count < 0)
+ return count;
+
+ iov_iter_truncate(from, count);
+ return iov_iter_count(from);
+}
+
+/*
* Handle direct writes. For sequential zone files, this is the only possible
* write path. For these files, check that the user is issuing writes
* sequentially from the end of the file. This code assumes that the block layer
struct super_block *sb = inode->i_sb;
bool sync = is_sync_kiocb(iocb);
bool append = false;
- size_t count;
- ssize_t ret;
+ ssize_t ret, count;
/*
* For async direct IOs to sequential zone files, refuse IOCB_NOWAIT
inode_lock(inode);
}
- ret = generic_write_checks(iocb, from);
- if (ret <= 0)
+ count = zonefs_write_checks(iocb, from);
+ if (count <= 0) {
+ ret = count;
goto inode_unlock;
-
- iov_iter_truncate(from, zi->i_max_size - iocb->ki_pos);
- count = iov_iter_count(from);
+ }
if ((iocb->ki_pos | count) & (sb->s_blocksize - 1)) {
ret = -EINVAL;
inode_lock(inode);
}
- ret = generic_write_checks(iocb, from);
+ ret = zonefs_write_checks(iocb, from);
if (ret <= 0)
goto inode_unlock;
- iov_iter_truncate(from, zi->i_max_size - iocb->ki_pos);
-
ret = iomap_file_buffered_write(iocb, from, &zonefs_iomap_ops);
if (ret > 0)
iocb->ki_pos += ret;
mutex_lock(&zi->i_truncate_mutex);
- zi->i_wr_refcnt++;
- if (zi->i_wr_refcnt == 1) {
-
+ if (!zi->i_wr_refcnt) {
if (atomic_inc_return(&sbi->s_open_zones) > sbi->s_max_open_zones) {
atomic_dec(&sbi->s_open_zones);
ret = -EBUSY;
if (i_size_read(inode) < zi->i_max_size) {
ret = zonefs_zone_mgmt(inode, REQ_OP_ZONE_OPEN);
if (ret) {
- zi->i_wr_refcnt--;
atomic_dec(&sbi->s_open_zones);
goto unlock;
}
}
}
+ zi->i_wr_refcnt++;
+
unlock:
mutex_unlock(&zi->i_truncate_mutex);
struct acpi_device_pnp {
acpi_bus_id bus_id; /* Object name */
+ int instance_no; /* Instance number of this object */
struct acpi_pnp_type type; /* ID type */
acpi_bus_address bus_address; /* _ADR */
char *unique_id; /* _UID */
* crypto_free_acomp() -- free ACOMPRESS tfm handle
*
* @tfm: ACOMPRESS tfm handle allocated with crypto_alloc_acomp()
+ *
+ * If @tfm is a NULL or error pointer, this function does nothing.
*/
static inline void crypto_free_acomp(struct crypto_acomp *tfm)
{
/**
* crypto_free_aead() - zeroize and free aead handle
* @tfm: cipher handle to be freed
+ *
+ * If @tfm is a NULL or error pointer, this function does nothing.
*/
static inline void crypto_free_aead(struct crypto_aead *tfm)
{
* crypto_free_akcipher() - free AKCIPHER tfm handle
*
* @tfm: AKCIPHER tfm handle allocated with crypto_alloc_akcipher()
+ *
+ * If @tfm is a NULL or error pointer, this function does nothing.
*/
static inline void crypto_free_akcipher(struct crypto_akcipher *tfm)
{
hchacha_block_generic(state, out, nrounds);
}
-void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv);
-static inline void chacha_init_generic(u32 *state, const u32 *key, const u8 *iv)
+static inline void chacha_init_consts(u32 *state)
{
state[0] = 0x61707865; /* "expa" */
state[1] = 0x3320646e; /* "nd 3" */
state[2] = 0x79622d32; /* "2-by" */
state[3] = 0x6b206574; /* "te k" */
+}
+
+void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv);
+static inline void chacha_init_generic(u32 *state, const u32 *key, const u8 *iv)
+{
+ chacha_init_consts(state);
state[4] = key[0];
state[5] = key[1];
state[6] = key[2];
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2021 HiSilicon */
+
+#ifndef _CRYTO_ECC_CURVE_H
+#define _CRYTO_ECC_CURVE_H
+
+#include <linux/types.h>
+
+/**
+ * struct ecc_point - elliptic curve point in affine coordinates
+ *
+ * @x: X coordinate in vli form.
+ * @y: Y coordinate in vli form.
+ * @ndigits: Length of vlis in u64 qwords.
+ */
+struct ecc_point {
+ u64 *x;
+ u64 *y;
+ u8 ndigits;
+};
+
+/**
+ * struct ecc_curve - definition of elliptic curve
+ *
+ * @name: Short name of the curve.
+ * @g: Generator point of the curve.
+ * @p: Prime number, if Barrett's reduction is used for this curve
+ * pre-calculated value 'mu' is appended to the @p after ndigits.
+ * Use of Barrett's reduction is heuristically determined in
+ * vli_mmod_fast().
+ * @n: Order of the curve group.
+ * @a: Curve parameter a.
+ * @b: Curve parameter b.
+ */
+struct ecc_curve {
+ char *name;
+ struct ecc_point g;
+ u64 *p;
+ u64 *n;
+ u64 *a;
+ u64 *b;
+};
+
+/**
+ * ecc_get_curve() - get elliptic curve;
+ * @curve_id: Curves IDs:
+ * defined in 'include/crypto/ecdh.h';
+ *
+ * Returns curve if get curve succssful, NULL otherwise
+ */
+const struct ecc_curve *ecc_get_curve(unsigned int curve_id);
+
+/**
+ * ecc_get_curve25519() - get curve25519 curve;
+ *
+ * Returns curve25519
+ */
+const struct ecc_curve *ecc_get_curve25519(void);
+
+#endif
/* Curves IDs */
#define ECC_CURVE_NIST_P192 0x0001
#define ECC_CURVE_NIST_P256 0x0002
+#define ECC_CURVE_NIST_P384 0x0003
/**
* struct ecdh - define an ECDH private key
*
- * @curve_id: ECC curve the key is based on.
* @key: Private ECDH key
* @key_size: Size of the private ECDH key
*/
struct ecdh {
- unsigned short curve_id;
char *key;
unsigned short key_size;
};
/**
* crypto_free_ahash() - zeroize and free the ahash handle
* @tfm: cipher handle to be freed
+ *
+ * If @tfm is a NULL or error pointer, this function does nothing.
*/
static inline void crypto_free_ahash(struct crypto_ahash *tfm)
{
/**
* crypto_free_shash() - zeroize and free the message digest handle
* @tfm: cipher handle to be freed
+ *
+ * If @tfm is a NULL or error pointer, this function does nothing.
*/
static inline void crypto_free_shash(struct crypto_shash *tfm)
{
* only the ε-almost-∆-universal hash function (not the full MAC) is computed.
*/
-void poly1305_core_setkey(struct poly1305_core_key *key, const u8 *raw_key);
+void poly1305_core_setkey(struct poly1305_core_key *key,
+ const u8 raw_key[POLY1305_BLOCK_SIZE]);
static inline void poly1305_core_init(struct poly1305_state *state)
{
*state = (struct poly1305_state){};
* crypto_free_kpp() - free KPP tfm handle
*
* @tfm: KPP tfm handle allocated with crypto_alloc_kpp()
+ *
+ * If @tfm is a NULL or error pointer, this function does nothing.
*/
static inline void crypto_free_kpp(struct crypto_kpp *tfm)
{
};
};
-void poly1305_init_arch(struct poly1305_desc_ctx *desc, const u8 *key);
-void poly1305_init_generic(struct poly1305_desc_ctx *desc, const u8 *key);
+void poly1305_init_arch(struct poly1305_desc_ctx *desc,
+ const u8 key[POLY1305_KEY_SIZE]);
+void poly1305_init_generic(struct poly1305_desc_ctx *desc,
+ const u8 key[POLY1305_KEY_SIZE]);
static inline void poly1305_init(struct poly1305_desc_ctx *desc, const u8 *key)
{
/**
* crypto_free_rng() - zeroize and free RNG handle
* @tfm: cipher handle to be freed
+ *
+ * If @tfm is a NULL or error pointer, this function does nothing.
*/
static inline void crypto_free_rng(struct crypto_rng *tfm)
{
/**
* crypto_free_skcipher() - zeroize and free cipher handle
* @tfm: cipher handle to be freed
+ *
+ * If @tfm is a NULL or error pointer, this function does nothing.
*/
static inline void crypto_free_skcipher(struct crypto_skcipher *tfm)
{
static inline void ttm_bo_unpin(struct ttm_buffer_object *bo)
{
dma_resv_assert_held(bo->base.resv);
- WARN_ON_ONCE(!bo->pin_count);
WARN_ON_ONCE(!kref_read(&bo->kref));
- --bo->pin_count;
+ if (bo->pin_count)
+ --bo->pin_count;
+ else
+ WARN_ON_ONCE(true);
}
int ttm_mem_evict_first(struct ttm_bo_device *bdev,
/*
* Constant for device tree bindings for Turris Mox module configuration bus
*
- * Copyright (C) 2019 Marek Behun <marek.behun@nic.cz>
+ * Copyright (C) 2019 Marek Behún <kabel@kernel.org>
*/
#ifndef _DT_BINDINGS_BUS_MOXTET_H
return key->payload.data[asym_key_ids];
}
+static inline
+const struct public_key *asymmetric_key_public_key(const struct key *key)
+{
+ return key->payload.data[asym_crypto];
+}
+
extern struct key *find_asymmetric_key(struct key *keyring,
const struct asymmetric_key_id *id_0,
const struct asymmetric_key_id *id_1,
#define restrict_link_by_builtin_and_secondary_trusted restrict_link_by_builtin_trusted
#endif
+extern struct pkcs7_message *pkcs7;
#ifdef CONFIG_SYSTEM_BLACKLIST_KEYRING
extern int mark_hash_blacklisted(const char *hash);
extern int is_hash_blacklisted(const u8 *hash, size_t hash_len,
}
#endif
+#ifdef CONFIG_SYSTEM_REVOCATION_LIST
+extern int add_key_to_revocation_list(const char *data, size_t size);
+extern int is_key_on_revocation_list(struct pkcs7_message *pkcs7);
+#else
+static inline int add_key_to_revocation_list(const char *data, size_t size)
+{
+ return 0;
+}
+static inline int is_key_on_revocation_list(struct pkcs7_message *pkcs7)
+{
+ return -ENOKEY;
+}
+#endif
+
#ifdef CONFIG_IMA_BLACKLIST_KEYRING
extern struct key *ima_blacklist_keyring;
#include <linux/rcupdate.h>
#include <linux/tpm.h>
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) "trusted_key: " fmt
+
#define MIN_KEY_SIZE 32
#define MAX_KEY_SIZE 128
#define MAX_BLOB_SIZE 512
unsigned int key_len;
unsigned int blob_len;
unsigned char migratable;
+ unsigned char old_format;
unsigned char key[MAX_KEY_SIZE + 1];
unsigned char blob[MAX_BLOB_SIZE];
};
uint16_t keytype;
uint32_t keyhandle;
unsigned char keyauth[TPM_DIGEST_SIZE];
+ uint32_t blobauth_len;
unsigned char blobauth[TPM_DIGEST_SIZE];
uint32_t pcrinfo_len;
unsigned char pcrinfo[MAX_PCRINFO_SIZE];
uint32_t policyhandle;
};
+struct trusted_key_ops {
+ /*
+ * flag to indicate if trusted key implementation supports migration
+ * or not.
+ */
+ unsigned char migratable;
+
+ /* Initialize key interface. */
+ int (*init)(void);
+
+ /* Seal a key. */
+ int (*seal)(struct trusted_key_payload *p, char *datablob);
+
+ /* Unseal a key. */
+ int (*unseal)(struct trusted_key_payload *p, char *datablob);
+
+ /* Get a randomized key. */
+ int (*get_random)(unsigned char *key, size_t key_len);
+
+ /* Exit key interface. */
+ void (*exit)(void);
+};
+
+struct trusted_key_source {
+ char *name;
+ struct trusted_key_ops *ops;
+};
+
extern struct key_type key_type_trusted;
+#define TRUSTED_DEBUG 0
+
+#if TRUSTED_DEBUG
+static inline void dump_payload(struct trusted_key_payload *p)
+{
+ pr_info("key_len %d\n", p->key_len);
+ print_hex_dump(KERN_INFO, "key ", DUMP_PREFIX_NONE,
+ 16, 1, p->key, p->key_len, 0);
+ pr_info("bloblen %d\n", p->blob_len);
+ print_hex_dump(KERN_INFO, "blob ", DUMP_PREFIX_NONE,
+ 16, 1, p->blob, p->blob_len, 0);
+ pr_info("migratable %d\n", p->migratable);
+}
+#else
+static inline void dump_payload(struct trusted_key_payload *p)
+{
+}
+#endif
+
#endif /* _KEYS_TRUSTED_TYPE_H */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019-2021 Linaro Ltd.
+ *
+ * Author:
+ * Sumit Garg <sumit.garg@linaro.org>
+ */
+
+#ifndef __TEE_TRUSTED_KEY_H
+#define __TEE_TRUSTED_KEY_H
+
+#include <keys/trusted-type.h>
+
+extern struct trusted_key_ops trusted_key_tee_ops;
+
+#endif
#define LOAD32N(buffer, offset) (*(uint32_t *)&buffer[offset])
#define LOAD16(buffer, offset) (ntohs(*(uint16_t *)&buffer[offset]))
+extern struct trusted_key_ops trusted_key_tpm_ops;
+
struct osapsess {
uint32_t handle;
unsigned char secret[SHA1_DIGEST_SIZE];
#if TPM_DEBUG
static inline void dump_options(struct trusted_key_options *o)
{
- pr_info("trusted_key: sealing key type %d\n", o->keytype);
- pr_info("trusted_key: sealing key handle %0X\n", o->keyhandle);
- pr_info("trusted_key: pcrlock %d\n", o->pcrlock);
- pr_info("trusted_key: pcrinfo %d\n", o->pcrinfo_len);
+ pr_info("sealing key type %d\n", o->keytype);
+ pr_info("sealing key handle %0X\n", o->keyhandle);
+ pr_info("pcrlock %d\n", o->pcrlock);
+ pr_info("pcrinfo %d\n", o->pcrinfo_len);
print_hex_dump(KERN_INFO, "pcrinfo ", DUMP_PREFIX_NONE,
16, 1, o->pcrinfo, o->pcrinfo_len, 0);
}
-static inline void dump_payload(struct trusted_key_payload *p)
-{
- pr_info("trusted_key: key_len %d\n", p->key_len);
- print_hex_dump(KERN_INFO, "key ", DUMP_PREFIX_NONE,
- 16, 1, p->key, p->key_len, 0);
- pr_info("trusted_key: bloblen %d\n", p->blob_len);
- print_hex_dump(KERN_INFO, "blob ", DUMP_PREFIX_NONE,
- 16, 1, p->blob, p->blob_len, 0);
- pr_info("trusted_key: migratable %d\n", p->migratable);
-}
-
static inline void dump_sess(struct osapsess *s)
{
print_hex_dump(KERN_INFO, "trusted-key: handle ", DUMP_PREFIX_NONE,
16, 1, &s->handle, 4, 0);
- pr_info("trusted-key: secret:\n");
+ pr_info("secret:\n");
print_hex_dump(KERN_INFO, "", DUMP_PREFIX_NONE,
16, 1, &s->secret, SHA1_DIGEST_SIZE, 0);
pr_info("trusted-key: enonce:\n");
{
int len;
- pr_info("\ntrusted-key: tpm buffer\n");
+ pr_info("\ntpm buffer\n");
len = LOAD32(buf, TPM_SIZE_OFFSET);
print_hex_dump(KERN_INFO, "", DUMP_PREFIX_NONE, 16, 1, buf, len, 0);
}
{
}
-static inline void dump_payload(struct trusted_key_payload *p)
-{
-}
-
static inline void dump_sess(struct osapsess *s)
{
}
#define ARMV8_PMU_CYCLE_IDX (ARMV8_PMU_MAX_COUNTERS - 1)
#define ARMV8_PMU_MAX_COUNTER_PAIRS ((ARMV8_PMU_MAX_COUNTERS + 1) >> 1)
+DECLARE_STATIC_KEY_FALSE(kvm_arm_pmu_available);
+
+static __always_inline bool kvm_arm_support_pmu_v3(void)
+{
+ return static_branch_likely(&kvm_arm_pmu_available);
+}
+
#ifdef CONFIG_HW_PERF_EVENTS
struct kvm_pmc {
void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val);
void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
u64 select_idx);
-bool kvm_arm_support_pmu_v3(void);
int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu,
struct kvm_device_attr *attr);
int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu,
static inline void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) {}
static inline void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu,
u64 data, u64 select_idx) {}
-static inline bool kvm_arm_support_pmu_v3(void) { return false; }
static inline int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu,
struct kvm_device_attr *attr)
{
void __acpi_unmap_table(void __iomem *map, unsigned long size);
int early_acpi_boot_init(void);
int acpi_boot_init (void);
+void acpi_boot_table_prepare (void);
void acpi_boot_table_init (void);
int acpi_mps_check (void);
int acpi_numa_init (void);
+int acpi_locate_initial_tables (void);
+void acpi_reserve_initial_tables (void);
+void acpi_table_init_complete (void);
int acpi_table_init (void);
int acpi_table_parse(char *id, acpi_tbl_table_handler handler);
int __init acpi_table_parse_entries(char *id, unsigned long table_size,
return 0;
}
+static inline void acpi_boot_table_prepare(void)
+{
+}
+
static inline void acpi_boot_table_init(void)
{
- return;
}
static inline int acpi_mps_check(void)
#if defined(CONFIG_ACPI) && defined(CONFIG_GPIOLIB)
bool acpi_gpio_get_irq_resource(struct acpi_resource *ares,
struct acpi_resource_gpio **agpio);
-int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index);
+int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *name, int index);
#else
static inline bool acpi_gpio_get_irq_resource(struct acpi_resource *ares,
struct acpi_resource_gpio **agpio)
{
return false;
}
-static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index)
+static inline int acpi_dev_gpio_irq_get_by(struct acpi_device *adev,
+ const char *name, int index)
{
return -ENXIO;
}
#endif
+static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index)
+{
+ return acpi_dev_gpio_irq_get_by(adev, NULL, index);
+}
+
/* Device properties */
#ifdef CONFIG_ACPI
#define amba_get_drvdata(d) dev_get_drvdata(&d->dev)
#define amba_set_drvdata(d,p) dev_set_drvdata(&d->dev, p)
+#ifdef CONFIG_ARM_AMBA
int amba_driver_register(struct amba_driver *);
void amba_driver_unregister(struct amba_driver *);
+#else
+static inline int amba_driver_register(struct amba_driver *drv)
+{
+ return -EINVAL;
+}
+static inline void amba_driver_unregister(struct amba_driver *drv)
+{
+}
+#endif
+
struct amba_device *amba_device_alloc(const char *, resource_size_t, size_t);
void amba_device_put(struct amba_device *);
int amba_device_add(struct amba_device *, struct resource *);
/*
* rWTM BIU Mailbox driver for Armada 37xx
*
- * Author: Marek Behun <marek.behun@nic.cz>
+ * Author: Marek Behún <kabel@kernel.org>
*/
#ifndef _LINUX_ARMADA_37XX_RWTM_MAILBOX_H_
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef _LINUX_ASN1_ENCODER_H
+#define _LINUX_ASN1_ENCODER_H
+
+#include <linux/types.h>
+#include <linux/asn1.h>
+#include <linux/asn1_ber_bytecode.h>
+#include <linux/bug.h>
+
+#define asn1_oid_len(oid) (sizeof(oid)/sizeof(u32))
+unsigned char *
+asn1_encode_integer(unsigned char *data, const unsigned char *end_data,
+ s64 integer);
+unsigned char *
+asn1_encode_oid(unsigned char *data, const unsigned char *end_data,
+ u32 oid[], int oid_len);
+unsigned char *
+asn1_encode_tag(unsigned char *data, const unsigned char *end_data,
+ u32 tag, const unsigned char *string, int len);
+unsigned char *
+asn1_encode_octet_string(unsigned char *data,
+ const unsigned char *end_data,
+ const unsigned char *string, u32 len);
+unsigned char *
+asn1_encode_sequence(unsigned char *data, const unsigned char *end_data,
+ const unsigned char *seq, int len);
+unsigned char *
+asn1_encode_boolean(unsigned char *data, const unsigned char *end_data,
+ bool val);
+
+#endif
const char *type; /* device type name */
int number; /* device index */
void *dev_data; /* per-device data */
- void *phy_data; /* private PHY date */
+ void *phy_data; /* private PHY data */
unsigned long flags; /* device flags (ATM_DF_*) */
struct list_head local; /* local ATM addresses */
struct list_head lecs; /* LECS ATM addresses learned via ILMI */
u16 vsi_id;
u16 key_len;
u8 key[1]; /* RSS hash key, packed bytes */
- u8 pad[1];
};
VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_key);
u16 vsi_id;
u16 lut_entries;
u8 lut[1]; /* RSS lookup table */
- u8 pad[1];
};
VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_lut);
#define BIO_BUG_ON
#endif
-#define BIO_MAX_PAGES 256U
+#define BIO_MAX_VECS 256U
static inline unsigned int bio_max_segs(unsigned int nr_segs)
{
- return min(nr_segs, BIO_MAX_PAGES);
+ return min(nr_segs, BIO_MAX_VECS);
}
#define bio_prio(bio) (bio)->bi_ioprio
#define RQF_ELVPRIV ((__force req_flags_t)(1 << 12))
/* account into disk and partition IO statistics */
#define RQF_IO_STAT ((__force req_flags_t)(1 << 13))
-/* request came from our alloc pool */
-#define RQF_ALLOCED ((__force req_flags_t)(1 << 14))
/* runtime pm request */
#define RQF_PM ((__force req_flags_t)(1 << 15))
/* on IO scheduler merge hash */
#include <linux/preempt.h>
-#ifdef CONFIG_TRACE_IRQFLAGS
+#if defined(CONFIG_PREEMPT_RT) || defined(CONFIG_TRACE_IRQFLAGS)
extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt);
#else
static __always_inline void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
__local_bh_enable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET);
}
+#ifdef CONFIG_PREEMPT_RT
+extern bool local_bh_blocked(void);
+#else
+static inline bool local_bh_blocked(void) { return false; }
+#endif
+
#endif /* _LINUX_BH_H */
#include <linux/capability.h>
#include <linux/sched/mm.h>
#include <linux/slab.h>
+#include <linux/percpu-refcount.h>
struct bpf_verifier_env;
struct bpf_verifier_log;
struct bpf_local_storage_map;
struct kobject;
struct mem_cgroup;
+struct module;
extern struct idr btf_idr;
extern spinlock_t btf_idr_lock;
* fentry = a set of program to run before calling original function
* fexit = a set of program to run after original function
*/
-int arch_prepare_bpf_trampoline(void *image, void *image_end,
+struct bpf_tramp_image;
+int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end,
const struct btf_func_model *m, u32 flags,
struct bpf_tramp_progs *tprogs,
void *orig_call);
void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start);
u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog);
void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start);
+void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr);
+void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr);
struct bpf_ksym {
unsigned long start;
BPF_TRAMP_REPLACE, /* more than MAX */
};
+struct bpf_tramp_image {
+ void *image;
+ struct bpf_ksym ksym;
+ struct percpu_ref pcref;
+ void *ip_after_call;
+ void *ip_epilogue;
+ union {
+ struct rcu_head rcu;
+ struct work_struct work;
+ };
+};
+
struct bpf_trampoline {
/* hlist for trampoline_table */
struct hlist_node hlist;
/* Number of attached programs. A counter per kind. */
int progs_cnt[BPF_TRAMP_MAX];
/* Executable image of trampoline */
- void *image;
+ struct bpf_tramp_image *cur_image;
u64 selector;
- struct bpf_ksym ksym;
+ struct module *mod;
};
struct bpf_attach_target_info {
void bpf_image_ksym_del(struct bpf_ksym *ksym);
void bpf_ksym_add(struct bpf_ksym *ksym);
void bpf_ksym_del(struct bpf_ksym *ksym);
+int bpf_jit_charge_modmem(u32 pages);
+void bpf_jit_uncharge_modmem(u32 pages);
#else
static inline int bpf_trampoline_link_prog(struct bpf_prog *prog,
struct bpf_trampoline *tr)
bool func_proto_unreliable;
bool sleepable;
bool tail_call_reachable;
- enum bpf_tramp_prog_type trampoline_prog_type;
struct hlist_node tramp_hlist;
/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
const struct btf_type *attach_func_proto;
_ret; \
})
-#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null) \
+#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null, set_cg_storage) \
({ \
struct bpf_prog_array_item *_item; \
struct bpf_prog *_prog; \
goto _out; \
_item = &_array->items[0]; \
while ((_prog = READ_ONCE(_item->prog))) { \
- bpf_cgroup_storage_set(_item->cgroup_storage); \
+ if (set_cg_storage) \
+ bpf_cgroup_storage_set(_item->cgroup_storage); \
_ret &= func(_prog, ctx); \
_item++; \
} \
})
#define BPF_PROG_RUN_ARRAY(array, ctx, func) \
- __BPF_PROG_RUN_ARRAY(array, ctx, func, false)
+ __BPF_PROG_RUN_ARRAY(array, ctx, func, false, true)
#define BPF_PROG_RUN_ARRAY_CHECK(array, ctx, func) \
- __BPF_PROG_RUN_ARRAY(array, ctx, func, true)
+ __BPF_PROG_RUN_ARRAY(array, ctx, func, true, false)
#ifdef CONFIG_BPF_SYSCALL
DECLARE_PER_CPU(int, bpf_prog_active);
static inline void can_skb_set_owner(struct sk_buff *skb, struct sock *sk)
{
- if (sk) {
- sock_hold(sk);
+ /* If the socket has already been closed by user space, the
+ * refcount may already be 0 (and the socket will be freed
+ * after the last TX skb has been freed). So only increase
+ * socket refcount if the refcount is > 0.
+ */
+ if (sk && refcount_inc_not_zero(&sk->sk_refcnt)) {
skb->destructor = sock_efree;
skb->sk = sk;
}
* @mark_unstable: Optional function to inform the clocksource driver that
* the watchdog marked the clocksource unstable
* @tick_stable: Optional function called periodically from the watchdog
- * code to provide stable syncrhonization points
+ * code to provide stable synchronization points
* @wd_list: List head to enqueue into the watchdog list (internal)
* @cs_last: Last clocksource value for clocksource watchdog
* @wd_last: Last watchdog value corresponding to @cs_last
#define __no_sanitize_thread
#endif
+#if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP)
+#define __HAVE_BUILTIN_BSWAP32__
+#define __HAVE_BUILTIN_BSWAP64__
+#define __HAVE_BUILTIN_BSWAP16__
+#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */
+
#if __has_feature(undefined_behavior_sanitizer)
/* GCC does not have __SANITIZE_UNDEFINED__ */
#define __no_sanitize_undefined \
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifdef __LINUX_COMPILER_VERSION_H
+#error "Please do not include <linux/compiler-version.h>. This is done by the build system."
+#endif
+#define __LINUX_COMPILER_VERSION_H
+
+/*
+ * This header exists to force full rebuild when the compiler is upgraded.
+ *
+ * When fixdep scans this, it will find this string "CONFIG_CC_VERSION_TEXT"
+ * and add dependency on include/config/cc/version/text.h, which is touched
+ * by Kconfig when the version string from the compiler changes.
+ */
{
}
+static inline int add_cpu(unsigned int cpu) { return 0;}
+
#endif /* CONFIG_SMP */
extern struct bus_type cpu_subsys;
static inline void lockdep_assert_cpus_held(void) { }
static inline void cpu_hotplug_disable(void) { }
static inline void cpu_hotplug_enable(void) { }
+static inline int remove_cpu(unsigned int cpu) { return -EPERM; }
static inline void smp_shutdown_nonboot_cpus(unsigned int primary_cpu) { }
#endif /* !CONFIG_HOTPLUG_CPU */
CPUHP_AP_RISCV_TIMER_STARTING,
CPUHP_AP_CLINT_TIMER_STARTING,
CPUHP_AP_CSKY_TIMER_STARTING,
+ CPUHP_AP_TI_GP_TIMER_STARTING,
CPUHP_AP_HYPERV_TIMER_STARTING,
CPUHP_AP_KVM_STARTING,
CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING,
CPUHP_AP_PERF_ARM_HISI_DDRC_ONLINE,
CPUHP_AP_PERF_ARM_HISI_HHA_ONLINE,
CPUHP_AP_PERF_ARM_HISI_L3_ONLINE,
+ CPUHP_AP_PERF_ARM_HISI_PA_ONLINE,
+ CPUHP_AP_PERF_ARM_HISI_SLLC_ONLINE,
CPUHP_AP_PERF_ARM_L2X0_ONLINE,
CPUHP_AP_PERF_ARM_QCOM_L2_ONLINE,
CPUHP_AP_PERF_ARM_QCOM_L3_ONLINE,
#define dm_target_passes_integrity(type) ((type)->features & DM_TARGET_PASSES_INTEGRITY)
/*
- * Indicates that a target supports host-managed zoned block devices.
+ * Indicates support for zoned block devices:
+ * - DM_TARGET_ZONED_HM: the target also supports host-managed zoned
+ * block devices but does not support combining different zoned models.
+ * - DM_TARGET_MIXED_ZONED_MODEL: the target supports combining multiple
+ * devices with different zoned models.
*/
#ifdef CONFIG_BLK_DEV_ZONED
#define DM_TARGET_ZONED_HM 0x00000040
#define DM_TARGET_PASSES_CRYPTO 0x00000100
#define dm_target_passes_crypto(type) ((type)->features & DM_TARGET_PASSES_CRYPTO)
+#ifdef CONFIG_BLK_DEV_ZONED
+#define DM_TARGET_MIXED_ZONED_MODEL 0x00000200
+#define dm_target_supports_mixed_zoned_model(type) \
+ ((type)->features & DM_TARGET_MIXED_ZONED_MODEL)
+#else
+#define DM_TARGET_MIXED_ZONED_MODEL 0x00000000
+#define dm_target_supports_mixed_zoned_model(type) (false)
+#endif
+
struct dm_target {
struct dm_table *table;
struct target_type *type;
*/
typedef guid_t efi_guid_t __aligned(__alignof__(u32));
-#define EFI_GUID(a,b,c,d0,d1,d2,d3,d4,d5,d6,d7) \
- GUID_INIT(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7)
+#define EFI_GUID(a, b, c, d...) (efi_guid_t){ { \
+ (a) & 0xff, ((a) >> 8) & 0xff, ((a) >> 16) & 0xff, ((a) >> 24) & 0xff, \
+ (b) & 0xff, ((b) >> 8) & 0xff, \
+ (c) & 0xff, ((c) >> 8) & 0xff, d } }
/*
* Generic EFI table header
*
* This is a combination of syscall_exit_to_user_mode_work() (1,2) and
* exit_to_user_mode(). This function is preferred unless there is a
- * compelling architectural reason to use the seperate functions.
+ * compelling architectural reason to use the separate functions.
*/
void syscall_exit_to_user_mode(struct pt_regs *regs);
* irqentry_exit_to_user_mode - Interrupt exit work
* @regs: Pointer to current's pt_regs
*
- * Invoked with interrupts disbled and fully valid regs. Returns with all
+ * Invoked with interrupts disabled and fully valid regs. Returns with all
* work handled, interrupts disabled such that the caller can immediately
* switch to user mode. Called from architecture specific interrupt
* handling code.
int ethtool_op_get_ts_info(struct net_device *dev, struct ethtool_ts_info *eti);
-/**
- * struct ethtool_link_ext_state_info - link extended state and substate.
- */
+/* Link extended state and substate. */
struct ethtool_link_ext_state_info {
enum ethtool_link_ext_state link_ext_state;
union {
__ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising);
} link_modes;
u32 lanes;
- enum ethtool_link_mode_bit_indices link_mode;
};
/**
* do not attach ext_substate attribute to netlink message). If link_ext_state
* and link_ext_substate are unknown, return -ENODATA. If not implemented,
* link_ext_state and link_ext_substate will not be sent to userspace.
+ * @get_eeprom_len: Read range of EEPROM addresses for validation of
+ * @get_eeprom and @set_eeprom requests.
+ * Returns 0 if device does not support EEPROM access.
* @get_eeprom: Read data from the device EEPROM.
* Should fill in the magic field. Don't need to check len for zero
* or wraparound. Fill in the data argument with the eeprom values
* @get_module_eeprom: Get the eeprom information from the plug-in module
* @get_eee: Get Energy-Efficient (EEE) supported and status.
* @set_eee: Set EEE status (enable/disable) as well as LPI timers.
+ * @get_tunable: Read the value of a driver / device tunable.
+ * @set_tunable: Set the value of a driver / device tunable.
* @get_per_queue_coalesce: Get interrupt coalescing parameters per queue.
* It must check that the given queue number is valid. If neither a RX nor
* a TX queue has this number, return -EINVAL. If only a RX queue or a TX
* @get_sset_count: Get number of strings that @get_strings will write.
* @get_strings: Return a set of strings that describe the requested objects
* @get_stats: Return extended statistics about the PHY device.
- * @start_cable_test - Start a cable test
- * @start_cable_test_tdr - Start a Time Domain Reflectometry cable test
+ * @start_cable_test: Start a cable test
+ * @start_cable_test_tdr: Start a Time Domain Reflectometry cable test
*
* All operations are optional (i.e. the function pointer may be set to %NULL)
* and callers must take this into account. Callers must hold the RTNL lock.
*/
void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops);
+/*
+ * ethtool_params_from_link_mode - Derive link parameters from a given link mode
+ * @link_ksettings: Link parameters to be derived from the link mode
+ * @link_mode: Link mode
+ */
+void
+ethtool_params_from_link_mode(struct ethtool_link_ksettings *link_ksettings,
+ enum ethtool_link_mode_bit_indices link_mode);
#endif /* _LINUX_ETHTOOL_H */
struct extcon_dev *edev, unsigned int id,
struct notifier_block *nb) { }
+static inline int extcon_register_notifier_all(struct extcon_dev *edev,
+ struct notifier_block *nb)
+{
+ return 0;
+}
+
+static inline int extcon_unregister_notifier_all(struct extcon_dev *edev,
+ struct notifier_block *nb)
+{
+ return 0;
+}
+
+static inline int devm_extcon_register_notifier_all(struct device *dev,
+ struct extcon_dev *edev,
+ struct notifier_block *nb)
+{
+ return 0;
+}
+
+static inline void devm_extcon_unregister_notifier_all(struct device *dev,
+ struct extcon_dev *edev,
+ struct notifier_block *nb) { }
+
static inline struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name)
{
return ERR_PTR(-ENODEV);
* COMMAND_RECONFIG_FLAG_PARTIAL:
* Set to FPGA configuration type (full or partial).
*/
-#define COMMAND_RECONFIG_FLAG_PARTIAL 1
+#define COMMAND_RECONFIG_FLAG_PARTIAL 0
/*
* Timeout settings for service clients:
* get GpioIo type explicitly, this quirk may be used.
*/
#define ACPI_GPIO_QUIRK_ONLY_GPIOIO BIT(1)
+/* Use given pin as an absolute GPIO number in the system */
+#define ACPI_GPIO_QUIRK_ABSOLUTE_NUMBER BIT(2)
unsigned int quirks;
};
#include <linux/preempt.h>
#include <linux/lockdep.h>
#include <linux/ftrace_irq.h>
+#include <linux/sched.h>
#include <linux/vtime.h>
#include <asm/hardirq.h>
int host1x_device_init(struct host1x_device *device);
int host1x_device_exit(struct host1x_device *device);
-int host1x_client_register(struct host1x_client *client);
+int __host1x_client_register(struct host1x_client *client,
+ struct lock_class_key *key);
+#define host1x_client_register(class) \
+ ({ \
+ static struct lock_class_key __key; \
+ __host1x_client_register(class, &__key); \
+ })
+
int host1x_client_unregister(struct host1x_client *client);
int host1x_client_suspend(struct host1x_client *client);
return !cgroup_subsys_enabled(hugetlb_cgrp_subsys);
}
+static inline void hugetlb_cgroup_put_rsvd_cgroup(struct hugetlb_cgroup *h_cg)
+{
+ css_put(&h_cg->css);
+}
+
extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
struct hugetlb_cgroup **ptr);
extern int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages,
extern void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv,
struct file_region *rg,
- unsigned long nr_pages);
+ unsigned long nr_pages,
+ bool region_del);
extern void hugetlb_cgroup_file_init(void) __init;
extern void hugetlb_cgroup_migrate(struct page *oldhpage,
#else
static inline void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv,
struct file_region *rg,
- unsigned long nr_pages)
+ unsigned long nr_pages,
+ bool region_del)
{
}
return true;
}
+static inline void hugetlb_cgroup_put_rsvd_cgroup(struct hugetlb_cgroup *h_cg)
+{
+}
+
static inline int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
struct hugetlb_cgroup **ptr)
{
if (likely(success)) {
struct vlan_pcpu_stats *pcpu_stats;
- pcpu_stats = this_cpu_ptr(vlan->pcpu_stats);
+ pcpu_stats = get_cpu_ptr(vlan->pcpu_stats);
u64_stats_update_begin(&pcpu_stats->syncp);
pcpu_stats->rx_packets++;
pcpu_stats->rx_bytes += len;
if (multicast)
pcpu_stats->rx_multicast++;
u64_stats_update_end(&pcpu_stats->syncp);
+ put_cpu_ptr(vlan->pcpu_stats);
} else {
this_cpu_inc(vlan->pcpu_stats->rx_errors);
}
* interrupt handler after suspending interrupts. For system
* wakeup devices users need to implement wakeup detection in
* their interrupt handlers.
+ * IRQF_NO_AUTOEN - Don't enable IRQ or NMI automatically when users request it.
+ * Users will enable it explicitly by enable_irq() or enable_nmi()
+ * later.
*/
#define IRQF_SHARED 0x00000080
#define IRQF_PROBE_SHARED 0x00000100
#define IRQF_NO_THREAD 0x00010000
#define IRQF_EARLY_RESUME 0x00020000
#define IRQF_COND_SUSPEND 0x00040000
+#define IRQF_NO_AUTOEN 0x00080000
#define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD)
TASKLET_STATE_RUN /* Tasklet is running (SMP only) */
};
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)
static inline int tasklet_trylock(struct tasklet_struct *t)
{
return !test_and_set_bit(TASKLET_STATE_RUN, &(t)->state);
}
-static inline void tasklet_unlock(struct tasklet_struct *t)
-{
- smp_mb__before_atomic();
- clear_bit(TASKLET_STATE_RUN, &(t)->state);
-}
+void tasklet_unlock(struct tasklet_struct *t);
+void tasklet_unlock_wait(struct tasklet_struct *t);
+void tasklet_unlock_spin_wait(struct tasklet_struct *t);
-static inline void tasklet_unlock_wait(struct tasklet_struct *t)
-{
- while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { barrier(); }
-}
#else
-#define tasklet_trylock(t) 1
-#define tasklet_unlock_wait(t) do { } while (0)
-#define tasklet_unlock(t) do { } while (0)
+static inline int tasklet_trylock(struct tasklet_struct *t) { return 1; }
+static inline void tasklet_unlock(struct tasklet_struct *t) { }
+static inline void tasklet_unlock_wait(struct tasklet_struct *t) { }
+static inline void tasklet_unlock_spin_wait(struct tasklet_struct *t) { }
#endif
extern void __tasklet_schedule(struct tasklet_struct *t);
smp_mb__after_atomic();
}
+/*
+ * Do not use in new code. Disabling tasklets from atomic contexts is
+ * error prone and should be avoided.
+ */
+static inline void tasklet_disable_in_atomic(struct tasklet_struct *t)
+{
+ tasklet_disable_nosync(t);
+ tasklet_unlock_spin_wait(t);
+ smp_mb();
+}
+
static inline void tasklet_disable(struct tasklet_struct *t)
{
tasklet_disable_nosync(t);
}
extern void tasklet_kill(struct tasklet_struct *t);
-extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu);
extern void tasklet_init(struct tasklet_struct *t,
void (*func)(unsigned long), unsigned long data);
extern void tasklet_setup(struct tasklet_struct *t,
#include <linux/sched.h>
#include <linux/xarray.h>
-struct io_wq_work_node {
- struct io_wq_work_node *next;
-};
-
-struct io_wq_work_list {
- struct io_wq_work_node *first;
- struct io_wq_work_node *last;
-};
-
-struct io_uring_task {
- /* submission side */
- struct xarray xa;
- struct wait_queue_head wait;
- struct file *last;
- void *io_wq;
- struct percpu_counter inflight;
- atomic_t in_idle;
- bool sqpoll;
-
- spinlock_t task_lock;
- struct io_wq_work_list task_list;
- unsigned long task_state;
- struct callback_head task_work;
-};
-
#if defined(CONFIG_IO_URING)
struct sock *io_uring_get_socket(struct file *file);
void __io_uring_task_cancel(void);
* IRQ_SET_MASK_NOCPY - OK, chip did update irq_common_data.affinity
* IRQ_SET_MASK_OK_DONE - Same as IRQ_SET_MASK_OK for core. Special code to
* support stacked irqchips, which indicates skipping
- * all descendent irqchips.
+ * all descendant irqchips.
*/
enum {
IRQ_SET_MASK_OK = 0,
/*
* Must only be called of irqchip.irq_set_affinity() or low level
- * hieararchy domain allocation functions.
+ * hierarchy domain allocation functions.
*/
static inline void irqd_set_single_target(struct irq_data *d)
{
*/
extern void (*handle_arch_irq)(struct pt_regs *) __ro_after_init;
#else
+#ifndef set_handle_irq
#define set_handle_irq(handle_irq) \
do { \
(void)handle_irq; \
WARN_ON(1); \
} while (0)
#endif
+#endif
#endif /* _LINUX_IRQ_H */
const struct irq_domain_ops *vpe_ops,
const struct irq_domain_ops *sgi_ops);
+bool gic_cpuif_has_vsgi(void);
+
#endif
* @last_unhandled: aging timer for unhandled count
* @irqs_unhandled: stats field for spurious unhandled interrupts
* @threads_handled: stats field for deferred spurious detection of threaded handlers
- * @threads_handled_last: comparator field for deferred spurious detection of theraded handlers
+ * @threads_handled_last: comparator field for deferred spurious detection of threaded handlers
* @lock: locking for SMP
* @affinity_hint: hint to user space for preferred irq affinity
* @affinity_notify: context for notification of affinity changes
* setting up one or more generic chips for interrupt controllers
* drivers using the generic chip library which uses this pointer.
* @parent: Pointer to parent irq_domain to support hierarchy irq_domains
- * @debugfs_file: dentry for the domain debugfs file
*
* Revmap data, used internally by irq_domain
* @revmap_direct_max_irq: The largest hwirq that can be set for controllers that
#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
struct irq_domain *parent;
#endif
-#ifdef CONFIG_GENERIC_IRQ_DEBUGFS
- struct dentry *debugfs_file;
-#endif
/* reverse map data. The linear map gets appended to the irq_domain */
irq_hw_number_t hwirq_max;
extern unsigned int irq_find_mapping(struct irq_domain *host,
irq_hw_number_t hwirq);
extern unsigned int irq_create_direct_mapping(struct irq_domain *host);
-extern int irq_create_strict_mappings(struct irq_domain *domain,
- unsigned int irq_base,
- irq_hw_number_t hwirq_base, int count);
-
-static inline int irq_create_identity_mapping(struct irq_domain *host,
- irq_hw_number_t hwirq)
-{
- return irq_create_strict_mappings(host, hwirq, hwirq, 1);
-}
extern const struct irq_domain_ops irq_domain_simple_ops;
[0 ... (count) - 1] = STATIC_KEY_FALSE_INIT, \
}
+#define _DEFINE_STATIC_KEY_1(name) DEFINE_STATIC_KEY_TRUE(name)
+#define _DEFINE_STATIC_KEY_0(name) DEFINE_STATIC_KEY_FALSE(name)
+#define DEFINE_STATIC_KEY_MAYBE(cfg, name) \
+ __PASTE(_DEFINE_STATIC_KEY_, IS_ENABLED(cfg))(name)
+
+#define _DEFINE_STATIC_KEY_RO_1(name) DEFINE_STATIC_KEY_TRUE_RO(name)
+#define _DEFINE_STATIC_KEY_RO_0(name) DEFINE_STATIC_KEY_FALSE_RO(name)
+#define DEFINE_STATIC_KEY_MAYBE_RO(cfg, name) \
+ __PASTE(_DEFINE_STATIC_KEY_RO_, IS_ENABLED(cfg))(name)
+
+#define _DECLARE_STATIC_KEY_1(name) DECLARE_STATIC_KEY_TRUE(name)
+#define _DECLARE_STATIC_KEY_0(name) DECLARE_STATIC_KEY_FALSE(name)
+#define DECLARE_STATIC_KEY_MAYBE(cfg, name) \
+ __PASTE(_DECLARE_STATIC_KEY_, IS_ENABLED(cfg))(name)
+
extern bool ____wrong_branch_error(void);
#define static_key_enabled(x) \
#endif /* CONFIG_JUMP_LABEL */
+#define static_branch_maybe(config, x) \
+ (IS_ENABLED(config) ? static_branch_likely(x) \
+ : static_branch_unlikely(x))
+
/*
* Advanced usage; refcount, branch is enabled when: count != 0
*/
#endif /* CONFIG_KASAN */
-#if defined(CONFIG_KASAN) && CONFIG_KASAN_STACK
+#if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK)
void kasan_unpoison_task_stack(struct task_struct *task);
#else
static inline void kasan_unpoison_task_stack(struct task_struct *task) {}
#endif /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS*/
+#ifdef CONFIG_KASAN_HW_TAGS
+
+void kasan_report_async(void);
+
+#endif /* CONFIG_KASAN_HW_TAGS */
+
#ifdef CONFIG_KASAN_SW_TAGS
void __init kasan_init_sw_tags(void);
#else
#ifndef __LINUX_KCONFIG_H
#define __LINUX_KCONFIG_H
-/* CONFIG_CC_VERSION_TEXT (Do not delete this comment. See help in Kconfig) */
-
#include <generated/autoconf.h>
#ifdef CONFIG_CPU_BIG_ENDIAN
/* Marvel 88E1111 in Finisar SFP module with modified PHY ID */
#define MARVELL_PHY_ID_88E1111_FINISAR 0x01ff0cc0
-/* The MV88e6390 Ethernet switch contains embedded PHYs. These PHYs do
+/* These Ethernet switch families contain embedded PHYs, but they do
* not have a model ID. So the switch driver traps reads to the ID2
* register and returns the switch family ID
*/
-#define MARVELL_PHY_ID_88E6390 0x01410f90
+#define MARVELL_PHY_ID_88E6341_FAMILY 0x01410f41
+#define MARVELL_PHY_ID_88E6390_FAMILY 0x01410f90
#define MARVELL_PHY_FAMILY_ID(id) ((id) >> 4)
/*
* Set the allocation direction to bottom-up or top-down.
*/
-static inline void memblock_set_bottom_up(bool enable)
+static inline __init_memblock void memblock_set_bottom_up(bool enable)
{
memblock.bottom_up = enable;
}
* if this is true, that said, memblock will allocate memory
* in bottom-up direction.
*/
-static inline bool memblock_bottom_up(void)
+static inline __init_memblock bool memblock_bottom_up(void)
{
return memblock.bottom_up;
}
rcu_read_unlock();
}
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-void mem_cgroup_split_huge_fixup(struct page *head);
-#endif
+void split_page_memcg(struct page *head, unsigned int nr);
#else /* CONFIG_MEMCG */
return 0;
}
-static inline void mem_cgroup_split_huge_fixup(struct page *head)
+static inline void split_page_memcg(struct page *head, unsigned int nr)
{
}
u8 reserved_at_60[0x18];
u8 log_max_ft_num[0x8];
- u8 reserved_at_80[0x18];
+ u8 reserved_at_80[0x10];
+ u8 log_max_flow_counter[0x8];
u8 log_max_destination[0x8];
- u8 log_max_flow_counter[0x8];
- u8 reserved_at_a8[0x10];
+ u8 reserved_at_a0[0x18];
u8 log_max_flow[0x8];
u8 reserved_at_c0[0x40];
u8 fec_override_admin_100g_2x[0x10];
u8 fec_override_admin_50g_1x[0x10];
+
+ u8 reserved_at_140[0x140];
};
struct mlx5_ifc_ppcnt_reg_bits {
struct mlx5_ifc_bufferx_reg_bits buffer[10];
- u8 reserved_at_2e0[0x40];
+ u8 reserved_at_2e0[0x80];
};
struct mlx5_ifc_qtct_reg_bits {
}
}
+static inline int mlx5_get_qp_default_ts(struct mlx5_core_dev *dev)
+{
+ return !MLX5_CAP_ROCE(dev, qp_ts_format) ?
+ MLX5_QPC_TIMESTAMP_FORMAT_FREE_RUNNING :
+ MLX5_QPC_TIMESTAMP_FORMAT_DEFAULT;
+}
+
#endif /* MLX5_QP_H */
GUP_PIN_COUNTING_BIAS;
}
+static inline bool is_cow_mapping(vm_flags_t flags)
+{
+ return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
+}
+
+/*
+ * This should most likely only be called during fork() to see whether we
+ * should break the cow immediately for a page on the src mm.
+ */
+static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma,
+ struct page *page)
+{
+ if (!is_cow_mapping(vma->vm_flags))
+ return false;
+
+ if (!atomic_read(&vma->vm_mm->has_pinned))
+ return false;
+
+ return page_maybe_dma_pinned(page);
+}
+
#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
#define SECTION_IN_PAGE_FLAGS
#endif
#if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
+/*
+ * KASAN per-page tags are stored xor'ed with 0xff. This allows to avoid
+ * setting tags for all pages to native kernel tag value 0xff, as the default
+ * value 0x00 maps to 0xff.
+ */
+
static inline u8 page_kasan_tag(const struct page *page)
{
- if (kasan_enabled())
- return (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK;
- return 0xff;
+ u8 tag = 0xff;
+
+ if (kasan_enabled()) {
+ tag = (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK;
+ tag ^= 0xff;
+ }
+
+ return tag;
}
static inline void page_kasan_tag_set(struct page *page, u8 tag)
{
if (kasan_enabled()) {
+ tag ^= 0xff;
page->flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT);
page->flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT;
}
static inline void kernel_unpoison_pages(struct page *page, int numpages) { }
#endif
-DECLARE_STATIC_KEY_FALSE(init_on_alloc);
+DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, init_on_alloc);
static inline bool want_init_on_alloc(gfp_t flags)
{
- if (static_branch_unlikely(&init_on_alloc))
+ if (static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON,
+ &init_on_alloc))
return true;
return flags & __GFP_ZERO;
}
-DECLARE_STATIC_KEY_FALSE(init_on_free);
+DECLARE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free);
static inline bool want_init_on_free(void)
{
- return static_branch_unlikely(&init_on_free);
+ return static_branch_maybe(CONFIG_INIT_ON_FREE_DEFAULT_ON,
+ &init_on_free);
}
extern bool _debug_pagealloc_enabled_early;
#endif
#define AT_VECTOR_SIZE (2*(AT_VECTOR_SIZE_ARCH + AT_VECTOR_SIZE_BASE + 1))
+#define INIT_PASID 0
struct address_space;
struct mem_cgroup;
* the last refcount is dropped.
*
* If blockable argument is set to false then the callback cannot
- * sleep and has to return with -EAGAIN. 0 should be returned
- * otherwise. Please note that if invalidate_range_start approves
- * a non-blocking behavior then the same applies to
- * invalidate_range_end.
- *
+ * sleep and has to return with -EAGAIN if sleeping would be required.
+ * 0 should be returned otherwise. Please note that notifiers that can
+ * fail invalidate_range_start are not allowed to implement
+ * invalidate_range_end, as there is no mechanism for informing the
+ * notifier that its start failed.
*/
int (*invalidate_range_start)(struct mmu_notifier *subscription,
const struct mmu_notifier_range *range);
#include <linux/percpu.h>
#include <asm/module.h>
-/* Not Yet Implemented */
-#define MODULE_SUPPORTED_DEVICE(name)
-
#define MODULE_NAME_LEN MAX_PARAM_PREFIX_LEN
struct modversion_info {
/*
* Turris Mox module configuration bus driver
*
- * Copyright (C) 2019 Marek Behun <marek.behun@nic.cz>
+ * Copyright (C) 2019 Marek Behún <kabel@kernel.org>
*/
#ifndef __LINUX_MOXTET_H
# define mutex_lock_interruptible_nested(lock, subclass) mutex_lock_interruptible(lock)
# define mutex_lock_killable_nested(lock, subclass) mutex_lock_killable(lock)
# define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock)
-# define mutex_lock_io_nested(lock, subclass) mutex_lock(lock)
+# define mutex_lock_io_nested(lock, subclass) mutex_lock_io(lock)
#endif
/*
enum nvdimm_event {
NVDIMM_REVALIDATE_POISON,
+ NVDIMM_REVALIDATE_REGION,
};
enum nvdimm_claim_class {
NAPI_STATE_IN_BUSY_POLL, /* sk_busy_loop() owns this NAPI */
NAPI_STATE_PREFER_BUSY_POLL, /* prefer busy-polling over softirq processing*/
NAPI_STATE_THREADED, /* The poll is performed inside its own thread*/
+ NAPI_STATE_SCHED_THREADED, /* Napi is currently scheduled in threaded mode */
};
enum {
NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL),
NAPIF_STATE_PREFER_BUSY_POLL = BIT(NAPI_STATE_PREFER_BUSY_POLL),
NAPIF_STATE_THREADED = BIT(NAPI_STATE_THREADED),
+ NAPIF_STATE_SCHED_THREADED = BIT(NAPI_STATE_SCHED_THREADED),
};
enum gro_result {
int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode);
-int xdp_umem_query(struct net_device *dev, u16 queue_id);
-
int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb);
unsigned int valid_hooks;
/* Man behind the curtain... */
- struct xt_table_info __rcu *private;
+ struct xt_table_info *private;
/* Set this to THIS_MODULE if you are a module, otherwise NULL */
struct module *me;
* since addend is most likely 1
*/
__this_cpu_add(xt_recseq.sequence, addend);
- smp_wmb();
+ smp_mb();
return addend;
}
struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *);
-struct xt_table_info
-*xt_table_get_private_protected(const struct xt_table *table);
-
#ifdef CONFIG_COMPAT
#include <net/compat.h>
int arpt_register_table(struct net *net, const struct xt_table *table,
const struct arpt_replace *repl,
const struct nf_hook_ops *ops, struct xt_table **res);
-void arpt_unregister_table(struct net *net, struct xt_table *table,
- const struct nf_hook_ops *ops);
+void arpt_unregister_table(struct net *net, struct xt_table *table);
+void arpt_unregister_table_pre_exit(struct net *net, struct xt_table *table,
+ const struct nf_hook_ops *ops);
extern unsigned int arpt_do_table(struct sk_buff *skb,
const struct nf_hook_state *state,
struct xt_table *table);
const struct ebt_table *table,
const struct nf_hook_ops *ops,
struct ebt_table **res);
-extern void ebt_unregister_table(struct net *net, struct ebt_table *table,
- const struct nf_hook_ops *);
+extern void ebt_unregister_table(struct net *net, struct ebt_table *table);
+void ebt_unregister_table_pre_exit(struct net *net, const char *tablename,
+ const struct nf_hook_ops *ops);
extern unsigned int ebt_do_table(struct sk_buff *skb,
const struct nf_hook_state *state,
struct ebt_table *table);
enum OID {
OID_id_dsa_with_sha1, /* 1.2.840.10030.4.3 */
OID_id_dsa, /* 1.2.840.10040.4.1 */
- OID_id_ecdsa_with_sha1, /* 1.2.840.10045.4.1 */
OID_id_ecPublicKey, /* 1.2.840.10045.2.1 */
+ OID_id_prime192v1, /* 1.2.840.10045.3.1.1 */
+ OID_id_prime256v1, /* 1.2.840.10045.3.1.7 */
+ OID_id_ecdsa_with_sha1, /* 1.2.840.10045.4.1 */
+ OID_id_ecdsa_with_sha224, /* 1.2.840.10045.4.3.1 */
+ OID_id_ecdsa_with_sha256, /* 1.2.840.10045.4.3.2 */
+ OID_id_ecdsa_with_sha384, /* 1.2.840.10045.4.3.3 */
+ OID_id_ecdsa_with_sha512, /* 1.2.840.10045.4.3.4 */
/* PKCS#1 {iso(1) member-body(2) us(840) rsadsi(113549) pkcs(1) pkcs-1(1)} */
OID_rsaEncryption, /* 1.2.840.113549.1.1.1 */
OID_certAuthInfoAccess, /* 1.3.6.1.5.5.7.1.1 */
OID_sha1, /* 1.3.14.3.2.26 */
+ OID_id_ansip384r1, /* 1.3.132.0.34 */
OID_sha256, /* 2.16.840.1.101.3.4.2.1 */
OID_sha384, /* 2.16.840.1.101.3.4.2.2 */
OID_sha512, /* 2.16.840.1.101.3.4.2.3 */
OID_SM2_with_SM3, /* 1.2.156.10197.1.501 */
OID_sm3WithRSAEncryption, /* 1.2.156.10197.1.504 */
+ /* TCG defined OIDS for TPM based keys */
+ OID_TPMLoadableKey, /* 2.23.133.10.1.3 */
+ OID_TPMImportableKey, /* 2.23.133.10.1.4 */
+ OID_TPMSealedData, /* 2.23.133.10.1.5 */
+
OID__NR
};
extern enum OID look_up_OID(const void *data, size_t datasize);
+extern int parse_OID(const void *data, size_t datasize, enum OID *oid);
extern int sprint_oid(const void *, size_t, char *, size_t);
extern int sprint_OID(enum OID, char *, size_t);
return pgoff;
}
-/* This has the same layout as wait_bit_key - see fs/cachefiles/rdwr.c */
struct wait_page_key {
struct page *page;
int bit_nr;
int put_and_wait_on_page_locked(struct page *page, int state);
void wait_on_page_writeback(struct page *page);
+int wait_on_page_writeback_killable(struct page *page);
extern void end_page_writeback(struct page *page);
void wait_for_stable_page(struct page *page);
#define PERF_ATTACH_TASK 0x04
#define PERF_ATTACH_TASK_DATA 0x08
#define PERF_ATTACH_ITRACE 0x10
+#define PERF_ATTACH_SCHED_CB 0x20
struct perf_cgroup;
struct perf_buffer;
struct list_head cgrp_cpuctx_entry;
#endif
+ struct list_head sched_cb_entry;
int sched_cb_usage;
int online;
#define pgprot_device pgprot_noncached
#endif
+#ifndef pgprot_mhp
+#define pgprot_mhp(prot) (prot)
+#endif
+
#ifdef CONFIG_MMU
#ifndef pgprot_modify
#define pgprot_modify pgprot_modify
* omap2+ specific GPIO registers
*/
#define OMAP24XX_GPIO_REVISION 0x0000
+#define OMAP24XX_GPIO_SYSCONFIG 0x0010
#define OMAP24XX_GPIO_IRQSTATUS1 0x0018
#define OMAP24XX_GPIO_IRQSTATUS2 0x0028
#define OMAP24XX_GPIO_IRQENABLE2 0x002c
#define OMAP24XX_GPIO_SETDATAOUT 0x0094
#define OMAP4_GPIO_REVISION 0x0000
+#define OMAP4_GPIO_SYSCONFIG 0x0010
#define OMAP4_GPIO_EOI 0x0020
#define OMAP4_GPIO_IRQSTATUSRAW0 0x0024
#define OMAP4_GPIO_IRQSTATUSRAW1 0x0028
#ifndef __ASSEMBLER__
struct omap_gpio_reg_offs {
u16 revision;
+ u16 sysconfig;
u16 direction;
u16 datain;
u16 dataout;
#define nmi_count() (preempt_count() & NMI_MASK)
#define hardirq_count() (preempt_count() & HARDIRQ_MASK)
-#define softirq_count() (preempt_count() & SOFTIRQ_MASK)
+#ifdef CONFIG_PREEMPT_RT
+# define softirq_count() (current->softirq_disable_cnt & SOFTIRQ_MASK)
+#else
+# define softirq_count() (preempt_count() & SOFTIRQ_MASK)
+#endif
#define irq_count() (nmi_count() | hardirq_count() | softirq_count())
/*
const struct fwnode_handle *parent);
void fwnode_remove_software_node(struct fwnode_handle *fwnode);
-int device_add_software_node(struct device *dev, const struct software_node *swnode);
+int device_add_software_node(struct device *dev, const struct software_node *node);
void device_remove_software_node(struct device *dev);
int device_create_managed_software_node(struct device *dev,
int geni_icc_enable(struct geni_se *se);
int geni_icc_disable(struct geni_se *se);
-
-void geni_remove_earlycon_icc_vote(void);
#endif
#endif
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _LINUX_RANDOMIZE_KSTACK_H
+#define _LINUX_RANDOMIZE_KSTACK_H
+
+#include <linux/kernel.h>
+#include <linux/jump_label.h>
+#include <linux/percpu-defs.h>
+
+DECLARE_STATIC_KEY_MAYBE(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT,
+ randomize_kstack_offset);
+DECLARE_PER_CPU(u32, kstack_offset);
+
+/*
+ * Do not use this anywhere else in the kernel. This is used here because
+ * it provides an arch-agnostic way to grow the stack with correct
+ * alignment. Also, since this use is being explicitly masked to a max of
+ * 10 bits, stack-clash style attacks are unlikely. For more details see
+ * "VLAs" in Documentation/process/deprecated.rst
+ */
+void *__builtin_alloca(size_t size);
+/*
+ * Use, at most, 10 bits of entropy. We explicitly cap this to keep the
+ * "VLA" from being unbounded (see above). 10 bits leaves enough room for
+ * per-arch offset masks to reduce entropy (by removing higher bits, since
+ * high entropy may overly constrain usable stack space), and for
+ * compiler/arch-specific stack alignment to remove the lower bits.
+ */
+#define KSTACK_OFFSET_MAX(x) ((x) & 0x3FF)
+
+/*
+ * These macros must be used during syscall entry when interrupts and
+ * preempt are disabled, and after user registers have been stored to
+ * the stack.
+ */
+#define add_random_kstack_offset() do { \
+ if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \
+ &randomize_kstack_offset)) { \
+ u32 offset = raw_cpu_read(kstack_offset); \
+ u8 *ptr = __builtin_alloca(KSTACK_OFFSET_MAX(offset)); \
+ /* Keep allocation even after "ptr" loses scope. */ \
+ asm volatile("" : "=o"(*ptr) :: "memory"); \
+ } \
+} while (0)
+
+#define choose_random_kstack_offset(rand) do { \
+ if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \
+ &randomize_kstack_offset)) { \
+ u32 offset = raw_cpu_read(kstack_offset); \
+ offset ^= (rand); \
+ raw_cpu_write(kstack_offset, offset); \
+ } \
+} while (0)
+
+#endif
#define rcu_sleep_check() \
do { \
rcu_preempt_sleep_check(); \
- RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map), \
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \
+ RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map), \
"Illegal context switch in RCU-bh read-side critical section"); \
RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map), \
"Illegal context switch in RCU-sched read-side critical section"); \
#define BUCK6_FPWM 0x04
#define BUCK6_ENMODE_MASK 0x03
+/* PCA9450_REG_BUCK123_PRESET_EN bit */
+#define BUCK123_PRESET_EN 0x80
+
/* PCA9450_BUCK1OUT_DVS0 bits */
#define BUCK1OUT_DVS0_MASK 0x7F
#define BUCK1OUT_DVS0_DEFAULT 0x14
* System call restart block.
*/
struct restart_block {
+ unsigned long arch_data;
long (*fn)(struct restart_block *);
union {
/* For futex_wait and futex_wait_requeue_pi */
int softirq_context;
int irq_config;
#endif
+#ifdef CONFIG_PREEMPT_RT
+ int softirq_disable_cnt;
+#endif
#ifdef CONFIG_LOCKDEP
# define MAX_LOCK_DEPTH 48UL
* another oom-unkillable task does this it should blame itself.
*/
rcu_read_lock();
- ret = tsk->vfork_done && tsk->real_parent->mm == tsk->mm;
+ ret = tsk->vfork_done &&
+ rcu_dereference(tsk->real_parent)->mm == tsk->mm;
rcu_read_unlock();
return ret;
* seqcount_latch_init() - runtime initializer for seqcount_latch_t
* @s: Pointer to the seqcount_latch_t instance
*/
-static inline void seqcount_latch_init(seqcount_latch_t *s)
-{
- seqcount_init(&s->seqcount);
-}
+#define seqcount_latch_init(s) seqcount_init(&(s)->seqcount)
/**
* raw_read_seqcount_latch() - pick even/odd latch data copy
struct tc_skb_ext {
__u32 chain;
__u16 mru;
+ bool post_ct;
};
#endif
static inline void sk_psock_restore_proto(struct sock *sk,
struct sk_psock *psock)
{
- sk->sk_prot->unhash = psock->saved_unhash;
if (inet_csk_has_ulp(sk)) {
+ /* TLS does not have an unhash proto in SW cases, but we need
+ * to ensure we stop using the sock_map unhash routine because
+ * the associated psock is being removed. So use the original
+ * unhash handler.
+ */
+ WRITE_ONCE(sk->sk_prot->unhash, psock->saved_unhash);
tcp_update_ulp(sk, psock->sk_proto, psock->saved_write_space);
} else {
sk->sk_write_space = psock->saved_write_space;
*/
void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
struct task_struct *task, struct pt_regs *regs);
+
+/**
+ * arch_stack_walk_reliable - Architecture specific function to walk the
+ * stack reliably
+ *
+ * @consume_entry: Callback which is invoked by the architecture code for
+ * each entry.
+ * @cookie: Caller supplied pointer which is handed back to
+ * @consume_entry
+ * @task: Pointer to a task struct, can be NULL
+ *
+ * This function returns an error if it detects any unreliable
+ * features of the stack. Otherwise it guarantees that the stack
+ * trace is reliable.
+ *
+ * If the task is not 'current', the caller *must* ensure the task is
+ * inactive and its stack is pinned.
+ */
int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, void *cookie,
struct task_struct *task);
+
void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie,
const struct pt_regs *regs);
* static_call(name)(args...);
* static_call_cond(name)(args...);
* static_call_update(name, func);
+ * static_call_query(name);
*
* Usage example:
*
*
* which will include the required value tests to avoid NULL-pointer
* dereferences.
+ *
+ * To query which function is currently set to be called, use:
+ *
+ * func = static_call_query(name);
*/
#include <linux/types.h>
STATIC_CALL_TRAMP_ADDR(name), func); \
})
+#define static_call_query(name) (READ_ONCE(STATIC_CALL_KEY(name).func))
+
#ifdef CONFIG_HAVE_STATIC_CALL_INLINE
extern int __init static_call_init(void);
struct static_call_site *sites;
};
-struct static_call_key {
- void *func;
- union {
- /* bit 0: 0 = mods, 1 = sites */
- unsigned long type;
- struct static_call_mod *mods;
- struct static_call_site *sites;
- };
-};
-
/* For finding the key associated with a trampoline */
struct static_call_tramp_key {
s32 tramp;
static inline int static_call_init(void) { return 0; }
-struct static_call_key {
- void *func;
-};
-
#define __DEFINE_STATIC_CALL(name, _func, _func_init) \
DECLARE_STATIC_CALL(name, _func); \
struct static_call_key STATIC_CALL_KEY(name) = { \
}; \
ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)
+
#define static_call_cond(name) (void)__static_call(name)
static inline
static inline int static_call_init(void) { return 0; }
-struct static_call_key {
- void *func;
-};
-
static inline long __static_call_return0(void)
{
return 0;
__raw_static_call(name); \
})
+struct static_call_key {
+ void *func;
+ union {
+ /* bit 0: 0 = mods, 1 = sites */
+ unsigned long type;
+ struct static_call_mod *mods;
+ struct static_call_site *sites;
+ };
+};
+
#else /* !CONFIG_HAVE_STATIC_CALL_INLINE */
#define __STATIC_CALL_ADDRESSABLE(name)
#define __static_call(name) __raw_static_call(name)
+struct static_call_key {
+ void *func;
+};
+
#endif /* CONFIG_HAVE_STATIC_CALL_INLINE */
#ifdef MODULE
#else
+struct static_call_key {
+ void *func;
+};
+
#define static_call(name) \
((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func))
const struct cpumask *cpus);
#else /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */
-static inline int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data,
+static __always_inline int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data,
const struct cpumask *cpus)
{
unsigned long flags;
return ret;
}
-static inline int stop_machine(cpu_stop_fn_t fn, void *data,
- const struct cpumask *cpus)
+static __always_inline int
+stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus)
{
return stop_machine_cpuslocked(fn, data, cpus);
}
-static inline int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
- const struct cpumask *cpus)
+static __always_inline int
+stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
+ const struct cpumask *cpus)
{
return stop_machine(fn, data, cpus);
}
wait_queue_head_t sc_send_wait; /* SQ exhaustion waitlist */
unsigned long sc_flags;
- u32 sc_pending_recvs;
struct list_head sc_read_complete_q;
struct work_struct sc_work;
struct ts_state
{
unsigned int offset;
- char cb[40];
+ char cb[48];
};
/**
#include <linux/types.h>
#include <linux/bug.h>
#include <linux/restart_block.h>
+#include <linux/errno.h>
#ifdef CONFIG_THREAD_INFO_IN_TASK
/*
#ifdef __KERNEL__
+#ifndef arch_set_restart_data
+#define arch_set_restart_data(restart) do { } while (0)
+#endif
+
+static inline long set_restart_fn(struct restart_block *restart,
+ long (*fn)(struct restart_block *))
+{
+ restart->fn = fn;
+ arch_set_restart_data(restart);
+ return -ERESTART_RESTARTBLOCK;
+}
+
#ifndef THREAD_ALIGN
#define THREAD_ALIGN THREAD_SIZE
#endif
* This allows conversion of cycle counter values which were generated
* in the past.
*/
-extern u64 timecounter_cyc2time(struct timecounter *tc,
+extern u64 timecounter_cyc2time(const struct timecounter *tc,
u64 cycle_tstamp);
#endif
/*
* kernel variables
- * Note: maximum error = NTP synch distance = dispersion + delay / 2;
+ * Note: maximum error = NTP sync distance = dispersion + delay / 2;
* estimated error = NTP dispersion.
*/
extern unsigned long tick_usec; /* USER_HZ period (usec) */
};
enum tpm2_object_attributes {
+ TPM2_OA_FIXED_TPM = BIT(1),
+ TPM2_OA_FIXED_PARENT = BIT(4),
TPM2_OA_USER_WITH_AUTH = BIT(6),
};
}
#endif
+#if BITS_PER_LONG == 32 && defined(CONFIG_SMP)
+#define u64_stats_init(syncp) seqcount_init(&(syncp)->seq)
+#else
static inline void u64_stats_init(struct u64_stats_sync *syncp)
{
-#if BITS_PER_LONG == 32 && defined(CONFIG_SMP)
- seqcount_init(&syncp->seq);
-#endif
}
+#endif
static inline void u64_stats_update_begin(struct u64_stats_sync *syncp)
{
extern int usb_reset_device(struct usb_device *dev);
extern void usb_queue_reset_device(struct usb_interface *dev);
+extern struct device *usb_intf_get_dma_device(struct usb_interface *intf);
+
#ifdef CONFIG_ACPI
extern int usb_acpi_set_power_state(struct usb_device *hdev, int index,
bool enable);
/* lies about caching, so always sync */ \
US_FLAG(NO_SAME, 0x40000000) \
/* Cannot handle WRITE_SAME */ \
+ US_FLAG(SENSE_AFTER_SYNC, 0x80000000) \
+ /* Do REQUEST_SENSE after SYNCHRONIZE_CACHE */ \
#define US_FLAG(name, value) US_FL_##name = value ,
enum { US_DO_ALL_FLAGS };
kgid_t group;
struct ns_common ns;
unsigned long flags;
+ /* parent_could_setfcap: true if the creator if this ns had CAP_SETFCAP
+ * in its effective capability set at the child ns creation time. */
+ bool parent_could_setfcap;
#ifdef CONFIG_KEYS
/* List of joinable keyrings in this namespace. Modification access of
int umd_load_blob(struct umd_info *info, const void *data, size_t len);
int umd_unload_blob(struct umd_info *info);
int fork_usermode_driver(struct umd_info *info);
+void umd_cleanup_helper(struct umd_info *info);
#endif /* __LINUX_USERMODE_DRIVER_H__ */
struct vdpa_device *__vdpa_alloc_device(struct device *parent,
const struct vdpa_config_ops *config,
- int nvqs, size_t size, const char *name);
+ size_t size, const char *name);
-#define vdpa_alloc_device(dev_struct, member, parent, config, nvqs, name) \
+#define vdpa_alloc_device(dev_struct, member, parent, config, name) \
container_of(__vdpa_alloc_device( \
- parent, config, nvqs, \
+ parent, config, \
sizeof(dev_struct) + \
BUILD_BUG_ON_ZERO(offsetof( \
dev_struct, member)), name), \
dev_struct, member)
-int vdpa_register_device(struct vdpa_device *vdev);
+int vdpa_register_device(struct vdpa_device *vdev, int nvqs);
void vdpa_unregister_device(struct vdpa_device *vdev);
-int _vdpa_register_device(struct vdpa_device *vdev);
+int _vdpa_register_device(struct vdpa_device *vdev, int nvqs);
void _vdpa_unregister_device(struct vdpa_device *vdev);
/**
void virtio_break_device(struct virtio_device *dev);
void virtio_config_changed(struct virtio_device *dev);
-void virtio_config_disable(struct virtio_device *dev);
-void virtio_config_enable(struct virtio_device *dev);
int virtio_finalize_features(struct virtio_device *dev);
#ifdef CONFIG_PM_SLEEP
int virtio_device_freeze(struct virtio_device *dev);
return -EINVAL;
}
+ skb_reset_mac_header(skb);
+
if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
- u16 start = __virtio16_to_cpu(little_endian, hdr->csum_start);
- u16 off = __virtio16_to_cpu(little_endian, hdr->csum_offset);
+ u32 start = __virtio16_to_cpu(little_endian, hdr->csum_start);
+ u32 off = __virtio16_to_cpu(little_endian, hdr->csum_offset);
+ u32 needed = start + max_t(u32, thlen, off + sizeof(__sum16));
+
+ if (!pskb_may_pull(skb, needed))
+ return -EINVAL;
if (!skb_partial_csum_set(skb, start, off))
return -EINVAL;
p_off = skb_transport_offset(skb) + thlen;
- if (p_off > skb_headlen(skb))
+ if (!pskb_may_pull(skb, p_off))
return -EINVAL;
} else {
/* gso packets without NEEDS_CSUM do not set transport_offset.
if (gso_type && skb->network_header) {
struct flow_keys_basic keys;
- if (!skb->protocol)
+ if (!skb->protocol) {
+ __be16 protocol = dev_parse_header_protocol(skb);
+
virtio_net_hdr_set_proto(skb, hdr);
+ if (protocol && protocol != skb->protocol)
+ return -EINVAL;
+ }
retry:
if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys,
NULL, 0, 0, 0,
}
p_off = keys.control.thoff + thlen;
- if (p_off > skb_headlen(skb) ||
+ if (!pskb_may_pull(skb, p_off) ||
keys.basic.ip_proto != ip_proto)
return -EINVAL;
skb_set_transport_header(skb, keys.control.thoff);
} else if (gso_type) {
p_off = thlen;
- if (p_off > skb_headlen(skb))
+ if (!pskb_may_pull(skb, p_off))
return -EINVAL;
}
}
*/
static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx)
{
-#ifdef CONFIG_DEBUG_MUTEXES
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
mutex_release(&ctx->dep_map, _THIS_IP_);
-
+#endif
+#ifdef CONFIG_DEBUG_MUTEXES
DEBUG_LOCKS_WARN_ON(ctx->acquired);
if (!IS_ENABLED(CONFIG_PROVE_LOCKING))
/*
*
* This structure is used either directly or via the XA_LIMIT() macro
* to communicate the range of IDs that are valid for allocation.
- * Two common ranges are predefined for you:
+ * Three common ranges are predefined for you:
* * xa_limit_32b - [0 - UINT_MAX]
* * xa_limit_31b - [0 - INT_MAX]
+ * * xa_limit_16b - [0 - USHRT_MAX]
*/
struct xa_limit {
u32 max;
#define xa_limit_32b XA_LIMIT(0, UINT_MAX)
#define xa_limit_31b XA_LIMIT(0, INT_MAX)
+#define xa_limit_16b XA_LIMIT(0, USHRT_MAX)
typedef unsigned __bitwise xa_mark_t;
#define XA_MARK_0 ((__force xa_mark_t)0U)
struct rc_map map;
};
+#ifdef CONFIG_MEDIA_CEC_RC
+/*
+ * rc_map_list from rc-cec.c
+ */
+extern struct rc_map_list cec_map;
+#endif
+
/* Routines from rc-map.c */
/**
void tcf_idr_cleanup(struct tc_action_net *tn, u32 index);
int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
struct tc_action **a, int bind);
-int __tcf_idr_release(struct tc_action *a, bool bind, bool strict);
-
-static inline int tcf_idr_release(struct tc_action *a, bool bind)
-{
- return __tcf_idr_release(a, bind, false);
-}
+int tcf_idr_release(struct tc_action *a, bool bind);
int tcf_register_action(struct tc_action_ops *a, struct pernet_operations *ops);
int tcf_unregister_action(struct tc_action_ops *a,
int nr_actions, struct tcf_result *res);
int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
struct nlattr *est, char *name, int ovr, int bind,
- struct tc_action *actions[], size_t *attr_size,
+ struct tc_action *actions[], int init_res[], size_t *attr_size,
bool rtnl_held, struct netlink_ext_ack *extack);
struct tc_action_ops *tc_action_load_ops(char *name, struct nlattr *nla,
bool rtnl_held,
struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
struct nlattr *nla, struct nlattr *est,
char *name, int ovr, int bind,
- struct tc_action_ops *ops, bool rtnl_held,
+ struct tc_action_ops *a_o, int *init_res,
+ bool rtnl_held,
struct netlink_ext_ack *extack);
int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], int bind,
int ref, bool terse);
dst->ops->update_pmtu(dst, NULL, skb, mtu, false);
}
+struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie);
+void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
+ struct sk_buff *skb, u32 mtu, bool confirm_neigh);
+void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
+ struct sk_buff *skb);
+u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old);
+struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst,
+ struct sk_buff *skb,
+ const void *daddr);
+unsigned int dst_blackhole_mtu(const struct dst_entry *dst);
+
#endif /* _NET_DST_H */
return inet_csk_reqsk_queue_len(sk) >= sk->sk_max_ack_backlog;
}
-void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req);
+bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req);
void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req);
static inline void inet_csk_prepare_for_destroy_sock(struct sock *sk)
struct nft_flowtable *flowtable;
bool update;
struct list_head hook_list;
+ u32 flags;
};
#define nft_trans_flowtable(trans) \
(((struct nft_trans_flowtable *)trans->data)->update)
#define nft_trans_flowtable_hooks(trans) \
(((struct nft_trans_flowtable *)trans->data)->hook_list)
+#define nft_trans_flowtable_flags(trans) \
+ (((struct nft_trans_flowtable *)trans->data)->flags)
int __init nft_chain_filter_init(void);
void nft_chain_filter_fini(void);
#if IS_ENABLED(CONFIG_IPV6)
struct dst_ops xfrm6_dst_ops;
#endif
- spinlock_t xfrm_state_lock;
+ spinlock_t xfrm_state_lock;
+ seqcount_spinlock_t xfrm_state_hash_generation;
+
spinlock_t xfrm_policy_lock;
struct mutex xfrm_cfg_mutex;
};
int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg,
struct netlink_ext_ack *extack);
+/* Caller should either hold rcu_read_lock(), or RTNL. */
static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh)
{
struct nh_info *nhi;
return NULL;
}
+/* Variant of nexthop_fib6_nh().
+ * Caller should either hold rcu_read_lock_bh(), or RTNL.
+ */
+static inline struct fib6_nh *nexthop_fib6_nh_bh(struct nexthop *nh)
+{
+ struct nh_info *nhi;
+
+ if (nh->is_group) {
+ struct nh_group *nh_grp;
+
+ nh_grp = rcu_dereference_bh_rtnl(nh->nh_grp);
+ nh = nexthop_mpath_select(nh_grp, 0);
+ if (!nh)
+ return NULL;
+ }
+
+ nhi = rcu_dereference_bh_rtnl(nh->nh_info);
+ if (nhi->family == AF_INET6)
+ return &nhi->fib6_nh;
+
+ return NULL;
+}
+
static inline struct net_device *fib6_info_nh_dev(struct fib6_info *f6i)
{
struct fib6_nh *fib6_nh;
v->qcount = -1;
}
-static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog, u8 Scell_log)
+static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog,
+ u8 Scell_log, u8 *stab)
{
- if (fls(qth_min) + Wlog > 32)
+ if (fls(qth_min) + Wlog >= 32)
return false;
- if (fls(qth_max) + Wlog > 32)
+ if (fls(qth_max) + Wlog >= 32)
return false;
if (Scell_log >= 32)
return false;
if (qth_max < qth_min)
return false;
+ if (stab) {
+ int i;
+
+ for (i = 0; i < RED_STAB_SIZE; i++)
+ if (stab[i] >= 32)
+ return false;
+ }
return true;
}
int shift;
/*
- * The problem: ideally, average length queue recalcultion should
+ * The problem: ideally, average length queue recalculation should
* be done over constant clock intervals. This is too expensive, so
* that the calculation is driven by outgoing packets.
* When the queue is idle we have to model this clock by hand.
*
* @list: Used internally
* @kind: Identifier
+ * @netns_refund: Physical device, move to init_net on netns exit
* @maxtype: Highest device specific netlink attribute number
* @policy: Netlink policy for device specific attribute validation
* @validate: Optional validation function for netlink/changelink parameters
size_t priv_size;
void (*setup)(struct net_device *dev);
+ bool netns_refund;
unsigned int maxtype;
const struct nla_policy *policy;
int (*validate)(struct nlattr *tb[],
int (*validate_link_af)(const struct net_device *dev,
const struct nlattr *attr);
int (*set_link_af)(struct net_device *dev,
- const struct nlattr *attr);
-
+ const struct nlattr *attr,
+ struct netlink_ext_ack *extack);
int (*fill_stats_af)(struct sk_buff *skb,
const struct net_device *dev);
size_t (*get_stats_af_size)(const struct net_device *dev);
WRITE_ONCE(sk->sk_ack_backlog, sk->sk_ack_backlog + 1);
}
+/* Note: If you think the test should be:
+ * return READ_ONCE(sk->sk_ack_backlog) >= READ_ONCE(sk->sk_max_ack_backlog);
+ * Then please take a look at commit 64a146513f8f ("[NET]: Revert incorrect accept queue backlog changes.")
+ */
static inline bool sk_acceptq_is_full(const struct sock *sk)
{
return READ_ONCE(sk->sk_ack_backlog) > READ_ONCE(sk->sk_max_ack_backlog);
sk_mem_charge(sk, skb->truesize);
}
+static inline void skb_set_owner_sk_safe(struct sk_buff *skb, struct sock *sk)
+{
+ if (sk && refcount_inc_not_zero(&sk->sk_refcnt)) {
+ skb_orphan(skb);
+ skb->destructor = sock_efree;
+ skb->sk = sk;
+ }
+}
+
void sk_reset_timer(struct sock *sk, struct timer_list *timer,
unsigned long expires);
return __xfrm_policy_check(sk, ndir, skb, family);
return (!net->xfrm.policy_count[dir] && !secpath_exists(skb)) ||
- (skb_dst(skb)->flags & DST_NOPOLICY) ||
+ (skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY)) ||
__xfrm_policy_check(sk, ndir, skb, family);
}
int xfrm_trans_queue(struct sk_buff *skb,
int (*finish)(struct net *, struct sock *,
struct sk_buff *));
-int xfrm_output_resume(struct sk_buff *skb, int err);
+int xfrm_output_resume(struct sock *sk, struct sk_buff *skb, int err);
int xfrm_output(struct sock *sk, struct sk_buff *skb);
#if IS_ENABLED(CONFIG_NET_PKTGEN)
ISCSI_CONN_UP = 0,
ISCSI_CONN_DOWN,
ISCSI_CONN_FAILED,
+ ISCSI_CONN_BOUND,
};
struct iscsi_cls_conn {
__entry->entropy_count, (void *)__entry->IP)
);
-TRACE_EVENT(push_to_pool,
- TP_PROTO(const char *pool_name, int pool_bits, int input_bits),
-
- TP_ARGS(pool_name, pool_bits, input_bits),
-
- TP_STRUCT__entry(
- __field( const char *, pool_name )
- __field( int, pool_bits )
- __field( int, input_bits )
- ),
-
- TP_fast_assign(
- __entry->pool_name = pool_name;
- __entry->pool_bits = pool_bits;
- __entry->input_bits = input_bits;
- ),
-
- TP_printk("%s: pool_bits %d input_pool_bits %d",
- __entry->pool_name, __entry->pool_bits,
- __entry->input_bits)
-);
-
TRACE_EVENT(debit_entropy,
TP_PROTO(const char *pool_name, int debit_bits),
MINOR(__entry->dev), __entry->input_bits)
);
-TRACE_EVENT(xfer_secondary_pool,
- TP_PROTO(const char *pool_name, int xfer_bits, int request_bits,
- int pool_entropy, int input_entropy),
-
- TP_ARGS(pool_name, xfer_bits, request_bits, pool_entropy,
- input_entropy),
-
- TP_STRUCT__entry(
- __field( const char *, pool_name )
- __field( int, xfer_bits )
- __field( int, request_bits )
- __field( int, pool_entropy )
- __field( int, input_entropy )
- ),
-
- TP_fast_assign(
- __entry->pool_name = pool_name;
- __entry->xfer_bits = xfer_bits;
- __entry->request_bits = request_bits;
- __entry->pool_entropy = pool_entropy;
- __entry->input_entropy = input_entropy;
- ),
-
- TP_printk("pool %s xfer_bits %d request_bits %d pool_entropy %d "
- "input_entropy %d", __entry->pool_name, __entry->xfer_bits,
- __entry->request_bits, __entry->pool_entropy,
- __entry->input_entropy)
-);
-
DECLARE_EVENT_CLASS(random__get_random_bytes,
TP_PROTO(int nbytes, unsigned long IP),
TP_ARGS(pool_name, nbytes, entropy_count, IP)
);
-DEFINE_EVENT(random__extract_entropy, extract_entropy_user,
- TP_PROTO(const char *pool_name, int nbytes, int entropy_count,
- unsigned long IP),
-
- TP_ARGS(pool_name, nbytes, entropy_count, IP)
-);
-
-TRACE_EVENT(random_read,
- TP_PROTO(int got_bits, int need_bits, int pool_left, int input_left),
-
- TP_ARGS(got_bits, need_bits, pool_left, input_left),
-
- TP_STRUCT__entry(
- __field( int, got_bits )
- __field( int, need_bits )
- __field( int, pool_left )
- __field( int, input_left )
- ),
-
- TP_fast_assign(
- __entry->got_bits = got_bits;
- __entry->need_bits = need_bits;
- __entry->pool_left = pool_left;
- __entry->input_left = input_left;
- ),
-
- TP_printk("got_bits %d still_needed_bits %d "
- "blocking_pool_entropy_left %d input_entropy_left %d",
- __entry->got_bits, __entry->got_bits, __entry->pool_left,
- __entry->input_left)
-);
-
TRACE_EVENT(urandom_read,
TP_PROTO(int got_bits, int pool_left, int input_left),
TP_STRUCT__entry(
__field( void *, work )
__field( void *, function)
- __field( const char *, workqueue)
+ __string( workqueue, pwq->wq->name)
__field( unsigned int, req_cpu )
__field( unsigned int, cpu )
),
TP_fast_assign(
__entry->work = work;
__entry->function = work->func;
- __entry->workqueue = pwq->wq->name;
+ __assign_str(workqueue, pwq->wq->name);
__entry->req_cpu = req_cpu;
__entry->cpu = pwq->pool->cpu;
),
TP_printk("work struct=%p function=%ps workqueue=%s req_cpu=%u cpu=%u",
- __entry->work, __entry->function, __entry->workqueue,
+ __entry->work, __entry->function, __get_str(workqueue),
__entry->req_cpu, __entry->cpu)
);
#ifndef _UAPI__LINUX_BLKPG_H
#define _UAPI__LINUX_BLKPG_H
-/*
- * Partition table and disk geometry handling
- *
- * A single ioctl with lots of subfunctions:
- *
- * Device number stuff:
- * get_whole_disk() (given the device number of a partition,
- * find the device number of the encompassing disk)
- * get_all_partitions() (given the device number of a disk, return the
- * device numbers of all its known partitions)
- *
- * Partition stuff:
- * add_partition()
- * delete_partition()
- * test_partition_in_use() (also for test_disk_in_use)
- *
- * Geometry stuff:
- * get_geometry()
- * set_geometry()
- * get_bios_drivedata()
- *
- * For today, only the partition stuff - aeb, 990515
- */
#include <linux/compiler.h>
#include <linux/ioctl.h>
long long start; /* starting offset in bytes */
long long length; /* length in bytes */
int pno; /* partition number */
- char devname[BLKPG_DEVNAMELTH]; /* partition name, like sda5 or c0d1p2,
- to be used in kernel messages */
- char volname[BLKPG_VOLNAMELTH]; /* volume label */
+ char devname[BLKPG_DEVNAMELTH]; /* unused / ignored */
+ char volname[BLKPG_VOLNAMELTH]; /* unused / ignore */
};
#endif /* _UAPI__LINUX_BLKPG_H */
*
* long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags)
* Description
-
- * Check ctx packet size against exceeding MTU of net device (based
+ * Check packet size against exceeding MTU of net device (based
* on *ifindex*). This helper will likely be used in combination
* with helpers that adjust/change the packet size.
*
* against the current net device. This is practical if this isn't
* used prior to redirect.
*
+ * On input *mtu_len* must be a valid pointer, else verifier will
+ * reject BPF program. If the value *mtu_len* is initialized to
+ * zero then the ctx packet size is use. When value *mtu_len* is
+ * provided as input this specify the L3 length that the MTU check
+ * is done against. Remember XDP and TC length operate at L2, but
+ * this value is L3 as this correlate to MTU and IP-header tot_len
+ * values which are L3 (similar behavior as bpf_fib_lookup).
+ *
* The Linux kernel route table can configure MTUs on a more
* specific per route level, which is not provided by this helper.
* For route level MTU checks use the **bpf_fib_lookup**\ ()
*
* On return *mtu_len* pointer contains the MTU value of the net
* device. Remember the net device configured MTU is the L3 size,
- * which is returned here and XDP and TX length operate at L2.
+ * which is returned here and XDP and TC length operate at L2.
* Helper take this into account for you, but remember when using
- * MTU value in your BPF-code. On input *mtu_len* must be a valid
- * pointer and be initialized (to zero), else verifier will reject
- * BPF program.
+ * MTU value in your BPF-code.
*
* Return
* * 0 on success, and populate MTU value in *mtu_len* pointer.
*/
__u8 len;
__u8 can_dlc; /* deprecated */
- };
+ } __attribute__((packed)); /* disable padding added in some ABIs */
__u8 __pad; /* padding */
__u8 __res0; /* reserved / padding */
__u8 len8_dlc; /* optional DLC for 8 byte payload length (9 .. 15) */
#define CAP_AUDIT_CONTROL 30
-/* Set or remove capabilities on files */
+/* Set or remove capabilities on files.
+ Map uid=0 into a child user namespace. */
#define CAP_SETFCAP 31
#define NT_ARM_PACA_KEYS 0x407 /* ARM pointer authentication address keys */
#define NT_ARM_PACG_KEYS 0x408 /* ARM pointer authentication generic key */
#define NT_ARM_TAGGED_ADDR_CTRL 0x409 /* arm64 tagged address control (prctl()) */
+#define NT_ARM_PAC_ENABLED_KEYS 0x40a /* arm64 ptr auth enabled keys (prctl()) */
#define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */
#define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */
#define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */
* have the same layout for 32-bit and 64-bit userland.
*/
+/* Note on reserved space.
+ * Reserved fields must not be accessed directly by user space because
+ * they may be replaced by a different field in the future. They must
+ * be initialized to zero before making the request, e.g. via memset
+ * of the entire structure or implicitly by not being set in a structure
+ * initializer.
+ */
+
/**
* struct ethtool_cmd - DEPRECATED, link control and status
* This structure is DEPRECATED, please use struct ethtool_link_settings.
* and other link features that the link partner advertised
* through autonegotiation; 0 if unknown or not applicable.
* Read-only.
+ * @reserved: Reserved for future use; see the note on reserved space.
*
* The link speed in Mbps is split between @speed and @speed_hi. Use
* the ethtool_cmd_speed() and ethtool_cmd_speed_set() functions to
* @bus_info: Device bus address. This should match the dev_name()
* string for the underlying bus device, if there is one. May be
* an empty string.
+ * @reserved2: Reserved for future use; see the note on reserved space.
* @n_priv_flags: Number of flags valid for %ETHTOOL_GPFLAGS and
* %ETHTOOL_SPFLAGS commands; also the number of strings in the
* %ETH_SS_PRIV_FLAGS set
* @tx_lpi_timer: Time in microseconds the interface delays prior to asserting
* its tx lpi (after reaching 'idle' state). Effective only when eee
* was negotiated and tx_lpi_enabled was set.
+ * @reserved: Reserved for future use; see the note on reserved space.
*/
struct ethtool_eee {
__u32 cmd;
* @cmd: %ETHTOOL_GMODULEINFO
* @type: Standard the module information conforms to %ETH_MODULE_SFF_xxxx
* @eeprom_len: Length of the eeprom
+ * @reserved: Reserved for future use; see the note on reserved space.
*
* This structure is used to return the information to
* properly size memory for a subsequent call to %ETHTOOL_GMODULEEEPROM.
__u32 tx_pause;
};
-/**
- * enum ethtool_link_ext_state - link extended state
- */
+/* Link extended state */
enum ethtool_link_ext_state {
ETHTOOL_LINK_EXT_STATE_AUTONEG,
ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE,
ETHTOOL_LINK_EXT_STATE_OVERHEAT,
};
-/**
- * enum ethtool_link_ext_substate_autoneg - more information in addition to
- * ETHTOOL_LINK_EXT_STATE_AUTONEG.
- */
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_AUTONEG. */
enum ethtool_link_ext_substate_autoneg {
ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_PARTNER_DETECTED = 1,
ETHTOOL_LINK_EXT_SUBSTATE_AN_ACK_NOT_RECEIVED,
ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_HCD,
};
-/**
- * enum ethtool_link_ext_substate_link_training - more information in addition to
- * ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE.
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE.
*/
enum ethtool_link_ext_substate_link_training {
ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_FRAME_LOCK_NOT_ACQUIRED = 1,
ETHTOOL_LINK_EXT_SUBSTATE_LT_REMOTE_FAULT,
};
-/**
- * enum ethtool_link_ext_substate_logical_mismatch - more information in addition
- * to ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH.
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH.
*/
enum ethtool_link_ext_substate_link_logical_mismatch {
ETHTOOL_LINK_EXT_SUBSTATE_LLM_PCS_DID_NOT_ACQUIRE_BLOCK_LOCK = 1,
ETHTOOL_LINK_EXT_SUBSTATE_LLM_RS_FEC_IS_NOT_LOCKED,
};
-/**
- * enum ethtool_link_ext_substate_bad_signal_integrity - more information in
- * addition to ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY.
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY.
*/
enum ethtool_link_ext_substate_bad_signal_integrity {
ETHTOOL_LINK_EXT_SUBSTATE_BSI_LARGE_NUMBER_OF_PHYSICAL_ERRORS = 1,
ETHTOOL_LINK_EXT_SUBSTATE_BSI_UNSUPPORTED_RATE,
};
-/**
- * enum ethtool_link_ext_substate_cable_issue - more information in
- * addition to ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE.
- */
+/* More information in addition to ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE. */
enum ethtool_link_ext_substate_cable_issue {
ETHTOOL_LINK_EXT_SUBSTATE_CI_UNSUPPORTED_CABLE = 1,
ETHTOOL_LINK_EXT_SUBSTATE_CI_CABLE_TEST_FAILURE,
* now deprecated
* @ETH_SS_FEATURES: Device feature names
* @ETH_SS_RSS_HASH_FUNCS: RSS hush function names
+ * @ETH_SS_TUNABLES: tunable names
* @ETH_SS_PHY_STATS: Statistic names, for use with %ETHTOOL_GPHYSTATS
* @ETH_SS_PHY_TUNABLES: PHY tunable names
* @ETH_SS_LINK_MODES: link mode names
* @ETH_SS_TS_TX_TYPES: timestamping Tx types
* @ETH_SS_TS_RX_FILTERS: timestamping Rx filters
* @ETH_SS_UDP_TUNNEL_TYPES: UDP tunnel types
+ *
+ * @ETH_SS_COUNT: number of defined string sets
*/
enum ethtool_stringset {
ETH_SS_TEST = 0,
/**
* struct ethtool_sset_info - string set information
* @cmd: Command number = %ETHTOOL_GSSET_INFO
+ * @reserved: Reserved for future use; see the note on reserved space.
* @sset_mask: On entry, a bitmask of string sets to query, with bits
* numbered according to &enum ethtool_stringset. On return, a
* bitmask of those string sets queried that are supported.
* @flags: A bitmask of flags from &enum ethtool_test_flags. Some
* flags may be set by the user on entry; others may be set by
* the driver on return.
+ * @reserved: Reserved for future use; see the note on reserved space.
* @len: On return, the number of test results
* @data: Array of test results
*
* @vlan_etype: VLAN EtherType
* @vlan_tci: VLAN tag control information
* @data: user defined data
+ * @padding: Reserved for future use; see the note on reserved space.
*
* Note, @vlan_etype, @vlan_tci, and @data are only valid if %FLOW_EXT
* is set in &struct ethtool_rx_flow_spec @flow_type.
* hardware hash key.
* @hfunc: Defines the current RSS hash function used by HW (or to be set to).
* Valid values are one of the %ETH_RSS_HASH_*.
- * @rsvd: Reserved for future extensions.
+ * @rsvd8: Reserved for future use; see the note on reserved space.
+ * @rsvd32: Reserved for future use; see the note on reserved space.
* @rss_config: RX ring/queue index for each hash value i.e., indirection table
* of @indir_size __u32 elements, followed by hash key of @key_size
* bytes.
* @so_timestamping: bit mask of the sum of the supported SO_TIMESTAMPING flags
* @phc_index: device index of the associated PHC, or -1 if there is none
* @tx_types: bit mask of the supported hwtstamp_tx_types enumeration values
+ * @tx_reserved: Reserved for future use; see the note on reserved space.
* @rx_filters: bit mask of the supported hwtstamp_rx_filters enumeration values
+ * @rx_reserved: Reserved for future use; see the note on reserved space.
*
* The bits in the 'tx_types' and 'rx_filters' fields correspond to
* the 'hwtstamp_tx_types' and 'hwtstamp_rx_filters' enumeration values,
* autonegotiation; 0 if unknown or not applicable. Read-only.
* @transceiver: Used to distinguish different possible PHY types,
* reported consistently by PHYLIB. Read-only.
+ * @master_slave_cfg: Master/slave port mode.
+ * @master_slave_state: Master/slave port state.
+ * @reserved: Reserved for future use; see the note on reserved space.
+ * @reserved1: Reserved for future use; see the note on reserved space.
+ * @link_mode_masks: Variable length bitmaps.
*
* If autonegotiation is disabled, the speed and @duplex represent the
* fixed link mode and are writable if the driver supports multiple
};
/* Device ioctls: */
-#define FUSE_DEV_IOC_CLONE _IOR(229, 0, uint32_t)
+#define FUSE_DEV_IOC_MAGIC 229
+#define FUSE_DEV_IOC_CLONE _IOR(FUSE_DEV_IOC_MAGIC, 0, uint32_t)
struct fuse_lseek_in {
uint64_t fh;
uint32_t rsvd2:8;
};
- uint16_t delta_rec_size;
- uint16_t crc_val;
+ uint32_t delta_rec_size;
+ uint32_t crc_val;
/* DIF check & strip */
struct {
L2TP_ATTR_RX_ERRORS, /* u64 */
L2TP_ATTR_STATS_PAD,
L2TP_ATTR_RX_COOKIE_DISCARDS, /* u64 */
+ L2TP_ATTR_RX_INVALID, /* u64 */
__L2TP_ATTR_STATS_MAX,
};
#define NFCT_HELPER_STATUS_DISABLED 0
#define NFCT_HELPER_STATUS_ENABLED 1
-enum nfnl_acct_msg_types {
+enum nfnl_cthelper_msg_types {
NFNL_MSG_CTHELPER_NEW,
NFNL_MSG_CTHELPER_GET,
NFNL_MSG_CTHELPER_DEL,
# define SYSCALL_DISPATCH_FILTER_ALLOW 0
# define SYSCALL_DISPATCH_FILTER_BLOCK 1
+/* Set/get enabled arm64 pointer authentication keys */
+#define PR_PAC_SET_ENABLED_KEYS 60
+#define PR_PAC_GET_ENABLED_KEYS 61
+
#endif /* _LINUX_PRCTL_H */
#define __UAPI_PSAMPLE_H
enum {
- /* sampled packet metadata */
PSAMPLE_ATTR_IIFINDEX,
PSAMPLE_ATTR_OIFINDEX,
PSAMPLE_ATTR_ORIGSIZE,
PSAMPLE_ATTR_GROUP_SEQ,
PSAMPLE_ATTR_SAMPLE_RATE,
PSAMPLE_ATTR_DATA,
- PSAMPLE_ATTR_TUNNEL,
-
- /* commands attributes */
PSAMPLE_ATTR_GROUP_REFCOUNT,
+ PSAMPLE_ATTR_TUNNEL,
__PSAMPLE_ATTR_MAX
};
* @op: operation code
* @hard: hard state (0/1)
* @soft: soft state (0/1)
+ *
+ * Structure used for userspace communication on /dev/rfkill,
+ * used for events from the kernel and control to the kernel.
+ */
+struct rfkill_event {
+ __u32 idx;
+ __u8 type;
+ __u8 op;
+ __u8 soft;
+ __u8 hard;
+} __attribute__((packed));
+
+/**
+ * struct rfkill_event_ext - events for userspace on /dev/rfkill
+ * @idx: index of dev rfkill
+ * @type: type of the rfkill struct
+ * @op: operation code
+ * @hard: hard state (0/1)
+ * @soft: soft state (0/1)
* @hard_block_reasons: valid if hard is set. One or several reasons from
* &enum rfkill_hard_block_reasons.
*
* Structure used for userspace communication on /dev/rfkill,
* used for events from the kernel and control to the kernel.
+ *
+ * See the extensibility docs below.
*/
-struct rfkill_event {
+struct rfkill_event_ext {
__u32 idx;
__u8 type;
__u8 op;
__u8 soft;
__u8 hard;
+
+ /*
+ * older kernels will accept/send only up to this point,
+ * and if extended further up to any chunk marked below
+ */
+
__u8 hard_block_reasons;
} __attribute__((packed));
-/*
- * We are planning to be backward and forward compatible with changes
- * to the event struct, by adding new, optional, members at the end.
- * When reading an event (whether the kernel from userspace or vice
- * versa) we need to accept anything that's at least as large as the
- * version 1 event size, but might be able to accept other sizes in
- * the future.
+/**
+ * DOC: Extensibility
+ *
+ * Originally, we had planned to allow backward and forward compatible
+ * changes by just adding fields at the end of the structure that are
+ * then not reported on older kernels on read(), and not written to by
+ * older kernels on write(), with the kernel reporting the size it did
+ * accept as the result.
+ *
+ * This would have allowed userspace to detect on read() and write()
+ * which kernel structure version it was dealing with, and if was just
+ * recompiled it would have gotten the new fields, but obviously not
+ * accessed them, but things should've continued to work.
+ *
+ * Unfortunately, while actually exercising this mechanism to add the
+ * hard block reasons field, we found that userspace (notably systemd)
+ * did all kinds of fun things not in line with this scheme:
+ *
+ * 1. treat the (expected) short writes as an error;
+ * 2. ask to read sizeof(struct rfkill_event) but then compare the
+ * actual return value to RFKILL_EVENT_SIZE_V1 and treat any
+ * mismatch as an error.
+ *
+ * As a consequence, just recompiling with a new struct version caused
+ * things to no longer work correctly on old and new kernels.
+ *
+ * Hence, we've rolled back &struct rfkill_event to the original version
+ * and added &struct rfkill_event_ext. This effectively reverts to the
+ * old behaviour for all userspace, unless it explicitly opts in to the
+ * rules outlined here by using the new &struct rfkill_event_ext.
+ *
+ * Userspace using &struct rfkill_event_ext must adhere to the following
+ * rules
*
- * One exception is the kernel -- we already have two event sizes in
- * that we've made the 'hard' member optional since our only option
- * is to ignore it anyway.
+ * 1. accept short writes, optionally using them to detect that it's
+ * running on an older kernel;
+ * 2. accept short reads, knowing that this means it's running on an
+ * older kernel;
+ * 3. treat reads that are as long as requested as acceptable, not
+ * checking against RFKILL_EVENT_SIZE_V1 or such.
*/
-#define RFKILL_EVENT_SIZE_V1 8
+#define RFKILL_EVENT_SIZE_V1 sizeof(struct rfkill_event)
/* ioctl for turning off rfkill-input (if present) */
#define RFKILL_IOC_MAGIC 'R'
#define HISI_QM_API_VER_BASE "hisi_qm_v1"
#define HISI_QM_API_VER2_BASE "hisi_qm_v2"
+#define HISI_QM_API_VER3_BASE "hisi_qm_v3"
/* UACCE_CMD_QM_SET_QP_CTX: Set qp algorithm type */
#define UACCE_CMD_QM_SET_QP_CTX _IOWR('H', 10, struct hisi_qp_ctx)
#include <xen/xen.h>
#include <linux/acpi.h>
-#define ACPI_MEMORY_DEVICE_CLASS "memory"
-#define ACPI_MEMORY_DEVICE_HID "PNP0C80"
-#define ACPI_MEMORY_DEVICE_NAME "Hotplug Mem Device"
-
-int xen_stub_memory_device_init(void);
-void xen_stub_memory_device_exit(void);
-
-#define ACPI_PROCESSOR_CLASS "processor"
-#define ACPI_PROCESSOR_DEVICE_HID "ACPI0007"
-#define ACPI_PROCESSOR_DEVICE_NAME "Processor"
-
-int xen_stub_processor_init(void);
-void xen_stub_processor_exit(void);
-
-void xen_pcpu_hotplug_sync(void);
-int xen_pcpu_id(uint32_t acpi_id);
-
-static inline int xen_acpi_get_pxm(acpi_handle h)
-{
- unsigned long long pxm;
- acpi_status status;
- acpi_handle handle;
- acpi_handle phandle = h;
-
- do {
- handle = phandle;
- status = acpi_evaluate_integer(handle, "_PXM", NULL, &pxm);
- if (ACPI_SUCCESS(status))
- return pxm;
- status = acpi_get_parent(handle, &phandle);
- } while (ACPI_SUCCESS(status));
-
- return -ENXIO;
-}
-
int xen_acpi_notify_hypervisor_sleep(u8 sleep_state,
u32 pm1a_cnt, u32 pm1b_cnd);
int xen_acpi_notify_hypervisor_extended_sleep(u8 sleep_state,
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ARM_SWIOTLB_XEN_H
+#define _ASM_ARM_SWIOTLB_XEN_H
+
+extern int xen_swiotlb_detect(void);
+
+#endif /* _ASM_ARM_SWIOTLB_XEN_H */
#include <linux/page-flags.h>
#include <linux/kernel.h>
+/*
+ * Technically there's no reliably invalid grant reference or grant handle,
+ * so pick the value that is the most unlikely one to be observed valid.
+ */
+#define INVALID_GRANT_REF ((grant_ref_t)-1)
+#define INVALID_GRANT_HANDLE ((grant_handle_t)-1)
+
#define GNTTAB_RESERVED_XENSTORE 1
/* NR_GRANT_FRAMES must be less than or equal to that configured in Xen */
*/
#define XENFEAT_linux_rsdp_unrestricted 15
+/*
+ * A direct-mapped (or 1:1 mapped) domain is a domain for which its
+ * local pages have gfn == mfn. If a domain is direct-mapped,
+ * XENFEAT_direct_mapped is set; otherwise XENFEAT_not_direct_mapped
+ * is set.
+ *
+ * If neither flag is set (e.g. older Xen releases) the assumptions are:
+ * - not auto_translated domains (x86 only) are always direct-mapped
+ * - on x86, auto_translated domains are not direct-mapped
+ * - on ARM, Dom0 is direct-mapped, DomUs are not
+ */
+#define XENFEAT_not_direct_mapped 16
+#define XENFEAT_direct_mapped 17
+
#define XENFEAT_NR_SUBMAPS 1
#endif /* __XEN_PUBLIC_FEATURES_H__ */
#define __LINUX_SWIOTLB_XEN_H
#include <linux/swiotlb.h>
+#include <asm/xen/swiotlb-xen.h>
void xen_dma_sync_for_cpu(struct device *dev, dma_addr_t handle,
size_t size, enum dma_data_direction dir);
#define XENBUS_MAX_RING_GRANT_ORDER 4
#define XENBUS_MAX_RING_GRANTS (1U << XENBUS_MAX_RING_GRANT_ORDER)
-#define INVALID_GRANT_HANDLE (~0U)
/* Register callback to watch this node. */
struct xenbus_watch
When the compiler is updated, Kconfig will be invoked.
- Ensure full rebuild when the compiler is updated
- include/linux/kconfig.h contains this option in the comment line so
- fixdep adds include/config/cc/version/text.h into the auto-generated
- dependency. When the compiler is updated, syncconfig will touch it
- and then every file will be rebuilt.
+ include/linux/compiler-version.h contains this option in the comment
+ line so fixdep adds include/config/cc/version/text.h into the
+ auto-generated dependency. When the compiler is updated, syncconfig
+ will touch it and then every file will be rebuilt.
config CC_IS_GCC
def_bool $(success,test "$(cc-name)" = GCC)
config COMPILE_TEST
bool "Compile also drivers which will not load"
- depends on !UML && !S390
- default n
+ depends on HAS_IOMEM
help
Some drivers can be compiled on a different platform than they are
intended to be run on. Despite they cannot be loaded there (or even
pti_init();
}
+#ifdef CONFIG_HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
+DEFINE_STATIC_KEY_MAYBE_RO(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT,
+ randomize_kstack_offset);
+DEFINE_PER_CPU(u32, kstack_offset);
+
+static int __init early_randomize_kstack_offset(char *buf)
+{
+ int ret;
+ bool bool_result;
+
+ ret = kstrtobool(buf, &bool_result);
+ if (ret)
+ return ret;
+
+ if (bool_result)
+ static_branch_enable(&randomize_kstack_offset);
+ else
+ static_branch_disable(&randomize_kstack_offset);
+ return 0;
+}
+early_param("randomize_kstack_offset", early_randomize_kstack_offset);
+#endif
+
void __init __weak arch_call_rest_init(void)
{
rest_init();
fd = *(int *)key;
f = fget_raw(fd);
if (!f)
- return NULL;
+ return ERR_PTR(-EBADF);
sdata = inode_storage_lookup(f->f_inode, map, true);
fput(f);
tprogs[BPF_TRAMP_FENTRY].progs[0] = prog;
tprogs[BPF_TRAMP_FENTRY].nr_progs = 1;
- err = arch_prepare_bpf_trampoline(image,
+ err = arch_prepare_bpf_trampoline(NULL, image,
st_map->image + PAGE_SIZE,
&st_ops->func_models[i], 0,
tprogs, NULL);
* is not supported yet.
* BPF_PROG_TYPE_RAW_TRACEPOINT is fine.
*/
- if (log->level & BPF_LOG_LEVEL)
- bpf_log(log, "arg#%d type is not a struct\n", arg);
return NULL;
}
tname = btf_name_by_offset(btf, t->name_off);
}
pure_initcall(bpf_jit_charge_init);
-static int bpf_jit_charge_modmem(u32 pages)
+int bpf_jit_charge_modmem(u32 pages)
{
if (atomic_long_add_return(pages, &bpf_jit_current) >
(bpf_jit_limit >> PAGE_SHIFT)) {
return 0;
}
-static void bpf_jit_uncharge_modmem(u32 pages)
+void bpf_jit_uncharge_modmem(u32 pages)
{
atomic_long_sub(pages, &bpf_jit_current);
}
* clone is guaranteed to not be locked.
*/
fp->aux = NULL;
+ fp->stats = NULL;
+ fp->active = NULL;
__bpf_prog_free(fp);
}
/* Return TRUE if the JIT backend wants verifier to enable sub-register usage
* analysis code and wants explicit zero extension inserted by verifier.
* Otherwise, return FALSE.
+ *
+ * The verifier inserts an explicit zero extension after BPF_CMPXCHGs even if
+ * you don't override this. JITs that don't want these extra insns can detect
+ * them using insn_is_zext.
*/
bool __weak bpf_jit_needs_zext(void)
{
[BPF_ADD >> 4] = "add",
[BPF_AND >> 4] = "and",
[BPF_OR >> 4] = "or",
- [BPF_XOR >> 4] = "or",
+ [BPF_XOR >> 4] = "xor",
};
static const char *const bpf_ldst_string[] = {
return PTR_ERR(raw);
if (type == BPF_TYPE_PROG)
- ret = bpf_prog_new_fd(raw);
+ ret = (f_flags != O_RDWR) ? -EINVAL : bpf_prog_new_fd(raw);
else if (type == BPF_TYPE_MAP)
ret = bpf_map_new_fd(raw, f_flags);
else if (type == BPF_TYPE_LINK)
- ret = bpf_link_new_fd(raw);
+ ret = (f_flags != O_RDWR) ? -EINVAL : bpf_link_new_fd(raw);
else
return -ENOENT;
&magic, sizeof(magic), &pos);
if (n != sizeof(magic))
return -EPIPE;
+
tgid = umd_ops.info.tgid;
- wait_event(tgid->wait_pidfd, thread_group_exited(tgid));
- umd_ops.info.tgid = NULL;
+ if (tgid) {
+ wait_event(tgid->wait_pidfd, thread_group_exited(tgid));
+ umd_cleanup_helper(&umd_ops.info);
+ }
return 0;
}
static void __exit fini_umd(void)
{
+ struct pid *tgid;
+
bpf_preload_ops = NULL;
+
/* kill UMD in case it's still there due to earlier error */
- kill_pid(umd_ops.info.tgid, SIGKILL, 1);
- umd_ops.info.tgid = NULL;
+ tgid = umd_ops.info.tgid;
+ if (tgid) {
+ kill_pid(tgid, SIGKILL, 1);
+
+ wait_event(tgid->wait_pidfd, thread_group_exited(tgid));
+ umd_cleanup_helper(&umd_ops.info);
+ }
umd_unload_blob(&umd_ops.info);
}
late_initcall(load_umd);
BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf,
u32, size, u64, flags)
{
- struct pt_regs *regs = task_pt_regs(task);
+ struct pt_regs *regs;
+ long res;
- return __bpf_get_stack(regs, task, NULL, buf, size, flags);
+ if (!try_get_task_stack(task))
+ return -EFAULT;
+
+ regs = task_pt_regs(task);
+ res = __bpf_get_stack(regs, task, NULL, buf, size, flags);
+ put_task_stack(task);
+
+ return res;
}
BTF_ID_LIST_SINGLE(bpf_get_task_stack_btf_ids, struct, task_struct)
err = PTR_ERR(btf);
goto free_map;
}
+ if (btf_is_kernel(btf)) {
+ btf_put(btf);
+ err = -EACCES;
+ goto free_map;
+ }
map->btf = btf;
if (attr->btf_value_type_id) {
#include <linux/btf.h>
#include <linux/rcupdate_trace.h>
#include <linux/rcupdate_wait.h>
+#include <linux/module.h>
/* dummy _ops. The verifier will operate on target program's ops. */
const struct bpf_verifier_ops bpf_extension_verifier_ops = {
PAGE_SIZE, true, ksym->name);
}
-static void bpf_trampoline_ksym_add(struct bpf_trampoline *tr)
-{
- struct bpf_ksym *ksym = &tr->ksym;
-
- snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu", tr->key);
- bpf_image_ksym_add(tr->image, ksym);
-}
-
static struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
{
struct bpf_trampoline *tr;
struct hlist_head *head;
- void *image;
int i;
mutex_lock(&trampoline_mutex);
if (!tr)
goto out;
- /* is_root was checked earlier. No need for bpf_jit_charge_modmem() */
- image = bpf_jit_alloc_exec_page();
- if (!image) {
- kfree(tr);
- tr = NULL;
- goto out;
- }
-
tr->key = key;
INIT_HLIST_NODE(&tr->hlist);
hlist_add_head(&tr->hlist, head);
mutex_init(&tr->mutex);
for (i = 0; i < BPF_TRAMP_MAX; i++)
INIT_HLIST_HEAD(&tr->progs_hlist[i]);
- tr->image = image;
- INIT_LIST_HEAD_RCU(&tr->ksym.lnode);
- bpf_trampoline_ksym_add(tr);
out:
mutex_unlock(&trampoline_mutex);
return tr;
}
+static int bpf_trampoline_module_get(struct bpf_trampoline *tr)
+{
+ struct module *mod;
+ int err = 0;
+
+ preempt_disable();
+ mod = __module_text_address((unsigned long) tr->func.addr);
+ if (mod && !try_module_get(mod))
+ err = -ENOENT;
+ preempt_enable();
+ tr->mod = mod;
+ return err;
+}
+
+static void bpf_trampoline_module_put(struct bpf_trampoline *tr)
+{
+ module_put(tr->mod);
+ tr->mod = NULL;
+}
+
static int is_ftrace_location(void *ip)
{
long addr;
ret = unregister_ftrace_direct((long)ip, (long)old_addr);
else
ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, NULL);
+
+ if (!ret)
+ bpf_trampoline_module_put(tr);
return ret;
}
return ret;
tr->func.ftrace_managed = ret;
+ if (bpf_trampoline_module_get(tr))
+ return -ENOENT;
+
if (tr->func.ftrace_managed)
ret = register_ftrace_direct((long)ip, (long)new_addr);
else
ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, NULL, new_addr);
+
+ if (ret)
+ bpf_trampoline_module_put(tr);
return ret;
}
return tprogs;
}
+static void __bpf_tramp_image_put_deferred(struct work_struct *work)
+{
+ struct bpf_tramp_image *im;
+
+ im = container_of(work, struct bpf_tramp_image, work);
+ bpf_image_ksym_del(&im->ksym);
+ bpf_jit_free_exec(im->image);
+ bpf_jit_uncharge_modmem(1);
+ percpu_ref_exit(&im->pcref);
+ kfree_rcu(im, rcu);
+}
+
+/* callback, fexit step 3 or fentry step 2 */
+static void __bpf_tramp_image_put_rcu(struct rcu_head *rcu)
+{
+ struct bpf_tramp_image *im;
+
+ im = container_of(rcu, struct bpf_tramp_image, rcu);
+ INIT_WORK(&im->work, __bpf_tramp_image_put_deferred);
+ schedule_work(&im->work);
+}
+
+/* callback, fexit step 2. Called after percpu_ref_kill confirms. */
+static void __bpf_tramp_image_release(struct percpu_ref *pcref)
+{
+ struct bpf_tramp_image *im;
+
+ im = container_of(pcref, struct bpf_tramp_image, pcref);
+ call_rcu_tasks(&im->rcu, __bpf_tramp_image_put_rcu);
+}
+
+/* callback, fexit or fentry step 1 */
+static void __bpf_tramp_image_put_rcu_tasks(struct rcu_head *rcu)
+{
+ struct bpf_tramp_image *im;
+
+ im = container_of(rcu, struct bpf_tramp_image, rcu);
+ if (im->ip_after_call)
+ /* the case of fmod_ret/fexit trampoline and CONFIG_PREEMPTION=y */
+ percpu_ref_kill(&im->pcref);
+ else
+ /* the case of fentry trampoline */
+ call_rcu_tasks(&im->rcu, __bpf_tramp_image_put_rcu);
+}
+
+static void bpf_tramp_image_put(struct bpf_tramp_image *im)
+{
+ /* The trampoline image that calls original function is using:
+ * rcu_read_lock_trace to protect sleepable bpf progs
+ * rcu_read_lock to protect normal bpf progs
+ * percpu_ref to protect trampoline itself
+ * rcu tasks to protect trampoline asm not covered by percpu_ref
+ * (which are few asm insns before __bpf_tramp_enter and
+ * after __bpf_tramp_exit)
+ *
+ * The trampoline is unreachable before bpf_tramp_image_put().
+ *
+ * First, patch the trampoline to avoid calling into fexit progs.
+ * The progs will be freed even if the original function is still
+ * executing or sleeping.
+ * In case of CONFIG_PREEMPT=y use call_rcu_tasks() to wait on
+ * first few asm instructions to execute and call into
+ * __bpf_tramp_enter->percpu_ref_get.
+ * Then use percpu_ref_kill to wait for the trampoline and the original
+ * function to finish.
+ * Then use call_rcu_tasks() to make sure few asm insns in
+ * the trampoline epilogue are done as well.
+ *
+ * In !PREEMPT case the task that got interrupted in the first asm
+ * insns won't go through an RCU quiescent state which the
+ * percpu_ref_kill will be waiting for. Hence the first
+ * call_rcu_tasks() is not necessary.
+ */
+ if (im->ip_after_call) {
+ int err = bpf_arch_text_poke(im->ip_after_call, BPF_MOD_JUMP,
+ NULL, im->ip_epilogue);
+ WARN_ON(err);
+ if (IS_ENABLED(CONFIG_PREEMPTION))
+ call_rcu_tasks(&im->rcu, __bpf_tramp_image_put_rcu_tasks);
+ else
+ percpu_ref_kill(&im->pcref);
+ return;
+ }
+
+ /* The trampoline without fexit and fmod_ret progs doesn't call original
+ * function and doesn't use percpu_ref.
+ * Use call_rcu_tasks_trace() to wait for sleepable progs to finish.
+ * Then use call_rcu_tasks() to wait for the rest of trampoline asm
+ * and normal progs.
+ */
+ call_rcu_tasks_trace(&im->rcu, __bpf_tramp_image_put_rcu_tasks);
+}
+
+static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, u32 idx)
+{
+ struct bpf_tramp_image *im;
+ struct bpf_ksym *ksym;
+ void *image;
+ int err = -ENOMEM;
+
+ im = kzalloc(sizeof(*im), GFP_KERNEL);
+ if (!im)
+ goto out;
+
+ err = bpf_jit_charge_modmem(1);
+ if (err)
+ goto out_free_im;
+
+ err = -ENOMEM;
+ im->image = image = bpf_jit_alloc_exec_page();
+ if (!image)
+ goto out_uncharge;
+
+ err = percpu_ref_init(&im->pcref, __bpf_tramp_image_release, 0, GFP_KERNEL);
+ if (err)
+ goto out_free_image;
+
+ ksym = &im->ksym;
+ INIT_LIST_HEAD_RCU(&ksym->lnode);
+ snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu_%u", key, idx);
+ bpf_image_ksym_add(image, ksym);
+ return im;
+
+out_free_image:
+ bpf_jit_free_exec(im->image);
+out_uncharge:
+ bpf_jit_uncharge_modmem(1);
+out_free_im:
+ kfree(im);
+out:
+ return ERR_PTR(err);
+}
+
static int bpf_trampoline_update(struct bpf_trampoline *tr)
{
- void *old_image = tr->image + ((tr->selector + 1) & 1) * PAGE_SIZE/2;
- void *new_image = tr->image + (tr->selector & 1) * PAGE_SIZE/2;
+ struct bpf_tramp_image *im;
struct bpf_tramp_progs *tprogs;
u32 flags = BPF_TRAMP_F_RESTORE_REGS;
int err, total;
return PTR_ERR(tprogs);
if (total == 0) {
- err = unregister_fentry(tr, old_image);
+ err = unregister_fentry(tr, tr->cur_image->image);
+ bpf_tramp_image_put(tr->cur_image);
+ tr->cur_image = NULL;
tr->selector = 0;
goto out;
}
+ im = bpf_tramp_image_alloc(tr->key, tr->selector);
+ if (IS_ERR(im)) {
+ err = PTR_ERR(im);
+ goto out;
+ }
+
if (tprogs[BPF_TRAMP_FEXIT].nr_progs ||
tprogs[BPF_TRAMP_MODIFY_RETURN].nr_progs)
flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME;
- /* Though the second half of trampoline page is unused a task could be
- * preempted in the middle of the first half of trampoline and two
- * updates to trampoline would change the code from underneath the
- * preempted task. Hence wait for tasks to voluntarily schedule or go
- * to userspace.
- * The same trampoline can hold both sleepable and non-sleepable progs.
- * synchronize_rcu_tasks_trace() is needed to make sure all sleepable
- * programs finish executing.
- * Wait for these two grace periods together.
- */
- synchronize_rcu_mult(call_rcu_tasks, call_rcu_tasks_trace);
-
- err = arch_prepare_bpf_trampoline(new_image, new_image + PAGE_SIZE / 2,
+ err = arch_prepare_bpf_trampoline(im, im->image, im->image + PAGE_SIZE,
&tr->func.model, flags, tprogs,
tr->func.addr);
if (err < 0)
goto out;
- if (tr->selector)
+ WARN_ON(tr->cur_image && tr->selector == 0);
+ WARN_ON(!tr->cur_image && tr->selector);
+ if (tr->cur_image)
/* progs already running at this address */
- err = modify_fentry(tr, old_image, new_image);
+ err = modify_fentry(tr, tr->cur_image->image, im->image);
else
/* first time registering */
- err = register_fentry(tr, new_image);
+ err = register_fentry(tr, im->image);
if (err)
goto out;
+ if (tr->cur_image)
+ bpf_tramp_image_put(tr->cur_image);
+ tr->cur_image = im;
tr->selector++;
out:
kfree(tprogs);
goto out;
if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FEXIT])))
goto out;
- bpf_image_ksym_del(&tr->ksym);
- /* This code will be executed when all bpf progs (both sleepable and
- * non-sleepable) went through
- * bpf_prog_put()->call_rcu[_tasks_trace]()->bpf_prog_free_deferred().
- * Hence no need for another synchronize_rcu_tasks_trace() here,
- * but synchronize_rcu_tasks() is still needed, since trampoline
- * may not have had any sleepable programs and we need to wait
- * for tasks to get out of trampoline code before freeing it.
+ /* This code will be executed even when the last bpf_tramp_image
+ * is alive. All progs are detached from the trampoline and the
+ * trampoline image is patched with jmp into epilogue to skip
+ * fexit progs. The fentry-only trampoline will be freed via
+ * multiple rcu callbacks.
*/
- synchronize_rcu_tasks();
- bpf_jit_free_exec(tr->image);
hlist_del(&tr->hlist);
kfree(tr);
out:
rcu_read_unlock_trace();
}
+void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr)
+{
+ percpu_ref_get(&tr->pcref);
+}
+
+void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr)
+{
+ percpu_ref_put(&tr->pcref);
+}
+
int __weak
-arch_prepare_bpf_trampoline(void *image, void *image_end,
+arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end,
const struct btf_func_model *m, u32 flags,
struct bpf_tramp_progs *tprogs,
void *orig_call)
func_id == BPF_FUNC_skc_to_tcp_request_sock;
}
+static bool is_cmpxchg_insn(const struct bpf_insn *insn)
+{
+ return BPF_CLASS(insn->code) == BPF_STX &&
+ BPF_MODE(insn->code) == BPF_ATOMIC &&
+ insn->imm == BPF_CMPXCHG;
+}
+
/* string representation of 'enum bpf_reg_type' */
static const char * const reg_type_str[] = {
[NOT_INIT] = "?",
reg->type = PTR_TO_RDWR_BUF;
break;
default:
- WARN_ON("unknown nullable register type");
+ WARN_ONCE(1, "unknown nullable register type");
}
}
}
if (class == BPF_STX) {
- if (reg->type != SCALAR_VALUE)
+ /* BPF_STX (including atomic variants) has multiple source
+ * operands, one of which is a ptr. Check whether the caller is
+ * asking about it.
+ */
+ if (t == SRC_OP && reg->type != SCALAR_VALUE)
return true;
return BPF_SIZE(code) == BPF_DW;
}
return true;
}
-/* Return TRUE if INSN doesn't have explicit value define. */
-static bool insn_no_def(struct bpf_insn *insn)
+/* Return the regno defined by the insn, or -1. */
+static int insn_def_regno(const struct bpf_insn *insn)
{
- u8 class = BPF_CLASS(insn->code);
-
- return (class == BPF_JMP || class == BPF_JMP32 ||
- class == BPF_STX || class == BPF_ST);
+ switch (BPF_CLASS(insn->code)) {
+ case BPF_JMP:
+ case BPF_JMP32:
+ case BPF_ST:
+ return -1;
+ case BPF_STX:
+ if (BPF_MODE(insn->code) == BPF_ATOMIC &&
+ (insn->imm & BPF_FETCH)) {
+ if (insn->imm == BPF_CMPXCHG)
+ return BPF_REG_0;
+ else
+ return insn->src_reg;
+ } else {
+ return -1;
+ }
+ default:
+ return insn->dst_reg;
+ }
}
/* Return TRUE if INSN has defined any 32-bit value explicitly. */
static bool insn_has_def32(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
- if (insn_no_def(insn))
+ int dst_reg = insn_def_regno(insn);
+
+ if (dst_reg == -1)
return false;
- return !is_reg64(env, insn, insn->dst_reg, NULL, DST_OP);
+ return !is_reg64(env, insn, dst_reg, NULL, DST_OP);
}
static void mark_insn_zext(struct bpf_verifier_env *env,
return &env->insn_aux_data[env->insn_idx];
}
+enum {
+ REASON_BOUNDS = -1,
+ REASON_TYPE = -2,
+ REASON_PATHS = -3,
+ REASON_LIMIT = -4,
+ REASON_STACK = -5,
+};
+
static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
- u32 *ptr_limit, u8 opcode, bool off_is_neg)
+ const struct bpf_reg_state *off_reg,
+ u32 *alu_limit, u8 opcode)
{
+ bool off_is_neg = off_reg->smin_value < 0;
bool mask_to_left = (opcode == BPF_ADD && off_is_neg) ||
(opcode == BPF_SUB && !off_is_neg);
- u32 off;
+ u32 max = 0, ptr_limit = 0;
+
+ if (!tnum_is_const(off_reg->var_off) &&
+ (off_reg->smin_value < 0) != (off_reg->smax_value < 0))
+ return REASON_BOUNDS;
switch (ptr_reg->type) {
case PTR_TO_STACK:
- /* Indirect variable offset stack access is prohibited in
- * unprivileged mode so it's not handled here.
+ /* Offset 0 is out-of-bounds, but acceptable start for the
+ * left direction, see BPF_REG_FP. Also, unknown scalar
+ * offset where we would need to deal with min/max bounds is
+ * currently prohibited for unprivileged.
*/
- off = ptr_reg->off + ptr_reg->var_off.value;
- if (mask_to_left)
- *ptr_limit = MAX_BPF_STACK + off;
- else
- *ptr_limit = -off;
- return 0;
+ max = MAX_BPF_STACK + mask_to_left;
+ ptr_limit = -(ptr_reg->var_off.value + ptr_reg->off);
+ break;
case PTR_TO_MAP_VALUE:
- if (mask_to_left) {
- *ptr_limit = ptr_reg->umax_value + ptr_reg->off;
- } else {
- off = ptr_reg->smin_value + ptr_reg->off;
- *ptr_limit = ptr_reg->map_ptr->value_size - off;
- }
- return 0;
+ max = ptr_reg->map_ptr->value_size;
+ ptr_limit = (mask_to_left ?
+ ptr_reg->smin_value :
+ ptr_reg->umax_value) + ptr_reg->off;
+ break;
default:
- return -EINVAL;
+ return REASON_TYPE;
}
+
+ if (ptr_limit >= max)
+ return REASON_LIMIT;
+ *alu_limit = ptr_limit;
+ return 0;
}
static bool can_skip_alu_sanitation(const struct bpf_verifier_env *env,
if (aux->alu_state &&
(aux->alu_state != alu_state ||
aux->alu_limit != alu_limit))
- return -EACCES;
+ return REASON_PATHS;
/* Corresponding fixup done in fixup_bpf_calls(). */
aux->alu_state = alu_state;
return update_alu_sanitation_state(aux, BPF_ALU_NON_POINTER, 0);
}
+static bool sanitize_needed(u8 opcode)
+{
+ return opcode == BPF_ADD || opcode == BPF_SUB;
+}
+
static int sanitize_ptr_alu(struct bpf_verifier_env *env,
struct bpf_insn *insn,
const struct bpf_reg_state *ptr_reg,
+ const struct bpf_reg_state *off_reg,
struct bpf_reg_state *dst_reg,
- bool off_is_neg)
+ struct bpf_insn_aux_data *tmp_aux,
+ const bool commit_window)
{
+ struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : tmp_aux;
struct bpf_verifier_state *vstate = env->cur_state;
- struct bpf_insn_aux_data *aux = cur_aux(env);
+ bool off_is_neg = off_reg->smin_value < 0;
bool ptr_is_dst_reg = ptr_reg == dst_reg;
u8 opcode = BPF_OP(insn->code);
u32 alu_state, alu_limit;
struct bpf_reg_state tmp;
bool ret;
+ int err;
if (can_skip_alu_sanitation(env, insn))
return 0;
if (vstate->speculative)
goto do_sim;
- alu_state = off_is_neg ? BPF_ALU_NEG_VALUE : 0;
- alu_state |= ptr_is_dst_reg ?
- BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;
+ err = retrieve_ptr_limit(ptr_reg, off_reg, &alu_limit, opcode);
+ if (err < 0)
+ return err;
- if (retrieve_ptr_limit(ptr_reg, &alu_limit, opcode, off_is_neg))
- return 0;
- if (update_alu_sanitation_state(aux, alu_state, alu_limit))
- return -EACCES;
+ if (commit_window) {
+ /* In commit phase we narrow the masking window based on
+ * the observed pointer move after the simulated operation.
+ */
+ alu_state = tmp_aux->alu_state;
+ alu_limit = abs(tmp_aux->alu_limit - alu_limit);
+ } else {
+ alu_state = off_is_neg ? BPF_ALU_NEG_VALUE : 0;
+ alu_state |= ptr_is_dst_reg ?
+ BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;
+ }
+
+ err = update_alu_sanitation_state(aux, alu_state, alu_limit);
+ if (err < 0)
+ return err;
do_sim:
+ /* If we're in commit phase, we're done here given we already
+ * pushed the truncated dst_reg into the speculative verification
+ * stack.
+ */
+ if (commit_window)
+ return 0;
+
/* Simulate and find potential out-of-bounds access under
* speculative execution from truncation as a result of
* masking when off was not within expected range. If off
ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true);
if (!ptr_is_dst_reg && ret)
*dst_reg = tmp;
- return !ret ? -EFAULT : 0;
+ return !ret ? REASON_STACK : 0;
+}
+
+static int sanitize_err(struct bpf_verifier_env *env,
+ const struct bpf_insn *insn, int reason,
+ const struct bpf_reg_state *off_reg,
+ const struct bpf_reg_state *dst_reg)
+{
+ static const char *err = "pointer arithmetic with it prohibited for !root";
+ const char *op = BPF_OP(insn->code) == BPF_ADD ? "add" : "sub";
+ u32 dst = insn->dst_reg, src = insn->src_reg;
+
+ switch (reason) {
+ case REASON_BOUNDS:
+ verbose(env, "R%d has unknown scalar with mixed signed bounds, %s\n",
+ off_reg == dst_reg ? dst : src, err);
+ break;
+ case REASON_TYPE:
+ verbose(env, "R%d has pointer with unsupported alu operation, %s\n",
+ off_reg == dst_reg ? src : dst, err);
+ break;
+ case REASON_PATHS:
+ verbose(env, "R%d tried to %s from different maps, paths or scalars, %s\n",
+ dst, op, err);
+ break;
+ case REASON_LIMIT:
+ verbose(env, "R%d tried to %s beyond pointer bounds, %s\n",
+ dst, op, err);
+ break;
+ case REASON_STACK:
+ verbose(env, "R%d could not be pushed for speculative verification, %s\n",
+ dst, err);
+ break;
+ default:
+ verbose(env, "verifier internal error: unknown reason (%d)\n",
+ reason);
+ break;
+ }
+
+ return -EACCES;
}
/* check that stack access falls within stack limits and that 'reg' doesn't
return 0;
}
+static int sanitize_check_bounds(struct bpf_verifier_env *env,
+ const struct bpf_insn *insn,
+ const struct bpf_reg_state *dst_reg)
+{
+ u32 dst = insn->dst_reg;
+
+ /* For unprivileged we require that resulting offset must be in bounds
+ * in order to be able to sanitize access later on.
+ */
+ if (env->bypass_spec_v1)
+ return 0;
+
+ switch (dst_reg->type) {
+ case PTR_TO_STACK:
+ if (check_stack_access_for_ptr_arithmetic(env, dst, dst_reg,
+ dst_reg->off + dst_reg->var_off.value))
+ return -EACCES;
+ break;
+ case PTR_TO_MAP_VALUE:
+ if (check_map_access(env, dst, dst_reg->off, 1, false)) {
+ verbose(env, "R%d pointer arithmetic of map value goes out of range, "
+ "prohibited for !root\n", dst);
+ return -EACCES;
+ }
+ break;
+ default:
+ break;
+ }
+
+ return 0;
+}
/* Handles arithmetic on a pointer and a scalar: computes new min/max and var_off.
* Caller should also handle BPF_MOV case separately.
smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value;
u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value,
umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value;
- u32 dst = insn->dst_reg, src = insn->src_reg;
+ struct bpf_insn_aux_data tmp_aux = {};
u8 opcode = BPF_OP(insn->code);
+ u32 dst = insn->dst_reg;
int ret;
dst_reg = ®s[dst];
verbose(env, "R%d pointer arithmetic on %s prohibited\n",
dst, reg_type_str[ptr_reg->type]);
return -EACCES;
- case PTR_TO_MAP_VALUE:
- if (!env->allow_ptr_leaks && !known && (smin_val < 0) != (smax_val < 0)) {
- verbose(env, "R%d has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root\n",
- off_reg == dst_reg ? dst : src);
- return -EACCES;
- }
- fallthrough;
default:
break;
}
/* pointer types do not carry 32-bit bounds at the moment. */
__mark_reg32_unbounded(dst_reg);
+ if (sanitize_needed(opcode)) {
+ ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg,
+ &tmp_aux, false);
+ if (ret < 0)
+ return sanitize_err(env, insn, ret, off_reg, dst_reg);
+ }
+
switch (opcode) {
case BPF_ADD:
- ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0);
- if (ret < 0) {
- verbose(env, "R%d tried to add from different maps or paths\n", dst);
- return ret;
- }
/* We can take a fixed offset as long as it doesn't overflow
* the s32 'off' field
*/
}
break;
case BPF_SUB:
- ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0);
- if (ret < 0) {
- verbose(env, "R%d tried to sub from different maps or paths\n", dst);
- return ret;
- }
if (dst_reg == off_reg) {
/* scalar -= pointer. Creates an unknown scalar */
verbose(env, "R%d tried to subtract pointer from scalar\n",
__reg_deduce_bounds(dst_reg);
__reg_bound_offset(dst_reg);
- /* For unprivileged we require that resulting offset must be in bounds
- * in order to be able to sanitize access later on.
- */
- if (!env->bypass_spec_v1) {
- if (dst_reg->type == PTR_TO_MAP_VALUE &&
- check_map_access(env, dst, dst_reg->off, 1, false)) {
- verbose(env, "R%d pointer arithmetic of map value goes out of range, "
- "prohibited for !root\n", dst);
- return -EACCES;
- } else if (dst_reg->type == PTR_TO_STACK &&
- check_stack_access_for_ptr_arithmetic(
- env, dst, dst_reg, dst_reg->off +
- dst_reg->var_off.value)) {
- return -EACCES;
- }
+ if (sanitize_check_bounds(env, insn, dst_reg) < 0)
+ return -EACCES;
+ if (sanitize_needed(opcode)) {
+ ret = sanitize_ptr_alu(env, insn, dst_reg, off_reg, dst_reg,
+ &tmp_aux, true);
+ if (ret < 0)
+ return sanitize_err(env, insn, ret, off_reg, dst_reg);
}
return 0;
s32 s32_min_val, s32_max_val;
u32 u32_min_val, u32_max_val;
u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32;
- u32 dst = insn->dst_reg;
- int ret;
bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64);
+ int ret;
smin_val = src_reg.smin_value;
smax_val = src_reg.smax_value;
return 0;
}
+ if (sanitize_needed(opcode)) {
+ ret = sanitize_val_alu(env, insn);
+ if (ret < 0)
+ return sanitize_err(env, insn, ret, NULL, NULL);
+ }
+
/* Calculate sign/unsigned bounds and tnum for alu32 and alu64 bit ops.
* There are two classes of instructions: The first class we track both
* alu32 and alu64 sign/unsigned bounds independently this provides the
*/
switch (opcode) {
case BPF_ADD:
- ret = sanitize_val_alu(env, insn);
- if (ret < 0) {
- verbose(env, "R%d tried to add from different pointers or scalars\n", dst);
- return ret;
- }
scalar32_min_max_add(dst_reg, &src_reg);
scalar_min_max_add(dst_reg, &src_reg);
dst_reg->var_off = tnum_add(dst_reg->var_off, src_reg.var_off);
break;
case BPF_SUB:
- ret = sanitize_val_alu(env, insn);
- if (ret < 0) {
- verbose(env, "R%d tried to sub from different pointers or scalars\n", dst);
- return ret;
- }
scalar32_min_max_sub(dst_reg, &src_reg);
scalar_min_max_sub(dst_reg, &src_reg);
dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off);
btf = btf_get_by_fd(attr->prog_btf_fd);
if (IS_ERR(btf))
return PTR_ERR(btf);
+ if (btf_is_kernel(btf)) {
+ btf_put(btf);
+ return -EACCES;
+ }
env->prog->aux->btf = btf;
err = check_btf_func(env, attr, uattr);
for (i = 0; i < len; i++) {
int adj_idx = i + delta;
struct bpf_insn insn;
- u8 load_reg;
+ int load_reg;
insn = insns[adj_idx];
+ load_reg = insn_def_regno(&insn);
if (!aux[adj_idx].zext_dst) {
u8 code, class;
u32 imm_rnd;
code = insn.code;
class = BPF_CLASS(code);
- if (insn_no_def(&insn))
+ if (load_reg == -1)
continue;
/* NOTE: arg "reg" (the fourth one) is only used for
- * BPF_STX which has been ruled out in above
- * check, it is safe to pass NULL here.
+ * BPF_STX + SRC_OP, so it is safe to pass NULL
+ * here.
*/
- if (is_reg64(env, &insn, insn.dst_reg, NULL, DST_OP)) {
+ if (is_reg64(env, &insn, load_reg, NULL, DST_OP)) {
if (class == BPF_LD &&
BPF_MODE(code) == BPF_IMM)
i++;
imm_rnd = get_random_int();
rnd_hi32_patch[0] = insn;
rnd_hi32_patch[1].imm = imm_rnd;
- rnd_hi32_patch[3].dst_reg = insn.dst_reg;
+ rnd_hi32_patch[3].dst_reg = load_reg;
patch = rnd_hi32_patch;
patch_len = 4;
goto apply_patch_buffer;
}
- if (!bpf_jit_needs_zext())
+ /* Add in an zero-extend instruction if a) the JIT has requested
+ * it or b) it's a CMPXCHG.
+ *
+ * The latter is because: BPF_CMPXCHG always loads a value into
+ * R0, therefore always zero-extends. However some archs'
+ * equivalent instruction only does this load when the
+ * comparison is successful. This detail of CMPXCHG is
+ * orthogonal to the general zero-extension behaviour of the
+ * CPU, so it's treated independently of bpf_jit_needs_zext.
+ */
+ if (!bpf_jit_needs_zext() && !is_cmpxchg_insn(&insn))
continue;
- /* zext_dst means that we want to zero-extend whatever register
- * the insn defines, which is dst_reg most of the time, with
- * the notable exception of BPF_STX + BPF_ATOMIC + BPF_FETCH.
- */
- if (BPF_CLASS(insn.code) == BPF_STX &&
- BPF_MODE(insn.code) == BPF_ATOMIC) {
- /* BPF_STX + BPF_ATOMIC insns without BPF_FETCH do not
- * define any registers, therefore zext_dst cannot be
- * set.
- */
- if (WARN_ON(!(insn.imm & BPF_FETCH)))
- return -EINVAL;
- load_reg = insn.imm == BPF_CMPXCHG ? BPF_REG_0
- : insn.src_reg;
- } else {
- load_reg = insn.dst_reg;
+ if (WARN_ON(load_reg == -1)) {
+ verbose(env, "verifier bug. zext_dst is set, but no reg is defined\n");
+ return -EFAULT;
}
zext_patch[0] = insn;
off_reg = issrc ? insn->src_reg : insn->dst_reg;
if (isneg)
*patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1);
- *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit - 1);
+ *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit);
*patch++ = BPF_ALU64_REG(BPF_SUB, BPF_REG_AX, off_reg);
*patch++ = BPF_ALU64_REG(BPF_OR, BPF_REG_AX, off_reg);
*patch++ = BPF_ALU64_IMM(BPF_NEG, BPF_REG_AX, 0);
u32 btf_id, member_idx;
const char *mname;
+ if (!prog->gpl_compatible) {
+ verbose(env, "struct ops programs must have a GPL compatible license\n");
+ return -EINVAL;
+ }
+
btf_id = prog->aux->attach_btf_id;
st_ops = bpf_struct_ops_find(btf_id);
if (!st_ops) {
* Checking for rcu_is_watching() here would prevent the nesting
* interrupt to invoke rcu_irq_enter(). If that nested interrupt is
* the tick then rcu_flavor_sched_clock_irq() would wrongfully
- * assume that it is the first interupt and eventually claim
+ * assume that it is the first interrupt and eventually claim
* quiescent state and end grace periods prematurely.
*
* Unconditionally invoke rcu_irq_enter() so RCU state stays
instrumentation_begin();
if (IS_ENABLED(CONFIG_PREEMPTION)) {
-#ifdef CONFIG_PREEMT_DYNAMIC
+#ifdef CONFIG_PREEMPT_DYNAMIC
static_call(irqentry_exit_cond_resched)();
#else
irqentry_exit_cond_resched();
static atomic_t perf_sched_count;
static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
+static DEFINE_PER_CPU(int, perf_sched_cb_usages);
static DEFINE_PER_CPU(struct pmu_event_list, pmu_sb_events);
static atomic_t nr_mmap_events __read_mostly;
}
}
+static DEFINE_PER_CPU(struct list_head, sched_cb_list);
+
void perf_sched_cb_dec(struct pmu *pmu)
{
struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
- --cpuctx->sched_cb_usage;
+ this_cpu_dec(perf_sched_cb_usages);
+
+ if (!--cpuctx->sched_cb_usage)
+ list_del(&cpuctx->sched_cb_entry);
}
{
struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
- cpuctx->sched_cb_usage++;
+ if (!cpuctx->sched_cb_usage++)
+ list_add(&cpuctx->sched_cb_entry, this_cpu_ptr(&sched_cb_list));
+
+ this_cpu_inc(perf_sched_cb_usages);
}
/*
perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
}
+static void perf_pmu_sched_task(struct task_struct *prev,
+ struct task_struct *next,
+ bool sched_in)
+{
+ struct perf_cpu_context *cpuctx;
+
+ if (prev == next)
+ return;
+
+ list_for_each_entry(cpuctx, this_cpu_ptr(&sched_cb_list), sched_cb_entry) {
+ /* will be handled in perf_event_context_sched_in/out */
+ if (cpuctx->task_ctx)
+ continue;
+
+ __perf_pmu_sched_task(cpuctx, sched_in);
+ }
+}
+
static void perf_event_switch(struct task_struct *task,
struct task_struct *next_prev, bool sched_in);
{
int ctxn;
+ if (__this_cpu_read(perf_sched_cb_usages))
+ perf_pmu_sched_task(task, next, false);
+
if (atomic_read(&nr_switch_events))
perf_event_switch(task, next, false);
if (atomic_read(&nr_switch_events))
perf_event_switch(task, prev, true);
+
+ if (__this_cpu_read(perf_sched_cb_usages))
+ perf_pmu_sched_task(prev, task, true);
}
static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
if (event->parent)
return;
- if (event->attach_state & PERF_ATTACH_TASK)
+ if (event->attach_state & (PERF_ATTACH_TASK | PERF_ATTACH_SCHED_CB))
dec = true;
if (event->attr.mmap || event->attr.mmap_data)
atomic_dec(&nr_mmap_events);
if (event->parent)
return;
- if (event->attach_state & PERF_ATTACH_TASK)
+ if (event->attach_state & (PERF_ATTACH_TASK | PERF_ATTACH_SCHED_CB))
inc = true;
if (event->attr.mmap || event->attr.mmap_data)
atomic_inc(&nr_mmap_events);
#ifdef CONFIG_CGROUP_PERF
INIT_LIST_HEAD(&per_cpu(cgrp_cpuctx_list, cpu));
#endif
+ INIT_LIST_HEAD(&per_cpu(sched_cb_list, cpu));
}
}
#endif
}
+static void mm_init_pasid(struct mm_struct *mm)
+{
+#ifdef CONFIG_IOMMU_SUPPORT
+ mm->pasid = INIT_PASID;
+#endif
+}
+
static void mm_init_uprobes_state(struct mm_struct *mm)
{
#ifdef CONFIG_UPROBES
mm_init_cpumask(mm);
mm_init_aio(mm);
mm_init_owner(mm, p);
+ mm_init_pasid(mm);
RCU_INIT_POINTER(mm->exe_file, NULL);
mmu_notifier_subscriptions_init(mm);
init_tlb_flush_pending(mm);
p = dup_task_struct(current, node);
if (!p)
goto fork_out;
- if (args->io_thread)
+ if (args->io_thread) {
+ /*
+ * Mark us an IO worker, and block any signal that isn't
+ * fatal or STOP
+ */
p->flags |= PF_IO_WORKER;
+ siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP));
+ }
/*
* This _must_ happen before we call free_task(), i.e. before we jump
.stack_size = (unsigned long)arg,
.io_thread = 1,
};
- struct task_struct *tsk;
- tsk = copy_process(NULL, 0, node, &args);
- if (!IS_ERR(tsk)) {
- sigfillset(&tsk->blocked);
- sigdelsetmask(&tsk->blocked, sigmask(SIGKILL));
- }
- return tsk;
+ return copy_process(NULL, 0, node, &args);
}
/*
goto out;
restart = ¤t->restart_block;
- restart->fn = futex_wait_restart;
restart->futex.uaddr = uaddr;
restart->futex.val = val;
restart->futex.time = *abs_time;
restart->futex.bitset = bitset;
restart->futex.flags = flags | FLAGS_HAS_TIMEOUT;
- ret = -ERESTART_RESTARTBLOCK;
+ ret = set_restart_fn(restart, futex_wait_restart);
out:
if (to) {
u32 ident;
u32 checksum;
+#if CONFIG_CLANG_VERSION < 110000
u8 use_extra_checksum;
+#endif
u32 cfg_checksum;
u32 num_counters;
u64 *counters;
+#if CONFIG_CLANG_VERSION < 110000
const char *function_name;
+#endif
};
static struct gcov_info *current_info;
}
EXPORT_SYMBOL(llvm_gcov_init);
+#if CONFIG_CLANG_VERSION < 110000
void llvm_gcda_start_file(const char *orig_filename, const char version[4],
u32 checksum)
{
current_info->checksum = checksum;
}
EXPORT_SYMBOL(llvm_gcda_start_file);
+#else
+void llvm_gcda_start_file(const char *orig_filename, u32 version, u32 checksum)
+{
+ current_info->filename = orig_filename;
+ current_info->version = version;
+ current_info->checksum = checksum;
+}
+EXPORT_SYMBOL(llvm_gcda_start_file);
+#endif
+#if CONFIG_CLANG_VERSION < 110000
void llvm_gcda_emit_function(u32 ident, const char *function_name,
u32 func_checksum, u8 use_extra_checksum, u32 cfg_checksum)
{
list_add_tail(&info->head, ¤t_info->functions);
}
+#else
+void llvm_gcda_emit_function(u32 ident, u32 func_checksum, u32 cfg_checksum)
+{
+ struct gcov_fn_info *info = kzalloc(sizeof(*info), GFP_KERNEL);
+
+ if (!info)
+ return;
+
+ INIT_LIST_HEAD(&info->head);
+ info->ident = ident;
+ info->checksum = func_checksum;
+ info->cfg_checksum = cfg_checksum;
+ list_add_tail(&info->head, ¤t_info->functions);
+}
+#endif
EXPORT_SYMBOL(llvm_gcda_emit_function);
void llvm_gcda_emit_arcs(u32 num_counters, u64 *counters)
!list_is_last(&fn_ptr2->head, &info2->functions)) {
if (fn_ptr1->checksum != fn_ptr2->checksum)
return false;
+#if CONFIG_CLANG_VERSION < 110000
if (fn_ptr1->use_extra_checksum != fn_ptr2->use_extra_checksum)
return false;
if (fn_ptr1->use_extra_checksum &&
fn_ptr1->cfg_checksum != fn_ptr2->cfg_checksum)
return false;
+#else
+ if (fn_ptr1->cfg_checksum != fn_ptr2->cfg_checksum)
+ return false;
+#endif
fn_ptr1 = list_next_entry(fn_ptr1, head);
fn_ptr2 = list_next_entry(fn_ptr2, head);
}
}
}
+#if CONFIG_CLANG_VERSION < 110000
static struct gcov_fn_info *gcov_fn_info_dup(struct gcov_fn_info *fn)
{
size_t cv_size; /* counter values size */
kfree(fn_dup);
return NULL;
}
+#else
+static struct gcov_fn_info *gcov_fn_info_dup(struct gcov_fn_info *fn)
+{
+ size_t cv_size; /* counter values size */
+ struct gcov_fn_info *fn_dup = kmemdup(fn, sizeof(*fn),
+ GFP_KERNEL);
+ if (!fn_dup)
+ return NULL;
+ INIT_LIST_HEAD(&fn_dup->head);
+
+ cv_size = fn->num_counters * sizeof(fn->counters[0]);
+ fn_dup->counters = vmalloc(cv_size);
+ if (!fn_dup->counters) {
+ kfree(fn_dup);
+ return NULL;
+ }
+
+ memcpy(fn_dup->counters, fn->counters, cv_size);
+
+ return fn_dup;
+}
+#endif
/**
* gcov_info_dup - duplicate profiling data set
* gcov_info_free - release memory for profiling data set duplicate
* @info: profiling data set duplicate to free
*/
+#if CONFIG_CLANG_VERSION < 110000
void gcov_info_free(struct gcov_info *info)
{
struct gcov_fn_info *fn, *tmp;
kfree(info->filename);
kfree(info);
}
+#else
+void gcov_info_free(struct gcov_info *info)
+{
+ struct gcov_fn_info *fn, *tmp;
+
+ list_for_each_entry_safe(fn, tmp, &info->functions, head) {
+ vfree(fn->counters);
+ list_del(&fn->head);
+ kfree(fn);
+ }
+ kfree(info->filename);
+ kfree(info);
+}
+#endif
#define ITER_STRIDE PAGE_SIZE
list_for_each_entry(fi_ptr, &info->functions, head) {
u32 i;
- u32 len = 2;
-
- if (fi_ptr->use_extra_checksum)
- len++;
pos += store_gcov_u32(buffer, pos, GCOV_TAG_FUNCTION);
- pos += store_gcov_u32(buffer, pos, len);
+#if CONFIG_CLANG_VERSION < 110000
+ pos += store_gcov_u32(buffer, pos,
+ fi_ptr->use_extra_checksum ? 3 : 2);
+#else
+ pos += store_gcov_u32(buffer, pos, 3);
+#endif
pos += store_gcov_u32(buffer, pos, fi_ptr->ident);
pos += store_gcov_u32(buffer, pos, fi_ptr->checksum);
+#if CONFIG_CLANG_VERSION < 110000
if (fi_ptr->use_extra_checksum)
pos += store_gcov_u32(buffer, pos, fi_ptr->cfg_checksum);
+#else
+ pos += store_gcov_u32(buffer, pos, fi_ptr->cfg_checksum);
+#endif
pos += store_gcov_u32(buffer, pos, GCOV_TAG_COUNTER_BASE);
pos += store_gcov_u32(buffer, pos, fi_ptr->num_counters * 2);
* handle_edge_irq - edge type IRQ handler
* @desc: the interrupt description structure for this irq
*
- * Interrupt occures on the falling and/or rising edge of a hardware
+ * Interrupt occurs on the falling and/or rising edge of a hardware
* signal. The occurrence is latched into the irq controller hardware
* and must be acked in order to be reenabled. After the ack another
* interrupt can happen on the same source even before the first one
/*
* When another irq arrived while we were handling
* one, we could have masked the irq.
- * Renable it, if it was not disabled in meantime.
+ * Reenable it, if it was not disabled in meantime.
*/
if (unlikely(desc->istate & IRQS_PENDING)) {
if (!irqd_irq_disabled(&desc->irq_data) &&
* @dest: The affinity mask to set
* @force: Flag to enforce setting (disable online checks)
*
- * Conditinal, as the underlying parent chip might not implement it.
+ * Conditional, as the underlying parent chip might not implement it.
*/
int irq_chip_set_affinity_parent(struct irq_data *data,
const struct cpumask *dest, bool force)
#endif
/**
- * irq_chip_compose_msi_msg - Componse msi message for a irq chip
+ * irq_chip_compose_msi_msg - Compose msi message for a irq chip
* @data: Pointer to interrupt specific data
* @msg: Pointer to the MSI message
*
/*
* What should we do if we get a hw irq event on an illegal vector?
- * Each architecture has to answer this themself.
+ * Each architecture has to answer this themselves.
*/
static void ack_bad(struct irq_data *data)
{
* @irq: linux irq number to be destroyed
* @dest: cpumask of cpus which should have the IPI removed
*
- * The IPIs allocated with irq_reserve_ipi() are retuerned to the system
+ * The IPIs allocated with irq_reserve_ipi() are returned to the system
* destroying all virqs associated with them.
*
* Return 0 on success or error code on failure.
struct irq_sim_work_ctx *work_ctx;
};
-struct irq_sim_devres {
- struct irq_domain *domain;
-};
-
static void irq_sim_irqmask(struct irq_data *data)
{
struct irq_sim_irq_ctx *irq_ctx = irq_data_get_irq_chip_data(data);
* irq_domain_create_sim - Create a new interrupt simulator irq_domain and
* allocate a range of dummy interrupts.
*
- * @fnode: struct fwnode_handle to be associated with this domain.
+ * @fwnode: struct fwnode_handle to be associated with this domain.
* @num_irqs: Number of interrupts to allocate.
*
* On success: return a new irq_domain object.
}
EXPORT_SYMBOL_GPL(irq_domain_remove_sim);
-static void devm_irq_domain_release_sim(struct device *dev, void *res)
+static void devm_irq_domain_remove_sim(void *data)
{
- struct irq_sim_devres *this = res;
+ struct irq_domain *domain = data;
- irq_domain_remove_sim(this->domain);
+ irq_domain_remove_sim(domain);
}
/**
* a managed device.
*
* @dev: Device to initialize the simulator object for.
- * @fnode: struct fwnode_handle to be associated with this domain.
+ * @fwnode: struct fwnode_handle to be associated with this domain.
* @num_irqs: Number of interrupts to allocate
*
* On success: return a new irq_domain object.
struct fwnode_handle *fwnode,
unsigned int num_irqs)
{
- struct irq_sim_devres *dr;
+ struct irq_domain *domain;
+ int ret;
- dr = devres_alloc(devm_irq_domain_release_sim,
- sizeof(*dr), GFP_KERNEL);
- if (!dr)
- return ERR_PTR(-ENOMEM);
+ domain = irq_domain_create_sim(fwnode, num_irqs);
+ if (IS_ERR(domain))
+ return domain;
- dr->domain = irq_domain_create_sim(fwnode, num_irqs);
- if (IS_ERR(dr->domain)) {
- devres_free(dr);
- return dr->domain;
- }
+ ret = devm_add_action_or_reset(dev, devm_irq_domain_remove_sim, domain);
+ if (ret)
+ return ERR_PTR(ret);
- devres_add(dev, dr);
- return dr->domain;
+ return domain;
}
EXPORT_SYMBOL_GPL(devm_irq_domain_create_sim);
cpulist_parse(str, irq_default_affinity);
/*
* Set at least the boot cpu. We don't want to end up with
- * bugreports caused by random comandline masks
+ * bugreports caused by random commandline masks
*/
cpumask_set_cpu(smp_processor_id(), irq_default_affinity);
return 1;
* @name: Optional user provided domain name
* @pa: Optional user-provided physical address
*
- * Allocate a struct irqchip_fwid, and return a poiner to the embedded
+ * Allocate a struct irqchip_fwid, and return a pointer to the embedded
* fwnode_handle (or NULL on failure).
*
* Note: The types IRQCHIP_FWNODE_NAMED and IRQCHIP_FWNODE_NAMED_ID are
pr_debug("irq_create_mapping(0x%p, 0x%lx)\n", domain, hwirq);
- /* Look for default domain if nececssary */
+ /* Look for default domain if necessary */
if (domain == NULL)
domain = irq_default_domain;
if (domain == NULL) {
}
EXPORT_SYMBOL_GPL(irq_create_mapping_affinity);
-/**
- * irq_create_strict_mappings() - Map a range of hw irqs to fixed linux irqs
- * @domain: domain owning the interrupt range
- * @irq_base: beginning of linux IRQ range
- * @hwirq_base: beginning of hardware IRQ range
- * @count: Number of interrupts to map
- *
- * This routine is used for allocating and mapping a range of hardware
- * irqs to linux irqs where the linux irq numbers are at pre-defined
- * locations. For use by controllers that already have static mappings
- * to insert in to the domain.
- *
- * Non-linear users can use irq_create_identity_mapping() for IRQ-at-a-time
- * domain insertion.
- *
- * 0 is returned upon success, while any failure to establish a static
- * mapping is treated as an error.
- */
-int irq_create_strict_mappings(struct irq_domain *domain, unsigned int irq_base,
- irq_hw_number_t hwirq_base, int count)
-{
- struct device_node *of_node;
- int ret;
-
- of_node = irq_domain_get_of_node(domain);
- ret = irq_alloc_descs(irq_base, irq_base, count,
- of_node_to_nid(of_node));
- if (unlikely(ret < 0))
- return ret;
-
- irq_domain_associate_many(domain, irq_base, hwirq_base, count);
- return 0;
-}
-EXPORT_SYMBOL_GPL(irq_create_strict_mappings);
-
static int irq_domain_translate(struct irq_domain *d,
struct irq_fwspec *fwspec,
irq_hw_number_t *hwirq, unsigned int *type)
{
struct irq_data *data;
- /* Look for default domain if nececssary */
+ /* Look for default domain if necessary */
if (domain == NULL)
domain = irq_default_domain;
if (domain == NULL)
* The whole process to setup an IRQ has been split into two steps.
* The first step, __irq_domain_alloc_irqs(), is to allocate IRQ
* descriptor and required hardware resources. The second step,
- * irq_domain_activate_irq(), is to program hardwares with preallocated
+ * irq_domain_activate_irq(), is to program the hardware with preallocated
* resources. In this way, it's easier to rollback when failing to
* allocate resources.
*/
/**
* irq_domain_alloc_irqs_parent - Allocate interrupts from parent domain
+ * @domain: Domain below which interrupts must be allocated
* @irq_base: Base IRQ number
* @nr_irqs: Number of IRQs to allocate
* @arg: Allocation data (arch/domain specific)
- *
- * Check whether the domain has been setup recursive. If not allocate
- * through the parent domain.
*/
int irq_domain_alloc_irqs_parent(struct irq_domain *domain,
unsigned int irq_base, unsigned int nr_irqs,
/**
* irq_domain_free_irqs_parent - Free interrupts from parent domain
+ * @domain: Domain below which interrupts must be freed
* @irq_base: Base IRQ number
* @nr_irqs: Number of IRQs to free
- *
- * Check whether the domain has been setup recursive. If not free
- * through the parent domain.
*/
void irq_domain_free_irqs_parent(struct irq_domain *domain,
unsigned int irq_base, unsigned int nr_irqs)
static void debugfs_add_domain_dir(struct irq_domain *d)
{
- if (!d->name || !domain_dir || d->debugfs_file)
+ if (!d->name || !domain_dir)
return;
- d->debugfs_file = debugfs_create_file(d->name, 0444, domain_dir, d,
- &irq_domain_debug_fops);
+ debugfs_create_file(d->name, 0444, domain_dir, d,
+ &irq_domain_debug_fops);
}
static void debugfs_remove_domain_dir(struct irq_domain *d)
{
- debugfs_remove(d->debugfs_file);
- d->debugfs_file = NULL;
+ debugfs_remove(debugfs_lookup(d->name, domain_dir));
}
void __init irq_domain_debugfs_init(struct dentry *root)
/**
* irq_set_thread_affinity - Notify irq threads to adjust affinity
- * @desc: irq descriptor which has affitnity changed
+ * @desc: irq descriptor which has affinity changed
*
* We just set IRQTF_AFFINITY and delegate the affinity setting
* to the interrupt thread itself. We can not call
* If the interrupt is not yet activated, just store the affinity
* mask and do not call the chip driver at all. On activation the
* driver has to make sure anyway that the interrupt is in a
- * useable state so startup works.
+ * usable state so startup works.
*/
if (!IS_ENABLED(CONFIG_IRQ_DOMAIN_HIERARCHY) ||
irqd_is_activated(data) || !irqd_affinity_on_activate(data))
* to IRQS_INPROGRESS and the irq line is masked forever.
*
* This also serializes the state of shared oneshot handlers
- * versus "desc->threads_onehsot |= action->thread_mask;" in
+ * versus "desc->threads_oneshot |= action->thread_mask;" in
* irq_wake_thread(). See the comment there which explains the
* serialization.
*/
irqreturn_t ret;
local_bh_disable();
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+ local_irq_disable();
ret = action->thread_fn(action->irq, action->dev_id);
if (ret == IRQ_HANDLED)
atomic_inc(&desc->threads_handled);
irq_finalize_oneshot(desc, action);
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+ local_irq_enable();
local_bh_enable();
return ret;
}
/*
* Interrupts explicitly requested as threaded interrupts want to be
- * preemtible - many of them need to sleep and wait for slow busses to
+ * preemptible - many of them need to sleep and wait for slow busses to
* complete.
*/
static irqreturn_t irq_thread_fn(struct irq_desc *desc,
irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
}
- if (irq_settings_can_autoenable(desc)) {
+ if (!(new->flags & IRQF_NO_AUTOEN) &&
+ irq_settings_can_autoenable(desc)) {
irq_startup(desc, IRQ_RESEND, IRQ_START_COND);
} else {
/*
/* Last action releases resources */
if (!desc->action) {
/*
- * Reaquire bus lock as irq_release_resources() might
+ * Reacquire bus lock as irq_release_resources() might
* require it to deallocate resources over the slow bus.
*/
chip_bus_lock(desc);
* which interrupt is which (messes up the interrupt freeing
* logic etc).
*
+ * Also shared interrupts do not go well with disabling auto enable.
+ * The sharing interrupt might request it while it's still disabled
+ * and then wait for interrupts forever.
+ *
* Also IRQF_COND_SUSPEND only makes sense for shared interrupts and
* it cannot be set along with IRQF_NO_SUSPEND.
*/
if (((irqflags & IRQF_SHARED) && !dev_id) ||
+ ((irqflags & IRQF_SHARED) && (irqflags & IRQF_NO_AUTOEN)) ||
(!(irqflags & IRQF_SHARED) && (irqflags & IRQF_COND_SUSPEND)) ||
((irqflags & IRQF_NO_SUSPEND) && (irqflags & IRQF_COND_SUSPEND)))
return -EINVAL;
desc = irq_to_desc(irq);
- if (!desc || irq_settings_can_autoenable(desc) ||
+ if (!desc || (irq_settings_can_autoenable(desc) &&
+ !(irqflags & IRQF_NO_AUTOEN)) ||
!irq_settings_can_request(desc) ||
WARN_ON(irq_settings_is_per_cpu_devid(desc)) ||
!irq_supports_nmi(desc))
* irq_get_irqchip_state - returns the irqchip state of a interrupt.
* @irq: Interrupt line that is forwarded to a VM
* @which: One of IRQCHIP_STATE_* the caller wants to know about
- * @state: a pointer to a boolean where the state is to be storeed
+ * @state: a pointer to a boolean where the state is to be stored
*
* This call snapshots the internal irqchip state of an
* interrupt, returning into @state the bit corresponding to
* irq_matrix_reserve - Reserve interrupts
* @m: Matrix pointer
*
- * This is merily a book keeping call. It increments the number of globally
+ * This is merely a book keeping call. It increments the number of globally
* reserved interrupt bits w/o actually allocating them. This allows to
* setup interrupt descriptors w/o assigning low level resources to it.
* The actual allocation happens when the interrupt gets activated.
*/
void irq_matrix_reserve(struct irq_matrix *m)
{
- if (m->global_reserved <= m->global_available &&
- m->global_reserved + 1 > m->global_available)
+ if (m->global_reserved == m->global_available)
pr_warn("Interrupt reservation exceeds available resources\n");
m->global_reserved++;
* irq_matrix_remove_reserved - Remove interrupt reservation
* @m: Matrix pointer
*
- * This is merily a book keeping call. It decrements the number of globally
+ * This is merely a book keeping call. It decrements the number of globally
* reserved interrupt bits. This is used to undo irq_matrix_reserve() when the
* interrupt was never in use and a real vector allocated, which undid the
* reservation.
if (WARN_ON_ONCE(bit < m->alloc_start || bit >= m->alloc_end))
return;
- clear_bit(bit, cm->alloc_map);
+ if (WARN_ON_ONCE(!test_and_clear_bit(bit, cm->alloc_map)))
+ return;
+
cm->allocated--;
if(managed)
cm->managed_allocated--;
/**
* irq_fixup_move_pending - Cleanup irq move pending from a dying CPU
- * @desc: Interrupt descpriptor to clean up
+ * @desc: Interrupt descriptor to clean up
* @force_clear: If set clear the move pending bit unconditionally.
* If not set, clear it only when the dying CPU is the
* last one in the pending mask.
*
* This file is licensed under GPLv2.
*
- * This file contains common code to support Message Signalled Interrupt for
+ * This file contains common code to support Message Signaled Interrupts for
* PCI compatible and non PCI compatible devices.
*/
#include <linux/types.h>
if (!irq_can_set_affinity_usr(irq) || no_irq_affinity)
return -EIO;
- if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
+ if (!zalloc_cpumask_var(&new_value, GFP_KERNEL))
return -ENOMEM;
if (type)
cpumask_var_t new_value;
int err;
- if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
+ if (!zalloc_cpumask_var(&new_value, GFP_KERNEL))
return -ENOMEM;
err = cpumask_parse_user(buffer, count, new_value);
if (!try_retrigger(desc))
err = irq_sw_resend(desc);
- /* If the retrigger was successfull, mark it with the REPLAY bit */
+ /* If the retrigger was successful, mark it with the REPLAY bit */
if (!err)
desc->istate |= IRQS_REPLAY;
return err;
desc->irqs_unhandled -= ok;
}
+ if (likely(!desc->irqs_unhandled))
+ return;
+
+ /* Now getting into unhandled irq detection */
desc->irq_count++;
if (likely(desc->irq_count < 100000))
return;
* 2. Log interval
*
* We saw the irq timings allow to compute the interval of the
- * occurrences for a specific interrupt. We can reasonibly assume the
+ * occurrences for a specific interrupt. We can reasonably assume the
* longer is the interval, the higher is the error for the next event
* and we can consider storing those interval values into an array
* where each slot in the array correspond to an interval at the power
* Copy the content of the circular buffer into another buffer
* in order to linearize the buffer instead of dealing with
* wrapping indexes and shifted array which will be prone to
- * error and extremelly difficult to debug.
+ * error and extremely difficult to debug.
*/
for (i = 0; i < count; i++) {
int index = (start + i) & IRQ_TIMINGS_MASK;
/*
* The interrupt triggered more than one second apart, that
- * ends the sequence as predictible for our purpose. In this
+ * ends the sequence as predictable for our purpose. In this
* case, assume we have the beginning of a sequence and the
* timestamp is the first value. As it is impossible to
* predict anything at this point, return.
* If more than the array size interrupts happened during the
* last busy/idle cycle, the index wrapped up and we have to
* begin with the next element in the array which is the last one
- * in the sequence, otherwise it is a the index 0.
+ * in the sequence, otherwise it is at the index 0.
*
* - have an indication of the interrupts activity on this CPU
* (eg. irq/sec)
return false;
if (!kernel_text_address(jump_entry_code(entry))) {
+ /*
+ * This skips patching built-in __exit, which
+ * is part of init_section_contains() but is
+ * not part of kernel_text_address().
+ *
+ * Skipping built-in __exit is fine since it
+ * will never be executed.
+ */
WARN_ONCE(!jump_entry_is_init(entry),
"can't patch jump_label at %pS",
(void *)jump_entry_code(entry));
printk(KERN_CONT " (");
__print_lock_name(class);
- printk(KERN_CONT "){%s}-{%hd:%hd}", usage,
+ printk(KERN_CONT "){%s}-{%d:%d}", usage,
class->wait_type_outer ?: class->wait_type_inner,
class->wait_type_inner);
}
/* Debug-check: all keys must be persistent! */
debug_locks_off();
pr_err("INFO: trying to register non-static key.\n");
- pr_err("the code is fine but needs lockdep annotation.\n");
+ pr_err("The code is fine but needs lockdep annotation, or maybe\n");
+ pr_err("you didn't initialize this object before use?\n");
pr_err("turning off the locking correctness validator.\n");
dump_stack();
return false;
/*
* For good efficiency of modular, we use power of 2
*/
-#define MAX_CIRCULAR_QUEUE_SIZE 4096UL
+#define MAX_CIRCULAR_QUEUE_SIZE (1UL << CONFIG_LOCKDEP_CIRCULAR_QUEUE_BITS)
#define CQ_MASK (MAX_CIRCULAR_QUEUE_SIZE-1)
/*
#define MAX_STACK_TRACE_ENTRIES 262144UL
#define STACK_TRACE_HASH_SIZE 8192
#else
-#define MAX_LOCKDEP_ENTRIES 32768UL
+#define MAX_LOCKDEP_ENTRIES (1UL << CONFIG_LOCKDEP_BITS)
-#define MAX_LOCKDEP_CHAINS_BITS 16
+#define MAX_LOCKDEP_CHAINS_BITS CONFIG_LOCKDEP_CHAINS_BITS
/*
* Stack-trace: tightly packed array of stack backtrace
* addresses. Protected by the hash_lock.
*/
-#define MAX_STACK_TRACE_ENTRIES 524288UL
-#define STACK_TRACE_HASH_SIZE 16384
+#define MAX_STACK_TRACE_ENTRIES (1UL << CONFIG_LOCKDEP_STACK_TRACE_BITS)
+#define STACK_TRACE_HASH_SIZE (1 << CONFIG_LOCKDEP_STACK_TRACE_HASH_BITS)
#endif
/*
*/
static __always_inline bool
mutex_optimistic_spin(struct mutex *lock, struct ww_acquire_ctx *ww_ctx,
- const bool use_ww_ctx, struct mutex_waiter *waiter)
+ struct mutex_waiter *waiter)
{
if (!waiter) {
/*
#else
static __always_inline bool
mutex_optimistic_spin(struct mutex *lock, struct ww_acquire_ctx *ww_ctx,
- const bool use_ww_ctx, struct mutex_waiter *waiter)
+ struct mutex_waiter *waiter)
{
return false;
}
struct ww_mutex *ww;
int ret;
+ if (!use_ww_ctx)
+ ww_ctx = NULL;
+
might_sleep();
#ifdef CONFIG_DEBUG_MUTEXES
#endif
ww = container_of(lock, struct ww_mutex, base);
- if (use_ww_ctx && ww_ctx) {
+ if (ww_ctx) {
if (unlikely(ww_ctx == READ_ONCE(ww->ctx)))
return -EALREADY;
mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip);
if (__mutex_trylock(lock) ||
- mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, NULL)) {
+ mutex_optimistic_spin(lock, ww_ctx, NULL)) {
/* got the lock, yay! */
lock_acquired(&lock->dep_map, ip);
- if (use_ww_ctx && ww_ctx)
+ if (ww_ctx)
ww_mutex_set_context_fastpath(ww, ww_ctx);
preempt_enable();
return 0;
* After waiting to acquire the wait_lock, try again.
*/
if (__mutex_trylock(lock)) {
- if (use_ww_ctx && ww_ctx)
+ if (ww_ctx)
__ww_mutex_check_waiters(lock, ww_ctx);
goto skip_wait;
goto err;
}
- if (use_ww_ctx && ww_ctx) {
+ if (ww_ctx) {
ret = __ww_mutex_check_kill(lock, &waiter, ww_ctx);
if (ret)
goto err;
* ww_mutex needs to always recheck its position since its waiter
* list is not FIFO ordered.
*/
- if ((use_ww_ctx && ww_ctx) || !first) {
+ if (ww_ctx || !first) {
first = __mutex_waiter_is_first(lock, &waiter);
if (first)
__mutex_set_flag(lock, MUTEX_FLAG_HANDOFF);
* or we must see its unlock and acquire.
*/
if (__mutex_trylock(lock) ||
- (first && mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, &waiter)))
+ (first && mutex_optimistic_spin(lock, ww_ctx, &waiter)))
break;
spin_lock(&lock->wait_lock);
acquired:
__set_current_state(TASK_RUNNING);
- if (use_ww_ctx && ww_ctx) {
+ if (ww_ctx) {
/*
* Wound-Wait; we stole the lock (!first_waiter), check the
* waiters as anyone might want to wound us.
/* got the lock - cleanup and rejoice! */
lock_acquired(&lock->dep_map, ip);
- if (use_ww_ctx && ww_ctx)
+ if (ww_ctx)
ww_mutex_lock_acquired(ww, ww_ctx);
spin_unlock(&lock->wait_lock);
*/
void queued_write_lock_slowpath(struct qrwlock *lock)
{
+ int cnts;
+
/* Put the writer into the wait queue */
arch_spin_lock(&lock->wait_lock);
/* When no more readers or writers, set the locked flag */
do {
- atomic_cond_read_acquire(&lock->cnts, VAL == _QW_WAITING);
- } while (atomic_cmpxchg_relaxed(&lock->cnts, _QW_WAITING,
- _QW_LOCKED) != _QW_WAITING);
+ cnts = atomic_cond_read_relaxed(&lock->cnts, VAL == _QW_WAITING);
+ } while (!atomic_try_cmpxchg_acquire(&lock->cnts, &cnts, _QW_LOCKED));
unlock:
arch_spin_unlock(&lock->wait_lock);
}
return 0;
}
-core_initcall(em_debug_init);
+fs_initcall(em_debug_init);
#else /* CONFIG_DEBUG_FS */
static void em_debug_create_pd(struct device *dev) {}
static void em_debug_remove_pd(struct device *dev) {}
cpumask_var_t new_value;
int err;
- if (!alloc_cpumask_var(&new_value, GFP_KERNEL))
+ if (!zalloc_cpumask_var(&new_value, GFP_KERNEL))
return -ENOMEM;
err = cpumask_parse_user(buffer, count, new_value);
audit_ptrace(task);
retval = -EPERM;
- if (unlikely(task->flags & (PF_KTHREAD | PF_IO_WORKER)))
+ if (unlikely(task->flags & PF_KTHREAD))
goto out;
if (same_thread_group(task, current))
goto out;
void kernel_restart(char *cmd)
{
kernel_restart_prepare(cmd);
- if (pm_power_off_prepare)
- pm_power_off_prepare();
migrate_to_reboot_cpu();
syscore_shutdown();
if (!cmd)
struct set_affinity_pending *pending;
};
+/*
+ * @refs: number of wait_for_completion()
+ * @stop_pending: is @stop_work in use
+ */
struct set_affinity_pending {
refcount_t refs;
+ unsigned int stop_pending;
struct completion done;
struct cpu_stop_work stop_work;
struct migration_arg arg;
*/
static int migration_cpu_stop(void *data)
{
- struct set_affinity_pending *pending;
struct migration_arg *arg = data;
+ struct set_affinity_pending *pending = arg->pending;
struct task_struct *p = arg->task;
int dest_cpu = arg->dest_cpu;
struct rq *rq = this_rq();
raw_spin_lock(&p->pi_lock);
rq_lock(rq, &rf);
- pending = p->migration_pending;
/*
* If task_rq(p) != rq, it cannot be migrated here, because we're
* holding rq->lock, if p->on_rq == 0 it cannot get enqueued because
goto out;
if (pending) {
- p->migration_pending = NULL;
+ if (p->migration_pending == pending)
+ p->migration_pending = NULL;
complete = true;
}
- /* migrate_enable() -- we must not race against SCA */
if (dest_cpu < 0) {
- /*
- * When this was migrate_enable() but we no longer
- * have a @pending, a concurrent SCA 'fixed' things
- * and we should be valid again. Nothing to do.
- */
- if (!pending) {
- WARN_ON_ONCE(!cpumask_test_cpu(task_cpu(p), &p->cpus_mask));
+ if (cpumask_test_cpu(task_cpu(p), &p->cpus_mask))
goto out;
- }
dest_cpu = cpumask_any_distribute(&p->cpus_mask);
}
else
p->wake_cpu = dest_cpu;
- } else if (dest_cpu < 0 || pending) {
+ /*
+ * XXX __migrate_task() can fail, at which point we might end
+ * up running on a dodgy CPU, AFAICT this can only happen
+ * during CPU hotplug, at which point we'll get pushed out
+ * anyway, so it's probably not a big deal.
+ */
+
+ } else if (pending) {
/*
* This happens when we get migrated between migrate_enable()'s
* preempt_enable() and scheduling the stopper task. At that
* ->pi_lock, so the allowed mask is stable - if it got
* somewhere allowed, we're done.
*/
- if (pending && cpumask_test_cpu(task_cpu(p), p->cpus_ptr)) {
- p->migration_pending = NULL;
+ if (cpumask_test_cpu(task_cpu(p), p->cpus_ptr)) {
+ if (p->migration_pending == pending)
+ p->migration_pending = NULL;
complete = true;
goto out;
}
/*
- * When this was migrate_enable() but we no longer have an
- * @pending, a concurrent SCA 'fixed' things and we should be
- * valid again. Nothing to do.
- */
- if (!pending) {
- WARN_ON_ONCE(!cpumask_test_cpu(task_cpu(p), &p->cpus_mask));
- goto out;
- }
-
- /*
* When migrate_enable() hits a rq mis-match we can't reliably
* determine is_migration_disabled() and so have to chase after
* it.
*/
+ WARN_ON_ONCE(!pending->stop_pending);
task_rq_unlock(rq, p, &rf);
stop_one_cpu_nowait(task_cpu(p), migration_cpu_stop,
&pending->arg, &pending->stop_work);
return 0;
}
out:
+ if (pending)
+ pending->stop_pending = false;
task_rq_unlock(rq, p, &rf);
if (complete)
complete_all(&pending->done);
- /* For pending->{arg,stop_work} */
- pending = arg->pending;
- if (pending && refcount_dec_and_test(&pending->refs))
- wake_up_var(&pending->refs);
-
return 0;
}
int dest_cpu, unsigned int flags)
{
struct set_affinity_pending my_pending = { }, *pending = NULL;
- struct migration_arg arg = {
- .task = p,
- .dest_cpu = dest_cpu,
- };
- bool complete = false;
+ bool stop_pending, complete = false;
/* Can the task run on the task's current CPU? If so, we're done */
if (cpumask_test_cpu(task_cpu(p), &p->cpus_mask)) {
push_task = get_task_struct(p);
}
+ /*
+ * If there are pending waiters, but no pending stop_work,
+ * then complete now.
+ */
pending = p->migration_pending;
- if (pending) {
- refcount_inc(&pending->refs);
+ if (pending && !pending->stop_pending) {
p->migration_pending = NULL;
complete = true;
}
+
task_rq_unlock(rq, p, rf);
if (push_task) {
}
if (complete)
- goto do_complete;
+ complete_all(&pending->done);
return 0;
}
/* Install the request */
refcount_set(&my_pending.refs, 1);
init_completion(&my_pending.done);
+ my_pending.arg = (struct migration_arg) {
+ .task = p,
+ .dest_cpu = -1, /* any */
+ .pending = &my_pending,
+ };
+
p->migration_pending = &my_pending;
} else {
pending = p->migration_pending;
return -EINVAL;
}
- if (flags & SCA_MIGRATE_ENABLE) {
-
- refcount_inc(&pending->refs); /* pending->{arg,stop_work} */
- p->migration_flags &= ~MDF_PUSH;
- task_rq_unlock(rq, p, rf);
-
- pending->arg = (struct migration_arg) {
- .task = p,
- .dest_cpu = -1,
- .pending = pending,
- };
-
- stop_one_cpu_nowait(cpu_of(rq), migration_cpu_stop,
- &pending->arg, &pending->stop_work);
-
- return 0;
- }
-
if (task_running(rq, p) || p->state == TASK_WAKING) {
/*
- * Lessen races (and headaches) by delegating
- * is_migration_disabled(p) checks to the stopper, which will
- * run on the same CPU as said p.
+ * MIGRATE_ENABLE gets here because 'p == current', but for
+ * anything else we cannot do is_migration_disabled(), punt
+ * and have the stopper function handle it all race-free.
*/
+ stop_pending = pending->stop_pending;
+ if (!stop_pending)
+ pending->stop_pending = true;
+
+ if (flags & SCA_MIGRATE_ENABLE)
+ p->migration_flags &= ~MDF_PUSH;
+
task_rq_unlock(rq, p, rf);
- stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
+ if (!stop_pending) {
+ stop_one_cpu_nowait(cpu_of(rq), migration_cpu_stop,
+ &pending->arg, &pending->stop_work);
+ }
+
+ if (flags & SCA_MIGRATE_ENABLE)
+ return 0;
} else {
if (!is_migration_disabled(p)) {
if (task_on_rq_queued(p))
rq = move_queued_task(rq, rf, p, dest_cpu);
- p->migration_pending = NULL;
- complete = true;
+ if (!pending->stop_pending) {
+ p->migration_pending = NULL;
+ complete = true;
+ }
}
task_rq_unlock(rq, p, rf);
-do_complete:
if (complete)
complete_all(&pending->done);
}
wait_for_completion(&pending->done);
if (refcount_dec_and_test(&pending->refs))
- wake_up_var(&pending->refs);
+ wake_up_var(&pending->refs); /* No UaF, just an address */
/*
* Block the original owner of &pending until all subsequent callers
*/
wait_var_event(&my_pending.refs, !refcount_read(&my_pending.refs));
+ /* ARGH */
+ WARN_ON_ONCE(my_pending.stop_pending);
+
return 0;
}
cpu = smp_processor_id();
delta = sched_clock_cpu(cpu) - irqtime->irq_start_time;
irqtime->irq_start_time += delta;
- pc = preempt_count() - offset;
+ pc = irq_count() - offset;
/*
* We do not account for softirq time from ksoftirqd here.
void vtime_account_irq(struct task_struct *tsk, unsigned int offset)
{
- unsigned int pc = preempt_count() - offset;
+ unsigned int pc = irq_count() - offset;
if (pc & HARDIRQ_OFFSET) {
vtime_account_hardirq(tsk);
}
rcu_read_unlock();
- preempt_disable();
- smp_call_function_many(tmpmask, ipi_sync_rq_state, mm, 1);
- preempt_enable();
+ on_each_cpu_mask(tmpmask, ipi_sync_rq_state, mm, true);
free_cpumask_var(tmpmask);
cpus_read_unlock();
return true;
/* Only allow kernel generated signals to this kthread */
- if (unlikely((t->flags & (PF_KTHREAD | PF_IO_WORKER)) &&
+ if (unlikely((t->flags & PF_KTHREAD) &&
(handler == SIG_KTHREAD_KERNEL) && !force))
return true;
/*
* Skip useless siginfo allocation for SIGKILL and kernel threads.
*/
- if ((sig == SIGKILL) || (t->flags & (PF_KTHREAD | PF_IO_WORKER)))
+ if ((sig == SIGKILL) || (t->flags & PF_KTHREAD))
goto out_set;
/*
}
/*
+ * PF_IO_WORKER threads will catch and exit on fatal signals
+ * themselves. They have cleanup that must be performed, so
+ * we cannot call do_exit() on their behalf.
+ */
+ if (current->flags & PF_IO_WORKER)
+ goto out;
+
+ /*
* Death signals, no core dump.
*/
do_group_exit(ksig->info.si_signo);
/* NOTREACHED */
}
spin_unlock_irq(&sighand->siglock);
-
+out:
ksig->sig = signr;
if (!(ksig->ka.sa.sa_flags & SA_EXPOSE_TAGBITS))
#include <linux/kernel_stat.h>
#include <linux/interrupt.h>
#include <linux/init.h>
+#include <linux/local_lock.h>
#include <linux/mm.h>
#include <linux/notifier.h>
#include <linux/percpu.h>
#include <linux/smpboot.h>
#include <linux/tick.h>
#include <linux/irq.h>
+#include <linux/wait_bit.h>
#include <asm/softirq_stack.h>
#endif
/*
- * preempt_count and SOFTIRQ_OFFSET usage:
- * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving
- * softirq processing.
- * - preempt_count is changed by SOFTIRQ_DISABLE_OFFSET (= 2 * SOFTIRQ_OFFSET)
+ * SOFTIRQ_OFFSET usage:
+ *
+ * On !RT kernels 'count' is the preempt counter, on RT kernels this applies
+ * to a per CPU counter and to task::softirqs_disabled_cnt.
+ *
+ * - count is changed by SOFTIRQ_OFFSET on entering or leaving softirq
+ * processing.
+ *
+ * - count is changed by SOFTIRQ_DISABLE_OFFSET (= 2 * SOFTIRQ_OFFSET)
* on local_bh_disable or local_bh_enable.
+ *
* This lets us distinguish between whether we are currently processing
* softirq and whether we just have bh disabled.
*/
+#ifdef CONFIG_PREEMPT_RT
+
+/*
+ * RT accounts for BH disabled sections in task::softirqs_disabled_cnt and
+ * also in per CPU softirq_ctrl::cnt. This is necessary to allow tasks in a
+ * softirq disabled section to be preempted.
+ *
+ * The per task counter is used for softirq_count(), in_softirq() and
+ * in_serving_softirqs() because these counts are only valid when the task
+ * holding softirq_ctrl::lock is running.
+ *
+ * The per CPU counter prevents pointless wakeups of ksoftirqd in case that
+ * the task which is in a softirq disabled section is preempted or blocks.
+ */
+struct softirq_ctrl {
+ local_lock_t lock;
+ int cnt;
+};
+
+static DEFINE_PER_CPU(struct softirq_ctrl, softirq_ctrl) = {
+ .lock = INIT_LOCAL_LOCK(softirq_ctrl.lock),
+};
+
+/**
+ * local_bh_blocked() - Check for idle whether BH processing is blocked
+ *
+ * Returns false if the per CPU softirq::cnt is 0 otherwise true.
+ *
+ * This is invoked from the idle task to guard against false positive
+ * softirq pending warnings, which would happen when the task which holds
+ * softirq_ctrl::lock was the only running task on the CPU and blocks on
+ * some other lock.
+ */
+bool local_bh_blocked(void)
+{
+ return __this_cpu_read(softirq_ctrl.cnt) != 0;
+}
+
+void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
+{
+ unsigned long flags;
+ int newcnt;
+
+ WARN_ON_ONCE(in_hardirq());
+
+ /* First entry of a task into a BH disabled section? */
+ if (!current->softirq_disable_cnt) {
+ if (preemptible()) {
+ local_lock(&softirq_ctrl.lock);
+ /* Required to meet the RCU bottomhalf requirements. */
+ rcu_read_lock();
+ } else {
+ DEBUG_LOCKS_WARN_ON(this_cpu_read(softirq_ctrl.cnt));
+ }
+ }
+
+ /*
+ * Track the per CPU softirq disabled state. On RT this is per CPU
+ * state to allow preemption of bottom half disabled sections.
+ */
+ newcnt = __this_cpu_add_return(softirq_ctrl.cnt, cnt);
+ /*
+ * Reflect the result in the task state to prevent recursion on the
+ * local lock and to make softirq_count() & al work.
+ */
+ current->softirq_disable_cnt = newcnt;
+
+ if (IS_ENABLED(CONFIG_TRACE_IRQFLAGS) && newcnt == cnt) {
+ raw_local_irq_save(flags);
+ lockdep_softirqs_off(ip);
+ raw_local_irq_restore(flags);
+ }
+}
+EXPORT_SYMBOL(__local_bh_disable_ip);
+
+static void __local_bh_enable(unsigned int cnt, bool unlock)
+{
+ unsigned long flags;
+ int newcnt;
+
+ DEBUG_LOCKS_WARN_ON(current->softirq_disable_cnt !=
+ this_cpu_read(softirq_ctrl.cnt));
+
+ if (IS_ENABLED(CONFIG_TRACE_IRQFLAGS) && softirq_count() == cnt) {
+ raw_local_irq_save(flags);
+ lockdep_softirqs_on(_RET_IP_);
+ raw_local_irq_restore(flags);
+ }
+
+ newcnt = __this_cpu_sub_return(softirq_ctrl.cnt, cnt);
+ current->softirq_disable_cnt = newcnt;
+
+ if (!newcnt && unlock) {
+ rcu_read_unlock();
+ local_unlock(&softirq_ctrl.lock);
+ }
+}
+
+void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
+{
+ bool preempt_on = preemptible();
+ unsigned long flags;
+ u32 pending;
+ int curcnt;
+
+ WARN_ON_ONCE(in_irq());
+ lockdep_assert_irqs_enabled();
+
+ local_irq_save(flags);
+ curcnt = __this_cpu_read(softirq_ctrl.cnt);
+
+ /*
+ * If this is not reenabling soft interrupts, no point in trying to
+ * run pending ones.
+ */
+ if (curcnt != cnt)
+ goto out;
+
+ pending = local_softirq_pending();
+ if (!pending || ksoftirqd_running(pending))
+ goto out;
+
+ /*
+ * If this was called from non preemptible context, wake up the
+ * softirq daemon.
+ */
+ if (!preempt_on) {
+ wakeup_softirqd();
+ goto out;
+ }
+
+ /*
+ * Adjust softirq count to SOFTIRQ_OFFSET which makes
+ * in_serving_softirq() become true.
+ */
+ cnt = SOFTIRQ_OFFSET;
+ __local_bh_enable(cnt, false);
+ __do_softirq();
+
+out:
+ __local_bh_enable(cnt, preempt_on);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(__local_bh_enable_ip);
+
+/*
+ * Invoked from ksoftirqd_run() outside of the interrupt disabled section
+ * to acquire the per CPU local lock for reentrancy protection.
+ */
+static inline void ksoftirqd_run_begin(void)
+{
+ __local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
+ local_irq_disable();
+}
+
+/* Counterpart to ksoftirqd_run_begin() */
+static inline void ksoftirqd_run_end(void)
+{
+ __local_bh_enable(SOFTIRQ_OFFSET, true);
+ WARN_ON_ONCE(in_interrupt());
+ local_irq_enable();
+}
+
+static inline void softirq_handle_begin(void) { }
+static inline void softirq_handle_end(void) { }
+
+static inline bool should_wake_ksoftirqd(void)
+{
+ return !this_cpu_read(softirq_ctrl.cnt);
+}
+
+static inline void invoke_softirq(void)
+{
+ if (should_wake_ksoftirqd())
+ wakeup_softirqd();
+}
+
+#else /* CONFIG_PREEMPT_RT */
-#ifdef CONFIG_TRACE_IRQFLAGS
/*
- * This is for softirq.c-internal use, where hardirqs are disabled
+ * This one is for softirq.c-internal use, where hardirqs are disabled
* legitimately:
*/
+#ifdef CONFIG_TRACE_IRQFLAGS
void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
{
unsigned long flags;
}
EXPORT_SYMBOL(__local_bh_enable_ip);
+static inline void softirq_handle_begin(void)
+{
+ __local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
+}
+
+static inline void softirq_handle_end(void)
+{
+ __local_bh_enable(SOFTIRQ_OFFSET);
+ WARN_ON_ONCE(in_interrupt());
+}
+
+static inline void ksoftirqd_run_begin(void)
+{
+ local_irq_disable();
+}
+
+static inline void ksoftirqd_run_end(void)
+{
+ local_irq_enable();
+}
+
+static inline bool should_wake_ksoftirqd(void)
+{
+ return true;
+}
+
static inline void invoke_softirq(void)
{
if (ksoftirqd_running(local_softirq_pending()))
local_irq_restore(flags);
}
+#endif /* !CONFIG_PREEMPT_RT */
+
/*
* We restart softirq processing for at most MAX_SOFTIRQ_RESTART times,
* but break the loop if need_resched() is set or after 2 ms.
pending = local_softirq_pending();
- __local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
+ softirq_handle_begin();
in_hardirq = lockdep_softirq_start();
account_softirq_enter(current);
pending >>= softirq_bit;
}
- if (__this_cpu_read(ksoftirqd) == current)
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT) &&
+ __this_cpu_read(ksoftirqd) == current)
rcu_softirq_qs();
+
local_irq_disable();
pending = local_softirq_pending();
account_softirq_exit(current);
lockdep_softirq_end(in_hardirq);
- __local_bh_enable(SOFTIRQ_OFFSET);
- WARN_ON_ONCE(in_interrupt());
+ softirq_handle_end();
current_restore_flags(old_flags, PF_MEMALLOC);
}
* Otherwise we wake up ksoftirqd to make sure we
* schedule the softirq soon.
*/
- if (!in_interrupt())
+ if (!in_interrupt() && should_wake_ksoftirqd())
wakeup_softirqd();
}
}
EXPORT_SYMBOL(__tasklet_hi_schedule);
+static bool tasklet_clear_sched(struct tasklet_struct *t)
+{
+ if (test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) {
+ wake_up_var(&t->state);
+ return true;
+ }
+
+ WARN_ONCE(1, "tasklet SCHED state not set: %s %pS\n",
+ t->use_callback ? "callback" : "func",
+ t->use_callback ? (void *)t->callback : (void *)t->func);
+
+ return false;
+}
+
static void tasklet_action_common(struct softirq_action *a,
struct tasklet_head *tl_head,
unsigned int softirq_nr)
if (tasklet_trylock(t)) {
if (!atomic_read(&t->count)) {
- if (!test_and_clear_bit(TASKLET_STATE_SCHED,
- &t->state))
- BUG();
- if (t->use_callback)
- t->callback(t);
- else
- t->func(t->data);
+ if (tasklet_clear_sched(t)) {
+ if (t->use_callback)
+ t->callback(t);
+ else
+ t->func(t->data);
+ }
tasklet_unlock(t);
continue;
}
}
EXPORT_SYMBOL(tasklet_init);
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)
+/*
+ * Do not use in new code. Waiting for tasklets from atomic contexts is
+ * error prone and should be avoided.
+ */
+void tasklet_unlock_spin_wait(struct tasklet_struct *t)
+{
+ while (test_bit(TASKLET_STATE_RUN, &(t)->state)) {
+ if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+ /*
+ * Prevent a live lock when current preempted soft
+ * interrupt processing or prevents ksoftirqd from
+ * running. If the tasklet runs on a different CPU
+ * then this has no effect other than doing the BH
+ * disable/enable dance for nothing.
+ */
+ local_bh_disable();
+ local_bh_enable();
+ } else {
+ cpu_relax();
+ }
+ }
+}
+EXPORT_SYMBOL(tasklet_unlock_spin_wait);
+#endif
+
void tasklet_kill(struct tasklet_struct *t)
{
if (in_interrupt())
pr_notice("Attempt to kill tasklet from interrupt\n");
- while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) {
- do {
- yield();
- } while (test_bit(TASKLET_STATE_SCHED, &t->state));
- }
+ while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state))
+ wait_var_event(&t->state, !test_bit(TASKLET_STATE_SCHED, &t->state));
+
tasklet_unlock_wait(t);
- clear_bit(TASKLET_STATE_SCHED, &t->state);
+ tasklet_clear_sched(t);
}
EXPORT_SYMBOL(tasklet_kill);
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)
+void tasklet_unlock(struct tasklet_struct *t)
+{
+ smp_mb__before_atomic();
+ clear_bit(TASKLET_STATE_RUN, &t->state);
+ smp_mb__after_atomic();
+ wake_up_var(&t->state);
+}
+EXPORT_SYMBOL_GPL(tasklet_unlock);
+
+void tasklet_unlock_wait(struct tasklet_struct *t)
+{
+ wait_var_event(&t->state, !test_bit(TASKLET_STATE_RUN, &t->state));
+}
+EXPORT_SYMBOL_GPL(tasklet_unlock_wait);
+#endif
+
void __init softirq_init(void)
{
int cpu;
static void run_ksoftirqd(unsigned int cpu)
{
- local_irq_disable();
+ ksoftirqd_run_begin();
if (local_softirq_pending()) {
/*
* We can safely run softirq on inline stack, as we are not deep
* in the task stack here.
*/
__do_softirq();
- local_irq_enable();
+ ksoftirqd_run_end();
cond_resched();
return;
}
- local_irq_enable();
+ ksoftirqd_run_end();
}
#ifdef CONFIG_HOTPLUG_CPU
-/*
- * tasklet_kill_immediate is called to remove a tasklet which can already be
- * scheduled for execution on @cpu.
- *
- * Unlike tasklet_kill, this function removes the tasklet
- * _immediately_, even if the tasklet is in TASKLET_STATE_SCHED state.
- *
- * When this function is called, @cpu must be in the CPU_DEAD state.
- */
-void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu)
-{
- struct tasklet_struct **i;
-
- BUG_ON(cpu_online(cpu));
- BUG_ON(test_bit(TASKLET_STATE_RUN, &t->state));
-
- if (!test_bit(TASKLET_STATE_SCHED, &t->state))
- return;
-
- /* CPU is dead, so no lock needed. */
- for (i = &per_cpu(tasklet_vec, cpu).head; *i; i = &(*i)->next) {
- if (*i == t) {
- *i = t->next;
- /* If this was the tail element, move the tail ptr */
- if (*i == NULL)
- per_cpu(tasklet_vec, cpu).tail = i;
- return;
- }
- }
- BUG();
-}
-
static int takeover_tasklets(unsigned int cpu)
{
/* CPU is dead, so no lock needed. */
return (void *)((long)site->addr + (long)&site->addr);
}
+static inline unsigned long __static_call_key(const struct static_call_site *site)
+{
+ return (long)site->key + (long)&site->key;
+}
static inline struct static_call_key *static_call_key(const struct static_call_site *site)
{
- return (struct static_call_key *)
- (((long)site->key + (long)&site->key) & ~STATIC_CALL_SITE_FLAGS);
+ return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS);
}
/* These assume the key is word-aligned. */
static inline bool static_call_is_init(struct static_call_site *site)
{
- return ((long)site->key + (long)&site->key) & STATIC_CALL_SITE_INIT;
+ return __static_call_key(site) & STATIC_CALL_SITE_INIT;
}
static inline bool static_call_is_tail(struct static_call_site *site)
{
- return ((long)site->key + (long)&site->key) & STATIC_CALL_SITE_TAIL;
+ return __static_call_key(site) & STATIC_CALL_SITE_TAIL;
}
static inline void static_call_set_init(struct static_call_site *site)
{
- site->key = ((long)static_call_key(site) | STATIC_CALL_SITE_INIT) -
+ site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) -
(long)&site->key;
}
};
for (site_mod = &first; site_mod; site_mod = site_mod->next) {
+ bool init = system_state < SYSTEM_RUNNING;
struct module *mod = site_mod->mod;
if (!site_mod->sites) {
if (mod) {
stop = mod->static_call_sites +
mod->num_static_call_sites;
+ init = mod->state == MODULE_STATE_COMING;
}
#endif
site < stop && static_call_key(site) == key; site++) {
void *site_addr = static_call_addr(site);
- if (static_call_is_init(site)) {
- /*
- * Don't write to call sites which were in
- * initmem and have since been freed.
- */
- if (!mod && system_state >= SYSTEM_RUNNING)
- continue;
- if (mod && !within_module_init((unsigned long)site_addr, mod))
- continue;
- }
+ if (!init && static_call_is_init(site))
+ continue;
if (!kernel_text_address((unsigned long)site_addr)) {
- WARN_ONCE(1, "can't patch static call site at %pS",
+ /*
+ * This skips patching built-in __exit, which
+ * is part of init_section_contains() but is
+ * not part of kernel_text_address().
+ *
+ * Skipping built-in __exit is fine since it
+ * will never be executed.
+ */
+ WARN_ONCE(!static_call_is_init(site),
+ "can't patch static call site at %pS",
site_addr);
continue;
}
arch_static_call_transform(site_addr, NULL, func,
- static_call_is_tail(site));
+ static_call_is_tail(site));
}
}
struct static_call_site *site;
for (site = start; site != stop; site++) {
- unsigned long addr = (unsigned long)static_call_key(site);
+ unsigned long s_key = __static_call_key(site);
+ unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS;
unsigned long key;
/*
return -EINVAL;
}
- site->key = (key - (long)&site->key) |
- (site->key & STATIC_CALL_SITE_FLAGS);
+ key |= s_key & STATIC_CALL_SITE_FLAGS;
+ site->key = key - (long)&site->key;
}
return __static_call_init(mod, start, stop);
#ifndef PAC_RESET_KEYS
# define PAC_RESET_KEYS(a, b) (-EINVAL)
#endif
+#ifndef PAC_SET_ENABLED_KEYS
+# define PAC_SET_ENABLED_KEYS(a, b, c) (-EINVAL)
+#endif
+#ifndef PAC_GET_ENABLED_KEYS
+# define PAC_GET_ENABLED_KEYS(a) (-EINVAL)
+#endif
#ifndef SET_TAGGED_ADDR_CTRL
# define SET_TAGGED_ADDR_CTRL(a) (-EINVAL)
#endif
* up to the caller to provide sane values here, otherwise userspace
* tools which use this vector might be unhappy.
*/
- unsigned long user_auxv[AT_VECTOR_SIZE];
+ unsigned long user_auxv[AT_VECTOR_SIZE] = {};
if (len > sizeof(user_auxv))
return -EINVAL;
return -EINVAL;
error = PAC_RESET_KEYS(me, arg2);
break;
+ case PR_PAC_SET_ENABLED_KEYS:
+ if (arg4 || arg5)
+ return -EINVAL;
+ error = PAC_SET_ENABLED_KEYS(me, arg2, arg3);
+ break;
+ case PR_PAC_GET_ENABLED_KEYS:
+ if (arg2 || arg3 || arg4 || arg5)
+ return -EINVAL;
+ error = PAC_GET_ENABLED_KEYS(me);
+ break;
case PR_SET_TAGGED_ADDR_CTRL:
if (arg3 || arg4 || arg5)
return -EINVAL;
/*
* Alarmtimer interface
*
- * This interface provides a timer which is similarto hrtimers,
+ * This interface provides a timer which is similar to hrtimers,
* but triggers a RTC alarm if the box is suspend.
*
* This interface is influenced by the Android RTC Alarm timer
* interface.
*
- * Copyright (C) 2010 IBM Corperation
+ * Copyright (C) 2010 IBM Corporation
*
* Author: John Stultz <john.stultz@linaro.org>
*/
/**
* alarm_timer_nsleep - alarmtimer nanosleep
* @which_clock: clockid
- * @flags: determins abstime or relative
+ * @flags: determines abstime or relative
* @tsreq: requested sleep time (abs or rel)
*
* Handles clock_nanosleep calls against _ALARM clockids
if (flags == TIMER_ABSTIME)
return -ERESTARTNOHAND;
- restart->fn = alarm_timer_nsleep_restart;
restart->nanosleep.clockid = type;
restart->nanosleep.expires = exp;
+ set_restart_fn(restart, alarm_timer_nsleep_restart);
return ret;
}
* calculated mult and shift factors. This guarantees that no 64bit
* overflow happens when the input value of the conversion is
* multiplied with the calculated mult factor. Larger ranges may
- * reduce the conversion accuracy by chosing smaller mult and shift
+ * reduce the conversion accuracy by choosing smaller mult and shift
* factors.
*/
void
* the suspend time when resuming system.
*
* This function is called late in the suspend process from timekeeping_suspend(),
- * that means processes are freezed, non-boot cpus and interrupts are disabled
+ * that means processes are frozen, non-boot cpus and interrupts are disabled
* now. It is therefore possible to start the suspend timer without taking the
* clocksource mutex.
*/
}
/*
- * Recomputes cpu_base::*next_timer and returns the earliest expires_next but
- * does not set cpu_base::*expires_next, that is done by hrtimer_reprogram.
+ * Recomputes cpu_base::*next_timer and returns the earliest expires_next
+ * but does not set cpu_base::*expires_next, that is done by
+ * hrtimer[_force]_reprogram and hrtimer_interrupt only. When updating
+ * cpu_base::*expires_next right away, reprogramming logic would no longer
+ * work.
*
* When a softirq is pending, we can ignore the HRTIMER_ACTIVE_SOFT bases,
* those timers will get run whenever the softirq gets handled, at the end of
return expires_next;
}
+static ktime_t hrtimer_update_next_event(struct hrtimer_cpu_base *cpu_base)
+{
+ ktime_t expires_next, soft = KTIME_MAX;
+
+ /*
+ * If the soft interrupt has already been activated, ignore the
+ * soft bases. They will be handled in the already raised soft
+ * interrupt.
+ */
+ if (!cpu_base->softirq_activated) {
+ soft = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_SOFT);
+ /*
+ * Update the soft expiry time. clock_settime() might have
+ * affected it.
+ */
+ cpu_base->softirq_expires_next = soft;
+ }
+
+ expires_next = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_HARD);
+ /*
+ * If a softirq timer is expiring first, update cpu_base->next_timer
+ * and program the hardware with the soft expiry time.
+ */
+ if (expires_next > soft) {
+ cpu_base->next_timer = cpu_base->softirq_next_timer;
+ expires_next = soft;
+ }
+
+ return expires_next;
+}
+
static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base)
{
ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset;
{
ktime_t expires_next;
- /*
- * Find the current next expiration time.
- */
- expires_next = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_ALL);
-
- if (cpu_base->next_timer && cpu_base->next_timer->is_soft) {
- /*
- * When the softirq is activated, hrtimer has to be
- * programmed with the first hard hrtimer because soft
- * timer interrupt could occur too late.
- */
- if (cpu_base->softirq_activated)
- expires_next = __hrtimer_get_next_event(cpu_base,
- HRTIMER_ACTIVE_HARD);
- else
- cpu_base->softirq_expires_next = expires_next;
- }
+ expires_next = hrtimer_update_next_event(cpu_base);
if (skip_equal && expires_next == cpu_base->expires_next)
return;
* T1 is removed, so this code is called and would reprogram
* the hardware to 5s from now. Any hrtimer_start after that
* will not reprogram the hardware due to hang_detected being
- * set. So we'd effectivly block all timers until the T2 event
+ * set. So we'd effectively block all timers until the T2 event
* fires.
*/
if (!__hrtimer_hres_active(cpu_base) || cpu_base->hang_detected)
* cpu_base->next_timer. This happens when we remove the first
* timer on a remote cpu. No harm as we never dereference
* cpu_base->next_timer. So the worst thing what can happen is
- * an superflous call to hrtimer_force_reprogram() on the
+ * an superfluous call to hrtimer_force_reprogram() on the
* remote cpu later on if the same timer gets enqueued again.
*/
if (reprogram && timer == cpu_base->next_timer)
* The counterpart to hrtimer_cancel_wait_running().
*
* If there is a waiter for cpu_base->expiry_lock, then it was waiting for
- * the timer callback to finish. Drop expiry_lock and reaquire it. That
+ * the timer callback to finish. Drop expiry_lock and reacquire it. That
* allows the waiter to acquire the lock and make progress.
*/
static void hrtimer_sync_wait_running(struct hrtimer_cpu_base *cpu_base,
int base;
/*
- * On PREEMPT_RT enabled kernels hrtimers which are not explicitely
+ * On PREEMPT_RT enabled kernels hrtimers which are not explicitly
* marked for hard interrupt expiry mode are moved into soft
* interrupt context for latency reasons and because the callbacks
* can invoke functions which might sleep on RT, e.g. spin_lock().
* hrtimer_init - initialize a timer to the given clock
* @timer: the timer to be initialized
* @clock_id: the clock to be used
- * @mode: The modes which are relevant for intitialization:
+ * @mode: The modes which are relevant for initialization:
* HRTIMER_MODE_ABS, HRTIMER_MODE_REL, HRTIMER_MODE_ABS_SOFT,
* HRTIMER_MODE_REL_SOFT
*
* insufficient for that.
*
* The sequence numbers are required because otherwise we could still observe
- * a false negative if the read side got smeared over multiple consequtive
+ * a false negative if the read side got smeared over multiple consecutive
* __run_hrtimer() invocations.
*/
* minimizing wakeups, not running timers at the
* earliest interrupt after their soft expiration.
* This allows us to avoid using a Priority Search
- * Tree, which can answer a stabbing querry for
+ * Tree, which can answer a stabbing query for
* overlapping intervals and instead use the simple
* BST we already have.
* We don't add extra wakeups by delaying timers that
__hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD);
- /* Reevaluate the clock bases for the next expiry */
- expires_next = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_ALL);
+ /* Reevaluate the clock bases for the [soft] next expiry */
+ expires_next = hrtimer_update_next_event(cpu_base);
/*
* Store the new expiry value so the migration code can verify
* against it.
clockid_t clock_id, enum hrtimer_mode mode)
{
/*
- * On PREEMPT_RT enabled kernels hrtimers which are not explicitely
+ * On PREEMPT_RT enabled kernels hrtimers which are not explicitly
* marked for hard interrupt expiry mode are moved into soft
* interrupt context either for latency reasons or because the
* hrtimer callback takes regular spinlocks or invokes other
* the same CPU. That causes a latency spike due to the wakeup of
* a gazillion threads.
*
- * OTOH, priviledged real-time user space applications rely on the
+ * OTOH, privileged real-time user space applications rely on the
* low latency of hard interrupt wakeups. If the current task is in
* a real-time scheduling class, mark the mode for hard interrupt
* expiry.
}
restart = ¤t->restart_block;
- restart->fn = hrtimer_nanosleep_restart;
restart->nanosleep.clockid = t.timer.base->clockid;
restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer);
+ set_restart_fn(restart, hrtimer_nanosleep_restart);
out:
destroy_hrtimer_on_stack(&t.timer);
return ret;
* the timer interrupt frequency HZ and it suffers
* inaccuracies caused by missed or lost timer
* interrupts and the inability for the timer
- * interrupt hardware to accuratly tick at the
+ * interrupt hardware to accurately tick at the
* requested HZ value. It is also not recommended
* for "tick-less" systems.
*/
struct timespec64 *to_set,
const struct timespec64 *now)
{
- /* Allowed error in tv_nsec, arbitarily set to 5 jiffies in ns. */
+ /* Allowed error in tv_nsec, arbitrarily set to 5 jiffies in ns. */
const unsigned long TIME_SET_NSEC_FUZZ = TICK_NSEC * 5;
struct timespec64 delay = {.tv_sec = -1,
.tv_nsec = set_offset_nsec};
* @tsk: Task for which cputime needs to be started
* @samples: Storage for time samples
*
- * The thread group cputime accouting is avoided when there are no posix
+ * The thread group cputime accounting is avoided when there are no posix
* CPU timers armed. Before starting a timer it's required to check whether
* the time accounting is active. If not, a full update of the atomic
* accounting store needs to be done and the accounting enabled.
/*
* If posix timer expiry is handled in task work context then
* timer::it_lock can be taken without disabling interrupts as all
- * other locking happens in task context. This requires a seperate
+ * other locking happens in task context. This requires a separate
* lock class key otherwise regular posix timer expiry would record
* the lock class being taken in interrupt context and generate a
* false positive warning.
check_process_timers(tsk, &firing);
/*
- * The above timer checks have updated the exipry cache and
+ * The above timer checks have updated the expiry cache and
* because nothing can have queued or modified timers after
* sighand lock was taken above it is guaranteed to be
* consistent. So the next timer interrupt fastpath check
if (flags & TIMER_ABSTIME)
return -ERESTARTNOHAND;
- restart_block->fn = posix_cpu_nsleep_restart;
restart_block->nanosleep.clockid = which_clock;
+ set_restart_fn(restart_block, posix_cpu_nsleep_restart);
}
return error;
}
err = do_clock_adjtime(which_clock, &ktx);
- if (err >= 0)
- err = put_old_timex32(utp, &ktx);
+ if (err >= 0 && put_old_timex32(utp, &ktx))
+ return -EFAULT;
return err;
}
#define DEBUGFS_FILENAME "udelay_test"
static DEFINE_MUTEX(udelay_test_lock);
-static struct dentry *udelay_test_debugfs_file;
static int udelay_test_usecs;
static int udelay_test_iterations = DEFAULT_ITERATIONS;
static int __init udelay_test_init(void)
{
mutex_lock(&udelay_test_lock);
- udelay_test_debugfs_file = debugfs_create_file(DEBUGFS_FILENAME,
- S_IRUSR, NULL, NULL, &udelay_test_debugfs_ops);
+ debugfs_create_file(DEBUGFS_FILENAME, S_IRUSR, NULL, NULL,
+ &udelay_test_debugfs_ops);
mutex_unlock(&udelay_test_lock);
return 0;
static void __exit udelay_test_exit(void)
{
mutex_lock(&udelay_test_lock);
- debugfs_remove(udelay_test_debugfs_file);
+ debugfs_remove(debugfs_lookup(DEBUGFS_FILENAME, NULL));
mutex_unlock(&udelay_test_lock);
}
* reasons.
*
* Each caller tries to arm the hrtimer on its own CPU, but if the
- * hrtimer callbback function is currently running, then
+ * hrtimer callback function is currently running, then
* hrtimer_start() cannot move it and the timer stays on the CPU on
* which it is assigned at the moment.
*
tick_broadcast_device.evtdev = dev;
if (!cpumask_empty(tick_broadcast_mask))
tick_broadcast_start_periodic(dev);
+
+ if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT))
+ return;
+
+ /*
+ * If the system already runs in oneshot mode, switch the newly
+ * registered broadcast device to oneshot mode explicitly.
+ */
+ if (tick_broadcast_oneshot_active()) {
+ tick_broadcast_switch_to_oneshot();
+ return;
+ }
+
/*
* Inform all cpus about this. We might be in a situation
* where we did not switch to oneshot mode because the per cpu
* notification the systems stays stuck in periodic mode
* forever.
*/
- if (dev->features & CLOCK_EVT_FEAT_ONESHOT)
- tick_clock_notify();
+ tick_clock_notify();
}
/*
}
/*
- * Check, if the device is disfunctional and a place holder, which
+ * Check, if the device is dysfunctional and a placeholder, which
* needs to be handled by the broadcast device.
*/
int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
* - the broadcast device exists
* - the broadcast device is not a hrtimer based one
* - the broadcast device is in periodic mode to
- * avoid a hickup during switch to oneshot mode
+ * avoid a hiccup during switch to oneshot mode
*/
if (bc && !(bc->features & CLOCK_EVT_FEAT_HRTIMER) &&
tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
td = &per_cpu(tick_cpu_device, cpu);
curdev = td->evtdev;
- /* cpu local device ? */
- if (!tick_check_percpu(curdev, newdev, cpu))
- goto out_bc;
-
- /* Preference decision */
- if (!tick_check_preferred(curdev, newdev))
+ if (!tick_check_replacement(curdev, newdev))
goto out_bc;
if (!try_module_get(newdev->owner))
}
/**
- * tick_resume_onshot - resume oneshot mode
+ * tick_resume_oneshot - resume oneshot mode
*/
void tick_resume_oneshot(void)
{
* Aside of that check whether the local timer softirq is
* pending. If so its a bad idea to call get_next_timer_interrupt()
* because there is an already expired timer, so it will request
- * immeditate expiry, which rearms the hardware timer with a
+ * immediate expiry, which rearms the hardware timer with a
* minimal delta which brings us back to this place
* immediately. Lather, rinse and repeat...
*/
if (unlikely(local_softirq_pending())) {
static int ratelimit;
- if (ratelimit < 10 &&
+ if (ratelimit < 10 && !local_bh_blocked() &&
(local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) {
pr_warn("NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #%02x!!!\n",
(unsigned int) local_softirq_pending());
* @inidle: Indicator that the CPU is in the tick idle mode
* @tick_stopped: Indicator that the idle tick has been stopped
* @idle_active: Indicator that the CPU is actively in the tick idle mode;
- * it is resetted during irq handling phases.
+ * it is reset during irq handling phases.
* @do_timer_lst: CPU was the last one doing do_timer before going idle
* @got_idle_tick: Tick timer function has run with @inidle set
* @last_tick: Store the last tick expiry time when the tick
/*
* The TICK_NSEC - 1 rounds up the value to the next resolution. Note
* that a remainder subtract here would not do the right thing as the
- * resolution values don't fall on second boundries. I.e. the line:
+ * resolution values don't fall on second boundaries. I.e. the line:
* nsec -= nsec % TICK_NSEC; is NOT a correct resolution rounding.
* Note that due to the small error in the multiplier here, this
* rounding is incorrect for sufficiently large values of tv_nsec, but
return ns;
}
-u64 timecounter_cyc2time(struct timecounter *tc,
+u64 timecounter_cyc2time(const struct timecounter *tc,
u64 cycle_tstamp)
{
u64 delta = (cycle_tstamp - tc->cycle_last) & tc->cc->mask;
* careful cache layout of the timekeeper because the sequence count and
* struct tk_read_base would then need two cache lines instead of one.
*
- * Access to the time keeper clock source is disabled accross the innermost
+ * Access to the time keeper clock source is disabled across the innermost
* steps of suspend/resume. The accessors still work, but the timestamps
* are frozen until time keeping is resumed which happens very early.
*
* For regular suspend/resume there is no observable difference vs. sched
* clock, but it might affect some of the nasty low level debug printks.
*
- * OTOH, access to sched clock is not guaranteed accross suspend/resume on
+ * OTOH, access to sched clock is not guaranteed across suspend/resume on
* all systems either so it depends on the hardware in use.
*
* If that turns out to be a real problem then this could be mitigated by
EXPORT_SYMBOL_GPL(ktime_get_coarse_with_offset);
/**
- * ktime_mono_to_any() - convert mononotic time to any other time
+ * ktime_mono_to_any() - convert monotonic time to any other time
* @tmono: time to convert.
* @offs: which offset to use
*/
static int change_clocksource(void *data)
{
struct timekeeper *tk = &tk_core.timekeeper;
- struct clocksource *new, *old;
+ struct clocksource *new, *old = NULL;
unsigned long flags;
+ bool change = false;
new = (struct clocksource *) data;
- raw_spin_lock_irqsave(&timekeeper_lock, flags);
- write_seqcount_begin(&tk_core.seq);
-
- timekeeping_forward_now(tk);
/*
* If the cs is in module, get a module reference. Succeeds
* for built-in code (owner == NULL) as well.
*/
if (try_module_get(new->owner)) {
- if (!new->enable || new->enable(new) == 0) {
- old = tk->tkr_mono.clock;
- tk_setup_internals(tk, new);
- if (old->disable)
- old->disable(old);
- module_put(old->owner);
- } else {
+ if (!new->enable || new->enable(new) == 0)
+ change = true;
+ else
module_put(new->owner);
- }
}
+
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
+ write_seqcount_begin(&tk_core.seq);
+
+ timekeeping_forward_now(tk);
+
+ if (change) {
+ old = tk->tkr_mono.clock;
+ tk_setup_internals(tk, new);
+ }
+
timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);
write_seqcount_end(&tk_core.seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+ if (old) {
+ if (old->disable)
+ old->disable(old);
+
+ module_put(old->owner);
+ }
+
return 0;
}
* xtime_nsec_1 = offset + xtime_nsec_2
* Which gives us:
* xtime_nsec_2 = xtime_nsec_1 - offset
- * Which simplfies to:
+ * Which simplifies to:
* xtime_nsec -= offset
*/
if ((mult_adj > 0) && (tk->tkr_mono.mult + mult_adj < mult_adj)) {
/*
* Validate if a timespec/timeval used to inject a time
- * offset is valid. Offsets can be postive or negative, so
+ * offset is valid. Offsets can be positive or negative, so
* we don't check tv_sec. The value of the timeval/timespec
* is the sum of its fields,but *NOTE*:
* The field tv_usec/tv_nsec must always be non-negative and
/*
* No need to forward if we are close enough below jiffies.
* Also while executing timers, base->clk is 1 offset ahead
- * of jiffies to avoid endless requeuing to current jffies.
+ * of jiffies to avoid endless requeuing to current jiffies.
*/
if ((long)(jnow - base->clk) < 1)
return;
* The counterpart to del_timer_wait_running().
*
* If there is a waiter for base->expiry_lock, then it was waiting for the
- * timer callback to finish. Drop expiry_lock and reaquire it. That allows
+ * timer callback to finish. Drop expiry_lock and reacquire it. That allows
* the waiter to acquire the lock and make progress.
*/
static void timer_sync_wait_running(struct timer_base *base)
/*
* If the current clocksource is not VDSO capable, then spare the
- * update of the high reolution parts.
+ * update of the high resolution parts.
*/
if (clock_mode != VDSO_CLOCKMODE_NONE)
update_vdso_data(vdata, tk);
pg = start_pg;
while (pg) {
order = get_count_order(pg->size / ENTRIES_PER_PAGE);
- free_pages((unsigned long)pg->records, order);
+ if (order >= 0)
+ free_pages((unsigned long)pg->records, order);
start_pg = pg->next;
kfree(pg);
pg = start_pg;
return NULL;
}
+static struct ftrace_direct_func *ftrace_alloc_direct_func(unsigned long addr)
+{
+ struct ftrace_direct_func *direct;
+
+ direct = kmalloc(sizeof(*direct), GFP_KERNEL);
+ if (!direct)
+ return NULL;
+ direct->addr = addr;
+ direct->count = 0;
+ list_add_rcu(&direct->next, &ftrace_direct_funcs);
+ ftrace_direct_func_count++;
+ return direct;
+}
+
/**
* register_ftrace_direct - Call a custom trampoline directly
* @ip: The address of the nop at the beginning of a function
direct = ftrace_find_direct_func(addr);
if (!direct) {
- direct = kmalloc(sizeof(*direct), GFP_KERNEL);
+ direct = ftrace_alloc_direct_func(addr);
if (!direct) {
kfree(entry);
goto out_unlock;
}
- direct->addr = addr;
- direct->count = 0;
- list_add_rcu(&direct->next, &ftrace_direct_funcs);
- ftrace_direct_func_count++;
}
entry->ip = ip;
int modify_ftrace_direct(unsigned long ip,
unsigned long old_addr, unsigned long new_addr)
{
+ struct ftrace_direct_func *direct, *new_direct = NULL;
struct ftrace_func_entry *entry;
struct dyn_ftrace *rec;
int ret = -ENODEV;
if (entry->direct != old_addr)
goto out_unlock;
+ direct = ftrace_find_direct_func(old_addr);
+ if (WARN_ON(!direct))
+ goto out_unlock;
+ if (direct->count > 1) {
+ ret = -ENOMEM;
+ new_direct = ftrace_alloc_direct_func(new_addr);
+ if (!new_direct)
+ goto out_unlock;
+ direct->count--;
+ new_direct->count++;
+ } else {
+ direct->addr = new_addr;
+ }
+
/*
* If there's no other ftrace callback on the rec->ip location,
* then it can be changed directly by the architecture.
ret = 0;
}
+ if (unlikely(ret && new_direct)) {
+ direct->count++;
+ list_del_rcu(&new_direct->next);
+ synchronize_rcu_tasks();
+ kfree(new_direct);
+ ftrace_direct_func_count--;
+ }
+
out_unlock:
mutex_unlock(&ftrace_lock);
mutex_unlock(&direct_mutex);
clear_mod_from_hashes(pg);
order = get_count_order(pg->size / ENTRIES_PER_PAGE);
- free_pages((unsigned long)pg->records, order);
+ if (order >= 0)
+ free_pages((unsigned long)pg->records, order);
tmp_page = pg->next;
kfree(pg);
ftrace_number_of_pages -= 1 << order;
if (!pg->index) {
*last_pg = pg->next;
order = get_count_order(pg->size / ENTRIES_PER_PAGE);
- free_pages((unsigned long)pg->records, order);
+ if (order >= 0)
+ free_pages((unsigned long)pg->records, order);
ftrace_number_of_pages -= 1 << order;
ftrace_number_of_groups--;
kfree(pg);
size = nr_entries * sizeof(unsigned long);
event = __trace_buffer_lock_reserve(buffer, TRACE_STACK,
- sizeof(*entry) + size, trace_ctx);
+ (sizeof(*entry) - sizeof(entry->caller)) + size,
+ trace_ctx);
if (!event)
goto out;
entry = ring_buffer_event_data(event);
{
char *tmp;
- if (iter->fmt == static_fmt_buf)
+ /*
+ * iter->tr is NULL when used with tp_printk, which makes
+ * this get called where it is not safe to call krealloc().
+ */
+ if (!iter->tr || iter->fmt == static_fmt_buf)
return NULL;
tmp = krealloc(iter->fmt, iter->fmt_size + STATIC_FMT_BUF_SIZE,
if (WARN_ON_ONCE(!fmt))
return fmt;
- if (iter->tr->trace_flags & TRACE_ITER_HASH_PTR)
+ if (!iter->tr || iter->tr->trace_flags & TRACE_ITER_HASH_PTR)
return fmt;
p = fmt;
cpumask_var_t tracing_cpumask_new;
int err;
- if (!alloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL))
+ if (!zalloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL))
return -ENOMEM;
err = cpumask_parse_user(ubuf, count, tracing_cpumask_new);
{
if (tracepoint_printk) {
tracepoint_print_iter =
- kmalloc(sizeof(*tracepoint_print_iter), GFP_KERNEL);
+ kzalloc(sizeof(*tracepoint_print_iter), GFP_KERNEL);
if (MEM_FAIL(!tracepoint_print_iter,
"Failed to allocate trace iterator\n"))
tracepoint_printk = 0;
event = p + 1;
*p = '\0';
}
- if (event[0] == '\0')
- return -EINVAL;
+ if (event[0] == '\0') {
+ ret = -EINVAL;
+ goto out;
+ }
mutex_lock(&event_mutex);
for_each_dyn_event_safe(pos, n) {
if (!ns)
goto fail_dec;
+ ns->parent_could_setfcap = cap_raised(new->cap_effective, CAP_SETFCAP);
ret = ns_alloc_inum(&ns->ns);
if (ret)
goto fail_free;
return 0;
}
+/**
+ * verify_root_map() - check the uid 0 mapping
+ * @file: idmapping file
+ * @map_ns: user namespace of the target process
+ * @new_map: requested idmap
+ *
+ * If a process requests mapping parent uid 0 into the new ns, verify that the
+ * process writing the map had the CAP_SETFCAP capability as the target process
+ * will be able to write fscaps that are valid in ancestor user namespaces.
+ *
+ * Return: true if the mapping is allowed, false if not.
+ */
+static bool verify_root_map(const struct file *file,
+ struct user_namespace *map_ns,
+ struct uid_gid_map *new_map)
+{
+ int idx;
+ const struct user_namespace *file_ns = file->f_cred->user_ns;
+ struct uid_gid_extent *extent0 = NULL;
+
+ for (idx = 0; idx < new_map->nr_extents; idx++) {
+ if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS)
+ extent0 = &new_map->extent[idx];
+ else
+ extent0 = &new_map->forward[idx];
+ if (extent0->lower_first == 0)
+ break;
+
+ extent0 = NULL;
+ }
+
+ if (!extent0)
+ return true;
+
+ if (map_ns == file_ns) {
+ /* The process unshared its ns and is writing to its own
+ * /proc/self/uid_map. User already has full capabilites in
+ * the new namespace. Verify that the parent had CAP_SETFCAP
+ * when it unshared.
+ * */
+ if (!file_ns->parent_could_setfcap)
+ return false;
+ } else {
+ /* Process p1 is writing to uid_map of p2, who is in a child
+ * user namespace to p1's. Verify that the opener of the map
+ * file has CAP_SETFCAP against the parent of the new map
+ * namespace */
+ if (!file_ns_capable(file, map_ns->parent, CAP_SETFCAP))
+ return false;
+ }
+
+ return true;
+}
+
static ssize_t map_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos,
int cap_setid,
struct uid_gid_map *parent_map)
{
struct seq_file *seq = file->private_data;
- struct user_namespace *ns = seq->private;
+ struct user_namespace *map_ns = seq->private;
struct uid_gid_map new_map;
unsigned idx;
struct uid_gid_extent extent;
/*
* Adjusting namespace settings requires capabilities on the target.
*/
- if (cap_valid(cap_setid) && !file_ns_capable(file, ns, CAP_SYS_ADMIN))
+ if (cap_valid(cap_setid) && !file_ns_capable(file, map_ns, CAP_SYS_ADMIN))
goto out;
/* Parse the user data */
ret = -EPERM;
/* Validate the user is allowed to use user id's mapped to. */
- if (!new_idmap_permitted(file, ns, cap_setid, &new_map))
+ if (!new_idmap_permitted(file, map_ns, cap_setid, &new_map))
goto out;
ret = -EPERM;
struct uid_gid_map *new_map)
{
const struct cred *cred = file->f_cred;
+
+ if (cap_setid == CAP_SETUID && !verify_root_map(file, ns, new_map))
+ return false;
+
/* Don't allow mappings that would allow anything that wouldn't
* be allowed without the establishment of unprivileged mappings.
*/
struct umd_info *umd_info = info->data;
/* cleanup if umh_setup() was successful but exec failed */
- if (info->retval) {
- fput(umd_info->pipe_to_umh);
- fput(umd_info->pipe_from_umh);
- put_pid(umd_info->tgid);
- umd_info->tgid = NULL;
- }
+ if (info->retval)
+ umd_cleanup_helper(umd_info);
+}
+
+/**
+ * umd_cleanup_helper - release the resources which were allocated in umd_setup
+ * @info: information about usermode driver
+ */
+void umd_cleanup_helper(struct umd_info *info)
+{
+ fput(info->pipe_to_umh);
+ fput(info->pipe_from_umh);
+ put_pid(info->tgid);
+ info->tgid = NULL;
}
+EXPORT_SYMBOL_GPL(umd_cleanup_helper);
/**
* fork_usermode_driver - fork a usermode driver
* update as well, the only side effect might be a cycle delay for
* the softlockup check.
*/
- for_each_cpu(cpu, &watchdog_allowed_mask)
+ for_each_cpu(cpu, &watchdog_allowed_mask) {
per_cpu(watchdog_touch_ts, cpu) = SOFTLOCKUP_RESET;
- wq_watchdog_touch(-1);
+ wq_watchdog_touch(cpu);
+ }
}
void touch_softlockup_watchdog_sync(void)
*/
lockdep_assert_irqs_disabled();
- debug_work_activate(work);
/* if draining, only works from the same workqueue are allowed */
if (unlikely(wq->flags & __WQ_DRAINING) &&
worklist = &pwq->delayed_works;
}
+ debug_work_activate(work);
insert_work(pwq, work, worklist, work_flags);
out:
continue;
/* get the latest of pool and touched timestamps */
+ if (pool->cpu >= 0)
+ touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu));
+ else
+ touched = READ_ONCE(wq_watchdog_touched);
pool_ts = READ_ONCE(pool->watchdog_ts);
- touched = READ_ONCE(wq_watchdog_touched);
if (time_after(pool_ts, touched))
ts = pool_ts;
else
ts = touched;
- if (pool->cpu >= 0) {
- unsigned long cpu_touched =
- READ_ONCE(per_cpu(wq_watchdog_touched_cpu,
- pool->cpu));
- if (time_after(cpu_touched, ts))
- ts = cpu_touched;
- }
-
/* did we stall? */
if (time_after(jiffies, ts + thresh)) {
lockup_detected = true;
{
if (cpu >= 0)
per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies;
- else
- wq_watchdog_touched = jiffies;
+
+ wq_watchdog_touched = jiffies;
}
static void wq_watchdog_set_thresh(unsigned long thresh)
config PLDMFW
bool
default n
+
+config ASN1_ENCODER
+ tristate
bool
depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT
select STACKTRACE
- select FRAME_POINTER if !MIPS && !PPC && !ARM && !S390 && !MICROBLAZE && !ARC && !X86
+ depends on FRAME_POINTER || MIPS || PPC || S390 || MICROBLAZE || ARM || ARC || X86
select KALLSYMS
select KALLSYMS_ALL
config LOCKDEP_SMALL
bool
+config LOCKDEP_BITS
+ int "Bitsize for MAX_LOCKDEP_ENTRIES"
+ depends on LOCKDEP && !LOCKDEP_SMALL
+ range 10 30
+ default 15
+ help
+ Try increasing this value if you hit "BUG: MAX_LOCKDEP_ENTRIES too low!" message.
+
+config LOCKDEP_CHAINS_BITS
+ int "Bitsize for MAX_LOCKDEP_CHAINS"
+ depends on LOCKDEP && !LOCKDEP_SMALL
+ range 10 30
+ default 16
+ help
+ Try increasing this value if you hit "BUG: MAX_LOCKDEP_CHAINS too low!" message.
+
+config LOCKDEP_STACK_TRACE_BITS
+ int "Bitsize for MAX_STACK_TRACE_ENTRIES"
+ depends on LOCKDEP && !LOCKDEP_SMALL
+ range 10 30
+ default 19
+ help
+ Try increasing this value if you hit "BUG: MAX_STACK_TRACE_ENTRIES too low!" message.
+
+config LOCKDEP_STACK_TRACE_HASH_BITS
+ int "Bitsize for STACK_TRACE_HASH_SIZE"
+ depends on LOCKDEP && !LOCKDEP_SMALL
+ range 10 30
+ default 14
+ help
+ Try increasing this value if you need large MAX_STACK_TRACE_ENTRIES.
+
+config LOCKDEP_CIRCULAR_QUEUE_BITS
+ int "Bitsize for elements in circular_queue struct"
+ depends on LOCKDEP
+ range 10 30
+ default 12
+ help
+ Try increasing this value if you hit "lockdep bfs error:-1" warning due to __cq_enqueue() failure.
+
config DEBUG_LOCKDEP
bool "Lock dependency engine debugging"
depends on DEBUG_KERNEL && LOCKDEP
depends on DEBUG_KERNEL
depends on STACKTRACE_SUPPORT
depends on PROC_FS
- select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM && !ARC && !X86
+ depends on FRAME_POINTER || MIPS || PPC || S390 || MICROBLAZE || ARM || ARC || X86
select KALLSYMS
select KALLSYMS_ALL
select STACKTRACE
depends on FAULT_INJECTION_DEBUG_FS && STACKTRACE_SUPPORT
depends on !X86_64
select STACKTRACE
- select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM && !ARC && !X86
+ depends on FRAME_POINTER || MIPS || PPC || S390 || MICROBLAZE || ARM || ARC || X86
help
Provide stacktrace filter for fault-injection capabilities
endchoice
-config KASAN_STACK_ENABLE
+config KASAN_STACK
bool "Enable stack instrumentation (unsafe)" if CC_IS_CLANG && !COMPILE_TEST
depends on KASAN_GENERIC || KASAN_SW_TAGS
+ default y if CC_IS_GCC
help
The LLVM stack address sanitizer has a know problem that
causes excessive stack usage in a lot of functions, see
CONFIG_COMPILE_TEST. On gcc it is assumed to always be safe
to use and enabled by default.
-config KASAN_STACK
- int
- default 1 if KASAN_STACK_ENABLE || CC_IS_GCC
- default 0
-
config KASAN_SW_TAGS_IDENTIFY
bool "Enable memory corruption identification"
depends on KASAN_SW_TAGS
obj-$(CONFIG_PERCPU_TEST) += percpu_test.o
obj-$(CONFIG_ASN1) += asn1_decoder.o
+obj-$(CONFIG_ASN1_ENCODER) += asn1_encoder.o
obj-$(CONFIG_FONT_SUPPORT) += fonts/
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Simple encoder primitives for ASN.1 BER/DER/CER
+ *
+ * Copyright (C) 2019 James.Bottomley@HansenPartnership.com
+ */
+
+#include <linux/asn1_encoder.h>
+#include <linux/bug.h>
+#include <linux/string.h>
+#include <linux/module.h>
+
+/**
+ * asn1_encode_integer() - encode positive integer to ASN.1
+ * @data: pointer to the pointer to the data
+ * @end_data: end of data pointer, points one beyond last usable byte in @data
+ * @integer: integer to be encoded
+ *
+ * This is a simplified encoder: it only currently does
+ * positive integers, but it should be simple enough to add the
+ * negative case if a use comes along.
+ */
+unsigned char *
+asn1_encode_integer(unsigned char *data, const unsigned char *end_data,
+ s64 integer)
+{
+ int data_len = end_data - data;
+ unsigned char *d = &data[2];
+ bool found = false;
+ int i;
+
+ if (WARN(integer < 0,
+ "BUG: integer encode only supports positive integers"))
+ return ERR_PTR(-EINVAL);
+
+ if (IS_ERR(data))
+ return data;
+
+ /* need at least 3 bytes for tag, length and integer encoding */
+ if (data_len < 3)
+ return ERR_PTR(-EINVAL);
+
+ /* remaining length where at d (the start of the integer encoding) */
+ data_len -= 2;
+
+ data[0] = _tag(UNIV, PRIM, INT);
+ if (integer == 0) {
+ *d++ = 0;
+ goto out;
+ }
+
+ for (i = sizeof(integer); i > 0 ; i--) {
+ int byte = integer >> (8 * (i - 1));
+
+ if (!found && byte == 0)
+ continue;
+
+ /*
+ * for a positive number the first byte must have bit
+ * 7 clear in two's complement (otherwise it's a
+ * negative number) so prepend a leading zero if
+ * that's not the case
+ */
+ if (!found && (byte & 0x80)) {
+ /*
+ * no check needed here, we already know we
+ * have len >= 1
+ */
+ *d++ = 0;
+ data_len--;
+ }
+
+ found = true;
+ if (data_len == 0)
+ return ERR_PTR(-EINVAL);
+
+ *d++ = byte;
+ data_len--;
+ }
+
+ out:
+ data[1] = d - data - 2;
+
+ return d;
+}
+EXPORT_SYMBOL_GPL(asn1_encode_integer);
+
+/* calculate the base 128 digit values setting the top bit of the first octet */
+static int asn1_encode_oid_digit(unsigned char **_data, int *data_len, u32 oid)
+{
+ unsigned char *data = *_data;
+ int start = 7 + 7 + 7 + 7;
+ int ret = 0;
+
+ if (*data_len < 1)
+ return -EINVAL;
+
+ /* quick case */
+ if (oid == 0) {
+ *data++ = 0x80;
+ (*data_len)--;
+ goto out;
+ }
+
+ while (oid >> start == 0)
+ start -= 7;
+
+ while (start > 0 && *data_len > 0) {
+ u8 byte;
+
+ byte = oid >> start;
+ oid = oid - (byte << start);
+ start -= 7;
+ byte |= 0x80;
+ *data++ = byte;
+ (*data_len)--;
+ }
+
+ if (*data_len > 0) {
+ *data++ = oid;
+ (*data_len)--;
+ } else {
+ ret = -EINVAL;
+ }
+
+ out:
+ *_data = data;
+ return ret;
+}
+
+/**
+ * asn1_encode_oid() - encode an oid to ASN.1
+ * @data: position to begin encoding at
+ * @end_data: end of data pointer, points one beyond last usable byte in @data
+ * @oid: array of oids
+ * @oid_len: length of oid array
+ *
+ * this encodes an OID up to ASN.1 when presented as an array of OID values
+ */
+unsigned char *
+asn1_encode_oid(unsigned char *data, const unsigned char *end_data,
+ u32 oid[], int oid_len)
+{
+ int data_len = end_data - data;
+ unsigned char *d = data + 2;
+ int i, ret;
+
+ if (WARN(oid_len < 2, "OID must have at least two elements"))
+ return ERR_PTR(-EINVAL);
+
+ if (WARN(oid_len > 32, "OID is too large"))
+ return ERR_PTR(-EINVAL);
+
+ if (IS_ERR(data))
+ return data;
+
+
+ /* need at least 3 bytes for tag, length and OID encoding */
+ if (data_len < 3)
+ return ERR_PTR(-EINVAL);
+
+ data[0] = _tag(UNIV, PRIM, OID);
+ *d++ = oid[0] * 40 + oid[1];
+
+ data_len -= 3;
+
+ ret = 0;
+
+ for (i = 2; i < oid_len; i++) {
+ ret = asn1_encode_oid_digit(&d, &data_len, oid[i]);
+ if (ret < 0)
+ return ERR_PTR(ret);
+ }
+
+ data[1] = d - data - 2;
+
+ return d;
+}
+EXPORT_SYMBOL_GPL(asn1_encode_oid);
+
+/**
+ * asn1_encode_length() - encode a length to follow an ASN.1 tag
+ * @data: pointer to encode at
+ * @data_len: pointer to remaning length (adjusted by routine)
+ * @len: length to encode
+ *
+ * This routine can encode lengths up to 65535 using the ASN.1 rules.
+ * It will accept a negative length and place a zero length tag
+ * instead (to keep the ASN.1 valid). This convention allows other
+ * encoder primitives to accept negative lengths as singalling the
+ * sequence will be re-encoded when the length is known.
+ */
+static int asn1_encode_length(unsigned char **data, int *data_len, int len)
+{
+ if (*data_len < 1)
+ return -EINVAL;
+
+ if (len < 0) {
+ *((*data)++) = 0;
+ (*data_len)--;
+ return 0;
+ }
+
+ if (len <= 0x7f) {
+ *((*data)++) = len;
+ (*data_len)--;
+ return 0;
+ }
+
+ if (*data_len < 2)
+ return -EINVAL;
+
+ if (len <= 0xff) {
+ *((*data)++) = 0x81;
+ *((*data)++) = len & 0xff;
+ *data_len -= 2;
+ return 0;
+ }
+
+ if (*data_len < 3)
+ return -EINVAL;
+
+ if (len <= 0xffff) {
+ *((*data)++) = 0x82;
+ *((*data)++) = (len >> 8) & 0xff;
+ *((*data)++) = len & 0xff;
+ *data_len -= 3;
+ return 0;
+ }
+
+ if (WARN(len > 0xffffff, "ASN.1 length can't be > 0xffffff"))
+ return -EINVAL;
+
+ if (*data_len < 4)
+ return -EINVAL;
+ *((*data)++) = 0x83;
+ *((*data)++) = (len >> 16) & 0xff;
+ *((*data)++) = (len >> 8) & 0xff;
+ *((*data)++) = len & 0xff;
+ *data_len -= 4;
+
+ return 0;
+}
+
+/**
+ * asn1_encode_tag() - add a tag for optional or explicit value
+ * @data: pointer to place tag at
+ * @end_data: end of data pointer, points one beyond last usable byte in @data
+ * @tag: tag to be placed
+ * @string: the data to be tagged
+ * @len: the length of the data to be tagged
+ *
+ * Note this currently only handles short form tags < 31.
+ *
+ * Standard usage is to pass in a @tag, @string and @length and the
+ * @string will be ASN.1 encoded with @tag and placed into @data. If
+ * the encoding would put data past @end_data then an error is
+ * returned, otherwise a pointer to a position one beyond the encoding
+ * is returned.
+ *
+ * To encode in place pass a NULL @string and -1 for @len and the
+ * maximum allowable beginning and end of the data; all this will do
+ * is add the current maximum length and update the data pointer to
+ * the place where the tag contents should be placed is returned. The
+ * data should be copied in by the calling routine which should then
+ * repeat the prior statement but now with the known length. In order
+ * to avoid having to keep both before and after pointers, the repeat
+ * expects to be called with @data pointing to where the first encode
+ * returned it and still NULL for @string but the real length in @len.
+ */
+unsigned char *
+asn1_encode_tag(unsigned char *data, const unsigned char *end_data,
+ u32 tag, const unsigned char *string, int len)
+{
+ int data_len = end_data - data;
+ int ret;
+
+ if (WARN(tag > 30, "ASN.1 tag can't be > 30"))
+ return ERR_PTR(-EINVAL);
+
+ if (!string && WARN(len > 127,
+ "BUG: recode tag is too big (>127)"))
+ return ERR_PTR(-EINVAL);
+
+ if (IS_ERR(data))
+ return data;
+
+ if (!string && len > 0) {
+ /*
+ * we're recoding, so move back to the start of the
+ * tag and install a dummy length because the real
+ * data_len should be NULL
+ */
+ data -= 2;
+ data_len = 2;
+ }
+
+ if (data_len < 2)
+ return ERR_PTR(-EINVAL);
+
+ *(data++) = _tagn(CONT, CONS, tag);
+ data_len--;
+ ret = asn1_encode_length(&data, &data_len, len);
+ if (ret < 0)
+ return ERR_PTR(ret);
+
+ if (!string)
+ return data;
+
+ if (data_len < len)
+ return ERR_PTR(-EINVAL);
+
+ memcpy(data, string, len);
+ data += len;
+
+ return data;
+}
+EXPORT_SYMBOL_GPL(asn1_encode_tag);
+
+/**
+ * asn1_encode_octet_string() - encode an ASN.1 OCTET STRING
+ * @data: pointer to encode at
+ * @end_data: end of data pointer, points one beyond last usable byte in @data
+ * @string: string to be encoded
+ * @len: length of string
+ *
+ * Note ASN.1 octet strings may contain zeros, so the length is obligatory.
+ */
+unsigned char *
+asn1_encode_octet_string(unsigned char *data,
+ const unsigned char *end_data,
+ const unsigned char *string, u32 len)
+{
+ int data_len = end_data - data;
+ int ret;
+
+ if (IS_ERR(data))
+ return data;
+
+ /* need minimum of 2 bytes for tag and length of zero length string */
+ if (data_len < 2)
+ return ERR_PTR(-EINVAL);
+
+ *(data++) = _tag(UNIV, PRIM, OTS);
+ data_len--;
+
+ ret = asn1_encode_length(&data, &data_len, len);
+ if (ret)
+ return ERR_PTR(ret);
+
+ if (data_len < len)
+ return ERR_PTR(-EINVAL);
+
+ memcpy(data, string, len);
+ data += len;
+
+ return data;
+}
+EXPORT_SYMBOL_GPL(asn1_encode_octet_string);
+
+/**
+ * asn1_encode_sequence() - wrap a byte stream in an ASN.1 SEQUENCE
+ * @data: pointer to encode at
+ * @end_data: end of data pointer, points one beyond last usable byte in @data
+ * @seq: data to be encoded as a sequence
+ * @len: length of the data to be encoded as a sequence
+ *
+ * Fill in a sequence. To encode in place, pass NULL for @seq and -1
+ * for @len; then call again once the length is known (still with NULL
+ * for @seq). In order to avoid having to keep both before and after
+ * pointers, the repeat expects to be called with @data pointing to
+ * where the first encode placed it.
+ */
+unsigned char *
+asn1_encode_sequence(unsigned char *data, const unsigned char *end_data,
+ const unsigned char *seq, int len)
+{
+ int data_len = end_data - data;
+ int ret;
+
+ if (!seq && WARN(len > 127,
+ "BUG: recode sequence is too big (>127)"))
+ return ERR_PTR(-EINVAL);
+
+ if (IS_ERR(data))
+ return data;
+
+ if (!seq && len >= 0) {
+ /*
+ * we're recoding, so move back to the start of the
+ * sequence and install a dummy length because the
+ * real length should be NULL
+ */
+ data -= 2;
+ data_len = 2;
+ }
+
+ if (data_len < 2)
+ return ERR_PTR(-EINVAL);
+
+ *(data++) = _tag(UNIV, CONS, SEQ);
+ data_len--;
+
+ ret = asn1_encode_length(&data, &data_len, len);
+ if (ret)
+ return ERR_PTR(ret);
+
+ if (!seq)
+ return data;
+
+ if (data_len < len)
+ return ERR_PTR(-EINVAL);
+
+ memcpy(data, seq, len);
+ data += len;
+
+ return data;
+}
+EXPORT_SYMBOL_GPL(asn1_encode_sequence);
+
+/**
+ * asn1_encode_boolean() - encode a boolean value to ASN.1
+ * @data: pointer to encode at
+ * @end_data: end of data pointer, points one beyond last usable byte in @data
+ * @val: the boolean true/false value
+ */
+unsigned char *
+asn1_encode_boolean(unsigned char *data, const unsigned char *end_data,
+ bool val)
+{
+ int data_len = end_data - data;
+
+ if (IS_ERR(data))
+ return data;
+
+ /* booleans are 3 bytes: tag, length == 1 and value == 0 or 1 */
+ if (data_len < 3)
+ return ERR_PTR(-EINVAL);
+
+ *(data++) = _tag(UNIV, PRIM, BOOL);
+ data_len--;
+
+ asn1_encode_length(&data, &data_len, 1);
+
+ if (val)
+ *(data++) = 1;
+ else
+ *(data++) = 0;
+
+ return data;
+}
+EXPORT_SYMBOL_GPL(asn1_encode_boolean);
+
+MODULE_LICENSE("GPL");
}
/**
- * chacha_block - generate one keystream block and increment block counter
+ * chacha_block_generic - generate one keystream block and increment block counter
* @state: input state matrix (16 32-bit words)
* @stream: output keystream block (64 bytes)
* @nrounds: number of rounds (20 or 12; 20 is recommended)
/**
* hchacha_block_generic - abbreviated ChaCha core, for XChaCha
* @state: input state matrix (16 32-bit words)
- * @out: output (8 32-bit words)
+ * @stream: output (8 32-bit words)
* @nrounds: number of rounds (20 or 12; 20 is recommended)
*
* HChaCha is the ChaCha equivalent of HSalsa and is an intermediate step
#include <asm/unaligned.h>
#include <crypto/internal/poly1305.h>
-void poly1305_core_setkey(struct poly1305_core_key *key, const u8 raw_key[16])
+void poly1305_core_setkey(struct poly1305_core_key *key,
+ const u8 raw_key[POLY1305_BLOCK_SIZE])
{
/* r &= 0xffffffc0ffffffc0ffffffc0fffffff */
key->key.r[0] = (get_unaligned_le32(&raw_key[0])) & 0x3ffffff;
typedef __uint128_t u128;
-void poly1305_core_setkey(struct poly1305_core_key *key, const u8 raw_key[16])
+void poly1305_core_setkey(struct poly1305_core_key *key,
+ const u8 raw_key[POLY1305_BLOCK_SIZE])
{
u64 t0, t1;
#include <linux/module.h>
#include <asm/unaligned.h>
-void poly1305_init_generic(struct poly1305_desc_ctx *desc, const u8 *key)
+void poly1305_init_generic(struct poly1305_desc_ctx *desc,
+ const u8 key[POLY1305_KEY_SIZE])
{
poly1305_core_setkey(&desc->core_r, key);
desc->s[0] = get_unaligned_le32(key + 16);
};
/**
- * cpio_data find_cpio_data - Search for files in an uncompressed cpio
+ * find_cpio_data - Search for files in an uncompressed cpio
* @path: The directory to search for, including a slash at the end
* @data: Pointer to the cpio archive or a header inside
* @len: Remaining length of the cpio based on data pointer
* matching file itself. It can be used to iterate through the cpio
* to find all files inside of a directory path.
*
- * @return: struct cpio_data containing the address, length and
+ * Return: &struct cpio_data containing the address, length and
* filename (with the directory path cut off) of the found file.
* If you search for a filename and not for files in a directory,
* pass the absolute path of the filename in the cpio and make sure
}
#endif
-#ifndef ARCH_HAS_SORT_EXTABLE
#ifndef ARCH_HAS_RELATIVE_EXTABLE
#define swap_ex NULL
#else
m->num_exentries--;
}
#endif /* CONFIG_MODULES */
-#endif /* !ARCH_HAS_SORT_EXTABLE */
-
-#ifndef ARCH_HAS_SEARCH_EXTABLE
static int cmp_ex_search(const void *key, const void *elt)
{
return bsearch(&value, base, num,
sizeof(struct exception_table_entry), cmp_ex_search);
}
-#endif
/**
* lc_create - prepares to track objects in an active set
* @name: descriptive name only used in lc_seq_printf_stats and lc_seq_dump_details
+ * @cache: cache root pointer
* @max_pending_changes: maximum changes to accumulate until a transaction is required
* @e_count: number of elements allowed to be active simultaneously
* @e_size: size of the tracked objects
}
/**
- * lc_dump - Dump a complete LRU cache to seq in textual form.
+ * lc_seq_dump_details - Dump a complete LRU cache to seq in textual form.
* @lc: the lru cache to operate on
* @seq: the &struct seq_file pointer to seq_printf into
* @utext: user supplied additional "heading" or other info
return res + div64_u64(a * b, c);
}
+EXPORT_SYMBOL(mul_u64_u64_div_u64);
#endif
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/bug.h>
+#include <linux/asn1.h>
#include "oid_registry_data.c"
MODULE_DESCRIPTION("OID Registry");
}
EXPORT_SYMBOL_GPL(look_up_OID);
+/**
+ * parse_OID - Parse an OID from a bytestream
+ * @data: Binary representation of the header + OID
+ * @datasize: Size of the binary representation
+ * @oid: Pointer to oid to return result
+ *
+ * Parse an OID from a bytestream that holds the OID in the format
+ * ASN1_OID | length | oid. The length indicator must equal to datasize - 2.
+ * -EBADMSG is returned if the bytestream is too short.
+ */
+int parse_OID(const void *data, size_t datasize, enum OID *oid)
+{
+ const unsigned char *v = data;
+
+ /* we need 2 bytes of header and at least 1 byte for oid */
+ if (datasize < 3 || v[0] != ASN1_OID || v[1] != datasize - 2)
+ return -EBADMSG;
+
+ *oid = look_up_OID(data + 2, datasize - 2);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(parse_OID);
+
/*
* sprint_OID - Print an Object Identifier into a buffer
* @data: The encoded OID to print
* parman_prio_init - initializes a parman priority chunk
* @parman: parman instance
* @prio: parman prio structure to be initialized
- * @prority: desired priority of the chunk
+ * @priority: desired priority of the chunk
*
* Note: all locking must be provided by the caller.
*
EXPORT_SYMBOL(parman_item_add);
/**
- * parman_item_del - deletes parman item
+ * parman_item_remove - deletes parman item
* @parman: parman instance
* @prio: parman prio instance to delete the item from
* @item: parman item instance
/**
* radix_tree_find_next_bit - find the next set bit in a memory region
*
- * @addr: The address to base the search on
- * @size: The bitmap size in bits
- * @offset: The bitnumber to start searching at
+ * @node: where to begin the search
+ * @tag: the tag index
+ * @offset: the bitnumber to start searching at
*
* Unrollable variant of find_next_bit() for constant size arrays.
* Tail bits starting from size to roundup(size, BITS_PER_LONG) must be zero.
/**
* radix_tree_shrink - shrink radix tree to minimum height
- * @root radix tree root
+ * @root: radix tree root
*/
static inline bool radix_tree_shrink(struct radix_tree_root *root)
{
}
/**
- * __radix_tree_insert - insert into a radix tree
+ * radix_tree_insert - insert into a radix tree
* @root: radix tree root
* @index: index key
* @item: item to insert
/**
* radix_tree_iter_replace - replace item in a slot
* @root: radix tree root
+ * @iter: iterator state
* @slot: pointer to slot
* @item: new item to store in the slot.
*
* resource named "kasan_data". Do not use this name for KUnit resources
* outside of KASAN tests.
*
- * For hardware tag-based KASAN, when a tag fault happens, tag checking is
- * normally auto-disabled. When this happens, this test handler reenables
- * tag checking. As tag checking can be only disabled or enabled per CPU, this
- * handler disables migration (preemption).
+ * For hardware tag-based KASAN in sync mode, when a tag fault happens, tag
+ * checking is auto-disabled. When this happens, this test handler reenables
+ * tag checking. As tag checking can be only disabled or enabled per CPU,
+ * this handler disables migration (preemption).
*
* Since the compiler doesn't see that the expression can change the fail_data
* fields, it can reorder or optimize away the accesses to those fields.
* expression to prevent that.
*/
#define KUNIT_EXPECT_KASAN_FAIL(test, expression) do { \
- if (IS_ENABLED(CONFIG_KASAN_HW_TAGS)) \
+ if (IS_ENABLED(CONFIG_KASAN_HW_TAGS) && \
+ !kasan_async_mode_enabled()) \
migrate_disable(); \
WRITE_ONCE(fail_data.report_expected, true); \
WRITE_ONCE(fail_data.report_found, false); \
barrier(); \
expression; \
barrier(); \
+ if (kasan_async_mode_enabled()) \
+ kasan_force_async_fault(); \
+ barrier(); \
KUNIT_EXPECT_EQ(test, \
READ_ONCE(fail_data.report_expected), \
READ_ONCE(fail_data.report_found)); \
- if (IS_ENABLED(CONFIG_KASAN_HW_TAGS)) { \
+ if (IS_ENABLED(CONFIG_KASAN_HW_TAGS) && \
+ !kasan_async_mode_enabled()) { \
if (READ_ONCE(fail_data.report_found)) \
- kasan_enable_tagging(); \
+ kasan_enable_tagging_sync(); \
migrate_enable(); \
} \
} while (0)
char *kmem;
char __user *usermem;
size_t size = 10;
- int unused;
+ int __maybe_unused unused;
kmem = kmalloc(size, GFP_KERNEL);
if (!kmem)
#ifdef CONFIG_XARRAY_MULTI
static void check_split_1(struct xarray *xa, unsigned long index,
- unsigned int order)
+ unsigned int order, unsigned int new_order)
{
- XA_STATE(xas, xa, index);
- void *entry;
- unsigned int i = 0;
+ XA_STATE_ORDER(xas, xa, index, new_order);
+ unsigned int i;
xa_store_order(xa, index, order, xa, GFP_KERNEL);
xas_split_alloc(&xas, xa, order, GFP_KERNEL);
xas_lock(&xas);
xas_split(&xas, xa, order);
+ for (i = 0; i < (1 << order); i += (1 << new_order))
+ __xa_store(xa, index + i, xa_mk_index(index + i), 0);
xas_unlock(&xas);
- xa_for_each(xa, index, entry) {
- XA_BUG_ON(xa, entry != xa);
- i++;
+ for (i = 0; i < (1 << order); i++) {
+ unsigned int val = index + (i & ~((1 << new_order) - 1));
+ XA_BUG_ON(xa, xa_load(xa, index + i) != xa_mk_index(val));
}
- XA_BUG_ON(xa, i != 1 << order);
xa_set_mark(xa, index, XA_MARK_0);
XA_BUG_ON(xa, !xa_get_mark(xa, index, XA_MARK_0));
static noinline void check_split(struct xarray *xa)
{
- unsigned int order;
+ unsigned int order, new_order;
XA_BUG_ON(xa, !xa_empty(xa));
for (order = 1; order < 2 * XA_CHUNK_SHIFT; order++) {
- check_split_1(xa, 0, order);
- check_split_1(xa, 1UL << order, order);
- check_split_1(xa, 3UL << order, order);
+ for (new_order = 0; new_order < order; new_order++) {
+ check_split_1(xa, 0, order, new_order);
+ check_split_1(xa, 1UL << order, order, new_order);
+ check_split_1(xa, 3UL << order, order, new_order);
+ }
}
}
#else
* xas_split_alloc() - Allocate memory for splitting an entry.
* @xas: XArray operation state.
* @entry: New entry which will be stored in the array.
- * @order: New entry order.
+ * @order: Current entry order.
* @gfp: Memory allocation flags.
*
* This function should be called before calling xas_split().
do {
unsigned int i;
- void *sibling;
+ void *sibling = NULL;
struct xa_node *node;
node = kmem_cache_alloc(radix_tree_node_cachep, gfp);
for (i = 0; i < XA_CHUNK_SIZE; i++) {
if ((i & mask) == 0) {
RCU_INIT_POINTER(node->slots[i], entry);
- sibling = xa_mk_sibling(0);
+ sibling = xa_mk_sibling(i);
} else {
RCU_INIT_POINTER(node->slots[i], sibling);
}
* xas_split() - Split a multi-index entry into smaller entries.
* @xas: XArray operation state.
* @entry: New entry to store in the array.
- * @order: New entry order.
+ * @order: Current entry order.
*
- * The value in the entry is copied to all the replacement entries.
+ * The size of the new entries is set in @xas. The value in @entry is
+ * copied to all the replacement entries.
*
* Context: Any context. The caller should hold the xa_lock.
*/
put:
put_page(page);
next:
- if (!xa_is_value(page) && PageTransHuge(page))
- xas_set(&xas, page->index + thp_nr_pages(page));
+ if (!xa_is_value(page) && PageTransHuge(page)) {
+ unsigned int nr_pages = thp_nr_pages(page);
+
+ /* Final THP may cross MAX_LFS_FILESIZE on 32-bit */
+ xas_set(&xas, page->index + nr_pages);
+ if (xas.xa_index < nr_pages)
+ break;
+ }
}
rcu_read_unlock();
loff_t end, int whence)
{
XA_STATE(xas, &mapping->i_pages, start >> PAGE_SHIFT);
- pgoff_t max = (end - 1) / PAGE_SIZE;
+ pgoff_t max = (end - 1) >> PAGE_SHIFT;
bool seek_data = (whence == SEEK_DATA);
struct page *page;
rcu_read_lock();
while ((page = find_get_entry(&xas, max, XA_PRESENT))) {
- loff_t pos = xas.xa_index * PAGE_SIZE;
+ loff_t pos = (u64)xas.xa_index << PAGE_SHIFT;
+ unsigned int seek_size;
if (start < pos) {
if (!seek_data)
start = pos;
}
- pos += seek_page_size(&xas, page);
+ seek_size = seek_page_size(&xas, page);
+ pos = round_up(pos + 1, seek_size);
start = page_seek_hole_data(&xas, mapping, page, start, pos,
seek_data);
if (start < pos)
goto unlock;
+ if (start >= end)
+ break;
+ if (seek_size > PAGE_SIZE)
+ xas_set(&xas, pos >> PAGE_SHIFT);
if (!xa_is_value(page))
put_page(page);
}
- rcu_read_unlock();
-
if (seek_data)
- return -ENXIO;
- goto out;
-
+ start = -ENXIO;
unlock:
rcu_read_unlock();
- if (!xa_is_value(page))
+ if (page && !xa_is_value(page))
put_page(page);
-out:
if (start > end)
return end;
return start;
FOLL_FORCE | FOLL_DUMP | FOLL_GET);
if (locked)
mmap_read_unlock(mm);
+
+ if (ret == 1 && is_page_poisoned(page))
+ return NULL;
+
return (ret == 1) ? page : NULL;
}
#endif /* CONFIG_ELF_CORE */
BUG_ON(end1 > page_size(page) || end2 > page_size(page));
+ if (start1 >= end1)
+ start1 = end1 = 0;
+ if (start2 >= end2)
+ start2 = end2 = 0;
+
for (i = 0; i < compound_nr(page); i++) {
void *kaddr = NULL;
- if (start1 < PAGE_SIZE || start2 < PAGE_SIZE)
- kaddr = kmap_atomic(page + i);
-
if (start1 >= PAGE_SIZE) {
start1 -= PAGE_SIZE;
end1 -= PAGE_SIZE;
} else {
unsigned this_end = min_t(unsigned, end1, PAGE_SIZE);
- if (end1 > start1)
+ if (end1 > start1) {
+ kaddr = kmap_atomic(page + i);
memset(kaddr + start1, 0, this_end - start1);
+ }
end1 -= this_end;
start1 = 0;
}
} else {
unsigned this_end = min_t(unsigned, end2, PAGE_SIZE);
- if (end2 > start2)
+ if (end2 > start2) {
+ if (!kaddr)
+ kaddr = kmap_atomic(page + i);
memset(kaddr + start2, 0, this_end - start2);
+ }
end2 -= this_end;
start2 = 0;
}
int idx;
/* With debug all even slots are unmapped and act as guard */
- if (IS_ENABLED(CONFIG_DEBUG_HIGHMEM) && !(i & 0x01)) {
+ if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) {
WARN_ON_ONCE(!pte_none(pteval));
continue;
}
int idx;
/* With debug all even slots are unmapped and act as guard */
- if (IS_ENABLED(CONFIG_DEBUG_HIGHMEM) && !(i & 0x01)) {
+ if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) {
WARN_ON_ONCE(!pte_none(pteval));
continue;
}
* best effort that the pinned pages won't be replaced by another
* random page during the coming copy-on-write.
*/
- if (unlikely(is_cow_mapping(vma->vm_flags) &&
- atomic_read(&src_mm->has_pinned) &&
- page_maybe_dma_pinned(src_page))) {
+ if (unlikely(page_needs_cow_for_dma(vma, src_page))) {
pte_free(dst_mm, pgtable);
spin_unlock(src_ptl);
spin_unlock(dst_ptl);
}
/* Please refer to comments in copy_huge_pmd() */
- if (unlikely(is_cow_mapping(vma->vm_flags) &&
- atomic_read(&src_mm->has_pinned) &&
- page_maybe_dma_pinned(pud_page(pud)))) {
+ if (unlikely(page_needs_cow_for_dma(vma, pud_page(pud)))) {
spin_unlock(src_ptl);
spin_unlock(dst_ptl);
__split_huge_pud(vma, src_pud, addr);
int i;
/* complete memcg works before add pages to LRU */
- mem_cgroup_split_huge_fixup(head);
+ split_page_memcg(head, nr);
if (PageAnon(head) && PageSwapCache(head)) {
swp_entry_t entry = { .val = page_private(head) };
nrg->reservation_counter =
&h_cg->rsvd_hugepage[hstate_index(h)];
nrg->css = &h_cg->css;
+ /*
+ * The caller will hold exactly one h_cg->css reference for the
+ * whole contiguous reservation region. But this area might be
+ * scattered when there are already some file_regions reside in
+ * it. As a result, many file_regions may share only one css
+ * reference. In order to ensure that one file_region must hold
+ * exactly one h_cg->css reference, we should do css_get for
+ * each file_region and leave the reference held by caller
+ * untouched.
+ */
+ css_get(&h_cg->css);
if (!resv->pages_per_hpage)
resv->pages_per_hpage = pages_per_huge_page(h);
/* pages_per_hpage should be the same for all entries in
#endif
}
+static void put_uncharge_info(struct file_region *rg)
+{
+#ifdef CONFIG_CGROUP_HUGETLB
+ if (rg->css)
+ css_put(rg->css);
+#endif
+}
+
static bool has_same_uncharge_info(struct file_region *rg,
struct file_region *org)
{
prg->to = rg->to;
list_del(&rg->link);
+ put_uncharge_info(rg);
kfree(rg);
rg = prg;
nrg->from = rg->from;
list_del(&rg->link);
+ put_uncharge_info(rg);
kfree(rg);
}
}
+static inline long
+hugetlb_resv_map_add(struct resv_map *map, struct file_region *rg, long from,
+ long to, struct hstate *h, struct hugetlb_cgroup *cg,
+ long *regions_needed)
+{
+ struct file_region *nrg;
+
+ if (!regions_needed) {
+ nrg = get_file_region_entry_from_cache(map, from, to);
+ record_hugetlb_cgroup_uncharge_info(cg, h, map, nrg);
+ list_add(&nrg->link, rg->link.prev);
+ coalesce_file_region(map, nrg);
+ } else
+ *regions_needed += 1;
+
+ return to - from;
+}
+
/*
* Must be called with resv->lock held.
*
long add = 0;
struct list_head *head = &resv->regions;
long last_accounted_offset = f;
- struct file_region *rg = NULL, *trg = NULL, *nrg = NULL;
+ struct file_region *rg = NULL, *trg = NULL;
if (regions_needed)
*regions_needed = 0;
/* When we find a region that starts beyond our range, we've
* finished.
*/
- if (rg->from > t)
+ if (rg->from >= t)
break;
/* Add an entry for last_accounted_offset -> rg->from, and
* update last_accounted_offset.
*/
- if (rg->from > last_accounted_offset) {
- add += rg->from - last_accounted_offset;
- if (!regions_needed) {
- nrg = get_file_region_entry_from_cache(
- resv, last_accounted_offset, rg->from);
- record_hugetlb_cgroup_uncharge_info(h_cg, h,
- resv, nrg);
- list_add(&nrg->link, rg->link.prev);
- coalesce_file_region(resv, nrg);
- } else
- *regions_needed += 1;
- }
+ if (rg->from > last_accounted_offset)
+ add += hugetlb_resv_map_add(resv, rg,
+ last_accounted_offset,
+ rg->from, h, h_cg,
+ regions_needed);
last_accounted_offset = rg->to;
}
/* Handle the case where our range extends beyond
* last_accounted_offset.
*/
- if (last_accounted_offset < t) {
- add += t - last_accounted_offset;
- if (!regions_needed) {
- nrg = get_file_region_entry_from_cache(
- resv, last_accounted_offset, t);
- record_hugetlb_cgroup_uncharge_info(h_cg, h, resv, nrg);
- list_add(&nrg->link, rg->link.prev);
- coalesce_file_region(resv, nrg);
- } else
- *regions_needed += 1;
- }
+ if (last_accounted_offset < t)
+ add += hugetlb_resv_map_add(resv, rg, last_accounted_offset,
+ t, h, h_cg, regions_needed);
VM_BUG_ON(add < 0);
return add;
del += t - f;
hugetlb_cgroup_uncharge_file_region(
- resv, rg, t - f);
+ resv, rg, t - f, false);
/* New entry for end of split region */
nrg->from = t;
if (f <= rg->from && t >= rg->to) { /* Remove entire region */
del += rg->to - rg->from;
hugetlb_cgroup_uncharge_file_region(resv, rg,
- rg->to - rg->from);
+ rg->to - rg->from, true);
list_del(&rg->link);
kfree(rg);
continue;
if (f <= rg->from) { /* Trim beginning of region */
hugetlb_cgroup_uncharge_file_region(resv, rg,
- t - rg->from);
+ t - rg->from, false);
del += t - rg->from;
rg->from = t;
} else { /* Trim end of region */
hugetlb_cgroup_uncharge_file_region(resv, rg,
- rg->to - f);
+ rg->to - f, false);
del += rg->to - f;
rg->to = f;
return false;
}
+static void
+hugetlb_install_page(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr,
+ struct page *new_page)
+{
+ __SetPageUptodate(new_page);
+ set_huge_pte_at(vma->vm_mm, addr, ptep, make_huge_pte(vma, new_page, 1));
+ hugepage_add_new_anon_rmap(new_page, vma, addr);
+ hugetlb_count_add(pages_per_huge_page(hstate_vma(vma)), vma->vm_mm);
+ ClearHPageRestoreReserve(new_page);
+ SetHPageMigratable(new_page);
+}
+
int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
struct vm_area_struct *vma)
{
pte_t *src_pte, *dst_pte, entry, dst_entry;
struct page *ptepage;
unsigned long addr;
- int cow;
+ bool cow = is_cow_mapping(vma->vm_flags);
struct hstate *h = hstate_vma(vma);
unsigned long sz = huge_page_size(h);
+ unsigned long npages = pages_per_huge_page(h);
struct address_space *mapping = vma->vm_file->f_mapping;
struct mmu_notifier_range range;
int ret = 0;
- cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
-
if (cow) {
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, src,
vma->vm_start,
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
entry = huge_ptep_get(src_pte);
dst_entry = huge_ptep_get(dst_pte);
+again:
if (huge_pte_none(entry) || !huge_pte_none(dst_entry)) {
/*
* Skip if src entry none. Also, skip in the
}
set_huge_swap_pte_at(dst, addr, dst_pte, entry, sz);
} else {
+ entry = huge_ptep_get(src_pte);
+ ptepage = pte_page(entry);
+ get_page(ptepage);
+
+ /*
+ * This is a rare case where we see pinned hugetlb
+ * pages while they're prone to COW. We need to do the
+ * COW earlier during fork.
+ *
+ * When pre-allocating the page or copying data, we
+ * need to be without the pgtable locks since we could
+ * sleep during the process.
+ */
+ if (unlikely(page_needs_cow_for_dma(vma, ptepage))) {
+ pte_t src_pte_old = entry;
+ struct page *new;
+
+ spin_unlock(src_ptl);
+ spin_unlock(dst_ptl);
+ /* Do not use reserve as it's private owned */
+ new = alloc_huge_page(vma, addr, 1);
+ if (IS_ERR(new)) {
+ put_page(ptepage);
+ ret = PTR_ERR(new);
+ break;
+ }
+ copy_user_huge_page(new, ptepage, addr, vma,
+ npages);
+ put_page(ptepage);
+
+ /* Install the new huge page if src pte stable */
+ dst_ptl = huge_pte_lock(h, dst, dst_pte);
+ src_ptl = huge_pte_lockptr(h, src, src_pte);
+ spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
+ entry = huge_ptep_get(src_pte);
+ if (!pte_same(src_pte_old, entry)) {
+ put_page(new);
+ /* dst_entry won't change as in child */
+ goto again;
+ }
+ hugetlb_install_page(vma, dst_pte, addr, new);
+ spin_unlock(src_ptl);
+ spin_unlock(dst_ptl);
+ continue;
+ }
+
if (cow) {
/*
* No need to notify as we are downgrading page
*/
huge_ptep_set_wrprotect(src, addr, src_pte);
}
- entry = huge_ptep_get(src_pte);
- ptepage = pte_page(entry);
- get_page(ptepage);
+
page_dup_rmap(ptepage, true);
set_huge_pte_at(dst, addr, dst_pte, entry);
- hugetlb_count_add(pages_per_huge_page(h), dst);
+ hugetlb_count_add(npages, dst);
}
spin_unlock(src_ptl);
spin_unlock(dst_ptl);
*/
long rsv_adjust;
+ /*
+ * hugetlb_cgroup_uncharge_cgroup_rsvd() will put the
+ * reference to h_cg->css. See comment below for detail.
+ */
hugetlb_cgroup_uncharge_cgroup_rsvd(
hstate_index(h),
(chg - add) * pages_per_huge_page(h), h_cg);
rsv_adjust = hugepage_subpool_put_pages(spool,
chg - add);
hugetlb_acct_memory(h, -rsv_adjust);
+ } else if (h_cg) {
+ /*
+ * The file_regions will hold their own reference to
+ * h_cg->css. So we should release the reference held
+ * via hugetlb_cgroup_charge_cgroup_rsvd() when we are
+ * done.
+ */
+ hugetlb_cgroup_put_rsvd_cgroup(h_cg);
}
}
return true;
void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv,
struct file_region *rg,
- unsigned long nr_pages)
+ unsigned long nr_pages,
+ bool region_del)
{
if (hugetlb_cgroup_disabled() || !resv || !rg || !nr_pages)
return;
!resv->reservation_counter) {
page_counter_uncharge(rg->reservation_counter,
nr_pages * resv->pages_per_hpage);
- css_put(rg->css);
+ /*
+ * Only do css_put(rg->css) when we delete the entire region
+ * because one file_region must hold exactly one css reference.
+ */
+ if (region_del)
+ css_put(rg->css);
}
}
set_page_count(page, 1);
}
+/*
+ * When kernel touch the user page, the user page may be have been marked
+ * poison but still mapped in user space, if without this page, the kernel
+ * can guarantee the data integrity and operation success, the kernel is
+ * better to check the posion status and avoid touching it, be good not to
+ * panic, coredump for process fatal signal is a sample case matching this
+ * scenario. Or if kernel can't guarantee the data integrity, it's better
+ * not to call this function, let kernel touch the poison page and get to
+ * panic.
+ */
+static inline bool is_page_poisoned(struct page *page)
+{
+ if (PageHWPoison(page))
+ return true;
+ else if (PageHuge(page) && PageHWPoison(compound_head(page)))
+ return true;
+
+ return false;
+}
+
extern unsigned long highest_memmap_pfn;
/*
*/
#define buddy_order_unsafe(page) READ_ONCE(page_private(page))
-static inline bool is_cow_mapping(vm_flags_t flags)
-{
- return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
-}
-
/*
* These three helpers classifies VMAs for virtual memory accounting.
*/
kasan_unpoison(address, size);
}
-#if CONFIG_KASAN_STACK
+#ifdef CONFIG_KASAN_STACK
/* Unpoison the entire stack for a task. */
void kasan_unpoison_task_stack(struct task_struct *task)
{
KASAN_ARG_ON,
};
+enum kasan_arg_mode {
+ KASAN_ARG_MODE_DEFAULT,
+ KASAN_ARG_MODE_SYNC,
+ KASAN_ARG_MODE_ASYNC,
+};
+
enum kasan_arg_stacktrace {
KASAN_ARG_STACKTRACE_DEFAULT,
KASAN_ARG_STACKTRACE_OFF,
};
static enum kasan_arg kasan_arg __ro_after_init;
+static enum kasan_arg_mode kasan_arg_mode __ro_after_init;
static enum kasan_arg_stacktrace kasan_arg_stacktrace __ro_after_init;
static enum kasan_arg_fault kasan_arg_fault __ro_after_init;
DEFINE_STATIC_KEY_FALSE(kasan_flag_enabled);
EXPORT_SYMBOL(kasan_flag_enabled);
+/* Whether the asynchronous mode is enabled. */
+bool kasan_flag_async __ro_after_init;
+EXPORT_SYMBOL_GPL(kasan_flag_async);
+
/* Whether to collect alloc/free stack traces. */
DEFINE_STATIC_KEY_FALSE(kasan_flag_stacktrace);
}
early_param("kasan", early_kasan_flag);
+/* kasan.mode=sync/async */
+static int __init early_kasan_mode(char *arg)
+{
+ if (!arg)
+ return -EINVAL;
+
+ if (!strcmp(arg, "sync"))
+ kasan_arg_mode = KASAN_ARG_MODE_SYNC;
+ else if (!strcmp(arg, "async"))
+ kasan_arg_mode = KASAN_ARG_MODE_ASYNC;
+ else
+ return -EINVAL;
+
+ return 0;
+}
+early_param("kasan.mode", early_kasan_mode);
+
/* kasan.stacktrace=off/on */
static int __init early_kasan_flag_stacktrace(char *arg)
{
return;
hw_init_tags(KASAN_TAG_MAX);
- hw_enable_tagging();
+
+ /*
+ * Enable async mode only when explicitly requested through
+ * the command line.
+ */
+ if (kasan_arg_mode == KASAN_ARG_MODE_ASYNC)
+ hw_enable_tagging_async();
+ else
+ hw_enable_tagging_sync();
}
/* kasan_init_hw_tags() is called once on boot CPU. */
/* Enable KASAN. */
static_branch_enable(&kasan_flag_enabled);
+ switch (kasan_arg_mode) {
+ case KASAN_ARG_MODE_DEFAULT:
+ /*
+ * Default to sync mode.
+ * Do nothing, kasan_flag_async keeps its default value.
+ */
+ break;
+ case KASAN_ARG_MODE_SYNC:
+ /* Do nothing, kasan_flag_async keeps its default value. */
+ break;
+ case KASAN_ARG_MODE_ASYNC:
+ /* Async mode enabled. */
+ kasan_flag_async = true;
+ break;
+ }
+
switch (kasan_arg_stacktrace) {
case KASAN_ARG_STACKTRACE_DEFAULT:
/* Default to enabling stack trace collection. */
}
EXPORT_SYMBOL_GPL(kasan_set_tagging_report_once);
-void kasan_enable_tagging(void)
+void kasan_enable_tagging_sync(void)
+{
+ hw_enable_tagging_sync();
+}
+EXPORT_SYMBOL_GPL(kasan_enable_tagging_sync);
+
+void kasan_force_async_fault(void)
{
- hw_enable_tagging();
+ hw_force_async_tag_fault();
}
-EXPORT_SYMBOL_GPL(kasan_enable_tagging);
+EXPORT_SYMBOL_GPL(kasan_force_async_fault);
#endif
#include <linux/stackdepot.h>
#ifdef CONFIG_KASAN_HW_TAGS
+
#include <linux/static_key.h>
+
DECLARE_STATIC_KEY_FALSE(kasan_flag_stacktrace);
+extern bool kasan_flag_async __ro_after_init;
+
static inline bool kasan_stack_collection_enabled(void)
{
return static_branch_unlikely(&kasan_flag_stacktrace);
}
+
+static inline bool kasan_async_mode_enabled(void)
+{
+ return kasan_flag_async;
+}
#else
+
static inline bool kasan_stack_collection_enabled(void)
{
return true;
}
+
+static inline bool kasan_async_mode_enabled(void)
+{
+ return false;
+}
+
#endif
extern bool kasan_flag_panic __ro_after_init;
+extern bool kasan_flag_async __ro_after_init;
#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
#define KASAN_GRANULE_SIZE (1UL << KASAN_SHADOW_SCALE_SHIFT)
const char *kasan_get_bug_type(struct kasan_access_info *info);
void kasan_metadata_fetch_row(char *buffer, void *row);
-#if defined(CONFIG_KASAN_GENERIC) && CONFIG_KASAN_STACK
+#if defined(CONFIG_KASAN_GENERIC) && defined(CONFIG_KASAN_STACK)
void kasan_print_address_stack_frame(const void *addr);
#else
static inline void kasan_print_address_stack_frame(const void *addr) { }
#ifdef CONFIG_KASAN_HW_TAGS
-#ifndef arch_enable_tagging
-#define arch_enable_tagging()
+#ifndef arch_enable_tagging_sync
+#define arch_enable_tagging_sync()
+#endif
+#ifndef arch_enable_tagging_async
+#define arch_enable_tagging_async()
#endif
#ifndef arch_init_tags
#define arch_init_tags(max_tag)
#ifndef arch_set_tagging_report_once
#define arch_set_tagging_report_once(state)
#endif
+#ifndef arch_force_async_tag_fault
+#define arch_force_async_tag_fault()
+#endif
#ifndef arch_get_random_tag
#define arch_get_random_tag() (0xFF)
#endif
#define arch_set_mem_tag_range(addr, size, tag) ((void *)(addr))
#endif
-#define hw_enable_tagging() arch_enable_tagging()
+#define hw_enable_tagging_sync() arch_enable_tagging_sync()
+#define hw_enable_tagging_async() arch_enable_tagging_async()
#define hw_init_tags(max_tag) arch_init_tags(max_tag)
#define hw_set_tagging_report_once(state) arch_set_tagging_report_once(state)
+#define hw_force_async_tag_fault() arch_force_async_tag_fault()
#define hw_get_random_tag() arch_get_random_tag()
#define hw_get_mem_tag(addr) arch_get_mem_tag(addr)
#define hw_set_mem_tag_range(addr, size, tag) arch_set_mem_tag_range((addr), (size), (tag))
#else /* CONFIG_KASAN_HW_TAGS */
-#define hw_enable_tagging()
+#define hw_enable_tagging_sync()
+#define hw_enable_tagging_async()
#define hw_set_tagging_report_once(state)
#endif /* CONFIG_KASAN_HW_TAGS */
#if defined(CONFIG_KASAN_HW_TAGS) && IS_ENABLED(CONFIG_KASAN_KUNIT_TEST)
void kasan_set_tagging_report_once(bool state);
-void kasan_enable_tagging(void);
+void kasan_enable_tagging_sync(void);
+void kasan_force_async_fault(void);
#else /* CONFIG_KASAN_HW_TAGS || CONFIG_KASAN_KUNIT_TEST */
static inline void kasan_set_tagging_report_once(bool state) { }
-static inline void kasan_enable_tagging(void) { }
+static inline void kasan_enable_tagging_sync(void) { }
+static inline void kasan_force_async_fault(void) { }
#endif /* CONFIG_KASAN_HW_TAGS || CONFIG_KASAN_KUNIT_TEST */
static void end_report(unsigned long *flags, unsigned long addr)
{
- trace_error_report_end(ERROR_DETECTOR_KASAN, addr);
+ if (!kasan_async_mode_enabled())
+ trace_error_report_end(ERROR_DETECTOR_KASAN, addr);
pr_err("==================================================================\n");
add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
spin_unlock_irqrestore(&report_lock, *flags);
end_report(&flags, (unsigned long)object);
}
+#ifdef CONFIG_KASAN_HW_TAGS
+void kasan_report_async(void)
+{
+ unsigned long flags;
+
+#if IS_ENABLED(CONFIG_KUNIT)
+ if (current->kunit_test)
+ kasan_update_kunit_status(current->kunit_test);
+#endif /* IS_ENABLED(CONFIG_KUNIT) */
+
+ start_report(&flags);
+ pr_err("BUG: KASAN: invalid-access\n");
+ pr_err("Asynchronous mode enabled: no access details available\n");
+ pr_err("\n");
+ dump_stack();
+ end_report(&flags, 0);
+}
+#endif /* CONFIG_KASAN_HW_TAGS */
+
static void __kasan_report(unsigned long addr, size_t size, bool is_write,
unsigned long ip)
{
memcpy(buffer, kasan_mem_to_shadow(row), META_BYTES_PER_ROW);
}
-#if CONFIG_KASAN_STACK
+#ifdef CONFIG_KASAN_STACK
static bool __must_check tokenize_frame_descr(const char **frame_descr,
char *token, size_t max_tok_len,
unsigned long *value)
#include <linux/debugfs.h>
#include <linux/kcsan-checks.h>
#include <linux/kfence.h>
+#include <linux/kmemleak.h>
#include <linux/list.h>
#include <linux/lockdep.h>
#include <linux/memblock.h>
addr += 2 * PAGE_SIZE;
}
+ /*
+ * The pool is live and will never be deallocated from this point on.
+ * Remove the pool object from the kmemleak object tree, as it would
+ * otherwise overlap with allocations returned by kfence_alloc(), which
+ * are registered with kmemleak through the slab post-alloc hook.
+ */
+ kmemleak_free(__kfence_pool);
+
return true;
err:
#include "kfence.h"
+/* May be overridden by <asm/kfence.h>. */
+#ifndef ARCH_FUNC_PREFIX
+#define ARCH_FUNC_PREFIX ""
+#endif
+
extern bool no_hash_pointers;
/* Helper function to either print to a seq_file or to console. */
for (skipnr = 0; skipnr < num_entries; skipnr++) {
int len = scnprintf(buf, sizeof(buf), "%ps", (void *)stack_entries[skipnr]);
- if (str_has_prefix(buf, "kfence_") || str_has_prefix(buf, "__kfence_") ||
- !strncmp(buf, "__slab_free", len)) {
+ if (str_has_prefix(buf, ARCH_FUNC_PREFIX "kfence_") ||
+ str_has_prefix(buf, ARCH_FUNC_PREFIX "__kfence_") ||
+ !strncmp(buf, ARCH_FUNC_PREFIX "__slab_free", len)) {
/*
* In case of tail calls from any of the below
* to any of the above.
}
/* Also the *_bulk() variants by only checking prefixes. */
- if (str_has_prefix(buf, "kfree") ||
- str_has_prefix(buf, "kmem_cache_free") ||
- str_has_prefix(buf, "__kmalloc") ||
- str_has_prefix(buf, "kmem_cache_alloc"))
+ if (str_has_prefix(buf, ARCH_FUNC_PREFIX "kfree") ||
+ str_has_prefix(buf, ARCH_FUNC_PREFIX "kmem_cache_free") ||
+ str_has_prefix(buf, ARCH_FUNC_PREFIX "__kmalloc") ||
+ str_has_prefix(buf, ARCH_FUNC_PREFIX "kmem_cache_alloc"))
goto found;
}
if (fallback < num_entries)
lockdep_assert_held(&meta->lock);
if (meta->state == KFENCE_OBJECT_UNUSED) {
- seq_con_printf(seq, "kfence-#%zd unused\n", meta - kfence_metadata);
+ seq_con_printf(seq, "kfence-#%td unused\n", meta - kfence_metadata);
return;
}
seq_con_printf(seq,
- "kfence-#%zd [0x%p-0x%p"
+ "kfence-#%td [0x%p-0x%p"
", size=%d, cache=%s] allocated by task %d:\n",
meta - kfence_metadata, (void *)start, (void *)(start + size - 1), size,
(cache && cache->name) ? cache->name : "<destroyed>", meta->alloc_track.pid);
pr_err("BUG: KFENCE: out-of-bounds %s in %pS\n\n", get_access_type(is_write),
(void *)stack_entries[skipnr]);
- pr_err("Out-of-bounds %s at 0x%p (%luB %s of kfence-#%zd):\n",
+ pr_err("Out-of-bounds %s at 0x%p (%luB %s of kfence-#%td):\n",
get_access_type(is_write), (void *)address,
left_of_object ? meta->addr - address : address - meta->addr,
left_of_object ? "left" : "right", object_index);
case KFENCE_ERROR_UAF:
pr_err("BUG: KFENCE: use-after-free %s in %pS\n\n", get_access_type(is_write),
(void *)stack_entries[skipnr]);
- pr_err("Use-after-free %s at 0x%p (in kfence-#%zd):\n",
+ pr_err("Use-after-free %s at 0x%p (in kfence-#%td):\n",
get_access_type(is_write), (void *)address, object_index);
break;
case KFENCE_ERROR_CORRUPTION:
pr_err("BUG: KFENCE: memory corruption in %pS\n\n", (void *)stack_entries[skipnr]);
pr_err("Corrupted memory at 0x%p ", (void *)address);
print_diff_canary(address, 16, meta);
- pr_cont(" (in kfence-#%zd):\n", object_index);
+ pr_cont(" (in kfence-#%td):\n", object_index);
break;
case KFENCE_ERROR_INVALID:
pr_err("BUG: KFENCE: invalid %s in %pS\n\n", get_access_type(is_write),
break;
case KFENCE_ERROR_INVALID_FREE:
pr_err("BUG: KFENCE: invalid free in %pS\n\n", (void *)stack_entries[skipnr]);
- pr_err("Invalid free of 0x%p (in kfence-#%zd):\n", (void *)address,
+ pr_err("Invalid free of 0x%p (in kfence-#%td):\n", (void *)address,
object_index);
break;
}
#include <linux/atomic.h>
#include <linux/kasan.h>
+#include <linux/kfence.h>
#include <linux/kmemleak.h>
#include <linux/memory_hotplug.h>
atomic_set(&object->use_count, 1);
object->flags = OBJECT_ALLOCATED;
object->pointer = ptr;
- object->size = size;
+ object->size = kfence_ksize((void *)ptr) ?: size;
object->excess_ref = 0;
object->min_count = min_count;
object->count = 0; /* white color initially */
goto release_task;
}
- mm = mm_access(task, PTRACE_MODE_ATTACH_FSCREDS);
+ /* Require PTRACE_MODE_READ to avoid leaking ASLR metadata. */
+ mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
if (IS_ERR_OR_NULL(mm)) {
ret = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH;
goto release_task;
}
+ /*
+ * Require CAP_SYS_NICE for influencing process performance. Note that
+ * only non-destructive hints are currently supported.
+ */
+ if (!capable(CAP_SYS_NICE)) {
+ ret = -EPERM;
+ goto release_mm;
+ }
+
total_len = iov_iter_count(&iter);
while (iov_iter_count(&iter)) {
if (ret == 0)
ret = total_len - iov_iter_count(&iter);
+release_mm:
mmput(mm);
release_task:
put_task_struct(task);
return 0;
}
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
/* Huge pud */
walk->action = ACTION_CONTINUE;
if (pud_trans_huge(pudval) || pud_devmap(pudval))
WARN_ON(pud_write(pudval) || pud_dirty(pudval));
+#endif
return 0;
}
#endif /* CONFIG_MEMCG_KMEM */
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/*
- * Because page_memcg(head) is not set on compound tails, set it now.
+ * Because page_memcg(head) is not set on tails, set it now.
*/
-void mem_cgroup_split_huge_fixup(struct page *head)
+void split_page_memcg(struct page *head, unsigned int nr)
{
struct mem_cgroup *memcg = page_memcg(head);
int i;
- if (mem_cgroup_disabled())
+ if (mem_cgroup_disabled() || !memcg)
return;
- for (i = 1; i < HPAGE_PMD_NR; i++) {
- css_get(&memcg->css);
- head[i].memcg_data = (unsigned long)memcg;
- }
+ for (i = 1; i < nr; i++)
+ head[i].memcg_data = head->memcg_data;
+ css_get_many(&memcg->css, nr - 1);
}
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#ifdef CONFIG_MEMCG_SWAP
/**
zero_pfn = page_to_pfn(ZERO_PAGE(0));
return 0;
}
-core_initcall(init_zero_pfn);
+early_initcall(init_zero_pfn);
void mm_trace_rss_stat(struct mm_struct *mm, int member, long count)
{
pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss,
struct page **prealloc, pte_t pte, struct page *page)
{
- struct mm_struct *src_mm = src_vma->vm_mm;
struct page *new_page;
- if (!is_cow_mapping(src_vma->vm_flags))
- return 1;
-
/*
* What we want to do is to check whether this page may
* have been pinned by the parent process. If so,
* the page count. That might give false positives for
* for pinning, but it will work correctly.
*/
- if (likely(!atomic_read(&src_mm->has_pinned)))
- return 1;
- if (likely(!page_maybe_dma_pinned(page)))
+ if (likely(!page_needs_cow_for_dma(src_vma, page)))
return 1;
new_page = *prealloc;
return handle_userfault(vmf, VM_UFFD_WP);
}
+ /*
+ * Userfaultfd write-protect can defer flushes. Ensure the TLB
+ * is flushed in this case before copying.
+ */
+ if (unlikely(userfaultfd_wp(vmf->vma) &&
+ mm_tlb_flush_pending(vmf->vma->vm_mm)))
+ flush_tlb_page(vmf->vma, vmf->address);
+
vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte);
if (!vmf->page) {
/*
*/
int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
{
- struct mhp_params params = { .pgprot = PAGE_KERNEL };
+ struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) };
u64 start, size;
bool new_node = false;
int ret;
* MAP_PRIVATE r: (no) no r: (yes) yes r: (no) yes r: (no) yes
* w: (no) no w: (no) no w: (copy) copy w: (no) no
* x: (no) no x: (no) yes x: (no) yes x: (yes) yes
+ *
+ * On arm64, PROT_EXEC has the following behaviour for both MAP_SHARED and
+ * MAP_PRIVATE (with Enhanced PAN supported):
+ * r: (no) no
+ * w: (no) no
+ * x: (yes) yes
*/
pgprot_t protection_map[16] __ro_after_init = {
__P000, __P001, __P010, __P011, __P100, __P101, __P110, __P111,
tlb_flush_mmu_free(tlb);
}
-/**
- * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down
- * @tlb: the mmu_gather structure to initialize
- * @mm: the mm_struct of the target address space
- * @fullmm: @mm is without users and we're going to destroy the full address
- * space (exit/execve)
- *
- * Called to initialize an (on-stack) mmu_gather structure for page-table
- * tear-down from @mm.
- */
static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
bool fullmm)
{
inc_tlb_flush_pending(tlb->mm);
}
+/**
+ * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down
+ * @tlb: the mmu_gather structure to initialize
+ * @mm: the mm_struct of the target address space
+ *
+ * Called to initialize an (on-stack) mmu_gather structure for page-table
+ * tear-down from @mm.
+ */
void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm)
{
__tlb_gather_mmu(tlb, mm, false);
}
+/**
+ * tlb_gather_mmu_fullmm - initialize an mmu_gather structure for page-table tear-down
+ * @tlb: the mmu_gather structure to initialize
+ * @mm: the mm_struct of the target address space
+ *
+ * In this case, @mm is without users and we're going to destroy the
+ * full address space (exit/execve).
+ *
+ * Called to initialize an (on-stack) mmu_gather structure for page-table
+ * tear-down from @mm.
+ */
void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm)
{
__tlb_gather_mmu(tlb, mm, true);
"");
WARN_ON(mmu_notifier_range_blockable(range) ||
_ret != -EAGAIN);
+ /*
+ * We call all the notifiers on any EAGAIN,
+ * there is no way for a notifier to know if
+ * its start method failed, thus a start that
+ * does EAGAIN can't also do end.
+ */
+ WARN_ON(ops->invalidate_range_end);
ret = _ret;
}
}
}
+
+ if (ret) {
+ /*
+ * Must be non-blocking to get here. If there are multiple
+ * notifiers and one or more failed start, any that succeeded
+ * start are expecting their end to be called. Do so now.
+ */
+ hlist_for_each_entry_rcu(subscription, &subscriptions->list,
+ hlist, srcu_read_lock_held(&srcu)) {
+ if (!subscription->ops->invalidate_range_end)
+ continue;
+
+ subscription->ops->invalidate_range_end(subscription,
+ range);
+ }
+ }
srcu_read_unlock(&srcu, id);
return ret;
return false;
}
-/**
+/*
* Check whether unreclaimable slab amount is greater than
* all user memory(LRU pages).
* dump_unreclaimable_slab() could help in the case that
}
EXPORT_SYMBOL_GPL(wait_on_page_writeback);
+/*
+ * Wait for a page to complete writeback. Returns -EINTR if we get a
+ * fatal signal while waiting.
+ */
+int wait_on_page_writeback_killable(struct page *page)
+{
+ while (PageWriteback(page)) {
+ trace_wait_on_page_writeback(page, page_mapping(page));
+ if (wait_on_page_bit_killable(page, PG_writeback))
+ return -EINTR;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(wait_on_page_writeback_killable);
+
/**
* wait_for_stable_page() - wait for writeback to finish, if necessary.
* @page: The page to wait on.
int percpu_pagelist_fraction;
gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
-DEFINE_STATIC_KEY_FALSE(init_on_alloc);
+DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_ALLOC_DEFAULT_ON, init_on_alloc);
EXPORT_SYMBOL(init_on_alloc);
-DEFINE_STATIC_KEY_FALSE(init_on_free);
+DEFINE_STATIC_KEY_MAYBE(CONFIG_INIT_ON_FREE_DEFAULT_ON, init_on_free);
EXPORT_SYMBOL(init_on_free);
static bool _init_on_alloc_enabled_early __read_mostly
kernel_poison_pages(page, 1 << order);
/*
+ * With hardware tag-based KASAN, memory tags must be set before the
+ * page becomes unavailable via debug_pagealloc or arch_free_page.
+ */
+ kasan_free_nondeferred_pages(page, order);
+
+ /*
* arch_free_page() can make the page's contents inaccessible. s390
* does this. So nothing which can access the page's contents should
* happen after this.
debug_pagealloc_unmap_pages(page, 1 << order);
- kasan_free_nondeferred_pages(page, order);
-
return true;
}
for (i = 1; i < (1 << order); i++)
set_page_refcounted(page + i);
split_page_owner(page, 1 << order);
+ split_page_memcg(page, 1 << order);
}
EXPORT_SYMBOL_GPL(split_page);
}
}
+#if !defined(CONFIG_FLAT_NODE_MEM_MAP)
+/*
+ * Only struct pages that correspond to ranges defined by memblock.memory
+ * are zeroed and initialized by going through __init_single_page() during
+ * memmap_init_zone().
+ *
+ * But, there could be struct pages that correspond to holes in
+ * memblock.memory. This can happen because of the following reasons:
+ * - physical memory bank size is not necessarily the exact multiple of the
+ * arbitrary section size
+ * - early reserved memory may not be listed in memblock.memory
+ * - memory layouts defined with memmap= kernel parameter may not align
+ * nicely with memmap sections
+ *
+ * Explicitly initialize those struct pages so that:
+ * - PG_Reserved is set
+ * - zone and node links point to zone and node that span the page if the
+ * hole is in the middle of a zone
+ * - zone and node links point to adjacent zone/node if the hole falls on
+ * the zone boundary; the pages in such holes will be prepended to the
+ * zone/node above the hole except for the trailing pages in the last
+ * section that will be appended to the zone/node below.
+ */
+static u64 __meminit init_unavailable_range(unsigned long spfn,
+ unsigned long epfn,
+ int zone, int node)
+{
+ unsigned long pfn;
+ u64 pgcnt = 0;
+
+ for (pfn = spfn; pfn < epfn; pfn++) {
+ if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) {
+ pfn = ALIGN_DOWN(pfn, pageblock_nr_pages)
+ + pageblock_nr_pages - 1;
+ continue;
+ }
+ __init_single_page(pfn_to_page(pfn), pfn, zone, node);
+ __SetPageReserved(pfn_to_page(pfn));
+ pgcnt++;
+ }
+
+ return pgcnt;
+}
+#else
+static inline u64 init_unavailable_range(unsigned long spfn, unsigned long epfn,
+ int zone, int node)
+{
+ return 0;
+}
+#endif
+
void __meminit __weak memmap_init_zone(struct zone *zone)
{
unsigned long zone_start_pfn = zone->zone_start_pfn;
unsigned long zone_end_pfn = zone_start_pfn + zone->spanned_pages;
int i, nid = zone_to_nid(zone), zone_id = zone_idx(zone);
+ static unsigned long hole_pfn;
unsigned long start_pfn, end_pfn;
+ u64 pgcnt = 0;
for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
start_pfn = clamp(start_pfn, zone_start_pfn, zone_end_pfn);
memmap_init_range(end_pfn - start_pfn, nid,
zone_id, start_pfn, zone_end_pfn,
MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
+
+ if (hole_pfn < start_pfn)
+ pgcnt += init_unavailable_range(hole_pfn, start_pfn,
+ zone_id, nid);
+ hole_pfn = end_pfn;
}
+
+#ifdef CONFIG_SPARSEMEM
+ /*
+ * Initialize the hole in the range [zone_end_pfn, section_end].
+ * If zone boundary falls in the middle of a section, this hole
+ * will be re-initialized during the call to this function for the
+ * higher zone.
+ */
+ end_pfn = round_up(zone_end_pfn, PAGES_PER_SECTION);
+ if (hole_pfn < end_pfn)
+ pgcnt += init_unavailable_range(hole_pfn, end_pfn,
+ zone_id, nid);
+#endif
+
+ if (pgcnt)
+ pr_info(" %s zone: %llu pages in unavailable ranges\n",
+ zone->name, pgcnt);
}
static int zone_batchsize(struct zone *zone)
free_area_init_node(nid);
}
-#if !defined(CONFIG_FLAT_NODE_MEM_MAP)
-/*
- * Initialize all valid struct pages in the range [spfn, epfn) and mark them
- * PageReserved(). Return the number of struct pages that were initialized.
- */
-static u64 __init init_unavailable_range(unsigned long spfn, unsigned long epfn)
-{
- unsigned long pfn;
- u64 pgcnt = 0;
-
- for (pfn = spfn; pfn < epfn; pfn++) {
- if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) {
- pfn = ALIGN_DOWN(pfn, pageblock_nr_pages)
- + pageblock_nr_pages - 1;
- continue;
- }
- /*
- * Use a fake node/zone (0) for now. Some of these pages
- * (in memblock.reserved but not in memblock.memory) will
- * get re-initialized via reserve_bootmem_region() later.
- */
- __init_single_page(pfn_to_page(pfn), pfn, 0, 0);
- __SetPageReserved(pfn_to_page(pfn));
- pgcnt++;
- }
-
- return pgcnt;
-}
-
-/*
- * Only struct pages that are backed by physical memory are zeroed and
- * initialized by going through __init_single_page(). But, there are some
- * struct pages which are reserved in memblock allocator and their fields
- * may be accessed (for example page_to_pfn() on some configuration accesses
- * flags). We must explicitly initialize those struct pages.
- *
- * This function also addresses a similar issue where struct pages are left
- * uninitialized because the physical address range is not covered by
- * memblock.memory or memblock.reserved. That could happen when memblock
- * layout is manually configured via memmap=, or when the highest physical
- * address (max_pfn) does not end on a section boundary.
- */
-static void __init init_unavailable_mem(void)
-{
- phys_addr_t start, end;
- u64 i, pgcnt;
- phys_addr_t next = 0;
-
- /*
- * Loop through unavailable ranges not covered by memblock.memory.
- */
- pgcnt = 0;
- for_each_mem_range(i, &start, &end) {
- if (next < start)
- pgcnt += init_unavailable_range(PFN_DOWN(next),
- PFN_UP(start));
- next = end;
- }
-
- /*
- * Early sections always have a fully populated memmap for the whole
- * section - see pfn_valid(). If the last section has holes at the
- * end and that section is marked "online", the memmap will be
- * considered initialized. Make sure that memmap has a well defined
- * state.
- */
- pgcnt += init_unavailable_range(PFN_DOWN(next),
- round_up(max_pfn, PAGES_PER_SECTION));
-
- /*
- * Struct pages that do not have backing memory. This could be because
- * firmware is using some of this memory, or for some other reasons.
- */
- if (pgcnt)
- pr_info("Zeroed struct page in unavailable ranges: %lld pages", pgcnt);
-}
-#else
-static inline void __init init_unavailable_mem(void)
-{
-}
-#endif /* !CONFIG_FLAT_NODE_MEM_MAP */
-
#if MAX_NUMNODES > 1
/*
* Figure out the number of possible node ids.
/* Initialise every node */
mminit_verify_pageflags_layout();
setup_nr_node_ids();
- init_unavailable_mem();
for_each_online_node(nid) {
pg_data_t *pgdat = NODE_DATA(nid);
free_area_init_node(nid);
void *addr;
addr = kmap_atomic(page);
+ kasan_disable_current();
/*
* Page poisoning when enabled poisons each and every page
* that is freed to buddy. Thus no extra check is done to
* see if a page was poisoned.
*/
- check_poison_mem(addr, PAGE_SIZE);
+ check_poison_mem(kasan_reset_tag(addr), PAGE_SIZE);
+ kasan_enable_current();
kunmap_atomic(addr);
}
extern struct list_head *pcpu_chunk_lists;
extern int pcpu_nr_slots;
-extern int pcpu_nr_empty_pop_pages;
+extern int pcpu_nr_empty_pop_pages[];
extern struct pcpu_chunk *pcpu_first_chunk;
extern struct pcpu_chunk *pcpu_reserved_chunk;
int slot, max_nr_alloc;
int *buffer;
enum pcpu_chunk_type type;
+ int nr_empty_pop_pages;
alloc_buffer:
spin_lock_irq(&pcpu_lock);
goto alloc_buffer;
}
-#define PL(X) \
+ nr_empty_pop_pages = 0;
+ for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++)
+ nr_empty_pop_pages += pcpu_nr_empty_pop_pages[type];
+
+#define PL(X) \
seq_printf(m, " %-20s: %12lld\n", #X, (long long int)pcpu_stats_ai.X)
seq_printf(m,
PU(nr_max_chunks);
PU(min_alloc_size);
PU(max_alloc_size);
- P("empty_pop_pages", pcpu_nr_empty_pop_pages);
+ P("empty_pop_pages", nr_empty_pop_pages);
seq_putc(m, '\n');
#undef PU
static LIST_HEAD(pcpu_map_extend_chunks);
/*
- * The number of empty populated pages, protected by pcpu_lock. The
- * reserved chunk doesn't contribute to the count.
+ * The number of empty populated pages by chunk type, protected by pcpu_lock.
+ * The reserved chunk doesn't contribute to the count.
*/
-int pcpu_nr_empty_pop_pages;
+int pcpu_nr_empty_pop_pages[PCPU_NR_CHUNK_TYPES];
/*
* The number of populated pages in use by the allocator, protected by
{
chunk->nr_empty_pop_pages += nr;
if (chunk != pcpu_reserved_chunk)
- pcpu_nr_empty_pop_pages += nr;
+ pcpu_nr_empty_pop_pages[pcpu_chunk_type(chunk)] += nr;
}
/*
mutex_unlock(&pcpu_alloc_mutex);
}
- if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW)
+ if (pcpu_nr_empty_pop_pages[type] < PCPU_EMPTY_POP_PAGES_LOW)
pcpu_schedule_balance_work();
/* clear the areas and return address relative to base address */
pcpu_atomic_alloc_failed = false;
} else {
nr_to_pop = clamp(PCPU_EMPTY_POP_PAGES_HIGH -
- pcpu_nr_empty_pop_pages,
+ pcpu_nr_empty_pop_pages[type],
0, PCPU_EMPTY_POP_PAGES_HIGH);
}
/* link the first chunk in */
pcpu_first_chunk = chunk;
- pcpu_nr_empty_pop_pages = pcpu_first_chunk->nr_empty_pop_pages;
+ pcpu_nr_empty_pop_pages[PCPU_CHUNK_ROOT] = pcpu_first_chunk->nr_empty_pop_pages;
pcpu_chunk_relocate(pcpu_first_chunk, -1);
/* include all regions of the first chunk */
unsigned long next, struct mm_walk *walk)
{
struct ptdump_state *st = walk->private;
- pte_t val = READ_ONCE(*pte);
+ pte_t val = ptep_get(pte);
if (st->effective_prot)
st->effective_prot(st, 4, pte_val(val));
spin_unlock_irqrestore(&z->lock, flags);
}
-/**
- * shuffle_free_memory - reduce the predictability of the page allocator
+/*
+ * __shuffle_free_memory - reduce the predictability of the page allocator
* @pgdat: node page data
*/
void __meminit __shuffle_free_memory(pg_data_t *pgdat)
gfp_t flags, void *objp, unsigned long caller)
{
WARN_ON_ONCE(cachep->ctor && (flags & __GFP_ZERO));
- if (!objp)
+ if (!objp || is_kfence_address(objp))
return objp;
if (cachep->flags & SLAB_POISON) {
check_poison_obj(cachep, objp);
static inline bool slab_want_init_on_alloc(gfp_t flags, struct kmem_cache *c)
{
- if (static_branch_unlikely(&init_on_alloc)) {
+ if (static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON,
+ &init_on_alloc)) {
if (c->ctor)
return false;
if (c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON))
static inline bool slab_want_init_on_free(struct kmem_cache *c)
{
- if (static_branch_unlikely(&init_on_free))
+ if (static_branch_maybe(CONFIG_INIT_ON_FREE_DEFAULT_ON,
+ &init_on_free))
return !(c->ctor ||
(c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)));
return false;
t = acquire_slab(s, n, page, object == NULL, &objects);
if (!t)
- continue; /* cmpxchg raced */
+ break;
available += objects;
if (!object) {
page = list_entry(pos, struct page, lru);
zhdr = page_address(page);
- if (test_bit(PAGE_HEADLESS, &page->private))
+ if (test_bit(PAGE_HEADLESS, &page->private)) {
+ /*
+ * For non-headless pages, we wait to do this
+ * until we have the page lock to avoid racing
+ * with __z3fold_alloc(). Headless pages don't
+ * have a lock (and __z3fold_alloc() will never
+ * see them), but we still need to test and set
+ * PAGE_CLAIMED to avoid racing with
+ * z3fold_free(), so just do it now before
+ * leaving the loop.
+ */
+ if (test_and_set_bit(PAGE_CLAIMED, &page->private))
+ continue;
+
break;
+ }
if (kref_get_unless_zero(&zhdr->refcount) == 0) {
zhdr = NULL;
}
p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", count);
- if (!count) {
- p9_tag_remove(clnt, req);
- return 0;
- }
if (non_zc) {
int n = copy_to_iter(dataptr, count, to);
MODULE_AUTHOR(BATADV_DRIVER_AUTHOR);
MODULE_DESCRIPTION(BATADV_DRIVER_DESC);
-MODULE_SUPPORTED_DEVICE(BATADV_DRIVER_DEVICE);
MODULE_VERSION(BATADV_SOURCE_VERSION);
MODULE_ALIAS_RTNL_LINK("batadv");
MODULE_ALIAS_GENL_FAMILY(BATADV_NL_NAME);
hlist_for_each_entry(vlan, &orig_node->vlan_list, list) {
tt_vlan->vid = htons(vlan->vid);
tt_vlan->crc = htonl(vlan->tt.crc);
+ tt_vlan->reserved = 0;
tt_vlan++;
}
tt_vlan->vid = htons(vlan->vid);
tt_vlan->crc = htonl(vlan->tt.crc);
+ tt_vlan->reserved = 0;
tt_vlan++;
}
int err;
struct ecdh p = {0};
- p.curve_id = ECC_CURVE_NIST_P256;
-
if (private_key) {
tmp = kmalloc(32, GFP_KERNEL);
if (!tmp)
calltime = ktime_get();
- tfm = crypto_alloc_kpp("ecdh", 0, 0);
+ tfm = crypto_alloc_kpp("ecdh-nist-p256", 0, 0);
if (IS_ERR(tfm)) {
BT_ERR("Unable to create ECDH crypto context");
err = PTR_ERR(tfm);
goto zfree_smp;
}
- smp->tfm_ecdh = crypto_alloc_kpp("ecdh", 0, 0);
+ smp->tfm_ecdh = crypto_alloc_kpp("ecdh-nist-p256", 0, 0);
if (IS_ERR(smp->tfm_ecdh)) {
BT_ERR("Unable to create ECDH crypto context");
goto free_shash;
return ERR_CAST(tfm_cmac);
}
- tfm_ecdh = crypto_alloc_kpp("ecdh", 0, 0);
+ tfm_ecdh = crypto_alloc_kpp("ecdh-nist-p256", 0, 0);
if (IS_ERR(tfm_ecdh)) {
BT_ERR("Unable to create ECDH crypto context");
crypto_free_shash(tfm_cmac);
return PTR_ERR(tfm_cmac);
}
- tfm_ecdh = crypto_alloc_kpp("ecdh", 0, 0);
+ tfm_ecdh = crypto_alloc_kpp("ecdh-nist-p256", 0, 0);
if (IS_ERR(tfm_ecdh)) {
BT_ERR("Unable to create ECDH crypto context");
crypto_free_shash(tfm_cmac);
{
if (!fdb->dst)
return;
+ if (test_bit(BR_FDB_LOCAL, &fdb->flags))
+ return;
switch (type) {
case RTM_DELNEIGH:
&net->xt.broute_table);
}
+static void __net_exit broute_net_pre_exit(struct net *net)
+{
+ ebt_unregister_table_pre_exit(net, "broute", &ebt_ops_broute);
+}
+
static void __net_exit broute_net_exit(struct net *net)
{
- ebt_unregister_table(net, net->xt.broute_table, &ebt_ops_broute);
+ ebt_unregister_table(net, net->xt.broute_table);
}
static struct pernet_operations broute_net_ops = {
.init = broute_net_init,
.exit = broute_net_exit,
+ .pre_exit = broute_net_pre_exit,
};
static int __init ebtable_broute_init(void)
&net->xt.frame_filter);
}
+static void __net_exit frame_filter_net_pre_exit(struct net *net)
+{
+ ebt_unregister_table_pre_exit(net, "filter", ebt_ops_filter);
+}
+
static void __net_exit frame_filter_net_exit(struct net *net)
{
- ebt_unregister_table(net, net->xt.frame_filter, ebt_ops_filter);
+ ebt_unregister_table(net, net->xt.frame_filter);
}
static struct pernet_operations frame_filter_net_ops = {
.init = frame_filter_net_init,
.exit = frame_filter_net_exit,
+ .pre_exit = frame_filter_net_pre_exit,
};
static int __init ebtable_filter_init(void)
&net->xt.frame_nat);
}
+static void __net_exit frame_nat_net_pre_exit(struct net *net)
+{
+ ebt_unregister_table_pre_exit(net, "nat", ebt_ops_nat);
+}
+
static void __net_exit frame_nat_net_exit(struct net *net)
{
- ebt_unregister_table(net, net->xt.frame_nat, ebt_ops_nat);
+ ebt_unregister_table(net, net->xt.frame_nat);
}
static struct pernet_operations frame_nat_net_ops = {
.init = frame_nat_net_init,
.exit = frame_nat_net_exit,
+ .pre_exit = frame_nat_net_pre_exit,
};
static int __init ebtable_nat_init(void)
return ret;
}
-void ebt_unregister_table(struct net *net, struct ebt_table *table,
- const struct nf_hook_ops *ops)
+static struct ebt_table *__ebt_find_table(struct net *net, const char *name)
+{
+ struct ebt_table *t;
+
+ mutex_lock(&ebt_mutex);
+
+ list_for_each_entry(t, &net->xt.tables[NFPROTO_BRIDGE], list) {
+ if (strcmp(t->name, name) == 0) {
+ mutex_unlock(&ebt_mutex);
+ return t;
+ }
+ }
+
+ mutex_unlock(&ebt_mutex);
+ return NULL;
+}
+
+void ebt_unregister_table_pre_exit(struct net *net, const char *name, const struct nf_hook_ops *ops)
+{
+ struct ebt_table *table = __ebt_find_table(net, name);
+
+ if (table)
+ nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
+}
+EXPORT_SYMBOL(ebt_unregister_table_pre_exit);
+
+void ebt_unregister_table(struct net *net, struct ebt_table *table)
{
- nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
__ebt_unregister_table(net, table);
}
MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>");
MODULE_ALIAS("can-proto-2");
+#define BCM_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_ifindex)
+
/*
* easy access to the first 64 bit of can(fd)_frame payload. cp->data is
* 64 bit aligned so the offset has to be multiples of 8 which is ensured
/* no bound device as default => check msg_name */
DECLARE_SOCKADDR(struct sockaddr_can *, addr, msg->msg_name);
- if (msg->msg_namelen < CAN_REQUIRED_SIZE(*addr, can_ifindex))
+ if (msg->msg_namelen < BCM_MIN_NAMELEN)
return -EINVAL;
if (addr->can_family != AF_CAN)
struct net *net = sock_net(sk);
int ret = 0;
- if (len < CAN_REQUIRED_SIZE(*addr, can_ifindex))
+ if (len < BCM_MIN_NAMELEN)
return -EINVAL;
lock_sock(sk);
sock_recv_ts_and_drops(msg, sk, skb);
if (msg->msg_name) {
- __sockaddr_check_size(sizeof(struct sockaddr_can));
- msg->msg_namelen = sizeof(struct sockaddr_can);
+ __sockaddr_check_size(BCM_MIN_NAMELEN);
+ msg->msg_namelen = BCM_MIN_NAMELEN;
memcpy(msg->msg_name, skb->cb, msg->msg_namelen);
}
MODULE_AUTHOR("Oliver Hartkopp <socketcan@hartkopp.net>");
MODULE_ALIAS("can-proto-6");
+#define ISOTP_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_addr.tp)
+
#define SINGLE_MASK(id) (((id) & CAN_EFF_FLAG) ? \
(CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \
(CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG))
nskb->dev = dev;
can_skb_set_owner(nskb, sk);
ncf = (struct canfd_frame *)nskb->data;
- skb_put(nskb, so->ll.mtu);
+ skb_put_zero(nskb, so->ll.mtu);
/* create & send flow control reply */
ncf->can_id = so->txid;
if (ae)
ncf->data[0] = so->opt.ext_address;
- if (so->ll.mtu == CANFD_MTU)
- ncf->flags = so->ll.tx_flags;
+ ncf->flags = so->ll.tx_flags;
can_send_ret = can_send(nskb, 1);
if (can_send_ret)
can_skb_prv(skb)->skbcnt = 0;
cf = (struct canfd_frame *)skb->data;
- skb_put(skb, so->ll.mtu);
+ skb_put_zero(skb, so->ll.mtu);
/* create consecutive frame */
isotp_fill_dataframe(cf, so, ae, 0);
so->tx.sn %= 16;
so->tx.bs++;
- if (so->ll.mtu == CANFD_MTU)
- cf->flags = so->ll.tx_flags;
+ cf->flags = so->ll.tx_flags;
skb->dev = dev;
can_skb_set_owner(skb, sk);
so->tx.idx = 0;
cf = (struct canfd_frame *)skb->data;
- skb_put(skb, so->ll.mtu);
+ skb_put_zero(skb, so->ll.mtu);
/* check for single frame transmission depending on TX_DL */
if (size <= so->tx.ll_dl - SF_PCI_SZ4 - ae - off) {
}
/* send the first or only CAN frame */
- if (so->ll.mtu == CANFD_MTU)
- cf->flags = so->ll.tx_flags;
+ cf->flags = so->ll.tx_flags;
skb->dev = dev;
skb->sk = sk;
sock_recv_timestamp(msg, sk, skb);
if (msg->msg_name) {
- msg->msg_namelen = sizeof(struct sockaddr_can);
+ __sockaddr_check_size(ISOTP_MIN_NAMELEN);
+ msg->msg_namelen = ISOTP_MIN_NAMELEN;
memcpy(msg->msg_name, skb->cb, msg->msg_namelen);
}
int notify_enetdown = 0;
int do_rx_reg = 1;
- if (len < CAN_REQUIRED_SIZE(struct sockaddr_can, can_addr.tp))
+ if (len < ISOTP_MIN_NAMELEN)
return -EINVAL;
/* do not register frame reception for functional addressing */
if (peer)
return -EOPNOTSUPP;
- memset(addr, 0, sizeof(*addr));
+ memset(addr, 0, ISOTP_MIN_NAMELEN);
addr->can_family = AF_CAN;
addr->can_ifindex = so->ifindex;
addr->can_addr.tp.rx_id = so->rxid;
addr->can_addr.tp.tx_id = so->txid;
- return sizeof(*addr);
+ return ISOTP_MIN_NAMELEN;
}
static int isotp_setsockopt(struct socket *sock, int level, int optname,
if (ll.mtu != CAN_MTU && ll.mtu != CANFD_MTU)
return -EINVAL;
- if (ll.mtu == CAN_MTU && ll.tx_dl > CAN_MAX_DLEN)
+ if (ll.mtu == CAN_MTU &&
+ (ll.tx_dl > CAN_MAX_DLEN || ll.tx_flags != 0))
return -EINVAL;
memcpy(&so->ll, &ll, sizeof(ll));
MODULE_AUTHOR("Urs Thuermann <urs.thuermann@volkswagen.de>");
MODULE_ALIAS("can-proto-1");
+#define RAW_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_ifindex)
+
#define MASK_ALL 0
/* A raw socket has a list of can_filters attached to it, each receiving
int err = 0;
int notify_enetdown = 0;
- if (len < CAN_REQUIRED_SIZE(*addr, can_ifindex))
+ if (len < RAW_MIN_NAMELEN)
return -EINVAL;
if (addr->can_family != AF_CAN)
return -EINVAL;
if (peer)
return -EOPNOTSUPP;
- memset(addr, 0, sizeof(*addr));
+ memset(addr, 0, RAW_MIN_NAMELEN);
addr->can_family = AF_CAN;
addr->can_ifindex = ro->ifindex;
- return sizeof(*addr);
+ return RAW_MIN_NAMELEN;
}
static int raw_setsockopt(struct socket *sock, int level, int optname,
if (msg->msg_name) {
DECLARE_SOCKADDR(struct sockaddr_can *, addr, msg->msg_name);
- if (msg->msg_namelen < CAN_REQUIRED_SIZE(*addr, can_ifindex))
+ if (msg->msg_namelen < RAW_MIN_NAMELEN)
return -EINVAL;
if (addr->can_family != AF_CAN)
sock_recv_ts_and_drops(msg, sk, skb);
if (msg->msg_name) {
- __sockaddr_check_size(sizeof(struct sockaddr_can));
- msg->msg_namelen = sizeof(struct sockaddr_can);
+ __sockaddr_check_size(RAW_MIN_NAMELEN);
+ msg->msg_namelen = RAW_MIN_NAMELEN;
memcpy(msg->msg_name, skb->cb, msg->msg_namelen);
}
return -ENOMEM;
for_each_netdev(net, d) {
+ struct netdev_name_node *name_node;
+ list_for_each_entry(name_node, &d->name_node->list, list) {
+ if (!sscanf(name_node->name, name, &i))
+ continue;
+ if (i < 0 || i >= max_netdevices)
+ continue;
+
+ /* avoid cases where sscanf is not exact inverse of printf */
+ snprintf(buf, IFNAMSIZ, name, i);
+ if (!strncmp(buf, name_node->name, IFNAMSIZ))
+ set_bit(i, inuse);
+ }
if (!sscanf(d->name, name, &i))
continue;
if (i < 0 || i >= max_netdevices)
*/
thread = READ_ONCE(napi->thread);
if (thread) {
+ /* Avoid doing set_bit() if the thread is in
+ * INTERRUPTIBLE state, cause napi_thread_wait()
+ * makes sure to proceed with napi polling
+ * if the thread is explicitly woken from here.
+ */
+ if (READ_ONCE(thread->state) != TASK_INTERRUPTIBLE)
+ set_bit(NAPI_STATE_SCHED_THREADED, &napi->state);
wake_up_process(thread);
return;
}
NAPI_GRO_CB(skb)->frag0_len = 0;
if (!skb_headlen(skb) && pinfo->nr_frags &&
- !PageHighMem(skb_frag_page(frag0))) {
+ !PageHighMem(skb_frag_page(frag0)) &&
+ (!NET_IP_ALIGN || !(skb_frag_off(frag0) & 3))) {
NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int,
skb_frag_size(frag0),
WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED));
new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED |
+ NAPIF_STATE_SCHED_THREADED |
NAPIF_STATE_PREFER_BUSY_POLL);
/* If STATE_MISSED was set, leave STATE_SCHED set,
static int napi_thread_wait(struct napi_struct *napi)
{
+ bool woken = false;
+
set_current_state(TASK_INTERRUPTIBLE);
- while (!kthread_should_stop() && !napi_disable_pending(napi)) {
- if (test_bit(NAPI_STATE_SCHED, &napi->state)) {
+ while (!kthread_should_stop()) {
+ /* Testing SCHED_THREADED bit here to make sure the current
+ * kthread owns this napi and could poll on this napi.
+ * Testing SCHED bit is not enough because SCHED bit might be
+ * set by some other busy poll thread or by napi_disable().
+ */
+ if (test_bit(NAPI_STATE_SCHED_THREADED, &napi->state) || woken) {
WARN_ON(!list_empty(&napi->poll_list));
__set_current_state(TASK_RUNNING);
return 0;
}
schedule();
+ /* woken being true indicates this thread owns this napi. */
+ woken = true;
set_current_state(TASK_INTERRUPTIBLE);
}
__set_current_state(TASK_RUNNING);
+
return -1;
}
continue;
/* Leave virtual devices for the generic cleanup */
- if (dev->rtnl_link_ops)
+ if (dev->rtnl_link_ops && !dev->rtnl_link_ops->netns_refund)
continue;
/* Push remaining network devices to init_net */
return 0;
err_module_put:
+ for_each_possible_cpu(cpu) {
+ struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu);
+ struct sk_buff *skb;
+
+ del_timer_sync(&hw_data->send_timer);
+ cancel_work_sync(&hw_data->dm_alert_work);
+ while ((skb = __skb_dequeue(&hw_data->drop_queue))) {
+ struct devlink_trap_metadata *hw_metadata;
+
+ hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata;
+ net_dm_hw_metadata_free(hw_metadata);
+ consume_skb(skb);
+ }
+ }
module_put(THIS_MODULE);
return rc;
}
err_unregister_trace:
unregister_trace_kfree_skb(ops->kfree_skb_probe, NULL);
err_module_put:
+ for_each_possible_cpu(cpu) {
+ struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu);
+ struct sk_buff *skb;
+
+ del_timer_sync(&data->send_timer);
+ cancel_work_sync(&data->dm_alert_work);
+ while ((skb = __skb_dequeue(&data->drop_queue)))
+ consume_skb(skb);
+ }
module_put(THIS_MODULE);
return rc;
}
}
EXPORT_SYMBOL(__dst_destroy_metrics_generic);
-static struct dst_ops md_dst_ops = {
- .family = AF_UNSPEC,
-};
+struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie)
+{
+ return NULL;
+}
-static int dst_md_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb)
+u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old)
{
- WARN_ONCE(1, "Attempting to call output on metadata dst\n");
- kfree_skb(skb);
- return 0;
+ return NULL;
}
-static int dst_md_discard(struct sk_buff *skb)
+struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst,
+ struct sk_buff *skb,
+ const void *daddr)
{
- WARN_ONCE(1, "Attempting to call input on metadata dst\n");
- kfree_skb(skb);
- return 0;
+ return NULL;
+}
+
+void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
+ struct sk_buff *skb, u32 mtu,
+ bool confirm_neigh)
+{
+}
+EXPORT_SYMBOL_GPL(dst_blackhole_update_pmtu);
+
+void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
+ struct sk_buff *skb)
+{
+}
+EXPORT_SYMBOL_GPL(dst_blackhole_redirect);
+
+unsigned int dst_blackhole_mtu(const struct dst_entry *dst)
+{
+ unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+ return mtu ? : dst->dev->mtu;
}
+EXPORT_SYMBOL_GPL(dst_blackhole_mtu);
+
+static struct dst_ops dst_blackhole_ops = {
+ .family = AF_UNSPEC,
+ .neigh_lookup = dst_blackhole_neigh_lookup,
+ .check = dst_blackhole_check,
+ .cow_metrics = dst_blackhole_cow_metrics,
+ .update_pmtu = dst_blackhole_update_pmtu,
+ .redirect = dst_blackhole_redirect,
+ .mtu = dst_blackhole_mtu,
+};
static void __metadata_dst_init(struct metadata_dst *md_dst,
enum metadata_type type, u8 optslen)
-
{
struct dst_entry *dst;
dst = &md_dst->dst;
- dst_init(dst, &md_dst_ops, NULL, 1, DST_OBSOLETE_NONE,
+ dst_init(dst, &dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE,
DST_METADATA | DST_NOCOUNT);
-
- dst->input = dst_md_discard;
- dst->output = dst_md_discard_out;
-
memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst));
md_dst->type = type;
}
if (unlikely(flags & ~(BPF_MTU_CHK_SEGS)))
return -EINVAL;
- if (unlikely(flags & BPF_MTU_CHK_SEGS && len_diff))
+ if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len)))
return -EINVAL;
dev = __dev_via_ifindex(dev, ifindex);
mtu = READ_ONCE(dev->mtu);
dev_len = mtu + dev->hard_header_len;
- skb_len = skb->len + len_diff; /* minus result pass check */
+
+ /* If set use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */
+ skb_len = *mtu_len ? *mtu_len + dev->hard_header_len : skb->len;
+
+ skb_len += len_diff; /* minus result pass check */
if (skb_len <= dev_len) {
ret = BPF_MTU_CHK_RET_SUCCESS;
goto out;
/* Add L2-header as dev MTU is L3 size */
dev_len = mtu + dev->hard_header_len;
+ /* Use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */
+ if (*mtu_len)
+ xdp_len = *mtu_len + dev->hard_header_len;
+
xdp_len += len_diff; /* minus result pass check */
if (xdp_len > dev_len)
ret = BPF_MTU_CHK_RET_FRAG_NEEDED;
* avoid confusion with packets without such field
*/
if (icmp_has_id(ih->type))
- key_icmp->id = ih->un.echo.id ? : 1;
+ key_icmp->id = ih->un.echo.id ? ntohs(ih->un.echo.id) : 1;
else
key_icmp->id = 0;
}
* we can reinject the packet there.
*/
n2 = NULL;
- if (dst) {
+ if (dst && dst->obsolete != DST_OBSOLETE_DEAD) {
n2 = dst_neigh_lookup_skb(dst, skb);
if (n2)
n1 = n2;
out_err:
cb->args[1] = idx;
cb->args[0] = h;
- cb->seq = net->dev_base_seq;
+ cb->seq = tgt_net->dev_base_seq;
nl_dump_check_consistent(cb, nlmsg_hdr(skb));
if (netnsid >= 0)
put_net(tgt_net);
BUG_ON(!(af_ops = rtnl_af_lookup(nla_type(af))));
- err = af_ops->set_link_af(dev, af);
+ err = af_ops->set_link_af(dev, af, extack);
if (err < 0) {
rcu_read_unlock();
goto errout;
struct ts_state state;
unsigned int ret;
+ BUILD_BUG_ON(sizeof(struct skb_seq_state) > sizeof(state.cb));
+
config->get_next_block = skb_ts_get_next_block;
config->finish = skb_ts_finish;
if (unlikely(!msg))
return -EAGAIN;
sk_msg_init(msg);
+ skb_set_owner_r(skb, sk);
return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
}
{
switch (verdict) {
case __SK_REDIRECT:
- skb_set_owner_r(skb, sk);
sk_psock_skb_redirect(skb);
break;
case __SK_PASS:
rcu_read_lock();
prog = READ_ONCE(psock->progs.skb_verdict);
if (likely(prog)) {
- /* We skip full set_owner_r here because if we do a SK_PASS
- * or SK_DROP we can skip skb memory accounting and use the
- * TLS context.
- */
skb->sk = psock->sk;
tcp_skb_bpf_redirect_clear(skb);
ret = sk_psock_bpf_run(psock, prog, skb);
kfree_skb(skb);
goto out;
}
- skb_set_owner_r(skb, sk);
prog = READ_ONCE(psock->progs.skb_verdict);
if (likely(prog)) {
+ skb->sk = sk;
tcp_skb_bpf_redirect_clear(skb);
ret = sk_psock_bpf_run(psock, prog, skb);
ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
+ skb->sk = NULL;
}
sk_psock_verdict_apply(psock, skb, ret);
out:
kfree_skb(skb);
goto out;
}
- skb_set_owner_r(skb, sk);
prog = READ_ONCE(psock->progs.skb_verdict);
if (likely(prog)) {
+ skb->sk = sk;
tcp_skb_bpf_redirect_clear(skb);
ret = sk_psock_bpf_run(psock, prog, skb);
ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
+ skb->sk = NULL;
}
sk_psock_verdict_apply(psock, skb, ret);
out:
if (skb_is_tcp_pure_ack(skb))
return;
- if (can_skb_orphan_partial(skb)) {
- struct sock *sk = skb->sk;
-
- if (refcount_inc_not_zero(&sk->sk_refcnt)) {
- WARN_ON(refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc));
- skb->destructor = sock_efree;
- }
- } else {
+ if (can_skb_orphan_partial(skb))
+ skb_set_owner_sk_safe(skb, skb->sk);
+ else
skb_orphan(skb);
- }
}
EXPORT_SYMBOL(skb_orphan_partial);
twsk_prot->twsk_slab = NULL;
}
+static int tw_prot_init(const struct proto *prot)
+{
+ struct timewait_sock_ops *twsk_prot = prot->twsk_prot;
+
+ if (!twsk_prot)
+ return 0;
+
+ twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s",
+ prot->name);
+ if (!twsk_prot->twsk_slab_name)
+ return -ENOMEM;
+
+ twsk_prot->twsk_slab =
+ kmem_cache_create(twsk_prot->twsk_slab_name,
+ twsk_prot->twsk_obj_size, 0,
+ SLAB_ACCOUNT | prot->slab_flags,
+ NULL);
+ if (!twsk_prot->twsk_slab) {
+ pr_crit("%s: Can't create timewait sock SLAB cache!\n",
+ prot->name);
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
static void req_prot_cleanup(struct request_sock_ops *rsk_prot)
{
if (!rsk_prot)
if (req_prot_init(prot))
goto out_free_request_sock_slab;
- if (prot->twsk_prot != NULL) {
- prot->twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s", prot->name);
-
- if (prot->twsk_prot->twsk_slab_name == NULL)
- goto out_free_request_sock_slab;
-
- prot->twsk_prot->twsk_slab =
- kmem_cache_create(prot->twsk_prot->twsk_slab_name,
- prot->twsk_prot->twsk_obj_size,
- 0,
- SLAB_ACCOUNT |
- prot->slab_flags,
- NULL);
- if (prot->twsk_prot->twsk_slab == NULL)
- goto out_free_timewait_sock_slab;
- }
+ if (tw_prot_init(prot))
+ goto out_free_timewait_sock_slab;
}
mutex_lock(&proto_list_mutex);
/* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */
xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
page = virt_to_head_page(data);
- napi_direct &= !xdp_return_frame_no_direct();
+ if (napi_direct && xdp_return_frame_no_direct())
+ napi_direct = false;
page_pool_put_full_page(xa->page_pool, page, napi_direct);
rcu_read_unlock();
break;
if (!ipv6_unicast_destination(skb))
return 0; /* discard, don't send a reset here */
+ if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) {
+ __IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS);
+ return 0;
+ }
+
if (dccp_bad_service_code(sk, service)) {
dcb->dccpd_reset_code = DCCP_RESET_CODE_BAD_SERVICE_CODE;
goto drop;
config NET_DSA_TAG_OCELOT_8021Q
tristate "Tag driver for Ocelot family of switches, using VLAN"
+ depends on MSCC_OCELOT_SWITCH_LIB || \
+ (MSCC_OCELOT_SWITCH_LIB=n && COMPILE_TEST)
select NET_DSA_TAG_8021Q
help
Say Y or M if you want to enable support for tagging frames with a
list_for_each_entry(dp, &dst->ports, list) {
err = dsa_port_setup(dp);
- if (err)
+ if (err) {
+ dsa_port_devlink_teardown(dp);
+ dp->type = DSA_PORT_TYPE_UNUSED;
+ err = dsa_port_devlink_setup(dp);
+ if (err)
+ goto teardown;
continue;
+ }
}
return 0;
{
struct dsa_switch *ds = dp->ds;
struct dsa_switch_tree *dst = ds->dst;
+ const struct dsa_device_ops *tag_ops;
enum dsa_tag_protocol tag_protocol;
tag_protocol = dsa_get_tag_protocol(dp, master);
* nothing to do here.
*/
} else {
- dst->tag_ops = dsa_tag_driver_get(tag_protocol);
- if (IS_ERR(dst->tag_ops)) {
- if (PTR_ERR(dst->tag_ops) == -ENOPROTOOPT)
+ tag_ops = dsa_tag_driver_get(tag_protocol);
+ if (IS_ERR(tag_ops)) {
+ if (PTR_ERR(tag_ops) == -ENOPROTOOPT)
return -EPROBE_DEFER;
dev_warn(ds->dev, "No tagger for this switch\n");
dp->master = NULL;
- return PTR_ERR(dst->tag_ops);
+ return PTR_ERR(tag_ops);
}
+
+ dst->tag_ops = tag_ops;
}
dp->master = master;
void dsa_port_hsr_leave(struct dsa_port *dp, struct net_device *hsr);
extern const struct phylink_mac_ops dsa_port_phylink_mac_ops;
-static inline bool dsa_port_offloads_netdev(struct dsa_port *dp,
- struct net_device *dev)
+static inline bool dsa_port_offloads_bridge_port(struct dsa_port *dp,
+ struct net_device *dev)
{
/* Switchdev offloading can be configured on: */
*/
return true;
- if (dp->bridge_dev == dev)
- /* DSA ports connected to a bridge, and event was emitted
- * for the bridge.
- */
- return true;
-
if (dp->lag_dev == dev)
/* DSA ports connected to a bridge via a LAG */
return true;
return false;
}
+static inline bool dsa_port_offloads_bridge(struct dsa_port *dp,
+ struct net_device *bridge_dev)
+{
+ /* DSA ports connected to a bridge, and event was emitted
+ * for the bridge.
+ */
+ return dp->bridge_dev == bridge_dev;
+}
+
/* Returns true if any port of this tree offloads the given net_device */
-static inline bool dsa_tree_offloads_netdev(struct dsa_switch_tree *dst,
- struct net_device *dev)
+static inline bool dsa_tree_offloads_bridge_port(struct dsa_switch_tree *dst,
+ struct net_device *dev)
{
struct dsa_port *dp;
list_for_each_entry(dp, &dst->ports, list)
- if (dsa_port_offloads_netdev(dp, dev))
+ if (dsa_port_offloads_bridge_port(dp, dev))
return true;
return false;
struct dsa_port *dp = dsa_slave_to_port(dev);
int ret;
- if (!dsa_port_offloads_netdev(dp, attr->orig_dev))
- return -EOPNOTSUPP;
-
switch (attr->id) {
case SWITCHDEV_ATTR_ID_PORT_STP_STATE:
+ if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev))
+ return -EOPNOTSUPP;
+
ret = dsa_port_set_state(dp, attr->u.stp_state);
break;
case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING:
+ if (!dsa_port_offloads_bridge(dp, attr->orig_dev))
+ return -EOPNOTSUPP;
+
ret = dsa_port_vlan_filtering(dp, attr->u.vlan_filtering,
extack);
break;
case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME:
+ if (!dsa_port_offloads_bridge(dp, attr->orig_dev))
+ return -EOPNOTSUPP;
+
ret = dsa_port_ageing_time(dp, attr->u.ageing_time);
break;
case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS:
+ if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev))
+ return -EOPNOTSUPP;
+
ret = dsa_port_pre_bridge_flags(dp, attr->u.brport_flags,
extack);
break;
case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS:
+ if (!dsa_port_offloads_bridge_port(dp, attr->orig_dev))
+ return -EOPNOTSUPP;
+
ret = dsa_port_bridge_flags(dp, attr->u.brport_flags, extack);
break;
case SWITCHDEV_ATTR_ID_BRIDGE_MROUTER:
+ if (!dsa_port_offloads_bridge(dp, attr->orig_dev))
+ return -EOPNOTSUPP;
+
ret = dsa_port_mrouter(dp->cpu_dp, attr->u.mrouter, extack);
break;
default:
struct switchdev_obj_port_vlan vlan;
int err;
- if (!dsa_port_offloads_netdev(dp, obj->orig_dev))
- return -EOPNOTSUPP;
-
if (dsa_port_skip_vlan_configuration(dp)) {
NL_SET_ERR_MSG_MOD(extack, "skipping configuration of VLAN");
return 0;
switch (obj->id) {
case SWITCHDEV_OBJ_ID_PORT_MDB:
- if (!dsa_port_offloads_netdev(dp, obj->orig_dev))
+ if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev))
return -EOPNOTSUPP;
+
err = dsa_port_mdb_add(dp, SWITCHDEV_OBJ_PORT_MDB(obj));
break;
case SWITCHDEV_OBJ_ID_HOST_MDB:
+ if (!dsa_port_offloads_bridge(dp, obj->orig_dev))
+ return -EOPNOTSUPP;
+
/* DSA can directly translate this to a normal MDB add,
* but on the CPU port.
*/
err = dsa_port_mdb_add(dp->cpu_dp, SWITCHDEV_OBJ_PORT_MDB(obj));
break;
case SWITCHDEV_OBJ_ID_PORT_VLAN:
+ if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev))
+ return -EOPNOTSUPP;
+
err = dsa_slave_vlan_add(dev, obj, extack);
break;
case SWITCHDEV_OBJ_ID_MRP:
- if (!dsa_port_offloads_netdev(dp, obj->orig_dev))
+ if (!dsa_port_offloads_bridge(dp, obj->orig_dev))
return -EOPNOTSUPP;
+
err = dsa_port_mrp_add(dp, SWITCHDEV_OBJ_MRP(obj));
break;
case SWITCHDEV_OBJ_ID_RING_ROLE_MRP:
- if (!dsa_port_offloads_netdev(dp, obj->orig_dev))
+ if (!dsa_port_offloads_bridge(dp, obj->orig_dev))
return -EOPNOTSUPP;
+
err = dsa_port_mrp_add_ring_role(dp,
SWITCHDEV_OBJ_RING_ROLE_MRP(obj));
break;
struct switchdev_obj_port_vlan *vlan;
int err;
- if (!dsa_port_offloads_netdev(dp, obj->orig_dev))
- return -EOPNOTSUPP;
-
if (dsa_port_skip_vlan_configuration(dp))
return 0;
switch (obj->id) {
case SWITCHDEV_OBJ_ID_PORT_MDB:
- if (!dsa_port_offloads_netdev(dp, obj->orig_dev))
+ if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev))
return -EOPNOTSUPP;
+
err = dsa_port_mdb_del(dp, SWITCHDEV_OBJ_PORT_MDB(obj));
break;
case SWITCHDEV_OBJ_ID_HOST_MDB:
+ if (!dsa_port_offloads_bridge(dp, obj->orig_dev))
+ return -EOPNOTSUPP;
+
/* DSA can directly translate this to a normal MDB add,
* but on the CPU port.
*/
err = dsa_port_mdb_del(dp->cpu_dp, SWITCHDEV_OBJ_PORT_MDB(obj));
break;
case SWITCHDEV_OBJ_ID_PORT_VLAN:
+ if (!dsa_port_offloads_bridge_port(dp, obj->orig_dev))
+ return -EOPNOTSUPP;
+
err = dsa_slave_vlan_del(dev, obj);
break;
case SWITCHDEV_OBJ_ID_MRP:
- if (!dsa_port_offloads_netdev(dp, obj->orig_dev))
+ if (!dsa_port_offloads_bridge(dp, obj->orig_dev))
return -EOPNOTSUPP;
+
err = dsa_port_mrp_del(dp, SWITCHDEV_OBJ_MRP(obj));
break;
case SWITCHDEV_OBJ_ID_RING_ROLE_MRP:
- if (!dsa_port_offloads_netdev(dp, obj->orig_dev))
+ if (!dsa_port_offloads_bridge(dp, obj->orig_dev))
return -EOPNOTSUPP;
+
err = dsa_port_mrp_del_ring_role(dp,
SWITCHDEV_OBJ_RING_ROLE_MRP(obj));
break;
* other ports bridged with the LAG should be able to
* autonomously forward towards it.
*/
- if (dsa_tree_offloads_netdev(dp->ds->dst, dev))
+ if (dsa_tree_offloads_bridge_port(dp->ds->dst, dev))
return NOTIFY_DONE;
}
bool unset_vlan_filtering = br_vlan_enabled(info->br);
struct dsa_switch_tree *dst = ds->dst;
struct netlink_ext_ack extack = {0};
- int err, i;
+ int err, port;
if (dst->index == info->tree_index && ds->index == info->sw_index &&
ds->ops->port_bridge_join)
* it. That is a good thing, because that lets us handle it and also
* handle the case where the switch's vlan_filtering setting is global
* (not per port). When that happens, the correct moment to trigger the
- * vlan_filtering callback is only when the last port left this bridge.
+ * vlan_filtering callback is only when the last port leaves the last
+ * VLAN-aware bridge.
*/
if (unset_vlan_filtering && ds->vlan_filtering_is_global) {
- for (i = 0; i < ds->num_ports; i++) {
- if (i == info->port)
- continue;
- if (dsa_to_port(ds, i)->bridge_dev == info->br) {
+ for (port = 0; port < ds->num_ports; port++) {
+ struct net_device *bridge_dev;
+
+ bridge_dev = dsa_to_port(ds, port)->bridge_dev;
+
+ if (bridge_dev && br_vlan_enabled(bridge_dev)) {
unset_vlan_filtering = false;
break;
}
#define MTK_HDR_LEN 4
#define MTK_HDR_XMIT_UNTAGGED 0
#define MTK_HDR_XMIT_TAGGED_TPID_8100 1
+#define MTK_HDR_XMIT_TAGGED_TPID_88A8 2
#define MTK_HDR_RECV_SOURCE_PORT_MASK GENMASK(2, 0)
#define MTK_HDR_XMIT_DP_BIT_MASK GENMASK(5, 0)
#define MTK_HDR_XMIT_SA_DIS BIT(6)
struct net_device *dev)
{
struct dsa_port *dp = dsa_slave_to_port(dev);
+ u8 xmit_tpid;
u8 *mtk_tag;
- bool is_vlan_skb = true;
unsigned char *dest = eth_hdr(skb)->h_dest;
bool is_multicast_skb = is_multicast_ether_addr(dest) &&
!is_broadcast_ether_addr(dest);
* the both special and VLAN tag at the same time and then look up VLAN
* table with VID.
*/
- if (!skb_vlan_tagged(skb)) {
+ switch (skb->protocol) {
+ case htons(ETH_P_8021Q):
+ xmit_tpid = MTK_HDR_XMIT_TAGGED_TPID_8100;
+ break;
+ case htons(ETH_P_8021AD):
+ xmit_tpid = MTK_HDR_XMIT_TAGGED_TPID_88A8;
+ break;
+ default:
+ xmit_tpid = MTK_HDR_XMIT_UNTAGGED;
skb_push(skb, MTK_HDR_LEN);
memmove(skb->data, skb->data + MTK_HDR_LEN, 2 * ETH_ALEN);
- is_vlan_skb = false;
}
mtk_tag = skb->data + 2 * ETH_ALEN;
/* Mark tag attribute on special tag insertion to notify hardware
* whether that's a combined special tag with 802.1Q header.
*/
- mtk_tag[0] = is_vlan_skb ? MTK_HDR_XMIT_TAGGED_TPID_8100 :
- MTK_HDR_XMIT_UNTAGGED;
+ mtk_tag[0] = xmit_tpid;
mtk_tag[1] = (1 << dp->index) & MTK_HDR_XMIT_DP_BIT_MASK;
/* Disable SA learning for multicast frames */
mtk_tag[1] |= MTK_HDR_XMIT_SA_DIS;
/* Tag control information is kept for 802.1Q */
- if (!is_vlan_skb) {
+ if (xmit_tpid == MTK_HDR_XMIT_UNTAGGED) {
mtk_tag[2] = 0;
mtk_tag[3] = 0;
}
struct net_device *dev)
{
struct dsa_port *dp = dsa_slave_to_port(dev);
+ __be16 *p;
u8 *tag;
- u16 *p;
u16 out;
/* Pad out to at least 60 bytes */
- if (unlikely(eth_skb_pad(skb)))
- return NULL;
- if (skb_cow_head(skb, RTL4_A_HDR_LEN) < 0)
+ if (unlikely(__skb_put_padto(skb, ETH_ZLEN, false)))
return NULL;
netdev_dbg(dev, "add realtek tag to package to port %d\n",
tag = skb->data + 2 * ETH_ALEN;
/* Set Ethertype */
- p = (u16 *)tag;
+ p = (__be16 *)tag;
*p = htons(RTL4_A_ETHERTYPE);
out = (RTL4_A_PROTOCOL_RTL8366RB << 12) | (2 << 8);
- /* The lower bits is the port numer */
+ /* The lower bits is the port number */
out |= (u8)dp->index;
- p = (u16 *)(tag + 2);
+ p = (__be16 *)(tag + 2);
*p = htons(out);
return skb;
struct ethtool_channels channels = {};
struct ethnl_req_info req_info = {};
struct nlattr **tb = info->attrs;
- const struct nlattr *err_attr;
+ u32 err_attr, max_rx_in_use = 0;
const struct ethtool_ops *ops;
struct net_device *dev;
- u32 max_rx_in_use = 0;
int ret;
ret = ethnl_parse_header_dev_get(&req_info,
/* ensure new channel counts are within limits */
if (channels.rx_count > channels.max_rx)
- err_attr = tb[ETHTOOL_A_CHANNELS_RX_COUNT];
+ err_attr = ETHTOOL_A_CHANNELS_RX_COUNT;
else if (channels.tx_count > channels.max_tx)
- err_attr = tb[ETHTOOL_A_CHANNELS_TX_COUNT];
+ err_attr = ETHTOOL_A_CHANNELS_TX_COUNT;
else if (channels.other_count > channels.max_other)
- err_attr = tb[ETHTOOL_A_CHANNELS_OTHER_COUNT];
+ err_attr = ETHTOOL_A_CHANNELS_OTHER_COUNT;
else if (channels.combined_count > channels.max_combined)
- err_attr = tb[ETHTOOL_A_CHANNELS_COMBINED_COUNT];
+ err_attr = ETHTOOL_A_CHANNELS_COMBINED_COUNT;
else
- err_attr = NULL;
+ err_attr = 0;
if (err_attr) {
ret = -EINVAL;
- NL_SET_ERR_MSG_ATTR(info->extack, err_attr,
+ NL_SET_ERR_MSG_ATTR(info->extack, tb[err_attr],
"requested channel count exceeds maximum");
goto out_ops;
}
/* ensure there is at least one RX and one TX channel */
if (!channels.combined_count && !channels.rx_count)
- err_attr = tb[ETHTOOL_A_CHANNELS_RX_COUNT];
+ err_attr = ETHTOOL_A_CHANNELS_RX_COUNT;
else if (!channels.combined_count && !channels.tx_count)
- err_attr = tb[ETHTOOL_A_CHANNELS_TX_COUNT];
+ err_attr = ETHTOOL_A_CHANNELS_TX_COUNT;
else
- err_attr = NULL;
+ err_attr = 0;
if (err_attr) {
if (mod_combined)
- err_attr = tb[ETHTOOL_A_CHANNELS_COMBINED_COUNT];
+ err_attr = ETHTOOL_A_CHANNELS_COMBINED_COUNT;
ret = -EINVAL;
- NL_SET_ERR_MSG_ATTR(info->extack, err_attr, "requested channel counts would result in no RX or TX channel being configured");
+ NL_SET_ERR_MSG_ATTR(info->extack, tb[err_attr],
+ "requested channel counts would result in no RX or TX channel being configured");
goto out_ops;
}
__DEFINE_LINK_MODE_PARAMS(10000, KR, Full),
[ETHTOOL_LINK_MODE_10000baseR_FEC_BIT] = {
.speed = SPEED_10000,
+ .lanes = 1,
.duplex = DUPLEX_FULL,
},
__DEFINE_LINK_MODE_PARAMS(20000, MLD2, Full),
rtnl_unlock();
}
EXPORT_SYMBOL_GPL(ethtool_set_ethtool_phy_ops);
+
+void
+ethtool_params_from_link_mode(struct ethtool_link_ksettings *link_ksettings,
+ enum ethtool_link_mode_bit_indices link_mode)
+{
+ const struct link_mode_info *link_info;
+
+ if (WARN_ON_ONCE(link_mode >= __ETHTOOL_LINK_MODE_MASK_NBITS))
+ return;
+
+ link_info = &link_mode_params[link_mode];
+ link_ksettings->base.speed = link_info->speed;
+ link_ksettings->lanes = link_info->lanes;
+ link_ksettings->base.duplex = link_info->duplex;
+}
+EXPORT_SYMBOL_GPL(ethtool_params_from_link_mode);
ethnl_update_bool32(&eee.eee_enabled, tb[ETHTOOL_A_EEE_ENABLED], &mod);
ethnl_update_bool32(&eee.tx_lpi_enabled,
tb[ETHTOOL_A_EEE_TX_LPI_ENABLED], &mod);
- ethnl_update_bool32(&eee.tx_lpi_timer, tb[ETHTOOL_A_EEE_TX_LPI_TIMER],
- &mod);
+ ethnl_update_u32(&eee.tx_lpi_timer, tb[ETHTOOL_A_EEE_TX_LPI_TIMER],
+ &mod);
ret = 0;
if (!mod)
goto out_ops;
int __ethtool_get_link_ksettings(struct net_device *dev,
struct ethtool_link_ksettings *link_ksettings)
{
- const struct link_mode_info *link_info;
- int err;
-
ASSERT_RTNL();
if (!dev->ethtool_ops->get_link_ksettings)
return -EOPNOTSUPP;
memset(link_ksettings, 0, sizeof(*link_ksettings));
-
- link_ksettings->link_mode = -1;
- err = dev->ethtool_ops->get_link_ksettings(dev, link_ksettings);
- if (err)
- return err;
-
- if (link_ksettings->link_mode != -1) {
- link_info = &link_mode_params[link_ksettings->link_mode];
- link_ksettings->base.speed = link_info->speed;
- link_ksettings->lanes = link_info->lanes;
- link_ksettings->base.duplex = link_info->duplex;
- }
-
- return 0;
+ return dev->ethtool_ops->get_link_ksettings(dev, link_ksettings);
}
EXPORT_SYMBOL(__ethtool_get_link_ksettings);
/**
* ethnl_put_strz() - put string attribute with fixed size string
- * @skb: skb with the message
- * @attrype: attribute type
- * @s: ETH_GSTRING_LEN sized string (may not be null terminated)
+ * @skb: skb with the message
+ * @attrtype: attribute type
+ * @s: ETH_GSTRING_LEN sized string (may not be null terminated)
*
* Puts an attribute with null terminated string from @s into the message.
*
if (!dev->ethtool_ops->get_pauseparam)
return -EOPNOTSUPP;
+ ethtool_stats_init((u64 *)&data->pausestat,
+ sizeof(data->pausestat) / 8);
+
ret = ethnl_ops_begin(dev);
if (ret < 0)
return ret;
dev->ethtool_ops->get_pauseparam(dev, &data->pauseparam);
if (req_base->flags & ETHTOOL_FLAG_STATS &&
- dev->ethtool_ops->get_pause_stats) {
- ethtool_stats_init((u64 *)&data->pausestat,
- sizeof(data->pausestat) / 8);
+ dev->ethtool_ops->get_pause_stats)
dev->ethtool_ops->get_pause_stats(dev, &data->pausestat);
- }
ethnl_ops_complete(dev);
return 0;
master = hsr_port_get_hsr(hsr, HSR_PT_MASTER);
if (master) {
skb->dev = master->dev;
+ skb_reset_mac_header(skb);
hsr_forward_skb(skb, master);
} else {
atomic_long_inc(&dev->tx_dropped);
{
struct hsr_frame_info frame;
- if (skb_mac_header(skb) != skb->data) {
- WARN_ONCE(1, "%s:%d: Malformed frame (port_src %s)\n",
- __FILE__, __LINE__, port->dev->name);
- goto out_drop;
- }
-
if (fill_frame_info(&frame, skb, port) < 0)
goto out_drop;
desc->mode = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_KEY_MODE]);
if (desc->mode == IEEE802154_SCF_KEY_IMPLICIT) {
- if (!info->attrs[IEEE802154_ATTR_PAN_ID] &&
- !(info->attrs[IEEE802154_ATTR_SHORT_ADDR] ||
- info->attrs[IEEE802154_ATTR_HW_ADDR]))
+ if (!info->attrs[IEEE802154_ATTR_PAN_ID])
return -EINVAL;
desc->device_addr.pan_id = nla_get_shortaddr(info->attrs[IEEE802154_ATTR_PAN_ID]);
desc->device_addr.mode = IEEE802154_ADDR_SHORT;
desc->device_addr.short_addr = nla_get_shortaddr(info->attrs[IEEE802154_ATTR_SHORT_ADDR]);
} else {
+ if (!info->attrs[IEEE802154_ATTR_HW_ADDR])
+ return -EINVAL;
+
desc->device_addr.mode = IEEE802154_ADDR_LONG;
desc->device_addr.extended_addr = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_HW_ADDR]);
}
goto nla_put_failure;
#ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL
+ if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
+ goto out;
+
if (nl802154_get_llsec_params(msg, rdev, wpan_dev) < 0)
goto nla_put_failure;
+
+out:
#endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */
genlmsg_end(msg, hdr);
u32 changed = 0;
int ret;
+ if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
+ return -EOPNOTSUPP;
+
if (info->attrs[NL802154_ATTR_SEC_ENABLED]) {
u8 enabled;
if (err)
return err;
+ if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) {
+ err = skb->len;
+ goto out_err;
+ }
+
if (!wpan_dev->netdev) {
err = -EINVAL;
goto out_err;
struct ieee802154_llsec_key_id id = { };
u32 commands[NL802154_CMD_FRAME_NR_IDS / 32] = { };
- if (nla_parse_nested_deprecated(attrs, NL802154_KEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_KEY], nl802154_key_policy, info->extack))
+ if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
+ return -EOPNOTSUPP;
+
+ if (!info->attrs[NL802154_ATTR_SEC_KEY] ||
+ nla_parse_nested_deprecated(attrs, NL802154_KEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_KEY], nl802154_key_policy, info->extack))
return -EINVAL;
if (!attrs[NL802154_KEY_ATTR_USAGE_FRAMES] ||
struct nlattr *attrs[NL802154_KEY_ATTR_MAX + 1];
struct ieee802154_llsec_key_id id;
- if (nla_parse_nested_deprecated(attrs, NL802154_KEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_KEY], nl802154_key_policy, info->extack))
+ if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
+ return -EOPNOTSUPP;
+
+ if (!info->attrs[NL802154_ATTR_SEC_KEY] ||
+ nla_parse_nested_deprecated(attrs, NL802154_KEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_KEY], nl802154_key_policy, info->extack))
return -EINVAL;
if (ieee802154_llsec_parse_key_id(attrs[NL802154_KEY_ATTR_ID], &id) < 0)
if (err)
return err;
+ if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) {
+ err = skb->len;
+ goto out_err;
+ }
+
if (!wpan_dev->netdev) {
err = -EINVAL;
goto out_err;
struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
struct ieee802154_llsec_device dev_desc;
+ if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
+ return -EOPNOTSUPP;
+
if (ieee802154_llsec_parse_device(info->attrs[NL802154_ATTR_SEC_DEVICE],
&dev_desc) < 0)
return -EINVAL;
struct nlattr *attrs[NL802154_DEV_ATTR_MAX + 1];
__le64 extended_addr;
- if (nla_parse_nested_deprecated(attrs, NL802154_DEV_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVICE], nl802154_dev_policy, info->extack))
+ if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
+ return -EOPNOTSUPP;
+
+ if (!info->attrs[NL802154_ATTR_SEC_DEVICE] ||
+ nla_parse_nested_deprecated(attrs, NL802154_DEV_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVICE], nl802154_dev_policy, info->extack))
return -EINVAL;
if (!attrs[NL802154_DEV_ATTR_EXTENDED_ADDR])
if (err)
return err;
+ if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) {
+ err = skb->len;
+ goto out_err;
+ }
+
if (!wpan_dev->netdev) {
err = -EINVAL;
goto out_err;
struct ieee802154_llsec_device_key key;
__le64 extended_addr;
+ if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
+ return -EOPNOTSUPP;
+
if (!info->attrs[NL802154_ATTR_SEC_DEVKEY] ||
nla_parse_nested_deprecated(attrs, NL802154_DEVKEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVKEY], nl802154_devkey_policy, info->extack) < 0)
return -EINVAL;
struct ieee802154_llsec_device_key key;
__le64 extended_addr;
- if (nla_parse_nested_deprecated(attrs, NL802154_DEVKEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVKEY], nl802154_devkey_policy, info->extack))
+ if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
+ return -EOPNOTSUPP;
+
+ if (!info->attrs[NL802154_ATTR_SEC_DEVKEY] ||
+ nla_parse_nested_deprecated(attrs, NL802154_DEVKEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVKEY], nl802154_devkey_policy, info->extack))
return -EINVAL;
if (!attrs[NL802154_DEVKEY_ATTR_EXTENDED_ADDR])
if (err)
return err;
+ if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) {
+ err = skb->len;
+ goto out_err;
+ }
+
if (!wpan_dev->netdev) {
err = -EINVAL;
goto out_err;
struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
struct ieee802154_llsec_seclevel sl;
+ if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
+ return -EOPNOTSUPP;
+
if (llsec_parse_seclevel(info->attrs[NL802154_ATTR_SEC_LEVEL],
&sl) < 0)
return -EINVAL;
struct wpan_dev *wpan_dev = dev->ieee802154_ptr;
struct ieee802154_llsec_seclevel sl;
+ if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR)
+ return -EOPNOTSUPP;
+
if (!info->attrs[NL802154_ATTR_SEC_LEVEL] ||
llsec_parse_seclevel(info->attrs[NL802154_ATTR_SEC_LEVEL],
&sl) < 0)
#define NL802154_FLAG_NEED_NETDEV 0x02
#define NL802154_FLAG_NEED_RTNL 0x04
#define NL802154_FLAG_CHECK_NETDEV_UP 0x08
-#define NL802154_FLAG_NEED_NETDEV_UP (NL802154_FLAG_NEED_NETDEV |\
- NL802154_FLAG_CHECK_NETDEV_UP)
#define NL802154_FLAG_NEED_WPAN_DEV 0x10
-#define NL802154_FLAG_NEED_WPAN_DEV_UP (NL802154_FLAG_NEED_WPAN_DEV |\
- NL802154_FLAG_CHECK_NETDEV_UP)
static int nl802154_pre_doit(const struct genl_ops *ops, struct sk_buff *skb,
struct genl_info *info)
}
kfree(AH_SKB_CB(skb)->tmp);
- xfrm_output_resume(skb, err);
+ xfrm_output_resume(skb->sk, skb, err);
}
static int ah_output(struct xfrm_state *x, struct sk_buff *skb)
ret_val = -ENOENT;
goto doi_remove_return;
}
- if (!refcount_dec_and_test(&doi_def->refcount)) {
- spin_unlock(&cipso_v4_doi_list_lock);
- ret_val = -EBUSY;
- goto doi_remove_return;
- }
list_del_rcu(&doi_def->list);
spin_unlock(&cipso_v4_doi_list_lock);
- cipso_v4_cache_invalidate();
- call_rcu(&doi_def->rcu, cipso_v4_doi_free_rcu);
+ cipso_v4_doi_putdef(doi_def);
ret_val = 0;
doi_remove_return:
if (!refcount_dec_and_test(&doi_def->refcount))
return;
- spin_lock(&cipso_v4_doi_list_lock);
- list_del_rcu(&doi_def->list);
- spin_unlock(&cipso_v4_doi_list_lock);
cipso_v4_cache_invalidate();
call_rcu(&doi_def->rcu, cipso_v4_doi_free_rcu);
{
buf[0] = IPOPT_CIPSO;
buf[1] = CIPSO_V4_HDR_LEN + len;
- *(__be32 *)&buf[2] = htonl(doi_def->doi);
+ put_unaligned_be32(doi_def->doi, &buf[2]);
}
/**
return 0;
}
-static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla)
+static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla,
+ struct netlink_ext_ack *extack)
{
struct in_device *in_dev = __in_dev_get_rcu(dev);
struct nlattr *a, *tb[IFLA_INET_MAX+1];
x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP)
esp_output_tail_tcp(x, skb);
else
- xfrm_output_resume(skb, err);
+ xfrm_output_resume(skb->sk, skb, err);
}
}
if ((!(skb->dev->gso_partial_features & NETIF_F_HW_ESP) &&
!(features & NETIF_F_HW_ESP)) || x->xso.dev != skb->dev)
- esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK);
+ esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK |
+ NETIF_F_SCTP_CRC);
else if (!(features & NETIF_F_HW_ESP_TX_CSUM) &&
!(skb->dev->gso_partial_features & NETIF_F_HW_ESP_TX_CSUM))
- esp_features = features & ~NETIF_F_CSUM_MASK;
+ esp_features = features & ~(NETIF_F_CSUM_MASK |
+ NETIF_F_SCTP_CRC);
xo->flags |= XFRM_GSO_SEGMENT;
ip_hdr(skb)->tot_len = htons(skb->len);
ip_send_check(ip_hdr(skb));
- if (hw_offload)
+ if (hw_offload) {
+ if (!skb_ext_add(skb, SKB_EXT_SEC_PATH))
+ return -ENOMEM;
+
+ xo = xfrm_offload(skb);
+ if (!xo)
+ return -EINVAL;
+
+ xo->flags |= XFRM_XMIT;
return 0;
+ }
err = esp_output_tail(x, skb, &esp);
if (err)
return found;
}
-void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req)
+bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req)
{
- if (reqsk_queue_unlink(req)) {
+ bool unlinked = reqsk_queue_unlink(req);
+
+ if (unlinked) {
reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
reqsk_put(req);
}
+ return unlinked;
}
EXPORT_SYMBOL(inet_csk_reqsk_queue_drop);
#define PEER_MAX_GC 32
/* Exported for sysctl_net_ipv4. */
-int inet_peer_threshold __read_mostly = 65536 + 128; /* start to throw entries more
+int inet_peer_threshold __read_mostly; /* start to throw entries more
* aggressively at this stage */
int inet_peer_minttl __read_mostly = 120 * HZ; /* TTL under high load: 120 sec */
int inet_peer_maxttl __read_mostly = 10 * 60 * HZ; /* usual time to live: 10 min */
/* Called from ip_output.c:ip_init */
void __init inet_initpeers(void)
{
- struct sysinfo si;
+ u64 nr_entries;
- /* Use the straight interface to information about memory. */
- si_meminfo(&si);
- /* The values below were suggested by Alexey Kuznetsov
- * <kuznet@ms2.inr.ac.ru>. I don't have any opinion about the values
- * myself. --SAW
- */
- if (si.totalram <= (32768*1024)/PAGE_SIZE)
- inet_peer_threshold >>= 1; /* max pool size about 1MB on IA32 */
- if (si.totalram <= (16384*1024)/PAGE_SIZE)
- inet_peer_threshold >>= 1; /* about 512KB */
- if (si.totalram <= (8192*1024)/PAGE_SIZE)
- inet_peer_threshold >>= 2; /* about 128KB */
+ /* 1% of physical memory */
+ nr_entries = div64_ul((u64)totalram_pages() << PAGE_SHIFT,
+ 100 * L1_CACHE_ALIGN(sizeof(struct inet_peer)));
+
+ inet_peer_threshold = clamp_val(nr_entries, 4096, 65536 + 128);
peer_cachep = kmem_cache_create("inet_peer_cache",
sizeof(struct inet_peer),
if (!skb_is_gso(skb) &&
(inner_iph->frag_off & htons(IP_DF)) &&
mtu < pkt_size) {
- memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
+ icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
return -E2BIG;
}
}
if (!skb_is_gso(skb) && mtu >= IPV6_MIN_MTU &&
mtu < pkt_size) {
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+ icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
return -E2BIG;
}
}
}
if (dst->flags & DST_XFRM_QUEUE)
- goto queued;
+ goto xmit;
if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) {
dev->stats.tx_carrier_errors++;
if (skb->len > mtu) {
skb_dst_update_pmtu_no_confirm(skb, mtu);
if (skb->protocol == htons(ETH_P_IP)) {
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
- htonl(mtu));
+ if (!(ip_hdr(skb)->frag_off & htons(IP_DF)))
+ goto xmit;
+ icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+ htonl(mtu));
} else {
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+ icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
}
dst_release(dst);
goto tx_error;
}
-queued:
+xmit:
skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev)));
skb_dst_set(skb, dst);
skb->dev = skb_dst(skb)->dev;
*/
static void __init ic_close_devs(void)
{
- struct net_device *selected_dev = ic_dev->dev;
+ struct net_device *selected_dev = ic_dev ? ic_dev->dev : NULL;
struct ic_device *d, *next;
struct net_device *dev;
next = ic_first_dev;
while ((d = next)) {
bool bring_down = (d != ic_dev);
- struct net_device *lower_dev;
+ struct net_device *lower;
struct list_head *iter;
next = d->next;
dev = d->dev;
- netdev_for_each_lower_dev(selected_dev, lower_dev, iter) {
- if (dev == lower_dev) {
- bring_down = false;
- break;
+ if (selected_dev) {
+ netdev_for_each_lower_dev(selected_dev, lower, iter) {
+ if (dev == lower) {
+ bring_down = false;
+ break;
+ }
}
}
if (bring_down) {
local_bh_disable();
addend = xt_write_recseq_begin();
- private = rcu_access_pointer(table->private);
+ private = READ_ONCE(table->private); /* Address dependency. */
cpu = smp_processor_id();
table_base = private->entries;
jumpstack = (struct arpt_entry **)private->jumpstack[cpu];
{
unsigned int countersize;
struct xt_counters *counters;
- const struct xt_table_info *private = xt_table_get_private_protected(table);
+ const struct xt_table_info *private = table->private;
/* We need atomic snapshot of counters: rest doesn't change
* (other than comefrom, which userspace doesn't care
unsigned int off, num;
const struct arpt_entry *e;
struct xt_counters *counters;
- struct xt_table_info *private = xt_table_get_private_protected(table);
+ struct xt_table_info *private = table->private;
int ret = 0;
void *loc_cpu_entry;
t = xt_request_find_table_lock(net, NFPROTO_ARP, name);
if (!IS_ERR(t)) {
struct arpt_getinfo info;
- const struct xt_table_info *private = xt_table_get_private_protected(t);
+ const struct xt_table_info *private = t->private;
#ifdef CONFIG_COMPAT
struct xt_table_info tmp;
t = xt_find_table_lock(net, NFPROTO_ARP, get.name);
if (!IS_ERR(t)) {
- const struct xt_table_info *private = xt_table_get_private_protected(t);
+ const struct xt_table_info *private = t->private;
if (get.size == private->size)
ret = copy_entries_to_user(private->size,
}
local_bh_disable();
- private = xt_table_get_private_protected(t);
+ private = t->private;
if (private->number != tmp.num_counters) {
ret = -EINVAL;
goto unlock_up_free;
if (!newinfo)
goto out_unlock;
+ memset(newinfo->entries, 0, size);
+
newinfo->number = compatr->num_entries;
for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
newinfo->hook_entry[i] = compatr->hook_entry[i];
void __user *userptr)
{
struct xt_counters *counters;
- const struct xt_table_info *private = xt_table_get_private_protected(table);
+ const struct xt_table_info *private = table->private;
void __user *pos;
unsigned int size;
int ret = 0;
xt_compat_lock(NFPROTO_ARP);
t = xt_find_table_lock(net, NFPROTO_ARP, get.name);
if (!IS_ERR(t)) {
- const struct xt_table_info *private = xt_table_get_private_protected(t);
+ const struct xt_table_info *private = t->private;
struct xt_table_info info;
ret = compat_table_info(private, &info);
return ret;
}
-void arpt_unregister_table(struct net *net, struct xt_table *table,
- const struct nf_hook_ops *ops)
+void arpt_unregister_table_pre_exit(struct net *net, struct xt_table *table,
+ const struct nf_hook_ops *ops)
{
nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
+}
+EXPORT_SYMBOL(arpt_unregister_table_pre_exit);
+
+void arpt_unregister_table(struct net *net, struct xt_table *table)
+{
__arpt_unregister_table(net, table);
}
return err;
}
+static void __net_exit arptable_filter_net_pre_exit(struct net *net)
+{
+ if (net->ipv4.arptable_filter)
+ arpt_unregister_table_pre_exit(net, net->ipv4.arptable_filter,
+ arpfilter_ops);
+}
+
static void __net_exit arptable_filter_net_exit(struct net *net)
{
if (!net->ipv4.arptable_filter)
return;
- arpt_unregister_table(net, net->ipv4.arptable_filter, arpfilter_ops);
+ arpt_unregister_table(net, net->ipv4.arptable_filter);
net->ipv4.arptable_filter = NULL;
}
static struct pernet_operations arptable_filter_net_ops = {
.exit = arptable_filter_net_exit,
+ .pre_exit = arptable_filter_net_pre_exit,
};
static int __init arptable_filter_init(void)
WARN_ON(!(table->valid_hooks & (1 << hook)));
local_bh_disable();
addend = xt_write_recseq_begin();
- private = rcu_access_pointer(table->private);
+ private = READ_ONCE(table->private); /* Address dependency. */
cpu = smp_processor_id();
table_base = private->entries;
jumpstack = (struct ipt_entry **)private->jumpstack[cpu];
{
unsigned int countersize;
struct xt_counters *counters;
- const struct xt_table_info *private = xt_table_get_private_protected(table);
+ const struct xt_table_info *private = table->private;
/* We need atomic snapshot of counters: rest doesn't change
(other than comefrom, which userspace doesn't care
unsigned int off, num;
const struct ipt_entry *e;
struct xt_counters *counters;
- const struct xt_table_info *private = xt_table_get_private_protected(table);
+ const struct xt_table_info *private = table->private;
int ret = 0;
const void *loc_cpu_entry;
t = xt_request_find_table_lock(net, AF_INET, name);
if (!IS_ERR(t)) {
struct ipt_getinfo info;
- const struct xt_table_info *private = xt_table_get_private_protected(t);
+ const struct xt_table_info *private = t->private;
#ifdef CONFIG_COMPAT
struct xt_table_info tmp;
t = xt_find_table_lock(net, AF_INET, get.name);
if (!IS_ERR(t)) {
- const struct xt_table_info *private = xt_table_get_private_protected(t);
+ const struct xt_table_info *private = t->private;
if (get.size == private->size)
ret = copy_entries_to_user(private->size,
t, uptr->entrytable);
}
local_bh_disable();
- private = xt_table_get_private_protected(t);
+ private = t->private;
if (private->number != tmp.num_counters) {
ret = -EINVAL;
goto unlock_up_free;
if (!newinfo)
goto out_unlock;
+ memset(newinfo->entries, 0, size);
+
newinfo->number = compatr->num_entries;
for (i = 0; i < NF_INET_NUMHOOKS; i++) {
newinfo->hook_entry[i] = compatr->hook_entry[i];
void __user *userptr)
{
struct xt_counters *counters;
- const struct xt_table_info *private = xt_table_get_private_protected(table);
+ const struct xt_table_info *private = table->private;
void __user *pos;
unsigned int size;
int ret = 0;
xt_compat_lock(AF_INET);
t = xt_find_table_lock(net, AF_INET, get.name);
if (!IS_ERR(t)) {
- const struct xt_table_info *private = xt_table_get_private_protected(t);
+ const struct xt_table_info *private = t->private;
struct xt_table_info info;
ret = compat_table_info(private, &info);
if (!ret && get.size == info.size)
/* rtnl */
/* remove all nexthops tied to a device being deleted */
-static void nexthop_flush_dev(struct net_device *dev)
+static void nexthop_flush_dev(struct net_device *dev, unsigned long event)
{
unsigned int hash = nh_dev_hashfn(dev->ifindex);
struct net *net = dev_net(dev);
if (nhi->fib_nhc.nhc_dev != dev)
continue;
+ if (nhi->reject_nh &&
+ (event == NETDEV_DOWN || event == NETDEV_CHANGE))
+ continue;
+
remove_nexthop(net, nhi->nh_parent, NULL);
}
}
switch (event) {
case NETDEV_DOWN:
case NETDEV_UNREGISTER:
- nexthop_flush_dev(dev);
+ nexthop_flush_dev(dev, event);
break;
case NETDEV_CHANGE:
if (!(dev_get_flags(dev) & (IFF_RUNNING | IFF_LOWER_UP)))
- nexthop_flush_dev(dev);
+ nexthop_flush_dev(dev, event);
break;
case NETDEV_CHANGEMTU:
info_ext = ptr;
return rth;
}
-static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie)
-{
- return NULL;
-}
-
-static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst)
-{
- unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
-
- return mtu ? : dst->dev->mtu;
-}
-
-static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
- struct sk_buff *skb, u32 mtu,
- bool confirm_neigh)
-{
-}
-
-static void ipv4_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
- struct sk_buff *skb)
-{
-}
-
-static u32 *ipv4_rt_blackhole_cow_metrics(struct dst_entry *dst,
- unsigned long old)
-{
- return NULL;
-}
-
static struct dst_ops ipv4_dst_blackhole_ops = {
- .family = AF_INET,
- .check = ipv4_blackhole_dst_check,
- .mtu = ipv4_blackhole_mtu,
- .default_advmss = ipv4_default_advmss,
- .update_pmtu = ipv4_rt_blackhole_update_pmtu,
- .redirect = ipv4_rt_blackhole_redirect,
- .cow_metrics = ipv4_rt_blackhole_cow_metrics,
- .neigh_lookup = ipv4_neigh_lookup,
+ .family = AF_INET,
+ .default_advmss = ipv4_default_advmss,
+ .neigh_lookup = ipv4_neigh_lookup,
+ .check = dst_blackhole_check,
+ .cow_metrics = dst_blackhole_cow_metrics,
+ .update_pmtu = dst_blackhole_update_pmtu,
+ .redirect = dst_blackhole_redirect,
+ .mtu = dst_blackhole_mtu,
};
struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig)
if (!table)
goto err_alloc;
- /* Update the variables to point into the current struct net */
- for (i = 0; i < ARRAY_SIZE(ipv4_net_table) - 1; i++)
- table[i].data += (void *)net - (void *)&init_net;
+ for (i = 0; i < ARRAY_SIZE(ipv4_net_table) - 1; i++) {
+ if (table[i].data) {
+ /* Update the variables to point into
+ * the current struct net
+ */
+ table[i].data += (void *)net - (void *)&init_net;
+ } else {
+ /* Entries without data pointer are global;
+ * Make them read-only in non-init_net ns
+ */
+ table[i].mode &= ~0222;
+ }
+ }
}
net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table);
break;
case TCP_QUEUE_SEQ:
- if (sk->sk_state != TCP_CLOSE)
+ if (sk->sk_state != TCP_CLOSE) {
err = -EPERM;
- else if (tp->repair_queue == TCP_SEND_QUEUE)
- WRITE_ONCE(tp->write_seq, val);
- else if (tp->repair_queue == TCP_RECV_QUEUE) {
- WRITE_ONCE(tp->rcv_nxt, val);
- WRITE_ONCE(tp->copied_seq, val);
- }
- else
+ } else if (tp->repair_queue == TCP_SEND_QUEUE) {
+ if (!tcp_rtx_queue_empty(sk))
+ err = -EPERM;
+ else
+ WRITE_ONCE(tp->write_seq, val);
+ } else if (tp->repair_queue == TCP_RECV_QUEUE) {
+ if (tp->rcv_nxt != tp->copied_seq) {
+ err = -EPERM;
+ } else {
+ WRITE_ONCE(tp->rcv_nxt, val);
+ WRITE_ONCE(tp->copied_seq, val);
+ }
+ } else {
err = -EINVAL;
+ }
break;
case TCP_REPAIR_OPTIONS:
if (get_user(len, optlen))
return -EFAULT;
- if (len < offsetofend(struct tcp_zerocopy_receive, length))
+ if (len < 0 ||
+ len < offsetofend(struct tcp_zerocopy_receive, length))
return -EINVAL;
if (unlikely(len > sizeof(zc))) {
err = check_zeroed_user(optval + sizeof(zc),
tcp_reset(sk, skb);
}
if (!fastopen) {
- inet_csk_reqsk_queue_drop(sk, req);
- __NET_INC_STATS(sock_net(sk), LINUX_MIB_EMBRYONICRSTS);
+ bool unlinked = inet_csk_reqsk_queue_drop(sk, req);
+
+ if (unlinked)
+ __NET_INC_STATS(sock_net(sk), LINUX_MIB_EMBRYONICRSTS);
+ *req_stolen = !unlinked;
}
return NULL;
}
val = up->gso_size;
break;
+ case UDP_GRO:
+ val = up->gro_enabled;
+ break;
+
/* The following two cannot be changed on UDP sockets, the return is
* always 0 (which corresponds to the full checksum coverage of UDP). */
case UDPLITE_SEND_CSCOV:
}
if (!sk || NAPI_GRO_CB(skb)->encap_mark ||
- (skb->ip_summed != CHECKSUM_PARTIAL &&
+ (uh->check && skb->ip_summed != CHECKSUM_PARTIAL &&
NAPI_GRO_CB(skb)->csum_cnt == 0 &&
!NAPI_GRO_CB(skb)->csum_valid) ||
!udp_sk(sk)->gro_receive)
return 0;
}
-static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token)
+static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token,
+ struct netlink_ext_ack *extack)
{
struct inet6_ifaddr *ifp;
struct net_device *dev = idev->dev;
if (!token)
return -EINVAL;
- if (dev->flags & (IFF_LOOPBACK | IFF_NOARP))
+
+ if (dev->flags & IFF_LOOPBACK) {
+ NL_SET_ERR_MSG_MOD(extack, "Device is loopback");
return -EINVAL;
- if (!ipv6_accept_ra(idev))
+ }
+
+ if (dev->flags & IFF_NOARP) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Device does not do neighbour discovery");
+ return -EINVAL;
+ }
+
+ if (!ipv6_accept_ra(idev)) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Router advertisement is disabled on device");
return -EINVAL;
- if (idev->cnf.rtr_solicits == 0)
+ }
+
+ if (idev->cnf.rtr_solicits == 0) {
+ NL_SET_ERR_MSG(extack,
+ "Router solicitation is disabled on device");
return -EINVAL;
+ }
write_lock_bh(&idev->lock);
return 0;
}
-static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla)
+static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla,
+ struct netlink_ext_ack *extack)
{
struct inet6_dev *idev = __in6_dev_get(dev);
struct nlattr *tb[IFLA_INET6_MAX + 1];
BUG();
if (tb[IFLA_INET6_TOKEN]) {
- err = inet6_set_iftoken(idev, nla_data(tb[IFLA_INET6_TOKEN]));
+ err = inet6_set_iftoken(idev, nla_data(tb[IFLA_INET6_TOKEN]),
+ extack);
if (err)
return err;
}
}
kfree(AH_SKB_CB(skb)->tmp);
- xfrm_output_resume(skb, err);
+ xfrm_output_resume(skb->sk, skb, err);
}
static int ah6_output(struct xfrm_state *x, struct sk_buff *skb)
static struct calipso_map_cache_bkt *calipso_cache;
+static void calipso_cache_invalidate(void);
+static void calipso_doi_putdef(struct calipso_doi *doi_def);
+
/* Label Mapping Cache Functions
*/
ret_val = -ENOENT;
goto doi_remove_return;
}
- if (!refcount_dec_and_test(&doi_def->refcount)) {
- spin_unlock(&calipso_doi_list_lock);
- ret_val = -EBUSY;
- goto doi_remove_return;
- }
list_del_rcu(&doi_def->list);
spin_unlock(&calipso_doi_list_lock);
- call_rcu(&doi_def->rcu, calipso_doi_free_rcu);
+ calipso_doi_putdef(doi_def);
ret_val = 0;
doi_remove_return:
if (!refcount_dec_and_test(&doi_def->refcount))
return;
- spin_lock(&calipso_doi_list_lock);
- list_del_rcu(&doi_def->list);
- spin_unlock(&calipso_doi_list_lock);
+ calipso_cache_invalidate();
call_rcu(&doi_def->rcu, calipso_doi_free_rcu);
}
x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP)
esp_output_tail_tcp(x, skb);
else
- xfrm_output_resume(skb, err);
+ xfrm_output_resume(skb->sk, skb, err);
}
}
skb->encap_hdr_csum = 1;
if (!(features & NETIF_F_HW_ESP) || x->xso.dev != skb->dev)
- esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK);
+ esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK |
+ NETIF_F_SCTP_CRC);
else if (!(features & NETIF_F_HW_ESP_TX_CSUM))
- esp_features = features & ~NETIF_F_CSUM_MASK;
+ esp_features = features & ~(NETIF_F_CSUM_MASK |
+ NETIF_F_SCTP_CRC);
xo->flags |= XFRM_GSO_SEGMENT;
ipv6_hdr(skb)->payload_len = htons(len);
- if (hw_offload)
+ if (hw_offload) {
+ if (!skb_ext_add(skb, SKB_EXT_SEC_PATH))
+ return -ENOMEM;
+
+ xo = xfrm_offload(skb);
+ if (!xo)
+ return -EINVAL;
+
+ xo->flags |= XFRM_XMIT;
return 0;
+ }
err = esp6_output_tail(x, skb, &esp);
if (err)
const struct net_device *dev;
if (rt->nh)
- fib6_nh = nexthop_fib6_nh(rt->nh);
+ fib6_nh = nexthop_fib6_nh_bh(rt->nh);
seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen);
tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset];
if (tel->encap_limit == 0) {
- icmpv6_send(skb, ICMPV6_PARAMPROB,
- ICMPV6_HDR_FIELD, offset + 2);
+ icmpv6_ndo_send(skb, ICMPV6_PARAMPROB,
+ ICMPV6_HDR_FIELD, offset + 2);
return -1;
}
*encap_limit = tel->encap_limit - 1;
if (err != 0) {
/* XXX: send ICMP error even if DF is not set. */
if (err == -EMSGSIZE)
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
- htonl(mtu));
+ icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+ htonl(mtu));
return -1;
}
&mtu, skb->protocol);
if (err != 0) {
if (err == -EMSGSIZE)
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+ icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
return -1;
}
/* XXX: send ICMP error even if DF is not set. */
if (err == -EMSGSIZE) {
if (skb->protocol == htons(ETH_P_IP))
- icmp_send(skb, ICMP_DEST_UNREACH,
- ICMP_FRAG_NEEDED, htonl(mtu));
+ icmp_ndo_send(skb, ICMP_DEST_UNREACH,
+ ICMP_FRAG_NEEDED, htonl(mtu));
else
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+ icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
}
goto tx_err;
if (ipv6_addr_is_multicast(&hdr->saddr))
goto err;
- /* While RFC4291 is not explicit about v4mapped addresses
- * in IPv6 headers, it seems clear linux dual-stack
- * model can not deal properly with these.
- * Security models could be fooled by ::ffff:127.0.0.1 for example.
- *
- * https://tools.ietf.org/html/draft-itojun-v6ops-v4mapped-harmful-02
- */
- if (ipv6_addr_v4mapped(&hdr->saddr))
- goto err;
-
skb->transport_header = skb->network_header + sizeof(*hdr);
IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
tel = (void *)&skb_network_header(skb)[offset];
if (tel->encap_limit == 0) {
- icmpv6_send(skb, ICMPV6_PARAMPROB,
- ICMPV6_HDR_FIELD, offset + 2);
+ icmpv6_ndo_send(skb, ICMPV6_PARAMPROB,
+ ICMPV6_HDR_FIELD, offset + 2);
return -1;
}
encap_limit = tel->encap_limit - 1;
if (err == -EMSGSIZE)
switch (protocol) {
case IPPROTO_IPIP:
- icmp_send(skb, ICMP_DEST_UNREACH,
- ICMP_FRAG_NEEDED, htonl(mtu));
+ icmp_ndo_send(skb, ICMP_DEST_UNREACH,
+ ICMP_FRAG_NEEDED, htonl(mtu));
break;
case IPPROTO_IPV6:
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+ icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
break;
default:
break;
t = rtnl_dereference(t->next);
}
}
+
+ t = rtnl_dereference(ip6n->tnls_wc[0]);
+ while (t) {
+ /* If dev is in the same netns, it has already
+ * been added to the list by the previous loop.
+ */
+ if (!net_eq(dev_net(t->dev), net))
+ unregister_netdevice_queue(t->dev, list);
+ t = rtnl_dereference(t->next);
+ }
}
static int __net_init ip6_tnl_init_net(struct net *net)
}
if (dst->flags & DST_XFRM_QUEUE)
- goto queued;
+ goto xmit;
x = dst->xfrm;
if (!vti6_state_check(x, &t->parms.raddr, &t->parms.laddr))
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+ icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
} else {
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
- htonl(mtu));
+ if (!(ip_hdr(skb)->frag_off & htons(IP_DF)))
+ goto xmit;
+ icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+ htonl(mtu));
}
err = -EMSGSIZE;
goto tx_err_dst_release;
}
-queued:
+xmit:
skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev)));
skb_dst_set(skb, dst);
skb->dev = skb_dst(skb)->dev;
local_bh_disable();
addend = xt_write_recseq_begin();
- private = rcu_access_pointer(table->private);
+ private = READ_ONCE(table->private); /* Address dependency. */
cpu = smp_processor_id();
table_base = private->entries;
jumpstack = (struct ip6t_entry **)private->jumpstack[cpu];
{
unsigned int countersize;
struct xt_counters *counters;
- const struct xt_table_info *private = xt_table_get_private_protected(table);
+ const struct xt_table_info *private = table->private;
/* We need atomic snapshot of counters: rest doesn't change
(other than comefrom, which userspace doesn't care
unsigned int off, num;
const struct ip6t_entry *e;
struct xt_counters *counters;
- const struct xt_table_info *private = xt_table_get_private_protected(table);
+ const struct xt_table_info *private = table->private;
int ret = 0;
const void *loc_cpu_entry;
t = xt_request_find_table_lock(net, AF_INET6, name);
if (!IS_ERR(t)) {
struct ip6t_getinfo info;
- const struct xt_table_info *private = xt_table_get_private_protected(t);
+ const struct xt_table_info *private = t->private;
#ifdef CONFIG_COMPAT
struct xt_table_info tmp;
t = xt_find_table_lock(net, AF_INET6, get.name);
if (!IS_ERR(t)) {
- struct xt_table_info *private = xt_table_get_private_protected(t);
+ struct xt_table_info *private = t->private;
if (get.size == private->size)
ret = copy_entries_to_user(private->size,
t, uptr->entrytable);
}
local_bh_disable();
- private = xt_table_get_private_protected(t);
+ private = t->private;
if (private->number != tmp.num_counters) {
ret = -EINVAL;
goto unlock_up_free;
if (!newinfo)
goto out_unlock;
+ memset(newinfo->entries, 0, size);
+
newinfo->number = compatr->num_entries;
for (i = 0; i < NF_INET_NUMHOOKS; i++) {
newinfo->hook_entry[i] = compatr->hook_entry[i];
void __user *userptr)
{
struct xt_counters *counters;
- const struct xt_table_info *private = xt_table_get_private_protected(table);
+ const struct xt_table_info *private = table->private;
void __user *pos;
unsigned int size;
int ret = 0;
xt_compat_lock(AF_INET6);
t = xt_find_table_lock(net, AF_INET6, get.name);
if (!IS_ERR(t)) {
- const struct xt_table_info *private = xt_table_get_private_protected(t);
+ const struct xt_table_info *private = t->private;
struct xt_table_info info;
ret = compat_table_info(private, &info);
if (!ret && get.size == info.size)
*/
v4addr = LOOPBACK4_IPV6;
if (!(addr_type & IPV6_ADDR_MULTICAST) &&
- !sock_net(sk)->ipv6.sysctl.ip_nonlocal_bind) {
+ !ipv6_can_nonlocal_bind(sock_net(sk), inet)) {
err = -EADDRNOTAVAIL;
if (!ipv6_chk_addr(sock_net(sk), &addr->sin6_addr,
dev, 0)) {
.confirm_neigh = ip6_confirm_neigh,
};
-static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst)
-{
- unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
-
- return mtu ? : dst->dev->mtu;
-}
-
-static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
- struct sk_buff *skb, u32 mtu,
- bool confirm_neigh)
-{
-}
-
-static void ip6_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
- struct sk_buff *skb)
-{
-}
-
static struct dst_ops ip6_dst_blackhole_ops = {
- .family = AF_INET6,
- .destroy = ip6_dst_destroy,
- .check = ip6_dst_check,
- .mtu = ip6_blackhole_mtu,
- .default_advmss = ip6_default_advmss,
- .update_pmtu = ip6_rt_blackhole_update_pmtu,
- .redirect = ip6_rt_blackhole_redirect,
- .cow_metrics = dst_cow_metrics_generic,
- .neigh_lookup = ip6_dst_neigh_lookup,
+ .family = AF_INET6,
+ .default_advmss = ip6_default_advmss,
+ .neigh_lookup = ip6_dst_neigh_lookup,
+ .check = ip6_dst_check,
+ .destroy = ip6_dst_destroy,
+ .cow_metrics = dst_cow_metrics_generic,
+ .update_pmtu = dst_blackhole_update_pmtu,
+ .redirect = dst_blackhole_redirect,
+ .mtu = dst_blackhole_mtu,
};
static const u32 ip6_template_metrics[RTAX_MAX] = {
* nexthops have been replaced by first new, the rest should
* be added to it.
*/
- cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL |
- NLM_F_REPLACE);
- cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE;
+ if (cfg->fc_nlinfo.nlh) {
+ cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL |
+ NLM_F_REPLACE);
+ cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE;
+ }
nhn++;
}
skb_dst_update_pmtu_no_confirm(skb, mtu);
if (skb->len > mtu && !skb_is_gso(skb)) {
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+ icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
ip_rt_put(rt);
goto tx_error;
}
if (dev->rtnl_link_ops == &sit_link_ops)
unregister_netdevice_queue(dev, head);
- for (prio = 1; prio < 4; prio++) {
+ for (prio = 0; prio < 4; prio++) {
int h;
- for (h = 0; h < IP6_SIT_HASH_SIZE; h++) {
+ for (h = 0; h < (prio ? IP6_SIT_HASH_SIZE : 1); h++) {
struct ip_tunnel *t;
t = rtnl_dereference(sitn->tunnels[prio][h]);
if (!ipv6_unicast_destination(skb))
goto drop;
+ if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) {
+ __IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS);
+ return 0;
+ }
+
return tcp_conn_request(&tcp6_request_sock_ops,
&tcp_request_sock_ipv6_ops, sk, skb);
/* Parse and check optional cookie */
if (session->peer_cookie_len > 0) {
if (memcmp(ptr, &session->peer_cookie[0], session->peer_cookie_len)) {
- pr_warn_ratelimited("%s: cookie mismatch (%u/%u). Discarding.\n",
- tunnel->name, tunnel->tunnel_id,
- session->session_id);
+ pr_debug_ratelimited("%s: cookie mismatch (%u/%u). Discarding.\n",
+ tunnel->name, tunnel->tunnel_id,
+ session->session_id);
atomic_long_inc(&session->stats.rx_cookie_discards);
goto discard;
}
* If user has configured mandatory sequence numbers, discard.
*/
if (session->recv_seq) {
- pr_warn_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n",
- session->name);
+ pr_debug_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n",
+ session->name);
atomic_long_inc(&session->stats.rx_seq_discards);
goto discard;
}
session->send_seq = 0;
l2tp_session_set_header_len(session, tunnel->version);
} else if (session->send_seq) {
- pr_warn_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n",
- session->name);
+ pr_debug_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n",
+ session->name);
atomic_long_inc(&session->stats.rx_seq_discards);
goto discard;
}
/* Short packet? */
if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) {
- pr_warn_ratelimited("%s: recv short packet (len=%d)\n",
- tunnel->name, skb->len);
- goto error;
+ pr_debug_ratelimited("%s: recv short packet (len=%d)\n",
+ tunnel->name, skb->len);
+ goto invalid;
}
/* Point to L2TP header */
/* Check protocol version */
version = hdrflags & L2TP_HDR_VER_MASK;
if (version != tunnel->version) {
- pr_warn_ratelimited("%s: recv protocol version mismatch: got %d expected %d\n",
- tunnel->name, version, tunnel->version);
- goto error;
+ pr_debug_ratelimited("%s: recv protocol version mismatch: got %d expected %d\n",
+ tunnel->name, version, tunnel->version);
+ goto invalid;
}
/* Get length of L2TP packet */
/* If type is control packet, it is handled by userspace. */
if (hdrflags & L2TP_HDRFLAG_T)
- goto error;
+ goto pass;
/* Skip flags */
ptr += 2;
l2tp_session_dec_refcount(session);
/* Not found? Pass to userspace to deal with */
- pr_warn_ratelimited("%s: no session found (%u/%u). Passing up.\n",
- tunnel->name, tunnel_id, session_id);
- goto error;
+ pr_debug_ratelimited("%s: no session found (%u/%u). Passing up.\n",
+ tunnel->name, tunnel_id, session_id);
+ goto pass;
}
if (tunnel->version == L2TP_HDR_VER_3 &&
l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr))
- goto error;
+ goto invalid;
l2tp_recv_common(session, skb, ptr, optr, hdrflags, length);
l2tp_session_dec_refcount(session);
return 0;
-error:
+invalid:
+ atomic_long_inc(&tunnel->stats.rx_invalid);
+
+pass:
/* Put UDP header back */
__skb_push(skb, sizeof(struct udphdr));
atomic_long_t rx_oos_packets;
atomic_long_t rx_errors;
atomic_long_t rx_cookie_discards;
+ atomic_long_t rx_invalid;
};
struct l2tp_tunnel;
L2TP_ATTR_STATS_PAD) ||
nla_put_u64_64bit(skb, L2TP_ATTR_RX_ERRORS,
atomic_long_read(&tunnel->stats.rx_errors),
+ L2TP_ATTR_STATS_PAD) ||
+ nla_put_u64_64bit(skb, L2TP_ATTR_RX_INVALID,
+ atomic_long_read(&tunnel->stats.rx_invalid),
L2TP_ATTR_STATS_PAD))
goto nla_put_failure;
nla_nest_end(skb, nest);
L2TP_ATTR_STATS_PAD) ||
nla_put_u64_64bit(skb, L2TP_ATTR_RX_ERRORS,
atomic_long_read(&session->stats.rx_errors),
+ L2TP_ATTR_STATS_PAD) ||
+ nla_put_u64_64bit(skb, L2TP_ATTR_RX_INVALID,
+ atomic_long_read(&session->stats.rx_invalid),
L2TP_ATTR_STATS_PAD))
goto nla_put_failure;
nla_nest_end(skb, nest);
struct aead_request *aead_req;
int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm);
u8 *__aad;
+ int ret;
aead_req = kzalloc(reqsize + aad_len, GFP_ATOMIC);
if (!aead_req)
aead_request_set_crypt(aead_req, sg, sg, data_len, b_0);
aead_request_set_ad(aead_req, sg[0].length);
- crypto_aead_encrypt(aead_req);
+ ret = crypto_aead_encrypt(aead_req);
kfree_sensitive(aead_req);
- return 0;
+ return ret;
}
int aead_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, size_t aad_len,
struct aead_request *aead_req;
int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm);
const __le16 *fc;
+ int ret;
if (data_len < GMAC_MIC_LEN)
return -EINVAL;
aead_request_set_crypt(aead_req, sg, sg, 0, iv);
aead_request_set_ad(aead_req, GMAC_AAD_LEN + data_len);
- crypto_aead_encrypt(aead_req);
+ ret = crypto_aead_encrypt(aead_req);
kfree_sensitive(aead_req);
- return 0;
+ return ret;
}
struct crypto_aead *ieee80211_aes_gmac_key_setup(const u8 key[],
}
if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN &&
- sta->sdata->u.vlan.sta)
+ sta->sdata->u.vlan.sta) {
+ ieee80211_clear_fast_rx(sta);
RCU_INIT_POINTER(sta->sdata->u.vlan.sta, NULL);
+ }
if (test_sta_flag(sta, WLAN_STA_AUTHORIZED))
ieee80211_vif_dec_num_mcast(sta->sdata);
continue;
for (j = 0; j < IEEE80211_HT_MCS_MASK_LEN; j++) {
- if (~sdata->rc_rateidx_mcs_mask[i][j]) {
+ if (sdata->rc_rateidx_mcs_mask[i][j] != 0xff) {
sdata->rc_has_mcs_mask[i] = true;
break;
}
}
for (j = 0; j < NL80211_VHT_NSS_MAX; j++) {
- if (~sdata->rc_rateidx_vht_mcs_mask[i][j]) {
+ if (sdata->rc_rateidx_vht_mcs_mask[i][j] != 0xffff) {
sdata->rc_has_vht_mcs_mask[i] = true;
break;
}
/* remove beacon */
kfree(sdata->u.ibss.ie);
+ sdata->u.ibss.ie = NULL;
+ sdata->u.ibss.ie_len = 0;
/* on the next join, re-program HT parameters */
memset(&ifibss->ht_capa, 0, sizeof(ifibss->ht_capa));
continue;
if (!dflt_chandef.chan) {
+ /*
+ * Assign the first enabled channel to dflt_chandef
+ * from the list of channels
+ */
+ for (i = 0; i < sband->n_channels; i++)
+ if (!(sband->channels[i].flags &
+ IEEE80211_CHAN_DISABLED))
+ break;
+ /* if none found then use the first anyway */
+ if (i == sband->n_channels)
+ i = 0;
cfg80211_chandef_create(&dflt_chandef,
- &sband->channels[0],
+ &sband->channels[i],
NL80211_CHAN_NO_HT);
/* init channel we're on */
if (!local->use_chanctx && !local->_oper_chandef.chan) {
timeout = sta->rx_stats.last_rx;
timeout += IEEE80211_CONNECTION_IDLE_TIME;
- if (time_is_before_jiffies(timeout)) {
+ /* If timeout is after now, then update timer to fire at
+ * the later date, but do not actually probe at this time.
+ */
+ if (time_is_after_jiffies(timeout)) {
mod_timer(&ifmgd->conn_mon_timer, round_jiffies_up(timeout));
return;
}
he_oper_ie = cfg80211_find_ext_ie(WLAN_EID_EXT_HE_OPERATION,
ies->data, ies->len);
if (he_oper_ie &&
- he_oper_ie[1] == ieee80211_he_oper_size(&he_oper_ie[3]))
+ he_oper_ie[1] >= ieee80211_he_oper_size(&he_oper_ie[3]))
he_oper = (void *)(he_oper_ie + 3);
else
he_oper = NULL;
static u16
minstrel_ht_next_inc_rate(struct minstrel_ht_sta *mi, u32 fast_rate_dur)
{
- struct minstrel_mcs_group_data *mg;
u8 type = MINSTREL_SAMPLE_TYPE_INC;
int i, index = 0;
u8 group;
group = mi->sample[type].sample_group;
for (i = 0; i < ARRAY_SIZE(minstrel_mcs_groups); i++) {
group = (group + 1) % ARRAY_SIZE(minstrel_mcs_groups);
- mg = &mi->groups[group];
index = minstrel_ht_group_min_rate_offset(mi, group,
fast_rate_dur);
test_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags))
goto out;
- if (vif->txqs_stopped[ieee80211_ac_from_tid(txq->tid)]) {
+ if (vif->txqs_stopped[txq->ac]) {
set_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags);
goto out;
}
break;
case WLAN_EID_EXT_HE_OPERATION:
if (len >= sizeof(*elems->he_operation) &&
- len == ieee80211_he_oper_size(data) - 1) {
+ len >= ieee80211_he_oper_size(data) - 1) {
if (crc)
*crc = crc32_be(*crc, (void *)elem,
elem->datalen + 2);
crypto_free_sync_skcipher(key->tfm0);
err_tfm:
for (i = 0; i < ARRAY_SIZE(key->tfm); i++)
- if (key->tfm[i])
+ if (!IS_ERR_OR_NULL(key->tfm[i]))
crypto_free_aead(key->tfm[i]);
kfree_sensitive(key);
#include <linux/netdev_features.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
+#include <net/mpls.h>
static struct sk_buff *mpls_gso_segment(struct sk_buff *skb,
netdev_features_t features)
skb_reset_network_header(skb);
mpls_hlen = skb_inner_network_header(skb) - skb_network_header(skb);
+ if (unlikely(!mpls_hlen || mpls_hlen % MPLS_HLEN))
+ goto out;
if (unlikely(!pskb_may_pull(skb, mpls_hlen)))
goto out;
}
static u64 add_addr_generate_hmac(u64 key1, u64 key2, u8 addr_id,
- struct in_addr *addr)
+ struct in_addr *addr, u16 port)
{
u8 hmac[SHA256_DIGEST_SIZE];
u8 msg[7];
msg[0] = addr_id;
memcpy(&msg[1], &addr->s_addr, 4);
- msg[5] = 0;
- msg[6] = 0;
+ msg[5] = port >> 8;
+ msg[6] = port & 0xFF;
mptcp_crypto_hmac_sha(key1, key2, msg, 7, hmac);
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
static u64 add_addr6_generate_hmac(u64 key1, u64 key2, u8 addr_id,
- struct in6_addr *addr)
+ struct in6_addr *addr, u16 port)
{
u8 hmac[SHA256_DIGEST_SIZE];
u8 msg[19];
msg[0] = addr_id;
memcpy(&msg[1], &addr->s6_addr, 16);
- msg[17] = 0;
- msg[18] = 0;
+ msg[17] = port >> 8;
+ msg[18] = port & 0xFF;
mptcp_crypto_hmac_sha(key1, key2, msg, 19, hmac);
opts->ahmac = add_addr_generate_hmac(msk->local_key,
msk->remote_key,
opts->addr_id,
- &opts->addr);
+ &opts->addr,
+ opts->port);
}
}
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
opts->ahmac = add_addr6_generate_hmac(msk->local_key,
msk->remote_key,
opts->addr_id,
- &opts->addr6);
+ &opts->addr6,
+ opts->port);
}
}
#endif
if (mp_opt->family == MPTCP_ADDR_IPVERSION_4)
hmac = add_addr_generate_hmac(msk->remote_key,
msk->local_key,
- mp_opt->addr_id, &mp_opt->addr);
+ mp_opt->addr_id, &mp_opt->addr,
+ mp_opt->port);
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
else
hmac = add_addr6_generate_hmac(msk->remote_key,
msk->local_key,
- mp_opt->addr_id, &mp_opt->addr6);
+ mp_opt->addr_id, &mp_opt->addr6,
+ mp_opt->port);
#endif
pr_debug("msk=%p, ahmac=%llu, mp_opt->ahmac=%llu\n",
#include <linux/netdevice.h>
#include <linux/sched/signal.h>
#include <linux/atomic.h>
-#include <linux/igmp.h>
#include <net/sock.h>
#include <net/inet_common.h>
#include <net/inet_hashtables.h>
#include <net/tcp_states.h>
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
#include <net/transp_v6.h>
-#include <net/addrconf.h>
#endif
#include <net/mptcp.h>
#include <net/xfrm.h>
}
}
+static void __mptcp_clean_una_wakeup(struct sock *sk)
+{
+ __mptcp_clean_una(sk);
+ mptcp_write_space(sk);
+}
+
static void mptcp_enter_memory_pressure(struct sock *sk)
{
struct mptcp_subflow_context *subflow;
*/
while (skbs->qlen > 1) {
skb = __skb_dequeue_tail(skbs);
+ *total_ts -= skb->truesize;
__kfree_skb(skb);
}
return skbs->qlen > 0;
release_sock(ssk);
}
-static void mptcp_push_pending(struct sock *sk, unsigned int flags)
+static void __mptcp_push_pending(struct sock *sk, unsigned int flags)
{
struct sock *prev_ssk = NULL, *ssk = NULL;
struct mptcp_sock *msk = mptcp_sk(sk);
wait_for_memory:
mptcp_set_nospace(sk);
- mptcp_push_pending(sk, msg->msg_flags);
+ __mptcp_push_pending(sk, msg->msg_flags);
ret = sk_stream_wait_memory(sk, &timeo);
if (ret)
goto out;
}
if (copied)
- mptcp_push_pending(sk, msg->msg_flags);
+ __mptcp_push_pending(sk, msg->msg_flags);
out:
release_sock(sk);
return backup;
}
+static void mptcp_dispose_initial_subflow(struct mptcp_sock *msk)
+{
+ if (msk->subflow) {
+ iput(SOCK_INODE(msk->subflow));
+ msk->subflow = NULL;
+ }
+}
+
/* subflow sockets can be either outgoing (connect) or incoming
* (accept).
*
static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
struct mptcp_subflow_context *subflow)
{
+ struct mptcp_sock *msk = mptcp_sk(sk);
+
list_del(&subflow->node);
lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
release_sock(ssk);
sock_put(ssk);
+
+ if (ssk == msk->last_snd)
+ msk->last_snd = NULL;
+
+ if (ssk == msk->ack_hint)
+ msk->ack_hint = NULL;
+
+ if (ssk == msk->first)
+ msk->first = NULL;
+
+ if (msk->subflow && ssk == msk->subflow->sk)
+ mptcp_dispose_initial_subflow(msk);
}
void mptcp_close_ssk(struct sock *sk, struct sock *ssk,
mptcp_close_wake_up(sk);
}
-static void mptcp_worker(struct work_struct *work)
+static void __mptcp_retrans(struct sock *sk)
{
- struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work);
- struct sock *ssk, *sk = &msk->sk.icsk_inet.sk;
+ struct mptcp_sock *msk = mptcp_sk(sk);
struct mptcp_sendmsg_info info = {};
struct mptcp_data_frag *dfrag;
size_t copied = 0;
- int state, ret;
+ struct sock *ssk;
+ int ret;
+
+ __mptcp_clean_una_wakeup(sk);
+ dfrag = mptcp_rtx_head(sk);
+ if (!dfrag)
+ return;
+
+ ssk = mptcp_subflow_get_retrans(msk);
+ if (!ssk)
+ goto reset_timer;
+
+ lock_sock(ssk);
+
+ /* limit retransmission to the bytes already sent on some subflows */
+ info.sent = 0;
+ info.limit = dfrag->already_sent;
+ while (info.sent < dfrag->already_sent) {
+ if (!mptcp_alloc_tx_skb(sk, ssk))
+ break;
+
+ ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
+ if (ret <= 0)
+ break;
+
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
+ copied += ret;
+ info.sent += ret;
+ }
+ if (copied)
+ tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
+ info.size_goal);
+
+ mptcp_set_timeout(sk, ssk);
+ release_sock(ssk);
+
+reset_timer:
+ if (!mptcp_timer_pending(sk))
+ mptcp_reset_timer(sk);
+}
+
+static void mptcp_worker(struct work_struct *work)
+{
+ struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work);
+ struct sock *sk = &msk->sk.icsk_inet.sk;
+ int state;
lock_sock(sk);
state = sk->sk_state;
if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
__mptcp_close_subflow(msk);
- if (!test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags))
- goto unlock;
-
- __mptcp_clean_una(sk);
- dfrag = mptcp_rtx_head(sk);
- if (!dfrag)
- goto unlock;
-
- ssk = mptcp_subflow_get_retrans(msk);
- if (!ssk)
- goto reset_unlock;
-
- lock_sock(ssk);
-
- /* limit retransmission to the bytes already sent on some subflows */
- info.sent = 0;
- info.limit = dfrag->already_sent;
- while (info.sent < dfrag->already_sent) {
- if (!mptcp_alloc_tx_skb(sk, ssk))
- break;
-
- ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
- if (ret <= 0)
- break;
-
- MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
- copied += ret;
- info.sent += ret;
- }
- if (copied)
- tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
- info.size_goal);
-
- mptcp_set_timeout(sk, ssk);
- release_sock(ssk);
-
-reset_unlock:
- if (!mptcp_timer_pending(sk))
- mptcp_reset_timer(sk);
+ if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags))
+ __mptcp_retrans(sk);
unlock:
release_sock(sk);
might_sleep();
- /* dispose the ancillatory tcp socket, if any */
- if (msk->subflow) {
- iput(SOCK_INODE(msk->subflow));
- msk->subflow = NULL;
- }
-
/* be sure to always acquire the join list lock, to sync vs
* mptcp_finish_join().
*/
sk_stream_kill_queues(sk);
xfrm_sk_free_policy(sk);
sk_refcnt_debug_release(sk);
+ mptcp_dispose_initial_subflow(msk);
sock_put(sk);
}
return ret;
}
+static bool mptcp_unsupported(int level, int optname)
+{
+ if (level == SOL_IP) {
+ switch (optname) {
+ case IP_ADD_MEMBERSHIP:
+ case IP_ADD_SOURCE_MEMBERSHIP:
+ case IP_DROP_MEMBERSHIP:
+ case IP_DROP_SOURCE_MEMBERSHIP:
+ case IP_BLOCK_SOURCE:
+ case IP_UNBLOCK_SOURCE:
+ case MCAST_JOIN_GROUP:
+ case MCAST_LEAVE_GROUP:
+ case MCAST_JOIN_SOURCE_GROUP:
+ case MCAST_LEAVE_SOURCE_GROUP:
+ case MCAST_BLOCK_SOURCE:
+ case MCAST_UNBLOCK_SOURCE:
+ case MCAST_MSFILTER:
+ return true;
+ }
+ return false;
+ }
+ if (level == SOL_IPV6) {
+ switch (optname) {
+ case IPV6_ADDRFORM:
+ case IPV6_ADD_MEMBERSHIP:
+ case IPV6_DROP_MEMBERSHIP:
+ case IPV6_JOIN_ANYCAST:
+ case IPV6_LEAVE_ANYCAST:
+ case MCAST_JOIN_GROUP:
+ case MCAST_LEAVE_GROUP:
+ case MCAST_JOIN_SOURCE_GROUP:
+ case MCAST_LEAVE_SOURCE_GROUP:
+ case MCAST_BLOCK_SOURCE:
+ case MCAST_UNBLOCK_SOURCE:
+ case MCAST_MSFILTER:
+ return true;
+ }
+ return false;
+ }
+ return false;
+}
+
static int mptcp_setsockopt(struct sock *sk, int level, int optname,
sockptr_t optval, unsigned int optlen)
{
pr_debug("msk=%p", msk);
+ if (mptcp_unsupported(level, optname))
+ return -ENOPROTOOPT;
+
if (level == SOL_SOCKET)
return mptcp_setsockopt_sol_socket(msk, optname, optval, optlen);
{
unsigned long flags, nflags;
- /* push_pending may touch wmem_reserved, do it before the later
- * cleanup
- */
- if (test_and_clear_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->flags))
- __mptcp_clean_una(sk);
- if (test_and_clear_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags)) {
- /* mptcp_push_pending() acquires the subflow socket lock
+ for (;;) {
+ flags = 0;
+ if (test_and_clear_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags))
+ flags |= BIT(MPTCP_PUSH_PENDING);
+ if (!flags)
+ break;
+
+ /* the following actions acquire the subflow socket lock
*
* 1) can't be invoked in atomic scope
* 2) must avoid ABBA deadlock with msk socket spinlock: the RX
*/
spin_unlock_bh(&sk->sk_lock.slock);
- mptcp_push_pending(sk, 0);
+ if (flags & BIT(MPTCP_PUSH_PENDING))
+ __mptcp_push_pending(sk, 0);
+
+ cond_resched();
spin_lock_bh(&sk->sk_lock.slock);
}
+
+ if (test_and_clear_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->flags))
+ __mptcp_clean_una_wakeup(sk);
if (test_and_clear_bit(MPTCP_ERROR_REPORT, &mptcp_sk(sk)->flags))
__mptcp_error_report(sk);
- /* clear any wmem reservation and errors */
+ /* push_pending may touch wmem_reserved, ensure we do the cleanup
+ * later
+ */
__mptcp_update_wmem(sk);
__mptcp_update_rmem(sk);
/* PM/worker can now acquire the first subflow socket
* lock without racing with listener queue cleanup,
* we can notify it, if needed.
+ *
+ * Even if remote has reset the initial subflow by now
+ * the refcnt is still at least one.
*/
subflow = mptcp_subflow_ctx(msk->first);
list_add(&subflow->node, &msk->conn_list);
return mask;
}
-static int mptcp_release(struct socket *sock)
-{
- struct mptcp_subflow_context *subflow;
- struct sock *sk = sock->sk;
- struct mptcp_sock *msk;
-
- if (!sk)
- return 0;
-
- lock_sock(sk);
-
- msk = mptcp_sk(sk);
-
- mptcp_for_each_subflow(msk, subflow) {
- struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-
- ip_mc_drop_socket(ssk);
- }
-
- release_sock(sk);
-
- return inet_release(sock);
-}
-
static const struct proto_ops mptcp_stream_ops = {
.family = PF_INET,
.owner = THIS_MODULE,
- .release = mptcp_release,
+ .release = inet_release,
.bind = mptcp_bind,
.connect = mptcp_stream_connect,
.socketpair = sock_no_socketpair,
}
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
-static int mptcp6_release(struct socket *sock)
-{
- struct mptcp_subflow_context *subflow;
- struct mptcp_sock *msk;
- struct sock *sk = sock->sk;
-
- if (!sk)
- return 0;
-
- lock_sock(sk);
-
- msk = mptcp_sk(sk);
-
- mptcp_for_each_subflow(msk, subflow) {
- struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-
- ip_mc_drop_socket(ssk);
- ipv6_sock_mc_close(ssk);
- ipv6_sock_ac_close(ssk);
- }
-
- release_sock(sk);
- return inet6_release(sock);
-}
-
static const struct proto_ops mptcp_v6_stream_ops = {
.family = PF_INET6,
.owner = THIS_MODULE,
- .release = mptcp6_release,
+ .release = inet6_release,
.bind = mptcp_bind,
.connect = mptcp_stream_connect,
.socketpair = sock_no_socketpair,
#define TCPOLEN_MPTCP_DSS_MAP64 14
#define TCPOLEN_MPTCP_DSS_CHECKSUM 2
#define TCPOLEN_MPTCP_ADD_ADDR 16
-#define TCPOLEN_MPTCP_ADD_ADDR_PORT 20
+#define TCPOLEN_MPTCP_ADD_ADDR_PORT 18
#define TCPOLEN_MPTCP_ADD_ADDR_BASE 8
-#define TCPOLEN_MPTCP_ADD_ADDR_BASE_PORT 12
+#define TCPOLEN_MPTCP_ADD_ADDR_BASE_PORT 10
#define TCPOLEN_MPTCP_ADD_ADDR6 28
-#define TCPOLEN_MPTCP_ADD_ADDR6_PORT 32
+#define TCPOLEN_MPTCP_ADD_ADDR6_PORT 30
#define TCPOLEN_MPTCP_ADD_ADDR6_BASE 20
-#define TCPOLEN_MPTCP_ADD_ADDR6_BASE_PORT 24
-#define TCPOLEN_MPTCP_PORT_LEN 4
+#define TCPOLEN_MPTCP_ADD_ADDR6_BASE_PORT 22
+#define TCPOLEN_MPTCP_PORT_LEN 2
+#define TCPOLEN_MPTCP_PORT_ALIGN 2
#define TCPOLEN_MPTCP_RM_ADDR_BASE 4
#define TCPOLEN_MPTCP_PRIO 3
#define TCPOLEN_MPTCP_PRIO_ALIGN 4
len = TCPOLEN_MPTCP_ADD_ADDR6_BASE;
if (!echo)
len += MPTCPOPT_THMAC_LEN;
+ /* account for 2 trailing 'nop' options */
if (port)
- len += TCPOLEN_MPTCP_PORT_LEN;
+ len += TCPOLEN_MPTCP_PORT_LEN + TCPOLEN_MPTCP_PORT_ALIGN;
return len;
}
if (!ipv6_unicast_destination(skb))
goto drop;
+ if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) {
+ __IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS);
+ return 0;
+ }
+
return tcp_conn_request(&mptcp_subflow_request_sock_ops,
&subflow_request_sock_ipv6_ops, sk, skb);
/* move the msk reference ownership to the subflow */
subflow_req->msk = NULL;
ctx->conn = (struct sock *)owner;
- if (!mptcp_finish_join(child))
- goto dispose_child;
-
- SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX);
- tcp_rsk(req)->drop_req = true;
if (subflow_use_different_sport(owner, sk)) {
pr_debug("ack inet_sport=%d %d",
ntohs(inet_sk((struct sock *)owner)->inet_sport));
if (!mptcp_pm_sport_in_anno_list(owner, sk)) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTACKRX);
- goto out;
+ goto dispose_child;
}
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTACKRX);
}
+
+ if (!mptcp_finish_join(child))
+ goto dispose_child;
+
+ SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX);
+ tcp_rsk(req)->drop_req = true;
}
}
spin_lock_bh(&msk->join_list_lock);
list_del(&subflow->node);
spin_unlock_bh(&msk->join_list_lock);
+ sock_put(mptcp_subflow_tcp_sock(subflow));
failed:
subflow->disposable = 1;
monitor_state = nc->monitor.state;
spin_unlock_irqrestore(&nc->lock, flags);
- if (!enabled || chained) {
- ncsi_stop_channel_monitor(nc);
- return;
- }
+ if (!enabled)
+ return; /* expected race disabling timer */
+ if (WARN_ON_ONCE(chained))
+ goto bad_state;
+
if (state != NCSI_CHANNEL_INACTIVE &&
state != NCSI_CHANNEL_ACTIVE) {
- ncsi_stop_channel_monitor(nc);
+bad_state:
+ netdev_warn(ndp->ndev.dev,
+ "Bad NCSI monitor state channel %d 0x%x %s queue\n",
+ nc->id, state, chained ? "on" : "off");
+ spin_lock_irqsave(&nc->lock, flags);
+ nc->monitor.enabled = false;
+ spin_unlock_irqrestore(&nc->lock, flags);
return;
}
ncsi_report_link(ndp, true);
ndp->flags |= NCSI_DEV_RESHUFFLE;
- ncsi_stop_channel_monitor(nc);
-
ncm = &nc->modes[NCSI_MODE_LINK];
spin_lock_irqsave(&nc->lock, flags);
+ nc->monitor.enabled = false;
nc->state = NCSI_CHANNEL_INVISIBLE;
ncm->data[2] &= ~0x1;
spin_unlock_irqrestore(&nc->lock, flags);
return NULL;
pr_info("nf_conntrack: default automatic helper assignment "
"has been turned off for security reasons and CT-based "
- " firewall rule not found. Use the iptables CT target "
+ "firewall rule not found. Use the iptables CT target "
"to attach helpers instead.\n");
net->ct.auto_assign_helper_warned = 1;
return NULL;
return __nf_ct_helper_find(&ct->tuplehash[IP_CT_DIR_REPLY].tuple);
}
-
int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl,
gfp_t flags)
{
memset(&m, 0xFF, sizeof(m));
memcpy(&m.src.u3, &mask->src.u3, sizeof(m.src.u3));
m.src.u.all = mask->src.u.all;
+ m.src.l3num = tuple->src.l3num;
m.dst.protonum = tuple->dst.protonum;
nest_parms = nla_nest_start(skb, CTA_EXPECT_MASK);
enum ip_conntrack_info ctinfo,
const struct nf_hook_state *state)
{
- if (state->pf != NFPROTO_IPV4)
- return -NF_ACCEPT;
-
if (!nf_ct_is_confirmed(ct)) {
unsigned int *timeouts = nf_ct_timeout_lookup(ct);
IP_CT_EXP_CHALLENGE_ACK;
}
spin_unlock_bh(&ct->lock);
- nf_ct_l4proto_log_invalid(skb, ct, "invalid packet ignored in "
- "state %s ", tcp_conntrack_names[old_state]);
+ nf_ct_l4proto_log_invalid(skb, ct,
+ "packet (index %d) in dir %d ignored, state %s",
+ index, dir,
+ tcp_conntrack_names[old_state]);
return NF_ACCEPT;
case TCP_CONNTRACK_MAX:
/* Special case for SYN proxy: when the SYN to the server or
case IPPROTO_GRE: return "gre";
case IPPROTO_SCTP: return "sctp";
case IPPROTO_UDPLITE: return "udplite";
+ case IPPROTO_ICMPV6: return "icmpv6";
}
return "unknown";
{
int err;
- INIT_DEFERRABLE_WORK(&flowtable->gc_work, nf_flow_offload_work_gc);
+ INIT_DELAYED_WORK(&flowtable->gc_work, nf_flow_offload_work_gc);
flow_block_init(&flowtable->flow_block);
init_rwsem(&flowtable->flow_block_lock);
const __be32 *addr, const __be32 *mask)
{
struct flow_action_entry *entry;
- int i;
+ int i, j;
- for (i = 0; i < sizeof(struct in6_addr) / sizeof(u32); i += sizeof(u32)) {
+ for (i = 0, j = 0; i < sizeof(struct in6_addr) / sizeof(u32); i += sizeof(u32), j++) {
entry = flow_action_entry_next(flow_rule);
flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP6,
- offset + i, &addr[i], mask);
+ offset + i, &addr[j], mask);
}
}
}
static unsigned int
-nf_nat_ipv4_in(void *priv, struct sk_buff *skb,
- const struct nf_hook_state *state)
+nf_nat_ipv4_pre_routing(void *priv, struct sk_buff *skb,
+ const struct nf_hook_state *state)
{
unsigned int ret;
__be32 daddr = ip_hdr(skb)->daddr;
}
static unsigned int
+nf_nat_ipv4_local_in(void *priv, struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ __be32 saddr = ip_hdr(skb)->saddr;
+ struct sock *sk = skb->sk;
+ unsigned int ret;
+
+ ret = nf_nat_ipv4_fn(priv, skb, state);
+
+ if (ret == NF_ACCEPT && sk && saddr != ip_hdr(skb)->saddr &&
+ !inet_sk_transparent(sk))
+ skb_orphan(skb); /* TCP edemux obtained wrong socket */
+
+ return ret;
+}
+
+static unsigned int
nf_nat_ipv4_out(void *priv, struct sk_buff *skb,
const struct nf_hook_state *state)
{
static const struct nf_hook_ops nf_nat_ipv4_ops[] = {
/* Before packet filtering, change destination */
{
- .hook = nf_nat_ipv4_in,
+ .hook = nf_nat_ipv4_pre_routing,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_PRE_ROUTING,
.priority = NF_IP_PRI_NAT_DST,
},
/* After packet filtering, change source */
{
- .hook = nf_nat_ipv4_fn,
+ .hook = nf_nat_ipv4_local_in,
.pf = NFPROTO_IPV4,
.hooknum = NF_INET_LOCAL_IN,
.priority = NF_IP_PRI_NAT_SRC,
if (flags == ctx->table->flags)
return 0;
+ if ((nft_table_has_owner(ctx->table) &&
+ !(flags & NFT_TABLE_F_OWNER)) ||
+ (!nft_table_has_owner(ctx->table) &&
+ flags & NFT_TABLE_F_OWNER))
+ return -EOPNOTSUPP;
+
trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE,
sizeof(struct nft_trans_table));
if (trans == NULL)
return -ENOMEM;
}
-static void nft_set_elem_expr_setup(const struct nft_set_ext *ext, int i,
- struct nft_expr *expr_array[])
+static int nft_set_elem_expr_setup(struct nft_ctx *ctx,
+ const struct nft_set_ext *ext,
+ struct nft_expr *expr_array[],
+ u32 num_exprs)
{
struct nft_set_elem_expr *elem_expr = nft_set_ext_expr(ext);
- struct nft_expr *expr = nft_setelem_expr_at(elem_expr, elem_expr->size);
+ struct nft_expr *expr;
+ int i, err;
+
+ for (i = 0; i < num_exprs; i++) {
+ expr = nft_setelem_expr_at(elem_expr, elem_expr->size);
+ err = nft_expr_clone(expr, expr_array[i]);
+ if (err < 0)
+ goto err_elem_expr_setup;
+
+ elem_expr->size += expr_array[i]->ops->size;
+ nft_expr_destroy(ctx, expr_array[i]);
+ expr_array[i] = NULL;
+ }
+
+ return 0;
- memcpy(expr, expr_array[i], expr_array[i]->ops->size);
- elem_expr->size += expr_array[i]->ops->size;
- kfree(expr_array[i]);
- expr_array[i] = NULL;
+err_elem_expr_setup:
+ for (; i < num_exprs; i++) {
+ nft_expr_destroy(ctx, expr_array[i]);
+ expr_array[i] = NULL;
+ }
+
+ return -ENOMEM;
}
static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
*nft_set_ext_obj(ext) = obj;
obj->use++;
}
- for (i = 0; i < num_exprs; i++)
- nft_set_elem_expr_setup(ext, i, expr_array);
+ err = nft_set_elem_expr_setup(ctx, ext, expr_array, num_exprs);
+ if (err < 0)
+ goto err_elem_expr;
trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set);
- if (trans == NULL)
- goto err_trans;
+ if (trans == NULL) {
+ err = -ENOMEM;
+ goto err_elem_expr;
+ }
ext->genmask = nft_genmask_cur(ctx->net) | NFT_SET_ELEM_BUSY_MASK;
err = set->ops->insert(ctx->net, set, &elem, &ext2);
set->ops->remove(ctx->net, set, &elem);
err_element_clash:
kfree(trans);
-err_trans:
+err_elem_expr:
if (obj)
obj->use--;
list_for_each_entry(hook, hook_list, list) {
list_for_each_entry(ft, &table->flowtables, list) {
+ if (!nft_is_active_next(net, ft))
+ continue;
+
list_for_each_entry(hook2, &ft->hook_list, list) {
if (hook->ops.dev == hook2->ops.dev &&
hook->ops.pf == hook2->ops.pf) {
struct nft_hook *hook, *next;
struct nft_trans *trans;
bool unregister = false;
+ u32 flags;
int err;
err = nft_flowtable_parse_hook(ctx, nla[NFTA_FLOWTABLE_HOOK],
}
}
+ if (nla[NFTA_FLOWTABLE_FLAGS]) {
+ flags = ntohl(nla_get_be32(nla[NFTA_FLOWTABLE_FLAGS]));
+ if (flags & ~NFT_FLOWTABLE_MASK)
+ return -EOPNOTSUPP;
+ if ((flowtable->data.flags & NFT_FLOWTABLE_HW_OFFLOAD) ^
+ (flags & NFT_FLOWTABLE_HW_OFFLOAD))
+ return -EOPNOTSUPP;
+ } else {
+ flags = flowtable->data.flags;
+ }
+
err = nft_register_flowtable_net_hooks(ctx->net, ctx->table,
&flowtable_hook.list, flowtable);
if (err < 0)
goto err_flowtable_update_hook;
}
+ nft_trans_flowtable_flags(trans) = flags;
nft_trans_flowtable(trans) = flowtable;
nft_trans_flowtable_update(trans) = true;
INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans));
if (nla[NFTA_FLOWTABLE_FLAGS]) {
flowtable->data.flags =
ntohl(nla_get_be32(nla[NFTA_FLOWTABLE_FLAGS]));
- if (flowtable->data.flags & ~NFT_FLOWTABLE_MASK)
+ if (flowtable->data.flags & ~NFT_FLOWTABLE_MASK) {
+ err = -EOPNOTSUPP;
goto err3;
+ }
}
write_pnet(&flowtable->data.net, net);
break;
case NFT_MSG_NEWFLOWTABLE:
if (nft_trans_flowtable_update(trans)) {
+ nft_trans_flowtable(trans)->data.flags =
+ nft_trans_flowtable_flags(trans);
nf_tables_flowtable_notify(&trans->ctx,
nft_trans_flowtable(trans),
&nft_trans_flowtable_hooks(trans),
{
struct nft_table *table;
- list_for_each_entry(table, &net->nft.tables, list)
+ list_for_each_entry(table, &net->nft.tables, list) {
+ if (nft_table_has_owner(table))
+ continue;
+
__nft_release_hook(net, table);
+ }
}
static void __nft_release_table(struct net *net, struct nft_table *table)
nf_tables_table_destroy(&ctx);
}
-static void __nft_release_tables(struct net *net, u32 nlpid)
+static void __nft_release_tables(struct net *net)
{
struct nft_table *table, *nt;
list_for_each_entry_safe(table, nt, &net->nft.tables, list) {
- if (nft_table_has_owner(table) &&
- nlpid != table->nlpid)
+ if (nft_table_has_owner(table))
continue;
__nft_release_table(net, table);
mutex_lock(&net->nft.commit_mutex);
if (!list_empty(&net->nft.commit_list))
__nf_tables_abort(net, NFNL_ABORT_NONE);
- __nft_release_tables(net, 0);
+ __nft_release_tables(net);
mutex_unlock(&net->nft.commit_mutex);
WARN_ON_ONCE(!list_empty(&net->nft.tables));
WARN_ON_ONCE(!list_empty(&net->nft.module_list));
return -EOVERFLOW;
if (pkts) {
- tokens = div_u64(limit->nsecs, limit->rate) * limit->burst;
+ tokens = div64_u64(limit->nsecs, limit->rate) * limit->burst;
} else {
/* The token bucket size limits the number of tokens can be
* accumulated. tokens_max specifies the bucket size.
* tokens_max = unit * (rate + burst) / rate.
*/
- tokens = div_u64(limit->nsecs * (limit->rate + limit->burst),
+ tokens = div64_u64(limit->nsecs * (limit->rate + limit->burst),
limit->rate);
}
const struct xt_match *m;
int have_rev = 0;
+ mutex_lock(&xt[af].mutex);
list_for_each_entry(m, &xt[af].match, list) {
if (strcmp(m->name, name) == 0) {
if (m->revision > *bestp)
have_rev = 1;
}
}
+ mutex_unlock(&xt[af].mutex);
if (af != NFPROTO_UNSPEC && !have_rev)
return match_revfn(NFPROTO_UNSPEC, name, revision, bestp);
const struct xt_target *t;
int have_rev = 0;
+ mutex_lock(&xt[af].mutex);
list_for_each_entry(t, &xt[af].target, list) {
if (strcmp(t->name, name) == 0) {
if (t->revision > *bestp)
have_rev = 1;
}
}
+ mutex_unlock(&xt[af].mutex);
if (af != NFPROTO_UNSPEC && !have_rev)
return target_revfn(NFPROTO_UNSPEC, name, revision, bestp);
{
int have_rev, best = -1;
- mutex_lock(&xt[af].mutex);
if (target == 1)
have_rev = target_revfn(af, name, revision, &best);
else
have_rev = match_revfn(af, name, revision, &best);
- mutex_unlock(&xt[af].mutex);
/* Nothing at all? Return 0 to try loading module. */
if (best == -1) {
{
const struct xt_match *match = m->u.kernel.match;
struct compat_xt_entry_match *cm = (struct compat_xt_entry_match *)m;
- int pad, off = xt_compat_match_offset(match);
+ int off = xt_compat_match_offset(match);
u_int16_t msize = cm->u.user.match_size;
char name[sizeof(m->u.user.name)];
match->compat_from_user(m->data, cm->data);
else
memcpy(m->data, cm->data, msize - sizeof(*cm));
- pad = XT_ALIGN(match->matchsize) - match->matchsize;
- if (pad > 0)
- memset(m->data + match->matchsize, 0, pad);
msize += off;
m->u.user.match_size = msize;
{
const struct xt_target *target = t->u.kernel.target;
struct compat_xt_entry_target *ct = (struct compat_xt_entry_target *)t;
- int pad, off = xt_compat_target_offset(target);
+ int off = xt_compat_target_offset(target);
u_int16_t tsize = ct->u.user.target_size;
char name[sizeof(t->u.user.name)];
target->compat_from_user(t->data, ct->data);
else
memcpy(t->data, ct->data, tsize - sizeof(*ct));
- pad = XT_ALIGN(target->targetsize) - target->targetsize;
- if (pad > 0)
- memset(t->data + target->targetsize, 0, pad);
tsize += off;
t->u.user.target_size = tsize;
}
EXPORT_SYMBOL(xt_counters_alloc);
-struct xt_table_info
-*xt_table_get_private_protected(const struct xt_table *table)
-{
- return rcu_dereference_protected(table->private,
- mutex_is_locked(&xt[table->af].mutex));
-}
-EXPORT_SYMBOL(xt_table_get_private_protected);
-
struct xt_table_info *
xt_replace_table(struct xt_table *table,
unsigned int num_counters,
int *error)
{
struct xt_table_info *private;
+ unsigned int cpu;
int ret;
ret = xt_jumpstack_alloc(newinfo);
}
/* Do the substitution. */
- private = xt_table_get_private_protected(table);
+ local_bh_disable();
+ private = table->private;
/* Check inside lock: is the old number correct? */
if (num_counters != private->number) {
pr_debug("num_counters != table->private->number (%u/%u)\n",
num_counters, private->number);
+ local_bh_enable();
*error = -EAGAIN;
return NULL;
}
newinfo->initial_entries = private->initial_entries;
+ /*
+ * Ensure contents of newinfo are visible before assigning to
+ * private.
+ */
+ smp_wmb();
+ table->private = newinfo;
- rcu_assign_pointer(table->private, newinfo);
- synchronize_rcu();
+ /* make sure all cpus see new ->private value */
+ smp_mb();
+
+ /*
+ * Even though table entries have now been swapped, other CPU's
+ * may still be using the old entries...
+ */
+ local_bh_enable();
+
+ /* ... so wait for even xt_recseq on all cpus */
+ for_each_possible_cpu(cpu) {
+ seqcount_t *s = &per_cpu(xt_recseq, cpu);
+ u32 seq = raw_read_seqcount(s);
+
+ if (seq & 1) {
+ do {
+ cond_resched();
+ cpu_relax();
+ } while (seq == raw_read_seqcount(s));
+ }
+ }
audit_log_nfcfg(table->name, table->af, private->number,
!private->number ? AUDIT_XT_OP_REGISTER :
}
/* Simplifies replace_table code. */
- rcu_assign_pointer(table->private, bootstrap);
+ table->private = bootstrap;
if (!xt_replace_table(table, 0, newinfo, &ret))
goto unlock;
- private = xt_table_get_private_protected(table);
+ private = table->private;
pr_debug("table->private->number = %u\n", private->number);
/* save number of initial entries */
struct xt_table_info *private;
mutex_lock(&xt[table->af].mutex);
- private = xt_table_get_private_protected(table);
- RCU_INIT_POINTER(table->private, NULL);
+ private = table->private;
list_del(&table->list);
mutex_unlock(&xt[table->af].mutex);
audit_log_nfcfg(table->name, table->af, private->number,
break;
}
+ cipso_v4_doi_putdef(doi_def);
rcu_read_unlock();
genlmsg_end(ans_skb, data);
list_retry:
/* XXX - this limit is a guesstimate */
if (nlsze_mult < 4) {
+ cipso_v4_doi_putdef(doi_def);
rcu_read_unlock();
kfree_skb(ans_skb);
nlsze_mult *= 2;
goto list_start;
}
list_failure_lock:
+ cipso_v4_doi_putdef(doi_def);
rcu_read_unlock();
list_failure:
kfree_skb(ans_skb);
return -EINVAL;
}
- netlink_lock_table();
if (nlk->netlink_bind && groups) {
int group;
if (!err)
continue;
netlink_undo_bind(group, groups, sk);
- goto unlock;
+ return err;
}
}
/* No need for barriers here as we return to user-space without
* using any of the bound attributes.
*/
+ netlink_lock_table();
if (!bound) {
err = nladdr->nl_pid ?
netlink_insert(sk, nladdr->nl_pid) :
llcp_sock->service_name_len,
GFP_KERNEL);
if (!llcp_sock->service_name) {
+ nfc_llcp_local_put(llcp_sock->local);
ret = -ENOMEM;
goto put_dev;
}
llcp_sock->ssap = nfc_llcp_get_sdp_ssap(local, llcp_sock);
if (llcp_sock->ssap == LLCP_SAP_MAX) {
+ nfc_llcp_local_put(llcp_sock->local);
kfree(llcp_sock->service_name);
llcp_sock->service_name = NULL;
ret = -EADDRINUSE;
ret = -EISCONN;
goto error;
}
+ if (sk->sk_state == LLCP_CONNECTING) {
+ ret = -EINPROGRESS;
+ goto error;
+ }
dev = nfc_get_device(addr->dev_idx);
if (dev == NULL) {
llcp_sock->local = nfc_llcp_local_get(local);
llcp_sock->ssap = nfc_llcp_get_local_ssap(local);
if (llcp_sock->ssap == LLCP_SAP_MAX) {
+ nfc_llcp_local_put(llcp_sock->local);
ret = -ENOMEM;
goto put_dev;
}
sock_unlink:
nfc_llcp_sock_unlink(&local->connecting_sockets, sk);
+ kfree(llcp_sock->service_name);
+ llcp_sock->service_name = NULL;
sock_llcp_release:
nfc_llcp_put_ssap(local, llcp_sock->ssap);
+ nfc_llcp_local_put(llcp_sock->local);
put_dev:
nfc_put_device(dev);
/* This is called to initialize CT key fields possibly coming in from the local
* stack.
*/
-void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key)
+void ovs_ct_fill_key(const struct sk_buff *skb,
+ struct sw_flow_key *key,
+ bool post_ct)
{
- ovs_ct_update_key(skb, NULL, key, false, false);
+ ovs_ct_update_key(skb, NULL, key, post_ct, false);
}
int ovs_ct_put_key(const struct sw_flow_key *swkey,
if (skb_nfct(skb)) {
nf_conntrack_put(skb_nfct(skb));
nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
- ovs_ct_fill_key(skb, key);
+ ovs_ct_fill_key(skb, key, false);
}
return 0;
static int ovs_ct_limit_get_default_limit(struct ovs_ct_limit_info *info,
struct sk_buff *reply)
{
- struct ovs_zone_limit zone_limit;
-
- zone_limit.zone_id = OVS_ZONE_LIMIT_DEFAULT_ZONE;
- zone_limit.limit = info->default_limit;
+ struct ovs_zone_limit zone_limit = {
+ .zone_id = OVS_ZONE_LIMIT_DEFAULT_ZONE,
+ .limit = info->default_limit,
+ };
return nla_put_nohdr(reply, sizeof(zone_limit), &zone_limit);
}
const struct ovs_conntrack_info *);
int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key);
-void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key);
+void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key,
+ bool post_ct);
int ovs_ct_put_key(const struct sw_flow_key *swkey,
const struct sw_flow_key *output, struct sk_buff *skb);
void ovs_ct_free_action(const struct nlattr *a);
}
static inline void ovs_ct_fill_key(const struct sk_buff *skb,
- struct sw_flow_key *key)
+ struct sw_flow_key *key,
+ bool post_ct)
{
key->ct_state = 0;
key->ct_zone = 0;
#if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
struct tc_skb_ext *tc_ext;
#endif
+ bool post_ct = false;
int res, err;
/* Extract metadata from packet. */
tc_ext = skb_ext_find(skb, TC_SKB_EXT);
key->recirc_id = tc_ext ? tc_ext->chain : 0;
OVS_CB(skb)->mru = tc_ext ? tc_ext->mru : 0;
+ post_ct = tc_ext ? tc_ext->post_ct : false;
} else {
key->recirc_id = 0;
}
err = key_extract(skb, key);
if (!err)
- ovs_ct_fill_key(skb, key); /* Must be after key_extract(). */
+ ovs_ct_fill_key(skb, key, post_ct); /* Must be after key_extract(). */
return err;
}
flow = kzalloc(sizeof(*flow), GFP_KERNEL);
if (flow) {
init_waitqueue_head(&flow->resume_tx);
- radix_tree_insert(&node->qrtr_tx_flow, key, flow);
+ if (radix_tree_insert(&node->qrtr_tx_flow, key, flow)) {
+ kfree(flow);
+ flow = NULL;
+ }
}
}
mutex_unlock(&node->qrtr_tx_lock);
if (len == 0 || len & 3)
return -EINVAL;
- skb = netdev_alloc_skb(NULL, len);
+ skb = __netdev_alloc_skb(NULL, len, GFP_ATOMIC | __GFP_NOWARN);
if (!skb)
return -ENOMEM;
plen = (len + 3) & ~3;
skb = sock_alloc_send_skb(sk, plen + QRTR_HDR_MAX_SIZE,
msg->msg_flags & MSG_DONTWAIT, &rc);
- if (!skb)
+ if (!skb) {
+ rc = -ENOMEM;
goto out_node;
+ }
skb_reserve(skb, QRTR_HDR_MAX_SIZE);
rc = copied;
if (addr) {
+ /* There is an anonymous 2-byte hole after sq_family,
+ * make sure to clear it.
+ */
+ memset(addr, 0, sizeof(*addr));
+
addr->sq_family = AF_QIPCRTR;
addr->sq_node = cb->src_node;
addr->sq_port = cb->src_port;
rm->data.op_nents = DIV_ROUND_UP(total_len, PAGE_SIZE);
rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs);
if (IS_ERR(rm->data.op_sg)) {
+ void *err = ERR_CAST(rm->data.op_sg);
rds_message_put(rm);
- return ERR_CAST(rm->data.op_sg);
+ return err;
}
for (i = 0; i < rm->data.op_nents; ++i) {
struct rfkill_int_event {
struct list_head list;
- struct rfkill_event ev;
+ struct rfkill_event_ext ev;
};
struct rfkill_data {
}
#endif /* CONFIG_RFKILL_LEDS */
-static void rfkill_fill_event(struct rfkill_event *ev, struct rfkill *rfkill,
+static void rfkill_fill_event(struct rfkill_event_ext *ev,
+ struct rfkill *rfkill,
enum rfkill_operation op)
{
unsigned long flags;
size_t count, loff_t *pos)
{
struct rfkill *rfkill;
- struct rfkill_event ev;
+ struct rfkill_event_ext ev;
int ret;
/* we don't need the 'hard' variable but accept it */
return 0;
}
-int __tcf_idr_release(struct tc_action *p, bool bind, bool strict)
+static int __tcf_idr_release(struct tc_action *p, bool bind, bool strict)
{
int ret = 0;
return ret;
}
-EXPORT_SYMBOL(__tcf_idr_release);
+
+int tcf_idr_release(struct tc_action *a, bool bind)
+{
+ const struct tc_action_ops *ops = a->ops;
+ int ret;
+
+ ret = __tcf_idr_release(a, bind, false);
+ if (ret == ACT_P_DELETED)
+ module_put(ops->owner);
+ return ret;
+}
+EXPORT_SYMBOL(tcf_idr_release);
static size_t tcf_action_shared_attrs_size(const struct tc_action *act)
{
}
p->idrinfo = idrinfo;
+ __module_get(ops->owner);
p->ops = ops;
*a = p;
return 0;
struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
struct nlattr *nla, struct nlattr *est,
char *name, int ovr, int bind,
- struct tc_action_ops *a_o, bool rtnl_held,
+ struct tc_action_ops *a_o, int *init_res,
+ bool rtnl_held,
struct netlink_ext_ack *extack)
{
struct nla_bitfield32 flags = { 0, 0 };
}
if (err < 0)
goto err_out;
+ *init_res = err;
if (!name && tb[TCA_ACT_COOKIE])
tcf_set_action_cookie(&a->act_cookie, cookie);
if (!name)
a->hw_stats = hw_stats;
- /* module count goes up only when brand new policy is created
- * if it exists and is only bound to in a_o->init() then
- * ACT_P_CREATED is not returned (a zero is).
- */
- if (err != ACT_P_CREATED)
- module_put(a_o->owner);
-
return a;
err_out:
int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
struct nlattr *est, char *name, int ovr, int bind,
- struct tc_action *actions[], size_t *attr_size,
+ struct tc_action *actions[], int init_res[], size_t *attr_size,
bool rtnl_held, struct netlink_ext_ack *extack)
{
struct tc_action_ops *ops[TCA_ACT_MAX_PRIO] = {};
for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) {
act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind,
- ops[i - 1], rtnl_held, extack);
+ ops[i - 1], &init_res[i - 1], rtnl_held,
+ extack);
if (IS_ERR(act)) {
err = PTR_ERR(act);
goto err;
tcf_idr_insert_many(actions);
*attr_size = tcf_action_full_attrs_size(sz);
- return i - 1;
+ err = i - 1;
+ goto err_mod;
err:
tcf_action_destroy(actions, bind);
struct netlink_ext_ack *extack)
{
size_t attr_size = 0;
- int loop, ret;
+ int loop, ret, i;
struct tc_action *actions[TCA_ACT_MAX_PRIO] = {};
+ int init_res[TCA_ACT_MAX_PRIO] = {};
for (loop = 0; loop < 10; loop++) {
ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0,
- actions, &attr_size, true, extack);
+ actions, init_res, &attr_size, true, extack);
if (ret != -EAGAIN)
break;
}
if (ret < 0)
return ret;
ret = tcf_add_notify(net, n, actions, portid, attr_size, extack);
- if (ovr)
- tcf_action_put_many(actions);
+
+ /* only put existing actions */
+ for (i = 0; i < TCA_ACT_MAX_PRIO; i++)
+ if (init_res[i] == ACT_P_CREATED)
+ actions[i] = NULL;
+ tcf_action_put_many(actions);
return ret;
}
tcf_lastuse_update(&c->tcf_tm);
if (clear) {
+ qdisc_skb_cb(skb)->post_ct = false;
ct = nf_ct_get(skb, &ctinfo);
if (ct) {
nf_conntrack_put(&ct->ct_general);
nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
}
- goto out;
+ goto out_clear;
}
family = tcf_ct_skb_nf_family(skb);
skb_push_rcsum(skb, nh_ofs);
out:
- tcf_action_update_bstats(&c->common, skb);
qdisc_skb_cb(skb)->post_ct = true;
+out_clear:
+ tcf_action_update_bstats(&c->common, skb);
if (defrag)
qdisc_skb_cb(skb)->pkt_len = skb->len;
return retval;
struct net_device *dev = block_cb->indr.dev;
struct Qdisc *sch = block_cb->indr.sch;
struct netlink_ext_ack extack = {};
- struct flow_block_offload bo;
+ struct flow_block_offload bo = {};
tcf_block_offload_init(&bo, dev, sch, FLOW_BLOCK_UNBIND,
block_cb->indr.binder_type,
return TC_ACT_SHOT;
ext->chain = last_executed_chain;
ext->mru = qdisc_skb_cb(skb)->mru;
+ ext->post_ct = qdisc_skb_cb(skb)->post_ct;
}
return ret;
{
#ifdef CONFIG_NET_CLS_ACT
{
+ int init_res[TCA_ACT_MAX_PRIO] = {};
struct tc_action *act;
size_t attr_size = 0;
return PTR_ERR(a_o);
act = tcf_action_init_1(net, tp, tb[exts->police],
rate_tlv, "police", ovr,
- TCA_ACT_BIND, a_o, rtnl_held,
- extack);
- if (IS_ERR(act)) {
- module_put(a_o->owner);
+ TCA_ACT_BIND, a_o, init_res,
+ rtnl_held, extack);
+ module_put(a_o->owner);
+ if (IS_ERR(act))
return PTR_ERR(act);
- }
act->type = exts->type = TCA_OLD_COMPAT;
exts->actions[0] = act;
err = tcf_action_init(net, tp, tb[exts->action],
rate_tlv, NULL, ovr, TCA_ACT_BIND,
- exts->actions, &attr_size,
- rtnl_held, extack);
+ exts->actions, init_res,
+ &attr_size, rtnl_held, extack);
if (err < 0)
return err;
exts->nr_actions = err;
&mask->ct_state, TCA_FLOWER_KEY_CT_STATE_MASK,
sizeof(key->ct_state));
- err = fl_validate_ct_state(mask->ct_state,
+ err = fl_validate_ct_state(key->ct_state & mask->ct_state,
tb[TCA_FLOWER_KEY_CT_STATE_MASK],
extack);
if (err)
static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb,
struct tcmsg *tcm, struct netlink_callback *cb,
- int *t_p, int s_t)
+ int *t_p, int s_t, bool recur)
{
struct Qdisc *q;
int b;
if (tc_dump_tclass_qdisc(root, skb, tcm, cb, t_p, s_t) < 0)
return -1;
- if (!qdisc_dev(root))
+ if (!qdisc_dev(root) || !recur)
return 0;
if (tcm->tcm_parent) {
s_t = cb->args[0];
t = 0;
- if (tc_dump_tclass_root(dev->qdisc, skb, tcm, cb, &t, s_t) < 0)
+ if (tc_dump_tclass_root(dev->qdisc, skb, tcm, cb, &t, s_t, true) < 0)
goto done;
dev_queue = dev_ingress_queue(dev);
if (dev_queue &&
tc_dump_tclass_root(dev_queue->qdisc_sleeping, skb, tcm, cb,
- &t, s_t) < 0)
+ &t, s_t, false) < 0)
goto done;
done:
struct sk_buff **old = NULL;
unsigned int mask;
u32 max_P;
+ u8 *stab;
if (opt == NULL)
return -EINVAL;
max_P = tb[TCA_CHOKE_MAX_P] ? nla_get_u32(tb[TCA_CHOKE_MAX_P]) : 0;
ctl = nla_data(tb[TCA_CHOKE_PARMS]);
-
- if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log))
+ stab = nla_data(tb[TCA_CHOKE_STAB]);
+ if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log, stab))
return -EINVAL;
if (ctl->limit > CHOKE_MAX_QUEUE)
red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog,
ctl->Plog, ctl->Scell_log,
- nla_data(tb[TCA_CHOKE_STAB]),
+ stab,
max_P);
red_set_vars(&q->vars);
struct gred_sched *table = qdisc_priv(sch);
struct gred_sched_data *q = table->tab[dp];
- if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log)) {
+ if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log, stab)) {
NL_SET_ERR_MSG_MOD(extack, "invalid RED parameters");
return -EINVAL;
}
struct nlattr *tb[TCA_HTB_MAX + 1];
struct tc_htb_glob *gopt;
unsigned int ntx;
+ bool offload;
int err;
qdisc_watchdog_init(&q->watchdog, sch);
if (gopt->version != HTB_VER >> 16)
return -EINVAL;
- q->offload = nla_get_flag(tb[TCA_HTB_OFFLOAD]);
+ offload = nla_get_flag(tb[TCA_HTB_OFFLOAD]);
- if (q->offload) {
+ if (offload) {
if (sch->parent != TC_H_ROOT)
return -EOPNOTSUPP;
q->rate2quantum = 1;
q->defcls = gopt->defcls;
- if (!q->offload)
+ if (!offload)
return 0;
for (ntx = 0; ntx < q->num_direct_qdiscs; ntx++) {
if (err)
goto err_free_qdiscs;
+ /* Defer this assignment, so that htb_destroy skips offload-related
+ * parts (especially calling ndo_setup_tc) on errors.
+ */
+ q->offload = true;
+
return 0;
err_free_qdiscs:
- /* TC_HTB_CREATE call failed, avoid any further calls to the driver. */
- q->offload = false;
-
for (ntx = 0; ntx < q->num_direct_qdiscs && q->direct_qdiscs[ntx];
ntx++)
qdisc_put(q->direct_qdiscs[ntx]);
{
struct net_device *dev = qdisc_dev(sch);
struct tc_htb_qopt_offload offload_opt;
+ struct htb_sched *q = qdisc_priv(sch);
int err;
+ if (!q->offload)
+ return sch->dev_queue;
+
offload_opt = (struct tc_htb_qopt_offload) {
.command = TC_HTB_LEAF_QUERY_QUEUE,
.classid = TC_H_MIN(tcm->tcm_parent),
cl->parent->common.classid,
NULL);
if (q->offload) {
- if (new_q)
+ if (new_q) {
htb_set_lockdep_class_child(new_q);
- htb_parent_to_leaf_offload(sch, dev_queue, new_q);
+ htb_parent_to_leaf_offload(sch, dev_queue, new_q);
+ }
}
}
unsigned char flags;
int err;
u32 max_P;
+ u8 *stab;
if (tb[TCA_RED_PARMS] == NULL ||
tb[TCA_RED_STAB] == NULL)
max_P = tb[TCA_RED_MAX_P] ? nla_get_u32(tb[TCA_RED_MAX_P]) : 0;
ctl = nla_data(tb[TCA_RED_PARMS]);
- if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log))
+ stab = nla_data(tb[TCA_RED_STAB]);
+ if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog,
+ ctl->Scell_log, stab))
return -EINVAL;
err = red_get_flags(ctl->flags, TC_RED_HISTORIC_FLAGS,
red_set_parms(&q->parms,
ctl->qth_min, ctl->qth_max, ctl->Wlog,
ctl->Plog, ctl->Scell_log,
- nla_data(tb[TCA_RED_STAB]),
+ stab,
max_P);
red_set_vars(&q->vars);
}
if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max,
- ctl_v1->Wlog, ctl_v1->Scell_log))
+ ctl_v1->Wlog, ctl_v1->Scell_log, NULL))
return -EINVAL;
if (ctl_v1 && ctl_v1->qth_min) {
p = kmalloc(sizeof(*p), GFP_KERNEL);
struct teql_sched_data *dat = qdisc_priv(sch);
struct teql_master *master = dat->m;
+ if (!master)
+ return;
+
prev = master->slaves;
if (prev) {
do {
if (!(type & IPV6_ADDR_UNICAST))
return 0;
- return sp->inet.freebind || net->ipv6.sysctl.ip_nonlocal_bind ||
- ipv6_chk_addr(net, in6, NULL, 0);
+ return ipv6_can_nonlocal_bind(net, &sp->inet) ||
+ ipv6_chk_addr(net, in6, NULL, 0);
}
/* This function checks if the address is a valid address to be used for
net = sock_net(&opt->inet.sk);
rcu_read_lock();
dev = dev_get_by_index_rcu(net, addr->v6.sin6_scope_id);
- if (!dev || !(opt->inet.freebind ||
- net->ipv6.sysctl.ip_nonlocal_bind ||
+ if (!dev || !(ipv6_can_nonlocal_bind(net, &opt->inet) ||
ipv6_chk_addr(net, &addr->v6.sin6_addr,
dev, 0))) {
rcu_read_unlock();
goto out;
}
- rcu_read_lock();
- if (__sk_dst_get(sk) != tp->dst) {
- dst_hold(tp->dst);
- sk_setup_caps(sk, tp->dst);
- }
- rcu_read_unlock();
-
/* pack up chunks */
pkt_count = sctp_packet_pack(packet, head, gso, gfp);
if (!pkt_count) {
static void sctp_outq_flush_transports(struct sctp_flush_ctx *ctx)
{
+ struct sock *sk = ctx->asoc->base.sk;
struct list_head *ltransport;
struct sctp_packet *packet;
struct sctp_transport *t;
t = list_entry(ltransport, struct sctp_transport, send_ready);
packet = &t->packet;
if (!sctp_packet_empty(packet)) {
+ rcu_read_lock();
+ if (t->dst && __sk_dst_get(sk) != t->dst) {
+ dst_hold(t->dst);
+ sk_setup_caps(sk, t->dst);
+ }
+ rcu_read_unlock();
error = sctp_packet_transmit(packet, ctx->gfp);
if (error < 0)
ctx->q->asoc->base.sk->sk_err = -error;
/* Supposedly, no process has access to the socket, but
* the net layers still may.
- * Also, sctp_destroy_sock() needs to be called with addr_wq_lock
- * held and that should be grabbed before socket lock.
*/
- spin_lock_bh(&net->sctp.addr_wq_lock);
- bh_lock_sock_nested(sk);
+ local_bh_disable();
+ bh_lock_sock(sk);
/* Hold the sock, since sk_common_release() will put sock_put()
* and we have just a little more cleanup.
sk_common_release(sk);
bh_unlock_sock(sk);
- spin_unlock_bh(&net->sctp.addr_wq_lock);
+ local_bh_enable();
sock_put(sk);
sk_sockets_allocated_inc(sk);
sock_prot_inuse_add(net, sk->sk_prot, 1);
- /* Nothing can fail after this block, otherwise
- * sctp_destroy_sock() will be called without addr_wq_lock held
- */
if (net->sctp.default_auto_asconf) {
spin_lock(&sock_net(sk)->sctp.addr_wq_lock);
list_add_tail(&sp->auto_asconf_list,
if (sp->do_auto_asconf) {
sp->do_auto_asconf = 0;
+ spin_lock_bh(&sock_net(sk)->sctp.addr_wq_lock);
list_del(&sp->auto_asconf_list);
+ spin_unlock_bh(&sock_net(sk)->sctp.addr_wq_lock);
}
sctp_endpoint_free(sp->ep);
local_bh_disable();
return 1;
/* Verify that we can hold this TSN and that it will not
- * overlfow our map
+ * overflow our map
*/
if (!TSN_lt(tsn, map->base_tsn + SCTP_TSN_MAP_SIZE))
return -1;
svcauth_gss_release(struct svc_rqst *rqstp)
{
struct gss_svc_data *gsd = (struct gss_svc_data *)rqstp->rq_auth_data;
- struct rpc_gss_wire_cred *gc = &gsd->clcred;
+ struct rpc_gss_wire_cred *gc;
struct xdr_buf *resbuf = &rqstp->rq_res;
int stat = -EINVAL;
struct sunrpc_net *sn = net_generic(SVC_NET(rqstp), sunrpc_net_id);
+ if (!gsd)
+ goto out;
+ gc = &gsd->clcred;
if (gc->gc_proc != RPC_GSS_PROC_DATA)
goto out;
/* Release can be called twice, but we only wrap once. */
if (rqstp->rq_cred.cr_group_info)
put_group_info(rqstp->rq_cred.cr_group_info);
rqstp->rq_cred.cr_group_info = NULL;
- if (gsd->rsci)
+ if (gsd && gsd->rsci) {
cache_put(&gsd->rsci->h, sn->rsc_cache);
- gsd->rsci = NULL;
-
+ gsd->rsci = NULL;
+ }
return stat;
}
rpc_set_active(task);
rpc_make_runnable(rpciod_workqueue, task);
- if (!is_async)
+ if (!is_async) {
+ unsigned int pflags = memalloc_nofs_save();
__rpc_execute(task);
+ memalloc_nofs_restore(pflags);
+ }
}
static void rpc_async_schedule(struct work_struct *work)
sendit:
if (svc_authorise(rqstp))
- goto close;
+ goto close_xprt;
return 1; /* Caller can now send it */
release_dropit:
return 0;
close:
+ svc_authorise(rqstp);
+close_xprt:
if (rqstp->rq_xprt && test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags))
svc_close_xprt(rqstp->rq_xprt);
dprintk("svc: svc_process close\n");
err_short_len:
svc_printk(rqstp, "short len %zd, dropping request\n",
argv->iov_len);
- goto close;
+ goto close_xprt;
err_bad_rpc:
serv->sv_stats->rpcbadfmt++;
struct svc_xprt *xprt;
int ret = 0;
- spin_lock(&serv->sv_lock);
+ spin_lock_bh(&serv->sv_lock);
list_for_each_entry(xprt, xprt_list, xpt_list) {
if (xprt->xpt_net != net)
continue;
set_bit(XPT_CLOSE, &xprt->xpt_flags);
svc_xprt_enqueue(xprt);
}
- spin_unlock(&serv->sv_lock);
+ spin_unlock_bh(&serv->sv_lock);
return ret;
}
xprt->timeout = &xprt_rdma_bc_timeout;
xprt_set_bound(xprt);
xprt_set_connected(xprt);
- xprt->bind_timeout = RPCRDMA_BIND_TO;
- xprt->reestablish_timeout = RPCRDMA_INIT_REEST_TO;
- xprt->idle_timeout = RPCRDMA_IDLE_DISC_TO;
+ xprt->bind_timeout = 0;
+ xprt->reestablish_timeout = 0;
+ xprt->idle_timeout = 0;
xprt->prot = XPRT_TRANSPORT_BC_RDMA;
xprt->ops = &xprt_rdma_bc_procs;
svc_rdma_recv_ctxt_put(rdma, ctxt);
}
-static bool svc_rdma_refresh_recvs(struct svcxprt_rdma *rdma,
- unsigned int wanted, bool temp)
+static int __svc_rdma_post_recv(struct svcxprt_rdma *rdma,
+ struct svc_rdma_recv_ctxt *ctxt)
{
- const struct ib_recv_wr *bad_wr = NULL;
- struct svc_rdma_recv_ctxt *ctxt;
- struct ib_recv_wr *recv_chain;
int ret;
- recv_chain = NULL;
- while (wanted--) {
- ctxt = svc_rdma_recv_ctxt_get(rdma);
- if (!ctxt)
- break;
-
- trace_svcrdma_post_recv(ctxt);
- ctxt->rc_temp = temp;
- ctxt->rc_recv_wr.next = recv_chain;
- recv_chain = &ctxt->rc_recv_wr;
- rdma->sc_pending_recvs++;
- }
- if (!recv_chain)
- return false;
-
- ret = ib_post_recv(rdma->sc_qp, recv_chain, &bad_wr);
+ trace_svcrdma_post_recv(ctxt);
+ ret = ib_post_recv(rdma->sc_qp, &ctxt->rc_recv_wr, NULL);
if (ret)
goto err_post;
- return true;
+ return 0;
err_post:
- while (bad_wr) {
- ctxt = container_of(bad_wr, struct svc_rdma_recv_ctxt,
- rc_recv_wr);
- bad_wr = bad_wr->next;
- svc_rdma_recv_ctxt_put(rdma, ctxt);
- }
-
trace_svcrdma_rq_post_err(rdma, ret);
- /* Since we're destroying the xprt, no need to reset
- * sc_pending_recvs. */
- return false;
+ svc_rdma_recv_ctxt_put(rdma, ctxt);
+ return ret;
+}
+
+static int svc_rdma_post_recv(struct svcxprt_rdma *rdma)
+{
+ struct svc_rdma_recv_ctxt *ctxt;
+
+ if (test_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags))
+ return 0;
+ ctxt = svc_rdma_recv_ctxt_get(rdma);
+ if (!ctxt)
+ return -ENOMEM;
+ return __svc_rdma_post_recv(rdma, ctxt);
}
/**
*/
bool svc_rdma_post_recvs(struct svcxprt_rdma *rdma)
{
- return svc_rdma_refresh_recvs(rdma, rdma->sc_max_requests, true);
+ struct svc_rdma_recv_ctxt *ctxt;
+ unsigned int i;
+ int ret;
+
+ for (i = 0; i < rdma->sc_max_requests; i++) {
+ ctxt = svc_rdma_recv_ctxt_get(rdma);
+ if (!ctxt)
+ return false;
+ ctxt->rc_temp = true;
+ ret = __svc_rdma_post_recv(rdma, ctxt);
+ if (ret)
+ return false;
+ }
+ return true;
}
/**
* @cq: Completion Queue context
* @wc: Work Completion object
*
+ * NB: The svc_xprt/svcxprt_rdma is pinned whenever it's possible that
+ * the Receive completion handler could be running.
*/
static void svc_rdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc)
{
struct ib_cqe *cqe = wc->wr_cqe;
struct svc_rdma_recv_ctxt *ctxt;
- rdma->sc_pending_recvs--;
-
/* WARNING: Only wc->wr_cqe and wc->status are reliable */
ctxt = container_of(cqe, struct svc_rdma_recv_ctxt, rc_cqe);
if (wc->status != IB_WC_SUCCESS)
goto flushed;
+ if (svc_rdma_post_recv(rdma))
+ goto post_err;
+
/* All wc fields are now known to be valid */
ctxt->rc_byte_len = wc->byte_len;
spin_unlock(&rdma->sc_rq_dto_lock);
if (!test_bit(RDMAXPRT_CONN_PENDING, &rdma->sc_flags))
svc_xprt_enqueue(&rdma->sc_xprt);
-
- if (!test_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags) &&
- rdma->sc_pending_recvs < rdma->sc_max_requests)
- if (!svc_rdma_refresh_recvs(rdma, RPCRDMA_MAX_RECV_BATCH,
- false))
- goto post_err;
-
return;
flushed:
- svc_rdma_recv_ctxt_put(rdma, ctxt);
post_err:
+ svc_rdma_recv_ctxt_put(rdma, ctxt);
set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags);
svc_xprt_enqueue(&rdma->sc_xprt);
}
* care of initializing all other fields.
*/
struct tipc_bearer {
- void __rcu *media_ptr; /* initalized by media */
- u32 mtu; /* initalized by media */
- struct tipc_media_addr addr; /* initalized by media */
+ void __rcu *media_ptr; /* initialized by media */
+ u32 mtu; /* initialized by media */
+ struct tipc_media_addr addr; /* initialized by media */
char name[TIPC_MAX_BEARER_NAME];
struct tipc_media *media;
struct tipc_media_addr bcast_addr;
goto rcv;
if (tipc_aead_clone(&tmp, aead) < 0)
goto rcv;
+ WARN_ON(!refcount_inc_not_zero(&tmp->refcnt));
if (tipc_crypto_key_attach(rx, tmp, ehdr->tx_key, false) < 0) {
tipc_aead_free(&tmp->rcu);
goto rcv;
}
tipc_aead_put(aead);
- aead = tipc_aead_get(tmp);
+ aead = tmp;
}
if (unlikely(err)) {
* - A spin lock to protect the registry of kernel/driver users (reg.c)
* - A global spin_lock (tipc_port_lock), which only task is to ensure
* consistency where more than one port is involved in an operation,
- * i.e., whe a port is part of a linked list of ports.
+ * i.e., when a port is part of a linked list of ports.
* There are two such lists; 'port_list', which is used for management,
* and 'wait_list', which is used to queue ports during congestion.
*
}
/* tipc_node_xmit_skb(): send single buffer to destination
- * Buffers sent via this functon are generally TIPC_SYSTEM_IMPORTANCE
+ * Buffers sent via this function are generally TIPC_SYSTEM_IMPORTANCE
* messages, which will not be rejected
* The only exception is datagram messages rerouted after secondary
* lookup, which are rare and safe to dispose of anyway.
#ifdef CONFIG_TIPC_CRYPTO
static int tipc_nl_retrieve_key(struct nlattr **attrs,
- struct tipc_aead_key **key)
+ struct tipc_aead_key **pkey)
{
struct nlattr *attr = attrs[TIPC_NLA_NODE_KEY];
+ struct tipc_aead_key *key;
if (!attr)
return -ENODATA;
- *key = (struct tipc_aead_key *)nla_data(attr);
- if (nla_len(attr) < tipc_aead_key_size(*key))
+ if (nla_len(attr) < sizeof(*key))
+ return -EINVAL;
+ key = (struct tipc_aead_key *)nla_data(attr);
+ if (key->keylen > TIPC_AEAD_KEYLEN_MAX ||
+ nla_len(attr) < tipc_aead_key_size(key))
return -EINVAL;
+ *pkey = key;
return 0;
}
spin_lock_bh(&inputq->lock);
if (skb_peek(arrvq) == skb) {
skb_queue_splice_tail_init(&tmpq, inputq);
- kfree_skb(__skb_dequeue(arrvq));
+ __skb_dequeue(arrvq);
}
spin_unlock_bh(&inputq->lock);
__skb_queue_purge(&tmpq);
vsk->buffer_size = psk->buffer_size;
vsk->buffer_min_size = psk->buffer_min_size;
vsk->buffer_max_size = psk->buffer_max_size;
+ security_sk_clone(parent, sk);
} else {
vsk->trusted = ns_capable_noaudit(&init_user_ns, CAP_NET_ADMIN);
vsk->owner = get_current_cred();
* Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
* Copyright 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2020 Intel Corporation
+ * Copyright (C) 2018-2021 Intel Corporation
*/
#include <linux/if.h>
struct wireless_dev *result = NULL;
bool have_ifidx = attrs[NL80211_ATTR_IFINDEX];
bool have_wdev_id = attrs[NL80211_ATTR_WDEV];
- u64 wdev_id;
+ u64 wdev_id = 0;
int wiphy_idx = -1;
int ifidx = -1;
unsigned int len = nla_len(attr);
const struct element *elem;
const struct ieee80211_mgmt *mgmt = (void *)data;
- bool s1g_bcn = ieee80211_is_s1g_beacon(mgmt->frame_control);
unsigned int fixedlen, hdrlen;
+ bool s1g_bcn;
+ if (len < offsetofend(typeof(*mgmt), frame_control))
+ goto err;
+
+ s1g_bcn = ieee80211_is_s1g_beacon(mgmt->frame_control);
if (s1g_bcn) {
fixedlen = offsetof(struct ieee80211_ext,
u.s1g_beacon.variable);
rdev, info->attrs[NL80211_ATTR_UNSOL_BCAST_PROBE_RESP],
¶ms);
if (err)
- return err;
+ goto out;
}
nl80211_calculate_ap_params(¶ms);
#define NL80211_FLAG_NEED_WDEV_UP (NL80211_FLAG_NEED_WDEV |\
NL80211_FLAG_CHECK_NETDEV_UP)
#define NL80211_FLAG_CLEAR_SKB 0x20
+#define NL80211_FLAG_NO_WIPHY_MTX 0x40
static int nl80211_pre_doit(const struct genl_ops *ops, struct sk_buff *skb,
struct genl_info *info)
info->user_ptr[0] = rdev;
}
- if (rdev) {
+ if (rdev && !(ops->internal_flags & NL80211_FLAG_NO_WIPHY_MTX)) {
wiphy_lock(&rdev->wiphy);
/* we keep the mutex locked until post_doit */
__release(&rdev->wiphy.mtx);
}
}
- if (info->user_ptr[0]) {
+ if (info->user_ptr[0] &&
+ !(ops->internal_flags & NL80211_FLAG_NO_WIPHY_MTX)) {
struct cfg80211_registered_device *rdev = info->user_ptr[0];
/* we kept the mutex locked since pre_doit */
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
.doit = nl80211_wiphy_netns,
.flags = GENL_UNS_ADMIN_PERM,
- .internal_flags = NL80211_FLAG_NEED_WIPHY,
+ .internal_flags = NL80211_FLAG_NEED_WIPHY |
+ NL80211_FLAG_NEED_RTNL |
+ NL80211_FLAG_NO_WIPHY_MTX,
},
{
.cmd = NL80211_CMD_GET_SURVEY,
return NULL;
if (ext) {
- struct ieee80211_s1g_bcn_compat_ie *compat;
- u8 *ie;
+ const struct ieee80211_s1g_bcn_compat_ie *compat;
+ const struct element *elem;
- ie = (void *)cfg80211_find_ie(WLAN_EID_S1G_BCN_COMPAT,
- variable, ielen);
- if (!ie)
+ elem = cfg80211_find_elem(WLAN_EID_S1G_BCN_COMPAT,
+ variable, ielen);
+ if (!elem)
+ return NULL;
+ if (elem->datalen < sizeof(*compat))
return NULL;
- compat = (void *)(ie + 2);
+ compat = (void *)elem->data;
bssid = ext->u.s1g_beacon.sa;
capability = le16_to_cpu(compat->compat_info);
beacon_int = le16_to_cpu(compat->beacon_int);
cfg80211_sme_free(wdev);
}
- if (WARN_ON(wdev->conn))
+ if (wdev->conn)
return -EINPROGRESS;
wdev->conn = kzalloc(sizeof(*wdev->conn), GFP_KERNEL);
case XFRM_MSG_GETSADINFO:
case XFRM_MSG_GETSPDINFO:
default:
- WARN_ONCE(1, "unsupported nlmsg_type %d", nlh_src->nlmsg_type);
+ pr_warn_once("unsupported nlmsg_type %d\n", nlh_src->nlmsg_type);
return ERR_PTR(-EOPNOTSUPP);
}
return xfrm_nla_cpy(dst, src, nla_len(src));
default:
BUILD_BUG_ON(XFRMA_MAX != XFRMA_IF_ID);
- WARN_ONCE(1, "unsupported nla_type %d", src->nla_type);
+ pr_warn_once("unsupported nla_type %d\n", src->nla_type);
return -EOPNOTSUPP;
}
}
struct sk_buff *new = NULL;
int err;
- if (WARN_ON_ONCE(type >= ARRAY_SIZE(xfrm_msg_min)))
+ if (type >= ARRAY_SIZE(xfrm_msg_min)) {
+ pr_warn_once("unsupported nlmsg_type %d\n", nlh_src->nlmsg_type);
return -EOPNOTSUPP;
+ }
if (skb_shinfo(skb)->frag_list == NULL) {
new = alloc_skb(skb->len + skb_tailroom(skb), GFP_ATOMIC);
struct nlmsghdr *nlmsg = dst;
struct nlattr *nla;
+ /* xfrm_user_rcv_msg_compat() relies on fact that 32-bit messages
+ * have the same len or shorted than 64-bit ones.
+ * 32-bit translation that is bigger than 64-bit original is unexpected.
+ */
if (WARN_ON_ONCE(copy_len > payload))
copy_len = payload;
return skb;
}
- xo->flags |= XFRM_XMIT;
-
if (skb_is_gso(skb) && unlikely(x->xso.dev != dev)) {
struct sk_buff *segs;
icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
} else {
+ if (!(ip_hdr(skb)->frag_off & htons(IP_DF)))
+ goto xmit;
icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
}
return -EMSGSIZE;
}
+xmit:
xfrmi_scrub_packet(skb, !net_eq(xi->net, dev_net(dev)));
skb_dst_set(skb, dst);
skb->dev = tdev;
return err;
}
-int xfrm_output_resume(struct sk_buff *skb, int err)
+int xfrm_output_resume(struct sock *sk, struct sk_buff *skb, int err)
{
struct net *net = xs_net(skb_dst(skb)->xfrm);
while (likely((err = xfrm_output_one(skb, err)) == 0)) {
nf_reset_ct(skb);
- err = skb_dst(skb)->ops->local_out(net, skb->sk, skb);
+ err = skb_dst(skb)->ops->local_out(net, sk, skb);
if (unlikely(err != 1))
goto out;
if (!skb_dst(skb)->xfrm)
- return dst_output(net, skb->sk, skb);
+ return dst_output(net, sk, skb);
err = nf_hook(skb_dst(skb)->ops->family,
- NF_INET_POST_ROUTING, net, skb->sk, skb,
+ NF_INET_POST_ROUTING, net, sk, skb,
NULL, skb_dst(skb)->dev, xfrm_output2);
if (unlikely(err != 1))
goto out;
static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- return xfrm_output_resume(skb, 1);
+ return xfrm_output_resume(sk, skb, 1);
}
static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb)
{
int err;
+ if (x->outer_mode.encap == XFRM_MODE_BEET &&
+ ip_is_fragment(ip_hdr(skb))) {
+ net_warn_ratelimited("BEET mode doesn't support inner IPv4 fragments\n");
+ return -EAFNOSUPPORT;
+ }
+
err = xfrm4_tunnel_check_size(skb);
if (err)
return err;
static int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb)
{
#if IS_ENABLED(CONFIG_IPV6)
+ unsigned int ptr = 0;
int err;
+ if (x->outer_mode.encap == XFRM_MODE_BEET &&
+ ipv6_find_hdr(skb, &ptr, NEXTHDR_FRAGMENT, NULL, NULL) >= 0) {
+ net_warn_ratelimited("BEET mode doesn't support inner IPv6 fragments\n");
+ return -EAFNOSUPPORT;
+ }
+
err = xfrm6_tunnel_check_size(skb);
if (err)
return err;
*/
static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024;
-static __read_mostly seqcount_t xfrm_state_hash_generation = SEQCNT_ZERO(xfrm_state_hash_generation);
static struct kmem_cache *xfrm_state_cache __ro_after_init;
static DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task);
}
spin_lock_bh(&net->xfrm.xfrm_state_lock);
- write_seqcount_begin(&xfrm_state_hash_generation);
+ write_seqcount_begin(&net->xfrm.xfrm_state_hash_generation);
nhashmask = (nsize / sizeof(struct hlist_head)) - 1U;
odst = xfrm_state_deref_prot(net->xfrm.state_bydst, net);
rcu_assign_pointer(net->xfrm.state_byspi, nspi);
net->xfrm.state_hmask = nhashmask;
- write_seqcount_end(&xfrm_state_hash_generation);
+ write_seqcount_end(&net->xfrm.xfrm_state_hash_generation);
spin_unlock_bh(&net->xfrm.xfrm_state_lock);
osize = (ohashmask + 1) * sizeof(struct hlist_head);
to_put = NULL;
- sequence = read_seqcount_begin(&xfrm_state_hash_generation);
+ sequence = read_seqcount_begin(&net->xfrm.xfrm_state_hash_generation);
rcu_read_lock();
h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family);
if (to_put)
xfrm_state_put(to_put);
- if (read_seqcount_retry(&xfrm_state_hash_generation, sequence)) {
+ if (read_seqcount_retry(&net->xfrm.xfrm_state_hash_generation, sequence)) {
*err = -EAGAIN;
if (x) {
xfrm_state_put(x);
net->xfrm.state_num = 0;
INIT_WORK(&net->xfrm.state_hash_work, xfrm_hash_resize);
spin_lock_init(&net->xfrm.xfrm_state_lock);
+ seqcount_spinlock_init(&net->xfrm.xfrm_state_hash_generation,
+ &net->xfrm.xfrm_state_lock);
return 0;
out_byspi:
xdpsock_cleanup();
+ munmap(bufs, NUM_FRAMES * opt_xsk_frame_size);
+
return 0;
}
hostprogs-always-$(CONFIG_MODULE_SIG_FORMAT) += sign-file
hostprogs-always-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += extract-cert
hostprogs-always-$(CONFIG_SYSTEM_EXTRA_CERTIFICATE) += insert-sys-cert
+hostprogs-always-$(CONFIG_SYSTEM_REVOCATION_LIST) += extract-cert
HOSTCFLAGS_sorttable.o = -I$(srctree)/tools/include
HOSTCFLAGS_asn1_compiler.o = -I$(srctree)/include
CFLAGS_KASAN_NOSANITIZE := -fno-builtin
KASAN_SHADOW_OFFSET ?= $(CONFIG_KASAN_SHADOW_OFFSET)
+cc-param = $(call cc-option, -mllvm -$(1), $(call cc-option, --param $(1)))
+
+ifdef CONFIG_KASAN_STACK
+ stack_enable := 1
+else
+ stack_enable := 0
+endif
+
ifdef CONFIG_KASAN_GENERIC
ifdef CONFIG_KASAN_INLINE
CFLAGS_KASAN_MINIMAL := -fsanitize=kernel-address
-cc-param = $(call cc-option, -mllvm -$(1), $(call cc-option, --param $(1)))
-
# -fasan-shadow-offset fails without -fsanitize
CFLAGS_KASAN_SHADOW := $(call cc-option, -fsanitize=kernel-address \
-fasan-shadow-offset=$(KASAN_SHADOW_OFFSET), \
CFLAGS_KASAN := $(CFLAGS_KASAN_SHADOW) \
$(call cc-param,asan-globals=1) \
$(call cc-param,asan-instrumentation-with-call-threshold=$(call_threshold)) \
- $(call cc-param,asan-stack=$(CONFIG_KASAN_STACK)) \
+ $(call cc-param,asan-stack=$(stack_enable)) \
$(call cc-param,asan-instrument-allocas=1)
endif
ifdef CONFIG_KASAN_SW_TAGS
ifdef CONFIG_KASAN_INLINE
- instrumentation_flags := -mllvm -hwasan-mapping-offset=$(KASAN_SHADOW_OFFSET)
+ instrumentation_flags := $(call cc-param,hwasan-mapping-offset=$(KASAN_SHADOW_OFFSET))
else
- instrumentation_flags := -mllvm -hwasan-instrument-with-calls=1
+ instrumentation_flags := $(call cc-param,hwasan-instrument-with-calls=1)
endif
CFLAGS_KASAN := -fsanitize=kernel-hwaddress \
- -mllvm -hwasan-instrument-stack=$(CONFIG_KASAN_STACK) \
- -mllvm -hwasan-use-short-granules=0 \
+ $(call cc-param,hwasan-instrument-stack=$(stack_enable)) \
+ $(call cc-param,hwasan-use-short-granules=0) \
$(instrumentation_flags)
endif # CONFIG_KASAN_SW_TAGS
quiet_cmd_dtc = DTC $@
cmd_dtc = $(HOSTCC) -E $(dtc_cpp_flags) -x assembler-with-cpp -o $(dtc-tmp) $< ; \
- $(DTC) -O $(patsubst .%,%,$(suffix $@)) -o $@ -b 0 \
+ $(DTC) -o $@ -b 0 \
$(addprefix -i,$(dir $<) $(DTC_INCLUDE)) $(DTC_FLAGS) \
-d $(depfile).dtc.tmp $(dtc-tmp) ; \
cat $(depfile).pre.tmp $(depfile).dtc.tmp > $(depfile)
endef
$(obj)/%.dt.yaml: $(src)/%.dts $(DTC) $(DT_TMP_SCHEMA) FORCE
- $(call if_changed_rule,dtc,yaml)
+ $(call if_changed_rule,dtc)
dtc-tmp = $(subst $(comma),_,$(dot-target).dts.tmp)
fi
if arg_contain -E "$@"; then
- # For scripts/gcc-version.sh; This emulates GCC 20.0.0
+ # For scripts/cc-version.sh; This emulates GCC 20.0.0
if arg_contain - "$@"; then
- sed 's/^__GNUC__$/20/; s/^__GNUC_MINOR__$/0/; s/^__GNUC_PATCHLEVEL__$/0/'
+ sed -n '/^GCC/{s/__GNUC__/20/; s/__GNUC_MINOR__/0/; s/__GNUC_PATCHLEVEL__/0/; p;}'
exit 0
else
echo "no input files" >&2
echo "%gs"
exit 0
fi
+
+ # For arch/powerpc/tools/gcc-check-mprofile-kernel.sh
+ if arg_contain -m64 "$@" && arg_contain -mlittle-endian "$@" &&
+ arg_contain -mprofile-kernel "$@"; then
+ if ! test -t 0 && ! grep -q notrace; then
+ echo "_mcount"
+ fi
+ exit 0
+ fi
fi
# To set GCC_PLUGINS
echo $plugin_dir
exit 0
fi
+
+# inverted return value
+if arg_contain -D__SIZEOF_INT128__=0 "$@"; then
+ exit 1
+fi
GCC_PLUGINS_DIR = $(shell $(CC) -print-file-name=plugin)
plugin_cxxflags = -Wp,-MMD,$(depfile) $(KBUILD_HOSTCXXFLAGS) -fPIC \
+ -include $(srctree)/include/linux/compiler-version.h \
-I $(GCC_PLUGINS_DIR)/include -I $(obj) -std=gnu++11 \
-fno-rtti -fno-exceptions -fasynchronous-unwind-tables \
-ggdb -Wno-narrowing -Wno-unused-variable \
# Get the first line of the --version output.
IFS='
'
-set -- $("$@" --version)
+set -- $(LC_ALL=C "$@" --version)
# Split the line on spaces.
IFS=' '
elif [ "$1" = GNU -a "$2" = gold ]; then
echo "gold linker is not supported as it is not capable of linking the kernel proper." >&2
exit 1
-elif [ "$1" = LLD ]; then
- version=$2
- min_version=$lld_min_version
- name=LLD
- disp_name=LLD
else
- echo "$orig_args: unknown linker" >&2
- exit 1
+ while [ $# -gt 1 -a "$1" != "LLD" ]; do
+ shift
+ done
+
+ if [ "$1" = LLD ]; then
+ version=$2
+ min_version=$lld_min_version
+ name=LLD
+ disp_name=LLD
+ else
+ echo "$orig_args: unknown linker" >&2
+ exit 1
+ fi
fi
# Some distributions append a package release number, as in 2.34-4.fc32
__patchable_function_entries : { *(__patchable_function_entries) }
+#ifdef CONFIG_LTO_CLANG
/*
* With CONFIG_LTO_CLANG, LLD always enables -fdata-sections and
* -ffunction-sections, which increases the size of the final module.
}
.text : { *(.text .text.[0-9a-zA-Z_]*) }
+#endif
}
/* bring in arch-specific sections */
config GCC_PLUGIN_STRUCTLEAK_BYREF
bool "zero-init structs passed by reference (strong)"
depends on GCC_PLUGINS
- depends on !(KASAN && KASAN_STACK=1)
+ depends on !(KASAN && KASAN_STACK)
select GCC_PLUGIN_STRUCTLEAK
help
Zero-initialize any structures on the stack that may
config GCC_PLUGIN_STRUCTLEAK_BYREF_ALL
bool "zero-init anything passed by reference (very strong)"
depends on GCC_PLUGINS
- depends on !(KASAN && KASAN_STACK=1)
+ depends on !(KASAN && KASAN_STACK)
select GCC_PLUGIN_STRUCTLEAK
help
Zero-initialize any stack variables that may be passed
__u32 magic, nsmagic;
struct inode *inode = d_backing_inode(dentry);
struct user_namespace *task_ns = current_user_ns(),
- *fs_ns = inode->i_sb->s_user_ns,
- *ancestor;
+ *fs_ns = inode->i_sb->s_user_ns;
kuid_t rootid;
size_t newsize;
if (nsrootid == -1)
return -EINVAL;
- /*
- * Do not allow allow adding a v3 filesystem capability xattr
- * if the rootid field is ambiguous.
- */
- for (ancestor = task_ns->parent; ancestor; ancestor = ancestor->parent) {
- if (from_kuid(ancestor, rootid) == 0)
- return -EINVAL;
- }
-
newsize = sizeof(struct vfs_ns_cap_data);
nscap = kmalloc(newsize, GFP_ATOMIC);
if (!nscap)
{
struct public_key_signature pks;
struct signature_v2_hdr *hdr = (struct signature_v2_hdr *)sig;
+ const struct public_key *pk;
struct key *key;
int ret;
memset(&pks, 0, sizeof(pks));
pks.hash_algo = hash_algo_name[hdr->hash_algo];
- switch (hdr->hash_algo) {
- case HASH_ALGO_STREEBOG_256:
- case HASH_ALGO_STREEBOG_512:
- /* EC-RDSA and Streebog should go together. */
- pks.pkey_algo = "ecrdsa";
- pks.encoding = "raw";
- break;
- case HASH_ALGO_SM3_256:
- /* SM2 and SM3 should go together. */
- pks.pkey_algo = "sm2";
- pks.encoding = "raw";
- break;
- default:
- pks.pkey_algo = "rsa";
+
+ pk = asymmetric_key_public_key(key);
+ pks.pkey_algo = pk->pkey_algo;
+ if (!strcmp(pk->pkey_algo, "rsa"))
pks.encoding = "pkcs1";
- break;
- }
+ else if (!strncmp(pk->pkey_algo, "ecdsa-", 6))
+ /* edcsa-nist-p192 etc. */
+ pks.encoding = "x962";
+ else if (!strcmp(pk->pkey_algo, "ecrdsa") ||
+ !strcmp(pk->pkey_algo, "sm2"))
+ pks.encoding = "raw";
+ else
+ return -ENOPKG;
+
pks.digest = (u8 *)data;
pks.digest_size = datalen;
pks.s = hdr->sig;
struct rb_node *node, *parent = NULL;
struct integrity_iint_cache *iint, *test_iint;
+ /*
+ * The integrity's "iint_cache" is initialized at security_init(),
+ * unless it is not included in the ordered list of LSMs enabled
+ * on the boot command line.
+ */
+ if (!iint_cache)
+ panic("%s: lsm=integrity required.\n", __func__);
+
iint = integrity_iint_find(inode);
if (iint)
return iint;
}
/*
+ * Add an X509 cert to the revocation list.
+ */
+static __init void uefi_revocation_list_x509(const char *source,
+ const void *data, size_t len)
+{
+ add_key_to_revocation_list(data, len);
+}
+
+/*
* Return the appropriate handler for particular signature list types found in
* the UEFI db and MokListRT tables.
*/
return uefi_blacklist_x509_tbs;
if (efi_guidcmp(*sig_type, efi_cert_sha256_guid) == 0)
return uefi_blacklist_binary;
+ if (efi_guidcmp(*sig_type, efi_cert_x509_guid) == 0)
+ return uefi_revocation_list_x509;
return 0;
}
static int __init load_uefi_certs(void)
{
efi_guid_t secure_var = EFI_IMAGE_SECURITY_DATABASE_GUID;
- void *db = NULL, *dbx = NULL;
- unsigned long dbsize = 0, dbxsize = 0;
+ efi_guid_t mok_var = EFI_SHIM_LOCK_GUID;
+ void *db = NULL, *dbx = NULL, *mokx = NULL;
+ unsigned long dbsize = 0, dbxsize = 0, mokxsize = 0;
efi_status_t status;
int rc = 0;
kfree(dbx);
}
+ mokx = get_cert_list(L"MokListXRT", &mok_var, &mokxsize, &status);
+ if (!mokx) {
+ if (status == EFI_NOT_FOUND)
+ pr_debug("mokx variable wasn't found\n");
+ else
+ pr_info("Couldn't get mokx list\n");
+ } else {
+ rc = parse_efi_signature_list("UEFI:MokListXRT",
+ mokx, mokxsize,
+ get_handler_for_dbx);
+ if (rc)
+ pr_err("Couldn't parse mokx signatures %d\n", rc);
+ kfree(mokx);
+ }
+
/* Load the MokListRT certs */
rc = load_moklist_certs();
select CRYPTO_HMAC
select CRYPTO_SHA1
select CRYPTO_HASH_INFO
+ select ASN1_ENCODER
+ select OID_REGISTRY
+ select ASN1
help
This option provides support for creating, sealing, and unsealing
keys in the kernel. Trusted keys are random number symmetric keys,
#
obj-$(CONFIG_TRUSTED_KEYS) += trusted.o
+trusted-y += trusted_core.o
trusted-y += trusted_tpm1.o
+
+$(obj)/trusted_tpm2.o: $(obj)/tpm2key.asn1.h
trusted-y += trusted_tpm2.o
+trusted-y += tpm2key.asn1.o
+
+trusted-$(CONFIG_TEE) += trusted_tee.o
--- /dev/null
+---
+--- ASN.1 for TPM 2.0 keys
+---
+
+TPMKey ::= SEQUENCE {
+ type OBJECT IDENTIFIER ({tpm2_key_type}),
+ emptyAuth [0] EXPLICIT BOOLEAN OPTIONAL,
+ parent INTEGER ({tpm2_key_parent}),
+ pubkey OCTET STRING ({tpm2_key_pub}),
+ privkey OCTET STRING ({tpm2_key_priv})
+ }
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2010 IBM Corporation
+ * Copyright (c) 2019-2021, Linaro Limited
+ *
+ * See Documentation/security/keys/trusted-encrypted.rst
+ */
+
+#include <keys/user-type.h>
+#include <keys/trusted-type.h>
+#include <keys/trusted_tee.h>
+#include <keys/trusted_tpm.h>
+#include <linux/capability.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/key-type.h>
+#include <linux/module.h>
+#include <linux/parser.h>
+#include <linux/rcupdate.h>
+#include <linux/slab.h>
+#include <linux/static_call.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+
+static char *trusted_key_source;
+module_param_named(source, trusted_key_source, charp, 0);
+MODULE_PARM_DESC(source, "Select trusted keys source (tpm or tee)");
+
+static const struct trusted_key_source trusted_key_sources[] = {
+#if defined(CONFIG_TCG_TPM)
+ { "tpm", &trusted_key_tpm_ops },
+#endif
+#if defined(CONFIG_TEE)
+ { "tee", &trusted_key_tee_ops },
+#endif
+};
+
+DEFINE_STATIC_CALL_NULL(trusted_key_init, *trusted_key_sources[0].ops->init);
+DEFINE_STATIC_CALL_NULL(trusted_key_seal, *trusted_key_sources[0].ops->seal);
+DEFINE_STATIC_CALL_NULL(trusted_key_unseal,
+ *trusted_key_sources[0].ops->unseal);
+DEFINE_STATIC_CALL_NULL(trusted_key_get_random,
+ *trusted_key_sources[0].ops->get_random);
+DEFINE_STATIC_CALL_NULL(trusted_key_exit, *trusted_key_sources[0].ops->exit);
+static unsigned char migratable;
+
+enum {
+ Opt_err,
+ Opt_new, Opt_load, Opt_update,
+};
+
+static const match_table_t key_tokens = {
+ {Opt_new, "new"},
+ {Opt_load, "load"},
+ {Opt_update, "update"},
+ {Opt_err, NULL}
+};
+
+/*
+ * datablob_parse - parse the keyctl data and fill in the
+ * payload structure
+ *
+ * On success returns 0, otherwise -EINVAL.
+ */
+static int datablob_parse(char **datablob, struct trusted_key_payload *p)
+{
+ substring_t args[MAX_OPT_ARGS];
+ long keylen;
+ int ret = -EINVAL;
+ int key_cmd;
+ char *c;
+
+ /* main command */
+ c = strsep(datablob, " \t");
+ if (!c)
+ return -EINVAL;
+ key_cmd = match_token(c, key_tokens, args);
+ switch (key_cmd) {
+ case Opt_new:
+ /* first argument is key size */
+ c = strsep(datablob, " \t");
+ if (!c)
+ return -EINVAL;
+ ret = kstrtol(c, 10, &keylen);
+ if (ret < 0 || keylen < MIN_KEY_SIZE || keylen > MAX_KEY_SIZE)
+ return -EINVAL;
+ p->key_len = keylen;
+ ret = Opt_new;
+ break;
+ case Opt_load:
+ /* first argument is sealed blob */
+ c = strsep(datablob, " \t");
+ if (!c)
+ return -EINVAL;
+ p->blob_len = strlen(c) / 2;
+ if (p->blob_len > MAX_BLOB_SIZE)
+ return -EINVAL;
+ ret = hex2bin(p->blob, c, p->blob_len);
+ if (ret < 0)
+ return -EINVAL;
+ ret = Opt_load;
+ break;
+ case Opt_update:
+ ret = Opt_update;
+ break;
+ case Opt_err:
+ return -EINVAL;
+ }
+ return ret;
+}
+
+static struct trusted_key_payload *trusted_payload_alloc(struct key *key)
+{
+ struct trusted_key_payload *p = NULL;
+ int ret;
+
+ ret = key_payload_reserve(key, sizeof(*p));
+ if (ret < 0)
+ goto err;
+ p = kzalloc(sizeof(*p), GFP_KERNEL);
+ if (!p)
+ goto err;
+
+ p->migratable = migratable;
+err:
+ return p;
+}
+
+/*
+ * trusted_instantiate - create a new trusted key
+ *
+ * Unseal an existing trusted blob or, for a new key, get a
+ * random key, then seal and create a trusted key-type key,
+ * adding it to the specified keyring.
+ *
+ * On success, return 0. Otherwise return errno.
+ */
+static int trusted_instantiate(struct key *key,
+ struct key_preparsed_payload *prep)
+{
+ struct trusted_key_payload *payload = NULL;
+ size_t datalen = prep->datalen;
+ char *datablob, *orig_datablob;
+ int ret = 0;
+ int key_cmd;
+ size_t key_len;
+
+ if (datalen <= 0 || datalen > 32767 || !prep->data)
+ return -EINVAL;
+
+ orig_datablob = datablob = kmalloc(datalen + 1, GFP_KERNEL);
+ if (!datablob)
+ return -ENOMEM;
+ memcpy(datablob, prep->data, datalen);
+ datablob[datalen] = '\0';
+
+ payload = trusted_payload_alloc(key);
+ if (!payload) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ key_cmd = datablob_parse(&datablob, payload);
+ if (key_cmd < 0) {
+ ret = key_cmd;
+ goto out;
+ }
+
+ dump_payload(payload);
+
+ switch (key_cmd) {
+ case Opt_load:
+ ret = static_call(trusted_key_unseal)(payload, datablob);
+ dump_payload(payload);
+ if (ret < 0)
+ pr_info("key_unseal failed (%d)\n", ret);
+ break;
+ case Opt_new:
+ key_len = payload->key_len;
+ ret = static_call(trusted_key_get_random)(payload->key,
+ key_len);
+ if (ret < 0)
+ goto out;
+
+ if (ret != key_len) {
+ pr_info("key_create failed (%d)\n", ret);
+ ret = -EIO;
+ goto out;
+ }
+
+ ret = static_call(trusted_key_seal)(payload, datablob);
+ if (ret < 0)
+ pr_info("key_seal failed (%d)\n", ret);
+ break;
+ default:
+ ret = -EINVAL;
+ }
+out:
+ kfree_sensitive(orig_datablob);
+ if (!ret)
+ rcu_assign_keypointer(key, payload);
+ else
+ kfree_sensitive(payload);
+ return ret;
+}
+
+static void trusted_rcu_free(struct rcu_head *rcu)
+{
+ struct trusted_key_payload *p;
+
+ p = container_of(rcu, struct trusted_key_payload, rcu);
+ kfree_sensitive(p);
+}
+
+/*
+ * trusted_update - reseal an existing key with new PCR values
+ */
+static int trusted_update(struct key *key, struct key_preparsed_payload *prep)
+{
+ struct trusted_key_payload *p;
+ struct trusted_key_payload *new_p;
+ size_t datalen = prep->datalen;
+ char *datablob, *orig_datablob;
+ int ret = 0;
+
+ if (key_is_negative(key))
+ return -ENOKEY;
+ p = key->payload.data[0];
+ if (!p->migratable)
+ return -EPERM;
+ if (datalen <= 0 || datalen > 32767 || !prep->data)
+ return -EINVAL;
+
+ orig_datablob = datablob = kmalloc(datalen + 1, GFP_KERNEL);
+ if (!datablob)
+ return -ENOMEM;
+
+ new_p = trusted_payload_alloc(key);
+ if (!new_p) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ memcpy(datablob, prep->data, datalen);
+ datablob[datalen] = '\0';
+ ret = datablob_parse(&datablob, new_p);
+ if (ret != Opt_update) {
+ ret = -EINVAL;
+ kfree_sensitive(new_p);
+ goto out;
+ }
+
+ /* copy old key values, and reseal with new pcrs */
+ new_p->migratable = p->migratable;
+ new_p->key_len = p->key_len;
+ memcpy(new_p->key, p->key, p->key_len);
+ dump_payload(p);
+ dump_payload(new_p);
+
+ ret = static_call(trusted_key_seal)(new_p, datablob);
+ if (ret < 0) {
+ pr_info("key_seal failed (%d)\n", ret);
+ kfree_sensitive(new_p);
+ goto out;
+ }
+
+ rcu_assign_keypointer(key, new_p);
+ call_rcu(&p->rcu, trusted_rcu_free);
+out:
+ kfree_sensitive(orig_datablob);
+ return ret;
+}
+
+/*
+ * trusted_read - copy the sealed blob data to userspace in hex.
+ * On success, return to userspace the trusted key datablob size.
+ */
+static long trusted_read(const struct key *key, char *buffer,
+ size_t buflen)
+{
+ const struct trusted_key_payload *p;
+ char *bufp;
+ int i;
+
+ p = dereference_key_locked(key);
+ if (!p)
+ return -EINVAL;
+
+ if (buffer && buflen >= 2 * p->blob_len) {
+ bufp = buffer;
+ for (i = 0; i < p->blob_len; i++)
+ bufp = hex_byte_pack(bufp, p->blob[i]);
+ }
+ return 2 * p->blob_len;
+}
+
+/*
+ * trusted_destroy - clear and free the key's payload
+ */
+static void trusted_destroy(struct key *key)
+{
+ kfree_sensitive(key->payload.data[0]);
+}
+
+struct key_type key_type_trusted = {
+ .name = "trusted",
+ .instantiate = trusted_instantiate,
+ .update = trusted_update,
+ .destroy = trusted_destroy,
+ .describe = user_describe,
+ .read = trusted_read,
+};
+EXPORT_SYMBOL_GPL(key_type_trusted);
+
+static int __init init_trusted(void)
+{
+ int i, ret = 0;
+
+ for (i = 0; i < ARRAY_SIZE(trusted_key_sources); i++) {
+ if (trusted_key_source &&
+ strncmp(trusted_key_source, trusted_key_sources[i].name,
+ strlen(trusted_key_sources[i].name)))
+ continue;
+
+ static_call_update(trusted_key_init,
+ trusted_key_sources[i].ops->init);
+ static_call_update(trusted_key_seal,
+ trusted_key_sources[i].ops->seal);
+ static_call_update(trusted_key_unseal,
+ trusted_key_sources[i].ops->unseal);
+ static_call_update(trusted_key_get_random,
+ trusted_key_sources[i].ops->get_random);
+ static_call_update(trusted_key_exit,
+ trusted_key_sources[i].ops->exit);
+ migratable = trusted_key_sources[i].ops->migratable;
+
+ ret = static_call(trusted_key_init)();
+ if (!ret)
+ break;
+ }
+
+ /*
+ * encrypted_keys.ko depends on successful load of this module even if
+ * trusted key implementation is not found.
+ */
+ if (ret == -ENODEV)
+ return 0;
+
+ return ret;
+}
+
+static void __exit cleanup_trusted(void)
+{
+ static_call(trusted_key_exit)();
+}
+
+late_initcall(init_trusted);
+module_exit(cleanup_trusted);
+
+MODULE_LICENSE("GPL");
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019-2021 Linaro Ltd.
+ *
+ * Author:
+ * Sumit Garg <sumit.garg@linaro.org>
+ */
+
+#include <linux/err.h>
+#include <linux/key-type.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/tee_drv.h>
+#include <linux/uuid.h>
+
+#include <keys/trusted_tee.h>
+
+#define DRIVER_NAME "trusted-key-tee"
+
+/*
+ * Get random data for symmetric key
+ *
+ * [out] memref[0] Random data
+ */
+#define TA_CMD_GET_RANDOM 0x0
+
+/*
+ * Seal trusted key using hardware unique key
+ *
+ * [in] memref[0] Plain key
+ * [out] memref[1] Sealed key datablob
+ */
+#define TA_CMD_SEAL 0x1
+
+/*
+ * Unseal trusted key using hardware unique key
+ *
+ * [in] memref[0] Sealed key datablob
+ * [out] memref[1] Plain key
+ */
+#define TA_CMD_UNSEAL 0x2
+
+/**
+ * struct trusted_key_tee_private - TEE Trusted key private data
+ * @dev: TEE based Trusted key device.
+ * @ctx: TEE context handler.
+ * @session_id: Trusted key TA session identifier.
+ * @shm_pool: Memory pool shared with TEE device.
+ */
+struct trusted_key_tee_private {
+ struct device *dev;
+ struct tee_context *ctx;
+ u32 session_id;
+ struct tee_shm *shm_pool;
+};
+
+static struct trusted_key_tee_private pvt_data;
+
+/*
+ * Have the TEE seal(encrypt) the symmetric key
+ */
+static int trusted_tee_seal(struct trusted_key_payload *p, char *datablob)
+{
+ int ret;
+ struct tee_ioctl_invoke_arg inv_arg;
+ struct tee_param param[4];
+ struct tee_shm *reg_shm_in = NULL, *reg_shm_out = NULL;
+
+ memset(&inv_arg, 0, sizeof(inv_arg));
+ memset(¶m, 0, sizeof(param));
+
+ reg_shm_in = tee_shm_register(pvt_data.ctx, (unsigned long)p->key,
+ p->key_len, TEE_SHM_DMA_BUF |
+ TEE_SHM_KERNEL_MAPPED);
+ if (IS_ERR(reg_shm_in)) {
+ dev_err(pvt_data.dev, "key shm register failed\n");
+ return PTR_ERR(reg_shm_in);
+ }
+
+ reg_shm_out = tee_shm_register(pvt_data.ctx, (unsigned long)p->blob,
+ sizeof(p->blob), TEE_SHM_DMA_BUF |
+ TEE_SHM_KERNEL_MAPPED);
+ if (IS_ERR(reg_shm_out)) {
+ dev_err(pvt_data.dev, "blob shm register failed\n");
+ ret = PTR_ERR(reg_shm_out);
+ goto out;
+ }
+
+ inv_arg.func = TA_CMD_SEAL;
+ inv_arg.session = pvt_data.session_id;
+ inv_arg.num_params = 4;
+
+ param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT;
+ param[0].u.memref.shm = reg_shm_in;
+ param[0].u.memref.size = p->key_len;
+ param[0].u.memref.shm_offs = 0;
+ param[1].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT;
+ param[1].u.memref.shm = reg_shm_out;
+ param[1].u.memref.size = sizeof(p->blob);
+ param[1].u.memref.shm_offs = 0;
+
+ ret = tee_client_invoke_func(pvt_data.ctx, &inv_arg, param);
+ if ((ret < 0) || (inv_arg.ret != 0)) {
+ dev_err(pvt_data.dev, "TA_CMD_SEAL invoke err: %x\n",
+ inv_arg.ret);
+ ret = -EFAULT;
+ } else {
+ p->blob_len = param[1].u.memref.size;
+ }
+
+out:
+ if (reg_shm_out)
+ tee_shm_free(reg_shm_out);
+ if (reg_shm_in)
+ tee_shm_free(reg_shm_in);
+
+ return ret;
+}
+
+/*
+ * Have the TEE unseal(decrypt) the symmetric key
+ */
+static int trusted_tee_unseal(struct trusted_key_payload *p, char *datablob)
+{
+ int ret;
+ struct tee_ioctl_invoke_arg inv_arg;
+ struct tee_param param[4];
+ struct tee_shm *reg_shm_in = NULL, *reg_shm_out = NULL;
+
+ memset(&inv_arg, 0, sizeof(inv_arg));
+ memset(¶m, 0, sizeof(param));
+
+ reg_shm_in = tee_shm_register(pvt_data.ctx, (unsigned long)p->blob,
+ p->blob_len, TEE_SHM_DMA_BUF |
+ TEE_SHM_KERNEL_MAPPED);
+ if (IS_ERR(reg_shm_in)) {
+ dev_err(pvt_data.dev, "blob shm register failed\n");
+ return PTR_ERR(reg_shm_in);
+ }
+
+ reg_shm_out = tee_shm_register(pvt_data.ctx, (unsigned long)p->key,
+ sizeof(p->key), TEE_SHM_DMA_BUF |
+ TEE_SHM_KERNEL_MAPPED);
+ if (IS_ERR(reg_shm_out)) {
+ dev_err(pvt_data.dev, "key shm register failed\n");
+ ret = PTR_ERR(reg_shm_out);
+ goto out;
+ }
+
+ inv_arg.func = TA_CMD_UNSEAL;
+ inv_arg.session = pvt_data.session_id;
+ inv_arg.num_params = 4;
+
+ param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT;
+ param[0].u.memref.shm = reg_shm_in;
+ param[0].u.memref.size = p->blob_len;
+ param[0].u.memref.shm_offs = 0;
+ param[1].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT;
+ param[1].u.memref.shm = reg_shm_out;
+ param[1].u.memref.size = sizeof(p->key);
+ param[1].u.memref.shm_offs = 0;
+
+ ret = tee_client_invoke_func(pvt_data.ctx, &inv_arg, param);
+ if ((ret < 0) || (inv_arg.ret != 0)) {
+ dev_err(pvt_data.dev, "TA_CMD_UNSEAL invoke err: %x\n",
+ inv_arg.ret);
+ ret = -EFAULT;
+ } else {
+ p->key_len = param[1].u.memref.size;
+ }
+
+out:
+ if (reg_shm_out)
+ tee_shm_free(reg_shm_out);
+ if (reg_shm_in)
+ tee_shm_free(reg_shm_in);
+
+ return ret;
+}
+
+/*
+ * Have the TEE generate random symmetric key
+ */
+static int trusted_tee_get_random(unsigned char *key, size_t key_len)
+{
+ int ret;
+ struct tee_ioctl_invoke_arg inv_arg;
+ struct tee_param param[4];
+ struct tee_shm *reg_shm = NULL;
+
+ memset(&inv_arg, 0, sizeof(inv_arg));
+ memset(¶m, 0, sizeof(param));
+
+ reg_shm = tee_shm_register(pvt_data.ctx, (unsigned long)key, key_len,
+ TEE_SHM_DMA_BUF | TEE_SHM_KERNEL_MAPPED);
+ if (IS_ERR(reg_shm)) {
+ dev_err(pvt_data.dev, "key shm register failed\n");
+ return PTR_ERR(reg_shm);
+ }
+
+ inv_arg.func = TA_CMD_GET_RANDOM;
+ inv_arg.session = pvt_data.session_id;
+ inv_arg.num_params = 4;
+
+ param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT;
+ param[0].u.memref.shm = reg_shm;
+ param[0].u.memref.size = key_len;
+ param[0].u.memref.shm_offs = 0;
+
+ ret = tee_client_invoke_func(pvt_data.ctx, &inv_arg, param);
+ if ((ret < 0) || (inv_arg.ret != 0)) {
+ dev_err(pvt_data.dev, "TA_CMD_GET_RANDOM invoke err: %x\n",
+ inv_arg.ret);
+ ret = -EFAULT;
+ } else {
+ ret = param[0].u.memref.size;
+ }
+
+ tee_shm_free(reg_shm);
+
+ return ret;
+}
+
+static int optee_ctx_match(struct tee_ioctl_version_data *ver, const void *data)
+{
+ if (ver->impl_id == TEE_IMPL_ID_OPTEE)
+ return 1;
+ else
+ return 0;
+}
+
+static int trusted_key_probe(struct device *dev)
+{
+ struct tee_client_device *rng_device = to_tee_client_device(dev);
+ int ret;
+ struct tee_ioctl_open_session_arg sess_arg;
+
+ memset(&sess_arg, 0, sizeof(sess_arg));
+
+ pvt_data.ctx = tee_client_open_context(NULL, optee_ctx_match, NULL,
+ NULL);
+ if (IS_ERR(pvt_data.ctx))
+ return -ENODEV;
+
+ memcpy(sess_arg.uuid, rng_device->id.uuid.b, TEE_IOCTL_UUID_LEN);
+ sess_arg.clnt_login = TEE_IOCTL_LOGIN_REE_KERNEL;
+ sess_arg.num_params = 0;
+
+ ret = tee_client_open_session(pvt_data.ctx, &sess_arg, NULL);
+ if ((ret < 0) || (sess_arg.ret != 0)) {
+ dev_err(dev, "tee_client_open_session failed, err: %x\n",
+ sess_arg.ret);
+ ret = -EINVAL;
+ goto out_ctx;
+ }
+ pvt_data.session_id = sess_arg.session;
+
+ ret = register_key_type(&key_type_trusted);
+ if (ret < 0)
+ goto out_sess;
+
+ pvt_data.dev = dev;
+
+ return 0;
+
+out_sess:
+ tee_client_close_session(pvt_data.ctx, pvt_data.session_id);
+out_ctx:
+ tee_client_close_context(pvt_data.ctx);
+
+ return ret;
+}
+
+static int trusted_key_remove(struct device *dev)
+{
+ unregister_key_type(&key_type_trusted);
+ tee_client_close_session(pvt_data.ctx, pvt_data.session_id);
+ tee_client_close_context(pvt_data.ctx);
+
+ return 0;
+}
+
+static const struct tee_client_device_id trusted_key_id_table[] = {
+ {UUID_INIT(0xf04a0fe7, 0x1f5d, 0x4b9b,
+ 0xab, 0xf7, 0x61, 0x9b, 0x85, 0xb4, 0xce, 0x8c)},
+ {}
+};
+MODULE_DEVICE_TABLE(tee, trusted_key_id_table);
+
+static struct tee_client_driver trusted_key_driver = {
+ .id_table = trusted_key_id_table,
+ .driver = {
+ .name = DRIVER_NAME,
+ .bus = &tee_bus_type,
+ .probe = trusted_key_probe,
+ .remove = trusted_key_remove,
+ },
+};
+
+static int trusted_tee_init(void)
+{
+ return driver_register(&trusted_key_driver.driver);
+}
+
+static void trusted_tee_exit(void)
+{
+ driver_unregister(&trusted_key_driver.driver);
+}
+
+struct trusted_key_ops trusted_key_tee_ops = {
+ .migratable = 0, /* non-migratable */
+ .init = trusted_tee_init,
+ .seal = trusted_tee_seal,
+ .unseal = trusted_tee_unseal,
+ .get_random = trusted_tee_get_random,
+ .exit = trusted_tee_exit,
+};
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2010 IBM Corporation
- *
- * Author:
- * David Safford <safford@us.ibm.com>
+ * Copyright (c) 2019-2021, Linaro Limited
*
* See Documentation/security/keys/trusted-encrypted.rst
*/
#include <crypto/hash_info.h>
-#include <linux/uaccess.h>
-#include <linux/module.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/parser.h>
#include <linux/string.h>
#include <linux/err.h>
-#include <keys/user-type.h>
#include <keys/trusted-type.h>
#include <linux/key-type.h>
-#include <linux/rcupdate.h>
#include <linux/crypto.h>
#include <crypto/hash.h>
#include <crypto/sha1.h>
-#include <linux/capability.h>
#include <linux/tpm.h>
#include <linux/tpm_command.h>
sdesc = init_sdesc(hashalg);
if (IS_ERR(sdesc)) {
- pr_info("trusted_key: can't alloc %s\n", hash_alg);
+ pr_info("can't alloc %s\n", hash_alg);
return PTR_ERR(sdesc);
}
sdesc = init_sdesc(hmacalg);
if (IS_ERR(sdesc)) {
- pr_info("trusted_key: can't alloc %s\n", hmac_alg);
+ pr_info("can't alloc %s\n", hmac_alg);
return PTR_ERR(sdesc);
}
sdesc = init_sdesc(hashalg);
if (IS_ERR(sdesc)) {
- pr_info("trusted_key: can't alloc %s\n", hash_alg);
+ pr_info("can't alloc %s\n", hash_alg);
return PTR_ERR(sdesc);
}
sdesc = init_sdesc(hashalg);
if (IS_ERR(sdesc)) {
- pr_info("trusted_key: can't alloc %s\n", hash_alg);
+ pr_info("can't alloc %s\n", hash_alg);
return PTR_ERR(sdesc);
}
ret = crypto_shash_init(&sdesc->shash);
sdesc = init_sdesc(hashalg);
if (IS_ERR(sdesc)) {
- pr_info("trusted_key: can't alloc %s\n", hash_alg);
+ pr_info("can't alloc %s\n", hash_alg);
return PTR_ERR(sdesc);
}
ret = crypto_shash_init(&sdesc->shash);
/* sessions for unsealing key and data */
ret = oiap(tb, &authhandle1, enonce1);
if (ret < 0) {
- pr_info("trusted_key: oiap failed (%d)\n", ret);
+ pr_info("oiap failed (%d)\n", ret);
return ret;
}
ret = oiap(tb, &authhandle2, enonce2);
if (ret < 0) {
- pr_info("trusted_key: oiap failed (%d)\n", ret);
+ pr_info("oiap failed (%d)\n", ret);
return ret;
}
return ret;
if (ret != TPM_NONCE_SIZE) {
- pr_info("trusted_key: tpm_get_random failed (%d)\n", ret);
+ pr_info("tpm_get_random failed (%d)\n", ret);
return -EIO;
}
ret = TSS_authhmac(authdata1, keyauth, TPM_NONCE_SIZE,
ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE);
if (ret < 0) {
- pr_info("trusted_key: authhmac failed (%d)\n", ret);
+ pr_info("authhmac failed (%d)\n", ret);
return ret;
}
*datalen, TPM_DATA_OFFSET + sizeof(uint32_t), 0,
0);
if (ret < 0) {
- pr_info("trusted_key: TSS_checkhmac2 failed (%d)\n", ret);
+ pr_info("TSS_checkhmac2 failed (%d)\n", ret);
return ret;
}
memcpy(data, tb->data + TPM_DATA_OFFSET + sizeof(uint32_t), *datalen);
p->key, p->key_len + 1, p->blob, &p->blob_len,
o->blobauth, o->pcrinfo, o->pcrinfo_len);
if (ret < 0)
- pr_info("trusted_key: srkseal failed (%d)\n", ret);
+ pr_info("srkseal failed (%d)\n", ret);
tpm_buf_destroy(&tb);
return ret;
ret = tpm_unseal(&tb, o->keyhandle, o->keyauth, p->blob, p->blob_len,
o->blobauth, p->key, &p->key_len);
if (ret < 0)
- pr_info("trusted_key: srkunseal failed (%d)\n", ret);
+ pr_info("srkunseal failed (%d)\n", ret);
else
/* pull migratable flag out of sealed key */
p->migratable = p->key[--p->key_len];
enum {
Opt_err,
- Opt_new, Opt_load, Opt_update,
Opt_keyhandle, Opt_keyauth, Opt_blobauth,
Opt_pcrinfo, Opt_pcrlock, Opt_migratable,
Opt_hash,
};
static const match_table_t key_tokens = {
- {Opt_new, "new"},
- {Opt_load, "load"},
- {Opt_update, "update"},
{Opt_keyhandle, "keyhandle=%s"},
{Opt_keyauth, "keyauth=%s"},
{Opt_blobauth, "blobauth=%s"},
opt->hash = tpm2 ? HASH_ALGO_SHA256 : HASH_ALGO_SHA1;
+ if (!c)
+ return 0;
+
while ((p = strsep(&c, " \t"))) {
if (*p == '\0' || *p == ' ' || *p == '\t')
continue;
return -EINVAL;
break;
case Opt_blobauth:
- if (strlen(args[0].from) != 2 * SHA1_DIGEST_SIZE)
- return -EINVAL;
- res = hex2bin(opt->blobauth, args[0].from,
- SHA1_DIGEST_SIZE);
- if (res < 0)
- return -EINVAL;
+ /*
+ * TPM 1.2 authorizations are sha1 hashes passed in as
+ * hex strings. TPM 2.0 authorizations are simple
+ * passwords (although it can take a hash as well)
+ */
+ opt->blobauth_len = strlen(args[0].from);
+
+ if (opt->blobauth_len == 2 * TPM_DIGEST_SIZE) {
+ res = hex2bin(opt->blobauth, args[0].from,
+ TPM_DIGEST_SIZE);
+ if (res < 0)
+ return -EINVAL;
+
+ opt->blobauth_len = TPM_DIGEST_SIZE;
+ break;
+ }
+
+ if (tpm2 && opt->blobauth_len <= sizeof(opt->blobauth)) {
+ memcpy(opt->blobauth, args[0].from,
+ opt->blobauth_len);
+ break;
+ }
+
+ return -EINVAL;
+
break;
+
case Opt_migratable:
if (*args[0].from == '0')
pay->migratable = 0;
if (i == HASH_ALGO__LAST)
return -EINVAL;
if (!tpm2 && i != HASH_ALGO_SHA1) {
- pr_info("trusted_key: TPM 1.x only supports SHA-1.\n");
+ pr_info("TPM 1.x only supports SHA-1.\n");
return -EINVAL;
}
break;
return 0;
}
-/*
- * datablob_parse - parse the keyctl data and fill in the
- * payload and options structures
- *
- * On success returns 0, otherwise -EINVAL.
- */
-static int datablob_parse(char *datablob, struct trusted_key_payload *p,
- struct trusted_key_options *o)
-{
- substring_t args[MAX_OPT_ARGS];
- long keylen;
- int ret = -EINVAL;
- int key_cmd;
- char *c;
-
- /* main command */
- c = strsep(&datablob, " \t");
- if (!c)
- return -EINVAL;
- key_cmd = match_token(c, key_tokens, args);
- switch (key_cmd) {
- case Opt_new:
- /* first argument is key size */
- c = strsep(&datablob, " \t");
- if (!c)
- return -EINVAL;
- ret = kstrtol(c, 10, &keylen);
- if (ret < 0 || keylen < MIN_KEY_SIZE || keylen > MAX_KEY_SIZE)
- return -EINVAL;
- p->key_len = keylen;
- ret = getoptions(datablob, p, o);
- if (ret < 0)
- return ret;
- ret = Opt_new;
- break;
- case Opt_load:
- /* first argument is sealed blob */
- c = strsep(&datablob, " \t");
- if (!c)
- return -EINVAL;
- p->blob_len = strlen(c) / 2;
- if (p->blob_len > MAX_BLOB_SIZE)
- return -EINVAL;
- ret = hex2bin(p->blob, c, p->blob_len);
- if (ret < 0)
- return -EINVAL;
- ret = getoptions(datablob, p, o);
- if (ret < 0)
- return ret;
- ret = Opt_load;
- break;
- case Opt_update:
- /* all arguments are options */
- ret = getoptions(datablob, p, o);
- if (ret < 0)
- return ret;
- ret = Opt_update;
- break;
- case Opt_err:
- return -EINVAL;
- break;
- }
- return ret;
-}
-
static struct trusted_key_options *trusted_options_alloc(void)
{
struct trusted_key_options *options;
return options;
}
-static struct trusted_key_payload *trusted_payload_alloc(struct key *key)
+static int trusted_tpm_seal(struct trusted_key_payload *p, char *datablob)
{
- struct trusted_key_payload *p = NULL;
- int ret;
-
- ret = key_payload_reserve(key, sizeof *p);
- if (ret < 0)
- return p;
- p = kzalloc(sizeof *p, GFP_KERNEL);
- if (p)
- p->migratable = 1; /* migratable by default */
- return p;
-}
-
-/*
- * trusted_instantiate - create a new trusted key
- *
- * Unseal an existing trusted blob or, for a new key, get a
- * random key, then seal and create a trusted key-type key,
- * adding it to the specified keyring.
- *
- * On success, return 0. Otherwise return errno.
- */
-static int trusted_instantiate(struct key *key,
- struct key_preparsed_payload *prep)
-{
- struct trusted_key_payload *payload = NULL;
struct trusted_key_options *options = NULL;
- size_t datalen = prep->datalen;
- char *datablob;
int ret = 0;
- int key_cmd;
- size_t key_len;
int tpm2;
tpm2 = tpm_is_tpm2(chip);
if (tpm2 < 0)
return tpm2;
- if (datalen <= 0 || datalen > 32767 || !prep->data)
- return -EINVAL;
-
- datablob = kmalloc(datalen + 1, GFP_KERNEL);
- if (!datablob)
+ options = trusted_options_alloc();
+ if (!options)
return -ENOMEM;
- memcpy(datablob, prep->data, datalen);
- datablob[datalen] = '\0';
- options = trusted_options_alloc();
- if (!options) {
- ret = -ENOMEM;
- goto out;
- }
- payload = trusted_payload_alloc(key);
- if (!payload) {
- ret = -ENOMEM;
+ ret = getoptions(datablob, p, options);
+ if (ret < 0)
goto out;
- }
+ dump_options(options);
- key_cmd = datablob_parse(datablob, payload, options);
- if (key_cmd < 0) {
- ret = key_cmd;
+ if (!options->keyhandle && !tpm2) {
+ ret = -EINVAL;
goto out;
}
- if (!options->keyhandle) {
- ret = -EINVAL;
+ if (tpm2)
+ ret = tpm2_seal_trusted(chip, p, options);
+ else
+ ret = key_seal(p, options);
+ if (ret < 0) {
+ pr_info("key_seal failed (%d)\n", ret);
goto out;
}
- dump_payload(payload);
- dump_options(options);
-
- switch (key_cmd) {
- case Opt_load:
- if (tpm2)
- ret = tpm2_unseal_trusted(chip, payload, options);
- else
- ret = key_unseal(payload, options);
- dump_payload(payload);
- dump_options(options);
- if (ret < 0)
- pr_info("trusted_key: key_unseal failed (%d)\n", ret);
- break;
- case Opt_new:
- key_len = payload->key_len;
- ret = tpm_get_random(chip, payload->key, key_len);
- if (ret < 0)
- goto out;
-
- if (ret != key_len) {
- pr_info("trusted_key: key_create failed (%d)\n", ret);
- ret = -EIO;
+ if (options->pcrlock) {
+ ret = pcrlock(options->pcrlock);
+ if (ret < 0) {
+ pr_info("pcrlock failed (%d)\n", ret);
goto out;
}
- if (tpm2)
- ret = tpm2_seal_trusted(chip, payload, options);
- else
- ret = key_seal(payload, options);
- if (ret < 0)
- pr_info("trusted_key: key_seal failed (%d)\n", ret);
- break;
- default:
- ret = -EINVAL;
- goto out;
}
- if (!ret && options->pcrlock)
- ret = pcrlock(options->pcrlock);
out:
- kfree_sensitive(datablob);
kfree_sensitive(options);
- if (!ret)
- rcu_assign_keypointer(key, payload);
- else
- kfree_sensitive(payload);
return ret;
}
-static void trusted_rcu_free(struct rcu_head *rcu)
+static int trusted_tpm_unseal(struct trusted_key_payload *p, char *datablob)
{
- struct trusted_key_payload *p;
-
- p = container_of(rcu, struct trusted_key_payload, rcu);
- kfree_sensitive(p);
-}
-
-/*
- * trusted_update - reseal an existing key with new PCR values
- */
-static int trusted_update(struct key *key, struct key_preparsed_payload *prep)
-{
- struct trusted_key_payload *p;
- struct trusted_key_payload *new_p;
- struct trusted_key_options *new_o;
- size_t datalen = prep->datalen;
- char *datablob;
+ struct trusted_key_options *options = NULL;
int ret = 0;
+ int tpm2;
- if (key_is_negative(key))
- return -ENOKEY;
- p = key->payload.data[0];
- if (!p->migratable)
- return -EPERM;
- if (datalen <= 0 || datalen > 32767 || !prep->data)
- return -EINVAL;
+ tpm2 = tpm_is_tpm2(chip);
+ if (tpm2 < 0)
+ return tpm2;
- datablob = kmalloc(datalen + 1, GFP_KERNEL);
- if (!datablob)
+ options = trusted_options_alloc();
+ if (!options)
return -ENOMEM;
- new_o = trusted_options_alloc();
- if (!new_o) {
- ret = -ENOMEM;
- goto out;
- }
- new_p = trusted_payload_alloc(key);
- if (!new_p) {
- ret = -ENOMEM;
- goto out;
- }
- memcpy(datablob, prep->data, datalen);
- datablob[datalen] = '\0';
- ret = datablob_parse(datablob, new_p, new_o);
- if (ret != Opt_update) {
- ret = -EINVAL;
- kfree_sensitive(new_p);
+ ret = getoptions(datablob, p, options);
+ if (ret < 0)
goto out;
- }
+ dump_options(options);
- if (!new_o->keyhandle) {
+ if (!options->keyhandle && !tpm2) {
ret = -EINVAL;
- kfree_sensitive(new_p);
goto out;
}
- /* copy old key values, and reseal with new pcrs */
- new_p->migratable = p->migratable;
- new_p->key_len = p->key_len;
- memcpy(new_p->key, p->key, p->key_len);
- dump_payload(p);
- dump_payload(new_p);
+ if (tpm2)
+ ret = tpm2_unseal_trusted(chip, p, options);
+ else
+ ret = key_unseal(p, options);
+ if (ret < 0)
+ pr_info("key_unseal failed (%d)\n", ret);
- ret = key_seal(new_p, new_o);
- if (ret < 0) {
- pr_info("trusted_key: key_seal failed (%d)\n", ret);
- kfree_sensitive(new_p);
- goto out;
- }
- if (new_o->pcrlock) {
- ret = pcrlock(new_o->pcrlock);
+ if (options->pcrlock) {
+ ret = pcrlock(options->pcrlock);
if (ret < 0) {
- pr_info("trusted_key: pcrlock failed (%d)\n", ret);
- kfree_sensitive(new_p);
+ pr_info("pcrlock failed (%d)\n", ret);
goto out;
}
}
- rcu_assign_keypointer(key, new_p);
- call_rcu(&p->rcu, trusted_rcu_free);
out:
- kfree_sensitive(datablob);
- kfree_sensitive(new_o);
+ kfree_sensitive(options);
return ret;
}
-/*
- * trusted_read - copy the sealed blob data to userspace in hex.
- * On success, return to userspace the trusted key datablob size.
- */
-static long trusted_read(const struct key *key, char *buffer,
- size_t buflen)
-{
- const struct trusted_key_payload *p;
- char *bufp;
- int i;
-
- p = dereference_key_locked(key);
- if (!p)
- return -EINVAL;
-
- if (buffer && buflen >= 2 * p->blob_len) {
- bufp = buffer;
- for (i = 0; i < p->blob_len; i++)
- bufp = hex_byte_pack(bufp, p->blob[i]);
- }
- return 2 * p->blob_len;
-}
-
-/*
- * trusted_destroy - clear and free the key's payload
- */
-static void trusted_destroy(struct key *key)
+static int trusted_tpm_get_random(unsigned char *key, size_t key_len)
{
- kfree_sensitive(key->payload.data[0]);
+ return tpm_get_random(chip, key, key_len);
}
-struct key_type key_type_trusted = {
- .name = "trusted",
- .instantiate = trusted_instantiate,
- .update = trusted_update,
- .destroy = trusted_destroy,
- .describe = user_describe,
- .read = trusted_read,
-};
-
-EXPORT_SYMBOL_GPL(key_type_trusted);
-
static void trusted_shash_release(void)
{
if (hashalg)
hmacalg = crypto_alloc_shash(hmac_alg, 0, 0);
if (IS_ERR(hmacalg)) {
- pr_info("trusted_key: could not allocate crypto %s\n",
+ pr_info("could not allocate crypto %s\n",
hmac_alg);
return PTR_ERR(hmacalg);
}
hashalg = crypto_alloc_shash(hash_alg, 0, 0);
if (IS_ERR(hashalg)) {
- pr_info("trusted_key: could not allocate crypto %s\n",
+ pr_info("could not allocate crypto %s\n",
hash_alg);
ret = PTR_ERR(hashalg);
goto hashalg_fail;
return 0;
}
-static int __init init_trusted(void)
+static int __init trusted_tpm_init(void)
{
int ret;
- /* encrypted_keys.ko depends on successful load of this module even if
- * TPM is not used.
- */
chip = tpm_default_chip();
if (!chip)
- return 0;
+ return -ENODEV;
ret = init_digests();
if (ret < 0)
return ret;
}
-static void __exit cleanup_trusted(void)
+static void trusted_tpm_exit(void)
{
if (chip) {
put_device(&chip->dev);
}
}
-late_initcall(init_trusted);
-module_exit(cleanup_trusted);
-
-MODULE_LICENSE("GPL");
+struct trusted_key_ops trusted_key_tpm_ops = {
+ .migratable = 1, /* migratable by default */
+ .init = trusted_tpm_init,
+ .seal = trusted_tpm_seal,
+ .unseal = trusted_tpm_unseal,
+ .get_random = trusted_tpm_get_random,
+ .exit = trusted_tpm_exit,
+};
* Copyright (C) 2014 Intel Corporation
*/
+#include <linux/asn1_encoder.h>
+#include <linux/oid_registry.h>
#include <linux/string.h>
#include <linux/err.h>
#include <linux/tpm.h>
#include <keys/trusted-type.h>
#include <keys/trusted_tpm.h>
+#include <asm/unaligned.h>
+
+#include "tpm2key.asn1.h"
+
static struct tpm2_hash tpm2_hash_map[] = {
{HASH_ALGO_SHA1, TPM_ALG_SHA1},
{HASH_ALGO_SHA256, TPM_ALG_SHA256},
{HASH_ALGO_SM3_256, TPM_ALG_SM3_256},
};
+static u32 tpm2key_oid[] = { 2, 23, 133, 10, 1, 5 };
+
+static int tpm2_key_encode(struct trusted_key_payload *payload,
+ struct trusted_key_options *options,
+ u8 *src, u32 len)
+{
+ const int SCRATCH_SIZE = PAGE_SIZE;
+ u8 *scratch = kmalloc(SCRATCH_SIZE, GFP_KERNEL);
+ u8 *work = scratch, *work1;
+ u8 *end_work = scratch + SCRATCH_SIZE;
+ u8 *priv, *pub;
+ u16 priv_len, pub_len;
+
+ priv_len = get_unaligned_be16(src) + 2;
+ priv = src;
+
+ src += priv_len;
+
+ pub_len = get_unaligned_be16(src) + 2;
+ pub = src;
+
+ if (!scratch)
+ return -ENOMEM;
+
+ work = asn1_encode_oid(work, end_work, tpm2key_oid,
+ asn1_oid_len(tpm2key_oid));
+
+ if (options->blobauth_len == 0) {
+ unsigned char bool[3], *w = bool;
+ /* tag 0 is emptyAuth */
+ w = asn1_encode_boolean(w, w + sizeof(bool), true);
+ if (WARN(IS_ERR(w), "BUG: Boolean failed to encode"))
+ return PTR_ERR(w);
+ work = asn1_encode_tag(work, end_work, 0, bool, w - bool);
+ }
+
+ /*
+ * Assume both octet strings will encode to a 2 byte definite length
+ *
+ * Note: For a well behaved TPM, this warning should never
+ * trigger, so if it does there's something nefarious going on
+ */
+ if (WARN(work - scratch + pub_len + priv_len + 14 > SCRATCH_SIZE,
+ "BUG: scratch buffer is too small"))
+ return -EINVAL;
+
+ work = asn1_encode_integer(work, end_work, options->keyhandle);
+ work = asn1_encode_octet_string(work, end_work, pub, pub_len);
+ work = asn1_encode_octet_string(work, end_work, priv, priv_len);
+
+ work1 = payload->blob;
+ work1 = asn1_encode_sequence(work1, work1 + sizeof(payload->blob),
+ scratch, work - scratch);
+ if (WARN(IS_ERR(work1), "BUG: ASN.1 encoder failed"))
+ return PTR_ERR(work1);
+
+ return work1 - payload->blob;
+}
+
+struct tpm2_key_context {
+ u32 parent;
+ const u8 *pub;
+ u32 pub_len;
+ const u8 *priv;
+ u32 priv_len;
+};
+
+static int tpm2_key_decode(struct trusted_key_payload *payload,
+ struct trusted_key_options *options,
+ u8 **buf)
+{
+ int ret;
+ struct tpm2_key_context ctx;
+ u8 *blob;
+
+ memset(&ctx, 0, sizeof(ctx));
+
+ ret = asn1_ber_decoder(&tpm2key_decoder, &ctx, payload->blob,
+ payload->blob_len);
+ if (ret < 0)
+ return ret;
+
+ if (ctx.priv_len + ctx.pub_len > MAX_BLOB_SIZE)
+ return -EINVAL;
+
+ blob = kmalloc(ctx.priv_len + ctx.pub_len + 4, GFP_KERNEL);
+ if (!blob)
+ return -ENOMEM;
+
+ *buf = blob;
+ options->keyhandle = ctx.parent;
+
+ memcpy(blob, ctx.priv, ctx.priv_len);
+ blob += ctx.priv_len;
+
+ memcpy(blob, ctx.pub, ctx.pub_len);
+
+ return 0;
+}
+
+int tpm2_key_parent(void *context, size_t hdrlen,
+ unsigned char tag,
+ const void *value, size_t vlen)
+{
+ struct tpm2_key_context *ctx = context;
+ const u8 *v = value;
+ int i;
+
+ ctx->parent = 0;
+ for (i = 0; i < vlen; i++) {
+ ctx->parent <<= 8;
+ ctx->parent |= v[i];
+ }
+
+ return 0;
+}
+
+int tpm2_key_type(void *context, size_t hdrlen,
+ unsigned char tag,
+ const void *value, size_t vlen)
+{
+ enum OID oid = look_up_OID(value, vlen);
+
+ if (oid != OID_TPMSealedData) {
+ char buffer[50];
+
+ sprint_oid(value, vlen, buffer, sizeof(buffer));
+ pr_debug("OID is \"%s\" which is not TPMSealedData\n",
+ buffer);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+int tpm2_key_pub(void *context, size_t hdrlen,
+ unsigned char tag,
+ const void *value, size_t vlen)
+{
+ struct tpm2_key_context *ctx = context;
+
+ ctx->pub = value;
+ ctx->pub_len = vlen;
+
+ return 0;
+}
+
+int tpm2_key_priv(void *context, size_t hdrlen,
+ unsigned char tag,
+ const void *value, size_t vlen)
+{
+ struct tpm2_key_context *ctx = context;
+
+ ctx->priv = value;
+ ctx->priv_len = vlen;
+
+ return 0;
+}
+
/**
* tpm_buf_append_auth() - append TPMS_AUTH_COMMAND to the buffer.
*
struct trusted_key_payload *payload,
struct trusted_key_options *options)
{
- unsigned int blob_len;
+ int blob_len = 0;
struct tpm_buf buf;
u32 hash;
+ u32 flags;
int i;
int rc;
if (i == ARRAY_SIZE(tpm2_hash_map))
return -EINVAL;
- rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_CREATE);
+ if (!options->keyhandle)
+ return -EINVAL;
+
+ rc = tpm_try_get_ops(chip);
if (rc)
return rc;
TPM_DIGEST_SIZE);
/* sensitive */
- tpm_buf_append_u16(&buf, 4 + TPM_DIGEST_SIZE + payload->key_len + 1);
+ tpm_buf_append_u16(&buf, 4 + options->blobauth_len + payload->key_len);
+
+ tpm_buf_append_u16(&buf, options->blobauth_len);
+ if (options->blobauth_len)
+ tpm_buf_append(&buf, options->blobauth, options->blobauth_len);
- tpm_buf_append_u16(&buf, TPM_DIGEST_SIZE);
- tpm_buf_append(&buf, options->blobauth, TPM_DIGEST_SIZE);
- tpm_buf_append_u16(&buf, payload->key_len + 1);
+ tpm_buf_append_u16(&buf, payload->key_len);
tpm_buf_append(&buf, payload->key, payload->key_len);
- tpm_buf_append_u8(&buf, payload->migratable);
/* public */
tpm_buf_append_u16(&buf, 14 + options->policydigest_len);
tpm_buf_append_u16(&buf, TPM_ALG_KEYEDHASH);
tpm_buf_append_u16(&buf, hash);
+ /* key properties */
+ flags = 0;
+ flags |= options->policydigest_len ? 0 : TPM2_OA_USER_WITH_AUTH;
+ flags |= payload->migratable ? (TPM2_OA_FIXED_TPM |
+ TPM2_OA_FIXED_PARENT) : 0;
+ tpm_buf_append_u32(&buf, flags);
+
/* policy */
- if (options->policydigest_len) {
- tpm_buf_append_u32(&buf, 0);
- tpm_buf_append_u16(&buf, options->policydigest_len);
+ tpm_buf_append_u16(&buf, options->policydigest_len);
+ if (options->policydigest_len)
tpm_buf_append(&buf, options->policydigest,
options->policydigest_len);
- } else {
- tpm_buf_append_u32(&buf, TPM2_OA_USER_WITH_AUTH);
- tpm_buf_append_u16(&buf, 0);
- }
/* public parameters */
tpm_buf_append_u16(&buf, TPM_ALG_NULL);
goto out;
}
- memcpy(payload->blob, &buf.data[TPM_HEADER_SIZE + 4], blob_len);
- payload->blob_len = blob_len;
+ blob_len = tpm2_key_encode(payload, options,
+ &buf.data[TPM_HEADER_SIZE + 4],
+ blob_len);
out:
tpm_buf_destroy(&buf);
else
rc = -EPERM;
}
+ if (blob_len < 0)
+ return blob_len;
+
+ payload->blob_len = blob_len;
tpm_put_ops(chip);
return rc;
unsigned int private_len;
unsigned int public_len;
unsigned int blob_len;
+ u8 *blob, *pub;
int rc;
+ u32 attrs;
+
+ rc = tpm2_key_decode(payload, options, &blob);
+ if (rc) {
+ /* old form */
+ blob = payload->blob;
+ payload->old_format = 1;
+ }
+
+ /* new format carries keyhandle but old format doesn't */
+ if (!options->keyhandle)
+ return -EINVAL;
- private_len = be16_to_cpup((__be16 *) &payload->blob[0]);
- if (private_len > (payload->blob_len - 2))
+ /* must be big enough for at least the two be16 size counts */
+ if (payload->blob_len < 4)
+ return -EINVAL;
+
+ private_len = get_unaligned_be16(blob);
+
+ /* must be big enough for following public_len */
+ if (private_len + 2 + 2 > (payload->blob_len))
+ return -E2BIG;
+
+ public_len = get_unaligned_be16(blob + 2 + private_len);
+ if (private_len + 2 + public_len + 2 > payload->blob_len)
return -E2BIG;
- public_len = be16_to_cpup((__be16 *) &payload->blob[2 + private_len]);
+ pub = blob + 2 + private_len + 2;
+ /* key attributes are always at offset 4 */
+ attrs = get_unaligned_be32(pub + 4);
+
+ if ((attrs & (TPM2_OA_FIXED_TPM | TPM2_OA_FIXED_PARENT)) ==
+ (TPM2_OA_FIXED_TPM | TPM2_OA_FIXED_PARENT))
+ payload->migratable = 0;
+ else
+ payload->migratable = 1;
+
blob_len = private_len + public_len + 4;
if (blob_len > payload->blob_len)
return -E2BIG;
options->keyauth /* hmac */,
TPM_DIGEST_SIZE);
- tpm_buf_append(&buf, payload->blob, blob_len);
+ tpm_buf_append(&buf, blob, blob_len);
if (buf.flags & TPM_BUF_OVERFLOW) {
rc = -E2BIG;
(__be32 *) &buf.data[TPM_HEADER_SIZE]);
out:
+ if (blob != payload->blob)
+ kfree(blob);
tpm_buf_destroy(&buf);
if (rc > 0)
NULL /* nonce */, 0,
TPM2_SA_CONTINUE_SESSION,
options->blobauth /* hmac */,
- TPM_DIGEST_SIZE);
+ options->blobauth_len);
rc = tpm_transmit_cmd(chip, &buf, 6, "unsealing");
if (rc > 0)
if (!rc) {
data_len = be16_to_cpup(
(__be16 *) &buf.data[TPM_HEADER_SIZE + 4]);
- if (data_len < MIN_KEY_SIZE || data_len > MAX_KEY_SIZE + 1) {
+ if (data_len < MIN_KEY_SIZE || data_len > MAX_KEY_SIZE) {
rc = -EFAULT;
goto out;
}
}
data = &buf.data[TPM_HEADER_SIZE + 6];
- memcpy(payload->key, data, data_len - 1);
- payload->key_len = data_len - 1;
- payload->migratable = data[data_len - 1];
+ if (payload->old_format) {
+ /* migratable flag is at the end of the key */
+ memcpy(payload->key, data, data_len - 1);
+ payload->key_len = data_len - 1;
+ payload->migratable = data[data_len - 1];
+ } else {
+ /*
+ * migratable flag already collected from key
+ * attributes
+ */
+ memcpy(payload->key, data, data_len);
+ payload->key_len = data_len;
+ }
}
out:
return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_GENFS_SECLABEL_SYMLINKS]);
}
+struct selinux_policy_convert_data;
+
+struct selinux_load_state {
+ struct selinux_policy *policy;
+ struct selinux_policy_convert_data *convert_data;
+};
+
int security_mls_enabled(struct selinux_state *state);
int security_load_policy(struct selinux_state *state,
- void *data, size_t len,
- struct selinux_policy **newpolicyp);
+ void *data, size_t len,
+ struct selinux_load_state *load_state);
void selinux_policy_commit(struct selinux_state *state,
- struct selinux_policy *newpolicy);
+ struct selinux_load_state *load_state);
void selinux_policy_cancel(struct selinux_state *state,
- struct selinux_policy *policy);
+ struct selinux_load_state *load_state);
int security_read_policy(struct selinux_state *state,
void **data, size_t *len);
int security_read_state_kernel(struct selinux_state *state,
ret = sel_make_bools(newpolicy, tmp_bool_dir, &tmp_bool_num,
&tmp_bool_names, &tmp_bool_values);
- if (ret) {
- pr_err("SELinux: failed to load policy booleans\n");
+ if (ret)
goto out;
- }
ret = sel_make_classes(newpolicy, tmp_class_dir,
&fsi->last_class_ino);
- if (ret) {
- pr_err("SELinux: failed to load policy classes\n");
+ if (ret)
goto out;
- }
/* booleans */
old_dentry = fsi->bool_dir;
{
struct selinux_fs_info *fsi = file_inode(file)->i_sb->s_fs_info;
- struct selinux_policy *newpolicy;
+ struct selinux_load_state load_state;
ssize_t length;
void *data = NULL;
if (copy_from_user(data, buf, count) != 0)
goto out;
- length = security_load_policy(fsi->state, data, count, &newpolicy);
+ length = security_load_policy(fsi->state, data, count, &load_state);
if (length) {
pr_warn_ratelimited("SELinux: failed to load policy\n");
goto out;
}
- length = sel_make_policy_nodes(fsi, newpolicy);
+ length = sel_make_policy_nodes(fsi, load_state.policy);
if (length) {
- selinux_policy_cancel(fsi->state, newpolicy);
- goto out1;
+ pr_warn_ratelimited("SELinux: failed to initialize selinuxfs\n");
+ selinux_policy_cancel(fsi->state, &load_state);
+ goto out;
}
- selinux_policy_commit(fsi->state, newpolicy);
+ selinux_policy_commit(fsi->state, &load_state);
length = count;
-out1:
audit_log(audit_context(), GFP_KERNEL, AUDIT_MAC_POLICY_LOAD,
"auid=%u ses=%u lsm=selinux res=1",
from_kuid(&init_user_ns, audit_get_loginuid(current)),
struct avtab_node *prev, *cur, *newnode;
u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD);
- if (!h)
+ if (!h || !h->nslot)
return -EINVAL;
hvalue = avtab_hash(key, h->mask);
struct avtab_node *prev, *cur;
u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD);
- if (!h)
+ if (!h || !h->nslot)
return NULL;
hvalue = avtab_hash(key, h->mask);
for (prev = NULL, cur = h->htable[hvalue];
struct avtab_node *cur;
u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD);
- if (!h)
+ if (!h || !h->nslot)
return NULL;
hvalue = avtab_hash(key, h->mask);
struct avtab_node *cur;
u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD);
- if (!h)
+ if (!h || !h->nslot)
return NULL;
hvalue = avtab_hash(key, h->mask);
}
kvfree(h->htable);
h->htable = NULL;
+ h->nel = 0;
h->nslot = 0;
h->mask = 0;
}
{
h->htable = NULL;
h->nel = 0;
+ h->nslot = 0;
+ h->mask = 0;
}
-int avtab_alloc(struct avtab *h, u32 nrules)
+static int avtab_alloc_common(struct avtab *h, u32 nslot)
{
- u32 mask = 0;
- u32 shift = 0;
- u32 work = nrules;
- u32 nslot = 0;
-
- if (nrules == 0)
- goto avtab_alloc_out;
-
- while (work) {
- work = work >> 1;
- shift++;
- }
- if (shift > 2)
- shift = shift - 2;
- nslot = 1 << shift;
- if (nslot > MAX_AVTAB_HASH_BUCKETS)
- nslot = MAX_AVTAB_HASH_BUCKETS;
- mask = nslot - 1;
+ if (!nslot)
+ return 0;
h->htable = kvcalloc(nslot, sizeof(void *), GFP_KERNEL);
if (!h->htable)
return -ENOMEM;
- avtab_alloc_out:
- h->nel = 0;
h->nslot = nslot;
- h->mask = mask;
- pr_debug("SELinux: %d avtab hash slots, %d rules.\n",
- h->nslot, nrules);
+ h->mask = nslot - 1;
return 0;
}
-int avtab_duplicate(struct avtab *new, struct avtab *orig)
+int avtab_alloc(struct avtab *h, u32 nrules)
{
- int i;
- struct avtab_node *node, *tmp, *tail;
-
- memset(new, 0, sizeof(*new));
+ int rc;
+ u32 nslot = 0;
- new->htable = kvcalloc(orig->nslot, sizeof(void *), GFP_KERNEL);
- if (!new->htable)
- return -ENOMEM;
- new->nslot = orig->nslot;
- new->mask = orig->mask;
-
- for (i = 0; i < orig->nslot; i++) {
- tail = NULL;
- for (node = orig->htable[i]; node; node = node->next) {
- tmp = kmem_cache_zalloc(avtab_node_cachep, GFP_KERNEL);
- if (!tmp)
- goto error;
- tmp->key = node->key;
- if (tmp->key.specified & AVTAB_XPERMS) {
- tmp->datum.u.xperms =
- kmem_cache_zalloc(avtab_xperms_cachep,
- GFP_KERNEL);
- if (!tmp->datum.u.xperms) {
- kmem_cache_free(avtab_node_cachep, tmp);
- goto error;
- }
- tmp->datum.u.xperms = node->datum.u.xperms;
- } else
- tmp->datum.u.data = node->datum.u.data;
-
- if (tail)
- tail->next = tmp;
- else
- new->htable[i] = tmp;
-
- tail = tmp;
- new->nel++;
+ if (nrules != 0) {
+ u32 shift = 1;
+ u32 work = nrules >> 3;
+ while (work) {
+ work >>= 1;
+ shift++;
}
+ nslot = 1 << shift;
+ if (nslot > MAX_AVTAB_HASH_BUCKETS)
+ nslot = MAX_AVTAB_HASH_BUCKETS;
+
+ rc = avtab_alloc_common(h, nslot);
+ if (rc)
+ return rc;
}
+ pr_debug("SELinux: %d avtab hash slots, %d rules.\n", nslot, nrules);
return 0;
-error:
- avtab_destroy(new);
- return -ENOMEM;
+}
+
+int avtab_alloc_dup(struct avtab *new, const struct avtab *orig)
+{
+ return avtab_alloc_common(new, orig->nslot);
}
void avtab_hash_eval(struct avtab *h, char *tag)
void avtab_init(struct avtab *h);
int avtab_alloc(struct avtab *, u32);
-int avtab_duplicate(struct avtab *new, struct avtab *orig);
+int avtab_alloc_dup(struct avtab *new, const struct avtab *orig);
struct avtab_datum *avtab_search(struct avtab *h, struct avtab_key *k);
void avtab_destroy(struct avtab *h);
void avtab_hash_eval(struct avtab *h, char *tag);
struct cond_av_list *orig,
struct avtab *avtab)
{
- struct avtab_node *avnode;
u32 i;
memset(new, 0, sizeof(*new));
return -ENOMEM;
for (i = 0; i < orig->len; i++) {
- avnode = avtab_search_node(avtab, &orig->nodes[i]->key);
- if (WARN_ON(!avnode))
- return -EINVAL;
- new->nodes[i] = avnode;
+ new->nodes[i] = avtab_insert_nonunique(avtab,
+ &orig->nodes[i]->key,
+ &orig->nodes[i]->datum);
+ if (!new->nodes[i])
+ return -ENOMEM;
new->len++;
}
{
int rc, i, j;
- rc = avtab_duplicate(&newp->te_cond_avtab, &origp->te_cond_avtab);
+ rc = avtab_alloc_dup(&newp->te_cond_avtab, &origp->te_cond_avtab);
if (rc)
return rc;
#include "policycap_names.h"
#include "ima.h"
+struct convert_context_args {
+ struct selinux_state *state;
+ struct policydb *oldp;
+ struct policydb *newp;
+};
+
+struct selinux_policy_convert_data {
+ struct convert_context_args args;
+ struct sidtab_convert_params sidtab_params;
+};
+
/* Forward declaration. */
static int context_struct_to_string(struct policydb *policydb,
struct context *context,
if (!str)
goto out;
}
+retry:
rcu_read_lock();
policy = rcu_dereference(state->policy);
policydb = &policy->policydb;
} else if (rc)
goto out_unlock;
rc = sidtab_context_to_sid(sidtab, &context, sid);
+ if (rc == -ESTALE) {
+ rcu_read_unlock();
+ if (context.str) {
+ str = context.str;
+ context.str = NULL;
+ }
+ context_destroy(&context);
+ goto retry;
+ }
context_destroy(&context);
out_unlock:
rcu_read_unlock();
struct selinux_policy *policy;
struct policydb *policydb;
struct sidtab *sidtab;
- struct class_datum *cladatum = NULL;
+ struct class_datum *cladatum;
struct context *scontext, *tcontext, newcontext;
struct sidtab_entry *sentry, *tentry;
struct avtab_key avkey;
goto out;
}
+retry:
+ cladatum = NULL;
context_init(&newcontext);
rcu_read_lock();
}
/* Obtain the sid for the context. */
rc = sidtab_context_to_sid(sidtab, &newcontext, out_sid);
+ if (rc == -ESTALE) {
+ rcu_read_unlock();
+ context_destroy(&newcontext);
+ goto retry;
+ }
out_unlock:
rcu_read_unlock();
context_destroy(&newcontext);
return 0;
}
-struct convert_context_args {
- struct selinux_state *state;
- struct policydb *oldp;
- struct policydb *newp;
-};
-
/*
* Convert the values in the security context
* structure `oldc' from the values specified
}
void selinux_policy_cancel(struct selinux_state *state,
- struct selinux_policy *policy)
+ struct selinux_load_state *load_state)
{
struct selinux_policy *oldpolicy;
lockdep_is_held(&state->policy_mutex));
sidtab_cancel_convert(oldpolicy->sidtab);
- selinux_policy_free(policy);
+ selinux_policy_free(load_state->policy);
+ kfree(load_state->convert_data);
}
static void selinux_notify_policy_change(struct selinux_state *state,
}
void selinux_policy_commit(struct selinux_state *state,
- struct selinux_policy *newpolicy)
+ struct selinux_load_state *load_state)
{
- struct selinux_policy *oldpolicy;
+ struct selinux_policy *oldpolicy, *newpolicy = load_state->policy;
+ unsigned long flags;
u32 seqno;
oldpolicy = rcu_dereference_protected(state->policy,
seqno = newpolicy->latest_granting;
/* Install the new policy. */
- rcu_assign_pointer(state->policy, newpolicy);
+ if (oldpolicy) {
+ sidtab_freeze_begin(oldpolicy->sidtab, &flags);
+ rcu_assign_pointer(state->policy, newpolicy);
+ sidtab_freeze_end(oldpolicy->sidtab, &flags);
+ } else {
+ rcu_assign_pointer(state->policy, newpolicy);
+ }
/* Load the policycaps from the new policy */
security_load_policycaps(state, newpolicy);
/* Free the old policy */
synchronize_rcu();
selinux_policy_free(oldpolicy);
+ kfree(load_state->convert_data);
/* Notify others of the policy change */
selinux_notify_policy_change(state, seqno);
* loading the new policy.
*/
int security_load_policy(struct selinux_state *state, void *data, size_t len,
- struct selinux_policy **newpolicyp)
+ struct selinux_load_state *load_state)
{
struct selinux_policy *newpolicy, *oldpolicy;
- struct sidtab_convert_params convert_params;
- struct convert_context_args args;
+ struct selinux_policy_convert_data *convert_data;
int rc = 0;
struct policy_file file = { data, len }, *fp = &file;
goto err_mapping;
}
-
if (!selinux_initialized(state)) {
/* First policy load, so no need to preserve state from old policy */
- *newpolicyp = newpolicy;
+ load_state->policy = newpolicy;
+ load_state->convert_data = NULL;
return 0;
}
goto err_free_isids;
}
+ convert_data = kmalloc(sizeof(*convert_data), GFP_KERNEL);
+ if (!convert_data) {
+ rc = -ENOMEM;
+ goto err_free_isids;
+ }
+
/*
* Convert the internal representations of contexts
* in the new SID table.
*/
- args.state = state;
- args.oldp = &oldpolicy->policydb;
- args.newp = &newpolicy->policydb;
+ convert_data->args.state = state;
+ convert_data->args.oldp = &oldpolicy->policydb;
+ convert_data->args.newp = &newpolicy->policydb;
- convert_params.func = convert_context;
- convert_params.args = &args;
- convert_params.target = newpolicy->sidtab;
+ convert_data->sidtab_params.func = convert_context;
+ convert_data->sidtab_params.args = &convert_data->args;
+ convert_data->sidtab_params.target = newpolicy->sidtab;
- rc = sidtab_convert(oldpolicy->sidtab, &convert_params);
+ rc = sidtab_convert(oldpolicy->sidtab, &convert_data->sidtab_params);
if (rc) {
pr_err("SELinux: unable to convert the internal"
" representation of contexts in the new SID"
" table\n");
- goto err_free_isids;
+ goto err_free_convert_data;
}
- *newpolicyp = newpolicy;
+ load_state->policy = newpolicy;
+ load_state->convert_data = convert_data;
return 0;
+err_free_convert_data:
+ kfree(convert_data);
err_free_isids:
sidtab_destroy(newpolicy->sidtab);
err_mapping:
struct policydb *policydb;
struct sidtab *sidtab;
struct ocontext *c;
- int rc = 0;
+ int rc;
if (!selinux_initialized(state)) {
*out_sid = SECINITSID_PORT;
return 0;
}
+retry:
+ rc = 0;
rcu_read_lock();
policy = rcu_dereference(state->policy);
policydb = &policy->policydb;
if (!c->sid[0]) {
rc = sidtab_context_to_sid(sidtab, &c->context[0],
&c->sid[0]);
+ if (rc == -ESTALE) {
+ rcu_read_unlock();
+ goto retry;
+ }
if (rc)
goto out;
}
struct policydb *policydb;
struct sidtab *sidtab;
struct ocontext *c;
- int rc = 0;
+ int rc;
if (!selinux_initialized(state)) {
*out_sid = SECINITSID_UNLABELED;
return 0;
}
+retry:
+ rc = 0;
rcu_read_lock();
policy = rcu_dereference(state->policy);
policydb = &policy->policydb;
rc = sidtab_context_to_sid(sidtab,
&c->context[0],
&c->sid[0]);
+ if (rc == -ESTALE) {
+ rcu_read_unlock();
+ goto retry;
+ }
if (rc)
goto out;
}
struct policydb *policydb;
struct sidtab *sidtab;
struct ocontext *c;
- int rc = 0;
+ int rc;
if (!selinux_initialized(state)) {
*out_sid = SECINITSID_UNLABELED;
return 0;
}
+retry:
+ rc = 0;
rcu_read_lock();
policy = rcu_dereference(state->policy);
policydb = &policy->policydb;
if (!c->sid[0]) {
rc = sidtab_context_to_sid(sidtab, &c->context[0],
&c->sid[0]);
+ if (rc == -ESTALE) {
+ rcu_read_unlock();
+ goto retry;
+ }
if (rc)
goto out;
}
struct selinux_policy *policy;
struct policydb *policydb;
struct sidtab *sidtab;
- int rc = 0;
+ int rc;
struct ocontext *c;
if (!selinux_initialized(state)) {
return 0;
}
+retry:
+ rc = 0;
rcu_read_lock();
policy = rcu_dereference(state->policy);
policydb = &policy->policydb;
if (!c->sid[0] || !c->sid[1]) {
rc = sidtab_context_to_sid(sidtab, &c->context[0],
&c->sid[0]);
+ if (rc == -ESTALE) {
+ rcu_read_unlock();
+ goto retry;
+ }
if (rc)
goto out;
rc = sidtab_context_to_sid(sidtab, &c->context[1],
&c->sid[1]);
+ if (rc == -ESTALE) {
+ rcu_read_unlock();
+ goto retry;
+ }
if (rc)
goto out;
}
return 0;
}
+retry:
rcu_read_lock();
policy = rcu_dereference(state->policy);
policydb = &policy->policydb;
rc = sidtab_context_to_sid(sidtab,
&c->context[0],
&c->sid[0]);
+ if (rc == -ESTALE) {
+ rcu_read_unlock();
+ goto retry;
+ }
if (rc)
goto out;
}
struct sidtab *sidtab;
struct context *fromcon, usercon;
u32 *mysids = NULL, *mysids2, sid;
- u32 mynel = 0, maxnel = SIDS_NEL;
+ u32 i, j, mynel, maxnel = SIDS_NEL;
struct user_datum *user;
struct role_datum *role;
struct ebitmap_node *rnode, *tnode;
- int rc = 0, i, j;
+ int rc;
*sids = NULL;
*nel = 0;
if (!selinux_initialized(state))
- goto out;
+ return 0;
+
+ mysids = kcalloc(maxnel, sizeof(*mysids), GFP_KERNEL);
+ if (!mysids)
+ return -ENOMEM;
+retry:
+ mynel = 0;
rcu_read_lock();
policy = rcu_dereference(state->policy);
policydb = &policy->policydb;
usercon.user = user->value;
- rc = -ENOMEM;
- mysids = kcalloc(maxnel, sizeof(*mysids), GFP_ATOMIC);
- if (!mysids)
- goto out_unlock;
-
ebitmap_for_each_positive_bit(&user->roles, rnode, i) {
role = policydb->role_val_to_struct[i];
usercon.role = i + 1;
continue;
rc = sidtab_context_to_sid(sidtab, &usercon, &sid);
+ if (rc == -ESTALE) {
+ rcu_read_unlock();
+ goto retry;
+ }
if (rc)
goto out_unlock;
if (mynel < maxnel) {
rcu_read_unlock();
if (rc || !mynel) {
kfree(mysids);
- goto out;
+ return rc;
}
rc = -ENOMEM;
mysids2 = kcalloc(mynel, sizeof(*mysids2), GFP_KERNEL);
if (!mysids2) {
kfree(mysids);
- goto out;
+ return rc;
}
for (i = 0, j = 0; i < mynel; i++) {
struct av_decision dummy_avd;
mysids2[j++] = mysids[i];
cond_resched();
}
- rc = 0;
kfree(mysids);
*sids = mysids2;
*nel = j;
-out:
- return rc;
+ return 0;
}
/**
* Obtain a SID to use for a file in a filesystem that
* cannot support xattr or use a fixed labeling behavior like
* transition SIDs or task SIDs.
+ *
+ * WARNING: This function may return -ESTALE, indicating that the caller
+ * must retry the operation after re-acquiring the policy pointer!
*/
static inline int __security_genfs_sid(struct selinux_policy *policy,
const char *fstype,
return 0;
}
- rcu_read_lock();
- policy = rcu_dereference(state->policy);
- retval = __security_genfs_sid(policy,
- fstype, path, orig_sclass, sid);
- rcu_read_unlock();
+ do {
+ rcu_read_lock();
+ policy = rcu_dereference(state->policy);
+ retval = __security_genfs_sid(policy, fstype, path,
+ orig_sclass, sid);
+ rcu_read_unlock();
+ } while (retval == -ESTALE);
return retval;
}
struct selinux_policy *policy;
struct policydb *policydb;
struct sidtab *sidtab;
- int rc = 0;
+ int rc;
struct ocontext *c;
struct superblock_security_struct *sbsec = sb->s_security;
const char *fstype = sb->s_type->name;
return 0;
}
+retry:
+ rc = 0;
rcu_read_lock();
policy = rcu_dereference(state->policy);
policydb = &policy->policydb;
if (!c->sid[0]) {
rc = sidtab_context_to_sid(sidtab, &c->context[0],
&c->sid[0]);
+ if (rc == -ESTALE) {
+ rcu_read_unlock();
+ goto retry;
+ }
if (rc)
goto out;
}
} else {
rc = __security_genfs_sid(policy, fstype, "/",
SECCLASS_DIR, &sbsec->sid);
+ if (rc == -ESTALE) {
+ rcu_read_unlock();
+ goto retry;
+ }
if (rc) {
sbsec->behavior = SECURITY_FS_USE_NONE;
rc = 0;
u32 len;
int rc;
- rc = 0;
if (!selinux_initialized(state)) {
*new_sid = sid;
- goto out;
+ return 0;
}
+retry:
+ rc = 0;
context_init(&newcon);
rcu_read_lock();
}
}
rc = sidtab_context_to_sid(sidtab, &newcon, new_sid);
+ if (rc == -ESTALE) {
+ rcu_read_unlock();
+ context_destroy(&newcon);
+ goto retry;
+ }
out_unlock:
rcu_read_unlock();
context_destroy(&newcon);
-out:
return rc;
}
return 0;
}
+retry:
+ rc = 0;
rcu_read_lock();
policy = rcu_dereference(state->policy);
policydb = &policy->policydb;
goto out;
}
rc = -EIDRM;
- if (!mls_context_isvalid(policydb, &ctx_new))
- goto out_free;
+ if (!mls_context_isvalid(policydb, &ctx_new)) {
+ ebitmap_destroy(&ctx_new.range.level[0].cat);
+ goto out;
+ }
rc = sidtab_context_to_sid(sidtab, &ctx_new, sid);
+ ebitmap_destroy(&ctx_new.range.level[0].cat);
+ if (rc == -ESTALE) {
+ rcu_read_unlock();
+ goto retry;
+ }
if (rc)
- goto out_free;
+ goto out;
security_netlbl_cache_add(secattr, *sid);
-
- ebitmap_destroy(&ctx_new.range.level[0].cat);
} else
*sid = SECSID_NULL;
- rcu_read_unlock();
- return 0;
-out_free:
- ebitmap_destroy(&ctx_new.range.level[0].cat);
out:
rcu_read_unlock();
return rc;
for (i = 0; i < SECINITSID_NUM; i++)
s->isids[i].set = 0;
+ s->frozen = false;
s->count = 0;
s->convert = NULL;
hash_init(s->context_to_sid);
if (*sid)
goto out_unlock;
+ if (unlikely(s->frozen)) {
+ /*
+ * This sidtab is now frozen - tell the caller to abort and
+ * get the new one.
+ */
+ rc = -ESTALE;
+ goto out_unlock;
+ }
+
count = s->count;
convert = s->convert;
spin_unlock_irqrestore(&s->lock, flags);
}
+void sidtab_freeze_begin(struct sidtab *s, unsigned long *flags) __acquires(&s->lock)
+{
+ spin_lock_irqsave(&s->lock, *flags);
+ s->frozen = true;
+ s->convert = NULL;
+}
+void sidtab_freeze_end(struct sidtab *s, unsigned long *flags) __releases(&s->lock)
+{
+ spin_unlock_irqrestore(&s->lock, *flags);
+}
+
static void sidtab_destroy_entry(struct sidtab_entry *entry)
{
context_destroy(&entry->context);
u32 count;
/* access only under spinlock */
struct sidtab_convert_params *convert;
+ bool frozen;
spinlock_t lock;
#if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0
void sidtab_cancel_convert(struct sidtab *s);
+void sidtab_freeze_begin(struct sidtab *s, unsigned long *flags) __acquires(&s->lock);
+void sidtab_freeze_end(struct sidtab *s, unsigned long *flags) __releases(&s->lock);
+
int sidtab_context_to_sid(struct sidtab *s, struct context *context, u32 *sid);
void sidtab_destroy(struct sidtab *s);
static bool tomoyo_kernel_service(void)
{
/* Nothing to do if I am a kernel service. */
- return (current->flags & (PF_KTHREAD | PF_IO_WORKER)) == PF_KTHREAD;
+ return current->flags & PF_KTHREAD;
}
/**
MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
MODULE_DESCRIPTION("A loopback soundcard");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ALSA,Loopback soundcard}}");
#define MAX_PCM_SUBSTREAMS 8
return -ENOMEM;
kctl->id.device = dev;
kctl->id.subdevice = substr;
+
+ /* Add the control before copying the id so that
+ * the numid field of the id is set in the copy.
+ */
+ err = snd_ctl_add(card, kctl);
+ if (err < 0)
+ return err;
+
switch (idx) {
case ACTIVE_IDX:
setup->active_id = kctl->id;
default:
break;
}
- err = snd_ctl_add(card, kctl);
- if (err < 0)
- return err;
}
}
}
MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
MODULE_DESCRIPTION("Dummy soundcard (/dev/null)");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ALSA,Dummy soundcard}}");
#define MAX_PCM_DEVICES 4
#define MAX_PCM_SUBSTREAMS 128
MODULE_AUTHOR("Michael T. Mayers");
MODULE_DESCRIPTION("MOTU MidiTimePiece AV multiport MIDI");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{MOTU,MidiTimePiece AV multiport MIDI}}");
// io resources
#define MTPAV_IOBASE 0x378
MODULE_AUTHOR("Matthias Koenig <mk@phasorlab.de>");
MODULE_DESCRIPTION("ESI Miditerminal 4140");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ESI,Miditerminal 4140}}");
/*********************************************************************
* Chip specific
MODULE_AUTHOR("Stas Sergeev <stsp@users.sourceforge.net>");
MODULE_DESCRIPTION("PC-Speaker driver");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{PC-Speaker, pcsp}}");
MODULE_ALIAS("platform:pcspkr");
static int index = SNDRV_DEFAULT_IDX1; /* Index 0-MAX */
MODULE_AUTHOR("Levent Guendogdu, Tobias Gehrig, Matthias Koenig");
MODULE_DESCRIPTION("Midiman Portman2x4");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Midiman,Portman2x4}}");
/*********************************************************************
* Chip specific
MODULE_DESCRIPTION("MIDI serial u16550");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ALSA, MIDI serial u16550}}");
#define SNDRV_SERIAL_SOUNDCANVAS 0 /* Roland Soundcanvas; F5 NN selects part */
#define SNDRV_SERIAL_MS124T 1 /* Midiator MS-124T */
MODULE_AUTHOR("Takashi Iwai <tiwai@suse.de>");
MODULE_DESCRIPTION("Dummy soundcard for virtual rawmidi devices");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ALSA,Virtual rawmidi device}}");
#define MAX_MIDI_DEVICES 4
struct reg_params tx_params, rx_params;
if (dice->substreams_counter == 0) {
- if (get_register_params(dice, &tx_params, &rx_params) >= 0) {
- amdtp_domain_stop(&dice->domain);
+ if (get_register_params(dice, &tx_params, &rx_params) >= 0)
finish_session(dice, &tx_params, &rx_params);
- }
+ amdtp_domain_stop(&dice->domain);
release_resources(dice);
}
}
if (!nhlt)
return 0;
+ if (nhlt->header.length <= sizeof(struct acpi_table_header)) {
+ dev_warn(dev, "Invalid DMIC description table\n");
+ return 0;
+ }
+
for (j = 0, epnt = nhlt->desc; j < nhlt->endpoint_count; j++,
epnt = (struct nhlt_endpoint *)((u8 *)epnt + epnt->length)) {
MODULE_AUTHOR("Massimo Piccioni <dafastidio@libero.it>");
MODULE_DESCRIPTION("AD1816A, AD1815");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Highscreen,Sound-Boostar 16 3D},"
- "{Analog Devices,AD1815},"
- "{Analog Devices,AD1816A},"
- "{TerraTec,Base 64},"
- "{TerraTec,AudioSystem EWS64S},"
- "{Aztech/Newcom SC-16 3D},"
- "{Shark Predator ISA}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 1-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
MODULE_DESCRIPTION(CRD_NAME);
MODULE_AUTHOR("Tugrul Galatali <galatalt@stuy.edu>, Jaroslav Kysela <perex@perex.cz>");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Analog Devices,AD1848},"
- "{Analog Devices,AD1847},"
- "{Crystal Semiconductors,CS4248}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
#define PFX "als100: "
MODULE_DESCRIPTION("Avance Logic ALS007/ALS1X0");
-MODULE_SUPPORTED_DEVICE("{{Diamond Technologies DT-019X},"
- "{Avance Logic ALS-007}}"
- "{{Avance Logic,ALS100 - PRO16PNP},"
- "{Avance Logic,ALS110},"
- "{Avance Logic,ALS120},"
- "{Avance Logic,ALS200},"
- "{3D Melody,MF1000},"
- "{Digimate,3D Sound},"
- "{Avance Logic,ALS120},"
- "{RTL,RTL3000}}");
-
MODULE_AUTHOR("Massimo Piccioni <dafastidio@libero.it>");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Massimo Piccioni <dafastidio@libero.it>");
MODULE_DESCRIPTION("Aztech Systems AZT2320");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Aztech Systems,PRO16V},"
- "{Aztech Systems,AZT2320},"
- "{Aztech Systems,AZT3300},"
- "{Aztech Systems,AZT2320},"
- "{Aztech Systems,AZT3000}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
MODULE_AUTHOR("George Talusan <gstalusan@uwaterloo.ca>");
MODULE_DESCRIPTION("C-Media CMI8330/CMI8329");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{C-Media,CMI8330,isapnp:{CMI0001,@@@0001,@X@0001}}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;
MODULE_DESCRIPTION(CRD_NAME);
MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Crystal Semiconductors,CS4231}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Cirrus Logic CS4232-9");
-MODULE_SUPPORTED_DEVICE("{{Turtle Beach,TBS-2000},"
- "{Turtle Beach,Tropez Plus},"
- "{SIC CrystalWave 32},"
- "{Hewlett Packard,Omnibook 5500},"
- "{TerraTec,Maestro 32/96},"
- "{Philips,PCA70PS}},"
- "{{Crystal Semiconductors,CS4235},"
- "{Crystal Semiconductors,CS4236},"
- "{Crystal Semiconductors,CS4237},"
- "{Crystal Semiconductors,CS4238},"
- "{Crystal Semiconductors,CS4239},"
- "{Acer,AW37},"
- "{Acer,AW35/Pro},"
- "{Crystal,3D},"
- "{Crystal Computer,TidalWave128},"
- "{Dell,Optiplex GX1},"
- "{Dell,Workstation 400 sound},"
- "{EliteGroup,P5TX-LA sound},"
- "{Gallant,SC-70P},"
- "{Gateway,E1000 Onboard CS4236B},"
- "{Genius,Sound Maker 3DJ},"
- "{Hewlett Packard,HP6330 sound},"
- "{IBM,PC 300PL sound},"
- "{IBM,Aptiva 2137 E24},"
- "{IBM,IntelliStation M Pro},"
- "{Intel,Marlin Spike Mobo CS4235},"
- "{Intel PR440FX Onboard},"
- "{Guillemot,MaxiSound 16 PnP},"
- "{NewClear,3D},"
- "{TerraTec,AudioSystem EWS64L/XL},"
- "{Typhoon Soundsystem,CS4236B},"
- "{Turtle Beach,Malibu},"
- "{Unknown,Digital PC 5000 Onboard}}");
-
MODULE_ALIAS("snd_cs4232");
#define IDENT "CS4232+"
MODULE_DESCRIPTION(CRD_NAME);
MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ESS,ES688 PnP AudioDrive,pnp:ESS0100},"
- "{ESS,ES1688 PnP AudioDrive,pnp:ESS0102},"
- "{ESS,ES688 AudioDrive,pnp:ESS6881},"
- "{ESS,ES1688 AudioDrive,pnp:ESS1681}}");
-
MODULE_ALIAS("snd_es968");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
/* Card level */
-MODULE_AUTHOR("Christian Fischbach <fishbach@pool.informatik.rwth-aachen.de>, Abramo Bagnara <abramo@alsa-project.org>");
+MODULE_AUTHOR("Christian Fischbach <fishbach@pool.informatik.rwth-aachen.de>, Abramo Bagnara <abramo@alsa-project.org>");
MODULE_DESCRIPTION("ESS ES18xx AudioDrive");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ESS,ES1868 PnP AudioDrive},"
- "{ESS,ES1869 PnP AudioDrive},"
- "{ESS,ES1878 PnP AudioDrive},"
- "{ESS,ES1879 PnP AudioDrive},"
- "{ESS,ES1887 PnP AudioDrive},"
- "{ESS,ES1888 PnP AudioDrive},"
- "{ESS,ES1887 AudioDrive},"
- "{ESS,ES1888 AudioDrive}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
MODULE_DESCRIPTION(CRD_NAME);
MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Gravis,UltraSound Classic}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
MODULE_DESCRIPTION(CRD_NAME);
MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Gravis,UltraSound Extreme}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
MODULE_DESCRIPTION("Gravis UltraSound MAX");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Gravis,UltraSound MAX}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
MODULE_LICENSE("GPL");
#ifndef SNDRV_STB
MODULE_DESCRIPTION("AMD InterWave");
-MODULE_SUPPORTED_DEVICE("{{Gravis,UltraSound Plug & Play},"
- "{STB,SoundRage32},"
- "{MED,MED3210},"
- "{Dynasonix,Dynasonix Pro},"
- "{Panasonic,PCA761AW}}");
#else
MODULE_DESCRIPTION("AMD InterWave STB with TEA6330T");
-MODULE_SUPPORTED_DEVICE("{{AMD,InterWave STB with TEA6330T}}");
#endif
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
MODULE_DESCRIPTION("Yamaha OPL3SA2+");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Yamaha,YMF719E-S},"
- "{Genius,Sound Maker 3DX},"
- "{Yamaha,OPL3SA3},"
- "{Intel,AL440LX sound},"
- "{NeoMagic,MagicWave 3DX}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
MODULE_AUTHOR("Martin Langer <martin-langer@gmx.de>");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Miro miroSOUND PCM1 pro, PCM12, PCM20 Radio");
-MODULE_SUPPORTED_DEVICE("{{Miro,miroSOUND PCM1 pro}, "
- "{Miro,miroSOUND PCM12}, "
- "{Miro,miroSOUND PCM20 Radio}}");
static int index = SNDRV_DEFAULT_IDX1; /* Index 0-MAX */
static char *id = SNDRV_DEFAULT_STR1; /* ID for this card */
MODULE_LICENSE("GPL");
#ifdef OPTi93X
MODULE_DESCRIPTION("OPTi93X");
-MODULE_SUPPORTED_DEVICE("{{OPTi,82C931/3}}");
#else /* OPTi93X */
#ifdef CS4231
MODULE_DESCRIPTION("OPTi92X - CS4231");
-MODULE_SUPPORTED_DEVICE("{{OPTi,82C924 (CS4231)},"
- "{OPTi,82C925 (CS4231)}}");
#else /* CS4231 */
MODULE_DESCRIPTION("OPTi92X - AD1848");
-MODULE_SUPPORTED_DEVICE("{{OPTi,82C924 (AD1848)},"
- "{OPTi,82C925 (AD1848)},"
- "{OAK,Mozart}}");
#endif /* CS4231 */
#endif /* OPTi93X */
#define PFX "jazz16: "
MODULE_DESCRIPTION("Media Vision Jazz16");
-MODULE_SUPPORTED_DEVICE("{{Media Vision ??? },"
- "{RTL,RTL3000}}");
-
MODULE_AUTHOR("Krzysztof Helt <krzysztof.h1@wp.pl>");
MODULE_LICENSE("GPL");
MODULE_LICENSE("GPL");
#ifndef SNDRV_SBAWE
MODULE_DESCRIPTION("Sound Blaster 16");
-MODULE_SUPPORTED_DEVICE("{{Creative Labs,SB 16},"
- "{Creative Labs,SB Vibra16S},"
- "{Creative Labs,SB Vibra16C},"
- "{Creative Labs,SB Vibra16CL},"
- "{Creative Labs,SB Vibra16X}}");
#else
MODULE_DESCRIPTION("Sound Blaster AWE");
-MODULE_SUPPORTED_DEVICE("{{Creative Labs,SB AWE 32},"
- "{Creative Labs,SB AWE 64},"
- "{Creative Labs,SB AWE 64 Gold}}");
#endif
#if 0
MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
MODULE_DESCRIPTION("Sound Blaster 1.0/2.0/Pro");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Creative Labs,SB 1.0/SB 2.0/SB Pro}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
MODULE_AUTHOR("Krzysztof Helt");
MODULE_DESCRIPTION("Gallant SC-6000");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Gallant, SC-6000},"
- "{AudioExcel, Audio Excel DSP 16},"
- "{Zoltrix, AV302}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
MODULE_AUTHOR("Paul Barton-Davis <pbd@op.net>");
MODULE_DESCRIPTION("Turtle Beach Wavefront");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Turtle Beach,Maui/Tropez/Tropez+}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
MODULE_AUTHOR("Vivien Chappelier <vivien.chappelier@linux-mips.org>");
MODULE_DESCRIPTION("SGI O2 Audio");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Silicon Graphics, O2 Audio}}");
static int index = SNDRV_DEFAULT_IDX1; /* Index 0-MAX */
static char *id = SNDRV_DEFAULT_STR1; /* ID for this card */
MODULE_AUTHOR("Kyle McMartin <kyle@parisc-linux.org>, Thibaut Varene <t-bone@parisc-linux.org>");
MODULE_DESCRIPTION("Analog Devices AD1889 ALSA sound driver");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Analog Devices,AD1889}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
module_param_array(index, int, NULL, 0444);
MODULE_AUTHOR("Matt Wu <Matt_Wu@acersoftech.com.cn>");
MODULE_DESCRIPTION("ALI M5451");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ALI,M5451,pci},{ALI,M5451}}");
static int index = SNDRV_DEFAULT_IDX1; /* Index */
static char *id = SNDRV_DEFAULT_STR1; /* ID for this card */
MODULE_AUTHOR("Ash Willis <ashwillis@programmer.net>");
MODULE_DESCRIPTION("Avance Logic ALS300");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Avance Logic,ALS300},{Avance Logic,ALS300+}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;
MODULE_AUTHOR("Bart Hartgers <bart@etpmod.phys.tue.nl>, Andreas Mohr");
MODULE_DESCRIPTION("Avance Logic ALS4000");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Avance Logic,ALS4000}}");
#if IS_REACHABLE(CONFIG_GAMEPORT)
#define SUPPORT_JOYSTICK 1
MODULE_AUTHOR("Takashi Iwai <tiwai@suse.de>");
MODULE_DESCRIPTION("ATI IXP AC97 controller");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ATI,IXP150/200/250/300/400/600}}");
static int index = SNDRV_DEFAULT_IDX1; /* Index 0-MAX */
static char *id = SNDRV_DEFAULT_STR1; /* ID for this card */
MODULE_AUTHOR("Takashi Iwai <tiwai@suse.de>");
MODULE_DESCRIPTION("ATI IXP MC97 controller");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ATI,IXP150/200/250}}");
static int index = -2; /* Exclude the first card */
static char *id = SNDRV_DEFAULT_STR1; /* ID for this card */
MODULE_DESCRIPTION("Aureal vortex");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Aureal Semiconductor Inc., Aureal Vortex Sound Processor}}");
-
MODULE_DEVICE_TABLE(pci, snd_vortex_ids);
static void vortex_fix_latency(struct pci_dev *vortex)
MODULE_AUTHOR("Andreas Mohr <andi AT lisas.de>");
MODULE_DESCRIPTION("Aztech AZF3328 (PCI168)");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Aztech,AZF3328}}");
#if IS_REACHABLE(CONFIG_GAMEPORT)
#define SUPPORT_GAMEPORT 1
MODULE_AUTHOR("Clemens Ladisch <clemens@ladisch.de>");
MODULE_DESCRIPTION("Brooktree Bt87x audio driver");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Brooktree,Bt878},"
- "{Brooktree,Bt879}}");
static int index[SNDRV_CARDS] = {[0 ... (SNDRV_CARDS - 1)] = -2}; /* Exclude the first card */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
MODULE_AUTHOR("James Courtier-Dutton <James@superbug.demon.co.uk>");
MODULE_DESCRIPTION("CA0106");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Creative,SB CA0106 chip}}");
// module parameters (see "Module Parameters")
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
MODULE_AUTHOR("Takashi Iwai <tiwai@suse.de>");
MODULE_DESCRIPTION("C-Media CMI8x38 PCI");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{C-Media,CMI8738},"
- "{C-Media,CMI8738B},"
- "{C-Media,CMI8338A},"
- "{C-Media,CMI8338B}}");
#if IS_REACHABLE(CONFIG_GAMEPORT)
#define SUPPORT_JOYSTICK 1
MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
MODULE_DESCRIPTION("Cirrus Logic CS4281");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Cirrus Logic,CS4281}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
MODULE_DESCRIPTION("Cirrus Logic Sound Fusion CS46XX");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Cirrus Logic,Sound Fusion (CS4280)},"
- "{Cirrus Logic,Sound Fusion (CS4610)},"
- "{Cirrus Logic,Sound Fusion (CS4612)},"
- "{Cirrus Logic,Sound Fusion (CS4615)},"
- "{Cirrus Logic,Sound Fusion (CS4622)},"
- "{Cirrus Logic,Sound Fusion (CS4624)},"
- "{Cirrus Logic,Sound Fusion (CS4630)}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
MODULE_AUTHOR("Jaya Kumar");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("CS5535 Audio");
-MODULE_SUPPORTED_DEVICE("CS5535 Audio");
MODULE_AUTHOR("Creative Technology Ltd");
MODULE_DESCRIPTION("X-Fi driver version 1.03");
MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("{{Creative Labs, Sound Blaster X-Fi}");
static unsigned int reference_rate = 48000;
static unsigned int multiple = 2;
MODULE_AUTHOR("Giuliano Pochini <pochini@shiny.it>");
MODULE_LICENSE("GPL v2");
MODULE_DESCRIPTION("Echoaudio " ECHOCARD_NAME " soundcards driver");
-MODULE_SUPPORTED_DEVICE("{{Echoaudio," ECHOCARD_NAME "}}");
MODULE_DEVICE_TABLE(pci, snd_echo_ids);
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
MODULE_DESCRIPTION("EMU10K1");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Creative Labs,SB Live!/PCI512/E-mu APS},"
- "{Creative Labs,SB Audigy}}");
#if IS_ENABLED(CONFIG_SND_SEQUENCER)
#define ENABLE_SYNTH
MODULE_AUTHOR("Francisco Moraes <fmoraes@nc.rr.com>");
MODULE_DESCRIPTION("EMU10K1X");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Dell Creative Labs,SB Live!}");
// module parameters (see "Module Parameters")
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
MODULE_LICENSE("GPL");
#ifdef CHIP1370
MODULE_DESCRIPTION("Ensoniq AudioPCI ES1370");
-MODULE_SUPPORTED_DEVICE("{{Ensoniq,AudioPCI-97 ES1370},"
- "{Creative Labs,SB PCI64/128 (ES1370)}}");
#endif
#ifdef CHIP1371
MODULE_DESCRIPTION("Ensoniq/Creative AudioPCI ES1371+");
-MODULE_SUPPORTED_DEVICE("{{Ensoniq,AudioPCI ES1371/73},"
- "{Ensoniq,AudioPCI ES1373},"
- "{Creative Labs,Ectiva EV1938},"
- "{Creative Labs,SB PCI64/128 (ES1371/73)},"
- "{Creative Labs,Vibra PCI128},"
- "{Ectiva,EV1938}}");
#endif
#if IS_REACHABLE(CONFIG_GAMEPORT)
MODULE_AUTHOR("Jaromir Koutek <miri@punknet.cz>");
MODULE_DESCRIPTION("ESS Solo-1");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ESS,ES1938},"
- "{ESS,ES1946},"
- "{ESS,ES1969},"
- "{TerraTec,128i PCI}}");
#if IS_REACHABLE(CONFIG_GAMEPORT)
#define SUPPORT_JOYSTICK 1
MODULE_DESCRIPTION("ESS Maestro");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ESS,Maestro 2e},"
- "{ESS,Maestro 2},"
- "{ESS,Maestro 1},"
- "{TerraTec,DMX}}");
#if IS_REACHABLE(CONFIG_GAMEPORT)
#define SUPPORT_JOYSTICK 1
MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
MODULE_DESCRIPTION("ForteMedia FM801");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ForteMedia,FM801},"
- "{Genius,SoundMaker Live 5.1}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
if (codec->bus->shutdown)
return;
+ /* ignore unsol events during system suspend/resume */
+ if (codec->core.dev.power.power_state.event != PM_EVENT_ON)
+ return;
+
if (codec->patch_ops.unsol_event)
codec->patch_ops.unsol_event(codec, ev);
}
20,
178000000);
- /* by some reason, the playback stream stalls on PulseAudio with
- * tsched=1 when a capture stream triggers. Until we figure out the
- * real cause, disable tsched mode by telling the PCM info flag.
- */
- if (chip->driver_caps & AZX_DCAPS_AMD_WORKAROUND)
- runtime->hw.info |= SNDRV_PCM_INFO_BATCH;
-
if (chip->align_buffer_size)
/* constrain buffer sizes to be multiple of 128
bytes. This is more efficient in terms of memory
spec->micmute_led.led_mode = MICMUTE_LED_FOLLOW_MUTE;
spec->micmute_led.capture = 0;
- spec->micmute_led.led_value = 0;
+ spec->micmute_led.led_value = -1;
spec->micmute_led.old_hook = spec->cap_sync_hook;
spec->cap_sync_hook = update_micmute_led;
if (!snd_hda_gen_add_kctl(spec, NULL, &micmute_led_mode_ctl))
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Intel, ICH6},"
- "{Intel, ICH6M},"
- "{Intel, ICH7},"
- "{Intel, ESB2},"
- "{Intel, ICH8},"
- "{Intel, ICH9},"
- "{Intel, ICH10},"
- "{Intel, PCH},"
- "{Intel, CPT},"
- "{Intel, PPT},"
- "{Intel, LPT},"
- "{Intel, LPT_LP},"
- "{Intel, WPT_LP},"
- "{Intel, SPT},"
- "{Intel, SPT_LP},"
- "{Intel, HPT},"
- "{Intel, PBG},"
- "{Intel, SCH},"
- "{ATI, SB450},"
- "{ATI, SB600},"
- "{ATI, RS600},"
- "{ATI, RS690},"
- "{ATI, RS780},"
- "{ATI, R600},"
- "{ATI, RV630},"
- "{ATI, RV610},"
- "{ATI, RV670},"
- "{ATI, RV635},"
- "{ATI, RV620},"
- "{ATI, RV770},"
- "{VIA, VT8251},"
- "{VIA, VT8237A},"
- "{SiS, SIS966},"
- "{ULI, M5461}}");
MODULE_DESCRIPTION("Intel HDA driver");
#if defined(CONFIG_PM) && defined(CONFIG_VGA_SWITCHEROO)
struct snd_card *card = dev_get_drvdata(dev);
struct azx *chip;
+ if (!azx_is_pm_ready(card))
+ return 0;
+
chip = card->private_data;
chip->pm_prepared = 1;
+ snd_power_change_state(card, SNDRV_CTL_POWER_D3hot);
+
+ flush_work(&azx_bus(chip)->unsol_work);
/* HDA controller always requires different WAKEEN for runtime suspend
* and system suspend, so don't use direct-complete here.
struct snd_card *card = dev_get_drvdata(dev);
struct azx *chip;
+ if (!azx_is_pm_ready(card))
+ return;
+
chip = card->private_data;
+ snd_power_change_state(card, SNDRV_CTL_POWER_D0);
chip->pm_prepared = 0;
}
SND_PCI_QUIRK(0x1102, 0x0013, "Recon3D", QUIRK_R3D),
SND_PCI_QUIRK(0x1102, 0x0018, "Recon3D", QUIRK_R3D),
SND_PCI_QUIRK(0x1102, 0x0051, "Sound Blaster AE-5", QUIRK_AE5),
+ SND_PCI_QUIRK(0x1102, 0x0191, "Sound Blaster AE-5 Plus", QUIRK_AE5),
SND_PCI_QUIRK(0x1102, 0x0081, "Sound Blaster AE-7", QUIRK_AE7),
{}
};
return 0;
}
+static void cxt_init_gpio_led(struct hda_codec *codec)
+{
+ struct conexant_spec *spec = codec->spec;
+ unsigned int mask = spec->gpio_mute_led_mask | spec->gpio_mic_led_mask;
+
+ if (mask) {
+ snd_hda_codec_write(codec, 0x01, 0, AC_VERB_SET_GPIO_MASK,
+ mask);
+ snd_hda_codec_write(codec, 0x01, 0, AC_VERB_SET_GPIO_DIRECTION,
+ mask);
+ snd_hda_codec_write(codec, 0x01, 0, AC_VERB_SET_GPIO_DATA,
+ spec->gpio_led);
+ }
+}
+
static int cx_auto_init(struct hda_codec *codec)
{
struct conexant_spec *spec = codec->spec;
if (!spec->dynamic_eapd)
cx_auto_turn_eapd(codec, spec->num_eapds, spec->eapds, true);
+ cxt_init_gpio_led(codec);
snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_INIT);
return 0;
CXT_FIXUP_HP_SPECTRE,
CXT_FIXUP_HP_GATE_MIC,
CXT_FIXUP_MUTE_LED_GPIO,
+ CXT_FIXUP_HP_ZBOOK_MUTE_LED,
CXT_FIXUP_HEADSET_MIC,
CXT_FIXUP_HP_MIC_NO_PRESENCE,
};
return 0;
}
-
-static void cxt_fixup_mute_led_gpio(struct hda_codec *codec,
- const struct hda_fixup *fix, int action)
+static void cxt_setup_mute_led(struct hda_codec *codec,
+ unsigned int mute, unsigned int mic_mute)
{
struct conexant_spec *spec = codec->spec;
- static const struct hda_verb gpio_init[] = {
- { 0x01, AC_VERB_SET_GPIO_MASK, 0x03 },
- { 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x03 },
- {}
- };
- if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+ spec->gpio_led = 0;
+ spec->mute_led_polarity = 0;
+ if (mute) {
snd_hda_gen_add_mute_led_cdev(codec, cxt_gpio_mute_update);
- spec->gpio_led = 0;
- spec->mute_led_polarity = 0;
- spec->gpio_mute_led_mask = 0x01;
- spec->gpio_mic_led_mask = 0x02;
+ spec->gpio_mute_led_mask = mute;
+ }
+ if (mic_mute) {
snd_hda_gen_add_micmute_led_cdev(codec, cxt_gpio_micmute_update);
+ spec->gpio_mic_led_mask = mic_mute;
}
- snd_hda_add_verbs(codec, gpio_init);
- if (spec->gpio_led)
- snd_hda_codec_write(codec, 0x01, 0, AC_VERB_SET_GPIO_DATA,
- spec->gpio_led);
}
+static void cxt_fixup_mute_led_gpio(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ if (action == HDA_FIXUP_ACT_PRE_PROBE)
+ cxt_setup_mute_led(codec, 0x01, 0x02);
+}
+
+static void cxt_fixup_hp_zbook_mute_led(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ if (action == HDA_FIXUP_ACT_PRE_PROBE)
+ cxt_setup_mute_led(codec, 0x10, 0x20);
+}
/* ThinkPad X200 & co with cxt5051 */
static const struct hda_pintbl cxt_pincfg_lenovo_x200[] = {
.type = HDA_FIXUP_FUNC,
.v.func = cxt_fixup_mute_led_gpio,
},
+ [CXT_FIXUP_HP_ZBOOK_MUTE_LED] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = cxt_fixup_hp_zbook_mute_led,
+ },
[CXT_FIXUP_HEADSET_MIC] = {
.type = HDA_FIXUP_FUNC,
.v.func = cxt_fixup_headset_mic,
SND_PCI_QUIRK(0x103c, 0x8299, "HP 800 G3 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x103c, 0x829a, "HP 800 G3 DM", CXT_FIXUP_HP_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x103c, 0x8402, "HP ProBook 645 G4", CXT_FIXUP_MUTE_LED_GPIO),
+ SND_PCI_QUIRK(0x103c, 0x8427, "HP ZBook Studio G5", CXT_FIXUP_HP_ZBOOK_MUTE_LED),
+ SND_PCI_QUIRK(0x103c, 0x844f, "HP ZBook Studio G5", CXT_FIXUP_HP_ZBOOK_MUTE_LED),
SND_PCI_QUIRK(0x103c, 0x8455, "HP Z2 G4", CXT_FIXUP_HP_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x103c, 0x8456, "HP Z2 G4 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x103c, 0x8457, "HP Z2 G4 mini", CXT_FIXUP_HP_MIC_NO_PRESENCE),
{ .id = CXT_FIXUP_MUTE_LED_EAPD, .name = "mute-led-eapd" },
{ .id = CXT_FIXUP_HP_DOCK, .name = "hp-dock" },
{ .id = CXT_FIXUP_MUTE_LED_GPIO, .name = "mute-led-gpio" },
+ { .id = CXT_FIXUP_HP_ZBOOK_MUTE_LED, .name = "hp-zbook-mute-led" },
{ .id = CXT_FIXUP_HP_MIC_NO_PRESENCE, .name = "hp-mic-fix" },
{}
};
}
#ifdef CONFIG_PM
+static int generic_hdmi_suspend(struct hda_codec *codec)
+{
+ struct hdmi_spec *spec = codec->spec;
+ int pin_idx;
+
+ for (pin_idx = 0; pin_idx < spec->num_pins; pin_idx++) {
+ struct hdmi_spec_per_pin *per_pin = get_pin(spec, pin_idx);
+ cancel_delayed_work_sync(&per_pin->work);
+ }
+ return 0;
+}
+
static int generic_hdmi_resume(struct hda_codec *codec)
{
struct hdmi_spec *spec = codec->spec;
.build_controls = generic_hdmi_build_controls,
.unsol_event = hdmi_unsol_event,
#ifdef CONFIG_PM
+ .suspend = generic_hdmi_suspend,
.resume = generic_hdmi_resume,
#endif
};
snd_hda_sequence_write(codec, verbs);
}
+/* Fix the speaker amp after resume, etc */
+static void alc269vb_fixup_aspire_e1_coef(struct hda_codec *codec,
+ const struct hda_fixup *fix,
+ int action)
+{
+ if (action == HDA_FIXUP_ACT_INIT)
+ alc_update_coef_idx(codec, 0x0d, 0x6000, 0x6000);
+}
+
static void alc269_fixup_pcm_44k(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
}
}
+static void alc236_fixup_hp_gpio_led(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ alc_fixup_hp_gpio_led(codec, action, 0x02, 0x01);
+}
+
static void alc269_fixup_hp_gpio_led(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
case 0x10ec0274:
case 0x10ec0294:
alc_process_coef_fw(codec, coef0274);
- msleep(80);
+ msleep(850);
val = alc_read_coef_idx(codec, 0x46);
is_ctia = (val & 0x00f0) == 0x00f0;
break;
struct hda_jack_callback *jack)
{
snd_hda_gen_hp_automute(codec, jack);
+ alc_update_headset_mode(codec);
}
static void alc_probe_headset_mode(struct hda_codec *codec)
ALC283_FIXUP_HEADSET_MIC,
ALC255_FIXUP_MIC_MUTE_LED,
ALC282_FIXUP_ASPIRE_V5_PINS,
+ ALC269VB_FIXUP_ASPIRE_E1_COEF,
ALC280_FIXUP_HP_GPIO4,
ALC286_FIXUP_HP_GPIO_LED,
ALC280_FIXUP_HP_GPIO2_MIC_HOTKEY,
ALC294_FIXUP_ASUS_GX502_VERBS,
ALC285_FIXUP_HP_GPIO_LED,
ALC285_FIXUP_HP_MUTE_LED,
+ ALC236_FIXUP_HP_GPIO_LED,
ALC236_FIXUP_HP_MUTE_LED,
ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET,
ALC295_FIXUP_ASUS_MIC_NO_PRESENCE,
{ },
},
},
+ [ALC269VB_FIXUP_ASPIRE_E1_COEF] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc269vb_fixup_aspire_e1_coef,
+ },
[ALC280_FIXUP_HP_GPIO4] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc280_fixup_hp_gpio4,
.type = HDA_FIXUP_FUNC,
.v.func = alc285_fixup_hp_mute_led,
},
+ [ALC236_FIXUP_HP_GPIO_LED] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc236_fixup_hp_gpio_led,
+ },
[ALC236_FIXUP_HP_MUTE_LED] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc236_fixup_hp_mute_led,
SND_PCI_QUIRK(0x1025, 0x0762, "Acer Aspire E1-472", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572),
SND_PCI_QUIRK(0x1025, 0x0775, "Acer Aspire E1-572", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572),
SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS),
+ SND_PCI_QUIRK(0x1025, 0x0840, "Acer Aspire E1", ALC269VB_FIXUP_ASPIRE_E1_COEF),
SND_PCI_QUIRK(0x1025, 0x101c, "Acer Veriton N2510G", ALC269_FIXUP_LIFEBOOK),
SND_PCI_QUIRK(0x1025, 0x102b, "Acer Aspire C24-860", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1025, 0x1065, "Acer Aspire C20-820", ALC269VC_FIXUP_ACER_HEADSET_MIC),
SND_PCI_QUIRK(0x103c, 0x8783, "HP ZBook Fury 15 G7 Mobile Workstation",
ALC285_FIXUP_HP_GPIO_AMP_INIT),
SND_PCI_QUIRK(0x103c, 0x87c8, "HP", ALC287_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x87e5, "HP ProBook 440 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x87f2, "HP ProBook 640 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x87f4, "HP", ALC287_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x87f5, "HP", ALC287_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x87f7, "HP Spectre x360 14", ALC245_FIXUP_HP_X360_AMP),
+ SND_PCI_QUIRK(0x103c, 0x8846, "HP EliteBook 850 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x884c, "HP EliteBook 840 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x1b35, 0x1237, "CZC L101", ALC269_FIXUP_CZC_L101),
SND_PCI_QUIRK(0x1b7d, 0xa831, "Ordissimo EVE2 ", ALC269VB_FIXUP_ORDISSIMO_EVE2), /* Also known as Malata PC-B1303 */
SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1d72, 0x1947, "RedmiBook Air", ALC255_FIXUP_XIAOMI_HEADSET_MIC),
SND_PCI_QUIRK(0x10ec, 0x118c, "Medion EE4254 MD62100", ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE),
SND_PCI_QUIRK(0x1c06, 0x2013, "Lemote A1802", ALC269_FIXUP_LEMOTE_A1802),
SND_PCI_QUIRK(0x1c06, 0x2015, "Lemote A190X", ALC269_FIXUP_LEMOTE_A190X),
{.id = ALC283_FIXUP_HEADSET_MIC, .name = "alc283-headset"},
{.id = ALC255_FIXUP_MIC_MUTE_LED, .name = "alc255-dell-mute"},
{.id = ALC282_FIXUP_ASPIRE_V5_PINS, .name = "aspire-v5"},
+ {.id = ALC269VB_FIXUP_ASPIRE_E1_COEF, .name = "aspire-e1-coef"},
{.id = ALC280_FIXUP_HP_GPIO4, .name = "hp-gpio4"},
{.id = ALC286_FIXUP_HP_GPIO_LED, .name = "hp-gpio-led"},
{.id = ALC280_FIXUP_HP_GPIO2_MIC_HOTKEY, .name = "hp-gpio2-hotkey"},
MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
MODULE_DESCRIPTION("ICEnsemble ICE1712 (Envy24)");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{"
- HOONTECH_DEVICE_DESC
- DELTA_DEVICE_DESC
- EWS_DEVICE_DESC
- "{ICEnsemble,Generic ICE1712},"
- "{ICEnsemble,Generic Envy24}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
MODULE_DESCRIPTION("VIA ICEnsemble ICE1724/1720 (Envy24HT/PT)");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{"
- REVO_DEVICE_DESC
- AMP_AUDIO2000_DEVICE_DESC
- AUREON_DEVICE_DESC
- VT1720_MOBO_DEVICE_DESC
- PONTIS_DEVICE_DESC
- PRODIGY192_DEVICE_DESC
- PRODIGY_HIFI_DEVICE_DESC
- JULI_DEVICE_DESC
- MAYA44_DEVICE_DESC
- PHASE_DEVICE_DESC
- WTM_DEVICE_DESC
- SE_DEVICE_DESC
- QTET_DEVICE_DESC
- "{VIA,VT1720},"
- "{VIA,VT1724},"
- "{ICEnsemble,Generic ICE1724},"
- "{ICEnsemble,Generic Envy24HT}"
- "{ICEnsemble,Generic Envy24PT}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
MODULE_DESCRIPTION("Intel 82801AA,82901AB,i810,i820,i830,i840,i845,MX440; SiS 7012; Ali 5455");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Intel,82801AA-ICH},"
- "{Intel,82901AB-ICH0},"
- "{Intel,82801BA-ICH2},"
- "{Intel,82801CA-ICH3},"
- "{Intel,82801DB-ICH4},"
- "{Intel,ICH5},"
- "{Intel,ICH6},"
- "{Intel,ICH7},"
- "{Intel,6300ESB},"
- "{Intel,ESB2},"
- "{Intel,MX440},"
- "{SiS,SI7012},"
- "{NVidia,nForce Audio},"
- "{NVidia,nForce2 Audio},"
- "{NVidia,nForce3 Audio},"
- "{NVidia,MCP04},"
- "{NVidia,MCP501},"
- "{NVidia,CK804},"
- "{NVidia,CK8},"
- "{NVidia,CK8S},"
- "{AMD,AMD768},"
- "{AMD,AMD8111},"
- "{ALI,M5455}}");
static int index = SNDRV_DEFAULT_IDX1; /* Index 0-MAX */
static char *id = SNDRV_DEFAULT_STR1; /* ID for this card */
MODULE_DESCRIPTION("Intel 82801AA,82901AB,i810,i820,i830,i840,i845,MX440; "
"SiS 7013; NVidia MCP/2/2S/3 modems");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Intel,82801AA-ICH},"
- "{Intel,82901AB-ICH0},"
- "{Intel,82801BA-ICH2},"
- "{Intel,82801CA-ICH3},"
- "{Intel,82801DB-ICH4},"
- "{Intel,ICH5},"
- "{Intel,ICH6},"
- "{Intel,ICH7},"
- "{Intel,MX440},"
- "{SiS,7013},"
- "{NVidia,NForce Modem},"
- "{NVidia,NForce2 Modem},"
- "{NVidia,NForce2s Modem},"
- "{NVidia,NForce3 Modem},"
- "{AMD,AMD768}}");
static int index = -2; /* Exclude the first card */
static char *id = SNDRV_DEFAULT_STR1; /* ID for this card */
MODULE_DESCRIPTION("korg1212");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{KORG,korg1212}}");
MODULE_FIRMWARE("korg/k1212.dsp");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
*/
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Digigram, Lola}}");
MODULE_DESCRIPTION("Digigram Lola driver");
MODULE_AUTHOR("Takashi Iwai <tiwai@suse.de>");
MODULE_AUTHOR("Tim Blechmann");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("digigram lx6464es");
-MODULE_SUPPORTED_DEVICE("{digigram lx6464es{}}");
-
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;
MODULE_AUTHOR("Zach Brown <zab@zabbo.net>, Takashi Iwai <tiwai@suse.de>");
MODULE_DESCRIPTION("ESS Maestro3 PCI");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{ESS,Maestro3 PCI},"
- "{ESS,ES1988},"
- "{ESS,Allegro PCI},"
- "{ESS,Allegro-1 PCI},"
- "{ESS,Canyon3D-2/LE PCI}}");
MODULE_FIRMWARE("ess/maestro3_assp_kernel.fw");
MODULE_FIRMWARE("ess/maestro3_assp_minisrc.fw");
MODULE_AUTHOR("Digigram <alsa@digigram.com>");
MODULE_DESCRIPTION("Digigram " CARD_NAME);
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Digigram," CARD_NAME "}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
MODULE_AUTHOR("Takashi Iwai <tiwai@suse.de>");
MODULE_DESCRIPTION("NeoMagic NM256AV/ZX");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{NeoMagic,NM256AV},"
- "{NeoMagic,NM256ZX}}");
/*
* some compile conditions.
MODULE_AUTHOR("Clemens Ladisch <clemens@ladisch.de>");
MODULE_DESCRIPTION("C-Media CMI8788 driver");
MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("{{C-Media,CMI8786}"
- ",{C-Media,CMI8787}"
- ",{C-Media,CMI8788}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;
MODULE_AUTHOR("Clemens Ladisch <clemens@ladisch.de>");
MODULE_DESCRIPTION("Studio Evolution SE6X driver");
MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("{{Studio Evolution,SE6X}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;
MODULE_AUTHOR("Clemens Ladisch <clemens@ladisch.de>");
MODULE_DESCRIPTION("Asus Virtuoso driver");
MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("{{Asus,AV66},{Asus,AV100},{Asus,AV200}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR;
"Marc Titinger <titinger@digigram.com>");
MODULE_DESCRIPTION("Digigram " DRIVER_NAME " " PCXHR_DRIVER_VERSION_STRING);
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Digigram," DRIVER_NAME "}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
MODULE_AUTHOR("Peter Gruber <nokos@gmx.net>");
MODULE_DESCRIPTION("riptide");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Conexant,Riptide}}");
MODULE_FIRMWARE("riptide.hex");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX;
MODULE_AUTHOR("Martin Langer <martin-langer@gmx.de>, Pilo Chambert <pilo.c@wanadoo.fr>");
MODULE_DESCRIPTION("RME Digi32, Digi32/8, Digi32 PRO");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{RME,Digi32}," "{RME,Digi32/8}," "{RME,Digi32 PRO}}");
/* Defines for RME Digi32 series */
#define RME32_SPDIF_NCHANNELS 2
MODULE_DESCRIPTION("RME Digi96, Digi96/8, Digi96/8 PRO, Digi96/8 PST, "
"Digi96/8 PAD");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{RME,Digi96},"
- "{RME,Digi96/8},"
- "{RME,Digi96/8 PRO},"
- "{RME,Digi96/8 PST},"
- "{RME,Digi96/8 PAD}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
MODULE_AUTHOR("Paul Davis <paul@linuxaudiosystems.com>, Marcus Andersson, Thomas Charbonnel <thomas@undata.org>");
MODULE_DESCRIPTION("RME Hammerfall DSP");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{RME Hammerfall-DSP},"
- "{RME HDSP-9652},"
- "{RME HDSP-9632}}");
MODULE_FIRMWARE("rpm_firmware.bin");
MODULE_FIRMWARE("multiface_firmware.bin");
MODULE_FIRMWARE("multiface_firmware_rev11.bin");
);
MODULE_DESCRIPTION("RME HDSPM");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{RME HDSPM-MADI}}");
/* --- Write registers. ---
These are defined as byte-offsets from the iobase value. */
MODULE_AUTHOR("Paul Davis <pbd@op.net>, Winfried Ritsch");
MODULE_DESCRIPTION("RME Digi9652/Digi9636");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{RME,Hammerfall},"
- "{RME,Hammerfall-Light}}");
/* The Hammerfall has two sets of 24 ADAT + 2 S/PDIF channels, one for
capture, one for playback. Both the ADAT and S/PDIF channels appear
MODULE_AUTHOR("David Dillow <dave@thedillows.org>");
MODULE_DESCRIPTION("SiS7019");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{SiS,SiS7019 Audio Accelerator}}");
static int index = SNDRV_DEFAULT_IDX1; /* Index 0-MAX */
static char *id = SNDRV_DEFAULT_STR1; /* ID for this card */
MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
MODULE_DESCRIPTION("S3 SonicVibes PCI");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{S3,SonicVibes PCI}}");
#if IS_REACHABLE(CONFIG_GAMEPORT)
#define SUPPORT_JOYSTICK 1
MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>, <audio@tridentmicro.com>");
MODULE_DESCRIPTION("Trident 4D-WaveDX/NX & SiS SI7018");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Trident,4DWave DX},"
- "{Trident,4DWave NX},"
- "{SiS,SI7018 PCI Audio},"
- "{Best Union,Miss Melody 4DWave PCI},"
- "{HIS,4DWave PCI},"
- "{Warpspeed,ONSpeed 4DWave PCI},"
- "{Aztech Systems,PCI 64-Q3D},"
- "{Addonics,SV 750},"
- "{CHIC,True Sound 4Dwave},"
- "{Shark,Predator4D-PCI},"
- "{Jaton,SonicWave 4D},"
- "{Hoontech,SoundTrack Digital 4DWave NX}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
MODULE_DESCRIPTION("VIA VT82xx audio");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{VIA,VT82C686A/B/C,pci},{VIA,VT8233A/C,8235}}");
#if IS_REACHABLE(CONFIG_GAMEPORT)
#define SUPPORT_JOYSTICK 1
MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
MODULE_DESCRIPTION("VIA VT82xx modem");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{VIA,VT82C686A/B/C modem,pci}}");
static int index = -2; /* Exclude the first card */
static char *id = SNDRV_DEFAULT_STR1; /* ID for this card */
MODULE_AUTHOR("Takashi Iwai <tiwai@suse.de>");
MODULE_DESCRIPTION("Digigram VX222 V2/Mic");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Digigram," CARD_NAME "}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
MODULE_DESCRIPTION("Yamaha DS-1 PCI");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Yamaha,YMF724},"
- "{Yamaha,YMF724F},"
- "{Yamaha,YMF740},"
- "{Yamaha,YMF740C},"
- "{Yamaha,YMF744},"
- "{Yamaha,YMF754}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
MODULE_DESCRIPTION("Sound Core " CARD_NAME);
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Sound Core," CARD_NAME "}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
#include <sound/initval.h>
#include <sound/tlv.h>
-/*
- */
-
MODULE_AUTHOR("Takashi Iwai <tiwai@suse.de>");
MODULE_DESCRIPTION("Digigram VXPocket");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Digigram,VXPocket},{Digigram,VXPocket440}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
#define CHIP_NAME "PMac"
MODULE_DESCRIPTION("PowerMac");
-MODULE_SUPPORTED_DEVICE("{{Apple,PowerMac}}");
MODULE_LICENSE("GPL");
static int index = SNDRV_DEFAULT_IDX1; /* Index 0-MAX */
MODULE_AUTHOR("Adrian McMenamin <adrian@mcmen.demon.co.uk>");
MODULE_DESCRIPTION("Dreamcast AICA sound (pcm) driver");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Yamaha/SEGA, AICA}}");
MODULE_FIRMWARE("aica_firmware.bin");
/* module parameters */
MODULE_AUTHOR("Rafael Ignacio Zurita <rizurita@yahoo.com>");
MODULE_DESCRIPTION("SuperH DAC audio driver");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{SuperH DAC audio support}}");
/* Module Parameters */
static int index = SNDRV_DEFAULT_IDX1;
&cygnus_ssp_dai[active_port_count]);
/* negative is err, 0 is active and good, 1 is disabled */
- if (err < 0)
+ if (err < 0) {
+ of_node_put(child_node);
return err;
+ }
else if (!err) {
dev_dbg(dev, "Activating DAI: %s\n",
cygnus_ssp_dai[active_port_count].name);
imply SND_SOC_SI476X
imply SND_SOC_SIMPLE_AMPLIFIER
imply SND_SOC_SIMPLE_MUX
- imply SND_SOC_SIRF_AUDIO_CODEC
imply SND_SOC_SPDIF
imply SND_SOC_SSM2305
imply SND_SOC_SSM2518
tristate "Simple Audio Mux"
select GPIOLIB
-config SND_SOC_SIRF_AUDIO_CODEC
- tristate "SiRF SoC internal audio codec"
- select REGMAP_MMIO
-
config SND_SOC_SPDIF
tristate "S/PDIF CODEC"
{ .compatible = "asahi-kasei,ak4497", .data = &ak4497_drvdata},
{ },
};
+MODULE_DEVICE_TABLE(of, ak4458_of_match);
static struct i2c_driver ak4458_i2c_driver = {
.driver = {
{ .compatible = "asahi-kasei,ak5558"},
{ }
};
+MODULE_DEVICE_TABLE(of, ak5558_i2c_dt_ids);
static struct i2c_driver ak5558_i2c_driver = {
.driver = {
};
static DECLARE_TLV_DB_SCALE(adc_tlv, -9600, 100, false);
-static DECLARE_TLV_DB_SCALE(mixer_tlv, -6200, 100, false);
+static DECLARE_TLV_DB_SCALE(mixer_tlv, -6300, 100, true);
static const char * const cs42l42_hpf_freq_text[] = {
"1.86Hz", "120Hz", "235Hz", "466Hz"
CS42L42_DAC_HPF_EN_SHIFT, true, false),
SOC_DOUBLE_R_TLV("Mixer Volume", CS42L42_MIXER_CHA_VOL,
CS42L42_MIXER_CHB_VOL, CS42L42_MIXER_CH_VOL_SHIFT,
- 0x3e, 1, mixer_tlv)
+ 0x3f, 1, mixer_tlv)
};
static int cs42l42_hpdrv_evt(struct snd_soc_dapm_widget *w,
{"HP", NULL, "HPDRV"}
};
-static int cs42l42_set_bias_level(struct snd_soc_component *component,
- enum snd_soc_bias_level level)
-{
- struct cs42l42_private *cs42l42 = snd_soc_component_get_drvdata(component);
- int ret;
-
- switch (level) {
- case SND_SOC_BIAS_ON:
- break;
- case SND_SOC_BIAS_PREPARE:
- break;
- case SND_SOC_BIAS_STANDBY:
- if (snd_soc_component_get_bias_level(component) == SND_SOC_BIAS_OFF) {
- regcache_cache_only(cs42l42->regmap, false);
- regcache_sync(cs42l42->regmap);
- ret = regulator_bulk_enable(
- ARRAY_SIZE(cs42l42->supplies),
- cs42l42->supplies);
- if (ret != 0) {
- dev_err(component->dev,
- "Failed to enable regulators: %d\n",
- ret);
- return ret;
- }
- }
- break;
- case SND_SOC_BIAS_OFF:
-
- regcache_cache_only(cs42l42->regmap, true);
- regulator_bulk_disable(ARRAY_SIZE(cs42l42->supplies),
- cs42l42->supplies);
- break;
- }
-
- return 0;
-}
-
static int cs42l42_component_probe(struct snd_soc_component *component)
{
struct cs42l42_private *cs42l42 =
static const struct snd_soc_component_driver soc_component_dev_cs42l42 = {
.probe = cs42l42_component_probe,
- .set_bias_level = cs42l42_set_bias_level,
.dapm_widgets = cs42l42_dapm_widgets,
.num_dapm_widgets = ARRAY_SIZE(cs42l42_dapm_widgets),
.dapm_routes = cs42l42_audio_map,
CS42L42_CLK_OASRC_SEL_MASK,
CS42L42_CLK_OASRC_SEL_12 <<
CS42L42_CLK_OASRC_SEL_SHIFT);
- /* channel 1 on low LRCLK, 32 bit */
- snd_soc_component_update_bits(component,
- CS42L42_ASP_RX_DAI0_CH1_AP_RES,
- CS42L42_ASP_RX_CH_AP_MASK |
- CS42L42_ASP_RX_CH_RES_MASK,
- (CS42L42_ASP_RX_CH_AP_LOW <<
- CS42L42_ASP_RX_CH_AP_SHIFT) |
- (CS42L42_ASP_RX_CH_RES_32 <<
- CS42L42_ASP_RX_CH_RES_SHIFT));
- /* Channel 2 on high LRCLK, 32 bit */
- snd_soc_component_update_bits(component,
- CS42L42_ASP_RX_DAI0_CH2_AP_RES,
- CS42L42_ASP_RX_CH_AP_MASK |
- CS42L42_ASP_RX_CH_RES_MASK,
- (CS42L42_ASP_RX_CH_AP_HI <<
- CS42L42_ASP_RX_CH_AP_SHIFT) |
- (CS42L42_ASP_RX_CH_RES_32 <<
- CS42L42_ASP_RX_CH_RES_SHIFT));
if (pll_ratio_table[i].mclk_src_sel == 0) {
/* Pass the clock straight through */
snd_soc_component_update_bits(component,
/* Bitclock/frame inversion */
switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
case SND_SOC_DAIFMT_NB_NF:
+ asp_cfg_val |= CS42L42_ASP_SCPOL_NOR << CS42L42_ASP_SCPOL_SHIFT;
break;
case SND_SOC_DAIFMT_NB_IF:
- asp_cfg_val |= CS42L42_ASP_POL_INV <<
- CS42L42_ASP_LCPOL_IN_SHIFT;
+ asp_cfg_val |= CS42L42_ASP_SCPOL_NOR << CS42L42_ASP_SCPOL_SHIFT;
+ asp_cfg_val |= CS42L42_ASP_LCPOL_INV << CS42L42_ASP_LCPOL_SHIFT;
break;
case SND_SOC_DAIFMT_IB_NF:
- asp_cfg_val |= CS42L42_ASP_POL_INV <<
- CS42L42_ASP_SCPOL_IN_DAC_SHIFT;
break;
case SND_SOC_DAIFMT_IB_IF:
- asp_cfg_val |= CS42L42_ASP_POL_INV <<
- CS42L42_ASP_LCPOL_IN_SHIFT;
- asp_cfg_val |= CS42L42_ASP_POL_INV <<
- CS42L42_ASP_SCPOL_IN_DAC_SHIFT;
+ asp_cfg_val |= CS42L42_ASP_LCPOL_INV << CS42L42_ASP_LCPOL_SHIFT;
break;
}
- snd_soc_component_update_bits(component, CS42L42_ASP_CLK_CFG,
- CS42L42_ASP_MODE_MASK |
- CS42L42_ASP_SCPOL_IN_DAC_MASK |
- CS42L42_ASP_LCPOL_IN_MASK, asp_cfg_val);
+ snd_soc_component_update_bits(component, CS42L42_ASP_CLK_CFG, CS42L42_ASP_MODE_MASK |
+ CS42L42_ASP_SCPOL_MASK |
+ CS42L42_ASP_LCPOL_MASK,
+ asp_cfg_val);
return 0;
}
{
struct snd_soc_component *component = dai->component;
struct cs42l42_private *cs42l42 = snd_soc_component_get_drvdata(component);
- int retval;
+ unsigned int width = (params_width(params) / 8) - 1;
+ unsigned int val = 0;
cs42l42->srate = params_rate(params);
- cs42l42->swidth = params_width(params);
- retval = cs42l42_pll_config(component);
+ switch(substream->stream) {
+ case SNDRV_PCM_STREAM_PLAYBACK:
+ val |= width << CS42L42_ASP_RX_CH_RES_SHIFT;
+ /* channel 1 on low LRCLK */
+ snd_soc_component_update_bits(component, CS42L42_ASP_RX_DAI0_CH1_AP_RES,
+ CS42L42_ASP_RX_CH_AP_MASK |
+ CS42L42_ASP_RX_CH_RES_MASK, val);
+ /* Channel 2 on high LRCLK */
+ val |= CS42L42_ASP_RX_CH_AP_HI << CS42L42_ASP_RX_CH_AP_SHIFT;
+ snd_soc_component_update_bits(component, CS42L42_ASP_RX_DAI0_CH2_AP_RES,
+ CS42L42_ASP_RX_CH_AP_MASK |
+ CS42L42_ASP_RX_CH_RES_MASK, val);
+ break;
+ default:
+ break;
+ }
- return retval;
+ return cs42l42_pll_config(component);
}
static int cs42l42_set_sysclk(struct snd_soc_dai *dai,
return 0;
}
-#define CS42L42_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S18_3LE | \
- SNDRV_PCM_FMTBIT_S20_3LE | SNDRV_PCM_FMTBIT_S24_LE | \
- SNDRV_PCM_FMTBIT_S32_LE)
+#define CS42L42_FORMATS (SNDRV_PCM_FMTBIT_S16_LE |\
+ SNDRV_PCM_FMTBIT_S24_LE |\
+ SNDRV_PCM_FMTBIT_S32_LE )
static const struct snd_soc_dai_ops cs42l42_ops = {
dev_dbg(&i2c_client->dev, "Found reset GPIO\n");
gpiod_set_value_cansleep(cs42l42->reset_gpio, 1);
}
- mdelay(3);
+ usleep_range(CS42L42_BOOT_TIME_US, CS42L42_BOOT_TIME_US * 2);
/* Request IRQ */
ret = devm_request_threaded_irq(&i2c_client->dev,
}
gpiod_set_value_cansleep(cs42l42->reset_gpio, 1);
+ usleep_range(CS42L42_BOOT_TIME_US, CS42L42_BOOT_TIME_US * 2);
regcache_cache_only(cs42l42->regmap, false);
regcache_sync(cs42l42->regmap);
#define CS42L42_ASP_SLAVE_MODE 0x00
#define CS42L42_ASP_MODE_SHIFT 4
#define CS42L42_ASP_MODE_MASK (1 << CS42L42_ASP_MODE_SHIFT)
-#define CS42L42_ASP_SCPOL_IN_DAC_SHIFT 2
-#define CS42L42_ASP_SCPOL_IN_DAC_MASK (1 << CS42L42_ASP_SCPOL_IN_DAC_SHIFT)
-#define CS42L42_ASP_LCPOL_IN_SHIFT 0
-#define CS42L42_ASP_LCPOL_IN_MASK (1 << CS42L42_ASP_LCPOL_IN_SHIFT)
-#define CS42L42_ASP_POL_INV 1
+#define CS42L42_ASP_SCPOL_SHIFT 2
+#define CS42L42_ASP_SCPOL_MASK (3 << CS42L42_ASP_SCPOL_SHIFT)
+#define CS42L42_ASP_SCPOL_NOR 3
+#define CS42L42_ASP_LCPOL_SHIFT 0
+#define CS42L42_ASP_LCPOL_MASK (3 << CS42L42_ASP_LCPOL_SHIFT)
+#define CS42L42_ASP_LCPOL_INV 3
#define CS42L42_ASP_FRM_CFG (CS42L42_PAGE_12 + 0x08)
#define CS42L42_ASP_STP_SHIFT 4
#define CS42L42_FRAC2_VAL(val) (((val) & 0xff0000) >> 16)
#define CS42L42_NUM_SUPPLIES 5
+#define CS42L42_BOOT_TIME_US 3000
static const char *const cs42l42_supply_names[CS42L42_NUM_SUPPLIES] = {
"VA",
struct completion pdn_done;
u32 sclk;
u32 srate;
- u32 swidth;
u8 plug_state;
u8 hs_type;
u8 ts_inv;
1, 1, TLV_DB_SCALE_ITEM(0, 0, 0),
2, 2, TLV_DB_SCALE_ITEM(250, 0, 0),
3, 3, TLV_DB_SCALE_ITEM(450, 0, 0),
- 4, 4, TLV_DB_SCALE_ITEM(700, 0, 0),
- 5, 5, TLV_DB_SCALE_ITEM(1000, 0, 0),
- 6, 6, TLV_DB_SCALE_ITEM(1300, 0, 0),
- 7, 7, TLV_DB_SCALE_ITEM(1600, 0, 0),
- 8, 8, TLV_DB_SCALE_ITEM(1800, 0, 0),
- 9, 9, TLV_DB_SCALE_ITEM(2100, 0, 0),
- 10, 10, TLV_DB_SCALE_ITEM(2400, 0, 0),
+ 4, 7, TLV_DB_SCALE_ITEM(700, 300, 0),
+ 8, 10, TLV_DB_SCALE_ITEM(1800, 300, 0),
);
static const SNDRV_CTL_TLVD_DECLARE_DB_RANGE(hpout_vol_tlv,
{
struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
u16 val, ec_hq_reg;
- int ec_tx;
+ int ec_tx = -1;
val = snd_soc_component_read(component,
CDC_RX_INP_MUX_RX_MIX_CFG4);
/* set MCLK and NPL rates */
clk_set_rate(rx->clks[2].clk, MCLK_FREQ);
- clk_set_rate(rx->clks[3].clk, MCLK_FREQ);
+ clk_set_rate(rx->clks[3].clk, 2 * MCLK_FREQ);
ret = clk_bulk_prepare_enable(RX_NUM_CLKS_MAX, rx->clks);
if (ret)
/* set MCLK and NPL rates */
clk_set_rate(tx->clks[2].clk, MCLK_FREQ);
- clk_set_rate(tx->clks[3].clk, MCLK_FREQ);
+ clk_set_rate(tx->clks[3].clk, 2 * MCLK_FREQ);
ret = clk_bulk_prepare_enable(TX_NUM_CLKS_MAX, tx->clks);
if (ret)
struct device *dev;
unsigned long active_ch_mask[VA_MACRO_MAX_DAIS];
unsigned long active_ch_cnt[VA_MACRO_MAX_DAIS];
- unsigned long active_decimator[VA_MACRO_MAX_DAIS];
u16 dmic_clk_div;
int dec_mode[VA_MACRO_NUM_DECIMATORS];
if (enable) {
set_bit(dec_id, &va->active_ch_mask[dai_id]);
va->active_ch_cnt[dai_id]++;
- va->active_decimator[dai_id] = dec_id;
} else {
clear_bit(dec_id, &va->active_ch_mask[dai_id]);
va->active_ch_cnt[dai_id]--;
- va->active_decimator[dai_id] = -1;
}
snd_soc_dapm_mixer_update_power(widget->dapm, kcontrol, enable, update);
struct va_macro *va = snd_soc_component_get_drvdata(component);
u16 tx_vol_ctl_reg, decimator;
- decimator = va->active_decimator[dai->id];
-
- tx_vol_ctl_reg = CDC_VA_TX0_TX_PATH_CTL +
- VA_MACRO_TX_PATH_OFFSET * decimator;
- if (mute)
- snd_soc_component_update_bits(component, tx_vol_ctl_reg,
- CDC_VA_TX_PATH_PGA_MUTE_EN_MASK,
- CDC_VA_TX_PATH_PGA_MUTE_EN);
- else
- snd_soc_component_update_bits(component, tx_vol_ctl_reg,
- CDC_VA_TX_PATH_PGA_MUTE_EN_MASK,
- CDC_VA_TX_PATH_PGA_MUTE_DISABLE);
+ for_each_set_bit(decimator, &va->active_ch_mask[dai->id],
+ VA_MACRO_DEC_MAX) {
+ tx_vol_ctl_reg = CDC_VA_TX0_TX_PATH_CTL +
+ VA_MACRO_TX_PATH_OFFSET * decimator;
+ if (mute)
+ snd_soc_component_update_bits(component, tx_vol_ctl_reg,
+ CDC_VA_TX_PATH_PGA_MUTE_EN_MASK,
+ CDC_VA_TX_PATH_PGA_MUTE_EN);
+ else
+ snd_soc_component_update_bits(component, tx_vol_ctl_reg,
+ CDC_VA_TX_PATH_PGA_MUTE_EN_MASK,
+ CDC_VA_TX_PATH_PGA_MUTE_DISABLE);
+ }
return 0;
}
struct snd_kcontrol *kcontrol, int event)
{
struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
- u16 gain_reg;
+ u16 path_reg, gain_reg;
int val;
- switch (w->reg) {
- case CDC_WSA_RX0_RX_PATH_MIX_CTL:
+ switch (w->shift) {
+ case WSA_MACRO_RX_MIX0:
+ path_reg = CDC_WSA_RX0_RX_PATH_MIX_CTL;
gain_reg = CDC_WSA_RX0_RX_VOL_MIX_CTL;
break;
- case CDC_WSA_RX1_RX_PATH_MIX_CTL:
+ case WSA_MACRO_RX_MIX1:
+ path_reg = CDC_WSA_RX1_RX_PATH_MIX_CTL;
gain_reg = CDC_WSA_RX1_RX_VOL_MIX_CTL;
break;
default:
snd_soc_component_write(component, gain_reg, val);
break;
case SND_SOC_DAPM_POST_PMD:
- snd_soc_component_update_bits(component, w->reg,
+ snd_soc_component_update_bits(component, path_reg,
CDC_WSA_RX_PATH_MIX_CLK_EN_MASK,
CDC_WSA_RX_PATH_MIX_CLK_DISABLE);
break;
SND_SOC_DAPM_MUX("WSA_RX0 INP0", SND_SOC_NOPM, 0, 0, &rx0_prim_inp0_mux),
SND_SOC_DAPM_MUX("WSA_RX0 INP1", SND_SOC_NOPM, 0, 0, &rx0_prim_inp1_mux),
SND_SOC_DAPM_MUX("WSA_RX0 INP2", SND_SOC_NOPM, 0, 0, &rx0_prim_inp2_mux),
- SND_SOC_DAPM_MUX_E("WSA_RX0 MIX INP", CDC_WSA_RX0_RX_PATH_MIX_CTL,
- 0, 0, &rx0_mix_mux, wsa_macro_enable_mix_path,
+ SND_SOC_DAPM_MUX_E("WSA_RX0 MIX INP", SND_SOC_NOPM, WSA_MACRO_RX_MIX0,
+ 0, &rx0_mix_mux, wsa_macro_enable_mix_path,
SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD),
SND_SOC_DAPM_MUX("WSA_RX1 INP0", SND_SOC_NOPM, 0, 0, &rx1_prim_inp0_mux),
SND_SOC_DAPM_MUX("WSA_RX1 INP1", SND_SOC_NOPM, 0, 0, &rx1_prim_inp1_mux),
SND_SOC_DAPM_MUX("WSA_RX1 INP2", SND_SOC_NOPM, 0, 0, &rx1_prim_inp2_mux),
- SND_SOC_DAPM_MUX_E("WSA_RX1 MIX INP", CDC_WSA_RX1_RX_PATH_MIX_CTL,
- 0, 0, &rx1_mix_mux, wsa_macro_enable_mix_path,
+ SND_SOC_DAPM_MUX_E("WSA_RX1 MIX INP", SND_SOC_NOPM, WSA_MACRO_RX_MIX1,
+ 0, &rx1_mix_mux, wsa_macro_enable_mix_path,
SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMD),
SND_SOC_DAPM_MIXER_E("WSA_RX INT0 MIX", SND_SOC_NOPM, 0, 0, NULL, 0,
case MAX98373_R2054_MEAS_ADC_PVDD_CH_READBACK:
case MAX98373_R2055_MEAS_ADC_THERM_CH_READBACK:
case MAX98373_R20B6_BDE_CUR_STATE_READBACK:
+ case MAX98373_R20FF_GLOBAL_SHDN:
case MAX98373_R21FF_REV_ID:
return true;
default:
case MAX98373_R2054_MEAS_ADC_PVDD_CH_READBACK:
case MAX98373_R2055_MEAS_ADC_THERM_CH_READBACK:
case MAX98373_R20B6_BDE_CUR_STATE_READBACK:
+ case MAX98373_R20FF_GLOBAL_SHDN:
case MAX98373_R21FF_REV_ID:
/* SoundWire Control Port Registers */
case MAX98373_R0040_SCP_INIT_STAT_1 ... MAX98373_R0070_SCP_FRAME_CTLR:
regmap_update_bits(max98373->regmap,
MAX98373_R20FF_GLOBAL_SHDN,
MAX98373_GLOBAL_EN_MASK, 1);
+ usleep_range(30000, 31000);
break;
case SND_SOC_DAPM_POST_PMD:
regmap_update_bits(max98373->regmap,
MAX98373_R20FF_GLOBAL_SHDN,
MAX98373_GLOBAL_EN_MASK, 0);
+ usleep_range(30000, 31000);
max98373->tdm_mode = false;
break;
default:
case RT1015_VENDOR_ID:
case RT1015_DEVICE_ID:
case RT1015_PRO_ALT:
+ case RT1015_MAN_I2C:
case RT1015_DAC3:
case RT1015_VBAT_TEST_OUT1:
case RT1015_VBAT_TEST_OUT2:
msleep(300);
regmap_write(regmap, RT1015_PWR_STATE_CTRL, 0x0008);
regmap_write(regmap, RT1015_SYS_RST1, 0x05F5);
+ regmap_write(regmap, RT1015_CLK_DET, 0x8000);
regcache_cache_bypass(regmap, false);
regcache_mark_dirty(regmap);
}
static const DECLARE_TLV_DB_SCALE(out_vol_tlv, -4650, 150, 0);
-static const DECLARE_TLV_DB_SCALE(dac_vol_tlv, -65625, 375, 0);
+static const DECLARE_TLV_DB_MINMAX(dac_vol_tlv, -6562, 0);
static const DECLARE_TLV_DB_SCALE(in_vol_tlv, -3450, 150, 0);
-static const DECLARE_TLV_DB_SCALE(adc_vol_tlv, -17625, 375, 0);
+static const DECLARE_TLV_DB_MINMAX(adc_vol_tlv, -1762, 3000);
static const DECLARE_TLV_DB_SCALE(adc_bst_tlv, 0, 1200, 0);
/* {0, +20, +24, +30, +35, +40, +44, +50, +52} dB */
}
static const DECLARE_TLV_DB_SCALE(out_vol_tlv, -4650, 150, 0);
-static const DECLARE_TLV_DB_SCALE(dac_vol_tlv, -65625, 375, 0);
+static const DECLARE_TLV_DB_MINMAX(dac_vol_tlv, -6562, 0);
static const DECLARE_TLV_DB_SCALE(in_vol_tlv, -3450, 150, 0);
-static const DECLARE_TLV_DB_SCALE(adc_vol_tlv, -17625, 375, 0);
+static const DECLARE_TLV_DB_MINMAX(adc_vol_tlv, -1762, 3000);
static const DECLARE_TLV_DB_SCALE(adc_bst_tlv, 0, 1200, 0);
/* {0, +20, +24, +30, +35, +40, +44, +50, +52} dB */
{
struct rt5659_priv *rt5659 = snd_soc_component_get_drvdata(component);
unsigned int reg_val = 0;
+ int ret;
if (freq == rt5659->sysclk && clk_id == rt5659->sysclk_src)
return 0;
switch (clk_id) {
case RT5659_SCLK_S_MCLK:
+ ret = clk_set_rate(rt5659->mclk, freq);
+ if (ret)
+ return ret;
+
reg_val |= RT5659_SCLK_SRC_MCLK;
break;
case RT5659_SCLK_S_PLL1:
static SOC_ENUM_SINGLE_DECL(rt5670_if2_adc_enum, RT5670_DIG_INF1_DATA,
RT5670_IF2_ADC_SEL_SFT, rt5670_data_select);
+/*
+ * For reliable output-mute LED control we need a "DAC1 Playback Switch" control.
+ * We emulate this by only clearing the RT5670_M_DAC1_L/_R AD_DA_MIXER register
+ * bits when both our emulated DAC1 Playback Switch control and the DAC1 MIXL/R
+ * DAPM-mixer DAC1 input are enabled.
+ */
+static void rt5670_update_ad_da_mixer_dac1_m_bits(struct rt5670_priv *rt5670)
+{
+ int val = RT5670_M_DAC1_L | RT5670_M_DAC1_R;
+
+ if (rt5670->dac1_mixl_dac1_switch && rt5670->dac1_playback_switch_l)
+ val &= ~RT5670_M_DAC1_L;
+
+ if (rt5670->dac1_mixr_dac1_switch && rt5670->dac1_playback_switch_r)
+ val &= ~RT5670_M_DAC1_R;
+
+ regmap_update_bits(rt5670->regmap, RT5670_AD_DA_MIXER,
+ RT5670_M_DAC1_L | RT5670_M_DAC1_R, val);
+}
+
+static int rt5670_dac1_playback_switch_get(struct snd_kcontrol *kcontrol,
+ struct snd_ctl_elem_value *ucontrol)
+{
+ struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
+ struct rt5670_priv *rt5670 = snd_soc_component_get_drvdata(component);
+
+ ucontrol->value.integer.value[0] = rt5670->dac1_playback_switch_l;
+ ucontrol->value.integer.value[1] = rt5670->dac1_playback_switch_r;
+
+ return 0;
+}
+
+static int rt5670_dac1_playback_switch_put(struct snd_kcontrol *kcontrol,
+ struct snd_ctl_elem_value *ucontrol)
+{
+ struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
+ struct rt5670_priv *rt5670 = snd_soc_component_get_drvdata(component);
+
+ if (rt5670->dac1_playback_switch_l == ucontrol->value.integer.value[0] &&
+ rt5670->dac1_playback_switch_r == ucontrol->value.integer.value[1])
+ return 0;
+
+ rt5670->dac1_playback_switch_l = ucontrol->value.integer.value[0];
+ rt5670->dac1_playback_switch_r = ucontrol->value.integer.value[1];
+
+ rt5670_update_ad_da_mixer_dac1_m_bits(rt5670);
+
+ return 1;
+}
+
static const struct snd_kcontrol_new rt5670_snd_controls[] = {
/* Headphone Output Volume */
- SOC_DOUBLE("HP Playback Switch", RT5670_HP_VOL,
- RT5670_L_MUTE_SFT, RT5670_R_MUTE_SFT, 1, 1),
SOC_DOUBLE_TLV("HP Playback Volume", RT5670_HP_VOL,
RT5670_L_VOL_SFT, RT5670_R_VOL_SFT,
39, 1, out_vol_tlv),
/* OUTPUT Control */
- SOC_DOUBLE("OUT Channel Switch", RT5670_LOUT1,
- RT5670_VOL_L_SFT, RT5670_VOL_R_SFT, 1, 1),
SOC_DOUBLE_TLV("OUT Playback Volume", RT5670_LOUT1,
RT5670_L_VOL_SFT, RT5670_R_VOL_SFT, 39, 1, out_vol_tlv),
/* DAC Digital Volume */
SOC_DOUBLE("DAC2 Playback Switch", RT5670_DAC_CTRL,
RT5670_M_DAC_L2_VOL_SFT, RT5670_M_DAC_R2_VOL_SFT, 1, 1),
+ SOC_DOUBLE_EXT("DAC1 Playback Switch", SND_SOC_NOPM, 0, 1, 1, 0,
+ rt5670_dac1_playback_switch_get, rt5670_dac1_playback_switch_put),
SOC_DOUBLE_TLV("DAC1 Playback Volume", RT5670_DAC1_DIG_VOL,
RT5670_L_VOL_SFT, RT5670_R_VOL_SFT,
175, 0, dac_vol_tlv),
RT5670_M_MONO_ADC_R2_SFT, 1, 1),
};
+/* See comment above rt5670_update_ad_da_mixer_dac1_m_bits() */
+static int rt5670_put_dac1_mix_dac1_switch(struct snd_kcontrol *kcontrol,
+ struct snd_ctl_elem_value *ucontrol)
+{
+ struct soc_mixer_control *mc = (struct soc_mixer_control *)kcontrol->private_value;
+ struct snd_soc_component *component = snd_soc_dapm_kcontrol_component(kcontrol);
+ struct rt5670_priv *rt5670 = snd_soc_component_get_drvdata(component);
+ int ret;
+
+ if (mc->shift == 0)
+ rt5670->dac1_mixl_dac1_switch = ucontrol->value.integer.value[0];
+ else
+ rt5670->dac1_mixr_dac1_switch = ucontrol->value.integer.value[0];
+
+ /* Apply the update (if any) */
+ ret = snd_soc_dapm_put_volsw(kcontrol, ucontrol);
+ if (ret == 0)
+ return 0;
+
+ rt5670_update_ad_da_mixer_dac1_m_bits(rt5670);
+
+ return 1;
+}
+
+#define SOC_DAPM_SINGLE_RT5670_DAC1_SW(name, shift) \
+ SOC_SINGLE_EXT(name, SND_SOC_NOPM, shift, 1, 0, \
+ snd_soc_dapm_get_volsw, rt5670_put_dac1_mix_dac1_switch)
+
static const struct snd_kcontrol_new rt5670_dac_l_mix[] = {
SOC_DAPM_SINGLE("Stereo ADC Switch", RT5670_AD_DA_MIXER,
RT5670_M_ADCMIX_L_SFT, 1, 1),
- SOC_DAPM_SINGLE("DAC1 Switch", RT5670_AD_DA_MIXER,
- RT5670_M_DAC1_L_SFT, 1, 1),
+ SOC_DAPM_SINGLE_RT5670_DAC1_SW("DAC1 Switch", 0),
};
static const struct snd_kcontrol_new rt5670_dac_r_mix[] = {
SOC_DAPM_SINGLE("Stereo ADC Switch", RT5670_AD_DA_MIXER,
RT5670_M_ADCMIX_R_SFT, 1, 1),
- SOC_DAPM_SINGLE("DAC1 Switch", RT5670_AD_DA_MIXER,
- RT5670_M_DAC1_R_SFT, 1, 1),
+ SOC_DAPM_SINGLE_RT5670_DAC1_SW("DAC1 Switch", 1),
};
static const struct snd_kcontrol_new rt5670_sto_dac_l_mix[] = {
RT5670_PWR_ADC_S1F_BIT, 0, NULL, 0),
SND_SOC_DAPM_SUPPLY("ADC Stereo2 Filter", RT5670_PWR_DIG2,
RT5670_PWR_ADC_S2F_BIT, 0, NULL, 0),
- SND_SOC_DAPM_MIXER("Sto1 ADC MIXL", RT5670_STO1_ADC_DIG_VOL,
- RT5670_L_MUTE_SFT, 1, rt5670_sto1_adc_l_mix,
- ARRAY_SIZE(rt5670_sto1_adc_l_mix)),
- SND_SOC_DAPM_MIXER("Sto1 ADC MIXR", RT5670_STO1_ADC_DIG_VOL,
- RT5670_R_MUTE_SFT, 1, rt5670_sto1_adc_r_mix,
- ARRAY_SIZE(rt5670_sto1_adc_r_mix)),
+ SND_SOC_DAPM_MIXER("Sto1 ADC MIXL", SND_SOC_NOPM, 0, 0,
+ rt5670_sto1_adc_l_mix, ARRAY_SIZE(rt5670_sto1_adc_l_mix)),
+ SND_SOC_DAPM_MIXER("Sto1 ADC MIXR", SND_SOC_NOPM, 0, 0,
+ rt5670_sto1_adc_r_mix, ARRAY_SIZE(rt5670_sto1_adc_r_mix)),
SND_SOC_DAPM_MIXER("Sto2 ADC MIXL", SND_SOC_NOPM, 0, 0,
rt5670_sto2_adc_l_mix,
ARRAY_SIZE(rt5670_sto2_adc_l_mix)),
dev_info(&i2c->dev, "quirk JD mode 3\n");
}
+ /*
+ * Enable the emulated "DAC1 Playback Switch" by default to avoid
+ * muting the output with older UCM profiles.
+ */
+ rt5670->dac1_playback_switch_l = true;
+ rt5670->dac1_playback_switch_r = true;
+ /* The Power-On-Reset values for the DAC1 mixer have the DAC1 input enabled. */
+ rt5670->dac1_mixl_dac1_switch = true;
+ rt5670->dac1_mixr_dac1_switch = true;
+
rt5670->regmap = devm_regmap_init_i2c(i2c, &rt5670_regmap);
if (IS_ERR(rt5670->regmap)) {
ret = PTR_ERR(rt5670->regmap);
/* global definition */
#define RT5670_L_MUTE (0x1 << 15)
#define RT5670_L_MUTE_SFT 15
-#define RT5670_VOL_L_MUTE (0x1 << 14)
-#define RT5670_VOL_L_SFT 14
#define RT5670_R_MUTE (0x1 << 7)
#define RT5670_R_MUTE_SFT 7
-#define RT5670_VOL_R_MUTE (0x1 << 6)
-#define RT5670_VOL_R_SFT 6
#define RT5670_L_VOL_MASK (0x3f << 8)
#define RT5670_L_VOL_SFT 8
#define RT5670_R_VOL_MASK (0x3f)
int dsp_rate;
int jack_type;
int jack_type_saved;
+
+ bool dac1_mixl_dac1_switch;
+ bool dac1_mixr_dac1_switch;
+ bool dac1_playback_switch_l;
+ bool dac1_playback_switch_r;
};
void rt5670_jack_suspend(struct snd_soc_component *component);
return 0;
}
+static void rt711_remove(struct snd_soc_component *component)
+{
+ struct rt711_priv *rt711 = snd_soc_component_get_drvdata(component);
+
+ regcache_cache_only(rt711->regmap, true);
+}
+
static const struct snd_soc_component_driver soc_codec_dev_rt711 = {
.probe = rt711_probe,
.set_bias_level = rt711_set_bias_level,
.dapm_routes = rt711_audio_map,
.num_dapm_routes = ARRAY_SIZE(rt711_audio_map),
.set_jack = rt711_set_jack_detect,
+ .remove = rt711_remove,
};
static int rt711_set_sdw_stream(struct snd_soc_dai *dai, void *sdw_stream,
{ SGTL5000_DAP_EQ_BASS_BAND4, 0x002f },
{ SGTL5000_DAP_MAIN_CHAN, 0x8000 },
{ SGTL5000_DAP_MIX_CHAN, 0x0000 },
- { SGTL5000_DAP_AVC_CTRL, 0x0510 },
+ { SGTL5000_DAP_AVC_CTRL, 0x5100 },
{ SGTL5000_DAP_AVC_THRESHOLD, 0x1473 },
{ SGTL5000_DAP_AVC_ATTACK, 0x0028 },
{ SGTL5000_DAP_AVC_DECAY, 0x0050 },
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * SiRF inner codec controllers define
- *
- * Copyright (c) 2011 Cambridge Silicon Radio Limited, a CSR plc group company.
- */
-
-#ifndef _SIRF_AUDIO_CODEC_H
-#define _SIRF_AUDIO_CODEC_H
-
-
-#define AUDIO_IC_CODEC_PWR (0x00E0)
-#define AUDIO_IC_CODEC_CTRL0 (0x00E4)
-#define AUDIO_IC_CODEC_CTRL1 (0x00E8)
-#define AUDIO_IC_CODEC_CTRL2 (0x00EC)
-#define AUDIO_IC_CODEC_CTRL3 (0x00F0)
-
-#define MICBIASEN (1 << 3)
-
-#define IC_RDACEN (1 << 0)
-#define IC_LDACEN (1 << 1)
-#define IC_HSREN (1 << 2)
-#define IC_HSLEN (1 << 3)
-#define IC_SPEN (1 << 4)
-#define IC_CPEN (1 << 5)
-
-#define IC_HPRSELR (1 << 6)
-#define IC_HPLSELR (1 << 7)
-#define IC_HPRSELL (1 << 8)
-#define IC_HPLSELL (1 << 9)
-#define IC_SPSELR (1 << 10)
-#define IC_SPSELL (1 << 11)
-
-#define IC_MONOR (1 << 12)
-#define IC_MONOL (1 << 13)
-
-#define IC_RXOSRSEL (1 << 28)
-#define IC_CPFREQ (1 << 29)
-#define IC_HSINVEN (1 << 30)
-
-#define IC_MICINREN (1 << 0)
-#define IC_MICINLEN (1 << 1)
-#define IC_MICIN1SEL (1 << 2)
-#define IC_MICIN2SEL (1 << 3)
-#define IC_MICDIFSEL (1 << 4)
-#define IC_LINEIN1SEL (1 << 5)
-#define IC_LINEIN2SEL (1 << 6)
-#define IC_RADCEN (1 << 7)
-#define IC_LADCEN (1 << 8)
-#define IC_ALM (1 << 9)
-
-#define IC_DIGMICEN (1 << 22)
-#define IC_DIGMICFREQ (1 << 23)
-#define IC_ADC14B_12 (1 << 24)
-#define IC_FIRDAC_HSL_EN (1 << 25)
-#define IC_FIRDAC_HSR_EN (1 << 26)
-#define IC_FIRDAC_LOUT_EN (1 << 27)
-#define IC_POR (1 << 28)
-#define IC_CODEC_CLK_EN (1 << 29)
-#define IC_HP_3DB_BOOST (1 << 30)
-
-#define IC_ADC_LEFT_GAIN_SHIFT 16
-#define IC_ADC_RIGHT_GAIN_SHIFT 10
-#define IC_ADC_GAIN_MASK 0x3F
-#define IC_MIC_MAX_GAIN 0x39
-
-#define IC_RXPGAR_MASK 0x3F
-#define IC_RXPGAR_SHIFT 14
-#define IC_RXPGAL_MASK 0x3F
-#define IC_RXPGAL_SHIFT 21
-#define IC_RXPGAR 0x7B
-#define IC_RXPGAL 0x7B
-
-#define AUDIO_PORT_TX_FIFO_LEVEL_CHECK_MASK 0x3F
-#define AUDIO_PORT_TX_FIFO_SC_OFFSET 0
-#define AUDIO_PORT_TX_FIFO_LC_OFFSET 10
-#define AUDIO_PORT_TX_FIFO_HC_OFFSET 20
-
-#define TX_FIFO_SC(x) (((x) & AUDIO_PORT_TX_FIFO_LEVEL_CHECK_MASK) \
- << AUDIO_PORT_TX_FIFO_SC_OFFSET)
-#define TX_FIFO_LC(x) (((x) & AUDIO_PORT_TX_FIFO_LEVEL_CHECK_MASK) \
- << AUDIO_PORT_TX_FIFO_LC_OFFSET)
-#define TX_FIFO_HC(x) (((x) & AUDIO_PORT_TX_FIFO_LEVEL_CHECK_MASK) \
- << AUDIO_PORT_TX_FIFO_HC_OFFSET)
-
-#define AUDIO_PORT_RX_FIFO_LEVEL_CHECK_MASK 0x0F
-#define AUDIO_PORT_RX_FIFO_SC_OFFSET 0
-#define AUDIO_PORT_RX_FIFO_LC_OFFSET 10
-#define AUDIO_PORT_RX_FIFO_HC_OFFSET 20
-
-#define RX_FIFO_SC(x) (((x) & AUDIO_PORT_RX_FIFO_LEVEL_CHECK_MASK) \
- << AUDIO_PORT_RX_FIFO_SC_OFFSET)
-#define RX_FIFO_LC(x) (((x) & AUDIO_PORT_RX_FIFO_LEVEL_CHECK_MASK) \
- << AUDIO_PORT_RX_FIFO_LC_OFFSET)
-#define RX_FIFO_HC(x) (((x) & AUDIO_PORT_RX_FIFO_LEVEL_CHECK_MASK) \
- << AUDIO_PORT_RX_FIFO_HC_OFFSET)
-#define AUDIO_PORT_IC_CODEC_TX_CTRL (0x00F4)
-#define AUDIO_PORT_IC_CODEC_RX_CTRL (0x00F8)
-
-#define AUDIO_PORT_IC_TXFIFO_OP (0x00FC)
-#define AUDIO_PORT_IC_TXFIFO_LEV_CHK (0x0100)
-#define AUDIO_PORT_IC_TXFIFO_STS (0x0104)
-#define AUDIO_PORT_IC_TXFIFO_INT (0x0108)
-#define AUDIO_PORT_IC_TXFIFO_INT_MSK (0x010C)
-
-#define AUDIO_PORT_IC_RXFIFO_OP (0x0110)
-#define AUDIO_PORT_IC_RXFIFO_LEV_CHK (0x0114)
-#define AUDIO_PORT_IC_RXFIFO_STS (0x0118)
-#define AUDIO_PORT_IC_RXFIFO_INT (0x011C)
-#define AUDIO_PORT_IC_RXFIFO_INT_MSK (0x0120)
-
-#define AUDIO_FIFO_START (1 << 0)
-#define AUDIO_FIFO_RESET (1 << 1)
-
-#define AUDIO_FIFO_FULL (1 << 0)
-#define AUDIO_FIFO_EMPTY (1 << 1)
-#define AUDIO_FIFO_OFLOW (1 << 2)
-#define AUDIO_FIFO_UFLOW (1 << 3)
-
-#define IC_TX_ENABLE (0x03)
-#define IC_RX_ENABLE_MONO (0x01)
-#define IC_RX_ENABLE_STEREO (0x03)
-
-#endif /*__SIRF_AUDIO_CODEC_H*/
wcd = snd_soc_component_get_drvdata(dai->component);
+ if (tx_num > WCD934X_TX_MAX || rx_num > WCD934X_RX_MAX) {
+ dev_err(wcd->dev, "Invalid tx %d or rx %d channel count\n",
+ tx_num, rx_num);
+ return -EINVAL;
+ }
+
if (!tx_slot || !rx_slot) {
dev_err(wcd->dev, "Invalid tx_slot=%p, rx_slot=%p\n",
tx_slot, rx_slot);
best_freq_out = -EINVAL;
*sysclk_idx = *dac_idx = *bclk_idx = -1;
- for (i = 0; i < ARRAY_SIZE(sysclk_divs); ++i) {
+ /*
+ * From Datasheet, the PLL performs best when f2 is between
+ * 90MHz and 100MHz, the desired sysclk output is 11.2896MHz
+ * or 12.288MHz, then sysclkdiv = 2 is the best choice.
+ * So search sysclk_divs from 2 to 1 other than from 1 to 2.
+ */
+ for (i = ARRAY_SIZE(sysclk_divs) - 1; i >= 0; --i) {
if (sysclk_divs[i] == -1)
continue;
for (j = 0; j < ARRAY_SIZE(dac_divs); ++j) {
ESAI_SAICR_SYNC, esai_priv->synchronous ?
ESAI_SAICR_SYNC : 0);
- /* Set a default slot number -- 2 */
+ /* Set slots count */
regmap_update_bits(esai_priv->regmap, REG_ESAI_TCCR,
- ESAI_xCCR_xDC_MASK, ESAI_xCCR_xDC(2));
+ ESAI_xCCR_xDC_MASK,
+ ESAI_xCCR_xDC(esai_priv->slots));
regmap_update_bits(esai_priv->regmap, REG_ESAI_RCCR,
- ESAI_xCCR_xDC_MASK, ESAI_xCCR_xDC(2));
+ ESAI_xCCR_xDC_MASK,
+ ESAI_xCCR_xDC(esai_priv->slots));
}
return 0;
static int _fsl_ssi_set_dai_fmt(struct fsl_ssi *ssi, unsigned int fmt)
{
u32 strcr = 0, scr = 0, stcr, srcr, mask;
+ unsigned int slots;
ssi->dai_fmt = fmt;
return -EINVAL;
}
+ slots = ssi->slots ? : 2;
regmap_update_bits(ssi->regs, REG_SSI_STCCR,
- SSI_SxCCR_DC_MASK, SSI_SxCCR_DC(2));
+ SSI_SxCCR_DC_MASK, SSI_SxCCR_DC(slots));
regmap_update_bits(ssi->regs, REG_SSI_SRCCR,
- SSI_SxCCR_DC_MASK, SSI_SxCCR_DC(2));
+ SSI_SxCCR_DC_MASK, SSI_SxCCR_DC(slots));
/* Data on rising edge of bclk, frame low, 1clk before data */
strcr |= SSI_STCR_TFSI | SSI_STCR_TSCKP | SSI_STCR_TEFS;
* or device's module clock.
*/
clk = devm_get_clk_from_child(dev, node, NULL);
- if (IS_ERR(clk))
- clk = devm_get_clk_from_child(dev, dlc->of_node, NULL);
-
if (!IS_ERR(clk)) {
- simple_dai->clk = clk;
simple_dai->sysclk = clk_get_rate(clk);
- } else if (!of_property_read_u32(node, "system-clock-frequency",
- &val)) {
+
+ simple_dai->clk = clk;
+ } else if (!of_property_read_u32(node, "system-clock-frequency", &val)) {
simple_dai->sysclk = val;
+ } else {
+ clk = devm_get_clk_from_child(dev, dlc->of_node, NULL);
+ if (!IS_ERR(clk))
+ simple_dai->sysclk = clk_get_rate(clk);
}
if (of_property_read_bool(node, "system-clock-direction-out"))
.stream_name = "Headset Playback",
.channels_min = SST_STEREO,
.channels_max = SST_STEREO,
- .rates = SNDRV_PCM_RATE_44100|SNDRV_PCM_RATE_48000,
- .formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE,
+ .rates = SNDRV_PCM_RATE_48000,
+ .formats = SNDRV_PCM_FMTBIT_S16_LE,
},
.capture = {
.stream_name = "Headset Capture",
.channels_min = 1,
.channels_max = 2,
- .rates = SNDRV_PCM_RATE_44100|SNDRV_PCM_RATE_48000,
- .formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE,
+ .rates = SNDRV_PCM_RATE_48000,
+ .formats = SNDRV_PCM_FMTBIT_S16_LE,
},
},
{
.stream_name = "Deepbuffer Playback",
.channels_min = SST_STEREO,
.channels_max = SST_STEREO,
- .rates = SNDRV_PCM_RATE_44100|SNDRV_PCM_RATE_48000,
- .formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE,
+ .rates = SNDRV_PCM_RATE_48000,
+ .formats = SNDRV_PCM_FMTBIT_S16_LE,
},
},
{
},
.driver_data = (void *)(BYT_RT5640_DMIC1_MAP |
BYT_RT5640_JD_SRC_JD1_IN4P |
- BYT_RT5640_OVCD_TH_1500UA |
+ BYT_RT5640_OVCD_TH_2000UA |
BYT_RT5640_OVCD_SF_0P75 |
BYT_RT5640_MCLK_EN),
},
/* set tdm */
if (tdm_priv->bck_invert)
- tdm_con |= 1 << BCK_INVERSE_SFT;
+ regmap_update_bits(afe->regmap, AUDIO_TOP_CON3,
+ BCK_INVERSE_MASK_SFT,
+ 0x1 << BCK_INVERSE_SFT);
if (tdm_priv->lck_invert)
tdm_con |= 1 << LRCK_INVERSE_SFT;
/*****************************************************************************
* R E G I S T E R D E F I N I T I O N
*****************************************************************************/
+/* AUDIO_TOP_CON3 */
+#define BCK_INVERSE_SFT 3
+#define BCK_INVERSE_MASK 0x1
+#define BCK_INVERSE_MASK_SFT (0x1 << 3)
+
/* AFE_DAC_CON0 */
#define VUL12_ON_SFT 31
#define VUL12_ON_MASK 0x1
#define TDM_EN_SFT 0
#define TDM_EN_MASK 0x1
#define TDM_EN_MASK_SFT (0x1 << 0)
-#define BCK_INVERSE_SFT 1
-#define BCK_INVERSE_MASK 0x1
-#define BCK_INVERSE_MASK_SFT (0x1 << 1)
#define LRCK_INVERSE_SFT 2
#define LRCK_INVERSE_MASK 0x1
#define LRCK_INVERSE_MASK_SFT (0x1 << 2)
for_each_child_of_node(dev->of_node, node) {
ret = of_property_read_u32(node, "reg", &id);
- if (ret || id < 0 || id >= data->variant->num_dai) {
+ if (ret || id < 0) {
dev_err(dev, "valid dai id not found: %d\n", ret);
continue;
}
#define SPK_TDM_RX_MASK 0x03
#define NUM_TDM_SLOTS 8
#define SLIM_MAX_TX_PORTS 16
-#define SLIM_MAX_RX_PORTS 16
+#define SLIM_MAX_RX_PORTS 13
#define WCD934X_DEFAULT_MCLK_RATE 9600000
struct sdm845_snd_data {
struct snd_soc_jack jack;
bool jack_setup;
- bool stream_prepared[SLIM_MAX_RX_PORTS];
+ bool stream_prepared[AFE_PORT_MAX];
struct snd_soc_card *card;
uint32_t pri_mi2s_clk_count;
uint32_t sec_mi2s_clk_count;
uint32_t quat_tdm_clk_count;
- struct sdw_stream_runtime *sruntime[SLIM_MAX_RX_PORTS];
+ struct sdw_stream_runtime *sruntime[AFE_PORT_MAX];
};
static unsigned int tdm_slot_offset[8] = {0, 4, 8, 12, 16, 20, 24, 28};
#include <linux/of.h>
#include <linux/of_graph.h>
#include <linux/dmi.h>
+#include <linux/acpi.h>
#include <sound/core.h>
#include <sound/pcm.h>
#include <sound/pcm_params.h>
if (card->long_name)
return 0; /* long name already set by driver or from DMI */
+ if (!is_acpi_device_node(card->dev->fwnode))
+ return 0;
+
/* make up dmi long name as: vendor-product-version-board */
vendor = dmi_get_system_info(DMI_BOARD_VENDOR);
if (!vendor || !is_dmi_valid(vendor)) {
{
struct snd_sof_dev *sdev = dev_get_drvdata(dev);
- return snd_sof_shutdown(sdev);
+ if (IS_ENABLED(CONFIG_SND_SOC_SOF_PROBE_WORK_QUEUE))
+ cancel_work_sync(&sdev->probe_work);
+
+ if (sdev->fw_state == SOF_FW_BOOT_COMPLETE)
+ return snd_sof_shutdown(sdev);
+
+ return 0;
}
EXPORT_SYMBOL(snd_sof_device_shutdown);
/* apollolake ops */
const struct snd_sof_dsp_ops sof_apl_ops = {
- /* probe and remove */
+ /* probe/remove/shutdown */
.probe = hda_dsp_probe,
.remove = hda_dsp_remove,
+ .shutdown = hda_dsp_shutdown,
/* Register IO */
.write = sof_io_write,
/* cannonlake ops */
const struct snd_sof_dsp_ops sof_cnl_ops = {
- /* probe and remove */
+ /* probe/remove/shutdown */
.probe = hda_dsp_probe,
.remove = hda_dsp_remove,
+ .shutdown = hda_dsp_shutdown,
/* Register IO */
.write = sof_io_write,
};
EXPORT_SYMBOL_NS(cnl_chip_info, SND_SOC_SOF_INTEL_HDA_COMMON);
-const struct sof_intel_dsp_desc ehl_chip_info = {
- /* Elkhartlake */
- .cores_num = 4,
- .init_core_mask = 1,
- .host_managed_cores_mask = BIT(0),
- .ipc_req = CNL_DSP_REG_HIPCIDR,
- .ipc_req_mask = CNL_DSP_REG_HIPCIDR_BUSY,
- .ipc_ack = CNL_DSP_REG_HIPCIDA,
- .ipc_ack_mask = CNL_DSP_REG_HIPCIDA_DONE,
- .ipc_ctl = CNL_DSP_REG_HIPCCTL,
- .rom_init_timeout = 300,
- .ssp_count = ICL_SSP_COUNT,
- .ssp_base_offset = CNL_SSP_BASE_OFFSET,
-};
-EXPORT_SYMBOL_NS(ehl_chip_info, SND_SOC_SOF_INTEL_HDA_COMMON);
-
const struct sof_intel_dsp_desc jsl_chip_info = {
/* Jasperlake */
.cores_num = 2,
ret = snd_sof_dsp_read_poll_timeout(sdev, HDA_DSP_BAR,
HDA_DSP_REG_ADSPCS, adspcs,
- !(adspcs & HDA_DSP_ADSPCS_SPA_MASK(core_mask)),
+ !(adspcs & HDA_DSP_ADSPCS_CPA_MASK(core_mask)),
HDA_DSP_REG_POLL_INTERVAL_US,
HDA_DSP_PD_TIMEOUT * USEC_PER_MSEC);
if (ret < 0)
val = snd_sof_dsp_read(sdev, HDA_DSP_BAR, HDA_DSP_REG_ADSPCS);
- is_enable = (val & HDA_DSP_ADSPCS_CPA_MASK(core_mask)) &&
- (val & HDA_DSP_ADSPCS_SPA_MASK(core_mask)) &&
- !(val & HDA_DSP_ADSPCS_CRST_MASK(core_mask)) &&
- !(val & HDA_DSP_ADSPCS_CSTALL_MASK(core_mask));
+#define MASK_IS_EQUAL(v, m, field) ({ \
+ u32 _m = field(m); \
+ ((v) & _m) == _m; \
+})
+
+ is_enable = MASK_IS_EQUAL(val, core_mask, HDA_DSP_ADSPCS_CPA_MASK) &&
+ MASK_IS_EQUAL(val, core_mask, HDA_DSP_ADSPCS_SPA_MASK) &&
+ !(val & HDA_DSP_ADSPCS_CRST_MASK(core_mask)) &&
+ !(val & HDA_DSP_ADSPCS_CSTALL_MASK(core_mask));
+
+#undef MASK_IS_EQUAL
dev_dbg(sdev->dev, "DSP core(s) enabled? %d : core_mask %x\n",
is_enable, core_mask);
return snd_sof_dsp_set_power_state(sdev, &target_dsp_state);
}
+int hda_dsp_shutdown(struct snd_sof_dev *sdev)
+{
+ sdev->system_suspend_target = SOF_SUSPEND_S3;
+ return snd_sof_suspend(sdev->dev);
+}
+
int hda_dsp_set_hw_params_upon_resume(struct snd_sof_dev *sdev)
{
#if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA)
/* dsp_unmap: not currently used */
iounmap(sdev->bar[HDA_DSP_BAR]);
hdac_bus_unmap:
+ platform_device_unregister(hdev->dmic_dev);
iounmap(bus->remap_addr);
hda_codec_i915_exit(sdev);
err:
int hda_dsp_runtime_suspend(struct snd_sof_dev *sdev);
int hda_dsp_runtime_resume(struct snd_sof_dev *sdev);
int hda_dsp_runtime_idle(struct snd_sof_dev *sdev);
+int hda_dsp_shutdown(struct snd_sof_dev *sdev);
int hda_dsp_set_hw_params_upon_resume(struct snd_sof_dev *sdev);
void hda_dsp_dump(struct snd_sof_dev *sdev, u32 flags);
void hda_ipc_dump(struct snd_sof_dev *sdev);
/* Icelake ops */
const struct snd_sof_dsp_ops sof_icl_ops = {
- /* probe and remove */
+ /* probe/remove/shutdown */
.probe = hda_dsp_probe,
.remove = hda_dsp_remove,
+ .shutdown = hda_dsp_shutdown,
/* Register IO */
.write = sof_io_write,
.default_tplg_path = "intel/sof-tplg",
.default_fw_filename = "sof-ehl.ri",
.nocodec_tplg_filename = "sof-ehl-nocodec.tplg",
- .ops = &sof_cnl_ops,
+ .ops = &sof_tgl_ops,
};
static const struct sof_dev_desc adls_desc = {
/* probe/remove/shutdown */
.probe = hda_dsp_probe,
.remove = hda_dsp_remove,
- .shutdown = hda_dsp_remove,
+ .shutdown = hda_dsp_shutdown,
/* Register IO */
.write = sof_io_write,
};
EXPORT_SYMBOL_NS(tglh_chip_info, SND_SOC_SOF_INTEL_HDA_COMMON);
+const struct sof_intel_dsp_desc ehl_chip_info = {
+ /* Elkhartlake */
+ .cores_num = 4,
+ .init_core_mask = 1,
+ .host_managed_cores_mask = BIT(0),
+ .ipc_req = CNL_DSP_REG_HIPCIDR,
+ .ipc_req_mask = CNL_DSP_REG_HIPCIDR_BUSY,
+ .ipc_ack = CNL_DSP_REG_HIPCIDA,
+ .ipc_ack_mask = CNL_DSP_REG_HIPCIDA_DONE,
+ .ipc_ctl = CNL_DSP_REG_HIPCCTL,
+ .rom_init_timeout = 300,
+ .ssp_count = ICL_SSP_COUNT,
+ .ssp_base_offset = CNL_SSP_BASE_OFFSET,
+};
+EXPORT_SYMBOL_NS(ehl_chip_info, SND_SOC_SOF_INTEL_HDA_COMMON);
+
const struct sof_intel_dsp_desc adls_chip_info = {
/* Alderlake-S */
.cores_num = 2,
return ERR_PTR(-ENOMEM);
card->dev = dev;
+ card->owner = THIS_MODULE;
card->name = "sun4i-codec";
card->dapm_widgets = sun4i_codec_card_dapm_widgets;
card->num_dapm_widgets = ARRAY_SIZE(sun4i_codec_card_dapm_widgets);
return ERR_PTR(-ENOMEM);
card->dev = dev;
+ card->owner = THIS_MODULE;
card->name = "A31 Audio Codec";
card->dapm_widgets = sun6i_codec_card_dapm_widgets;
card->num_dapm_widgets = ARRAY_SIZE(sun6i_codec_card_dapm_widgets);
return ERR_PTR(-ENOMEM);
card->dev = dev;
+ card->owner = THIS_MODULE;
card->name = "A23 Audio Codec";
card->dapm_widgets = sun6i_codec_card_dapm_widgets;
card->num_dapm_widgets = ARRAY_SIZE(sun6i_codec_card_dapm_widgets);
return ERR_PTR(-ENOMEM);
card->dev = dev;
+ card->owner = THIS_MODULE;
card->name = "H3 Audio Codec";
card->dapm_widgets = sun6i_codec_card_dapm_widgets;
card->num_dapm_widgets = ARRAY_SIZE(sun6i_codec_card_dapm_widgets);
return ERR_PTR(-ENOMEM);
card->dev = dev;
+ card->owner = THIS_MODULE;
card->name = "V3s Audio Codec";
card->dapm_widgets = sun6i_codec_card_dapm_widgets;
card->num_dapm_widgets = ARRAY_SIZE(sun6i_codec_card_dapm_widgets);
MODULE_AUTHOR("Thomas K. Dyas and David S. Miller");
MODULE_DESCRIPTION("Sun AMD7930");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Sun,AMD7930}}");
/* Device register layout. */
MODULE_AUTHOR("Jaroslav Kysela, Derrick J. Brashear and David S. Miller");
MODULE_DESCRIPTION("Sun CS4231");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Sun,CS4231}}");
#ifdef SBUS_SUPPORT
struct sbus_dma_info {
MODULE_AUTHOR("Rudolf Koenig, Brent Baccala and Martin Habets");
MODULE_DESCRIPTION("Sun DBRI");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Sun,DBRI}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
MODULE_AUTHOR("Torsten Schenk <torsten.schenk@zoho.com>");
MODULE_DESCRIPTION("TerraTec DMX 6Fire USB audio driver");
MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("{{TerraTec,DMX 6Fire USB}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-max */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* Id for card */
MODULE_AUTHOR("Daniel Mack <daniel@caiaq.de>");
MODULE_DESCRIPTION("caiaq USB audio");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Native Instruments,RigKontrol2},"
- "{Native Instruments,RigKontrol3},"
- "{Native Instruments,Kore Controller},"
- "{Native Instruments,Kore Controller 2},"
- "{Native Instruments,Audio Kontrol 1},"
- "{Native Instruments,Audio 2 DJ},"
- "{Native Instruments,Audio 4 DJ},"
- "{Native Instruments,Audio 8 DJ},"
- "{Native Instruments,Traktor Audio 2},"
- "{Native Instruments,Session I/O},"
- "{Native Instruments,GuitarRig mobile},"
- "{Native Instruments,Traktor Kontrol X1},"
- "{Native Instruments,Traktor Kontrol S4},"
- "{Native Instruments,Maschine Controller}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-max */
static char* id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* Id for this card */
MODULE_AUTHOR("Takashi Iwai <tiwai@suse.de>");
MODULE_DESCRIPTION("USB Audio");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{Generic,USB Audio}}");
-
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-MAX */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* ID for this card */
snd_media_device_create(chip, intf);
}
+ if (quirk)
+ chip->quirk_type = quirk->type;
+
usb_chip[chip->index] = chip;
chip->intf[chip->num_interfaces] = intf;
chip->num_interfaces++;
}
}
+ if (chip->quirk_type & QUIRK_SETUP_DISABLE_AUTOSUSPEND)
+ usb_enable_autosuspend(interface_to_usbdev(intf));
+
chip->num_interfaces--;
if (chip->num_interfaces <= 0) {
usb_chip[chip->index] = NULL;
MODULE_AUTHOR("Antonio Ospite <ao2@amarulasolutions.com>");
MODULE_DESCRIPTION("M2Tech hiFace USB-SPDIF audio driver");
MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("{{M2Tech,Young},"
- "{M2Tech,hiFace},"
- "{M2Tech,North Star},"
- "{M2Tech,W4S Young},"
- "{M2Tech,Corrson},"
- "{M2Tech,AUDIA},"
- "{M2Tech,SL Audio},"
- "{M2Tech,Empirical},"
- "{M2Tech,Rockna},"
- "{M2Tech,Pathos},"
- "{M2Tech,Metronome},"
- "{M2Tech,CAD},"
- "{M2Tech,Audio Esclusive},"
- "{M2Tech,Rotel},"
- "{M2Tech,Eeaudio},"
- "{The Chord Company,CHORD},"
- "{AVA Group A/S,Vitus}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-max */
static char *id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* Id for card */
MODULE_DESCRIPTION("Edirol UA-101/1000 driver");
MODULE_AUTHOR("Clemens Ladisch <clemens@ladisch.de>");
MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("{{Edirol,UA-101},{Edirol,UA-1000}}");
/*
* Should not be lower than the minimum scheduling delay of the host
u8 group = (private_value & SND_DJM_GROUP_MASK) >> SND_DJM_GROUP_SHIFT;
u16 value = elem->value.enumerated.item[0];
- kctl->private_value = ((device << SND_DJM_DEVICE_SHIFT) |
+ kctl->private_value = (((unsigned long)device << SND_DJM_DEVICE_SHIFT) |
(group << SND_DJM_GROUP_SHIFT) |
value);
value = device->controls[i].default_value;
knew.name = device->controls[i].name;
knew.private_value = (
- (device_idx << SND_DJM_DEVICE_SHIFT) |
+ ((unsigned long)device_idx << SND_DJM_DEVICE_SHIFT) |
(i << SND_DJM_GROUP_SHIFT) |
value);
err = snd_djm_controls_update(mixer, device_idx, i, value);
struct usb_driver *driver,
const struct snd_usb_audio_quirk *quirk)
{
- driver->supports_autosuspend = 0;
+ usb_disable_autosuspend(interface_to_usbdev(iface));
return 1; /* Continue with creating streams and mixer */
}
case USB_ID(0x1901, 0x0191): /* GE B850V3 CP2114 audio interface */
case USB_ID(0x21b4, 0x0081): /* AudioQuest DragonFly */
case USB_ID(0x2912, 0x30c8): /* Audioengine D1 */
+ case USB_ID(0x413c, 0xa506): /* Dell AE515 sound bar */
+ case USB_ID(0x046d, 0x084c): /* Logitech ConferenceCam Connect */
return true;
}
&& (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
msleep(20);
+ /*
+ * Plantronics headsets (C320, C320-M, etc) need a delay to avoid
+ * random microhpone failures.
+ */
+ if (USB_ID_VENDOR(chip->usb_id) == 0x047f &&
+ (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
+ msleep(20);
+
/* Zoom R16/24, many Logitech(at least H650e/H570e/BCC950),
* Jabra 550a, Kingston HyperX needs a tiny delay here,
* otherwise requests like get/set frequency return
struct snd_card *card;
struct usb_interface *intf[MAX_CARD_INTERFACES];
u32 usb_id;
+ uint16_t quirk_type;
struct mutex mutex;
unsigned int system_suspend;
atomic_t active;
MODULE_AUTHOR("Karsten Wiese <annabellesgarden@yahoo.de>");
MODULE_DESCRIPTION("TASCAM "NAME_ALLCAPS" Version 0.8.7.2");
MODULE_LICENSE("GPL");
-MODULE_SUPPORTED_DEVICE("{{TASCAM(0x1604),"NAME_ALLCAPS"(0x8001)(0x8005)(0x8007)}}");
static int index[SNDRV_CARDS] = SNDRV_DEFAULT_IDX; /* Index 0-max */
static char* id[SNDRV_CARDS] = SNDRV_DEFAULT_STR; /* Id for this card */
MODULE_AUTHOR("Jerome Anand <jerome.anand@intel.com>");
MODULE_DESCRIPTION("Intel HDMI Audio driver");
MODULE_LICENSE("GPL v2");
-MODULE_SUPPORTED_DEVICE("{Intel,Intel_HAD}");
MODULE_DESCRIPTION("Xen virtual sound device frontend");
MODULE_LICENSE("GPL");
MODULE_ALIAS("xen:" XENSND_DRIVER_NAME);
-MODULE_SUPPORTED_DEVICE("{{ALSA,Virtual soundcard}}");
* sequential memory pages only.
*/
-/* XXX From arch/ia64/include/uapi/asm/gcc_intrin.h */
-#define ia64_mf() asm volatile ("mf" ::: "memory")
-
#define mb() ia64_mf()
#define rmb() mb()
#define wmb() mb()
#define ACR_SIZE 4
-#define PTRACE_OLDSETOPTIONS 21
-
+#define PTRACE_OLDSETOPTIONS 21
+#define PTRACE_SYSEMU 31
+#define PTRACE_SYSEMU_SINGLESTEP 32
#ifndef __ASSEMBLY__
#include <linux/stddef.h>
#include <linux/types.h>
/*
* Defines x86 CPU feature bits
*/
-#define NCAPINTS 19 /* N 32-bit words worth of info */
+#define NCAPINTS 20 /* N 32-bit words worth of info */
#define NBUGINTS 1 /* N 32-bit bug flags */
/*
#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in IA32 userspace */
#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */
#define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */
-#define X86_FEATURE_SME_COHERENT ( 3*32+17) /* "" AMD hardware-enforced cache coherency */
+/* FREE! ( 3*32+17) */
#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" LFENCE synchronizes RDTSC */
#define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */
#define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */
#define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
-#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */
+/* FREE! ( 7*32+10) */
#define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */
#define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */
#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */
#define X86_FEATURE_SSBD ( 7*32+17) /* Speculative Store Bypass Disable */
#define X86_FEATURE_MBA ( 7*32+18) /* Memory Bandwidth Allocation */
#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* "" Fill RSB on context switches */
-#define X86_FEATURE_SEV ( 7*32+20) /* AMD Secure Encrypted Virtualization */
+/* FREE! ( 7*32+20) */
#define X86_FEATURE_USE_IBPB ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* "" Use IBRS during runtime firmware calls */
#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */
#define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */
#define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */
#define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */
-#define X86_FEATURE_SEV_ES ( 8*32+20) /* AMD Secure Encrypted Virtualization - Encrypted State */
-#define X86_FEATURE_VM_PAGE_FLUSH ( 8*32+21) /* "" VM Page Flush MSR is supported */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
#define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */
/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
+#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */
#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */
/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
#define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */
#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */
#define X86_FEATURE_VGIF (15*32+16) /* Virtual GIF */
+#define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* "" SVME addr check */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */
#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/
#define X86_FEATURE_CORE_CAPABILITIES (18*32+30) /* "" IA32_CORE_CAPABILITIES MSR */
#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* "" Speculative Store Bypass Disable */
+/* AMD-defined memory encryption features, CPUID level 0x8000001f (EAX), word 19 */
+#define X86_FEATURE_SME (19*32+ 0) /* AMD Secure Memory Encryption */
+#define X86_FEATURE_SEV (19*32+ 1) /* AMD Secure Encrypted Virtualization */
+#define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* "" VM Page Flush MSR is supported */
+#define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */
+#define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */
+
/*
* BUG word(s)
*/
#define MSR_IA32_APICBASE_ENABLE (1<<11)
#define MSR_IA32_APICBASE_BASE (0xfffff<<12)
-#define MSR_IA32_TSCDEADLINE 0x000006e0
-
#define MSR_IA32_UCODE_WRITE 0x00000079
#define MSR_IA32_UCODE_REV 0x0000008b
#define KVM_NR_IRQCHIPS 3
#define KVM_RUN_X86_SMM (1 << 0)
+#define KVM_RUN_X86_BUS_LOCK (1 << 1)
/* for KVM_GET_REGS and KVM_SET_REGS */
struct kvm_regs {
#define EXIT_REASON_XRSTORS 64
#define EXIT_REASON_UMWAIT 67
#define EXIT_REASON_TPAUSE 68
+#define EXIT_REASON_BUS_LOCK 74
#define VMX_EXIT_REASONS \
{ EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \
{ EXIT_REASON_XSAVES, "XSAVES" }, \
{ EXIT_REASON_XRSTORS, "XRSTORS" }, \
{ EXIT_REASON_UMWAIT, "UMWAIT" }, \
- { EXIT_REASON_TPAUSE, "TPAUSE" }
+ { EXIT_REASON_TPAUSE, "TPAUSE" }, \
+ { EXIT_REASON_BUS_LOCK, "BUS_LOCK" }
#define VMX_EXIT_REASON_FLAGS \
{ VMX_EXIT_REASONS_FAILED_VMENTRY, "FAILED_VMENTRY" }
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for x86/kcpuid tool
+
+kcpuid : kcpuid.c
+
+CFLAGS = -Wextra
+
+BINDIR ?= /usr/sbin
+
+HWDATADIR ?= /usr/share/misc/
+
+override CFLAGS += -O2 -Wall -I../../../include
+
+%: %.c
+ $(CC) $(CFLAGS) -o $@ $< $(LDFLAGS)
+
+.PHONY : clean
+clean :
+ @rm -f kcpuid
+
+install : kcpuid
+ install -d $(DESTDIR)$(BINDIR)
+ install -m 755 -p kcpuid $(DESTDIR)$(BINDIR)/kcpuid
+ install -m 444 -p cpuid.csv $(HWDATADIR)/cpuid.csv
--- /dev/null
+# The basic row format is:
+# LEAF, SUBLEAF, register_name, bits, short_name, long_description
+
+# Leaf 00H
+ 0, 0, EAX, 31:0, max_basic_leafs, Max input value for supported subleafs
+
+# Leaf 01H
+ 1, 0, EAX, 3:0, stepping, Stepping ID
+ 1, 0, EAX, 7:4, model, Model
+ 1, 0, EAX, 11:8, family, Family ID
+ 1, 0, EAX, 13:12, processor, Processor Type
+ 1, 0, EAX, 19:16, model_ext, Extended Model ID
+ 1, 0, EAX, 27:20, family_ext, Extended Family ID
+
+ 1, 0, EBX, 7:0, brand, Brand Index
+ 1, 0, EBX, 15:8, clflush_size, CLFLUSH line size (value * 8) in bytes
+ 1, 0, EBX, 23:16, max_cpu_id, Maxim number of addressable logic cpu in this package
+ 1, 0, EBX, 31:24, apic_id, Initial APIC ID
+
+ 1, 0, ECX, 0, sse3, Streaming SIMD Extensions 3(SSE3)
+ 1, 0, ECX, 1, pclmulqdq, PCLMULQDQ instruction supported
+ 1, 0, ECX, 2, dtes64, DS area uses 64-bit layout
+ 1, 0, ECX, 3, mwait, MONITOR/MWAIT supported
+ 1, 0, ECX, 4, ds_cpl, CPL Qualified Debug Store which allows for branch message storage qualified by CPL
+ 1, 0, ECX, 5, vmx, Virtual Machine Extensions supported
+ 1, 0, ECX, 6, smx, Safer Mode Extension supported
+ 1, 0, ECX, 7, eist, Enhanced Intel SpeedStep Technology
+ 1, 0, ECX, 8, tm2, Thermal Monitor 2
+ 1, 0, ECX, 9, ssse3, Supplemental Streaming SIMD Extensions 3 (SSSE3)
+ 1, 0, ECX, 10, l1_ctx_id, L1 data cache could be set to either adaptive mode or shared mode (check IA32_MISC_ENABLE bit 24 definition)
+ 1, 0, ECX, 11, sdbg, IA32_DEBUG_INTERFACE MSR for silicon debug supported
+ 1, 0, ECX, 12, fma, FMA extensions using YMM state supported
+ 1, 0, ECX, 13, cmpxchg16b, 'CMPXCHG16B - Compare and Exchange Bytes' supported
+ 1, 0, ECX, 14, xtpr_update, xTPR Update Control supported
+ 1, 0, ECX, 15, pdcm, Perfmon and Debug Capability present
+ 1, 0, ECX, 17, pcid, Process-Context Identifiers feature present
+ 1, 0, ECX, 18, dca, Prefetching data from a memory mapped device supported
+ 1, 0, ECX, 19, sse4_1, SSE4.1 feature present
+ 1, 0, ECX, 20, sse4_2, SSE4.2 feature present
+ 1, 0, ECX, 21, x2apic, x2APIC supported
+ 1, 0, ECX, 22, movbe, MOVBE instruction supported
+ 1, 0, ECX, 23, popcnt, POPCNT instruction supported
+ 1, 0, ECX, 24, tsc_deadline_timer, LAPIC supports one-shot operation using a TSC deadline value
+ 1, 0, ECX, 25, aesni, AESNI instruction supported
+ 1, 0, ECX, 26, xsave, XSAVE/XRSTOR processor extended states (XSETBV/XGETBV/XCR0)
+ 1, 0, ECX, 27, osxsave, OS has set CR4.OSXSAVE bit to enable XSETBV/XGETBV/XCR0
+ 1, 0, ECX, 28, avx, AVX instruction supported
+ 1, 0, ECX, 29, f16c, 16-bit floating-point conversion instruction supported
+ 1, 0, ECX, 30, rdrand, RDRAND instruction supported
+
+ 1, 0, EDX, 0, fpu, x87 FPU on chip
+ 1, 0, EDX, 1, vme, Virtual-8086 Mode Enhancement
+ 1, 0, EDX, 2, de, Debugging Extensions
+ 1, 0, EDX, 3, pse, Page Size Extensions
+ 1, 0, EDX, 4, tsc, Time Stamp Counter
+ 1, 0, EDX, 5, msr, RDMSR and WRMSR Support
+ 1, 0, EDX, 6, pae, Physical Address Extensions
+ 1, 0, EDX, 7, mce, Machine Check Exception
+ 1, 0, EDX, 8, cx8, CMPXCHG8B instr
+ 1, 0, EDX, 9, apic, APIC on Chip
+ 1, 0, EDX, 11, sep, SYSENTER and SYSEXIT instrs
+ 1, 0, EDX, 12, mtrr, Memory Type Range Registers
+ 1, 0, EDX, 13, pge, Page Global Bit
+ 1, 0, EDX, 14, mca, Machine Check Architecture
+ 1, 0, EDX, 15, cmov, Conditional Move Instrs
+ 1, 0, EDX, 16, pat, Page Attribute Table
+ 1, 0, EDX, 17, pse36, 36-Bit Page Size Extension
+ 1, 0, EDX, 18, psn, Processor Serial Number
+ 1, 0, EDX, 19, clflush, CLFLUSH instr
+# 1, 0, EDX, 20,
+ 1, 0, EDX, 21, ds, Debug Store
+ 1, 0, EDX, 22, acpi, Thermal Monitor and Software Controlled Clock Facilities
+ 1, 0, EDX, 23, mmx, Intel MMX Technology
+ 1, 0, EDX, 24, fxsr, XSAVE and FXRSTOR Instrs
+ 1, 0, EDX, 25, sse, SSE
+ 1, 0, EDX, 26, sse2, SSE2
+ 1, 0, EDX, 27, ss, Self Snoop
+ 1, 0, EDX, 28, hit, Max APIC IDs
+ 1, 0, EDX, 29, tm, Thermal Monitor
+# 1, 0, EDX, 30,
+ 1, 0, EDX, 31, pbe, Pending Break Enable
+
+# Leaf 02H
+# cache and TLB descriptor info
+
+# Leaf 03H
+# Precessor Serial Number, introduced on Pentium III, not valid for
+# latest models
+
+# Leaf 04H
+# thread/core and cache topology
+ 4, 0, EAX, 4:0, cache_type, Cache type like instr/data or unified
+ 4, 0, EAX, 7:5, cache_level, Cache Level (starts at 1)
+ 4, 0, EAX, 8, cache_self_init, Cache Self Initialization
+ 4, 0, EAX, 9, fully_associate, Fully Associative cache
+# 4, 0, EAX, 13:10, resvd, resvd
+ 4, 0, EAX, 25:14, max_logical_id, Max number of addressable IDs for logical processors sharing the cache
+ 4, 0, EAX, 31:26, max_phy_id, Max number of addressable IDs for processors in phy package
+
+ 4, 0, EBX, 11:0, cache_linesize, Size of a cache line in bytes
+ 4, 0, EBX, 21:12, cache_partition, Physical Line partitions
+ 4, 0, EBX, 31:22, cache_ways, Ways of associativity
+ 4, 0, ECX, 31:0, cache_sets, Number of Sets - 1
+ 4, 0, EDX, 0, c_wbinvd, 1 means WBINVD/INVD is not ganranteed to act upon lower level caches of non-originating threads sharing this cache
+ 4, 0, EDX, 1, c_incl, Whether cache is inclusive of lower cache level
+ 4, 0, EDX, 2, c_comp_index, Complex Cache Indexing
+
+# Leaf 05H
+# MONITOR/MWAIT
+ 5, 0, EAX, 15:0, min_mon_size, Smallest monitor line size in bytes
+ 5, 0, EBX, 15:0, max_mon_size, Largest monitor line size in bytes
+ 5, 0, ECX, 0, mwait_ext, Enum of Monitor-Mwait extensions supported
+ 5, 0, ECX, 1, mwait_irq_break, Largest monitor line size in bytes
+ 5, 0, EDX, 3:0, c0_sub_stats, Number of C0* sub C-states supported using MWAIT
+ 5, 0, EDX, 7:4, c1_sub_stats, Number of C1* sub C-states supported using MWAIT
+ 5, 0, EDX, 11:8, c2_sub_stats, Number of C2* sub C-states supported using MWAIT
+ 5, 0, EDX, 15:12, c3_sub_stats, Number of C3* sub C-states supported using MWAIT
+ 5, 0, EDX, 19:16, c4_sub_stats, Number of C4* sub C-states supported using MWAIT
+ 5, 0, EDX, 23:20, c5_sub_stats, Number of C5* sub C-states supported using MWAIT
+ 5, 0, EDX, 27:24, c6_sub_stats, Number of C6* sub C-states supported using MWAIT
+ 5, 0, EDX, 31:28, c7_sub_stats, Number of C7* sub C-states supported using MWAIT
+
+# Leaf 06H
+# Thermal & Power Management
+
+ 6, 0, EAX, 0, dig_temp, Digital temperature sensor supported
+ 6, 0, EAX, 1, turbo, Intel Turbo Boost
+ 6, 0, EAX, 2, arat, Always running APIC timer
+# 6, 0, EAX, 3, resv, Reserved
+ 6, 0, EAX, 4, pln, Power limit notifications supported
+ 6, 0, EAX, 5, ecmd, Clock modulation duty cycle extension supported
+ 6, 0, EAX, 6, ptm, Package thermal management supported
+ 6, 0, EAX, 7, hwp, HWP base register
+ 6, 0, EAX, 8, hwp_notify, HWP notification
+ 6, 0, EAX, 9, hwp_act_window, HWP activity window
+ 6, 0, EAX, 10, hwp_energy, HWP energy performance preference
+ 6, 0, EAX, 11, hwp_pkg_req, HWP package level request
+# 6, 0, EAX, 12, resv, Reserved
+ 6, 0, EAX, 13, hdc, HDC base registers supported
+ 6, 0, EAX, 14, turbo3, Turbo Boost Max 3.0
+ 6, 0, EAX, 15, hwp_cap, Highest Performance change supported
+ 6, 0, EAX, 16, hwp_peci, HWP PECI override is supported
+ 6, 0, EAX, 17, hwp_flex, Flexible HWP is supported
+ 6, 0, EAX, 18, hwp_fast, Fast access mode for the IA32_HWP_REQUEST MSR is supported
+# 6, 0, EAX, 19, resv, Reserved
+ 6, 0, EAX, 20, hwp_ignr, Ignoring Idle Logical Processor HWP request is supported
+
+ 6, 0, EBX, 3:0, therm_irq_thresh, Number of Interrupt Thresholds in Digital Thermal Sensor
+ 6, 0, ECX, 0, aperfmperf, Presence of IA32_MPERF and IA32_APERF
+ 6, 0, ECX, 3, energ_bias, Performance-energy bias preference supported
+
+# Leaf 07H
+# ECX == 0
+# AVX512 refers to https://en.wikipedia.org/wiki/AVX-512
+# XXX: Do we really need to enumerate each and every AVX512 sub features
+
+ 7, 0, EBX, 0, fsgsbase, RDFSBASE/RDGSBASE/WRFSBASE/WRGSBASE supported
+ 7, 0, EBX, 1, tsc_adjust, TSC_ADJUST MSR supported
+ 7, 0, EBX, 2, sgx, Software Guard Extensions
+ 7, 0, EBX, 3, bmi1, BMI1
+ 7, 0, EBX, 4, hle, Hardware Lock Elision
+ 7, 0, EBX, 5, avx2, AVX2
+# 7, 0, EBX, 6, fdp_excp_only, x87 FPU Data Pointer updated only on x87 exceptions
+ 7, 0, EBX, 7, smep, Supervisor-Mode Execution Prevention
+ 7, 0, EBX, 8, bmi2, BMI2
+ 7, 0, EBX, 9, rep_movsb, Enhanced REP MOVSB/STOSB
+ 7, 0, EBX, 10, invpcid, INVPCID instruction
+ 7, 0, EBX, 11, rtm, Restricted Transactional Memory
+ 7, 0, EBX, 12, rdt_m, Intel RDT Monitoring capability
+ 7, 0, EBX, 13, depc_fpu_cs_ds, Deprecates FPU CS and FPU DS
+ 7, 0, EBX, 14, mpx, Memory Protection Extensions
+ 7, 0, EBX, 15, rdt_a, Intel RDT Allocation capability
+ 7, 0, EBX, 16, avx512f, AVX512 Foundation instr
+ 7, 0, EBX, 17, avx512dq, AVX512 Double and Quadword AVX512 instr
+ 7, 0, EBX, 18, rdseed, RDSEED instr
+ 7, 0, EBX, 19, adx, ADX instr
+ 7, 0, EBX, 20, smap, Supervisor Mode Access Prevention
+ 7, 0, EBX, 21, avx512ifma, AVX512 Integer Fused Multiply Add
+# 7, 0, EBX, 22, resvd, resvd
+ 7, 0, EBX, 23, clflushopt, CLFLUSHOPT instr
+ 7, 0, EBX, 24, clwb, CLWB instr
+ 7, 0, EBX, 25, intel_pt, Intel Processor Trace instr
+ 7, 0, EBX, 26, avx512pf, Prefetch
+ 7, 0, EBX, 27, avx512er, AVX512 Exponent Reciproca instr
+ 7, 0, EBX, 28, avx512cd, AVX512 Conflict Detection instr
+ 7, 0, EBX, 29, sha, Intel Secure Hash Algorithm Extensions instr
+ 7, 0, EBX, 26, avx512bw, AVX512 Byte & Word instr
+ 7, 0, EBX, 28, avx512vl, AVX512 Vector Length Extentions (VL)
+ 7, 0, ECX, 0, prefetchwt1, X
+ 7, 0, ECX, 1, avx512vbmi, AVX512 Vector Byte Manipulation Instructions
+ 7, 0, ECX, 2, umip, User-mode Instruction Prevention
+
+ 7, 0, ECX, 3, pku, Protection Keys for User-mode pages
+ 7, 0, ECX, 4, ospke, CR4 PKE set to enable protection keys
+# 7, 0, ECX, 16:5, resvd, resvd
+ 7, 0, ECX, 21:17, mawau, The value of MAWAU used by the BNDLDX and BNDSTX instructions in 64-bit mode
+ 7, 0, ECX, 22, rdpid, RDPID and IA32_TSC_AUX
+# 7, 0, ECX, 29:23, resvd, resvd
+ 7, 0, ECX, 30, sgx_lc, SGX Launch Configuration
+# 7, 0, ECX, 31, resvd, resvd
+
+# Leaf 08H
+#
+
+
+# Leaf 09H
+# Direct Cache Access (DCA) information
+ 9, 0, ECX, 31:0, dca_cap, The value of IA32_PLATFORM_DCA_CAP
+
+# Leaf 0AH
+# Architectural Performance Monitoring
+#
+# Do we really need to print out the PMU related stuff?
+# Does normal user really care about it?
+#
+ 0xA, 0, EAX, 7:0, pmu_ver, Performance Monitoring Unit version
+ 0xA, 0, EAX, 15:8, pmu_gp_cnt_num, Numer of general-purose PMU counters per logical CPU
+ 0xA, 0, EAX, 23:16, pmu_cnt_bits, Bit wideth of PMU counter
+ 0xA, 0, EAX, 31:24, pmu_ebx_bits, Length of EBX bit vector to enumerate PMU events
+
+ 0xA, 0, EBX, 0, pmu_no_core_cycle_evt, Core cycle event not available
+ 0xA, 0, EBX, 1, pmu_no_instr_ret_evt, Instruction retired event not available
+ 0xA, 0, EBX, 2, pmu_no_ref_cycle_evt, Reference cycles event not available
+ 0xA, 0, EBX, 3, pmu_no_llc_ref_evt, Last-level cache reference event not available
+ 0xA, 0, EBX, 4, pmu_no_llc_mis_evt, Last-level cache misses event not available
+ 0xA, 0, EBX, 5, pmu_no_br_instr_ret_evt, Branch instruction retired event not available
+ 0xA, 0, EBX, 6, pmu_no_br_mispredict_evt, Branch mispredict retired event not available
+
+ 0xA, 0, ECX, 4:0, pmu_fixed_cnt_num, Performance Monitoring Unit version
+ 0xA, 0, ECX, 12:5, pmu_fixed_cnt_bits, Numer of PMU counters per logical CPU
+
+# Leaf 0BH
+# Extended Topology Enumeration Leaf
+#
+
+ 0xB, 0, EAX, 4:0, id_shift, Number of bits to shift right on x2APIC ID to get a unique topology ID of the next level type
+ 0xB, 0, EBX, 15:0, cpu_nr, Number of logical processors at this level type
+ 0xB, 0, ECX, 15:8, lvl_type, 0-Invalid 1-SMT 2-Core
+ 0xB, 0, EDX, 31:0, x2apic_id, x2APIC ID the current logical processor
+
+
+# Leaf 0DH
+# Processor Extended State
+
+ 0xD, 0, EAX, 0, x87, X87 state
+ 0xD, 0, EAX, 1, sse, SSE state
+ 0xD, 0, EAX, 2, avx, AVX state
+ 0xD, 0, EAX, 4:3, mpx, MPX state
+ 0xD, 0, EAX, 7:5, avx512, AVX-512 state
+ 0xD, 0, EAX, 9, pkru, PKRU state
+
+ 0xD, 0, EBX, 31:0, max_sz_xcr0, Maximum size (bytes) required by enabled features in XCR0
+ 0xD, 0, ECX, 31:0, max_sz_xsave, Maximum size (bytes) of the XSAVE/XRSTOR save area
+
+ 0xD, 1, EAX, 0, xsaveopt, XSAVEOPT available
+ 0xD, 1, EAX, 1, xsavec, XSAVEC and compacted form supported
+ 0xD, 1, EAX, 2, xgetbv, XGETBV supported
+ 0xD, 1, EAX, 3, xsaves, XSAVES/XRSTORS and IA32_XSS supported
+
+ 0xD, 1, EBX, 31:0, max_sz_xcr0, Maximum size (bytes) required by enabled features in XCR0
+ 0xD, 1, ECX, 8, pt, PT state
+ 0xD, 1, ECX, 11, cet_usr, CET user state
+ 0xD, 1, ECX, 12, cet_supv, CET supervisor state
+ 0xD, 1, ECX, 13, hdc, HDC state
+ 0xD, 1, ECX, 16, hwp, HWP state
+
+# Leaf 0FH
+# Intel RDT Monitoring
+
+ 0xF, 0, EBX, 31:0, rmid_range, Maximum range (zero-based) of RMID within this physical processor of all types
+ 0xF, 0, EDX, 1, l3c_rdt_mon, L3 Cache RDT Monitoring supported
+
+ 0xF, 1, ECX, 31:0, rmid_range, Maximum range (zero-based) of RMID of this types
+ 0xF, 1, EDX, 0, l3c_ocp_mon, L3 Cache occupancy Monitoring supported
+ 0xF, 1, EDX, 1, l3c_tbw_mon, L3 Cache Total Bandwidth Monitoring supported
+ 0xF, 1, EDX, 2, l3c_lbw_mon, L3 Cache Local Bandwidth Monitoring supported
+
+# Leaf 10H
+# Intel RDT Allocation
+
+ 0x10, 0, EBX, 1, l3c_rdt_alloc, L3 Cache Allocation supported
+ 0x10, 0, EBX, 2, l2c_rdt_alloc, L2 Cache Allocation supported
+ 0x10, 0, EBX, 3, mem_bw_alloc, Memory Bandwidth Allocation supported
+
+
+# Leaf 12H
+# SGX Capability
+#
+# Some detailed SGX features not added yet
+
+ 0x12, 0, EAX, 0, sgx1, L3 Cache Allocation supported
+ 0x12, 1, EAX, 0, sgx2, L3 Cache Allocation supported
+
+
+# Leaf 14H
+# Intel Processor Tracer
+#
+
+# Leaf 15H
+# Time Stamp Counter and Nominal Core Crystal Clock Information
+
+ 0x15, 0, EAX, 31:0, tsc_denominator, The denominator of the TSC/”core crystal clock” ratio
+ 0x15, 0, EBX, 31:0, tsc_numerator, The numerator of the TSC/”core crystal clock” ratio
+ 0x15, 0, ECX, 31:0, nom_freq, Nominal frequency of the core crystal clock in Hz
+
+# Leaf 16H
+# Processor Frequency Information
+
+ 0x16, 0, EAX, 15:0, cpu_base_freq, Processor Base Frequency in MHz
+ 0x16, 0, EBX, 15:0, cpu_max_freq, Maximum Frequency in MHz
+ 0x16, 0, ECX, 15:0, bus_freq, Bus (Reference) Frequency in MHz
+
+# Leaf 17H
+# System-On-Chip Vendor Attribute
+
+ 0x17, 0, EAX, 31:0, max_socid, Maximum input value of supported sub-leaf
+ 0x17, 0, EBX, 15:0, soc_vid, SOC Vendor ID
+ 0x17, 0, EBX, 16, std_vid, SOC Vendor ID is assigned via an industry standard scheme
+ 0x17, 0, ECX, 31:0, soc_pid, SOC Project ID assigned by vendor
+ 0x17, 0, EDX, 31:0, soc_sid, SOC Stepping ID
+
+# Leaf 18H
+# Deterministic Address Translation Parameters
+
+
+# Leaf 19H
+# Key Locker Leaf
+
+
+# Leaf 1AH
+# Hybrid Information
+
+ 0x1A, 0, EAX, 31:24, core_type, 20H-Intel_Atom 40H-Intel_Core
+
+
+# Leaf 1FH
+# V2 Extended Topology - A preferred superset to leaf 0BH
+
+
+# According to SDM
+# 40000000H - 4FFFFFFFH is invalid range
+
+
+# Leaf 80000001H
+# Extended Processor Signature and Feature Bits
+
+0x80000001, 0, ECX, 0, lahf_lm, LAHF/SAHF available in 64-bit mode
+0x80000001, 0, ECX, 5, lzcnt, LZCNT
+0x80000001, 0, ECX, 8, prefetchw, PREFETCHW
+
+0x80000001, 0, EDX, 11, sysret, SYSCALL/SYSRET supported
+0x80000001, 0, EDX, 20, exec_dis, Execute Disable Bit available
+0x80000001, 0, EDX, 26, 1gb_page, 1GB page supported
+0x80000001, 0, EDX, 27, rdtscp, RDTSCP and IA32_TSC_AUX are available
+#0x80000001, 0, EDX, 29, 64b, 64b Architecture supported
+
+# Leaf 80000002H/80000003H/80000004H
+# Processor Brand String
+
+# Leaf 80000005H
+# Reserved
+
+# Leaf 80000006H
+# Extended L2 Cache Features
+
+0x80000006, 0, ECX, 7:0, clsize, Cache Line size in bytes
+0x80000006, 0, ECX, 15:12, l2c_assoc, L2 Associativity
+0x80000006, 0, ECX, 31:16, csize, Cache size in 1K units
+
+
+# Leaf 80000007H
+
+0x80000007, 0, EDX, 8, nonstop_tsc, Invariant TSC available
+
+
+# Leaf 80000008H
+
+0x80000008, 0, EAX, 7:0, phy_adr_bits, Physical Address Bits
+0x80000008, 0, EAX, 15:8, lnr_adr_bits, Linear Address Bits
+0x80000007, 0, EBX, 9, wbnoinvd, WBNOINVD
+
+# 0x8000001E
+# EAX: Extended APIC ID
+0x8000001E, 0, EAX, 31:0, extended_apic_id, Extended APIC ID
+# EBX: Core Identifiers
+0x8000001E, 0, EBX, 7:0, core_id, Identifies the logical core ID
+0x8000001E, 0, EBX, 15:8, threads_per_core, The number of threads per core is threads_per_core + 1
+# ECX: Node Identifiers
+0x8000001E, 0, ECX, 7:0, node_id, Node ID
+0x8000001E, 0, ECX, 10:8, nodes_per_processor, Nodes per processor { 0: 1 node, else reserved }
+
+# 8000001F: AMD Secure Encryption
+0x8000001F, 0, EAX, 0, sme, Secure Memory Encryption
+0x8000001F, 0, EAX, 1, sev, Secure Encrypted Virtualization
+0x8000001F, 0, EAX, 2, vmpgflush, VM Page Flush MSR
+0x8000001F, 0, EAX, 3, seves, SEV Encrypted State
+0x8000001F, 0, EBX, 5:0, c-bit, Page table bit number used to enable memory encryption
+0x8000001F, 0, EBX, 11:6, mem_encrypt_physaddr_width, Reduction of physical address space in bits with SME enabled
+0x8000001F, 0, ECX, 31:0, num_encrypted_guests, Maximum ASID value that may be used for an SEV-enabled guest
+0x8000001F, 0, EDX, 31:0, minimum_sev_asid, Minimum ASID value that must be used for an SEV-enabled, SEV-ES-disabled guest
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+
+#include <stdio.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <string.h>
+#include <getopt.h>
+
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+
+typedef unsigned int u32;
+typedef unsigned long long u64;
+
+char *def_csv = "/usr/share/misc/cpuid.csv";
+char *user_csv;
+
+
+/* Cover both single-bit flag and multiple-bits fields */
+struct bits_desc {
+ /* start and end bits */
+ int start, end;
+ /* 0 or 1 for 1-bit flag */
+ int value;
+ char simp[32];
+ char detail[256];
+};
+
+/* descriptor info for eax/ebx/ecx/edx */
+struct reg_desc {
+ /* number of valid entries */
+ int nr;
+ struct bits_desc descs[32];
+};
+
+enum {
+ R_EAX = 0,
+ R_EBX,
+ R_ECX,
+ R_EDX,
+ NR_REGS
+};
+
+struct subleaf {
+ u32 index;
+ u32 sub;
+ u32 eax, ebx, ecx, edx;
+ struct reg_desc info[NR_REGS];
+};
+
+/* Represent one leaf (basic or extended) */
+struct cpuid_func {
+ /*
+ * Array of subleafs for this func, if there is no subleafs
+ * then the leafs[0] is the main leaf
+ */
+ struct subleaf *leafs;
+ int nr;
+};
+
+struct cpuid_range {
+ /* array of main leafs */
+ struct cpuid_func *funcs;
+ /* number of valid leafs */
+ int nr;
+ bool is_ext;
+};
+
+/*
+ * basic: basic functions range: [0... ]
+ * ext: extended functions range: [0x80000000... ]
+ */
+struct cpuid_range *leafs_basic, *leafs_ext;
+
+static int num_leafs;
+static bool is_amd;
+static bool show_details;
+static bool show_raw;
+static bool show_flags_only = true;
+static u32 user_index = 0xFFFFFFFF;
+static u32 user_sub = 0xFFFFFFFF;
+static int flines;
+
+static inline void cpuid(u32 *eax, u32 *ebx, u32 *ecx, u32 *edx)
+{
+ /* ecx is often an input as well as an output. */
+ asm volatile("cpuid"
+ : "=a" (*eax),
+ "=b" (*ebx),
+ "=c" (*ecx),
+ "=d" (*edx)
+ : "0" (*eax), "2" (*ecx));
+}
+
+static inline bool has_subleafs(u32 f)
+{
+ if (f == 0x7 || f == 0xd)
+ return true;
+
+ if (is_amd) {
+ if (f == 0x8000001d)
+ return true;
+ return false;
+ }
+
+ switch (f) {
+ case 0x4:
+ case 0xb:
+ case 0xf:
+ case 0x10:
+ case 0x14:
+ case 0x18:
+ case 0x1f:
+ return true;
+ default:
+ return false;
+ }
+}
+
+static void leaf_print_raw(struct subleaf *leaf)
+{
+ if (has_subleafs(leaf->index)) {
+ if (leaf->sub == 0)
+ printf("0x%08x: subleafs:\n", leaf->index);
+
+ printf(" %2d: EAX=0x%08x, EBX=0x%08x, ECX=0x%08x, EDX=0x%08x\n",
+ leaf->sub, leaf->eax, leaf->ebx, leaf->ecx, leaf->edx);
+ } else {
+ printf("0x%08x: EAX=0x%08x, EBX=0x%08x, ECX=0x%08x, EDX=0x%08x\n",
+ leaf->index, leaf->eax, leaf->ebx, leaf->ecx, leaf->edx);
+ }
+}
+
+/* Return true is the input eax/ebx/ecx/edx are all zero */
+static bool cpuid_store(struct cpuid_range *range, u32 f, int subleaf,
+ u32 a, u32 b, u32 c, u32 d)
+{
+ struct cpuid_func *func;
+ struct subleaf *leaf;
+ int s = 0;
+
+ if (a == 0 && b == 0 && c == 0 && d == 0)
+ return true;
+
+ /*
+ * Cut off vendor-prefix from CPUID function as we're using it as an
+ * index into ->funcs.
+ */
+ func = &range->funcs[f & 0xffff];
+
+ if (!func->leafs) {
+ func->leafs = malloc(sizeof(struct subleaf));
+ if (!func->leafs)
+ perror("malloc func leaf");
+
+ func->nr = 1;
+ } else {
+ s = func->nr;
+ func->leafs = realloc(func->leafs, (s + 1) * sizeof(*leaf));
+ if (!func->leafs)
+ perror("realloc f->leafs");
+
+ func->nr++;
+ }
+
+ leaf = &func->leafs[s];
+
+ leaf->index = f;
+ leaf->sub = subleaf;
+ leaf->eax = a;
+ leaf->ebx = b;
+ leaf->ecx = c;
+ leaf->edx = d;
+
+ return false;
+}
+
+static void raw_dump_range(struct cpuid_range *range)
+{
+ u32 f;
+ int i;
+
+ printf("%s Leafs :\n", range->is_ext ? "Extended" : "Basic");
+ printf("================\n");
+
+ for (f = 0; (int)f < range->nr; f++) {
+ struct cpuid_func *func = &range->funcs[f];
+ u32 index = f;
+
+ if (range->is_ext)
+ index += 0x80000000;
+
+ /* Skip leaf without valid items */
+ if (!func->nr)
+ continue;
+
+ /* First item is the main leaf, followed by all subleafs */
+ for (i = 0; i < func->nr; i++)
+ leaf_print_raw(&func->leafs[i]);
+ }
+}
+
+#define MAX_SUBLEAF_NUM 32
+struct cpuid_range *setup_cpuid_range(u32 input_eax)
+{
+ u32 max_func, idx_func;
+ int subleaf;
+ struct cpuid_range *range;
+ u32 eax, ebx, ecx, edx;
+ u32 f = input_eax;
+ int max_subleaf;
+ bool allzero;
+
+ eax = input_eax;
+ ebx = ecx = edx = 0;
+
+ cpuid(&eax, &ebx, &ecx, &edx);
+ max_func = eax;
+ idx_func = (max_func & 0xffff) + 1;
+
+ range = malloc(sizeof(struct cpuid_range));
+ if (!range)
+ perror("malloc range");
+
+ if (input_eax & 0x80000000)
+ range->is_ext = true;
+ else
+ range->is_ext = false;
+
+ range->funcs = malloc(sizeof(struct cpuid_func) * idx_func);
+ if (!range->funcs)
+ perror("malloc range->funcs");
+
+ range->nr = idx_func;
+ memset(range->funcs, 0, sizeof(struct cpuid_func) * idx_func);
+
+ for (; f <= max_func; f++) {
+ eax = f;
+ subleaf = ecx = 0;
+
+ cpuid(&eax, &ebx, &ecx, &edx);
+ allzero = cpuid_store(range, f, subleaf, eax, ebx, ecx, edx);
+ if (allzero)
+ continue;
+ num_leafs++;
+
+ if (!has_subleafs(f))
+ continue;
+
+ max_subleaf = MAX_SUBLEAF_NUM;
+
+ /*
+ * Some can provide the exact number of subleafs,
+ * others have to be tried (0xf)
+ */
+ if (f == 0x7 || f == 0x14 || f == 0x17 || f == 0x18)
+ max_subleaf = (eax & 0xff) + 1;
+
+ if (f == 0xb)
+ max_subleaf = 2;
+
+ for (subleaf = 1; subleaf < max_subleaf; subleaf++) {
+ eax = f;
+ ecx = subleaf;
+
+ cpuid(&eax, &ebx, &ecx, &edx);
+ allzero = cpuid_store(range, f, subleaf,
+ eax, ebx, ecx, edx);
+ if (allzero)
+ continue;
+ num_leafs++;
+ }
+
+ }
+
+ return range;
+}
+
+/*
+ * The basic row format for cpuid.csv is
+ * LEAF,SUBLEAF,register_name,bits,short name,long description
+ *
+ * like:
+ * 0, 0, EAX, 31:0, max_basic_leafs, Max input value for supported subleafs
+ * 1, 0, ECX, 0, sse3, Streaming SIMD Extensions 3(SSE3)
+ */
+static int parse_line(char *line)
+{
+ char *str;
+ int i;
+ struct cpuid_range *range;
+ struct cpuid_func *func;
+ struct subleaf *leaf;
+ u32 index;
+ u32 sub;
+ char buffer[512];
+ char *buf;
+ /*
+ * Tokens:
+ * 1. leaf
+ * 2. subleaf
+ * 3. register
+ * 4. bits
+ * 5. short name
+ * 6. long detail
+ */
+ char *tokens[6];
+ struct reg_desc *reg;
+ struct bits_desc *bdesc;
+ int reg_index;
+ char *start, *end;
+
+ /* Skip comments and NULL line */
+ if (line[0] == '#' || line[0] == '\n')
+ return 0;
+
+ strncpy(buffer, line, 511);
+ buffer[511] = 0;
+ str = buffer;
+ for (i = 0; i < 5; i++) {
+ tokens[i] = strtok(str, ",");
+ if (!tokens[i])
+ goto err_exit;
+ str = NULL;
+ }
+ tokens[5] = strtok(str, "\n");
+ if (!tokens[5])
+ goto err_exit;
+
+ /* index/main-leaf */
+ index = strtoull(tokens[0], NULL, 0);
+
+ if (index & 0x80000000)
+ range = leafs_ext;
+ else
+ range = leafs_basic;
+
+ index &= 0x7FFFFFFF;
+ /* Skip line parsing for non-existing indexes */
+ if ((int)index >= range->nr)
+ return -1;
+
+ func = &range->funcs[index];
+
+ /* Return if the index has no valid item on this platform */
+ if (!func->nr)
+ return 0;
+
+ /* subleaf */
+ sub = strtoul(tokens[1], NULL, 0);
+ if ((int)sub > func->nr)
+ return -1;
+
+ leaf = &func->leafs[sub];
+ buf = tokens[2];
+
+ if (strcasestr(buf, "EAX"))
+ reg_index = R_EAX;
+ else if (strcasestr(buf, "EBX"))
+ reg_index = R_EBX;
+ else if (strcasestr(buf, "ECX"))
+ reg_index = R_ECX;
+ else if (strcasestr(buf, "EDX"))
+ reg_index = R_EDX;
+ else
+ goto err_exit;
+
+ reg = &leaf->info[reg_index];
+ bdesc = ®->descs[reg->nr++];
+
+ /* bit flag or bits field */
+ buf = tokens[3];
+
+ end = strtok(buf, ":");
+ bdesc->end = strtoul(end, NULL, 0);
+ bdesc->start = bdesc->end;
+
+ /* start != NULL means it is bit fields */
+ start = strtok(NULL, ":");
+ if (start)
+ bdesc->start = strtoul(start, NULL, 0);
+
+ strcpy(bdesc->simp, tokens[4]);
+ strcpy(bdesc->detail, tokens[5]);
+ return 0;
+
+err_exit:
+ printf("Warning: wrong line format:\n");
+ printf("\tline[%d]: %s\n", flines, line);
+ return -1;
+}
+
+/* Parse csv file, and construct the array of all leafs and subleafs */
+static void parse_text(void)
+{
+ FILE *file;
+ char *filename, *line = NULL;
+ size_t len = 0;
+ int ret;
+
+ if (show_raw)
+ return;
+
+ filename = user_csv ? user_csv : def_csv;
+ file = fopen(filename, "r");
+ if (!file) {
+ /* Fallback to a csv in the same dir */
+ file = fopen("./cpuid.csv", "r");
+ }
+
+ if (!file) {
+ printf("Fail to open '%s'\n", filename);
+ return;
+ }
+
+ while (1) {
+ ret = getline(&line, &len, file);
+ flines++;
+ if (ret > 0)
+ parse_line(line);
+
+ if (feof(file))
+ break;
+ }
+
+ fclose(file);
+}
+
+
+/* Decode every eax/ebx/ecx/edx */
+static void decode_bits(u32 value, struct reg_desc *rdesc)
+{
+ struct bits_desc *bdesc;
+ int start, end, i;
+ u32 mask;
+
+ for (i = 0; i < rdesc->nr; i++) {
+ bdesc = &rdesc->descs[i];
+
+ start = bdesc->start;
+ end = bdesc->end;
+ if (start == end) {
+ /* single bit flag */
+ if (value & (1 << start))
+ printf("\t%-20s %s%s\n",
+ bdesc->simp,
+ show_details ? "-" : "",
+ show_details ? bdesc->detail : ""
+ );
+ } else {
+ /* bit fields */
+ if (show_flags_only)
+ continue;
+
+ mask = ((u64)1 << (end - start + 1)) - 1;
+ printf("\t%-20s\t: 0x%-8x\t%s%s\n",
+ bdesc->simp,
+ (value >> start) & mask,
+ show_details ? "-" : "",
+ show_details ? bdesc->detail : ""
+ );
+ }
+ }
+}
+
+static void show_leaf(struct subleaf *leaf)
+{
+ if (!leaf)
+ return;
+
+ if (show_raw)
+ leaf_print_raw(leaf);
+
+ decode_bits(leaf->eax, &leaf->info[R_EAX]);
+ decode_bits(leaf->ebx, &leaf->info[R_EBX]);
+ decode_bits(leaf->ecx, &leaf->info[R_ECX]);
+ decode_bits(leaf->edx, &leaf->info[R_EDX]);
+}
+
+static void show_func(struct cpuid_func *func)
+{
+ int i;
+
+ if (!func)
+ return;
+
+ for (i = 0; i < func->nr; i++)
+ show_leaf(&func->leafs[i]);
+}
+
+static void show_range(struct cpuid_range *range)
+{
+ int i;
+
+ for (i = 0; i < range->nr; i++)
+ show_func(&range->funcs[i]);
+}
+
+static inline struct cpuid_func *index_to_func(u32 index)
+{
+ struct cpuid_range *range;
+
+ range = (index & 0x80000000) ? leafs_ext : leafs_basic;
+ index &= 0x7FFFFFFF;
+
+ if (((index & 0xFFFF) + 1) > (u32)range->nr) {
+ printf("ERR: invalid input index (0x%x)\n", index);
+ return NULL;
+ }
+ return &range->funcs[index];
+}
+
+static void show_info(void)
+{
+ struct cpuid_func *func;
+
+ if (show_raw) {
+ /* Show all of the raw output of 'cpuid' instr */
+ raw_dump_range(leafs_basic);
+ raw_dump_range(leafs_ext);
+ return;
+ }
+
+ if (user_index != 0xFFFFFFFF) {
+ /* Only show specific leaf/subleaf info */
+ func = index_to_func(user_index);
+ if (!func)
+ return;
+
+ /* Dump the raw data also */
+ show_raw = true;
+
+ if (user_sub != 0xFFFFFFFF) {
+ if (user_sub + 1 <= (u32)func->nr) {
+ show_leaf(&func->leafs[user_sub]);
+ return;
+ }
+
+ printf("ERR: invalid input subleaf (0x%x)\n", user_sub);
+ }
+
+ show_func(func);
+ return;
+ }
+
+ printf("CPU features:\n=============\n\n");
+ show_range(leafs_basic);
+ show_range(leafs_ext);
+}
+
+static void setup_platform_cpuid(void)
+{
+ u32 eax, ebx, ecx, edx;
+
+ /* Check vendor */
+ eax = ebx = ecx = edx = 0;
+ cpuid(&eax, &ebx, &ecx, &edx);
+
+ /* "htuA" */
+ if (ebx == 0x68747541)
+ is_amd = true;
+
+ /* Setup leafs for the basic and extended range */
+ leafs_basic = setup_cpuid_range(0x0);
+ leafs_ext = setup_cpuid_range(0x80000000);
+}
+
+static void usage(void)
+{
+ printf("kcpuid [-abdfhr] [-l leaf] [-s subleaf]\n"
+ "\t-a|--all Show both bit flags and complex bit fields info\n"
+ "\t-b|--bitflags Show boolean flags only\n"
+ "\t-d|--detail Show details of the flag/fields (default)\n"
+ "\t-f|--flags Specify the cpuid csv file\n"
+ "\t-h|--help Show usage info\n"
+ "\t-l|--leaf=index Specify the leaf you want to check\n"
+ "\t-r|--raw Show raw cpuid data\n"
+ "\t-s|--subleaf=sub Specify the subleaf you want to check\n"
+ );
+}
+
+static struct option opts[] = {
+ { "all", no_argument, NULL, 'a' }, /* show both bit flags and fields */
+ { "bitflags", no_argument, NULL, 'b' }, /* only show bit flags, default on */
+ { "detail", no_argument, NULL, 'd' }, /* show detail descriptions */
+ { "file", required_argument, NULL, 'f' }, /* use user's cpuid file */
+ { "help", no_argument, NULL, 'h'}, /* show usage */
+ { "leaf", required_argument, NULL, 'l'}, /* only check a specific leaf */
+ { "raw", no_argument, NULL, 'r'}, /* show raw CPUID leaf data */
+ { "subleaf", required_argument, NULL, 's'}, /* check a specific subleaf */
+ { NULL, 0, NULL, 0 }
+};
+
+static int parse_options(int argc, char *argv[])
+{
+ int c;
+
+ while ((c = getopt_long(argc, argv, "abdf:hl:rs:",
+ opts, NULL)) != -1)
+ switch (c) {
+ case 'a':
+ show_flags_only = false;
+ break;
+ case 'b':
+ show_flags_only = true;
+ break;
+ case 'd':
+ show_details = true;
+ break;
+ case 'f':
+ user_csv = optarg;
+ break;
+ case 'h':
+ usage();
+ exit(1);
+ break;
+ case 'l':
+ /* main leaf */
+ user_index = strtoul(optarg, NULL, 0);
+ break;
+ case 'r':
+ show_raw = true;
+ break;
+ case 's':
+ /* subleaf */
+ user_sub = strtoul(optarg, NULL, 0);
+ break;
+ default:
+ printf("%s: Invalid option '%c'\n", argv[0], optopt);
+ return -1;
+ }
+
+ return 0;
+}
+
+/*
+ * Do 4 things in turn:
+ * 1. Parse user options
+ * 2. Parse and store all the CPUID leaf data supported on this platform
+ * 2. Parse the csv file, while skipping leafs which are not available
+ * on this platform
+ * 3. Print leafs info based on user options
+ */
+int main(int argc, char *argv[])
+{
+ if (parse_options(argc, argv))
+ return -1;
+
+ /* Setup the cpuid leafs of current platform */
+ setup_platform_cpuid();
+
+ /* Read and parse the 'cpuid.csv' */
+ parse_text();
+
+ show_info();
+ return 0;
+}
return btf_id__add(root, id, false);
}
+/* Older libelf.h and glibc elf.h might not yet define the ELF compression types. */
+#ifndef SHF_COMPRESSED
+#define SHF_COMPRESSED (1 << 11) /* Section with compressed data. */
+#endif
+
/*
* The data of compressed section should be aligned to 4
* (for 32bit) or 8 (for 64 bit) bytes. The binutils ld
all: $(OUTPUT)fixdep
+# Make sure there's anything to clean,
+# feature contains check for existing OUTPUT
+TMP_O := $(if $(OUTPUT),$(OUTPUT)/feature,./)
+
clean:
$(call QUIET_CLEAN, fixdep)
$(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
$(Q)rm -f $(OUTPUT)fixdep
$(call QUIET_CLEAN, feature-detect)
- $(Q)$(MAKE) -C feature/ clean >/dev/null
+ifneq ($(wildcard $(TMP_O)),)
+ $(Q)$(MAKE) -C feature OUTPUT=$(TMP_O) clean >/dev/null
+endif
$(OUTPUT)fixdep-in.o: FORCE
$(Q)$(MAKE) $(build)=fixdep
cfg['nr_nodes'] = prog['nr_online_nodes'].value_()
- if prog.type('struct kmem_cache').members[1][1] == 'flags':
+ if prog.type('struct kmem_cache').members[1].name == 'flags':
cfg['allocator'] = 'SLUB'
- elif prog.type('struct kmem_cache').members[1][1] == 'batchcount':
+ elif prog.type('struct kmem_cache').members[1].name == 'batchcount':
cfg['allocator'] = 'SLAB'
else:
err('Can\'t determine the slab allocator')
# look over all slab pages, belonging to non-root memcgs
# and look for objects belonging to the given memory cgroup
for page in for_each_slab_page(prog):
- objcg_vec_raw = page.obj_cgroups.value_()
+ objcg_vec_raw = page.memcg_data.value_()
if objcg_vec_raw == 0:
continue
cache = page.slab_cache
addr = cache.value_()
caches[addr] = cache
# clear the lowest bit to get the true obj_cgroups
- objcg_vec = Object(prog, page.obj_cgroups.type_,
+ objcg_vec = Object(prog, 'struct obj_cgroup **',
value=objcg_vec_raw & ~1)
if addr not in stats:
#define CORESIGHT_ETM_PMU_NAME "cs_etm"
#define CORESIGHT_ETM_PMU_SEED 0x10
-/* ETMv3.5/PTM's ETMCR config bit */
-#define ETM_OPT_CYCACC 12
-#define ETM_OPT_CTXTID 14
-#define ETM_OPT_TS 28
-#define ETM_OPT_RETSTK 29
+/*
+ * Below are the definition of bit offsets for perf option, and works as
+ * arbitrary values for all ETM versions.
+ *
+ * Most of them are orignally from ETMv3.5/PTM's ETMCR config, therefore,
+ * ETMv3.5/PTM doesn't define ETMCR config bits with prefix "ETM3_" and
+ * directly use below macros as config bits.
+ */
+#define ETM_OPT_CYCACC 12
+#define ETM_OPT_CTXTID 14
+#define ETM_OPT_CTXTID2 15
+#define ETM_OPT_TS 28
+#define ETM_OPT_RETSTK 29
/* ETMv4 CONFIGR programming bits for the ETM OPTs */
#define ETM4_CFG_BIT_CYCACC 4
#define ETM4_CFG_BIT_CTXTID 6
+#define ETM4_CFG_BIT_VMID 7
#define ETM4_CFG_BIT_TS 11
#define ETM4_CFG_BIT_RETSTK 12
+#define ETM4_CFG_BIT_VMID_OPT 15
static inline int coresight_get_trace_id(int cpu)
{
__raw_static_call(name); \
})
+struct static_call_key {
+ void *func;
+ union {
+ /* bit 0: 0 = mods, 1 = sites */
+ unsigned long type;
+ struct static_call_mod *mods;
+ struct static_call_site *sites;
+ };
+};
+
#else /* !CONFIG_HAVE_STATIC_CALL_INLINE */
#define __STATIC_CALL_ADDRESSABLE(name)
#define __static_call(name) __raw_static_call(name)
+struct static_call_key {
+ void *func;
+};
+
#endif /* CONFIG_HAVE_STATIC_CALL_INLINE */
#ifdef MODULE
#else
+struct static_call_key {
+ void *func;
+};
+
#define static_call(name) \
((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func))
#include "../../../arch/alpha/include/uapi/asm/errno.h"
#elif defined(__mips__)
#include "../../../arch/mips/include/uapi/asm/errno.h"
-#elif defined(__ia64__)
-#include "../../../arch/ia64/include/uapi/asm/errno.h"
#elif defined(__xtensa__)
#include "../../../arch/xtensa/include/uapi/asm/errno.h"
#else
-/**
- * \file drm.h
+/*
* Header for the Direct Rendering Manager
*
- * \author Rickard E. (Rik) Faith <faith@valinux.com>
+ * Author: Rickard E. (Rik) Faith <faith@valinux.com>
*
- * \par Acknowledgments:
- * Dec 1999, Richard Henderson <rth@twiddle.net>, move to generic \c cmpxchg.
+ * Acknowledgments:
+ * Dec 1999, Richard Henderson <rth@twiddle.net>, move to generic cmpxchg.
*/
/*
typedef unsigned int drm_drawable_t;
typedef unsigned int drm_magic_t;
-/**
+/*
* Cliprect.
*
* \warning: If you change this structure, make sure you change
unsigned short y2;
};
-/**
+/*
* Drawable information.
*/
struct drm_drawable_info {
struct drm_clip_rect *rects;
};
-/**
+/*
* Texture region,
*/
struct drm_tex_region {
unsigned int age;
};
-/**
+/*
* Hardware lock.
*
* The lock structure is a simple cache-line aligned integer. To avoid
char padding[60]; /**< Pad to cache line */
};
-/**
+/*
* DRM_IOCTL_VERSION ioctl argument type.
*
* \sa drmGetVersion().
char __user *desc; /**< User-space buffer to hold desc */
};
-/**
+/*
* DRM_IOCTL_GET_UNIQUE ioctl argument type.
*
* \sa drmGetBusid() and drmSetBusId().
int unused;
};
-/**
+/*
* DRM_IOCTL_CONTROL ioctl argument type.
*
* \sa drmCtlInstHandler() and drmCtlUninstHandler().
int irq;
};
-/**
+/*
* Type of memory to map.
*/
enum drm_map_type {
_DRM_CONSISTENT = 5 /**< Consistent memory for PCI DMA */
};
-/**
+/*
* Memory mapping flags.
*/
enum drm_map_flags {
void *handle; /**< Handle of map */
};
-/**
+/*
* DRM_IOCTL_GET_MAP, DRM_IOCTL_ADD_MAP and DRM_IOCTL_RM_MAP ioctls
* argument type.
*
/* Private data */
};
-/**
+/*
* DRM_IOCTL_GET_CLIENT ioctl argument type.
*/
struct drm_client {
/* Add to the *END* of the list */
};
-/**
+/*
* DRM_IOCTL_GET_STATS ioctl argument type.
*/
struct drm_stats {
} data[15];
};
-/**
+/*
* Hardware locking flags.
*/
enum drm_lock_flags {
_DRM_HALT_CUR_QUEUES = 0x20 /**< Halt all current queues */
};
-/**
+/*
* DRM_IOCTL_LOCK, DRM_IOCTL_UNLOCK and DRM_IOCTL_FINISH ioctl argument type.
*
* \sa drmGetLock() and drmUnlock().
enum drm_lock_flags flags;
};
-/**
+/*
* DMA flags
*
* \warning
_DRM_DMA_LARGER_OK = 0x40 /**< Larger-than-requested buffers OK */
};
-/**
+/*
* DRM_IOCTL_ADD_BUFS and DRM_IOCTL_MARK_BUFS ioctl argument type.
*
* \sa drmAddBufs().
*/
};
-/**
+/*
* DRM_IOCTL_INFO_BUFS ioctl argument type.
*/
struct drm_buf_info {
struct drm_buf_desc __user *list;
};
-/**
+/*
* DRM_IOCTL_FREE_BUFS ioctl argument type.
*/
struct drm_buf_free {
int __user *list;
};
-/**
+/*
* Buffer information
*
* \sa drm_buf_map.
void __user *address; /**< Address of buffer */
};
-/**
+/*
* DRM_IOCTL_MAP_BUFS ioctl argument type.
*/
struct drm_buf_map {
struct drm_buf_pub __user *list; /**< Buffer information */
};
-/**
+/*
* DRM_IOCTL_DMA ioctl argument type.
*
* Indices here refer to the offset into the buffer list in drm_buf_get.
_DRM_CONTEXT_2DONLY = 0x02
};
-/**
+/*
* DRM_IOCTL_ADD_CTX ioctl argument type.
*
* \sa drmCreateContext() and drmDestroyContext().
enum drm_ctx_flags flags;
};
-/**
+/*
* DRM_IOCTL_RES_CTX ioctl argument type.
*/
struct drm_ctx_res {
struct drm_ctx __user *contexts;
};
-/**
+/*
* DRM_IOCTL_ADD_DRAW and DRM_IOCTL_RM_DRAW ioctl argument type.
*/
struct drm_draw {
drm_drawable_t handle;
};
-/**
+/*
* DRM_IOCTL_UPDATE_DRAW ioctl argument type.
*/
typedef enum {
unsigned long long data;
};
-/**
+/*
* DRM_IOCTL_GET_MAGIC and DRM_IOCTL_AUTH_MAGIC ioctl argument type.
*/
struct drm_auth {
drm_magic_t magic;
};
-/**
+/*
* DRM_IOCTL_IRQ_BUSID ioctl argument type.
*
* \sa drmGetInterruptFromBusID().
long tval_usec;
};
-/**
+/*
* DRM_IOCTL_WAIT_VBLANK ioctl argument type.
*
* \sa drmWaitVBlank().
#define _DRM_PRE_MODESET 1
#define _DRM_POST_MODESET 2
-/**
+/*
* DRM_IOCTL_MODESET_CTL ioctl argument type
*
* \sa drmModesetCtl().
__u32 cmd;
};
-/**
+/*
* DRM_IOCTL_AGP_ENABLE ioctl argument type.
*
* \sa drmAgpEnable().
unsigned long mode; /**< AGP mode */
};
-/**
+/*
* DRM_IOCTL_AGP_ALLOC and DRM_IOCTL_AGP_FREE ioctls argument type.
*
* \sa drmAgpAlloc() and drmAgpFree().
unsigned long physical; /**< Physical used by i810 */
};
-/**
+/*
* DRM_IOCTL_AGP_BIND and DRM_IOCTL_AGP_UNBIND ioctls argument type.
*
* \sa drmAgpBind() and drmAgpUnbind().
unsigned long offset; /**< In bytes -- will round to page boundary */
};
-/**
+/*
* DRM_IOCTL_AGP_INFO ioctl argument type.
*
* \sa drmAgpVersionMajor(), drmAgpVersionMinor(), drmAgpGetMode(),
unsigned short id_device;
};
-/**
+/*
* DRM_IOCTL_SG_ALLOC ioctl argument type.
*/
struct drm_scatter_gather {
unsigned long handle; /**< Used for mapping / unmapping */
};
-/**
+/*
* DRM_IOCTL_SET_VERSION ioctl argument type.
*/
struct drm_set_version {
int drm_dd_minor;
};
-/** DRM_IOCTL_GEM_CLOSE ioctl argument type */
+/* DRM_IOCTL_GEM_CLOSE ioctl argument type */
struct drm_gem_close {
/** Handle of the object to be closed. */
__u32 handle;
__u32 pad;
};
-/** DRM_IOCTL_GEM_FLINK ioctl argument type */
+/* DRM_IOCTL_GEM_FLINK ioctl argument type */
struct drm_gem_flink {
/** Handle for the object being named */
__u32 handle;
__u32 name;
};
-/** DRM_IOCTL_GEM_OPEN ioctl argument type */
+/* DRM_IOCTL_GEM_OPEN ioctl argument type */
struct drm_gem_open {
/** Name of object being opened */
__u32 name;
#define DRM_CAP_SYNCOBJ 0x13
#define DRM_CAP_SYNCOBJ_TIMELINE 0x14
-/** DRM_IOCTL_GET_CAP ioctl argument type */
+/* DRM_IOCTL_GET_CAP ioctl argument type */
struct drm_get_cap {
__u64 capability;
__u64 value;
/**
* DRM_CLIENT_CAP_ATOMIC
*
- * If set to 1, the DRM core will expose atomic properties to userspace
+ * If set to 1, the DRM core will expose atomic properties to userspace. This
+ * implicitly enables &DRM_CLIENT_CAP_UNIVERSAL_PLANES and
+ * &DRM_CLIENT_CAP_ASPECT_RATIO.
*/
#define DRM_CLIENT_CAP_ATOMIC 3
*/
#define DRM_CLIENT_CAP_WRITEBACK_CONNECTORS 5
-/** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
+/* DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
struct drm_set_client_cap {
__u64 capability;
__u64 value;
#define DRM_IOCTL_MODE_GETFB2 DRM_IOWR(0xCE, struct drm_mode_fb_cmd2)
-/**
+/*
* Device specific ioctls should only be in their respective headers
* The device specific ioctl range is from 0x40 to 0x9f.
* Generic IOCTLS restart at 0xA0.
#define DRM_COMMAND_BASE 0x40
#define DRM_COMMAND_END 0xA0
-/**
+/*
* Header for events written back to userspace on the drm fd. The
* type defines the type of event, the length specifies the total
* length of the event (including the header), and user_data is
#define I915_PMU_REQUESTED_FREQUENCY __I915_PMU_OTHER(1)
#define I915_PMU_INTERRUPTS __I915_PMU_OTHER(2)
#define I915_PMU_RC6_RESIDENCY __I915_PMU_OTHER(3)
+#define I915_PMU_SOFTWARE_GT_AWAKE_TIME __I915_PMU_OTHER(4)
-#define I915_PMU_LAST I915_PMU_RC6_RESIDENCY
+#define I915_PMU_LAST /* Deprecated - do not use */ I915_PMU_RC6_RESIDENCY
/* Each region is a minimum of 16k, and there are at most 255 of them.
*/
*
* long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags)
* Description
-
* Check ctx packet size against exceeding MTU of net device (based
* on *ifindex*). This helper will likely be used in combination
* with helpers that adjust/change the packet size.
} u;
};
+struct kvm_xen_exit {
+#define KVM_EXIT_XEN_HCALL 1
+ __u32 type;
+ union {
+ struct {
+ __u32 longmode;
+ __u32 cpl;
+ __u64 input;
+ __u64 result;
+ __u64 params[6];
+ } hcall;
+ } u;
+};
+
#define KVM_S390_GET_SKEYS_NONE 1
#define KVM_S390_SKEYS_MAX 1048576
#define KVM_EXIT_X86_WRMSR 30
#define KVM_EXIT_DIRTY_RING_FULL 31
#define KVM_EXIT_AP_RESET_HOLD 32
+#define KVM_EXIT_X86_BUS_LOCK 33
+#define KVM_EXIT_XEN 34
/* For KVM_EXIT_INTERNAL_ERROR */
/* Emulate instruction failed. */
__u32 index; /* kernel -> user */
__u64 data; /* kernel <-> user */
} msr;
+ /* KVM_EXIT_XEN */
+ struct kvm_xen_exit xen;
/* Fix the size of the union. */
char padding[256];
};
#define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
#define KVM_CAP_SYS_HYPERV_CPUID 191
#define KVM_CAP_DIRTY_LOG_RING 192
+#define KVM_CAP_X86_BUS_LOCK_EXIT 193
#define KVM_CAP_PPC_DAWR1 194
#ifdef KVM_CAP_IRQ_ROUTING
#endif
#ifdef KVM_CAP_XEN_HVM
+#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0)
+#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1)
+#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2)
+#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3)
+
struct kvm_xen_hvm_config {
__u32 flags;
__u32 msr;
/* Available with KVM_CAP_DIRTY_LOG_RING */
#define KVM_RESET_DIRTY_RINGS _IO(KVMIO, 0xc7)
+/* Per-VM Xen attributes */
+#define KVM_XEN_HVM_GET_ATTR _IOWR(KVMIO, 0xc8, struct kvm_xen_hvm_attr)
+#define KVM_XEN_HVM_SET_ATTR _IOW(KVMIO, 0xc9, struct kvm_xen_hvm_attr)
+
+struct kvm_xen_hvm_attr {
+ __u16 type;
+ __u16 pad[3];
+ union {
+ __u8 long_mode;
+ __u8 vector;
+ struct {
+ __u64 gfn;
+ } shared_info;
+ __u64 pad[8];
+ } u;
+};
+
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
+#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0
+#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1
+#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2
+
+/* Per-vCPU Xen attributes */
+#define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr)
+#define KVM_XEN_VCPU_SET_ATTR _IOW(KVMIO, 0xcb, struct kvm_xen_vcpu_attr)
+
+struct kvm_xen_vcpu_attr {
+ __u16 type;
+ __u16 pad[3];
+ union {
+ __u64 gpa;
+ __u64 pad[8];
+ struct {
+ __u64 state;
+ __u64 state_entry_time;
+ __u64 time_running;
+ __u64 time_runnable;
+ __u64 time_blocked;
+ __u64 time_offline;
+ } runstate;
+ } u;
+};
+
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 0x2
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4
+#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5
+
/* Secure Encrypted Virtualization command */
enum sev_cmd_id {
/* Guest initialization commands */
KVM_SEV_DBG_ENCRYPT,
/* Guest certificates commands */
KVM_SEV_CERT_EXPORT,
+ /* Attestation report */
+ KVM_SEV_GET_ATTESTATION_REPORT,
KVM_SEV_NR_MAX,
};
__u32 len;
};
+struct kvm_sev_attestation_report {
+ __u8 mnonce[16];
+ __u64 uaddr;
+ __u32 len;
+};
+
#define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0)
#define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1)
#define KVM_DEV_ASSIGN_MASK_INTX (1 << 2)
__u64 offset;
};
+#define KVM_BUS_LOCK_DETECTION_OFF (1 << 0)
+#define KVM_BUS_LOCK_DETECTION_EXIT (1 << 1)
+
#endif /* __LINUX_KVM_H */
#ifndef _UAPI_LINUX_MOUNT_H
#define _UAPI_LINUX_MOUNT_H
+#include <linux/types.h>
+
/*
* These are the fs-independent mount-flags: up to 32 flags are supported
*
#define MOUNT_ATTR_NOATIME 0x00000010 /* - Do not update access times. */
#define MOUNT_ATTR_STRICTATIME 0x00000020 /* - Always perform atime updates */
#define MOUNT_ATTR_NODIRATIME 0x00000080 /* Do not update directory access times */
+#define MOUNT_ATTR_IDMAP 0x00100000 /* Idmap mount to @userns_fd in struct mount_attr. */
+
+/*
+ * mount_setattr()
+ */
+struct mount_attr {
+ __u64 attr_set;
+ __u64 attr_clr;
+ __u64 propagation;
+ __u64 userns_fd;
+};
+
+/* List of all mount_attr versions. */
+#define MOUNT_ATTR_SIZE_VER0 32 /* sizeof first published struct */
#endif /* _UAPI_LINUX_MOUNT_H */
#define RESOLVE_IN_ROOT 0x10 /* Make all jumps to "/" and ".."
be scoped inside the dirfd
(similar to chroot(2)). */
+#define RESOLVE_CACHED 0x20 /* Only complete if resolution can be
+ completed through cached lookup. May
+ return -EAGAIN if that's not
+ possible. */
#endif /* _UAPI_LINUX_OPENAT2_H */
ExecStart=/usr/bin/kvm_stat -dtcz -s 10 -L /var/log/kvm_stat.csv
ExecReload=/bin/kill -HUP $MAINPID
Restart=always
+RestartSec=60s
SyslogIdentifier=kvm_stat
SyslogLevel=debug
if [ ! -d '$(DESTDIR_SQ)$2' ]; then \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2'; \
fi; \
- $(INSTALL) $1 $(if $3,-m $3,) '$(DESTDIR_SQ)$2'
+ $(INSTALL) $(if $3,-m $3,) $1 '$(DESTDIR_SQ)$2'
endef
install_lib: all_cmd
return err;
case BTF_KIND_ARRAY:
- return btf_dump_order_type(d, btf_array(t)->type, through_ptr);
+ return btf_dump_order_type(d, btf_array(t)->type, false);
case BTF_KIND_STRUCT:
case BTF_KIND_UNION: {
if (!elf_rawdata(elf_getscn(obj->efile.elf, obj->efile.shstrndx), NULL)) {
pr_warn("elf: failed to get section names strings from %s: %s\n",
obj->path, elf_errmsg(-1));
- return -LIBBPF_ERRNO__FORMAT;
+ err = -LIBBPF_ERRNO__FORMAT;
+ goto errout;
}
/* Old LLVM set e_machine to EM_NONE */
memset(&sa, 0, sizeof(sa));
sa.nl_family = AF_NETLINK;
- sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+ sock = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, NETLINK_ROUTE);
if (sock < 0)
return -errno;
if ((len & BPF_RINGBUF_DISCARD_BIT) == 0) {
sample = (void *)len_ptr + BPF_RINGBUF_HDR_SZ;
err = r->sample_cb(r->ctx, sample, len);
- if (err) {
+ if (err < 0) {
/* update consumer pos and bail out */
smp_store_release(r->consumer_pos,
cons_pos);
int fd;
int refcount;
struct list_head ctx_list;
+ bool rx_ring_setup_done;
+ bool tx_ring_setup_done;
};
struct xsk_ctx {
if (fd < 0)
continue;
+ memset(&map_info, 0, map_len);
err = bpf_obj_get_info_by_fd(fd, &map_info, &map_len);
if (err) {
close(fd);
continue;
}
- if (!strcmp(map_info.name, "xsks_map")) {
+ if (!strncmp(map_info.name, "xsks_map", sizeof(map_info.name))) {
ctx->xsks_map_fd = fd;
- continue;
+ break;
}
close(fd);
return NULL;
}
-static void xsk_put_ctx(struct xsk_ctx *ctx)
+static void xsk_put_ctx(struct xsk_ctx *ctx, bool unmap)
{
struct xsk_umem *umem = ctx->umem;
struct xdp_mmap_offsets off;
int err;
- if (--ctx->refcount == 0) {
- err = xsk_get_mmap_offsets(umem->fd, &off);
- if (!err) {
- munmap(ctx->fill->ring - off.fr.desc,
- off.fr.desc + umem->config.fill_size *
- sizeof(__u64));
- munmap(ctx->comp->ring - off.cr.desc,
- off.cr.desc + umem->config.comp_size *
- sizeof(__u64));
- }
+ if (--ctx->refcount)
+ return;
- list_del(&ctx->list);
- free(ctx);
- }
+ if (!unmap)
+ goto out_free;
+
+ err = xsk_get_mmap_offsets(umem->fd, &off);
+ if (err)
+ goto out_free;
+
+ munmap(ctx->fill->ring - off.fr.desc, off.fr.desc + umem->config.fill_size *
+ sizeof(__u64));
+ munmap(ctx->comp->ring - off.cr.desc, off.cr.desc + umem->config.comp_size *
+ sizeof(__u64));
+
+out_free:
+ list_del(&ctx->list);
+ free(ctx);
}
static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk,
memcpy(ctx->ifname, ifname, IFNAMSIZ - 1);
ctx->ifname[IFNAMSIZ - 1] = '\0';
- umem->fill_save = NULL;
- umem->comp_save = NULL;
ctx->fill = fill;
ctx->comp = comp;
list_add(&ctx->list, &umem->ctx_list);
struct xsk_ring_cons *comp,
const struct xsk_socket_config *usr_config)
{
+ bool unmap, rx_setup_done = false, tx_setup_done = false;
void *rx_map = NULL, *tx_map = NULL;
struct sockaddr_xdp sxdp = {};
struct xdp_mmap_offsets off;
if (!umem || !xsk_ptr || !(rx || tx))
return -EFAULT;
+ unmap = umem->fill_save != fill;
+
xsk = calloc(1, sizeof(*xsk));
if (!xsk)
return -ENOMEM;
}
} else {
xsk->fd = umem->fd;
+ rx_setup_done = umem->rx_ring_setup_done;
+ tx_setup_done = umem->tx_ring_setup_done;
}
ctx = xsk_get_ctx(umem, ifindex, queue_id);
}
xsk->ctx = ctx;
- if (rx) {
+ if (rx && !rx_setup_done) {
err = setsockopt(xsk->fd, SOL_XDP, XDP_RX_RING,
&xsk->config.rx_size,
sizeof(xsk->config.rx_size));
err = -errno;
goto out_put_ctx;
}
+ if (xsk->fd == umem->fd)
+ umem->rx_ring_setup_done = true;
}
- if (tx) {
+ if (tx && !tx_setup_done) {
err = setsockopt(xsk->fd, SOL_XDP, XDP_TX_RING,
&xsk->config.tx_size,
sizeof(xsk->config.tx_size));
err = -errno;
goto out_put_ctx;
}
+ if (xsk->fd == umem->fd)
+ umem->rx_ring_setup_done = true;
}
err = xsk_get_mmap_offsets(xsk->fd, &off);
}
*xsk_ptr = xsk;
+ umem->fill_save = NULL;
+ umem->comp_save = NULL;
return 0;
out_mmap_tx:
munmap(rx_map, off.rx.desc +
xsk->config.rx_size * sizeof(struct xdp_desc));
out_put_ctx:
- xsk_put_ctx(ctx);
+ xsk_put_ctx(ctx, unmap);
out_socket:
if (--umem->refcount)
close(xsk->fd);
struct xsk_ring_cons *rx, struct xsk_ring_prod *tx,
const struct xsk_socket_config *usr_config)
{
+ if (!umem)
+ return -EFAULT;
+
return xsk_socket__create_shared(xsk_ptr, ifname, queue_id, umem,
rx, tx, umem->fill_save,
umem->comp_save, usr_config);
}
}
- xsk_put_ctx(ctx);
+ xsk_put_ctx(ctx, true);
umem->refcount--;
/* Do not close an fd that also has an associated umem connected
void perf_evlist__init(struct perf_evlist *evlist)
{
- int i;
-
- for (i = 0; i < PERF_EVLIST__HLIST_SIZE; ++i)
- INIT_HLIST_HEAD(&evlist->heads[i]);
INIT_LIST_HEAD(&evlist->entries);
evlist->nr_entries = 0;
fdarray__init(&evlist->pollfd, 64);
+ perf_evlist__reset_id_hash(evlist);
}
static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
hlist_add_head(&sid->node, &evlist->heads[hash]);
}
+void perf_evlist__reset_id_hash(struct perf_evlist *evlist)
+{
+ int i;
+
+ for (i = 0; i < PERF_EVLIST__HLIST_SIZE; ++i)
+ INIT_HLIST_HEAD(&evlist->heads[i]);
+}
+
void perf_evlist__id_add(struct perf_evlist *evlist,
struct perf_evsel *evsel,
int cpu, int thread, u64 id)
struct perf_evsel *evsel,
int cpu, int thread, int fd);
+void perf_evlist__reset_id_hash(struct perf_evlist *evlist);
+
#endif /* __LIBPERF_INTERNAL_EVLIST_H */
if (update_cfi_state(insn, &state->cfi, op))
return 1;
+ if (!insn->alt_group)
+ continue;
+
if (op->dest.type == OP_DEST_PUSHF) {
if (!state->uaccess_stack) {
state->uaccess_stack = 1;
Show just the sample frequency used for each event.
-v::
---verbose=::
+--verbose::
Show all fields.
-g::
specified: function_graph or function.
-v::
---verbose=::
- Verbosity level.
+--verbose::
+ Increase the verbosity level.
-F::
--funcs::
OPTIONS
-------
-v::
---verbose=::
+--verbose::
Increase verbosity level, showing details about symbol table loading, etc.
Filter out events for these pids and for 'trace' itself (comma separated list).
-v::
---verbose=::
- Verbosity level.
+--verbose::
+ Increase the verbosity level.
--no-inherit::
Child tasks do not inherit counters.
arch_errno_tbl := $(srctree)/tools/perf/trace/beauty/arch_errno_names.sh
$(arch_errno_name_array): $(arch_errno_tbl)
- $(Q)$(SHELL) '$(arch_errno_tbl)' $(firstword $(CC)) $(arch_errno_hdr_dir) > $@
+ $(Q)$(SHELL) '$(arch_errno_tbl)' '$(patsubst -%,,$(CC))' $(arch_errno_hdr_dir) > $@
sync_file_range_arrays := $(beauty_outdir)/sync_file_range_arrays.c
sync_file_range_tbls := $(srctree)/tools/perf/trace/beauty/sync_file_range.sh
### Cleaning rules
-#
-# This is here, not in Makefile.config, because Makefile.config does
-# not get included for the clean target:
-#
-config-clean:
- $(call QUIET_CLEAN, config)
- $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ $(if $(OUTPUT),OUTPUT=$(OUTPUT)feature/,) clean >/dev/null
-
python-clean:
$(python-clean)
bpf-skel-clean:
$(call QUIET_CLEAN, bpf-skel) $(RM) -r $(SKEL_TMP_OUT) $(SKELETONS)
-clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBPERF)-clean config-clean fixdep-clean python-clean bpf-skel-clean
+clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBPERF)-clean fixdep-clean python-clean bpf-skel-clean
$(call QUIET_CLEAN, core-objs) $(RM) $(LIBPERF_A) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS)
$(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
$(Q)$(RM) $(OUTPUT).config-detected
return err;
}
+#define ETM_SET_OPT_CTXTID (1 << 0)
+#define ETM_SET_OPT_TS (1 << 1)
+#define ETM_SET_OPT_MASK (ETM_SET_OPT_CTXTID | ETM_SET_OPT_TS)
+
static int cs_etm_set_option(struct auxtrace_record *itr,
struct evsel *evsel, u32 option)
{
!cpu_map__has(online_cpus, i))
continue;
- if (option & ETM_OPT_CTXTID) {
+ if (option & ETM_SET_OPT_CTXTID) {
err = cs_etm_set_context_id(itr, evsel, i);
if (err)
goto out;
}
- if (option & ETM_OPT_TS) {
+ if (option & ETM_SET_OPT_TS) {
err = cs_etm_set_timestamp(itr, evsel, i);
if (err)
goto out;
}
- if (option & ~(ETM_OPT_CTXTID | ETM_OPT_TS))
+ if (option & ~(ETM_SET_OPT_MASK))
/* Nothing else is currently supported */
goto out;
}
evsel__set_sample_bit(cs_etm_evsel, CPU);
err = cs_etm_set_option(itr, cs_etm_evsel,
- ETM_OPT_CTXTID | ETM_OPT_TS);
+ ETM_SET_OPT_CTXTID | ETM_SET_OPT_TS);
if (err)
goto out;
}
#
0 nospu restart_syscall sys_restart_syscall
1 nospu exit sys_exit
-2 32 fork ppc_fork sys_fork
-2 64 fork sys_fork
-2 spu fork sys_ni_syscall
+2 nospu fork sys_fork
3 common read sys_read
4 common write sys_write
5 common open sys_open compat_sys_open
119 32 sigreturn sys_sigreturn compat_sys_sigreturn
119 64 sigreturn sys_ni_syscall
119 spu sigreturn sys_ni_syscall
-120 32 clone ppc_clone sys_clone
-120 64 clone sys_clone
-120 spu clone sys_ni_syscall
+120 nospu clone sys_clone
121 common setdomainname sys_setdomainname
122 common uname sys_newuname
123 common modify_ldt sys_ni_syscall
186 spu sendfile sys_sendfile64
187 common getpmsg sys_ni_syscall
188 common putpmsg sys_ni_syscall
-189 32 vfork ppc_vfork sys_vfork
-189 64 vfork sys_vfork
-189 spu vfork sys_ni_syscall
+189 nospu vfork sys_vfork
190 common ugetrlimit sys_getrlimit compat_sys_getrlimit
191 common readahead sys_readahead compat_sys_readahead
192 32 mmap2 sys_mmap2 compat_sys_mmap2
248 32 clock_nanosleep sys_clock_nanosleep_time32
248 64 clock_nanosleep sys_clock_nanosleep
248 spu clock_nanosleep sys_clock_nanosleep
-249 32 swapcontext ppc_swapcontext compat_sys_swapcontext
-249 64 swapcontext sys_swapcontext
-249 spu swapcontext sys_ni_syscall
+249 nospu swapcontext sys_swapcontext compat_sys_swapcontext
250 common tgkill sys_tgkill
251 32 utimes sys_utimes_time32
251 64 utimes sys_utimes
432 common fsmount sys_fsmount
433 common fspick sys_fspick
434 common pidfd_open sys_pidfd_open
-435 32 clone3 ppc_clone3 sys_clone3
-435 64 clone3 sys_clone3
-435 spu clone3 sys_ni_syscall
+435 nospu clone3 sys_clone3
436 common close_range sys_close_range
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
439 common faccessat2 sys_faccessat2
440 common process_madvise sys_process_madvise
441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2
+442 common mount_setattr sys_mount_setattr
439 common faccessat2 sys_faccessat2 sys_faccessat2
440 common process_madvise sys_process_madvise sys_process_madvise
441 common epoll_pwait2 sys_epoll_pwait2 compat_sys_epoll_pwait2
+442 common mount_setattr sys_mount_setattr sys_mount_setattr
# Syscall table generation
#
-out := $(OUTPUT)arch/x86/include/generated/asm
-header := $(out)/syscalls_64.c
-sys := $(srctree)/tools/perf/arch/x86/entry/syscalls
-systbl := $(sys)/syscalltbl.sh
+generated := $(OUTPUT)arch/x86/include/generated
+out := $(generated)/asm
+header := $(out)/syscalls_64.c
+sys := $(srctree)/tools/perf/arch/x86/entry/syscalls
+systbl := $(sys)/syscalltbl.sh
# Create output directory if not already present
_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
$(Q)$(SHELL) '$(systbl)' $(sys)/syscall_64.tbl 'x86_64' > $@
clean::
- $(call QUIET_CLEAN, x86) $(RM) $(header)
+ $(call QUIET_CLEAN, x86) $(RM) -r $(header) $(generated)
archheaders: $(header)
439 common faccessat2 sys_faccessat2
440 common process_madvise sys_process_madvise
441 common epoll_pwait2 sys_epoll_pwait2
+442 common mount_setattr sys_mount_setattr
#
# Due to a historical design error, certain syscalls are numbered differently
int test__insn_x86(struct test *test __maybe_unused, int subtest);
int test__intel_pt_pkt_decoder(struct test *test, int subtest);
int test__bp_modify(struct test *test, int subtest);
+int test__x86_sample_parsing(struct test *test, int subtest);
#ifdef HAVE_DWARF_UNWIND_SUPPORT
struct thread;
perf-y += arch-tests.o
perf-y += rdpmc.o
+perf-y += sample-parsing.o
perf-$(CONFIG_AUXTRACE) += insn-x86.o intel-pt-pkt-decoder-test.o
perf-$(CONFIG_X86_64) += bp-modify.o
},
#endif
{
+ .desc = "x86 Sample parsing",
+ .func = test__x86_sample_parsing,
+ },
+ {
.func = NULL,
},
// SPDX-License-Identifier: GPL-2.0
#include <linux/types.h>
-#include "../../../../arch/x86/include/asm/insn.h"
#include <string.h>
#include "debug.h"
#include "tests/tests.h"
#include "arch-tests.h"
+#include "../../../../arch/x86/include/asm/insn.h"
#include "intel-pt-decoder/intel-pt-insn-decoder.h"
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+#include <stdbool.h>
+#include <inttypes.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+#include "event.h"
+#include "evsel.h"
+#include "debug.h"
+#include "util/synthetic-events.h"
+
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+#define COMP(m) do { \
+ if (s1->m != s2->m) { \
+ pr_debug("Samples differ at '"#m"'\n"); \
+ return false; \
+ } \
+} while (0)
+
+static bool samples_same(const struct perf_sample *s1,
+ const struct perf_sample *s2,
+ u64 type)
+{
+ if (type & PERF_SAMPLE_WEIGHT_STRUCT)
+ COMP(ins_lat);
+
+ return true;
+}
+
+static int do_test(u64 sample_type)
+{
+ struct evsel evsel = {
+ .needs_swap = false,
+ .core = {
+ . attr = {
+ .sample_type = sample_type,
+ .read_format = 0,
+ },
+ },
+ };
+ union perf_event *event;
+ struct perf_sample sample = {
+ .weight = 101,
+ .ins_lat = 102,
+ };
+ struct perf_sample sample_out;
+ size_t i, sz, bufsz;
+ int err, ret = -1;
+
+ sz = perf_event__sample_event_size(&sample, sample_type, 0);
+ bufsz = sz + 4096; /* Add a bit for overrun checking */
+ event = malloc(bufsz);
+ if (!event) {
+ pr_debug("malloc failed\n");
+ return -1;
+ }
+
+ memset(event, 0xff, bufsz);
+ event->header.type = PERF_RECORD_SAMPLE;
+ event->header.misc = 0;
+ event->header.size = sz;
+
+ err = perf_event__synthesize_sample(event, sample_type, 0, &sample);
+ if (err) {
+ pr_debug("%s failed for sample_type %#"PRIx64", error %d\n",
+ "perf_event__synthesize_sample", sample_type, err);
+ goto out_free;
+ }
+
+ /* The data does not contain 0xff so we use that to check the size */
+ for (i = bufsz; i > 0; i--) {
+ if (*(i - 1 + (u8 *)event) != 0xff)
+ break;
+ }
+ if (i != sz) {
+ pr_debug("Event size mismatch: actual %zu vs expected %zu\n",
+ i, sz);
+ goto out_free;
+ }
+
+ evsel.sample_size = __evsel__sample_size(sample_type);
+
+ err = evsel__parse_sample(&evsel, event, &sample_out);
+ if (err) {
+ pr_debug("%s failed for sample_type %#"PRIx64", error %d\n",
+ "evsel__parse_sample", sample_type, err);
+ goto out_free;
+ }
+
+ if (!samples_same(&sample, &sample_out, sample_type)) {
+ pr_debug("parsing failed for sample_type %#"PRIx64"\n",
+ sample_type);
+ goto out_free;
+ }
+
+ ret = 0;
+out_free:
+ free(event);
+
+ return ret;
+}
+
+/**
+ * test__x86_sample_parsing - test X86 specific sample parsing
+ *
+ * This function implements a test that synthesizes a sample event, parses it
+ * and then checks that the parsed sample matches the original sample. If the
+ * test passes %0 is returned, otherwise %-1 is returned.
+ *
+ * For now, the PERF_SAMPLE_WEIGHT_STRUCT is the only X86 specific sample type.
+ * The test only checks the PERF_SAMPLE_WEIGHT_STRUCT type.
+ */
+int test__x86_sample_parsing(struct test *test __maybe_unused, int subtest __maybe_unused)
+{
+ return do_test(PERF_SAMPLE_WEIGHT_STRUCT);
+}
// SPDX-License-Identifier: GPL-2.0
-#include "../../../../arch/x86/include/asm/insn.h"
#include "archinsn.h"
#include "event.h"
#include "machine.h"
#include "thread.h"
#include "symbol.h"
+#include "../../../../arch/x86/include/asm/insn.h"
void arch_fetch_insn(struct perf_sample *sample,
struct thread *thread,
static void bind_to_memnode(int node)
{
- unsigned long nodemask;
+ struct bitmask *node_mask;
int ret;
if (node == NUMA_NO_NODE)
return;
- BUG_ON(g->p.nr_nodes > (int)sizeof(nodemask)*8);
- nodemask = 1L << node;
+ node_mask = numa_allocate_nodemask();
+ BUG_ON(!node_mask);
- ret = set_mempolicy(MPOL_BIND, &nodemask, sizeof(nodemask)*8);
- dprintf("binding to node %d, mask: %016lx => %d\n", node, nodemask, ret);
+ numa_bitmask_clearall(node_mask);
+ numa_bitmask_setbit(node_mask, node);
+ ret = set_mempolicy(MPOL_BIND, node_mask->maskp, node_mask->size + 1);
+ dprintf("binding to node %d, mask: %016lx => %d\n", node, *node_mask->maskp, ret);
+
+ numa_bitmask_free(node_mask);
BUG_ON(ret);
}
prctl(0, bytes_worked);
}
-#define MAX_NR_NODES 64
-
/*
* Count the number of nodes a process's threads
* are spread out on.
*/
static int count_process_nodes(int process_nr)
{
- char node_present[MAX_NR_NODES] = { 0, };
+ char *node_present;
int nodes;
int n, t;
+ node_present = (char *)malloc(g->p.nr_nodes * sizeof(char));
+ BUG_ON(!node_present);
+ for (nodes = 0; nodes < g->p.nr_nodes; nodes++)
+ node_present[nodes] = 0;
+
for (t = 0; t < g->p.nr_threads; t++) {
struct thread_data *td;
int task_nr;
td = g->threads + task_nr;
node = numa_node_of_cpu(td->curr_cpu);
- if (node < 0) /* curr_cpu was likely still -1 */
+ if (node < 0) /* curr_cpu was likely still -1 */ {
+ free(node_present);
return 0;
+ }
node_present[node] = 1;
}
nodes = 0;
- for (n = 0; n < MAX_NR_NODES; n++)
+ for (n = 0; n < g->p.nr_nodes; n++)
nodes += node_present[n];
+ free(node_present);
return nodes;
}
{
unsigned int loops_done_min, loops_done_max;
int process_groups;
- int nodes[MAX_NR_NODES];
+ int *nodes;
int distance;
int nr_min;
int nr_max;
if (!g->p.show_convergence && !g->p.measure_convergence)
return;
+ nodes = (int *)malloc(g->p.nr_nodes * sizeof(int));
+ BUG_ON(!nodes);
for (node = 0; node < g->p.nr_nodes; node++)
nodes[node] = 0;
BUG_ON(sum > g->p.nr_tasks);
- if (0 && (sum < g->p.nr_tasks))
+ if (0 && (sum < g->p.nr_tasks)) {
+ free(nodes);
return;
+ }
/*
* Count the number of distinct process groups present
}
tprintf("\n");
}
+
+ free(nodes);
}
static void show_summary(double runtime_ns_max, int l, double *convergence)
g->p.nr_nodes = numa_max_node() + 1;
/* char array in count_process_nodes(): */
- BUG_ON(g->p.nr_nodes > MAX_NR_NODES || g->p.nr_nodes < 0);
+ BUG_ON(g->p.nr_nodes < 0);
if (g->p.show_quiet && !g->p.show_details)
g->p.show_details = -1;
num_groups, num_groups * 2 * num_fds,
thread_mode ? "threads" : "processes");
printf(" %14s: %lu.%03lu [sec]\n", "Total time",
- diff.tv_sec,
+ (unsigned long) diff.tv_sec,
(unsigned long) (diff.tv_usec / USEC_PER_MSEC));
break;
case BENCH_FORMAT_SIMPLE:
- printf("%lu.%03lu\n", diff.tv_sec,
+ printf("%lu.%03lu\n", (unsigned long) diff.tv_sec,
(unsigned long) (diff.tv_usec / USEC_PER_MSEC));
break;
default:
result_usec += diff.tv_usec;
printf(" %14s: %lu.%03lu [sec]\n\n", "Total time",
- diff.tv_sec,
+ (unsigned long) diff.tv_sec,
(unsigned long) (diff.tv_usec / USEC_PER_MSEC));
printf(" %14lf usecs/op\n",
case BENCH_FORMAT_SIMPLE:
printf("%lu.%03lu\n",
- diff.tv_sec,
+ (unsigned long) diff.tv_sec,
(unsigned long) (diff.tv_usec / USEC_PER_MSEC));
break;
result_usec += diff.tv_usec;
printf(" %14s: %lu.%03lu [sec]\n\n", "Total time",
- diff.tv_sec,
+ (unsigned long) diff.tv_sec,
(unsigned long) (diff.tv_usec/1000));
printf(" %14lf usecs/op\n",
case BENCH_FORMAT_SIMPLE:
printf("%lu.%03lu\n",
- diff.tv_sec,
+ (unsigned long) diff.tv_sec,
(unsigned long) (diff.tv_usec / 1000));
break;
struct daemon_session *session;
char name[100];
- if (get_session_name(var, name, sizeof(name)))
+ if (get_session_name(var, name, sizeof(name) - 1))
return -EINVAL;
var = strchr(var, '.');
dup2(fd, 2);
close(fd);
- if (mkfifo(SESSION_CONTROL, O_RDWR) && errno != EEXIST) {
+ if (mkfifo(SESSION_CONTROL, 0600) && errno != EEXIST) {
perror("failed: create control fifo");
return -1;
}
- if (mkfifo(SESSION_ACK, O_RDWR) && errno != EEXIST) {
+ if (mkfifo(SESSION_ACK, 0600) && errno != EEXIST) {
perror("failed: create ack fifo");
return -1;
}
int status;
pid_t pid;
+ /*
+ * Take signal fd data as pure signal notification and check all
+ * the sessions state. The reason is that multiple signals can get
+ * coalesced in kernel and we can receive only single signal even
+ * if multiple SIGCHLD were generated.
+ */
err = read(daemon->signal_fd, &si, sizeof(struct signalfd_siginfo));
- if (err != sizeof(struct signalfd_siginfo))
+ if (err != sizeof(struct signalfd_siginfo)) {
+ pr_err("failed to read signal fd\n");
return -1;
+ }
list_for_each_entry(session, &daemon->sessions, list) {
+ if (session->pid == -1)
+ continue;
- if (session->pid != (int) si.ssi_pid)
+ pid = waitpid(session->pid, &status, WNOHANG);
+ if (pid <= 0)
continue;
- pid = waitpid(session->pid, &status, 0);
- if (pid == session->pid) {
- if (WIFEXITED(status)) {
- pr_info("session '%s' exited, status=%d\n",
- session->name, WEXITSTATUS(status));
- } else if (WIFSIGNALED(status)) {
- pr_info("session '%s' killed (signal %d)\n",
- session->name, WTERMSIG(status));
- } else if (WIFSTOPPED(status)) {
- pr_info("session '%s' stopped (signal %d)\n",
- session->name, WSTOPSIG(status));
- } else {
- pr_info("session '%s' Unexpected status (0x%x)\n",
- session->name, status);
- }
+ if (WIFEXITED(status)) {
+ pr_info("session '%s' exited, status=%d\n",
+ session->name, WEXITSTATUS(status));
+ } else if (WIFSIGNALED(status)) {
+ pr_info("session '%s' killed (signal %d)\n",
+ session->name, WTERMSIG(status));
+ } else if (WIFSTOPPED(status)) {
+ pr_info("session '%s' stopped (signal %d)\n",
+ session->name, WSTOPSIG(status));
+ } else {
+ pr_info("session '%s' Unexpected status (0x%x)\n",
+ session->name, status);
}
session->state = KILL;
session->pid = -1;
- return pid;
}
return 0;
.fd = daemon->signal_fd,
.events = POLLIN,
};
- pid_t wpid = 0, pid = session->pid;
time_t start;
start = time(NULL);
int err = poll(&pollfd, 1, 1000);
if (err > 0) {
- wpid = handle_signalfd(daemon);
+ handle_signalfd(daemon);
} else if (err < 0) {
perror("failed: poll\n");
return -1;
if (start + secs < time(NULL))
return -1;
- } while (wpid != pid);
+ } while (session->pid != -1);
return 0;
}
daemon_session__signal(session, SIGKILL);
break;
default:
- break;
+ pr_err("failed to wait for session %s\n",
+ session->name);
+ return;
}
how++;
daemon__signal(daemon, SIGKILL);
break;
default:
- break;
+ pr_err("failed to wait for sessions\n");
+ return;
}
how++;
close(sock_fd);
if (conf_fd != -1)
close(conf_fd);
- if (conf_fd != -1)
+ if (signal_fd != -1)
close(signal_fd);
pr_info("daemon exited\n");
out_delete:
data__for_each_file(i, d) {
- perf_session__delete(d->session);
+ if (!IS_ERR(d->session))
+ perf_session__delete(d->session);
data__free(d);
}
for (i = 0; i < perf_thread_map__nr(ftrace->evlist->core.threads); i++) {
scnprintf(buf, sizeof(buf), "%d",
- ftrace->evlist->core.threads->map[i]);
+ perf_thread_map__pid(ftrace->evlist->core.threads, i));
if (append_tracing_file("set_ftrace_pid", buf) < 0)
return -1;
}
}
data.path = inject.input_name;
- inject.session = perf_session__new(&data, true, &inject.tool);
+ inject.session = perf_session__new(&data, inject.output.is_pipe, &inject.tool);
if (IS_ERR(inject.session))
return PTR_ERR(inject.session);
evlist__config(evlist, &trace->opts, &callchain_param);
- signal(SIGCHLD, sig_handler);
- signal(SIGINT, sig_handler);
-
if (forks) {
err = evlist__prepare_workload(evlist, &trace->opts.target, argv, false, NULL);
if (err < 0) {
signal(SIGSEGV, sighandler_dump_stack);
signal(SIGFPE, sighandler_dump_stack);
+ signal(SIGCHLD, sig_handler);
+ signal(SIGINT, sig_handler);
trace.evlist = evlist__new();
trace.sctbl = syscalltbl__new();
fi
BUILDIDS=$(mktemp /tmp/perf-archive-buildids.XXXXXX)
-NOBUILDID=0000000000000000000000000000000000000000
-perf buildid-list -i $PERF_DATA --with-hits | grep -v "^$NOBUILDID " > $BUILDIDS
+perf buildid-list -i $PERF_DATA --with-hits | grep -v "^ " > $BUILDIDS
if [ ! -s $BUILDIDS ] ; then
echo "perf archive: no build-ids found"
rm $BUILDIDS || true
struct stat st;
char path_perf[PATH_MAX];
char path_dir[PATH_MAX];
+ char *exec_path;
/* First try development tree tests. */
if (!lstat("./tests", &st))
return run_dir("./tests", "./perf");
+ exec_path = get_argv_exec_path();
+ if (exec_path == NULL)
+ return -1;
+
/* Then installed path. */
- snprintf(path_dir, PATH_MAX, "%s/tests", get_argv_exec_path());
+ snprintf(path_dir, PATH_MAX, "%s/tests", exec_path);
snprintf(path_perf, PATH_MAX, "%s/perf", BINDIR);
+ free(exec_path);
if (!lstat(path_dir, &st) &&
!lstat(path_perf, &st))
.msg_load_fail = "check your vmlinux setting?",
.target_func = &epoll_pwait_loop,
.expect_result = (NR_ITERS + 1) / 2,
- .pin = true,
+ .pin = true,
},
#ifdef HAVE_BPF_PROLOGUE
{
.expect_result = (NR_ITERS + 1) / 4,
},
#endif
- {
- .prog_id = LLVM_TESTCASE_BPF_RELOCATION,
- .desc = "BPF relocation checker",
- .name = "[bpf_relocation_test]",
- .msg_compile_fail = "fix 'perf test LLVM' first",
- .msg_load_fail = "libbpf error when dealing with relocation",
- },
};
static int do_test(struct bpf_object *obj, int (*func)(void),
out_put:
thread__put(thread);
out_err:
-
- if (evlist) {
- evlist__delete(evlist);
- } else {
- perf_cpu_map__put(cpus);
- perf_thread_map__put(threads);
- }
+ evlist__delete(evlist);
+ perf_cpu_map__put(cpus);
+ perf_thread_map__put(threads);
machine__delete_threads(machine);
machine__delete(machine);
return -1;
cpu_map__snprint(map, buf, sizeof(buf));
+ perf_cpu_map__put(map);
+
return !strcmp(buf, str);
}
if (evlist) {
evlist__disable(evlist);
evlist__delete(evlist);
- } else {
- perf_cpu_map__put(cpus);
- perf_thread_map__put(threads);
}
+ perf_cpu_map__put(cpus);
+ perf_thread_map__put(threads);
return err;
}
out_delete_evlist:
evlist__delete(evlist);
- cpus = NULL;
- threads = NULL;
out_free_cpus:
perf_cpu_map__put(cpus);
out_free_threads:
out_err:
evlist__delete(evlist);
+ perf_cpu_map__put(cpus);
+ perf_thread_map__put(threads);
return err;
}
if (type & PERF_SAMPLE_WEIGHT)
COMP(weight);
- if (type & PERF_SAMPLE_WEIGHT_STRUCT)
- COMP(ins_lat);
-
if (type & PERF_SAMPLE_DATA_SRC)
COMP(data_src);
.cgroup = 114,
.data_page_size = 115,
.code_page_size = 116,
- .ins_lat = 117,
.aux_sample = {
.size = sizeof(aux_data),
.data = (void *)aux_data,
-#!/bin/sh
+#!/bin/bash
# daemon operations
# SPDX-License-Identifier: GPL-2.0
base=BASE
[session-size]
-run = -e cpu-clock
+run = -e cpu-clock -m 1 sleep 10
[session-time]
-run = -e task-clock
+run = -e task-clock -m 1 sleep 10
EOF
sed -i -e "s|BASE|${base}|" ${config}
# check 1st session
# pid:size:-e cpu-clock:base/size:base/size/output:base/size/control:base/size/ack:0
local line=`perf daemon --config ${config} -x: | head -2 | tail -1`
- check_line_other "${line}" size "-e cpu-clock" ${base}/session-size \
+ check_line_other "${line}" size "-e cpu-clock -m 1 sleep 10" ${base}/session-size \
${base}/session-size/output ${base}/session-size/control \
${base}/session-size/ack "0"
# check 2nd session
# pid:time:-e task-clock:base/time:base/time/output:base/time/control:base/time/ack:0
local line=`perf daemon --config ${config} -x: | head -3 | tail -1`
- check_line_other "${line}" time "-e task-clock" ${base}/session-time \
+ check_line_other "${line}" time "-e task-clock -m 1 sleep 10" ${base}/session-time \
${base}/session-time/output ${base}/session-time/control \
${base}/session-time/ack "0"
base=BASE
[session-size]
-run = -e cpu-clock
+run = -e cpu-clock -m 1 sleep 10
[session-time]
-run = -e task-clock
+run = -e task-clock -m 1 sleep 10
EOF
sed -i -e "s|BASE|${base}|" ${config}
# check 2nd session
# pid:time:-e task-clock:base/time:base/time/output:base/time/control:base/time/ack:0
local line=`perf daemon --config ${config} -x: | head -3 | tail -1`
- check_line_other "${line}" time "-e task-clock" ${base}/session-time \
+ check_line_other "${line}" time "-e task-clock -m 1 sleep 10" ${base}/session-time \
${base}/session-time/output ${base}/session-time/control ${base}/session-time/ack "0"
local pid=`echo "${line}" | awk 'BEGIN { FS = ":" } ; { print $1 }'`
base=BASE
[session-size]
-run = -e cpu-clock
+run = -e cpu-clock -m 1 sleep 10
[session-time]
-run = -e cpu-clock
+run = -e cpu-clock -m 1 sleep 10
EOF
# TEST 1 - change config
# check reconfigured 2nd session
# pid:time:-e task-clock:base/time:base/time/output:base/time/control:base/time/ack:0
local line=`perf daemon --config ${config} -x: | head -3 | tail -1`
- check_line_other "${line}" time "-e cpu-clock" ${base}/session-time \
+ check_line_other "${line}" time "-e cpu-clock -m 1 sleep 10" ${base}/session-time \
${base}/session-time/output ${base}/session-time/control ${base}/session-time/ack "0"
# TEST 2 - empty config
base=BASE
[session-size]
-run = -e cpu-clock
+run = -e cpu-clock -m 1 sleep 10
[session-time]
-run = -e task-clock
+run = -e task-clock -m 1 sleep 10
EOF
sed -i -e "s|BASE|${base}|" ${config}
base=BASE
[session-test]
-run = -e cpu-clock --switch-output
+run = -e cpu-clock --switch-output -m 1 sleep 10
EOF
sed -i -e "s|BASE|${base}|" ${config}
base=BASE
[session-size]
-run = -e cpu-clock
+run = -e cpu-clock -m 1 sleep 10
[session-time]
-run = -e task-clock
+run = -e task-clock -m 1 sleep 10
EOF
sed -i -e "s|BASE|${base}|" ${config}
base=BASE
[session-size]
-run = -e cpu-clock
+run = -e cpu-clock -m 1 sleep 10
EOF
sed -i -e "s|BASE|${base}|" ${config}
.disabled = 1,
.freq = 1,
};
- struct perf_cpu_map *cpus;
- struct perf_thread_map *threads;
+ struct perf_cpu_map *cpus = NULL;
+ struct perf_thread_map *threads = NULL;
struct mmap *md;
attr.sample_freq = 500;
if (!cpus || !threads) {
err = -ENOMEM;
pr_debug("Not enough memory to create thread/cpu maps\n");
- goto out_free_maps;
+ goto out_delete_evlist;
}
perf_evlist__set_maps(&evlist->core, cpus, threads);
- cpus = NULL;
- threads = NULL;
-
if (evlist__open(evlist)) {
const char *knob = "/proc/sys/kernel/perf_event_max_sample_rate";
err = -1;
}
-out_free_maps:
+out_delete_evlist:
perf_cpu_map__put(cpus);
perf_thread_map__put(threads);
-out_delete_evlist:
evlist__delete(evlist);
return err;
}
if (evlist) {
evlist__disable(evlist);
evlist__delete(evlist);
- } else {
- perf_cpu_map__put(cpus);
- perf_thread_map__put(threads);
}
+ perf_cpu_map__put(cpus);
+ perf_thread_map__put(threads);
return err;
if (!cpus || !threads) {
err = -ENOMEM;
pr_debug("Not enough memory to create thread/cpu maps\n");
- goto out_free_maps;
+ goto out_delete_evlist;
}
perf_evlist__set_maps(&evlist->core, cpus, threads);
- cpus = NULL;
- threads = NULL;
-
err = evlist__prepare_workload(evlist, &target, argv, false, workload_exec_failed_signal);
if (err < 0) {
pr_debug("Couldn't run the workload!\n");
if (retry_count++ > 1000) {
pr_debug("Failed after retrying 1000 times\n");
err = -1;
- goto out_free_maps;
+ goto out_delete_evlist;
}
goto retry;
err = -1;
}
-out_free_maps:
+out_delete_evlist:
perf_cpu_map__put(cpus);
perf_thread_map__put(threads);
-out_delete_evlist:
evlist__delete(evlist);
return err;
}
TEST_ASSERT_VAL("failed to synthesize map",
!perf_event__synthesize_thread_map2(NULL, threads, process_event, NULL));
+ perf_thread_map__put(threads);
return 0;
}
{
struct perf_thread_map *threads;
char *str;
- int i;
TEST_ASSERT_VAL("failed to allocate map string",
asprintf(&str, "%d,%d", getpid(), getppid()) >= 0);
threads = thread_map__new_str(str, NULL, 0, false);
+ free(str);
TEST_ASSERT_VAL("failed to allocate thread_map",
threads);
TEST_ASSERT_VAL("failed to not remove thread",
thread_map__remove(threads, 0));
- for (i = 0; i < threads->nr; i++)
- zfree(&threads->map[i].comm);
-
- free(threads);
+ perf_thread_map__put(threads);
return 0;
}
printf "static const char *x86_MSRs[] = {\n"
regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MSR_([[:alnum:]][[:alnum:]_]+)[[:space:]]+(0x00000[[:xdigit:]]+)[[:space:]]*.*'
-egrep $regex ${x86_msr_index} | egrep -v 'MSR_(ATOM|P[46]|IA32_(TSCDEADLINE|UCODE_REV)|IDT_FCR4)' | \
+egrep $regex ${x86_msr_index} | egrep -v 'MSR_(ATOM|P[46]|IA32_(TSC_DEADLINE|UCODE_REV)|IDT_FCR4)' | \
sed -r "s/$regex/\2 \1/g" | sort -n | \
xargs printf "\t[%s] = \"%s\",\n"
printf "};\n\n"
if ((hdr & SPE_HEADER0_MASK2) == SPE_HEADER0_EXTENDED) {
/* 16-bit extended format header */
- ext_hdr = 1;
+ if (len == 1)
+ return ARM_SPE_BAD_PACKET;
+ ext_hdr = 1;
hdr = buf[1];
if (hdr == SPE_HEADER1_ALIGNMENT)
return arm_spe_get_alignment(buf, len, packet);
queue->set = true;
queue->tid = buffer->tid;
queue->cpu = buffer->cpu;
- } else if (buffer->cpu != queue->cpu || buffer->tid != queue->tid) {
- pr_err("auxtrace queue conflict: cpu %d, tid %d vs cpu %d, tid %d\n",
- queue->cpu, queue->tid, buffer->cpu, buffer->tid);
- return -EINVAL;
}
buffer->buffer_nr = queues->next_buffer_nr++;
break;
}
- if (itr)
+ if (itr && itr->parse_snapshot_options)
return itr->parse_snapshot_options(itr, opts, str);
pr_err("No AUX area tracing to snapshot\n");
double ratio = 0.0;
if (block_fmt->total_cycles)
- ratio = (double)bi->cycles / (double)block_fmt->total_cycles;
+ ratio = (double)bi->cycles_aggr / (double)block_fmt->total_cycles;
return color_pct(hpp, block_fmt->width, 100.0 * ratio);
}
double l, r;
if (block_fmt->total_cycles) {
- l = ((double)bi_l->cycles /
+ l = ((double)bi_l->cycles_aggr /
(double)block_fmt->total_cycles) * 100000.0;
- r = ((double)bi_r->cycles /
+ r = ((double)bi_r->cycles_aggr /
(double)block_fmt->total_cycles) * 100000.0;
return (int64_t)l - (int64_t)r;
}
}
if (info_linear->info_len < offsetof(struct bpf_prog_info, prog_tags)) {
+ free(info_linear);
pr_debug("%s: the kernel is too old, aborting\n", __func__);
return -2;
}
info = &info_linear->info;
+ if (!info->jited_ksyms) {
+ free(info_linear);
+ return -1;
+ }
/* number of ksyms, func_lengths, and tags should match */
sub_prog_cnt = info->nr_jited_ksyms;
if (sub_prog_cnt != info->nr_prog_tags ||
- sub_prog_cnt != info->nr_jited_func_lens)
+ sub_prog_cnt != info->nr_jited_func_lens) {
+ free(info_linear);
return -1;
+ }
/* check BTF func info support */
if (info->btf_id && info->nr_func_info && info->func_info_rec_size) {
/* btf func info number should be same as sub_prog_cnt */
if (sub_prog_cnt != info->nr_func_info) {
pr_debug("%s: mismatch in BPF sub program count and BTF function info count, aborting\n", __func__);
- err = -1;
- goto out;
+ free(info_linear);
+ return -1;
}
if (btf__get_from_id(info->btf_id, &btf)) {
pr_debug("%s: failed to get BTF of id %u, aborting\n", __func__, info->btf_id);
int perf_data__create_dir(struct perf_data *data, int nr)
{
struct perf_data_file *files = NULL;
- int i, ret = -1;
+ int i, ret;
if (WARN_ON(!data->is_dir))
return -EINVAL;
for (i = 0; i < nr; i++) {
struct perf_data_file *file = &files[i];
- if (asprintf(&file->path, "%s/data.%d", data->path, i) < 0)
+ ret = asprintf(&file->path, "%s/data.%d", data->path, i);
+ if (ret < 0)
goto out_err;
ret = open(file->path, O_RDWR|O_CREAT|O_TRUNC, S_IRUSR|S_IWUSR);
perf_evsel__free_fd(&evsel->core);
perf_evsel__free_id(&evsel->core);
}
+ perf_evlist__reset_id_hash(&evlist->core);
}
static int evlist__create_syswide_maps(struct evlist *evlist)
#include "string2.h"
#include "memswap.h"
#include "util.h"
+#include "hashmap.h"
#include "../perf-sys.h"
#include "util/parse-branch-options.h"
#include <internal/xyarray.h>
zfree(&evsel->group_name);
zfree(&evsel->name);
zfree(&evsel->pmu_name);
- zfree(&evsel->per_pkg_mask);
+ evsel__zero_per_pkg(evsel);
+ hashmap__free(evsel->per_pkg_mask);
+ evsel->per_pkg_mask = NULL;
zfree(&evsel->metric_events);
perf_evsel__object.fini(evsel);
}
return store_evsel_ids(evsel, evlist);
}
+
+void evsel__zero_per_pkg(struct evsel *evsel)
+{
+ struct hashmap_entry *cur;
+ size_t bkt;
+
+ if (evsel->per_pkg_mask) {
+ hashmap__for_each_entry(evsel->per_pkg_mask, cur, bkt)
+ free((char *)cur->key);
+
+ hashmap__clear(evsel->per_pkg_mask);
+ }
+}
union perf_event;
struct bpf_counter_ops;
struct target;
+struct hashmap;
typedef int (evsel__sb_cb_t)(union perf_event *event, void *data);
bool merged_stat;
bool reset_group;
bool errored;
- unsigned long *per_pkg_mask;
+ struct hashmap *per_pkg_mask;
struct evsel *leader;
struct list_head config_terms;
int err;
int evsel__store_ids(struct evsel *evsel, struct evlist *evlist);
+void evsel__zero_per_pkg(struct evsel *evsel);
#endif /* __PERF_EVSEL_H */
fprintf(fp, "# clockid: %s (%u)\n", clockid_name(clockid), clockid);
fprintf(fp, "# reference time: %s = %ld.%06d (TOD) = %ld.%09ld (%s)\n",
- tstr, tod_ns.tv_sec, (int) tod_ns.tv_usec,
- clockid_ns.tv_sec, clockid_ns.tv_nsec,
+ tstr, (long) tod_ns.tv_sec, (int) tod_ns.tv_usec,
+ (long) clockid_ns.tv_sec, clockid_ns.tv_nsec,
clockid_name(clockid));
}
if (strstarts(filename, "/system/lib/")) {
char *ndk, *app;
const char *arch;
- size_t ndk_length;
- size_t app_length;
+ int ndk_length, app_length;
ndk = getenv("NDK_ROOT");
app = getenv("APP_PLATFORM");
if (new_length > PATH_MAX)
return false;
snprintf(newfilename, new_length,
- "%s/platforms/%s/arch-%s/usr/lib/%s",
- ndk, app, arch, libname);
+ "%.*s/platforms/%.*s/arch-%s/usr/lib/%s",
+ ndk_length, ndk, app_length, app, arch, libname);
return true;
}
int maps__clone(struct thread *thread, struct maps *parent)
{
struct maps *maps = thread->maps;
- int err = -ENOMEM;
+ int err;
struct map *map;
down_read(&parent->lock);
maps__for_each_entry(parent, map) {
struct map *new = map__clone(map);
- if (new == NULL)
+
+ if (new == NULL) {
+ err = -ENOMEM;
goto out_unlock;
+ }
err = unwind__prepare_access(maps, new, NULL);
if (err)
struct perf_cpu_map *cpus = pmu ? perf_cpu_map__get(pmu->cpus) :
cpu_list ? perf_cpu_map__new(cpu_list) : NULL;
+ if (pmu && attr->type == PERF_TYPE_RAW)
+ perf_pmu__warn_invalid_config(pmu, attr->config, name);
+
if (init_attr)
event_attr_init(attr);
%type <str> PE_EVENT_NAME
%type <str> PE_PMU_EVENT_PRE PE_PMU_EVENT_SUF PE_KERNEL_PMU_EVENT PE_PMU_EVENT_FAKE
%type <str> PE_DRV_CFG_TERM
+%type <str> event_pmu_name
%destructor { free ($$); } <str>
%type <term> event_term
%destructor { parse_events_term__delete ($$); } <term>
event_legacy_raw sep_dc |
event_bpf_file
+event_pmu_name:
+PE_NAME | PE_PMU_EVENT_PRE
+
event_pmu:
-PE_NAME opt_pmu_config
+event_pmu_name opt_pmu_config
{
struct parse_events_state *parse_state = _parse_state;
struct parse_events_error *error = parse_state->error;
return nr_caps;
}
+
+void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
+ char *name)
+{
+ struct perf_pmu_format *format;
+ __u64 masks = 0, bits;
+ char buf[100];
+ unsigned int i;
+
+ list_for_each_entry(format, &pmu->format, list) {
+ if (format->value != PERF_PMU_FORMAT_VALUE_CONFIG)
+ continue;
+
+ for_each_set_bit(i, format->bits, PERF_PMU_FORMAT_BITS)
+ masks |= 1ULL << i;
+ }
+
+ /*
+ * Kernel doesn't export any valid format bits.
+ */
+ if (masks == 0)
+ return;
+
+ bits = config & ~masks;
+ if (bits == 0)
+ return;
+
+ bitmap_scnprintf((unsigned long *)&bits, sizeof(bits) * 8, buf, sizeof(buf));
+
+ pr_warning("WARNING: event '%s' not valid (bits %s of config "
+ "'%llx' not supported by kernel)!\n",
+ name ?: "N/A", buf, config);
+}
int perf_pmu__caps_parse(struct perf_pmu *pmu);
+void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
+ char *name);
+
#endif /* __PMU_H */
util/units.c
util/affinity.c
util/rwsem.c
+util/hashmap.c
if (strncasecmp(tok, sd->name, strlen(tok)))
continue;
- if (sort__mode != SORT_MODE__MEMORY)
+ if (sort__mode != SORT_MODE__BRANCH)
return -EINVAL;
return __sort_dimension__add_output(list, sd);
if (strncasecmp(tok, sd->name, strlen(tok)))
continue;
- if (sort__mode != SORT_MODE__BRANCH)
+ if (sort__mode != SORT_MODE__MEMORY)
return -EINVAL;
return __sort_dimension__add_output(list, sd);
if (config->interval_clear)
puts(CONSOLE_CLEAR);
- sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, config->csv_sep);
+ sprintf(prefix, "%6lu.%09lu%s", (unsigned long) ts->tv_sec, ts->tv_nsec, config->csv_sep);
if ((num_print_interval == 0 && !config->csv_output) || config->interval_clear) {
switch (config->aggr_mode) {
#include "evlist.h"
#include "evsel.h"
#include "thread_map.h"
+#include "hashmap.h"
#include <linux/zalloc.h>
void update_stats(struct stats *stats, u64 val)
}
}
-static void zero_per_pkg(struct evsel *counter)
+static size_t pkg_id_hash(const void *__key, void *ctx __maybe_unused)
{
- if (counter->per_pkg_mask)
- memset(counter->per_pkg_mask, 0, cpu__max_cpu());
+ uint64_t *key = (uint64_t *) __key;
+
+ return *key & 0xffffffff;
+}
+
+static bool pkg_id_equal(const void *__key1, const void *__key2,
+ void *ctx __maybe_unused)
+{
+ uint64_t *key1 = (uint64_t *) __key1;
+ uint64_t *key2 = (uint64_t *) __key2;
+
+ return *key1 == *key2;
}
static int check_per_pkg(struct evsel *counter,
struct perf_counts_values *vals, int cpu, bool *skip)
{
- unsigned long *mask = counter->per_pkg_mask;
+ struct hashmap *mask = counter->per_pkg_mask;
struct perf_cpu_map *cpus = evsel__cpus(counter);
- int s;
+ int s, d, ret = 0;
+ uint64_t *key;
*skip = false;
return 0;
if (!mask) {
- mask = zalloc(cpu__max_cpu());
+ mask = hashmap__new(pkg_id_hash, pkg_id_equal, NULL);
if (!mask)
return -ENOMEM;
if (s < 0)
return -1;
- *skip = test_and_set_bit(s, mask) == 1;
- return 0;
+ /*
+ * On multi-die system, die_id > 0. On no-die system, die_id = 0.
+ * We use hashmap(socket, die) to check the used socket+die pair.
+ */
+ d = cpu_map__get_die(cpus, cpu, NULL).die;
+ if (d < 0)
+ return -1;
+
+ key = malloc(sizeof(*key));
+ if (!key)
+ return -ENOMEM;
+
+ *key = (uint64_t)d << 32 | s;
+ if (hashmap__find(mask, (void *)key, NULL))
+ *skip = true;
+ else
+ ret = hashmap__add(mask, (void *)key, (void *)1);
+
+ return ret;
}
static int
}
if (counter->per_pkg)
- zero_per_pkg(counter);
+ evsel__zero_per_pkg(counter);
ret = process_counter_maps(config, counter);
if (ret)
while (!io.eof) {
static const char anonstr[] = "//anon";
- size_t size;
+ size_t size, aligned_size;
/* ensure null termination since stack will be reused. */
event->mmap2.filename[0] = '\0';
}
size = strlen(event->mmap2.filename) + 1;
- size = PERF_ALIGN(size, sizeof(u64));
+ aligned_size = PERF_ALIGN(size, sizeof(u64));
event->mmap2.len -= event->mmap.start;
event->mmap2.header.size = (sizeof(event->mmap2) -
- (sizeof(event->mmap2.filename) - size));
- memset(event->mmap2.filename + size, 0, machine->id_hdr_size);
+ (sizeof(event->mmap2.filename) - aligned_size));
+ memset(event->mmap2.filename + size, 0, machine->id_hdr_size +
+ (aligned_size - size));
event->mmap2.header.size += machine->id_hdr_size;
event->mmap2.pid = tgid;
event->mmap2.tid = pid;
for (i = 0; i < n; i++) {
char *end;
pid_t _pid;
- bool kernel_thread;
+ bool kernel_thread = false;
_pid = strtol(dirent[i]->d_name, &end, 10);
if (*end)
pr_debug("error reading saved cmdlines\n");
goto out;
}
+ buf[ret] = '\0';
parse_saved_cmdline(pevent, buf, size);
ret = 0;
if (dso != NULL) {
__dsos__add(&machine->dsos, dso);
dso__set_long_name(dso, long_name, false);
+ /* Put dso here because __dsos_add already got it */
+ dso__put(dso);
}
return dso;
fprintf(outf, "cpu%d: MSR_TURBO_RATIO_LIMIT: 0x%08llx\n",
base_cpu, msr);
- /**
+ /*
* Turbo encoding in KNL is as follows:
* [0] -- Reserved
* [7:1] -- Base value of number of active cores of bucket 1.
# CONFIG_RESET_BRCMSTB_RESCAL is not set
# CONFIG_RESET_INTEL_GW is not set
# CONFIG_ADI_AXI_ADC is not set
+# CONFIG_DEBUG_PAGEALLOC is not set
+# CONFIG_PAGE_POISONING is not set
CONFIG_IS_NOT_SET_PATTERN = r'^# CONFIG_(\w+) is not set$'
CONFIG_PATTERN = r'^CONFIG_(\w+)=(\S+|".*")$'
-KconfigEntryBase = collections.namedtuple('KconfigEntry', ['name', 'value'])
+KconfigEntryBase = collections.namedtuple('KconfigEntryBase', ['name', 'value'])
class KconfigEntry(KconfigEntryBase):
return NULL;
}
+/*
+ * There are always either 1 or 2 objects in the IDR. If we find nothing,
+ * or we find something at an ID we didn't expect, that's a bug.
+ */
void idr_find_test_1(int anchor_id, int throbber_id)
{
pthread_t throbber;
time_t start = time(NULL);
- pthread_create(&throbber, NULL, idr_throbber, &throbber_id);
-
BUG_ON(idr_alloc(&find_idr, xa_mk_value(anchor_id), anchor_id,
anchor_id + 1, GFP_KERNEL) != anchor_id);
+ pthread_create(&throbber, NULL, idr_throbber, &throbber_id);
+
+ rcu_read_lock();
do {
int id = 0;
void *entry = idr_get_next(&find_idr, &id);
- BUG_ON(entry != xa_mk_value(id));
+ rcu_read_unlock();
+ if ((id != anchor_id && id != throbber_id) ||
+ entry != xa_mk_value(id)) {
+ printf("%s(%d, %d): %p at %d\n", __func__, anchor_id,
+ throbber_id, entry, id);
+ abort();
+ }
+ rcu_read_lock();
} while (time(NULL) < start + 11);
+ rcu_read_unlock();
pthread_join(throbber, NULL);
int __weak main(void)
{
+ rcu_register_thread();
radix_tree_init();
idr_checks();
ida_tests();
rcu_barrier();
if (nr_allocated)
printf("nr_allocated = %d\n", nr_allocated);
+ rcu_unregister_thread();
return 0;
}
int __weak main(void)
{
+ rcu_register_thread();
radix_tree_init();
multiorder_checks();
+ rcu_unregister_thread();
return 0;
}
int __weak main(void)
{
+ rcu_register_thread();
radix_tree_init();
xarray_tests();
radix_tree_cpu_dead(1);
rcu_barrier();
if (nr_allocated)
printf("nr_allocated = %d\n", nr_allocated);
+ rcu_unregister_thread();
return 0;
}
ARCH ?= $(shell uname -m 2>/dev/null || echo not)
ifneq (,$(filter $(ARCH),aarch64 arm64))
-ARM64_SUBTARGETS ?= tags signal pauth fp mte
+ARM64_SUBTARGETS ?= tags signal pauth fp mte bti
else
ARM64_SUBTARGETS :=
endif
--- /dev/null
+btitest
+nobtitest
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0
+
+TEST_GEN_PROGS := btitest nobtitest
+
+PROGS := $(patsubst %,gen/%,$(TEST_GEN_PROGS))
+
+# These tests are built as freestanding binaries since otherwise BTI
+# support in ld.so is required which is not currently widespread; when
+# it is available it will still be useful to test this separately as the
+# cases for statically linked and dynamically lined binaries are
+# slightly different.
+
+CFLAGS_NOBTI = -DBTI=0
+CFLAGS_BTI = -mbranch-protection=standard -DBTI=1
+
+CFLAGS_COMMON = -ffreestanding -Wall -Wextra $(CFLAGS)
+
+BTI_CC_COMMAND = $(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -c -o $@ $<
+NOBTI_CC_COMMAND = $(CC) $(CFLAGS_NOBTI) $(CFLAGS_COMMON) -c -o $@ $<
+
+%-bti.o: %.c
+ $(BTI_CC_COMMAND)
+
+%-bti.o: %.S
+ $(BTI_CC_COMMAND)
+
+%-nobti.o: %.c
+ $(NOBTI_CC_COMMAND)
+
+%-nobti.o: %.S
+ $(NOBTI_CC_COMMAND)
+
+BTI_OBJS = \
+ test-bti.o \
+ signal-bti.o \
+ start-bti.o \
+ syscall-bti.o \
+ system-bti.o \
+ teststubs-bti.o \
+ trampoline-bti.o
+gen/btitest: $(BTI_OBJS)
+ $(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -nostdlib -o $@ $^
+
+NOBTI_OBJS = \
+ test-nobti.o \
+ signal-nobti.o \
+ start-nobti.o \
+ syscall-nobti.o \
+ system-nobti.o \
+ teststubs-nobti.o \
+ trampoline-nobti.o
+gen/nobtitest: $(NOBTI_OBJS)
+ $(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -nostdlib -o $@ $^
+
+# Including KSFT lib.mk here will also mangle the TEST_GEN_PROGS list
+# to account for any OUTPUT target-dirs optionally provided by
+# the toplevel makefile
+include ../../lib.mk
+
+$(TEST_GEN_PROGS): $(PROGS)
+ cp $(PROGS) $(OUTPUT)/
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 Arm Limited
+ * Original author: Dave Martin <Dave.Martin@arm.com>
+ */
+
+#ifndef ASSEMBLER_H
+#define ASSEMBLER_H
+
+#define NT_GNU_PROPERTY_TYPE_0 5
+#define GNU_PROPERTY_AARCH64_FEATURE_1_AND 0xc0000000
+
+/* Bits for GNU_PROPERTY_AARCH64_FEATURE_1_BTI */
+#define GNU_PROPERTY_AARCH64_FEATURE_1_BTI (1U << 0)
+#define GNU_PROPERTY_AARCH64_FEATURE_1_PAC (1U << 1)
+
+
+.macro startfn name:req
+ .globl \name
+\name:
+ .macro endfn
+ .size \name, . - \name
+ .type \name, @function
+ .purgem endfn
+ .endm
+.endm
+
+.macro emit_aarch64_feature_1_and
+ .pushsection .note.gnu.property, "a"
+ .align 3
+ .long 2f - 1f
+ .long 6f - 3f
+ .long NT_GNU_PROPERTY_TYPE_0
+1: .string "GNU"
+2:
+ .align 3
+3: .long GNU_PROPERTY_AARCH64_FEATURE_1_AND
+ .long 5f - 4f
+4:
+#if BTI
+ .long GNU_PROPERTY_AARCH64_FEATURE_1_PAC | \
+ GNU_PROPERTY_AARCH64_FEATURE_1_BTI
+#else
+ .long 0
+#endif
+5:
+ .align 3
+6:
+ .popsection
+.endm
+
+.macro paciasp
+ hint 0x19
+.endm
+
+.macro autiasp
+ hint 0x1d
+.endm
+
+.macro __bti_
+ hint 0x20
+.endm
+
+.macro __bti_c
+ hint 0x22
+.endm
+
+.macro __bti_j
+ hint 0x24
+.endm
+
+.macro __bti_jc
+ hint 0x26
+.endm
+
+.macro bti what=
+ __bti_\what
+.endm
+
+#endif /* ! ASSEMBLER_H */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 Arm Limited
+ * Original author: Dave Martin <Dave.Martin@arm.com>
+ */
+
+#ifndef BTITEST_H
+#define BTITEST_H
+
+/* Trampolines for calling the test stubs: */
+void call_using_br_x0(void (*)(void));
+void call_using_br_x16(void (*)(void));
+void call_using_blr(void (*)(void));
+
+/* Test stubs: */
+void nohint_func(void);
+void bti_none_func(void);
+void bti_c_func(void);
+void bti_j_func(void);
+void bti_jc_func(void);
+void paciasp_func(void);
+
+#endif /* !BTITEST_H */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 Arm Limited
+ * Original author: Dave Martin <Dave.Martin@arm.com>
+ */
+
+#ifndef COMPILER_H
+#define COMPILER_H
+
+#define __always_unused __attribute__((__unused__))
+#define __noreturn __attribute__((__noreturn__))
+#define __unreachable() __builtin_unreachable()
+
+/* curse(e) has value e, but the compiler cannot assume so */
+#define curse(e) ({ \
+ __typeof__(e) __curse_e = (e); \
+ asm ("" : "+r" (__curse_e)); \
+ __curse_e; \
+})
+
+#endif /* ! COMPILER_H */
--- /dev/null
+btitest
+nobtitest
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 Arm Limited
+ * Original author: Dave Martin <Dave.Martin@arm.com>
+ */
+
+#include "system.h"
+#include "signal.h"
+
+int sigemptyset(sigset_t *s)
+{
+ unsigned int i;
+
+ for (i = 0; i < _NSIG_WORDS; ++i)
+ s->sig[i] = 0;
+
+ return 0;
+}
+
+int sigaddset(sigset_t *s, int n)
+{
+ if (n < 1 || n > _NSIG)
+ return -EINVAL;
+
+ s->sig[(n - 1) / _NSIG_BPW] |= 1UL << (n - 1) % _NSIG_BPW;
+ return 0;
+}
+
+int sigaction(int n, struct sigaction *sa, const struct sigaction *old)
+{
+ return syscall(__NR_rt_sigaction, n, sa, old, sizeof(sa->sa_mask));
+}
+
+int sigprocmask(int how, const sigset_t *mask, sigset_t *old)
+{
+ return syscall(__NR_rt_sigprocmask, how, mask, old, sizeof(*mask));
+}
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 Arm Limited
+ * Original author: Dave Martin <Dave.Martin@arm.com>
+ */
+
+#ifndef SIGNAL_H
+#define SIGNAL_H
+
+#include <linux/signal.h>
+
+#include "system.h"
+
+typedef __sighandler_t sighandler_t;
+
+int sigemptyset(sigset_t *s);
+int sigaddset(sigset_t *s, int n);
+int sigaction(int n, struct sigaction *sa, const struct sigaction *old);
+int sigprocmask(int how, const sigset_t *mask, sigset_t *old);
+
+#endif /* ! SIGNAL_H */
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 Arm Limited
+ * Original author: Dave Martin <Dave.Martin@arm.com>
+ */
+
+#include "assembler.h"
+
+startfn _start
+ mov x0, sp
+ b start
+endfn
+
+emit_aarch64_feature_1_and
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 Arm Limited
+ * Original author: Dave Martin <Dave.Martin@arm.com>
+ */
+
+#include "assembler.h"
+
+startfn syscall
+ bti c
+ mov w8, w0
+ mov x0, x1
+ mov x1, x2
+ mov x2, x3
+ mov x3, x4
+ mov x4, x5
+ mov x5, x6
+ mov x6, x7
+ svc #0
+ ret
+endfn
+
+emit_aarch64_feature_1_and
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019 Arm Limited
+ * Original author: Dave Martin <Dave.Martin@arm.com>
+ */
+
+#include "system.h"
+
+#include <asm/unistd.h>
+
+#include "compiler.h"
+
+void __noreturn exit(int n)
+{
+ syscall(__NR_exit, n);
+ __unreachable();
+}
+
+ssize_t write(int fd, const void *buf, size_t size)
+{
+ return syscall(__NR_write, fd, buf, size);
+}
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 Arm Limited
+ * Original author: Dave Martin <Dave.Martin@arm.com>
+ */
+
+#ifndef SYSTEM_H
+#define SYSTEM_H
+
+#include <linux/types.h>
+#include <linux/stddef.h>
+
+typedef __kernel_size_t size_t;
+typedef __kernel_ssize_t ssize_t;
+
+#include <linux/errno.h>
+#include <asm/hwcap.h>
+#include <asm/ptrace.h>
+#include <asm/unistd.h>
+
+#include "compiler.h"
+
+long syscall(int nr, ...);
+
+void __noreturn exit(int n);
+ssize_t write(int fd, const void *buf, size_t size);
+
+#endif /* ! SYSTEM_H */
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2019,2021 Arm Limited
+ * Original author: Dave Martin <Dave.Martin@arm.com>
+ */
+
+#include "system.h"
+
+#include <linux/errno.h>
+#include <linux/auxvec.h>
+#include <linux/signal.h>
+#include <asm/sigcontext.h>
+#include <asm/ucontext.h>
+
+typedef struct ucontext ucontext_t;
+
+#include "btitest.h"
+#include "compiler.h"
+#include "signal.h"
+
+#define EXPECTED_TESTS 18
+
+static volatile unsigned int test_num = 1;
+static unsigned int test_passed;
+static unsigned int test_failed;
+static unsigned int test_skipped;
+
+static void fdputs(int fd, const char *str)
+{
+ size_t len = 0;
+ const char *p = str;
+
+ while (*p++)
+ ++len;
+
+ write(fd, str, len);
+}
+
+static void putstr(const char *str)
+{
+ fdputs(1, str);
+}
+
+static void putnum(unsigned int num)
+{
+ char c;
+
+ if (num / 10)
+ putnum(num / 10);
+
+ c = '0' + (num % 10);
+ write(1, &c, 1);
+}
+
+#define puttestname(test_name, trampoline_name) do { \
+ putstr(test_name); \
+ putstr("/"); \
+ putstr(trampoline_name); \
+} while (0)
+
+void print_summary(void)
+{
+ putstr("# Totals: pass:");
+ putnum(test_passed);
+ putstr(" fail:");
+ putnum(test_failed);
+ putstr(" xfail:0 xpass:0 skip:");
+ putnum(test_skipped);
+ putstr(" error:0\n");
+}
+
+static const char *volatile current_test_name;
+static const char *volatile current_trampoline_name;
+static volatile int sigill_expected, sigill_received;
+
+static void handler(int n, siginfo_t *si __always_unused,
+ void *uc_ __always_unused)
+{
+ ucontext_t *uc = uc_;
+
+ putstr("# \t[SIGILL in ");
+ puttestname(current_test_name, current_trampoline_name);
+ putstr(", BTYPE=");
+ write(1, &"00011011"[((uc->uc_mcontext.pstate & PSR_BTYPE_MASK)
+ >> PSR_BTYPE_SHIFT) * 2], 2);
+ if (!sigill_expected) {
+ putstr("]\n");
+ putstr("not ok ");
+ putnum(test_num);
+ putstr(" ");
+ puttestname(current_test_name, current_trampoline_name);
+ putstr("(unexpected SIGILL)\n");
+ print_summary();
+ exit(128 + n);
+ }
+
+ putstr(" (expected)]\n");
+ sigill_received = 1;
+ /* zap BTYPE so that resuming the faulting code will work */
+ uc->uc_mcontext.pstate &= ~PSR_BTYPE_MASK;
+}
+
+static int skip_all;
+
+static void __do_test(void (*trampoline)(void (*)(void)),
+ void (*fn)(void),
+ const char *trampoline_name,
+ const char *name,
+ int expect_sigill)
+{
+ if (skip_all) {
+ test_skipped++;
+ putstr("ok ");
+ putnum(test_num);
+ putstr(" ");
+ puttestname(name, trampoline_name);
+ putstr(" # SKIP\n");
+
+ return;
+ }
+
+ /* Branch Target exceptions should only happen in BTI binaries: */
+ if (!BTI)
+ expect_sigill = 0;
+
+ sigill_expected = expect_sigill;
+ sigill_received = 0;
+ current_test_name = name;
+ current_trampoline_name = trampoline_name;
+
+ trampoline(fn);
+
+ if (expect_sigill && !sigill_received) {
+ putstr("not ok ");
+ test_failed++;
+ } else {
+ putstr("ok ");
+ test_passed++;
+ }
+ putnum(test_num++);
+ putstr(" ");
+ puttestname(name, trampoline_name);
+ putstr("\n");
+}
+
+#define do_test(expect_sigill_br_x0, \
+ expect_sigill_br_x16, \
+ expect_sigill_blr, \
+ name) \
+do { \
+ __do_test(call_using_br_x0, name, "call_using_br_x0", #name, \
+ expect_sigill_br_x0); \
+ __do_test(call_using_br_x16, name, "call_using_br_x16", #name, \
+ expect_sigill_br_x16); \
+ __do_test(call_using_blr, name, "call_using_blr", #name, \
+ expect_sigill_blr); \
+} while (0)
+
+void start(int *argcp)
+{
+ struct sigaction sa;
+ void *const *p;
+ const struct auxv_entry {
+ unsigned long type;
+ unsigned long val;
+ } *auxv;
+ unsigned long hwcap = 0, hwcap2 = 0;
+
+ putstr("TAP version 13\n");
+ putstr("1..");
+ putnum(EXPECTED_TESTS);
+ putstr("\n");
+
+ /* Gross hack for finding AT_HWCAP2 from the initial process stack: */
+ p = (void *const *)argcp + 1 + *argcp + 1; /* start of environment */
+ /* step over environment */
+ while (*p++)
+ ;
+ for (auxv = (const struct auxv_entry *)p; auxv->type != AT_NULL; ++auxv) {
+ switch (auxv->type) {
+ case AT_HWCAP:
+ hwcap = auxv->val;
+ break;
+ case AT_HWCAP2:
+ hwcap2 = auxv->val;
+ break;
+ default:
+ break;
+ }
+ }
+
+ if (hwcap & HWCAP_PACA)
+ putstr("# HWCAP_PACA present\n");
+ else
+ putstr("# HWCAP_PACA not present\n");
+
+ if (hwcap2 & HWCAP2_BTI) {
+ putstr("# HWCAP2_BTI present\n");
+ if (!(hwcap & HWCAP_PACA))
+ putstr("# Bad hardware? Expect problems.\n");
+ } else {
+ putstr("# HWCAP2_BTI not present\n");
+ skip_all = 1;
+ }
+
+ putstr("# Test binary");
+ if (!BTI)
+ putstr(" not");
+ putstr(" built for BTI\n");
+
+ sa.sa_handler = (sighandler_t)(void *)handler;
+ sa.sa_flags = SA_SIGINFO;
+ sigemptyset(&sa.sa_mask);
+ sigaction(SIGILL, &sa, NULL);
+ sigaddset(&sa.sa_mask, SIGILL);
+ sigprocmask(SIG_UNBLOCK, &sa.sa_mask, NULL);
+
+ do_test(1, 1, 1, nohint_func);
+ do_test(1, 1, 1, bti_none_func);
+ do_test(1, 0, 0, bti_c_func);
+ do_test(0, 0, 1, bti_j_func);
+ do_test(0, 0, 0, bti_jc_func);
+ do_test(1, 0, 0, paciasp_func);
+
+ print_summary();
+
+ if (test_num - 1 != EXPECTED_TESTS)
+ putstr("# WARNING - EXPECTED TEST COUNT WRONG\n");
+
+ if (test_failed)
+ exit(1);
+ else
+ exit(0);
+}
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 Arm Limited
+ * Original author: Dave Martin <Dave.Martin@arm.com>
+ */
+
+#include "assembler.h"
+
+startfn bti_none_func
+ bti
+ ret
+endfn
+
+startfn bti_c_func
+ bti c
+ ret
+endfn
+
+startfn bti_j_func
+ bti j
+ ret
+endfn
+
+startfn bti_jc_func
+ bti jc
+ ret
+endfn
+
+startfn paciasp_func
+ paciasp
+ autiasp
+ ret
+endfn
+
+startfn nohint_func
+ ret
+endfn
+
+emit_aarch64_feature_1_and
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 Arm Limited
+ * Original author: Dave Martin <Dave.Martin@arm.com>
+ */
+
+#include "assembler.h"
+
+startfn call_using_br_x0
+ bti c
+ br x0
+endfn
+
+startfn call_using_br_x16
+ bti c
+ mov x16, x0
+ br x16
+endfn
+
+startfn call_using_blr
+ paciasp
+ stp x29, x30, [sp, #-16]!
+ blr x0
+ ldp x29, x30, [sp], #16
+ autiasp
+ ret
+endfn
+
+emit_aarch64_feature_1_and
ksft_print_cnts();
- return 0;
+ return ret;
}
// Set up test pattern in the FFR
// x0: pid
// x2: generation
+//
+// We need to generate a canonical FFR value, which consists of a number of
+// low "1" bits, followed by a number of zeros. This gives us 17 unique values
+// per 16 bits of FFR, so we create a 4 bit signature out of the PID and
+// generation, and use that as the initial number of ones in the pattern.
+// We fill the upper lanes of FFR with zeros.
// Beware: corrupts P0.
function setup_ffr
mov x4, x30
- bl pattern
+ and w0, w0, #0x3
+ bfi w0, w2, #2, #2
+ mov w1, #1
+ lsl w1, w1, w0
+ sub w1, w1, #1
+
ldr x0, =ffrref
- ldr x1, =scratch
- rdvl x2, #1
- lsr x2, x2, #3
- bl memcpy
+ strh w1, [x0], 2
+ rdvl x1, #1
+ lsr x1, x1, #3
+ sub x1, x1, #2
+ bl memclr
mov x0, #0
ldr x1, =ffrref
# SPDX-License-Identifier: GPL-2.0
# Copyright (C) 2020 ARM Limited
-CFLAGS += -std=gnu99 -I. -lpthread
+# preserve CC value from top level Makefile
+ifeq ($(CC),cc)
+CC := $(CROSS_COMPILE)gcc
+endif
+
+CFLAGS += -std=gnu99 -I. -pthread
+LDFLAGS += -pthread
SRCS := $(filter-out mte_common_util.c,$(wildcard *.c))
PROGS := $(patsubst %.c,%,$(SRCS))
#Add mte compiler option
-ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep gcc),)
CFLAGS += -march=armv8.5-a+memtag
-endif
#check if the compiler works well
mte_cc_support := $(shell if ($(CC) $(CFLAGS) -E -x c /dev/null -o /dev/null 2>&1) then echo "1"; fi)
# Get Kernel headers installed and use them.
KSFT_KHDR_INSTALL := 1
+else
+ $(warning compiler "$(CC)" does not support the ARMv8.5 MTE extension.)
+ $(warning test program "mte" will not be created.)
endif
# Include KSFT lib.mk.
include ../../lib.mk
ifeq ($(mte_cc_support),1)
-$(TEST_GEN_PROGS): mte_common_util.c mte_common_util.h mte_helper.S
+$(TEST_GEN_PROGS): mte_common_util.c mte_helper.S
endif
ksft_print_msg("ERR: missing %s\n", str);
return 0;
}
- fscanf(f, "%lu", &val);
+ if (fscanf(f, "%lu", &val) != 1) {
+ ksft_print_msg("ERR: parsing %s\n", str);
+ val = 0;
+ }
fclose(f);
return val;
}
if (fd == -1)
return KSFT_FAIL;
for (i = 0; i < len; i++)
- write(fd, &val, sizeof(val));
+ if (write(fd, &val, sizeof(val)) != sizeof(val))
+ return KSFT_FAIL;
lseek(fd, 0, 0);
ptr = mte_allocate_memory(len, mem_type, mapping, true);
if (check_allocated_memory(ptr, len, mem_type, true) != KSFT_PASS) {
}
/* Initialize the file for mappable size */
lseek(fd, 0, SEEK_SET);
- for (index = INIT_BUFFER_SIZE; index < size; index += INIT_BUFFER_SIZE)
- write(fd, buffer, INIT_BUFFER_SIZE);
+ for (index = INIT_BUFFER_SIZE; index < size; index += INIT_BUFFER_SIZE) {
+ if (write(fd, buffer, INIT_BUFFER_SIZE) != INIT_BUFFER_SIZE) {
+ perror("initialising buffer");
+ return NULL;
+ }
+ }
index -= INIT_BUFFER_SIZE;
- write(fd, buffer, size - index);
+ if (write(fd, buffer, size - index) != size - index) {
+ perror("initialising buffer");
+ return NULL;
+ }
return __mte_allocate_memory_range(size, mem_type, mapping, 0, 0, tags, fd);
}
/* Initialize the file for mappable size */
lseek(fd, 0, SEEK_SET);
for (index = INIT_BUFFER_SIZE; index < map_size; index += INIT_BUFFER_SIZE)
- write(fd, buffer, INIT_BUFFER_SIZE);
+ if (write(fd, buffer, INIT_BUFFER_SIZE) != INIT_BUFFER_SIZE) {
+ perror("initialising buffer");
+ return NULL;
+ }
index -= INIT_BUFFER_SIZE;
- write(fd, buffer, map_size - index);
+ if (write(fd, buffer, map_size - index) != map_size - index) {
+ perror("initialising buffer");
+ return NULL;
+ }
return __mte_allocate_memory_range(size, mem_type, mapping, range_before,
range_after, true, fd);
}
en |= (incl_mask << PR_MTE_TAG_SHIFT);
/* Enable address tagging ABI, mte error reporting mode and tag inclusion mask. */
- if (!prctl(PR_SET_TAGGED_ADDR_CTRL, en, 0, 0, 0) == 0) {
+ if (prctl(PR_SET_TAGGED_ADDR_CTRL, en, 0, 0, 0) != 0) {
ksft_print_msg("FAIL:prctl PR_SET_TAGGED_ADDR_CTRL for mte mode\n");
return -EINVAL;
}
return 0;
}
-#define ID_AA64PFR1_MTE_SHIFT 8
-#define ID_AA64PFR1_MTE 2
-
int mte_default_setup(void)
{
- unsigned long hwcaps = getauxval(AT_HWCAP);
+ unsigned long hwcaps2 = getauxval(AT_HWCAP2);
unsigned long en = 0;
int ret;
- if (!(hwcaps & HWCAP_CPUID)) {
- ksft_print_msg("FAIL: CPUID registers unavailable\n");
- return KSFT_FAIL;
- }
- /* Read ID_AA64PFR1_EL1 register */
- asm volatile("mrs %0, id_aa64pfr1_el1" : "=r"(hwcaps) : : "memory");
- if (((hwcaps >> ID_AA64PFR1_MTE_SHIFT) & MT_TAG_MASK) != ID_AA64PFR1_MTE) {
+ if (!(hwcaps2 & HWCAP2_MTE)) {
ksft_print_msg("FAIL: MTE features unavailable\n");
return KSFT_SKIP;
}
/* Create a file in the tmpfs filesystem */
fd = mkstemp(&filename[0]);
if (fd == -1) {
+ perror(filename);
ksft_print_msg("FAIL: Unable to open temporary file\n");
return 0;
}
#include <test_progs.h>
#include "bpf_dctcp.skel.h"
#include "bpf_cubic.skel.h"
+#include "bpf_tcp_nogpl.skel.h"
#define min(a, b) ((a) < (b) ? (a) : (b))
bpf_dctcp__destroy(dctcp_skel);
}
+static char *err_str;
+static bool found;
+
+static int libbpf_debug_print(enum libbpf_print_level level,
+ const char *format, va_list args)
+{
+ char *log_buf;
+
+ if (level != LIBBPF_WARN ||
+ strcmp(format, "libbpf: \n%s\n")) {
+ vprintf(format, args);
+ return 0;
+ }
+
+ log_buf = va_arg(args, char *);
+ if (!log_buf)
+ goto out;
+ if (err_str && strstr(log_buf, err_str) != NULL)
+ found = true;
+out:
+ printf(format, log_buf);
+ return 0;
+}
+
+static void test_invalid_license(void)
+{
+ libbpf_print_fn_t old_print_fn;
+ struct bpf_tcp_nogpl *skel;
+
+ err_str = "struct ops programs must have a GPL compatible license";
+ found = false;
+ old_print_fn = libbpf_set_print(libbpf_debug_print);
+
+ skel = bpf_tcp_nogpl__open_and_load();
+ ASSERT_NULL(skel, "bpf_tcp_nogpl");
+ ASSERT_EQ(found, true, "expected_err_msg");
+
+ bpf_tcp_nogpl__destroy(skel);
+ libbpf_set_print(old_print_fn);
+}
+
void test_bpf_tcp_ca(void)
{
if (test__start_subtest("dctcp"))
test_dctcp();
if (test__start_subtest("cubic"))
test_cubic();
+ if (test__start_subtest("invalid_license"))
+ test_invalid_license();
}
test_check_mtu_run_xdp(skel, skel->progs.xdp_use_helper, mtu);
test_check_mtu_run_xdp(skel, skel->progs.xdp_exceed_mtu, mtu);
test_check_mtu_run_xdp(skel, skel->progs.xdp_minus_delta, mtu);
+ test_check_mtu_run_xdp(skel, skel->progs.xdp_input_len, mtu);
+ test_check_mtu_run_xdp(skel, skel->progs.xdp_input_len_exceed, mtu);
cleanup:
test_check_mtu__destroy(skel);
test_check_mtu_run_tc(skel, skel->progs.tc_exceed_mtu, mtu);
test_check_mtu_run_tc(skel, skel->progs.tc_exceed_mtu_da, mtu);
test_check_mtu_run_tc(skel, skel->progs.tc_minus_delta, mtu);
+ test_check_mtu_run_tc(skel, skel->progs.tc_input_len, mtu);
+ test_check_mtu_run_tc(skel, skel->progs.tc_input_len_exceed, mtu);
cleanup:
test_check_mtu__destroy(skel);
}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#define _GNU_SOURCE
+#include <sched.h>
+#include <test_progs.h>
+#include <time.h>
+#include <sys/mman.h>
+#include <sys/syscall.h>
+#include "fexit_sleep.skel.h"
+
+static int do_sleep(void *skel)
+{
+ struct fexit_sleep *fexit_skel = skel;
+ struct timespec ts1 = { .tv_nsec = 1 };
+ struct timespec ts2 = { .tv_sec = 10 };
+
+ fexit_skel->bss->pid = getpid();
+ (void)syscall(__NR_nanosleep, &ts1, NULL);
+ (void)syscall(__NR_nanosleep, &ts2, NULL);
+ return 0;
+}
+
+#define STACK_SIZE (1024 * 1024)
+static char child_stack[STACK_SIZE];
+
+void test_fexit_sleep(void)
+{
+ struct fexit_sleep *fexit_skel = NULL;
+ int wstatus, duration = 0;
+ pid_t cpid;
+ int err, fexit_cnt;
+
+ fexit_skel = fexit_sleep__open_and_load();
+ if (CHECK(!fexit_skel, "fexit_skel_load", "fexit skeleton failed\n"))
+ goto cleanup;
+
+ err = fexit_sleep__attach(fexit_skel);
+ if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err))
+ goto cleanup;
+
+ cpid = clone(do_sleep, child_stack + STACK_SIZE, CLONE_FILES | SIGCHLD, fexit_skel);
+ if (CHECK(cpid == -1, "clone", strerror(errno)))
+ goto cleanup;
+
+ /* wait until first sys_nanosleep ends and second sys_nanosleep starts */
+ while (READ_ONCE(fexit_skel->bss->fentry_cnt) != 2);
+ fexit_cnt = READ_ONCE(fexit_skel->bss->fexit_cnt);
+ if (CHECK(fexit_cnt != 1, "fexit_cnt", "%d", fexit_cnt))
+ goto cleanup;
+
+ /* close progs and detach them. That will trigger two nop5->jmp5 rewrites
+ * in the trampolines to skip nanosleep_fexit prog.
+ * The nanosleep_fentry prog will get detached first.
+ * The nanosleep_fexit prog will get detached second.
+ * Detaching will trigger freeing of both progs JITed images.
+ * There will be two dying bpf_tramp_image-s, but only the initial
+ * bpf_tramp_image (with both _fentry and _fexit progs will be stuck
+ * waiting for percpu_ref_kill to confirm). The other one
+ * will be freed quickly.
+ */
+ close(bpf_program__fd(fexit_skel->progs.nanosleep_fentry));
+ close(bpf_program__fd(fexit_skel->progs.nanosleep_fexit));
+ fexit_sleep__detach(fexit_skel);
+
+ /* kill the thread to unwind sys_nanosleep stack through the trampoline */
+ kill(cpid, 9);
+
+ if (CHECK(waitpid(cpid, &wstatus, 0) == -1, "waitpid", strerror(errno)))
+ goto cleanup;
+ if (CHECK(WEXITSTATUS(wstatus) != 0, "exitstatus", "failed"))
+ goto cleanup;
+
+ /* The bypassed nanosleep_fexit prog shouldn't have executed.
+ * Unlike progs the maps were not freed and directly accessible.
+ */
+ fexit_cnt = READ_ONCE(fexit_skel->bss->fexit_cnt);
+ if (CHECK(fexit_cnt != 1, "fexit_cnt", "%d", fexit_cnt))
+ goto cleanup;
+
+cleanup:
+ fexit_sleep__destroy(fexit_skel);
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <linux/types.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "X";
+
+void BPF_STRUCT_OPS(nogpltcp_init, struct sock *sk)
+{
+}
+
+SEC(".struct_ops")
+struct tcp_congestion_ops bpf_nogpltcp = {
+ .init = (void *)nogpltcp_init,
+ .name = "bpf_nogpltcp",
+};
};
};
+struct struct_in_array {};
+
+struct struct_in_array_typed {};
+
+typedef struct struct_in_array_typed struct_in_array_t[2];
+
struct struct_with_embedded_stuff {
int a;
struct {
} r[5];
struct struct_in_struct s[10];
int t[11];
+ struct struct_in_array (*u)[2];
+ struct_in_array_t *v;
};
struct root_struct {
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char LICENSE[] SEC("license") = "GPL";
+
+int pid = 0;
+int fentry_cnt = 0;
+int fexit_cnt = 0;
+
+SEC("fentry/__x64_sys_nanosleep")
+int BPF_PROG(nanosleep_fentry, const struct pt_regs *regs)
+{
+ if ((int)bpf_get_current_pid_tgid() != pid)
+ return 0;
+
+ fentry_cnt++;
+ return 0;
+}
+
+SEC("fexit/__x64_sys_nanosleep")
+int BPF_PROG(nanosleep_fexit, const struct pt_regs *regs, int ret)
+{
+ if ((int)bpf_get_current_pid_tgid() != pid)
+ return 0;
+
+ fexit_cnt++;
+ return 0;
+}
#define STRSIZE 2048
#define EXPECTED_STRSIZE 256
+#if defined(bpf_target_s390)
+/* NULL points to a readable struct lowcore on s390, so take the last page */
+#define BADPTR ((void *)0xFFFFFFFFFFFFF000ULL)
+#else
+#define BADPTR 0
+#endif
+
#ifndef ARRAY_SIZE
#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
#endif
}
/* Check invalid ptr value */
- p.ptr = 0;
+ p.ptr = BADPTR;
__ret = bpf_snprintf_btf(str, STRSIZE, &p, sizeof(p), 0);
if (__ret >= 0) {
- bpf_printk("printing NULL should generate error, got (%d)",
- __ret);
+ bpf_printk("printing %llx should generate error, got (%d)",
+ (unsigned long long)BADPTR, __ret);
ret = -ERANGE;
}
return retval;
}
+SEC("xdp")
+int xdp_input_len(struct xdp_md *ctx)
+{
+ int retval = XDP_PASS; /* Expected retval on successful test */
+ void *data_end = (void *)(long)ctx->data_end;
+ void *data = (void *)(long)ctx->data;
+ __u32 ifindex = GLOBAL_USER_IFINDEX;
+ __u32 data_len = data_end - data;
+
+ /* API allow user give length to check as input via mtu_len param,
+ * resulting MTU value is still output in mtu_len param after call.
+ *
+ * Input len is L3, like MTU and iph->tot_len.
+ * Remember XDP data_len is L2.
+ */
+ __u32 mtu_len = data_len - ETH_HLEN;
+
+ if (bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0))
+ retval = XDP_ABORTED;
+
+ global_bpf_mtu_xdp = mtu_len;
+ return retval;
+}
+
+SEC("xdp")
+int xdp_input_len_exceed(struct xdp_md *ctx)
+{
+ int retval = XDP_ABORTED; /* Fail */
+ __u32 ifindex = GLOBAL_USER_IFINDEX;
+ int err;
+
+ /* API allow user give length to check as input via mtu_len param,
+ * resulting MTU value is still output in mtu_len param after call.
+ *
+ * Input length value is L3 size like MTU.
+ */
+ __u32 mtu_len = GLOBAL_USER_MTU;
+
+ mtu_len += 1; /* Exceed with 1 */
+
+ err = bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0);
+ if (err == BPF_MTU_CHK_RET_FRAG_NEEDED)
+ retval = XDP_PASS ; /* Success in exceeding MTU check */
+
+ global_bpf_mtu_xdp = mtu_len;
+ return retval;
+}
+
SEC("classifier")
int tc_use_helper(struct __sk_buff *ctx)
{
global_bpf_mtu_xdp = mtu_len;
return retval;
}
+
+SEC("classifier")
+int tc_input_len(struct __sk_buff *ctx)
+{
+ int retval = BPF_OK; /* Expected retval on successful test */
+ __u32 ifindex = GLOBAL_USER_IFINDEX;
+
+ /* API allow user give length to check as input via mtu_len param,
+ * resulting MTU value is still output in mtu_len param after call.
+ *
+ * Input length value is L3 size.
+ */
+ __u32 mtu_len = GLOBAL_USER_MTU;
+
+ if (bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0))
+ retval = BPF_DROP;
+
+ global_bpf_mtu_xdp = mtu_len;
+ return retval;
+}
+
+SEC("classifier")
+int tc_input_len_exceed(struct __sk_buff *ctx)
+{
+ int retval = BPF_DROP; /* Fail */
+ __u32 ifindex = GLOBAL_USER_IFINDEX;
+ int err;
+
+ /* API allow user give length to check as input via mtu_len param,
+ * resulting MTU value is still output in mtu_len param after call.
+ *
+ * Input length value is L3 size like MTU.
+ */
+ __u32 mtu_len = GLOBAL_USER_MTU;
+
+ mtu_len += 1; /* Exceed with 1 */
+
+ err = bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0);
+ if (err == BPF_MTU_CHK_RET_FRAG_NEEDED)
+ retval = BPF_OK; /* Success in exceeding MTU check */
+
+ global_bpf_mtu_xdp = mtu_len;
+ return retval;
+}
SEC("cgroup_skb/ingress")
int test_cls(struct __sk_buff *skb)
{
- return foo(skb);
+ return foo((const void *)skb);
}
}
ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt));
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
+ if (ret < 0)
+ gopt.opt_class = 0;
bpf_trace_printk(fmt, sizeof(fmt),
key.tunnel_id, key.remote_ipv4, gopt.opt_class);
}
ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt));
- if (ret < 0) {
- ERROR(ret);
- return TC_ACT_SHOT;
- }
+ if (ret < 0)
+ gopt.opt_class = 0;
bpf_trace_printk(fmt, sizeof(fmt),
key.tunnel_id, key.remote_ipv4, gopt.opt_class);
BPF_MOV64_IMM(BPF_REG_5, 0),
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
BPF_FUNC_csum_diff),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xffff),
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.fixup_map_array_ro = { 3 },
.result = ACCEPT,
- .retval = -29,
+ .retval = 65507,
},
{
"invalid write map access into a read-only array 1",
},
.result = ACCEPT,
},
+{
+ "BPF_ATOMIC_AND with fetch - r0 as source reg",
+ .insns = {
+ /* val = 0x110; */
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0x110),
+ /* old = atomic_fetch_and(&val, 0x011); */
+ BPF_MOV64_IMM(BPF_REG_0, 0x011),
+ BPF_ATOMIC_OP(BPF_DW, BPF_AND | BPF_FETCH, BPF_REG_10, BPF_REG_0, -8),
+ /* if (old != 0x110) exit(3); */
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0x110, 2),
+ BPF_MOV64_IMM(BPF_REG_0, 3),
+ BPF_EXIT_INSN(),
+ /* if (val != 0x010) exit(2); */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -8),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0x010, 2),
+ BPF_MOV64_IMM(BPF_REG_1, 2),
+ BPF_EXIT_INSN(),
+ /* exit(0); */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+},
.result = REJECT,
.errstr = "invalid read from stack",
},
+{
+ "BPF_W cmpxchg should zero top 32 bits",
+ .insns = {
+ /* r0 = U64_MAX; */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_ALU64_IMM(BPF_SUB, BPF_REG_0, 1),
+ /* u64 val = r0; */
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+ /* r0 = (u32)atomic_cmpxchg((u32 *)&val, r0, 1); */
+ BPF_MOV32_IMM(BPF_REG_1, 1),
+ BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, BPF_REG_10, BPF_REG_1, -8),
+ /* r1 = 0x00000000FFFFFFFFull; */
+ BPF_MOV64_IMM(BPF_REG_1, 1),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 32),
+ BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 1),
+ /* if (r0 != r1) exit(1); */
+ BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_1, 2),
+ BPF_MOV32_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ /* exit(0); */
+ BPF_MOV32_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+},
},
.result = ACCEPT,
},
+{
+ "BPF_W atomic_fetch_or should zero top 32 bits",
+ .insns = {
+ /* r1 = U64_MAX; */
+ BPF_MOV64_IMM(BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_SUB, BPF_REG_1, 1),
+ /* u64 val = r1; */
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_1, -8),
+ /* r1 = (u32)atomic_fetch_or((u32 *)&val, 2); */
+ BPF_MOV32_IMM(BPF_REG_1, 2),
+ BPF_ATOMIC_OP(BPF_W, BPF_OR | BPF_FETCH, BPF_REG_10, BPF_REG_1, -8),
+ /* r2 = 0x00000000FFFFFFFF; */
+ BPF_MOV64_IMM(BPF_REG_2, 1),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_2, 32),
+ BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 1),
+ /* if (r2 != r1) exit(1); */
+ BPF_JMP_REG(BPF_JEQ, BPF_REG_2, BPF_REG_1, 2),
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+ BPF_EXIT_INSN(),
+ /* exit(0); */
+ BPF_MOV32_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+},
},
.fixup_map_hash_8b = { 3 },
/* not actually fully unbounded, but the bound is very high */
- .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root",
- .result_unpriv = REJECT,
.errstr = "value -4294967168 makes map_value pointer be out of bounds",
.result = REJECT,
},
BPF_EXIT_INSN(),
},
.fixup_map_hash_8b = { 3 },
- /* not actually fully unbounded, but the bound is very high */
- .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root",
- .result_unpriv = REJECT,
.errstr = "value -4294967168 makes map_value pointer be out of bounds",
.result = REJECT,
},
BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
BPF_EXIT_INSN(),
},
- .result = REJECT,
+ .errstr_unpriv = "R1 has pointer with unsupported alu operation",
.errstr = "R0 tried to subtract pointer from scalar",
+ .result = REJECT,
},
{
"check deducing bounds from const, 2",
BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R1 has pointer with unsupported alu operation",
+ .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 1,
},
BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
BPF_EXIT_INSN(),
},
- .result = REJECT,
+ .errstr_unpriv = "R1 has pointer with unsupported alu operation",
.errstr = "R0 tried to subtract pointer from scalar",
+ .result = REJECT,
},
{
"check deducing bounds from const, 4",
.insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_JMP_IMM(BPF_JSLE, BPF_REG_0, 0, 1),
BPF_EXIT_INSN(),
BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 1),
BPF_EXIT_INSN(),
- BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_6, BPF_REG_0),
BPF_EXIT_INSN(),
},
+ .errstr_unpriv = "R6 has pointer with unsupported alu operation",
+ .result_unpriv = REJECT,
.result = ACCEPT,
},
{
BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
BPF_EXIT_INSN(),
},
- .result = REJECT,
+ .errstr_unpriv = "R1 has pointer with unsupported alu operation",
.errstr = "R0 tried to subtract pointer from scalar",
+ .result = REJECT,
},
{
"check deducing bounds from const, 6",
BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
BPF_EXIT_INSN(),
},
- .result = REJECT,
+ .errstr_unpriv = "R1 has pointer with unsupported alu operation",
.errstr = "R0 tried to subtract pointer from scalar",
+ .result = REJECT,
},
{
"check deducing bounds from const, 7",
offsetof(struct __sk_buff, mark)),
BPF_EXIT_INSN(),
},
- .result = REJECT,
+ .errstr_unpriv = "R1 has pointer with unsupported alu operation",
.errstr = "dereference of modified ctx ptr",
+ .result = REJECT,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
offsetof(struct __sk_buff, mark)),
BPF_EXIT_INSN(),
},
- .result = REJECT,
+ .errstr_unpriv = "R1 has pointer with unsupported alu operation",
.errstr = "dereference of modified ctx ptr",
+ .result = REJECT,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
BPF_EXIT_INSN(),
},
- .result = REJECT,
+ .errstr_unpriv = "R1 has pointer with unsupported alu operation",
.errstr = "R0 tried to subtract pointer from scalar",
+ .result = REJECT,
},
{
"check deducing bounds from const, 10",
BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
BPF_EXIT_INSN(),
},
- .result = REJECT,
.errstr = "math between ctx pointer and register with unbounded min value is not allowed",
+ .result = REJECT,
},
},
.fixup_map_hash_8b = { 3 },
.errstr = "unbounded min value",
- .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
.result = REJECT,
},
{
},
.fixup_map_hash_8b = { 3 },
.errstr = "unbounded min value",
- .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
.result = REJECT,
},
{
},
.fixup_map_hash_8b = { 3 },
.errstr = "unbounded min value",
- .errstr_unpriv = "R8 has unknown scalar with mixed signed bounds",
.result = REJECT,
},
{
},
.fixup_map_hash_8b = { 3 },
.errstr = "unbounded min value",
- .errstr_unpriv = "R8 has unknown scalar with mixed signed bounds",
.result = REJECT,
},
{
},
.fixup_map_hash_8b = { 3 },
.errstr = "unbounded min value",
- .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
.result = REJECT,
},
{
},
.fixup_map_hash_8b = { 3 },
.errstr = "unbounded min value",
- .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
.result = REJECT,
},
{
},
.fixup_map_hash_8b = { 3 },
.errstr = "unbounded min value",
- .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
.result = REJECT,
},
{
},
.fixup_map_hash_8b = { 3 },
.errstr = "unbounded min value",
- .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
.result = REJECT,
},
{
},
.fixup_map_hash_8b = { 3 },
.errstr = "unbounded min value",
- .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
.result = REJECT,
},
{
},
.fixup_map_hash_8b = { 3 },
.errstr = "unbounded min value",
- .errstr_unpriv = "R7 has unknown scalar with mixed signed bounds",
.result = REJECT,
},
{
},
.fixup_map_hash_8b = { 4 },
.errstr = "unbounded min value",
- .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
.result = REJECT,
},
{
},
.fixup_map_hash_8b = { 3 },
.errstr = "unbounded min value",
- .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds",
.result = REJECT,
- .result_unpriv = REJECT,
},
BPF_EXIT_INSN(),
},
.fixup_map_hash_16b = { 4 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R1 has pointer with unsupported alu operation",
.result = ACCEPT,
},
{
BPF_EXIT_INSN(),
},
.fixup_map_hash_16b = { 4 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R0 has pointer with unsupported alu operation",
.result = ACCEPT,
},
.result = ACCEPT,
},
{
- "unpriv: adding of fp",
+ "unpriv: adding of fp, reg",
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_MOV64_IMM(BPF_REG_1, 0),
.result = ACCEPT,
},
{
+ "unpriv: adding of fp, imm",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0),
+ BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8),
+ BPF_EXIT_INSN(),
+ },
+ .errstr_unpriv = "R1 stack pointer arithmetic goes out of range",
+ .result_unpriv = REJECT,
+ .result = ACCEPT,
+},
+{
"unpriv: cmp of stack pointer",
.insns = {
BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
.fixup_map_hash_16b = { 5 },
.fixup_map_array_48b = { 8 },
.result = ACCEPT,
- .result_unpriv = REJECT,
- .errstr_unpriv = "R1 tried to add from different maps",
.retval = 1,
},
{
.fixup_map_array_48b = { 1 },
.result = ACCEPT,
.result_unpriv = REJECT,
- .errstr_unpriv = "R2 tried to add from different pointers or scalars",
+ .errstr_unpriv = "R2 tried to add from different maps, paths or scalars",
.retval = 0,
},
{
.fixup_map_array_48b = { 1 },
.result = ACCEPT,
.result_unpriv = REJECT,
- .errstr_unpriv = "R2 tried to add from different maps or paths",
+ .errstr_unpriv = "R2 tried to add from different maps, paths or scalars",
.retval = 0,
},
{
.retval = 0xabcdef12,
},
{
+ "map access: value_ptr += N, value_ptr -= N known scalar",
+ .insns = {
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+ BPF_MOV32_IMM(BPF_REG_1, 0x12345678),
+ BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 2),
+ BPF_MOV64_IMM(BPF_REG_1, 2),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 3 },
+ .result = ACCEPT,
+ .retval = 0x12345678,
+},
+{
"map access: unknown scalar += value_ptr, 1",
.insns = {
BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
# SPDX-License-Identifier: GPL-2.0-only
-gpio-mockup-chardev
+gpio-mockup-cdev
/x86_64/debug_regs
/x86_64/evmcs_test
/x86_64/get_cpuid_test
+/x86_64/get_msr_index_features
/x86_64/kvm_pv_test
+/x86_64/hyperv_clock
/x86_64/hyperv_cpuid
/x86_64/mmio_warning_test
/x86_64/platform_info_test
+/x86_64/set_boot_cpu_id
/x86_64/set_sregs_test
/x86_64/smm_test
/x86_64/state_test
LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c
TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test
+TEST_GEN_PROGS_x86_64 += x86_64/get_msr_index_features
TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
TEST_GEN_PROGS_x86_64 += x86_64/get_cpuid_test
+TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock
TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test
TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test
TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test
+TEST_GEN_PROGS_x86_64 += x86_64/set_boot_cpu_id
TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test
TEST_GEN_PROGS_x86_64 += x86_64/smm_test
TEST_GEN_PROGS_x86_64 += x86_64/state_test
kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
vm_create_irqchip(vm);
- fprintf(stderr, "%s: [%d] start vcpus\n", __func__, run);
+ pr_debug("%s: [%d] start vcpus\n", __func__, run);
for (i = 0; i < VCPU_NUM; ++i) {
vm_vcpu_add_default(vm, i, guest_code);
payloads[i].vm = vm;
check_set_affinity(throw_away, &cpu_set);
}
}
- fprintf(stderr, "%s: [%d] all threads launched\n", __func__, run);
+ pr_debug("%s: [%d] all threads launched\n", __func__, run);
sem_post(sem);
for (i = 0; i < VCPU_NUM; ++i)
check_join(threads[i], &b);
if (pid == 0)
run_test(i); /* This function always exits */
- fprintf(stderr, "%s: [%d] waiting semaphore\n", __func__, i);
+ pr_debug("%s: [%d] waiting semaphore\n", __func__, i);
sem_wait(sem);
r = (rand() % DELAY_US_MAX) + 1;
- fprintf(stderr, "%s: [%d] waiting %dus\n", __func__, i, r);
+ pr_debug("%s: [%d] waiting %dus\n", __func__, i, r);
usleep(r);
r = waitpid(pid, &s, WNOHANG);
TEST_ASSERT(r != pid,
"%s: [%d] child exited unexpectedly status: [%d]",
__func__, i, s);
- fprintf(stderr, "%s: [%d] killing child\n", __func__, i);
+ pr_debug("%s: [%d] killing child\n", __func__, i);
kill(pid, SIGKILL);
}
#include "sparsebit.h"
+#define KVM_DEV_PATH "/dev/kvm"
#define KVM_MAX_VCPUS 512
/*
int _vcpu_ioctl(struct kvm_vm *vm, uint32_t vcpuid, unsigned long ioctl,
void *arg);
void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
+int _vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg);
void kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
int _kvm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
{
int ret;
- ret = ioctl(vm->fd, cmd, arg);
+ ret = _vm_ioctl(vm, cmd, arg);
TEST_ASSERT(ret == 0, "vm ioctl %lu failed, rc: %i errno: %i (%s)",
cmd, ret, errno, strerror(errno));
}
+int _vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg)
+{
+ return ioctl(vm->fd, cmd, arg);
+}
+
/*
* KVM system ioctl
*
#include "sparsebit.h"
-#define KVM_DEV_PATH "/dev/kvm"
-
struct userspace_mem_region {
struct kvm_userspace_memory_region region;
struct sparsebit *unused_phy_pages;
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test that KVM_GET_MSR_INDEX_LIST and
+ * KVM_GET_MSR_FEATURE_INDEX_LIST work as intended
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+static int kvm_num_index_msrs(int kvm_fd, int nmsrs)
+{
+ struct kvm_msr_list *list;
+ int r;
+
+ list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
+ list->nmsrs = nmsrs;
+ r = ioctl(kvm_fd, KVM_GET_MSR_INDEX_LIST, list);
+ TEST_ASSERT(r == -1 && errno == E2BIG,
+ "Unexpected result from KVM_GET_MSR_INDEX_LIST probe, r: %i",
+ r);
+
+ r = list->nmsrs;
+ free(list);
+ return r;
+}
+
+static void test_get_msr_index(void)
+{
+ int old_res, res, kvm_fd, r;
+ struct kvm_msr_list *list;
+
+ kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
+ if (kvm_fd < 0)
+ exit(KSFT_SKIP);
+
+ old_res = kvm_num_index_msrs(kvm_fd, 0);
+ TEST_ASSERT(old_res != 0, "Expecting nmsrs to be > 0");
+
+ if (old_res != 1) {
+ res = kvm_num_index_msrs(kvm_fd, 1);
+ TEST_ASSERT(res > 1, "Expecting nmsrs to be > 1");
+ TEST_ASSERT(res == old_res, "Expecting nmsrs to be identical");
+ }
+
+ list = malloc(sizeof(*list) + old_res * sizeof(list->indices[0]));
+ list->nmsrs = old_res;
+ r = ioctl(kvm_fd, KVM_GET_MSR_INDEX_LIST, list);
+
+ TEST_ASSERT(r == 0,
+ "Unexpected result from KVM_GET_MSR_FEATURE_INDEX_LIST, r: %i",
+ r);
+ TEST_ASSERT(list->nmsrs == old_res, "Expecting nmsrs to be identical");
+ free(list);
+
+ close(kvm_fd);
+}
+
+static int kvm_num_feature_msrs(int kvm_fd, int nmsrs)
+{
+ struct kvm_msr_list *list;
+ int r;
+
+ list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
+ list->nmsrs = nmsrs;
+ r = ioctl(kvm_fd, KVM_GET_MSR_FEATURE_INDEX_LIST, list);
+ TEST_ASSERT(r == -1 && errno == E2BIG,
+ "Unexpected result from KVM_GET_MSR_FEATURE_INDEX_LIST probe, r: %i",
+ r);
+
+ r = list->nmsrs;
+ free(list);
+ return r;
+}
+
+struct kvm_msr_list *kvm_get_msr_feature_list(int kvm_fd, int nmsrs)
+{
+ struct kvm_msr_list *list;
+ int r;
+
+ list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
+ list->nmsrs = nmsrs;
+ r = ioctl(kvm_fd, KVM_GET_MSR_FEATURE_INDEX_LIST, list);
+
+ TEST_ASSERT(r == 0,
+ "Unexpected result from KVM_GET_MSR_FEATURE_INDEX_LIST, r: %i",
+ r);
+
+ return list;
+}
+
+static void test_get_msr_feature(void)
+{
+ int res, old_res, i, kvm_fd;
+ struct kvm_msr_list *feature_list;
+
+ kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
+ if (kvm_fd < 0)
+ exit(KSFT_SKIP);
+
+ old_res = kvm_num_feature_msrs(kvm_fd, 0);
+ TEST_ASSERT(old_res != 0, "Expecting nmsrs to be > 0");
+
+ if (old_res != 1) {
+ res = kvm_num_feature_msrs(kvm_fd, 1);
+ TEST_ASSERT(res > 1, "Expecting nmsrs to be > 1");
+ TEST_ASSERT(res == old_res, "Expecting nmsrs to be identical");
+ }
+
+ feature_list = kvm_get_msr_feature_list(kvm_fd, old_res);
+ TEST_ASSERT(old_res == feature_list->nmsrs,
+ "Unmatching number of msr indexes");
+
+ for (i = 0; i < feature_list->nmsrs; i++)
+ kvm_get_feature_msr(feature_list->indices[i]);
+
+ free(feature_list);
+ close(kvm_fd);
+}
+
+int main(int argc, char *argv[])
+{
+ if (kvm_check_cap(KVM_CAP_GET_MSR_FEATURES))
+ test_get_msr_feature();
+
+ test_get_msr_index();
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021, Red Hat, Inc.
+ *
+ * Tests for Hyper-V clocksources
+ */
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+struct ms_hyperv_tsc_page {
+ volatile u32 tsc_sequence;
+ u32 reserved1;
+ volatile u64 tsc_scale;
+ volatile s64 tsc_offset;
+} __packed;
+
+#define HV_X64_MSR_GUEST_OS_ID 0x40000000
+#define HV_X64_MSR_TIME_REF_COUNT 0x40000020
+#define HV_X64_MSR_REFERENCE_TSC 0x40000021
+#define HV_X64_MSR_TSC_FREQUENCY 0x40000022
+#define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106
+#define HV_X64_MSR_TSC_EMULATION_CONTROL 0x40000107
+
+/* Simplified mul_u64_u64_shr() */
+static inline u64 mul_u64_u64_shr64(u64 a, u64 b)
+{
+ union {
+ u64 ll;
+ struct {
+ u32 low, high;
+ } l;
+ } rm, rn, rh, a0, b0;
+ u64 c;
+
+ a0.ll = a;
+ b0.ll = b;
+
+ rm.ll = (u64)a0.l.low * b0.l.high;
+ rn.ll = (u64)a0.l.high * b0.l.low;
+ rh.ll = (u64)a0.l.high * b0.l.high;
+
+ rh.l.low = c = rm.l.high + rn.l.high + rh.l.low;
+ rh.l.high = (c >> 32) + rh.l.high;
+
+ return rh.ll;
+}
+
+static inline void nop_loop(void)
+{
+ int i;
+
+ for (i = 0; i < 1000000; i++)
+ asm volatile("nop");
+}
+
+static inline void check_tsc_msr_rdtsc(void)
+{
+ u64 tsc_freq, r1, r2, t1, t2;
+ s64 delta_ns;
+
+ tsc_freq = rdmsr(HV_X64_MSR_TSC_FREQUENCY);
+ GUEST_ASSERT(tsc_freq > 0);
+
+ /* First, check MSR-based clocksource */
+ r1 = rdtsc();
+ t1 = rdmsr(HV_X64_MSR_TIME_REF_COUNT);
+ nop_loop();
+ r2 = rdtsc();
+ t2 = rdmsr(HV_X64_MSR_TIME_REF_COUNT);
+
+ GUEST_ASSERT(r2 > r1 && t2 > t1);
+
+ /* HV_X64_MSR_TIME_REF_COUNT is in 100ns */
+ delta_ns = ((t2 - t1) * 100) - ((r2 - r1) * 1000000000 / tsc_freq);
+ if (delta_ns < 0)
+ delta_ns = -delta_ns;
+
+ /* 1% tolerance */
+ GUEST_ASSERT(delta_ns * 100 < (t2 - t1) * 100);
+}
+
+static inline u64 get_tscpage_ts(struct ms_hyperv_tsc_page *tsc_page)
+{
+ return mul_u64_u64_shr64(rdtsc(), tsc_page->tsc_scale) + tsc_page->tsc_offset;
+}
+
+static inline void check_tsc_msr_tsc_page(struct ms_hyperv_tsc_page *tsc_page)
+{
+ u64 r1, r2, t1, t2;
+
+ /* Compare TSC page clocksource with HV_X64_MSR_TIME_REF_COUNT */
+ t1 = get_tscpage_ts(tsc_page);
+ r1 = rdmsr(HV_X64_MSR_TIME_REF_COUNT);
+
+ /* 10 ms tolerance */
+ GUEST_ASSERT(r1 >= t1 && r1 - t1 < 100000);
+ nop_loop();
+
+ t2 = get_tscpage_ts(tsc_page);
+ r2 = rdmsr(HV_X64_MSR_TIME_REF_COUNT);
+ GUEST_ASSERT(r2 >= t1 && r2 - t2 < 100000);
+}
+
+static void guest_main(struct ms_hyperv_tsc_page *tsc_page, vm_paddr_t tsc_page_gpa)
+{
+ u64 tsc_scale, tsc_offset;
+
+ /* Set Guest OS id to enable Hyper-V emulation */
+ GUEST_SYNC(1);
+ wrmsr(HV_X64_MSR_GUEST_OS_ID, (u64)0x8100 << 48);
+ GUEST_SYNC(2);
+
+ check_tsc_msr_rdtsc();
+
+ GUEST_SYNC(3);
+
+ /* Set up TSC page is disabled state, check that it's clean */
+ wrmsr(HV_X64_MSR_REFERENCE_TSC, tsc_page_gpa);
+ GUEST_ASSERT(tsc_page->tsc_sequence == 0);
+ GUEST_ASSERT(tsc_page->tsc_scale == 0);
+ GUEST_ASSERT(tsc_page->tsc_offset == 0);
+
+ GUEST_SYNC(4);
+
+ /* Set up TSC page is enabled state */
+ wrmsr(HV_X64_MSR_REFERENCE_TSC, tsc_page_gpa | 0x1);
+ GUEST_ASSERT(tsc_page->tsc_sequence != 0);
+
+ GUEST_SYNC(5);
+
+ check_tsc_msr_tsc_page(tsc_page);
+
+ GUEST_SYNC(6);
+
+ tsc_offset = tsc_page->tsc_offset;
+ /* Call KVM_SET_CLOCK from userspace, check that TSC page was updated */
+
+ GUEST_SYNC(7);
+ /* Sanity check TSC page timestamp, it should be close to 0 */
+ GUEST_ASSERT(get_tscpage_ts(tsc_page) < 100000);
+
+ GUEST_ASSERT(tsc_page->tsc_offset != tsc_offset);
+
+ nop_loop();
+
+ /*
+ * Enable Re-enlightenment and check that TSC page stays constant across
+ * KVM_SET_CLOCK.
+ */
+ wrmsr(HV_X64_MSR_REENLIGHTENMENT_CONTROL, 0x1 << 16 | 0xff);
+ wrmsr(HV_X64_MSR_TSC_EMULATION_CONTROL, 0x1);
+ tsc_offset = tsc_page->tsc_offset;
+ tsc_scale = tsc_page->tsc_scale;
+ GUEST_SYNC(8);
+ GUEST_ASSERT(tsc_page->tsc_offset == tsc_offset);
+ GUEST_ASSERT(tsc_page->tsc_scale == tsc_scale);
+
+ GUEST_SYNC(9);
+
+ check_tsc_msr_tsc_page(tsc_page);
+
+ /*
+ * Disable re-enlightenment and TSC page, check that KVM doesn't update
+ * it anymore.
+ */
+ wrmsr(HV_X64_MSR_REENLIGHTENMENT_CONTROL, 0);
+ wrmsr(HV_X64_MSR_TSC_EMULATION_CONTROL, 0);
+ wrmsr(HV_X64_MSR_REFERENCE_TSC, 0);
+ memset(tsc_page, 0, sizeof(*tsc_page));
+
+ GUEST_SYNC(10);
+ GUEST_ASSERT(tsc_page->tsc_sequence == 0);
+ GUEST_ASSERT(tsc_page->tsc_offset == 0);
+ GUEST_ASSERT(tsc_page->tsc_scale == 0);
+
+ GUEST_DONE();
+}
+
+#define VCPU_ID 0
+
+static void host_check_tsc_msr_rdtsc(struct kvm_vm *vm)
+{
+ u64 tsc_freq, r1, r2, t1, t2;
+ s64 delta_ns;
+
+ tsc_freq = vcpu_get_msr(vm, VCPU_ID, HV_X64_MSR_TSC_FREQUENCY);
+ TEST_ASSERT(tsc_freq > 0, "TSC frequency must be nonzero");
+
+ /* First, check MSR-based clocksource */
+ r1 = rdtsc();
+ t1 = vcpu_get_msr(vm, VCPU_ID, HV_X64_MSR_TIME_REF_COUNT);
+ nop_loop();
+ r2 = rdtsc();
+ t2 = vcpu_get_msr(vm, VCPU_ID, HV_X64_MSR_TIME_REF_COUNT);
+
+ TEST_ASSERT(t2 > t1, "Time reference MSR is not monotonic (%ld <= %ld)", t1, t2);
+
+ /* HV_X64_MSR_TIME_REF_COUNT is in 100ns */
+ delta_ns = ((t2 - t1) * 100) - ((r2 - r1) * 1000000000 / tsc_freq);
+ if (delta_ns < 0)
+ delta_ns = -delta_ns;
+
+ /* 1% tolerance */
+ TEST_ASSERT(delta_ns * 100 < (t2 - t1) * 100,
+ "Elapsed time does not match (MSR=%ld, TSC=%ld)",
+ (t2 - t1) * 100, (r2 - r1) * 1000000000 / tsc_freq);
+}
+
+int main(void)
+{
+ struct kvm_vm *vm;
+ struct kvm_run *run;
+ struct ucall uc;
+ vm_vaddr_t tsc_page_gva;
+ int stage;
+
+ vm = vm_create_default(VCPU_ID, 0, guest_main);
+ run = vcpu_state(vm, VCPU_ID);
+
+ vcpu_set_hv_cpuid(vm, VCPU_ID);
+
+ tsc_page_gva = vm_vaddr_alloc(vm, getpagesize(), 0x10000, 0, 0);
+ memset(addr_gpa2hva(vm, tsc_page_gva), 0x0, getpagesize());
+ TEST_ASSERT((addr_gva2gpa(vm, tsc_page_gva) & (getpagesize() - 1)) == 0,
+ "TSC page has to be page aligned\n");
+ vcpu_args_set(vm, VCPU_ID, 2, tsc_page_gva, addr_gva2gpa(vm, tsc_page_gva));
+
+ host_check_tsc_msr_rdtsc(vm);
+
+ for (stage = 1;; stage++) {
+ _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Stage %d: unexpected exit reason: %u (%s),\n",
+ stage, run->exit_reason,
+ exit_reason_str(run->exit_reason));
+
+ switch (get_ucall(vm, VCPU_ID, &uc)) {
+ case UCALL_ABORT:
+ TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],
+ __FILE__, uc.args[1]);
+ /* NOT REACHED */
+ case UCALL_SYNC:
+ break;
+ case UCALL_DONE:
+ /* Keep in sync with guest_main() */
+ TEST_ASSERT(stage == 11, "Testing ended prematurely, stage %d\n",
+ stage);
+ goto out;
+ default:
+ TEST_FAIL("Unknown ucall %lu", uc.cmd);
+ }
+
+ TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
+ uc.args[1] == stage,
+ "Stage %d: Unexpected register values vmexit, got %lx",
+ stage, (ulong)uc.args[1]);
+
+ /* Reset kvmclock triggering TSC page update */
+ if (stage == 7 || stage == 8 || stage == 10) {
+ struct kvm_clock_data clock = {0};
+
+ vm_ioctl(vm, KVM_SET_CLOCK, &clock);
+ }
+ }
+
+out:
+ kvm_vm_free(vm);
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test that KVM_SET_BOOT_CPU_ID works as intended
+ *
+ * Copyright (C) 2020, Red Hat, Inc.
+ */
+#define _GNU_SOURCE /* for program_invocation_name */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+#define N_VCPU 2
+#define VCPU_ID0 0
+#define VCPU_ID1 1
+
+static uint32_t get_bsp_flag(void)
+{
+ return rdmsr(MSR_IA32_APICBASE) & MSR_IA32_APICBASE_BSP;
+}
+
+static void guest_bsp_vcpu(void *arg)
+{
+ GUEST_SYNC(1);
+
+ GUEST_ASSERT(get_bsp_flag() != 0);
+
+ GUEST_DONE();
+}
+
+static void guest_not_bsp_vcpu(void *arg)
+{
+ GUEST_SYNC(1);
+
+ GUEST_ASSERT(get_bsp_flag() == 0);
+
+ GUEST_DONE();
+}
+
+static void test_set_boot_busy(struct kvm_vm *vm)
+{
+ int res;
+
+ res = _vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *) VCPU_ID0);
+ TEST_ASSERT(res == -1 && errno == EBUSY,
+ "KVM_SET_BOOT_CPU_ID set while running vm");
+}
+
+static void run_vcpu(struct kvm_vm *vm, uint32_t vcpuid)
+{
+ struct ucall uc;
+ int stage;
+
+ for (stage = 0; stage < 2; stage++) {
+
+ vcpu_run(vm, vcpuid);
+
+ switch (get_ucall(vm, vcpuid, &uc)) {
+ case UCALL_SYNC:
+ TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") &&
+ uc.args[1] == stage + 1,
+ "Stage %d: Unexpected register values vmexit, got %lx",
+ stage + 1, (ulong)uc.args[1]);
+ test_set_boot_busy(vm);
+ break;
+ case UCALL_DONE:
+ TEST_ASSERT(stage == 1,
+ "Expected GUEST_DONE in stage 2, got stage %d",
+ stage);
+ break;
+ case UCALL_ABORT:
+ TEST_ASSERT(false, "%s at %s:%ld\n\tvalues: %#lx, %#lx",
+ (const char *)uc.args[0], __FILE__,
+ uc.args[1], uc.args[2], uc.args[3]);
+ default:
+ TEST_ASSERT(false, "Unexpected exit: %s",
+ exit_reason_str(vcpu_state(vm, vcpuid)->exit_reason));
+ }
+ }
+}
+
+static struct kvm_vm *create_vm(void)
+{
+ struct kvm_vm *vm;
+ uint64_t vcpu_pages = (DEFAULT_STACK_PGS) * 2;
+ uint64_t extra_pg_pages = vcpu_pages / PTES_PER_MIN_PAGE * N_VCPU;
+ uint64_t pages = DEFAULT_GUEST_PHY_PAGES + vcpu_pages + extra_pg_pages;
+
+ pages = vm_adjust_num_guest_pages(VM_MODE_DEFAULT, pages);
+ vm = vm_create(VM_MODE_DEFAULT, pages, O_RDWR);
+
+ kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+ vm_create_irqchip(vm);
+
+ return vm;
+}
+
+static void add_x86_vcpu(struct kvm_vm *vm, uint32_t vcpuid, bool bsp_code)
+{
+ if (bsp_code)
+ vm_vcpu_add_default(vm, vcpuid, guest_bsp_vcpu);
+ else
+ vm_vcpu_add_default(vm, vcpuid, guest_not_bsp_vcpu);
+
+ vcpu_set_cpuid(vm, vcpuid, kvm_get_supported_cpuid());
+}
+
+static void run_vm_bsp(uint32_t bsp_vcpu)
+{
+ struct kvm_vm *vm;
+ bool is_bsp_vcpu1 = bsp_vcpu == VCPU_ID1;
+
+ vm = create_vm();
+
+ if (is_bsp_vcpu1)
+ vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *) VCPU_ID1);
+
+ add_x86_vcpu(vm, VCPU_ID0, !is_bsp_vcpu1);
+ add_x86_vcpu(vm, VCPU_ID1, is_bsp_vcpu1);
+
+ run_vcpu(vm, VCPU_ID0);
+ run_vcpu(vm, VCPU_ID1);
+
+ kvm_vm_free(vm);
+}
+
+static void check_set_bsp_busy(void)
+{
+ struct kvm_vm *vm;
+ int res;
+
+ vm = create_vm();
+
+ add_x86_vcpu(vm, VCPU_ID0, true);
+ add_x86_vcpu(vm, VCPU_ID1, false);
+
+ res = _vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *) VCPU_ID1);
+ TEST_ASSERT(res == -1 && errno == EBUSY, "KVM_SET_BOOT_CPU_ID set after adding vcpu");
+
+ run_vcpu(vm, VCPU_ID0);
+ run_vcpu(vm, VCPU_ID1);
+
+ res = _vm_ioctl(vm, KVM_SET_BOOT_CPU_ID, (void *) VCPU_ID1);
+ TEST_ASSERT(res == -1 && errno == EBUSY, "KVM_SET_BOOT_CPU_ID set to a terminated vcpu");
+
+ kvm_vm_free(vm);
+}
+
+int main(int argc, char *argv[])
+{
+ if (!kvm_check_cap(KVM_CAP_SET_BOOT_CPU_ID)) {
+ print_skip("set_boot_cpu_id not available");
+ return 0;
+ }
+
+ run_vm_bsp(VCPU_ID0);
+ run_vm_bsp(VCPU_ID1);
+ run_vm_bsp(VCPU_ID0);
+
+ check_set_bsp_busy();
+}
*.sh
!run.sh
+!stack-entropy.sh
# NOTE: $(OUTPUT) won't get default value if used before lib.mk
TEST_FILES := tests.txt
+TEST_PROGS := stack-entropy.sh
TEST_GEN_PROGS = $(patsubst %,$(OUTPUT)/%.sh,$(shell awk '{print $$1}' tests.txt | sed -e 's/\#//'))
all: $(TEST_GEN_PROGS)
--- /dev/null
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Measure kernel stack entropy by sampling via LKDTM's REPORT_STACK test.
+set -e
+samples="${1:-1000}"
+
+# Capture dmesg continuously since it may fill up depending on sample size.
+log=$(mktemp -t stack-entropy-XXXXXX)
+dmesg --follow >"$log" & pid=$!
+report=-1
+for i in $(seq 1 $samples); do
+ echo "REPORT_STACK" >/sys/kernel/debug/provoke-crash/DIRECT
+ if [ -t 1 ]; then
+ percent=$(( 100 * $i / $samples ))
+ if [ "$percent" -ne "$report" ]; then
+ /bin/echo -en "$percent%\r"
+ report="$percent"
+ fi
+ fi
+done
+kill "$pid"
+
+# Count unique offsets since last run.
+seen=$(tac "$log" | grep -m1 -B"$samples"0 'Starting stack offset' | \
+ grep 'Stack offset' | awk '{print $NF}' | sort | uniq -c | wc -l)
+bits=$(echo "obase=2; $seen" | bc | wc -L)
+echo "Bits of stack entropy: $bits"
+rm -f "$log"
+
+# We would expect any functional stack randomization to be at least 5 bits.
+if [ "$bits" -lt 5 ]; then
+ exit 1
+else
+ exit 0
+fi
run_cmd "$IP nexthop replace id 2 blackhole dev veth1"
log_test $? 2 "Blackhole nexthop with other attributes"
+ # blackhole nexthop should not be affected by the state of the loopback
+ # device
+ run_cmd "$IP link set dev lo down"
+ check_nexthop "id 2" "id 2 blackhole"
+ log_test $? 0 "Blackhole nexthop with loopback device down"
+
+ run_cmd "$IP link set dev lo up"
+
#
# groups
#
test_gretap_stp()
{
+ # Sometimes after mirror installation, the neighbor's state is not valid.
+ # The reason is that there is no SW datapath activity related to the
+ # neighbor for the remote GRE address. Therefore whether the corresponding
+ # neighbor will be valid is a matter of luck, and the test is thus racy.
+ # Set the neighbor's state to permanent, so it would be always valid.
+ ip neigh replace 192.0.2.130 lladdr $(mac_get $h3) \
+ nud permanent dev br2
full_test_span_gre_stp gt4 $swp3.555 "mirror to gretap"
}
test_ip6gretap_stp()
{
+ ip neigh replace 2001:db8:2::2 lladdr $(mac_get $h3) \
+ nud permanent dev br2
full_test_span_gre_stp gt6 $swp3.555 "mirror to ip6gretap"
}
{
# In accordance with INET_ECN_decapsulate()
__test_ecn_decap 00 00 0x00
+ __test_ecn_decap 00 01 0x00
+ __test_ecn_decap 00 02 0x00
+ # 00 03 is tested in test_ecn_decap_error()
+ __test_ecn_decap 01 00 0x01
__test_ecn_decap 01 01 0x01
- __test_ecn_decap 02 01 0x02
+ __test_ecn_decap 01 02 0x01
__test_ecn_decap 01 03 0x03
+ __test_ecn_decap 02 00 0x02
+ __test_ecn_decap 02 01 0x01
+ __test_ecn_decap 02 02 0x02
__test_ecn_decap 02 03 0x03
+ __test_ecn_decap 03 00 0x03
+ __test_ecn_decap 03 01 0x03
+ __test_ecn_decap 03 02 0x03
+ __test_ecn_decap 03 03 0x03
test_ecn_decap_error
}
break;
default:
printk("got unknown msg type %d", msg->type);
- };
+ }
}
static int grand_child_f(unsigned int nr, int cmd_fd, void *buf)
timeout=30
mptcp_connect=""
capture=0
+do_all_tests=1
TEST_COUNT=0
-j DROP
}
-for arg in "$@"; do
- if [ "$arg" = "-c" ]; then
- capture=1
- fi
-done
-
ip -Version > /dev/null 2>&1
if [ $? -ne 0 ];then
echo "SKIP: Could not run test without ip tool"
echo " -4 v4mapped_tests"
echo " -b backup_tests"
echo " -p add_addr_ports_tests"
- echo " -c syncookies_tests"
+ echo " -k syncookies_tests"
+ echo " -c capture pcap files"
echo " -h help"
}
make_file "$sin" "server" 1
trap cleanup EXIT
-if [ -z $1 ]; then
+for arg in "$@"; do
+ # check for "capture" arg before launching tests
+ if [[ "${arg}" =~ ^"-"[0-9a-zA-Z]*"c"[0-9a-zA-Z]*$ ]]; then
+ capture=1
+ fi
+
+ # exception for the capture option, the rest means: a part of the tests
+ if [ "${arg}" != "-c" ]; then
+ do_all_tests=0
+ fi
+done
+
+if [ $do_all_tests -eq 1 ]; then
all_tests
exit $ret
fi
-while getopts 'fsltra64bpch' opt; do
+while getopts 'fsltra64bpkch' opt; do
case $opt in
f)
subflows_tests
p)
add_addr_ports_tests
;;
- c)
+ k)
syncookies_tests
;;
+ c)
+ ;;
h | *)
usage
;;
};
struct reuse_opts unreusable_opts[12] = {
- {0, 0, 0, 0},
- {0, 0, 0, 1},
- {0, 0, 1, 0},
- {0, 0, 1, 1},
- {0, 1, 0, 0},
- {0, 1, 0, 1},
- {0, 1, 1, 0},
- {0, 1, 1, 1},
- {1, 0, 0, 0},
- {1, 0, 0, 1},
- {1, 0, 1, 0},
- {1, 0, 1, 1},
+ {{0, 0}, {0, 0}},
+ {{0, 0}, {0, 1}},
+ {{0, 0}, {1, 0}},
+ {{0, 0}, {1, 1}},
+ {{0, 1}, {0, 0}},
+ {{0, 1}, {0, 1}},
+ {{0, 1}, {1, 0}},
+ {{0, 1}, {1, 1}},
+ {{1, 0}, {0, 0}},
+ {{1, 0}, {0, 1}},
+ {{1, 0}, {1, 0}},
+ {{1, 0}, {1, 1}},
};
struct reuse_opts reusable_opts[4] = {
- {1, 1, 0, 0},
- {1, 1, 0, 1},
- {1, 1, 1, 0},
- {1, 1, 1, 1},
+ {{1, 1}, {0, 0}},
+ {{1, 1}, {0, 1}},
+ {{1, 1}, {1, 0}},
+ {{1, 1}, {1, 1}},
};
int bind_port(struct __test_metadata *_metadata, int reuseaddr, int reuseport)
TEST_PROGS := nft_trans_stress.sh nft_nat.sh bridge_brouter.sh \
conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \
nft_concat_range.sh nft_conntrack_helper.sh \
- nft_queue.sh nft_meta.sh \
+ nft_queue.sh nft_meta.sh nf_nat_edemux.sh \
ipip-conntrack-mtu.sh
LDLIBS = -lmnl
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test NAT source port clash resolution
+#
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+ret=0
+
+sfx=$(mktemp -u "XXXXXXXX")
+ns1="ns1-$sfx"
+ns2="ns2-$sfx"
+
+cleanup()
+{
+ ip netns del $ns1
+ ip netns del $ns2
+}
+
+iperf3 -v > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without iperf3"
+ exit $ksft_skip
+fi
+
+iptables --version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without iptables"
+ exit $ksft_skip
+fi
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without ip tool"
+ exit $ksft_skip
+fi
+
+ip netns add "$ns1"
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not create net namespace $ns1"
+ exit $ksft_skip
+fi
+
+trap cleanup EXIT
+
+ip netns add $ns2
+
+# Connect the namespaces using a veth pair
+ip link add name veth2 type veth peer name veth1
+ip link set netns $ns1 dev veth1
+ip link set netns $ns2 dev veth2
+
+ip netns exec $ns1 ip link set up dev lo
+ip netns exec $ns1 ip link set up dev veth1
+ip netns exec $ns1 ip addr add 192.168.1.1/24 dev veth1
+
+ip netns exec $ns2 ip link set up dev lo
+ip netns exec $ns2 ip link set up dev veth2
+ip netns exec $ns2 ip addr add 192.168.1.2/24 dev veth2
+
+# Create a server in one namespace
+ip netns exec $ns1 iperf3 -s > /dev/null 2>&1 &
+iperfs=$!
+
+# Restrict source port to just one so we don't have to exhaust
+# all others.
+ip netns exec $ns2 sysctl -q net.ipv4.ip_local_port_range="10000 10000"
+
+# add a virtual IP using DNAT
+ip netns exec $ns2 iptables -t nat -A OUTPUT -d 10.96.0.1/32 -p tcp --dport 443 -j DNAT --to-destination 192.168.1.1:5201
+
+# ... and route it to the other namespace
+ip netns exec $ns2 ip route add 10.96.0.1 via 192.168.1.1
+
+sleep 1
+
+# add a persistent connection from the other namespace
+ip netns exec $ns2 nc -q 10 -w 10 192.168.1.1 5201 > /dev/null &
+
+sleep 1
+
+# ip daddr:dport will be rewritten to 192.168.1.1 5201
+# NAT must reallocate source port 10000 because
+# 192.168.1.2:10000 -> 192.168.1.1:5201 is already in use
+echo test | ip netns exec $ns2 nc -w 3 -q 3 10.96.0.1 443 >/dev/null
+ret=$?
+
+kill $iperfs
+
+# Check nc can connect to 10.96.0.1:443 (aka 192.168.1.1:5201).
+if [ $ret -eq 0 ]; then
+ echo "PASS: nc can connect via NAT'd address"
+else
+ echo "FAIL: nc cannot connect via NAT'd address"
+ exit 1
+fi
+
+exit 0
#define __aligned(x) __attribute__((__aligned__(x)))
#define __packed __attribute__((packed))
-#include "../../../../arch/x86/kernel/cpu/sgx/arch.h"
+#include "../../../../arch/x86/include/asm/sgx.h"
#include "../../../../arch/x86/include/asm/enclu.h"
#include "../../../../arch/x86/include/uapi/asm/sgx.h"
fd = open(path, O_RDONLY);
if (fd == -1) {
- perror("open()");
+ perror("enclave executable open()");
return false;
}
ret = stat(path, &sb);
if (ret) {
- perror("stat()");
+ perror("enclave executable stat()");
goto err;
}
bin = mmap(NULL, sb.st_size, PROT_READ, MAP_PRIVATE, fd, 0);
if (bin == MAP_FAILED) {
- perror("mmap()");
+ perror("enclave executable mmap()");
goto err;
}
ioc.src = (unsigned long)secs;
rc = ioctl(encl->fd, SGX_IOC_ENCLAVE_CREATE, &ioc);
if (rc) {
- fprintf(stderr, "SGX_IOC_ENCLAVE_CREATE failed: errno=%d\n",
- errno);
+ perror("SGX_IOC_ENCLAVE_CREATE failed");
munmap((void *)secs->base, encl->encl_size);
return false;
}
rc = ioctl(encl->fd, SGX_IOC_ENCLAVE_ADD_PAGES, &ioc);
if (rc < 0) {
- fprintf(stderr, "SGX_IOC_ENCLAVE_ADD_PAGES failed: errno=%d.\n",
- errno);
+ perror("SGX_IOC_ENCLAVE_ADD_PAGES failed");
return false;
}
return true;
}
+
+
bool encl_load(const char *path, struct encl *encl)
{
+ const char device_path[] = "/dev/sgx_enclave";
Elf64_Phdr *phdr_tbl;
off_t src_offset;
Elf64_Ehdr *ehdr;
+ struct stat sb;
+ void *ptr;
int i, j;
int ret;
+ int fd = -1;
memset(encl, 0, sizeof(*encl));
- ret = open("/dev/sgx_enclave", O_RDWR);
- if (ret < 0) {
- fprintf(stderr, "Unable to open /dev/sgx_enclave\n");
+ fd = open(device_path, O_RDWR);
+ if (fd < 0) {
+ perror("Unable to open /dev/sgx_enclave");
+ goto err;
+ }
+
+ ret = stat(device_path, &sb);
+ if (ret) {
+ perror("device file stat()");
+ goto err;
+ }
+
+ /*
+ * This just checks if the /dev file has these permission
+ * bits set. It does not check that the current user is
+ * the owner or in the owning group.
+ */
+ if (!(sb.st_mode & (S_IXUSR | S_IXGRP | S_IXOTH))) {
+ fprintf(stderr, "no execute permissions on device file %s\n", device_path);
+ goto err;
+ }
+
+ ptr = mmap(NULL, PAGE_SIZE, PROT_READ, MAP_SHARED, fd, 0);
+ if (ptr == (void *)-1) {
+ perror("mmap for read");
+ goto err;
+ }
+ munmap(ptr, PAGE_SIZE);
+
+#define ERR_MSG \
+"mmap() succeeded for PROT_READ, but failed for PROT_EXEC.\n" \
+" Check that current user has execute permissions on %s and \n" \
+" that /dev does not have noexec set: mount | grep \"/dev .*noexec\"\n" \
+" If so, remount it executable: mount -o remount,exec /dev\n\n"
+
+ ptr = mmap(NULL, PAGE_SIZE, PROT_EXEC, MAP_SHARED, fd, 0);
+ if (ptr == (void *)-1) {
+ fprintf(stderr, ERR_MSG, device_path);
goto err;
}
+ munmap(ptr, PAGE_SIZE);
- encl->fd = ret;
+ encl->fd = fd;
if (!encl_map_bin(path, encl))
goto err;
return true;
err:
+ if (fd != -1)
+ close(fd);
encl_delete(encl);
return false;
}
area = mmap(NULL, encl_size * 2, PROT_NONE,
MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
if (area == MAP_FAILED) {
- perror("mmap");
+ perror("reservation mmap()");
return false;
}
ioc.sigstruct = (uint64_t)&encl->sigstruct;
ret = ioctl(encl->fd, SGX_IOC_ENCLAVE_INIT, &ioc);
if (ret) {
- fprintf(stderr, "SGX_IOC_ENCLAVE_INIT failed: errno=%d\n",
- errno);
+ perror("SGX_IOC_ENCLAVE_INIT failed");
return false;
}
#include <sys/stat.h>
#include <sys/time.h>
#include <sys/types.h>
+#include <sys/auxv.h>
#include "defines.h"
#include "main.h"
#include "../kselftest.h"
Elf64_Word *elf_hashtab;
};
-static void *vdso_get_base_addr(char *envp[])
-{
- Elf64_auxv_t *auxv;
- int i;
-
- for (i = 0; envp[i]; i++)
- ;
-
- auxv = (Elf64_auxv_t *)&envp[i + 1];
-
- for (i = 0; auxv[i].a_type != AT_NULL; i++) {
- if (auxv[i].a_type == AT_SYSINFO_EHDR)
- return (void *)auxv[i].a_un.a_val;
- }
-
- return NULL;
-}
-
static Elf64_Dyn *vdso_get_dyntab(void *addr)
{
Elf64_Ehdr *ehdr = addr;
return 0;
}
-int main(int argc, char *argv[], char *envp[])
+int main(int argc, char *argv[])
{
struct sgx_enclave_run run;
struct vdso_symtab symtab;
addr = mmap((void *)encl.encl_base + seg->offset, seg->size,
seg->prot, MAP_SHARED | MAP_FIXED, encl.fd, 0);
if (addr == MAP_FAILED) {
- fprintf(stderr, "mmap() failed, errno=%d.\n", errno);
+ perror("mmap() segment failed");
exit(KSFT_FAIL);
}
}
memset(&run, 0, sizeof(run));
run.tcs = encl.encl_base;
- addr = vdso_get_base_addr(envp);
+ /* Get vDSO base address */
+ addr = (void *)getauxval(AT_SYSINFO_EHDR);
if (!addr)
goto err;
* (C) Copyright IBM 2012
* Licensed under the GPLv2
*
- * NOTE: This is a meta-test which quickly changes the clocksourc and
+ * NOTE: This is a meta-test which quickly changes the clocksource and
* then uses other tests to detect problems. Thus this test requires
* that the inconsistency-check and nanosleep tests be present in the
* same directory it is run from.
return -1;
}
- /* Check everything is sane before we start switching asyncrhonously */
+ /* Check everything is sane before we start switching asynchronously */
for (i = 0; i < count; i++) {
printf("Validating clocksource %s\n", clocksource_list[i]);
if (change_clocksource(clocksource_list[i])) {
* Licensed under the GPLv2
*
* This test signals the kernel to insert a leap second
- * every day at midnight GMT. This allows for stessing the
+ * every day at midnight GMT. This allows for stressing the
* kernel's leap-second behavior, as well as how well applications
* handle the leap-second discontinuity.
*
* (C) Copyright 2013, 2015 Linaro Limited
* Licensed under the GPL
*
- * This test demonstrates leapsecond deadlock that is possibe
+ * This test demonstrates leapsecond deadlock that is possible
* on kernels from 2.6.26 to 3.3.
*
- * WARNING: THIS WILL LIKELY HARDHANG SYSTEMS AND MAY LOSE DATA
+ * WARNING: THIS WILL LIKELY HARD HANG SYSTEMS AND MAY LOSE DATA
* RUN AT YOUR OWN RISK!
* To build:
* $ gcc leapcrash.c -o leapcrash -lrt
/* The shared thread shares a global list
* that each thread fills while holding the lock.
- * This stresses clock syncronization across cpus.
+ * This stresses clock synchronization across cpus.
*/
void *shared_thread(void *arg)
{
ifeq ($(CAN_BUILD_I386),1)
$(BINARIES_32): CFLAGS += -m32
$(BINARIES_32): LDLIBS += -lrt -ldl -lm
-$(BINARIES_32): %_32: %.c
+$(BINARIES_32): $(OUTPUT)/%_32: %.c
$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@
$(foreach t,$(TARGETS),$(eval $(call gen-target-rule-32,$(t))))
endif
ifeq ($(CAN_BUILD_X86_64),1)
$(BINARIES_64): CFLAGS += -m64
$(BINARIES_64): LDLIBS += -lrt -ldl
-$(BINARIES_64): %_64: %.c
+$(BINARIES_64): $(OUTPUT)/%_64: %.c
$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@
$(foreach t,$(TARGETS),$(eval $(call gen-target-rule-64,$(t))))
endif
ret
.size call64_from_32, .-call64_from_32
+
+.section .note.GNU-stack,"",%progbits
projects / platform / kernel / linux-starfive.git / commitdiff