frequency adjustment value (a positive integer) in
parts per billion.
+What: /sys/class/ptp/ptpN/max_vclocks
+Date: May 2021
+Contact: Yangbo Lu <yangbo.lu@nxp.com>
+Description:
+ This file contains the maximum number of ptp vclocks.
+ Write integer to re-configure it.
+
What: /sys/class/ptp/ptpN/n_alarms
Date: September 2010
Contact: Richard Cochran <richardcochran@gmail.com>
This file contains the number of programmable pins
offered by the PTP hardware clock.
+What: /sys/class/ptp/ptpN/n_vclocks
+Date: May 2021
+Contact: Yangbo Lu <yangbo.lu@nxp.com>
+Description:
+ This file contains the number of virtual PTP clocks in
+ use. By default, the value is 0 meaning that only the
+ physical clock is in use. Setting the value creates
+ the corresponding number of virtual clocks and causes
+ the physical clock to become free running. Setting the
+ value back to 0 deletes the virtual clocks and
+ switches the physical clock back to normal, adjustable
+ operation.
+
What: /sys/class/ptp/ptpN/pins
Date: March 2014
Contact: Richard Cochran <richardcochran@gmail.com>
1. User addresses not accessed by the kernel but used for address space
management (e.g. ``mprotect()``, ``madvise()``). The use of valid
- tagged pointers in this context is allowed with the exception of
- ``brk()``, ``mmap()`` and the ``new_address`` argument to
- ``mremap()`` as these have the potential to alias with existing
- user addresses.
-
- NOTE: This behaviour changed in v5.6 and so some earlier kernels may
- incorrectly accept valid tagged pointers for the ``brk()``,
- ``mmap()`` and ``mremap()`` system calls.
+ tagged pointers in this context is allowed with these exceptions:
+
+ - ``brk()``, ``mmap()`` and the ``new_address`` argument to
+ ``mremap()`` as these have the potential to alias with existing
+ user addresses.
+
+ NOTE: This behaviour changed in v5.6 and so some earlier kernels may
+ incorrectly accept valid tagged pointers for the ``brk()``,
+ ``mmap()`` and ``mremap()`` system calls.
+
+ - The ``range.start``, ``start`` and ``dst`` arguments to the
+ ``UFFDIO_*`` ``ioctl()``s used on a file descriptor obtained from
+ ``userfaultfd()``, as fault addresses subsequently obtained by reading
+ the file descriptor will be untagged, which may otherwise confuse
+ tag-unaware programs.
+
+ NOTE: This behaviour changed in v5.14 and so some earlier kernels may
+ incorrectly accept valid tagged pointers for this system call.
2. User addresses accessed by the kernel (e.g. ``write()``). This ABI
relaxation is disabled by default and the application thread needs to
.. note::
TODO(brendanhiggins@google.com): There are various issues with UML and
versions of gcc 7 and up. You're likely to run into missing ``.gcda``
- files or compile errors. We know one `faulty GCC commit
- <https://github.com/gcc-mirror/gcc/commit/8c9434c2f9358b8b8bad2c1990edf10a21645f9d>`_
- but not how we'd go about getting this fixed. The compile errors still
- need some investigation.
-
-.. note::
- TODO(brendanhiggins@google.com): for recent versions of Linux
- (5.10-5.12, maybe earlier), there's a bug with gcov counters not being
- flushed in UML. This translates to very low (<1%) reported coverage. This is
- related to the above issue and can be worked around by replacing the
- one call to ``uml_abort()`` (it's in ``os_dump_core()``) with a plain
- ``exit()``.
-
+ files or compile errors.
This is different from the "normal" way of getting coverage information that is
documented in Documentation/dev-tools/gcov.rst.
reg:
minItems: 1
- maxItems: 3
items:
- description: base register
- description: power register
- reg
- clocks
- interrupts
- - resets
- ports
allOf:
reg:
maxItems: 1
-patternProperties:
- "^adi,bypass-attenuator-in[0-4]$":
- description: |
- Configures bypassing the individual voltage input attenuator. If
- set to 1 the attenuator is bypassed if set to 0 the attenuator is
- not bypassed. If the property is absent then the attenuator
- retains it's configuration from the bios/bootloader.
- $ref: /schemas/types.yaml#/definitions/uint32
- enum: [0, 1]
-
- "^adi,pwm-active-state$":
+ adi,pwm-active-state:
description: |
Integer array, represents the active state of the pwm outputs If set to 0
the pwm uses a logic low output for 100% duty cycle. If set to 1 the pwm
enum: [0, 1]
default: 1
+patternProperties:
+ "^adi,bypass-attenuator-in[0-4]$":
+ description: |
+ Configures bypassing the individual voltage input attenuator. If
+ set to 1 the attenuator is bypassed if set to 0 the attenuator is
+ not bypassed. If the property is absent then the attenuator
+ retains it's configuration from the bios/bootloader.
+ $ref: /schemas/types.yaml#/definitions/uint32
+ enum: [0, 1]
+
required:
- compatible
- reg
items:
- const: marvell,ap806-smmu-500
- const: arm,mmu-500
- - description: NVIDIA SoCs that program two ARM MMU-500s identically
- items:
- description: NVIDIA SoCs that require memory controller interaction
and may program multiple ARM MMU-500s identically with the memory
controller interleaving translations between multiple instances
for improved performance.
items:
- enum:
- - const: nvidia,tegra194-smmu
- - const: nvidia,tegra186-smmu
+ - nvidia,tegra194-smmu
+ - nvidia,tegra186-smmu
- const: nvidia,smmu-500
- items:
- const: arm,mmu-500
- description: configuration registers for MMU instance 0
- description: configuration registers for MMU instance 1
minItems: 1
- maxItems: 2
interrupts:
items:
- description: interruption for MMU instance 0
- description: interruption for MMU instance 1
minItems: 1
- maxItems: 2
clocks:
items:
ranges:
minItems: 1
- maxItems: 3
description: |
Memory bus areas for interacting with the devices. Reflects
the memory layout with four integer values following:
interrupts:
minItems: 1
- maxItems: 3
items:
- description: NAND CTLRDY interrupt
- description: FLASH_DMA_DONE if flash DMA is available
interrupt-names:
minItems: 1
- maxItems: 3
items:
- const: nand_ctlrdy
- const: flash_dma_done
then:
properties:
reg-names:
- minItems: 2
- maxItems: 2
items:
- const: nand
- const: nand-int-base
then:
properties:
reg-names:
- minItems: 3
- maxItems: 3
items:
- const: nand
- const: nand-int-base
then:
properties:
reg-names:
- minItems: 3
- maxItems: 3
items:
- const: nand
- const: iproc-idm
reg:
oneOf:
- enum:
- - 0
- - 1
+ - 0
+ - 1
required:
- compatible
For the properties relevant to the ethernet controller connected to the GPMC
refer to the binding documentation of the device. For example, the documentation
-for the SMSC 911x is Documentation/devicetree/bindings/net/smsc911x.txt
+for the SMSC 911x is Documentation/devicetree/bindings/net/smsc,lan9115.yaml
Child nodes need to specify the GPMC bus address width using the "bank-width"
property but is possible that an ethernet controller also has a property to
+++ /dev/null
-IMX8 glue layer controller, NXP imx8 families support Synopsys MAC 5.10a IP.
-
-This file documents platform glue layer for IMX.
-Please see stmmac.txt for the other unchanged properties.
-
-The device node has following properties.
-
-Required properties:
-- compatible: Should be "nxp,imx8mp-dwmac-eqos" to select glue layer
- and "snps,dwmac-5.10a" to select IP version.
-- clocks: Must contain a phandle for each entry in clock-names.
-- clock-names: Should be "stmmaceth" for the host clock.
- Should be "pclk" for the MAC apb clock.
- Should be "ptp_ref" for the MAC timer clock.
- Should be "tx" for the MAC RGMII TX clock:
- Should be "mem" for EQOS MEM clock.
- - "mem" clock is required for imx8dxl platform.
- - "mem" clock is not required for imx8mp platform.
-- interrupt-names: Should contain a list of interrupt names corresponding to
- the interrupts in the interrupts property, if available.
- Should be "macirq" for the main MAC IRQ
- Should be "eth_wake_irq" for the IT which wake up system
-- intf_mode: Should be phandle/offset pair. The phandle to the syscon node which
- encompases the GPR register, and the offset of the GPR register.
- - required for imx8mp platform.
- - is optional for imx8dxl platform.
-
-Optional properties:
-- intf_mode: is optional for imx8dxl platform.
-- snps,rmii_refclk_ext: to select RMII reference clock from external.
-
-Example:
- eqos: ethernet@30bf0000 {
- compatible = "nxp,imx8mp-dwmac-eqos", "snps,dwmac-5.10a";
- reg = <0x30bf0000 0x10000>;
- interrupts = <GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>,
- <GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>;
- interrupt-names = "eth_wake_irq", "macirq";
- clocks = <&clk IMX8MP_CLK_ENET_QOS_ROOT>,
- <&clk IMX8MP_CLK_QOS_ENET_ROOT>,
- <&clk IMX8MP_CLK_ENET_QOS_TIMER>,
- <&clk IMX8MP_CLK_ENET_QOS>;
- clock-names = "stmmaceth", "pclk", "ptp_ref", "tx";
- assigned-clocks = <&clk IMX8MP_CLK_ENET_AXI>,
- <&clk IMX8MP_CLK_ENET_QOS_TIMER>,
- <&clk IMX8MP_CLK_ENET_QOS>;
- assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_266M>,
- <&clk IMX8MP_SYS_PLL2_100M>,
- <&clk IMX8MP_SYS_PLL2_125M>;
- assigned-clock-rates = <0>, <100000000>, <125000000>;
- nvmem-cells = <ð_mac0>;
- nvmem-cell-names = "mac-address";
- nvmem_macaddr_swap;
- intf_mode = <&gpr 0x4>;
- status = "disabled";
- };
--- /dev/null
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/nxp,dwmac-imx.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: NXP i.MX8 DWMAC glue layer Device Tree Bindings
+
+maintainers:
+ - Joakim Zhang <qiangqing.zhang@nxp.com>
+
+# We need a select here so we don't match all nodes with 'snps,dwmac'
+select:
+ properties:
+ compatible:
+ contains:
+ enum:
+ - nxp,imx8mp-dwmac-eqos
+ - nxp,imx8dxl-dwmac-eqos
+ required:
+ - compatible
+
+allOf:
+ - $ref: "snps,dwmac.yaml#"
+
+properties:
+ compatible:
+ oneOf:
+ - items:
+ - enum:
+ - nxp,imx8mp-dwmac-eqos
+ - nxp,imx8dxl-dwmac-eqos
+ - const: snps,dwmac-5.10a
+
+ clocks:
+ minItems: 3
+ maxItems: 5
+ items:
+ - description: MAC host clock
+ - description: MAC apb clock
+ - description: MAC timer clock
+ - description: MAC RGMII TX clock
+ - description: EQOS MEM clock
+
+ clock-names:
+ minItems: 3
+ maxItems: 5
+ contains:
+ enum:
+ - stmmaceth
+ - pclk
+ - ptp_ref
+ - tx
+ - mem
+
+ intf_mode:
+ $ref: /schemas/types.yaml#/definitions/phandle-array
+ description:
+ Should be phandle/offset pair. The phandle to the syscon node which
+ encompases the GPR register, and the offset of the GPR register.
+
+ snps,rmii_refclk_ext:
+ $ref: /schemas/types.yaml#/definitions/flag
+ description:
+ To select RMII reference clock from external.
+
+required:
+ - compatible
+ - clocks
+ - clock-names
+
+unevaluatedProperties: false
+
+examples:
+ - |
+ #include <dt-bindings/interrupt-controller/arm-gic.h>
+ #include <dt-bindings/interrupt-controller/irq.h>
+ #include <dt-bindings/clock/imx8mp-clock.h>
+
+ eqos: ethernet@30bf0000 {
+ compatible = "nxp,imx8mp-dwmac-eqos","snps,dwmac-5.10a";
+ reg = <0x30bf0000 0x10000>;
+ interrupts = <GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "macirq", "eth_wake_irq";
+ clocks = <&clk IMX8MP_CLK_ENET_QOS_ROOT>,
+ <&clk IMX8MP_CLK_QOS_ENET_ROOT>,
+ <&clk IMX8MP_CLK_ENET_QOS_TIMER>,
+ <&clk IMX8MP_CLK_ENET_QOS>;
+ clock-names = "stmmaceth", "pclk", "ptp_ref", "tx";
+ phy-mode = "rgmii";
+ status = "disabled";
+ };
--- /dev/null
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/smsc,lan9115.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Smart Mixed-Signal Connectivity (SMSC) LAN911x/912x Controller
+
+maintainers:
+ - Shawn Guo <shawnguo@kernel.org>
+
+allOf:
+ - $ref: ethernet-controller.yaml#
+
+properties:
+ compatible:
+ oneOf:
+ - const: smsc,lan9115
+ - items:
+ - enum:
+ - smsc,lan89218
+ - smsc,lan9117
+ - smsc,lan9118
+ - smsc,lan9220
+ - smsc,lan9221
+ - const: smsc,lan9115
+
+ reg:
+ maxItems: 1
+
+ reg-shift: true
+
+ reg-io-width:
+ enum: [ 2, 4 ]
+ default: 2
+
+ interrupts:
+ minItems: 1
+ items:
+ - description:
+ LAN interrupt line
+ - description:
+ Optional PME (power management event) interrupt that is able to wake
+ up the host system with a 50ms pulse on network activity
+
+ clocks:
+ maxItems: 1
+
+ phy-mode: true
+
+ smsc,irq-active-high:
+ type: boolean
+ description: Indicates the IRQ polarity is active-high
+
+ smsc,irq-push-pull:
+ type: boolean
+ description: Indicates the IRQ type is push-pull
+
+ smsc,force-internal-phy:
+ type: boolean
+ description: Forces SMSC LAN controller to use internal PHY
+
+ smsc,force-external-phy:
+ type: boolean
+ description: Forces SMSC LAN controller to use external PHY
+
+ smsc,save-mac-address:
+ type: boolean
+ description:
+ Indicates that MAC address needs to be saved before resetting the
+ controller
+
+ reset-gpios:
+ maxItems: 1
+ description:
+ A GPIO line connected to the RESET (active low) signal of the device.
+ On many systems this is wired high so the device goes out of reset at
+ power-on, but if it is under program control, this optional GPIO can
+ wake up in response to it.
+
+ vdd33a-supply:
+ description: 3.3V analog power supply
+
+ vddvario-supply:
+ description: IO logic power supply
+
+required:
+ - compatible
+ - reg
+ - interrupts
+
+# There are lots of bus-specific properties ("qcom,*", "samsung,*", "fsl,*",
+# "gpmc,*", ...) to be found, that actually depend on the compatible value of
+# the parent node.
+additionalProperties: true
+
+examples:
+ - |
+ #include <dt-bindings/gpio/gpio.h>
+
+ ethernet@f4000000 {
+ compatible = "smsc,lan9220", "smsc,lan9115";
+ reg = <0xf4000000 0x2000000>;
+ phy-mode = "mii";
+ interrupt-parent = <&gpio1>;
+ interrupts = <31>, <32>;
+ reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>;
+ reg-io-width = <4>;
+ smsc,irq-push-pull;
+ };
+++ /dev/null
-* Smart Mixed-Signal Connectivity (SMSC) LAN911x/912x Controller
-
-Required properties:
-- compatible : Should be "smsc,lan<model>", "smsc,lan9115"
-- reg : Address and length of the io space for SMSC LAN
-- interrupts : one or two interrupt specifiers
- - The first interrupt is the SMSC LAN interrupt line
- - The second interrupt (if present) is the PME (power
- management event) interrupt that is able to wake up the host
- system with a 50ms pulse on network activity
-- phy-mode : See ethernet.txt file in the same directory
-
-Optional properties:
-- reg-shift : Specify the quantity to shift the register offsets by
-- reg-io-width : Specify the size (in bytes) of the IO accesses that
- should be performed on the device. Valid value for SMSC LAN is
- 2 or 4. If it's omitted or invalid, the size would be 2.
-- smsc,irq-active-high : Indicates the IRQ polarity is active-high
-- smsc,irq-push-pull : Indicates the IRQ type is push-pull
-- smsc,force-internal-phy : Forces SMSC LAN controller to use
- internal PHY
-- smsc,force-external-phy : Forces SMSC LAN controller to use
- external PHY
-- smsc,save-mac-address : Indicates that mac address needs to be saved
- before resetting the controller
-- reset-gpios : a GPIO line connected to the RESET (active low) signal
- of the device. On many systems this is wired high so the device goes
- out of reset at power-on, but if it is under program control, this
- optional GPIO can wake up in response to it.
-- vdd33a-supply, vddvario-supply : 3.3V analog and IO logic power supplies
-
-Examples:
-
-lan9220@f4000000 {
- compatible = "smsc,lan9220", "smsc,lan9115";
- reg = <0xf4000000 0x2000000>;
- phy-mode = "mii";
- interrupt-parent = <&gpio1>;
- interrupts = <31>, <32>;
- reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>;
- reg-io-width = <4>;
- smsc,irq-push-pull;
-};
- snps,dwmac-4.00
- snps,dwmac-4.10a
- snps,dwmac-4.20a
+ - snps,dwmac-5.10a
- snps,dwxgmac
- snps,dwxgmac-2.10
- snps,dwmac-4.00
- snps,dwmac-4.10a
- snps,dwmac-4.20a
+ - snps,dwmac-5.10a
- snps,dwxgmac
- snps,dwxgmac-2.10
- snps,dwmac-4.00
- snps,dwmac-4.10a
- snps,dwmac-4.20a
+ - snps,dwmac-5.10a
- snps,dwxgmac
- snps,dwxgmac-2.10
- st,spear600-gmac
Type-C spec states minimum CC pin debounce of 100 ms and maximum
of 200 ms. However, some solutions might need more than 200 ms.
+ refclk-dig:
+ type: object
+ description: |
+ WIZ node should have subnode for refclk_dig to select the reference
+ clock source for the reference clock used in the PHY and PMA digital
+ logic.
+ properties:
+ clocks:
+ minItems: 2
+ maxItems: 4
+ description: Phandle to two (Torrent) or four (Sierra) clock nodes representing
+ the inputs to refclk_dig
+
+ "#clock-cells":
+ const: 0
+
+ assigned-clocks:
+ maxItems: 1
+
+ assigned-clock-parents:
+ maxItems: 1
+
+ required:
+ - clocks
+ - "#clock-cells"
+ - assigned-clocks
+ - assigned-clock-parents
+
patternProperties:
"^pll[0|1]-refclk$":
type: object
- clocks
- "#clock-cells"
- "^refclk-dig$":
- type: object
- description: |
- WIZ node should have subnode for refclk_dig to select the reference
- clock source for the reference clock used in the PHY and PMA digital
- logic.
- properties:
- clocks:
- minItems: 2
- maxItems: 4
- description: Phandle to two (Torrent) or four (Sierra) clock nodes representing
- the inputs to refclk_dig
-
- "#clock-cells":
- const: 0
-
- assigned-clocks:
- maxItems: 1
-
- assigned-clock-parents:
- maxItems: 1
-
- required:
- - clocks
- - "#clock-cells"
- - assigned-clocks
- - assigned-clock-parents
-
"^serdes@[0-9a-f]+$":
type: object
description: |
maxItems: 1
power-domains:
+ deprecated: true
description:
Power domain to use for enable control. This binding is only
available if the compatible is chosen to regulator-fixed-domain.
maxItems: 1
required-opps:
+ deprecated: true
description:
Performance state to use for enable control. This binding is only
available if the compatible is chosen to regulator-fixed-domain. The
switching frequency must be one of following corresponding value
1.1MHz, 1.65MHz, 2.2MHz, 2.75MHz
- patternProperties:
- "^ldo[1-4]$":
+ ldortc:
type: object
$ref: regulator.yaml#
- "^ldortc$":
+ patternProperties:
+ "^ldo[1-4]$":
type: object
$ref: regulator.yaml#
unevaluatedProperties: false
- "^vsnvs$":
+ properties:
+ vsnvs:
type: object
$ref: regulator.yaml#
description:
maxItems: 1
clocks:
- minItems: 2
items:
- description: PCLK clocks
- description: EXTCLK clocks. Faraday calls it CLK1HZ and says the clock
ports:
$ref: /schemas/graph.yaml#/properties/ports
- properties:
+ patternProperties:
port(@[0-9a-f]+)?:
$ref: audio-graph-port.yaml#
unevaluatedProperties: false
description:
The SPI controller acts as a slave, instead of a master.
-allOf:
- - if:
- not:
- required:
- - spi-slave
- then:
- properties:
- "#address-cells":
- const: 1
- else:
- properties:
- "#address-cells":
- const: 0
-
-patternProperties:
- "^slave$":
+ slave:
type: object
properties:
required:
- compatible
+patternProperties:
"^.*@[0-9a-f]+$":
type: object
- compatible
- reg
+allOf:
+ - if:
+ not:
+ required:
+ - spi-slave
+ then:
+ properties:
+ "#address-cells":
+ const: 1
+ else:
+ properties:
+ "#address-cells":
+ const: 0
+
additionalProperties: true
examples:
interrupts:
minItems: 1
- maxItems: 2
items:
- description: Host controller interrupt
- description: Device controller interrupt in isp1761
interrupt-names:
minItems: 1
- maxItems: 2
items:
- const: host
- const: peripheral
As a technical note, when directories and files are specified, the
entire CONFIG_INITRAMFS_SOURCE is passed to
-usr/gen_initramfs_list.sh. This means that CONFIG_INITRAMFS_SOURCE
+usr/gen_initramfs.sh. This means that CONFIG_INITRAMFS_SOURCE
can really be interpreted as any legal argument to
-gen_initramfs_list.sh. If a directory is specified as an argument then
+gen_initramfs.sh. If a directory is specified as an argument then
the contents are scanned, uid/gid translation is performed, and
usr/gen_init_cpio file directives are output. If a directory is
-specified as an argument to usr/gen_initramfs_list.sh then the
+specified as an argument to usr/gen_initramfs.sh then the
contents of the file are simply copied to the output. All of the output
directives from directory scanning and file contents copying are
processed by usr/gen_init_cpio.
-See also 'usr/gen_initramfs_list.sh -h'.
+See also 'usr/gen_initramfs.sh -h'.
Where's this all leading?
=========================
--- /dev/null
+#
+# Feature name: thread-info-in-task
+# Kconfig: THREAD_INFO_IN_TASK
+# description: arch makes use of the core kernel facility to embedd thread_info in task_struct
+#
+ -----------------------
+ | arch |status|
+ -----------------------
+ | alpha: | TODO |
+ | arc: | TODO |
+ | arm: | TODO |
+ | arm64: | ok |
+ | csky: | TODO |
+ | h8300: | TODO |
+ | hexagon: | TODO |
+ | ia64: | TODO |
+ | m68k: | TODO |
+ | microblaze: | TODO |
+ | mips: | TODO |
+ | nds32: | ok |
+ | nios2: | TODO |
+ | openrisc: | TODO |
+ | parisc: | TODO |
+ | powerpc: | ok |
+ | riscv: | ok |
+ | s390: | ok |
+ | sh: | TODO |
+ | sparc: | TODO |
+ | um: | TODO |
+ | x86: | ok |
+ | xtensa: | TODO |
+ -----------------------
| openrisc: | TODO |
| parisc: | TODO |
| powerpc: | ok |
- | riscv: | TODO |
+ | riscv: | ok |
| s390: | TODO |
| sh: | ok |
| sparc: | TODO |
The kernel does not depend on external cpio tools. If you specify a
directory instead of a configuration file, the kernel's build infrastructure
creates a configuration file from that directory (usr/Makefile calls
-usr/gen_initramfs_list.sh), and proceeds to package up that directory
+usr/gen_initramfs.sh), and proceeds to package up that directory
using the config file (by feeding it to usr/gen_init_cpio, which is created
from usr/gen_init_cpio.c). The kernel's build-time cpio creation code is
entirely self-contained, and the kernel's boot-time extractor is also
These are the various configuration flags that can be used to control
and monitor the behavior of AF_XDP sockets.
-XDP_COPY and XDP_ZERO_COPY bind flags
--------------------------------------
+XDP_COPY and XDP_ZEROCOPY bind flags
+------------------------------------
When you bind to a socket, the kernel will first try to use zero-copy
copy. If zero-copy is not supported, it will fall back on using copy
like to force a certain mode, you can use the following flags. If you
pass the XDP_COPY flag to the bind call, the kernel will force the
socket into copy mode. If it cannot use copy mode, the bind call will
-fail with an error. Conversely, the XDP_ZERO_COPY flag will force the
+fail with an error. Conversely, the XDP_ZEROCOPY flag will force the
socket into zero-copy mode or fail.
XDP_SHARED_UMEM bind flag
``ETHTOOL_MSG_FEC_SET`` set FEC settings
``ETHTOOL_MSG_MODULE_EEPROM_GET`` read SFP module EEPROM
``ETHTOOL_MSG_STATS_GET`` get standard statistics
+ ``ETHTOOL_MSG_PHC_VCLOCKS_GET`` get PHC virtual clocks info
===================================== ================================
Kernel to userspace:
``ETHTOOL_MSG_FEC_NTF`` FEC settings
``ETHTOOL_MSG_MODULE_EEPROM_GET_REPLY`` read SFP module EEPROM
``ETHTOOL_MSG_STATS_GET_REPLY`` standard statistics
+ ``ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY`` PHC virtual clocks info
======================================== =================================
``GET`` requests are sent by userspace applications to retrieve device
etherStatsPkts512to1023Octets 512 1023
============================= ==== ====
+PHC_VCLOCKS_GET
+===============
+
+Query device PHC virtual clocks information.
+
+Request contents:
+
+ ==================================== ====== ==========================
+ ``ETHTOOL_A_PHC_VCLOCKS_HEADER`` nested request header
+ ==================================== ====== ==========================
+
+Kernel response contents:
+
+ ==================================== ====== ==========================
+ ``ETHTOOL_A_PHC_VCLOCKS_HEADER`` nested reply header
+ ``ETHTOOL_A_PHC_VCLOCKS_NUM`` u32 PHC virtual clocks number
+ ``ETHTOOL_A_PHC_VCLOCKS_INDEX`` s32 PHC index array
+ ==================================== ====== ==========================
+
Request translation
===================
n/a ``ETHTOOL_MSG_CABLE_TEST_ACT``
n/a ``ETHTOOL_MSG_CABLE_TEST_TDR_ACT``
n/a ``ETHTOOL_MSG_TUNNEL_INFO_GET``
+ n/a ``ETHTOOL_MSG_PHC_VCLOCKS_GET``
=================================== =====================================
initial value when the blackhole issue goes away.
0 to disable the blackhole detection.
- By default, it is set to 1hr.
+ By default, it is set to 0 (feature is disabled).
tcp_fastopen_key - list of comma separated 32-digit hexadecimal INTEGERs
The list consists of a primary key and an optional backup key. The
gets overloaded very easily and netdev@vger really doesn't need more
traffic if we can help it.
+netdevsim is great, can I extend it for my out-of-tree tests?
+-------------------------------------------------------------
+
+No, `netdevsim` is a test vehicle solely for upstream tests.
+(Please add your tests under tools/testing/selftests/.)
+
+We also give no guarantees that `netdevsim` won't change in the future
+in a way which would break what would normally be considered uAPI.
+
+Is netdevsim considered a "user" of an API?
+-------------------------------------------
+
+Linux kernel has a long standing rule that no API should be added unless
+it has a real, in-tree user. Mock-ups and tests based on `netdevsim` are
+strongly encouraged when adding new APIs, but `netdevsim` in itself
+is **not** considered a use case/user.
+
Any other tips to help ensure my net/net-next patch gets OK'd?
--------------------------------------------------------------
Attention to detail. Re-read your own work as if you were the
Be conservative in what you do, be liberal in what you accept from others.
If it's non-zero, we mark only out of window RST segments as INVALID.
+nf_conntrack_tcp_ignore_invalid_rst - BOOLEAN
+ - 0 - disabled (default)
+ - 1 - enabled
+
+ If it's 1, we don't mark out of window RST segments as INVALID.
+
nf_conntrack_tcp_loose - BOOLEAN
- 0 - disabled
- not 0 - enabled (default)
state (f.e. VLAN).
IF_OPER_TESTING (4):
- Unused in current kernel.
+ Interface is in testing mode, for example executing driver self-tests
+ or media (cable) test. It can't be used for normal traffic until tests
+ complete.
IF_OPER_DORMANT (5):
Interface is L1 up, but waiting for an external event, f.e. for a
Note that for certain kind of soft-devices, which are not managing any
real hardware, it is possible to set this bit from userspace. One
-should use TVL IFLA_CARRIER to do so.
+should use TLV IFLA_CARRIER to do so.
netif_carrier_ok() can be used to query that bit.
Linux Kernel TIPC
=================
-TIPC (Transparent Inter Process Communication) is a protocol that is
-specially designed for intra-cluster communication.
+Introduction
+============
-For more information about TIPC, see http://tipc.sourceforge.net.
+TIPC (Transparent Inter Process Communication) is a protocol that is specially
+designed for intra-cluster communication. It can be configured to transmit
+messages either on UDP or directly across Ethernet. Message delivery is
+sequence guaranteed, loss free and flow controlled. Latency times are shorter
+than with any other known protocol, while maximal throughput is comparable to
+that of TCP.
+
+TIPC Features
+-------------
+
+- Cluster wide IPC service
+
+ Have you ever wished you had the convenience of Unix Domain Sockets even when
+ transmitting data between cluster nodes? Where you yourself determine the
+ addresses you want to bind to and use? Where you don't have to perform DNS
+ lookups and worry about IP addresses? Where you don't have to start timers
+ to monitor the continuous existence of peer sockets? And yet without the
+ downsides of that socket type, such as the risk of lingering inodes?
+
+ Welcome to the Transparent Inter Process Communication service, TIPC in short,
+ which gives you all of this, and a lot more.
+
+- Service Addressing
+
+ A fundamental concept in TIPC is that of Service Addressing which makes it
+ possible for a programmer to chose his own address, bind it to a server
+ socket and let client programs use only that address for sending messages.
+
+- Service Tracking
+
+ A client wanting to wait for the availability of a server, uses the Service
+ Tracking mechanism to subscribe for binding and unbinding/close events for
+ sockets with the associated service address.
+
+ The service tracking mechanism can also be used for Cluster Topology Tracking,
+ i.e., subscribing for availability/non-availability of cluster nodes.
+
+ Likewise, the service tracking mechanism can be used for Cluster Connectivity
+ Tracking, i.e., subscribing for up/down events for individual links between
+ cluster nodes.
+
+- Transmission Modes
+
+ Using a service address, a client can send datagram messages to a server socket.
+
+ Using the same address type, it can establish a connection towards an accepting
+ server socket.
+
+ It can also use a service address to create and join a Communication Group,
+ which is the TIPC manifestation of a brokerless message bus.
+
+ Multicast with very good performance and scalability is available both in
+ datagram mode and in communication group mode.
+
+- Inter Node Links
+
+ Communication between any two nodes in a cluster is maintained by one or two
+ Inter Node Links, which both guarantee data traffic integrity and monitor
+ the peer node's availability.
+
+- Cluster Scalability
+
+ By applying the Overlapping Ring Monitoring algorithm on the inter node links
+ it is possible to scale TIPC clusters up to 1000 nodes with a maintained
+ neighbor failure discovery time of 1-2 seconds. For smaller clusters this
+ time can be made much shorter.
+
+- Neighbor Discovery
+
+ Neighbor Node Discovery in the cluster is done by Ethernet broadcast or UDP
+ multicast, when any of those services are available. If not, configured peer
+ IP addresses can be used.
+
+- Configuration
+
+ When running TIPC in single node mode no configuration whatsoever is needed.
+ When running in cluster mode TIPC must as a minimum be given a node address
+ (before Linux 4.17) and told which interface to attach to. The "tipc"
+ configuration tool makes is possible to add and maintain many more
+ configuration parameters.
+
+- Performance
+
+ TIPC message transfer latency times are better than in any other known protocol.
+ Maximal byte throughput for inter-node connections is still somewhat lower than
+ for TCP, while they are superior for intra-node and inter-container throughput
+ on the same host.
+
+- Language Support
+
+ The TIPC user API has support for C, Python, Perl, Ruby, D and Go.
+
+More Information
+----------------
+
+- How to set up TIPC:
+
+ http://tipc.io/getting_started.html
+
+- How to program with TIPC:
+
+ http://tipc.io/programming.html
+
+- How to contribute to TIPC:
+
+- http://tipc.io/contacts.html
+
+- More details about TIPC specification:
+
+ http://tipc.io/protocol.html
+
+
+Implementation
+==============
+
+TIPC is implemented as a kernel module in net/tipc/ directory.
TIPC Base Types
---------------
with the event, in nanoseconds. May be
modified by .usecs to have timestamps
interpreted as microseconds.
- cpu int the cpu on which the event occurred.
+ common_cpu int the cpu on which the event occurred.
====================== ==== =======================================
Extended error information
(顺便说一句,值得注意的是,合并窗口期间集成的更改并不是凭空产生的;它们是经
提前收集、测试和分级的。稍后将详细描述该过程的工作方式。)
-合并窗口持续大约两周。在这段时间结束时,LinusTorvalds将声明窗口已关闭,并
+合并窗口持续大约两周。在这段时间结束时,Linus Torvalds将声明窗口已关闭,并
释放第一个“rc”内核。例如,对于目标为5.6的内核,在合并窗口结束时发生的释放
将被称为5.6-rc1。-rc1 版本是一个信号,表示合并新特性的时间已经过去,稳定下一
个内核的时间已经到来。
补丁如何进入内核
----------------
-只有一个人可以将补丁合并到主线内核存储库中:LinusTorvalds。但是,在进入
+只有一个人可以将补丁合并到主线内核存储库中:Linus Torvalds。但是,在进入
2.6.38内核的9500多个补丁中,只有112个(大约1.3%)是由Linus自己直接选择的。
内核项目已经发展到一个没有一个开发人员可以在没有支持的情况下检查和选择每个
补丁的规模。内核开发人员处理这种增长的方式是使用围绕信任链构建的助理系统。
use PPIs designated for specific cpus. The irq field is interpreted
like this::
- bits: | 31 ... 28 | 27 ... 24 | 23 ... 16 | 15 ... 0 |
+ bits: | 31 ... 28 | 27 ... 24 | 23 ... 16 | 15 ... 0 |
field: | vcpu2_index | irq_type | vcpu_index | irq_id |
The irq_type field has the following values:
Errors:
====== ============================================================
- ENOENT no such register
- EINVAL invalid register ID, or no such register or used with VMs in
+ ENOENT no such register
+ EINVAL invalid register ID, or no such register or used with VMs in
protected virtualization mode on s390
- EPERM (arm64) register access not allowed before vcpu finalization
+ EPERM (arm64) register access not allowed before vcpu finalization
====== ============================================================
(These error codes are indicative only: do not rely on a specific error
Errors include:
======== ============================================================
- ENOENT no such register
- EINVAL invalid register ID, or no such register or used with VMs in
+ ENOENT no such register
+ EINVAL invalid register ID, or no such register or used with VMs in
protected virtualization mode on s390
- EPERM (arm64) register access not allowed before vcpu finalization
+ EPERM (arm64) register access not allowed before vcpu finalization
======== ============================================================
(These error codes are indicative only: do not rely on a specific error
Errors:
====== =================================================================
- EINVAL the target is unknown, or the combination of features is invalid.
- ENOENT a features bit specified is unknown.
+ EINVAL the target is unknown, or the combination of features is invalid.
+ ENOENT a features bit specified is unknown.
====== =================================================================
This tells KVM what type of CPU to present to the guest, and what
-optional features it should have. This will cause a reset of the cpu
-registers to their initial values. If this is not called, KVM_RUN will
+optional features it should have. This will cause a reset of the cpu
+registers to their initial values. If this is not called, KVM_RUN will
return ENOEXEC for that vcpu.
The initial values are defined as:
Errors:
===== ==============================================================
- E2BIG the reg index list is too big to fit in the array specified by
- the user (the number required will be written into n).
+ E2BIG the reg index list is too big to fit in the array specified by
+ the user (the number required will be written into n).
===== ==============================================================
::
ARM/arm64 divides the id field into two parts, a device id and an
address type id specific to the individual device::
- bits: | 63 ... 32 | 31 ... 16 | 15 ... 0 |
+ bits: | 63 ... 32 | 31 ... 16 | 15 ... 0 |
field: | 0x00000000 | device id | addr type id |
ARM/arm64 currently only require this when using the in-kernel GIC
trap and emulate MSRs that are outside of the scope of KVM as well as
limit the attack surface on KVM's MSR emulation code.
-8.28 KVM_CAP_ENFORCE_PV_CPUID
+8.28 KVM_CAP_ENFORCE_PV_FEATURE_CPUID
-----------------------------
Architectures: x86
Creative Commons is not a party to its public
licenses. Notwithstanding, Creative Commons may elect to apply one of
its public licenses to material it publishes and in those instances
-will be considered the “Licensor.” The text of the Creative Commons
+will be considered the "Licensor." The text of the Creative Commons
public licenses is dedicated to the public domain under the CC0 Public
Domain Dedication. Except for the limited purpose of indicating that
material is shared under a Creative Commons public license or as
F: include/uapi/linux/wmi.h
ACRN HYPERVISOR SERVICE MODULE
-M: Shuo Liu <shuo.a.liu@intel.com>
+M: Fei Li <fei1.li@intel.com>
L: acrn-dev@lists.projectacrn.org (subscribers-only)
S: Supported
W: https://projectacrn.org
AMD IOMMU (AMD-VI)
M: Joerg Roedel <joro@8bytes.org>
+R: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
L: iommu@lists.linux-foundation.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git
F: drivers/input/touchscreen/goodix.c
GOOGLE ETHERNET DRIVERS
-M: Catherine Sullivan <csully@google.com>
-R: Sagi Shahar <sagis@google.com>
-R: Jon Olson <jonolson@google.com>
+M: Jeroen de Borst <jeroendb@google.com>
+R: Catherine Sullivan <csully@google.com>
+R: David Awogbemila <awogbemila@google.com>
L: netdev@vger.kernel.org
S: Supported
F: Documentation/networking/device_drivers/ethernet/google/gve.rst
T: git git://linuxtv.org/media_tree.git
F: drivers/media/radio/radio-maxiradio*
+MCAB MICROCHIP CAN BUS ANALYZER TOOL DRIVER
+R: Yasushi SHOJI <yashi@spacecubics.com>
+L: linux-can@vger.kernel.org
+S: Maintained
+F: drivers/net/can/usb/mcba_usb.c
+
MCAN MMIO DEVICE DRIVER
M: Chandrasekar Ramakrishnan <rcsekar@samsung.com>
L: linux-can@vger.kernel.org
MEDIATEK SWITCH DRIVER
M: Sean Wang <sean.wang@mediatek.com>
M: Landen Chao <Landen.Chao@mediatek.com>
+M: DENG Qingfang <dqfext@gmail.com>
L: netdev@vger.kernel.org
S: Maintained
F: drivers/net/dsa/mt7530.*
F: drivers/ptp/*
F: include/linux/ptp_cl*
+PTP VIRTUAL CLOCK SUPPORT
+M: Yangbo Lu <yangbo.lu@nxp.com>
+L: netdev@vger.kernel.org
+S: Maintained
+F: drivers/ptp/ptp_vclock.c
+F: net/ethtool/phc_vclocks.c
+
PTRACE SUPPORT
M: Oleg Nesterov <oleg@redhat.com>
S: Maintained
L: amd-gfx@lists.freedesktop.org
S: Supported
T: git https://gitlab.freedesktop.org/agd5f/linux.git
+B: https://gitlab.freedesktop.org/drm/amd/-/issues
+C: irc://irc.oftc.net/radeon
F: drivers/gpu/drm/amd/
F: drivers/gpu/drm/radeon/
F: include/uapi/drm/amdgpu_drm.h
L: linux-usb@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/phy/hisilicon,hi3670-usb3.yaml
-F: drivers/phy/hisilicon/phy-kirin970-usb3.c
+F: drivers/phy/hisilicon/phy-hi3670-usb3.c
USB ISP116X DRIVER
M: Olav Kongas <ok@artecdesign.ee>
S: Supported
F: drivers/ptp/ptp_vmw.c
+VMWARE VMCI DRIVER
+M: Jorgen Hansen <jhansen@vmware.com>
+M: Vishnu Dasa <vdasa@vmware.com>
+L: linux-kernel@vger.kernel.org
+L: pv-drivers@vmware.com (private)
+S: Maintained
+F: drivers/misc/vmw_vmci/
+
VMWARE VMMOUSE SUBDRIVER
M: "VMware Graphics" <linux-graphics-maintainer@vmware.com>
M: "VMware, Inc." <pv-drivers@vmware.com>
VERSION = 5
PATCHLEVEL = 14
SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc5
NAME = Opossums on Parade
# *DOCUMENTATION*
PHONY += scripts_basic
scripts_basic:
$(Q)$(MAKE) $(build)=scripts/basic
- $(Q)rm -f .tmp_quiet_recordmcount
PHONY += outputmakefile
ifdef building_out_of_srctree
# This exploits the 'multi-target pattern rule' trick.
# The syncconfig should be executed only once to make all the targets.
# (Note: use the grouped target '&:' when we bump to GNU Make 4.3)
-quiet_cmd_syncconfig = SYNC $@
- cmd_syncconfig = $(MAKE) -f $(srctree)/Makefile syncconfig
-
+#
+# Do not use $(call cmd,...) here. That would suppress prompts from syncconfig,
+# so you cannot notice that Kconfig is waiting for the user input.
%/config/auto.conf %/config/auto.conf.cmd %/generated/autoconf.h: $(KCONFIG_CONFIG)
- +$(call cmd,syncconfig)
+ $(Q)$(kecho) " SYNC $@"
+ $(Q)$(MAKE) -f $(srctree)/Makefile syncconfig
else # !may-sync-config
# External modules and some install targets need include/generated/autoconf.h
# and include/config/auto.conf but do not care if they are up-to-date.
# Warn about unmarked fall-throughs in switch statement.
# Disabled for clang while comment to attribute conversion happens and
# https://github.com/ClangBuiltLinux/linux/issues/636 is discussed.
-KBUILD_CFLAGS += $(call cc-option,-Wimplicit-fallthrough,)
+KBUILD_CFLAGS += $(call cc-option,-Wimplicit-fallthrough=5,)
endif
# These warnings generated too much noise in a regular build.
$(Q)$(MAKE) $(build)=scripts scripts/unifdef
# ---------------------------------------------------------------------------
+# Install
+
+# Many distributions have the custom install script, /sbin/installkernel.
+# If DKMS is installed, 'make install' will eventually recuses back
+# to the this Makefile to build and install external modules.
+# Cancel sub_make_done so that options such as M=, V=, etc. are parsed.
+
+install: sub_make_done :=
+
+# ---------------------------------------------------------------------------
# Tools
ifdef CONFIG_STACK_VALIDATION
select PCI_SYSCALL if PCI
select HAVE_AOUT
select HAVE_ASM_MODVERSIONS
- select HAVE_IDE
select HAVE_PCSPKR_PLATFORM
select HAVE_PERF_EVENTS
select NEED_DMA_MAP_STATE
will run faster if you say N here.
See also the SMP-HOWTO available at
- <http://www.tldp.org/docs.html#howto>.
+ <https://www.tldp.org/docs.html#howto>.
If you don't know what to do here, say N.
#include "ksize.h"
extern unsigned long switch_to_osf_pal(unsigned long nr,
- struct pcb_struct * pcb_va, struct pcb_struct * pcb_pa,
+ struct pcb_struct *pcb_va, struct pcb_struct *pcb_pa,
unsigned long *vptb);
extern void move_stack(unsigned long new_stack);
START_ADDR KSEG address of the entry point of kernel code.
ZERO_PGE KSEG address of page full of zeroes, but
- upon entry to kerne cvan be expected
+ upon entry to kernel, it can be expected
to hold the parameter list and possible
INTRD information.
__attribute__ ((format (printf, 1, 2)));
/*
- * gzip delarations
+ * gzip declarations
*/
#define OF(args) args
#define STATIC static
CONFIG_ALPHA_LEGACY_START_ADDRESS=y
CONFIG_MATHEMU=y
CONFIG_CRYPTO_HMAC=y
+CONFIG_DEVTMPFS=y
#include <uapi/asm/compiler.h>
-/* Some idiots over in <linux/compiler.h> thought inline should imply
- always_inline. This breaks stuff. We'll include this file whenever
- we run into such problems. */
-
-#include <linux/compiler.h>
-#undef inline
-#undef __inline__
-#undef __inline
-#undef __always_inline
-#define __always_inline inline __attribute__((always_inline))
-
#endif /* __ALPHA_COMPILER_H */
return AUDIT_ARCH_ALPHA;
}
+static inline long syscall_get_return_value(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ return regs->r0;
+}
+
#endif /* _ASM_ALPHA_SYSCALL_H */
return -EFAULT;
state = ¤t_thread_info()->ieee_state;
- /* Update softare trap enable bits. */
+ /* Update software trap enable bits. */
*state = (*state & ~IEEE_SW_MASK) | (swcr & IEEE_SW_MASK);
/* Update the real fpcr. */
state = ¤t_thread_info()->ieee_state;
exc &= IEEE_STATUS_MASK;
- /* Update softare trap enable bits. */
+ /* Update software trap enable bits. */
swcr = (*state & IEEE_SW_MASK) | exc;
*state |= exc;
* Check that CPU performance counters are supported.
* - currently support EV67 and later CPUs.
* - actually some later revisions of the EV6 have the same PMC model as the
- * EV67 but we don't do suffiently deep CPU detection to detect them.
+ * EV67 but we don't do sufficiently deep CPU detection to detect them.
* Bad luck to the very few people who might have one, I guess.
*/
static int supported_cpu(void)
childstack->r26 = (unsigned long) ret_from_kernel_thread;
childstack->r9 = usp; /* function */
childstack->r10 = kthread_arg;
- childregs->hae = alpha_mv.hae_cache,
+ childregs->hae = alpha_mv.hae_cache;
childti->pcb.usp = 0;
return 0;
}
i, cluster->usage, cluster->start_pfn,
cluster->start_pfn + cluster->numpages);
- /* Bit 0 is console/PALcode reserved. Bit 1 is
- non-volatile memory -- we might want to mark
- this for later. */
- if (cluster->usage & 3)
- continue;
-
end = cluster->start_pfn + cluster->numpages;
if (end > max_low_pfn)
max_low_pfn = end;
memblock_add(PFN_PHYS(cluster->start_pfn),
cluster->numpages << PAGE_SHIFT);
+
+ /* Bit 0 is console/PALcode reserved. Bit 1 is
+ non-volatile memory -- we might want to mark
+ this for later. */
+ if (cluster->usage & 3)
+ memblock_reserve(PFN_PHYS(cluster->start_pfn),
+ cluster->numpages << PAGE_SHIFT);
}
/*
smp_send_stop(void)
{
cpumask_t to_whom;
- cpumask_copy(&to_whom, cpu_possible_mask);
+ cpumask_copy(&to_whom, cpu_online_mask);
cpumask_clear_cpu(smp_processor_id(), &to_whom);
#ifdef DEBUG_IPI_MSG
if (hard_smp_processor_id() != boot_cpu_id)
/* Use default IO. */
pci_add_resource(&bridge->windows, &ioport_resource);
- /* Irongate PCI memory aperture, calculate requred size before
+ /* Irongate PCI memory aperture, calculate required size before
setting it up. */
pci_add_resource(&bridge->windows, &irongate_mem);
long error;
/* Check the UAC bits to decide what the user wants us to do
- with the unaliged access. */
+ with the unaligned access. */
if (!(current_thread_info()->status & TS_UAC_NOPRINT)) {
if (__ratelimit(&ratelimit)) {
long do_alpha_fp_emul_imprecise(struct pt_regs *, unsigned long);
long do_alpha_fp_emul(unsigned long);
-int init_module(void)
+static int alpha_fp_emul_init_module(void)
{
save_emul_imprecise = alpha_fp_emul_imprecise;
save_emul = alpha_fp_emul;
alpha_fp_emul = do_alpha_fp_emul;
return 0;
}
+module_init(alpha_fp_emul_init_module);
-void cleanup_module(void)
+static void alpha_fp_emul_cleanup_module(void)
{
alpha_fp_emul_imprecise = save_emul_imprecise;
alpha_fp_emul = save_emul;
}
+module_exit(alpha_fp_emul_cleanup_module);
#undef alpha_fp_emul_imprecise
#define alpha_fp_emul_imprecise do_alpha_fp_emul_imprecise
egress:
return si_code;
}
+
+EXPORT_SYMBOL(__udiv_qrnnd);
select HAVE_FUNCTION_TRACER if !XIP_KERNEL
select HAVE_GCC_PLUGINS
select HAVE_HW_BREAKPOINT if PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7)
- select HAVE_IDE if PCI || ISA || PCMCIA
select HAVE_IRQ_TIME_ACCOUNTING
select HAVE_KERNEL_GZIP
select HAVE_KERNEL_LZ4
bool "FootBridge"
select CPU_SA110
select FOOTBRIDGE
- select HAVE_IDE
select NEED_MACH_IO_H if !MMU
select NEED_MACH_MEMORY_H
help
select IXP4XX_IRQ
select IXP4XX_TIMER
# With the new PCI driver this is not needed
- select NEED_MACH_IO_H if PCI_IXP4XX_LEGACY
+ select NEED_MACH_IO_H if IXP4XX_PCI_LEGACY
select USB_EHCI_BIG_ENDIAN_DESC
select USB_EHCI_BIG_ENDIAN_MMIO
help
select GENERIC_IRQ_MULTI_HANDLER
select GPIO_PXA
select GPIOLIB
- select HAVE_IDE
select IRQ_DOMAIN
select PLAT_PXA
select SPARSE_IRQ
select ARM_HAS_SG_CHAIN
select CPU_SA110
select FIQ
- select HAVE_IDE
select HAVE_PATA_PLATFORM
select ISA_DMA_API
select LEGACY_TIMER_TICK
select CPU_SA1100
select GENERIC_IRQ_MULTI_HANDLER
select GPIOLIB
- select HAVE_IDE
select IRQ_DOMAIN
select ISA
select NEED_MACH_MEMORY_H
select GENERIC_IRQ_CHIP
select GENERIC_IRQ_MULTI_HANDLER
select GPIOLIB
- select HAVE_IDE
select HAVE_LEGACY_CLK
select IRQ_DOMAIN
select NEED_MACH_IO_H if PCCARD
compatible = "ti,am4372-d_can", "ti,am3352-d_can";
reg = <0x0 0x2000>;
clocks = <&dcan1_fck>;
- clock-name = "fck";
+ clock-names = "fck";
syscon-raminit = <&scm_conf 0x644 1>;
interrupts = <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>;
status = "disabled";
status = "okay";
pinctrl-names = "default";
pinctrl-0 = <&i2c0_pins>;
- clock-frequency = <400000>;
+ clock-frequency = <100000>;
tps65218: tps65218@24 {
reg = <0x24>;
#include "aspeed-g5.dtsi"
#include <dt-bindings/gpio/aspeed-gpio.h>
#include <dt-bindings/i2c/i2c.h>
+#include <dt-bindings/interrupt-controller/irq.h>
/{
model = "ASRock E3C246D4I BMC";
&vuart {
status = "okay";
- aspeed,sirq-active-high;
+ aspeed,lpc-io-reg = <0x2f8>;
+ aspeed,lpc-interrupts = <3 IRQ_TYPE_LEVEL_HIGH>;
};
&mac0 {
reg = <0x69>;
};
- power-supply@6a {
+ power-supply@6b {
compatible = "ibm,cffps";
- reg = <0x6a>;
+ reg = <0x6b>;
};
- power-supply@6b {
+ power-supply@6d {
compatible = "ibm,cffps";
- reg = <0x6b>;
+ reg = <0x6d>;
};
};
&emmc {
status = "okay";
+ clk-phase-mmc-hs200 = <180>, <180>;
};
&fsim0 {
/*W0-W7*/ "","","","","","","","",
/*X0-X7*/ "","","","","","","","",
/*Y0-Y7*/ "","","","","","","","",
- /*Z0-Z7*/ "","","","","","","","",
- /*AA0-AA7*/ "","","","","","","","",
- /*AB0-AB7*/ "","","","","","","","",
- /*AC0-AC7*/ "","","","","","","","";
+ /*Z0-Z7*/ "","","","","","","","";
pin_mclr_vpp {
gpio-hog;
/*W0-W7*/ "","","","","","","","",
/*X0-X7*/ "","","","","","","","",
/*Y0-Y7*/ "","","","","","","","",
- /*Z0-Z7*/ "","","","","","","","",
- /*AA0-AA7*/ "","","","","","","","",
- /*AB0-AB7*/ "","","","","","","","",
- /*AC0-AC7*/ "","","","","","","","";
+ /*Z0-Z7*/ "","","","","","","","";
};
&fmc {
&emmc {
status = "okay";
+ clk-phase-mmc-hs200 = <36>, <270>;
};
&fsim0 {
pinctrl_power_button: powerbutgrp {
fsl,pins = <
- MX53_PAD_SD2_DATA2__GPIO1_13 0x1e4
+ MX53_PAD_SD2_DATA0__GPIO1_15 0x1e4
>;
};
pinctrl_power_out: poweroutgrp {
fsl,pins = <
- MX53_PAD_SD2_DATA0__GPIO1_15 0x1e4
+ MX53_PAD_SD2_DATA2__GPIO1_13 0x1e4
>;
};
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_microsom_enet_ar8035>;
phy-mode = "rgmii-id";
- phy-reset-duration = <2>;
+
+ /*
+ * The PHY seems to require a long-enough reset duration to avoid
+ * some rare issues where the PHY gets stuck in an inconsistent and
+ * non-functional state at boot-up. 10ms proved to be fine .
+ */
+ phy-reset-duration = <10>;
phy-reset-gpios = <&gpio4 15 GPIO_ACTIVE_LOW>;
status = "okay";
assigned-clock-rates = <0>, <198000000>;
cap-power-off-card;
keep-power-in-suspend;
+ max-frequency = <25000000>;
mmc-pwrseq = <&wifi_pwrseq>;
no-1-8-v;
non-removable;
regulator-max-microvolt = <5000000>;
};
- vdds_1v8_main: fixedregulator-vdds_1v8_main {
- compatible = "regulator-fixed";
- regulator-name = "vdds_1v8_main";
- vin-supply = <&smps7_reg>;
- regulator-min-microvolt = <1800000>;
- regulator-max-microvolt = <1800000>;
- };
-
vmmcsd_fixed: fixedregulator-mmcsd {
compatible = "regulator-fixed";
regulator-name = "vmmcsd_fixed";
regulator-boot-on;
};
+ vdds_1v8_main:
smps7_reg: smps7 {
/* VDDS_1v8_OMAP over VDDS_1v8_MAIN */
regulator-name = "smps7";
* EBI2. This has a 25MHz chrystal next to it, so no
* clocking is needed.
*/
- ethernet-ebi2@2,0 {
+ ethernet@2,0 {
compatible = "smsc,lan9221", "smsc,lan9115";
reg = <2 0x0 0x100>;
/*
phy-mode = "mii";
reg-io-width = <2>;
smsc,force-external-phy;
- /* IRQ on edge falling = active low */
- smsc,irq-active-low;
smsc,irq-push-pull;
/*
status = "disabled";
};
- vica: intc@10140000 {
+ vica: interrupt-controller@10140000 {
compatible = "arm,versatile-vic";
interrupt-controller;
#interrupt-cells = <1>;
reg = <0x10140000 0x20>;
};
- vicb: intc@10140020 {
+ vicb: interrupt-controller@10140020 {
compatible = "arm,versatile-vic";
interrupt-controller;
#interrupt-cells = <1>;
poll-interval = <20>;
/*
- * The EXTi IRQ line 3 is shared with touchscreen and ethernet,
+ * The EXTi IRQ line 3 is shared with ethernet,
* so mark this as polled GPIO key.
*/
button-0 {
};
/*
+ * The EXTi IRQ line 6 is shared with touchscreen,
+ * so mark this as polled GPIO key.
+ */
+ button-1 {
+ label = "TA2-GPIO-B";
+ linux,code = <KEY_B>;
+ gpios = <&gpiod 6 GPIO_ACTIVE_LOW>;
+ };
+
+ /*
* The EXTi IRQ line 0 is shared with PMIC,
* so mark this as polled GPIO key.
*/
gpio-keys {
compatible = "gpio-keys";
- button-1 {
- label = "TA2-GPIO-B";
- linux,code = <KEY_B>;
- gpios = <&gpiod 6 GPIO_ACTIVE_LOW>;
- wakeup-source;
- };
-
button-3 {
label = "TA4-GPIO-D";
linux,code = <KEY_D>;
label = "green:led5";
gpios = <&gpioc 6 GPIO_ACTIVE_HIGH>;
default-state = "off";
+ status = "disabled";
};
led-1 {
touchscreen@38 {
compatible = "edt,edt-ft5406";
reg = <0x38>;
- interrupt-parent = <&gpiog>;
- interrupts = <2 IRQ_TYPE_EDGE_FALLING>; /* GPIO E */
+ interrupt-parent = <&gpioc>;
+ interrupts = <6 IRQ_TYPE_EDGE_FALLING>; /* GPIO E */
};
};
aliases {
ethernet0 = ðernet0;
ethernet1 = &ksz8851;
+ rtc0 = &hwrtc;
+ rtc1 = &rtc;
};
memory@c0000000 {
reset-gpios = <&gpioh 3 GPIO_ACTIVE_LOW>;
reset-assert-us = <500>;
reset-deassert-us = <500>;
+ smsc,disable-energy-detect;
interrupt-parent = <&gpioi>;
interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
};
/delete-property/dmas;
/delete-property/dma-names;
- rtc@32 {
+ hwrtc: rtc@32 {
compatible = "microcrystal,rv8803";
reg = <0x32>;
};
#size-cells = <1>;
ranges;
- vic: intc@10140000 {
+ vic: interrupt-controller@10140000 {
compatible = "arm,versatile-vic";
interrupt-controller;
#interrupt-cells = <1>;
reg = <0x10140000 0x1000>;
- clear-mask = <0xffffffff>;
valid-mask = <0xffffffff>;
};
- sic: intc@10003000 {
+ sic: interrupt-controller@10003000 {
compatible = "arm,versatile-sic";
interrupt-controller;
#interrupt-cells = <1>;
amba {
/* The Versatile PB is using more SIC IRQ lines than the AB */
- sic: intc@10003000 {
+ sic: interrupt-controller@10003000 {
clear-mask = <0xffffffff>;
/*
* Valid interrupt lines mask according to
CONFIG_DRM_DISPLAY_CONNECTOR=y
CONFIG_DRM_SIMPLE_BRIDGE=y
CONFIG_DRM_PL111=y
-CONFIG_FB_MODE_HELPERS=y
-CONFIG_FB_MATROX=y
-CONFIG_FB_MATROX_MILLENIUM=y
-CONFIG_FB_MATROX_MYSTIQUE=y
+CONFIG_FB=y
CONFIG_BACKLIGHT_CLASS_DEVICE=y
# CONFIG_VGA_CONSOLE is not set
CONFIG_LOGO=y
CONFIG_USB_HSIC_USB3503=y
CONFIG_AB8500_USB=y
CONFIG_KEYSTONE_USB_PHY=m
-CONFIG_NOP_USB_XCEIV=m
+CONFIG_NOP_USB_XCEIV=y
CONFIG_AM335X_PHY_USB=m
CONFIG_TWL6030_USB=m
CONFIG_USB_GPIO_VBUS=y
CONFIG_ARCH_NOMADIK=y
CONFIG_MACH_NOMADIK_8815NHK=y
CONFIG_AEABI=y
-CONFIG_ZBOOT_ROM_TEXT=0x0
-CONFIG_ZBOOT_ROM_BSS=0x0
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
# CONFIG_BLK_DEV_BSG is not set
CONFIG_MTD_ONENAND=y
CONFIG_MTD_ONENAND_VERIFY_WRITE=y
CONFIG_MTD_ONENAND_GENERIC=y
-CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC=y
CONFIG_MTD_RAW_NAND=y
CONFIG_MTD_NAND_FSMC=y
+CONFIG_MTD_NAND_ECC_SW_HAMMING_SMC=y
CONFIG_BLK_DEV_LOOP=y
CONFIG_BLK_DEV_CRYPTOLOOP=y
CONFIG_BLK_DEV_RAM=y
CONFIG_DRM=y
CONFIG_DRM_PANEL_TPO_TPG110=y
CONFIG_DRM_PL111=y
+CONFIG_FB=y
CONFIG_BACKLIGHT_CLASS_DEVICE=y
CONFIG_BACKLIGHT_PWM=y
CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_CRYPTO_MD5=y
CONFIG_CRYPTO_SHA1=y
CONFIG_CRYPTO_DES=y
+# CONFIG_DEBUG_BUGVERBOSE is not set
CONFIG_DEBUG_INFO=y
-# CONFIG_ENABLE_MUST_CHECK is not set
CONFIG_DEBUG_FS=y
# CONFIG_SCHED_DEBUG is not set
# CONFIG_DEBUG_PREEMPT is not set
-# CONFIG_DEBUG_BUGVERBOSE is not set
CONFIG_DRM_DISPLAY_CONNECTOR=y
CONFIG_DRM_SIMPLE_BRIDGE=y
CONFIG_DRM_PL111=y
-CONFIG_FB_MODE_HELPERS=y
+CONFIG_FB=y
CONFIG_BACKLIGHT_CLASS_DEVICE=y
CONFIG_LOGO=y
-# CONFIG_LOGO_LINUX_MONO is not set
-# CONFIG_LOGO_LINUX_VGA16 is not set
CONFIG_SOUND=y
CONFIG_SND=y
# CONFIG_SND_DRIVERS is not set
CONFIG_DRM_SIMPLE_BRIDGE=y
CONFIG_DRM_I2C_ADV7511=y
CONFIG_DRM_I2C_ADV7511_AUDIO=y
+CONFIG_FB=y
CONFIG_FB_SH_MOBILE_LCDC=y
CONFIG_BACKLIGHT_PWM=y
CONFIG_BACKLIGHT_AS3711=y
CONFIG_TOUCHSCREEN_ATMEL_MXT=y
CONFIG_TOUCHSCREEN_BU21013=y
CONFIG_TOUCHSCREEN_CY8CTMA140=y
+CONFIG_TOUCHSCREEN_CYTTSP_CORE=y
+CONFIG_TOUCHSCREEN_CYTTSP_SPI=y
+CONFIG_TOUCHSCREEN_MMS114=y
+CONFIG_TOUCHSCREEN_ZINITIX=y
CONFIG_INPUT_MISC=y
CONFIG_INPUT_AB8500_PONKEY=y
CONFIG_INPUT_GPIO_VIBRA=y
CONFIG_DRM_PANEL_SONY_ACX424AKP=y
CONFIG_DRM_LIMA=y
CONFIG_DRM_MCDE=y
+CONFIG_FB=y
CONFIG_BACKLIGHT_CLASS_DEVICE=y
CONFIG_BACKLIGHT_KTD253=y
CONFIG_BACKLIGHT_GPIO=y
CONFIG_DRM_DISPLAY_CONNECTOR=y
CONFIG_DRM_SIMPLE_BRIDGE=y
CONFIG_DRM_PL111=y
-CONFIG_FB_MODE_HELPERS=y
+CONFIG_FB=y
CONFIG_BACKLIGHT_CLASS_DEVICE=y
CONFIG_LOGO=y
CONFIG_SOUND=y
CONFIG_NFSD_V3=y
CONFIG_NLS_CODEPAGE_850=m
CONFIG_NLS_ISO8859_1=m
-CONFIG_FONTS=y
-CONFIG_FONT_ACORN_8x8=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_FS=y
CONFIG_DEBUG_KERNEL=y
# CONFIG_NET_NS is not set
CONFIG_BLK_DEV_INITRD=y
CONFIG_PROFILING=y
-CONFIG_MODULES=y
-CONFIG_MODULE_UNLOAD=y
-# CONFIG_BLK_DEV_BSG is not set
CONFIG_ARCH_VEXPRESS=y
CONFIG_ARCH_VEXPRESS_DCSCB=y
CONFIG_ARCH_VEXPRESS_TC2_PM=y
CONFIG_VMSPLIT_2G=y
CONFIG_NR_CPUS=8
CONFIG_ARM_PSCI=y
-CONFIG_CMA=y
CONFIG_ZBOOT_ROM_TEXT=0x0
CONFIG_ZBOOT_ROM_BSS=0x0
CONFIG_CMDLINE="console=ttyAMA0"
CONFIG_CPU_IDLE=y
CONFIG_VFP=y
CONFIG_NEON=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+# CONFIG_BLK_DEV_BSG is not set
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+CONFIG_CMA=y
CONFIG_NET=y
CONFIG_PACKET=y
CONFIG_UNIX=y
CONFIG_NET_9P=y
CONFIG_NET_9P_VIRTIO=y
CONFIG_DEVTMPFS=y
-CONFIG_DMA_CMA=y
CONFIG_MTD=y
CONFIG_MTD_CMDLINE_PARTS=y
CONFIG_MTD_BLOCK=y
CONFIG_BLK_DEV_SD=y
CONFIG_SCSI_VIRTIO=y
CONFIG_ATA=y
-# CONFIG_SATA_PMP is not set
CONFIG_NETDEVICES=y
CONFIG_VIRTIO_NET=y
CONFIG_SMC91X=y
CONFIG_DRM_PANEL_SIMPLE=y
CONFIG_DRM_SII902X=y
CONFIG_DRM_PL111=y
-CONFIG_FB_MODE_HELPERS=y
+CONFIG_FB=y
CONFIG_BACKLIGHT_CLASS_DEVICE=y
CONFIG_LOGO=y
-# CONFIG_LOGO_LINUX_MONO is not set
-# CONFIG_LOGO_LINUX_VGA16 is not set
CONFIG_SOUND=y
CONFIG_SND=y
# CONFIG_SND_DRIVERS is not set
CONFIG_9P_FS=y
CONFIG_NLS_CODEPAGE_437=y
CONFIG_NLS_ISO8859_1=y
+# CONFIG_CRYPTO_HW is not set
+CONFIG_DMA_CMA=y
CONFIG_DEBUG_INFO=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_KERNEL=y
CONFIG_DETECT_HUNG_TASK=y
# CONFIG_SCHED_DEBUG is not set
CONFIG_DEBUG_USER=y
-# CONFIG_CRYPTO_HW is not set
select PM_GENERIC_DOMAINS_OF if PM && OF
select REGMAP_MMIO
select RESET_CONTROLLER
- select HAVE_IDE
select PINCTRL_SINGLE
if ARCH_DAVINCI
void v7_secondary_startup(void);
void imx_scu_map_io(void);
void imx_smp_prepare(void);
-void imx_gpcv2_set_core1_pdn_pup_by_software(bool pdn);
#else
static inline void imx_scu_map_io(void) {}
static inline void imx_smp_prepare(void) {}
void imx_gpc_restore_all(void);
void imx_gpc_hwirq_mask(unsigned int hwirq);
void imx_gpc_hwirq_unmask(unsigned int hwirq);
+void imx_gpcv2_set_core1_pdn_pup_by_software(bool pdn);
void imx_anatop_init(void);
void imx_anatop_pre_suspend(void);
void imx_anatop_post_resume(void);
struct perf_event *mmdc_events[MMDC_NUM_COUNTERS];
struct hlist_node node;
struct fsl_mmdc_devtype_data *devtype_data;
+ struct clk *mmdc_ipg_clk;
};
/*
cpuhp_state_remove_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node);
perf_pmu_unregister(&pmu_mmdc->pmu);
+ iounmap(pmu_mmdc->mmdc_base);
+ clk_disable_unprepare(pmu_mmdc->mmdc_ipg_clk);
kfree(pmu_mmdc);
return 0;
}
-static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_base)
+static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_base,
+ struct clk *mmdc_ipg_clk)
{
struct mmdc_pmu *pmu_mmdc;
char *name;
}
mmdc_num = mmdc_pmu_init(pmu_mmdc, mmdc_base, &pdev->dev);
+ pmu_mmdc->mmdc_ipg_clk = mmdc_ipg_clk;
if (mmdc_num == 0)
name = "mmdc";
else
#else
#define imx_mmdc_remove NULL
-#define imx_mmdc_perf_init(pdev, mmdc_base) 0
+#define imx_mmdc_perf_init(pdev, mmdc_base, mmdc_ipg_clk) 0
#endif
static int imx_mmdc_probe(struct platform_device *pdev)
val &= ~(1 << BP_MMDC_MAPSR_PSD);
writel_relaxed(val, reg);
- return imx_mmdc_perf_init(pdev, mmdc_base);
+ err = imx_mmdc_perf_init(pdev, mmdc_base, mmdc_ipg_clk);
+ if (err) {
+ iounmap(mmdc_base);
+ clk_disable_unprepare(mmdc_ipg_clk);
+ }
+
+ return err;
}
int imx_mmdc_get_ddr_type(void)
config MACH_GORAMO_MLR
bool "GORAMO Multi Link Router"
+ depends on IXP4XX_PCI_LEGACY
help
Say 'Y' here if you want your kernel to support GORAMO
MultiLink router.
/*
* PCI Control/Status Registers
*/
-#define IXP4XX_PCI_CSR(x) ((volatile u32 *)(IXP4XX_PCI_CFG_BASE_VIRT+(x)))
-
-#define PCI_NP_AD IXP4XX_PCI_CSR(PCI_NP_AD_OFFSET)
-#define PCI_NP_CBE IXP4XX_PCI_CSR(PCI_NP_CBE_OFFSET)
-#define PCI_NP_WDATA IXP4XX_PCI_CSR(PCI_NP_WDATA_OFFSET)
-#define PCI_NP_RDATA IXP4XX_PCI_CSR(PCI_NP_RDATA_OFFSET)
-#define PCI_CRP_AD_CBE IXP4XX_PCI_CSR(PCI_CRP_AD_CBE_OFFSET)
-#define PCI_CRP_WDATA IXP4XX_PCI_CSR(PCI_CRP_WDATA_OFFSET)
-#define PCI_CRP_RDATA IXP4XX_PCI_CSR(PCI_CRP_RDATA_OFFSET)
-#define PCI_CSR IXP4XX_PCI_CSR(PCI_CSR_OFFSET)
-#define PCI_ISR IXP4XX_PCI_CSR(PCI_ISR_OFFSET)
-#define PCI_INTEN IXP4XX_PCI_CSR(PCI_INTEN_OFFSET)
-#define PCI_DMACTRL IXP4XX_PCI_CSR(PCI_DMACTRL_OFFSET)
-#define PCI_AHBMEMBASE IXP4XX_PCI_CSR(PCI_AHBMEMBASE_OFFSET)
-#define PCI_AHBIOBASE IXP4XX_PCI_CSR(PCI_AHBIOBASE_OFFSET)
-#define PCI_PCIMEMBASE IXP4XX_PCI_CSR(PCI_PCIMEMBASE_OFFSET)
-#define PCI_AHBDOORBELL IXP4XX_PCI_CSR(PCI_AHBDOORBELL_OFFSET)
-#define PCI_PCIDOORBELL IXP4XX_PCI_CSR(PCI_PCIDOORBELL_OFFSET)
-#define PCI_ATPDMA0_AHBADDR IXP4XX_PCI_CSR(PCI_ATPDMA0_AHBADDR_OFFSET)
-#define PCI_ATPDMA0_PCIADDR IXP4XX_PCI_CSR(PCI_ATPDMA0_PCIADDR_OFFSET)
-#define PCI_ATPDMA0_LENADDR IXP4XX_PCI_CSR(PCI_ATPDMA0_LENADDR_OFFSET)
-#define PCI_ATPDMA1_AHBADDR IXP4XX_PCI_CSR(PCI_ATPDMA1_AHBADDR_OFFSET)
-#define PCI_ATPDMA1_PCIADDR IXP4XX_PCI_CSR(PCI_ATPDMA1_PCIADDR_OFFSET)
-#define PCI_ATPDMA1_LENADDR IXP4XX_PCI_CSR(PCI_ATPDMA1_LENADDR_OFFSET)
+#define _IXP4XX_PCI_CSR(x) ((volatile u32 *)(IXP4XX_PCI_CFG_BASE_VIRT+(x)))
+
+#define PCI_NP_AD _IXP4XX_PCI_CSR(PCI_NP_AD_OFFSET)
+#define PCI_NP_CBE _IXP4XX_PCI_CSR(PCI_NP_CBE_OFFSET)
+#define PCI_NP_WDATA _IXP4XX_PCI_CSR(PCI_NP_WDATA_OFFSET)
+#define PCI_NP_RDATA _IXP4XX_PCI_CSR(PCI_NP_RDATA_OFFSET)
+#define PCI_CRP_AD_CBE _IXP4XX_PCI_CSR(PCI_CRP_AD_CBE_OFFSET)
+#define PCI_CRP_WDATA _IXP4XX_PCI_CSR(PCI_CRP_WDATA_OFFSET)
+#define PCI_CRP_RDATA _IXP4XX_PCI_CSR(PCI_CRP_RDATA_OFFSET)
+#define PCI_CSR _IXP4XX_PCI_CSR(PCI_CSR_OFFSET)
+#define PCI_ISR _IXP4XX_PCI_CSR(PCI_ISR_OFFSET)
+#define PCI_INTEN _IXP4XX_PCI_CSR(PCI_INTEN_OFFSET)
+#define PCI_DMACTRL _IXP4XX_PCI_CSR(PCI_DMACTRL_OFFSET)
+#define PCI_AHBMEMBASE _IXP4XX_PCI_CSR(PCI_AHBMEMBASE_OFFSET)
+#define PCI_AHBIOBASE _IXP4XX_PCI_CSR(PCI_AHBIOBASE_OFFSET)
+#define PCI_PCIMEMBASE _IXP4XX_PCI_CSR(PCI_PCIMEMBASE_OFFSET)
+#define PCI_AHBDOORBELL _IXP4XX_PCI_CSR(PCI_AHBDOORBELL_OFFSET)
+#define PCI_PCIDOORBELL _IXP4XX_PCI_CSR(PCI_PCIDOORBELL_OFFSET)
+#define PCI_ATPDMA0_AHBADDR _IXP4XX_PCI_CSR(PCI_ATPDMA0_AHBADDR_OFFSET)
+#define PCI_ATPDMA0_PCIADDR _IXP4XX_PCI_CSR(PCI_ATPDMA0_PCIADDR_OFFSET)
+#define PCI_ATPDMA0_LENADDR _IXP4XX_PCI_CSR(PCI_ATPDMA0_LENADDR_OFFSET)
+#define PCI_ATPDMA1_AHBADDR _IXP4XX_PCI_CSR(PCI_ATPDMA1_AHBADDR_OFFSET)
+#define PCI_ATPDMA1_PCIADDR _IXP4XX_PCI_CSR(PCI_ATPDMA1_PCIADDR_OFFSET)
+#define PCI_ATPDMA1_LENADDR _IXP4XX_PCI_CSR(PCI_ATPDMA1_LENADDR_OFFSET)
/*
* PCI register values and bit definitions
struct omap_hwmod_ocp_if *oi;
struct clockdomain *clkdm;
struct clk_hw_omap *clk;
+ struct clk_hw *hw;
if (!oh)
return NULL;
c = oi->_clk;
}
- clk = to_clk_hw_omap(__clk_get_hw(c));
+ hw = __clk_get_hw(c);
+ if (!hw)
+ return NULL;
+
+ clk = to_clk_hw_omap(hw);
+ if (!clk)
+ return NULL;
+
clkdm = clk->clkdm;
if (!clkdm)
return NULL;
fallthrough; /* ??? */
case 256:
vram_size += PAGE_SIZE * 256;
+ break;
default:
break;
}
rn = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
emit_ldx_r(dst, rn, off, ctx, BPF_SIZE(code));
break;
+ /* speculation barrier */
+ case BPF_ST | BPF_NOSPEC:
+ break;
/* ST: *(size *)(dst + off) = imm */
case BPF_ST | BPF_MEM | BPF_W:
case BPF_ST | BPF_MEM | BPF_H:
depends on CC_HAS_BRANCH_PROT_PAC_RET_BTI
# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=94697
depends on !CC_IS_GCC || GCC_VERSION >= 100100
- depends on !(CC_IS_CLANG && GCOV_KERNEL)
+ # https://github.com/llvm/llvm-project/commit/a88c722e687e6780dcd6a58718350dc76fcc4cc9
+ depends on !CC_IS_CLANG || CLANG_VERSION >= 120000
depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS)
help
Build the kernel with Branch Target Identification annotations
If unsure, say N.
config RANDOMIZE_MODULE_REGION_FULL
- bool "Randomize the module region over a 4 GB range"
+ bool "Randomize the module region over a 2 GB range"
depends on RANDOMIZE_BASE
default y
help
- Randomizes the location of the module region inside a 4 GB window
+ Randomizes the location of the module region inside a 2 GB window
covering the core kernel. This way, it is less likely for modules
to leak information about the location of core kernel data structures
but it does imply that function calls between modules and the core
When this option is not set, the module region will be randomized over
a limited range that contains the [_stext, _etext] interval of the
- core kernel, so branch relocations are always in range.
+ core kernel, so branch relocations are almost always in range unless
+ ARM64_MODULE_PLTS is enabled and the region is exhausted. In this
+ particular case of region exhaustion, modules might be able to fall
+ back to a larger 2GB area.
config CC_HAVE_STACKPROTECTOR_SYSREG
def_bool $(cc-option,-mstack-protector-guard=sysreg -mstack-protector-guard-reg=sp_el0 -mstack-protector-guard-offset=0)
endif
ifeq ($(CONFIG_ARM64_ERRATUM_843419),y)
- ifneq ($(CONFIG_ARM64_LD_HAS_FIX_ERRATUM_843419),y)
-$(warning ld does not support --fix-cortex-a53-843419; kernel may be susceptible to erratum)
- else
+ ifeq ($(CONFIG_ARM64_LD_HAS_FIX_ERRATUM_843419),y)
LDFLAGS_vmlinux += --fix-cortex-a53-843419
endif
endif
-ifeq ($(CONFIG_ARM64_USE_LSE_ATOMICS), y)
- ifneq ($(CONFIG_ARM64_LSE_ATOMICS), y)
-$(warning LSE atomics not supported by binutils)
- endif
-endif
-
cc_has_k_constraint := $(call try-run,echo \
'int main(void) { \
asm volatile("and w0, w0, %w0" :: "K" (4294967295)); \
archprepare:
$(Q)$(MAKE) $(build)=arch/arm64/tools kapi
+ifeq ($(CONFIG_ARM64_ERRATUM_843419),y)
+ ifneq ($(CONFIG_ARM64_LD_HAS_FIX_ERRATUM_843419),y)
+ @echo "warning: ld does not support --fix-cortex-a53-843419; kernel may be susceptible to erratum" >&2
+ endif
+endif
+ifeq ($(CONFIG_ARM64_USE_LSE_ATOMICS),y)
+ ifneq ($(CONFIG_ARM64_LSE_ATOMICS),y)
+ @echo "warning: LSE atomics not supported by binutils" >&2
+ endif
+endif
+
# We use MRPROPER_FILES and CLEAN_FILES now
archclean:
&mscc_felix_port0 {
label = "swp0";
+ managed = "in-band-status";
phy-handle = <&phy0>;
phy-mode = "sgmii";
status = "okay";
&mscc_felix_port1 {
label = "swp1";
+ managed = "in-band-status";
phy-handle = <&phy1>;
phy-mode = "sgmii";
status = "okay";
};
};
- sysclk: clock-sysclk {
+ sysclk: sysclk {
compatible = "fixed-clock";
#clock-cells = <0>;
clock-frequency = <100000000>;
};
flexcan1: can@308c0000 {
- compatible = "fsl,imx8mp-flexcan", "fsl,imx6q-flexcan";
+ compatible = "fsl,imx8mp-flexcan";
reg = <0x308c0000 0x10000>;
interrupts = <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&clk IMX8MP_CLK_IPG_ROOT>,
};
flexcan2: can@308d0000 {
- compatible = "fsl,imx8mp-flexcan", "fsl,imx6q-flexcan";
+ compatible = "fsl,imx8mp-flexcan";
reg = <0x308d0000 0x10000>;
interrupts = <GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&clk IMX8MP_CLK_IPG_ROOT>,
eqos: ethernet@30bf0000 {
compatible = "nxp,imx8mp-dwmac-eqos", "snps,dwmac-5.10a";
reg = <0x30bf0000 0x10000>;
- interrupts = <GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>,
- <GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>;
- interrupt-names = "eth_wake_irq", "macirq";
+ interrupts = <GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "macirq", "eth_wake_irq";
clocks = <&clk IMX8MP_CLK_ENET_QOS_ROOT>,
<&clk IMX8MP_CLK_QOS_ENET_ROOT>,
<&clk IMX8MP_CLK_ENET_QOS_TIMER>,
aliases {
spi0 = &spi0;
ethernet1 = ð1;
+ mmc0 = &sdhci0;
+ mmc1 = &sdhci1;
};
chosen {
pinctrl-names = "default";
pinctrl-0 = <&i2c1_pins>;
clock-frequency = <100000>;
+ /delete-property/ mrvl,i2c-fast-mode;
status = "okay";
rtc@6f {
<&bpmp TEGRA194_CLK_XUSB_SS>,
<&bpmp TEGRA194_CLK_XUSB_FS>;
clock-names = "dev", "ss", "ss_src", "fs_src";
+ interconnects = <&mc TEGRA194_MEMORY_CLIENT_XUSB_DEVR &emc>,
+ <&mc TEGRA194_MEMORY_CLIENT_XUSB_DEVW &emc>;
+ interconnect-names = "dma-mem", "write";
+ iommus = <&smmu TEGRA194_SID_XUSB_DEV>;
power-domains = <&bpmp TEGRA194_POWER_DOMAIN_XUSBB>,
<&bpmp TEGRA194_POWER_DOMAIN_XUSBA>;
power-domain-names = "dev", "ss";
"xusb_ss", "xusb_ss_src", "xusb_hs_src",
"xusb_fs_src", "pll_u_480m", "clk_m",
"pll_e";
+ interconnects = <&mc TEGRA194_MEMORY_CLIENT_XUSB_HOSTR &emc>,
+ <&mc TEGRA194_MEMORY_CLIENT_XUSB_HOSTW &emc>;
+ interconnect-names = "dma-mem", "write";
+ iommus = <&smmu TEGRA194_SID_XUSB_HOST>;
power-domains = <&bpmp TEGRA194_POWER_DOMAIN_XUSBC>,
<&bpmp TEGRA194_POWER_DOMAIN_XUSBA>;
interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE1R &emc>,
<&mc TEGRA194_MEMORY_CLIENT_PCIE1W &emc>;
- interconnect-names = "read", "write";
+ interconnect-names = "dma-mem", "write";
+ iommus = <&smmu TEGRA194_SID_PCIE1>;
+ iommu-map = <0x0 &smmu TEGRA194_SID_PCIE1 0x1000>;
+ iommu-map-mask = <0x0>;
+ dma-coherent;
};
pcie@14120000 {
interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE2AR &emc>,
<&mc TEGRA194_MEMORY_CLIENT_PCIE2AW &emc>;
- interconnect-names = "read", "write";
+ interconnect-names = "dma-mem", "write";
+ iommus = <&smmu TEGRA194_SID_PCIE2>;
+ iommu-map = <0x0 &smmu TEGRA194_SID_PCIE2 0x1000>;
+ iommu-map-mask = <0x0>;
+ dma-coherent;
};
pcie@14140000 {
interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE3R &emc>,
<&mc TEGRA194_MEMORY_CLIENT_PCIE3W &emc>;
- interconnect-names = "read", "write";
+ interconnect-names = "dma-mem", "write";
+ iommus = <&smmu TEGRA194_SID_PCIE3>;
+ iommu-map = <0x0 &smmu TEGRA194_SID_PCIE3 0x1000>;
+ iommu-map-mask = <0x0>;
+ dma-coherent;
};
pcie@14160000 {
interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE4R &emc>,
<&mc TEGRA194_MEMORY_CLIENT_PCIE4W &emc>;
- interconnect-names = "read", "write";
+ interconnect-names = "dma-mem", "write";
+ iommus = <&smmu TEGRA194_SID_PCIE4>;
+ iommu-map = <0x0 &smmu TEGRA194_SID_PCIE4 0x1000>;
+ iommu-map-mask = <0x0>;
+ dma-coherent;
};
pcie@14180000 {
interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE0R &emc>,
<&mc TEGRA194_MEMORY_CLIENT_PCIE0W &emc>;
- interconnect-names = "read", "write";
+ interconnect-names = "dma-mem", "write";
+ iommus = <&smmu TEGRA194_SID_PCIE0>;
+ iommu-map = <0x0 &smmu TEGRA194_SID_PCIE0 0x1000>;
+ iommu-map-mask = <0x0>;
+ dma-coherent;
};
pcie@141a0000 {
interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE5R &emc>,
<&mc TEGRA194_MEMORY_CLIENT_PCIE5W &emc>;
- interconnect-names = "read", "write";
+ interconnect-names = "dma-mem", "write";
+ iommus = <&smmu TEGRA194_SID_PCIE5>;
+ iommu-map = <0x0 &smmu TEGRA194_SID_PCIE5 0x1000>;
+ iommu-map-mask = <0x0>;
+ dma-coherent;
};
pcie_ep@14160000 {
nvidia,aspm-cmrt-us = <60>;
nvidia,aspm-pwr-on-t-us = <20>;
nvidia,aspm-l0s-entrance-latency-us = <3>;
+
+ interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE4R &emc>,
+ <&mc TEGRA194_MEMORY_CLIENT_PCIE4W &emc>;
+ interconnect-names = "dma-mem", "write";
+ iommus = <&smmu TEGRA194_SID_PCIE4>;
+ iommu-map = <0x0 &smmu TEGRA194_SID_PCIE4 0x1000>;
+ iommu-map-mask = <0x0>;
+ dma-coherent;
};
pcie_ep@14180000 {
nvidia,aspm-cmrt-us = <60>;
nvidia,aspm-pwr-on-t-us = <20>;
nvidia,aspm-l0s-entrance-latency-us = <3>;
+
+ interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE0R &emc>,
+ <&mc TEGRA194_MEMORY_CLIENT_PCIE0W &emc>;
+ interconnect-names = "dma-mem", "write";
+ iommus = <&smmu TEGRA194_SID_PCIE0>;
+ iommu-map = <0x0 &smmu TEGRA194_SID_PCIE0 0x1000>;
+ iommu-map-mask = <0x0>;
+ dma-coherent;
};
pcie_ep@141a0000 {
nvidia,aspm-cmrt-us = <60>;
nvidia,aspm-pwr-on-t-us = <20>;
nvidia,aspm-l0s-entrance-latency-us = <3>;
+
+ interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE5R &emc>,
+ <&mc TEGRA194_MEMORY_CLIENT_PCIE5W &emc>;
+ interconnect-names = "dma-mem", "write";
+ iommus = <&smmu TEGRA194_SID_PCIE5>;
+ iommu-map = <0x0 &smmu TEGRA194_SID_PCIE5 0x1000>;
+ iommu-map-mask = <0x0>;
+ dma-coherent;
};
sram@40000000 {
* for 8x and 11.025x sample rate streams.
*/
assigned-clock-rates = <258000000>;
+
+ interconnects = <&mc TEGRA194_MEMORY_CLIENT_APEDMAR &emc>,
+ <&mc TEGRA194_MEMORY_CLIENT_APEDMAW &emc>;
+ interconnect-names = "dma-mem", "write";
+ iommus = <&smmu TEGRA194_SID_APE>;
};
tcu: tcu {
status = "okay";
extcon = <&usb2_id>;
- usb@7600000 {
+ dwc3@7600000 {
extcon = <&usb2_id>;
dr_mode = "otg";
maximum-speed = "high-speed";
status = "okay";
extcon = <&usb3_id>;
- usb@6a00000 {
+ dwc3@6a00000 {
extcon = <&usb3_id>;
dr_mode = "otg";
};
resets = <&gcc GCC_USB0_BCR>;
status = "disabled";
- dwc_0: usb@8a00000 {
+ dwc_0: dwc3@8a00000 {
compatible = "snps,dwc3";
reg = <0x8a00000 0xcd00>;
interrupts = <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>;
resets = <&gcc GCC_USB1_BCR>;
status = "disabled";
- dwc_1: usb@8c00000 {
+ dwc_1: dwc3@8c00000 {
compatible = "snps,dwc3";
reg = <0x8c00000 0xcd00>;
interrupts = <GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>;
power-domains = <&gcc USB30_GDSC>;
status = "disabled";
- usb@6a00000 {
+ dwc3@6a00000 {
compatible = "snps,dwc3";
reg = <0x06a00000 0xcc00>;
interrupts = <0 131 IRQ_TYPE_LEVEL_HIGH>;
qcom,select-utmi-as-pipe-clk;
status = "disabled";
- usb@7600000 {
+ dwc3@7600000 {
compatible = "snps,dwc3";
reg = <0x07600000 0xcc00>;
interrupts = <0 138 IRQ_TYPE_LEVEL_HIGH>;
resets = <&gcc GCC_USB_30_BCR>;
- usb3_dwc3: usb@a800000 {
+ usb3_dwc3: dwc3@a800000 {
compatible = "snps,dwc3";
reg = <0x0a800000 0xcd00>;
interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>;
&usb3 {
status = "okay";
- usb@7580000 {
+ dwc3@7580000 {
dr_mode = "host";
};
};
assigned-clock-rates = <19200000>, <200000000>;
status = "disabled";
- usb@7580000 {
+ dwc3@7580000 {
compatible = "snps,dwc3";
reg = <0x07580000 0xcd00>;
interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>;
assigned-clock-rates = <19200000>, <133333333>;
status = "disabled";
- usb@78c0000 {
+ dwc3@78c0000 {
compatible = "snps,dwc3";
reg = <0x078c0000 0xcc00>;
interrupts = <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>;
<&gem_noc MASTER_APPSS_PROC 0 &config_noc SLAVE_USB3 0>;
interconnect-names = "usb-ddr", "apps-usb";
- usb_1_dwc3: usb@a600000 {
+ usb_1_dwc3: dwc3@a600000 {
compatible = "snps,dwc3";
reg = <0 0x0a600000 0 0xe000>;
interrupts = <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>;
<&gladiator_noc MASTER_APPSS_PROC 0 &config_noc SLAVE_USB3_0 0>;
interconnect-names = "usb-ddr", "apps-usb";
- usb_1_dwc3: usb@a600000 {
+ usb_1_dwc3: dwc3@a600000 {
compatible = "snps,dwc3";
reg = <0 0x0a600000 0 0xcd00>;
interrupts = <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>;
<&gladiator_noc MASTER_APPSS_PROC 0 &config_noc SLAVE_USB3_1 0>;
interconnect-names = "usb-ddr", "apps-usb";
- usb_2_dwc3: usb@a800000 {
+ usb_2_dwc3: dwc3@a800000 {
compatible = "snps,dwc3";
reg = <0 0x0a800000 0 0xcd00>;
interrupts = <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>;
resets = <&gcc GCC_USB30_PRIM_BCR>;
- usb_1_dwc3: usb@a600000 {
+ usb_1_dwc3: dwc3@a600000 {
compatible = "snps,dwc3";
reg = <0 0x0a600000 0 0xcd00>;
interrupts = <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>;
<GIC_SPI 384 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "eri", "rxi", "txi",
"bri", "dri", "tei";
- clocks = <&cpg CPG_MOD R9A07G044_CLK_SCIF0>;
+ clocks = <&cpg CPG_MOD R9A07G044_SCIF0_CLK_PCK>;
clock-names = "fck";
power-domains = <&cpg>;
- resets = <&cpg R9A07G044_CLK_SCIF0>;
+ resets = <&cpg R9A07G044_SCIF0_RST_SYSTEM_N>;
status = "disabled";
};
* cache before the transfer is done, causing old data to be seen by
* the CPU.
*/
-#define ARCH_DMA_MINALIGN L1_CACHE_BYTES
+#define ARCH_DMA_MINALIGN (128)
#ifdef CONFIG_KASAN_SW_TAGS
#define ARCH_SLAB_MINALIGN (1ULL << KASAN_SHADOW_SCALE_SHIFT)
static inline unsigned long regs_return_value(struct pt_regs *regs)
{
- return regs->regs[0];
+ unsigned long val = regs->regs[0];
+
+ /*
+ * Audit currently uses regs_return_value() instead of
+ * syscall_get_return_value(). Apply the same sign-extension here until
+ * audit is updated to use syscall_get_return_value().
+ */
+ if (compat_user_mode(regs))
+ val = sign_extend64(val, 31);
+
+ return val;
}
static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
#include <linux/cpumask.h>
+#include <asm/smp.h>
#include <asm/types.h>
struct mpidr_hash {
* accounting information necessary for robust unwinding.
*
* @fp: The fp value in the frame record (or the real fp)
- * @pc: The fp value in the frame record (or the real lr)
+ * @pc: The lr value in the frame record (or the real lr)
*
* @stacks_done: Stacks which have been entirely unwound, for which it is no
* longer valid to unwind to.
regs->regs[0] = regs->orig_x0;
}
-
-static inline long syscall_get_error(struct task_struct *task,
- struct pt_regs *regs)
+static inline long syscall_get_return_value(struct task_struct *task,
+ struct pt_regs *regs)
{
- unsigned long error = regs->regs[0];
+ unsigned long val = regs->regs[0];
if (is_compat_thread(task_thread_info(task)))
- error = sign_extend64(error, 31);
+ val = sign_extend64(val, 31);
- return IS_ERR_VALUE(error) ? error : 0;
+ return val;
}
-static inline long syscall_get_return_value(struct task_struct *task,
- struct pt_regs *regs)
+static inline long syscall_get_error(struct task_struct *task,
+ struct pt_regs *regs)
{
- return regs->regs[0];
+ unsigned long error = syscall_get_return_value(task, regs);
+
+ return IS_ERR_VALUE(error) ? error : 0;
}
static inline void syscall_set_return_value(struct task_struct *task,
# It's not safe to invoke KCOV when portions of the kernel environment aren't
# available or are out-of-sync with HW state. Since `noinstr` doesn't always
# inhibit KCOV instrumentation, disable it for the entire compilation unit.
-KCOV_INSTRUMENT_entry.o := n
+KCOV_INSTRUMENT_entry-common.o := n
KCOV_INSTRUMENT_idle.o := n
# Object file lists.
#include <asm/mmu_context.h>
#include <asm/mte.h>
#include <asm/processor.h>
+#include <asm/smp.h>
#include <asm/sysreg.h>
#include <asm/traps.h>
#include <asm/virt.h>
__el0_fiq_handler_common(regs);
}
-static void __el0_error_handler_common(struct pt_regs *regs)
+static void noinstr __el0_error_handler_common(struct pt_regs *regs)
{
unsigned long esr = read_sysreg(esr_el1);
* a PAGE_SIZE multiple in the range [_etext - MODULES_VSIZE,
* _stext) . This guarantees that the resulting region still
* covers [_stext, _etext], and that all relative branches can
- * be resolved without veneers.
+ * be resolved without veneers unless this region is exhausted
+ * and we fall back to a larger 2GB window in module_alloc()
+ * when ARM64_MODULE_PLTS is enabled.
*/
module_range = MODULES_VSIZE - (u64)(_etext - _stext);
module_alloc_base = (u64)_etext + offset - MODULES_VSIZE;
}
#endif
-static void update_gcr_el1_excl(u64 excl)
-{
-
- /*
- * Note that the mask controlled by the user via prctl() is an
- * include while GCR_EL1 accepts an exclude mask.
- * No need for ISB since this only affects EL0 currently, implicit
- * with ERET.
- */
- sysreg_clear_set_s(SYS_GCR_EL1, SYS_GCR_EL1_EXCL_MASK, excl);
-}
-
static void set_gcr_el1_excl(u64 excl)
{
current->thread.gcr_user_excl = excl;
if (!system_supports_mte())
return;
- update_gcr_el1_excl(gcr_kernel_excl);
+ sysreg_clear_set_s(SYS_GCR_EL1, SYS_GCR_EL1_EXCL_MASK, gcr_kernel_excl);
+ isb();
}
long set_mte_ctrl(struct task_struct *task, unsigned long arg)
audit_syscall_exit(regs);
if (flags & _TIF_SYSCALL_TRACEPOINT)
- trace_sys_exit(regs, regs_return_value(regs));
+ trace_sys_exit(regs, syscall_get_return_value(current, regs));
if (flags & (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP))
tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT);
#include <asm/unistd.h>
#include <asm/fpsimd.h>
#include <asm/ptrace.h>
+#include <asm/syscall.h>
#include <asm/signal32.h>
#include <asm/traps.h>
#include <asm/vdso.h>
retval == -ERESTART_RESTARTBLOCK ||
(retval == -ERESTARTSYS &&
!(ksig.ka.sa.sa_flags & SA_RESTART)))) {
- regs->regs[0] = -EINTR;
+ syscall_set_return_value(current, regs, -EINTR, 0);
regs->pc = continue_addr;
}
EXPORT_SYMBOL(__arm_smccc_sve_check)
.macro SMCCC instr
+ stp x29, x30, [sp, #-16]!
+ mov x29, sp
alternative_if ARM64_SVE
bl __arm_smccc_sve_check
alternative_else_nop_endif
\instr #0
- ldr x4, [sp]
+ ldr x4, [sp, #16]
stp x0, x1, [x4, #ARM_SMCCC_RES_X0_OFFS]
stp x2, x3, [x4, #ARM_SMCCC_RES_X2_OFFS]
- ldr x4, [sp, #8]
+ ldr x4, [sp, #24]
cbz x4, 1f /* no quirk structure */
ldr x9, [x4, #ARM_SMCCC_QUIRK_ID_OFFS]
cmp x9, #ARM_SMCCC_QUIRK_QCOM_A6
b.ne 1f
str x6, [x4, ARM_SMCCC_QUIRK_STATE_OFFS]
-1: ret
+1: ldp x29, x30, [sp], #16
+ ret
.endm
/*
#ifdef CONFIG_STACKTRACE
-noinline void arch_stack_walk(stack_trace_consume_fn consume_entry,
+noinline notrace void arch_stack_walk(stack_trace_consume_fn consume_entry,
void *cookie, struct task_struct *task,
struct pt_regs *regs)
{
ret = do_ni_syscall(regs, scno);
}
- if (is_compat_task())
- ret = lower_32_bits(ret);
-
- regs->regs[0] = ret;
+ syscall_set_return_value(current, regs, 0, ret);
/*
* Ultimately, this value will get limited by KSTACK_OFFSET_MAX(),
* syscall. do_notify_resume() will send a signal to userspace
* before the syscall is restarted.
*/
- regs->regs[0] = -ERESTARTNOINTR;
+ syscall_set_return_value(current, regs, -ERESTARTNOINTR, 0);
return;
}
* anyway.
*/
if (scno == NO_SYSCALL)
- regs->regs[0] = -ENOSYS;
+ syscall_set_return_value(current, regs, -ENOSYS, 0);
scno = syscall_trace_enter(regs);
if (scno == NO_SYSCALL)
goto trace_exit;
vma_shift = get_vma_page_shift(vma, hva);
}
- shared = (vma->vm_flags & VM_PFNMAP);
+ shared = (vma->vm_flags & VM_SHARED);
switch (vma_shift) {
#ifndef __PAGETABLE_PMD_FOLDED
.endm
.macro ldrh1 reg, ptr, val
- user_ldst 9998f, ldtrh, \reg, \ptr, \val
+ user_ldst 9997f, ldtrh, \reg, \ptr, \val
.endm
.macro strh1 reg, ptr, val
.endm
.macro ldr1 reg, ptr, val
- user_ldst 9998f, ldtr, \reg, \ptr, \val
+ user_ldst 9997f, ldtr, \reg, \ptr, \val
.endm
.macro str1 reg, ptr, val
.endm
.macro ldp1 reg1, reg2, ptr, val
- user_ldp 9998f, \reg1, \reg2, \ptr, \val
+ user_ldp 9997f, \reg1, \reg2, \ptr, \val
.endm
.macro stp1 reg1, reg2, ptr, val
.endm
end .req x5
+srcin .req x15
SYM_FUNC_START(__arch_copy_from_user)
add end, x0, x2
+ mov srcin, x1
#include "copy_template.S"
mov x0, #0 // Nothing to copy
ret
.section .fixup,"ax"
.align 2
+9997: cmp dst, dstin
+ b.ne 9998f
+ // Before being absolutely sure we couldn't copy anything, try harder
+USER(9998f, ldtrb tmp1w, [srcin])
+ strb tmp1w, [dst], #1
9998: sub x0, end, dst // bytes not copied
ret
.previous
.endm
.macro ldrh1 reg, ptr, val
- user_ldst 9998f, ldtrh, \reg, \ptr, \val
+ user_ldst 9997f, ldtrh, \reg, \ptr, \val
.endm
.macro strh1 reg, ptr, val
- user_ldst 9998f, sttrh, \reg, \ptr, \val
+ user_ldst 9997f, sttrh, \reg, \ptr, \val
.endm
.macro ldr1 reg, ptr, val
- user_ldst 9998f, ldtr, \reg, \ptr, \val
+ user_ldst 9997f, ldtr, \reg, \ptr, \val
.endm
.macro str1 reg, ptr, val
- user_ldst 9998f, sttr, \reg, \ptr, \val
+ user_ldst 9997f, sttr, \reg, \ptr, \val
.endm
.macro ldp1 reg1, reg2, ptr, val
- user_ldp 9998f, \reg1, \reg2, \ptr, \val
+ user_ldp 9997f, \reg1, \reg2, \ptr, \val
.endm
.macro stp1 reg1, reg2, ptr, val
- user_stp 9998f, \reg1, \reg2, \ptr, \val
+ user_stp 9997f, \reg1, \reg2, \ptr, \val
.endm
end .req x5
-
+srcin .req x15
SYM_FUNC_START(__arch_copy_in_user)
add end, x0, x2
+ mov srcin, x1
#include "copy_template.S"
mov x0, #0
ret
.section .fixup,"ax"
.align 2
+9997: cmp dst, dstin
+ b.ne 9998f
+ // Before being absolutely sure we couldn't copy anything, try harder
+USER(9998f, ldtrb tmp1w, [srcin])
+USER(9998f, sttrb tmp1w, [dst])
+ add dst, dst, #1
9998: sub x0, end, dst // bytes not copied
ret
.previous
.endm
.macro strh1 reg, ptr, val
- user_ldst 9998f, sttrh, \reg, \ptr, \val
+ user_ldst 9997f, sttrh, \reg, \ptr, \val
.endm
.macro ldr1 reg, ptr, val
.endm
.macro str1 reg, ptr, val
- user_ldst 9998f, sttr, \reg, \ptr, \val
+ user_ldst 9997f, sttr, \reg, \ptr, \val
.endm
.macro ldp1 reg1, reg2, ptr, val
.endm
.macro stp1 reg1, reg2, ptr, val
- user_stp 9998f, \reg1, \reg2, \ptr, \val
+ user_stp 9997f, \reg1, \reg2, \ptr, \val
.endm
end .req x5
+srcin .req x15
SYM_FUNC_START(__arch_copy_to_user)
add end, x0, x2
+ mov srcin, x1
#include "copy_template.S"
mov x0, #0
ret
.section .fixup,"ax"
.align 2
+9997: cmp dst, dstin
+ b.ne 9998f
+ // Before being absolutely sure we couldn't copy anything, try harder
+ ldrb tmp1w, [srcin]
+USER(9998f, sttrb tmp1w, [dst])
+ add dst, dst, #1
9998: sub x0, end, dst // bytes not copied
ret
.previous
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/mte-def.h>
/* Assumptions:
*
#define REP8_7f 0x7f7f7f7f7f7f7f7f
#define REP8_80 0x8080808080808080
+/*
+ * When KASAN_HW_TAGS is in use, memory is checked at MTE_GRANULE_SIZE
+ * (16-byte) granularity, and we must ensure that no access straddles this
+ * alignment boundary.
+ */
+#ifdef CONFIG_KASAN_HW_TAGS
+#define MIN_PAGE_SIZE MTE_GRANULE_SIZE
+#else
#define MIN_PAGE_SIZE 4096
+#endif
/* Since strings are short on average, we check the first 16 bytes
of the string for a NUL character. In order to do an unaligned ldp
return dt_virt;
}
-#if CONFIG_PGTABLE_LEVELS > 3
int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot)
{
pud_t new_pud = pfn_pud(__phys_to_pfn(phys), mk_pud_sect_prot(prot));
return 1;
}
-int pud_clear_huge(pud_t *pudp)
-{
- if (!pud_sect(READ_ONCE(*pudp)))
- return 0;
- pud_clear(pudp);
- return 1;
-}
-#endif
-
-#if CONFIG_PGTABLE_LEVELS > 2
int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot)
{
pmd_t new_pmd = pfn_pmd(__phys_to_pfn(phys), mk_pmd_sect_prot(prot));
return 1;
}
+int pud_clear_huge(pud_t *pudp)
+{
+ if (!pud_sect(READ_ONCE(*pudp)))
+ return 0;
+ pud_clear(pudp);
+ return 1;
+}
+
int pmd_clear_huge(pmd_t *pmdp)
{
if (!pmd_sect(READ_ONCE(*pmdp)))
pmd_clear(pmdp);
return 1;
}
-#endif
int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr)
{
return ret;
break;
+ /* speculation barrier */
+ case BPF_ST | BPF_NOSPEC:
+ /*
+ * Nothing required here.
+ *
+ * In case of arm64, we rely on the firmware mitigation of
+ * Speculative Store Bypass as controlled via the ssbd kernel
+ * parameter. Whenever the mitigation is enabled, it works
+ * for all of the kernel code with no need to provide any
+ * additional instructions.
+ */
+ break;
+
/* ST: *(size *)(dst + off) = imm */
case BPF_ST | BPF_MEM | BPF_W:
case BPF_ST | BPF_MEM | BPF_H:
bool "H8MAX"
select H83069
select RAMKERNEL
- select HAVE_IDE
help
H8MAX Evaluation Board Support
More Information. (Japanese Only)
select HAVE_ASM_MODVERSIONS
select HAVE_UNSTABLE_SCHED_CLOCK
select HAVE_EXIT_THREAD
- select HAVE_IDE
select HAVE_KPROBES
select HAVE_KRETPROBES
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_DEBUG_BUGVERBOSE
select HAVE_EFFICIENT_UNALIGNED_ACCESS if !CPU_HAS_NO_UNALIGNED
select HAVE_FUTEX_CMPXCHG if MMU && FUTEX
- select HAVE_IDE
select HAVE_MOD_ARCH_SPECIFIC
select HAVE_UID16
select MMU_GATHER_NO_RANGE if MMU
depends on MMU
select MMU_MOTOROLA if MMU
select HAVE_ARCH_NVRAM_OPS
+ select HAVE_PATA_PLATFORM
select LEGACY_TIMER_TICK
help
This option enables support for the Apple Macintosh series of
DEFINE_CLK(sys, "sys.0", MCF_BUSCLK);
static struct clk_lookup m525x_clk_lookup[] = {
- CLKDEV_INIT(NULL, "pll.0", &pll),
+ CLKDEV_INIT(NULL, "pll.0", &clk_pll),
CLKDEV_INIT(NULL, "sys.0", &clk_sys),
CLKDEV_INIT("mcftmr.0", NULL, &clk_sys),
CLKDEV_INIT("mcftmr.1", NULL, &clk_sys),
select HAVE_FUNCTION_TRACER
select HAVE_GCC_PLUGINS
select HAVE_GENERIC_VDSO
- select HAVE_IDE
select HAVE_IOREMAP_PROT
select HAVE_IRQ_EXIT_ON_IRQ_STACK
select HAVE_IRQ_TIME_ACCOUNTING
ifdef CONFIG_MIPS
CHECKFLAGS += $(shell $(CC) $(KBUILD_CFLAGS) -dM -E -x c /dev/null | \
- egrep -vw '__GNUC_(|MINOR_|PATCHLEVEL_)_' | \
+ egrep -vw '__GNUC_(MINOR_|PATCHLEVEL_)?_' | \
sed -e "s/^\#define /-D'/" -e "s/ /'='/" -e "s/$$/'/" -e 's/\$$/&&/g')
endif
/* we only have a 32-bit FPU */
return SIGFPE;
#endif
- fallthrough;
+ /* fallthrough */
case FPU_32BIT:
if (cpu_has_fre) {
/* clear FRE */
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
{
- pmd_t *pmd = NULL;
+ pmd_t *pmd;
struct page *pg;
- pg = alloc_pages(GFP_KERNEL | __GFP_ACCOUNT, PMD_ORDER);
- if (pg) {
- pgtable_pmd_page_ctor(pg);
- pmd = (pmd_t *)page_address(pg);
- pmd_init((unsigned long)pmd, (unsigned long)invalid_pte_table);
+ pg = alloc_pages(GFP_KERNEL_ACCOUNT, PMD_ORDER);
+ if (!pg)
+ return NULL;
+
+ if (!pgtable_pmd_page_ctor(pg)) {
+ __free_pages(pg, PMD_ORDER);
+ return NULL;
}
+
+ pmd = (pmd_t *)page_address(pg);
+ pmd_init((unsigned long)pmd, (unsigned long)invalid_pte_table);
return pmd;
}
switch (boot_cpu_type()) {
default:
if (sizeof(long) == 4) {
+ fallthrough;
case CPU_LOONGSON2EF:
/* Loongson2 ebase is different than r4k, we have more space */
if ((p - tlb_handler) > 64)
default:
if (cpu_has_mips_r2_exec_hazard) {
uasm_i_ehb(&p);
+ fallthrough;
case CPU_CAVIUM_OCTEON:
case CPU_CAVIUM_OCTEON_PLUS:
.mapbase = 0x1f000900, /* The CBUS UART */
.irq = MIPS_CPU_IRQ_BASE + MIPSCPU_INT_MB2,
.uartclk = 3686400, /* Twice the usual clk! */
- .iotype = UPIO_MEM32,
+ .iotype = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN) ?
+ UPIO_MEM32BE : UPIO_MEM32,
.flags = CBUS_UART_FLAGS,
.regshift = 3,
},
}
break;
+ case BPF_ST | BPF_NOSPEC: /* speculation barrier */
+ break;
+
case BPF_ST | BPF_B | BPF_MEM:
case BPF_ST | BPF_H | BPF_MEM:
case BPF_ST | BPF_W | BPF_MEM:
vma = find_vma(mm, addr);
if (TASK_SIZE - len >= addr &&
- (!vma || addr + len <= vma->vm_start))
+ (!vma || addr + len <= vm_start_gap(vma)))
return addr;
}
def_bool y
select ARCH_32BIT_OFF_T if !64BIT
select ARCH_MIGHT_HAVE_PC_PARPORT
- select HAVE_IDE
select HAVE_FUNCTION_TRACER
select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_SYSCALL_TRACEPOINTS
select HAVE_HARDLOCKUP_DETECTOR_ARCH if PPC_BOOK3S_64 && SMP
select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH
select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx)
- select HAVE_IDE
select HAVE_IOREMAP_PROT
select HAVE_IRQ_EXIT_ON_IRQ_STACK
select HAVE_IRQ_TIME_ACCOUNTING
ccflags-y := -shared -fno-common -fno-builtin -nostdlib \
-Wl,-soname=linux-vdso64.so.1 -Wl,--hash-style=both
+
+# Go prior to 1.16.x assumes r30 is not clobbered by any VDSO code. That used to be true
+# by accident when the VDSO was hand-written asm code, but may not be now that the VDSO is
+# compiler generated. To avoid breaking Go tell GCC not to use r30. Impact on code
+# generation is minimal, it will just use r29 instead.
+ccflags-y += $(call cc-option, -ffixed-r30)
+
asflags-y := -D__VDSO64__ -s
targets += vdso64.lds
HFSCR_DSCR | HFSCR_VECVSX | HFSCR_FP | HFSCR_PREFIX;
if (cpu_has_feature(CPU_FTR_HVMODE)) {
vcpu->arch.hfscr &= mfspr(SPRN_HFSCR);
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
vcpu->arch.hfscr |= HFSCR_TM;
+#endif
}
if (cpu_has_feature(CPU_FTR_TM_COMP))
vcpu->arch.hfscr |= HFSCR_TM;
if (vcpu->kvm->arch.l1_ptcr == 0)
return H_NOT_AVAILABLE;
+ if (MSR_TM_TRANSACTIONAL(vcpu->arch.shregs.msr))
+ return H_BAD_MODE;
+
/* copy parameters in */
hv_ptr = kvmppc_get_gpr(vcpu, 4);
regs_ptr = kvmppc_get_gpr(vcpu, 5);
if (l2_hv.vcpu_token >= NR_CPUS)
return H_PARAMETER;
+ /*
+ * L1 must have set up a suspended state to enter the L2 in a
+ * transactional state, and only in that case. These have to be
+ * filtered out here to prevent causing a TM Bad Thing in the
+ * host HRFID. We could synthesize a TM Bad Thing back to the L1
+ * here but there doesn't seem like much point.
+ */
+ if (MSR_TM_SUSPENDED(vcpu->arch.shregs.msr)) {
+ if (!MSR_TM_ACTIVE(l2_regs.msr))
+ return H_BAD_MODE;
+ } else {
+ if (l2_regs.msr & MSR_TS_MASK)
+ return H_BAD_MODE;
+ if (WARN_ON_ONCE(vcpu->arch.shregs.msr & MSR_TS_MASK))
+ return H_BAD_MODE;
+ }
+
/* translate lpid */
l2 = kvmhv_get_nested(vcpu->kvm, l2_hv.lpid, true);
if (!l2)
*/
mtspr(SPRN_HDEC, hdec);
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+tm_return_to_guest:
+#endif
mtspr(SPRN_DAR, vcpu->arch.shregs.dar);
mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr);
mtspr(SPRN_SRR0, vcpu->arch.shregs.srr0);
* is in real suspend mode and is trying to transition to
* transactional mode.
*/
- if (local_paca->kvm_hstate.fake_suspend &&
+ if (!local_paca->kvm_hstate.fake_suspend &&
(vcpu->arch.shregs.msr & MSR_TS_S)) {
if (kvmhv_p9_tm_emulation_early(vcpu)) {
- /* Prevent it being handled again. */
- trap = 0;
+ /*
+ * Go straight back into the guest with the
+ * new NIP/MSR as set by TM emulation.
+ */
+ mtspr(SPRN_HSRR0, vcpu->arch.regs.nip);
+ mtspr(SPRN_HSRR1, vcpu->arch.shregs.msr);
+
+ /*
+ * tm_return_to_guest re-loads SRR0/1, DAR,
+ * DSISR after RI is cleared, in case they had
+ * been clobbered by a MCE.
+ */
+ __mtmsrd(0, 1); /* clear RI */
+ goto tm_return_to_guest;
}
}
#endif
* If we are in real mode, only switch MMU on after the MMU is
* switched to host, to avoid the P9_RADIX_PREFETCH_BUG.
*/
+ if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) &&
+ vcpu->arch.shregs.msr & MSR_TS_MASK)
+ msr |= MSR_TS_S;
+
__mtmsrd(msr, 0);
end_timing(vcpu);
* value so we can restore it on the way out.
*/
orig_rets = args.rets;
+ if (be32_to_cpu(args.nargs) >= ARRAY_SIZE(args.args)) {
+ /*
+ * Don't overflow our args array: ensure there is room for
+ * at least rets[0] (even if the call specifies 0 nret).
+ *
+ * Each handler must then check for the correct nargs and nret
+ * values, but they may always return failure in rets[0].
+ */
+ rc = -EINVAL;
+ goto fail;
+ }
args.rets = &args.args[be32_to_cpu(args.nargs)];
mutex_lock(&vcpu->kvm->arch.rtas_token_lock);
fail:
/*
* We only get here if the guest has called RTAS with a bogus
- * args pointer. That means we can't get to the args, and so we
- * can't fail the RTAS call. So fail right out to userspace,
- * which should kill the guest.
+ * args pointer or nargs/nret values that would overflow the
+ * array. That means we can't get to the args, and so we can't
+ * fail the RTAS call. So fail right out to userspace, which
+ * should kill the guest.
+ *
+ * SLOF should actually pass the hcall return value from the
+ * rtas handler call in r3, so enter_rtas could be modified to
+ * return a failure indication in r3 and we could return such
+ * errors to the guest rather than failing to host userspace.
+ * However old guests that don't test for failure could then
+ * continue silently after errors, so for now we won't do this.
*/
return rc;
}
{
struct kvm_enable_cap cap;
r = -EFAULT;
- vcpu_load(vcpu);
if (copy_from_user(&cap, argp, sizeof(cap)))
goto out;
+ vcpu_load(vcpu);
r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
vcpu_put(vcpu);
break;
case KVM_DIRTY_TLB: {
struct kvm_dirty_tlb dirty;
r = -EFAULT;
- vcpu_load(vcpu);
if (copy_from_user(&dirty, argp, sizeof(dirty)))
goto out;
+ vcpu_load(vcpu);
r = kvm_vcpu_ioctl_dirty_tlb(vcpu, &dirty);
vcpu_put(vcpu);
break;
mtspr(SPRN_MD_AP, MD_APG_KUAP);
}
#endif
+
+int pud_clear_huge(pud_t *pud)
+{
+ return 0;
+}
+
+int pmd_clear_huge(pmd_t *pmd)
+{
+ return 0;
+}
break;
/*
+ * BPF_ST NOSPEC (speculation barrier)
+ */
+ case BPF_ST | BPF_NOSPEC:
+ break;
+
+ /*
* BPF_ST(X)
*/
case BPF_STX | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = src */
break;
/*
+ * BPF_ST NOSPEC (speculation barrier)
+ */
+ case BPF_ST | BPF_NOSPEC:
+ break;
+
+ /*
* BPF_ST(X)
*/
case BPF_STX | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = src */
switch (regs->msr & SRR1_WAKEMASK) {
case SRR1_WAKEDEC:
set_dec(1);
+ break;
case SRR1_WAKEEE:
/*
* Handle these when interrupts get re-enabled and we take
switch(psurge_type) {
case PSURGE_DUAL:
out_8(psurge_sec_intr, ~0);
+ break;
case PSURGE_NONE:
break;
default:
#include "../../../../drivers/pci/pci.h"
DEFINE_STATIC_KEY_FALSE(shared_processor);
-EXPORT_SYMBOL_GPL(shared_processor);
+EXPORT_SYMBOL(shared_processor);
int CMO_PrPSP = -1;
int CMO_SecPSP = -1;
config STACKPROTECTOR_PER_TASK
def_bool y
+ depends on !GCC_PLUGIN_RANDSTRUCT
depends on STACKPROTECTOR && CC_HAVE_STACKPROTECTOR_TLS
+config PHYS_RAM_BASE_FIXED
+ bool "Explicitly specified physical RAM address"
+ default n
+
config PHYS_RAM_BASE
hex "Platform Physical RAM address"
+ depends on PHYS_RAM_BASE_FIXED
default "0x80000000"
help
This is the physical address of RAM in the system. It has to be
# This prevents XIP from being enabled by all{yes,mod}config, which
# fail to build since XIP doesn't support large kernels.
depends on !COMPILE_TEST
+ select PHYS_RAM_BASE_FIXED
help
Execute-In-Place allows the kernel to run from non-volatile storage
directly addressable by the CPU, such as NOR flash. This saves RAM
memory@80000000 {
device_type = "memory";
- reg = <0x0 0x80000000 0x2 0x00000000>;
+ reg = <0x0 0x80000000 0x4 0x00000000>;
};
soc {
#define ARCH_EFI_IRQ_FLAGS_MASK (SR_IE | SR_SPIE)
-/* Load initrd at enough distance from DRAM start */
+/* Load initrd anywhere in system RAM */
static inline unsigned long efi_get_max_initrd_addr(unsigned long image_addr)
{
- return image_addr + SZ_256M;
+ return ULONG_MAX;
}
#define alloc_screen_info(x...) (&screen_info)
};
extern struct kernel_mapping kernel_map;
+extern phys_addr_t phys_ram_base;
#ifdef CONFIG_64BIT
#define is_kernel_mapping(x) \
#define linear_mapping_pa_to_va(x) ((void *)((unsigned long)(x) + kernel_map.va_pa_offset))
#define kernel_mapping_pa_to_va(y) ({ \
unsigned long _y = y; \
- (_y >= CONFIG_PHYS_RAM_BASE) ? \
- (void *)((unsigned long)(_y) + kernel_map.va_kernel_pa_offset + XIP_OFFSET) : \
- (void *)((unsigned long)(_y) + kernel_map.va_kernel_xip_pa_offset); \
+ (IS_ENABLED(CONFIG_XIP_KERNEL) && _y < phys_ram_base) ? \
+ (void *)((unsigned long)(_y) + kernel_map.va_kernel_xip_pa_offset) : \
+ (void *)((unsigned long)(_y) + kernel_map.va_kernel_pa_offset + XIP_OFFSET); \
})
#define __pa_to_va_nodebug(x) linear_mapping_pa_to_va(x)
fp = frame_pointer(regs);
sp = user_stack_pointer(regs);
pc = instruction_pointer(regs);
- } else if (task == current) {
+ } else if (task == NULL || task == current) {
fp = (unsigned long)__builtin_frame_address(1);
sp = (unsigned long)__builtin_frame_address(0);
pc = (unsigned long)__builtin_return_address(0);
{
unsigned long pc = 0;
- if (likely(task && task != current && !task_is_running(task)))
+ if (likely(task && task != current && !task_is_running(task))) {
+ if (!try_get_task_stack(task))
+ return 0;
walk_stackframe(task, NULL, save_wchan, &pc);
+ put_task_stack(task);
+ }
return pc;
}
* t0 - end of uncopied dst
*/
add t0, a0, a2
- bgtu a0, t0, 5f
/*
* Use byte copy only if too small.
+ * SZREG holds 4 for RV32 and 8 for RV64
*/
- li a3, 8*SZREG /* size must be larger than size in word_copy */
+ li a3, 9*SZREG /* size must be larger than size in word_copy */
bltu a2, a3, .Lbyte_copy_tail
/*
- * Copy first bytes until dst is align to word boundary.
+ * Copy first bytes until dst is aligned to word boundary.
* a0 - start of dst
* t1 - start of aligned dst
*/
addi t1, a0, SZREG-1
andi t1, t1, ~(SZREG-1)
/* dst is already aligned, skip */
- beq a0, t1, .Lskip_first_bytes
+ beq a0, t1, .Lskip_align_dst
1:
/* a5 - one byte for copying data */
fixup lb a5, 0(a1), 10f
addi a0, a0, 1 /* dst */
bltu a0, t1, 1b /* t1 - start of aligned dst */
-.Lskip_first_bytes:
+.Lskip_align_dst:
/*
* Now dst is aligned.
* Use shift-copy if src is misaligned.
*
* a0 - start of aligned dst
* a1 - start of aligned src
- * a3 - a1 & mask:(SZREG-1)
* t0 - end of aligned dst
*/
- addi t0, t0, -(8*SZREG-1) /* not to over run */
+ addi t0, t0, -(8*SZREG) /* not to over run */
2:
fixup REG_L a4, 0(a1), 10f
fixup REG_L a5, SZREG(a1), 10f
addi a1, a1, 8*SZREG
bltu a0, t0, 2b
- addi t0, t0, 8*SZREG-1 /* revert to original value */
+ addi t0, t0, 8*SZREG /* revert to original value */
j .Lbyte_copy_tail
.Lshift_copy:
* For misaligned copy we still perform aligned word copy, but
* we need to use the value fetched from the previous iteration and
* do some shifts.
- * This is safe because reading less than a word size.
+ * This is safe because reading is less than a word size.
*
* a0 - start of aligned dst
* a1 - start of src
*/
/* calculating aligned word boundary for dst */
andi t1, t0, ~(SZREG-1)
- /* Converting unaligned src to aligned arc */
+ /* Converting unaligned src to aligned src */
andi a1, a1, ~(SZREG-1)
/*
* t3 - prev shift
* t4 - current shift
*/
- slli t3, a3, LGREG
+ slli t3, a3, 3 /* converting bytes in a3 to bits */
li a5, SZREG*8
sub t4, a5, t3
- /* Load the first word to combine with seceond word */
+ /* Load the first word to combine with second word */
fixup REG_L a5, 0(a1), 10f
3:
* a1 - start of remaining src
* t0 - end of remaining dst
*/
- bgeu a0, t0, 5f
+ bgeu a0, t0, .Lout_copy_user /* check if end of copy */
4:
fixup lb a5, 0(a1), 10f
addi a1, a1, 1 /* src */
addi a0, a0, 1 /* dst */
bltu a0, t0, 4b /* t0 - end of dst */
-5:
+.Lout_copy_user:
/* Disable access to user memory */
csrc CSR_STATUS, t6
li a0, 0
#define kernel_map (*(struct kernel_mapping *)XIP_FIXUP(&kernel_map))
#endif
+phys_addr_t phys_ram_base __ro_after_init;
+EXPORT_SYMBOL(phys_ram_base);
+
#ifdef CONFIG_XIP_KERNEL
extern char _xiprom[], _exiprom[];
#endif
}
/*
- * The default maximal physical memory size is -PAGE_OFFSET,
- * limit the memory size via mem.
+ * The default maximal physical memory size is -PAGE_OFFSET for 32-bit kernel,
+ * whereas for 64-bit kernel, the end of the virtual address space is occupied
+ * by the modules/BPF/kernel mappings which reduces the available size of the
+ * linear mapping.
+ * Limit the memory size via mem.
*/
+#ifdef CONFIG_64BIT
+static phys_addr_t memory_limit = -PAGE_OFFSET - SZ_4G;
+#else
static phys_addr_t memory_limit = -PAGE_OFFSET;
+#endif
static int __init early_mem(char *p)
{
{
phys_addr_t vmlinux_end = __pa_symbol(&_end);
phys_addr_t vmlinux_start = __pa_symbol(&_start);
- phys_addr_t max_mapped_addr = __pa(~(ulong)0);
- phys_addr_t dram_end;
+ phys_addr_t __maybe_unused max_mapped_addr;
+ phys_addr_t phys_ram_end;
#ifdef CONFIG_XIP_KERNEL
vmlinux_start = __pa_symbol(&_sdata);
#endif
memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
- dram_end = memblock_end_of_DRAM();
+
+ phys_ram_end = memblock_end_of_DRAM();
+#ifndef CONFIG_64BIT
+#ifndef CONFIG_XIP_KERNEL
+ phys_ram_base = memblock_start_of_DRAM();
+#endif
/*
* memblock allocator is not aware of the fact that last 4K bytes of
* the addressable memory can not be mapped because of IS_ERR_VALUE
* macro. Make sure that last 4k bytes are not usable by memblock
- * if end of dram is equal to maximum addressable memory.
+ * if end of dram is equal to maximum addressable memory. For 64-bit
+ * kernel, this problem can't happen here as the end of the virtual
+ * address space is occupied by the kernel mapping then this check must
+ * be done in create_kernel_page_table.
*/
- if (max_mapped_addr == (dram_end - 1))
+ max_mapped_addr = __pa(~(ulong)0);
+ if (max_mapped_addr == (phys_ram_end - 1))
memblock_set_current_limit(max_mapped_addr - 4096);
+#endif
- min_low_pfn = PFN_UP(memblock_start_of_DRAM());
- max_low_pfn = max_pfn = PFN_DOWN(dram_end);
+ min_low_pfn = PFN_UP(phys_ram_base);
+ max_low_pfn = max_pfn = PFN_DOWN(phys_ram_end);
dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn));
set_max_mapnr(max_low_pfn - ARCH_PFN_OFFSET);
kernel_map.xiprom = (uintptr_t)CONFIG_XIP_PHYS_ADDR;
kernel_map.xiprom_sz = (uintptr_t)(&_exiprom) - (uintptr_t)(&_xiprom);
+ phys_ram_base = CONFIG_PHYS_RAM_BASE;
kernel_map.phys_addr = (uintptr_t)CONFIG_PHYS_RAM_BASE;
kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_sdata);
BUG_ON((PAGE_OFFSET % PGDIR_SIZE) != 0);
BUG_ON((kernel_map.phys_addr % map_size) != 0);
+#ifdef CONFIG_64BIT
+ /*
+ * The last 4K bytes of the addressable memory can not be mapped because
+ * of IS_ERR_VALUE macro.
+ */
+ BUG_ON((kernel_map.virt_addr + kernel_map.size) > ADDRESS_SPACE_END - SZ_4K);
+#endif
+
pt_ops.alloc_pte = alloc_pte_early;
pt_ops.get_pte_virt = get_pte_virt_early;
#ifndef __PAGETABLE_PMD_FOLDED
if (start <= __pa(PAGE_OFFSET) &&
__pa(PAGE_OFFSET) < end)
start = __pa(PAGE_OFFSET);
+ if (end >= __pa(PAGE_OFFSET) + memory_limit)
+ end = __pa(PAGE_OFFSET) + memory_limit;
map_size = best_map_size(start, end - start);
for (pa = start; pa < end; pa += map_size) {
return -1;
break;
+ /* speculation barrier */
+ case BPF_ST | BPF_NOSPEC:
+ break;
+
case BPF_ST | BPF_MEM | BPF_B:
case BPF_ST | BPF_MEM | BPF_H:
case BPF_ST | BPF_MEM | BPF_W:
emit_ld(rd, 0, RV_REG_T1, ctx);
break;
+ /* speculation barrier */
+ case BPF_ST | BPF_NOSPEC:
+ break;
+
/* ST: *(size *)(dst + off) = imm */
case BPF_ST | BPF_MEM | BPF_B:
emit_imm(RV_REG_T1, imm, ctx);
KASAN_SANITIZE := n
obj-y := $(if $(CONFIG_KERNEL_UNCOMPRESSED),,decompressor.o) info.o
+obj-$(CONFIG_KERNEL_ZSTD) += clz_ctz.o
obj-all := $(obj-y) piggy.o syms.o
targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2
targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include "../../../../lib/clz_ctz.c"
#include <asm/errno.h>
#include <asm/sigp.h>
-#ifdef CC_USING_EXPOLINE
- .pushsection .dma.text.__s390_indirect_jump_r14,"axG"
-__dma__s390_indirect_jump_r14:
- larl %r1,0f
- ex 0,0(%r1)
- j .
-0: br %r14
- .popsection
-#endif
-
.section .dma.text,"ax"
/*
* Simplified version of expoline thunk. The normal thunks can not be used here,
* affects a few functions that are not performance-relevant.
*/
.macro BR_EX_DMA_r14
-#ifdef CC_USING_EXPOLINE
- jg __dma__s390_indirect_jump_r14
-#else
- br %r14
-#endif
+ larl %r1,0f
+ ex 0,0(%r1)
+ j .
+0: br %r14
.endm
/*
CONFIG_AUDIT=y
CONFIG_NO_HZ_IDLE=y
CONFIG_HIGH_RES_TIMERS=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_BPF_JIT=y
+CONFIG_BPF_JIT_ALWAYS_ON=y
+CONFIG_BPF_LSM=y
CONFIG_PREEMPT=y
+CONFIG_SCHED_CORE=y
CONFIG_BSD_PROCESS_ACCT=y
CONFIG_BSD_PROCESS_ACCT_V3=y
CONFIG_TASKSTATS=y
CONFIG_CGROUP_CPUACCT=y
CONFIG_CGROUP_PERF=y
CONFIG_CGROUP_BPF=y
+CONFIG_CGROUP_MISC=y
CONFIG_NAMESPACES=y
CONFIG_USER_NS=y
CONFIG_CHECKPOINT_RESTORE=y
CONFIG_SCHED_AUTOGROUP=y
CONFIG_EXPERT=y
# CONFIG_SYSFS_SYSCALL is not set
-CONFIG_BPF_LSM=y
-CONFIG_BPF_SYSCALL=y
CONFIG_USERFAULTFD=y
# CONFIG_COMPAT_BRK is not set
CONFIG_PROFILING=y
CONFIG_BLK_WBT=y
CONFIG_BLK_CGROUP_IOLATENCY=y
CONFIG_BLK_CGROUP_IOCOST=y
+CONFIG_BLK_CGROUP_IOPRIO=y
CONFIG_BLK_INLINE_ENCRYPTION=y
CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_FRONTSWAP=y
CONFIG_CMA_DEBUG=y
CONFIG_CMA_DEBUGFS=y
+CONFIG_CMA_SYSFS=y
CONFIG_CMA_AREAS=7
CONFIG_MEM_SOFT_DIRTY=y
CONFIG_ZSWAP=y
CONFIG_MPTCP=y
CONFIG_NETFILTER=y
CONFIG_BRIDGE_NETFILTER=m
+CONFIG_NETFILTER_NETLINK_HOOK=m
CONFIG_NF_CONNTRACK=m
CONFIG_NF_CONNTRACK_SECMARK=y
CONFIG_NF_CONNTRACK_EVENTS=y
CONFIG_IP_VS_PE_SIP=m
CONFIG_NFT_FIB_IPV4=m
CONFIG_NF_TABLES_ARP=y
+CONFIG_NF_LOG_IPV4=m
CONFIG_IP_NF_IPTABLES=m
CONFIG_IP_NF_MATCH_AH=m
CONFIG_IP_NF_MATCH_ECN=m
CONFIG_L2TP_V3=y
CONFIG_L2TP_IP=m
CONFIG_L2TP_ETH=m
-CONFIG_BRIDGE=m
+CONFIG_BRIDGE=y
CONFIG_BRIDGE_MRP=y
CONFIG_VLAN_8021Q=m
CONFIG_VLAN_8021Q_GVRP=y
CONFIG_VIRTIO_VSOCKETS=m
CONFIG_NETLINK_DIAG=m
CONFIG_CGROUP_NET_PRIO=y
-CONFIG_BPF_JIT=y
CONFIG_NET_PKTGEN=m
CONFIG_PCI=y
-CONFIG_PCI_IOV=y
# CONFIG_PCIEASPM is not set
CONFIG_PCI_DEBUG=y
+CONFIG_PCI_IOV=y
CONFIG_HOTPLUG_PCI=y
CONFIG_HOTPLUG_PCI_S390=y
CONFIG_DEVTMPFS=y
CONFIG_MD_FAULTY=m
CONFIG_MD_CLUSTER=m
CONFIG_BCACHE=m
-CONFIG_BLK_DEV_DM=m
+CONFIG_BLK_DEV_DM=y
CONFIG_DM_UNSTRIPED=m
CONFIG_DM_CRYPT=m
CONFIG_DM_SNAPSHOT=m
CONFIG_DM_MULTIPATH_HST=m
CONFIG_DM_MULTIPATH_IOA=m
CONFIG_DM_DELAY=m
+CONFIG_DM_INIT=y
CONFIG_DM_UEVENT=y
CONFIG_DM_FLAKEY=m
CONFIG_DM_VERITY=m
# CONFIG_NET_VENDOR_GOOGLE is not set
# CONFIG_NET_VENDOR_HUAWEI is not set
# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MICROSOFT is not set
# CONFIG_NET_VENDOR_MARVELL is not set
CONFIG_MLX4_EN=m
CONFIG_MLX5_CORE=m
CONFIG_LEGACY_PTY_COUNT=0
CONFIG_VIRTIO_CONSOLE=m
CONFIG_HW_RANDOM_VIRTIO=m
-CONFIG_RAW_DRIVER=m
CONFIG_HANGCHECK_TIMER=m
CONFIG_TN3270_FS=y
CONFIG_PPS=m
CONFIG_VFIO=m
CONFIG_VFIO_PCI=m
CONFIG_VFIO_MDEV=m
-CONFIG_VFIO_MDEV_DEVICE=m
CONFIG_VIRTIO_PCI=m
CONFIG_VIRTIO_BALLOON=m
CONFIG_VIRTIO_INPUT=y
CONFIG_CUSE=m
CONFIG_VIRTIO_FS=m
CONFIG_OVERLAY_FS=m
+CONFIG_NETFS_STATS=y
CONFIG_FSCACHE=m
CONFIG_CACHEFILES=m
CONFIG_ISO9660_FS=y
CONFIG_NFSD_V4=y
CONFIG_NFSD_V4_SECURITY_LABEL=y
CONFIG_CIFS=m
-CONFIG_CIFS_STATS2=y
CONFIG_CIFS_WEAK_PW_HASH=y
CONFIG_CIFS_UPCALL=y
CONFIG_CIFS_XATTR=y
CONFIG_SECURITY_SELINUX_DISABLE=y
CONFIG_SECURITY_LOCKDOWN_LSM=y
CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y
+CONFIG_SECURITY_LANDLOCK=y
CONFIG_INTEGRITY_SIGNATURE=y
CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
CONFIG_IMA=y
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_DH=m
CONFIG_CRYPTO_ECDH=m
+CONFIG_CRYPTO_ECDSA=m
CONFIG_CRYPTO_ECRDSA=m
CONFIG_CRYPTO_SM2=m
CONFIG_CRYPTO_CURVE25519=m
CONFIG_FAIL_FUNCTION=y
CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y
CONFIG_LKDTM=m
-CONFIG_TEST_LIST_SORT=y
CONFIG_TEST_MIN_HEAP=y
CONFIG_TEST_SORT=y
CONFIG_KPROBES_SANITY_TEST=y
CONFIG_ATOMIC64_SELFTEST=y
CONFIG_TEST_BITOPS=m
CONFIG_TEST_BPF=m
+CONFIG_TEST_LIVEPATCH=m
CONFIG_AUDIT=y
CONFIG_NO_HZ_IDLE=y
CONFIG_HIGH_RES_TIMERS=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_BPF_JIT=y
+CONFIG_BPF_JIT_ALWAYS_ON=y
+CONFIG_BPF_LSM=y
+CONFIG_SCHED_CORE=y
CONFIG_BSD_PROCESS_ACCT=y
CONFIG_BSD_PROCESS_ACCT_V3=y
CONFIG_TASKSTATS=y
CONFIG_CGROUP_CPUACCT=y
CONFIG_CGROUP_PERF=y
CONFIG_CGROUP_BPF=y
+CONFIG_CGROUP_MISC=y
CONFIG_NAMESPACES=y
CONFIG_USER_NS=y
CONFIG_CHECKPOINT_RESTORE=y
CONFIG_SCHED_AUTOGROUP=y
CONFIG_EXPERT=y
# CONFIG_SYSFS_SYSCALL is not set
-CONFIG_BPF_LSM=y
-CONFIG_BPF_SYSCALL=y
CONFIG_USERFAULTFD=y
# CONFIG_COMPAT_BRK is not set
CONFIG_PROFILING=y
CONFIG_BLK_WBT=y
CONFIG_BLK_CGROUP_IOLATENCY=y
CONFIG_BLK_CGROUP_IOCOST=y
+CONFIG_BLK_CGROUP_IOPRIO=y
CONFIG_BLK_INLINE_ENCRYPTION=y
CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK=y
CONFIG_PARTITION_ADVANCED=y
CONFIG_TRANSPARENT_HUGEPAGE=y
CONFIG_CLEANCACHE=y
CONFIG_FRONTSWAP=y
+CONFIG_CMA_SYSFS=y
CONFIG_CMA_AREAS=7
CONFIG_MEM_SOFT_DIRTY=y
CONFIG_ZSWAP=y
CONFIG_MPTCP=y
CONFIG_NETFILTER=y
CONFIG_BRIDGE_NETFILTER=m
+CONFIG_NETFILTER_NETLINK_HOOK=m
CONFIG_NF_CONNTRACK=m
CONFIG_NF_CONNTRACK_SECMARK=y
CONFIG_NF_CONNTRACK_EVENTS=y
CONFIG_IP_VS_PE_SIP=m
CONFIG_NFT_FIB_IPV4=m
CONFIG_NF_TABLES_ARP=y
+CONFIG_NF_LOG_IPV4=m
CONFIG_IP_NF_IPTABLES=m
CONFIG_IP_NF_MATCH_AH=m
CONFIG_IP_NF_MATCH_ECN=m
CONFIG_L2TP_V3=y
CONFIG_L2TP_IP=m
CONFIG_L2TP_ETH=m
-CONFIG_BRIDGE=m
+CONFIG_BRIDGE=y
CONFIG_BRIDGE_MRP=y
CONFIG_VLAN_8021Q=m
CONFIG_VLAN_8021Q_GVRP=y
CONFIG_VIRTIO_VSOCKETS=m
CONFIG_NETLINK_DIAG=m
CONFIG_CGROUP_NET_PRIO=y
-CONFIG_BPF_JIT=y
CONFIG_NET_PKTGEN=m
CONFIG_PCI=y
-CONFIG_PCI_IOV=y
# CONFIG_PCIEASPM is not set
+CONFIG_PCI_IOV=y
CONFIG_HOTPLUG_PCI=y
CONFIG_HOTPLUG_PCI_S390=y
CONFIG_UEVENT_HELPER=y
CONFIG_MD_FAULTY=m
CONFIG_MD_CLUSTER=m
CONFIG_BCACHE=m
-CONFIG_BLK_DEV_DM=m
+CONFIG_BLK_DEV_DM=y
CONFIG_DM_UNSTRIPED=m
CONFIG_DM_CRYPT=m
CONFIG_DM_SNAPSHOT=m
CONFIG_DM_MULTIPATH_HST=m
CONFIG_DM_MULTIPATH_IOA=m
CONFIG_DM_DELAY=m
+CONFIG_DM_INIT=y
CONFIG_DM_UEVENT=y
CONFIG_DM_FLAKEY=m
CONFIG_DM_VERITY=m
# CONFIG_NET_VENDOR_GOOGLE is not set
# CONFIG_NET_VENDOR_HUAWEI is not set
# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MICROSOFT is not set
# CONFIG_NET_VENDOR_MARVELL is not set
CONFIG_MLX4_EN=m
CONFIG_MLX5_CORE=m
CONFIG_LEGACY_PTY_COUNT=0
CONFIG_VIRTIO_CONSOLE=m
CONFIG_HW_RANDOM_VIRTIO=m
-CONFIG_RAW_DRIVER=m
CONFIG_HANGCHECK_TIMER=m
CONFIG_TN3270_FS=y
# CONFIG_PTP_1588_CLOCK is not set
CONFIG_VFIO=m
CONFIG_VFIO_PCI=m
CONFIG_VFIO_MDEV=m
-CONFIG_VFIO_MDEV_DEVICE=m
CONFIG_VIRTIO_PCI=m
CONFIG_VIRTIO_BALLOON=m
CONFIG_VIRTIO_INPUT=y
CONFIG_CUSE=m
CONFIG_VIRTIO_FS=m
CONFIG_OVERLAY_FS=m
+CONFIG_NETFS_STATS=y
CONFIG_FSCACHE=m
CONFIG_CACHEFILES=m
CONFIG_ISO9660_FS=y
CONFIG_NFSD_V4=y
CONFIG_NFSD_V4_SECURITY_LABEL=y
CONFIG_CIFS=m
-CONFIG_CIFS_STATS2=y
CONFIG_CIFS_WEAK_PW_HASH=y
CONFIG_CIFS_UPCALL=y
CONFIG_CIFS_XATTR=y
CONFIG_SECURITY_SELINUX_DISABLE=y
CONFIG_SECURITY_LOCKDOWN_LSM=y
CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y
+CONFIG_SECURITY_LANDLOCK=y
CONFIG_INTEGRITY_SIGNATURE=y
CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
CONFIG_IMA=y
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_DH=m
CONFIG_CRYPTO_ECDH=m
+CONFIG_CRYPTO_ECDSA=m
CONFIG_CRYPTO_ECRDSA=m
CONFIG_CRYPTO_SM2=m
CONFIG_CRYPTO_CURVE25519=m
CONFIG_DMA_CMA=y
CONFIG_CMA_SIZE_MBYTES=0
CONFIG_PRINTK_TIME=y
+CONFIG_DYNAMIC_DEBUG=y
CONFIG_DEBUG_INFO=y
CONFIG_DEBUG_INFO_DWARF4=y
CONFIG_GDB_SCRIPTS=y
CONFIG_PERCPU_TEST=m
CONFIG_ATOMIC64_SELFTEST=y
CONFIG_TEST_BPF=m
+CONFIG_TEST_LIVEPATCH=m
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
# CONFIG_COMPACTION is not set
# CONFIG_MIGRATION is not set
-# CONFIG_BOUNCE is not set
CONFIG_NET=y
# CONFIG_IUCV is not set
+# CONFIG_PCPU_DEV_REFCNT is not set
# CONFIG_ETHTOOL_NETLINK is not set
CONFIG_DEVTMPFS=y
CONFIG_BLK_DEV_RAM=y
# CONFIG_SERIO is not set
# CONFIG_HVC_IUCV is not set
# CONFIG_HW_RANDOM_S390 is not set
-CONFIG_RAW_DRIVER=y
# CONFIG_HMC_DRV is not set
# CONFIG_S390_TAPE is not set
# CONFIG_VMCP is not set
extern char ftrace_graph_caller_end;
extern unsigned long ftrace_plt;
+extern void *ftrace_func;
struct dyn_arch_ftrace { };
u64 instruction_sigp_init_cpu_reset;
u64 instruction_sigp_cpu_reset;
u64 instruction_sigp_unknown;
- u64 diagnose_10;
- u64 diagnose_44;
- u64 diagnose_9c;
- u64 diagnose_9c_ignored;
- u64 diagnose_9c_forward;
- u64 diagnose_258;
- u64 diagnose_308;
- u64 diagnose_500;
- u64 diagnose_other;
+ u64 instruction_diagnose_10;
+ u64 instruction_diagnose_44;
+ u64 instruction_diagnose_9c;
+ u64 diag_9c_ignored;
+ u64 diag_9c_forward;
+ u64 instruction_diagnose_258;
+ u64 instruction_diagnose_308;
+ u64 instruction_diagnose_500;
+ u64 instruction_diagnose_other;
u64 pfault_sync;
};
* trampoline (ftrace_plt), which clobbers also r1.
*/
+void *ftrace_func __read_mostly = ftrace_stub;
unsigned long ftrace_plt;
int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
int ftrace_update_ftrace_func(ftrace_func_t func)
{
+ ftrace_func = func;
return 0;
}
#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
aghik %r2,%r0,-MCOUNT_INSN_SIZE
lgrl %r4,function_trace_op
- lgrl %r1,ftrace_trace_function
+ lgrl %r1,ftrace_func
#else
lgr %r2,%r0
aghi %r2,-MCOUNT_INSN_SIZE
larl %r4,function_trace_op
lg %r4,0(%r4)
- larl %r1,ftrace_trace_function
+ larl %r1,ftrace_func
lg %r1,0(%r1)
#endif
lgr %r3,%r14
if (!cf_dbg) {
pr_err("Registration of s390dbf(cpum_cf) failed\n");
return -ENOMEM;
- };
+ }
debug_register_view(cf_dbg, &debug_sprintf_view);
cpumf_pmu.attr_groups = cpumf_cf_event_group();
case DIE_SSTEP:
if (uprobe_post_sstep_notifier(regs))
return NOTIFY_STOP;
+ break;
default:
break;
}
$(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_32)
obj-y += vdso32_wrapper.o
+targets += vdso32.lds
CPPFLAGS_vdso32.lds += -P -C -U$(ARCH)
# Disable gcov profiling, ubsan and kasan for VDSO code
.rela.dyn ALIGN(8) : { *(.rela.dyn) }
.got ALIGN(8) : { *(.got .toc) }
+ .got.plt ALIGN(8) : { *(.got.plt) }
_end = .;
PROVIDE(end = .);
.rela.dyn ALIGN(8) : { *(.rela.dyn) }
.got ALIGN(8) : { *(.got .toc) }
+ .got.plt ALIGN(8) : { *(.got.plt) }
_end = .;
PROVIDE(end = .);
start = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
end = vcpu->run->s.regs.gprs[vcpu->arch.sie_block->ipa & 0xf] + PAGE_SIZE;
- vcpu->stat.diagnose_10++;
+ vcpu->stat.instruction_diagnose_10++;
if (start & ~PAGE_MASK || end & ~PAGE_MASK || start >= end
|| start < 2 * PAGE_SIZE)
VCPU_EVENT(vcpu, 3, "diag page reference parameter block at 0x%llx",
vcpu->run->s.regs.gprs[rx]);
- vcpu->stat.diagnose_258++;
+ vcpu->stat.instruction_diagnose_258++;
if (vcpu->run->s.regs.gprs[rx] & 7)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
rc = read_guest(vcpu, vcpu->run->s.regs.gprs[rx], rx, &parm, sizeof(parm));
static int __diag_time_slice_end(struct kvm_vcpu *vcpu)
{
VCPU_EVENT(vcpu, 5, "%s", "diag time slice end");
- vcpu->stat.diagnose_44++;
+ vcpu->stat.instruction_diagnose_44++;
kvm_vcpu_on_spin(vcpu, true);
return 0;
}
int tid;
tid = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
- vcpu->stat.diagnose_9c++;
+ vcpu->stat.instruction_diagnose_9c++;
/* yield to self */
if (tid == vcpu->vcpu_id)
VCPU_EVENT(vcpu, 5,
"diag time slice end directed to %d: yield forwarded",
tid);
- vcpu->stat.diagnose_9c_forward++;
+ vcpu->stat.diag_9c_forward++;
return 0;
}
return 0;
no_yield:
VCPU_EVENT(vcpu, 5, "diag time slice end directed to %d: ignored", tid);
- vcpu->stat.diagnose_9c_ignored++;
+ vcpu->stat.diag_9c_ignored++;
return 0;
}
unsigned long subcode = vcpu->run->s.regs.gprs[reg] & 0xffff;
VCPU_EVENT(vcpu, 3, "diag ipl functions, subcode %lx", subcode);
- vcpu->stat.diagnose_308++;
+ vcpu->stat.instruction_diagnose_308++;
switch (subcode) {
case 3:
vcpu->run->s390_reset_flags = KVM_S390_RESET_CLEAR;
{
int ret;
- vcpu->stat.diagnose_500++;
+ vcpu->stat.instruction_diagnose_500++;
/* No virtio-ccw notification? Get out quickly. */
if (!vcpu->kvm->arch.css_support ||
(vcpu->run->s.regs.gprs[1] != KVM_S390_VIRTIO_CCW_NOTIFY))
case 0x500:
return __diag_virtio_hypercall(vcpu);
default:
- vcpu->stat.diagnose_other++;
+ vcpu->stat.instruction_diagnose_other++;
return -EOPNOTSUPP;
}
}
STATS_DESC_COUNTER(VCPU, instruction_sigp_init_cpu_reset),
STATS_DESC_COUNTER(VCPU, instruction_sigp_cpu_reset),
STATS_DESC_COUNTER(VCPU, instruction_sigp_unknown),
- STATS_DESC_COUNTER(VCPU, diagnose_10),
- STATS_DESC_COUNTER(VCPU, diagnose_44),
- STATS_DESC_COUNTER(VCPU, diagnose_9c),
- STATS_DESC_COUNTER(VCPU, diagnose_9c_ignored),
- STATS_DESC_COUNTER(VCPU, diagnose_9c_forward),
- STATS_DESC_COUNTER(VCPU, diagnose_258),
- STATS_DESC_COUNTER(VCPU, diagnose_308),
- STATS_DESC_COUNTER(VCPU, diagnose_500),
- STATS_DESC_COUNTER(VCPU, diagnose_other),
+ STATS_DESC_COUNTER(VCPU, instruction_diagnose_10),
+ STATS_DESC_COUNTER(VCPU, instruction_diagnose_44),
+ STATS_DESC_COUNTER(VCPU, instruction_diagnose_9c),
+ STATS_DESC_COUNTER(VCPU, diag_9c_ignored),
+ STATS_DESC_COUNTER(VCPU, diag_9c_forward),
+ STATS_DESC_COUNTER(VCPU, instruction_diagnose_258),
+ STATS_DESC_COUNTER(VCPU, instruction_diagnose_308),
+ STATS_DESC_COUNTER(VCPU, instruction_diagnose_500),
+ STATS_DESC_COUNTER(VCPU, instruction_diagnose_other),
STATS_DESC_COUNTER(VCPU, pfault_sync)
};
static_assert(ARRAY_SIZE(kvm_vcpu_stats_desc) ==
{
u32 r1 = reg2hex[b1];
- if (!jit->seen_reg[r1] && r1 >= 6 && r1 <= 15)
+ if (r1 >= 6 && r1 <= 15 && !jit->seen_reg[r1])
jit->seen_reg[r1] = 1;
}
}
break;
/*
+ * BPF_NOSPEC (speculation barrier)
+ */
+ case BPF_ST | BPF_NOSPEC:
+ break;
+ /*
* BPF_ST(X)
*/
case BPF_STX | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = src_reg */
select HAVE_FUTEX_CMPXCHG if FUTEX
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_HW_BREAKPOINT
- select HAVE_IDE if HAS_IOPORT_MAP
select HAVE_IOREMAP_PROT if MMU && !X2TLB
select HAVE_KERNEL_BZIP2
select HAVE_KERNEL_GZIP
select OF
select OF_PROMTREE
select HAVE_ASM_MODVERSIONS
- select HAVE_IDE
select HAVE_ARCH_KGDB if !SMP || SPARC64
select HAVE_ARCH_TRACEHOOK
select HAVE_ARCH_SECCOMP if SPARC64
return 1;
break;
}
+ /* speculation barrier */
+ case BPF_ST | BPF_NOSPEC:
+ break;
/* ST: *(size *)(dst + off) = imm */
case BPF_ST | BPF_MEM | BPF_W:
case BPF_ST | BPF_MEM | BPF_H:
select HAVE_FUNCTION_TRACER
select HAVE_GCC_PLUGINS
select HAVE_HW_BREAKPOINT
- select HAVE_IDE
select HAVE_IOREMAP_PROT
select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64
select HAVE_IRQ_TIME_ACCOUNTING
return;
for_each_set_bit(i, cpuc->dirty, X86_PMC_IDX_MAX) {
- /* Metrics and fake events don't have corresponding HW counters. */
- if (is_metric_idx(i) || (i == INTEL_PMC_IDX_FIXED_VLBR))
- continue;
- else if (i >= INTEL_PMC_IDX_FIXED)
+ if (i >= INTEL_PMC_IDX_FIXED) {
+ /* Metrics and fake events don't have corresponding HW counters. */
+ if ((i - INTEL_PMC_IDX_FIXED) >= hybrid(cpuc->pmu, num_counters_fixed))
+ continue;
+
wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + (i - INTEL_PMC_IDX_FIXED), 0);
- else
+ } else {
wrmsrl(x86_pmu_event_addr(i), 0);
+ }
}
bitmap_zero(cpuc->dirty, X86_PMC_IDX_MAX);
*/
static int intel_pmu_handle_irq(struct pt_regs *regs)
{
- struct cpu_hw_events *cpuc;
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ bool late_ack = hybrid_bit(cpuc->pmu, late_ack);
+ bool mid_ack = hybrid_bit(cpuc->pmu, mid_ack);
int loops;
u64 status;
int handled;
int pmu_enabled;
- cpuc = this_cpu_ptr(&cpu_hw_events);
-
/*
* Save the PMU state.
* It needs to be restored when leaving the handler.
*/
pmu_enabled = cpuc->enabled;
/*
- * No known reason to not always do late ACK,
- * but just in case do it opt-in.
+ * In general, the early ACK is only applied for old platforms.
+ * For the big core starts from Haswell, the late ACK should be
+ * applied.
+ * For the small core after Tremont, we have to do the ACK right
+ * before re-enabling counters, which is in the middle of the
+ * NMI handler.
*/
- if (!x86_pmu.late_ack)
+ if (!late_ack && !mid_ack)
apic_write(APIC_LVTPC, APIC_DM_NMI);
intel_bts_disable_local();
cpuc->enabled = 0;
goto again;
done:
+ if (mid_ack)
+ apic_write(APIC_LVTPC, APIC_DM_NMI);
/* Only restore PMU state when it's active. See x86_pmu_disable(). */
cpuc->enabled = pmu_enabled;
if (pmu_enabled)
* have been reset. This avoids spurious NMIs on
* Haswell CPUs.
*/
- if (x86_pmu.late_ack)
+ if (late_ack)
apic_write(APIC_LVTPC, APIC_DM_NMI);
return handled;
}
static_branch_enable(&perf_is_hybrid);
x86_pmu.num_hybrid_pmus = X86_HYBRID_NUM_PMUS;
- x86_pmu.late_ack = true;
x86_pmu.pebs_aliases = NULL;
x86_pmu.pebs_prec_dist = true;
x86_pmu.pebs_block = true;
pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX];
pmu->name = "cpu_core";
pmu->cpu_type = hybrid_big;
+ pmu->late_ack = true;
if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) {
pmu->num_counters = x86_pmu.num_counters + 2;
pmu->num_counters_fixed = x86_pmu.num_counters_fixed + 1;
pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX];
pmu->name = "cpu_atom";
pmu->cpu_type = hybrid_small;
+ pmu->mid_ack = true;
pmu->num_counters = x86_pmu.num_counters;
pmu->num_counters_fixed = x86_pmu.num_counters_fixed;
pmu->max_pebs_events = x86_pmu.max_pebs_events;
struct event_constraint *event_constraints;
struct event_constraint *pebs_constraints;
struct extra_reg *extra_regs;
+
+ unsigned int late_ack :1,
+ mid_ack :1,
+ enabled_ack :1;
};
static __always_inline struct x86_hybrid_pmu *hybrid_pmu(struct pmu *pmu)
__Fp; \
}))
+#define hybrid_bit(_pmu, _field) \
+({ \
+ bool __Fp = x86_pmu._field; \
+ \
+ if (is_hybrid() && (_pmu)) \
+ __Fp = hybrid_pmu(_pmu)->_field; \
+ \
+ __Fp; \
+})
+
enum hybrid_pmu_type {
hybrid_big = 0x40,
hybrid_small = 0x20,
/* PMI handler bits */
unsigned int late_ack :1,
+ mid_ack :1,
enabled_ack :1;
/*
* sysfs attrs
static inline void x86_pmu_disable_event(struct perf_event *event)
{
+ u64 disable_mask = __this_cpu_read(cpu_hw_events.perf_ctr_virt_mask);
struct hw_perf_event *hwc = &event->hw;
- wrmsrl(hwc->config_base, hwc->config);
+ wrmsrl(hwc->config_base, hwc->config & ~disable_mask);
if (is_counter_pair(hwc))
wrmsrl(x86_pmu_config_addr(hwc->idx + 1), 0);
for_each_present_cpu(i) {
if (i == 0)
continue;
- ret = hv_call_add_logical_proc(numa_cpu_node(i), i, i);
+ ret = hv_call_add_logical_proc(numa_cpu_node(i), i, cpu_physical_id(i));
BUG_ON(ret);
}
return (struct jump_label_patch){.code = code, .size = size};
}
-static inline void __jump_label_transform(struct jump_entry *entry,
- enum jump_label_type type,
- int init)
+static __always_inline void
+__jump_label_transform(struct jump_entry *entry,
+ enum jump_label_type type,
+ int init)
{
const struct jump_label_patch jlp = __jump_label_patch(entry, type);
edx.split.num_counters_fixed = min(cap.num_counters_fixed, MAX_FIXED_COUNTERS);
edx.split.bit_width_fixed = cap.bit_width_fixed;
- edx.split.anythread_deprecated = 1;
+ if (cap.version)
+ edx.split.anythread_deprecated = 1;
edx.split.reserved1 = 0;
edx.split.reserved2 = 0;
unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U);
unsigned phys_as = entry->eax & 0xff;
- if (!g_phys_as)
+ /*
+ * If TDP (NPT) is disabled use the adjusted host MAXPHYADDR as
+ * the guest operates in the same PA space as the host, i.e.
+ * reductions in MAXPHYADDR for memory encryption affect shadow
+ * paging, too.
+ *
+ * If TDP is enabled but an explicit guest MAXPHYADDR is not
+ * provided, use the raw bare metal MAXPHYADDR as reductions to
+ * the HPAs do not affect GPAs.
+ */
+ if (!tdp_enabled)
+ g_phys_as = boot_cpu_data.x86_phys_bits;
+ else if (!g_phys_as)
g_phys_as = phys_as;
+
entry->eax = g_phys_as | (virt_as << 8);
entry->edx = 0;
cpuid_entry_override(entry, CPUID_8000_0008_EBX);
case 0x8000001a:
case 0x8000001e:
break;
- /* Support memory encryption cpuid if host supports it */
case 0x8000001F:
- if (!kvm_cpu_cap_has(X86_FEATURE_SEV))
+ if (!kvm_cpu_cap_has(X86_FEATURE_SEV)) {
entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
- else
+ } else {
cpuid_entry_override(entry, CPUID_8000_001F_EAX);
+
+ /*
+ * Enumerate '0' for "PA bits reduction", the adjusted
+ * MAXPHYADDR is enumerated directly (see 0x80000008).
+ */
+ entry->ebx &= ~GENMASK(11, 6);
+ }
break;
/*Add support for Centaur's CPUID instruction*/
case 0xC0000000:
static int kvm_hv_hypercall_complete(struct kvm_vcpu *vcpu, u64 result)
{
+ trace_kvm_hv_hypercall_done(result);
kvm_hv_hypercall_set_result(vcpu, result);
++vcpu->stat.hypercalls;
return kvm_skip_emulated_instruction(vcpu);
int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
{
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
struct kvm_hv_hcall hc;
u64 ret = HV_STATUS_SUCCESS;
hc.rep_idx = (hc.param >> HV_HYPERCALL_REP_START_OFFSET) & 0xfff;
hc.rep = !!(hc.rep_cnt || hc.rep_idx);
- if (hc.fast && is_xmm_fast_hypercall(&hc))
- kvm_hv_hypercall_read_xmm(&hc);
-
trace_kvm_hv_hypercall(hc.code, hc.fast, hc.rep_cnt, hc.rep_idx,
hc.ingpa, hc.outgpa);
- if (unlikely(!hv_check_hypercall_access(to_hv_vcpu(vcpu), hc.code))) {
+ if (unlikely(!hv_check_hypercall_access(hv_vcpu, hc.code))) {
ret = HV_STATUS_ACCESS_DENIED;
goto hypercall_complete;
}
+ if (hc.fast && is_xmm_fast_hypercall(&hc)) {
+ if (unlikely(hv_vcpu->enforce_cpuid &&
+ !(hv_vcpu->cpuid_cache.features_edx &
+ HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE))) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+ }
+
+ kvm_hv_hypercall_read_xmm(&hc);
+ }
+
switch (hc.code) {
case HVCALL_NOTIFY_LONG_SPIN_WAIT:
if (unlikely(hc.rep)) {
static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic)
{
ioapic->rtc_status.pending_eoi = 0;
- bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID);
+ bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID + 1);
}
static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic);
struct dest_map {
/* vcpu bitmap where IRQ has been sent */
- DECLARE_BITMAP(map, KVM_MAX_VCPU_ID);
+ DECLARE_BITMAP(map, KVM_MAX_VCPU_ID + 1);
/*
* Vector sent to a given vcpu, only valid when
* the vcpu's bit in map is set
*/
- u8 vectors[KVM_MAX_VCPU_ID];
+ u8 vectors[KVM_MAX_VCPU_ID + 1];
};
#include <asm/kvm_page_track.h>
#include "trace.h"
+#include "paging.h"
+
extern bool itlb_multihit_kvm_mitigation;
int __read_mostly nx_huge_pages = -1;
* aggregate version in order to make the slab shrinker
* faster
*/
-static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, unsigned long nr)
+static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, long nr)
{
kvm->arch.n_used_mmu_pages += nr;
percpu_counter_add(&kvm_total_used_mmu_pages, nr);
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Shadow paging constants/helpers that don't need to be #undef'd. */
+#ifndef __KVM_X86_PAGING_H
+#define __KVM_X86_PAGING_H
+
+#define GUEST_PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
+#define PT64_LVL_ADDR_MASK(level) \
+ (GUEST_PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \
+ * PT64_LEVEL_BITS))) - 1))
+#define PT64_LVL_OFFSET_MASK(level) \
+ (GUEST_PT64_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \
+ * PT64_LEVEL_BITS))) - 1))
+#endif /* __KVM_X86_PAGING_H */
+
#define pt_element_t u64
#define guest_walker guest_walker64
#define FNAME(name) paging##64_##name
- #define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK
+ #define PT_BASE_ADDR_MASK GUEST_PT64_BASE_ADDR_MASK
#define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl)
#define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl)
#define PT_INDEX(addr, level) PT64_INDEX(addr, level)
#define pt_element_t u64
#define guest_walker guest_walkerEPT
#define FNAME(name) ept_##name
- #define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK
+ #define PT_BASE_ADDR_MASK GUEST_PT64_BASE_ADDR_MASK
#define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl)
#define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl)
#define PT_INDEX(addr, level) PT64_INDEX(addr, level)
#else
#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
#endif
-#define PT64_LVL_ADDR_MASK(level) \
- (PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \
- * PT64_LEVEL_BITS))) - 1))
-#define PT64_LVL_OFFSET_MASK(level) \
- (PT64_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \
- * PT64_LEVEL_BITS))) - 1))
#define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \
| shadow_x_mask | shadow_nx_mask | shadow_me_mask)
void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
- struct vmcb *vmcb = svm->vmcb;
+ struct vmcb *vmcb = svm->vmcb01.ptr;
bool activated = kvm_vcpu_apicv_active(vcpu);
if (!enable_apicv)
for (i = 0; i < MAX_INTERCEPT; i++)
c->intercepts[i] |= g->intercepts[i];
+
+ /* If SMI is not intercepted, ignore guest SMI intercept as well */
+ if (!intercept_smi)
+ vmcb_clr_intercept(c, INTERCEPT_SMI);
}
static void copy_vmcb_control_area(struct vmcb_control_area *dst,
return true;
}
-static void nested_load_control_from_vmcb12(struct vcpu_svm *svm,
- struct vmcb_control_area *control)
+void nested_load_control_from_vmcb12(struct vcpu_svm *svm,
+ struct vmcb_control_area *control)
{
copy_vmcb_control_area(&svm->nested.ctl, control);
* Also covers avic_vapic_bar, avic_backing_page, avic_logical_id,
* avic_physical_id.
*/
- WARN_ON(svm->vmcb01.ptr->control.int_ctl & AVIC_ENABLE_MASK);
+ WARN_ON(kvm_apicv_activated(svm->vcpu.kvm));
/* Copied from vmcb01. msrpm_base can be overwritten later. */
svm->vmcb->control.nested_ctl = svm->vmcb01.ptr->control.nested_ctl;
struct kvm_host_map map;
u64 vmcb12_gpa;
+ if (!svm->nested.hsave_msr) {
+ kvm_inject_gp(vcpu, 0);
+ return 1;
+ }
+
if (is_smm(vcpu)) {
kvm_queue_exception(vcpu, UD_VECTOR);
return 1;
return ret;
}
-void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb)
+/* Copy state save area fields which are handled by VMRUN */
+void svm_copy_vmrun_state(struct vmcb_save_area *to_save,
+ struct vmcb_save_area *from_save)
+{
+ to_save->es = from_save->es;
+ to_save->cs = from_save->cs;
+ to_save->ss = from_save->ss;
+ to_save->ds = from_save->ds;
+ to_save->gdtr = from_save->gdtr;
+ to_save->idtr = from_save->idtr;
+ to_save->rflags = from_save->rflags | X86_EFLAGS_FIXED;
+ to_save->efer = from_save->efer;
+ to_save->cr0 = from_save->cr0;
+ to_save->cr3 = from_save->cr3;
+ to_save->cr4 = from_save->cr4;
+ to_save->rax = from_save->rax;
+ to_save->rsp = from_save->rsp;
+ to_save->rip = from_save->rip;
+ to_save->cpl = 0;
+}
+
+void svm_copy_vmloadsave_state(struct vmcb *to_vmcb, struct vmcb *from_vmcb)
{
to_vmcb->save.fs = from_vmcb->save.fs;
to_vmcb->save.gs = from_vmcb->save.gs;
svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa;
- svm->vmcb01.ptr->save.es = save->es;
- svm->vmcb01.ptr->save.cs = save->cs;
- svm->vmcb01.ptr->save.ss = save->ss;
- svm->vmcb01.ptr->save.ds = save->ds;
- svm->vmcb01.ptr->save.gdtr = save->gdtr;
- svm->vmcb01.ptr->save.idtr = save->idtr;
- svm->vmcb01.ptr->save.rflags = save->rflags | X86_EFLAGS_FIXED;
- svm->vmcb01.ptr->save.efer = save->efer;
- svm->vmcb01.ptr->save.cr0 = save->cr0;
- svm->vmcb01.ptr->save.cr3 = save->cr3;
- svm->vmcb01.ptr->save.cr4 = save->cr4;
- svm->vmcb01.ptr->save.rax = save->rax;
- svm->vmcb01.ptr->save.rsp = save->rsp;
- svm->vmcb01.ptr->save.rip = save->rip;
- svm->vmcb01.ptr->save.cpl = 0;
-
+ svm_copy_vmrun_state(&svm->vmcb01.ptr->save, save);
nested_load_control_from_vmcb12(svm, ctl);
svm_switch_vmcb(svm, &svm->nested.vmcb02);
-
nested_vmcb02_prepare_control(svm);
-
kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
ret = 0;
out_free:
unsigned int max_sev_asid;
static unsigned int min_sev_asid;
static unsigned long sev_me_mask;
+static unsigned int nr_asids;
static unsigned long *sev_asid_bitmap;
static unsigned long *sev_reclaim_asid_bitmap;
/* Called with the sev_bitmap_lock held, or on shutdown */
static int sev_flush_asids(int min_asid, int max_asid)
{
- int ret, pos, error = 0;
+ int ret, asid, error = 0;
/* Check if there are any ASIDs to reclaim before performing a flush */
- pos = find_next_bit(sev_reclaim_asid_bitmap, max_asid, min_asid);
- if (pos >= max_asid)
+ asid = find_next_bit(sev_reclaim_asid_bitmap, nr_asids, min_asid);
+ if (asid > max_asid)
return -EBUSY;
/*
/* The flush process will flush all reclaimable SEV and SEV-ES ASIDs */
bitmap_xor(sev_asid_bitmap, sev_asid_bitmap, sev_reclaim_asid_bitmap,
- max_sev_asid);
- bitmap_zero(sev_reclaim_asid_bitmap, max_sev_asid);
+ nr_asids);
+ bitmap_zero(sev_reclaim_asid_bitmap, nr_asids);
return true;
}
static int sev_asid_new(struct kvm_sev_info *sev)
{
- int pos, min_asid, max_asid, ret;
+ int asid, min_asid, max_asid, ret;
bool retry = true;
enum misc_res_type type;
* SEV-enabled guests must use asid from min_sev_asid to max_sev_asid.
* SEV-ES-enabled guest can use from 1 to min_sev_asid - 1.
*/
- min_asid = sev->es_active ? 0 : min_sev_asid - 1;
+ min_asid = sev->es_active ? 1 : min_sev_asid;
max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid;
again:
- pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_asid);
- if (pos >= max_asid) {
+ asid = find_next_zero_bit(sev_asid_bitmap, max_asid + 1, min_asid);
+ if (asid > max_asid) {
if (retry && __sev_recycle_asids(min_asid, max_asid)) {
retry = false;
goto again;
goto e_uncharge;
}
- __set_bit(pos, sev_asid_bitmap);
+ __set_bit(asid, sev_asid_bitmap);
mutex_unlock(&sev_bitmap_lock);
- return pos + 1;
+ return asid;
e_uncharge:
misc_cg_uncharge(type, sev->misc_cg, 1);
put_misc_cg(sev->misc_cg);
static void sev_asid_free(struct kvm_sev_info *sev)
{
struct svm_cpu_data *sd;
- int cpu, pos;
+ int cpu;
enum misc_res_type type;
mutex_lock(&sev_bitmap_lock);
- pos = sev->asid - 1;
- __set_bit(pos, sev_reclaim_asid_bitmap);
+ __set_bit(sev->asid, sev_reclaim_asid_bitmap);
for_each_possible_cpu(cpu) {
sd = per_cpu(svm_data, cpu);
- sd->sev_vmcbs[pos] = NULL;
+ sd->sev_vmcbs[sev->asid] = NULL;
}
mutex_unlock(&sev_bitmap_lock);
/* Pin guest memory */
guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK,
PAGE_SIZE, &n, 0);
- if (!guest_page)
- return -EFAULT;
+ if (IS_ERR(guest_page))
+ return PTR_ERR(guest_page);
/* allocate memory for header and transport buffer */
ret = -ENOMEM;
}
/* Copy packet header to userspace. */
- ret = copy_to_user((void __user *)(uintptr_t)params.hdr_uaddr, hdr,
- params.hdr_len);
+ if (copy_to_user((void __user *)(uintptr_t)params.hdr_uaddr, hdr,
+ params.hdr_len))
+ ret = -EFAULT;
e_free_trans_data:
kfree(trans_data);
data.trans_len = params.trans_len;
/* Pin guest memory */
- ret = -EFAULT;
guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK,
PAGE_SIZE, &n, 0);
- if (!guest_page)
+ if (IS_ERR(guest_page)) {
+ ret = PTR_ERR(guest_page);
goto e_free_trans;
+ }
/* The RECEIVE_UPDATE_DATA command requires C-bit to be always set. */
data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset;
min_sev_asid = edx;
sev_me_mask = 1UL << (ebx & 0x3f);
- /* Initialize SEV ASID bitmaps */
- sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
+ /*
+ * Initialize SEV ASID bitmaps. Allocate space for ASID 0 in the bitmap,
+ * even though it's never used, so that the bitmap is indexed by the
+ * actual ASID.
+ */
+ nr_asids = max_sev_asid + 1;
+ sev_asid_bitmap = bitmap_zalloc(nr_asids, GFP_KERNEL);
if (!sev_asid_bitmap)
goto out;
- sev_reclaim_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
+ sev_reclaim_asid_bitmap = bitmap_zalloc(nr_asids, GFP_KERNEL);
if (!sev_reclaim_asid_bitmap) {
bitmap_free(sev_asid_bitmap);
sev_asid_bitmap = NULL;
return;
/* No need to take sev_bitmap_lock, all VMs have been destroyed. */
- sev_flush_asids(0, max_sev_asid);
+ sev_flush_asids(1, max_sev_asid);
bitmap_free(sev_asid_bitmap);
bitmap_free(sev_reclaim_asid_bitmap);
if (!sev_enabled)
return 0;
- sd->sev_vmcbs = kcalloc(max_sev_asid + 1, sizeof(void *), GFP_KERNEL);
+ sd->sev_vmcbs = kcalloc(nr_asids, sizeof(void *), GFP_KERNEL);
if (!sd->sev_vmcbs)
return -ENOMEM;
bool __read_mostly dump_invalid_vmcb;
module_param(dump_invalid_vmcb, bool, 0644);
+
+bool intercept_smi = true;
+module_param(intercept_smi, bool, 0444);
+
+
static bool svm_gp_erratum_intercept = true;
static u8 rsm_ins_bytes[] = "\x0f\xaa";
svm_set_intercept(svm, INTERCEPT_INTR);
svm_set_intercept(svm, INTERCEPT_NMI);
- svm_set_intercept(svm, INTERCEPT_SMI);
+
+ if (intercept_smi)
+ svm_set_intercept(svm, INTERCEPT_SMI);
+
svm_set_intercept(svm, INTERCEPT_SELECTIVE_CR0);
svm_set_intercept(svm, INTERCEPT_RDPMC);
svm_set_intercept(svm, INTERCEPT_CPUID);
goto error_free_vmsa_page;
}
- svm_vcpu_init_msrpm(vcpu, svm->msrpm);
-
svm->vmcb01.ptr = page_address(vmcb01_page);
svm->vmcb01.pa = __sme_set(page_to_pfn(vmcb01_page) << PAGE_SHIFT);
svm_switch_vmcb(svm, &svm->vmcb01);
init_vmcb(vcpu);
+ svm_vcpu_init_msrpm(vcpu, svm->msrpm);
+
svm_init_osvw(vcpu);
vcpu->arch.microcode_version = 0x01000065;
{
struct vmcb_control_area *control;
- /* The following fields are ignored when AVIC is enabled */
- WARN_ON(kvm_vcpu_apicv_active(&svm->vcpu));
+ /*
+ * The following fields are ignored when AVIC is enabled
+ */
+ WARN_ON(kvm_apicv_activated(svm->vcpu.kvm));
+
svm_set_intercept(svm, INTERCEPT_VINTR);
/*
{
struct vcpu_svm *svm = to_svm(vcpu);
- u64 fault_address = __sme_clr(svm->vmcb->control.exit_info_2);
+ u64 fault_address = svm->vmcb->control.exit_info_2;
u64 error_code = svm->vmcb->control.exit_info_1;
trace_kvm_page_fault(fault_address, error_code);
return 1;
}
+static int smi_interception(struct kvm_vcpu *vcpu)
+{
+ return 1;
+}
+
static int intr_interception(struct kvm_vcpu *vcpu)
{
++vcpu->stat.irq_exits;
ret = kvm_skip_emulated_instruction(vcpu);
if (vmload) {
- nested_svm_vmloadsave(vmcb12, svm->vmcb);
+ svm_copy_vmloadsave_state(svm->vmcb, vmcb12);
svm->sysenter_eip_hi = 0;
svm->sysenter_esp_hi = 0;
- } else
- nested_svm_vmloadsave(svm->vmcb, vmcb12);
+ } else {
+ svm_copy_vmloadsave_state(vmcb12, svm->vmcb);
+ }
kvm_vcpu_unmap(vcpu, &map, true);
svm_disable_lbrv(vcpu);
break;
case MSR_VM_HSAVE_PA:
- svm->nested.hsave_msr = data;
+ /*
+ * Old kernels did not validate the value written to
+ * MSR_VM_HSAVE_PA. Allow KVM_SET_MSR to set an invalid
+ * value to allow live migrating buggy or malicious guests
+ * originating from those kernels.
+ */
+ if (!msr->host_initiated && !page_address_valid(vcpu, data))
+ return 1;
+
+ svm->nested.hsave_msr = data & PAGE_MASK;
break;
case MSR_VM_CR:
return svm_set_vm_cr(vcpu, data);
[SVM_EXIT_EXCP_BASE + GP_VECTOR] = gp_interception,
[SVM_EXIT_INTR] = intr_interception,
[SVM_EXIT_NMI] = nmi_interception,
- [SVM_EXIT_SMI] = kvm_emulate_as_nop,
- [SVM_EXIT_INIT] = kvm_emulate_as_nop,
+ [SVM_EXIT_SMI] = smi_interception,
[SVM_EXIT_VINTR] = interrupt_window_interception,
[SVM_EXIT_RDPMC] = kvm_emulate_rdpmc,
[SVM_EXIT_CPUID] = kvm_emulate_cpuid,
static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
{
struct vcpu_svm *svm = to_svm(vcpu);
+ struct kvm_host_map map_save;
int ret;
if (is_guest_mode(vcpu)) {
ret = nested_svm_vmexit(svm);
if (ret)
return ret;
+
+ /*
+ * KVM uses VMCB01 to store L1 host state while L2 runs but
+ * VMCB01 is going to be used during SMM and thus the state will
+ * be lost. Temporary save non-VMLOAD/VMSAVE state to the host save
+ * area pointed to by MSR_VM_HSAVE_PA. APM guarantees that the
+ * format of the area is identical to guest save area offsetted
+ * by 0x400 (matches the offset of 'struct vmcb_save_area'
+ * within 'struct vmcb'). Note: HSAVE area may also be used by
+ * L1 hypervisor to save additional host context (e.g. KVM does
+ * that, see svm_prepare_guest_switch()) which must be
+ * preserved.
+ */
+ if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr),
+ &map_save) == -EINVAL)
+ return 1;
+
+ BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400);
+
+ svm_copy_vmrun_state(map_save.hva + 0x400,
+ &svm->vmcb01.ptr->save);
+
+ kvm_vcpu_unmap(vcpu, &map_save, true);
}
return 0;
}
static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
{
struct vcpu_svm *svm = to_svm(vcpu);
- struct kvm_host_map map;
+ struct kvm_host_map map, map_save;
int ret = 0;
if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) {
u64 saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0);
u64 guest = GET_SMSTATE(u64, smstate, 0x7ed8);
u64 vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0);
+ struct vmcb *vmcb12;
if (guest) {
if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
if (svm_allocate_nested(svm))
return 1;
- ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, map.hva);
+ vmcb12 = map.hva;
+
+ nested_load_control_from_vmcb12(svm, &vmcb12->control);
+
+ ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12);
kvm_vcpu_unmap(vcpu, &map, true);
+
+ /*
+ * Restore L1 host state from L1 HSAVE area as VMCB01 was
+ * used during SMM (see svm_enter_smm())
+ */
+ if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr),
+ &map_save) == -EINVAL)
+ return 1;
+
+ svm_copy_vmrun_state(&svm->vmcb01.ptr->save,
+ map_save.hva + 0x400);
+
+ kvm_vcpu_unmap(vcpu, &map_save, true);
}
}
#define MSRPM_OFFSETS 16
extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
extern bool npt_enabled;
+extern bool intercept_smi;
/*
* Clean bits in VMCB.
void svm_free_nested(struct vcpu_svm *svm);
int svm_allocate_nested(struct vcpu_svm *svm);
int nested_svm_vmrun(struct kvm_vcpu *vcpu);
-void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb);
+void svm_copy_vmrun_state(struct vmcb_save_area *to_save,
+ struct vmcb_save_area *from_save);
+void svm_copy_vmloadsave_state(struct vmcb *to_vmcb, struct vmcb *from_vmcb);
int nested_svm_vmexit(struct vcpu_svm *svm);
static inline int nested_svm_simple_vmexit(struct vcpu_svm *svm, u32 exit_code)
int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
bool has_error_code, u32 error_code);
int nested_svm_exit_special(struct vcpu_svm *svm);
+void nested_load_control_from_vmcb12(struct vcpu_svm *svm,
+ struct vmcb_control_area *control);
void nested_sync_control_from_vmcb02(struct vcpu_svm *svm);
void nested_vmcb02_compute_g_pat(struct vcpu_svm *svm);
void svm_switch_vmcb(struct vcpu_svm *svm, struct kvm_vmcb_info *target_vmcb);
* as we mark it dirty unconditionally towards end of vcpu
* init phase.
*/
- if (vmcb && vmcb_is_clean(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS) &&
+ if (vmcb_is_clean(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS) &&
hve->hv_enlightenments_control.msr_bitmap)
vmcb_mark_dirty(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS);
}
__entry->outgpa)
);
+TRACE_EVENT(kvm_hv_hypercall_done,
+ TP_PROTO(u64 result),
+ TP_ARGS(result),
+
+ TP_STRUCT__entry(
+ __field(__u64, result)
+ ),
+
+ TP_fast_assign(
+ __entry->result = result;
+ ),
+
+ TP_printk("result 0x%llx", __entry->result)
+);
+
/*
* Tracepoint for Xen hypercall.
*/
#include "vmx_ops.h"
#include "cpuid.h"
-extern const u32 vmx_msr_index[];
-
#define MSR_TYPE_R 1
#define MSR_TYPE_W 2
#define MSR_TYPE_RW 3
return 1;
break;
case MSR_KVM_ASYNC_PF_ACK:
- if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF))
+ if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT))
return 1;
if (data & 0x1) {
vcpu->arch.apf.pageready_pending = false;
msr_info->data = vcpu->arch.apf.msr_int_val;
break;
case MSR_KVM_ASYNC_PF_ACK:
- if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF))
+ if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT))
return 1;
msr_info->data = 0;
static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu)
{
- return kvm_arch_interrupt_allowed(vcpu) &&
- kvm_cpu_accept_dm_intr(vcpu);
+ /*
+ * Do not cause an interrupt window exit if an exception
+ * is pending or an event needs reinjection; userspace
+ * might want to inject the interrupt manually using KVM_SET_REGS
+ * or KVM_SET_SREGS. For that to work, we must be at an
+ * instruction boundary and with no events half-injected.
+ */
+ return (kvm_arch_interrupt_allowed(vcpu) &&
+ kvm_cpu_accept_dm_intr(vcpu) &&
+ !kvm_event_needs_reinjection(vcpu) &&
+ !vcpu->arch.exception.pending);
}
static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
set_debugreg(vcpu->arch.eff_db[3], 3);
set_debugreg(vcpu->arch.dr6, 6);
vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD;
+ } else if (unlikely(hw_breakpoint_active())) {
+ set_debugreg(0, 7);
}
for (;;) {
int r;
rdmsrl_safe(MSR_EFER, &host_efer);
- if (WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_NX) &&
- !(host_efer & EFER_NX)))
- return -EIO;
if (boot_cpu_has(X86_FEATURE_XSAVES))
rdmsrl(MSR_IA32_XSS, host_xss);
}
#endif
-#if CONFIG_PGTABLE_LEVELS > 3
/**
* pud_set_huge - setup kernel PUD mapping
*
}
/**
- * pud_clear_huge - clear kernel PUD mapping when it is set
- *
- * Returns 1 on success and 0 on failure (no PUD map is found).
- */
-int pud_clear_huge(pud_t *pud)
-{
- if (pud_large(*pud)) {
- pud_clear(pud);
- return 1;
- }
-
- return 0;
-}
-#endif
-
-#if CONFIG_PGTABLE_LEVELS > 2
-/**
* pmd_set_huge - setup kernel PMD mapping
*
* See text over pud_set_huge() above.
}
/**
+ * pud_clear_huge - clear kernel PUD mapping when it is set
+ *
+ * Returns 1 on success and 0 on failure (no PUD map is found).
+ */
+int pud_clear_huge(pud_t *pud)
+{
+ if (pud_large(*pud)) {
+ pud_clear(pud);
+ return 1;
+ }
+
+ return 0;
+}
+
+/**
* pmd_clear_huge - clear kernel PMD mapping when it is set
*
* Returns 1 on success and 0 on failure (no PMD map is found).
return 0;
}
-#endif
#ifdef CONFIG_X86_64
/**
for (i = 0; i < prog->aux->size_poke_tab; i++) {
poke = &prog->aux->poke_tab[i];
+ if (poke->aux && poke->aux != prog->aux)
+ continue;
+
WARN_ON_ONCE(READ_ONCE(poke->tailcall_target_stable));
if (poke->reason != BPF_POKE_REASON_TAIL_CALL)
}
break;
+ /* speculation barrier */
+ case BPF_ST | BPF_NOSPEC:
+ if (boot_cpu_has(X86_FEATURE_XMM2))
+ /* Emit 'lfence' */
+ EMIT3(0x0F, 0xAE, 0xE8);
+ break;
+
/* ST: *(u8*)(dst_reg + off) = imm */
case BPF_ST | BPF_MEM | BPF_B:
if (is_ereg(dst_reg))
i++;
break;
}
+ /* speculation barrier */
+ case BPF_ST | BPF_NOSPEC:
+ if (boot_cpu_has(X86_FEATURE_XMM2))
+ /* Emit 'lfence' */
+ EMIT3(0x0F, 0xAE, 0xE8);
+ break;
/* ST: *(u8*)(dst_reg + off) = imm */
case BPF_ST | BPF_MEM | BPF_H:
case BPF_ST | BPF_MEM | BPF_B:
[S_REL] =
"^(__init_(begin|end)|"
"__x86_cpu_dev_(start|end)|"
- "(__parainstructions|__alt_instructions)(|_end)|"
- "(__iommu_table|__apicdrivers|__smp_locks)(|_end)|"
+ "(__parainstructions|__alt_instructions)(_end)?|"
+ "(__iommu_table|__apicdrivers|__smp_locks)(_end)?|"
"__(start|end)_pci_.*|"
"__(start|end)_builtin_fw|"
- "__(start|stop)___ksymtab(|_gpl)|"
- "__(start|stop)___kcrctab(|_gpl)|"
+ "__(start|stop)___ksymtab(_gpl)?|"
+ "__(start|stop)___kcrctab(_gpl)?|"
"__(start|stop)___param|"
"__(start|stop)___modver|"
"__(start|stop)___bug_table|"
config XTENSA_PLATFORM_XT2000
bool "XT2000"
- select HAVE_IDE
help
XT2000 is the name of Tensilica's feature-rich emulation platform.
This hardware is capable of running a full Linux distribution.
return -1;
iocg_commit_bio(ctx->iocg, wait->bio, wait->abs_cost, cost);
+ wait->committed = true;
/*
* autoremove_wake_function() removes the wait entry only when it
- * actually changed the task state. We want the wait always
- * removed. Remove explicitly and use default_wake_function().
+ * actually changed the task state. We want the wait always removed.
+ * Remove explicitly and use default_wake_function(). Note that the
+ * order of operations is important as finish_wait() tests whether
+ * @wq_entry is removed without grabbing the lock.
*/
- list_del_init(&wq_entry->entry);
- wait->committed = true;
-
default_wake_function(wq_entry, mode, flags, key);
+ list_del_init_careful(&wq_entry->entry);
return 0;
}
enable = iolatency_set_min_lat_nsec(blkg, lat_val);
if (enable) {
- WARN_ON_ONCE(!blk_get_queue(blkg->q));
+ if (!blk_get_queue(blkg->q)) {
+ ret = -ENODEV;
+ goto out;
+ }
+
blkg_get(blkg);
}
percpu_ref_put(&q->q_usage_counter);
}
-static void blk_mq_sched_free_tags(struct blk_mq_tag_set *set,
- struct blk_mq_hw_ctx *hctx,
- unsigned int hctx_idx)
-{
- if (hctx->sched_tags) {
- blk_mq_free_rqs(set, hctx->sched_tags, hctx_idx);
- blk_mq_free_rq_map(hctx->sched_tags, set->flags);
- hctx->sched_tags = NULL;
- }
-}
-
static int blk_mq_sched_alloc_tags(struct request_queue *q,
struct blk_mq_hw_ctx *hctx,
unsigned int hctx_idx)
return -ENOMEM;
ret = blk_mq_alloc_rqs(set, hctx->sched_tags, hctx_idx, q->nr_requests);
- if (ret)
- blk_mq_sched_free_tags(set, hctx, hctx_idx);
+ if (ret) {
+ blk_mq_free_rq_map(hctx->sched_tags, set->flags);
+ hctx->sched_tags = NULL;
+ }
return ret;
}
disk_release_events(disk);
kfree(disk->random);
xa_destroy(&disk->part_tbl);
- bdput(disk->part0);
if (test_bit(GD_QUEUE_REF, &disk->state) && disk->queue)
blk_put_queue(disk->queue);
- kfree(disk);
+ bdput(disk->part0); /* frees the disk */
}
struct class block_class = {
.name = "block",
struct list_head *head = &kcq->rq_list[sched_domain];
spin_lock(&kcq->lock);
+ trace_block_rq_insert(rq);
if (at_head)
list_move(&rq->queuelist, head);
else
list_move_tail(&rq->queuelist, head);
sbitmap_set_bit(&khd->kcq_map[sched_domain],
rq->mq_ctx->index_hw[hctx->type]);
- trace_block_rq_insert(rq);
spin_unlock(&kcq->lock);
}
}
// SPDX-License-Identifier: GPL-2.0-or-later
-/**
+/*
* ldm - Support for Windows Logical Disk Manager (Dynamic Disks)
*
* Copyright (C) 2001,2002 Richard Russon <ldm@flatcap.org>
config ACPI_TABLE_OVERRIDE_VIA_BUILTIN_INITRD
bool "Override ACPI tables from built-in initrd"
depends on ACPI_TABLE_UPGRADE
- depends on INITRAMFS_SOURCE!="" && INITRAMFS_COMPRESSION=""
+ depends on INITRAMFS_SOURCE!="" && INITRAMFS_COMPRESSION_NONE
help
This option provides functionality to override arbitrary ACPI tables
from built-in uncompressed initrd.
(*element_ptr)->common.reference_count =
original_ref_count;
-
- /*
- * The original_element holds a reference from the package object
- * that represents _HID. Since a new element was created by _HID,
- * remove the reference from the _CID package.
- */
- acpi_ut_remove_reference(original_element);
}
element_ptr++;
#include <linux/module.h>
#include <linux/platform_device.h>
+struct pch_fivr_resp {
+ u64 status;
+ u64 result;
+};
+
+static int pch_fivr_read(acpi_handle handle, char *method, struct pch_fivr_resp *fivr_resp)
+{
+ struct acpi_buffer resp = { sizeof(struct pch_fivr_resp), fivr_resp};
+ struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+ struct acpi_buffer format = { sizeof("NN"), "NN" };
+ union acpi_object *obj;
+ acpi_status status;
+ int ret = -EFAULT;
+
+ status = acpi_evaluate_object(handle, method, NULL, &buffer);
+ if (ACPI_FAILURE(status))
+ return ret;
+
+ obj = buffer.pointer;
+ if (!obj || obj->type != ACPI_TYPE_PACKAGE)
+ goto release_buffer;
+
+ status = acpi_extract_package(obj, &format, &resp);
+ if (ACPI_FAILURE(status))
+ goto release_buffer;
+
+ if (fivr_resp->status)
+ goto release_buffer;
+
+ ret = 0;
+
+release_buffer:
+ kfree(buffer.pointer);
+ return ret;
+}
+
/*
* Presentation of attributes which are defined for INT1045
* They are:
char *buf)\
{\
struct acpi_device *acpi_dev = dev_get_drvdata(dev);\
- unsigned long long val;\
- acpi_status status;\
+ struct pch_fivr_resp fivr_resp;\
+ int status;\
\
- status = acpi_evaluate_integer(acpi_dev->handle, #method,\
- NULL, &val);\
- if (ACPI_SUCCESS(status))\
- return sprintf(buf, "%d\n", (int)val);\
- else\
- return -EINVAL;\
+ status = pch_fivr_read(acpi_dev->handle, #method, &fivr_resp);\
+ if (status)\
+ return status;\
+\
+ return sprintf(buf, "%llu\n", fivr_resp.result);\
}
#define PCH_FIVR_STORE(name, method) \
}
}
-static bool irq_is_legacy(struct acpi_resource_irq *irq)
-{
- return irq->triggering == ACPI_EDGE_SENSITIVE &&
- irq->polarity == ACPI_ACTIVE_HIGH &&
- irq->shareable == ACPI_EXCLUSIVE;
-}
-
/**
* acpi_dev_resource_interrupt - Extract ACPI interrupt resource information.
* @ares: Input ACPI resource object.
}
acpi_dev_get_irqresource(res, irq->interrupts[index],
irq->triggering, irq->polarity,
- irq->shareable, irq_is_legacy(irq));
+ irq->shareable, true);
break;
case ACPI_RESOURCE_TYPE_EXTENDED_IRQ:
ext_irq = &ares->data.extended_irq;
* Return the next match of ACPI device if another matching device was present
* at the moment of invocation, or NULL otherwise.
*
- * FIXME: The function does not tolerate the sudden disappearance of @adev, e.g.
- * in the case of a hotplug event. That said, the caller should ensure that
- * this will never happen.
- *
* The caller is responsible for invoking acpi_dev_put() on the returned device.
+ * On the other hand the function invokes acpi_dev_put() on the given @adev
+ * assuming that its reference counter had been increased beforehand.
*
* See additional information in acpi_dev_present() as well.
*/
match.hrv = hrv;
dev = bus_find_device(&acpi_bus_type, start, &match, acpi_dev_match_cb);
+ acpi_dev_put(adev);
return dev ? to_acpi_device(dev) : NULL;
}
EXPORT_SYMBOL(acpi_dev_get_next_match_dev);
* AMDI0006:
* - should use rev_id 0x0
* - function mask = 0x3: Should use Microsoft method
+ * AMDI0007:
+ * - Should use rev_id 0x2
+ * - Should only use AMD method
*/
const char *hid = acpi_device_hid(adev);
- rev_id = 0;
+ rev_id = strcmp(hid, "AMDI0007") ? 0 : 2;
lps0_dsm_func_mask = validate_dsm(adev->handle,
ACPI_LPS0_DSM_UUID_AMD, rev_id, &lps0_dsm_guid);
lps0_dsm_func_mask_microsoft = validate_dsm(adev->handle,
- ACPI_LPS0_DSM_UUID_MICROSOFT, rev_id,
+ ACPI_LPS0_DSM_UUID_MICROSOFT, 0,
&lps0_dsm_guid_microsoft);
if (lps0_dsm_func_mask > 0x3 && (!strcmp(hid, "AMD0004") ||
!strcmp(hid, "AMDI0005"))) {
lps0_dsm_func_mask = (lps0_dsm_func_mask << 1) | 0x1;
acpi_handle_debug(adev->handle, "_DSM UUID %s: Adjusted function mask: 0x%x\n",
ACPI_LPS0_DSM_UUID_AMD, lps0_dsm_func_mask);
+ } else if (lps0_dsm_func_mask_microsoft > 0 && !strcmp(hid, "AMDI0007")) {
+ lps0_dsm_func_mask_microsoft = -EINVAL;
+ acpi_handle_debug(adev->handle, "_DSM Using AMD method\n");
}
} else {
rev_id = 1;
}
EXPORT_SYMBOL_GPL(ata_sff_data_xfer32);
+static void ata_pio_xfer(struct ata_queued_cmd *qc, struct page *page,
+ unsigned int offset, size_t xfer_size)
+{
+ bool do_write = (qc->tf.flags & ATA_TFLAG_WRITE);
+ unsigned char *buf;
+
+ buf = kmap_atomic(page);
+ qc->ap->ops->sff_data_xfer(qc, buf + offset, xfer_size, do_write);
+ kunmap_atomic(buf);
+
+ if (!do_write && !PageSlab(page))
+ flush_dcache_page(page);
+}
+
/**
* ata_pio_sector - Transfer a sector of data.
* @qc: Command on going
*/
static void ata_pio_sector(struct ata_queued_cmd *qc)
{
- int do_write = (qc->tf.flags & ATA_TFLAG_WRITE);
struct ata_port *ap = qc->ap;
struct page *page;
unsigned int offset;
- unsigned char *buf;
if (!qc->cursg) {
qc->curbytes = qc->nbytes;
DPRINTK("data %s\n", qc->tf.flags & ATA_TFLAG_WRITE ? "write" : "read");
- /* do the actual data transfer */
- buf = kmap_atomic(page);
- ap->ops->sff_data_xfer(qc, buf + offset, qc->sect_size, do_write);
- kunmap_atomic(buf);
+ /*
+ * Split the transfer when it splits a page boundary. Note that the
+ * split still has to be dword aligned like all ATA data transfers.
+ */
+ WARN_ON_ONCE(offset % 4);
+ if (offset + qc->sect_size > PAGE_SIZE) {
+ unsigned int split_len = PAGE_SIZE - offset;
- if (!do_write && !PageSlab(page))
- flush_dcache_page(page);
+ ata_pio_xfer(qc, page, offset, split_len);
+ ata_pio_xfer(qc, nth_page(page, 1), 0,
+ qc->sect_size - split_len);
+ } else {
+ ata_pio_xfer(qc, page, offset, qc->sect_size);
+ }
qc->curbytes += qc->sect_size;
qc->cursg_ofs += qc->sect_size;
int __auxiliary_driver_register(struct auxiliary_driver *auxdrv,
struct module *owner, const char *modname)
{
+ int ret;
+
if (WARN_ON(!auxdrv->probe) || WARN_ON(!auxdrv->id_table))
return -EINVAL;
auxdrv->driver.bus = &auxiliary_bus_type;
auxdrv->driver.mod_name = modname;
- return driver_register(&auxdrv->driver);
+ ret = driver_register(&auxdrv->driver);
+ if (ret)
+ kfree(auxdrv->driver.name);
+
+ return ret;
}
EXPORT_SYMBOL_GPL(__auxiliary_driver_register);
return;
}
- snprintf(buf, len, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup));
- sysfs_remove_link(&con->kobj, buf);
+ if (device_is_registered(con)) {
+ snprintf(buf, len, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup));
+ sysfs_remove_link(&con->kobj, buf);
+ }
snprintf(buf, len, "consumer:%s:%s", dev_bus_name(con), dev_name(con));
sysfs_remove_link(&sup->kobj, buf);
kfree(buf);
else if (drv->remove)
drv->remove(dev);
probe_failed:
- kfree(dev->dma_range_map);
- dev->dma_range_map = NULL;
if (dev->bus)
blocking_notifier_call_chain(&dev->bus->p->bus_notifier,
BUS_NOTIFY_DRIVER_NOT_BOUND, dev);
device_links_no_driver(dev);
devres_release_all(dev);
arch_teardown_dma_ops(dev);
+ kfree(dev->dma_range_map);
+ dev->dma_range_map = NULL;
driver_sysfs_remove(dev);
dev->driver = NULL;
dev_set_drvdata(dev, NULL);
{
/*
* There is a small window in which user can write to 'loading'
- * between loading done and disappearance of 'loading'
+ * between loading done/aborted and disappearance of 'loading'
*/
- if (fw_sysfs_done(fw_priv))
+ if (fw_state_is_aborted(fw_priv) || fw_sysfs_done(fw_priv))
return;
- list_del_init(&fw_priv->pending_list);
fw_state_aborted(fw_priv);
}
* Same logic as fw_load_abort, only the DONE bit
* is ignored and we set ABORT only on failure.
*/
- list_del_init(&fw_priv->pending_list);
if (rc) {
fw_state_aborted(fw_priv);
written = rc;
}
mutex_lock(&fw_lock);
+ if (fw_state_is_aborted(fw_priv)) {
+ mutex_unlock(&fw_lock);
+ retval = -EINTR;
+ goto out;
+ }
list_add(&fw_priv->pending_list, &pending_fw_head);
mutex_unlock(&fw_lock);
if (fw_state_is_aborted(fw_priv)) {
if (retval == -ERESTARTSYS)
retval = -EINTR;
- else
- retval = -EAGAIN;
} else if (fw_priv->is_paged_buf && !fw_priv->data)
retval = -ENOMEM;
+out:
device_del(f_dev);
err_put_dev:
put_device(f_dev);
WRITE_ONCE(fw_st->status, status);
- if (status == FW_STATUS_DONE || status == FW_STATUS_ABORTED)
+ if (status == FW_STATUS_DONE || status == FW_STATUS_ABORTED) {
+#ifdef CONFIG_FW_LOADER_USER_HELPER
+ /*
+ * Doing this here ensures that the fw_priv is deleted from
+ * the pending list in all abort/done paths.
+ */
+ list_del_init(&fw_priv->pending_list);
+#endif
complete_all(&fw_st->completion);
+ }
}
static inline void fw_state_aborted(struct fw_priv *fw_priv)
return;
fw_priv = fw->priv;
+ mutex_lock(&fw_lock);
if (!fw_state_is_aborted(fw_priv))
fw_state_aborted(fw_priv);
+ mutex_unlock(&fw_lock);
}
/* called from request_firmware() and request_firmware_work_func() */
static DEFINE_IDR(loop_index_idr);
static DEFINE_MUTEX(loop_ctl_mutex);
+static DEFINE_MUTEX(loop_validate_mutex);
+
+/**
+ * loop_global_lock_killable() - take locks for safe loop_validate_file() test
+ *
+ * @lo: struct loop_device
+ * @global: true if @lo is about to bind another "struct loop_device", false otherwise
+ *
+ * Returns 0 on success, -EINTR otherwise.
+ *
+ * Since loop_validate_file() traverses on other "struct loop_device" if
+ * is_loop_device() is true, we need a global lock for serializing concurrent
+ * loop_configure()/loop_change_fd()/__loop_clr_fd() calls.
+ */
+static int loop_global_lock_killable(struct loop_device *lo, bool global)
+{
+ int err;
+
+ if (global) {
+ err = mutex_lock_killable(&loop_validate_mutex);
+ if (err)
+ return err;
+ }
+ err = mutex_lock_killable(&lo->lo_mutex);
+ if (err && global)
+ mutex_unlock(&loop_validate_mutex);
+ return err;
+}
+
+/**
+ * loop_global_unlock() - release locks taken by loop_global_lock_killable()
+ *
+ * @lo: struct loop_device
+ * @global: true if @lo was about to bind another "struct loop_device", false otherwise
+ */
+static void loop_global_unlock(struct loop_device *lo, bool global)
+{
+ mutex_unlock(&lo->lo_mutex);
+ if (global)
+ mutex_unlock(&loop_validate_mutex);
+}
static int max_part;
static int part_shift;
while (is_loop_device(f)) {
struct loop_device *l;
+ lockdep_assert_held(&loop_validate_mutex);
if (f->f_mapping->host->i_rdev == bdev->bd_dev)
return -EBADF;
l = I_BDEV(f->f_mapping->host)->bd_disk->private_data;
- if (l->lo_state != Lo_bound) {
+ if (l->lo_state != Lo_bound)
return -EINVAL;
- }
+ /* Order wrt setting lo->lo_backing_file in loop_configure(). */
+ rmb();
f = l->lo_backing_file;
}
if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
unsigned int arg)
{
- struct file *file = NULL, *old_file;
- int error;
- bool partscan;
+ struct file *file = fget(arg);
+ struct file *old_file;
+ int error;
+ bool partscan;
+ bool is_loop;
- error = mutex_lock_killable(&lo->lo_mutex);
+ if (!file)
+ return -EBADF;
+ is_loop = is_loop_device(file);
+ error = loop_global_lock_killable(lo, is_loop);
if (error)
- return error;
+ goto out_putf;
error = -ENXIO;
if (lo->lo_state != Lo_bound)
goto out_err;
if (!(lo->lo_flags & LO_FLAGS_READ_ONLY))
goto out_err;
- error = -EBADF;
- file = fget(arg);
- if (!file)
- goto out_err;
-
error = loop_validate_file(file, bdev);
if (error)
goto out_err;
loop_update_dio(lo);
blk_mq_unfreeze_queue(lo->lo_queue);
partscan = lo->lo_flags & LO_FLAGS_PARTSCAN;
- mutex_unlock(&lo->lo_mutex);
+ loop_global_unlock(lo, is_loop);
+
+ /*
+ * Flush loop_validate_file() before fput(), for l->lo_backing_file
+ * might be pointing at old_file which might be the last reference.
+ */
+ if (!is_loop) {
+ mutex_lock(&loop_validate_mutex);
+ mutex_unlock(&loop_validate_mutex);
+ }
/*
* We must drop file reference outside of lo_mutex as dropping
* the file ref can take open_mutex which creates circular locking
return 0;
out_err:
- mutex_unlock(&lo->lo_mutex);
- if (file)
- fput(file);
+ loop_global_unlock(lo, is_loop);
+out_putf:
+ fput(file);
return error;
}
struct block_device *bdev,
const struct loop_config *config)
{
- struct file *file;
- struct inode *inode;
+ struct file *file = fget(config->fd);
+ struct inode *inode;
struct address_space *mapping;
- int error;
- loff_t size;
- bool partscan;
- unsigned short bsize;
+ int error;
+ loff_t size;
+ bool partscan;
+ unsigned short bsize;
+ bool is_loop;
+
+ if (!file)
+ return -EBADF;
+ is_loop = is_loop_device(file);
/* This is safe, since we have a reference from open(). */
__module_get(THIS_MODULE);
- error = -EBADF;
- file = fget(config->fd);
- if (!file)
- goto out;
-
/*
* If we don't hold exclusive handle for the device, upgrade to it
* here to avoid changing device under exclusive owner.
goto out_putf;
}
- error = mutex_lock_killable(&lo->lo_mutex);
+ error = loop_global_lock_killable(lo, is_loop);
if (error)
goto out_bdev;
size = get_loop_size(lo, file);
loop_set_size(lo, size);
+ /* Order wrt reading lo_state in loop_validate_file(). */
+ wmb();
+
lo->lo_state = Lo_bound;
if (part_shift)
lo->lo_flags |= LO_FLAGS_PARTSCAN;
* put /dev/loopXX inode. Later in __loop_clr_fd() we bdput(bdev).
*/
bdgrab(bdev);
- mutex_unlock(&lo->lo_mutex);
+ loop_global_unlock(lo, is_loop);
if (partscan)
loop_reread_partitions(lo);
if (!(mode & FMODE_EXCL))
return 0;
out_unlock:
- mutex_unlock(&lo->lo_mutex);
+ loop_global_unlock(lo, is_loop);
out_bdev:
if (!(mode & FMODE_EXCL))
bd_abort_claiming(bdev, loop_configure);
out_putf:
fput(file);
-out:
/* This is safe: open() is still holding a reference. */
module_put(THIS_MODULE);
return error;
int lo_number;
struct loop_worker *pos, *worker;
+ /*
+ * Flush loop_configure() and loop_change_fd(). It is acceptable for
+ * loop_validate_file() to succeed, for actual clear operation has not
+ * started yet.
+ */
+ mutex_lock(&loop_validate_mutex);
+ mutex_unlock(&loop_validate_mutex);
+ /*
+ * loop_validate_file() now fails because l->lo_state != Lo_bound
+ * became visible.
+ */
+
mutex_lock(&lo->lo_mutex);
if (WARN_ON_ONCE(lo->lo_state != Lo_rundown)) {
err = -ENXIO;
n64cart_wait_dma();
- n64cart_write_reg(PI_DRAM_REG, dma_addr + bv->bv_offset);
+ n64cart_write_reg(PI_DRAM_REG, dma_addr);
n64cart_write_reg(PI_CART_REG, (bstart | CART_DOMAIN) & CART_MAX);
n64cart_write_reg(PI_WRITE_REG, bv->bv_len - 1);
if (disk) {
del_gendisk(disk);
- blk_mq_free_tag_set(&nbd->tag_set);
blk_cleanup_disk(disk);
+ blk_mq_free_tag_set(&nbd->tag_set);
}
/*
if (p) {
disk->gd = NULL;
del_gendisk(p);
- blk_mq_free_tag_set(&disk->tag_set);
blk_cleanup_disk(p);
+ blk_mq_free_tag_set(&disk->tag_set);
pi_release(disk->pi);
}
}
static bool rbd_quiesce_lock(struct rbd_device *rbd_dev)
{
- bool need_wait;
-
dout("%s rbd_dev %p\n", __func__, rbd_dev);
lockdep_assert_held_write(&rbd_dev->lock_rwsem);
*/
rbd_dev->lock_state = RBD_LOCK_STATE_RELEASING;
rbd_assert(!completion_done(&rbd_dev->releasing_wait));
- need_wait = !list_empty(&rbd_dev->running_list);
- downgrade_write(&rbd_dev->lock_rwsem);
- if (need_wait)
- wait_for_completion(&rbd_dev->releasing_wait);
- up_read(&rbd_dev->lock_rwsem);
+ if (list_empty(&rbd_dev->running_list))
+ return true;
+
+ up_write(&rbd_dev->lock_rwsem);
+ wait_for_completion(&rbd_dev->releasing_wait);
down_write(&rbd_dev->lock_rwsem);
if (rbd_dev->lock_state != RBD_LOCK_STATE_RELEASING)
if (!rbd_cid_equal(&cid, &rbd_empty_cid)) {
down_write(&rbd_dev->lock_rwsem);
if (rbd_cid_equal(&cid, &rbd_dev->owner_cid)) {
- /*
- * we already know that the remote client is
- * the owner
- */
- up_write(&rbd_dev->lock_rwsem);
- return;
+ dout("%s rbd_dev %p cid %llu-%llu == owner_cid\n",
+ __func__, rbd_dev, cid.gid, cid.handle);
+ } else {
+ rbd_set_owner_cid(rbd_dev, &cid);
}
-
- rbd_set_owner_cid(rbd_dev, &cid);
downgrade_write(&rbd_dev->lock_rwsem);
} else {
down_read(&rbd_dev->lock_rwsem);
if (!rbd_cid_equal(&cid, &rbd_empty_cid)) {
down_write(&rbd_dev->lock_rwsem);
if (!rbd_cid_equal(&cid, &rbd_dev->owner_cid)) {
- dout("%s rbd_dev %p unexpected owner, cid %llu-%llu != owner_cid %llu-%llu\n",
+ dout("%s rbd_dev %p cid %llu-%llu != owner_cid %llu-%llu\n",
__func__, rbd_dev, cid.gid, cid.handle,
rbd_dev->owner_cid.gid, rbd_dev->owner_cid.handle);
- up_write(&rbd_dev->lock_rwsem);
- return;
+ } else {
+ rbd_set_owner_cid(rbd_dev, &rbd_empty_cid);
}
-
- rbd_set_owner_cid(rbd_dev, &rbd_empty_cid);
downgrade_write(&rbd_dev->lock_rwsem);
} else {
down_read(&rbd_dev->lock_rwsem);
disk->minors = RBD_MINORS_PER_MAJOR;
}
disk->fops = &rbd_bd_ops;
+ disk->private_data = rbd_dev;
blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
/* QUEUE_FLAG_ADD_RANDOM is off by default for blk-mq */
static int blkif_ioctl(struct block_device *bdev, fmode_t mode,
unsigned command, unsigned long argument)
{
- struct blkfront_info *info = bdev->bd_disk->private_data;
int i;
- dev_dbg(&info->xbdev->dev, "command: 0x%x, argument: 0x%lx\n",
- command, (long)argument);
-
switch (command) {
case CDROMMULTISESSION:
- dev_dbg(&info->xbdev->dev, "FIXME: support multisession CDs later\n");
for (i = 0; i < sizeof(struct cdrom_multisession); i++)
if (put_user(0, (char __user *)(argument + i)))
return -EFAULT;
return 0;
-
- case CDROM_GET_CAPABILITY: {
- struct gendisk *gd = info->gd;
- if (gd->flags & GENHD_FL_CD)
+ case CDROM_GET_CAPABILITY:
+ if (bdev->bd_disk->flags & GENHD_FL_CD)
return 0;
return -EINVAL;
- }
-
default:
- /*printk(KERN_ALERT "ioctl %08x not supported by Xen blkdev\n",
- command);*/
- return -EINVAL; /* same return as native Linux */
+ return -EINVAL;
}
-
- return 0;
}
static unsigned long blkif_ring_get_request(struct blkfront_ring_info *rinfo,
return err;
}
-static void xlvbd_release_gendisk(struct blkfront_info *info)
-{
- unsigned int minor, nr_minors, i;
- struct blkfront_ring_info *rinfo;
-
- if (info->rq == NULL)
- return;
-
- /* No more blkif_request(). */
- blk_mq_stop_hw_queues(info->rq);
-
- for_each_rinfo(info, rinfo, i) {
- /* No more gnttab callback work. */
- gnttab_cancel_free_callback(&rinfo->callback);
-
- /* Flush gnttab callback work. Must be done with no locks held. */
- flush_work(&rinfo->work);
- }
-
- del_gendisk(info->gd);
-
- minor = info->gd->first_minor;
- nr_minors = info->gd->minors;
- xlbd_release_minors(minor, nr_minors);
-
- blk_cleanup_disk(info->gd);
- info->gd = NULL;
- blk_mq_free_tag_set(&info->tag_set);
-}
-
/* Already hold rinfo->ring_lock. */
static inline void kick_pending_request_queues_locked(struct blkfront_ring_info *rinfo)
{
return err;
}
-static void free_info(struct blkfront_info *info)
-{
- list_del(&info->info_list);
- kfree(info);
-}
-
/* Common code used when first setting up, and when resuming. */
static int talk_to_blkback(struct xenbus_device *dev,
struct blkfront_info *info)
xenbus_dev_fatal(dev, err, "%s", message);
destroy_blkring:
blkif_free(info, 0);
-
- mutex_lock(&blkfront_mutex);
- free_info(info);
- mutex_unlock(&blkfront_mutex);
-
- dev_set_drvdata(&dev->dev, NULL);
-
return err;
}
static void blkfront_closing(struct blkfront_info *info)
{
struct xenbus_device *xbdev = info->xbdev;
- struct block_device *bdev = NULL;
-
- mutex_lock(&info->mutex);
+ struct blkfront_ring_info *rinfo;
+ unsigned int i;
- if (xbdev->state == XenbusStateClosing) {
- mutex_unlock(&info->mutex);
+ if (xbdev->state == XenbusStateClosing)
return;
- }
- if (info->gd)
- bdev = bdgrab(info->gd->part0);
-
- mutex_unlock(&info->mutex);
-
- if (!bdev) {
- xenbus_frontend_closed(xbdev);
- return;
- }
+ /* No more blkif_request(). */
+ blk_mq_stop_hw_queues(info->rq);
+ blk_set_queue_dying(info->rq);
+ set_capacity(info->gd, 0);
- mutex_lock(&bdev->bd_disk->open_mutex);
+ for_each_rinfo(info, rinfo, i) {
+ /* No more gnttab callback work. */
+ gnttab_cancel_free_callback(&rinfo->callback);
- if (bdev->bd_openers) {
- xenbus_dev_error(xbdev, -EBUSY,
- "Device in use; refusing to close");
- xenbus_switch_state(xbdev, XenbusStateClosing);
- } else {
- xlvbd_release_gendisk(info);
- xenbus_frontend_closed(xbdev);
+ /* Flush gnttab callback work. Must be done with no locks held. */
+ flush_work(&rinfo->work);
}
- mutex_unlock(&bdev->bd_disk->open_mutex);
- bdput(bdev);
+ xenbus_frontend_closed(xbdev);
}
static void blkfront_setup_discard(struct blkfront_info *info)
break;
fallthrough;
case XenbusStateClosing:
- if (info)
- blkfront_closing(info);
+ blkfront_closing(info);
break;
}
}
static int blkfront_remove(struct xenbus_device *xbdev)
{
struct blkfront_info *info = dev_get_drvdata(&xbdev->dev);
- struct block_device *bdev = NULL;
- struct gendisk *disk;
dev_dbg(&xbdev->dev, "%s removed", xbdev->nodename);
- if (!info)
- return 0;
-
- blkif_free(info, 0);
-
- mutex_lock(&info->mutex);
-
- disk = info->gd;
- if (disk)
- bdev = bdgrab(disk->part0);
-
- info->xbdev = NULL;
- mutex_unlock(&info->mutex);
-
- if (!bdev) {
- mutex_lock(&blkfront_mutex);
- free_info(info);
- mutex_unlock(&blkfront_mutex);
- return 0;
- }
-
- /*
- * The xbdev was removed before we reached the Closed
- * state. See if it's safe to remove the disk. If the bdev
- * isn't closed yet, we let release take care of it.
- */
-
- mutex_lock(&disk->open_mutex);
- info = disk->private_data;
-
- dev_warn(disk_to_dev(disk),
- "%s was hot-unplugged, %d stale handles\n",
- xbdev->nodename, bdev->bd_openers);
+ del_gendisk(info->gd);
- if (info && !bdev->bd_openers) {
- xlvbd_release_gendisk(info);
- disk->private_data = NULL;
- mutex_lock(&blkfront_mutex);
- free_info(info);
- mutex_unlock(&blkfront_mutex);
- }
+ mutex_lock(&blkfront_mutex);
+ list_del(&info->info_list);
+ mutex_unlock(&blkfront_mutex);
- mutex_unlock(&disk->open_mutex);
- bdput(bdev);
+ blkif_free(info, 0);
+ xlbd_release_minors(info->gd->first_minor, info->gd->minors);
+ blk_cleanup_disk(info->gd);
+ blk_mq_free_tag_set(&info->tag_set);
+ kfree(info);
return 0;
}
return info->is_ready && info->xbdev;
}
-static int blkif_open(struct block_device *bdev, fmode_t mode)
-{
- struct gendisk *disk = bdev->bd_disk;
- struct blkfront_info *info;
- int err = 0;
-
- mutex_lock(&blkfront_mutex);
-
- info = disk->private_data;
- if (!info) {
- /* xbdev gone */
- err = -ERESTARTSYS;
- goto out;
- }
-
- mutex_lock(&info->mutex);
-
- if (!info->gd)
- /* xbdev is closed */
- err = -ERESTARTSYS;
-
- mutex_unlock(&info->mutex);
-
-out:
- mutex_unlock(&blkfront_mutex);
- return err;
-}
-
-static void blkif_release(struct gendisk *disk, fmode_t mode)
-{
- struct blkfront_info *info = disk->private_data;
- struct xenbus_device *xbdev;
-
- mutex_lock(&blkfront_mutex);
- if (disk->part0->bd_openers)
- goto out_mutex;
-
- /*
- * Check if we have been instructed to close. We will have
- * deferred this request, because the bdev was still open.
- */
-
- mutex_lock(&info->mutex);
- xbdev = info->xbdev;
-
- if (xbdev && xbdev->state == XenbusStateClosing) {
- /* pending switch to state closed */
- dev_info(disk_to_dev(disk), "releasing disk\n");
- xlvbd_release_gendisk(info);
- xenbus_frontend_closed(info->xbdev);
- }
-
- mutex_unlock(&info->mutex);
-
- if (!xbdev) {
- /* sudden device removal */
- dev_info(disk_to_dev(disk), "releasing disk\n");
- xlvbd_release_gendisk(info);
- disk->private_data = NULL;
- free_info(info);
- }
-
-out_mutex:
- mutex_unlock(&blkfront_mutex);
-}
-
static const struct block_device_operations xlvbd_block_fops =
{
.owner = THIS_MODULE,
- .open = blkif_open,
- .release = blkif_release,
.getgeo = blkif_getgeo,
.ioctl = blkif_ioctl,
.compat_ioctl = blkdev_compat_ptr_ioctl,
struct image_info *img_info);
void mhi_fw_load_handler(struct mhi_controller *mhi_cntrl);
int mhi_prepare_channel(struct mhi_controller *mhi_cntrl,
- struct mhi_chan *mhi_chan);
+ struct mhi_chan *mhi_chan, unsigned int flags);
int mhi_init_chan_ctxt(struct mhi_controller *mhi_cntrl,
struct mhi_chan *mhi_chan);
void mhi_deinit_chan_ctxt(struct mhi_controller *mhi_cntrl,
cmd_pkt = mhi_to_virtual(mhi_ring, ptr);
chan = MHI_TRE_GET_CMD_CHID(cmd_pkt);
- mhi_chan = &mhi_cntrl->mhi_chan[chan];
- write_lock_bh(&mhi_chan->lock);
- mhi_chan->ccs = MHI_TRE_GET_EV_CODE(tre);
- complete(&mhi_chan->completion);
- write_unlock_bh(&mhi_chan->lock);
+
+ if (chan < mhi_cntrl->max_chan &&
+ mhi_cntrl->mhi_chan[chan].configured) {
+ mhi_chan = &mhi_cntrl->mhi_chan[chan];
+ write_lock_bh(&mhi_chan->lock);
+ mhi_chan->ccs = MHI_TRE_GET_EV_CODE(tre);
+ complete(&mhi_chan->completion);
+ write_unlock_bh(&mhi_chan->lock);
+ } else {
+ dev_err(&mhi_cntrl->mhi_dev->dev,
+ "Completion packet for invalid channel ID: %d\n", chan);
+ }
mhi_del_ring_element(mhi_cntrl, mhi_ring);
}
}
int mhi_prepare_channel(struct mhi_controller *mhi_cntrl,
- struct mhi_chan *mhi_chan)
+ struct mhi_chan *mhi_chan, unsigned int flags)
{
int ret = 0;
struct device *dev = &mhi_chan->mhi_dev->dev;
if (ret)
goto error_pm_state;
+ if (mhi_chan->dir == DMA_FROM_DEVICE)
+ mhi_chan->pre_alloc = !!(flags & MHI_CH_INBOUND_ALLOC_BUFS);
+
/* Pre-allocate buffer for xfer ring */
if (mhi_chan->pre_alloc) {
int nr_el = get_nr_avail_ring_elements(mhi_cntrl,
}
/* Move channel to start state */
-int mhi_prepare_for_transfer(struct mhi_device *mhi_dev)
+int mhi_prepare_for_transfer(struct mhi_device *mhi_dev, unsigned int flags)
{
int ret, dir;
struct mhi_controller *mhi_cntrl = mhi_dev->mhi_cntrl;
if (!mhi_chan)
continue;
- ret = mhi_prepare_channel(mhi_cntrl, mhi_chan);
+ ret = mhi_prepare_channel(mhi_cntrl, mhi_chan, flags);
if (ret)
goto error_open_chan;
}
* @edl: emergency download mode firmware path (if any)
* @bar_num: PCI base address register to use for MHI MMIO register space
* @dma_data_width: DMA transfer word size (32 or 64 bits)
+ * @sideband_wake: Devices using dedicated sideband GPIO for wakeup instead
+ * of inband wake support (such as sdx24)
*/
struct mhi_pci_dev_info {
const struct mhi_controller_config *config;
const char *edl;
unsigned int bar_num;
unsigned int dma_data_width;
+ bool sideband_wake;
};
#define MHI_CHANNEL_CONFIG_UL(ch_num, ch_name, el_count, ev_ring) \
.doorbell_mode_switch = false, \
}
+#define MHI_CHANNEL_CONFIG_DL_AUTOQUEUE(ch_num, ch_name, el_count, ev_ring) \
+ { \
+ .num = ch_num, \
+ .name = ch_name, \
+ .num_elements = el_count, \
+ .event_ring = ev_ring, \
+ .dir = DMA_FROM_DEVICE, \
+ .ee_mask = BIT(MHI_EE_AMSS), \
+ .pollcfg = 0, \
+ .doorbell = MHI_DB_BRST_DISABLE, \
+ .lpm_notify = false, \
+ .offload_channel = false, \
+ .doorbell_mode_switch = false, \
+ .auto_queue = true, \
+ }
+
#define MHI_EVENT_CONFIG_CTRL(ev_ring, el_count) \
{ \
.num_elements = el_count, \
MHI_CHANNEL_CONFIG_UL(14, "QMI", 4, 0),
MHI_CHANNEL_CONFIG_DL(15, "QMI", 4, 0),
MHI_CHANNEL_CONFIG_UL(20, "IPCR", 8, 0),
- MHI_CHANNEL_CONFIG_DL(21, "IPCR", 8, 0),
+ MHI_CHANNEL_CONFIG_DL_AUTOQUEUE(21, "IPCR", 8, 0),
MHI_CHANNEL_CONFIG_UL_FP(34, "FIREHOSE", 32, 0),
MHI_CHANNEL_CONFIG_DL_FP(35, "FIREHOSE", 32, 0),
MHI_CHANNEL_CONFIG_HW_UL(100, "IP_HW0", 128, 2),
.edl = "qcom/sdx65m/edl.mbn",
.config = &modem_qcom_v1_mhiv_config,
.bar_num = MHI_PCI_DEFAULT_BAR_NUM,
- .dma_data_width = 32
+ .dma_data_width = 32,
+ .sideband_wake = false,
};
static const struct mhi_pci_dev_info mhi_qcom_sdx55_info = {
.edl = "qcom/sdx55m/edl.mbn",
.config = &modem_qcom_v1_mhiv_config,
.bar_num = MHI_PCI_DEFAULT_BAR_NUM,
- .dma_data_width = 32
+ .dma_data_width = 32,
+ .sideband_wake = false,
};
static const struct mhi_pci_dev_info mhi_qcom_sdx24_info = {
.edl = "qcom/prog_firehose_sdx24.mbn",
.config = &modem_qcom_v1_mhiv_config,
.bar_num = MHI_PCI_DEFAULT_BAR_NUM,
- .dma_data_width = 32
+ .dma_data_width = 32,
+ .sideband_wake = true,
};
static const struct mhi_channel_config mhi_quectel_em1xx_channels[] = {
.edl = "qcom/prog_firehose_sdx24.mbn",
.config = &modem_quectel_em1xx_config,
.bar_num = MHI_PCI_DEFAULT_BAR_NUM,
- .dma_data_width = 32
+ .dma_data_width = 32,
+ .sideband_wake = true,
};
static const struct mhi_channel_config mhi_foxconn_sdx55_channels[] = {
.edl = "qcom/sdx55m/edl.mbn",
.config = &modem_foxconn_sdx55_config,
.bar_num = MHI_PCI_DEFAULT_BAR_NUM,
- .dma_data_width = 32
+ .dma_data_width = 32,
+ .sideband_wake = false,
};
static const struct pci_device_id mhi_pci_id_table[] = {
mhi_cntrl->status_cb = mhi_pci_status_cb;
mhi_cntrl->runtime_get = mhi_pci_runtime_get;
mhi_cntrl->runtime_put = mhi_pci_runtime_put;
- mhi_cntrl->wake_get = mhi_pci_wake_get_nop;
- mhi_cntrl->wake_put = mhi_pci_wake_put_nop;
- mhi_cntrl->wake_toggle = mhi_pci_wake_toggle_nop;
+
+ if (info->sideband_wake) {
+ mhi_cntrl->wake_get = mhi_pci_wake_get_nop;
+ mhi_cntrl->wake_put = mhi_pci_wake_put_nop;
+ mhi_cntrl->wake_toggle = mhi_pci_wake_toggle_nop;
+ }
err = mhi_pci_claim(mhi_cntrl, info->bar_num, DMA_BIT_MASK(info->dma_data_width));
if (err)
* @cookie: data used by legacy platform callbacks
* @name: name if available
* @revision: interconnect target module revision
+ * @reserved: target module is reserved and already in use
* @enabled: sysc runtime enabled status
* @needs_resume: runtime resume needed on resume from suspend
* @child_needs_resume: runtime resume needed for child on resume from suspend
struct ti_sysc_cookie cookie;
const char *name;
u32 revision;
+ unsigned int reserved:1;
unsigned int enabled:1;
unsigned int needs_resume:1;
unsigned int child_needs_resume:1;
case SOC_3430 ... SOC_3630:
sysc_add_disabled(0x48304000); /* timer12 */
break;
+ case SOC_AM3:
+ sysc_add_disabled(0x48310000); /* rng */
default:
break;
}
return error;
error = sysc_check_active_timer(ddata);
- if (error)
- return error;
+ if (error == -EBUSY)
+ ddata->reserved = true;
error = sysc_get_clocks(ddata);
if (error)
sysc_show_registers(ddata);
ddata->dev->type = &sysc_device_type;
- error = of_platform_populate(ddata->dev->of_node, sysc_match_table,
- pdata ? pdata->auxdata : NULL,
- ddata->dev);
- if (error)
- goto err;
+
+ if (!ddata->reserved) {
+ error = of_platform_populate(ddata->dev->of_node,
+ sysc_match_table,
+ pdata ? pdata->auxdata : NULL,
+ ddata->dev);
+ if (error)
+ goto err;
+ }
INIT_DELAYED_WORK(&ddata->idle_work, ti_sysc_idle);
rc);
break;
}
+ break;
case OPAL_SUCCESS:
break;
default:
pvt_data->session = sess_arg.session;
/* Allocate dynamic shared memory with fTPM TA */
- pvt_data->shm = tee_shm_alloc(pvt_data->ctx,
- MAX_COMMAND_SIZE + MAX_RESPONSE_SIZE,
- TEE_SHM_MAPPED | TEE_SHM_DMA_BUF);
+ pvt_data->shm = tee_shm_alloc_kernel_buf(pvt_data->ctx,
+ MAX_COMMAND_SIZE +
+ MAX_RESPONSE_SIZE);
if (IS_ERR(pvt_data->shm)) {
- dev_err(dev, "%s: tee_shm_alloc failed\n", __func__);
+ dev_err(dev, "%s: tee_shm_alloc_kernel_buf failed\n", __func__);
rc = -ENOMEM;
goto out_shm_alloc;
}
}
EXPORT_SYMBOL_GPL(devm_clk_bulk_get_optional);
+static void devm_clk_bulk_release_all(struct device *dev, void *res)
+{
+ struct clk_bulk_devres *devres = res;
+
+ clk_bulk_put_all(devres->num_clks, devres->clks);
+}
+
int __must_check devm_clk_bulk_get_all(struct device *dev,
struct clk_bulk_data **clks)
{
struct clk_bulk_devres *devres;
int ret;
- devres = devres_alloc(devm_clk_bulk_release,
+ devres = devres_alloc(devm_clk_bulk_release_all,
sizeof(*devres), GFP_KERNEL);
if (!devres)
return -ENOMEM;
struct stm32f4_pll_post_div_data {
int idx;
- u8 pll_num;
+ int pll_idx;
const char *name;
const char *parent;
u8 flag;
#define MAX_POST_DIV 3
static const struct stm32f4_pll_post_div_data post_div_data[MAX_POST_DIV] = {
- { CLK_I2SQ_PDIV, PLL_I2S, "plli2s-q-div", "plli2s-q",
+ { CLK_I2SQ_PDIV, PLL_VCO_I2S, "plli2s-q-div", "plli2s-q",
CLK_SET_RATE_PARENT, STM32F4_RCC_DCKCFGR, 0, 5, 0, NULL},
- { CLK_SAIQ_PDIV, PLL_SAI, "pllsai-q-div", "pllsai-q",
+ { CLK_SAIQ_PDIV, PLL_VCO_SAI, "pllsai-q-div", "pllsai-q",
CLK_SET_RATE_PARENT, STM32F4_RCC_DCKCFGR, 8, 5, 0, NULL },
- { NO_IDX, PLL_SAI, "pllsai-r-div", "pllsai-r", CLK_SET_RATE_PARENT,
+ { NO_IDX, PLL_VCO_SAI, "pllsai-r-div", "pllsai-r", CLK_SET_RATE_PARENT,
STM32F4_RCC_DCKCFGR, 16, 2, 0, post_divr_table },
};
post_div->width,
post_div->flag_div,
post_div->div_table,
- clks[post_div->pll_num],
+ clks[post_div->pll_idx],
&stm32f4_clk_lock);
if (post_div->idx != NO_IDX)
config COMMON_CLK_HI3559A
bool "Hi3559A Clock Driver"
depends on ARCH_HISI || COMPILE_TEST
+ select RESET_HISI
default ARCH_HISI
help
Build the clock driver for hi3559a.
static struct clk_smd_rpm *msm8936_clks[] = {
[RPM_SMD_PCNOC_CLK] = &msm8916_pcnoc_clk,
- [RPM_SMD_PCNOC_A_CLK] = &msm8916_pcnoc_clk,
+ [RPM_SMD_PCNOC_A_CLK] = &msm8916_pcnoc_a_clk,
[RPM_SMD_SNOC_CLK] = &msm8916_snoc_clk,
[RPM_SMD_SNOC_A_CLK] = &msm8916_snoc_a_clk,
[RPM_SMD_BIMC_CLK] = &msm8916_bimc_clk,
CLK_PLL2_DIV20,
CLK_PLL3,
CLK_PLL3_DIV2,
+ CLK_PLL3_DIV2_4,
+ CLK_PLL3_DIV2_4_2,
CLK_PLL3_DIV4,
- CLK_PLL3_DIV8,
CLK_PLL4,
CLK_PLL5,
CLK_PLL5_DIV2,
};
/* Divider tables */
-static const struct clk_div_table dtable_3b[] = {
+static const struct clk_div_table dtable_1_32[] = {
{0, 1},
{1, 2},
{2, 4},
{3, 8},
{4, 32},
+ {0, 0},
};
static const struct cpg_core_clk r9a07g044_core_clks[] __initconst = {
DEF_FIXED(".pll2_div20", CLK_PLL2_DIV20, CLK_PLL2, 1, 20),
DEF_FIXED(".pll3_div2", CLK_PLL3_DIV2, CLK_PLL3, 1, 2),
+ DEF_FIXED(".pll3_div2_4", CLK_PLL3_DIV2_4, CLK_PLL3_DIV2, 1, 4),
+ DEF_FIXED(".pll3_div2_4_2", CLK_PLL3_DIV2_4_2, CLK_PLL3_DIV2_4, 1, 2),
DEF_FIXED(".pll3_div4", CLK_PLL3_DIV4, CLK_PLL3, 1, 4),
- DEF_FIXED(".pll3_div8", CLK_PLL3_DIV8, CLK_PLL3, 1, 8),
/* Core output clk */
DEF_FIXED("I", R9A07G044_CLK_I, CLK_PLL1, 1, 1),
DEF_DIV("P0", R9A07G044_CLK_P0, CLK_PLL2_DIV16, DIVPL2A,
- dtable_3b, CLK_DIVIDER_HIWORD_MASK),
+ dtable_1_32, CLK_DIVIDER_HIWORD_MASK),
DEF_FIXED("TSU", R9A07G044_CLK_TSU, CLK_PLL2_DIV20, 1, 1),
- DEF_DIV("P1", R9A07G044_CLK_P1, CLK_PLL3_DIV8,
- DIVPL3B, dtable_3b, CLK_DIVIDER_HIWORD_MASK),
+ DEF_DIV("P1", R9A07G044_CLK_P1, CLK_PLL3_DIV2_4,
+ DIVPL3B, dtable_1_32, CLK_DIVIDER_HIWORD_MASK),
+ DEF_DIV("P2", R9A07G044_CLK_P2, CLK_PLL3_DIV2_4_2,
+ DIVPL3A, dtable_1_32, CLK_DIVIDER_HIWORD_MASK),
};
static struct rzg2l_mod_clk r9a07g044_mod_clks[] = {
- DEF_MOD("gic", R9A07G044_CLK_GIC600,
- R9A07G044_CLK_P1,
- 0x514, BIT(0), (BIT(0) | BIT(1))),
- DEF_MOD("ia55", R9A07G044_CLK_IA55,
- R9A07G044_CLK_P1,
- 0x518, (BIT(0) | BIT(1)), BIT(0)),
- DEF_MOD("scif0", R9A07G044_CLK_SCIF0,
- R9A07G044_CLK_P0,
- 0x584, BIT(0), BIT(0)),
- DEF_MOD("scif1", R9A07G044_CLK_SCIF1,
- R9A07G044_CLK_P0,
- 0x584, BIT(1), BIT(1)),
- DEF_MOD("scif2", R9A07G044_CLK_SCIF2,
- R9A07G044_CLK_P0,
- 0x584, BIT(2), BIT(2)),
- DEF_MOD("scif3", R9A07G044_CLK_SCIF3,
- R9A07G044_CLK_P0,
- 0x584, BIT(3), BIT(3)),
- DEF_MOD("scif4", R9A07G044_CLK_SCIF4,
- R9A07G044_CLK_P0,
- 0x584, BIT(4), BIT(4)),
- DEF_MOD("sci0", R9A07G044_CLK_SCI0,
- R9A07G044_CLK_P0,
- 0x588, BIT(0), BIT(0)),
+ DEF_MOD("gic", R9A07G044_GIC600_GICCLK, R9A07G044_CLK_P1,
+ 0x514, 0),
+ DEF_MOD("ia55_pclk", R9A07G044_IA55_PCLK, R9A07G044_CLK_P2,
+ 0x518, 0),
+ DEF_MOD("ia55_clk", R9A07G044_IA55_CLK, R9A07G044_CLK_P1,
+ 0x518, 1),
+ DEF_MOD("scif0", R9A07G044_SCIF0_CLK_PCK, R9A07G044_CLK_P0,
+ 0x584, 0),
+ DEF_MOD("scif1", R9A07G044_SCIF1_CLK_PCK, R9A07G044_CLK_P0,
+ 0x584, 1),
+ DEF_MOD("scif2", R9A07G044_SCIF2_CLK_PCK, R9A07G044_CLK_P0,
+ 0x584, 2),
+ DEF_MOD("scif3", R9A07G044_SCIF3_CLK_PCK, R9A07G044_CLK_P0,
+ 0x584, 3),
+ DEF_MOD("scif4", R9A07G044_SCIF4_CLK_PCK, R9A07G044_CLK_P0,
+ 0x584, 4),
+ DEF_MOD("sci0", R9A07G044_SCI0_CLKP, R9A07G044_CLK_P0,
+ 0x588, 0),
+};
+
+static struct rzg2l_reset r9a07g044_resets[] = {
+ DEF_RST(R9A07G044_GIC600_GICRESET_N, 0x814, 0),
+ DEF_RST(R9A07G044_GIC600_DBG_GICRESET_N, 0x814, 1),
+ DEF_RST(R9A07G044_IA55_RESETN, 0x818, 0),
+ DEF_RST(R9A07G044_SCIF0_RST_SYSTEM_N, 0x884, 0),
+ DEF_RST(R9A07G044_SCIF1_RST_SYSTEM_N, 0x884, 1),
+ DEF_RST(R9A07G044_SCIF2_RST_SYSTEM_N, 0x884, 2),
+ DEF_RST(R9A07G044_SCIF3_RST_SYSTEM_N, 0x884, 3),
+ DEF_RST(R9A07G044_SCIF4_RST_SYSTEM_N, 0x884, 4),
+ DEF_RST(R9A07G044_SCI0_RST, 0x888, 0),
};
static const unsigned int r9a07g044_crit_mod_clks[] __initconst = {
- MOD_CLK_BASE + R9A07G044_CLK_GIC600,
+ MOD_CLK_BASE + R9A07G044_GIC600_GICCLK,
};
const struct rzg2l_cpg_info r9a07g044_cpg_info = {
/* Module Clocks */
.mod_clks = r9a07g044_mod_clks,
.num_mod_clks = ARRAY_SIZE(r9a07g044_mod_clks),
- .num_hw_mod_clks = R9A07G044_CLK_MIPI_DSI_PIN + 1,
+ .num_hw_mod_clks = R9A07G044_TSU_PCLK + 1,
+
+ /* Resets */
+ .resets = r9a07g044_resets,
+ .num_resets = ARRAY_SIZE(r9a07g044_resets),
};
#define SDIV(val) DIV_RSMASK(val, 0, 0x7)
#define CLK_ON_R(reg) (reg)
-#define CLK_MON_R(reg) (0x680 - 0x500 + (reg))
-#define CLK_RST_R(reg) (0x800 - 0x500 + (reg))
-#define CLK_MRST_R(reg) (0x980 - 0x500 + (reg))
+#define CLK_MON_R(reg) (0x180 + (reg))
+#define CLK_RST_R(reg) (reg)
+#define CLK_MRST_R(reg) (0x180 + (reg))
#define GET_REG_OFFSET(val) ((val >> 20) & 0xfff)
#define GET_REG_SAMPLL_CLK1(val) ((val >> 22) & 0xfff)
struct clk **clks;
unsigned int num_core_clks;
unsigned int num_mod_clks;
+ unsigned int num_resets;
unsigned int last_dt_core_clk;
struct raw_notifier_head notifiers;
*
* @hw: handle between common and hardware-specific interfaces
* @off: register offset
- * @onoff: ON/MON bits
- * @reset: reset bits
+ * @bit: ON/MON bit
* @priv: CPG/MSTP private data
*/
struct mstp_clock {
struct clk_hw hw;
u16 off;
- u8 onoff;
- u8 reset;
+ u8 bit;
struct rzg2l_cpg_priv *priv;
};
struct device *dev = priv->dev;
unsigned long flags;
unsigned int i;
+ u32 bitmask = BIT(clock->bit);
u32 value;
if (!clock->off) {
spin_lock_irqsave(&priv->rmw_lock, flags);
if (enable)
- value = (clock->onoff << 16) | clock->onoff;
+ value = (bitmask << 16) | bitmask;
else
- value = clock->onoff << 16;
+ value = bitmask << 16;
writel(value, priv->base + CLK_ON_R(reg));
spin_unlock_irqrestore(&priv->rmw_lock, flags);
return 0;
for (i = 1000; i > 0; --i) {
- if (((readl(priv->base + CLK_MON_R(reg))) & clock->onoff))
+ if (((readl(priv->base + CLK_MON_R(reg))) & bitmask))
break;
cpu_relax();
}
{
struct mstp_clock *clock = to_mod_clock(hw);
struct rzg2l_cpg_priv *priv = clock->priv;
+ u32 bitmask = BIT(clock->bit);
u32 value;
if (!clock->off) {
value = readl(priv->base + CLK_MON_R(clock->off));
- return !(value & clock->onoff);
+ return !(value & bitmask);
}
static const struct clk_ops rzg2l_mod_clock_ops = {
init.num_parents = 1;
clock->off = mod->off;
- clock->onoff = mod->onoff;
- clock->reset = mod->reset;
+ clock->bit = mod->bit;
clock->priv = priv;
clock->hw.init = &init;
{
struct rzg2l_cpg_priv *priv = rcdev_to_priv(rcdev);
const struct rzg2l_cpg_info *info = priv->info;
- unsigned int reg = info->mod_clks[id].off;
- u32 dis = info->mod_clks[id].reset;
+ unsigned int reg = info->resets[id].off;
+ u32 dis = BIT(info->resets[id].bit);
u32 we = dis << 16;
- dev_dbg(rcdev->dev, "reset name:%s id:%ld offset:0x%x\n",
- info->mod_clks[id].name, id, CLK_RST_R(reg));
+ dev_dbg(rcdev->dev, "reset id:%ld offset:0x%x\n", id, CLK_RST_R(reg));
/* Reset module */
writel(we, priv->base + CLK_RST_R(reg));
{
struct rzg2l_cpg_priv *priv = rcdev_to_priv(rcdev);
const struct rzg2l_cpg_info *info = priv->info;
- unsigned int reg = info->mod_clks[id].off;
- u32 value = info->mod_clks[id].reset << 16;
+ unsigned int reg = info->resets[id].off;
+ u32 value = BIT(info->resets[id].bit) << 16;
- dev_dbg(rcdev->dev, "assert name:%s id:%ld offset:0x%x\n",
- info->mod_clks[id].name, id, CLK_RST_R(reg));
+ dev_dbg(rcdev->dev, "assert id:%ld offset:0x%x\n", id, CLK_RST_R(reg));
writel(value, priv->base + CLK_RST_R(reg));
return 0;
{
struct rzg2l_cpg_priv *priv = rcdev_to_priv(rcdev);
const struct rzg2l_cpg_info *info = priv->info;
- unsigned int reg = info->mod_clks[id].off;
- u32 dis = info->mod_clks[id].reset;
+ unsigned int reg = info->resets[id].off;
+ u32 dis = BIT(info->resets[id].bit);
u32 value = (dis << 16) | dis;
- dev_dbg(rcdev->dev, "deassert name:%s id:%ld offset:0x%x\n",
- info->mod_clks[id].name, id, CLK_RST_R(reg));
+ dev_dbg(rcdev->dev, "deassert id:%ld offset:0x%x\n", id,
+ CLK_RST_R(reg));
writel(value, priv->base + CLK_RST_R(reg));
return 0;
{
struct rzg2l_cpg_priv *priv = rcdev_to_priv(rcdev);
const struct rzg2l_cpg_info *info = priv->info;
- unsigned int reg = info->mod_clks[id].off;
- u32 bitmask = info->mod_clks[id].reset;
+ unsigned int reg = info->resets[id].off;
+ u32 bitmask = BIT(info->resets[id].bit);
return !(readl(priv->base + CLK_MRST_R(reg)) & bitmask);
}
static int rzg2l_cpg_reset_xlate(struct reset_controller_dev *rcdev,
const struct of_phandle_args *reset_spec)
{
+ struct rzg2l_cpg_priv *priv = rcdev_to_priv(rcdev);
+ const struct rzg2l_cpg_info *info = priv->info;
unsigned int id = reset_spec->args[0];
- if (id >= rcdev->nr_resets) {
+ if (id >= rcdev->nr_resets || !info->resets[id].off) {
dev_err(rcdev->dev, "Invalid reset index %u\n", id);
return -EINVAL;
}
priv->rcdev.dev = priv->dev;
priv->rcdev.of_reset_n_cells = 1;
priv->rcdev.of_xlate = rzg2l_cpg_reset_xlate;
- priv->rcdev.nr_resets = priv->num_mod_clks;
+ priv->rcdev.nr_resets = priv->num_resets;
return devm_reset_controller_register(priv->dev, &priv->rcdev);
}
{
struct device_node *np = dev->of_node;
struct of_phandle_args clkspec;
+ bool once = true;
struct clk *clk;
int error;
int i = 0;
while (!of_parse_phandle_with_args(np, "clocks", "#clock-cells", i,
&clkspec)) {
- if (rzg2l_cpg_is_pm_clk(&clkspec))
- goto found;
-
- of_node_put(clkspec.np);
+ if (rzg2l_cpg_is_pm_clk(&clkspec)) {
+ if (once) {
+ once = false;
+ error = pm_clk_create(dev);
+ if (error) {
+ of_node_put(clkspec.np);
+ goto err;
+ }
+ }
+ clk = of_clk_get_from_provider(&clkspec);
+ of_node_put(clkspec.np);
+ if (IS_ERR(clk)) {
+ error = PTR_ERR(clk);
+ goto fail_destroy;
+ }
+
+ error = pm_clk_add_clk(dev, clk);
+ if (error) {
+ dev_err(dev, "pm_clk_add_clk failed %d\n",
+ error);
+ goto fail_put;
+ }
+ } else {
+ of_node_put(clkspec.np);
+ }
i++;
}
return 0;
-found:
- clk = of_clk_get_from_provider(&clkspec);
- of_node_put(clkspec.np);
-
- if (IS_ERR(clk))
- return PTR_ERR(clk);
-
- error = pm_clk_create(dev);
- if (error)
- goto fail_put;
-
- error = pm_clk_add_clk(dev, clk);
- if (error)
- goto fail_destroy;
-
- return 0;
+fail_put:
+ clk_put(clk);
fail_destroy:
pm_clk_destroy(dev);
-fail_put:
- clk_put(clk);
+err:
return error;
}
priv->clks = clks;
priv->num_core_clks = info->num_total_core_clks;
priv->num_mod_clks = info->num_hw_mod_clks;
+ priv->num_resets = info->num_resets;
priv->last_dt_core_clk = info->last_dt_core_clk;
for (i = 0; i < nclks; i++)
#define DDIV_PACK(offset, bitpos, size) \
(((offset) << 20) | ((bitpos) << 12) | ((size) << 8))
#define DIVPL2A DDIV_PACK(CPG_PL2_DDIV, 0, 3)
+#define DIVPL3A DDIV_PACK(CPG_PL3A_DDIV, 0, 3)
#define DIVPL3B DDIV_PACK(CPG_PL3A_DDIV, 4, 3)
/**
* @id: clock index in array containing all Core and Module Clocks
* @parent: id of parent clock
* @off: register offset
- * @onoff: ON/MON bits
- * @reset: reset bits
+ * @bit: ON/MON bit
*/
struct rzg2l_mod_clk {
const char *name;
unsigned int id;
unsigned int parent;
u16 off;
- u8 onoff;
- u8 reset;
+ u8 bit;
};
-#define DEF_MOD(_name, _id, _parent, _off, _onoff, _reset) \
- [_id] = { \
+#define DEF_MOD(_name, _id, _parent, _off, _bit) \
+ { \
.name = _name, \
- .id = MOD_CLK_BASE + _id, \
+ .id = MOD_CLK_BASE + (_id), \
.parent = (_parent), \
.off = (_off), \
- .onoff = (_onoff), \
- .reset = (_reset) \
+ .bit = (_bit), \
+ }
+
+/**
+ * struct rzg2l_reset - Reset definitions
+ *
+ * @off: register offset
+ * @bit: reset bit
+ */
+struct rzg2l_reset {
+ u16 off;
+ u8 bit;
+};
+
+#define DEF_RST(_id, _off, _bit) \
+ [_id] = { \
+ .off = (_off), \
+ .bit = (_bit) \
}
/**
unsigned int num_mod_clks;
unsigned int num_hw_mod_clks;
+ /* Resets */
+ const struct rzg2l_reset *resets;
+ unsigned int num_resets;
+
/* Critical Module Clocks that should not be disabled */
const unsigned int *crit_mod_clks;
unsigned int num_crit_mod_clks;
gate_ops->disable(gate_hw);
}
+static void clk_sdmmc_mux_disable_unused(struct clk_hw *hw)
+{
+ struct tegra_sdmmc_mux *sdmmc_mux = to_clk_sdmmc_mux(hw);
+ const struct clk_ops *gate_ops = sdmmc_mux->gate_ops;
+ struct clk_hw *gate_hw = &sdmmc_mux->gate.hw;
+
+ gate_ops->disable_unused(gate_hw);
+}
+
static void clk_sdmmc_mux_restore_context(struct clk_hw *hw)
{
struct clk_hw *parent = clk_hw_get_parent(hw);
.is_enabled = clk_sdmmc_mux_is_enabled,
.enable = clk_sdmmc_mux_enable,
.disable = clk_sdmmc_mux_disable,
+ .disable_unused = clk_sdmmc_mux_disable_unused,
.restore_context = clk_sdmmc_mux_restore_context,
};
return cpufreq_register_driver(&longhaul_driver);
case 10:
pr_err("Use acpi-cpufreq driver for VIA C7\n");
- default:
- ;
}
return -ENODEV;
alt_intercepts = 2 * idx_intercept_sum > cpu_data->total - idx_hit_sum;
alt_recent = idx_recent_sum > NR_RECENT / 2;
if (alt_recent || alt_intercepts) {
- s64 last_enabled_span_ns = duration_ns;
- int last_enabled_idx = idx;
+ s64 first_suitable_span_ns = duration_ns;
+ int first_suitable_idx = idx;
/*
* Look for the deepest idle state whose target residency had
intercept_sum = 0;
recent_sum = 0;
- for (i = idx - 1; i >= idx0; i--) {
+ for (i = idx - 1; i >= 0; i--) {
struct teo_bin *bin = &cpu_data->state_bins[i];
s64 span_ns;
intercept_sum += bin->intercepts;
recent_sum += bin->recent;
+ span_ns = teo_middle_of_bin(i, drv);
+
+ if ((!alt_recent || 2 * recent_sum > idx_recent_sum) &&
+ (!alt_intercepts ||
+ 2 * intercept_sum > idx_intercept_sum)) {
+ if (teo_time_ok(span_ns) &&
+ !dev->states_usage[i].disable) {
+ idx = i;
+ duration_ns = span_ns;
+ } else {
+ /*
+ * The current state is too shallow or
+ * disabled, so take the first enabled
+ * deeper state with suitable time span.
+ */
+ idx = first_suitable_idx;
+ duration_ns = first_suitable_span_ns;
+ }
+ break;
+ }
+
if (dev->states_usage[i].disable)
continue;
- span_ns = teo_middle_of_bin(i, drv);
if (!teo_time_ok(span_ns)) {
/*
- * The current state is too shallow, so select
- * the first enabled deeper state.
+ * The current state is too shallow, but if an
+ * alternative candidate state has been found,
+ * it may still turn out to be a better choice.
*/
- duration_ns = last_enabled_span_ns;
- idx = last_enabled_idx;
- break;
- }
+ if (first_suitable_idx != idx)
+ continue;
- if ((!alt_recent || 2 * recent_sum > idx_recent_sum) &&
- (!alt_intercepts ||
- 2 * intercept_sum > idx_intercept_sum)) {
- idx = i;
- duration_ns = span_ns;
break;
}
- last_enabled_span_ns = span_ns;
- last_enabled_idx = i;
+ first_suitable_span_ns = span_ns;
+ first_suitable_idx = i;
}
}
struct sync_file *b)
{
struct sync_file *sync_file;
- struct dma_fence **fences, **nfences, **a_fences, **b_fences;
- int i, i_a, i_b, num_fences, a_num_fences, b_num_fences;
+ struct dma_fence **fences = NULL, **nfences, **a_fences, **b_fences;
+ int i = 0, i_a, i_b, num_fences, a_num_fences, b_num_fences;
sync_file = sync_file_alloc();
if (!sync_file)
* If a sync_file can only be created with sync_file_merge
* and sync_file_create, this is a reasonable assumption.
*/
- for (i = i_a = i_b = 0; i_a < a_num_fences && i_b < b_num_fences; ) {
+ for (i_a = i_b = 0; i_a < a_num_fences && i_b < b_num_fences; ) {
struct dma_fence *pt_a = a_fences[i_a];
struct dma_fence *pt_b = b_fences[i_b];
fences = nfences;
}
- if (sync_file_set_fence(sync_file, fences, i) < 0) {
- kfree(fences);
+ if (sync_file_set_fence(sync_file, fences, i) < 0)
goto err;
- }
strlcpy(sync_file->user_name, name, sizeof(sync_file->user_name));
return sync_file;
err:
+ while (i)
+ dma_fence_put(fences[--i]);
+ kfree(fences);
fput(sync_file->file);
return NULL;
struct idxd_wq *wq;
};
+/*
+ * This is software defined error for the completion status. We overload the error code
+ * that will never appear in completion status and only SWERR register.
+ */
+enum idxd_completion_status {
+ IDXD_COMP_DESC_ABORT = 0xff,
+};
+
#define confdev_to_idxd(dev) container_of(dev, struct idxd_device, conf_dev)
#define confdev_to_wq(dev) container_of(dev, struct idxd_wq, conf_dev)
static inline void perfmon_exit(void) {}
#endif
+static inline void complete_desc(struct idxd_desc *desc, enum idxd_complete_type reason)
+{
+ idxd_dma_complete_txd(desc, reason);
+ idxd_free_desc(desc->wq, desc);
+}
+
#endif
spin_lock_init(&idxd->irq_entries[i].list_lock);
}
+ idxd_msix_perm_setup(idxd);
+
irq_entry = &idxd->irq_entries[0];
rc = request_threaded_irq(irq_entry->vector, NULL, idxd_misc_thread,
0, "idxd-misc", irq_entry);
}
idxd_unmask_error_interrupts(idxd);
- idxd_msix_perm_setup(idxd);
return 0;
err_wq_irqs:
err_misc_irq:
/* Disable error interrupt generation */
idxd_mask_error_interrupts(idxd);
+ idxd_msix_perm_clear(idxd);
err_irq_entries:
pci_free_irq_vectors(pdev);
dev_err(dev, "No usable interrupts\n");
for (i = 0; i < msixcnt; i++) {
irq_entry = &idxd->irq_entries[i];
synchronize_irq(irq_entry->vector);
- free_irq(irq_entry->vector, irq_entry);
if (i == 0)
continue;
idxd_flush_pending_llist(irq_entry);
idxd_flush_work_list(irq_entry);
}
-
- idxd_msix_perm_clear(idxd);
- idxd_release_int_handles(idxd);
- pci_free_irq_vectors(pdev);
- pci_iounmap(pdev, idxd->reg_base);
- pci_disable_device(pdev);
- destroy_workqueue(idxd->wq);
+ flush_workqueue(idxd->wq);
}
static void idxd_remove(struct pci_dev *pdev)
{
struct idxd_device *idxd = pci_get_drvdata(pdev);
+ struct idxd_irq_entry *irq_entry;
+ int msixcnt = pci_msix_vec_count(pdev);
+ int i;
dev_dbg(&pdev->dev, "%s called\n", __func__);
idxd_shutdown(pdev);
if (device_pasid_enabled(idxd))
idxd_disable_system_pasid(idxd);
idxd_unregister_devices(idxd);
- perfmon_pmu_remove(idxd);
+
+ for (i = 0; i < msixcnt; i++) {
+ irq_entry = &idxd->irq_entries[i];
+ free_irq(irq_entry->vector, irq_entry);
+ }
+ idxd_msix_perm_clear(idxd);
+ idxd_release_int_handles(idxd);
+ pci_free_irq_vectors(pdev);
+ pci_iounmap(pdev, idxd->reg_base);
iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA);
+ pci_disable_device(pdev);
+ destroy_workqueue(idxd->wq);
+ perfmon_pmu_remove(idxd);
+ device_unregister(&idxd->conf_dev);
}
static struct pci_driver idxd_pci_driver = {
return false;
}
-static inline void complete_desc(struct idxd_desc *desc, enum idxd_complete_type reason)
-{
- idxd_dma_complete_txd(desc, reason);
- idxd_free_desc(desc->wq, desc);
-}
-
static int irq_process_pending_llist(struct idxd_irq_entry *irq_entry,
enum irq_work_type wtype,
int *processed, u64 data)
reason = IDXD_COMPLETE_DEV_FAIL;
llist_for_each_entry_safe(desc, t, head, llnode) {
- if (desc->completion->status) {
- if ((desc->completion->status & DSA_COMP_STATUS_MASK) != DSA_COMP_SUCCESS)
+ u8 status = desc->completion->status & DSA_COMP_STATUS_MASK;
+
+ if (status) {
+ if (unlikely(status == IDXD_COMP_DESC_ABORT)) {
+ complete_desc(desc, IDXD_COMPLETE_ABORT);
+ (*processed)++;
+ continue;
+ }
+
+ if (unlikely(status != DSA_COMP_SUCCESS))
match_fault(desc, data);
complete_desc(desc, reason);
(*processed)++;
spin_unlock_irqrestore(&irq_entry->list_lock, flags);
list_for_each_entry(desc, &flist, list) {
- if ((desc->completion->status & DSA_COMP_STATUS_MASK) != DSA_COMP_SUCCESS)
+ u8 status = desc->completion->status & DSA_COMP_STATUS_MASK;
+
+ if (unlikely(status == IDXD_COMP_DESC_ABORT)) {
+ complete_desc(desc, IDXD_COMPLETE_ABORT);
+ continue;
+ }
+
+ if (unlikely(status != DSA_COMP_SUCCESS))
match_fault(desc, data);
complete_desc(desc, reason);
}
* Descriptor completion vectors are 1...N for MSIX. We will round
* robin through the N vectors.
*/
- wq->vec_ptr = (wq->vec_ptr % idxd->num_wq_irqs) + 1;
+ wq->vec_ptr = desc->vector = (wq->vec_ptr % idxd->num_wq_irqs) + 1;
if (!idxd->int_handles) {
desc->hw->int_handle = wq->vec_ptr;
} else {
- desc->vector = wq->vec_ptr;
/*
* int_handles are only for descriptor completion. However for device
* MSIX enumeration, vec 0 is used for misc interrupts. Therefore even
sbitmap_queue_clear(&wq->sbq, desc->id, cpu);
}
+static struct idxd_desc *list_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie,
+ struct idxd_desc *desc)
+{
+ struct idxd_desc *d, *n;
+
+ lockdep_assert_held(&ie->list_lock);
+ list_for_each_entry_safe(d, n, &ie->work_list, list) {
+ if (d == desc) {
+ list_del(&d->list);
+ return d;
+ }
+ }
+
+ /*
+ * At this point, the desc needs to be aborted is held by the completion
+ * handler where it has taken it off the pending list but has not added to the
+ * work list. It will be cleaned up by the interrupt handler when it sees the
+ * IDXD_COMP_DESC_ABORT for completion status.
+ */
+ return NULL;
+}
+
+static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie,
+ struct idxd_desc *desc)
+{
+ struct idxd_desc *d, *t, *found = NULL;
+ struct llist_node *head;
+ unsigned long flags;
+
+ desc->completion->status = IDXD_COMP_DESC_ABORT;
+ /*
+ * Grab the list lock so it will block the irq thread handler. This allows the
+ * abort code to locate the descriptor need to be aborted.
+ */
+ spin_lock_irqsave(&ie->list_lock, flags);
+ head = llist_del_all(&ie->pending_llist);
+ if (head) {
+ llist_for_each_entry_safe(d, t, head, llnode) {
+ if (d == desc) {
+ found = desc;
+ continue;
+ }
+ list_add_tail(&desc->list, &ie->work_list);
+ }
+ }
+
+ if (!found)
+ found = list_abort_desc(wq, ie, desc);
+ spin_unlock_irqrestore(&ie->list_lock, flags);
+
+ if (found)
+ complete_desc(found, IDXD_COMPLETE_ABORT);
+}
+
int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc)
{
struct idxd_device *idxd = wq->idxd;
+ struct idxd_irq_entry *ie = NULL;
void __iomem *portal;
int rc;
* even on UP because the recipient is a device.
*/
wmb();
+
+ /*
+ * Pending the descriptor to the lockless list for the irq_entry
+ * that we designated the descriptor to.
+ */
+ if (desc->hw->flags & IDXD_OP_FLAG_RCI) {
+ ie = &idxd->irq_entries[desc->vector];
+ llist_add(&desc->llnode, &ie->pending_llist);
+ }
+
if (wq_dedicated(wq)) {
iosubmit_cmds512(portal, desc->hw, 1);
} else {
* device is not accepting descriptor at all.
*/
rc = enqcmds(portal, desc->hw);
- if (rc < 0)
+ if (rc < 0) {
+ if (ie)
+ llist_abort_desc(wq, ie, desc);
return rc;
+ }
}
percpu_ref_put(&wq->wq_active);
-
- /*
- * Pending the descriptor to the lockless list for the irq_entry
- * that we designated the descriptor to.
- */
- if (desc->hw->flags & IDXD_OP_FLAG_RCI) {
- int vec;
-
- /*
- * If the driver is on host kernel, it would be the value
- * assigned to interrupt handle, which is index for MSIX
- * vector. If it's guest then can't use the int_handle since
- * that is the index to IMS for the entire device. The guest
- * device local index will be used.
- */
- vec = !idxd->int_handles ? desc->hw->int_handle : desc->vector;
- llist_add(&desc->llnode, &idxd->irq_entries[vec].pending_llist);
- }
-
return 0;
}
device_unregister(&group->conf_dev);
}
-
- device_unregister(&idxd->conf_dev);
}
int idxd_register_bus_type(void)
dma_length += sg_dma_len(sg);
}
+ imxdma_config_write(chan, &imxdmac->config, direction);
+
switch (imxdmac->word_size) {
case DMA_SLAVE_BUSWIDTH_4_BYTES:
if (sg_dma_len(sgl) & 3 || sgl->dma_address & 3)
case IDMAC_SDC_1:
case IDMAC_IC_7:
ipu_channel_set_priority(ipu, channel, true);
+ break;
default:
break;
}
case IDMAC_SDC_0:
case IDMAC_SDC_1:
n_desc = 4;
+ break;
default:
break;
}
case 16:
if (is_mpc8308)
return false;
+ break;
case 1:
case 2:
case 4:
return NULL;
ofdma_target = of_dma_find_controller(&dma_spec_target);
- if (!ofdma_target)
- return NULL;
+ if (!ofdma_target) {
+ ofdma->dma_router->route_free(ofdma->dma_router->dev,
+ route_data);
+ chan = ERR_PTR(-EPROBE_DEFER);
+ goto err;
+ }
chan = ofdma_target->of_dma_xlate(&dma_spec_target, ofdma_target);
if (IS_ERR_OR_NULL(chan)) {
}
}
+err:
/*
* Need to put the node back since the ofdma->of_dma_route_allocate
* has taken it for generating the new, translated dma_spec
error:
of_dma_controller_free(pdev->dev.of_node);
- pm_runtime_put(&pdev->dev);
error_pm:
+ pm_runtime_put(&pdev->dev);
pm_runtime_disable(&pdev->dev);
return ret;
}
chan->config_init = false;
- ret = pm_runtime_get_sync(dmadev->ddev.dev);
+ ret = pm_runtime_resume_and_get(dmadev->ddev.dev);
if (ret < 0)
return ret;
struct stm32_dma_device *dmadev = dev_get_drvdata(dev);
int id, ret, scr;
- ret = pm_runtime_get_sync(dev);
+ ret = pm_runtime_resume_and_get(dev);
if (ret < 0)
return ret;
/* Set dma request */
spin_lock_irqsave(&dmamux->lock, flags);
- ret = pm_runtime_get_sync(&pdev->dev);
+ ret = pm_runtime_resume_and_get(&pdev->dev);
if (ret < 0) {
spin_unlock_irqrestore(&dmamux->lock, flags);
goto error;
struct stm32_dmamux_data *stm32_dmamux = platform_get_drvdata(pdev);
int i, ret;
- ret = pm_runtime_get_sync(dev);
+ ret = pm_runtime_resume_and_get(dev);
if (ret < 0)
return ret;
if (ret < 0)
return ret;
- ret = pm_runtime_get_sync(dev);
+ ret = pm_runtime_resume_and_get(dev);
if (ret < 0)
return ret;
ud->tchan_cnt),
ud->rchan_cnt - bitmap_weight(ud->rchan_map,
ud->rchan_cnt));
+ break;
default:
break;
}
writel(0, xc->reg_ch_base + XDMAC_TSS);
/* wait until transfer is stopped */
- return readl_poll_timeout(xc->reg_ch_base + XDMAC_STAT, val,
- !(val & XDMAC_STAT_TENF), 100, 1000);
+ return readl_poll_timeout_atomic(xc->reg_ch_base + XDMAC_STAT, val,
+ !(val & XDMAC_STAT_TENF), 100, 1000);
}
/* xc->vc.lock must be held by caller */
* @genlock: Support genlock mode
* @err: Channel has errors
* @idle: Check for channel idle
+ * @terminating: Check for channel being synchronized by user
* @tasklet: Cleanup work after irq
* @config: Device configuration info
* @flush_on_fsync: Flush on Frame sync
bool genlock;
bool err;
bool idle;
+ bool terminating;
struct tasklet_struct tasklet;
struct xilinx_vdma_config config;
bool flush_on_fsync;
/* Run any dependencies, then free the descriptor */
dma_run_dependencies(&desc->async_tx);
xilinx_dma_free_tx_descriptor(chan, desc);
+
+ /*
+ * While we ran a callback the user called a terminate function,
+ * which takes care of cleaning up any remaining descriptors
+ */
+ if (chan->terminating)
+ break;
}
spin_unlock_irqrestore(&chan->lock, flags);
if (desc->cyclic)
chan->cyclic = true;
+ chan->terminating = false;
+
spin_unlock_irqrestore(&chan->lock, flags);
return cookie;
xilinx_dma_chan_reset(chan);
/* Remove and free all of the descriptors in the lists */
+ chan->terminating = true;
xilinx_dma_free_descriptors(chan);
chan->idle = true;
config EDAC_IGEN6
tristate "Intel client SoC Integrated MC"
depends on PCI && PCI_MMCONFIG && ARCH_HAVE_NMI_SAFE_CMPXCHG
- depends on X64_64 && X86_MCE_INTEL
+ depends on X86_64 && X86_MCE_INTEL
help
Support for error detection and correction on the Intel
client SoC Integrated Memory Controller using In-Band ECC IP.
struct ffa_driver *ffa_drv = to_ffa_driver(dev->driver);
struct ffa_device *ffa_dev = to_ffa_dev(dev);
- if (!ffa_device_match(dev, dev->driver))
- return -ENODEV;
-
return ffa_drv->probe(ffa_dev);
}
{
int ret;
+ if (!driver->probe)
+ return -EINVAL;
+
driver->driver.bus = &ffa_bus_type;
driver->driver.name = driver->name;
driver->driver.owner = owner;
#define PACK_TARGET_INFO(s, r) \
(FIELD_PREP(SENDER_ID_MASK, (s)) | FIELD_PREP(RECEIVER_ID_MASK, (r)))
-/**
+/*
* FF-A specification mentions explicitly about '4K pages'. This should
* not be confused with the kernel PAGE_SIZE, which is the translation
* granule kernel is configured and may be one among 4K, 16K and 64K.
static inline int ffa_to_linux_errno(int errno)
{
- if (errno < FFA_RET_SUCCESS && errno >= -ARRAY_SIZE(ffa_linux_errmap))
- return ffa_linux_errmap[-errno];
+ int err_idx = -errno;
+
+ if (err_idx >= 0 && err_idx < ARRAY_SIZE(ffa_linux_errmap))
+ return ffa_linux_errmap[err_idx];
return -EINVAL;
}
{
struct scmi_driver *scmi_drv = to_scmi_driver(dev->driver);
struct scmi_device *scmi_dev = to_scmi_dev(dev);
- const struct scmi_device_id *id;
-
- id = scmi_dev_match_id(scmi_dev, scmi_drv);
- if (!id)
- return -ENODEV;
if (!scmi_dev->handle)
return -EPROBE_DEFER;
{
int retval;
+ if (!driver->probe)
+ return -EINVAL;
+
retval = scmi_protocol_device_request(driver->id_table);
if (retval)
return retval;
SCMI_ERR_GENERIC = -8, /* Generic Error */
SCMI_ERR_HARDWARE = -9, /* Hardware Error */
SCMI_ERR_PROTOCOL = -10,/* Protocol Error */
- SCMI_ERR_MAX
};
/* List of all SCMI devices active in system */
static inline int scmi_to_linux_errno(int errno)
{
- if (errno < SCMI_SUCCESS && errno > SCMI_ERR_MAX)
- return scmi_linux_errmap[-errno];
+ int err_idx = -errno;
+
+ if (err_idx >= SCMI_SUCCESS && err_idx < ARRAY_SIZE(scmi_linux_errmap))
+ return scmi_linux_errmap[err_idx];
return -EIO;
}
const struct scmi_desc *desc = sinfo->desc;
/* Pre-allocated messages, no more than what hdr.seq can support */
- if (WARN_ON(desc->max_msg >= MSG_TOKEN_MAX)) {
- dev_err(dev, "Maximum message of %d exceeds supported %ld\n",
+ if (WARN_ON(!desc->max_msg || desc->max_msg > MSG_TOKEN_MAX)) {
+ dev_err(dev,
+ "Invalid maximum messages %d, not in range [1 - %lu]\n",
desc->max_msg, MSG_TOKEN_MAX);
return -EINVAL;
}
* @proto_id and @name: if device was still not existent it is created as a
* child of the specified SCMI instance @info and its transport properly
* initialized as usual.
+ *
+ * Return: A properly initialized scmi device, NULL otherwise.
*/
static inline struct scmi_device *
scmi_get_protocol_device(struct device_node *np, struct scmi_info *info,
*
* Generic devres managed helper to register a notifier_block against a
* protocol event.
+ *
+ * Return: 0 on Success
*/
static int scmi_devm_notifier_register(struct scmi_device *sdev,
u8 proto_id, u8 evt_id,
* Generic devres managed helper to explicitly un-register a notifier_block
* against a protocol event, which was previously registered using the above
* @scmi_devm_notifier_register.
+ *
+ * Return: 0 on Success
*/
static int scmi_devm_notifier_unregister(struct scmi_device *sdev,
u8 proto_id, u8 evt_id,
struct scmi_resp_sensor_reading_complete {
__le32 id;
- __le64 readings;
+ __le32 readings_low;
+ __le32 readings_high;
};
struct scmi_sensor_reading_resp {
resp = t->rx.buf;
if (le32_to_cpu(resp->id) == sensor_id)
- *value = get_unaligned_le64(&resp->readings);
+ *value =
+ get_unaligned_le64(&resp->readings_low);
else
ret = -EPROTO;
}
pvt_data.dev = dev;
- fw_shm_pool = tee_shm_alloc(pvt_data.ctx, MAX_SHM_MEM_SZ,
- TEE_SHM_MAPPED | TEE_SHM_DMA_BUF);
+ fw_shm_pool = tee_shm_alloc_kernel_buf(pvt_data.ctx, MAX_SHM_MEM_SZ);
if (IS_ERR(fw_shm_pool)) {
- dev_err(pvt_data.dev, "tee_shm_alloc failed\n");
+ dev_err(pvt_data.dev, "tee_shm_alloc_kernel_buf failed\n");
err = PTR_ERR(fw_shm_pool);
goto out_sess;
}
return 0;
}
+static void tee_bnxt_fw_shutdown(struct device *dev)
+{
+ tee_shm_free(pvt_data.fw_shm_pool);
+ tee_client_close_session(pvt_data.ctx, pvt_data.session_id);
+ tee_client_close_context(pvt_data.ctx);
+ pvt_data.ctx = NULL;
+}
+
static const struct tee_client_device_id tee_bnxt_fw_id_table[] = {
{UUID_INIT(0x6272636D, 0x2019, 0x0716,
0x42, 0x43, 0x4D, 0x5F, 0x53, 0x43, 0x48, 0x49)},
.bus = &tee_bus_type,
.probe = tee_bnxt_fw_probe,
.remove = tee_bnxt_fw_remove,
+ .shutdown = tee_bnxt_fw_shutdown,
},
};
break;
if (!adev->pnp.unique_id && node->acpi.uid == 0)
break;
- acpi_dev_put(adev);
}
if (!adev)
return -ENODEV;
static int efi_mem_reserve_iomem(phys_addr_t addr, u64 size)
{
struct resource *res, *parent;
+ int ret;
res = kzalloc(sizeof(struct resource), GFP_ATOMIC);
if (!res)
/* we expect a conflict with a 'System RAM' region */
parent = request_resource_conflict(&iomem_resource, res);
- return parent ? request_resource(parent, res) : 0;
+ ret = parent ? request_resource(parent, res) : 0;
+
+ /*
+ * Given that efi_mem_reserve_iomem() can be called at any
+ * time, only call memblock_reserve() if the architecture
+ * keeps the infrastructure around.
+ */
+ if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK) && !ret)
+ memblock_reserve(addr, size);
+
+ return ret;
}
int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size)
* @image: EFI loaded image protocol
* @load_addr: pointer to loaded initrd
* @load_size: size of loaded initrd
- * @soft_limit: preferred size of allocated memory for loading the initrd
- * @hard_limit: minimum size of allocated memory
+ * @soft_limit: preferred address for loading the initrd
+ * @hard_limit: upper limit address for loading the initrd
*
* Return: status code
*/
pr_err("EFI MOKvar config table is not valid\n");
return;
}
- efi_mem_reserve(efi.mokvar_table, map_size_needed);
+
+ if (md.type == EFI_BOOT_SERVICES_DATA)
+ efi_mem_reserve(efi.mokvar_table, map_size_needed);
+
efi_mokvar_table_size = map_size_needed;
}
tbl_size = sizeof(*log_tbl) + log_tbl->size;
memblock_reserve(efi.tpm_log, tbl_size);
- if (efi.tpm_final_log == EFI_INVALID_TABLE_ADDR ||
- log_tbl->version != EFI_TCG2_EVENT_LOG_FORMAT_TCG_2) {
- pr_warn(FW_BUG "TPM Final Events table missing or invalid\n");
+ if (efi.tpm_final_log == EFI_INVALID_TABLE_ADDR) {
+ pr_info("TPM Final Events table not present\n");
+ goto out;
+ } else if (log_tbl->version != EFI_TCG2_EVENT_LOG_FORMAT_TCG_2) {
+ pr_warn(FW_BUG "TPM Final Events table invalid\n");
goto out;
}
return 0;
priv->cpu = target;
+ perf_pmu_migrate_context(&priv->pmu, cpu, target);
+
return 0;
}
ret = devm_request_irq(&pdev->dev, mpc8xxx_gc->irqn,
mpc8xxx_gpio_irq_cascade,
- IRQF_SHARED, "gpio-cascade",
+ IRQF_NO_THREAD | IRQF_SHARED, "gpio-cascade",
mpc8xxx_gc);
if (ret) {
dev_err(&pdev->dev,
struct resource *res;
int ret, irq;
- irq = platform_get_irq(pdev, 0);
- if (irq < 0)
+ irq = platform_get_irq_optional(pdev, 0);
+ if (irq < 0 && irq != -ENXIO)
return irq;
res = platform_get_resource(pdev, IORESOURCE_IO, 0);
pm_runtime_enable(&pdev->dev);
- if (irq) {
+ if (irq > 0) {
struct irq_chip *irq_chip = &gpio->irq_chip;
u8 irq_status;
u32 max_level;
};
+#define codec_info_build(type, width, height, level) \
+ .codec_type = type,\
+ .max_width = width,\
+ .max_height = height,\
+ .max_pixels_per_frame = height * width,\
+ .max_level = level,
+
struct amdgpu_video_codecs {
const u32 codec_count;
const struct amdgpu_video_codec_info *codec_array;
#include <linux/slab.h>
#include <linux/power_supply.h>
#include <linux/pm_runtime.h>
+#include <linux/suspend.h>
#include <acpi/video.h>
#include <acpi/actbl.h>
*/
bool amdgpu_acpi_is_s0ix_supported(struct amdgpu_device *adev)
{
-#if defined(CONFIG_AMD_PMC) || defined(CONFIG_AMD_PMC_MODULE)
+#if IS_ENABLED(CONFIG_AMD_PMC) && IS_ENABLED(CONFIG_PM_SLEEP)
if (acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0) {
if (adev->flags & AMD_IS_APU)
- return true;
+ return pm_suspend_target_state == PM_SUSPEND_TO_IDLE;
}
#endif
return false;
struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv,
uint64_t *size);
int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
- struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv, bool *table_freed);
+ struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv);
int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu(
struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv);
int amdgpu_amdkfd_gpuvm_sync_memory(
static int update_gpuvm_pte(struct kgd_mem *mem,
struct kfd_mem_attachment *entry,
- struct amdgpu_sync *sync,
- bool *table_freed)
+ struct amdgpu_sync *sync)
{
struct amdgpu_bo_va *bo_va = entry->bo_va;
struct amdgpu_device *adev = entry->adev;
return ret;
/* Update the page tables */
- ret = amdgpu_vm_bo_update(adev, bo_va, false, table_freed);
+ ret = amdgpu_vm_bo_update(adev, bo_va, false);
if (ret) {
pr_err("amdgpu_vm_bo_update failed\n");
return ret;
static int map_bo_to_gpuvm(struct kgd_mem *mem,
struct kfd_mem_attachment *entry,
struct amdgpu_sync *sync,
- bool no_update_pte,
- bool *table_freed)
+ bool no_update_pte)
{
int ret;
if (no_update_pte)
return 0;
- ret = update_gpuvm_pte(mem, entry, sync, table_freed);
+ ret = update_gpuvm_pte(mem, entry, sync);
if (ret) {
pr_err("update_gpuvm_pte() failed\n");
goto update_gpuvm_pte_failed;
domain = alloc_domain = AMDGPU_GEM_DOMAIN_VRAM;
alloc_flags = AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE;
alloc_flags |= (flags & KFD_IOC_ALLOC_MEM_FLAGS_PUBLIC) ?
- AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED :
- AMDGPU_GEM_CREATE_NO_CPU_ACCESS;
+ AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED : 0;
} else if (flags & KFD_IOC_ALLOC_MEM_FLAGS_GTT) {
domain = alloc_domain = AMDGPU_GEM_DOMAIN_GTT;
alloc_flags = 0;
}
int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
- struct kgd_dev *kgd, struct kgd_mem *mem,
- void *drm_priv, bool *table_freed)
+ struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv)
{
struct amdgpu_device *adev = get_amdgpu_device(kgd);
struct amdgpu_vm *avm = drm_priv_to_vm(drm_priv);
entry->va, entry->va + bo_size, entry);
ret = map_bo_to_gpuvm(mem, entry, ctx.sync,
- is_invalid_userptr, table_freed);
+ is_invalid_userptr);
if (ret) {
pr_err("Failed to map bo to gpuvm\n");
goto out_unreserve;
continue;
kfd_mem_dmaunmap_attachment(mem, attachment);
- ret = update_gpuvm_pte(mem, attachment, &sync, NULL);
+ ret = update_gpuvm_pte(mem, attachment, &sync);
if (ret) {
pr_err("%s: update PTE failed\n", __func__);
/* make sure this gets validated again */
continue;
kfd_mem_dmaunmap_attachment(mem, attachment);
- ret = update_gpuvm_pte(mem, attachment, &sync_obj, NULL);
+ ret = update_gpuvm_pte(mem, attachment, &sync_obj);
if (ret) {
pr_debug("Memory eviction: update PTE failed. Try again\n");
goto validate_map_fail;
if (r)
return r;
- r = amdgpu_vm_bo_update(adev, fpriv->prt_va, false, NULL);
+ r = amdgpu_vm_bo_update(adev, fpriv->prt_va, false);
if (r)
return r;
if (amdgpu_mcbp || amdgpu_sriov_vf(adev)) {
bo_va = fpriv->csa_va;
BUG_ON(!bo_va);
- r = amdgpu_vm_bo_update(adev, bo_va, false, NULL);
+ r = amdgpu_vm_bo_update(adev, bo_va, false);
if (r)
return r;
if (bo_va == NULL)
continue;
- r = amdgpu_vm_bo_update(adev, bo_va, false, NULL);
+ r = amdgpu_vm_bo_update(adev, bo_va, false);
if (r)
return r;
r = amdgpu_device_get_job_timeout_settings(adev);
if (r) {
dev_err(adev->dev, "invalid lockup_timeout parameter syntax\n");
- goto failed_unmap;
+ return r;
}
/* early init functions */
r = amdgpu_device_ip_early_init(adev);
if (r)
- goto failed_unmap;
+ return r;
/* doorbell bar mapping and doorbell index init*/
amdgpu_device_doorbell_init(adev);
failed:
amdgpu_vf_error_trans_all(adev);
-failed_unmap:
- iounmap(adev->rmmio);
- adev->rmmio = NULL;
-
return r;
}
{0x1002, 0x734F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14},
/* Renoir */
+ {0x1002, 0x15E7, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU},
{0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU},
{0x1002, 0x1638, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU},
{0x1002, 0x164C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU},
/* Van Gogh */
{0x1002, 0x163F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VANGOGH|AMD_IS_APU},
+ /* Yellow Carp */
+ {0x1002, 0x164D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_YELLOW_CARP|AMD_IS_APU},
+ {0x1002, 0x1681, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_YELLOW_CARP|AMD_IS_APU},
+
/* Navy_Flounder */
{0x1002, 0x73C0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVY_FLOUNDER},
{0x1002, 0x73C1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVY_FLOUNDER},
{0x1002, 0x740F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ALDEBARAN|AMD_EXP_HW_SUPPORT},
{0x1002, 0x7410, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ALDEBARAN|AMD_EXP_HW_SUPPORT},
+ /* BEIGE_GOBY */
+ {0x1002, 0x7420, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
+ {0x1002, 0x7421, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
+ {0x1002, 0x7422, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
+ {0x1002, 0x7423, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
+ {0x1002, 0x743F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_BEIGE_GOBY},
+
{0, 0, 0}
};
if (bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS)
return -EPERM;
+ /* Workaround for Thunk bug creating PROT_NONE,MAP_PRIVATE mappings
+ * for debugger access to invisible VRAM. Should have used MAP_SHARED
+ * instead. Clearing VM_MAYWRITE prevents the mapping from ever
+ * becoming writable and makes is_cow_mapping(vm_flags) false.
+ */
+ if (is_cow_mapping(vma->vm_flags) &&
+ !(vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)))
+ vma->vm_flags &= ~VM_MAYWRITE;
+
return drm_gem_ttm_mmap(obj, vma);
}
if (operation == AMDGPU_VA_OP_MAP ||
operation == AMDGPU_VA_OP_REPLACE) {
- r = amdgpu_vm_bo_update(adev, bo_va, false, NULL);
+ r = amdgpu_vm_bo_update(adev, bo_va, false);
if (r)
goto error;
}
return true;
}
+static void amdgpu_restore_msix(struct amdgpu_device *adev)
+{
+ u16 ctrl;
+
+ pci_read_config_word(adev->pdev, adev->pdev->msix_cap + PCI_MSIX_FLAGS, &ctrl);
+ if (!(ctrl & PCI_MSIX_FLAGS_ENABLE))
+ return;
+
+ /* VF FLR */
+ ctrl &= ~PCI_MSIX_FLAGS_ENABLE;
+ pci_write_config_word(adev->pdev, adev->pdev->msix_cap + PCI_MSIX_FLAGS, ctrl);
+ ctrl |= PCI_MSIX_FLAGS_ENABLE;
+ pci_write_config_word(adev->pdev, adev->pdev->msix_cap + PCI_MSIX_FLAGS, ctrl);
+}
+
/**
* amdgpu_irq_init - initialize interrupt handling
*
{
int i, j, k;
+ if (amdgpu_sriov_vf(adev))
+ amdgpu_restore_msix(adev);
+
for (i = 0; i < AMDGPU_IRQ_CLIENTID_MAX; ++i) {
if (!adev->irq.client[i].sources)
continue;
/* query/inject/cure begin */
int amdgpu_ras_query_error_status(struct amdgpu_device *adev,
- struct ras_query_if *info)
+ struct ras_query_if *info)
{
struct ras_manager *obj = amdgpu_ras_find_obj(adev, &info->head);
struct ras_err_data err_data = {0, 0, 0, NULL};
return ret;
}
-/* get the total error counts on all IPs */
-void amdgpu_ras_query_error_count(struct amdgpu_device *adev,
- unsigned long *ce_count,
- unsigned long *ue_count)
+/**
+ * amdgpu_ras_query_error_count -- Get error counts of all IPs
+ * adev: pointer to AMD GPU device
+ * ce_count: pointer to an integer to be set to the count of correctible errors.
+ * ue_count: pointer to an integer to be set to the count of uncorrectible
+ * errors.
+ *
+ * If set, @ce_count or @ue_count, count and return the corresponding
+ * error counts in those integer pointers. Return 0 if the device
+ * supports RAS. Return -EOPNOTSUPP if the device doesn't support RAS.
+ */
+int amdgpu_ras_query_error_count(struct amdgpu_device *adev,
+ unsigned long *ce_count,
+ unsigned long *ue_count)
{
struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
struct ras_manager *obj;
unsigned long ce, ue;
if (!adev->ras_enabled || !con)
- return;
+ return -EOPNOTSUPP;
+
+ /* Don't count since no reporting.
+ */
+ if (!ce_count && !ue_count)
+ return 0;
ce = 0;
ue = 0;
struct ras_query_if info = {
.head = obj->head,
};
+ int res;
- if (amdgpu_ras_query_error_status(adev, &info))
- return;
+ res = amdgpu_ras_query_error_status(adev, &info);
+ if (res)
+ return res;
ce += info.ce_count;
ue += info.ue_count;
if (ue_count)
*ue_count = ue;
+
+ return 0;
}
/* query/inject/cure end */
/* Cache new values.
*/
- amdgpu_ras_query_error_count(adev, &ce_count, &ue_count);
- atomic_set(&con->ras_ce_count, ce_count);
- atomic_set(&con->ras_ue_count, ue_count);
+ if (amdgpu_ras_query_error_count(adev, &ce_count, &ue_count) == 0) {
+ atomic_set(&con->ras_ce_count, ce_count);
+ atomic_set(&con->ras_ue_count, ue_count);
+ }
pm_runtime_mark_last_busy(dev->dev);
Out:
/* Those are the cached values at init.
*/
- amdgpu_ras_query_error_count(adev, &ce_count, &ue_count);
- atomic_set(&con->ras_ce_count, ce_count);
- atomic_set(&con->ras_ue_count, ue_count);
+ if (amdgpu_ras_query_error_count(adev, &ce_count, &ue_count) == 0) {
+ atomic_set(&con->ras_ce_count, ce_count);
+ atomic_set(&con->ras_ue_count, ue_count);
+ }
return 0;
cleanup:
void amdgpu_ras_resume(struct amdgpu_device *adev);
void amdgpu_ras_suspend(struct amdgpu_device *adev);
-void amdgpu_ras_query_error_count(struct amdgpu_device *adev,
- unsigned long *ce_count,
- unsigned long *ue_count);
+int amdgpu_ras_query_error_count(struct amdgpu_device *adev,
+ unsigned long *ce_count,
+ unsigned long *ue_count);
/* error handling functions */
int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev,
{
struct drm_mm_node *node;
- if (!res) {
+ if (!res || res->mem_type == TTM_PL_SYSTEM) {
cur->start = start;
cur->size = size;
cur->remaining = size;
cur->node = NULL;
+ WARN_ON(res && start + size > res->num_pages << PAGE_SHIFT);
return;
}
r = vm->update_funcs->commit(¶ms, fence);
if (table_freed)
- *table_freed = *table_freed || params.table_freed;
+ *table_freed = params.table_freed;
error_unlock:
amdgpu_vm_eviction_unlock(vm);
* @adev: amdgpu_device pointer
* @bo_va: requested BO and VM object
* @clear: if true clear the entries
- * @table_freed: return true if page table is freed
*
* Fill in the page table entries for @bo_va.
*
* 0 for success, -EINVAL for failure.
*/
int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va,
- bool clear, bool *table_freed)
+ bool clear)
{
struct amdgpu_bo *bo = bo_va->base.bo;
struct amdgpu_vm *vm = bo_va->base.vm;
resv, mapping->start,
mapping->last, update_flags,
mapping->offset, mem,
- pages_addr, last_update, table_freed);
+ pages_addr, last_update, NULL);
if (r)
return r;
}
list_for_each_entry_safe(bo_va, tmp, &vm->moved, base.vm_status) {
/* Per VM BOs never need to bo cleared in the page tables */
- r = amdgpu_vm_bo_update(adev, bo_va, false, NULL);
+ r = amdgpu_vm_bo_update(adev, bo_va, false);
if (r)
return r;
}
else
clear = true;
- r = amdgpu_vm_bo_update(adev, bo_va, clear, NULL);
+ r = amdgpu_vm_bo_update(adev, bo_va, clear);
if (r)
return r;
struct dma_fence **fence, bool *free_table);
int amdgpu_vm_bo_update(struct amdgpu_device *adev,
struct amdgpu_bo_va *bo_va,
- bool clear, bool *table_freed);
+ bool clear);
bool amdgpu_vm_evictable(struct amdgpu_bo *bo);
void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev,
struct amdgpu_bo *bo, bool evicted);
static void dce_virtual_set_irq_funcs(struct amdgpu_device *adev)
{
- adev->crtc_irq.num_types = AMDGPU_CRTC_IRQ_VBLANK6 + 1;
+ adev->crtc_irq.num_types = adev->mode_info.num_crtc;
adev->crtc_irq.funcs = &dce_virtual_crtc_irq_funcs;
}
SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER7_SELECT, 0xf0f001ff, 0x00000000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER8_SELECT, 0xf0f001ff, 0x00000000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER9_SELECT, 0xf0f001ff, 0x00000000),
+ SOC15_REG_GOLDEN_VALUE(GC, 0, mmSX_DEBUG_1, 0x00010000, 0x00010020),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0xfff7ffff, 0x01030000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0xffbfffff, 0x00a00000)
};
SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_2, 0xffffffbf, 0x00000020),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL_1_Vangogh, 0xffffffff, 0x00070103),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQG_CONFIG, 0x000017ff, 0x00001000),
+ SOC15_REG_GOLDEN_VALUE(GC, 0, mmSX_DEBUG_1, 0x00010000, 0x00010020),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0xfff7ffff, 0x01030000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0xffffffff, 0x00400000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmVGT_GS_MAX_WAVE_ID, 0x00000fff, 0x000000ff),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER7_SELECT, 0xf0f001ff, 0x00000000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER8_SELECT, 0xf0f001ff, 0x00000000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER9_SELECT, 0xf0f001ff, 0x00000000),
+ SOC15_REG_GOLDEN_VALUE(GC, 0, mmSX_DEBUG_1, 0x00010000, 0x00010020),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0x01030000, 0x01030000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0x03a00000, 0x00a00000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmLDS_CONFIG, 0x00000020, 0x00000020)
return false;
}
+static bool check_if_enlarge_doorbell_range(struct amdgpu_device *adev)
+{
+ if ((adev->asic_type == CHIP_RENOIR) &&
+ (adev->gfx.me_fw_version >= 0x000000a5) &&
+ (adev->gfx.me_feature_version >= 52))
+ return true;
+ else
+ return false;
+}
+
static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev)
{
if (gfx_v9_0_should_disable_gfxoff(adev->pdev))
if (ring->use_doorbell) {
WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_LOWER,
(adev->doorbell_index.kiq * 2) << 2);
- WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER,
+ /* If GC has entered CGPG, ringing doorbell > first page
+ * doesn't wakeup GC. Enlarge CP_MEC_DOORBELL_RANGE_UPPER to
+ * workaround this issue. And this change has to align with firmware
+ * update.
+ */
+ if (check_if_enlarge_doorbell_range(adev))
+ WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER,
+ (adev->doorbell.size - 4));
+ else
+ WREG32_SOC15(GC, 0, mmCP_MEC_DOORBELL_RANGE_UPPER,
(adev->doorbell_index.userqueue_end * 2) << 2);
}
* otherwise the mailbox msg will be ruined/reseted by
* the VF FLR.
*/
- if (!down_read_trylock(&adev->reset_sem))
+ if (!down_write_trylock(&adev->reset_sem))
return;
amdgpu_virt_fini_data_exchange(adev);
flr_done:
atomic_set(&adev->in_gpu_reset, 0);
- up_read(&adev->reset_sem);
+ up_write(&adev->reset_sem);
/* Trigger recovery for world switch failure if no TDR */
if (amdgpu_device_should_recover_gpu(adev)
* otherwise the mailbox msg will be ruined/reseted by
* the VF FLR.
*/
- if (!down_read_trylock(&adev->reset_sem))
+ if (!down_write_trylock(&adev->reset_sem))
return;
amdgpu_virt_fini_data_exchange(adev);
flr_done:
atomic_set(&adev->in_gpu_reset, 0);
- up_read(&adev->reset_sem);
+ up_write(&adev->reset_sem);
/* Trigger recovery for world switch failure if no TDR */
if (amdgpu_device_should_recover_gpu(adev)
#include "smuio_v11_0.h"
#include "smuio_v11_0_6.h"
-#define codec_info_build(type, width, height, level) \
- .codec_type = type,\
- .max_width = width,\
- .max_height = height,\
- .max_pixels_per_frame = height * width,\
- .max_level = level,
-
static const struct amd_ip_funcs nv_common_ip_funcs;
/* Navi */
static const struct amdgpu_video_codec_info nv_video_codecs_encode_array[] =
{
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
- .max_width = 4096,
- .max_height = 2304,
- .max_pixels_per_frame = 4096 * 2304,
- .max_level = 0,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
- .max_width = 4096,
- .max_height = 2304,
- .max_pixels_per_frame = 4096 * 2304,
- .max_level = 0,
- },
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
};
static const struct amdgpu_video_codecs nv_video_codecs_encode =
/* Navi1x */
static const struct amdgpu_video_codec_info nv_video_codecs_decode_array[] =
{
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 3,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 5,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 52,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 4,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
- .max_width = 8192,
- .max_height = 4352,
- .max_pixels_per_frame = 8192 * 4352,
- .max_level = 186,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 0,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9,
- .max_width = 8192,
- .max_height = 4352,
- .max_pixels_per_frame = 8192 * 4352,
- .max_level = 0,
- },
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
};
static const struct amdgpu_video_codecs nv_video_codecs_decode =
/* Sienna Cichlid */
static const struct amdgpu_video_codec_info sc_video_codecs_decode_array[] =
{
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 3,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 5,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 52,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 4,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
- .max_width = 8192,
- .max_height = 4352,
- .max_pixels_per_frame = 8192 * 4352,
- .max_level = 186,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 0,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9,
- .max_width = 8192,
- .max_height = 4352,
- .max_pixels_per_frame = 8192 * 4352,
- .max_level = 0,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1,
- .max_width = 8192,
- .max_height = 4352,
- .max_pixels_per_frame = 8192 * 4352,
- .max_level = 0,
- },
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
};
static const struct amdgpu_video_codecs sc_video_codecs_decode =
/* SRIOV Sienna Cichlid, not const since data is controlled by host */
static struct amdgpu_video_codec_info sriov_sc_video_codecs_encode_array[] =
{
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
- .max_width = 4096,
- .max_height = 2304,
- .max_pixels_per_frame = 4096 * 2304,
- .max_level = 0,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
- .max_width = 4096,
- .max_height = 2304,
- .max_pixels_per_frame = 4096 * 2304,
- .max_level = 0,
- },
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
};
static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array[] =
{
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 3,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 5,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 52,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 4,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
- .max_width = 8192,
- .max_height = 4352,
- .max_pixels_per_frame = 8192 * 4352,
- .max_level = 186,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 0,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9,
- .max_width = 8192,
- .max_height = 4352,
- .max_pixels_per_frame = 8192 * 4352,
- .max_level = 0,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1,
- .max_width = 8192,
- .max_height = 4352,
- .max_pixels_per_frame = 8192 * 4352,
- .max_level = 0,
- },
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
};
static struct amdgpu_video_codecs sriov_sc_video_codecs_encode =
.codec_array = NULL,
};
+/* Yellow Carp*/
+static const struct amdgpu_video_codec_info yc_video_codecs_decode_array[] = {
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+};
+
+static const struct amdgpu_video_codecs yc_video_codecs_decode = {
+ .codec_count = ARRAY_SIZE(yc_video_codecs_decode_array),
+ .codec_array = yc_video_codecs_decode_array,
+};
+
static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode,
const struct amdgpu_video_codecs **codecs)
{
case CHIP_NAVY_FLOUNDER:
case CHIP_DIMGREY_CAVEFISH:
case CHIP_VANGOGH:
- case CHIP_YELLOW_CARP:
if (encode)
*codecs = &nv_video_codecs_encode;
else
*codecs = &sc_video_codecs_decode;
return 0;
+ case CHIP_YELLOW_CARP:
+ if (encode)
+ *codecs = &nv_video_codecs_encode;
+ else
+ *codecs = &yc_video_codecs_decode;
+ return 0;
case CHIP_BEIGE_GOBY:
if (encode)
*codecs = &bg_video_codecs_encode;
AMD_PG_SUPPORT_VCN |
AMD_PG_SUPPORT_VCN_DPG |
AMD_PG_SUPPORT_JPEG;
- adev->external_rev_id = adev->rev_id + 0x01;
+ if (adev->pdev->device == 0x1681)
+ adev->external_rev_id = adev->rev_id + 0x19;
+ else
+ adev->external_rev_id = adev->rev_id + 0x01;
break;
default:
/* FIXME: not supported yet */
err = psp_init_asd_microcode(psp, chip_name);
if (err)
- goto out;
+ return err;
snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ta.bin", chip_name);
err = request_firmware(&adev->psp.ta_fw, fw_name, adev->dev);
} else {
err = amdgpu_ucode_validate(adev->psp.ta_fw);
if (err)
- goto out2;
+ goto out;
ta_hdr = (const struct ta_firmware_header_v1_0 *)
adev->psp.ta_fw->data;
return 0;
-out2:
+out:
release_firmware(adev->psp.ta_fw);
adev->psp.ta_fw = NULL;
-out:
if (err) {
dev_err(adev->dev,
"psp v12.0: Failed to load firmware \"%s\"\n",
/* Vega, Raven, Arcturus */
static const struct amdgpu_video_codec_info vega_video_codecs_encode_array[] =
{
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
- .max_width = 4096,
- .max_height = 2304,
- .max_pixels_per_frame = 4096 * 2304,
- .max_level = 0,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
- .max_width = 4096,
- .max_height = 2304,
- .max_pixels_per_frame = 4096 * 2304,
- .max_level = 0,
- },
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
};
static const struct amdgpu_video_codecs vega_video_codecs_encode =
/* Vega */
static const struct amdgpu_video_codec_info vega_video_codecs_decode_array[] =
{
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 3,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 5,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 52,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 4,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 186,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 0,
- },
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 4096, 186)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
};
static const struct amdgpu_video_codecs vega_video_codecs_decode =
/* Raven */
static const struct amdgpu_video_codec_info rv_video_codecs_decode_array[] =
{
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 3,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 5,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 52,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 4,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 186,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 0,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 0,
- },
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 4096, 186)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 4096, 4096, 0)},
};
static const struct amdgpu_video_codecs rv_video_codecs_decode =
/* Renoir, Arcturus */
static const struct amdgpu_video_codec_info rn_video_codecs_decode_array[] =
{
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 3,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 5,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 52,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 4,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
- .max_width = 8192,
- .max_height = 4352,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 186,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 0,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9,
- .max_width = 8192,
- .max_height = 4352,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 0,
- },
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
};
static const struct amdgpu_video_codecs rn_video_codecs_decode =
long err = 0;
int i;
uint32_t *devices_arr = NULL;
- bool table_freed = false;
dev = kfd_device_by_id(GET_GPU_ID(args->handle));
if (!dev)
goto get_mem_obj_from_handle_failed;
}
err = amdgpu_amdkfd_gpuvm_map_memory_to_gpu(
- peer->kgd, (struct kgd_mem *)mem,
- peer_pdd->drm_priv, &table_freed);
+ peer->kgd, (struct kgd_mem *)mem, peer_pdd->drm_priv);
if (err) {
pr_err("Failed to map to gpu %d/%d\n",
i, args->n_devices);
}
/* Flush TLBs after waiting for the page table updates to complete */
- if (table_freed) {
- for (i = 0; i < args->n_devices; i++) {
- peer = kfd_device_by_id(devices_arr[i]);
- if (WARN_ON_ONCE(!peer))
- continue;
- peer_pdd = kfd_get_process_device_data(peer, p);
- if (WARN_ON_ONCE(!peer_pdd))
- continue;
- kfd_flush_tlb(peer_pdd, TLB_FLUSH_LEGACY);
- }
+ for (i = 0; i < args->n_devices; i++) {
+ peer = kfd_device_by_id(devices_arr[i]);
+ if (WARN_ON_ONCE(!peer))
+ continue;
+ peer_pdd = kfd_get_process_device_data(peer, p);
+ if (WARN_ON_ONCE(!peer_pdd))
+ continue;
+ kfd_flush_tlb(peer_pdd, TLB_FLUSH_LEGACY);
}
+
kfree(devices_arr);
return err;
}
args->n_success = i+1;
}
- mutex_unlock(&p->mutex);
-
- err = amdgpu_amdkfd_gpuvm_sync_memory(dev->kgd, (struct kgd_mem *) mem, true);
- if (err) {
- pr_debug("Sync memory failed, wait interrupted by user signal\n");
- goto sync_memory_failed;
- }
-
- /* Flush TLBs after waiting for the page table updates to complete */
- for (i = 0; i < args->n_devices; i++) {
- peer = kfd_device_by_id(devices_arr[i]);
- if (WARN_ON_ONCE(!peer))
- continue;
- peer_pdd = kfd_get_process_device_data(peer, p);
- if (WARN_ON_ONCE(!peer_pdd))
- continue;
- kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT);
- }
-
kfree(devices_arr);
+ mutex_unlock(&p->mutex);
+
return 0;
bind_process_to_device_failed:
unmap_memory_from_gpu_failed:
mutex_unlock(&p->mutex);
copy_from_user_failed:
-sync_memory_failed:
kfree(devices_arr);
return err;
}
if (err)
goto err_alloc_mem;
- err = amdgpu_amdkfd_gpuvm_map_memory_to_gpu(kdev->kgd, mem,
- pdd->drm_priv, NULL);
+ err = amdgpu_amdkfd_gpuvm_map_memory_to_gpu(kdev->kgd, mem, pdd->drm_priv);
if (err)
goto err_map_mem;
static void
svm_range_count_fault(struct amdgpu_device *adev, struct kfd_process *p,
- struct svm_range *prange, int32_t gpuidx)
+ int32_t gpuidx)
{
struct kfd_process_device *pdd;
- if (gpuidx == MAX_GPU_INSTANCE)
- /* fault is on different page of same range
- * or fault is skipped to recover later
- */
- pdd = svm_range_get_pdd_by_adev(prange, adev);
- else
- /* fault recovered
- * or fault cannot recover because GPU no access on the range
- */
- pdd = kfd_process_device_from_gpuidx(p, gpuidx);
+ /* fault is on different page of same range
+ * or fault is skipped to recover later
+ * or fault is on invalid virtual address
+ */
+ if (gpuidx == MAX_GPU_INSTANCE) {
+ uint32_t gpuid;
+ int r;
+ r = kfd_process_gpuid_from_kgd(p, adev, &gpuid, &gpuidx);
+ if (r < 0)
+ return;
+ }
+
+ /* fault is recovered
+ * or fault cannot recover because GPU no access on the range
+ */
+ pdd = kfd_process_device_from_gpuidx(p, gpuidx);
if (pdd)
WRITE_ONCE(pdd->faults, pdd->faults + 1);
}
mutex_unlock(&svms->lock);
mmap_read_unlock(mm);
- svm_range_count_fault(adev, p, prange, gpuidx);
+ svm_range_count_fault(adev, p, gpuidx);
mmput(mm);
out:
}
hdr = (const struct dmcub_firmware_header_v1_0 *)adev->dm.dmub_fw->data;
+ adev->dm.dmcub_fw_version = le32_to_cpu(hdr->header.ucode_version);
if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
adev->firmware.ucode[AMDGPU_UCODE_ID_DMCUB].ucode_id =
adev->dm.dmcub_fw_version);
}
- adev->dm.dmcub_fw_version = le32_to_cpu(hdr->header.ucode_version);
adev->dm.dmub_srv = kzalloc(sizeof(*adev->dm.dmub_srv), GFP_KERNEL);
dmub_srv = adev->dm.dmub_srv;
max_cll = conn_base->hdr_sink_metadata.hdmi_type1.max_cll;
min_cll = conn_base->hdr_sink_metadata.hdmi_type1.min_cll;
- if (caps->ext_caps->bits.oled == 1 ||
+ if (caps->ext_caps->bits.oled == 1 /*||
caps->ext_caps->bits.sdr_aux_backlight_control == 1 ||
- caps->ext_caps->bits.hdr_aux_backlight_control == 1)
+ caps->ext_caps->bits.hdr_aux_backlight_control == 1*/)
caps->aux_support = true;
if (amdgpu_backlight == 0)
#if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) || \
defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE)
/* restore the backlight level */
- if (dm->backlight_dev)
+ if (dm->backlight_dev && (amdgpu_dm_backlight_get_level(dm) != dm->brightness[0]))
amdgpu_dm_backlight_set_level(dm, dm->brightness[0]);
#endif
/*
REG_UPDATE(DENTIST_DISPCLK_CNTL,
DENTIST_DISPCLK_WDIVIDER, dispclk_wdivider);
-// REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, 1, 5, 100);
+ REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, 1, 50, 1000);
REG_UPDATE(DENTIST_DISPCLK_CNTL,
DENTIST_DPPCLK_WDIVIDER, dppclk_wdivider);
REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DPPCLK_CHG_DONE, 1, 5, 100);
for (i = 0; i < context->stream_count; i++) {
const struct dc_stream_state *stream = context->streams[i];
+ /* Extend the WA to DP for Linux*/
if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A ||
stream->signal == SIGNAL_TYPE_DVI_SINGLE_LINK ||
- stream->signal == SIGNAL_TYPE_DVI_DUAL_LINK)
+ stream->signal == SIGNAL_TYPE_DVI_DUAL_LINK ||
+ stream->signal == SIGNAL_TYPE_DISPLAY_PORT)
tmds_present = true;
}
&clk_mgr_base->bw_params->clk_table.entries[0].dtbclk_mhz,
&num_levels);
+ /* SOCCLK */
+ dcn3_init_single_clock(clk_mgr, PPCLK_SOCCLK,
+ &clk_mgr_base->bw_params->clk_table.entries[0].socclk_mhz,
+ &num_levels);
// DPREFCLK ???
/* DISPCLK */
#include "dc_dmub_srv.h"
+#include "yellow_carp_offset.h"
+
+#define regCLK1_CLK_PLL_REQ 0x0237
+#define regCLK1_CLK_PLL_REQ_BASE_IDX 0
+
+#define CLK1_CLK_PLL_REQ__FbMult_int__SHIFT 0x0
+#define CLK1_CLK_PLL_REQ__PllSpineDiv__SHIFT 0xc
+#define CLK1_CLK_PLL_REQ__FbMult_frac__SHIFT 0x10
+#define CLK1_CLK_PLL_REQ__FbMult_int_MASK 0x000001FFL
+#define CLK1_CLK_PLL_REQ__PllSpineDiv_MASK 0x0000F000L
+#define CLK1_CLK_PLL_REQ__FbMult_frac_MASK 0xFFFF0000L
+
+#define REG(reg_name) \
+ (CLK_BASE.instance[0].segment[reg ## reg_name ## _BASE_IDX] + reg ## reg_name)
+
#define TO_CLK_MGR_DCN31(clk_mgr)\
container_of(clk_mgr, struct clk_mgr_dcn31, base)
* also if safe to lower is false, we just go in the higher state
*/
if (safe_to_lower) {
- if (new_clocks->z9_support == DCN_Z9_SUPPORT_ALLOW &&
- new_clocks->z9_support != clk_mgr_base->clks.z9_support) {
+ if (new_clocks->zstate_support == DCN_ZSTATE_SUPPORT_ALLOW &&
+ new_clocks->zstate_support != clk_mgr_base->clks.zstate_support) {
dcn31_smu_set_Z9_support(clk_mgr, true);
- clk_mgr_base->clks.z9_support = new_clocks->z9_support;
+ clk_mgr_base->clks.zstate_support = new_clocks->zstate_support;
}
if (clk_mgr_base->clks.dtbclk_en && !new_clocks->dtbclk_en) {
}
}
} else {
- if (new_clocks->z9_support == DCN_Z9_SUPPORT_DISALLOW &&
- new_clocks->z9_support != clk_mgr_base->clks.z9_support) {
+ if (new_clocks->zstate_support == DCN_ZSTATE_SUPPORT_DISALLOW &&
+ new_clocks->zstate_support != clk_mgr_base->clks.zstate_support) {
dcn31_smu_set_Z9_support(clk_mgr, false);
- clk_mgr_base->clks.z9_support = new_clocks->z9_support;
+ clk_mgr_base->clks.zstate_support = new_clocks->zstate_support;
}
if (!clk_mgr_base->clks.dtbclk_en && new_clocks->dtbclk_en) {
static int get_vco_frequency_from_reg(struct clk_mgr_internal *clk_mgr)
{
- return 0;
+ /* get FbMult value */
+ struct fixed31_32 pll_req;
+ unsigned int fbmult_frac_val = 0;
+ unsigned int fbmult_int_val = 0;
+
+ /*
+ * Register value of fbmult is in 8.16 format, we are converting to 31.32
+ * to leverage the fix point operations available in driver
+ */
+
+ REG_GET(CLK1_CLK_PLL_REQ, FbMult_frac, &fbmult_frac_val); /* 16 bit fractional part*/
+ REG_GET(CLK1_CLK_PLL_REQ, FbMult_int, &fbmult_int_val); /* 8 bit integer part */
+
+ pll_req = dc_fixpt_from_int(fbmult_int_val);
+
+ /*
+ * since fractional part is only 16 bit in register definition but is 32 bit
+ * in our fix point definiton, need to shift left by 16 to obtain correct value
+ */
+ pll_req.value |= fbmult_frac_val << 16;
+
+ /* multiply by REFCLK period */
+ pll_req = dc_fixpt_mul_int(pll_req, clk_mgr->dfs_ref_freq_khz);
+
+ /* integer part is now VCO frequency in kHz */
+ return dc_fixpt_floor(pll_req);
}
static void dcn31_enable_pme_wa(struct clk_mgr *clk_mgr_base)
clk_mgr->clks.p_state_change_support = true;
clk_mgr->clks.prev_p_state_change_support = true;
clk_mgr->clks.pwr_state = DCN_PWR_STATE_UNKNOWN;
- clk_mgr->clks.z9_support = DCN_Z9_SUPPORT_UNKNOWN;
+ clk_mgr->clks.zstate_support = DCN_ZSTATE_SUPPORT_UNKNOWN;
}
static bool dcn31_are_clock_states_equal(struct dc_clocks *a,
return false;
else if (a->dcfclk_deep_sleep_khz != b->dcfclk_deep_sleep_khz)
return false;
- else if (a->z9_support != b->z9_support)
+ else if (a->zstate_support != b->zstate_support)
return false;
else if (a->dtbclk_en != b->dtbclk_en)
return false;
clk_mgr->base.dprefclk_ss_percentage = 0;
clk_mgr->base.dprefclk_ss_divider = 1000;
clk_mgr->base.ss_on_dprefclk = false;
+ clk_mgr->base.dfs_ref_freq_khz = 48000;
clk_mgr->smu_wm_set.wm_set = (struct dcn31_watermarks *)dm_helpers_allocate_gpu_mem(
clk_mgr->base.base.ctx,
#define __DCN31_CLK_MGR_H__
#include "clk_mgr_internal.h"
-//CLK1_CLK_PLL_REQ
-#ifndef CLK11_CLK1_CLK_PLL_REQ__FbMult_int__SHIFT
-#define CLK11_CLK1_CLK_PLL_REQ__FbMult_int__SHIFT 0x0
-#define CLK11_CLK1_CLK_PLL_REQ__PllSpineDiv__SHIFT 0xc
-#define CLK11_CLK1_CLK_PLL_REQ__FbMult_frac__SHIFT 0x10
-#define CLK11_CLK1_CLK_PLL_REQ__FbMult_int_MASK 0x000001FFL
-#define CLK11_CLK1_CLK_PLL_REQ__PllSpineDiv_MASK 0x0000F000L
-#define CLK11_CLK1_CLK_PLL_REQ__FbMult_frac_MASK 0xFFFF0000L
-//CLK1_CLK0_DFS_CNTL
-#define CLK11_CLK1_CLK0_DFS_CNTL__CLK0_DIVIDER__SHIFT 0x0
-#define CLK11_CLK1_CLK0_DFS_CNTL__CLK0_DIVIDER_MASK 0x0000007FL
-/*DPREF clock related*/
-#define CLK0_CLK3_DFS_CNTL__CLK3_DIVIDER__SHIFT 0x0
-#define CLK0_CLK3_DFS_CNTL__CLK3_DIVIDER_MASK 0x0000007FL
-#define CLK1_CLK3_DFS_CNTL__CLK3_DIVIDER__SHIFT 0x0
-#define CLK1_CLK3_DFS_CNTL__CLK3_DIVIDER_MASK 0x0000007FL
-#define CLK2_CLK3_DFS_CNTL__CLK3_DIVIDER__SHIFT 0x0
-#define CLK2_CLK3_DFS_CNTL__CLK3_DIVIDER_MASK 0x0000007FL
-#define CLK3_CLK3_DFS_CNTL__CLK3_DIVIDER__SHIFT 0x0
-#define CLK3_CLK3_DFS_CNTL__CLK3_DIVIDER_MASK 0x0000007FL
-
-//CLK3_0_CLK3_CLK_PLL_REQ
-#define CLK3_0_CLK3_CLK_PLL_REQ__FbMult_int__SHIFT 0x0
-#define CLK3_0_CLK3_CLK_PLL_REQ__PllSpineDiv__SHIFT 0xc
-#define CLK3_0_CLK3_CLK_PLL_REQ__FbMult_frac__SHIFT 0x10
-#define CLK3_0_CLK3_CLK_PLL_REQ__FbMult_int_MASK 0x000001FFL
-#define CLK3_0_CLK3_CLK_PLL_REQ__PllSpineDiv_MASK 0x0000F000L
-#define CLK3_0_CLK3_CLK_PLL_REQ__FbMult_frac_MASK 0xFFFF0000L
-
-#define mmCLK0_CLK3_DFS_CNTL 0x16C60
-#define mmCLK00_CLK0_CLK3_DFS_CNTL 0x16C60
-#define mmCLK01_CLK0_CLK3_DFS_CNTL 0x16E60
-#define mmCLK02_CLK0_CLK3_DFS_CNTL 0x17060
-#define mmCLK03_CLK0_CLK3_DFS_CNTL 0x17260
-
-#define mmCLK0_CLK_PLL_REQ 0x16C10
-#define mmCLK00_CLK0_CLK_PLL_REQ 0x16C10
-#define mmCLK01_CLK0_CLK_PLL_REQ 0x16E10
-#define mmCLK02_CLK0_CLK_PLL_REQ 0x17010
-#define mmCLK03_CLK0_CLK_PLL_REQ 0x17210
-
-#define mmCLK1_CLK_PLL_REQ 0x1B00D
-#define mmCLK10_CLK1_CLK_PLL_REQ 0x1B00D
-#define mmCLK11_CLK1_CLK_PLL_REQ 0x1B20D
-#define mmCLK12_CLK1_CLK_PLL_REQ 0x1B40D
-#define mmCLK13_CLK1_CLK_PLL_REQ 0x1B60D
-
-#define mmCLK2_CLK_PLL_REQ 0x17E0D
-
-/*AMCLK*/
-#define mmCLK11_CLK1_CLK0_DFS_CNTL 0x1B23F
-#define mmCLK11_CLK1_CLK_PLL_REQ 0x1B20D
-#endif
-
struct dcn31_watermarks;
struct dcn31_smu_watermark_set {
#include "dcn31_smu.h"
#include "yellow_carp_offset.h"
-#include "mp/mp_13_0_1_offset.h"
-#include "mp/mp_13_0_1_sh_mask.h"
+#include "mp/mp_13_0_2_offset.h"
+#include "mp/mp_13_0_2_sh_mask.h"
#define REG(reg_name) \
(MP0_BASE.instance[0].segment[reg ## reg_name ## _BASE_IDX] + reg ## reg_name)
{
enum dc_status status = DC_OK;
- if (lt_settings->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT)
- status = configure_lttpr_mode_non_transparent(link, lt_settings);
- else
+ if (lt_settings->lttpr_mode == LTTPR_MODE_TRANSPARENT)
status = configure_lttpr_mode_transparent(link);
+ else if (lt_settings->lttpr_mode == LTTPR_MODE_NON_TRANSPARENT)
+ status = configure_lttpr_mode_non_transparent(link, lt_settings);
+
return status;
}
link_enc = stream->link_enc;
else
link_enc = link->link_enc;
- ASSERT(link_enc);
/* We need to do this before the link training to ensure the idle pattern in SST
* mode will be sent right after the link training
*/
panel_mode = DP_PANEL_MODE_DEFAULT;
}
- } else
- panel_mode = DP_PANEL_MODE_DEFAULT;
+ }
}
#endif
bool dp_retrieve_lttpr_cap(struct dc_link *link)
{
uint8_t lttpr_dpcd_data[6];
- bool vbios_lttpr_enable = false;
- bool vbios_lttpr_interop = false;
- struct dc_bios *bios = link->dc->ctx->dc_bios;
+ bool vbios_lttpr_enable = link->dc->caps.vbios_lttpr_enable;
+ bool vbios_lttpr_interop = link->dc->caps.vbios_lttpr_aware;
enum dc_status status = DC_ERROR_UNEXPECTED;
bool is_lttpr_present = false;
memset(lttpr_dpcd_data, '\0', sizeof(lttpr_dpcd_data));
- /* Query BIOS to determine if LTTPR functionality is forced on by system */
- if (bios->funcs->get_lttpr_caps) {
- enum bp_result bp_query_result;
- uint8_t is_vbios_lttpr_enable = 0;
-
- bp_query_result = bios->funcs->get_lttpr_caps(bios, &is_vbios_lttpr_enable);
- vbios_lttpr_enable = (bp_query_result == BP_RESULT_OK) && !!is_vbios_lttpr_enable;
- }
-
- if (bios->funcs->get_lttpr_interop) {
- enum bp_result bp_query_result;
- uint8_t is_vbios_interop_enabled = 0;
-
- bp_query_result = bios->funcs->get_lttpr_interop(bios, &is_vbios_interop_enabled);
- vbios_lttpr_interop = (bp_query_result == BP_RESULT_OK) && !!is_vbios_interop_enabled;
- }
/*
* Logic to determine LTTPR mode
}
}
- if (link->dpcd_caps.panel_mode_edp) {
+ if (link->dpcd_caps.panel_mode_edp &&
+ (link->connector_signal == SIGNAL_TYPE_EDP ||
+ (link->connector_signal == SIGNAL_TYPE_DISPLAY_PORT &&
+ link->is_internal_display))) {
return DP_PANEL_MODE_EDP;
}
{
uint32_t default_backlight;
- if (link &&
- (link->dpcd_sink_ext_caps.bits.hdr_aux_backlight_control == 1 ||
- link->dpcd_sink_ext_caps.bits.sdr_aux_backlight_control == 1)) {
+ if (link && link->dpcd_sink_ext_caps.bits.oled == 1) {
if (!dc_link_read_default_bl_aux(link, &default_backlight))
default_backlight = 150000;
// if < 5 nits or > 5000, it might be wrong readback
* so use only 30 bpp on DCE_VERSION_11_0. Testing with DCE 11.2 and 8.3
* did not show such problems, so this seems to be the exception.
*/
- if (plane_state->ctx->dce_version != DCE_VERSION_11_0)
+ if (plane_state->ctx->dce_version > DCE_VERSION_11_0)
pipe_ctx->plane_res.scl_data.lb_params.depth = LB_PIXEL_DEPTH_36BPP;
else
pipe_ctx->plane_res.scl_data.lb_params.depth = LB_PIXEL_DEPTH_30BPP;
unsigned int cursor_cache_size;
struct dc_plane_cap planes[MAX_PLANES];
struct dc_color_caps color;
+ bool vbios_lttpr_aware;
+ bool vbios_lttpr_enable;
};
struct dc_bug_wa {
};
#if defined(CONFIG_DRM_AMD_DC_DCN)
-enum dcn_z9_support_state {
- DCN_Z9_SUPPORT_UNKNOWN,
- DCN_Z9_SUPPORT_ALLOW,
- DCN_Z9_SUPPORT_DISALLOW,
+enum dcn_zstate_support_state {
+ DCN_ZSTATE_SUPPORT_UNKNOWN,
+ DCN_ZSTATE_SUPPORT_ALLOW,
+ DCN_ZSTATE_SUPPORT_DISALLOW,
};
#endif
/*
int dramclk_khz;
bool p_state_change_support;
#if defined(CONFIG_DRM_AMD_DC_DCN)
- enum dcn_z9_support_state z9_support;
+ enum dcn_zstate_support_state zstate_support;
bool dtbclk_en;
#endif
enum dcn_pwr_state pwr_state;
uint32_t ODM_MEM_PWR_CTRL3;
uint32_t DMU_MEM_PWR_CNTL;
uint32_t MMHUBBUB_MEM_PWR_CNTL;
+ uint32_t DCHUBBUB_ARB_HOSTVM_CNTL;
};
/* set field name */
#define HWS_SF(blk_name, reg_name, field_name, post_fix)\
type DOMAIN_POWER_FORCEON;\
type DOMAIN_POWER_GATE;\
type DOMAIN_PGFSM_PWR_STATUS;\
- type HPO_HDMISTREAMCLK_G_GATE_DIS;
+ type HPO_HDMISTREAMCLK_G_GATE_DIS;\
+ type DISABLE_HOSTVM_FORCE_ALLOW_PSTATE;
struct dce_hwseq_shift {
HWSEQ_REG_FIELD_LIST(uint8_t)
const struct line_buffer_params *lb_params,
enum lb_memory_config mem_size_config)
{
+ uint32_t max_partitions = 63; /* Currently hardcoded on all ASICs before DCN 3.2 */
+
/* LB */
if (dpp->base.caps->dscl_data_proc_format == DSCL_DATA_PRCESSING_FIXED_FORMAT) {
/* DSCL caps: pixel data processed in fixed format */
LB_DATA_FORMAT__ALPHA_EN, lb_params->alpha_en); /* Alpha enable */
}
+ if (dpp->base.caps->max_lb_partitions == 31)
+ max_partitions = 31;
+
REG_SET_2(LB_MEMORY_CTRL, 0,
MEMORY_CONFIG, mem_size_config,
- LB_MAX_PARTITIONS, 63);
+ LB_MAX_PARTITIONS, max_partitions);
}
static const uint16_t *dpp1_dscl_get_filter_coeffs_64p(int taps, struct fixed31_32 ratio)
REG_UPDATE_2(OTG_GLOBAL_CONTROL1,
MASTER_UPDATE_LOCK_DB_X,
- h_blank_start - 200 - 1,
+ (h_blank_start - 200 - 1) / optc1->opp_count,
MASTER_UPDATE_LOCK_DB_Y,
v_blank_start - 1);
}
- timing->v_border_bottom;
pipes[pipe_cnt].pipe.dest.htotal = timing->h_total;
pipes[pipe_cnt].pipe.dest.vtotal = v_total;
- pipes[pipe_cnt].pipe.dest.hactive = timing->h_addressable;
- pipes[pipe_cnt].pipe.dest.vactive = timing->v_addressable;
+ pipes[pipe_cnt].pipe.dest.hactive =
+ timing->h_addressable + timing->h_border_left + timing->h_border_right;
+ pipes[pipe_cnt].pipe.dest.vactive =
+ timing->v_addressable + timing->v_border_top + timing->v_border_bottom;
pipes[pipe_cnt].pipe.dest.interlaced = timing->flags.INTERLACE;
pipes[pipe_cnt].pipe.dest.pixel_rate_mhz = timing->pix_clk_100hz/10000.0;
if (timing->timing_3d_format == TIMING_3D_FORMAT_HW_FRAME_PACKING)
return false;
}
+static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struct dc_state *context)
+{
+ int plane_count;
+ int i;
+
+ plane_count = 0;
+ for (i = 0; i < dc->res_pool->pipe_count; i++) {
+ if (context->res_ctx.pipe_ctx[i].plane_state)
+ plane_count++;
+ }
+
+ /*
+ * Zstate is allowed in following scenarios:
+ * 1. Single eDP with PSR enabled
+ * 2. 0 planes (No memory requests)
+ * 3. Single eDP without PSR but > 5ms stutter period
+ */
+ if (plane_count == 0)
+ return DCN_ZSTATE_SUPPORT_ALLOW;
+ else if (context->stream_count == 1 && context->streams[0]->signal == SIGNAL_TYPE_EDP) {
+ struct dc_link *link = context->streams[0]->sink->link;
+
+ if ((link->link_index == 0 && link->psr_settings.psr_feature_enabled)
+ || context->bw_ctx.dml.vba.StutterPeriod > 5000.0)
+ return DCN_ZSTATE_SUPPORT_ALLOW;
+ else
+ return DCN_ZSTATE_SUPPORT_DISALLOW;
+ } else
+ return DCN_ZSTATE_SUPPORT_DISALLOW;
+}
+
void dcn20_calculate_dlg_params(
struct dc *dc, struct dc_state *context,
display_e2e_pipe_params_st *pipes,
int vlevel)
{
int i, pipe_idx;
- int plane_count;
/* Writeback MCIF_WB arbitration parameters */
dc->res_pool->funcs->set_mcif_arb_params(dc, context, pipes, pipe_cnt);
!= dm_dram_clock_change_unsupported;
context->bw_ctx.bw.dcn.clk.dppclk_khz = 0;
- context->bw_ctx.bw.dcn.clk.z9_support = (context->bw_ctx.dml.vba.StutterPeriod > 5000.0) ?
- DCN_Z9_SUPPORT_ALLOW : DCN_Z9_SUPPORT_DISALLOW;
-
- plane_count = 0;
- for (i = 0; i < dc->res_pool->pipe_count; i++) {
- if (context->res_ctx.pipe_ctx[i].plane_state)
- plane_count++;
- }
-
- if (plane_count == 0)
- context->bw_ctx.bw.dcn.clk.z9_support = DCN_Z9_SUPPORT_ALLOW;
+ context->bw_ctx.bw.dcn.clk.zstate_support = decide_zstate_support(dc, context);
context->bw_ctx.bw.dcn.clk.dtbclk_en = is_dtbclk_required(dc, context);
.max_page_table_levels = 4,
.pte_chunk_size_kbytes = 2,
.meta_chunk_size_kbytes = 2,
+ .min_meta_chunk_size_bytes = 256,
.writeback_chunk_size_kbytes = 2,
.line_buffer_size_bits = 789504,
.is_line_buffer_bpp_fixed = 0,
int min_taps_y, min_taps_c;
enum lb_memory_config lb_config;
- /* Some ASICs does not support FP16 scaling, so we reject modes require this*/
- if (scl_data->viewport.width != scl_data->h_active &&
- scl_data->viewport.height != scl_data->v_active &&
- dpp->caps->dscl_data_proc_format == DSCL_DATA_PRCESSING_FIXED_FORMAT &&
- scl_data->format == PIXEL_FORMAT_FP16)
- return false;
-
if (scl_data->viewport.width > scl_data->h_active &&
dpp->ctx->dc->debug.max_downscale_src_width != 0 &&
scl_data->viewport.width > dpp->ctx->dc->debug.max_downscale_src_width)
dpp->tf_shift = tf_shift;
dpp->tf_mask = tf_mask;
- dpp->lb_pixel_depth_supported =
- LB_PIXEL_DEPTH_18BPP |
- LB_PIXEL_DEPTH_24BPP |
- LB_PIXEL_DEPTH_30BPP |
- LB_PIXEL_DEPTH_36BPP;
-
- dpp->lb_bits_per_entry = LB_BITS_PER_ENTRY;
- dpp->lb_memory_size = LB_TOTAL_NUMBER_OF_ENTRIES; /*0x1404*/
-
return true;
}
SRI(COLOR_KEYER_BLUE, CNVC_CFG, id), \
SRI(CURSOR_CONTROL, CURSOR0_, id),\
SRI(OBUF_MEM_PWR_CTRL, DSCL, id),\
+ SRI(DSCL_MEM_PWR_STATUS, DSCL, id), \
SRI(DSCL_MEM_PWR_CTRL, DSCL, id)
#define DPP_REG_LIST_DCN30(id)\
SRI(CM_SHAPER_LUT_DATA, CM, id),\
SRI(CM_MEM_PWR_CTRL2, CM, id), \
SRI(CM_MEM_PWR_STATUS2, CM, id), \
- SRI(DSCL_MEM_PWR_STATUS, DSCL, id), \
- SRI(DSCL_MEM_PWR_CTRL, DSCL, id), \
SRI(CM_BLNDGAM_RAMA_START_SLOPE_CNTL_B, CM, id),\
SRI(CM_BLNDGAM_RAMA_START_SLOPE_CNTL_G, CM, id),\
SRI(CM_BLNDGAM_RAMA_START_SLOPE_CNTL_R, CM, id),\
dc->caps.color.mpc.ogam_rom_caps.hlg = 0;
dc->caps.color.mpc.ocsc = 1;
+ /* read VBIOS LTTPR caps */
+ {
+ if (ctx->dc_bios->funcs->get_lttpr_caps) {
+ enum bp_result bp_query_result;
+ uint8_t is_vbios_lttpr_enable = 0;
+
+ bp_query_result = ctx->dc_bios->funcs->get_lttpr_caps(ctx->dc_bios, &is_vbios_lttpr_enable);
+ dc->caps.vbios_lttpr_enable = (bp_query_result == BP_RESULT_OK) && !!is_vbios_lttpr_enable;
+ }
+
+ if (ctx->dc_bios->funcs->get_lttpr_interop) {
+ enum bp_result bp_query_result;
+ uint8_t is_vbios_interop_enabled = 0;
+
+ bp_query_result = ctx->dc_bios->funcs->get_lttpr_interop(ctx->dc_bios,
+ &is_vbios_interop_enabled);
+ dc->caps.vbios_lttpr_aware = (bp_query_result == BP_RESULT_OK) && !!is_vbios_interop_enabled;
+ }
+ }
+
if (dc->ctx->dce_environment == DCE_ENV_PRODUCTION_DRV)
dc->debug = debug_defaults_drv;
else if (dc->ctx->dce_environment == DCE_ENV_FPGA_MAXIMUS) {
dcn3_02_soc.clock_limits[i].dispclk_mhz = max_dispclk_mhz;
dcn3_02_soc.clock_limits[i].dppclk_mhz = max_dppclk_mhz;
dcn3_02_soc.clock_limits[i].phyclk_mhz = max_phyclk_mhz;
- dcn3_02_soc.clock_limits[i].dtbclk_mhz = dcn3_02_soc.clock_limits[0].dtbclk_mhz;
+ /* Populate from bw_params for DTBCLK, SOCCLK */
+ if (!bw_params->clk_table.entries[i].dtbclk_mhz && i > 0)
+ dcn3_02_soc.clock_limits[i].dtbclk_mhz = dcn3_02_soc.clock_limits[i-1].dtbclk_mhz;
+ else
+ dcn3_02_soc.clock_limits[i].dtbclk_mhz = bw_params->clk_table.entries[i].dtbclk_mhz;
+ if (!bw_params->clk_table.entries[i].socclk_mhz && i > 0)
+ dcn3_02_soc.clock_limits[i].socclk_mhz = dcn3_02_soc.clock_limits[i-1].socclk_mhz;
+ else
+ dcn3_02_soc.clock_limits[i].socclk_mhz = bw_params->clk_table.entries[i].socclk_mhz;
/* These clocks cannot come from bw_params, always fill from dcn3_02_soc[1] */
- /* FCLK, PHYCLK_D18, SOCCLK, DSCCLK */
+ /* FCLK, PHYCLK_D18, DSCCLK */
dcn3_02_soc.clock_limits[i].phyclk_d18_mhz = dcn3_02_soc.clock_limits[0].phyclk_d18_mhz;
- dcn3_02_soc.clock_limits[i].socclk_mhz = dcn3_02_soc.clock_limits[0].socclk_mhz;
dcn3_02_soc.clock_limits[i].dscclk_mhz = dcn3_02_soc.clock_limits[0].dscclk_mhz;
}
/* re-init DML with updated bb */
.min_dcfclk = 500.0, /* TODO: set this to actual min DCFCLK */
.num_states = 1,
- .sr_exit_time_us = 26.5,
- .sr_enter_plus_exit_time_us = 31,
+ .sr_exit_time_us = 35.5,
+ .sr_enter_plus_exit_time_us = 40,
.urgent_latency_us = 4.0,
.urgent_latency_pixel_data_only_us = 4.0,
.urgent_latency_pixel_mixed_with_vm_data_us = 4.0,
dcn3_03_soc.clock_limits[i].dispclk_mhz = max_dispclk_mhz;
dcn3_03_soc.clock_limits[i].dppclk_mhz = max_dppclk_mhz;
dcn3_03_soc.clock_limits[i].phyclk_mhz = max_phyclk_mhz;
- dcn3_03_soc.clock_limits[i].dtbclk_mhz = dcn3_03_soc.clock_limits[0].dtbclk_mhz;
+ /* Populate from bw_params for DTBCLK, SOCCLK */
+ if (!bw_params->clk_table.entries[i].dtbclk_mhz && i > 0)
+ dcn3_03_soc.clock_limits[i].dtbclk_mhz = dcn3_03_soc.clock_limits[i-1].dtbclk_mhz;
+ else
+ dcn3_03_soc.clock_limits[i].dtbclk_mhz = bw_params->clk_table.entries[i].dtbclk_mhz;
+ if (!bw_params->clk_table.entries[i].socclk_mhz && i > 0)
+ dcn3_03_soc.clock_limits[i].socclk_mhz = dcn3_03_soc.clock_limits[i-1].socclk_mhz;
+ else
+ dcn3_03_soc.clock_limits[i].socclk_mhz = bw_params->clk_table.entries[i].socclk_mhz;
/* These clocks cannot come from bw_params, always fill from dcn3_03_soc[1] */
- /* FCLK, PHYCLK_D18, SOCCLK, DSCCLK */
+ /* FCLK, PHYCLK_D18, DSCCLK */
dcn3_03_soc.clock_limits[i].phyclk_d18_mhz = dcn3_03_soc.clock_limits[0].phyclk_d18_mhz;
- dcn3_03_soc.clock_limits[i].socclk_mhz = dcn3_03_soc.clock_limits[0].socclk_mhz;
dcn3_03_soc.clock_limits[i].dscclk_mhz = dcn3_03_soc.clock_limits[0].dscclk_mhz;
}
/* re-init DML with updated bb */
#include "dce/dmub_outbox.h"
#include "dc_link_dp.h"
#include "inc/link_dpcd.h"
+#include "dcn10/dcn10_hw_sequencer.h"
#define DC_LOGGER_INIT(logger)
is_hdmi_tmds = dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal);
is_dp = dc_is_dp_signal(pipe_ctx->stream->signal);
- if (!is_hdmi_tmds)
+ if (!is_hdmi_tmds && !is_dp)
return;
if (is_hdmi_tmds)
}
return false;
}
+
+static void apply_riommu_invalidation_wa(struct dc *dc)
+{
+ struct dce_hwseq *hws = dc->hwseq;
+
+ if (!hws->wa.early_riommu_invalidation)
+ return;
+
+ REG_UPDATE(DCHUBBUB_ARB_HOSTVM_CNTL, DISABLE_HOSTVM_FORCE_ALLOW_PSTATE, 0);
+}
+
+void dcn31_init_pipes(struct dc *dc, struct dc_state *context)
+{
+ dcn10_init_pipes(dc, context);
+ apply_riommu_invalidation_wa(dc);
+
+}
struct dc_state *context);
bool dcn31_is_abm_supported(struct dc *dc,
struct dc_state *context, struct dc_stream_state *stream);
+void dcn31_init_pipes(struct dc *dc, struct dc_state *context);
#endif /* __DC_HWSS_DCN31_H__ */
.set_flip_control_gsl = dcn20_set_flip_control_gsl,
.get_vupdate_offset_from_vsync = dcn10_get_vupdate_offset_from_vsync,
.calc_vupdate_position = dcn10_calc_vupdate_position,
- .apply_idle_power_optimizations = dcn30_apply_idle_power_optimizations,
.set_backlight_level = dcn21_set_backlight_level,
.set_abm_immediate_disable = dcn21_set_abm_immediate_disable,
.set_pipe = dcn21_set_pipe,
};
static const struct hwseq_private_funcs dcn31_private_funcs = {
- .init_pipes = dcn10_init_pipes,
+ .init_pipes = dcn31_init_pipes,
.update_plane_addr = dcn20_update_plane_addr,
.plane_atomic_disconnect = dcn10_plane_atomic_disconnect,
.update_mpcc = dcn20_update_mpcc,
.sr_exit_z8_time_us = 402.0,
.sr_enter_plus_exit_z8_time_us = 520.0,
.writeback_latency_us = 12.0,
+ .dram_channel_width_bytes = 4,
.round_trip_ping_latency_dcfclk_cycles = 106,
.urgent_latency_pixel_data_only_us = 4.0,
.urgent_latency_pixel_mixed_with_vm_data_us = 4.0,
#define HWSEQ_DCN31_REG_LIST()\
SR(DCHUBBUB_GLOBAL_TIMER_CNTL), \
+ SR(DCHUBBUB_ARB_HOSTVM_CNTL), \
SR(DIO_MEM_PWR_CTRL), \
SR(ODM_MEM_PWR_CTRL3), \
SR(DMU_MEM_PWR_CNTL), \
#define HWSEQ_DCN31_MASK_SH_LIST(mask_sh)\
HWSEQ_DCN_MASK_SH_LIST(mask_sh), \
HWS_SF(, DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_REFDIV, mask_sh), \
+ HWS_SF(, DCHUBBUB_ARB_HOSTVM_CNTL, DISABLE_HOSTVM_FORCE_ALLOW_PSTATE, mask_sh), \
HWS_SF(, DOMAIN0_PG_CONFIG, DOMAIN_POWER_FORCEON, mask_sh), \
HWS_SF(, DOMAIN0_PG_CONFIG, DOMAIN_POWER_GATE, mask_sh), \
HWS_SF(, DOMAIN1_PG_CONFIG, DOMAIN_POWER_FORCEON, mask_sh), \
hws->regs = &hwseq_reg;
hws->shifts = &hwseq_shift;
hws->masks = &hwseq_mask;
+ hws->wa.early_riommu_invalidation = true;
}
return hws;
}
dc->caps.color.mpc.ogam_rom_caps.hlg = 0;
dc->caps.color.mpc.ocsc = 1;
+ /* read VBIOS LTTPR caps */
+ {
+ if (ctx->dc_bios->funcs->get_lttpr_caps) {
+ enum bp_result bp_query_result;
+ uint8_t is_vbios_lttpr_enable = 0;
+
+ bp_query_result = ctx->dc_bios->funcs->get_lttpr_caps(ctx->dc_bios, &is_vbios_lttpr_enable);
+ dc->caps.vbios_lttpr_enable = (bp_query_result == BP_RESULT_OK) && !!is_vbios_lttpr_enable;
+ }
+
+ /* interop bit is implicit */
+ {
+ dc->caps.vbios_lttpr_aware = true;
+ }
+ }
+
if (dc->ctx->dce_environment == DCE_ENV_PRODUCTION_DRV)
dc->debug = debug_defaults_drv;
else if (dc->ctx->dce_environment == DCE_ENV_FPGA_MAXIMUS) {
else
*DestinationLinesForPrefetch = dst_y_prefetch_equ;
+ // Limit to prevent overflow in DST_Y_PREFETCH register
+ *DestinationLinesForPrefetch = dml_min(*DestinationLinesForPrefetch, 63.75);
+
dml_print("DML: VStartup: %d\n", VStartup);
dml_print("DML: TCalc: %f\n", TCalc);
dml_print("DML: TWait: %f\n", TWait);
}
} while ((locals->PrefetchSupported[i][j] != true || locals->VRatioInPrefetchSupported[i][j] != true)
&& (mode_lib->vba.NextMaxVStartup != mode_lib->vba.MaxMaxVStartup[0][0]
- || mode_lib->vba.NextPrefetchMode < mode_lib->vba.MaxPrefetchMode));
+ || mode_lib->vba.NextPrefetchMode <= mode_lib->vba.MaxPrefetchMode));
if (locals->PrefetchSupported[i][j] == true && locals->VRatioInPrefetchSupported[i][j] == true) {
mode_lib->vba.BandwidthAvailableForImmediateFlip = locals->ReturnBWPerState[i][0];
/* DSCL processing pixel data in fixed or float format */
enum dscl_data_processing_format dscl_data_proc_format;
+ /* max LB partitions */
+ unsigned int max_lb_partitions;
+
/* Calculates the number of partitions in the line buffer.
* The implementation of this function is overloaded for
* different versions of DSCL LB.
bool DEGVIDCN10_254;
bool DEGVIDCN21;
bool disallow_self_refresh_during_multi_plane_transition;
+ bool early_riommu_invalidation;
};
struct hwseq_wa_state {
bool dmub_dcn31_is_hw_init(struct dmub_srv *dmub)
{
- uint32_t is_hw_init;
+ union dmub_fw_boot_status status;
+ uint32_t is_enable;
- REG_GET(DMCUB_CNTL, DMCUB_ENABLE, &is_hw_init);
+ status.all = REG_READ(DMCUB_SCRATCH0);
+ REG_GET(DMCUB_CNTL, DMCUB_ENABLE, &is_enable);
- return is_hw_init != 0;
+ return is_enable != 0 && status.bits.dal_fw;
}
bool dmub_dcn31_is_supported(struct dmub_srv *dmub)
+++ /dev/null
-/*
- * Copyright 2020 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- *
- */
-#ifndef _mp_13_0_1_OFFSET_HEADER
-#define _mp_13_0_1_OFFSET_HEADER
-
-
-
-// addressBlock: mp_SmuMp0_SmnDec
-// base address: 0x0
-#define regMP0_SMN_C2PMSG_32 0x0060
-#define regMP0_SMN_C2PMSG_32_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_33 0x0061
-#define regMP0_SMN_C2PMSG_33_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_34 0x0062
-#define regMP0_SMN_C2PMSG_34_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_35 0x0063
-#define regMP0_SMN_C2PMSG_35_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_36 0x0064
-#define regMP0_SMN_C2PMSG_36_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_37 0x0065
-#define regMP0_SMN_C2PMSG_37_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_38 0x0066
-#define regMP0_SMN_C2PMSG_38_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_39 0x0067
-#define regMP0_SMN_C2PMSG_39_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_40 0x0068
-#define regMP0_SMN_C2PMSG_40_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_41 0x0069
-#define regMP0_SMN_C2PMSG_41_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_42 0x006a
-#define regMP0_SMN_C2PMSG_42_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_43 0x006b
-#define regMP0_SMN_C2PMSG_43_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_44 0x006c
-#define regMP0_SMN_C2PMSG_44_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_45 0x006d
-#define regMP0_SMN_C2PMSG_45_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_46 0x006e
-#define regMP0_SMN_C2PMSG_46_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_47 0x006f
-#define regMP0_SMN_C2PMSG_47_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_48 0x0070
-#define regMP0_SMN_C2PMSG_48_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_49 0x0071
-#define regMP0_SMN_C2PMSG_49_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_50 0x0072
-#define regMP0_SMN_C2PMSG_50_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_51 0x0073
-#define regMP0_SMN_C2PMSG_51_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_52 0x0074
-#define regMP0_SMN_C2PMSG_52_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_53 0x0075
-#define regMP0_SMN_C2PMSG_53_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_54 0x0076
-#define regMP0_SMN_C2PMSG_54_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_55 0x0077
-#define regMP0_SMN_C2PMSG_55_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_56 0x0078
-#define regMP0_SMN_C2PMSG_56_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_57 0x0079
-#define regMP0_SMN_C2PMSG_57_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_58 0x007a
-#define regMP0_SMN_C2PMSG_58_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_59 0x007b
-#define regMP0_SMN_C2PMSG_59_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_60 0x007c
-#define regMP0_SMN_C2PMSG_60_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_61 0x007d
-#define regMP0_SMN_C2PMSG_61_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_62 0x007e
-#define regMP0_SMN_C2PMSG_62_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_63 0x007f
-#define regMP0_SMN_C2PMSG_63_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_64 0x0080
-#define regMP0_SMN_C2PMSG_64_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_65 0x0081
-#define regMP0_SMN_C2PMSG_65_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_66 0x0082
-#define regMP0_SMN_C2PMSG_66_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_67 0x0083
-#define regMP0_SMN_C2PMSG_67_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_68 0x0084
-#define regMP0_SMN_C2PMSG_68_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_69 0x0085
-#define regMP0_SMN_C2PMSG_69_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_70 0x0086
-#define regMP0_SMN_C2PMSG_70_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_71 0x0087
-#define regMP0_SMN_C2PMSG_71_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_72 0x0088
-#define regMP0_SMN_C2PMSG_72_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_73 0x0089
-#define regMP0_SMN_C2PMSG_73_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_74 0x008a
-#define regMP0_SMN_C2PMSG_74_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_75 0x008b
-#define regMP0_SMN_C2PMSG_75_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_76 0x008c
-#define regMP0_SMN_C2PMSG_76_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_77 0x008d
-#define regMP0_SMN_C2PMSG_77_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_78 0x008e
-#define regMP0_SMN_C2PMSG_78_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_79 0x008f
-#define regMP0_SMN_C2PMSG_79_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_80 0x0090
-#define regMP0_SMN_C2PMSG_80_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_81 0x0091
-#define regMP0_SMN_C2PMSG_81_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_82 0x0092
-#define regMP0_SMN_C2PMSG_82_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_83 0x0093
-#define regMP0_SMN_C2PMSG_83_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_84 0x0094
-#define regMP0_SMN_C2PMSG_84_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_85 0x0095
-#define regMP0_SMN_C2PMSG_85_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_86 0x0096
-#define regMP0_SMN_C2PMSG_86_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_87 0x0097
-#define regMP0_SMN_C2PMSG_87_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_88 0x0098
-#define regMP0_SMN_C2PMSG_88_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_89 0x0099
-#define regMP0_SMN_C2PMSG_89_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_90 0x009a
-#define regMP0_SMN_C2PMSG_90_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_91 0x009b
-#define regMP0_SMN_C2PMSG_91_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_92 0x009c
-#define regMP0_SMN_C2PMSG_92_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_93 0x009d
-#define regMP0_SMN_C2PMSG_93_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_94 0x009e
-#define regMP0_SMN_C2PMSG_94_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_95 0x009f
-#define regMP0_SMN_C2PMSG_95_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_96 0x00a0
-#define regMP0_SMN_C2PMSG_96_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_97 0x00a1
-#define regMP0_SMN_C2PMSG_97_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_98 0x00a2
-#define regMP0_SMN_C2PMSG_98_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_99 0x00a3
-#define regMP0_SMN_C2PMSG_99_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_100 0x00a4
-#define regMP0_SMN_C2PMSG_100_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_101 0x00a5
-#define regMP0_SMN_C2PMSG_101_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_102 0x00a6
-#define regMP0_SMN_C2PMSG_102_BASE_IDX 0
-#define regMP0_SMN_C2PMSG_103 0x00a7
-#define regMP0_SMN_C2PMSG_103_BASE_IDX 0
-#define regMP0_SMN_IH_CREDIT 0x00c1
-#define regMP0_SMN_IH_CREDIT_BASE_IDX 0
-#define regMP0_SMN_IH_SW_INT 0x00c2
-#define regMP0_SMN_IH_SW_INT_BASE_IDX 0
-#define regMP0_SMN_IH_SW_INT_CTRL 0x00c3
-#define regMP0_SMN_IH_SW_INT_CTRL_BASE_IDX 0
-
-
-// addressBlock: mp_SmuMp1_SmnDec
-// base address: 0x0
-#define regMP1_SMN_C2PMSG_32 0x0260
-#define regMP1_SMN_C2PMSG_32_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_33 0x0261
-#define regMP1_SMN_C2PMSG_33_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_34 0x0262
-#define regMP1_SMN_C2PMSG_34_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_35 0x0263
-#define regMP1_SMN_C2PMSG_35_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_36 0x0264
-#define regMP1_SMN_C2PMSG_36_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_37 0x0265
-#define regMP1_SMN_C2PMSG_37_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_38 0x0266
-#define regMP1_SMN_C2PMSG_38_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_39 0x0267
-#define regMP1_SMN_C2PMSG_39_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_40 0x0268
-#define regMP1_SMN_C2PMSG_40_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_41 0x0269
-#define regMP1_SMN_C2PMSG_41_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_42 0x026a
-#define regMP1_SMN_C2PMSG_42_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_43 0x026b
-#define regMP1_SMN_C2PMSG_43_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_44 0x026c
-#define regMP1_SMN_C2PMSG_44_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_45 0x026d
-#define regMP1_SMN_C2PMSG_45_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_46 0x026e
-#define regMP1_SMN_C2PMSG_46_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_47 0x026f
-#define regMP1_SMN_C2PMSG_47_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_48 0x0270
-#define regMP1_SMN_C2PMSG_48_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_49 0x0271
-#define regMP1_SMN_C2PMSG_49_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_50 0x0272
-#define regMP1_SMN_C2PMSG_50_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_51 0x0273
-#define regMP1_SMN_C2PMSG_51_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_52 0x0274
-#define regMP1_SMN_C2PMSG_52_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_53 0x0275
-#define regMP1_SMN_C2PMSG_53_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_54 0x0276
-#define regMP1_SMN_C2PMSG_54_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_55 0x0277
-#define regMP1_SMN_C2PMSG_55_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_56 0x0278
-#define regMP1_SMN_C2PMSG_56_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_57 0x0279
-#define regMP1_SMN_C2PMSG_57_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_58 0x027a
-#define regMP1_SMN_C2PMSG_58_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_59 0x027b
-#define regMP1_SMN_C2PMSG_59_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_60 0x027c
-#define regMP1_SMN_C2PMSG_60_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_61 0x027d
-#define regMP1_SMN_C2PMSG_61_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_62 0x027e
-#define regMP1_SMN_C2PMSG_62_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_63 0x027f
-#define regMP1_SMN_C2PMSG_63_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_64 0x0280
-#define regMP1_SMN_C2PMSG_64_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_65 0x0281
-#define regMP1_SMN_C2PMSG_65_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_66 0x0282
-#define regMP1_SMN_C2PMSG_66_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_67 0x0283
-#define regMP1_SMN_C2PMSG_67_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_68 0x0284
-#define regMP1_SMN_C2PMSG_68_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_69 0x0285
-#define regMP1_SMN_C2PMSG_69_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_70 0x0286
-#define regMP1_SMN_C2PMSG_70_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_71 0x0287
-#define regMP1_SMN_C2PMSG_71_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_72 0x0288
-#define regMP1_SMN_C2PMSG_72_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_73 0x0289
-#define regMP1_SMN_C2PMSG_73_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_74 0x028a
-#define regMP1_SMN_C2PMSG_74_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_75 0x028b
-#define regMP1_SMN_C2PMSG_75_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_76 0x028c
-#define regMP1_SMN_C2PMSG_76_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_77 0x028d
-#define regMP1_SMN_C2PMSG_77_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_78 0x028e
-#define regMP1_SMN_C2PMSG_78_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_79 0x028f
-#define regMP1_SMN_C2PMSG_79_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_80 0x0290
-#define regMP1_SMN_C2PMSG_80_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_81 0x0291
-#define regMP1_SMN_C2PMSG_81_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_82 0x0292
-#define regMP1_SMN_C2PMSG_82_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_83 0x0293
-#define regMP1_SMN_C2PMSG_83_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_84 0x0294
-#define regMP1_SMN_C2PMSG_84_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_85 0x0295
-#define regMP1_SMN_C2PMSG_85_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_86 0x0296
-#define regMP1_SMN_C2PMSG_86_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_87 0x0297
-#define regMP1_SMN_C2PMSG_87_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_88 0x0298
-#define regMP1_SMN_C2PMSG_88_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_89 0x0299
-#define regMP1_SMN_C2PMSG_89_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_90 0x029a
-#define regMP1_SMN_C2PMSG_90_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_91 0x029b
-#define regMP1_SMN_C2PMSG_91_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_92 0x029c
-#define regMP1_SMN_C2PMSG_92_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_93 0x029d
-#define regMP1_SMN_C2PMSG_93_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_94 0x029e
-#define regMP1_SMN_C2PMSG_94_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_95 0x029f
-#define regMP1_SMN_C2PMSG_95_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_96 0x02a0
-#define regMP1_SMN_C2PMSG_96_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_97 0x02a1
-#define regMP1_SMN_C2PMSG_97_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_98 0x02a2
-#define regMP1_SMN_C2PMSG_98_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_99 0x02a3
-#define regMP1_SMN_C2PMSG_99_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_100 0x02a4
-#define regMP1_SMN_C2PMSG_100_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_101 0x02a5
-#define regMP1_SMN_C2PMSG_101_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_102 0x02a6
-#define regMP1_SMN_C2PMSG_102_BASE_IDX 0
-#define regMP1_SMN_C2PMSG_103 0x02a7
-#define regMP1_SMN_C2PMSG_103_BASE_IDX 0
-#define regMP1_SMN_IH_CREDIT 0x02c1
-#define regMP1_SMN_IH_CREDIT_BASE_IDX 0
-#define regMP1_SMN_IH_SW_INT 0x02c2
-#define regMP1_SMN_IH_SW_INT_BASE_IDX 0
-#define regMP1_SMN_IH_SW_INT_CTRL 0x02c3
-#define regMP1_SMN_IH_SW_INT_CTRL_BASE_IDX 0
-#define regMP1_SMN_FPS_CNT 0x02c4
-#define regMP1_SMN_FPS_CNT_BASE_IDX 0
-#define regMP1_SMN_EXT_SCRATCH0 0x0340
-#define regMP1_SMN_EXT_SCRATCH0_BASE_IDX 0
-#define regMP1_SMN_EXT_SCRATCH1 0x0341
-#define regMP1_SMN_EXT_SCRATCH1_BASE_IDX 0
-#define regMP1_SMN_EXT_SCRATCH2 0x0342
-#define regMP1_SMN_EXT_SCRATCH2_BASE_IDX 0
-#define regMP1_SMN_EXT_SCRATCH3 0x0343
-#define regMP1_SMN_EXT_SCRATCH3_BASE_IDX 0
-#define regMP1_SMN_EXT_SCRATCH4 0x0344
-#define regMP1_SMN_EXT_SCRATCH4_BASE_IDX 0
-#define regMP1_SMN_EXT_SCRATCH5 0x0345
-#define regMP1_SMN_EXT_SCRATCH5_BASE_IDX 0
-#define regMP1_SMN_EXT_SCRATCH6 0x0346
-#define regMP1_SMN_EXT_SCRATCH6_BASE_IDX 0
-#define regMP1_SMN_EXT_SCRATCH7 0x0347
-#define regMP1_SMN_EXT_SCRATCH7_BASE_IDX 0
-
-
-#endif
+++ /dev/null
-/*
- * Copyright 2020 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- *
- */
-#ifndef _mp_13_0_1_SH_MASK_HEADER
-#define _mp_13_0_1_SH_MASK_HEADER
-
-
-// addressBlock: mp_SmuMp0_SmnDec
-//MP0_SMN_C2PMSG_32
-#define MP0_SMN_C2PMSG_32__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_32__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_33
-#define MP0_SMN_C2PMSG_33__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_33__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_34
-#define MP0_SMN_C2PMSG_34__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_34__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_35
-#define MP0_SMN_C2PMSG_35__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_35__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_36
-#define MP0_SMN_C2PMSG_36__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_36__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_37
-#define MP0_SMN_C2PMSG_37__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_37__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_38
-#define MP0_SMN_C2PMSG_38__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_38__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_39
-#define MP0_SMN_C2PMSG_39__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_39__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_40
-#define MP0_SMN_C2PMSG_40__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_40__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_41
-#define MP0_SMN_C2PMSG_41__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_41__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_42
-#define MP0_SMN_C2PMSG_42__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_42__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_43
-#define MP0_SMN_C2PMSG_43__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_43__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_44
-#define MP0_SMN_C2PMSG_44__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_44__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_45
-#define MP0_SMN_C2PMSG_45__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_45__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_46
-#define MP0_SMN_C2PMSG_46__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_46__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_47
-#define MP0_SMN_C2PMSG_47__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_47__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_48
-#define MP0_SMN_C2PMSG_48__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_48__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_49
-#define MP0_SMN_C2PMSG_49__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_49__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_50
-#define MP0_SMN_C2PMSG_50__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_50__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_51
-#define MP0_SMN_C2PMSG_51__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_51__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_52
-#define MP0_SMN_C2PMSG_52__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_52__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_53
-#define MP0_SMN_C2PMSG_53__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_53__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_54
-#define MP0_SMN_C2PMSG_54__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_54__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_55
-#define MP0_SMN_C2PMSG_55__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_55__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_56
-#define MP0_SMN_C2PMSG_56__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_56__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_57
-#define MP0_SMN_C2PMSG_57__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_57__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_58
-#define MP0_SMN_C2PMSG_58__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_58__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_59
-#define MP0_SMN_C2PMSG_59__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_59__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_60
-#define MP0_SMN_C2PMSG_60__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_60__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_61
-#define MP0_SMN_C2PMSG_61__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_61__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_62
-#define MP0_SMN_C2PMSG_62__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_62__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_63
-#define MP0_SMN_C2PMSG_63__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_63__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_64
-#define MP0_SMN_C2PMSG_64__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_64__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_65
-#define MP0_SMN_C2PMSG_65__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_65__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_66
-#define MP0_SMN_C2PMSG_66__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_66__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_67
-#define MP0_SMN_C2PMSG_67__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_67__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_68
-#define MP0_SMN_C2PMSG_68__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_68__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_69
-#define MP0_SMN_C2PMSG_69__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_69__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_70
-#define MP0_SMN_C2PMSG_70__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_70__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_71
-#define MP0_SMN_C2PMSG_71__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_71__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_72
-#define MP0_SMN_C2PMSG_72__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_72__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_73
-#define MP0_SMN_C2PMSG_73__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_73__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_74
-#define MP0_SMN_C2PMSG_74__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_74__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_75
-#define MP0_SMN_C2PMSG_75__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_75__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_76
-#define MP0_SMN_C2PMSG_76__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_76__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_77
-#define MP0_SMN_C2PMSG_77__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_77__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_78
-#define MP0_SMN_C2PMSG_78__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_78__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_79
-#define MP0_SMN_C2PMSG_79__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_79__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_80
-#define MP0_SMN_C2PMSG_80__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_80__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_81
-#define MP0_SMN_C2PMSG_81__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_81__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_82
-#define MP0_SMN_C2PMSG_82__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_82__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_83
-#define MP0_SMN_C2PMSG_83__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_83__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_84
-#define MP0_SMN_C2PMSG_84__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_84__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_85
-#define MP0_SMN_C2PMSG_85__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_85__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_86
-#define MP0_SMN_C2PMSG_86__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_86__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_87
-#define MP0_SMN_C2PMSG_87__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_87__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_88
-#define MP0_SMN_C2PMSG_88__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_88__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_89
-#define MP0_SMN_C2PMSG_89__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_89__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_90
-#define MP0_SMN_C2PMSG_90__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_90__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_91
-#define MP0_SMN_C2PMSG_91__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_91__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_92
-#define MP0_SMN_C2PMSG_92__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_92__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_93
-#define MP0_SMN_C2PMSG_93__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_93__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_94
-#define MP0_SMN_C2PMSG_94__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_94__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_95
-#define MP0_SMN_C2PMSG_95__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_95__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_96
-#define MP0_SMN_C2PMSG_96__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_96__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_97
-#define MP0_SMN_C2PMSG_97__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_97__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_98
-#define MP0_SMN_C2PMSG_98__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_98__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_99
-#define MP0_SMN_C2PMSG_99__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_99__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_100
-#define MP0_SMN_C2PMSG_100__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_100__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_101
-#define MP0_SMN_C2PMSG_101__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_101__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_102
-#define MP0_SMN_C2PMSG_102__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_102__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_C2PMSG_103
-#define MP0_SMN_C2PMSG_103__CONTENT__SHIFT 0x0
-#define MP0_SMN_C2PMSG_103__CONTENT_MASK 0xFFFFFFFFL
-//MP0_SMN_IH_CREDIT
-#define MP0_SMN_IH_CREDIT__CREDIT_VALUE__SHIFT 0x0
-#define MP0_SMN_IH_CREDIT__CLIENT_ID__SHIFT 0x10
-#define MP0_SMN_IH_CREDIT__CREDIT_VALUE_MASK 0x00000003L
-#define MP0_SMN_IH_CREDIT__CLIENT_ID_MASK 0x00FF0000L
-//MP0_SMN_IH_SW_INT
-#define MP0_SMN_IH_SW_INT__ID__SHIFT 0x0
-#define MP0_SMN_IH_SW_INT__VALID__SHIFT 0x8
-#define MP0_SMN_IH_SW_INT__ID_MASK 0x000000FFL
-#define MP0_SMN_IH_SW_INT__VALID_MASK 0x00000100L
-//MP0_SMN_IH_SW_INT_CTRL
-#define MP0_SMN_IH_SW_INT_CTRL__INT_MASK__SHIFT 0x0
-#define MP0_SMN_IH_SW_INT_CTRL__INT_ACK__SHIFT 0x8
-#define MP0_SMN_IH_SW_INT_CTRL__INT_MASK_MASK 0x00000001L
-#define MP0_SMN_IH_SW_INT_CTRL__INT_ACK_MASK 0x00000100L
-
-
-// addressBlock: mp_SmuMp1Pub_CruDec
-//MP1_FIRMWARE_FLAGS
-#define MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED__SHIFT 0x0
-#define MP1_FIRMWARE_FLAGS__RESERVED__SHIFT 0x1
-#define MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK 0x00000001L
-#define MP1_FIRMWARE_FLAGS__RESERVED_MASK 0xFFFFFFFEL
-
-
-// addressBlock: mp_SmuMp1_SmnDec
-//MP1_SMN_C2PMSG_32
-#define MP1_SMN_C2PMSG_32__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_32__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_33
-#define MP1_SMN_C2PMSG_33__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_33__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_34
-#define MP1_SMN_C2PMSG_34__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_34__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_35
-#define MP1_SMN_C2PMSG_35__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_35__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_36
-#define MP1_SMN_C2PMSG_36__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_36__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_37
-#define MP1_SMN_C2PMSG_37__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_37__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_38
-#define MP1_SMN_C2PMSG_38__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_38__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_39
-#define MP1_SMN_C2PMSG_39__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_39__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_40
-#define MP1_SMN_C2PMSG_40__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_40__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_41
-#define MP1_SMN_C2PMSG_41__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_41__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_42
-#define MP1_SMN_C2PMSG_42__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_42__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_43
-#define MP1_SMN_C2PMSG_43__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_43__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_44
-#define MP1_SMN_C2PMSG_44__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_44__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_45
-#define MP1_SMN_C2PMSG_45__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_45__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_46
-#define MP1_SMN_C2PMSG_46__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_46__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_47
-#define MP1_SMN_C2PMSG_47__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_47__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_48
-#define MP1_SMN_C2PMSG_48__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_48__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_49
-#define MP1_SMN_C2PMSG_49__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_49__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_50
-#define MP1_SMN_C2PMSG_50__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_50__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_51
-#define MP1_SMN_C2PMSG_51__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_51__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_52
-#define MP1_SMN_C2PMSG_52__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_52__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_53
-#define MP1_SMN_C2PMSG_53__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_53__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_54
-#define MP1_SMN_C2PMSG_54__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_54__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_55
-#define MP1_SMN_C2PMSG_55__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_55__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_56
-#define MP1_SMN_C2PMSG_56__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_56__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_57
-#define MP1_SMN_C2PMSG_57__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_57__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_58
-#define MP1_SMN_C2PMSG_58__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_58__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_59
-#define MP1_SMN_C2PMSG_59__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_59__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_60
-#define MP1_SMN_C2PMSG_60__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_60__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_61
-#define MP1_SMN_C2PMSG_61__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_61__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_62
-#define MP1_SMN_C2PMSG_62__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_62__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_63
-#define MP1_SMN_C2PMSG_63__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_63__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_64
-#define MP1_SMN_C2PMSG_64__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_64__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_65
-#define MP1_SMN_C2PMSG_65__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_65__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_66
-#define MP1_SMN_C2PMSG_66__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_66__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_67
-#define MP1_SMN_C2PMSG_67__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_67__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_68
-#define MP1_SMN_C2PMSG_68__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_68__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_69
-#define MP1_SMN_C2PMSG_69__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_69__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_70
-#define MP1_SMN_C2PMSG_70__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_70__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_71
-#define MP1_SMN_C2PMSG_71__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_71__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_72
-#define MP1_SMN_C2PMSG_72__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_72__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_73
-#define MP1_SMN_C2PMSG_73__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_73__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_74
-#define MP1_SMN_C2PMSG_74__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_74__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_75
-#define MP1_SMN_C2PMSG_75__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_75__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_76
-#define MP1_SMN_C2PMSG_76__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_76__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_77
-#define MP1_SMN_C2PMSG_77__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_77__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_78
-#define MP1_SMN_C2PMSG_78__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_78__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_79
-#define MP1_SMN_C2PMSG_79__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_79__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_80
-#define MP1_SMN_C2PMSG_80__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_80__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_81
-#define MP1_SMN_C2PMSG_81__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_81__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_82
-#define MP1_SMN_C2PMSG_82__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_82__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_83
-#define MP1_SMN_C2PMSG_83__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_83__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_84
-#define MP1_SMN_C2PMSG_84__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_84__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_85
-#define MP1_SMN_C2PMSG_85__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_85__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_86
-#define MP1_SMN_C2PMSG_86__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_86__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_87
-#define MP1_SMN_C2PMSG_87__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_87__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_88
-#define MP1_SMN_C2PMSG_88__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_88__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_89
-#define MP1_SMN_C2PMSG_89__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_89__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_90
-#define MP1_SMN_C2PMSG_90__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_90__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_91
-#define MP1_SMN_C2PMSG_91__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_91__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_92
-#define MP1_SMN_C2PMSG_92__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_92__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_93
-#define MP1_SMN_C2PMSG_93__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_93__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_94
-#define MP1_SMN_C2PMSG_94__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_94__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_95
-#define MP1_SMN_C2PMSG_95__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_95__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_96
-#define MP1_SMN_C2PMSG_96__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_96__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_97
-#define MP1_SMN_C2PMSG_97__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_97__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_98
-#define MP1_SMN_C2PMSG_98__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_98__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_99
-#define MP1_SMN_C2PMSG_99__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_99__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_100
-#define MP1_SMN_C2PMSG_100__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_100__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_101
-#define MP1_SMN_C2PMSG_101__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_101__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_102
-#define MP1_SMN_C2PMSG_102__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_102__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_C2PMSG_103
-#define MP1_SMN_C2PMSG_103__CONTENT__SHIFT 0x0
-#define MP1_SMN_C2PMSG_103__CONTENT_MASK 0xFFFFFFFFL
-//MP1_SMN_IH_CREDIT
-#define MP1_SMN_IH_CREDIT__CREDIT_VALUE__SHIFT 0x0
-#define MP1_SMN_IH_CREDIT__CLIENT_ID__SHIFT 0x10
-#define MP1_SMN_IH_CREDIT__CREDIT_VALUE_MASK 0x00000003L
-#define MP1_SMN_IH_CREDIT__CLIENT_ID_MASK 0x00FF0000L
-//MP1_SMN_IH_SW_INT
-#define MP1_SMN_IH_SW_INT__ID__SHIFT 0x0
-#define MP1_SMN_IH_SW_INT__VALID__SHIFT 0x8
-#define MP1_SMN_IH_SW_INT__ID_MASK 0x000000FFL
-#define MP1_SMN_IH_SW_INT__VALID_MASK 0x00000100L
-//MP1_SMN_IH_SW_INT_CTRL
-#define MP1_SMN_IH_SW_INT_CTRL__INT_MASK__SHIFT 0x0
-#define MP1_SMN_IH_SW_INT_CTRL__INT_ACK__SHIFT 0x8
-#define MP1_SMN_IH_SW_INT_CTRL__INT_MASK_MASK 0x00000001L
-#define MP1_SMN_IH_SW_INT_CTRL__INT_ACK_MASK 0x00000100L
-//MP1_SMN_FPS_CNT
-#define MP1_SMN_FPS_CNT__COUNT__SHIFT 0x0
-#define MP1_SMN_FPS_CNT__COUNT_MASK 0xFFFFFFFFL
-//MP1_SMN_EXT_SCRATCH0
-#define MP1_SMN_EXT_SCRATCH0__DATA__SHIFT 0x0
-#define MP1_SMN_EXT_SCRATCH0__DATA_MASK 0xFFFFFFFFL
-//MP1_SMN_EXT_SCRATCH1
-#define MP1_SMN_EXT_SCRATCH1__DATA__SHIFT 0x0
-#define MP1_SMN_EXT_SCRATCH1__DATA_MASK 0xFFFFFFFFL
-//MP1_SMN_EXT_SCRATCH2
-#define MP1_SMN_EXT_SCRATCH2__DATA__SHIFT 0x0
-#define MP1_SMN_EXT_SCRATCH2__DATA_MASK 0xFFFFFFFFL
-//MP1_SMN_EXT_SCRATCH3
-#define MP1_SMN_EXT_SCRATCH3__DATA__SHIFT 0x0
-#define MP1_SMN_EXT_SCRATCH3__DATA_MASK 0xFFFFFFFFL
-//MP1_SMN_EXT_SCRATCH4
-#define MP1_SMN_EXT_SCRATCH4__DATA__SHIFT 0x0
-#define MP1_SMN_EXT_SCRATCH4__DATA_MASK 0xFFFFFFFFL
-//MP1_SMN_EXT_SCRATCH5
-#define MP1_SMN_EXT_SCRATCH5__DATA__SHIFT 0x0
-#define MP1_SMN_EXT_SCRATCH5__DATA_MASK 0xFFFFFFFFL
-//MP1_SMN_EXT_SCRATCH6
-#define MP1_SMN_EXT_SCRATCH6__DATA__SHIFT 0x0
-#define MP1_SMN_EXT_SCRATCH6__DATA_MASK 0xFFFFFFFFL
-//MP1_SMN_EXT_SCRATCH7
-#define MP1_SMN_EXT_SCRATCH7__DATA__SHIFT 0x0
-#define MP1_SMN_EXT_SCRATCH7__DATA_MASK 0xFFFFFFFFL
-
-
-#endif
#define PPSMC_MSG_SetSystemVirtualSTBtoDramAddrLow 0x41
#define PPSMC_MSG_GfxDriverResetRecovery 0x42
-#define PPSMC_Message_Count 0x43
+#define PPSMC_MSG_BoardPowerCalibration 0x43
+#define PPSMC_Message_Count 0x44
//PPSMC Reset Types
#define PPSMC_RESET_TYPE_WARM_RESET 0x00
__SMU_DUMMY_MAP(DisableDeterminism), \
__SMU_DUMMY_MAP(SetUclkDpmMode), \
__SMU_DUMMY_MAP(LightSBR), \
- __SMU_DUMMY_MAP(GfxDriverResetRecovery),
+ __SMU_DUMMY_MAP(GfxDriverResetRecovery), \
+ __SMU_DUMMY_MAP(BoardPowerCalibration),
#undef __SMU_DUMMY_MAP
#define __SMU_DUMMY_MAP(type) SMU_MSG_##type
#define SMU11_DRIVER_IF_VERSION_Navy_Flounder 0xE
#define SMU11_DRIVER_IF_VERSION_VANGOGH 0x03
#define SMU11_DRIVER_IF_VERSION_Dimgrey_Cavefish 0xF
-#define SMU11_DRIVER_IF_VERSION_Beige_Goby 0x9
+#define SMU11_DRIVER_IF_VERSION_Beige_Goby 0xD
/* MP Apertures */
#define MP0_Public 0x03800000
#include "amdgpu_smu.h"
#define SMU13_DRIVER_IF_VERSION_INV 0xFFFFFFFF
+#define SMU13_DRIVER_IF_VERSION_YELLOW_CARP 0x04
#define SMU13_DRIVER_IF_VERSION_ALDE 0x07
/* MP Apertures */
+++ /dev/null
-/*
- * Copyright 2020 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- */
-#ifndef __SMU_V13_0_1_H__
-#define __SMU_V13_0_1_H__
-
-#include "amdgpu_smu.h"
-
-#define SMU13_0_1_DRIVER_IF_VERSION_INV 0xFFFFFFFF
-#define SMU13_0_1_DRIVER_IF_VERSION_YELLOW_CARP 0x3
-
-/* MP Apertures */
-#define MP0_Public 0x03800000
-#define MP0_SRAM 0x03900000
-#define MP1_Public 0x03b00000
-#define MP1_SRAM 0x03c00004
-
-/* address block */
-#define smnMP1_FIRMWARE_FLAGS 0x3010024
-
-
-#if defined(SWSMU_CODE_LAYER_L2) || defined(SWSMU_CODE_LAYER_L3)
-
-int smu_v13_0_1_check_fw_status(struct smu_context *smu);
-
-int smu_v13_0_1_check_fw_version(struct smu_context *smu);
-
-int smu_v13_0_1_fini_smc_tables(struct smu_context *smu);
-
-int smu_v13_0_1_get_vbios_bootup_values(struct smu_context *smu);
-
-int smu_v13_0_1_set_default_dpm_tables(struct smu_context *smu);
-
-int smu_v13_0_1_set_driver_table_location(struct smu_context *smu);
-
-int smu_v13_0_1_gfx_off_control(struct smu_context *smu, bool enable);
-#endif
-#endif
case CHIP_SIENNA_CICHLID:
case CHIP_NAVY_FLOUNDER:
case CHIP_DIMGREY_CAVEFISH:
+ case CHIP_BEIGE_GOBY:
if (amdgpu_runtime_pm == 2)
ret = smu_cmn_send_smc_msg_with_param(smu,
SMU_MSG_EnterBaco,
# Makefile for the 'smu manager' sub-component of powerplay.
# It provides the smu management services for the driver.
-SMU13_MGR = smu_v13_0.o aldebaran_ppt.o smu_v13_0_1.o yellow_carp_ppt.o
+SMU13_MGR = smu_v13_0.o aldebaran_ppt.o yellow_carp_ppt.o
AMD_SWSMU_SMU13MGR = $(addprefix $(AMD_SWSMU_PATH)/smu13/,$(SMU13_MGR))
MSG_MAP(DisableDeterminism, PPSMC_MSG_DisableDeterminism, 0),
MSG_MAP(SetUclkDpmMode, PPSMC_MSG_SetUclkDpmMode, 0),
MSG_MAP(GfxDriverResetRecovery, PPSMC_MSG_GfxDriverResetRecovery, 0),
+ MSG_MAP(BoardPowerCalibration, PPSMC_MSG_BoardPowerCalibration, 0),
};
static const struct cmn2asic_mapping aldebaran_clk_map[SMU_CLK_COUNT] = {
return ret;
}
+static bool aldebaran_is_primary(struct smu_context *smu)
+{
+ struct amdgpu_device *adev = smu->adev;
+
+ if (adev->smuio.funcs && adev->smuio.funcs->get_die_id)
+ return adev->smuio.funcs->get_die_id(adev) == 0;
+
+ return true;
+}
+
+static int aldebaran_run_board_btc(struct smu_context *smu)
+{
+ u32 smu_version;
+ int ret;
+
+ if (!aldebaran_is_primary(smu))
+ return 0;
+
+ ret = smu_cmn_get_smc_version(smu, NULL, &smu_version);
+ if (ret) {
+ dev_err(smu->adev->dev, "Failed to get smu version!\n");
+ return ret;
+ }
+ if (smu_version <= 0x00441d00)
+ return 0;
+
+ ret = smu_cmn_send_smc_msg(smu, SMU_MSG_BoardPowerCalibration, NULL);
+ if (ret)
+ dev_err(smu->adev->dev, "Board power calibration failed!\n");
+
+ return ret;
+}
+
static int aldebaran_run_btc(struct smu_context *smu)
{
int ret;
ret = smu_cmn_send_smc_msg(smu, SMU_MSG_RunDcBtc, NULL);
if (ret)
dev_err(smu->adev->dev, "RunDcBtc failed!\n");
+ else
+ ret = aldebaran_run_board_btc(smu);
return ret;
}
return (abs(frequency1 - frequency2) <= EPSILON);
}
-static bool aldebaran_is_primary(struct smu_context *smu)
-{
- struct amdgpu_device *adev = smu->adev;
-
- if (adev->smuio.funcs && adev->smuio.funcs->get_die_id)
- return adev->smuio.funcs->get_die_id(adev) == 0;
-
- return true;
-}
-
static int aldebaran_get_smu_metrics_data(struct smu_context *smu,
MetricsMember_t member,
uint32_t *value)
case CHIP_ALDEBARAN:
smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_ALDE;
break;
+ case CHIP_YELLOW_CARP:
+ smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_YELLOW_CARP;
+ break;
default:
dev_err(smu->adev->dev, "smu unsupported asic type:%d.\n", smu->adev->asic_type);
smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_INV;
return ret;
}
+int smu_v13_0_gfx_off_control(struct smu_context *smu, bool enable)
+{
+ int ret = 0;
+ struct amdgpu_device *adev = smu->adev;
+
+ switch (adev->asic_type) {
+ case CHIP_YELLOW_CARP:
+ if (!(adev->pm.pp_feature & PP_GFXOFF_MASK))
+ return 0;
+ if (enable)
+ ret = smu_cmn_send_smc_msg(smu, SMU_MSG_AllowGfxOff, NULL);
+ else
+ ret = smu_cmn_send_smc_msg(smu, SMU_MSG_DisallowGfxOff, NULL);
+ break;
+ default:
+ break;
+ }
+
+ return ret;
+}
+
int smu_v13_0_system_features_control(struct smu_context *smu,
bool en)
{
+++ /dev/null
-/*
- * Copyright 2020 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- */
-
-//#include <linux/reboot.h>
-
-#define SWSMU_CODE_LAYER_L3
-
-#include "amdgpu.h"
-#include "amdgpu_smu.h"
-#include "smu_v13_0_1.h"
-#include "soc15_common.h"
-#include "smu_cmn.h"
-#include "atomfirmware.h"
-#include "amdgpu_atomfirmware.h"
-#include "amdgpu_atombios.h"
-#include "atom.h"
-
-#include "asic_reg/mp/mp_13_0_1_offset.h"
-#include "asic_reg/mp/mp_13_0_1_sh_mask.h"
-
-/*
- * DO NOT use these for err/warn/info/debug messages.
- * Use dev_err, dev_warn, dev_info and dev_dbg instead.
- * They are more MGPU friendly.
- */
-#undef pr_err
-#undef pr_warn
-#undef pr_info
-#undef pr_debug
-
-int smu_v13_0_1_check_fw_status(struct smu_context *smu)
-{
- struct amdgpu_device *adev = smu->adev;
- uint32_t mp1_fw_flags;
-
- mp1_fw_flags = RREG32_PCIE(MP1_Public |
- (smnMP1_FIRMWARE_FLAGS & 0xffffffff));
-
- if ((mp1_fw_flags & MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK) >>
- MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED__SHIFT)
- return 0;
-
- return -EIO;
-}
-
-int smu_v13_0_1_check_fw_version(struct smu_context *smu)
-{
- uint32_t if_version = 0xff, smu_version = 0xff;
- uint16_t smu_major;
- uint8_t smu_minor, smu_debug;
- int ret = 0;
-
- ret = smu_cmn_get_smc_version(smu, &if_version, &smu_version);
- if (ret)
- return ret;
-
- smu_major = (smu_version >> 16) & 0xffff;
- smu_minor = (smu_version >> 8) & 0xff;
- smu_debug = (smu_version >> 0) & 0xff;
-
- switch (smu->adev->asic_type) {
- case CHIP_YELLOW_CARP:
- smu->smc_driver_if_version = SMU13_0_1_DRIVER_IF_VERSION_YELLOW_CARP;
- break;
-
- default:
- dev_err(smu->adev->dev, "smu unsupported asic type:%d.\n", smu->adev->asic_type);
- smu->smc_driver_if_version = SMU13_0_1_DRIVER_IF_VERSION_INV;
- break;
- }
-
- dev_info(smu->adev->dev, "smu fw reported version = 0x%08x (%d.%d.%d)\n",
- smu_version, smu_major, smu_minor, smu_debug);
-
- /*
- * 1. if_version mismatch is not critical as our fw is designed
- * to be backward compatible.
- * 2. New fw usually brings some optimizations. But that's visible
- * only on the paired driver.
- * Considering above, we just leave user a warning message instead
- * of halt driver loading.
- */
- if (if_version != smu->smc_driver_if_version) {
- dev_info(smu->adev->dev, "smu driver if version = 0x%08x, smu fw if version = 0x%08x, "
- "smu fw version = 0x%08x (%d.%d.%d)\n",
- smu->smc_driver_if_version, if_version,
- smu_version, smu_major, smu_minor, smu_debug);
- dev_warn(smu->adev->dev, "SMU driver if version not matched\n");
- }
-
- return ret;
-}
-
-int smu_v13_0_1_fini_smc_tables(struct smu_context *smu)
-{
- struct smu_table_context *smu_table = &smu->smu_table;
-
- kfree(smu_table->clocks_table);
- smu_table->clocks_table = NULL;
-
- kfree(smu_table->metrics_table);
- smu_table->metrics_table = NULL;
-
- kfree(smu_table->watermarks_table);
- smu_table->watermarks_table = NULL;
-
- return 0;
-}
-
-static int smu_v13_0_1_atom_get_smu_clockinfo(struct amdgpu_device *adev,
- uint8_t clk_id,
- uint8_t syspll_id,
- uint32_t *clk_freq)
-{
- struct atom_get_smu_clock_info_parameters_v3_1 input = {0};
- struct atom_get_smu_clock_info_output_parameters_v3_1 *output;
- int ret, index;
-
- input.clk_id = clk_id;
- input.syspll_id = syspll_id;
- input.command = GET_SMU_CLOCK_INFO_V3_1_GET_CLOCK_FREQ;
- index = get_index_into_master_table(atom_master_list_of_command_functions_v2_1,
- getsmuclockinfo);
-
- ret = amdgpu_atom_execute_table(adev->mode_info.atom_context, index,
- (uint32_t *)&input);
- if (ret)
- return -EINVAL;
-
- output = (struct atom_get_smu_clock_info_output_parameters_v3_1 *)&input;
- *clk_freq = le32_to_cpu(output->atom_smu_outputclkfreq.smu_clock_freq_hz) / 10000;
-
- return 0;
-}
-
-int smu_v13_0_1_get_vbios_bootup_values(struct smu_context *smu)
-{
- int ret, index;
- uint16_t size;
- uint8_t frev, crev;
- struct atom_common_table_header *header;
- struct atom_firmware_info_v3_4 *v_3_4;
- struct atom_firmware_info_v3_3 *v_3_3;
- struct atom_firmware_info_v3_1 *v_3_1;
-
- index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1,
- firmwareinfo);
-
- ret = amdgpu_atombios_get_data_table(smu->adev, index, &size, &frev, &crev,
- (uint8_t **)&header);
- if (ret)
- return ret;
-
- if (header->format_revision != 3) {
- dev_err(smu->adev->dev, "unknown atom_firmware_info version! for smu13\n");
- return -EINVAL;
- }
-
- switch (header->content_revision) {
- case 0:
- case 1:
- case 2:
- v_3_1 = (struct atom_firmware_info_v3_1 *)header;
- smu->smu_table.boot_values.revision = v_3_1->firmware_revision;
- smu->smu_table.boot_values.gfxclk = v_3_1->bootup_sclk_in10khz;
- smu->smu_table.boot_values.uclk = v_3_1->bootup_mclk_in10khz;
- smu->smu_table.boot_values.socclk = 0;
- smu->smu_table.boot_values.dcefclk = 0;
- smu->smu_table.boot_values.vddc = v_3_1->bootup_vddc_mv;
- smu->smu_table.boot_values.vddci = v_3_1->bootup_vddci_mv;
- smu->smu_table.boot_values.mvddc = v_3_1->bootup_mvddc_mv;
- smu->smu_table.boot_values.vdd_gfx = v_3_1->bootup_vddgfx_mv;
- smu->smu_table.boot_values.cooling_id = v_3_1->coolingsolution_id;
- break;
- case 3:
- v_3_3 = (struct atom_firmware_info_v3_3 *)header;
- smu->smu_table.boot_values.revision = v_3_3->firmware_revision;
- smu->smu_table.boot_values.gfxclk = v_3_3->bootup_sclk_in10khz;
- smu->smu_table.boot_values.uclk = v_3_3->bootup_mclk_in10khz;
- smu->smu_table.boot_values.socclk = 0;
- smu->smu_table.boot_values.dcefclk = 0;
- smu->smu_table.boot_values.vddc = v_3_3->bootup_vddc_mv;
- smu->smu_table.boot_values.vddci = v_3_3->bootup_vddci_mv;
- smu->smu_table.boot_values.mvddc = v_3_3->bootup_mvddc_mv;
- smu->smu_table.boot_values.vdd_gfx = v_3_3->bootup_vddgfx_mv;
- smu->smu_table.boot_values.cooling_id = v_3_3->coolingsolution_id;
- break;
- case 4:
- default:
- v_3_4 = (struct atom_firmware_info_v3_4 *)header;
- smu->smu_table.boot_values.revision = v_3_4->firmware_revision;
- smu->smu_table.boot_values.gfxclk = v_3_4->bootup_sclk_in10khz;
- smu->smu_table.boot_values.uclk = v_3_4->bootup_mclk_in10khz;
- smu->smu_table.boot_values.socclk = 0;
- smu->smu_table.boot_values.dcefclk = 0;
- smu->smu_table.boot_values.vddc = v_3_4->bootup_vddc_mv;
- smu->smu_table.boot_values.vddci = v_3_4->bootup_vddci_mv;
- smu->smu_table.boot_values.mvddc = v_3_4->bootup_mvddc_mv;
- smu->smu_table.boot_values.vdd_gfx = v_3_4->bootup_vddgfx_mv;
- smu->smu_table.boot_values.cooling_id = v_3_4->coolingsolution_id;
- break;
- }
-
- smu->smu_table.boot_values.format_revision = header->format_revision;
- smu->smu_table.boot_values.content_revision = header->content_revision;
-
- smu_v13_0_1_atom_get_smu_clockinfo(smu->adev,
- (uint8_t)SMU11_SYSPLL0_SOCCLK_ID,
- (uint8_t)0,
- &smu->smu_table.boot_values.socclk);
-
- smu_v13_0_1_atom_get_smu_clockinfo(smu->adev,
- (uint8_t)SMU11_SYSPLL0_DCEFCLK_ID,
- (uint8_t)0,
- &smu->smu_table.boot_values.dcefclk);
-
- smu_v13_0_1_atom_get_smu_clockinfo(smu->adev,
- (uint8_t)SMU11_SYSPLL0_ECLK_ID,
- (uint8_t)0,
- &smu->smu_table.boot_values.eclk);
-
- smu_v13_0_1_atom_get_smu_clockinfo(smu->adev,
- (uint8_t)SMU11_SYSPLL0_VCLK_ID,
- (uint8_t)0,
- &smu->smu_table.boot_values.vclk);
-
- smu_v13_0_1_atom_get_smu_clockinfo(smu->adev,
- (uint8_t)SMU11_SYSPLL0_DCLK_ID,
- (uint8_t)0,
- &smu->smu_table.boot_values.dclk);
-
- if ((smu->smu_table.boot_values.format_revision == 3) &&
- (smu->smu_table.boot_values.content_revision >= 2))
- smu_v13_0_1_atom_get_smu_clockinfo(smu->adev,
- (uint8_t)SMU11_SYSPLL1_0_FCLK_ID,
- (uint8_t)SMU11_SYSPLL1_2_ID,
- &smu->smu_table.boot_values.fclk);
-
- return 0;
-}
-
-int smu_v13_0_1_set_default_dpm_tables(struct smu_context *smu)
-{
- struct smu_table_context *smu_table = &smu->smu_table;
-
- return smu_cmn_update_table(smu, SMU_TABLE_DPMCLOCKS, 0, smu_table->clocks_table, false);
-}
-
-int smu_v13_0_1_set_driver_table_location(struct smu_context *smu)
-{
- struct smu_table *driver_table = &smu->smu_table.driver_table;
- int ret = 0;
-
- if (!driver_table->mc_address)
- return 0;
-
- ret = smu_cmn_send_smc_msg_with_param(smu,
- SMU_MSG_SetDriverDramAddrHigh,
- upper_32_bits(driver_table->mc_address),
- NULL);
-
- if (ret)
- return ret;
-
- ret = smu_cmn_send_smc_msg_with_param(smu,
- SMU_MSG_SetDriverDramAddrLow,
- lower_32_bits(driver_table->mc_address),
- NULL);
-
- return ret;
-}
-
-int smu_v13_0_1_gfx_off_control(struct smu_context *smu, bool enable)
-{
- int ret = 0;
- struct amdgpu_device *adev = smu->adev;
-
- switch (adev->asic_type) {
- case CHIP_YELLOW_CARP:
- if (!(adev->pm.pp_feature & PP_GFXOFF_MASK))
- return 0;
- if (enable)
- ret = smu_cmn_send_smc_msg(smu, SMU_MSG_AllowGfxOff, NULL);
- else
- ret = smu_cmn_send_smc_msg(smu, SMU_MSG_DisallowGfxOff, NULL);
- break;
- default:
- break;
- }
-
- return ret;
-}
#include "amdgpu.h"
#include "amdgpu_smu.h"
-#include "smu_v13_0_1.h"
+#include "smu_v13_0.h"
#include "smu13_driver_if_yellow_carp.h"
#include "yellow_carp_ppt.h"
#include "smu_v13_0_1_ppsmc.h"
return -ENOMEM;
}
+static int yellow_carp_fini_smc_tables(struct smu_context *smu)
+{
+ struct smu_table_context *smu_table = &smu->smu_table;
+
+ kfree(smu_table->clocks_table);
+ smu_table->clocks_table = NULL;
+
+ kfree(smu_table->metrics_table);
+ smu_table->metrics_table = NULL;
+
+ kfree(smu_table->watermarks_table);
+ smu_table->watermarks_table = NULL;
+
+ return 0;
+}
+
static int yellow_carp_system_features_control(struct smu_context *smu, bool en)
{
struct smu_feature *feature = &smu->smu_feature;
if (index < 0)
return index == -EACCES ? 0 : index;
- mutex_lock(&smu->message_lock);
-
- ret = smu_cmn_send_msg_without_waiting(smu, (uint16_t)index, type);
-
- mutex_unlock(&smu->message_lock);
-
- mdelay(10);
+ ret = smu_cmn_send_smc_msg_with_param(smu, (uint16_t)index, type, NULL);
+ if (ret)
+ dev_err(smu->adev->dev, "Failed to mode reset!\n");
return ret;
}
return sizeof(struct gpu_metrics_v2_1);
}
+static int yellow_carp_set_default_dpm_tables(struct smu_context *smu)
+{
+ struct smu_table_context *smu_table = &smu->smu_table;
+
+ return smu_cmn_update_table(smu, SMU_TABLE_DPMCLOCKS, 0, smu_table->clocks_table, false);
+}
+
static int yellow_carp_od_edit_dpm_table(struct smu_context *smu, enum PP_OD_DPM_TABLE_COMMAND type,
long input[], uint32_t size)
{
}
static const struct pptable_funcs yellow_carp_ppt_funcs = {
- .check_fw_status = smu_v13_0_1_check_fw_status,
- .check_fw_version = smu_v13_0_1_check_fw_version,
+ .check_fw_status = smu_v13_0_check_fw_status,
+ .check_fw_version = smu_v13_0_check_fw_version,
.init_smc_tables = yellow_carp_init_smc_tables,
- .fini_smc_tables = smu_v13_0_1_fini_smc_tables,
- .get_vbios_bootup_values = smu_v13_0_1_get_vbios_bootup_values,
+ .fini_smc_tables = yellow_carp_fini_smc_tables,
+ .get_vbios_bootup_values = smu_v13_0_get_vbios_bootup_values,
.system_features_control = yellow_carp_system_features_control,
.send_smc_msg_with_param = smu_cmn_send_smc_msg_with_param,
.send_smc_msg = smu_cmn_send_smc_msg,
.dpm_set_vcn_enable = yellow_carp_dpm_set_vcn_enable,
.dpm_set_jpeg_enable = yellow_carp_dpm_set_jpeg_enable,
- .set_default_dpm_table = smu_v13_0_1_set_default_dpm_tables,
+ .set_default_dpm_table = yellow_carp_set_default_dpm_tables,
.read_sensor = yellow_carp_read_sensor,
.is_dpm_running = yellow_carp_is_dpm_running,
.set_watermarks_table = yellow_carp_set_watermarks_table,
.get_gpu_metrics = yellow_carp_get_gpu_metrics,
.get_enabled_mask = smu_cmn_get_enabled_32_bits_mask,
.get_pp_feature_mask = smu_cmn_get_pp_feature_mask,
- .set_driver_table_location = smu_v13_0_1_set_driver_table_location,
- .gfx_off_control = smu_v13_0_1_gfx_off_control,
+ .set_driver_table_location = smu_v13_0_set_driver_table_location,
+ .gfx_off_control = smu_v13_0_gfx_off_control,
.post_init = yellow_carp_post_smu_init,
.mode2_reset = yellow_carp_mode2_reset,
.get_dpm_ultimate_freq = yellow_carp_get_dpm_ultimate_freq,
if (drm_dev_is_unplugged(dev))
return -ENODEV;
+ if (DRM_IOCTL_TYPE(cmd) != DRM_IOCTL_BASE)
+ return -ENOTTY;
+
is_driver_ioctl = nr >= DRM_COMMAND_BASE && nr < DRM_COMMAND_END;
if (is_driver_ioctl) {
init_vbt_missing_defaults(struct drm_i915_private *i915)
{
enum port port;
- int ports = PORT_A | PORT_B | PORT_C | PORT_D | PORT_E | PORT_F;
+ int ports = BIT(PORT_A) | BIT(PORT_B) | BIT(PORT_C) |
+ BIT(PORT_D) | BIT(PORT_E) | BIT(PORT_F);
if (!HAS_DDI(i915) && !IS_CHERRYVIEW(i915))
return;
intel_ddi_init(dev_priv, PORT_B);
intel_ddi_init(dev_priv, PORT_C);
vlv_dsi_init(dev_priv);
- } else if (DISPLAY_VER(dev_priv) >= 9) {
+ } else if (DISPLAY_VER(dev_priv) == 10) {
intel_ddi_init(dev_priv, PORT_A);
intel_ddi_init(dev_priv, PORT_B);
intel_ddi_init(dev_priv, PORT_C);
intel_ddi_init(dev_priv, PORT_D);
intel_ddi_init(dev_priv, PORT_E);
intel_ddi_init(dev_priv, PORT_F);
+ } else if (DISPLAY_VER(dev_priv) >= 9) {
+ intel_ddi_init(dev_priv, PORT_A);
+ intel_ddi_init(dev_priv, PORT_B);
+ intel_ddi_init(dev_priv, PORT_C);
+ intel_ddi_init(dev_priv, PORT_D);
+ intel_ddi_init(dev_priv, PORT_E);
} else if (HAS_DDI(dev_priv)) {
u32 found;
#include "i915_gem_clflush.h"
#include "i915_gem_context.h"
#include "i915_gem_ioctls.h"
-#include "i915_sw_fence_work.h"
#include "i915_trace.h"
#include "i915_user_extensions.h"
-#include "i915_memcpy.h"
struct eb_vma {
struct i915_vma *vma;
int err;
struct intel_engine_cs *engine = eb->engine;
+ /* If we need to copy for the cmdparser, we will stall anyway */
+ if (eb_use_cmdparser(eb))
+ return ERR_PTR(-EWOULDBLOCK);
+
if (!reloc_can_use_engine(engine)) {
engine = engine->gt->engine_class[COPY_ENGINE_CLASS][0];
if (!engine)
return vma;
}
-struct eb_parse_work {
- struct dma_fence_work base;
- struct intel_engine_cs *engine;
- struct i915_vma *batch;
- struct i915_vma *shadow;
- struct i915_vma *trampoline;
- unsigned long batch_offset;
- unsigned long batch_length;
- unsigned long *jump_whitelist;
- const void *batch_map;
- void *shadow_map;
-};
-
-static int __eb_parse(struct dma_fence_work *work)
-{
- struct eb_parse_work *pw = container_of(work, typeof(*pw), base);
- int ret;
- bool cookie;
-
- cookie = dma_fence_begin_signalling();
- ret = intel_engine_cmd_parser(pw->engine,
- pw->batch,
- pw->batch_offset,
- pw->batch_length,
- pw->shadow,
- pw->jump_whitelist,
- pw->shadow_map,
- pw->batch_map);
- dma_fence_end_signalling(cookie);
-
- return ret;
-}
-
-static void __eb_parse_release(struct dma_fence_work *work)
-{
- struct eb_parse_work *pw = container_of(work, typeof(*pw), base);
-
- if (!IS_ERR_OR_NULL(pw->jump_whitelist))
- kfree(pw->jump_whitelist);
-
- if (pw->batch_map)
- i915_gem_object_unpin_map(pw->batch->obj);
- else
- i915_gem_object_unpin_pages(pw->batch->obj);
-
- i915_gem_object_unpin_map(pw->shadow->obj);
-
- if (pw->trampoline)
- i915_active_release(&pw->trampoline->active);
- i915_active_release(&pw->shadow->active);
- i915_active_release(&pw->batch->active);
-}
-
-static const struct dma_fence_work_ops eb_parse_ops = {
- .name = "eb_parse",
- .work = __eb_parse,
- .release = __eb_parse_release,
-};
-
-static inline int
-__parser_mark_active(struct i915_vma *vma,
- struct intel_timeline *tl,
- struct dma_fence *fence)
-{
- struct intel_gt_buffer_pool_node *node = vma->private;
-
- return i915_active_ref(&node->active, tl->fence_context, fence);
-}
-
-static int
-parser_mark_active(struct eb_parse_work *pw, struct intel_timeline *tl)
-{
- int err;
-
- mutex_lock(&tl->mutex);
-
- err = __parser_mark_active(pw->shadow, tl, &pw->base.dma);
- if (err)
- goto unlock;
-
- if (pw->trampoline) {
- err = __parser_mark_active(pw->trampoline, tl, &pw->base.dma);
- if (err)
- goto unlock;
- }
-
-unlock:
- mutex_unlock(&tl->mutex);
- return err;
-}
-
-static int eb_parse_pipeline(struct i915_execbuffer *eb,
- struct i915_vma *shadow,
- struct i915_vma *trampoline)
-{
- struct eb_parse_work *pw;
- struct drm_i915_gem_object *batch = eb->batch->vma->obj;
- bool needs_clflush;
- int err;
-
- GEM_BUG_ON(overflows_type(eb->batch_start_offset, pw->batch_offset));
- GEM_BUG_ON(overflows_type(eb->batch_len, pw->batch_length));
-
- pw = kzalloc(sizeof(*pw), GFP_KERNEL);
- if (!pw)
- return -ENOMEM;
-
- err = i915_active_acquire(&eb->batch->vma->active);
- if (err)
- goto err_free;
-
- err = i915_active_acquire(&shadow->active);
- if (err)
- goto err_batch;
-
- if (trampoline) {
- err = i915_active_acquire(&trampoline->active);
- if (err)
- goto err_shadow;
- }
-
- pw->shadow_map = i915_gem_object_pin_map(shadow->obj, I915_MAP_WB);
- if (IS_ERR(pw->shadow_map)) {
- err = PTR_ERR(pw->shadow_map);
- goto err_trampoline;
- }
-
- needs_clflush =
- !(batch->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ);
-
- pw->batch_map = ERR_PTR(-ENODEV);
- if (needs_clflush && i915_has_memcpy_from_wc())
- pw->batch_map = i915_gem_object_pin_map(batch, I915_MAP_WC);
-
- if (IS_ERR(pw->batch_map)) {
- err = i915_gem_object_pin_pages(batch);
- if (err)
- goto err_unmap_shadow;
- pw->batch_map = NULL;
- }
-
- pw->jump_whitelist =
- intel_engine_cmd_parser_alloc_jump_whitelist(eb->batch_len,
- trampoline);
- if (IS_ERR(pw->jump_whitelist)) {
- err = PTR_ERR(pw->jump_whitelist);
- goto err_unmap_batch;
- }
-
- dma_fence_work_init(&pw->base, &eb_parse_ops);
-
- pw->engine = eb->engine;
- pw->batch = eb->batch->vma;
- pw->batch_offset = eb->batch_start_offset;
- pw->batch_length = eb->batch_len;
- pw->shadow = shadow;
- pw->trampoline = trampoline;
-
- /* Mark active refs early for this worker, in case we get interrupted */
- err = parser_mark_active(pw, eb->context->timeline);
- if (err)
- goto err_commit;
-
- err = dma_resv_reserve_shared(pw->batch->resv, 1);
- if (err)
- goto err_commit;
-
- err = dma_resv_reserve_shared(shadow->resv, 1);
- if (err)
- goto err_commit;
-
- /* Wait for all writes (and relocs) into the batch to complete */
- err = i915_sw_fence_await_reservation(&pw->base.chain,
- pw->batch->resv, NULL, false,
- 0, I915_FENCE_GFP);
- if (err < 0)
- goto err_commit;
-
- /* Keep the batch alive and unwritten as we parse */
- dma_resv_add_shared_fence(pw->batch->resv, &pw->base.dma);
-
- /* Force execution to wait for completion of the parser */
- dma_resv_add_excl_fence(shadow->resv, &pw->base.dma);
-
- dma_fence_work_commit_imm(&pw->base);
- return 0;
-
-err_commit:
- i915_sw_fence_set_error_once(&pw->base.chain, err);
- dma_fence_work_commit_imm(&pw->base);
- return err;
-
-err_unmap_batch:
- if (pw->batch_map)
- i915_gem_object_unpin_map(batch);
- else
- i915_gem_object_unpin_pages(batch);
-err_unmap_shadow:
- i915_gem_object_unpin_map(shadow->obj);
-err_trampoline:
- if (trampoline)
- i915_active_release(&trampoline->active);
-err_shadow:
- i915_active_release(&shadow->active);
-err_batch:
- i915_active_release(&eb->batch->vma->active);
-err_free:
- kfree(pw);
- return err;
-}
-
static struct i915_vma *eb_dispatch_secure(struct i915_execbuffer *eb, struct i915_vma *vma)
{
/*
goto err_trampoline;
}
- err = eb_parse_pipeline(eb, shadow, trampoline);
+ err = dma_resv_reserve_shared(shadow->resv, 1);
+ if (err)
+ goto err_trampoline;
+
+ err = intel_engine_cmd_parser(eb->engine,
+ eb->batch->vma,
+ eb->batch_start_offset,
+ eb->batch_len,
+ shadow, trampoline);
if (err)
goto err_unpin_batch;
switch (obj->mm.madv) {
case I915_MADV_DONTNEED:
i915_gem_object_truncate(obj);
+ return;
case __I915_MADV_PURGED:
return;
}
intel_gt_pm_get(&eb.i915->gt);
for_each_uabi_engine(eb.engine, eb.i915) {
+ if (intel_engine_requires_cmd_parser(eb.engine) ||
+ intel_engine_using_cmd_parser(eb.engine))
+ continue;
+
reloc_cache_init(&eb.reloc_cache, eb.i915);
memset(map, POISON_INUSE, 4096);
__i915_gem_object_pin_pages(pt->base);
i915_gem_object_make_unshrinkable(pt->base);
- if (lvl ||
- gen8_pt_count(*start, end) < I915_PDES ||
- intel_vgpu_active(vm->i915))
- fill_px(pt, vm->scratch[lvl]->encode);
+ fill_px(pt, vm->scratch[lvl]->encode);
spin_lock(&pd->lock);
if (likely(!pd->entry[idx])) {
if (intel_has_pending_fb_unpin(ggtt->vm.i915))
return ERR_PTR(-EAGAIN);
- return ERR_PTR(-EDEADLK);
+ return ERR_PTR(-ENOBUFS);
}
int __i915_vma_pin_fence(struct i915_vma *vma)
if (drm_WARN_ON(&i915->drm, !engine))
return -EINVAL;
+ /*
+ * Due to d3_entered is used to indicate skipping PPGTT invalidation on
+ * vGPU reset, it's set on D0->D3 on PCI config write, and cleared after
+ * vGPU reset if in resuming.
+ * In S0ix exit, the device power state also transite from D3 to D0 as
+ * S3 resume, but no vGPU reset (triggered by QEMU devic model). After
+ * S0ix exit, all engines continue to work. However the d3_entered
+ * remains set which will break next vGPU reset logic (miss the expected
+ * PPGTT invalidation).
+ * Engines can only work in D0. Thus the 1st elsp write gives GVT a
+ * chance to clear d3_entered.
+ */
+ if (vgpu->d3_entered)
+ vgpu->d3_entered = false;
+
execlist = &vgpu->submission.execlist[engine->id];
execlist->elsp_dwords.data[3 - execlist->elsp_dwords.index] = data;
static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
struct drm_i915_gem_object *src_obj,
unsigned long offset, unsigned long length,
- void *dst, const void *src)
+ bool *needs_clflush_after)
{
- bool needs_clflush =
- !(src_obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ);
-
- if (src) {
- GEM_BUG_ON(!needs_clflush);
- i915_unaligned_memcpy_from_wc(dst, src + offset, length);
- } else {
- struct scatterlist *sg;
+ unsigned int src_needs_clflush;
+ unsigned int dst_needs_clflush;
+ void *dst, *src;
+ int ret;
+
+ ret = i915_gem_object_prepare_write(dst_obj, &dst_needs_clflush);
+ if (ret)
+ return ERR_PTR(ret);
+
+ dst = i915_gem_object_pin_map(dst_obj, I915_MAP_WB);
+ i915_gem_object_finish_access(dst_obj);
+ if (IS_ERR(dst))
+ return dst;
+
+ ret = i915_gem_object_prepare_read(src_obj, &src_needs_clflush);
+ if (ret) {
+ i915_gem_object_unpin_map(dst_obj);
+ return ERR_PTR(ret);
+ }
+
+ src = ERR_PTR(-ENODEV);
+ if (src_needs_clflush && i915_has_memcpy_from_wc()) {
+ src = i915_gem_object_pin_map(src_obj, I915_MAP_WC);
+ if (!IS_ERR(src)) {
+ i915_unaligned_memcpy_from_wc(dst,
+ src + offset,
+ length);
+ i915_gem_object_unpin_map(src_obj);
+ }
+ }
+ if (IS_ERR(src)) {
+ unsigned long x, n, remain;
void *ptr;
- unsigned int x, sg_ofs;
- unsigned long remain;
/*
* We can avoid clflushing partial cachelines before the write
* validate up to the end of the batch.
*/
remain = length;
- if (!(dst_obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ))
+ if (dst_needs_clflush & CLFLUSH_BEFORE)
remain = round_up(remain,
boot_cpu_data.x86_clflush_size);
ptr = dst;
x = offset_in_page(offset);
- sg = i915_gem_object_get_sg(src_obj, offset >> PAGE_SHIFT, &sg_ofs, false);
-
- while (remain) {
- unsigned long sg_max = sg->length >> PAGE_SHIFT;
-
- for (; remain && sg_ofs < sg_max; sg_ofs++) {
- unsigned long len = min(remain, PAGE_SIZE - x);
- void *map;
-
- map = kmap_atomic(nth_page(sg_page(sg), sg_ofs));
- if (needs_clflush)
- drm_clflush_virt_range(map + x, len);
- memcpy(ptr, map + x, len);
- kunmap_atomic(map);
-
- ptr += len;
- remain -= len;
- x = 0;
- }
-
- sg_ofs = 0;
- sg = sg_next(sg);
+ for (n = offset >> PAGE_SHIFT; remain; n++) {
+ int len = min(remain, PAGE_SIZE - x);
+
+ src = kmap_atomic(i915_gem_object_get_page(src_obj, n));
+ if (src_needs_clflush)
+ drm_clflush_virt_range(src + x, len);
+ memcpy(ptr, src + x, len);
+ kunmap_atomic(src);
+
+ ptr += len;
+ remain -= len;
+ x = 0;
}
}
+ i915_gem_object_finish_access(src_obj);
+
memset32(dst + length, 0, (dst_obj->base.size - length) / sizeof(u32));
/* dst_obj is returned with vmap pinned */
+ *needs_clflush_after = dst_needs_clflush & CLFLUSH_AFTER;
+
return dst;
}
if (target_cmd_index == offset)
return 0;
+ if (IS_ERR(jump_whitelist))
+ return PTR_ERR(jump_whitelist);
+
if (!test_bit(target_cmd_index, jump_whitelist)) {
DRM_DEBUG("CMD: BB_START to 0x%llx not a previously executed cmd\n",
jump_target);
return 0;
}
-/**
- * intel_engine_cmd_parser_alloc_jump_whitelist() - preallocate jump whitelist for intel_engine_cmd_parser()
- * @batch_length: length of the commands in batch_obj
- * @trampoline: Whether jump trampolines are used.
- *
- * Preallocates a jump whitelist for parsing the cmd buffer in intel_engine_cmd_parser().
- * This has to be preallocated, because the command parser runs in signaling context,
- * and may not allocate any memory.
- *
- * Return: NULL or pointer to a jump whitelist, or ERR_PTR() on failure. Use
- * IS_ERR() to check for errors. Must bre freed() with kfree().
- *
- * NULL is a valid value, meaning no allocation was required.
- */
-unsigned long *intel_engine_cmd_parser_alloc_jump_whitelist(u32 batch_length,
- bool trampoline)
+static unsigned long *alloc_whitelist(u32 batch_length)
{
unsigned long *jmp;
- if (trampoline)
- return NULL;
-
/*
* We expect batch_length to be less than 256KiB for known users,
* i.e. we need at most an 8KiB bitmap allocation which should be
* @batch_offset: byte offset in the batch at which execution starts
* @batch_length: length of the commands in batch_obj
* @shadow: validated copy of the batch buffer in question
- * @jump_whitelist: buffer preallocated with intel_engine_cmd_parser_alloc_jump_whitelist()
- * @shadow_map: mapping to @shadow vma
- * @batch_map: mapping to @batch vma
+ * @trampoline: true if we need to trampoline into privileged execution
*
* Parses the specified batch buffer looking for privilege violations as
* described in the overview.
* Return: non-zero if the parser finds violations or otherwise fails; -EACCES
* if the batch appears legal but should use hardware parsing
*/
+
int intel_engine_cmd_parser(struct intel_engine_cs *engine,
struct i915_vma *batch,
unsigned long batch_offset,
unsigned long batch_length,
struct i915_vma *shadow,
- unsigned long *jump_whitelist,
- void *shadow_map,
- const void *batch_map)
+ bool trampoline)
{
u32 *cmd, *batch_end, offset = 0;
struct drm_i915_cmd_descriptor default_desc = noop_desc;
const struct drm_i915_cmd_descriptor *desc = &default_desc;
+ bool needs_clflush_after = false;
+ unsigned long *jump_whitelist;
u64 batch_addr, shadow_addr;
int ret = 0;
- bool trampoline = !jump_whitelist;
GEM_BUG_ON(!IS_ALIGNED(batch_offset, sizeof(*cmd)));
GEM_BUG_ON(!IS_ALIGNED(batch_length, sizeof(*cmd)));
batch->size));
GEM_BUG_ON(!batch_length);
- cmd = copy_batch(shadow->obj, batch->obj, batch_offset, batch_length,
- shadow_map, batch_map);
+ cmd = copy_batch(shadow->obj, batch->obj,
+ batch_offset, batch_length,
+ &needs_clflush_after);
+ if (IS_ERR(cmd)) {
+ DRM_DEBUG("CMD: Failed to copy batch\n");
+ return PTR_ERR(cmd);
+ }
+
+ jump_whitelist = NULL;
+ if (!trampoline)
+ /* Defer failure until attempted use */
+ jump_whitelist = alloc_whitelist(batch_length);
shadow_addr = gen8_canonical_addr(shadow->node.start);
batch_addr = gen8_canonical_addr(batch->node.start + batch_offset);
i915_gem_object_flush_map(shadow->obj);
+ if (!IS_ERR_OR_NULL(jump_whitelist))
+ kfree(jump_whitelist);
+ i915_gem_object_unpin_map(shadow->obj);
return ret;
}
int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv);
int intel_engine_init_cmd_parser(struct intel_engine_cs *engine);
void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine);
-unsigned long *intel_engine_cmd_parser_alloc_jump_whitelist(u32 batch_length,
- bool trampoline);
-
int intel_engine_cmd_parser(struct intel_engine_cs *engine,
struct i915_vma *batch,
unsigned long batch_offset,
unsigned long batch_length,
struct i915_vma *shadow,
- unsigned long *jump_whitelist,
- void *shadow_map,
- const void *batch_map);
+ bool trampoline);
#define I915_CMD_PARSER_TRAMPOLINE_SIZE 8
/* intel_device_info.c */
atomic_inc(&active);
}
-static void __exit __i915_globals_flush(void)
+static void __i915_globals_flush(void)
{
atomic_inc(&active); /* skip shrinking */
atomic_dec(&active);
}
-void __exit i915_globals_exit(void)
+void i915_globals_exit(void)
{
GEM_BUG_ON(atomic_read(&active));
err = pci_register_driver(&i915_pci_driver);
if (err) {
i915_pmu_exit();
+ i915_globals_exit();
return err;
}
#define GEN12_HCP_SFC_LOCK_ACK_BIT REG_BIT(1)
#define GEN12_HCP_SFC_USAGE_BIT REG_BIT(0)
-#define GEN12_SFC_DONE(n) _MMIO(0x1cc00 + (n) * 0x100)
+#define GEN12_SFC_DONE(n) _MMIO(0x1cc000 + (n) * 0x1000)
#define GEN12_SFC_DONE_MAX 4
#define RING_PP_DIR_BASE(base) _MMIO((base) + 0x228)
do {
fence = *child++;
- if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
- i915_sw_fence_set_error_once(&rq->submit, fence->error);
+ if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
continue;
- }
if (fence->context == rq->fence.context)
continue;
do {
fence = *child++;
- if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
- i915_sw_fence_set_error_once(&rq->submit, fence->error);
+ if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
continue;
- }
/*
* Requests on the same timeline are explicitly ordered, along
info->pipe_mask &= ~BIT(PIPE_C);
info->cpu_transcoder_mask &= ~BIT(TRANSCODER_C);
}
- } else if (HAS_DISPLAY(dev_priv) && GRAPHICS_VER(dev_priv) >= 9) {
+ } else if (HAS_DISPLAY(dev_priv) && DISPLAY_VER(dev_priv) >= 9) {
u32 dfsm = intel_de_read(dev_priv, SKL_DFSM);
if (dfsm & SKL_DFSM_PIPE_A_DISABLE) {
info->pipe_mask &= ~BIT(PIPE_C);
info->cpu_transcoder_mask &= ~BIT(TRANSCODER_C);
}
- if (GRAPHICS_VER(dev_priv) >= 12 &&
+
+ if (DISPLAY_VER(dev_priv) >= 12 &&
(dfsm & TGL_DFSM_PIPE_D_DISABLE)) {
info->pipe_mask &= ~BIT(PIPE_D);
info->cpu_transcoder_mask &= ~BIT(TRANSCODER_D);
if (dfsm & SKL_DFSM_DISPLAY_PM_DISABLE)
info->display.has_fbc = 0;
- if (GRAPHICS_VER(dev_priv) >= 11 && (dfsm & ICL_DFSM_DMC_DISABLE))
+ if (DISPLAY_VER(dev_priv) >= 11 && (dfsm & ICL_DFSM_DMC_DISABLE))
info->display.has_dmc = 0;
- if (GRAPHICS_VER(dev_priv) >= 10 &&
+ if (DISPLAY_VER(dev_priv) >= 10 &&
(dfsm & CNL_DFSM_DISPLAY_DSC_DISABLE))
info->display.has_dsc = 0;
}
unsigned long status, val, val1;
int plane_id, dma0_state, dma1_state;
struct kmb_drm_private *kmb = to_kmb(dev);
+ u32 ctrl = 0;
status = kmb_read_lcd(kmb, LCD_INT_STATUS);
kmb_clr_bitmask_lcd(kmb, LCD_CONTROL,
kmb->plane_status[plane_id].ctrl);
+ ctrl = kmb_read_lcd(kmb, LCD_CONTROL);
+ if (!(ctrl & (LCD_CTRL_VL1_ENABLE |
+ LCD_CTRL_VL2_ENABLE |
+ LCD_CTRL_GL1_ENABLE |
+ LCD_CTRL_GL2_ENABLE))) {
+ /* If no LCD layers are using DMA,
+ * then disable DMA pipelined AXI read
+ * transactions.
+ */
+ kmb_clr_bitmask_lcd(kmb, LCD_CONTROL,
+ LCD_CTRL_PIPELINE_DMA);
+ }
+
kmb->plane_status[plane_id].disable = false;
}
}
.fops = &fops,
DRM_GEM_CMA_DRIVER_OPS_VMAP,
.name = "kmb-drm",
- .desc = "KEEMBAY DISPLAY DRIVER ",
- .date = "20201008",
- .major = 1,
- .minor = 0,
+ .desc = "KEEMBAY DISPLAY DRIVER",
+ .date = DRIVER_DATE,
+ .major = DRIVER_MAJOR,
+ .minor = DRIVER_MINOR,
};
static int kmb_remove(struct platform_device *pdev)
#define KMB_MAX_HEIGHT 1080 /*Max height in pixels */
#define KMB_MIN_WIDTH 1920 /*Max width in pixels */
#define KMB_MIN_HEIGHT 1080 /*Max height in pixels */
+
+#define DRIVER_DATE "20210223"
+#define DRIVER_MAJOR 1
+#define DRIVER_MINOR 1
+
#define KMB_LCD_DEFAULT_CLK 200000000
#define KMB_SYS_CLK_MHZ 500
kmb_set_bitmask_lcd(kmb, LCD_CONTROL, ctrl);
- /* FIXME no doc on how to set output format,these values are
- * taken from the Myriadx tests
+ /* Enable pipeline AXI read transactions for the DMA
+ * after setting graphics layers. This must be done
+ * in a separate write cycle.
+ */
+ kmb_set_bitmask_lcd(kmb, LCD_CONTROL, LCD_CTRL_PIPELINE_DMA);
+
+ /* FIXME no doc on how to set output format, these values are taken
+ * from the Myriadx tests
*/
out_format |= LCD_OUTF_FORMAT_RGB888;
plane->id = i;
}
+ /* Disable pipeline AXI read transactions for the DMA
+ * prior to setting graphics layers
+ */
+ kmb_clr_bitmask_lcd(kmb, LCD_CONTROL, LCD_CTRL_PIPELINE_DMA);
+
return primary;
cleanup:
drmm_kfree(drm, plane);
static const struct dpu_mdp_cfg sm8250_mdp[] = {
{
.name = "top_0", .id = MDP_TOP,
- .base = 0x0, .len = 0x45C,
+ .base = 0x0, .len = 0x494,
.features = 0,
.highest_bank_bit = 0x3, /* TODO: 2 for LP_DDR4 */
.clk_ctrls[DPU_CLK_CTRL_VIG0] = {
dp_write_link(catalog, REG_DP_HSYNC_VSYNC_WIDTH_POLARITY,
dp_catalog->width_blanking);
dp_write_link(catalog, REG_DP_ACTIVE_HOR_VER, dp_catalog->dp_active);
+ dp_write_p0(catalog, MMSS_DP_INTF_CONFIG, 0);
return 0;
}
* running. Add the global reset just before disabling the
* link clocks and core clocks.
*/
- ret = dp_ctrl_off(&ctrl->dp_ctrl);
+ ret = dp_ctrl_off_link_stream(&ctrl->dp_ctrl);
if (ret) {
DRM_ERROR("failed to disable DP controller\n");
return ret;
goto end;
}
+ dp->aux->drm_dev = drm;
rc = dp_aux_register(dp->aux);
if (rc) {
DRM_ERROR("DRM DP AUX register failed\n");
else
dp->dp_display.is_connected = false;
+ dp_display_handle_plugged_change(g_dp_display,
+ dp->dp_display.is_connected);
+
+
mutex_unlock(&dp->event_mutex);
return 0;
case MSM_BO_CACHED_COHERENT:
if (priv->has_cached_coherent)
break;
- /* fallthrough */
+ fallthrough;
default:
DRM_DEV_ERROR(dev->dev, "invalid cache flag: %x\n",
(flags & MSM_BO_CACHE_MASK));
.tlb_add_page = msm_iommu_tlb_add_page,
};
+static int msm_fault_handler(struct iommu_domain *domain, struct device *dev,
+ unsigned long iova, int flags, void *arg);
+
struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent)
{
struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(parent->dev);
if (!ttbr1_cfg)
return ERR_PTR(-ENODEV);
+ /*
+ * Defer setting the fault handler until we have a valid adreno_smmu
+ * to avoid accidentially installing a GPU specific fault handler for
+ * the display's iommu
+ */
+ iommu_set_fault_handler(iommu->domain, msm_fault_handler, iommu);
+
pagetable = kzalloc(sizeof(*pagetable), GFP_KERNEL);
if (!pagetable)
return ERR_PTR(-ENOMEM);
iommu->domain = domain;
msm_mmu_init(&iommu->base, dev, &funcs, MSM_MMU_IOMMU);
- iommu_set_fault_handler(domain, msm_fault_handler, iommu);
atomic_set(&iommu->pagetables, 0);
*/
if (bo->base.dev)
drm_gem_object_release(&bo->base);
+ else
+ dma_resv_fini(&bo->base._resv);
kfree(nvbo);
}
if (IS_ERR(nvbo))
return PTR_ERR(nvbo);
+ nvbo->bo.base.size = size;
+ dma_resv_init(&nvbo->bo.base._resv);
+ drm_vma_node_reset(&nvbo->bo.base.vma_node);
+
ret = nouveau_bo_init(nvbo, size, align, domain, sg, robj);
if (ret)
return ret;
if (ret)
return ret;
- ret = nt35510_read_id(nt);
- if (ret)
- return ret;
+ nt35510_read_id(nt);
/* Set up stuff in manufacturer control, page 1 */
ret = nt35510_send_long(nt, dsi, MCS_CMD_MAUCCTR,
drm_panel_remove(&ts->base);
mipi_dsi_device_unregister(ts->dsi);
- kfree(ts->dsi);
return 0;
}
static const struct panel_desc yes_optoelectronics_ytc700tlag_05_201c = {
.modes = &yes_optoelectronics_ytc700tlag_05_201c_mode,
.num_modes = 1,
- .bpc = 6,
+ .bpc = 8,
.size = {
.width = 154,
.height = 90,
struct qxl_bo *qbo;
struct qxl_device *qdev;
- if (!qxl_ttm_bo_is_qxl_bo(bo))
+ if (!qxl_ttm_bo_is_qxl_bo(bo) || !bo->resource)
return;
qbo = to_qxl_bo(bo);
qdev = to_qxl(qbo->tbo.base.dev);
return;
}
+ if (!mem)
+ return;
+
man = ttm_manager_type(bdev, mem->mem_type);
list_move_tail(&bo->lru, &man->lru[bo->priority]);
void ttm_mem_io_free(struct ttm_device *bdev,
struct ttm_resource *mem)
{
+ if (!mem)
+ return;
+
if (!mem->bus.offset && !mem->bus.addr)
return;
struct ttm_global ttm_glob;
EXPORT_SYMBOL(ttm_glob);
+struct dentry *ttm_debugfs_root;
+
static void ttm_global_release(void)
{
struct ttm_global *glob = &ttm_glob;
goto out;
ttm_pool_mgr_fini();
+ debugfs_remove(ttm_debugfs_root);
__free_page(glob->dummy_read_page);
memset(glob, 0, sizeof(*glob));
si_meminfo(&si);
+ ttm_debugfs_root = debugfs_create_dir("ttm", NULL);
+ if (IS_ERR(ttm_debugfs_root)) {
+ ret = PTR_ERR(ttm_debugfs_root);
+ ttm_debugfs_root = NULL;
+ goto out;
+ }
+
/* Limit the number of pages in the pool to about 50% of the total
* system memory.
*/
debugfs_create_atomic_t("buffer_objects", 0444, ttm_debugfs_root,
&glob->bo_count);
out:
+ if (ret && ttm_debugfs_root)
+ debugfs_remove(ttm_debugfs_root);
+ if (ret)
+ --ttm_glob_use_count;
mutex_unlock(&ttm_global_mutex);
return ret;
}
return tmp;
}
-struct dentry *ttm_debugfs_root;
-
-static int __init ttm_init(void)
-{
- ttm_debugfs_root = debugfs_create_dir("ttm", NULL);
- return 0;
-}
-
-static void __exit ttm_exit(void)
-{
- debugfs_remove(ttm_debugfs_root);
-}
-
-module_init(ttm_init);
-module_exit(ttm_exit);
-
MODULE_AUTHOR("Thomas Hellstrom, Jerome Glisse");
MODULE_DESCRIPTION("TTM memory manager subsystem (for DRM device)");
MODULE_LICENSE("GPL and additional rights");
struct drm_mm *mm = &rman->mm;
int ret;
+ if (!man)
+ return 0;
+
ttm_resource_manager_set_used(man, false);
ret = ttm_resource_manager_evict_all(bdev, man);
vc4_hdmi_cec_update_clk_div(vc4_hdmi);
if (vc4_hdmi->variant->external_irq_controller) {
- ret = devm_request_threaded_irq(&pdev->dev,
- platform_get_irq_byname(pdev, "cec-rx"),
- vc4_cec_irq_handler_rx_bare,
- vc4_cec_irq_handler_rx_thread, 0,
- "vc4 hdmi cec rx", vc4_hdmi);
+ ret = request_threaded_irq(platform_get_irq_byname(pdev, "cec-rx"),
+ vc4_cec_irq_handler_rx_bare,
+ vc4_cec_irq_handler_rx_thread, 0,
+ "vc4 hdmi cec rx", vc4_hdmi);
if (ret)
goto err_delete_cec_adap;
- ret = devm_request_threaded_irq(&pdev->dev,
- platform_get_irq_byname(pdev, "cec-tx"),
- vc4_cec_irq_handler_tx_bare,
- vc4_cec_irq_handler_tx_thread, 0,
- "vc4 hdmi cec tx", vc4_hdmi);
+ ret = request_threaded_irq(platform_get_irq_byname(pdev, "cec-tx"),
+ vc4_cec_irq_handler_tx_bare,
+ vc4_cec_irq_handler_tx_thread, 0,
+ "vc4 hdmi cec tx", vc4_hdmi);
if (ret)
- goto err_delete_cec_adap;
+ goto err_remove_cec_rx_handler;
} else {
HDMI_WRITE(HDMI_CEC_CPU_MASK_SET, 0xffffffff);
- ret = devm_request_threaded_irq(&pdev->dev, platform_get_irq(pdev, 0),
- vc4_cec_irq_handler,
- vc4_cec_irq_handler_thread, 0,
- "vc4 hdmi cec", vc4_hdmi);
+ ret = request_threaded_irq(platform_get_irq(pdev, 0),
+ vc4_cec_irq_handler,
+ vc4_cec_irq_handler_thread, 0,
+ "vc4 hdmi cec", vc4_hdmi);
if (ret)
goto err_delete_cec_adap;
}
ret = cec_register_adapter(vc4_hdmi->cec_adap, &pdev->dev);
if (ret < 0)
- goto err_delete_cec_adap;
+ goto err_remove_handlers;
return 0;
+err_remove_handlers:
+ if (vc4_hdmi->variant->external_irq_controller)
+ free_irq(platform_get_irq_byname(pdev, "cec-tx"), vc4_hdmi);
+ else
+ free_irq(platform_get_irq(pdev, 0), vc4_hdmi);
+
+err_remove_cec_rx_handler:
+ if (vc4_hdmi->variant->external_irq_controller)
+ free_irq(platform_get_irq_byname(pdev, "cec-rx"), vc4_hdmi);
+
err_delete_cec_adap:
cec_delete_adapter(vc4_hdmi->cec_adap);
static void vc4_hdmi_cec_exit(struct vc4_hdmi *vc4_hdmi)
{
+ struct platform_device *pdev = vc4_hdmi->pdev;
+
+ if (vc4_hdmi->variant->external_irq_controller) {
+ free_irq(platform_get_irq_byname(pdev, "cec-rx"), vc4_hdmi);
+ free_irq(platform_get_irq_byname(pdev, "cec-tx"), vc4_hdmi);
+ } else {
+ free_irq(platform_get_irq(pdev, 0), vc4_hdmi);
+ }
+
cec_unregister_adapter(vc4_hdmi->cec_adap);
}
#else
#include <drm/drm_ioctl.h>
#include <drm/drm_sysfs.h>
#include <drm/ttm/ttm_bo_driver.h>
+#include <drm/ttm/ttm_range_manager.h>
#include <drm/ttm/ttm_placement.h>
#include <generated/utsrelease.h>
resource_size_t vram_start;
resource_size_t vram_size;
resource_size_t prim_bb_mem;
- void __iomem *rmmio;
+ u32 __iomem *rmmio;
u32 *fifo_mem;
resource_size_t fifo_mem_size;
uint32_t fb_max_width;
ttm_bo_unpin(bo);
ttm_bo_unreserve(bo);
- ttm_bo_unpin(batch->otable_bo);
ttm_bo_put(batch->otable_bo);
batch->otable_bo = NULL;
}
depends on HID_LOGITECH
select POWER_SUPPLY
help
- Support for Logitech devices relyingon the HID++ Logitech specification
+ Support for Logitech devices relying on the HID++ Logitech specification
Say Y if you want support for Logitech devices relying on the HID++
specification. Such devices are the various Logitech Touchpads (T650,
cmd_base.cmd_v2.sensor_id = sensor_idx;
cmd_base.cmd_v2.length = 16;
- writeq(0x0, privdata->mmio + AMD_C2P_MSG2);
+ writeq(0x0, privdata->mmio + AMD_C2P_MSG1);
writel(cmd_base.ul, privdata->mmio + AMD_C2P_MSG0);
}
APPLE_RDESC_JIS },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_ANSI),
.driver_data = APPLE_HAS_FN },
+ { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_ANSI),
+ .driver_data = APPLE_HAS_FN },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_ISO),
.driver_data = APPLE_HAS_FN },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_ISO),
{
struct asus_kbd_leds *led = container_of(led_cdev, struct asus_kbd_leds,
cdev);
- if (led->brightness == brightness)
- return;
-
led->brightness = brightness;
schedule_work(&led->work);
}
int ret;
ret = ft260_get_system_config(hdev, &cfg);
- if (ret)
+ if (ret < 0)
return ret;
ft260_dbg("interface: 0x%02x\n", interface);
switch (cfg.chip_mode) {
case FT260_MODE_ALL:
case FT260_MODE_BOTH:
- if (interface == 1) {
+ if (interface == 1)
hid_info(hdev, "uart interface is not supported\n");
- return 0;
- }
- ret = 1;
+ else
+ ret = 1;
break;
case FT260_MODE_UART:
- if (interface == 0) {
- hid_info(hdev, "uart is unsupported on interface 0\n");
- ret = 0;
- }
+ hid_info(hdev, "uart interface is not supported\n");
break;
case FT260_MODE_I2C:
- if (interface == 1) {
- hid_info(hdev, "i2c is unsupported on interface 1\n");
- ret = 0;
- }
+ ret = 1;
break;
}
return ret;
if (ret < 0)
return ret;
- return scnprintf(buf, PAGE_SIZE, "%hi\n", *field);
+ return scnprintf(buf, PAGE_SIZE, "%d\n", *field);
}
static int ft260_word_show(struct hid_device *hdev, int id, u8 *cfg, int len,
if (ret < 0)
return ret;
- return scnprintf(buf, PAGE_SIZE, "%hi\n", le16_to_cpu(*field));
+ return scnprintf(buf, PAGE_SIZE, "%d\n", le16_to_cpu(*field));
}
#define FT260_ATTR_SHOW(name, reptype, id, type, func) \
static void ft260_remove(struct hid_device *hdev)
{
- int ret;
struct ft260_device *dev = hid_get_drvdata(hdev);
- ret = ft260_is_interface_enabled(hdev);
- if (ret <= 0)
+ if (!dev)
return;
sysfs_remove_group(&hdev->dev.kobj, &ft260_attr_group);
}
}
+static void hid_ishtp_cl_resume_handler(struct work_struct *work)
+{
+ struct ishtp_cl_data *client_data = container_of(work, struct ishtp_cl_data, resume_work);
+ struct ishtp_cl *hid_ishtp_cl = client_data->hid_ishtp_cl;
+
+ if (ishtp_wait_resume(ishtp_get_ishtp_device(hid_ishtp_cl))) {
+ client_data->suspended = false;
+ wake_up_interruptible(&client_data->ishtp_resume_wait);
+ }
+}
+
ishtp_print_log ishtp_hid_print_trace;
/**
init_waitqueue_head(&client_data->ishtp_resume_wait);
INIT_WORK(&client_data->work, hid_ishtp_cl_reset_handler);
+ INIT_WORK(&client_data->resume_work, hid_ishtp_cl_resume_handler);
+
ishtp_hid_print_trace = ishtp_trace_callback(cl_device);
hid_ishtp_trace(client_data, "%s hid_ishtp_cl %p\n", __func__,
hid_ishtp_cl);
- client_data->suspended = false;
+ schedule_work(&client_data->resume_work);
return 0;
}
int multi_packet_cnt;
struct work_struct work;
+ struct work_struct resume_work;
struct ishtp_cl_device *cl_device;
};
if (!device)
return 0;
- /*
- * When ISH needs hard reset, it is done asynchrnously, hence bus
- * resume will be called before full ISH resume
- */
- if (device->ishtp_dev->resume_flag)
- return 0;
-
driver = to_ishtp_cl_driver(dev->driver);
if (driver && driver->driver.pm) {
if (driver->driver.pm->resume)
EXPORT_SYMBOL(ishtp_device);
/**
+ * ishtp_wait_resume() - Wait for IPC resume
+ *
+ * Wait for IPC resume
+ *
+ * Return: resume complete or not
+ */
+bool ishtp_wait_resume(struct ishtp_device *dev)
+{
+ /* 50ms to get resume response */
+ #define WAIT_FOR_RESUME_ACK_MS 50
+
+ /* Waiting to get resume response */
+ if (dev->resume_flag)
+ wait_event_interruptible_timeout(dev->resume_wait,
+ !dev->resume_flag,
+ msecs_to_jiffies(WAIT_FOR_RESUME_ACK_MS));
+
+ return (!dev->resume_flag);
+}
+EXPORT_SYMBOL_GPL(ishtp_wait_resume);
+
+/**
* ishtp_get_pci_device() - Return PCI device dev pointer
* This interface is used to return PCI device pointer
* from ishtp_cl_device instance.
help
Say Y here if you want to support HID devices (from the USB
specification standpoint) that aren't strictly user interface
- devices, like monitor controls and Uninterruptable Power Supplies.
+ devices, like monitor controls and Uninterruptible Power Supplies.
This module supports these devices separately using a separate
event interface on /dev/usb/hiddevX (char 180:96 to 180:111).
int slot;
slot = input_mt_get_slot_by_key(input, hid_data->id);
+ if (slot < 0)
+ return;
+
input_mt_slot(input, slot);
input_mt_report_slot_state(input, MT_TOOL_FINGER, prox);
}
wacom_wac->shared->touch->product == 0xF6) {
input_dev->evbit[0] |= BIT_MASK(EV_SW);
__set_bit(SW_MUTE_DEVICE, input_dev->swbit);
- wacom_wac->shared->has_mute_touch_switch = true;
+ wacom_wac->has_mute_touch_switch = true;
}
fallthrough;
*/
mutex_lock(&vmbus_connection.channel_mutex);
+ list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
+ if (guid_equal(&channel->offermsg.offer.if_type,
+ &newchannel->offermsg.offer.if_type) &&
+ guid_equal(&channel->offermsg.offer.if_instance,
+ &newchannel->offermsg.offer.if_instance)) {
+ fnew = false;
+ newchannel->primary_channel = channel;
+ break;
+ }
+ }
+
init_vp_index(newchannel);
/* Remember the channels that should be cleaned up upon suspend. */
*/
atomic_dec(&vmbus_connection.offer_in_progress);
- list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
- if (guid_equal(&channel->offermsg.offer.if_type,
- &newchannel->offermsg.offer.if_type) &&
- guid_equal(&channel->offermsg.offer.if_instance,
- &newchannel->offermsg.offer.if_instance)) {
- fnew = false;
- break;
- }
- }
-
if (fnew) {
list_add_tail(&newchannel->listentry,
&vmbus_connection.chn_list);
/*
* Process the sub-channel.
*/
- newchannel->primary_channel = channel;
list_add_tail(&newchannel->sc_list, &channel->sc_list);
}
}
/*
+ * Check if CPUs used by other channels of the same device.
+ * It should only be called by init_vp_index().
+ */
+static bool hv_cpuself_used(u32 cpu, struct vmbus_channel *chn)
+{
+ struct vmbus_channel *primary = chn->primary_channel;
+ struct vmbus_channel *sc;
+
+ lockdep_assert_held(&vmbus_connection.channel_mutex);
+
+ if (!primary)
+ return false;
+
+ if (primary->target_cpu == cpu)
+ return true;
+
+ list_for_each_entry(sc, &primary->sc_list, sc_list)
+ if (sc != chn && sc->target_cpu == cpu)
+ return true;
+
+ return false;
+}
+
+/*
* We use this state to statically distribute the channel interrupt load.
*/
static int next_numa_node_id;
static void init_vp_index(struct vmbus_channel *channel)
{
bool perf_chn = hv_is_perf_channel(channel);
+ u32 i, ncpu = num_online_cpus();
cpumask_var_t available_mask;
struct cpumask *alloced_mask;
u32 target_cpu;
return;
}
- while (true) {
- numa_node = next_numa_node_id++;
- if (numa_node == nr_node_ids) {
- next_numa_node_id = 0;
- continue;
+ for (i = 1; i <= ncpu + 1; i++) {
+ while (true) {
+ numa_node = next_numa_node_id++;
+ if (numa_node == nr_node_ids) {
+ next_numa_node_id = 0;
+ continue;
+ }
+ if (cpumask_empty(cpumask_of_node(numa_node)))
+ continue;
+ break;
+ }
+ alloced_mask = &hv_context.hv_numa_map[numa_node];
+
+ if (cpumask_weight(alloced_mask) ==
+ cpumask_weight(cpumask_of_node(numa_node))) {
+ /*
+ * We have cycled through all the CPUs in the node;
+ * reset the alloced map.
+ */
+ cpumask_clear(alloced_mask);
}
- if (cpumask_empty(cpumask_of_node(numa_node)))
- continue;
- break;
- }
- alloced_mask = &hv_context.hv_numa_map[numa_node];
- if (cpumask_weight(alloced_mask) ==
- cpumask_weight(cpumask_of_node(numa_node))) {
- /*
- * We have cycled through all the CPUs in the node;
- * reset the alloced map.
- */
- cpumask_clear(alloced_mask);
- }
+ cpumask_xor(available_mask, alloced_mask,
+ cpumask_of_node(numa_node));
- cpumask_xor(available_mask, alloced_mask, cpumask_of_node(numa_node));
+ target_cpu = cpumask_first(available_mask);
+ cpumask_set_cpu(target_cpu, alloced_mask);
- target_cpu = cpumask_first(available_mask);
- cpumask_set_cpu(target_cpu, alloced_mask);
+ if (channel->offermsg.offer.sub_channel_index >= ncpu ||
+ i > ncpu || !hv_cpuself_used(target_cpu, channel))
+ break;
+ }
channel->target_cpu = target_cpu;
status = readb(i2c->base + MPC_I2C_SR);
if (status & CSR_MIF) {
- /* Read again to allow register to stabilise */
- status = readb(i2c->base + MPC_I2C_SR);
+ /* Wait up to 100us for transfer to properly complete */
+ readb_poll_timeout(i2c->base + MPC_I2C_SR, status, !(status & CSR_MCF), 0, 100);
writeb(0, i2c->base + MPC_I2C_SR);
mpc_i2c_do_intr(i2c, status);
return IRQ_HANDLED;
return ret;
}
+static int cma_init_conn_qp(struct rdma_id_private *id_priv, struct ib_qp *qp)
+{
+ struct ib_qp_attr qp_attr;
+ int qp_attr_mask, ret;
+
+ qp_attr.qp_state = IB_QPS_INIT;
+ ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask);
+ if (ret)
+ return ret;
+
+ return ib_modify_qp(qp, &qp_attr, qp_attr_mask);
+}
+
int rdma_create_qp(struct rdma_cm_id *id, struct ib_pd *pd,
struct ib_qp_init_attr *qp_init_attr)
{
struct rdma_id_private *id_priv;
struct ib_qp *qp;
- int ret = 0;
+ int ret;
id_priv = container_of(id, struct rdma_id_private, id);
if (id->device != pd->device) {
if (id->qp_type == IB_QPT_UD)
ret = cma_init_ud_qp(id_priv, qp);
+ else
+ ret = cma_init_conn_qp(id_priv, qp);
if (ret)
goto out_destroy;
if (!chip_ctx)
return -ENOMEM;
chip_ctx->chip_num = bp->chip_num;
+ chip_ctx->hw_stats_size = bp->hw_ring_stats_size;
rdev->chip_ctx = chip_ctx;
/* rest members to follow eventually */
dma_addr_t dma_map,
u32 *fw_stats_ctx_id)
{
+ struct bnxt_qplib_chip_ctx *chip_ctx = rdev->chip_ctx;
struct hwrm_stat_ctx_alloc_output resp = {0};
struct hwrm_stat_ctx_alloc_input req = {0};
struct bnxt_en_dev *en_dev = rdev->en_dev;
bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_STAT_CTX_ALLOC, -1, -1);
req.update_period_ms = cpu_to_le32(1000);
req.stats_dma_addr = cpu_to_le64(dma_map);
- req.stats_dma_length = cpu_to_le16(sizeof(struct ctx_hw_stats_ext));
+ req.stats_dma_length = cpu_to_le16(chip_ctx->hw_stats_size);
req.stat_ctx_flags = STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_ROCE;
bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp,
sizeof(resp), DFLT_HWRM_CMD_TIMEOUT);
static void bnxt_qplib_free_stats_ctx(struct pci_dev *pdev,
struct bnxt_qplib_stats *stats);
static int bnxt_qplib_alloc_stats_ctx(struct pci_dev *pdev,
+ struct bnxt_qplib_chip_ctx *cctx,
struct bnxt_qplib_stats *stats);
/* PBL */
goto fail;
stats_alloc:
/* Stats */
- rc = bnxt_qplib_alloc_stats_ctx(res->pdev, &ctx->stats);
+ rc = bnxt_qplib_alloc_stats_ctx(res->pdev, res->cctx, &ctx->stats);
if (rc)
goto fail;
}
static int bnxt_qplib_alloc_stats_ctx(struct pci_dev *pdev,
+ struct bnxt_qplib_chip_ctx *cctx,
struct bnxt_qplib_stats *stats)
{
memset(stats, 0, sizeof(*stats));
stats->fw_id = -1;
- /* 128 byte aligned context memory is required only for 57500.
- * However making this unconditional, it does not harm previous
- * generation.
- */
- stats->size = ALIGN(sizeof(struct ctx_hw_stats), 128);
+ stats->size = cctx->hw_stats_size;
stats->dma = dma_alloc_coherent(&pdev->dev, stats->size,
&stats->dma_map, GFP_KERNEL);
if (!stats->dma) {
u16 chip_num;
u8 chip_rev;
u8 chip_metal;
+ u16 hw_stats_size;
struct bnxt_qplib_drv_modes modes;
};
return !err || err == -ENODATA ? npolled : err;
}
+void c4iw_cq_rem_ref(struct c4iw_cq *chp)
+{
+ if (refcount_dec_and_test(&chp->refcnt))
+ complete(&chp->cq_rel_comp);
+}
+
int c4iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata)
{
struct c4iw_cq *chp;
chp = to_c4iw_cq(ib_cq);
xa_erase_irq(&chp->rhp->cqs, chp->cq.cqid);
- refcount_dec(&chp->refcnt);
- wait_event(chp->wait, !refcount_read(&chp->refcnt));
+ c4iw_cq_rem_ref(chp);
+ wait_for_completion(&chp->cq_rel_comp);
ucontext = rdma_udata_to_drv_context(udata, struct c4iw_ucontext,
ibucontext);
spin_lock_init(&chp->lock);
spin_lock_init(&chp->comp_handler_lock);
refcount_set(&chp->refcnt, 1);
- init_waitqueue_head(&chp->wait);
+ init_completion(&chp->cq_rel_comp);
ret = xa_insert_irq(&rhp->cqs, chp->cq.cqid, chp, GFP_KERNEL);
if (ret)
goto err_destroy_cq;
break;
}
done:
- if (refcount_dec_and_test(&chp->refcnt))
- wake_up(&chp->wait);
+ c4iw_cq_rem_ref(chp);
c4iw_qp_rem_ref(&qhp->ibqp);
out:
return;
spin_lock_irqsave(&chp->comp_handler_lock, flag);
(*chp->ibcq.comp_handler)(&chp->ibcq, chp->ibcq.cq_context);
spin_unlock_irqrestore(&chp->comp_handler_lock, flag);
- if (refcount_dec_and_test(&chp->refcnt))
- wake_up(&chp->wait);
+ c4iw_cq_rem_ref(chp);
} else {
pr_debug("unknown cqid 0x%x\n", qid);
xa_unlock_irqrestore(&dev->cqs, flag);
spinlock_t lock;
spinlock_t comp_handler_lock;
refcount_t refcnt;
- wait_queue_head_t wait;
+ struct completion cq_rel_comp;
struct c4iw_wr_wait *wr_waitp;
};
struct ib_mr *c4iw_get_dma_mr(struct ib_pd *pd, int acc);
int c4iw_dereg_mr(struct ib_mr *ib_mr, struct ib_udata *udata);
int c4iw_destroy_cq(struct ib_cq *ib_cq, struct ib_udata *udata);
+void c4iw_cq_rem_ref(struct c4iw_cq *chp);
int c4iw_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
struct ib_udata *udata);
int c4iw_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags);
hr_cmd->context =
kcalloc(hr_cmd->max_cmds, sizeof(*hr_cmd->context), GFP_KERNEL);
- if (!hr_cmd->context)
+ if (!hr_cmd->context) {
+ hr_dev->cmd_mod = 0;
return -ENOMEM;
+ }
for (i = 0; i < hr_cmd->max_cmds; ++i) {
hr_cmd->context[i].token = i;
spin_lock_init(&hr_cmd->context_lock);
hr_cmd->use_events = 1;
- down(&hr_cmd->poll_sem);
return 0;
}
kfree(hr_cmd->context);
hr_cmd->use_events = 0;
-
- up(&hr_cmd->poll_sem);
}
struct hns_roce_cmd_mailbox *
if (hr_dev->cmd_mod) {
ret = hns_roce_cmd_use_events(hr_dev);
- if (ret) {
+ if (ret)
dev_warn(dev,
"Cmd event mode failed, set back to poll!\n");
- hns_roce_cmd_use_polling(hr_dev);
- }
}
ret = hns_roce_init_hem(hr_dev);
* parses fpm commit info and copy base value
* of hmc objects in hmc_info
*/
-static enum irdma_status_code
+static void
irdma_sc_parse_fpm_commit_buf(struct irdma_sc_dev *dev, __le64 *buf,
struct irdma_hmc_obj_info *info, u32 *sd)
{
else
*sd = (u32)(size >> 21);
- return 0;
}
/**
* @dev: sc device struct
* @count: allocate count
*/
-enum irdma_status_code irdma_sc_repost_aeq_entries(struct irdma_sc_dev *dev, u32 count)
+void irdma_sc_repost_aeq_entries(struct irdma_sc_dev *dev, u32 count)
{
writel(count, dev->hw_regs[IRDMA_AEQALLOC]);
-
- return 0;
}
/**
ret_code = irdma_sc_commit_fpm_val(dev->cqp, 0, hmc_info->hmc_fn_id,
&commit_fpm_mem, true, wait_type);
if (!ret_code)
- ret_code = irdma_sc_parse_fpm_commit_buf(dev, dev->fpm_commit_buf,
- hmc_info->hmc_obj,
- &hmc_info->sd_table.sd_cnt);
+ irdma_sc_parse_fpm_commit_buf(dev, dev->fpm_commit_buf,
+ hmc_info->hmc_obj,
+ &hmc_info->sd_table.sd_cnt);
print_hex_dump_debug("HMC: COMMIT FPM BUFFER", DUMP_PREFIX_OFFSET, 16,
8, commit_fpm_mem.va, IRDMA_COMMIT_FPM_BUF_SIZE,
false);
* irdma_set_hw_rsrc - set hw memory resources.
* @rf: RDMA PCI function
*/
-static u32 irdma_set_hw_rsrc(struct irdma_pci_f *rf)
+static void irdma_set_hw_rsrc(struct irdma_pci_f *rf)
{
rf->allocated_qps = (void *)(rf->mem_rsrc +
(sizeof(struct irdma_arp_entry) * rf->arp_table_size));
spin_lock_init(&rf->arp_lock);
spin_lock_init(&rf->qptable_lock);
spin_lock_init(&rf->qh_list_lock);
-
- return 0;
}
/**
rf->arp_table = (struct irdma_arp_entry *)rf->mem_rsrc;
- ret = irdma_set_hw_rsrc(rf);
- if (ret)
- goto set_hw_rsrc_fail;
+ irdma_set_hw_rsrc(rf);
set_bit(0, rf->allocated_mrs);
set_bit(0, rf->allocated_qps);
return 0;
-set_hw_rsrc_fail:
- kfree(rf->mem_rsrc);
- rf->mem_rsrc = NULL;
mem_rsrc_kzalloc_fail:
kfree(rf->allocated_ws_nodes);
rf->allocated_ws_nodes = NULL;
pr_debug("INIT: Gen2 PF[%d] device remove success\n", PCI_FUNC(pf->pdev->devfn));
}
-static void irdma_fill_device_info(struct irdma_device *iwdev, struct ice_pf *pf)
+static void irdma_fill_device_info(struct irdma_device *iwdev, struct ice_pf *pf,
+ struct ice_vsi *vsi)
{
struct irdma_pci_f *rf = iwdev->rf;
- struct ice_vsi *vsi = ice_get_main_vsi(pf);
rf->cdev = pf;
rf->gen_ops.register_qset = irdma_lan_register_qset;
struct iidc_auxiliary_dev,
adev);
struct ice_pf *pf = iidc_adev->pf;
+ struct ice_vsi *vsi = ice_get_main_vsi(pf);
struct iidc_qos_params qos_info = {};
struct irdma_device *iwdev;
struct irdma_pci_f *rf;
struct irdma_l2params l2params = {};
int err;
+ if (!vsi)
+ return -EIO;
iwdev = ib_alloc_device(irdma_device, ibdev);
if (!iwdev)
return -ENOMEM;
return -ENOMEM;
}
- irdma_fill_device_info(iwdev, pf);
+ irdma_fill_device_info(iwdev, pf, vsi);
rf = iwdev->rf;
if (irdma_ctrl_init_hw(rf)) {
struct irdma_aeq_init_info *info);
enum irdma_status_code irdma_sc_get_next_aeqe(struct irdma_sc_aeq *aeq,
struct irdma_aeqe_info *info);
-enum irdma_status_code irdma_sc_repost_aeq_entries(struct irdma_sc_dev *dev,
- u32 count);
+void irdma_sc_repost_aeq_entries(struct irdma_sc_dev *dev, u32 count);
void irdma_sc_pd_init(struct irdma_sc_dev *dev, struct irdma_sc_pd *pd, u32 pd_id,
int abi_ver);
enum irdma_status_code irdma_uk_post_receive(struct irdma_qp_uk *qp,
struct irdma_post_rq_info *info)
{
- u32 total_size = 0, wqe_idx, i, byte_off;
+ u32 wqe_idx, i, byte_off;
u32 addl_frag_cnt;
__le64 *wqe;
u64 hdr;
if (qp->max_rq_frag_cnt < info->num_sges)
return IRDMA_ERR_INVALID_FRAG_COUNT;
- for (i = 0; i < info->num_sges; i++)
- total_size += info->sg_list[i].len;
-
wqe = irdma_qp_get_next_recv_wqe(qp, &wqe_idx);
if (!wqe)
return IRDMA_ERR_QP_TOOMANY_WRS_POSTED;
* @iwqp: qp ptr
* @init_info: initialize info to return
*/
-static int irdma_setup_virt_qp(struct irdma_device *iwdev,
+static void irdma_setup_virt_qp(struct irdma_device *iwdev,
struct irdma_qp *iwqp,
struct irdma_qp_init_info *init_info)
{
init_info->sq_pa = qpmr->sq_pbl.addr;
init_info->rq_pa = qpmr->rq_pbl.addr;
}
-
- return 0;
}
/**
}
}
init_info.qp_uk_init_info.abi_ver = iwpd->sc_pd.abi_ver;
- err_code = irdma_setup_virt_qp(iwdev, iwqp, &init_info);
+ irdma_setup_virt_qp(iwdev, iwqp, &init_info);
} else {
init_info.qp_uk_init_info.abi_ver = IRDMA_ABI_VER;
err_code = irdma_setup_kmode_qp(iwdev, iwqp, &init_info, init_attr);
*/
spin_unlock_irq(&ent->lock);
need_delay = need_resched() || someone_adding(cache) ||
- time_after(jiffies,
- READ_ONCE(cache->last_add) + 300 * HZ);
+ !time_after(jiffies,
+ READ_ONCE(cache->last_add) + 300 * HZ);
spin_lock_irq(&ent->lock);
if (ent->disabled)
goto out;
int num_buf;
void *vaddr;
int err;
+ int i;
umem = ib_umem_get(pd->ibpd.device, start, length, access);
if (IS_ERR(umem)) {
- pr_warn("err %d from rxe_umem_get\n",
- (int)PTR_ERR(umem));
+ pr_warn("%s: Unable to pin memory region err = %d\n",
+ __func__, (int)PTR_ERR(umem));
err = PTR_ERR(umem);
- goto err1;
+ goto err_out;
}
mr->umem = umem;
err = rxe_mr_alloc(mr, num_buf);
if (err) {
- pr_warn("err %d from rxe_mr_alloc\n", err);
- ib_umem_release(umem);
- goto err1;
+ pr_warn("%s: Unable to allocate memory for map\n",
+ __func__);
+ goto err_release_umem;
}
mr->page_shift = PAGE_SHIFT;
vaddr = page_address(sg_page_iter_page(&sg_iter));
if (!vaddr) {
- pr_warn("null vaddr\n");
- ib_umem_release(umem);
+ pr_warn("%s: Unable to get virtual address\n",
+ __func__);
err = -ENOMEM;
- goto err1;
+ goto err_cleanup_map;
}
buf->addr = (uintptr_t)vaddr;
return 0;
-err1:
+err_cleanup_map:
+ for (i = 0; i < mr->num_map; i++)
+ kfree(mr->map[i]);
+ kfree(mr->map);
+err_release_umem:
+ ib_umem_release(umem);
+err_out:
return err;
}
iph->version = IPVERSION;
iph->ihl = sizeof(struct iphdr) >> 2;
+ iph->tot_len = htons(skb->len);
iph->frag_off = df;
iph->protocol = proto;
iph->tos = tos;
pr_warn("%s: invalid num_sge in SRQ entry\n", __func__);
return RESPST_ERR_MALFORMED_WQE;
}
- size = sizeof(wqe) + wqe->dma.num_sge*sizeof(struct rxe_sge);
+ size = sizeof(*wqe) + wqe->dma.num_sge*sizeof(struct rxe_sge);
memcpy(&qp->resp.srq_wqe, wqe, size);
qp->resp.wqe = &qp->resp.srq_wqe.wqe;
{
struct icc_path **ptr, *path;
- ptr = devres_alloc(devm_icc_release, sizeof(**ptr), GFP_KERNEL);
+ ptr = devres_alloc(devm_icc_release, sizeof(*ptr), GFP_KERNEL);
if (!ptr)
return ERR_PTR(-ENOMEM);
}
node->avg_bw = node->init_avg;
node->peak_bw = node->init_peak;
+
+ if (provider->pre_aggregate)
+ provider->pre_aggregate(node);
+
if (provider->aggregate)
provider->aggregate(node, 0, node->init_avg, node->init_peak,
&node->avg_bw, &node->peak_bw);
+
provider->set(node, node);
node->avg_bw = 0;
node->peak_bw = 0;
dev_dbg(p->dev, "interconnect provider is in synced state\n");
list_for_each_entry(n, &p->nodes, node_list) {
if (n->init_avg || n->init_peak) {
+ n->init_avg = 0;
+ n->init_peak = 0;
aggregate_requests(n);
p->set(n, n);
}
{
size_t i;
struct qcom_icc_node *qn;
+ struct qcom_icc_provider *qp;
qn = node->data;
+ qp = to_qcom_provider(node->provider);
for (i = 0; i < QCOM_ICC_NUM_BUCKETS; i++) {
qn->sum_avg[i] = 0;
qn->max_peak[i] = 0;
}
+
+ for (i = 0; i < qn->num_bcms; i++)
+ qcom_icc_bcm_voter_add(qp->voter, qn->bcms[i]);
}
EXPORT_SYMBOL_GPL(qcom_icc_pre_aggregate);
{
size_t i;
struct qcom_icc_node *qn;
- struct qcom_icc_provider *qp;
qn = node->data;
- qp = to_qcom_provider(node->provider);
if (!tag)
tag = QCOM_ICC_TAG_ALWAYS;
qn->sum_avg[i] += avg_bw;
qn->max_peak[i] = max_t(u32, qn->max_peak[i], peak_bw);
}
+
+ if (node->init_avg || node->init_peak) {
+ qn->sum_avg[i] = max_t(u64, qn->sum_avg[i], node->init_avg);
+ qn->max_peak[i] = max_t(u64, qn->max_peak[i], node->init_peak);
+ }
}
*agg_avg += avg_bw;
*agg_peak = max_t(u32, *agg_peak, peak_bw);
- for (i = 0; i < qn->num_bcms; i++)
- qcom_icc_bcm_voter_add(qp->voter, qn->bcms[i]);
-
return 0;
}
EXPORT_SYMBOL_GPL(qcom_icc_aggregate);
int qcom_icc_set(struct icc_node *src, struct icc_node *dst)
{
struct qcom_icc_provider *qp;
- struct qcom_icc_node *qn;
struct icc_node *node;
if (!src)
node = src;
qp = to_qcom_provider(node->provider);
- qn = node->data;
-
- qn->sum_avg[QCOM_ICC_BUCKET_AMC] = max_t(u64, qn->sum_avg[QCOM_ICC_BUCKET_AMC],
- node->avg_bw);
- qn->max_peak[QCOM_ICC_BUCKET_AMC] = max_t(u64, qn->max_peak[QCOM_ICC_BUCKET_AMC],
- node->peak_bw);
qcom_icc_bcm_voter_commit(qp->voter);
switch (idx) {
case CMDQ_ERR_CERROR_ABT_IDX:
dev_err(smmu->dev, "retrying command fetch\n");
+ return;
case CMDQ_ERR_CERROR_NONE_IDX:
return;
case CMDQ_ERR_CERROR_ATC_INV_IDX:
ret = iommu_device_register(&qcom_iommu->iommu, &qcom_iommu_ops, dev);
if (ret) {
dev_err(dev, "Failed to register iommu\n");
- goto err_sysfs_remove;
+ return ret;
}
- ret = bus_set_iommu(&platform_bus_type, &qcom_iommu_ops);
- if (ret)
- goto err_unregister_device;
+ bus_set_iommu(&platform_bus_type, &qcom_iommu_ops);
if (qcom_iommu->local_base) {
pm_runtime_get_sync(dev);
}
return 0;
-
-err_unregister_device:
- iommu_device_unregister(&qcom_iommu->iommu);
-
-err_sysfs_remove:
- iommu_device_sysfs_remove(&qcom_iommu->iommu);
- return ret;
}
static int qcom_iommu_device_remove(struct platform_device *pdev)
return 0;
}
-static void domain_context_clear_one(struct intel_iommu *iommu, u8 bus, u8 devfn)
+static void domain_context_clear_one(struct device_domain_info *info, u8 bus, u8 devfn)
{
- unsigned long flags;
+ struct intel_iommu *iommu = info->iommu;
struct context_entry *context;
+ unsigned long flags;
u16 did_old;
if (!iommu)
spin_unlock_irqrestore(&iommu->lock, flags);
return;
}
- did_old = context_domain_id(context);
+
+ if (sm_supported(iommu)) {
+ if (hw_pass_through && domain_type_is_si(info->domain))
+ did_old = FLPT_DEFAULT_DID;
+ else
+ did_old = info->domain->iommu_did[iommu->seq_id];
+ } else {
+ did_old = context_domain_id(context);
+ }
+
context_clear_entry(context);
__iommu_flush_cache(iommu, context, sizeof(*context));
spin_unlock_irqrestore(&iommu->lock, flags);
0,
0,
DMA_TLB_DSI_FLUSH);
+
+ __iommu_flush_dev_iotlb(info, 0, MAX_AGAW_PFN_WIDTH);
}
static inline void unlink_domain_info(struct device_domain_info *info)
static int domain_context_clear_one_cb(struct pci_dev *pdev, u16 alias, void *opaque)
{
- struct intel_iommu *iommu = opaque;
+ struct device_domain_info *info = opaque;
- domain_context_clear_one(iommu, PCI_BUS_NUM(alias), alias & 0xff);
+ domain_context_clear_one(info, PCI_BUS_NUM(alias), alias & 0xff);
return 0;
}
* devices, unbinding the driver from any one of them will possibly leave
* the others unable to operate.
*/
-static void domain_context_clear(struct intel_iommu *iommu, struct device *dev)
+static void domain_context_clear(struct device_domain_info *info)
{
- if (!iommu || !dev || !dev_is_pci(dev))
+ if (!info->iommu || !info->dev || !dev_is_pci(info->dev))
return;
- pci_for_each_dma_alias(to_pci_dev(dev), &domain_context_clear_one_cb, iommu);
+ pci_for_each_dma_alias(to_pci_dev(info->dev),
+ &domain_context_clear_one_cb, info);
}
static void __dmar_remove_one_dev_info(struct device_domain_info *info)
iommu = info->iommu;
domain = info->domain;
- if (info->dev) {
+ if (info->dev && !dev_is_real_dma_subdevice(info->dev)) {
if (dev_is_pci(info->dev) && sm_supported(iommu))
intel_pasid_tear_down_entry(iommu, info->dev,
PASID_RID2PASID, false);
iommu_disable_dev_iotlb(info);
- if (!dev_is_real_dma_subdevice(info->dev))
- domain_context_clear(iommu, info->dev);
+ domain_context_clear(info);
intel_pasid_free_table(info->dev);
}
}
#define DT_HI_MASK GENMASK_ULL(39, 32)
+#define DTE_BASE_HI_MASK GENMASK(11, 4)
#define DT_SHIFT 28
static inline phys_addr_t rk_dte_addr_phys_v2(u32 addr)
{
- return (phys_addr_t)(addr & RK_DTE_PT_ADDRESS_MASK) |
- ((addr & DT_HI_MASK) << DT_SHIFT);
+ u64 addr64 = addr;
+ return (phys_addr_t)(addr64 & RK_DTE_PT_ADDRESS_MASK) |
+ ((addr64 & DTE_BASE_HI_MASK) << DT_SHIFT);
}
static inline u32 rk_dma_addr_dte_v2(dma_addr_t dt_dma)
/*
* When the device is faulty, it is not necessary to
* handle write error.
- * For failfast, this is the only remaining device,
- * We need to retry the write without FailFast.
*/
if (!test_bit(Faulty, &rdev->flags))
set_bit(R1BIO_WriteError, &r1_bio->state);
/*
* When the device is faulty, it is not necessary to
* handle write error.
- * For failfast, this is the only remaining device,
- * We need to retry the write without FailFast.
*/
if (!test_bit(Faulty, &rdev->flags))
set_bit(R10BIO_WriteError, &r10_bio->state);
else {
+ /* Fail the request */
+ set_bit(R10BIO_Degraded, &r10_bio->state);
r10_bio->devs[slot].bio = NULL;
to_put = bio;
dec_rdev = 1;
struct media_request *req)
{
struct vb2_buffer *vb;
+ enum vb2_buffer_state orig_state;
int ret;
if (q->error) {
* Add to the queued buffers list, a buffer will stay on it until
* dequeued in dqbuf.
*/
+ orig_state = vb->state;
list_add_tail(&vb->queued_entry, &q->queued_list);
q->queued_count++;
q->waiting_for_buffers = false;
if (q->streaming && !q->start_streaming_called &&
q->queued_count >= q->min_buffers_needed) {
ret = vb2_start_streaming(q);
- if (ret)
+ if (ret) {
+ /*
+ * Since vb2_core_qbuf will return with an error,
+ * we should return it to state DEQUEUED since
+ * the error indicates that the buffer wasn't queued.
+ */
+ list_del(&vb->queued_entry);
+ q->queued_count--;
+ vb->state = orig_state;
return ret;
+ }
}
dprintk(q, 2, "qbuf of buffer %d succeeded\n", vb->index);
int ret;
for_each_acpi_dev_match(adev, cfg->hid, NULL, -1) {
- if (!adev->status.enabled) {
- acpi_dev_put(adev);
+ if (!adev->status.enabled)
continue;
- }
if (bridge->n_sensors >= CIO2_NUM_PORTS) {
acpi_dev_put(adev);
}
sensor = &bridge->sensors[bridge->n_sensors];
- sensor->adev = adev;
strscpy(sensor->name, cfg->hid, sizeof(sensor->name));
ret = cio2_bridge_read_acpi_buffer(adev, "SSDB",
goto err_free_swnodes;
}
+ sensor->adev = acpi_dev_get(adev);
adev->fwnode.secondary = fwnode;
dev_info(&cio2->dev, "Found supported sensor %s\n",
com.cmd.hdr.Opcode = CMD_CONFIGURE_FREE_BUFFER;
com.cmd.hdr.Length = 6;
- memcpy(&com.cmd.ConfigureBuffers.config, config, 6);
+ memcpy(&com.cmd.ConfigureFreeBuffers.config, config, 6);
com.in_len = 6;
com.out_len = 0;
struct FW_CONFIGURE_FREE_BUFFERS {
struct FW_HEADER hdr;
- u8 UVI1_BufferLength;
- u8 UVI2_BufferLength;
- u8 TVO_BufferLength;
- u8 AUD1_BufferLength;
- u8 AUD2_BufferLength;
- u8 TVA_BufferLength;
+ struct {
+ u8 UVI1_BufferLength;
+ u8 UVI2_BufferLength;
+ u8 TVO_BufferLength;
+ u8 AUD1_BufferLength;
+ u8 AUD2_BufferLength;
+ u8 TVA_BufferLength;
+ } __packed config;
} __attribute__ ((__packed__));
struct FW_CONFIGURE_UART {
select VIDEOBUF2_DMA_CONTIG
select REGMAP_MMIO
select V4L2_FWNODE
+ select VIDEO_ATMEL_ISC_BASE
help
This module makes the ATMEL Image Sensor Controller available
as a v4l2 device.
select VIDEOBUF2_DMA_CONTIG
select REGMAP_MMIO
select V4L2_FWNODE
+ select VIDEO_ATMEL_ISC_BASE
help
This module makes the ATMEL eXtended Image Sensor Controller
available as a v4l2 device.
+config VIDEO_ATMEL_ISC_BASE
+ tristate
+ default n
+ help
+ ATMEL ISC and XISC common code base.
+
config VIDEO_ATMEL_ISI
tristate "ATMEL Image Sensor Interface (ISI) support"
depends on VIDEO_V4L2 && OF
# SPDX-License-Identifier: GPL-2.0-only
-atmel-isc-objs = atmel-sama5d2-isc.o atmel-isc-base.o
-atmel-xisc-objs = atmel-sama7g5-isc.o atmel-isc-base.o
+atmel-isc-objs = atmel-sama5d2-isc.o
+atmel-xisc-objs = atmel-sama7g5-isc.o
obj-$(CONFIG_VIDEO_ATMEL_ISI) += atmel-isi.o
+obj-$(CONFIG_VIDEO_ATMEL_ISC_BASE) += atmel-isc-base.o
obj-$(CONFIG_VIDEO_ATMEL_ISC) += atmel-isc.o
obj-$(CONFIG_VIDEO_ATMEL_XISC) += atmel-xisc.o
return 0;
}
+EXPORT_SYMBOL_GPL(isc_clk_init);
void isc_clk_cleanup(struct isc_device *isc)
{
clk_unregister(isc_clk->clk);
}
}
+EXPORT_SYMBOL_GPL(isc_clk_cleanup);
static int isc_queue_setup(struct vb2_queue *vq,
unsigned int *nbuffers, unsigned int *nplanes,
return ret;
}
+EXPORT_SYMBOL_GPL(isc_interrupt);
static void isc_hist_count(struct isc_device *isc, u32 *min, u32 *max)
{
.unbind = isc_async_unbind,
.complete = isc_async_complete,
};
+EXPORT_SYMBOL_GPL(isc_async_ops);
void isc_subdev_cleanup(struct isc_device *isc)
{
INIT_LIST_HEAD(&isc->subdev_entities);
}
+EXPORT_SYMBOL_GPL(isc_subdev_cleanup);
int isc_pipeline_init(struct isc_device *isc)
{
return 0;
}
+EXPORT_SYMBOL_GPL(isc_pipeline_init);
/* regmap configuration */
#define ATMEL_ISC_REG_MAX 0xd5c
.val_bits = 32,
.max_register = ATMEL_ISC_REG_MAX,
};
+EXPORT_SYMBOL_GPL(isc_regmap_config);
+MODULE_AUTHOR("Songjun Wu");
+MODULE_AUTHOR("Eugen Hristev");
+MODULE_DESCRIPTION("Atmel ISC common code base");
+MODULE_LICENSE("GPL v2");
} else {
/* read */
requesttype = (USB_TYPE_VENDOR | USB_DIR_IN);
- pipe = usb_rcvctrlpipe(d->udev, 0);
+
+ /*
+ * Zero-length transfers must use usb_sndctrlpipe() and
+ * rtl28xxu_identify_state() uses a zero-length i2c read
+ * command to determine the chip type.
+ */
+ if (req->size)
+ pipe = usb_rcvctrlpipe(d->udev, 0);
+ else
+ pipe = usb_sndctrlpipe(d->udev, 0);
}
ret = usb_control_msg(d->udev, pipe, 0, requesttype, req->value,
static int rtl28xxu_identify_state(struct dvb_usb_device *d, const char **name)
{
struct rtl28xxu_dev *dev = d_to_priv(d);
- u8 buf[1];
int ret;
- struct rtl28xxu_req req_demod_i2c = {0x0020, CMD_I2C_DA_RD, 1, buf};
+ struct rtl28xxu_req req_demod_i2c = {0x0020, CMD_I2C_DA_RD, 0, NULL};
dev_dbg(&d->intf->dev, "\n");
}
/*
- * If the 'label' property is not present for the AT24 EEPROM,
- * then nvmem_config.id is initialised to NVMEM_DEVID_AUTO,
- * and this will append the 'devid' to the name of the NVMEM
- * device. This is purely legacy and the AT24 driver has always
- * defaulted to this. However, if the 'label' property is
- * present then this means that the name is specified by the
- * firmware and this name should be used verbatim and so it is
- * not necessary to append the 'devid'.
+ * We initialize nvmem_config.id to NVMEM_DEVID_AUTO even if the
+ * label property is set as some platform can have multiple eeproms
+ * with same label and we can not register each of those with same
+ * label. Failing to register those eeproms trigger cascade failure
+ * on such platform.
*/
+ nvmem_config.id = NVMEM_DEVID_AUTO;
+
if (device_property_present(dev, "label")) {
- nvmem_config.id = NVMEM_DEVID_NONE;
err = device_property_read_string(dev, "label",
&nvmem_config.name);
if (err)
return err;
} else {
- nvmem_config.id = NVMEM_DEVID_AUTO;
nvmem_config.name = dev_name(dev);
}
#include <linux/errno.h>
#include <linux/hdreg.h>
#include <linux/kdev_t.h>
+#include <linux/kref.h>
#include <linux/blkdev.h>
#include <linux/cdev.h>
#include <linux/mutex.h>
#define MMC_BLK_CMD23 (1 << 0) /* Can do SET_BLOCK_COUNT for multiblock */
#define MMC_BLK_REL_WR (1 << 1) /* MMC Reliable write support */
- unsigned int usage;
+ struct kref kref;
unsigned int read_only;
unsigned int part_type;
unsigned int reset_done;
mutex_lock(&open_lock);
md = disk->private_data;
- if (md && md->usage == 0)
+ if (md && !kref_get_unless_zero(&md->kref))
md = NULL;
- if (md)
- md->usage++;
mutex_unlock(&open_lock);
return md;
return devidx;
}
-static void mmc_blk_put(struct mmc_blk_data *md)
+static void mmc_blk_kref_release(struct kref *ref)
{
- mutex_lock(&open_lock);
- md->usage--;
- if (md->usage == 0) {
- int devidx = mmc_get_devidx(md->disk);
+ struct mmc_blk_data *md = container_of(ref, struct mmc_blk_data, kref);
+ int devidx;
- ida_simple_remove(&mmc_blk_ida, devidx);
- put_disk(md->disk);
- kfree(md);
- }
+ devidx = mmc_get_devidx(md->disk);
+ ida_simple_remove(&mmc_blk_ida, devidx);
+
+ mutex_lock(&open_lock);
+ md->disk->private_data = NULL;
mutex_unlock(&open_lock);
+
+ put_disk(md->disk);
+ kfree(md);
+}
+
+static void mmc_blk_put(struct mmc_blk_data *md)
+{
+ kref_put(&md->kref, mmc_blk_kref_release);
}
static ssize_t power_ro_lock_show(struct device *dev,
INIT_LIST_HEAD(&md->part);
INIT_LIST_HEAD(&md->rpmbs);
- md->usage = 1;
+ kref_init(&md->kref);
+
md->queue.blkdata = md;
md->disk->major = MMC_BLOCK_MAJOR;
{
struct mmc_host *host = cls_dev_to_mmc_host(dev);
wakeup_source_unregister(host->ws);
- ida_simple_remove(&mmc_host_ida, host->index);
+ if (of_alias_get_id(host->parent->of_node, "mmc") < 0)
+ ida_simple_remove(&mmc_host_ida, host->index);
kfree(host);
}
*/
struct mmc_host *mmc_alloc_host(int extra, struct device *dev)
{
- int err;
+ int index;
struct mmc_host *host;
int alias_id, min_idx, max_idx;
alias_id = of_alias_get_id(dev->of_node, "mmc");
if (alias_id >= 0) {
- min_idx = alias_id;
- max_idx = alias_id + 1;
+ index = alias_id;
} else {
min_idx = mmc_first_nonreserved_index();
max_idx = 0;
- }
- err = ida_simple_get(&mmc_host_ida, min_idx, max_idx, GFP_KERNEL);
- if (err < 0) {
- kfree(host);
- return NULL;
+ index = ida_simple_get(&mmc_host_ida, min_idx, max_idx, GFP_KERNEL);
+ if (index < 0) {
+ kfree(host);
+ return NULL;
+ }
}
- host->index = err;
+ host->index = index;
dev_set_name(&host->class_dev, "mmc%d", host->index);
host->ws = wakeup_source_register(NULL, dev_name(&host->class_dev));
break;
}
}
+ fallthrough;
+
case JZ4740_MMC_STATE_DONE:
break;
}
#if BITS_PER_LONG >= 64
case 8:
onecmd |= (onecmd << (chip_mode * 32));
-#endif
fallthrough;
+#endif
case 4:
onecmd |= (onecmd << (chip_mode * 16));
fallthrough;
#if BITS_PER_LONG >= 64
case 8:
res |= (onestat >> (chip_mode * 32));
-#endif
fallthrough;
+#endif
case 4:
res |= (onestat >> (chip_mode * 16));
fallthrough;
static int bond_ipsec_add_sa(struct xfrm_state *xs)
{
struct net_device *bond_dev = xs->xso.dev;
+ struct bond_ipsec *ipsec;
struct bonding *bond;
struct slave *slave;
+ int err;
if (!bond_dev)
return -EINVAL;
+ rcu_read_lock();
bond = netdev_priv(bond_dev);
slave = rcu_dereference(bond->curr_active_slave);
- xs->xso.real_dev = slave->dev;
- bond->xs = xs;
+ if (!slave) {
+ rcu_read_unlock();
+ return -ENODEV;
+ }
- if (!(slave->dev->xfrmdev_ops
- && slave->dev->xfrmdev_ops->xdo_dev_state_add)) {
+ if (!slave->dev->xfrmdev_ops ||
+ !slave->dev->xfrmdev_ops->xdo_dev_state_add ||
+ netif_is_bond_master(slave->dev)) {
slave_warn(bond_dev, slave->dev, "Slave does not support ipsec offload\n");
+ rcu_read_unlock();
return -EINVAL;
}
- return slave->dev->xfrmdev_ops->xdo_dev_state_add(xs);
+ ipsec = kmalloc(sizeof(*ipsec), GFP_ATOMIC);
+ if (!ipsec) {
+ rcu_read_unlock();
+ return -ENOMEM;
+ }
+ xs->xso.real_dev = slave->dev;
+
+ err = slave->dev->xfrmdev_ops->xdo_dev_state_add(xs);
+ if (!err) {
+ ipsec->xs = xs;
+ INIT_LIST_HEAD(&ipsec->list);
+ spin_lock_bh(&bond->ipsec_lock);
+ list_add(&ipsec->list, &bond->ipsec_list);
+ spin_unlock_bh(&bond->ipsec_lock);
+ } else {
+ kfree(ipsec);
+ }
+ rcu_read_unlock();
+ return err;
+}
+
+static void bond_ipsec_add_sa_all(struct bonding *bond)
+{
+ struct net_device *bond_dev = bond->dev;
+ struct bond_ipsec *ipsec;
+ struct slave *slave;
+
+ rcu_read_lock();
+ slave = rcu_dereference(bond->curr_active_slave);
+ if (!slave)
+ goto out;
+
+ if (!slave->dev->xfrmdev_ops ||
+ !slave->dev->xfrmdev_ops->xdo_dev_state_add ||
+ netif_is_bond_master(slave->dev)) {
+ spin_lock_bh(&bond->ipsec_lock);
+ if (!list_empty(&bond->ipsec_list))
+ slave_warn(bond_dev, slave->dev,
+ "%s: no slave xdo_dev_state_add\n",
+ __func__);
+ spin_unlock_bh(&bond->ipsec_lock);
+ goto out;
+ }
+
+ spin_lock_bh(&bond->ipsec_lock);
+ list_for_each_entry(ipsec, &bond->ipsec_list, list) {
+ ipsec->xs->xso.real_dev = slave->dev;
+ if (slave->dev->xfrmdev_ops->xdo_dev_state_add(ipsec->xs)) {
+ slave_warn(bond_dev, slave->dev, "%s: failed to add SA\n", __func__);
+ ipsec->xs->xso.real_dev = NULL;
+ }
+ }
+ spin_unlock_bh(&bond->ipsec_lock);
+out:
+ rcu_read_unlock();
}
/**
static void bond_ipsec_del_sa(struct xfrm_state *xs)
{
struct net_device *bond_dev = xs->xso.dev;
+ struct bond_ipsec *ipsec;
struct bonding *bond;
struct slave *slave;
if (!bond_dev)
return;
+ rcu_read_lock();
bond = netdev_priv(bond_dev);
slave = rcu_dereference(bond->curr_active_slave);
if (!slave)
- return;
+ goto out;
- xs->xso.real_dev = slave->dev;
+ if (!xs->xso.real_dev)
+ goto out;
+
+ WARN_ON(xs->xso.real_dev != slave->dev);
- if (!(slave->dev->xfrmdev_ops
- && slave->dev->xfrmdev_ops->xdo_dev_state_delete)) {
+ if (!slave->dev->xfrmdev_ops ||
+ !slave->dev->xfrmdev_ops->xdo_dev_state_delete ||
+ netif_is_bond_master(slave->dev)) {
slave_warn(bond_dev, slave->dev, "%s: no slave xdo_dev_state_delete\n", __func__);
- return;
+ goto out;
}
slave->dev->xfrmdev_ops->xdo_dev_state_delete(xs);
+out:
+ spin_lock_bh(&bond->ipsec_lock);
+ list_for_each_entry(ipsec, &bond->ipsec_list, list) {
+ if (ipsec->xs == xs) {
+ list_del(&ipsec->list);
+ kfree(ipsec);
+ break;
+ }
+ }
+ spin_unlock_bh(&bond->ipsec_lock);
+ rcu_read_unlock();
+}
+
+static void bond_ipsec_del_sa_all(struct bonding *bond)
+{
+ struct net_device *bond_dev = bond->dev;
+ struct bond_ipsec *ipsec;
+ struct slave *slave;
+
+ rcu_read_lock();
+ slave = rcu_dereference(bond->curr_active_slave);
+ if (!slave) {
+ rcu_read_unlock();
+ return;
+ }
+
+ spin_lock_bh(&bond->ipsec_lock);
+ list_for_each_entry(ipsec, &bond->ipsec_list, list) {
+ if (!ipsec->xs->xso.real_dev)
+ continue;
+
+ if (!slave->dev->xfrmdev_ops ||
+ !slave->dev->xfrmdev_ops->xdo_dev_state_delete ||
+ netif_is_bond_master(slave->dev)) {
+ slave_warn(bond_dev, slave->dev,
+ "%s: no slave xdo_dev_state_delete\n",
+ __func__);
+ } else {
+ slave->dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs);
+ }
+ ipsec->xs->xso.real_dev = NULL;
+ }
+ spin_unlock_bh(&bond->ipsec_lock);
+ rcu_read_unlock();
}
/**
static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
{
struct net_device *bond_dev = xs->xso.dev;
- struct bonding *bond = netdev_priv(bond_dev);
- struct slave *curr_active = rcu_dereference(bond->curr_active_slave);
- struct net_device *slave_dev = curr_active->dev;
+ struct net_device *real_dev;
+ struct slave *curr_active;
+ struct bonding *bond;
+ int err;
- if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)
- return true;
+ bond = netdev_priv(bond_dev);
+ rcu_read_lock();
+ curr_active = rcu_dereference(bond->curr_active_slave);
+ real_dev = curr_active->dev;
- if (!(slave_dev->xfrmdev_ops
- && slave_dev->xfrmdev_ops->xdo_dev_offload_ok)) {
- slave_warn(bond_dev, slave_dev, "%s: no slave xdo_dev_offload_ok\n", __func__);
- return false;
+ if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
+ err = false;
+ goto out;
}
- xs->xso.real_dev = slave_dev;
- return slave_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs);
+ if (!xs->xso.real_dev) {
+ err = false;
+ goto out;
+ }
+
+ if (!real_dev->xfrmdev_ops ||
+ !real_dev->xfrmdev_ops->xdo_dev_offload_ok ||
+ netif_is_bond_master(real_dev)) {
+ err = false;
+ goto out;
+ }
+
+ err = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs);
+out:
+ rcu_read_unlock();
+ return err;
}
static const struct xfrmdev_ops bond_xfrmdev_ops = {
return;
#ifdef CONFIG_XFRM_OFFLOAD
- if (old_active && bond->xs)
- bond_ipsec_del_sa(bond->xs);
+ bond_ipsec_del_sa_all(bond);
#endif /* CONFIG_XFRM_OFFLOAD */
if (new_active) {
}
#ifdef CONFIG_XFRM_OFFLOAD
- if (new_active && bond->xs) {
- xfrm_dev_state_flush(dev_net(bond->dev), bond->dev, true);
- bond_ipsec_add_sa(bond->xs);
- }
+ bond_ipsec_add_sa_all(bond);
#endif /* CONFIG_XFRM_OFFLOAD */
/* resend IGMP joins since active slave has changed or
return bond_event_changename(event_bond);
case NETDEV_UNREGISTER:
bond_remove_proc_entry(event_bond);
+#ifdef CONFIG_XFRM_OFFLOAD
+ xfrm_dev_state_flush(dev_net(bond_dev), bond_dev, true);
+#endif /* CONFIG_XFRM_OFFLOAD */
break;
case NETDEV_REGISTER:
bond_create_proc_entry(event_bond);
#ifdef CONFIG_XFRM_OFFLOAD
/* set up xfrm device ops (only supported in active-backup right now) */
bond_dev->xfrmdev_ops = &bond_xfrmdev_ops;
- bond->xs = NULL;
+ INIT_LIST_HEAD(&bond->ipsec_list);
+ spin_lock_init(&bond->ipsec_lock);
#endif /* CONFIG_XFRM_OFFLOAD */
/* don't acquire bond device's netif_tx_lock when transmitting */
identified as N_CAIF. When this ldisc is opened from user space
it will redirect the TTY's traffic into the CAIF stack.
-config CAIF_HSI
- tristate "CAIF HSI transport driver"
- depends on CAIF
- default n
- help
- The CAIF low level driver for CAIF over HSI.
- Be aware that if you enable this then you also need to
- enable a low-level HSI driver.
-
config CAIF_VIRTIO
tristate "CAIF virtio transport driver"
depends on CAIF && HAS_DMA
# Serial interface
obj-$(CONFIG_CAIF_TTY) += caif_serial.o
-# HSI interface
-obj-$(CONFIG_CAIF_HSI) += caif_hsi.o
-
# Virtio interface
obj-$(CONFIG_CAIF_VIRTIO) += caif_virtio.o
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) ST-Ericsson AB 2010
- * Author: Daniel Martensson
- * Dmitry.Tarnyagin / dmitry.tarnyagin@lockless.no
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME fmt
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/device.h>
-#include <linux/netdevice.h>
-#include <linux/string.h>
-#include <linux/list.h>
-#include <linux/interrupt.h>
-#include <linux/delay.h>
-#include <linux/sched.h>
-#include <linux/if_arp.h>
-#include <linux/timer.h>
-#include <net/rtnetlink.h>
-#include <linux/pkt_sched.h>
-#include <net/caif/caif_layer.h>
-#include <net/caif/caif_hsi.h>
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Daniel Martensson");
-MODULE_DESCRIPTION("CAIF HSI driver");
-
-/* Returns the number of padding bytes for alignment. */
-#define PAD_POW2(x, pow) ((((x)&((pow)-1)) == 0) ? 0 :\
- (((pow)-((x)&((pow)-1)))))
-
-static const struct cfhsi_config hsi_default_config = {
-
- /* Inactivity timeout on HSI, ms */
- .inactivity_timeout = HZ,
-
- /* Aggregation timeout (ms) of zero means no aggregation is done*/
- .aggregation_timeout = 1,
-
- /*
- * HSI link layer flow-control thresholds.
- * Threshold values for the HSI packet queue. Flow-control will be
- * asserted when the number of packets exceeds q_high_mark. It will
- * not be de-asserted before the number of packets drops below
- * q_low_mark.
- * Warning: A high threshold value might increase throughput but it
- * will at the same time prevent channel prioritization and increase
- * the risk of flooding the modem. The high threshold should be above
- * the low.
- */
- .q_high_mark = 100,
- .q_low_mark = 50,
-
- /*
- * HSI padding options.
- * Warning: must be a base of 2 (& operation used) and can not be zero !
- */
- .head_align = 4,
- .tail_align = 4,
-};
-
-#define ON 1
-#define OFF 0
-
-static LIST_HEAD(cfhsi_list);
-
-static void cfhsi_inactivity_tout(struct timer_list *t)
-{
- struct cfhsi *cfhsi = from_timer(cfhsi, t, inactivity_timer);
-
- netdev_dbg(cfhsi->ndev, "%s.\n",
- __func__);
-
- /* Schedule power down work queue. */
- if (!test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))
- queue_work(cfhsi->wq, &cfhsi->wake_down_work);
-}
-
-static void cfhsi_update_aggregation_stats(struct cfhsi *cfhsi,
- const struct sk_buff *skb,
- int direction)
-{
- struct caif_payload_info *info;
- int hpad, tpad, len;
-
- info = (struct caif_payload_info *)&skb->cb;
- hpad = 1 + PAD_POW2((info->hdr_len + 1), cfhsi->cfg.head_align);
- tpad = PAD_POW2((skb->len + hpad), cfhsi->cfg.tail_align);
- len = skb->len + hpad + tpad;
-
- if (direction > 0)
- cfhsi->aggregation_len += len;
- else if (direction < 0)
- cfhsi->aggregation_len -= len;
-}
-
-static bool cfhsi_can_send_aggregate(struct cfhsi *cfhsi)
-{
- int i;
-
- if (cfhsi->cfg.aggregation_timeout == 0)
- return true;
-
- for (i = 0; i < CFHSI_PRIO_BEBK; ++i) {
- if (cfhsi->qhead[i].qlen)
- return true;
- }
-
- /* TODO: Use aggregation_len instead */
- if (cfhsi->qhead[CFHSI_PRIO_BEBK].qlen >= CFHSI_MAX_PKTS)
- return true;
-
- return false;
-}
-
-static struct sk_buff *cfhsi_dequeue(struct cfhsi *cfhsi)
-{
- struct sk_buff *skb;
- int i;
-
- for (i = 0; i < CFHSI_PRIO_LAST; ++i) {
- skb = skb_dequeue(&cfhsi->qhead[i]);
- if (skb)
- break;
- }
-
- return skb;
-}
-
-static int cfhsi_tx_queue_len(struct cfhsi *cfhsi)
-{
- int i, len = 0;
- for (i = 0; i < CFHSI_PRIO_LAST; ++i)
- len += skb_queue_len(&cfhsi->qhead[i]);
- return len;
-}
-
-static void cfhsi_abort_tx(struct cfhsi *cfhsi)
-{
- struct sk_buff *skb;
-
- for (;;) {
- spin_lock_bh(&cfhsi->lock);
- skb = cfhsi_dequeue(cfhsi);
- if (!skb)
- break;
-
- cfhsi->ndev->stats.tx_errors++;
- cfhsi->ndev->stats.tx_dropped++;
- cfhsi_update_aggregation_stats(cfhsi, skb, -1);
- spin_unlock_bh(&cfhsi->lock);
- kfree_skb(skb);
- }
- cfhsi->tx_state = CFHSI_TX_STATE_IDLE;
- if (!test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))
- mod_timer(&cfhsi->inactivity_timer,
- jiffies + cfhsi->cfg.inactivity_timeout);
- spin_unlock_bh(&cfhsi->lock);
-}
-
-static int cfhsi_flush_fifo(struct cfhsi *cfhsi)
-{
- char buffer[32]; /* Any reasonable value */
- size_t fifo_occupancy;
- int ret;
-
- netdev_dbg(cfhsi->ndev, "%s.\n",
- __func__);
-
- do {
- ret = cfhsi->ops->cfhsi_fifo_occupancy(cfhsi->ops,
- &fifo_occupancy);
- if (ret) {
- netdev_warn(cfhsi->ndev,
- "%s: can't get FIFO occupancy: %d.\n",
- __func__, ret);
- break;
- } else if (!fifo_occupancy)
- /* No more data, exitting normally */
- break;
-
- fifo_occupancy = min(sizeof(buffer), fifo_occupancy);
- set_bit(CFHSI_FLUSH_FIFO, &cfhsi->bits);
- ret = cfhsi->ops->cfhsi_rx(buffer, fifo_occupancy,
- cfhsi->ops);
- if (ret) {
- clear_bit(CFHSI_FLUSH_FIFO, &cfhsi->bits);
- netdev_warn(cfhsi->ndev,
- "%s: can't read data: %d.\n",
- __func__, ret);
- break;
- }
-
- ret = 5 * HZ;
- ret = wait_event_interruptible_timeout(cfhsi->flush_fifo_wait,
- !test_bit(CFHSI_FLUSH_FIFO, &cfhsi->bits), ret);
-
- if (ret < 0) {
- netdev_warn(cfhsi->ndev,
- "%s: can't wait for flush complete: %d.\n",
- __func__, ret);
- break;
- } else if (!ret) {
- ret = -ETIMEDOUT;
- netdev_warn(cfhsi->ndev,
- "%s: timeout waiting for flush complete.\n",
- __func__);
- break;
- }
- } while (1);
-
- return ret;
-}
-
-static int cfhsi_tx_frm(struct cfhsi_desc *desc, struct cfhsi *cfhsi)
-{
- int nfrms = 0;
- int pld_len = 0;
- struct sk_buff *skb;
- u8 *pfrm = desc->emb_frm + CFHSI_MAX_EMB_FRM_SZ;
-
- skb = cfhsi_dequeue(cfhsi);
- if (!skb)
- return 0;
-
- /* Clear offset. */
- desc->offset = 0;
-
- /* Check if we can embed a CAIF frame. */
- if (skb->len < CFHSI_MAX_EMB_FRM_SZ) {
- struct caif_payload_info *info;
- int hpad;
- int tpad;
-
- /* Calculate needed head alignment and tail alignment. */
- info = (struct caif_payload_info *)&skb->cb;
-
- hpad = 1 + PAD_POW2((info->hdr_len + 1), cfhsi->cfg.head_align);
- tpad = PAD_POW2((skb->len + hpad), cfhsi->cfg.tail_align);
-
- /* Check if frame still fits with added alignment. */
- if ((skb->len + hpad + tpad) <= CFHSI_MAX_EMB_FRM_SZ) {
- u8 *pemb = desc->emb_frm;
- desc->offset = CFHSI_DESC_SHORT_SZ;
- *pemb = (u8)(hpad - 1);
- pemb += hpad;
-
- /* Update network statistics. */
- spin_lock_bh(&cfhsi->lock);
- cfhsi->ndev->stats.tx_packets++;
- cfhsi->ndev->stats.tx_bytes += skb->len;
- cfhsi_update_aggregation_stats(cfhsi, skb, -1);
- spin_unlock_bh(&cfhsi->lock);
-
- /* Copy in embedded CAIF frame. */
- skb_copy_bits(skb, 0, pemb, skb->len);
-
- /* Consume the SKB */
- consume_skb(skb);
- skb = NULL;
- }
- }
-
- /* Create payload CAIF frames. */
- while (nfrms < CFHSI_MAX_PKTS) {
- struct caif_payload_info *info;
- int hpad;
- int tpad;
-
- if (!skb)
- skb = cfhsi_dequeue(cfhsi);
-
- if (!skb)
- break;
-
- /* Calculate needed head alignment and tail alignment. */
- info = (struct caif_payload_info *)&skb->cb;
-
- hpad = 1 + PAD_POW2((info->hdr_len + 1), cfhsi->cfg.head_align);
- tpad = PAD_POW2((skb->len + hpad), cfhsi->cfg.tail_align);
-
- /* Fill in CAIF frame length in descriptor. */
- desc->cffrm_len[nfrms] = hpad + skb->len + tpad;
-
- /* Fill head padding information. */
- *pfrm = (u8)(hpad - 1);
- pfrm += hpad;
-
- /* Update network statistics. */
- spin_lock_bh(&cfhsi->lock);
- cfhsi->ndev->stats.tx_packets++;
- cfhsi->ndev->stats.tx_bytes += skb->len;
- cfhsi_update_aggregation_stats(cfhsi, skb, -1);
- spin_unlock_bh(&cfhsi->lock);
-
- /* Copy in CAIF frame. */
- skb_copy_bits(skb, 0, pfrm, skb->len);
-
- /* Update payload length. */
- pld_len += desc->cffrm_len[nfrms];
-
- /* Update frame pointer. */
- pfrm += skb->len + tpad;
-
- /* Consume the SKB */
- consume_skb(skb);
- skb = NULL;
-
- /* Update number of frames. */
- nfrms++;
- }
-
- /* Unused length fields should be zero-filled (according to SPEC). */
- while (nfrms < CFHSI_MAX_PKTS) {
- desc->cffrm_len[nfrms] = 0x0000;
- nfrms++;
- }
-
- /* Check if we can piggy-back another descriptor. */
- if (cfhsi_can_send_aggregate(cfhsi))
- desc->header |= CFHSI_PIGGY_DESC;
- else
- desc->header &= ~CFHSI_PIGGY_DESC;
-
- return CFHSI_DESC_SZ + pld_len;
-}
-
-static void cfhsi_start_tx(struct cfhsi *cfhsi)
-{
- struct cfhsi_desc *desc = (struct cfhsi_desc *)cfhsi->tx_buf;
- int len, res;
-
- netdev_dbg(cfhsi->ndev, "%s.\n", __func__);
-
- if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))
- return;
-
- do {
- /* Create HSI frame. */
- len = cfhsi_tx_frm(desc, cfhsi);
- if (!len) {
- spin_lock_bh(&cfhsi->lock);
- if (unlikely(cfhsi_tx_queue_len(cfhsi))) {
- spin_unlock_bh(&cfhsi->lock);
- res = -EAGAIN;
- continue;
- }
- cfhsi->tx_state = CFHSI_TX_STATE_IDLE;
- /* Start inactivity timer. */
- mod_timer(&cfhsi->inactivity_timer,
- jiffies + cfhsi->cfg.inactivity_timeout);
- spin_unlock_bh(&cfhsi->lock);
- break;
- }
-
- /* Set up new transfer. */
- res = cfhsi->ops->cfhsi_tx(cfhsi->tx_buf, len, cfhsi->ops);
- if (WARN_ON(res < 0))
- netdev_err(cfhsi->ndev, "%s: TX error %d.\n",
- __func__, res);
- } while (res < 0);
-}
-
-static void cfhsi_tx_done(struct cfhsi *cfhsi)
-{
- netdev_dbg(cfhsi->ndev, "%s.\n", __func__);
-
- if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))
- return;
-
- /*
- * Send flow on if flow off has been previously signalled
- * and number of packets is below low water mark.
- */
- spin_lock_bh(&cfhsi->lock);
- if (cfhsi->flow_off_sent &&
- cfhsi_tx_queue_len(cfhsi) <= cfhsi->cfg.q_low_mark &&
- cfhsi->cfdev.flowctrl) {
-
- cfhsi->flow_off_sent = 0;
- cfhsi->cfdev.flowctrl(cfhsi->ndev, ON);
- }
-
- if (cfhsi_can_send_aggregate(cfhsi)) {
- spin_unlock_bh(&cfhsi->lock);
- cfhsi_start_tx(cfhsi);
- } else {
- mod_timer(&cfhsi->aggregation_timer,
- jiffies + cfhsi->cfg.aggregation_timeout);
- spin_unlock_bh(&cfhsi->lock);
- }
-
- return;
-}
-
-static void cfhsi_tx_done_cb(struct cfhsi_cb_ops *cb_ops)
-{
- struct cfhsi *cfhsi;
-
- cfhsi = container_of(cb_ops, struct cfhsi, cb_ops);
- netdev_dbg(cfhsi->ndev, "%s.\n",
- __func__);
-
- if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))
- return;
- cfhsi_tx_done(cfhsi);
-}
-
-static int cfhsi_rx_desc(struct cfhsi_desc *desc, struct cfhsi *cfhsi)
-{
- int xfer_sz = 0;
- int nfrms = 0;
- u16 *plen = NULL;
- u8 *pfrm = NULL;
-
- if ((desc->header & ~CFHSI_PIGGY_DESC) ||
- (desc->offset > CFHSI_MAX_EMB_FRM_SZ)) {
- netdev_err(cfhsi->ndev, "%s: Invalid descriptor.\n",
- __func__);
- return -EPROTO;
- }
-
- /* Check for embedded CAIF frame. */
- if (desc->offset) {
- struct sk_buff *skb;
- int len = 0;
- pfrm = ((u8 *)desc) + desc->offset;
-
- /* Remove offset padding. */
- pfrm += *pfrm + 1;
-
- /* Read length of CAIF frame (little endian). */
- len = *pfrm;
- len |= ((*(pfrm+1)) << 8) & 0xFF00;
- len += 2; /* Add FCS fields. */
-
- /* Sanity check length of CAIF frame. */
- if (unlikely(len > CFHSI_MAX_CAIF_FRAME_SZ)) {
- netdev_err(cfhsi->ndev, "%s: Invalid length.\n",
- __func__);
- return -EPROTO;
- }
-
- /* Allocate SKB (OK even in IRQ context). */
- skb = alloc_skb(len + 1, GFP_ATOMIC);
- if (!skb) {
- netdev_err(cfhsi->ndev, "%s: Out of memory !\n",
- __func__);
- return -ENOMEM;
- }
- caif_assert(skb != NULL);
-
- skb_put_data(skb, pfrm, len);
-
- skb->protocol = htons(ETH_P_CAIF);
- skb_reset_mac_header(skb);
- skb->dev = cfhsi->ndev;
-
- netif_rx_any_context(skb);
-
- /* Update network statistics. */
- cfhsi->ndev->stats.rx_packets++;
- cfhsi->ndev->stats.rx_bytes += len;
- }
-
- /* Calculate transfer length. */
- plen = desc->cffrm_len;
- while (nfrms < CFHSI_MAX_PKTS && *plen) {
- xfer_sz += *plen;
- plen++;
- nfrms++;
- }
-
- /* Check for piggy-backed descriptor. */
- if (desc->header & CFHSI_PIGGY_DESC)
- xfer_sz += CFHSI_DESC_SZ;
-
- if ((xfer_sz % 4) || (xfer_sz > (CFHSI_BUF_SZ_RX - CFHSI_DESC_SZ))) {
- netdev_err(cfhsi->ndev,
- "%s: Invalid payload len: %d, ignored.\n",
- __func__, xfer_sz);
- return -EPROTO;
- }
- return xfer_sz;
-}
-
-static int cfhsi_rx_desc_len(struct cfhsi_desc *desc)
-{
- int xfer_sz = 0;
- int nfrms = 0;
- u16 *plen;
-
- if ((desc->header & ~CFHSI_PIGGY_DESC) ||
- (desc->offset > CFHSI_MAX_EMB_FRM_SZ)) {
-
- pr_err("Invalid descriptor. %x %x\n", desc->header,
- desc->offset);
- return -EPROTO;
- }
-
- /* Calculate transfer length. */
- plen = desc->cffrm_len;
- while (nfrms < CFHSI_MAX_PKTS && *plen) {
- xfer_sz += *plen;
- plen++;
- nfrms++;
- }
-
- if (xfer_sz % 4) {
- pr_err("Invalid payload len: %d, ignored.\n", xfer_sz);
- return -EPROTO;
- }
- return xfer_sz;
-}
-
-static int cfhsi_rx_pld(struct cfhsi_desc *desc, struct cfhsi *cfhsi)
-{
- int rx_sz = 0;
- int nfrms = 0;
- u16 *plen = NULL;
- u8 *pfrm = NULL;
-
- /* Sanity check header and offset. */
- if (WARN_ON((desc->header & ~CFHSI_PIGGY_DESC) ||
- (desc->offset > CFHSI_MAX_EMB_FRM_SZ))) {
- netdev_err(cfhsi->ndev, "%s: Invalid descriptor.\n",
- __func__);
- return -EPROTO;
- }
-
- /* Set frame pointer to start of payload. */
- pfrm = desc->emb_frm + CFHSI_MAX_EMB_FRM_SZ;
- plen = desc->cffrm_len;
-
- /* Skip already processed frames. */
- while (nfrms < cfhsi->rx_state.nfrms) {
- pfrm += *plen;
- rx_sz += *plen;
- plen++;
- nfrms++;
- }
-
- /* Parse payload. */
- while (nfrms < CFHSI_MAX_PKTS && *plen) {
- struct sk_buff *skb;
- u8 *pcffrm = NULL;
- int len;
-
- /* CAIF frame starts after head padding. */
- pcffrm = pfrm + *pfrm + 1;
-
- /* Read length of CAIF frame (little endian). */
- len = *pcffrm;
- len |= ((*(pcffrm + 1)) << 8) & 0xFF00;
- len += 2; /* Add FCS fields. */
-
- /* Sanity check length of CAIF frames. */
- if (unlikely(len > CFHSI_MAX_CAIF_FRAME_SZ)) {
- netdev_err(cfhsi->ndev, "%s: Invalid length.\n",
- __func__);
- return -EPROTO;
- }
-
- /* Allocate SKB (OK even in IRQ context). */
- skb = alloc_skb(len + 1, GFP_ATOMIC);
- if (!skb) {
- netdev_err(cfhsi->ndev, "%s: Out of memory !\n",
- __func__);
- cfhsi->rx_state.nfrms = nfrms;
- return -ENOMEM;
- }
- caif_assert(skb != NULL);
-
- skb_put_data(skb, pcffrm, len);
-
- skb->protocol = htons(ETH_P_CAIF);
- skb_reset_mac_header(skb);
- skb->dev = cfhsi->ndev;
-
- netif_rx_any_context(skb);
-
- /* Update network statistics. */
- cfhsi->ndev->stats.rx_packets++;
- cfhsi->ndev->stats.rx_bytes += len;
-
- pfrm += *plen;
- rx_sz += *plen;
- plen++;
- nfrms++;
- }
-
- return rx_sz;
-}
-
-static void cfhsi_rx_done(struct cfhsi *cfhsi)
-{
- int res;
- int desc_pld_len = 0, rx_len, rx_state;
- struct cfhsi_desc *desc = NULL;
- u8 *rx_ptr, *rx_buf;
- struct cfhsi_desc *piggy_desc = NULL;
-
- desc = (struct cfhsi_desc *)cfhsi->rx_buf;
-
- netdev_dbg(cfhsi->ndev, "%s\n", __func__);
-
- if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))
- return;
-
- /* Update inactivity timer if pending. */
- spin_lock_bh(&cfhsi->lock);
- mod_timer_pending(&cfhsi->inactivity_timer,
- jiffies + cfhsi->cfg.inactivity_timeout);
- spin_unlock_bh(&cfhsi->lock);
-
- if (cfhsi->rx_state.state == CFHSI_RX_STATE_DESC) {
- desc_pld_len = cfhsi_rx_desc_len(desc);
-
- if (desc_pld_len < 0)
- goto out_of_sync;
-
- rx_buf = cfhsi->rx_buf;
- rx_len = desc_pld_len;
- if (desc_pld_len > 0 && (desc->header & CFHSI_PIGGY_DESC))
- rx_len += CFHSI_DESC_SZ;
- if (desc_pld_len == 0)
- rx_buf = cfhsi->rx_flip_buf;
- } else {
- rx_buf = cfhsi->rx_flip_buf;
-
- rx_len = CFHSI_DESC_SZ;
- if (cfhsi->rx_state.pld_len > 0 &&
- (desc->header & CFHSI_PIGGY_DESC)) {
-
- piggy_desc = (struct cfhsi_desc *)
- (desc->emb_frm + CFHSI_MAX_EMB_FRM_SZ +
- cfhsi->rx_state.pld_len);
-
- cfhsi->rx_state.piggy_desc = true;
-
- /* Extract payload len from piggy-backed descriptor. */
- desc_pld_len = cfhsi_rx_desc_len(piggy_desc);
- if (desc_pld_len < 0)
- goto out_of_sync;
-
- if (desc_pld_len > 0) {
- rx_len = desc_pld_len;
- if (piggy_desc->header & CFHSI_PIGGY_DESC)
- rx_len += CFHSI_DESC_SZ;
- }
-
- /*
- * Copy needed information from the piggy-backed
- * descriptor to the descriptor in the start.
- */
- memcpy(rx_buf, (u8 *)piggy_desc,
- CFHSI_DESC_SHORT_SZ);
- }
- }
-
- if (desc_pld_len) {
- rx_state = CFHSI_RX_STATE_PAYLOAD;
- rx_ptr = rx_buf + CFHSI_DESC_SZ;
- } else {
- rx_state = CFHSI_RX_STATE_DESC;
- rx_ptr = rx_buf;
- rx_len = CFHSI_DESC_SZ;
- }
-
- /* Initiate next read */
- if (test_bit(CFHSI_AWAKE, &cfhsi->bits)) {
- /* Set up new transfer. */
- netdev_dbg(cfhsi->ndev, "%s: Start RX.\n",
- __func__);
-
- res = cfhsi->ops->cfhsi_rx(rx_ptr, rx_len,
- cfhsi->ops);
- if (WARN_ON(res < 0)) {
- netdev_err(cfhsi->ndev, "%s: RX error %d.\n",
- __func__, res);
- cfhsi->ndev->stats.rx_errors++;
- cfhsi->ndev->stats.rx_dropped++;
- }
- }
-
- if (cfhsi->rx_state.state == CFHSI_RX_STATE_DESC) {
- /* Extract payload from descriptor */
- if (cfhsi_rx_desc(desc, cfhsi) < 0)
- goto out_of_sync;
- } else {
- /* Extract payload */
- if (cfhsi_rx_pld(desc, cfhsi) < 0)
- goto out_of_sync;
- if (piggy_desc) {
- /* Extract any payload in piggyback descriptor. */
- if (cfhsi_rx_desc(piggy_desc, cfhsi) < 0)
- goto out_of_sync;
- /* Mark no embedded frame after extracting it */
- piggy_desc->offset = 0;
- }
- }
-
- /* Update state info */
- memset(&cfhsi->rx_state, 0, sizeof(cfhsi->rx_state));
- cfhsi->rx_state.state = rx_state;
- cfhsi->rx_ptr = rx_ptr;
- cfhsi->rx_len = rx_len;
- cfhsi->rx_state.pld_len = desc_pld_len;
- cfhsi->rx_state.piggy_desc = desc->header & CFHSI_PIGGY_DESC;
-
- if (rx_buf != cfhsi->rx_buf)
- swap(cfhsi->rx_buf, cfhsi->rx_flip_buf);
- return;
-
-out_of_sync:
- netdev_err(cfhsi->ndev, "%s: Out of sync.\n", __func__);
- print_hex_dump_bytes("--> ", DUMP_PREFIX_NONE,
- cfhsi->rx_buf, CFHSI_DESC_SZ);
- schedule_work(&cfhsi->out_of_sync_work);
-}
-
-static void cfhsi_rx_slowpath(struct timer_list *t)
-{
- struct cfhsi *cfhsi = from_timer(cfhsi, t, rx_slowpath_timer);
-
- netdev_dbg(cfhsi->ndev, "%s.\n",
- __func__);
-
- cfhsi_rx_done(cfhsi);
-}
-
-static void cfhsi_rx_done_cb(struct cfhsi_cb_ops *cb_ops)
-{
- struct cfhsi *cfhsi;
-
- cfhsi = container_of(cb_ops, struct cfhsi, cb_ops);
- netdev_dbg(cfhsi->ndev, "%s.\n",
- __func__);
-
- if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))
- return;
-
- if (test_and_clear_bit(CFHSI_FLUSH_FIFO, &cfhsi->bits))
- wake_up_interruptible(&cfhsi->flush_fifo_wait);
- else
- cfhsi_rx_done(cfhsi);
-}
-
-static void cfhsi_wake_up(struct work_struct *work)
-{
- struct cfhsi *cfhsi = NULL;
- int res;
- int len;
- long ret;
-
- cfhsi = container_of(work, struct cfhsi, wake_up_work);
-
- if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))
- return;
-
- if (unlikely(test_bit(CFHSI_AWAKE, &cfhsi->bits))) {
- /* It happenes when wakeup is requested by
- * both ends at the same time. */
- clear_bit(CFHSI_WAKE_UP, &cfhsi->bits);
- clear_bit(CFHSI_WAKE_UP_ACK, &cfhsi->bits);
- return;
- }
-
- /* Activate wake line. */
- cfhsi->ops->cfhsi_wake_up(cfhsi->ops);
-
- netdev_dbg(cfhsi->ndev, "%s: Start waiting.\n",
- __func__);
-
- /* Wait for acknowledge. */
- ret = CFHSI_WAKE_TOUT;
- ret = wait_event_interruptible_timeout(cfhsi->wake_up_wait,
- test_and_clear_bit(CFHSI_WAKE_UP_ACK,
- &cfhsi->bits), ret);
- if (unlikely(ret < 0)) {
- /* Interrupted by signal. */
- netdev_err(cfhsi->ndev, "%s: Signalled: %ld.\n",
- __func__, ret);
-
- clear_bit(CFHSI_WAKE_UP, &cfhsi->bits);
- cfhsi->ops->cfhsi_wake_down(cfhsi->ops);
- return;
- } else if (!ret) {
- bool ca_wake = false;
- size_t fifo_occupancy = 0;
-
- /* Wakeup timeout */
- netdev_dbg(cfhsi->ndev, "%s: Timeout.\n",
- __func__);
-
- /* Check FIFO to check if modem has sent something. */
- WARN_ON(cfhsi->ops->cfhsi_fifo_occupancy(cfhsi->ops,
- &fifo_occupancy));
-
- netdev_dbg(cfhsi->ndev, "%s: Bytes in FIFO: %u.\n",
- __func__, (unsigned) fifo_occupancy);
-
- /* Check if we misssed the interrupt. */
- WARN_ON(cfhsi->ops->cfhsi_get_peer_wake(cfhsi->ops,
- &ca_wake));
-
- if (ca_wake) {
- netdev_err(cfhsi->ndev, "%s: CA Wake missed !.\n",
- __func__);
-
- /* Clear the CFHSI_WAKE_UP_ACK bit to prevent race. */
- clear_bit(CFHSI_WAKE_UP_ACK, &cfhsi->bits);
-
- /* Continue execution. */
- goto wake_ack;
- }
-
- clear_bit(CFHSI_WAKE_UP, &cfhsi->bits);
- cfhsi->ops->cfhsi_wake_down(cfhsi->ops);
- return;
- }
-wake_ack:
- netdev_dbg(cfhsi->ndev, "%s: Woken.\n",
- __func__);
-
- /* Clear power up bit. */
- set_bit(CFHSI_AWAKE, &cfhsi->bits);
- clear_bit(CFHSI_WAKE_UP, &cfhsi->bits);
-
- /* Resume read operation. */
- netdev_dbg(cfhsi->ndev, "%s: Start RX.\n", __func__);
- res = cfhsi->ops->cfhsi_rx(cfhsi->rx_ptr, cfhsi->rx_len, cfhsi->ops);
-
- if (WARN_ON(res < 0))
- netdev_err(cfhsi->ndev, "%s: RX err %d.\n", __func__, res);
-
- /* Clear power up acknowledment. */
- clear_bit(CFHSI_WAKE_UP_ACK, &cfhsi->bits);
-
- spin_lock_bh(&cfhsi->lock);
-
- /* Resume transmit if queues are not empty. */
- if (!cfhsi_tx_queue_len(cfhsi)) {
- netdev_dbg(cfhsi->ndev, "%s: Peer wake, start timer.\n",
- __func__);
- /* Start inactivity timer. */
- mod_timer(&cfhsi->inactivity_timer,
- jiffies + cfhsi->cfg.inactivity_timeout);
- spin_unlock_bh(&cfhsi->lock);
- return;
- }
-
- netdev_dbg(cfhsi->ndev, "%s: Host wake.\n",
- __func__);
-
- spin_unlock_bh(&cfhsi->lock);
-
- /* Create HSI frame. */
- len = cfhsi_tx_frm((struct cfhsi_desc *)cfhsi->tx_buf, cfhsi);
-
- if (likely(len > 0)) {
- /* Set up new transfer. */
- res = cfhsi->ops->cfhsi_tx(cfhsi->tx_buf, len, cfhsi->ops);
- if (WARN_ON(res < 0)) {
- netdev_err(cfhsi->ndev, "%s: TX error %d.\n",
- __func__, res);
- cfhsi_abort_tx(cfhsi);
- }
- } else {
- netdev_err(cfhsi->ndev,
- "%s: Failed to create HSI frame: %d.\n",
- __func__, len);
- }
-}
-
-static void cfhsi_wake_down(struct work_struct *work)
-{
- long ret;
- struct cfhsi *cfhsi = NULL;
- size_t fifo_occupancy = 0;
- int retry = CFHSI_WAKE_TOUT;
-
- cfhsi = container_of(work, struct cfhsi, wake_down_work);
- netdev_dbg(cfhsi->ndev, "%s.\n", __func__);
-
- if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))
- return;
-
- /* Deactivate wake line. */
- cfhsi->ops->cfhsi_wake_down(cfhsi->ops);
-
- /* Wait for acknowledge. */
- ret = CFHSI_WAKE_TOUT;
- ret = wait_event_interruptible_timeout(cfhsi->wake_down_wait,
- test_and_clear_bit(CFHSI_WAKE_DOWN_ACK,
- &cfhsi->bits), ret);
- if (ret < 0) {
- /* Interrupted by signal. */
- netdev_err(cfhsi->ndev, "%s: Signalled: %ld.\n",
- __func__, ret);
- return;
- } else if (!ret) {
- bool ca_wake = true;
-
- /* Timeout */
- netdev_err(cfhsi->ndev, "%s: Timeout.\n", __func__);
-
- /* Check if we misssed the interrupt. */
- WARN_ON(cfhsi->ops->cfhsi_get_peer_wake(cfhsi->ops,
- &ca_wake));
- if (!ca_wake)
- netdev_err(cfhsi->ndev, "%s: CA Wake missed !.\n",
- __func__);
- }
-
- /* Check FIFO occupancy. */
- while (retry) {
- WARN_ON(cfhsi->ops->cfhsi_fifo_occupancy(cfhsi->ops,
- &fifo_occupancy));
-
- if (!fifo_occupancy)
- break;
-
- set_current_state(TASK_INTERRUPTIBLE);
- schedule_timeout(1);
- retry--;
- }
-
- if (!retry)
- netdev_err(cfhsi->ndev, "%s: FIFO Timeout.\n", __func__);
-
- /* Clear AWAKE condition. */
- clear_bit(CFHSI_AWAKE, &cfhsi->bits);
-
- /* Cancel pending RX requests. */
- cfhsi->ops->cfhsi_rx_cancel(cfhsi->ops);
-}
-
-static void cfhsi_out_of_sync(struct work_struct *work)
-{
- struct cfhsi *cfhsi = NULL;
-
- cfhsi = container_of(work, struct cfhsi, out_of_sync_work);
-
- rtnl_lock();
- dev_close(cfhsi->ndev);
- rtnl_unlock();
-}
-
-static void cfhsi_wake_up_cb(struct cfhsi_cb_ops *cb_ops)
-{
- struct cfhsi *cfhsi = NULL;
-
- cfhsi = container_of(cb_ops, struct cfhsi, cb_ops);
- netdev_dbg(cfhsi->ndev, "%s.\n",
- __func__);
-
- set_bit(CFHSI_WAKE_UP_ACK, &cfhsi->bits);
- wake_up_interruptible(&cfhsi->wake_up_wait);
-
- if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))
- return;
-
- /* Schedule wake up work queue if the peer initiates. */
- if (!test_and_set_bit(CFHSI_WAKE_UP, &cfhsi->bits))
- queue_work(cfhsi->wq, &cfhsi->wake_up_work);
-}
-
-static void cfhsi_wake_down_cb(struct cfhsi_cb_ops *cb_ops)
-{
- struct cfhsi *cfhsi = NULL;
-
- cfhsi = container_of(cb_ops, struct cfhsi, cb_ops);
- netdev_dbg(cfhsi->ndev, "%s.\n",
- __func__);
-
- /* Initiating low power is only permitted by the host (us). */
- set_bit(CFHSI_WAKE_DOWN_ACK, &cfhsi->bits);
- wake_up_interruptible(&cfhsi->wake_down_wait);
-}
-
-static void cfhsi_aggregation_tout(struct timer_list *t)
-{
- struct cfhsi *cfhsi = from_timer(cfhsi, t, aggregation_timer);
-
- netdev_dbg(cfhsi->ndev, "%s.\n",
- __func__);
-
- cfhsi_start_tx(cfhsi);
-}
-
-static netdev_tx_t cfhsi_xmit(struct sk_buff *skb, struct net_device *dev)
-{
- struct cfhsi *cfhsi = NULL;
- int start_xfer = 0;
- int timer_active;
- int prio;
-
- if (!dev)
- return -EINVAL;
-
- cfhsi = netdev_priv(dev);
-
- switch (skb->priority) {
- case TC_PRIO_BESTEFFORT:
- case TC_PRIO_FILLER:
- case TC_PRIO_BULK:
- prio = CFHSI_PRIO_BEBK;
- break;
- case TC_PRIO_INTERACTIVE_BULK:
- prio = CFHSI_PRIO_VI;
- break;
- case TC_PRIO_INTERACTIVE:
- prio = CFHSI_PRIO_VO;
- break;
- case TC_PRIO_CONTROL:
- default:
- prio = CFHSI_PRIO_CTL;
- break;
- }
-
- spin_lock_bh(&cfhsi->lock);
-
- /* Update aggregation statistics */
- cfhsi_update_aggregation_stats(cfhsi, skb, 1);
-
- /* Queue the SKB */
- skb_queue_tail(&cfhsi->qhead[prio], skb);
-
- /* Sanity check; xmit should not be called after unregister_netdev */
- if (WARN_ON(test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))) {
- spin_unlock_bh(&cfhsi->lock);
- cfhsi_abort_tx(cfhsi);
- return -EINVAL;
- }
-
- /* Send flow off if number of packets is above high water mark. */
- if (!cfhsi->flow_off_sent &&
- cfhsi_tx_queue_len(cfhsi) > cfhsi->cfg.q_high_mark &&
- cfhsi->cfdev.flowctrl) {
- cfhsi->flow_off_sent = 1;
- cfhsi->cfdev.flowctrl(cfhsi->ndev, OFF);
- }
-
- if (cfhsi->tx_state == CFHSI_TX_STATE_IDLE) {
- cfhsi->tx_state = CFHSI_TX_STATE_XFER;
- start_xfer = 1;
- }
-
- if (!start_xfer) {
- /* Send aggregate if it is possible */
- bool aggregate_ready =
- cfhsi_can_send_aggregate(cfhsi) &&
- del_timer(&cfhsi->aggregation_timer) > 0;
- spin_unlock_bh(&cfhsi->lock);
- if (aggregate_ready)
- cfhsi_start_tx(cfhsi);
- return NETDEV_TX_OK;
- }
-
- /* Delete inactivity timer if started. */
- timer_active = del_timer_sync(&cfhsi->inactivity_timer);
-
- spin_unlock_bh(&cfhsi->lock);
-
- if (timer_active) {
- struct cfhsi_desc *desc = (struct cfhsi_desc *)cfhsi->tx_buf;
- int len;
- int res;
-
- /* Create HSI frame. */
- len = cfhsi_tx_frm(desc, cfhsi);
- WARN_ON(!len);
-
- /* Set up new transfer. */
- res = cfhsi->ops->cfhsi_tx(cfhsi->tx_buf, len, cfhsi->ops);
- if (WARN_ON(res < 0)) {
- netdev_err(cfhsi->ndev, "%s: TX error %d.\n",
- __func__, res);
- cfhsi_abort_tx(cfhsi);
- }
- } else {
- /* Schedule wake up work queue if the we initiate. */
- if (!test_and_set_bit(CFHSI_WAKE_UP, &cfhsi->bits))
- queue_work(cfhsi->wq, &cfhsi->wake_up_work);
- }
-
- return NETDEV_TX_OK;
-}
-
-static const struct net_device_ops cfhsi_netdevops;
-
-static void cfhsi_setup(struct net_device *dev)
-{
- int i;
- struct cfhsi *cfhsi = netdev_priv(dev);
- dev->features = 0;
- dev->type = ARPHRD_CAIF;
- dev->flags = IFF_POINTOPOINT | IFF_NOARP;
- dev->mtu = CFHSI_MAX_CAIF_FRAME_SZ;
- dev->priv_flags |= IFF_NO_QUEUE;
- dev->needs_free_netdev = true;
- dev->netdev_ops = &cfhsi_netdevops;
- for (i = 0; i < CFHSI_PRIO_LAST; ++i)
- skb_queue_head_init(&cfhsi->qhead[i]);
- cfhsi->cfdev.link_select = CAIF_LINK_HIGH_BANDW;
- cfhsi->cfdev.use_frag = false;
- cfhsi->cfdev.use_stx = false;
- cfhsi->cfdev.use_fcs = false;
- cfhsi->ndev = dev;
- cfhsi->cfg = hsi_default_config;
-}
-
-static int cfhsi_open(struct net_device *ndev)
-{
- struct cfhsi *cfhsi = netdev_priv(ndev);
- int res;
-
- clear_bit(CFHSI_SHUTDOWN, &cfhsi->bits);
-
- /* Initialize state vaiables. */
- cfhsi->tx_state = CFHSI_TX_STATE_IDLE;
- cfhsi->rx_state.state = CFHSI_RX_STATE_DESC;
-
- /* Set flow info */
- cfhsi->flow_off_sent = 0;
-
- /*
- * Allocate a TX buffer with the size of a HSI packet descriptors
- * and the necessary room for CAIF payload frames.
- */
- cfhsi->tx_buf = kzalloc(CFHSI_BUF_SZ_TX, GFP_KERNEL);
- if (!cfhsi->tx_buf) {
- res = -ENODEV;
- goto err_alloc_tx;
- }
-
- /*
- * Allocate a RX buffer with the size of two HSI packet descriptors and
- * the necessary room for CAIF payload frames.
- */
- cfhsi->rx_buf = kzalloc(CFHSI_BUF_SZ_RX, GFP_KERNEL);
- if (!cfhsi->rx_buf) {
- res = -ENODEV;
- goto err_alloc_rx;
- }
-
- cfhsi->rx_flip_buf = kzalloc(CFHSI_BUF_SZ_RX, GFP_KERNEL);
- if (!cfhsi->rx_flip_buf) {
- res = -ENODEV;
- goto err_alloc_rx_flip;
- }
-
- /* Initialize aggregation timeout */
- cfhsi->cfg.aggregation_timeout = hsi_default_config.aggregation_timeout;
-
- /* Initialize recieve vaiables. */
- cfhsi->rx_ptr = cfhsi->rx_buf;
- cfhsi->rx_len = CFHSI_DESC_SZ;
-
- /* Initialize spin locks. */
- spin_lock_init(&cfhsi->lock);
-
- /* Set up the driver. */
- cfhsi->cb_ops.tx_done_cb = cfhsi_tx_done_cb;
- cfhsi->cb_ops.rx_done_cb = cfhsi_rx_done_cb;
- cfhsi->cb_ops.wake_up_cb = cfhsi_wake_up_cb;
- cfhsi->cb_ops.wake_down_cb = cfhsi_wake_down_cb;
-
- /* Initialize the work queues. */
- INIT_WORK(&cfhsi->wake_up_work, cfhsi_wake_up);
- INIT_WORK(&cfhsi->wake_down_work, cfhsi_wake_down);
- INIT_WORK(&cfhsi->out_of_sync_work, cfhsi_out_of_sync);
-
- /* Clear all bit fields. */
- clear_bit(CFHSI_WAKE_UP_ACK, &cfhsi->bits);
- clear_bit(CFHSI_WAKE_DOWN_ACK, &cfhsi->bits);
- clear_bit(CFHSI_WAKE_UP, &cfhsi->bits);
- clear_bit(CFHSI_AWAKE, &cfhsi->bits);
-
- /* Create work thread. */
- cfhsi->wq = alloc_ordered_workqueue(cfhsi->ndev->name, WQ_MEM_RECLAIM);
- if (!cfhsi->wq) {
- netdev_err(cfhsi->ndev, "%s: Failed to create work queue.\n",
- __func__);
- res = -ENODEV;
- goto err_create_wq;
- }
-
- /* Initialize wait queues. */
- init_waitqueue_head(&cfhsi->wake_up_wait);
- init_waitqueue_head(&cfhsi->wake_down_wait);
- init_waitqueue_head(&cfhsi->flush_fifo_wait);
-
- /* Setup the inactivity timer. */
- timer_setup(&cfhsi->inactivity_timer, cfhsi_inactivity_tout, 0);
- /* Setup the slowpath RX timer. */
- timer_setup(&cfhsi->rx_slowpath_timer, cfhsi_rx_slowpath, 0);
- /* Setup the aggregation timer. */
- timer_setup(&cfhsi->aggregation_timer, cfhsi_aggregation_tout, 0);
-
- /* Activate HSI interface. */
- res = cfhsi->ops->cfhsi_up(cfhsi->ops);
- if (res) {
- netdev_err(cfhsi->ndev,
- "%s: can't activate HSI interface: %d.\n",
- __func__, res);
- goto err_activate;
- }
-
- /* Flush FIFO */
- res = cfhsi_flush_fifo(cfhsi);
- if (res) {
- netdev_err(cfhsi->ndev, "%s: Can't flush FIFO: %d.\n",
- __func__, res);
- goto err_net_reg;
- }
- return res;
-
- err_net_reg:
- cfhsi->ops->cfhsi_down(cfhsi->ops);
- err_activate:
- destroy_workqueue(cfhsi->wq);
- err_create_wq:
- kfree(cfhsi->rx_flip_buf);
- err_alloc_rx_flip:
- kfree(cfhsi->rx_buf);
- err_alloc_rx:
- kfree(cfhsi->tx_buf);
- err_alloc_tx:
- return res;
-}
-
-static int cfhsi_close(struct net_device *ndev)
-{
- struct cfhsi *cfhsi = netdev_priv(ndev);
- u8 *tx_buf, *rx_buf, *flip_buf;
-
- /* going to shutdown driver */
- set_bit(CFHSI_SHUTDOWN, &cfhsi->bits);
-
- /* Delete timers if pending */
- del_timer_sync(&cfhsi->inactivity_timer);
- del_timer_sync(&cfhsi->rx_slowpath_timer);
- del_timer_sync(&cfhsi->aggregation_timer);
-
- /* Cancel pending RX request (if any) */
- cfhsi->ops->cfhsi_rx_cancel(cfhsi->ops);
-
- /* Destroy workqueue */
- destroy_workqueue(cfhsi->wq);
-
- /* Store bufferes: will be freed later. */
- tx_buf = cfhsi->tx_buf;
- rx_buf = cfhsi->rx_buf;
- flip_buf = cfhsi->rx_flip_buf;
- /* Flush transmit queues. */
- cfhsi_abort_tx(cfhsi);
-
- /* Deactivate interface */
- cfhsi->ops->cfhsi_down(cfhsi->ops);
-
- /* Free buffers. */
- kfree(tx_buf);
- kfree(rx_buf);
- kfree(flip_buf);
- return 0;
-}
-
-static void cfhsi_uninit(struct net_device *dev)
-{
- struct cfhsi *cfhsi = netdev_priv(dev);
- ASSERT_RTNL();
- symbol_put(cfhsi_get_device);
- list_del(&cfhsi->list);
-}
-
-static const struct net_device_ops cfhsi_netdevops = {
- .ndo_uninit = cfhsi_uninit,
- .ndo_open = cfhsi_open,
- .ndo_stop = cfhsi_close,
- .ndo_start_xmit = cfhsi_xmit
-};
-
-static void cfhsi_netlink_parms(struct nlattr *data[], struct cfhsi *cfhsi)
-{
- int i;
-
- if (!data) {
- pr_debug("no params data found\n");
- return;
- }
-
- i = __IFLA_CAIF_HSI_INACTIVITY_TOUT;
- /*
- * Inactivity timeout in millisecs. Lowest possible value is 1,
- * and highest possible is NEXT_TIMER_MAX_DELTA.
- */
- if (data[i]) {
- u32 inactivity_timeout = nla_get_u32(data[i]);
- /* Pre-calculate inactivity timeout. */
- cfhsi->cfg.inactivity_timeout = inactivity_timeout * HZ / 1000;
- if (cfhsi->cfg.inactivity_timeout == 0)
- cfhsi->cfg.inactivity_timeout = 1;
- else if (cfhsi->cfg.inactivity_timeout > NEXT_TIMER_MAX_DELTA)
- cfhsi->cfg.inactivity_timeout = NEXT_TIMER_MAX_DELTA;
- }
-
- i = __IFLA_CAIF_HSI_AGGREGATION_TOUT;
- if (data[i])
- cfhsi->cfg.aggregation_timeout = nla_get_u32(data[i]);
-
- i = __IFLA_CAIF_HSI_HEAD_ALIGN;
- if (data[i])
- cfhsi->cfg.head_align = nla_get_u32(data[i]);
-
- i = __IFLA_CAIF_HSI_TAIL_ALIGN;
- if (data[i])
- cfhsi->cfg.tail_align = nla_get_u32(data[i]);
-
- i = __IFLA_CAIF_HSI_QHIGH_WATERMARK;
- if (data[i])
- cfhsi->cfg.q_high_mark = nla_get_u32(data[i]);
-
- i = __IFLA_CAIF_HSI_QLOW_WATERMARK;
- if (data[i])
- cfhsi->cfg.q_low_mark = nla_get_u32(data[i]);
-}
-
-static int caif_hsi_changelink(struct net_device *dev, struct nlattr *tb[],
- struct nlattr *data[],
- struct netlink_ext_ack *extack)
-{
- cfhsi_netlink_parms(data, netdev_priv(dev));
- netdev_state_change(dev);
- return 0;
-}
-
-static const struct nla_policy caif_hsi_policy[__IFLA_CAIF_HSI_MAX + 1] = {
- [__IFLA_CAIF_HSI_INACTIVITY_TOUT] = { .type = NLA_U32, .len = 4 },
- [__IFLA_CAIF_HSI_AGGREGATION_TOUT] = { .type = NLA_U32, .len = 4 },
- [__IFLA_CAIF_HSI_HEAD_ALIGN] = { .type = NLA_U32, .len = 4 },
- [__IFLA_CAIF_HSI_TAIL_ALIGN] = { .type = NLA_U32, .len = 4 },
- [__IFLA_CAIF_HSI_QHIGH_WATERMARK] = { .type = NLA_U32, .len = 4 },
- [__IFLA_CAIF_HSI_QLOW_WATERMARK] = { .type = NLA_U32, .len = 4 },
-};
-
-static size_t caif_hsi_get_size(const struct net_device *dev)
-{
- int i;
- size_t s = 0;
- for (i = __IFLA_CAIF_HSI_UNSPEC + 1; i < __IFLA_CAIF_HSI_MAX; i++)
- s += nla_total_size(caif_hsi_policy[i].len);
- return s;
-}
-
-static int caif_hsi_fill_info(struct sk_buff *skb, const struct net_device *dev)
-{
- struct cfhsi *cfhsi = netdev_priv(dev);
-
- if (nla_put_u32(skb, __IFLA_CAIF_HSI_INACTIVITY_TOUT,
- cfhsi->cfg.inactivity_timeout) ||
- nla_put_u32(skb, __IFLA_CAIF_HSI_AGGREGATION_TOUT,
- cfhsi->cfg.aggregation_timeout) ||
- nla_put_u32(skb, __IFLA_CAIF_HSI_HEAD_ALIGN,
- cfhsi->cfg.head_align) ||
- nla_put_u32(skb, __IFLA_CAIF_HSI_TAIL_ALIGN,
- cfhsi->cfg.tail_align) ||
- nla_put_u32(skb, __IFLA_CAIF_HSI_QHIGH_WATERMARK,
- cfhsi->cfg.q_high_mark) ||
- nla_put_u32(skb, __IFLA_CAIF_HSI_QLOW_WATERMARK,
- cfhsi->cfg.q_low_mark))
- return -EMSGSIZE;
-
- return 0;
-}
-
-static int caif_hsi_newlink(struct net *src_net, struct net_device *dev,
- struct nlattr *tb[], struct nlattr *data[],
- struct netlink_ext_ack *extack)
-{
- struct cfhsi *cfhsi = NULL;
- struct cfhsi_ops *(*get_ops)(void);
-
- ASSERT_RTNL();
-
- cfhsi = netdev_priv(dev);
- cfhsi_netlink_parms(data, cfhsi);
-
- get_ops = symbol_get(cfhsi_get_ops);
- if (!get_ops) {
- pr_err("%s: failed to get the cfhsi_ops\n", __func__);
- return -ENODEV;
- }
-
- /* Assign the HSI device. */
- cfhsi->ops = (*get_ops)();
- if (!cfhsi->ops) {
- pr_err("%s: failed to get the cfhsi_ops\n", __func__);
- goto err;
- }
-
- /* Assign the driver to this HSI device. */
- cfhsi->ops->cb_ops = &cfhsi->cb_ops;
- if (register_netdevice(dev)) {
- pr_warn("%s: caif_hsi device registration failed\n", __func__);
- goto err;
- }
- /* Add CAIF HSI device to list. */
- list_add_tail(&cfhsi->list, &cfhsi_list);
-
- return 0;
-err:
- symbol_put(cfhsi_get_ops);
- return -ENODEV;
-}
-
-static struct rtnl_link_ops caif_hsi_link_ops __read_mostly = {
- .kind = "cfhsi",
- .priv_size = sizeof(struct cfhsi),
- .setup = cfhsi_setup,
- .maxtype = __IFLA_CAIF_HSI_MAX,
- .policy = caif_hsi_policy,
- .newlink = caif_hsi_newlink,
- .changelink = caif_hsi_changelink,
- .get_size = caif_hsi_get_size,
- .fill_info = caif_hsi_fill_info,
-};
-
-static void __exit cfhsi_exit_module(void)
-{
- struct list_head *list_node;
- struct list_head *n;
- struct cfhsi *cfhsi;
-
- rtnl_link_unregister(&caif_hsi_link_ops);
-
- rtnl_lock();
- list_for_each_safe(list_node, n, &cfhsi_list) {
- cfhsi = list_entry(list_node, struct cfhsi, list);
- unregister_netdevice(cfhsi->ndev);
- }
- rtnl_unlock();
-}
-
-static int __init cfhsi_init_module(void)
-{
- return rtnl_link_register(&caif_hsi_link_ops);
-}
-
-module_init(cfhsi_init_module);
-module_exit(cfhsi_exit_module);
return ret;
}
-static u8 hi3110_cmd(struct spi_device *spi, u8 command)
+static int hi3110_cmd(struct spi_device *spi, u8 command)
{
struct hi3110_priv *priv = spi_get_drvdata(spi);
err, priv->regs_status.intf);
mcp251xfd_dump(priv);
mcp251xfd_chip_interrupts_disable(priv);
+ mcp251xfd_timestamp_stop(priv);
return handled;
}
unsigned int free_slots; /* remember number of available slots */
struct ems_cpc_msg active_params; /* active controller parameters */
+ void *rxbuf[MAX_RX_URBS];
+ dma_addr_t rxbuf_dma[MAX_RX_URBS];
};
static void ems_usb_read_interrupt_callback(struct urb *urb)
for (i = 0; i < MAX_RX_URBS; i++) {
struct urb *urb = NULL;
u8 *buf = NULL;
+ dma_addr_t buf_dma;
/* create a URB, and a buffer for it */
urb = usb_alloc_urb(0, GFP_KERNEL);
}
buf = usb_alloc_coherent(dev->udev, RX_BUFFER_SIZE, GFP_KERNEL,
- &urb->transfer_dma);
+ &buf_dma);
if (!buf) {
netdev_err(netdev, "No memory left for USB buffer\n");
usb_free_urb(urb);
break;
}
+ urb->transfer_dma = buf_dma;
+
usb_fill_bulk_urb(urb, dev->udev, usb_rcvbulkpipe(dev->udev, 2),
buf, RX_BUFFER_SIZE,
ems_usb_read_bulk_callback, dev);
break;
}
+ dev->rxbuf[i] = buf;
+ dev->rxbuf_dma[i] = buf_dma;
+
/* Drop reference, USB core will take care of freeing it */
usb_free_urb(urb);
}
usb_kill_anchored_urbs(&dev->rx_submitted);
+ for (i = 0; i < MAX_RX_URBS; ++i)
+ usb_free_coherent(dev->udev, RX_BUFFER_SIZE,
+ dev->rxbuf[i], dev->rxbuf_dma[i]);
+
usb_kill_anchored_urbs(&dev->tx_submitted);
atomic_set(&dev->active_tx_urbs, 0);
int net_count;
u32 version;
int rxinitdone;
+ void *rxbuf[MAX_RX_URBS];
+ dma_addr_t rxbuf_dma[MAX_RX_URBS];
};
struct esd_usb2_net_priv {
for (i = 0; i < MAX_RX_URBS; i++) {
struct urb *urb = NULL;
u8 *buf = NULL;
+ dma_addr_t buf_dma;
/* create a URB, and a buffer for it */
urb = usb_alloc_urb(0, GFP_KERNEL);
}
buf = usb_alloc_coherent(dev->udev, RX_BUFFER_SIZE, GFP_KERNEL,
- &urb->transfer_dma);
+ &buf_dma);
if (!buf) {
dev_warn(dev->udev->dev.parent,
"No memory left for USB buffer\n");
goto freeurb;
}
+ urb->transfer_dma = buf_dma;
+
usb_fill_bulk_urb(urb, dev->udev,
usb_rcvbulkpipe(dev->udev, 1),
buf, RX_BUFFER_SIZE,
usb_unanchor_urb(urb);
usb_free_coherent(dev->udev, RX_BUFFER_SIZE, buf,
urb->transfer_dma);
+ goto freeurb;
}
+ dev->rxbuf[i] = buf;
+ dev->rxbuf_dma[i] = buf_dma;
+
freeurb:
/* Drop reference, USB core will take care of freeing it */
usb_free_urb(urb);
int i, j;
usb_kill_anchored_urbs(&dev->rx_submitted);
+
+ for (i = 0; i < MAX_RX_URBS; ++i)
+ usb_free_coherent(dev->udev, RX_BUFFER_SIZE,
+ dev->rxbuf[i], dev->rxbuf_dma[i]);
+
for (i = 0; i < dev->net_count; i++) {
priv = dev->nets[i];
if (priv) {
break;
}
+ urb->transfer_dma = buf_dma;
+
usb_fill_bulk_urb(urb, priv->udev,
usb_rcvbulkpipe(priv->udev, MCBA_USB_EP_IN),
buf, MCBA_USB_RX_BUFF_SIZE,
#define PCAN_USB_BERR_MASK (PCAN_USB_ERR_RXERR | PCAN_USB_ERR_TXERR)
/* identify bus event packets with rx/tx error counters */
-#define PCAN_USB_ERR_CNT 0x80
+#define PCAN_USB_ERR_CNT_DEC 0x00 /* counters are decreasing */
+#define PCAN_USB_ERR_CNT_INC 0x80 /* counters are increasing */
/* private to PCAN-USB adapter */
struct pcan_usb {
/* acccording to the content of the packet */
switch (ir) {
- case PCAN_USB_ERR_CNT:
+ case PCAN_USB_ERR_CNT_DEC:
+ case PCAN_USB_ERR_CNT_INC:
/* save rx/tx error counters from in the device context */
- pdev->bec.rxerr = mc->ptr[0];
- pdev->bec.txerr = mc->ptr[1];
+ pdev->bec.rxerr = mc->ptr[1];
+ pdev->bec.txerr = mc->ptr[2];
break;
default:
u8 *cmd_msg_buffer;
struct mutex usb_8dev_cmd_lock;
-
+ void *rxbuf[MAX_RX_URBS];
+ dma_addr_t rxbuf_dma[MAX_RX_URBS];
};
/* tx frame */
for (i = 0; i < MAX_RX_URBS; i++) {
struct urb *urb = NULL;
u8 *buf;
+ dma_addr_t buf_dma;
/* create a URB, and a buffer for it */
urb = usb_alloc_urb(0, GFP_KERNEL);
}
buf = usb_alloc_coherent(priv->udev, RX_BUFFER_SIZE, GFP_KERNEL,
- &urb->transfer_dma);
+ &buf_dma);
if (!buf) {
netdev_err(netdev, "No memory left for USB buffer\n");
usb_free_urb(urb);
break;
}
+ urb->transfer_dma = buf_dma;
+
usb_fill_bulk_urb(urb, priv->udev,
usb_rcvbulkpipe(priv->udev,
USB_8DEV_ENDP_DATA_RX),
break;
}
+ priv->rxbuf[i] = buf;
+ priv->rxbuf_dma[i] = buf_dma;
+
/* Drop reference, USB core will take care of freeing it */
usb_free_urb(urb);
}
usb_kill_anchored_urbs(&priv->rx_submitted);
+ for (i = 0; i < MAX_RX_URBS; ++i)
+ usb_free_coherent(priv->udev, RX_BUFFER_SIZE,
+ priv->rxbuf[i], priv->rxbuf_dma[i]);
+
usb_kill_anchored_urbs(&priv->tx_submitted);
atomic_set(&priv->active_tx_urbs, 0);
if (of_property_read_u32(port, "reg",
&port_num))
continue;
- if (!(dev->port_mask & BIT(port_num)))
+ if (!(dev->port_mask & BIT(port_num))) {
+ of_node_put(port);
return -EINVAL;
+ }
of_get_phy_mode(port,
&dev->ports[port_num].interface);
}
int i;
reg[1] |= vid & CVID_MASK;
+ if (vid > 1)
+ reg[1] |= ATA2_IVL;
reg[2] |= (aging & AGE_TIMER_MASK) << AGE_TIMER;
reg[2] |= (port_mask & PORT_MAP_MASK) << PORT_MAP;
/* STATIC_ENT indicate that entry is static wouldn't
#define STATIC_EMP 0
#define STATIC_ENT 3
#define MT7530_ATA2 0x78
+#define ATA2_IVL BIT(15)
/* Register for address table write data */
#define MT7530_ATWD 0x7c
config NET_DSA_MV88E6XXX_PTP
bool "PTP support for Marvell 88E6xxx"
default n
- depends on PTP_1588_CLOCK
+ depends on NET_DSA_MV88E6XXX && PTP_1588_CLOCK
help
Say Y to enable PTP hardware timestamping on Marvell 88E6xxx switch
chips that support it.
int i, err;
if (!vid)
- return -EOPNOTSUPP;
+ return 0;
err = mv88e6xxx_vtu_get(chip, vid, &vlan);
if (err)
.port_set_speed_duplex = mv88e6341_port_set_speed_duplex,
.port_max_speed_mode = mv88e6341_port_max_speed_mode,
.port_tag_remap = mv88e6095_port_tag_remap,
+ .port_set_policy = mv88e6352_port_set_policy,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
.port_set_ucast_flood = mv88e6352_port_set_ucast_flood,
.port_set_mcast_flood = mv88e6352_port_set_mcast_flood,
.port_set_cmode = mv88e6341_port_set_cmode,
.port_setup_message_port = mv88e6xxx_setup_message_port,
.stats_snapshot = mv88e6390_g1_stats_snapshot,
- .stats_set_histogram = mv88e6095_g1_stats_set_histogram,
+ .stats_set_histogram = mv88e6390_g1_stats_set_histogram,
.stats_get_sset_count = mv88e6320_stats_get_sset_count,
.stats_get_strings = mv88e6320_stats_get_strings,
.stats_get_stats = mv88e6390_stats_get_stats,
.mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu,
.pot_clear = mv88e6xxx_g2_pot_clear,
.reset = mv88e6352_g1_reset,
+ .rmu_disable = mv88e6390_g1_rmu_disable,
+ .atu_get_hash = mv88e6165_g1_atu_get_hash,
+ .atu_set_hash = mv88e6165_g1_atu_set_hash,
.vtu_getnext = mv88e6352_g1_vtu_getnext,
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
.serdes_power = mv88e6390_serdes_power,
.serdes_irq_enable = mv88e6390_serdes_irq_enable,
.serdes_irq_status = mv88e6390_serdes_irq_status,
.gpio_ops = &mv88e6352_gpio_ops,
+ .serdes_get_sset_count = mv88e6390_serdes_get_sset_count,
+ .serdes_get_strings = mv88e6390_serdes_get_strings,
+ .serdes_get_stats = mv88e6390_serdes_get_stats,
+ .serdes_get_regs_len = mv88e6390_serdes_get_regs_len,
+ .serdes_get_regs = mv88e6390_serdes_get_regs,
.phylink_validate = mv88e6341_phylink_validate,
};
.port_set_speed_duplex = mv88e6341_port_set_speed_duplex,
.port_max_speed_mode = mv88e6341_port_max_speed_mode,
.port_tag_remap = mv88e6095_port_tag_remap,
+ .port_set_policy = mv88e6352_port_set_policy,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
.port_set_ucast_flood = mv88e6352_port_set_ucast_flood,
.port_set_mcast_flood = mv88e6352_port_set_mcast_flood,
.port_set_cmode = mv88e6341_port_set_cmode,
.port_setup_message_port = mv88e6xxx_setup_message_port,
.stats_snapshot = mv88e6390_g1_stats_snapshot,
- .stats_set_histogram = mv88e6095_g1_stats_set_histogram,
+ .stats_set_histogram = mv88e6390_g1_stats_set_histogram,
.stats_get_sset_count = mv88e6320_stats_get_sset_count,
.stats_get_strings = mv88e6320_stats_get_strings,
.stats_get_stats = mv88e6390_stats_get_stats,
.mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu,
.pot_clear = mv88e6xxx_g2_pot_clear,
.reset = mv88e6352_g1_reset,
+ .rmu_disable = mv88e6390_g1_rmu_disable,
+ .atu_get_hash = mv88e6165_g1_atu_get_hash,
+ .atu_set_hash = mv88e6165_g1_atu_set_hash,
.vtu_getnext = mv88e6352_g1_vtu_getnext,
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
.serdes_power = mv88e6390_serdes_power,
.gpio_ops = &mv88e6352_gpio_ops,
.avb_ops = &mv88e6390_avb_ops,
.ptp_ops = &mv88e6352_ptp_ops,
+ .serdes_get_sset_count = mv88e6390_serdes_get_sset_count,
+ .serdes_get_strings = mv88e6390_serdes_get_strings,
+ .serdes_get_stats = mv88e6390_serdes_get_stats,
+ .serdes_get_regs_len = mv88e6390_serdes_get_regs_len,
+ .serdes_get_regs = mv88e6390_serdes_get_regs,
.phylink_validate = mv88e6341_phylink_validate,
};
int mv88e6390_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port)
{
- if (mv88e6390_serdes_get_lane(chip, port) < 0)
+ if (mv88e6xxx_serdes_get_lane(chip, port) < 0)
return 0;
return ARRAY_SIZE(mv88e6390_serdes_hw_stats);
struct mv88e6390_serdes_hw_stat *stat;
int i;
- if (mv88e6390_serdes_get_lane(chip, port) < 0)
+ if (mv88e6xxx_serdes_get_lane(chip, port) < 0)
return 0;
for (i = 0; i < ARRAY_SIZE(mv88e6390_serdes_hw_stats); i++) {
int lane;
int i;
- lane = mv88e6390_serdes_get_lane(chip, port);
+ lane = mv88e6xxx_serdes_get_lane(chip, port);
if (lane < 0)
return 0;
return 0;
}
- ret = __ar9331_mdio_write(sbus, AR9331_SW_MDIO_PHY_MODE_REG, reg, val);
+ /* In case of this switch we work with 32bit registers on top of 16bit
+ * bus. Some registers (for example access to forwarding database) have
+ * trigger bit on the first 16bit half of request, the result and
+ * configuration of request in the second half.
+ * To make it work properly, we should do the second part of transfer
+ * before the first one is done.
+ */
+ ret = __ar9331_mdio_write(sbus, AR9331_SW_MDIO_PHY_MODE_REG, reg + 2,
+ val >> 16);
if (ret < 0)
goto error;
- ret = __ar9331_mdio_write(sbus, AR9331_SW_MDIO_PHY_MODE_REG, reg + 2,
- val >> 16);
+ ret = __ar9331_mdio_write(sbus, AR9331_SW_MDIO_PHY_MODE_REG, reg, val);
if (ret < 0)
goto error;
return 0;
+
error:
dev_err_ratelimited(&sbus->dev, "Bus error. Failed to write register.\n");
return ret;
hostcmd = SJA1105_HOSTCMD_INVALIDATE;
}
sja1105_packing(p, &hostcmd, 25, 23, size, op);
+}
+
+static void
+sja1105pqrs_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
+ enum packing_op op)
+{
+ int entry_size = SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY;
+
+ sja1105pqrs_common_l2_lookup_cmd_packing(buf, cmd, op, entry_size);
/* Hack - The hardware takes the 'index' field within
* struct sja1105_l2_lookup_entry as the index on which this command
* such that our API doesn't need to ask for a full-blown entry
* structure when e.g. a delete is requested.
*/
- sja1105_packing(buf, &cmd->index, 15, 6,
- SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY, op);
-}
-
-static void
-sja1105pqrs_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
- enum packing_op op)
-{
- int size = SJA1105PQRS_SIZE_L2_LOOKUP_ENTRY;
-
- return sja1105pqrs_common_l2_lookup_cmd_packing(buf, cmd, op, size);
+ sja1105_packing(buf, &cmd->index, 15, 6, entry_size, op);
}
static void
sja1110_l2_lookup_cmd_packing(void *buf, struct sja1105_dyn_cmd *cmd,
enum packing_op op)
{
- int size = SJA1110_SIZE_L2_LOOKUP_ENTRY;
+ int entry_size = SJA1110_SIZE_L2_LOOKUP_ENTRY;
+
+ sja1105pqrs_common_l2_lookup_cmd_packing(buf, cmd, op, entry_size);
- return sja1105pqrs_common_l2_lookup_cmd_packing(buf, cmd, op, size);
+ sja1105_packing(buf, &cmd->index, 10, 1, entry_size, op);
}
/* The switch is so retarded that it makes our command/entry abstraction
for (i = 0; i < ds->num_ports; i++) {
mac[i] = default_mac;
- if (i == dsa_upstream_port(priv->ds, i)) {
- /* STP doesn't get called for CPU port, so we need to
- * set the I/O parameters statically.
- */
- mac[i].dyn_learn = true;
- mac[i].ingress = true;
- mac[i].egress = true;
- }
+
+ /* Let sja1105_bridge_stp_state_set() keep address learning
+ * enabled for the CPU port.
+ */
+ if (dsa_is_cpu_port(ds, i))
+ priv->learn_ena |= BIT(i);
}
return 0;
if (dsa_is_cpu_port(ds, port))
v->pvid = true;
list_add(&v->list, &priv->dsa_8021q_vlans);
+
+ v = kmemdup(v, sizeof(*v), GFP_KERNEL);
+ if (!v)
+ return -ENOMEM;
+
+ list_add(&v->list, &priv->bridge_vlans);
}
((struct sja1105_vlan_lookup_entry *)table->entries)[0] = pvid;
int sja1105et_fdb_add(struct dsa_switch *ds, int port,
const unsigned char *addr, u16 vid)
{
- struct sja1105_l2_lookup_entry l2_lookup = {0};
+ struct sja1105_l2_lookup_entry l2_lookup = {0}, tmp;
struct sja1105_private *priv = ds->priv;
struct device *dev = ds->dev;
int last_unused = -1;
+ int start, end, i;
int bin, way, rc;
bin = sja1105et_fdb_hash(priv, addr, vid);
* mask? If yes, we need to do nothing. If not, we need
* to rewrite the entry by adding this port to it.
*/
- if (l2_lookup.destports & BIT(port))
+ if ((l2_lookup.destports & BIT(port)) && l2_lookup.lockeds)
return 0;
l2_lookup.destports |= BIT(port);
} else {
index, NULL, false);
}
}
+ l2_lookup.lockeds = true;
l2_lookup.index = sja1105et_fdb_index(bin, way);
rc = sja1105_dynamic_config_write(priv, BLK_IDX_L2_LOOKUP,
if (rc < 0)
return rc;
+ /* Invalidate a dynamically learned entry if that exists */
+ start = sja1105et_fdb_index(bin, 0);
+ end = sja1105et_fdb_index(bin, way);
+
+ for (i = start; i < end; i++) {
+ rc = sja1105_dynamic_config_read(priv, BLK_IDX_L2_LOOKUP,
+ i, &tmp);
+ if (rc == -ENOENT)
+ continue;
+ if (rc)
+ return rc;
+
+ if (tmp.macaddr != ether_addr_to_u64(addr) || tmp.vlanid != vid)
+ continue;
+
+ rc = sja1105_dynamic_config_write(priv, BLK_IDX_L2_LOOKUP,
+ i, NULL, false);
+ if (rc)
+ return rc;
+
+ break;
+ }
+
return sja1105_static_fdb_change(priv, port, &l2_lookup, true);
}
int sja1105pqrs_fdb_add(struct dsa_switch *ds, int port,
const unsigned char *addr, u16 vid)
{
- struct sja1105_l2_lookup_entry l2_lookup = {0};
+ struct sja1105_l2_lookup_entry l2_lookup = {0}, tmp;
struct sja1105_private *priv = ds->priv;
int rc, i;
/* Search for an existing entry in the FDB table */
l2_lookup.macaddr = ether_addr_to_u64(addr);
l2_lookup.vlanid = vid;
- l2_lookup.iotag = SJA1105_S_TAG;
l2_lookup.mask_macaddr = GENMASK_ULL(ETH_ALEN * 8 - 1, 0);
- if (priv->vlan_state != SJA1105_VLAN_UNAWARE) {
- l2_lookup.mask_vlanid = VLAN_VID_MASK;
- l2_lookup.mask_iotag = BIT(0);
- } else {
- l2_lookup.mask_vlanid = 0;
- l2_lookup.mask_iotag = 0;
- }
+ l2_lookup.mask_vlanid = VLAN_VID_MASK;
l2_lookup.destports = BIT(port);
+ tmp = l2_lookup;
+
rc = sja1105_dynamic_config_read(priv, BLK_IDX_L2_LOOKUP,
- SJA1105_SEARCH, &l2_lookup);
- if (rc == 0) {
- /* Found and this port is already in the entry's
+ SJA1105_SEARCH, &tmp);
+ if (rc == 0 && tmp.index != SJA1105_MAX_L2_LOOKUP_COUNT - 1) {
+ /* Found a static entry and this port is already in the entry's
* port mask => job done
*/
- if (l2_lookup.destports & BIT(port))
+ if ((tmp.destports & BIT(port)) && tmp.lockeds)
return 0;
+
+ l2_lookup = tmp;
+
/* l2_lookup.index is populated by the switch in case it
* found something.
*/
dev_err(ds->dev, "FDB is full, cannot add entry.\n");
return -EINVAL;
}
- l2_lookup.lockeds = true;
l2_lookup.index = i;
skip_finding_an_index:
+ l2_lookup.lockeds = true;
+
rc = sja1105_dynamic_config_write(priv, BLK_IDX_L2_LOOKUP,
l2_lookup.index, &l2_lookup,
true);
if (rc < 0)
return rc;
+ /* The switch learns dynamic entries and looks up the FDB left to
+ * right. It is possible that our addition was concurrent with the
+ * dynamic learning of the same address, so now that the static entry
+ * has been installed, we are certain that address learning for this
+ * particular address has been turned off, so the dynamic entry either
+ * is in the FDB at an index smaller than the static one, or isn't (it
+ * can also be at a larger index, but in that case it is inactive
+ * because the static FDB entry will match first, and the dynamic one
+ * will eventually age out). Search for a dynamically learned address
+ * prior to our static one and invalidate it.
+ */
+ tmp = l2_lookup;
+
+ rc = sja1105_dynamic_config_read(priv, BLK_IDX_L2_LOOKUP,
+ SJA1105_SEARCH, &tmp);
+ if (rc < 0) {
+ dev_err(ds->dev,
+ "port %d failed to read back entry for %pM vid %d: %pe\n",
+ port, addr, vid, ERR_PTR(rc));
+ return rc;
+ }
+
+ if (tmp.index < l2_lookup.index) {
+ rc = sja1105_dynamic_config_write(priv, BLK_IDX_L2_LOOKUP,
+ tmp.index, NULL, false);
+ if (rc < 0)
+ return rc;
+ }
+
return sja1105_static_fdb_change(priv, port, &l2_lookup, true);
}
l2_lookup.macaddr = ether_addr_to_u64(addr);
l2_lookup.vlanid = vid;
- l2_lookup.iotag = SJA1105_S_TAG;
l2_lookup.mask_macaddr = GENMASK_ULL(ETH_ALEN * 8 - 1, 0);
- if (priv->vlan_state != SJA1105_VLAN_UNAWARE) {
- l2_lookup.mask_vlanid = VLAN_VID_MASK;
- l2_lookup.mask_iotag = BIT(0);
- } else {
- l2_lookup.mask_vlanid = 0;
- l2_lookup.mask_iotag = 0;
- }
+ l2_lookup.mask_vlanid = VLAN_VID_MASK;
l2_lookup.destports = BIT(port);
rc = sja1105_dynamic_config_read(priv, BLK_IDX_L2_LOOKUP,
int ret_val;
u16 mii_bmcr_data = BMCR_RESET;
+ if (hw->nic_type == athr_mt) {
+ hw->phy_configured = true;
+ return 0;
+ }
+
if ((atl1c_read_phy_reg(hw, MII_PHYSID1, &hw->phy_id1) != 0) ||
(atl1c_read_phy_reg(hw, MII_PHYSID2, &hw->phy_id2) != 0)) {
dev_err(&pdev->dev, "Error get phy ID\n");
}
/* Allocated memory for FW statistics */
- if (bnx2x_alloc_fw_stats_mem(bp))
+ rc = bnx2x_alloc_fw_stats_mem(bp);
+ if (rc)
LOAD_ERROR_EXIT(bp, load_error0);
/* request pf to initialize status blocks */
if ((tpa_info->flags2 & RX_CMP_FLAGS2_META_FORMAT_VLAN) &&
(skb->dev->features & BNXT_HW_FEATURE_VLAN_ALL_RX)) {
- u16 vlan_proto = tpa_info->metadata >>
- RX_CMP_FLAGS2_METADATA_TPID_SFT;
+ __be16 vlan_proto = htons(tpa_info->metadata >>
+ RX_CMP_FLAGS2_METADATA_TPID_SFT);
u16 vtag = tpa_info->metadata & RX_CMP_FLAGS2_METADATA_TCI_MASK;
- __vlan_hwaccel_put_tag(skb, htons(vlan_proto), vtag);
+ if (eth_type_vlan(vlan_proto)) {
+ __vlan_hwaccel_put_tag(skb, vlan_proto, vtag);
+ } else {
+ dev_kfree_skb(skb);
+ return NULL;
+ }
}
skb_checksum_none_assert(skb);
(skb->dev->features & BNXT_HW_FEATURE_VLAN_ALL_RX)) {
u32 meta_data = le32_to_cpu(rxcmp1->rx_cmp_meta_data);
u16 vtag = meta_data & RX_CMP_FLAGS2_METADATA_TCI_MASK;
- u16 vlan_proto = meta_data >> RX_CMP_FLAGS2_METADATA_TPID_SFT;
+ __be16 vlan_proto = htons(meta_data >>
+ RX_CMP_FLAGS2_METADATA_TPID_SFT);
- __vlan_hwaccel_put_tag(skb, htons(vlan_proto), vtag);
+ if (eth_type_vlan(vlan_proto)) {
+ __vlan_hwaccel_put_tag(skb, vlan_proto, vtag);
+ } else {
+ dev_kfree_skb(skb);
+ goto next_rx;
+ }
}
skb_checksum_none_assert(skb);
bp->flags &= ~BNXT_FLAG_WOL_CAP;
if (flags & FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED)
bp->flags |= BNXT_FLAG_WOL_CAP;
- if (flags & FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED)
+ if (flags & FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED) {
__bnxt_hwrm_ptp_qcfg(bp);
+ } else {
+ kfree(bp->ptp_cfg);
+ bp->ptp_cfg = NULL;
+ }
} else {
#ifdef CONFIG_BNXT_SRIOV
struct bnxt_vf_info *vf = &bp->vf;
}
}
- bnxt_ptp_start(bp);
rc = bnxt_init_nic(bp, irq_re_init);
if (rc) {
netdev_err(bp->dev, "bnxt_init_nic err: %x\n", rc);
{
int rc = 0;
+ if (test_bit(BNXT_STATE_ABORT_ERR, &bp->state)) {
+ netdev_err(bp->dev, "A previous firmware reset has not completed, aborting half open\n");
+ rc = -ENODEV;
+ goto half_open_err;
+ }
+
rc = bnxt_alloc_mem(bp, false);
if (rc) {
netdev_err(bp->dev, "bnxt_alloc_mem err: %x\n", rc);
rc = bnxt_hwrm_if_change(bp, true);
if (rc)
return rc;
+
+ if (bnxt_ptp_init(bp)) {
+ netdev_warn(dev, "PTP initialization failed.\n");
+ kfree(bp->ptp_cfg);
+ bp->ptp_cfg = NULL;
+ }
rc = __bnxt_open_nic(bp, true, true);
if (rc) {
bnxt_hwrm_if_change(bp, false);
+ bnxt_ptp_clear(bp);
} else {
if (test_and_clear_bit(BNXT_STATE_FW_RESET_DET, &bp->state)) {
if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
{
struct bnxt *bp = netdev_priv(dev);
+ bnxt_ptp_clear(bp);
bnxt_hwmon_close(bp);
bnxt_close_nic(bp, true, true);
bnxt_hwrm_shutdown_link(bp);
bnxt_clear_int_mode(bp);
pci_disable_device(bp->pdev);
}
+ bnxt_ptp_clear(bp);
__bnxt_close_nic(bp, true, false);
bnxt_vf_reps_free(bp);
bnxt_clear_int_mode(bp);
(bp->fw_reset_max_dsecs * HZ / 10));
}
+static void bnxt_fw_reset_abort(struct bnxt *bp, int rc)
+{
+ clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
+ if (bp->fw_reset_state != BNXT_FW_RESET_STATE_POLL_VF) {
+ bnxt_ulp_start(bp, rc);
+ bnxt_dl_health_status_update(bp, false);
+ }
+ bp->fw_reset_state = 0;
+ dev_close(bp->dev);
+}
+
static void bnxt_fw_reset_task(struct work_struct *work)
{
struct bnxt *bp = container_of(work, struct bnxt, fw_reset_task.work);
- int rc;
+ int rc = 0;
if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
netdev_err(bp->dev, "bnxt_fw_reset_task() called when not in fw reset mode!\n");
}
bp->fw_reset_timestamp = jiffies;
rtnl_lock();
+ if (test_bit(BNXT_STATE_ABORT_ERR, &bp->state)) {
+ bnxt_fw_reset_abort(bp, rc);
+ rtnl_unlock();
+ return;
+ }
bnxt_fw_reset_close(bp);
if (bp->fw_cap & BNXT_FW_CAP_ERR_RECOVER_RELOAD) {
bp->fw_reset_state = BNXT_FW_RESET_STATE_POLL_FW_DOWN;
if (val == 0xffff) {
if (bnxt_fw_reset_timeout(bp)) {
netdev_err(bp->dev, "Firmware reset aborted, PCI config space invalid\n");
+ rc = -ETIMEDOUT;
goto fw_reset_abort;
}
bnxt_queue_fw_reset_work(bp, HZ / 1000);
clear_bit(BNXT_STATE_FW_FATAL_COND, &bp->state);
if (pci_enable_device(bp->pdev)) {
netdev_err(bp->dev, "Cannot re-enable PCI device\n");
+ rc = -ENODEV;
goto fw_reset_abort;
}
pci_set_master(bp->pdev);
}
rc = bnxt_open(bp->dev);
if (rc) {
- netdev_err(bp->dev, "bnxt_open_nic() failed\n");
- clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
- dev_close(bp->dev);
+ netdev_err(bp->dev, "bnxt_open() failed during FW reset\n");
+ bnxt_fw_reset_abort(bp, rc);
+ rtnl_unlock();
+ return;
}
bp->fw_reset_state = 0;
/* Make sure fw_reset_state is 0 before clearing the flag */
smp_mb__before_atomic();
clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
- bnxt_ulp_start(bp, rc);
- if (!rc)
- bnxt_reenable_sriov(bp);
+ bnxt_ulp_start(bp, 0);
+ bnxt_reenable_sriov(bp);
bnxt_vf_reps_alloc(bp);
bnxt_vf_reps_open(bp);
bnxt_dl_health_recovery_done(bp);
netdev_err(bp->dev, "fw_health_status 0x%x\n", sts);
}
fw_reset_abort:
- clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
- if (bp->fw_reset_state != BNXT_FW_RESET_STATE_POLL_VF)
- bnxt_dl_health_status_update(bp, false);
- bp->fw_reset_state = 0;
rtnl_lock();
- dev_close(bp->dev);
+ bnxt_fw_reset_abort(bp, rc);
rtnl_unlock();
}
if (BNXT_PF(bp))
devlink_port_type_clear(&bp->dl_port);
- bnxt_ptp_clear(bp);
pci_disable_pcie_error_reporting(pdev);
unregister_netdev(dev);
clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
rc);
}
- if (bnxt_ptp_init(bp)) {
- netdev_warn(dev, "PTP initialization failed.\n");
- kfree(bp->ptp_cfg);
- bp->ptp_cfg = NULL;
- }
bnxt_inv_fw_health_reg(bp);
bnxt_dl_register(bp);
if (netif_running(netdev))
bnxt_close(netdev);
- pci_disable_device(pdev);
+ if (pci_is_enabled(pdev))
+ pci_disable_device(pdev);
bnxt_free_ctx_mem(bp);
kfree(bp->ctx);
bp->ctx = NULL;
static int bnxt_ets_validate(struct bnxt *bp, struct ieee_ets *ets, u8 *tc)
{
int total_ets_bw = 0;
+ bool zero = false;
u8 max_tc = 0;
int i;
break;
case IEEE_8021QAZ_TSA_ETS:
total_ets_bw += ets->tc_tx_bw[i];
+ zero = zero || !ets->tc_tx_bw[i];
break;
default:
return -ENOTSUPP;
}
}
- if (total_ets_bw > 100)
+ if (total_ets_bw > 100) {
+ netdev_warn(bp->dev, "rejecting ETS config exceeding available bandwidth\n");
return -EINVAL;
+ }
+ if (zero && total_ets_bw == 100) {
+ netdev_warn(bp->dev, "rejecting ETS config starving a TC\n");
+ return -EINVAL;
+ }
if (max_tc >= bp->max_tc)
*tc = bp->max_tc;
bnxt_ptp_get_current_time(bp);
ptp->next_period = now + HZ;
+ if (time_after_eq(now, ptp->next_overflow_check)) {
+ spin_lock_bh(&ptp->ptp_lock);
+ timecounter_read(&ptp->tc);
+ spin_unlock_bh(&ptp->ptp_lock);
+ ptp->next_overflow_check = now + BNXT_PHC_OVERFLOW_PERIOD;
+ }
return HZ;
}
return 0;
}
-void bnxt_ptp_start(struct bnxt *bp)
-{
- struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
-
- if (!ptp)
- return;
-
- if (bp->flags & BNXT_FLAG_CHIP_P5) {
- spin_lock_bh(&ptp->ptp_lock);
- ptp->current_time = bnxt_refclk_read(bp, NULL);
- WRITE_ONCE(ptp->old_time, ptp->current_time);
- spin_unlock_bh(&ptp->ptp_lock);
- ptp_schedule_worker(ptp->ptp_clock, 0);
- }
-}
-
static const struct ptp_clock_info bnxt_ptp_caps = {
.owner = THIS_MODULE,
.name = "bnxt clock",
ptp->cc.shift = 0;
ptp->cc.mult = 1;
+ ptp->next_overflow_check = jiffies + BNXT_PHC_OVERFLOW_PERIOD;
timecounter_init(&ptp->tc, &ptp->cc, ktime_to_ns(ktime_get_real()));
ptp->ptp_info = bnxt_ptp_caps;
bnxt_unmap_ptp_regs(bp);
return err;
}
-
+ if (bp->flags & BNXT_FLAG_CHIP_P5) {
+ spin_lock_bh(&ptp->ptp_lock);
+ ptp->current_time = bnxt_refclk_read(bp, NULL);
+ WRITE_ONCE(ptp->old_time, ptp->current_time);
+ spin_unlock_bh(&ptp->ptp_lock);
+ ptp_schedule_worker(ptp->ptp_clock, 0);
+ }
return 0;
}
u64 current_time;
u64 old_time;
unsigned long next_period;
+ unsigned long next_overflow_check;
+ /* 48-bit PHC overflows in 78 hours. Check overflow every 19 hours. */
+ #define BNXT_PHC_OVERFLOW_PERIOD (19 * 3600 * HZ)
+
u16 tx_seqid;
struct bnxt *bp;
atomic_t tx_avail;
int bnxt_hwtstamp_get(struct net_device *dev, struct ifreq *ifr);
int bnxt_get_tx_ts_p5(struct bnxt *bp, struct sk_buff *skb);
int bnxt_get_rx_ts_p5(struct bnxt *bp, u64 *ts, u32 pkt_ts);
-void bnxt_ptp_start(struct bnxt *bp);
int bnxt_ptp_init(struct bnxt *bp);
void bnxt_ptp_clear(struct bnxt *bp);
#endif
if (!edev)
return ERR_PTR(-ENOMEM);
edev->en_ops = &bnxt_en_ops_tbl;
- if (bp->flags & BNXT_FLAG_ROCEV1_CAP)
- edev->flags |= BNXT_EN_FLAG_ROCEV1_CAP;
- if (bp->flags & BNXT_FLAG_ROCEV2_CAP)
- edev->flags |= BNXT_EN_FLAG_ROCEV2_CAP;
edev->net = dev;
edev->pdev = bp->pdev;
edev->l2_db_size = bp->db_size;
edev->l2_db_size_nc = bp->db_size;
bp->edev = edev;
}
+ edev->flags &= ~BNXT_EN_FLAG_ROCE_CAP;
+ if (bp->flags & BNXT_FLAG_ROCEV1_CAP)
+ edev->flags |= BNXT_EN_FLAG_ROCEV1_CAP;
+ if (bp->flags & BNXT_FLAG_ROCEV2_CAP)
+ edev->flags |= BNXT_EN_FLAG_ROCEV2_CAP;
return bp->edev;
}
EXPORT_SYMBOL(bnxt_ulp_probe);
switch (mode) {
case GENET_POWER_PASSIVE:
- reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS);
+ reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS |
+ EXT_ENERGY_DET_MASK);
if (GENET_IS_V5(priv)) {
reg &= ~(EXT_PWR_DOWN_PHY_EN |
EXT_PWR_DOWN_PHY_RD |
/* Returns a reusable dma control register value */
static u32 bcmgenet_dma_disable(struct bcmgenet_priv *priv)
{
+ unsigned int i;
u32 reg;
u32 dma_ctrl;
/* disable DMA */
dma_ctrl = 1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT) | DMA_EN;
+ for (i = 0; i < priv->hw_params->tx_queues; i++)
+ dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
reg &= ~dma_ctrl;
bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
+ dma_ctrl = 1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT) | DMA_EN;
+ for (i = 0; i < priv->hw_params->rx_queues; i++)
+ dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
reg &= ~dma_ctrl;
bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
{
struct bcmgenet_priv *priv = netdev_priv(dev);
unsigned long dma_ctrl;
- u32 reg;
int ret;
netif_dbg(priv, ifup, dev, "bcmgenet_open\n");
bcmgenet_set_hw_addr(priv, dev->dev_addr);
- if (priv->internal_phy) {
- reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
- reg |= EXT_ENERGY_DET_MASK;
- bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
- }
-
/* Disable RX/TX DMA and flush TX queues */
dma_ctrl = bcmgenet_dma_disable(priv);
struct bcmgenet_priv *priv = netdev_priv(dev);
struct bcmgenet_rxnfc_rule *rule;
unsigned long dma_ctrl;
- u32 reg;
int ret;
if (!netif_running(dev))
if (rule->state != BCMGENET_RXNFC_STATE_UNUSED)
bcmgenet_hfb_create_rxnfc_filter(priv, rule);
- if (priv->internal_phy) {
- reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
- reg |= EXT_ENERGY_DET_MASK;
- bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
- }
-
/* Disable RX/TX DMA and flush TX queues */
dma_ctrl = bcmgenet_dma_disable(priv);
reg |= CMD_RX_EN;
bcmgenet_umac_writel(priv, reg, UMAC_CMD);
- if (priv->hw_params->flags & GENET_HAS_EXT) {
- reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
- reg &= ~EXT_ENERGY_DET_MASK;
- bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
- }
-
reg = UMAC_IRQ_MPD_R;
if (hfb_enable)
reg |= UMAC_IRQ_HFB_SM | UMAC_IRQ_HFB_MM;
* bits 32:47 indicate the PVF num.
*/
for (q_no = 0; q_no < ern; q_no++) {
- reg_val = oct->pcie_port << CN23XX_PKT_INPUT_CTL_MAC_NUM_POS;
+ reg_val = (u64)oct->pcie_port << CN23XX_PKT_INPUT_CTL_MAC_NUM_POS;
/* for VF assigned queues. */
if (q_no < oct->sriov_info.pf_srn) {
{
unsigned int i;
+ if (!is_uld(adap))
+ return;
+
mutex_lock(&uld_mutex);
list_del(&adap->list_node);
*/
destroy_workqueue(adapter->workq);
- if (is_uld(adapter)) {
- detach_ulds(adapter);
- t4_uld_clean_up(adapter);
- }
+ detach_ulds(adapter);
+
+ for_each_port(adapter, i)
+ if (adapter->port[i]->reg_state == NETREG_REGISTERED)
+ unregister_netdev(adapter->port[i]);
+
+ t4_uld_clean_up(adapter);
adap_free_hma_mem(adapter);
cxgb4_free_mps_ref_entries(adapter);
- for_each_port(adapter, i)
- if (adapter->port[i]->reg_state == NETREG_REGISTERED)
- unregister_netdev(adapter->port[i]);
-
debugfs_remove_recursive(adapter->debugfs_root);
if (!is_t4(adapter->params.chip))
{
unsigned int i;
+ if (!is_uld(adap))
+ return;
+
mutex_lock(&uld_mutex);
for (i = 0; i < CXGB4_ULD_MAX; i++) {
if (!adap->uld[i].handle)
int i, option = find_cnt < MAX_UNITS ? options[find_cnt] : 0;
void __iomem *ioaddr;
- i = pci_enable_device(pdev);
+ i = pcim_enable_device(pdev);
if (i) return i;
pci_set_master(pdev);
ioaddr = pci_iomap(pdev, TULIP_BAR, netdev_res_size);
if (!ioaddr)
- goto err_out_free_res;
+ goto err_out_netdev;
for (i = 0; i < 3; i++)
((__le16 *)dev->dev_addr)[i] = cpu_to_le16(eeprom_read(ioaddr, i));
err_out_cleardev:
pci_iounmap(pdev, ioaddr);
-err_out_free_res:
- pci_release_regions(pdev);
err_out_netdev:
free_netdev (dev);
return -ENODEV;
if (dev) {
struct netdev_private *np = netdev_priv(dev);
unregister_netdev(dev);
- pci_release_regions(pdev);
pci_iounmap(pdev, np->base_addr);
free_netdev(dev);
}
if (err)
return err;
- err = dpaa2_switch_seed_bp(ethsw);
- if (err)
- goto err_free_dpbp;
-
err = dpaa2_switch_alloc_rings(ethsw);
if (err)
- goto err_drain_dpbp;
+ goto err_free_dpbp;
err = dpaa2_switch_setup_dpio(ethsw);
if (err)
goto err_destroy_rings;
+ err = dpaa2_switch_seed_bp(ethsw);
+ if (err)
+ goto err_deregister_dpio;
+
err = dpsw_ctrl_if_enable(ethsw->mc_io, 0, ethsw->dpsw_handle);
if (err) {
dev_err(ethsw->dev, "dpsw_ctrl_if_enable err %d\n", err);
- goto err_deregister_dpio;
+ goto err_drain_dpbp;
}
return 0;
+err_drain_dpbp:
+ dpaa2_switch_drain_bp(ethsw);
err_deregister_dpio:
dpaa2_switch_free_dpio(ethsw);
err_destroy_rings:
dpaa2_switch_destroy_rings(ethsw);
-err_drain_dpbp:
- dpaa2_switch_drain_bp(ethsw);
err_free_dpbp:
dpaa2_switch_free_dpbp(ethsw);
if (of_phy_is_fixed_link(np))
of_phy_deregister_fixed_link(np);
of_node_put(fep->phy_node);
- free_netdev(ndev);
clk_disable_unprepare(fep->clk_ahb);
clk_disable_unprepare(fep->clk_ipg);
pm_runtime_put_noidle(&pdev->dev);
pm_runtime_disable(&pdev->dev);
+ free_netdev(ndev);
return 0;
}
| SUPPORTED_Autoneg \
| SUPPORTED_Pause \
| SUPPORTED_Asym_Pause \
+ | SUPPORTED_FIBRE \
| SUPPORTED_MII)
static DEFINE_MUTEX(eth_lock);
err = pci_enable_device(pdev);
if (err)
- return -ENXIO;
+ return err;
err = pci_request_regions(pdev, "gvnic-cfg");
if (err)
pci_set_master(pdev);
- err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
if (err) {
dev_err(&pdev->dev, "Failed to set dma mask: err=%d\n", err);
goto abort_with_pci_region;
}
- err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
- if (err) {
- dev_err(&pdev->dev,
- "Failed to set consistent dma mask: err=%d\n", err);
- goto abort_with_pci_region;
- }
-
reg_bar = pci_iomap(pdev, GVE_REGISTER_BAR, 0);
if (!reg_bar) {
dev_err(&pdev->dev, "Failed to map pci bar!\n");
dev = alloc_etherdev_mqs(sizeof(*priv), max_tx_queues, max_rx_queues);
if (!dev) {
dev_err(&pdev->dev, "could not allocate netdev\n");
+ err = -ENOMEM;
goto abort_with_db_bar;
}
SET_NETDEV_DEV(dev, &pdev->dev);
err = register_netdev(dev);
if (err)
- goto abort_with_wq;
+ goto abort_with_gve_init;
dev_info(&pdev->dev, "GVE version %s\n", gve_version_str);
dev_info(&pdev->dev, "GVE queue format %d\n", (int)priv->queue_format);
queue_work(priv->gve_wq, &priv->service_task);
return 0;
+abort_with_gve_init:
+ gve_teardown_priv_resources(priv);
+
abort_with_wq:
destroy_workqueue(priv->gve_wq);
abort_with_enabled:
pci_disable_device(pdev);
- return -ENXIO;
+ return err;
}
static void gve_remove(struct pci_dev *pdev)
return 0;
}
- /* Prefetch the payload header. */
- prefetch((char *)buf_state->addr + buf_state->page_info.page_offset);
-#if L1_CACHE_BYTES < 128
- prefetch((char *)buf_state->addr + buf_state->page_info.page_offset +
- L1_CACHE_BYTES);
-#endif
-
if (eop && buf_len <= priv->rx_copybreak) {
rx->skb_head = gve_rx_copy(priv->dev, napi,
&buf_state->page_info, buf_len, 0);
/* buf unit size is cache_line_size, which is 64, so the shift is 6 */
#define PPE_BUF_SIZE_SHIFT 6
#define PPE_TX_BUF_HOLD BIT(31)
-#define CACHE_LINE_MASK 0x3F
+#define SOC_CACHE_LINE_MASK 0x3F
#else
#define PPE_CFG_QOS_VMID_GRP_SHIFT 8
#define PPE_CFG_RX_CTRL_ALIGN_SHIFT 11
#if defined(CONFIG_HI13X1_GMAC)
desc->cfg = (__force u32)cpu_to_be32(TX_CLEAR_WB | TX_FINISH_CACHE_INV
| TX_RELEASE_TO_PPE | priv->port << TX_POOL_SHIFT);
- desc->data_offset = (__force u32)cpu_to_be32(phys & CACHE_LINE_MASK);
- desc->send_addr = (__force u32)cpu_to_be32(phys & ~CACHE_LINE_MASK);
+ desc->data_offset = (__force u32)cpu_to_be32(phys & SOC_CACHE_LINE_MASK);
+ desc->send_addr = (__force u32)cpu_to_be32(phys & ~SOC_CACHE_LINE_MASK);
#else
desc->cfg = (__force u32)cpu_to_be32(TX_CLEAR_WB | TX_FINISH_CACHE_INV);
desc->send_addr = (__force u32)cpu_to_be32(phys);
u32 origin_mbx_msg;
bool received_resp;
int resp_status;
+ u16 match_id;
u8 additional_info[HCLGE_MBX_MAX_RESP_DATA_SIZE];
};
u8 mbx_need_resp;
u8 rsv1[1];
u8 msg_len;
- u8 rsv2[3];
+ u8 rsv2;
+ u16 match_id;
struct hclge_vf_to_pf_msg msg;
};
u8 dest_vfid;
u8 rsv[3];
u8 msg_len;
- u8 rsv1[3];
+ u8 rsv1;
+ u16 match_id;
struct hclge_pf_to_vf_msg msg;
};
if (ret)
return ret;
- if (test_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B, ae_dev->caps))
+ if (test_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B, ae_dev->caps)) {
ret = hclge_set_port_vlan_filter_bypass(hdev, vport->vport_id,
!enable);
- else if (!vport->vport_id)
+ } else if (!vport->vport_id) {
+ if (test_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, ae_dev->caps))
+ enable = false;
+
ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_PORT,
HCLGE_FILTER_FE_INGRESS,
enable, 0);
+ }
return ret;
}
resp_pf_to_vf->dest_vfid = vf_to_pf_req->mbx_src_vfid;
resp_pf_to_vf->msg_len = vf_to_pf_req->msg_len;
+ resp_pf_to_vf->match_id = vf_to_pf_req->match_id;
resp_pf_to_vf->msg.code = HCLGE_MBX_PF_VF_RESP;
resp_pf_to_vf->msg.vf_mbx_msg_code = vf_to_pf_req->msg.code;
#include "hclge_main.h"
#include "hnae3.h"
+static int hclge_ptp_get_cycle(struct hclge_dev *hdev)
+{
+ struct hclge_ptp *ptp = hdev->ptp;
+
+ ptp->cycle.quo = readl(hdev->ptp->io_base + HCLGE_PTP_CYCLE_QUO_REG) &
+ HCLGE_PTP_CYCLE_QUO_MASK;
+ ptp->cycle.numer = readl(hdev->ptp->io_base + HCLGE_PTP_CYCLE_NUM_REG);
+ ptp->cycle.den = readl(hdev->ptp->io_base + HCLGE_PTP_CYCLE_DEN_REG);
+
+ if (ptp->cycle.den == 0) {
+ dev_err(&hdev->pdev->dev, "invalid ptp cycle denominator!\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int hclge_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
{
struct hclge_dev *hdev = hclge_ptp_get_hdev(ptp);
+ struct hclge_ptp_cycle *cycle = &hdev->ptp->cycle;
u64 adj_val, adj_base, diff;
unsigned long flags;
bool is_neg = false;
is_neg = true;
}
- adj_base = HCLGE_PTP_CYCLE_ADJ_BASE * HCLGE_PTP_CYCLE_ADJ_UNIT;
+ adj_base = (u64)cycle->quo * (u64)cycle->den + (u64)cycle->numer;
adj_val = adj_base * ppb;
diff = div_u64(adj_val, 1000000000ULL);
/* This clock cycle is defined by three part: quotient, numerator
* and denominator. For example, 2.5ns, the quotient is 2,
- * denominator is fixed to HCLGE_PTP_CYCLE_ADJ_UNIT, and numerator
- * is 0.5 * HCLGE_PTP_CYCLE_ADJ_UNIT.
+ * denominator is fixed to ptp->cycle.den, and numerator
+ * is 0.5 * ptp->cycle.den.
*/
- quo = div_u64_rem(adj_val, HCLGE_PTP_CYCLE_ADJ_UNIT, &numerator);
+ quo = div_u64_rem(adj_val, cycle->den, &numerator);
spin_lock_irqsave(&hdev->ptp->lock, flags);
- writel(quo, hdev->ptp->io_base + HCLGE_PTP_CYCLE_QUO_REG);
+ writel(quo & HCLGE_PTP_CYCLE_QUO_MASK,
+ hdev->ptp->io_base + HCLGE_PTP_CYCLE_QUO_REG);
writel(numerator, hdev->ptp->io_base + HCLGE_PTP_CYCLE_NUM_REG);
- writel(HCLGE_PTP_CYCLE_ADJ_UNIT,
- hdev->ptp->io_base + HCLGE_PTP_CYCLE_DEN_REG);
+ writel(cycle->den, hdev->ptp->io_base + HCLGE_PTP_CYCLE_DEN_REG);
writel(HCLGE_PTP_CYCLE_ADJ_EN,
hdev->ptp->io_base + HCLGE_PTP_CYCLE_CFG_REG);
spin_unlock_irqrestore(&hdev->ptp->lock, flags);
ret = hclge_ptp_create_clock(hdev);
if (ret)
return ret;
+
+ ret = hclge_ptp_get_cycle(hdev);
+ if (ret)
+ return ret;
}
ret = hclge_ptp_int_en(hdev, true);
#define HCLGE_PTP_TIME_ADJ_REG 0x60
#define HCLGE_PTP_TIME_ADJ_EN BIT(0)
#define HCLGE_PTP_CYCLE_QUO_REG 0x64
+#define HCLGE_PTP_CYCLE_QUO_MASK GENMASK(7, 0)
#define HCLGE_PTP_CYCLE_DEN_REG 0x68
#define HCLGE_PTP_CYCLE_NUM_REG 0x6C
#define HCLGE_PTP_CYCLE_CFG_REG 0x70
#define HCLGE_PTP_CUR_TIME_SEC_L_REG 0x78
#define HCLGE_PTP_CUR_TIME_NSEC_REG 0x7C
-#define HCLGE_PTP_CYCLE_ADJ_BASE 2
#define HCLGE_PTP_CYCLE_ADJ_MAX 500000000
-#define HCLGE_PTP_CYCLE_ADJ_UNIT 100000000
#define HCLGE_PTP_SEC_H_OFFSET 32u
#define HCLGE_PTP_SEC_L_MASK GENMASK(31, 0)
#define HCLGE_PTP_FLAG_TX_EN 1
#define HCLGE_PTP_FLAG_RX_EN 2
+struct hclge_ptp_cycle {
+ u32 quo;
+ u32 numer;
+ u32 den;
+};
+
struct hclge_ptp {
struct hclge_dev *hdev;
struct ptp_clock *clock;
spinlock_t lock; /* protects ptp registers */
u32 ptp_cfg;
u32 last_tx_seqid;
+ struct hclge_ptp_cycle cycle;
unsigned long tx_start;
unsigned long tx_cnt;
unsigned long tx_skipped;
static int hclgevf_init_vlan_config(struct hclgevf_dev *hdev)
{
+ struct hnae3_handle *nic = &hdev->nic;
+ int ret;
+
+ ret = hclgevf_en_hw_strip_rxvtag(nic, true);
+ if (ret) {
+ dev_err(&hdev->pdev->dev,
+ "failed to enable rx vlan offload, ret = %d\n", ret);
+ return ret;
+ }
+
return hclgevf_set_vlan_filter(&hdev->nic, htons(ETH_P_8021Q), 0,
false);
}
return resp_code ? -resp_code : 0;
}
+#define HCLGEVF_MBX_MATCH_ID_START 1
static void hclgevf_reset_mbx_resp_status(struct hclgevf_dev *hdev)
{
/* this function should be called with mbx_resp.mbx_mutex held
hdev->mbx_resp.received_resp = false;
hdev->mbx_resp.origin_mbx_msg = 0;
hdev->mbx_resp.resp_status = 0;
+ hdev->mbx_resp.match_id++;
+ /* Update match_id and ensure the value of match_id is not zero */
+ if (hdev->mbx_resp.match_id == 0)
+ hdev->mbx_resp.match_id = HCLGEVF_MBX_MATCH_ID_START;
memset(hdev->mbx_resp.additional_info, 0, HCLGE_MBX_MAX_RESP_DATA_SIZE);
}
if (need_resp) {
mutex_lock(&hdev->mbx_resp.mbx_mutex);
hclgevf_reset_mbx_resp_status(hdev);
+ req->match_id = hdev->mbx_resp.match_id;
status = hclgevf_cmd_send(&hdev->hw, &desc, 1);
if (status) {
dev_err(&hdev->pdev->dev,
resp->additional_info[i] = *temp;
temp++;
}
+
+ /* If match_id is not zero, it means PF support
+ * match_id. If the match_id is right, VF get the
+ * right response, otherwise ignore the response.
+ * Driver will clear hdev->mbx_resp when send
+ * next message which need response.
+ */
+ if (req->match_id) {
+ if (req->match_id == resp->match_id)
+ resp->received_resp = true;
+ } else {
+ resp->received_resp = true;
+ }
break;
case HCLGE_MBX_LINK_STAT_CHANGE:
case HCLGE_MBX_ASSERTING_RESET:
tx_send_failed++;
tx_dropped++;
ret = NETDEV_TX_OK;
- ibmvnic_tx_scrq_flush(adapter, tx_scrq);
goto out;
}
dev_kfree_skb_any(skb);
tx_send_failed++;
tx_dropped++;
+ ibmvnic_tx_scrq_flush(adapter, tx_scrq);
ret = NETDEV_TX_OK;
goto out;
}
static void __ibmvnic_reset(struct work_struct *work)
{
- struct ibmvnic_rwi *rwi;
struct ibmvnic_adapter *adapter;
bool saved_state = false;
+ struct ibmvnic_rwi *tmprwi;
+ struct ibmvnic_rwi *rwi;
unsigned long flags;
u32 reset_state;
int rc = 0;
} else {
rc = do_reset(adapter, rwi, reset_state);
}
- kfree(rwi);
+ tmprwi = rwi;
adapter->last_reset_time = jiffies;
if (rc)
rwi = get_next_rwi(adapter);
+ /*
+ * If there is another reset queued, free the previous rwi
+ * and process the new reset even if previous reset failed
+ * (the previous reset could have failed because of a fail
+ * over for instance, so process the fail over).
+ *
+ * If there are no resets queued and the previous reset failed,
+ * the adapter would be in an undefined state. So retry the
+ * previous reset as a hard reset.
+ */
+ if (rwi)
+ kfree(tmprwi);
+ else if (rc)
+ rwi = tmprwi;
+
if (rwi && (rwi->reset_reason == VNIC_RESET_FAILOVER ||
- rwi->reset_reason == VNIC_RESET_MOBILITY))
+ rwi->reset_reason == VNIC_RESET_MOBILITY || rc))
adapter->force_reset_recovery = true;
}
err_ioremap:
free_netdev(netdev);
err_alloc_etherdev:
+ pci_disable_pcie_error_reporting(pdev);
pci_release_mem_regions(pdev);
err_pci_reg:
err_dma:
err_ioremap:
free_netdev(netdev);
err_alloc_netdev:
+ pci_disable_pcie_error_reporting(pdev);
pci_release_mem_regions(pdev);
err_pci_reg:
err_dma:
default:
/* if we got here and link is up something bad is afoot */
netdev_info(netdev,
- "WARNING: Link is up but PHY type 0x%x is not recognized.\n",
+ "WARNING: Link is up but PHY type 0x%x is not recognized, or incorrect cable is in use\n",
hw_link_info->phy_type);
}
dev_warn(&pf->pdev->dev,
"Device configuration forbids SW from starting the LLDP agent.\n");
return -EINVAL;
+ case I40E_AQ_RC_EAGAIN:
+ dev_warn(&pf->pdev->dev,
+ "Stop FW LLDP agent command is still being processed, please try again in a second.\n");
+ return -EBUSY;
default:
dev_warn(&pf->pdev->dev,
"Starting FW LLDP agent failed: error: %s, %s\n",
}
/**
- * i40e_vsi_control_tx - Start or stop a VSI's rings
+ * i40e_vsi_enable_tx - Start a VSI's rings
* @vsi: the VSI being configured
- * @enable: start or stop the rings
**/
-static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable)
+static int i40e_vsi_enable_tx(struct i40e_vsi *vsi)
{
struct i40e_pf *pf = vsi->back;
int i, pf_q, ret = 0;
for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
ret = i40e_control_wait_tx_q(vsi->seid, pf,
pf_q,
- false /*is xdp*/, enable);
+ false /*is xdp*/, true);
if (ret)
break;
ret = i40e_control_wait_tx_q(vsi->seid, pf,
pf_q + vsi->alloc_queue_pairs,
- true /*is xdp*/, enable);
+ true /*is xdp*/, true);
if (ret)
break;
}
}
/**
- * i40e_vsi_control_rx - Start or stop a VSI's rings
+ * i40e_vsi_enable_rx - Start a VSI's rings
* @vsi: the VSI being configured
- * @enable: start or stop the rings
**/
-static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable)
+static int i40e_vsi_enable_rx(struct i40e_vsi *vsi)
{
struct i40e_pf *pf = vsi->back;
int i, pf_q, ret = 0;
pf_q = vsi->base_queue;
for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
- ret = i40e_control_wait_rx_q(pf, pf_q, enable);
+ ret = i40e_control_wait_rx_q(pf, pf_q, true);
if (ret) {
dev_info(&pf->pdev->dev,
- "VSI seid %d Rx ring %d %sable timeout\n",
- vsi->seid, pf_q, (enable ? "en" : "dis"));
+ "VSI seid %d Rx ring %d enable timeout\n",
+ vsi->seid, pf_q);
break;
}
}
- /* Due to HW errata, on Rx disable only, the register can indicate done
- * before it really is. Needs 50ms to be sure
- */
- if (!enable)
- mdelay(50);
-
return ret;
}
int ret = 0;
/* do rx first for enable and last for disable */
- ret = i40e_vsi_control_rx(vsi, true);
+ ret = i40e_vsi_enable_rx(vsi);
if (ret)
return ret;
- ret = i40e_vsi_control_tx(vsi, true);
+ ret = i40e_vsi_enable_tx(vsi);
return ret;
}
+#define I40E_DISABLE_TX_GAP_MSEC 50
+
/**
* i40e_vsi_stop_rings - Stop a VSI's rings
* @vsi: the VSI being configured
**/
void i40e_vsi_stop_rings(struct i40e_vsi *vsi)
{
+ struct i40e_pf *pf = vsi->back;
+ int pf_q, err, q_end;
+
/* When port TX is suspended, don't wait */
if (test_bit(__I40E_PORT_SUSPENDED, vsi->back->state))
return i40e_vsi_stop_rings_no_wait(vsi);
- /* do rx first for enable and last for disable
- * Ignore return value, we need to shutdown whatever we can
- */
- i40e_vsi_control_tx(vsi, false);
- i40e_vsi_control_rx(vsi, false);
+ q_end = vsi->base_queue + vsi->num_queue_pairs;
+ for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++)
+ i40e_pre_tx_queue_cfg(&pf->hw, (u32)pf_q, false);
+
+ for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++) {
+ err = i40e_control_wait_rx_q(pf, pf_q, false);
+ if (err)
+ dev_info(&pf->pdev->dev,
+ "VSI seid %d Rx ring %d dissable timeout\n",
+ vsi->seid, pf_q);
+ }
+
+ msleep(I40E_DISABLE_TX_GAP_MSEC);
+ pf_q = vsi->base_queue;
+ for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++)
+ wr32(&pf->hw, I40E_QTX_ENA(pf_q), 0);
+
+ i40e_vsi_wait_queues_disabled(vsi);
}
/**
}
if (vsi->num_queue_pairs <
(mqprio_qopt->qopt.offset[i] + mqprio_qopt->qopt.count[i])) {
+ dev_err(&vsi->back->pdev->dev,
+ "Failed to create traffic channel, insufficient number of queues.\n");
return -EINVAL;
}
if (sum_max_rate > i40e_get_link_speed(vsi)) {
.ndo_poll_controller = i40e_netpoll,
#endif
.ndo_setup_tc = __i40e_setup_tc,
+ .ndo_select_queue = i40e_lan_select_queue,
.ndo_set_features = i40e_set_features,
.ndo_set_vf_mac = i40e_ndo_set_vf_mac,
.ndo_set_vf_vlan = i40e_ndo_set_vf_port_vlan,
return -1;
}
+static u16 i40e_swdcb_skb_tx_hash(struct net_device *dev,
+ const struct sk_buff *skb,
+ u16 num_tx_queues)
+{
+ u32 jhash_initval_salt = 0xd631614b;
+ u32 hash;
+
+ if (skb->sk && skb->sk->sk_hash)
+ hash = skb->sk->sk_hash;
+ else
+ hash = (__force u16)skb->protocol ^ skb->hash;
+
+ hash = jhash_1word(hash, jhash_initval_salt);
+
+ return (u16)(((u64)hash * num_tx_queues) >> 32);
+}
+
+u16 i40e_lan_select_queue(struct net_device *netdev,
+ struct sk_buff *skb,
+ struct net_device __always_unused *sb_dev)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_hw *hw;
+ u16 qoffset;
+ u16 qcount;
+ u8 tclass;
+ u16 hash;
+ u8 prio;
+
+ /* is DCB enabled at all? */
+ if (vsi->tc_config.numtc == 1)
+ return i40e_swdcb_skb_tx_hash(netdev, skb,
+ netdev->real_num_tx_queues);
+
+ prio = skb->priority;
+ hw = &vsi->back->hw;
+ tclass = hw->local_dcbx_config.etscfg.prioritytable[prio];
+ /* sanity check */
+ if (unlikely(!(vsi->tc_config.enabled_tc & BIT(tclass))))
+ tclass = 0;
+
+ /* select a queue assigned for the given TC */
+ qcount = vsi->tc_config.tc_info[tclass].qcount;
+ hash = i40e_swdcb_skb_tx_hash(netdev, skb, qcount);
+
+ qoffset = vsi->tc_config.tc_info[tclass].qoffset;
+ return qoffset + hash;
+}
+
/**
* i40e_xmit_xdp_ring - transmits an XDP buffer to an XDP Tx ring
* @xdpf: data to transmit
bool i40e_alloc_rx_buffers(struct i40e_ring *rxr, u16 cleaned_count);
netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev);
+u16 i40e_lan_select_queue(struct net_device *netdev, struct sk_buff *skb,
+ struct net_device *sb_dev);
void i40e_clean_tx_ring(struct i40e_ring *tx_ring);
void i40e_clean_rx_ring(struct i40e_ring *rx_ring);
int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring);
err_ioremap:
free_netdev(netdev);
err_alloc_etherdev:
+ pci_disable_pcie_error_reporting(pdev);
pci_release_regions(pdev);
err_pci_reg:
err_dma:
**/
static int igb_request_msix(struct igb_adapter *adapter)
{
+ unsigned int num_q_vectors = adapter->num_q_vectors;
struct net_device *netdev = adapter->netdev;
int i, err = 0, vector = 0, free_vector = 0;
if (err)
goto err_out;
- for (i = 0; i < adapter->num_q_vectors; i++) {
+ if (num_q_vectors > MAX_Q_VECTORS) {
+ num_q_vectors = MAX_Q_VECTORS;
+ dev_warn(&adapter->pdev->dev,
+ "The number of queue vectors (%d) is higher than max allowed (%d)\n",
+ adapter->num_q_vectors, MAX_Q_VECTORS);
+ }
+ for (i = 0; i < num_q_vectors; i++) {
struct igb_q_vector *q_vector = adapter->q_vector[i];
vector++;
**/
static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
{
- struct igb_ring *ring = adapter->tx_ring[queue];
struct net_device *netdev = adapter->netdev;
struct e1000_hw *hw = &adapter->hw;
+ struct igb_ring *ring;
u32 tqavcc, tqavctrl;
u16 value;
WARN_ON(hw->mac.type != e1000_i210);
WARN_ON(queue < 0 || queue > 1);
+ ring = adapter->tx_ring[queue];
/* If any of the Qav features is enabled, configure queues as SR and
* with HIGH PRIO. If none is, then configure them with LOW PRIO and
err_ioremap:
free_netdev(netdev);
err_alloc_etherdev:
+ pci_disable_pcie_error_reporting(pdev);
pci_release_mem_regions(pdev);
err_pci_reg:
err_dma:
DMA_TO_DEVICE);
}
+ tx_buffer->next_to_watch = NULL;
+
/* move us one more past the eop_desc for start of next pkt */
tx_buffer++;
i++;
if (hw->phy.ops.read_reg)
return hw->phy.ops.read_reg(hw, offset, data);
- return 0;
+ return -EOPNOTSUPP;
}
void igc_reinit_locked(struct igc_adapter *);
igc_unmap_tx_buffer(tx_ring->dev, tx_buffer);
}
+ tx_buffer->next_to_watch = NULL;
+
/* move us one more past the eop_desc for start of next pkt */
tx_buffer++;
i++;
err_ioremap:
free_netdev(netdev);
err_alloc_etherdev:
+ pci_disable_pcie_error_reporting(pdev);
pci_release_mem_regions(pdev);
err_pci_reg:
err_dma:
struct sk_buff *skb)
{
if (ring_uses_build_skb(rx_ring)) {
- unsigned long offset = (unsigned long)(skb->data) & ~PAGE_MASK;
+ unsigned long mask = (unsigned long)ixgbe_rx_pg_size(rx_ring) - 1;
+ unsigned long offset = (unsigned long)(skb->data) & mask;
dma_sync_single_range_for_cpu(rx_ring->dev,
IXGBE_CB(skb)->dma,
disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state);
free_netdev(netdev);
err_alloc_etherdev:
+ pci_disable_pcie_error_reporting(pdev);
pci_release_mem_regions(pdev);
err_pci_reg:
err_dma:
static int ixgbevf_ipsec_parse_proto_keys(struct xfrm_state *xs,
u32 *mykey, u32 *mysalt)
{
- struct net_device *dev = xs->xso.dev;
+ struct net_device *dev = xs->xso.real_dev;
unsigned char *key_data;
char *alg_name = NULL;
int key_len;
**/
static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs)
{
- struct net_device *dev = xs->xso.dev;
- struct ixgbevf_adapter *adapter = netdev_priv(dev);
- struct ixgbevf_ipsec *ipsec = adapter->ipsec;
+ struct net_device *dev = xs->xso.real_dev;
+ struct ixgbevf_adapter *adapter;
+ struct ixgbevf_ipsec *ipsec;
u16 sa_idx;
int ret;
+ adapter = netdev_priv(dev);
+ ipsec = adapter->ipsec;
+
if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) {
netdev_err(dev, "Unsupported protocol 0x%04x for IPsec offload\n",
xs->id.proto);
**/
static void ixgbevf_ipsec_del_sa(struct xfrm_state *xs)
{
- struct net_device *dev = xs->xso.dev;
- struct ixgbevf_adapter *adapter = netdev_priv(dev);
- struct ixgbevf_ipsec *ipsec = adapter->ipsec;
+ struct net_device *dev = xs->xso.real_dev;
+ struct ixgbevf_adapter *adapter;
+ struct ixgbevf_ipsec *ipsec;
u16 sa_idx;
+ adapter = netdev_priv(dev);
+ ipsec = adapter->ipsec;
+
if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) {
sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_RX_INDEX;
skb_frag_off_set(frag, pp->rx_offset_correction);
skb_frag_size_set(frag, data_len);
__skb_frag_set_page(frag, page);
-
- /* last fragment */
- if (len == *size) {
- struct skb_shared_info *sinfo;
-
- sinfo = xdp_get_shared_info_from_buff(xdp);
- sinfo->nr_frags = xdp_sinfo->nr_frags;
- memcpy(sinfo->frags, xdp_sinfo->frags,
- sinfo->nr_frags * sizeof(skb_frag_t));
- }
} else {
page_pool_put_full_page(rxq->page_pool, page, true);
}
+
+ /* last fragment */
+ if (len == *size) {
+ struct skb_shared_info *sinfo;
+
+ sinfo = xdp_get_shared_info_from_buff(xdp);
+ sinfo->nr_frags = xdp_sinfo->nr_frags;
+ memcpy(sinfo->frags, xdp_sinfo->frags,
+ sinfo->nr_frags * sizeof(skb_frag_t));
+ }
*size -= len;
}
rvu_mbox-y := mbox.o rvu_trace.o
rvu_af-y := cgx.o rvu.o rvu_cgx.o rvu_npa.o rvu_nix.o \
rvu_reg.o rvu_npc.o rvu_debugfs.o ptp.o rvu_npc_fs.o \
- rvu_cpt.o rvu_devlink.o rpm.o rvu_cn10k.o
+ rvu_cpt.o rvu_devlink.o rpm.o rvu_cn10k.o rvu_switch.o
return test_bit(lmac_id, &cgx->lmac_bmap);
}
+/* Helper function to get sequential index
+ * given the enabled LMAC of a CGX
+ */
+static int get_sequence_id_of_lmac(struct cgx *cgx, int lmac_id)
+{
+ int tmp, id = 0;
+
+ for_each_set_bit(tmp, &cgx->lmac_bmap, MAX_LMAC_PER_CGX) {
+ if (tmp == lmac_id)
+ break;
+ id++;
+ }
+
+ return id;
+}
+
struct mac_ops *get_mac_ops(void *cgxd)
{
if (!cgxd)
return mac;
}
+static void cfg2mac(u64 cfg, u8 *mac_addr)
+{
+ int i, index = 0;
+
+ for (i = ETH_ALEN - 1; i >= 0; i--, index++)
+ mac_addr[i] = (cfg >> (8 * index)) & 0xFF;
+}
+
int cgx_lmac_addr_set(u8 cgx_id, u8 lmac_id, u8 *mac_addr)
{
struct cgx *cgx_dev = cgx_get_pdata(cgx_id);
+ struct lmac *lmac = lmac_pdata(lmac_id, cgx_dev);
struct mac_ops *mac_ops;
+ int index, id;
u64 cfg;
+ /* access mac_ops to know csr_offset */
mac_ops = cgx_dev->mac_ops;
+
/* copy 6bytes from macaddr */
/* memcpy(&cfg, mac_addr, 6); */
cfg = mac2u64 (mac_addr);
- cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (lmac_id * 0x8)),
+ id = get_sequence_id_of_lmac(cgx_dev, lmac_id);
+
+ index = id * lmac->mac_to_index_bmap.max;
+
+ cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)),
cfg | CGX_DMAC_CAM_ADDR_ENABLE | ((u64)lmac_id << 49));
cfg = cgx_read(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0);
- cfg |= CGX_DMAC_CTL0_CAM_ENABLE;
+ cfg |= (CGX_DMAC_CTL0_CAM_ENABLE | CGX_DMAC_BCAST_MODE |
+ CGX_DMAC_MCAST_MODE);
cgx_write(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0, cfg);
return 0;
}
+u64 cgx_read_dmac_ctrl(void *cgxd, int lmac_id)
+{
+ struct mac_ops *mac_ops;
+ struct cgx *cgx = cgxd;
+
+ if (!cgxd || !is_lmac_valid(cgxd, lmac_id))
+ return 0;
+
+ cgx = cgxd;
+ /* Get mac_ops to know csr offset */
+ mac_ops = cgx->mac_ops;
+
+ return cgx_read(cgxd, lmac_id, CGXX_CMRX_RX_DMAC_CTL0);
+}
+
+u64 cgx_read_dmac_entry(void *cgxd, int index)
+{
+ struct mac_ops *mac_ops;
+ struct cgx *cgx;
+
+ if (!cgxd)
+ return 0;
+
+ cgx = cgxd;
+ mac_ops = cgx->mac_ops;
+ return cgx_read(cgx, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 8)));
+}
+
+int cgx_lmac_addr_add(u8 cgx_id, u8 lmac_id, u8 *mac_addr)
+{
+ struct cgx *cgx_dev = cgx_get_pdata(cgx_id);
+ struct lmac *lmac = lmac_pdata(lmac_id, cgx_dev);
+ struct mac_ops *mac_ops;
+ int index, idx;
+ u64 cfg = 0;
+ int id;
+
+ if (!lmac)
+ return -ENODEV;
+
+ mac_ops = cgx_dev->mac_ops;
+ /* Get available index where entry is to be installed */
+ idx = rvu_alloc_rsrc(&lmac->mac_to_index_bmap);
+ if (idx < 0)
+ return idx;
+
+ id = get_sequence_id_of_lmac(cgx_dev, lmac_id);
+
+ index = id * lmac->mac_to_index_bmap.max + idx;
+
+ cfg = mac2u64 (mac_addr);
+ cfg |= CGX_DMAC_CAM_ADDR_ENABLE;
+ cfg |= ((u64)lmac_id << 49);
+ cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)), cfg);
+
+ cfg = cgx_read(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0);
+ cfg |= (CGX_DMAC_BCAST_MODE | CGX_DMAC_CAM_ACCEPT);
+
+ if (is_multicast_ether_addr(mac_addr)) {
+ cfg &= ~GENMASK_ULL(2, 1);
+ cfg |= CGX_DMAC_MCAST_MODE_CAM;
+ lmac->mcast_filters_count++;
+ } else if (!lmac->mcast_filters_count) {
+ cfg |= CGX_DMAC_MCAST_MODE;
+ }
+
+ cgx_write(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0, cfg);
+
+ return idx;
+}
+
+int cgx_lmac_addr_reset(u8 cgx_id, u8 lmac_id)
+{
+ struct cgx *cgx_dev = cgx_get_pdata(cgx_id);
+ struct lmac *lmac = lmac_pdata(lmac_id, cgx_dev);
+ struct mac_ops *mac_ops;
+ u8 index = 0, id;
+ u64 cfg;
+
+ if (!lmac)
+ return -ENODEV;
+
+ mac_ops = cgx_dev->mac_ops;
+ /* Restore index 0 to its default init value as done during
+ * cgx_lmac_init
+ */
+ set_bit(0, lmac->mac_to_index_bmap.bmap);
+
+ id = get_sequence_id_of_lmac(cgx_dev, lmac_id);
+
+ index = id * lmac->mac_to_index_bmap.max + index;
+ cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)), 0);
+
+ /* Reset CGXX_CMRX_RX_DMAC_CTL0 register to default state */
+ cfg = cgx_read(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0);
+ cfg &= ~CGX_DMAC_CAM_ACCEPT;
+ cfg |= (CGX_DMAC_BCAST_MODE | CGX_DMAC_MCAST_MODE);
+ cgx_write(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0, cfg);
+
+ return 0;
+}
+
+/* Allows caller to change macaddress associated with index
+ * in dmac filter table including index 0 reserved for
+ * interface mac address
+ */
+int cgx_lmac_addr_update(u8 cgx_id, u8 lmac_id, u8 *mac_addr, u8 index)
+{
+ struct cgx *cgx_dev = cgx_get_pdata(cgx_id);
+ struct mac_ops *mac_ops;
+ struct lmac *lmac;
+ u64 cfg;
+ int id;
+
+ lmac = lmac_pdata(lmac_id, cgx_dev);
+ if (!lmac)
+ return -ENODEV;
+
+ mac_ops = cgx_dev->mac_ops;
+ /* Validate the index */
+ if (index >= lmac->mac_to_index_bmap.max)
+ return -EINVAL;
+
+ /* ensure index is already set */
+ if (!test_bit(index, lmac->mac_to_index_bmap.bmap))
+ return -EINVAL;
+
+ id = get_sequence_id_of_lmac(cgx_dev, lmac_id);
+
+ index = id * lmac->mac_to_index_bmap.max + index;
+
+ cfg = cgx_read(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)));
+ cfg &= ~CGX_RX_DMAC_ADR_MASK;
+ cfg |= mac2u64 (mac_addr);
+
+ cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)), cfg);
+ return 0;
+}
+
+int cgx_lmac_addr_del(u8 cgx_id, u8 lmac_id, u8 index)
+{
+ struct cgx *cgx_dev = cgx_get_pdata(cgx_id);
+ struct lmac *lmac = lmac_pdata(lmac_id, cgx_dev);
+ struct mac_ops *mac_ops;
+ u8 mac[ETH_ALEN];
+ u64 cfg;
+ int id;
+
+ if (!lmac)
+ return -ENODEV;
+
+ mac_ops = cgx_dev->mac_ops;
+ /* Validate the index */
+ if (index >= lmac->mac_to_index_bmap.max)
+ return -EINVAL;
+
+ /* Skip deletion for reserved index i.e. index 0 */
+ if (index == 0)
+ return 0;
+
+ rvu_free_rsrc(&lmac->mac_to_index_bmap, index);
+
+ id = get_sequence_id_of_lmac(cgx_dev, lmac_id);
+
+ index = id * lmac->mac_to_index_bmap.max + index;
+
+ /* Read MAC address to check whether it is ucast or mcast */
+ cfg = cgx_read(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)));
+
+ cfg2mac(cfg, mac);
+ if (is_multicast_ether_addr(mac))
+ lmac->mcast_filters_count--;
+
+ if (!lmac->mcast_filters_count) {
+ cfg = cgx_read(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0);
+ cfg &= ~GENMASK_ULL(2, 1);
+ cfg |= CGX_DMAC_MCAST_MODE;
+ cgx_write(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0, cfg);
+ }
+
+ cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)), 0);
+
+ return 0;
+}
+
+int cgx_lmac_addr_max_entries_get(u8 cgx_id, u8 lmac_id)
+{
+ struct cgx *cgx_dev = cgx_get_pdata(cgx_id);
+ struct lmac *lmac = lmac_pdata(lmac_id, cgx_dev);
+
+ if (lmac)
+ return lmac->mac_to_index_bmap.max;
+
+ return 0;
+}
+
u64 cgx_lmac_addr_get(u8 cgx_id, u8 lmac_id)
{
struct cgx *cgx_dev = cgx_get_pdata(cgx_id);
+ struct lmac *lmac = lmac_pdata(lmac_id, cgx_dev);
struct mac_ops *mac_ops;
+ int index;
u64 cfg;
+ int id;
mac_ops = cgx_dev->mac_ops;
- cfg = cgx_read(cgx_dev, 0, CGXX_CMRX_RX_DMAC_CAM0 + lmac_id * 0x8);
+ id = get_sequence_id_of_lmac(cgx_dev, lmac_id);
+
+ index = id * lmac->mac_to_index_bmap.max;
+
+ cfg = cgx_read(cgx_dev, 0, CGXX_CMRX_RX_DMAC_CAM0 + index * 0x8);
return cfg & CGX_RX_DMAC_ADR_MASK;
}
void cgx_lmac_promisc_config(int cgx_id, int lmac_id, bool enable)
{
struct cgx *cgx = cgx_get_pdata(cgx_id);
+ struct lmac *lmac = lmac_pdata(lmac_id, cgx);
+ u16 max_dmac = lmac->mac_to_index_bmap.max;
struct mac_ops *mac_ops;
+ int index, i;
u64 cfg = 0;
+ int id;
if (!cgx)
return;
+ id = get_sequence_id_of_lmac(cgx, lmac_id);
+
mac_ops = cgx->mac_ops;
if (enable) {
/* Enable promiscuous mode on LMAC */
cfg = cgx_read(cgx, lmac_id, CGXX_CMRX_RX_DMAC_CTL0);
- cfg &= ~(CGX_DMAC_CAM_ACCEPT | CGX_DMAC_MCAST_MODE);
- cfg |= CGX_DMAC_BCAST_MODE;
+ cfg &= ~CGX_DMAC_CAM_ACCEPT;
+ cfg |= (CGX_DMAC_BCAST_MODE | CGX_DMAC_MCAST_MODE);
cgx_write(cgx, lmac_id, CGXX_CMRX_RX_DMAC_CTL0, cfg);
- cfg = cgx_read(cgx, 0,
- (CGXX_CMRX_RX_DMAC_CAM0 + lmac_id * 0x8));
- cfg &= ~CGX_DMAC_CAM_ADDR_ENABLE;
- cgx_write(cgx, 0,
- (CGXX_CMRX_RX_DMAC_CAM0 + lmac_id * 0x8), cfg);
+ for (i = 0; i < max_dmac; i++) {
+ index = id * max_dmac + i;
+ cfg = cgx_read(cgx, 0,
+ (CGXX_CMRX_RX_DMAC_CAM0 + index * 0x8));
+ cfg &= ~CGX_DMAC_CAM_ADDR_ENABLE;
+ cgx_write(cgx, 0,
+ (CGXX_CMRX_RX_DMAC_CAM0 + index * 0x8), cfg);
+ }
} else {
/* Disable promiscuous mode */
cfg = cgx_read(cgx, lmac_id, CGXX_CMRX_RX_DMAC_CTL0);
cfg |= CGX_DMAC_CAM_ACCEPT | CGX_DMAC_MCAST_MODE;
cgx_write(cgx, lmac_id, CGXX_CMRX_RX_DMAC_CTL0, cfg);
- cfg = cgx_read(cgx, 0,
- (CGXX_CMRX_RX_DMAC_CAM0 + lmac_id * 0x8));
- cfg |= CGX_DMAC_CAM_ADDR_ENABLE;
- cgx_write(cgx, 0,
- (CGXX_CMRX_RX_DMAC_CAM0 + lmac_id * 0x8), cfg);
+ for (i = 0; i < max_dmac; i++) {
+ index = id * max_dmac + i;
+ cfg = cgx_read(cgx, 0,
+ (CGXX_CMRX_RX_DMAC_CAM0 + index * 0x8));
+ if ((cfg & CGX_RX_DMAC_ADR_MASK) != 0) {
+ cfg |= CGX_DMAC_CAM_ADDR_ENABLE;
+ cgx_write(cgx, 0,
+ (CGXX_CMRX_RX_DMAC_CAM0 +
+ index * 0x8),
+ cfg);
+ }
+ }
}
}
}
lmac->cgx = cgx;
+ lmac->mac_to_index_bmap.max =
+ MAX_DMAC_ENTRIES_PER_CGX / cgx->lmac_count;
+ err = rvu_alloc_bitmap(&lmac->mac_to_index_bmap);
+ if (err)
+ return err;
+
+ /* Reserve first entry for default MAC address */
+ set_bit(0, lmac->mac_to_index_bmap.bmap);
+
init_waitqueue_head(&lmac->wq_cmd_cmplt);
mutex_init(&lmac->cmd_lock);
spin_lock_init(&lmac->event_cb_lock);
/* Add reference */
cgx->lmac_idmap[lmac->lmac_id] = lmac;
- cgx->mac_ops->mac_pause_frm_config(cgx, lmac->lmac_id, true);
set_bit(lmac->lmac_id, &cgx->lmac_bmap);
+ cgx->mac_ops->mac_pause_frm_config(cgx, lmac->lmac_id, true);
}
return cgx_lmac_verify_fwi_version(cgx);
continue;
cgx->mac_ops->mac_pause_frm_config(cgx, lmac->lmac_id, false);
cgx_configure_interrupt(cgx, lmac, lmac->lmac_id, true);
+ kfree(lmac->mac_to_index_bmap.bmap);
kfree(lmac->name);
kfree(lmac);
}
#define CGX_ID_MASK 0x7
#define MAX_LMAC_PER_CGX 4
+#define MAX_DMAC_ENTRIES_PER_CGX 32
#define CGX_FIFO_LEN 65536 /* 64K for both Rx & Tx */
#define CGX_OFFSET(x) ((x) * MAX_LMAC_PER_CGX)
#define CGXX_CMRX_RX_DMAC_CTL0 (0x1F8 + mac_ops->csr_offset)
#define CGX_DMAC_CTL0_CAM_ENABLE BIT_ULL(3)
#define CGX_DMAC_CAM_ACCEPT BIT_ULL(3)
+#define CGX_DMAC_MCAST_MODE_CAM BIT_ULL(2)
#define CGX_DMAC_MCAST_MODE BIT_ULL(1)
#define CGX_DMAC_BCAST_MODE BIT_ULL(0)
#define CGXX_CMRX_RX_DMAC_CAM0 (0x200 + mac_ops->csr_offset)
#define CGX_DMAC_CAM_ADDR_ENABLE BIT_ULL(48)
+#define CGX_DMAC_CAM_ENTRY_LMACID GENMASK_ULL(50, 49)
#define CGXX_CMRX_RX_DMAC_CAM1 0x400
#define CGX_RX_DMAC_ADR_MASK GENMASK_ULL(47, 0)
#define CGXX_CMRX_TX_STAT0 0x700
int cgx_lmac_rx_tx_enable(void *cgxd, int lmac_id, bool enable);
int cgx_lmac_tx_enable(void *cgxd, int lmac_id, bool enable);
int cgx_lmac_addr_set(u8 cgx_id, u8 lmac_id, u8 *mac_addr);
+int cgx_lmac_addr_reset(u8 cgx_id, u8 lmac_id);
u64 cgx_lmac_addr_get(u8 cgx_id, u8 lmac_id);
+int cgx_lmac_addr_add(u8 cgx_id, u8 lmac_id, u8 *mac_addr);
+int cgx_lmac_addr_del(u8 cgx_id, u8 lmac_id, u8 index);
+int cgx_lmac_addr_max_entries_get(u8 cgx_id, u8 lmac_id);
void cgx_lmac_promisc_config(int cgx_id, int lmac_id, bool enable);
void cgx_lmac_enadis_rx_pause_fwding(void *cgxd, int lmac_id, bool enable);
int cgx_lmac_internal_loopback(void *cgxd, int lmac_id, bool enable);
unsigned long cgx_get_lmac_bmap(void *cgxd);
void cgx_lmac_write(int cgx_id, int lmac_id, u64 offset, u64 val);
u64 cgx_lmac_read(int cgx_id, int lmac_id, u64 offset);
+int cgx_lmac_addr_update(u8 cgx_id, u8 lmac_id, u8 *mac_addr, u8 index);
+u64 cgx_read_dmac_ctrl(void *cgxd, int lmac_id);
+u64 cgx_read_dmac_entry(void *cgxd, int index);
#endif /* CGX_H */
#include "rvu.h"
#include "cgx.h"
/**
- * struct lmac
+ * struct lmac - per lmac locks and properties
* @wq_cmd_cmplt: waitq to keep the process blocked until cmd completion
* @cmd_lock: Lock to serialize the command interface
* @resp: command response
* @link_info: link related information
+ * @mac_to_index_bmap: Mac address to CGX table index mapping
* @event_cb: callback for linkchange events
* @event_cb_lock: lock for serializing callback with unregister
- * @cmd_pend: flag set before new command is started
- * flag cleared after command response is received
* @cgx: parent cgx port
+ * @mcast_filters_count: Number of multicast filters installed
* @lmac_id: lmac port id
+ * @cmd_pend: flag set before new command is started
+ * flag cleared after command response is received
* @name: lmac port name
*/
struct lmac {
struct mutex cmd_lock;
u64 resp;
struct cgx_link_user_info link_info;
+ struct rsrc_bmap mac_to_index_bmap;
struct cgx_event_cb event_cb;
/* lock for serializing callback with unregister */
spinlock_t event_cb_lock;
- bool cmd_pend;
struct cgx *cgx;
+ u8 mcast_filters_count;
u8 lmac_id;
+ bool cmd_pend;
char *name;
};
M(VF_FLR, 0x006, vf_flr, msg_req, msg_rsp) \
M(PTP_OP, 0x007, ptp_op, ptp_req, ptp_rsp) \
M(GET_HW_CAP, 0x008, get_hw_cap, msg_req, get_hw_cap_rsp) \
+M(LMTST_TBL_SETUP, 0x00a, lmtst_tbl_setup, lmtst_tbl_setup_req, \
+ msg_rsp) \
M(SET_VF_PERM, 0x00b, set_vf_perm, set_vf_perm, msg_rsp) \
/* CGX mbox IDs (range 0x200 - 0x3FF) */ \
M(CGX_START_RXTX, 0x200, cgx_start_rxtx, msg_req, msg_rsp) \
M(CGX_FEATURES_GET, 0x215, cgx_features_get, msg_req, \
cgx_features_info_msg) \
M(RPM_STATS, 0x216, rpm_stats, msg_req, rpm_stats_rsp) \
- /* NPA mbox IDs (range 0x400 - 0x5FF) */ \
+M(CGX_MAC_ADDR_ADD, 0x217, cgx_mac_addr_add, cgx_mac_addr_add_req, \
+ cgx_mac_addr_add_rsp) \
+M(CGX_MAC_ADDR_DEL, 0x218, cgx_mac_addr_del, cgx_mac_addr_del_req, \
+ msg_rsp) \
+M(CGX_MAC_MAX_ENTRIES_GET, 0x219, cgx_mac_max_entries_get, msg_req, \
+ cgx_max_dmac_entries_get_rsp) \
+M(CGX_MAC_ADDR_RESET, 0x21A, cgx_mac_addr_reset, msg_req, msg_rsp) \
+M(CGX_MAC_ADDR_UPDATE, 0x21B, cgx_mac_addr_update, cgx_mac_addr_update_req, \
+ msg_rsp) \
/* NPA mbox IDs (range 0x400 - 0x5FF) */ \
M(NPA_LF_ALLOC, 0x400, npa_lf_alloc, \
npa_lf_alloc_req, npa_lf_alloc_rsp) \
u8 mac_addr[ETH_ALEN];
};
+/* Structure for requesting the operation to
+ * add DMAC filter entry into CGX interface
+ */
+struct cgx_mac_addr_add_req {
+ struct mbox_msghdr hdr;
+ u8 mac_addr[ETH_ALEN];
+};
+
+/* Structure for response against the operation to
+ * add DMAC filter entry into CGX interface
+ */
+struct cgx_mac_addr_add_rsp {
+ struct mbox_msghdr hdr;
+ u8 index;
+};
+
+/* Structure for requesting the operation to
+ * delete DMAC filter entry from CGX interface
+ */
+struct cgx_mac_addr_del_req {
+ struct mbox_msghdr hdr;
+ u8 index;
+};
+
+/* Structure for response against the operation to
+ * get maximum supported DMAC filter entries
+ */
+struct cgx_max_dmac_entries_get_rsp {
+ struct mbox_msghdr hdr;
+ u8 max_dmac_filters;
+};
+
struct cgx_link_user_info {
uint64_t link_up:1;
uint64_t full_duplex:1;
int status;
};
+struct cgx_mac_addr_update_req {
+ struct mbox_msghdr hdr;
+ u8 mac_addr[ETH_ALEN];
+ u8 index;
+};
+
#define RVU_LMAC_FEAT_FC BIT_ULL(0) /* pause frames */
#define RVU_LMAC_FEAT_PTP BIT_ULL(1) /* precision time protocol */
#define RVU_MAC_VERSION BIT_ULL(2)
u64 flags;
};
+struct lmtst_tbl_setup_req {
+ struct mbox_msghdr hdr;
+ u16 base_pcifunc;
+ u8 use_local_lmt_region;
+ u64 lmt_iova;
+ u64 rsvd[4];
+};
+
/* CPT mailbox error codes
* Range 901 - 1000.
*/
* Software assigns pkind for each incoming port such as CGX
* Ethernet interfaces, LBK interfaces, etc.
*/
+#define NPC_UNRESERVED_PKIND_COUNT NPC_RX_VLAN_EXDSA_PKIND
+
enum npc_pkind_type {
+ NPC_RX_LBK_PKIND = 0ULL,
NPC_RX_VLAN_EXDSA_PKIND = 56ULL,
NPC_RX_CHLEN24B_PKIND = 57ULL,
NPC_RX_CPT_HDR_PKIND,
/* Get numVFs attached to this PF and first HWVF */
cfg = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_CFG(pf));
- *numvfs = (cfg >> 12) & 0xFF;
- *hwvf = cfg & 0xFFF;
+ if (numvfs)
+ *numvfs = (cfg >> 12) & 0xFF;
+ if (hwvf)
+ *hwvf = cfg & 0xFFF;
}
static int rvu_get_hwvf(struct rvu *rvu, int pcifunc)
return rvu_detach_rsrcs(rvu, detach, detach->hdr.pcifunc);
}
-static int rvu_get_nix_blkaddr(struct rvu *rvu, u16 pcifunc)
+int rvu_get_nix_blkaddr(struct rvu *rvu, u16 pcifunc)
{
struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
int blkaddr = BLKADDR_NIX0, vf;
rvu_blklf_teardown(rvu, pcifunc, BLKADDR_SSOW);
rvu_blklf_teardown(rvu, pcifunc, BLKADDR_SSO);
rvu_blklf_teardown(rvu, pcifunc, BLKADDR_NPA);
+ rvu_reset_lmt_map_tbl(rvu, pcifunc);
rvu_detach_rsrcs(rvu, NULL, pcifunc);
mutex_unlock(&rvu->flr_lock);
}
if (!vfs)
return 0;
+ /* LBK channel number 63 is used for switching packets between
+ * CGX mapped VFs. Hence limit LBK pairs till 62 only.
+ */
+ if (vfs > 62)
+ vfs = 62;
+
/* Save VFs number for reference in VF interrupts handlers.
* Since interrupts might start arriving during SRIOV enablement
* ordinary API cannot be used to get number of enabled VFs.
/* Initialize debugfs */
rvu_dbg_init(rvu);
+ mutex_init(&rvu->rswitch.switch_lock);
+
return 0;
err_dl:
rvu_unregister_dl(rvu);
u8 nix_blkaddr; /* BLKADDR_NIX0/1 assigned to this PF */
u8 nix_rx_intf; /* NIX0_RX/NIX1_RX interface to NPC */
u8 nix_tx_intf; /* NIX0_TX/NIX1_TX interface to NPC */
+ u64 lmt_base_addr; /* Preseving the pcifunc's lmtst base addr*/
unsigned long flags;
};
size_t kpus;
};
+#define RVU_SWITCH_LBK_CHAN 63
+
+struct rvu_switch {
+ struct mutex switch_lock; /* Serialize flow installation */
+ u32 used_entries;
+ u16 *entry2pcifunc;
+ u16 mode;
+ u16 start_entry;
+};
+
struct rvu {
void __iomem *afreg_base;
void __iomem *pfreg_base;
/* CGX */
#define PF_CGXMAP_BASE 1 /* PF 0 is reserved for RVU PF */
+ u16 cgx_mapped_vfs; /* maximum CGX mapped VFs */
u8 cgx_mapped_pfs;
u8 cgx_cnt_max; /* CGX port count max */
u8 *pf2cgxlmac_map; /* pf to cgx_lmac map */
struct rvu_debugfs rvu_dbg;
#endif
struct rvu_devlink *rvu_dl;
+
+ /* RVU switch implementation over NPC with DMAC rules */
+ struct rvu_switch rswitch;
};
static inline void rvu_write64(struct rvu *rvu, u64 block, u64 offset, u64 val)
int rvu_cgx_start_stop_io(struct rvu *rvu, u16 pcifunc, bool start);
int rvu_cgx_nix_cuml_stats(struct rvu *rvu, void *cgxd, int lmac_id, int index,
int rxtxflag, u64 *stat);
+void rvu_cgx_disable_dmac_entries(struct rvu *rvu, u16 pcifunc);
+
/* NPA APIs */
int rvu_npa_init(struct rvu *rvu);
void rvu_npa_freemem(struct rvu *rvu);
struct nix_cn10k_aq_enq_req *aq_req,
struct nix_cn10k_aq_enq_rsp *aq_rsp,
u16 pcifunc, u8 ctype, u32 qidx);
+int rvu_get_nix_blkaddr(struct rvu *rvu, u16 pcifunc);
/* NPC APIs */
int rvu_npc_init(struct rvu *rvu);
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);
+int cgxlmac_to_pf(struct rvu *rvu, int cgx_id, int lmac_id);
int npc_get_nixlf_mcam_index(struct npc_mcam *mcam, u16 pcifunc, int nixlf,
int type);
int rvu_set_channels_base(struct rvu *rvu);
void rvu_program_channels(struct rvu *rvu);
+/* CN10K RVU - LMT*/
+void rvu_reset_lmt_map_tbl(struct rvu *rvu, u16 pcifunc);
+
#ifdef CONFIG_DEBUG_FS
void rvu_dbg_init(struct rvu *rvu);
void rvu_dbg_exit(struct rvu *rvu);
static inline void rvu_dbg_init(struct rvu *rvu) {}
static inline void rvu_dbg_exit(struct rvu *rvu) {}
#endif
+
+/* RVU Switch */
+void rvu_switch_enable(struct rvu *rvu);
+void rvu_switch_disable(struct rvu *rvu);
+void rvu_switch_update_rules(struct rvu *rvu, u16 pcifunc);
+
#endif /* RVU_H */
return rvu->cgxlmac2pf_map[CGX_OFFSET(cgx_id) + lmac_id];
}
-static int cgxlmac_to_pf(struct rvu *rvu, int cgx_id, int lmac_id)
+int cgxlmac_to_pf(struct rvu *rvu, int cgx_id, int lmac_id)
{
unsigned long pfmap;
unsigned long lmac_bmap;
int size, free_pkind;
int cgx, lmac, iter;
+ int numvfs, hwvfs;
if (!cgx_cnt_max)
return 0;
pkind->pfchan_map[free_pkind] = ((pf) & 0x3F) << 16;
rvu_map_cgx_nix_block(rvu, pf, cgx, lmac);
rvu->cgx_mapped_pfs++;
+ rvu_get_pf_numvfs(rvu, pf, &numvfs, &hwvfs);
+ rvu->cgx_mapped_vfs += numvfs;
pf++;
}
}
return 0;
}
+void rvu_cgx_disable_dmac_entries(struct rvu *rvu, u16 pcifunc)
+{
+ int pf = rvu_get_pf(pcifunc);
+ int i = 0, lmac_count = 0;
+ u8 max_dmac_filters;
+ u8 cgx_id, lmac_id;
+ void *cgx_dev;
+
+ if (!is_cgx_config_permitted(rvu, pcifunc))
+ return;
+
+ rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
+ cgx_dev = cgx_get_pdata(cgx_id);
+ lmac_count = cgx_get_lmac_cnt(cgx_dev);
+ max_dmac_filters = MAX_DMAC_ENTRIES_PER_CGX / lmac_count;
+
+ for (i = 0; i < max_dmac_filters; i++)
+ cgx_lmac_addr_del(cgx_id, lmac_id, i);
+
+ /* As cgx_lmac_addr_del does not clear entry for index 0
+ * so it needs to be done explicitly
+ */
+ cgx_lmac_addr_reset(cgx_id, lmac_id);
+}
+
int rvu_mbox_handler_cgx_start_rxtx(struct rvu *rvu, struct msg_req *req,
struct msg_rsp *rsp)
{
return 0;
}
+int rvu_mbox_handler_cgx_mac_addr_add(struct rvu *rvu,
+ struct cgx_mac_addr_add_req *req,
+ struct cgx_mac_addr_add_rsp *rsp)
+{
+ int pf = rvu_get_pf(req->hdr.pcifunc);
+ u8 cgx_id, lmac_id;
+ int rc = 0;
+
+ if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
+ return -EPERM;
+
+ rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
+ rc = cgx_lmac_addr_add(cgx_id, lmac_id, req->mac_addr);
+ if (rc >= 0) {
+ rsp->index = rc;
+ return 0;
+ }
+
+ return rc;
+}
+
+int rvu_mbox_handler_cgx_mac_addr_del(struct rvu *rvu,
+ struct cgx_mac_addr_del_req *req,
+ struct msg_rsp *rsp)
+{
+ int pf = rvu_get_pf(req->hdr.pcifunc);
+ u8 cgx_id, lmac_id;
+
+ if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
+ return -EPERM;
+
+ rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
+ return cgx_lmac_addr_del(cgx_id, lmac_id, req->index);
+}
+
+int rvu_mbox_handler_cgx_mac_max_entries_get(struct rvu *rvu,
+ struct msg_req *req,
+ struct cgx_max_dmac_entries_get_rsp
+ *rsp)
+{
+ int pf = rvu_get_pf(req->hdr.pcifunc);
+ u8 cgx_id, lmac_id;
+
+ /* If msg is received from PFs(which are not mapped to CGX LMACs)
+ * or VF then no entries are allocated for DMAC filters at CGX level.
+ * So returning zero.
+ */
+ if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) {
+ rsp->max_dmac_filters = 0;
+ return 0;
+ }
+
+ rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
+ rsp->max_dmac_filters = cgx_lmac_addr_max_entries_get(cgx_id, lmac_id);
+ return 0;
+}
+
int rvu_mbox_handler_cgx_mac_addr_get(struct rvu *rvu,
struct cgx_mac_addr_set_or_get *req,
struct cgx_mac_addr_set_or_get *rsp)
rsp->status = cgx_set_link_mode(cgxd, req->args, cgx_idx, lmac);
return 0;
}
+
+int rvu_mbox_handler_cgx_mac_addr_reset(struct rvu *rvu, struct msg_req *req,
+ struct msg_rsp *rsp)
+{
+ int pf = rvu_get_pf(req->hdr.pcifunc);
+ u8 cgx_id, lmac_id;
+
+ if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
+ return -EPERM;
+
+ rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
+ return cgx_lmac_addr_reset(cgx_id, lmac_id);
+}
+
+int rvu_mbox_handler_cgx_mac_addr_update(struct rvu *rvu,
+ struct cgx_mac_addr_update_req *req,
+ struct msg_rsp *rsp)
+{
+ int pf = rvu_get_pf(req->hdr.pcifunc);
+ u8 cgx_id, lmac_id;
+
+ if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
+ return -EPERM;
+
+ rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
+ return cgx_lmac_addr_update(cgx_id, lmac_id, req->mac_addr, req->index);
+}
#include "cgx.h"
#include "rvu_reg.h"
+/* RVU LMTST */
+#define LMT_TBL_OP_READ 0
+#define LMT_TBL_OP_WRITE 1
+#define LMT_MAP_TABLE_SIZE (128 * 1024)
+#define LMT_MAPTBL_ENTRY_SIZE 16
+
+/* Function to perform operations (read/write) on lmtst map table */
+static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val,
+ int lmt_tbl_op)
+{
+ void __iomem *lmt_map_base;
+ u64 tbl_base;
+
+ tbl_base = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_MAP_BASE);
+
+ lmt_map_base = ioremap_wc(tbl_base, LMT_MAP_TABLE_SIZE);
+ if (!lmt_map_base) {
+ dev_err(rvu->dev, "Failed to setup lmt map table mapping!!\n");
+ return -ENOMEM;
+ }
+
+ if (lmt_tbl_op == LMT_TBL_OP_READ) {
+ *val = readq(lmt_map_base + index);
+ } else {
+ writeq((*val), (lmt_map_base + index));
+ /* Flushing the AP interceptor cache to make APR_LMT_MAP_ENTRY_S
+ * changes effective. Write 1 for flush and read is being used as a
+ * barrier and sets up a data dependency. Write to 0 after a write
+ * to 1 to complete the flush.
+ */
+ rvu_write64(rvu, BLKADDR_APR, APR_AF_LMT_CTL, BIT_ULL(0));
+ rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_CTL);
+ rvu_write64(rvu, BLKADDR_APR, APR_AF_LMT_CTL, 0x00);
+ }
+
+ iounmap(lmt_map_base);
+ return 0;
+}
+
+static u32 rvu_get_lmtst_tbl_index(struct rvu *rvu, u16 pcifunc)
+{
+ return ((rvu_get_pf(pcifunc) * rvu->hw->total_vfs) +
+ (pcifunc & RVU_PFVF_FUNC_MASK)) * LMT_MAPTBL_ENTRY_SIZE;
+}
+
+static int rvu_get_lmtaddr(struct rvu *rvu, u16 pcifunc,
+ u64 iova, u64 *lmt_addr)
+{
+ u64 pa, val, pf;
+ int err;
+
+ if (!iova) {
+ dev_err(rvu->dev, "%s Requested Null address for transulation\n", __func__);
+ return -EINVAL;
+ }
+
+ rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_ADDR_REQ, iova);
+ pf = rvu_get_pf(pcifunc) & 0x1F;
+ val = BIT_ULL(63) | BIT_ULL(14) | BIT_ULL(13) | pf << 8 |
+ ((pcifunc & RVU_PFVF_FUNC_MASK) & 0xFF);
+ rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_TXN_REQ, val);
+
+ err = rvu_poll_reg(rvu, BLKADDR_RVUM, RVU_AF_SMMU_ADDR_RSP_STS, BIT_ULL(0), false);
+ if (err) {
+ dev_err(rvu->dev, "%s LMTLINE iova transulation failed\n", __func__);
+ return err;
+ }
+ val = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_ADDR_RSP_STS);
+ if (val & ~0x1ULL) {
+ dev_err(rvu->dev, "%s LMTLINE iova transulation failed err:%llx\n", __func__, val);
+ return -EIO;
+ }
+ /* PA[51:12] = RVU_AF_SMMU_TLN_FLIT1[60:21]
+ * PA[11:0] = IOVA[11:0]
+ */
+ pa = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_TLN_FLIT1) >> 21;
+ pa &= GENMASK_ULL(39, 0);
+ *lmt_addr = (pa << 12) | (iova & 0xFFF);
+
+ return 0;
+}
+
+static int rvu_update_lmtaddr(struct rvu *rvu, u16 pcifunc, u64 lmt_addr)
+{
+ struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
+ u32 tbl_idx;
+ int err = 0;
+ u64 val;
+
+ /* Read the current lmt addr of pcifunc */
+ tbl_idx = rvu_get_lmtst_tbl_index(rvu, pcifunc);
+ err = lmtst_map_table_ops(rvu, tbl_idx, &val, LMT_TBL_OP_READ);
+ if (err) {
+ dev_err(rvu->dev,
+ "Failed to read LMT map table: index 0x%x err %d\n",
+ tbl_idx, err);
+ return err;
+ }
+
+ /* Storing the seondary's lmt base address as this needs to be
+ * reverted in FLR. Also making sure this default value doesn't
+ * get overwritten on multiple calls to this mailbox.
+ */
+ if (!pfvf->lmt_base_addr)
+ pfvf->lmt_base_addr = val;
+
+ /* Update the LMT table with new addr */
+ err = lmtst_map_table_ops(rvu, tbl_idx, &lmt_addr, LMT_TBL_OP_WRITE);
+ if (err) {
+ dev_err(rvu->dev,
+ "Failed to update LMT map table: index 0x%x err %d\n",
+ tbl_idx, err);
+ return err;
+ }
+ return 0;
+}
+
+int rvu_mbox_handler_lmtst_tbl_setup(struct rvu *rvu,
+ struct lmtst_tbl_setup_req *req,
+ struct msg_rsp *rsp)
+{
+ u64 lmt_addr, val;
+ u32 pri_tbl_idx;
+ int err = 0;
+
+ /* Check if PF_FUNC wants to use it's own local memory as LMTLINE
+ * region, if so, convert that IOVA to physical address and
+ * populate LMT table with that address
+ */
+ if (req->use_local_lmt_region) {
+ err = rvu_get_lmtaddr(rvu, req->hdr.pcifunc,
+ req->lmt_iova, &lmt_addr);
+ if (err < 0)
+ return err;
+
+ /* Update the lmt addr for this PFFUNC in the LMT table */
+ err = rvu_update_lmtaddr(rvu, req->hdr.pcifunc, lmt_addr);
+ if (err)
+ return err;
+ }
+
+ /* Reconfiguring lmtst map table in lmt region shared mode i.e. make
+ * multiple PF_FUNCs to share an LMTLINE region, so primary/base
+ * pcifunc (which is passed as an argument to mailbox) is the one
+ * whose lmt base address will be shared among other secondary
+ * pcifunc (will be the one who is calling this mailbox).
+ */
+ if (req->base_pcifunc) {
+ /* Calculating the LMT table index equivalent to primary
+ * pcifunc.
+ */
+ pri_tbl_idx = rvu_get_lmtst_tbl_index(rvu, req->base_pcifunc);
+
+ /* Read the base lmt addr of the primary pcifunc */
+ err = lmtst_map_table_ops(rvu, pri_tbl_idx, &val,
+ LMT_TBL_OP_READ);
+ if (err) {
+ dev_err(rvu->dev,
+ "Failed to read LMT map table: index 0x%x err %d\n",
+ pri_tbl_idx, err);
+ return err;
+ }
+
+ /* Update the base lmt addr of secondary with primary's base
+ * lmt addr.
+ */
+ err = rvu_update_lmtaddr(rvu, req->hdr.pcifunc, val);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+/* Resetting the lmtst map table to original base addresses */
+void rvu_reset_lmt_map_tbl(struct rvu *rvu, u16 pcifunc)
+{
+ struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
+ u32 tbl_idx;
+ int err;
+
+ if (is_rvu_otx2(rvu))
+ return;
+
+ if (pfvf->lmt_base_addr) {
+ /* This corresponds to lmt map table index */
+ tbl_idx = rvu_get_lmtst_tbl_index(rvu, pcifunc);
+ /* Reverting back original lmt base addr for respective
+ * pcifunc.
+ */
+ err = lmtst_map_table_ops(rvu, tbl_idx, &pfvf->lmt_base_addr,
+ LMT_TBL_OP_WRITE);
+ if (err)
+ dev_err(rvu->dev,
+ "Failed to update LMT map table: index 0x%x err %d\n",
+ tbl_idx, err);
+ pfvf->lmt_base_addr = 0;
+ }
+}
+
int rvu_set_channels_base(struct rvu *rvu)
{
struct rvu_hwinfo *hw = rvu->hw;
return err;
}
-static int rvu_dbg_cgx_stat_display(struct seq_file *filp, void *unused)
+static int rvu_dbg_derive_lmacid(struct seq_file *filp, int *lmac_id)
{
struct dentry *current_dir;
- int err, lmac_id;
char *buf;
current_dir = filp->file->f_path.dentry->d_parent;
if (!buf)
return -EINVAL;
- err = kstrtoint(buf + 1, 10, &lmac_id);
- if (!err) {
- err = cgx_print_stats(filp, lmac_id);
- if (err)
- return err;
- }
+ return kstrtoint(buf + 1, 10, lmac_id);
+}
+
+static int rvu_dbg_cgx_stat_display(struct seq_file *filp, void *unused)
+{
+ int lmac_id, err;
+
+ err = rvu_dbg_derive_lmacid(filp, &lmac_id);
+ if (!err)
+ return cgx_print_stats(filp, lmac_id);
+
return err;
}
RVU_DEBUG_SEQ_FOPS(cgx_stat, cgx_stat_display, NULL);
+static int cgx_print_dmac_flt(struct seq_file *s, int lmac_id)
+{
+ struct pci_dev *pdev = NULL;
+ void *cgxd = s->private;
+ char *bcast, *mcast;
+ u16 index, domain;
+ u8 dmac[ETH_ALEN];
+ struct rvu *rvu;
+ u64 cfg, mac;
+ int pf;
+
+ rvu = pci_get_drvdata(pci_get_device(PCI_VENDOR_ID_CAVIUM,
+ PCI_DEVID_OCTEONTX2_RVU_AF, NULL));
+ if (!rvu)
+ return -ENODEV;
+
+ pf = cgxlmac_to_pf(rvu, cgx_get_cgxid(cgxd), lmac_id);
+ domain = 2;
+
+ pdev = pci_get_domain_bus_and_slot(domain, pf + 1, 0);
+ if (!pdev)
+ return 0;
+
+ cfg = cgx_read_dmac_ctrl(cgxd, lmac_id);
+ bcast = cfg & CGX_DMAC_BCAST_MODE ? "ACCEPT" : "REJECT";
+ mcast = cfg & CGX_DMAC_MCAST_MODE ? "ACCEPT" : "REJECT";
+
+ seq_puts(s,
+ "PCI dev RVUPF BROADCAST MULTICAST FILTER-MODE\n");
+ seq_printf(s, "%s PF%d %9s %9s",
+ dev_name(&pdev->dev), pf, bcast, mcast);
+ if (cfg & CGX_DMAC_CAM_ACCEPT)
+ seq_printf(s, "%12s\n\n", "UNICAST");
+ else
+ seq_printf(s, "%16s\n\n", "PROMISCUOUS");
+
+ seq_puts(s, "\nDMAC-INDEX ADDRESS\n");
+
+ for (index = 0 ; index < 32 ; index++) {
+ cfg = cgx_read_dmac_entry(cgxd, index);
+ /* Display enabled dmac entries associated with current lmac */
+ if (lmac_id == FIELD_GET(CGX_DMAC_CAM_ENTRY_LMACID, cfg) &&
+ FIELD_GET(CGX_DMAC_CAM_ADDR_ENABLE, cfg)) {
+ mac = FIELD_GET(CGX_RX_DMAC_ADR_MASK, cfg);
+ u64_to_ether_addr(mac, dmac);
+ seq_printf(s, "%7d %pM\n", index, dmac);
+ }
+ }
+
+ return 0;
+}
+
+static int rvu_dbg_cgx_dmac_flt_display(struct seq_file *filp, void *unused)
+{
+ int err, lmac_id;
+
+ err = rvu_dbg_derive_lmacid(filp, &lmac_id);
+ if (!err)
+ return cgx_print_dmac_flt(filp, lmac_id);
+
+ return err;
+}
+
+RVU_DEBUG_SEQ_FOPS(cgx_dmac_flt, cgx_dmac_flt_display, NULL);
+
static void rvu_dbg_cgx_init(struct rvu *rvu)
{
struct mac_ops *mac_ops;
debugfs_create_file("stats", 0600, rvu->rvu_dbg.lmac,
cgx, &rvu_dbg_cgx_stat_fops);
+ debugfs_create_file("mac_filter", 0600,
+ rvu->rvu_dbg.lmac, cgx,
+ &rvu_dbg_cgx_dmac_flt_fops);
}
}
}
int entry_acnt, entry_ecnt;
int cntr_acnt, cntr_ecnt;
- /* Skip PF0 */
- if (!pcifunc)
- return;
rvu_npc_get_mcam_entry_alloc_info(rvu, pcifunc, blkaddr,
&entry_acnt, &entry_ecnt);
rvu_npc_get_mcam_counter_alloc_info(rvu, pcifunc, blkaddr,
static void rvu_dbg_npc_mcam_show_action(struct seq_file *s,
struct rvu_npc_mcam_rule *rule)
{
- if (rule->intf == NIX_INTF_TX) {
+ if (is_npc_intf_tx(rule->intf)) {
switch (rule->tx_action.op) {
case NIX_TX_ACTIONOP_DROP:
seq_puts(s, "\taction: Drop\n");
rvu_nix_health_reporters_destroy(rvu_dl);
}
+static int rvu_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
+{
+ struct rvu_devlink *rvu_dl = devlink_priv(devlink);
+ struct rvu *rvu = rvu_dl->rvu;
+ struct rvu_switch *rswitch;
+
+ rswitch = &rvu->rswitch;
+ *mode = rswitch->mode;
+
+ return 0;
+}
+
+static int rvu_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
+ struct netlink_ext_ack *extack)
+{
+ struct rvu_devlink *rvu_dl = devlink_priv(devlink);
+ struct rvu *rvu = rvu_dl->rvu;
+ struct rvu_switch *rswitch;
+
+ rswitch = &rvu->rswitch;
+ switch (mode) {
+ case DEVLINK_ESWITCH_MODE_LEGACY:
+ case DEVLINK_ESWITCH_MODE_SWITCHDEV:
+ if (rswitch->mode == mode)
+ return 0;
+ rswitch->mode = mode;
+ if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV)
+ rvu_switch_enable(rvu);
+ else
+ rvu_switch_disable(rvu);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int rvu_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
struct netlink_ext_ack *extack)
{
static const struct devlink_ops rvu_devlink_ops = {
.info_get = rvu_devlink_info_get,
+ .eswitch_mode_get = rvu_devlink_eswitch_mode_get,
+ .eswitch_mode_set = rvu_devlink_eswitch_mode_set,
};
int rvu_register_dl(struct rvu *rvu)
struct devlink *dl;
int err;
- rvu_dl = kzalloc(sizeof(*rvu_dl), GFP_KERNEL);
- if (!rvu_dl)
- return -ENOMEM;
-
dl = devlink_alloc(&rvu_devlink_ops, sizeof(struct rvu_devlink));
if (!dl) {
dev_warn(rvu->dev, "devlink_alloc failed\n");
- kfree(rvu_dl);
return -ENOMEM;
}
if (err) {
dev_err(rvu->dev, "devlink register failed with error %d\n", err);
devlink_free(dl);
- kfree(rvu_dl);
return err;
}
+ rvu_dl = devlink_priv(dl);
rvu_dl->dl = dl;
rvu_dl->rvu = rvu;
rvu->rvu_dl = rvu_dl;
rvu_health_reporters_destroy(rvu);
devlink_unregister(dl);
devlink_free(dl);
- kfree(rvu_dl);
}
{
int err;
- /*Sync all in flight RX packets to LLC/DRAM */
+ /* Sync all in flight RX packets to LLC/DRAM */
rvu_write64(rvu, blkaddr, NIX_AF_RX_SW_SYNC, BIT_ULL(0));
err = rvu_poll_reg(rvu, blkaddr, NIX_AF_RX_SW_SYNC, BIT_ULL(0), true);
if (err)
- dev_err(rvu->dev, "NIX RX software sync failed\n");
+ dev_err(rvu->dev, "SYNC1: NIX RX software sync failed\n");
+
+ /* SW_SYNC ensures all existing transactions are finished and pkts
+ * are written to LLC/DRAM, queues should be teared down after
+ * successful SW_SYNC. Due to a HW errata, in some rare scenarios
+ * an existing transaction might end after SW_SYNC operation. To
+ * ensure operation is fully done, do the SW_SYNC twice.
+ */
+ rvu_write64(rvu, blkaddr, NIX_AF_RX_SW_SYNC, BIT_ULL(0));
+ err = rvu_poll_reg(rvu, blkaddr, NIX_AF_RX_SW_SYNC, BIT_ULL(0), true);
+ if (err)
+ dev_err(rvu->dev, "SYNC2: NIX RX software sync failed\n");
}
static bool is_valid_txschq(struct rvu *rvu, int blkaddr,
rvu_nix_chan_lbk(rvu, lbkid, vf + 1);
pfvf->rx_chan_cnt = 1;
pfvf->tx_chan_cnt = 1;
+ rvu_npc_set_pkind(rvu, NPC_RX_LBK_PKIND, pfvf);
rvu_npc_install_promisc_entry(rvu, pcifunc, nixlf,
pfvf->rx_chan_base,
pfvf->rx_chan_cnt);
/* Free and disable any MCAM entries used by this NIX LF */
rvu_npc_disable_mcam_entries(rvu, pcifunc, nixlf);
+
+ /* Disable DMAC filters used */
+ rvu_cgx_disable_dmac_entries(rvu, pcifunc);
}
int rvu_mbox_handler_nix_bp_disable(struct rvu *rvu,
pfvf_map[schq] = TXSCH_SET_FLAG(pfvf_map[schq], NIX_TXSCHQ_CFG_DONE);
}
+static void rvu_nix_tx_tl2_cfg(struct rvu *rvu, int blkaddr,
+ u16 pcifunc, struct nix_txsch *txsch)
+{
+ struct rvu_hwinfo *hw = rvu->hw;
+ int lbk_link_start, lbk_links;
+ u8 pf = rvu_get_pf(pcifunc);
+ int schq;
+
+ if (!is_pf_cgxmapped(rvu, pf))
+ return;
+
+ lbk_link_start = hw->cgx_links;
+
+ for (schq = 0; schq < txsch->schq.max; schq++) {
+ if (TXSCH_MAP_FUNC(txsch->pfvf_map[schq]) != pcifunc)
+ continue;
+ /* Enable all LBK links with channel 63 by default so that
+ * packets can be sent to LBK with a NPC TX MCAM rule
+ */
+ lbk_links = hw->lbk_links;
+ while (lbk_links--)
+ rvu_write64(rvu, blkaddr,
+ NIX_AF_TL3_TL2X_LINKX_CFG(schq,
+ lbk_link_start +
+ lbk_links),
+ BIT_ULL(12) | RVU_SWITCH_LBK_CHAN);
+ }
+}
+
int rvu_mbox_handler_nix_txschq_cfg(struct rvu *rvu,
struct nix_txschq_config *req,
struct msg_rsp *rsp)
rvu_write64(rvu, blkaddr, reg, regval);
}
+ rvu_nix_tx_tl2_cfg(rvu, blkaddr, pcifunc,
+ &nix_hw->txsch[NIX_TXSCH_LVL_TL2]);
+
return 0;
}
if (test_bit(PF_SET_VF_TRUSTED, &pfvf->flags) && from_vf)
ether_addr_copy(pfvf->default_mac, req->mac_addr);
+ rvu_switch_update_rules(rvu, pcifunc);
+
return 0;
}
vlan = &nix_hw->txvlan;
kfree(vlan->rsrc.bmap);
mutex_destroy(&vlan->rsrc_lock);
- devm_kfree(rvu->dev, vlan->entry2pfvf_map);
mcast = &nix_hw->mcast;
qmem_free(rvu->dev, mcast->mce_ctx);
pfvf = rvu_get_pfvf(rvu, pcifunc);
set_bit(NIXLF_INITIALIZED, &pfvf->flags);
+ rvu_switch_update_rules(rvu, pcifunc);
+
return rvu_cgx_start_stop_io(rvu, pcifunc, true);
}
owner = mcam->entry2pfvf_map[index];
target_func = (entry->action >> 4) & 0xffff;
/* do nothing when target is LBK/PF or owner is not PF */
- if (is_afvf(target_func) || (owner & RVU_PFVF_FUNC_MASK) ||
+ if (is_pffunc_af(owner) || is_afvf(target_func) ||
+ (owner & RVU_PFVF_FUNC_MASK) ||
!(target_func & RVU_PFVF_FUNC_MASK))
return;
{
int bank = npc_get_bank(mcam, index);
int kw = 0, actbank, actindex;
+ u8 tx_intf_mask = ~intf & 0x3;
+ u8 tx_intf = intf;
u64 cam0, cam1;
actbank = bank; /* Save bank id, to set action later on */
*/
for (; bank < (actbank + mcam->banks_per_entry); bank++, kw = kw + 2) {
/* Interface should be set in all banks */
+ if (is_npc_intf_tx(intf)) {
+ /* Last bit must be set and rest don't care
+ * for TX interfaces
+ */
+ tx_intf_mask = 0x1;
+ tx_intf = intf & tx_intf_mask;
+ tx_intf_mask = ~tx_intf & tx_intf_mask;
+ }
+
rvu_write64(rvu, blkaddr,
NPC_AF_MCAMEX_BANKX_CAMX_INTF(index, bank, 1),
- intf);
+ tx_intf);
rvu_write64(rvu, blkaddr,
NPC_AF_MCAMEX_BANKX_CAMX_INTF(index, bank, 0),
- ~intf & 0x3);
+ tx_intf_mask);
/* Set the match key */
npc_get_keyword(entry, kw, &cam0, &cam1);
eth_broadcast_addr((u8 *)&req.mask.dmac);
req.features = BIT_ULL(NPC_DMAC);
req.channel = chan;
+ req.chan_mask = 0xFFFU;
req.intf = pfvf->nix_rx_intf;
req.op = action.op;
req.hdr.pcifunc = 0; /* AF is requester */
eth_broadcast_addr((u8 *)&req.mask.dmac);
req.features = BIT_ULL(NPC_DMAC);
req.channel = chan;
+ req.chan_mask = 0xFFFU;
req.intf = pfvf->nix_rx_intf;
req.entry = index;
req.hdr.pcifunc = 0; /* AF is requester */
{
struct rvu_hwinfo *hw = rvu->hw;
int num_pkinds, num_kpus, idx;
- struct npc_pkind *pkind;
/* Disable all KPUs and their entries */
for (idx = 0; idx < hw->npc_kpus; idx++) {
* Check HW max count to avoid configuring junk or
* writing to unsupported CSR addresses.
*/
- pkind = &hw->pkind;
num_pkinds = rvu->kpu.pkinds;
- num_pkinds = min_t(int, pkind->rsrc.max, num_pkinds);
+ num_pkinds = min_t(int, hw->npc_pkinds, num_pkinds);
for (idx = 0; idx < num_pkinds; idx++)
npc_config_kpuaction(rvu, blkaddr, &rvu->kpu.ikpu[idx], 0, idx, true);
int nixlf_count = rvu_get_nixlf_count(rvu);
struct npc_mcam *mcam = &rvu->hw->mcam;
int rsvd, err;
+ u16 index;
+ int cntr;
u64 cfg;
/* Actual number of MCAM entries vary by entry size */
if (!mcam->entry2target_pffunc)
goto free_mem;
+ for (index = 0; index < mcam->bmap_entries; index++) {
+ mcam->entry2pfvf_map[index] = NPC_MCAM_INVALID_MAP;
+ mcam->entry2cntr_map[index] = NPC_MCAM_INVALID_MAP;
+ }
+
+ for (cntr = 0; cntr < mcam->counters.max; cntr++)
+ mcam->cntr2pfvf_map[cntr] = NPC_MCAM_INVALID_MAP;
+
mutex_init(&mcam->lock);
return 0;
if (npc_const1 & BIT_ULL(63))
npc_const2 = rvu_read64(rvu, blkaddr, NPC_AF_CONST2);
- pkind->rsrc.max = (npc_const1 >> 12) & 0xFFULL;
+ pkind->rsrc.max = NPC_UNRESERVED_PKIND_COUNT;
+ hw->npc_pkinds = (npc_const1 >> 12) & 0xFFULL;
hw->npc_kpu_entries = npc_const1 & 0xFFFULL;
hw->npc_kpus = (npc_const >> 8) & 0x1FULL;
hw->npc_intfs = npc_const & 0xFULL;
err = rvu_alloc_bitmap(&pkind->rsrc);
if (err)
return err;
+ /* Reserve PKIND#0 for LBKs. Power reset value of LBK_CH_PKIND is '0',
+ * no need to configure PKIND for all LBKs separately.
+ */
+ rvu_alloc_rsrc(&pkind->rsrc);
/* Allocate mem for pkind to PF and channel mapping info */
pkind->pfchan_map = devm_kcalloc(rvu->dev, pkind->rsrc.max,
}
/* Alloc request from PFFUNC with no NIXLF attached should be denied */
- if (!is_nixlf_attached(rvu, pcifunc))
+ if (!is_pffunc_af(pcifunc) && !is_nixlf_attached(rvu, pcifunc))
return NPC_MCAM_ALLOC_DENIED;
return npc_mcam_alloc_entries(mcam, pcifunc, req, rsp);
return NPC_MCAM_INVALID_REQ;
/* Free request from PFFUNC with no NIXLF attached, ignore */
- if (!is_nixlf_attached(rvu, pcifunc))
+ if (!is_pffunc_af(pcifunc) && !is_nixlf_attached(rvu, pcifunc))
return NPC_MCAM_INVALID_REQ;
mutex_lock(&mcam->lock);
if (rc)
goto exit;
- mcam->entry2pfvf_map[req->entry] = 0;
+ mcam->entry2pfvf_map[req->entry] = NPC_MCAM_INVALID_MAP;
mcam->entry2target_pffunc[req->entry] = 0x0;
npc_mcam_clear_bit(mcam, req->entry);
npc_enable_mcam_entry(rvu, mcam, blkaddr, req->entry, false);
else
nix_intf = pfvf->nix_rx_intf;
- if (npc_mcam_verify_channel(rvu, pcifunc, req->intf, channel)) {
+ if (!is_pffunc_af(pcifunc) &&
+ npc_mcam_verify_channel(rvu, pcifunc, req->intf, channel)) {
rc = NPC_MCAM_INVALID_REQ;
goto exit;
}
- if (npc_mcam_verify_pf_func(rvu, &req->entry_data, req->intf,
- pcifunc)) {
+ if (!is_pffunc_af(pcifunc) &&
+ npc_mcam_verify_pf_func(rvu, &req->entry_data, req->intf, pcifunc)) {
rc = NPC_MCAM_INVALID_REQ;
goto exit;
}
return NPC_MCAM_INVALID_REQ;
/* If the request is from a PFFUNC with no NIXLF attached, ignore */
- if (!is_nixlf_attached(rvu, pcifunc))
+ if (!is_pffunc_af(pcifunc) && !is_nixlf_attached(rvu, pcifunc))
return NPC_MCAM_INVALID_REQ;
/* Since list of allocated counter IDs needs to be sent to requester,
if (rc) {
/* Free allocated MCAM entry */
mutex_lock(&mcam->lock);
- mcam->entry2pfvf_map[entry] = 0;
+ mcam->entry2pfvf_map[entry] = NPC_MCAM_INVALID_MAP;
npc_mcam_clear_bit(mcam, entry);
mutex_unlock(&mcam->lock);
return rc;
static void npc_update_rx_entry(struct rvu *rvu, struct rvu_pfvf *pfvf,
struct mcam_entry *entry,
- struct npc_install_flow_req *req, u16 target)
+ struct npc_install_flow_req *req,
+ u16 target, bool pf_set_vfs_mac)
{
+ struct rvu_switch *rswitch = &rvu->rswitch;
struct nix_rx_action action;
- u64 chan_mask;
- chan_mask = req->chan_mask ? req->chan_mask : ~0ULL;
- npc_update_entry(rvu, NPC_CHAN, entry, req->channel, 0, chan_mask, 0,
- NIX_INTF_RX);
+ if (rswitch->mode == DEVLINK_ESWITCH_MODE_SWITCHDEV && pf_set_vfs_mac)
+ req->chan_mask = 0x0; /* Do not care channel */
+
+ npc_update_entry(rvu, NPC_CHAN, entry, req->channel, 0, req->chan_mask,
+ 0, NIX_INTF_RX);
*(u64 *)&action = 0x00;
action.pf_func = target;
struct npc_install_flow_req *req, u16 target)
{
struct nix_tx_action action;
+ u64 mask = ~0ULL;
+
+ /* If AF is installing then do not care about
+ * PF_FUNC in Send Descriptor
+ */
+ if (is_pffunc_af(req->hdr.pcifunc))
+ mask = 0;
npc_update_entry(rvu, NPC_PF_FUNC, entry, (__force u16)htons(target),
- 0, ~0ULL, 0, NIX_INTF_TX);
+ 0, mask, 0, NIX_INTF_TX);
*(u64 *)&action = 0x00;
action.op = req->op;
req->intf);
if (is_npc_intf_rx(req->intf))
- npc_update_rx_entry(rvu, pfvf, entry, req, target);
+ npc_update_rx_entry(rvu, pfvf, entry, req, target, pf_set_vfs_mac);
else
npc_update_tx_entry(rvu, pfvf, entry, req, target);
if (err)
return err;
- if (npc_mcam_verify_channel(rvu, target, req->intf, req->channel))
+ /* Skip channel validation if AF is installing */
+ if (!is_pffunc_af(req->hdr.pcifunc) &&
+ npc_mcam_verify_channel(rvu, target, req->intf, req->channel))
return -EINVAL;
pfvf = rvu_get_pfvf(rvu, target);
eth_broadcast_addr((u8 *)&req->mask.dmac);
}
+ /* Proceed if NIXLF is attached or not for TX rules */
err = nix_get_nixlf(rvu, target, &nixlf, NULL);
if (err && is_npc_intf_rx(req->intf) && !pf_set_vfs_mac)
return -EINVAL;
#define RVU_AF_PFX_VF_BAR4_ADDR (0x5400 | (a) << 4)
#define RVU_AF_PFX_VF_BAR4_CFG (0x5600 | (a) << 4)
#define RVU_AF_PFX_LMTLINE_ADDR (0x5800 | (a) << 4)
+#define RVU_AF_SMMU_ADDR_REQ (0x6000)
+#define RVU_AF_SMMU_TXN_REQ (0x6008)
+#define RVU_AF_SMMU_ADDR_RSP_STS (0x6010)
+#define RVU_AF_SMMU_ADDR_TLN (0x6018)
+#define RVU_AF_SMMU_TLN_FLIT1 (0x6030)
/* Admin function's privileged PF/VF registers */
#define RVU_PRIV_CONST (0x8000000)
#define LBK_LINK_CFG_ID_MASK GENMASK_ULL(11, 6)
#define LBK_LINK_CFG_BASE_MASK GENMASK_ULL(5, 0)
+/* APR */
+#define APR_AF_LMT_CFG (0x000ull)
+#define APR_AF_LMT_MAP_BASE (0x008ull)
+#define APR_AF_LMT_CTL (0x010ull)
+
#endif /* RVU_REG_H */
BLKADDR_NDC_NPA0 = 0xeULL,
BLKADDR_NDC_NIX1_RX = 0x10ULL,
BLKADDR_NDC_NIX1_TX = 0x11ULL,
- BLK_COUNT = 0x12ULL,
+ BLKADDR_APR = 0x16ULL,
+ BLK_COUNT = 0x17ULL,
};
/* RVU Block Type Enumeration */
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell OcteonTx2 RVU Admin Function driver
+ *
+ * Copyright (C) 2021 Marvell.
+ */
+
+#include <linux/bitfield.h>
+#include "rvu.h"
+
+static int rvu_switch_install_rx_rule(struct rvu *rvu, u16 pcifunc,
+ u16 chan_mask)
+{
+ struct npc_install_flow_req req = { 0 };
+ struct npc_install_flow_rsp rsp = { 0 };
+ struct rvu_pfvf *pfvf;
+
+ pfvf = rvu_get_pfvf(rvu, pcifunc);
+ /* If the pcifunc is not initialized then nothing to do.
+ * This same function will be called again via rvu_switch_update_rules
+ * after pcifunc is initialized.
+ */
+ if (!test_bit(NIXLF_INITIALIZED, &pfvf->flags))
+ return 0;
+
+ ether_addr_copy(req.packet.dmac, pfvf->mac_addr);
+ eth_broadcast_addr((u8 *)&req.mask.dmac);
+ req.hdr.pcifunc = 0; /* AF is requester */
+ req.vf = pcifunc;
+ req.features = BIT_ULL(NPC_DMAC);
+ req.channel = pfvf->rx_chan_base;
+ req.chan_mask = chan_mask;
+ req.intf = pfvf->nix_rx_intf;
+ req.op = NIX_RX_ACTION_DEFAULT;
+ req.default_rule = 1;
+
+ return rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp);
+}
+
+static int rvu_switch_install_tx_rule(struct rvu *rvu, u16 pcifunc, u16 entry)
+{
+ struct npc_install_flow_req req = { 0 };
+ struct npc_install_flow_rsp rsp = { 0 };
+ struct rvu_pfvf *pfvf;
+ u8 lbkid;
+
+ pfvf = rvu_get_pfvf(rvu, pcifunc);
+ /* If the pcifunc is not initialized then nothing to do.
+ * This same function will be called again via rvu_switch_update_rules
+ * after pcifunc is initialized.
+ */
+ if (!test_bit(NIXLF_INITIALIZED, &pfvf->flags))
+ return 0;
+
+ lbkid = pfvf->nix_blkaddr == BLKADDR_NIX0 ? 0 : 1;
+ ether_addr_copy(req.packet.dmac, pfvf->mac_addr);
+ eth_broadcast_addr((u8 *)&req.mask.dmac);
+ req.hdr.pcifunc = 0; /* AF is requester */
+ req.vf = pcifunc;
+ req.entry = entry;
+ req.features = BIT_ULL(NPC_DMAC);
+ req.intf = pfvf->nix_tx_intf;
+ req.op = NIX_TX_ACTIONOP_UCAST_CHAN;
+ req.index = (lbkid << 8) | RVU_SWITCH_LBK_CHAN;
+ req.set_cntr = 1;
+
+ return rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp);
+}
+
+static int rvu_switch_install_rules(struct rvu *rvu)
+{
+ struct rvu_switch *rswitch = &rvu->rswitch;
+ u16 start = rswitch->start_entry;
+ struct rvu_hwinfo *hw = rvu->hw;
+ u16 pcifunc, entry = 0;
+ int pf, vf, numvfs;
+ int err;
+
+ for (pf = 1; pf < hw->total_pfs; pf++) {
+ if (!is_pf_cgxmapped(rvu, pf))
+ continue;
+
+ pcifunc = pf << 10;
+ /* rvu_get_nix_blkaddr sets up the corresponding NIX block
+ * address and NIX RX and TX interfaces for a pcifunc.
+ * Generally it is called during attach call of a pcifunc but it
+ * is called here since we are pre-installing rules before
+ * nixlfs are attached
+ */
+ rvu_get_nix_blkaddr(rvu, pcifunc);
+
+ /* MCAM RX rule for a PF/VF already exists as default unicast
+ * rules installed by AF. Hence change the channel in those
+ * rules to ignore channel so that packets with the required
+ * DMAC received from LBK(by other PF/VFs in system) or from
+ * external world (from wire) are accepted.
+ */
+ err = rvu_switch_install_rx_rule(rvu, pcifunc, 0x0);
+ if (err) {
+ dev_err(rvu->dev, "RX rule for PF%d failed(%d)\n",
+ pf, err);
+ return err;
+ }
+
+ err = rvu_switch_install_tx_rule(rvu, pcifunc, start + entry);
+ if (err) {
+ dev_err(rvu->dev, "TX rule for PF%d failed(%d)\n",
+ pf, err);
+ return err;
+ }
+
+ rswitch->entry2pcifunc[entry++] = pcifunc;
+
+ rvu_get_pf_numvfs(rvu, pf, &numvfs, NULL);
+ for (vf = 0; vf < numvfs; vf++) {
+ pcifunc = pf << 10 | ((vf + 1) & 0x3FF);
+ rvu_get_nix_blkaddr(rvu, pcifunc);
+
+ err = rvu_switch_install_rx_rule(rvu, pcifunc, 0x0);
+ if (err) {
+ dev_err(rvu->dev,
+ "RX rule for PF%dVF%d failed(%d)\n",
+ pf, vf, err);
+ return err;
+ }
+
+ err = rvu_switch_install_tx_rule(rvu, pcifunc,
+ start + entry);
+ if (err) {
+ dev_err(rvu->dev,
+ "TX rule for PF%dVF%d failed(%d)\n",
+ pf, vf, err);
+ return err;
+ }
+
+ rswitch->entry2pcifunc[entry++] = pcifunc;
+ }
+ }
+
+ return 0;
+}
+
+void rvu_switch_enable(struct rvu *rvu)
+{
+ struct npc_mcam_alloc_entry_req alloc_req = { 0 };
+ struct npc_mcam_alloc_entry_rsp alloc_rsp = { 0 };
+ struct npc_delete_flow_req uninstall_req = { 0 };
+ struct npc_mcam_free_entry_req free_req = { 0 };
+ struct rvu_switch *rswitch = &rvu->rswitch;
+ struct msg_rsp rsp;
+ int ret;
+
+ alloc_req.contig = true;
+ alloc_req.count = rvu->cgx_mapped_pfs + rvu->cgx_mapped_vfs;
+ ret = rvu_mbox_handler_npc_mcam_alloc_entry(rvu, &alloc_req,
+ &alloc_rsp);
+ if (ret) {
+ dev_err(rvu->dev,
+ "Unable to allocate MCAM entries\n");
+ goto exit;
+ }
+
+ if (alloc_rsp.count != alloc_req.count) {
+ dev_err(rvu->dev,
+ "Unable to allocate %d MCAM entries, got %d\n",
+ alloc_req.count, alloc_rsp.count);
+ goto free_entries;
+ }
+
+ rswitch->entry2pcifunc = kcalloc(alloc_req.count, sizeof(u16),
+ GFP_KERNEL);
+ if (!rswitch->entry2pcifunc)
+ goto free_entries;
+
+ rswitch->used_entries = alloc_rsp.count;
+ rswitch->start_entry = alloc_rsp.entry;
+
+ ret = rvu_switch_install_rules(rvu);
+ if (ret)
+ goto uninstall_rules;
+
+ return;
+
+uninstall_rules:
+ uninstall_req.start = rswitch->start_entry;
+ uninstall_req.end = rswitch->start_entry + rswitch->used_entries - 1;
+ rvu_mbox_handler_npc_delete_flow(rvu, &uninstall_req, &rsp);
+ kfree(rswitch->entry2pcifunc);
+free_entries:
+ free_req.all = 1;
+ rvu_mbox_handler_npc_mcam_free_entry(rvu, &free_req, &rsp);
+exit:
+ return;
+}
+
+void rvu_switch_disable(struct rvu *rvu)
+{
+ struct npc_delete_flow_req uninstall_req = { 0 };
+ struct npc_mcam_free_entry_req free_req = { 0 };
+ struct rvu_switch *rswitch = &rvu->rswitch;
+ struct rvu_hwinfo *hw = rvu->hw;
+ int pf, vf, numvfs;
+ struct msg_rsp rsp;
+ u16 pcifunc;
+ int err;
+
+ if (!rswitch->used_entries)
+ return;
+
+ for (pf = 1; pf < hw->total_pfs; pf++) {
+ if (!is_pf_cgxmapped(rvu, pf))
+ continue;
+
+ pcifunc = pf << 10;
+ err = rvu_switch_install_rx_rule(rvu, pcifunc, 0xFFF);
+ if (err)
+ dev_err(rvu->dev,
+ "Reverting RX rule for PF%d failed(%d)\n",
+ pf, err);
+
+ rvu_get_pf_numvfs(rvu, pf, &numvfs, NULL);
+ for (vf = 0; vf < numvfs; vf++) {
+ pcifunc = pf << 10 | ((vf + 1) & 0x3FF);
+ err = rvu_switch_install_rx_rule(rvu, pcifunc, 0xFFF);
+ if (err)
+ dev_err(rvu->dev,
+ "Reverting RX rule for PF%dVF%d failed(%d)\n",
+ pf, vf, err);
+ }
+ }
+
+ uninstall_req.start = rswitch->start_entry;
+ uninstall_req.end = rswitch->start_entry + rswitch->used_entries - 1;
+ free_req.all = 1;
+ rvu_mbox_handler_npc_delete_flow(rvu, &uninstall_req, &rsp);
+ rvu_mbox_handler_npc_mcam_free_entry(rvu, &free_req, &rsp);
+ rswitch->used_entries = 0;
+ kfree(rswitch->entry2pcifunc);
+}
+
+void rvu_switch_update_rules(struct rvu *rvu, u16 pcifunc)
+{
+ struct rvu_switch *rswitch = &rvu->rswitch;
+ u32 max = rswitch->used_entries;
+ u16 entry;
+
+ if (!rswitch->used_entries)
+ return;
+
+ for (entry = 0; entry < max; entry++) {
+ if (rswitch->entry2pcifunc[entry] == pcifunc)
+ break;
+ }
+
+ if (entry >= max)
+ return;
+
+ rvu_switch_install_tx_rule(rvu, pcifunc, rswitch->start_entry + entry);
+ rvu_switch_install_rx_rule(rvu, pcifunc, 0x0);
+}
obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o
rvu_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \
- otx2_ptp.o otx2_flows.o otx2_tc.o cn10k.o
+ otx2_ptp.o otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o
rvu_nicvf-y := otx2_vf.o
ccflags-y += -I$(srctree)/drivers/net/ethernet/marvell/octeontx2/af
.refill_pool_ptrs = cn10k_refill_pool_ptrs,
};
-int cn10k_pf_lmtst_init(struct otx2_nic *pf)
+int cn10k_lmtst_init(struct otx2_nic *pfvf)
{
- int size, num_lines;
- u64 base;
- if (!test_bit(CN10K_LMTST, &pf->hw.cap_flag)) {
- pf->hw_ops = &otx2_hw_ops;
+ struct lmtst_tbl_setup_req *req;
+ int qcount, err;
+
+ if (!test_bit(CN10K_LMTST, &pfvf->hw.cap_flag)) {
+ pfvf->hw_ops = &otx2_hw_ops;
return 0;
}
- pf->hw_ops = &cn10k_hw_ops;
- base = pci_resource_start(pf->pdev, PCI_MBOX_BAR_NUM) +
- (MBOX_SIZE * (pf->total_vfs + 1));
-
- size = pci_resource_len(pf->pdev, PCI_MBOX_BAR_NUM) -
- (MBOX_SIZE * (pf->total_vfs + 1));
-
- pf->hw.lmt_base = ioremap(base, size);
+ pfvf->hw_ops = &cn10k_hw_ops;
+ qcount = pfvf->hw.max_queues;
+ /* LMTST lines allocation
+ * qcount = num_online_cpus();
+ * NPA = TX + RX + XDP.
+ * NIX = TX * 32 (For Burst SQE flush).
+ */
+ pfvf->tot_lmt_lines = (qcount * 3) + (qcount * 32);
+ pfvf->npa_lmt_lines = qcount * 3;
+ pfvf->nix_lmt_size = LMT_BURST_SIZE * LMT_LINE_SIZE;
- if (!pf->hw.lmt_base) {
- dev_err(pf->dev, "Unable to map PF LMTST region\n");
+ mutex_lock(&pfvf->mbox.lock);
+ req = otx2_mbox_alloc_msg_lmtst_tbl_setup(&pfvf->mbox);
+ if (!req) {
+ mutex_unlock(&pfvf->mbox.lock);
return -ENOMEM;
}
- /* FIXME: Get the num of LMTST lines from LMT table */
- pf->tot_lmt_lines = size / LMT_LINE_SIZE;
- num_lines = (pf->tot_lmt_lines - NIX_LMTID_BASE) /
- pf->hw.tx_queues;
- /* Number of LMT lines per SQ queues */
- pf->nix_lmt_lines = num_lines > 32 ? 32 : num_lines;
-
- pf->nix_lmt_size = pf->nix_lmt_lines * LMT_LINE_SIZE;
- return 0;
-}
+ req->use_local_lmt_region = true;
-int cn10k_vf_lmtst_init(struct otx2_nic *vf)
-{
- int size, num_lines;
-
- if (!test_bit(CN10K_LMTST, &vf->hw.cap_flag)) {
- vf->hw_ops = &otx2_hw_ops;
- return 0;
+ err = qmem_alloc(pfvf->dev, &pfvf->dync_lmt, pfvf->tot_lmt_lines,
+ LMT_LINE_SIZE);
+ if (err) {
+ mutex_unlock(&pfvf->mbox.lock);
+ return err;
}
+ pfvf->hw.lmt_base = (u64 *)pfvf->dync_lmt->base;
+ req->lmt_iova = (u64)pfvf->dync_lmt->iova;
- vf->hw_ops = &cn10k_hw_ops;
- size = pci_resource_len(vf->pdev, PCI_MBOX_BAR_NUM);
- vf->hw.lmt_base = ioremap_wc(pci_resource_start(vf->pdev,
- PCI_MBOX_BAR_NUM),
- size);
- if (!vf->hw.lmt_base) {
- dev_err(vf->dev, "Unable to map VF LMTST region\n");
- return -ENOMEM;
- }
+ err = otx2_sync_mbox_msg(&pfvf->mbox);
+ mutex_unlock(&pfvf->mbox.lock);
- vf->tot_lmt_lines = size / LMT_LINE_SIZE;
- /* LMTST lines per SQ */
- num_lines = (vf->tot_lmt_lines - NIX_LMTID_BASE) /
- vf->hw.tx_queues;
- vf->nix_lmt_lines = num_lines > 32 ? 32 : num_lines;
- vf->nix_lmt_size = vf->nix_lmt_lines * LMT_LINE_SIZE;
return 0;
}
-EXPORT_SYMBOL(cn10k_vf_lmtst_init);
+EXPORT_SYMBOL(cn10k_lmtst_init);
int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura)
{
struct otx2_snd_queue *sq;
sq = &pfvf->qset.sq[qidx];
- sq->lmt_addr = (__force u64 *)((u64)pfvf->hw.nix_lmt_base +
+ sq->lmt_addr = (u64 *)((u64)pfvf->hw.nix_lmt_base +
(qidx * pfvf->nix_lmt_size));
+ sq->lmt_id = pfvf->npa_lmt_lines + (qidx * LMT_BURST_SIZE);
+
/* Get memory to put this msg */
aq = otx2_mbox_alloc_msg_nix_cn10k_aq_enq(&pfvf->mbox);
if (!aq)
void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx)
{
- struct otx2_nic *pfvf = dev;
- int lmt_id = NIX_LMTID_BASE + (qidx * pfvf->nix_lmt_lines);
u64 val = 0, tar_addr = 0;
/* FIXME: val[0:10] LMT_ID.
* [12:15] no of LMTST - 1 in the burst.
* [19:63] data size of each LMTST in the burst except first.
*/
- val = (lmt_id & 0x7FF);
+ val = (sq->lmt_id & 0x7FF);
/* Target address for LMTST flush tells HW how many 128bit
* words are present.
* tar_addr[6:4] size of first LMTST - 1 in units of 128b.
void cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq);
void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx);
int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura);
-int cn10k_pf_lmtst_init(struct otx2_nic *pf);
-int cn10k_vf_lmtst_init(struct otx2_nic *vf);
+int cn10k_lmtst_init(struct otx2_nic *pfvf);
int cn10k_free_all_ipolicers(struct otx2_nic *pfvf);
int cn10k_alloc_matchall_ipolicer(struct otx2_nic *pfvf);
int cn10k_free_matchall_ipolicer(struct otx2_nic *pfvf);
/* update dmac field in vlan offload rule */
if (pfvf->flags & OTX2_FLAG_RX_VLAN_SUPPORT)
otx2_install_rxvlan_offload_flow(pfvf);
+ /* update dmac address in ntuple and DMAC filter list */
+ if (pfvf->flags & OTX2_FLAG_DMACFLTR_SUPPORT)
+ otx2_dmacflt_update_pfmac_flow(pfvf);
} else {
return -EPERM;
}
aq->cq.drop = RQ_DROP_LVL_CQ(pfvf->hw.rq_skid, cq->cqe_cnt);
aq->cq.drop_ena = 1;
- /* Enable receive CQ backpressure */
- aq->cq.bp_ena = 1;
- aq->cq.bpid = pfvf->bpid[0];
+ if (!is_otx2_lbkvf(pfvf->pdev)) {
+ /* Enable receive CQ backpressure */
+ aq->cq.bp_ena = 1;
+ aq->cq.bpid = pfvf->bpid[0];
- /* Set backpressure level is same as cq pass level */
- aq->cq.bp = RQ_PASS_LVL_CQ(pfvf->hw.rq_skid, qset->rqe_cnt);
+ /* Set backpressure level is same as cq pass level */
+ aq->cq.bp = RQ_PASS_LVL_CQ(pfvf->hw.rq_skid, qset->rqe_cnt);
+ }
}
/* Fill AQ info */
aq->aura.fc_hyst_bits = 0; /* Store count on all updates */
/* Enable backpressure for RQ aura */
- if (aura_id < pfvf->hw.rqpool_cnt) {
+ if (aura_id < pfvf->hw.rqpool_cnt && !is_otx2_lbkvf(pfvf->pdev)) {
aq->aura.bp_ena = 0;
aq->aura.nix0_bpid = pfvf->bpid[0];
/* Set backpressure level for RQ's Aura */
unsigned long cap_flag;
#define LMT_LINE_SIZE 128
-#define NIX_LMTID_BASE 72 /* RX + TX + XDP */
- void __iomem *lmt_base;
+#define LMT_BURST_SIZE 32 /* 32 LMTST lines for burst SQE flush */
+ u64 *lmt_base;
u64 *npa_lmt_base;
u64 *nix_lmt_base;
};
u16 tc_flower_offset;
u16 ntuple_max_flows;
u16 tc_max_flows;
+ u8 dmacflt_max_flows;
+ u8 *bmap_to_dmacindex;
+ unsigned long dmacflt_bmap;
struct list_head flow_list;
};
#define OTX2_FLAG_TC_FLOWER_SUPPORT BIT_ULL(11)
#define OTX2_FLAG_TC_MATCHALL_EGRESS_ENABLED BIT_ULL(12)
#define OTX2_FLAG_TC_MATCHALL_INGRESS_ENABLED BIT_ULL(13)
+#define OTX2_FLAG_DMACFLTR_SUPPORT BIT_ULL(14)
u64 flags;
struct otx2_qset qset;
/* Block address of NIX either BLKADDR_NIX0 or BLKADDR_NIX1 */
int nix_blkaddr;
/* LMTST Lines info */
+ struct qmem *dync_lmt;
u16 tot_lmt_lines;
- u16 nix_lmt_lines;
+ u16 npa_lmt_lines;
u32 nix_lmt_size;
struct otx2_ptp *ptp;
void otx2_shutdown_tc(struct otx2_nic *nic);
int otx2_setup_tc(struct net_device *netdev, enum tc_setup_type type,
void *type_data);
+/* CGX/RPM DMAC filters support */
+int otx2_dmacflt_get_max_cnt(struct otx2_nic *pf);
+int otx2_dmacflt_add(struct otx2_nic *pf, const u8 *mac, u8 bit_pos);
+int otx2_dmacflt_remove(struct otx2_nic *pf, const u8 *mac, u8 bit_pos);
+int otx2_dmacflt_update(struct otx2_nic *pf, u8 *mac, u8 bit_pos);
+void otx2_dmacflt_reinstall_flows(struct otx2_nic *pf);
+void otx2_dmacflt_update_pfmac_flow(struct otx2_nic *pfvf);
#endif /* OTX2_COMMON_H */
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell OcteonTx2 RVU Physcial Function ethernet driver
+ *
+ * Copyright (C) 2021 Marvell.
+ */
+
+#include "otx2_common.h"
+
+static int otx2_dmacflt_do_add(struct otx2_nic *pf, const u8 *mac,
+ u8 *dmac_index)
+{
+ struct cgx_mac_addr_add_req *req;
+ struct cgx_mac_addr_add_rsp *rsp;
+ int err;
+
+ mutex_lock(&pf->mbox.lock);
+
+ req = otx2_mbox_alloc_msg_cgx_mac_addr_add(&pf->mbox);
+ if (!req) {
+ mutex_unlock(&pf->mbox.lock);
+ return -ENOMEM;
+ }
+
+ ether_addr_copy(req->mac_addr, mac);
+ err = otx2_sync_mbox_msg(&pf->mbox);
+
+ if (!err) {
+ rsp = (struct cgx_mac_addr_add_rsp *)
+ otx2_mbox_get_rsp(&pf->mbox.mbox, 0, &req->hdr);
+ *dmac_index = rsp->index;
+ }
+
+ mutex_unlock(&pf->mbox.lock);
+ return err;
+}
+
+static int otx2_dmacflt_add_pfmac(struct otx2_nic *pf)
+{
+ struct cgx_mac_addr_set_or_get *req;
+ int err;
+
+ mutex_lock(&pf->mbox.lock);
+
+ req = otx2_mbox_alloc_msg_cgx_mac_addr_set(&pf->mbox);
+ if (!req) {
+ mutex_unlock(&pf->mbox.lock);
+ return -ENOMEM;
+ }
+
+ ether_addr_copy(req->mac_addr, pf->netdev->dev_addr);
+ err = otx2_sync_mbox_msg(&pf->mbox);
+
+ mutex_unlock(&pf->mbox.lock);
+ return err;
+}
+
+int otx2_dmacflt_add(struct otx2_nic *pf, const u8 *mac, u8 bit_pos)
+{
+ u8 *dmacindex;
+
+ /* Store dmacindex returned by CGX/RPM driver which will
+ * be used for macaddr update/remove
+ */
+ dmacindex = &pf->flow_cfg->bmap_to_dmacindex[bit_pos];
+
+ if (ether_addr_equal(mac, pf->netdev->dev_addr))
+ return otx2_dmacflt_add_pfmac(pf);
+ else
+ return otx2_dmacflt_do_add(pf, mac, dmacindex);
+}
+
+static int otx2_dmacflt_do_remove(struct otx2_nic *pfvf, const u8 *mac,
+ u8 dmac_index)
+{
+ struct cgx_mac_addr_del_req *req;
+ int err;
+
+ mutex_lock(&pfvf->mbox.lock);
+ req = otx2_mbox_alloc_msg_cgx_mac_addr_del(&pfvf->mbox);
+ if (!req) {
+ mutex_unlock(&pfvf->mbox.lock);
+ return -ENOMEM;
+ }
+
+ req->index = dmac_index;
+
+ err = otx2_sync_mbox_msg(&pfvf->mbox);
+ mutex_unlock(&pfvf->mbox.lock);
+
+ return err;
+}
+
+static int otx2_dmacflt_remove_pfmac(struct otx2_nic *pf)
+{
+ struct msg_req *req;
+ int err;
+
+ mutex_lock(&pf->mbox.lock);
+ req = otx2_mbox_alloc_msg_cgx_mac_addr_reset(&pf->mbox);
+ if (!req) {
+ mutex_unlock(&pf->mbox.lock);
+ return -ENOMEM;
+ }
+
+ err = otx2_sync_mbox_msg(&pf->mbox);
+
+ mutex_unlock(&pf->mbox.lock);
+ return err;
+}
+
+int otx2_dmacflt_remove(struct otx2_nic *pf, const u8 *mac,
+ u8 bit_pos)
+{
+ u8 dmacindex = pf->flow_cfg->bmap_to_dmacindex[bit_pos];
+
+ if (ether_addr_equal(mac, pf->netdev->dev_addr))
+ return otx2_dmacflt_remove_pfmac(pf);
+ else
+ return otx2_dmacflt_do_remove(pf, mac, dmacindex);
+}
+
+/* CGX/RPM blocks support max unicast entries of 32.
+ * on typical configuration MAC block associated
+ * with 4 lmacs, each lmac will have 8 dmac entries
+ */
+int otx2_dmacflt_get_max_cnt(struct otx2_nic *pf)
+{
+ struct cgx_max_dmac_entries_get_rsp *rsp;
+ struct msg_req *msg;
+ int err;
+
+ mutex_lock(&pf->mbox.lock);
+ msg = otx2_mbox_alloc_msg_cgx_mac_max_entries_get(&pf->mbox);
+
+ if (!msg) {
+ mutex_unlock(&pf->mbox.lock);
+ return -ENOMEM;
+ }
+
+ err = otx2_sync_mbox_msg(&pf->mbox);
+ if (err)
+ goto out;
+
+ rsp = (struct cgx_max_dmac_entries_get_rsp *)
+ otx2_mbox_get_rsp(&pf->mbox.mbox, 0, &msg->hdr);
+ pf->flow_cfg->dmacflt_max_flows = rsp->max_dmac_filters;
+
+out:
+ mutex_unlock(&pf->mbox.lock);
+ return err;
+}
+
+int otx2_dmacflt_update(struct otx2_nic *pf, u8 *mac, u8 bit_pos)
+{
+ struct cgx_mac_addr_update_req *req;
+ int rc;
+
+ mutex_lock(&pf->mbox.lock);
+
+ req = otx2_mbox_alloc_msg_cgx_mac_addr_update(&pf->mbox);
+
+ if (!req) {
+ mutex_unlock(&pf->mbox.lock);
+ return -ENOMEM;
+ }
+
+ ether_addr_copy(req->mac_addr, mac);
+ req->index = pf->flow_cfg->bmap_to_dmacindex[bit_pos];
+ rc = otx2_sync_mbox_msg(&pf->mbox);
+
+ mutex_unlock(&pf->mbox.lock);
+ return rc;
+}
err = otx2_set_real_num_queues(dev, channel->tx_count,
channel->rx_count);
if (err)
- goto fail;
+ return err;
pfvf->hw.rx_queues = channel->rx_count;
pfvf->hw.tx_queues = channel->tx_count;
pfvf->qset.cq_cnt = pfvf->hw.tx_queues + pfvf->hw.rx_queues;
-fail:
if (if_up)
- dev->netdev_ops->ndo_open(dev);
+ err = dev->netdev_ops->ndo_open(dev);
netdev_info(dev, "Setting num Tx rings to %d, Rx rings to %d success\n",
pfvf->hw.tx_queues, pfvf->hw.rx_queues);
qs->rqe_cnt = rx_count;
if (if_up)
- netdev->netdev_ops->ndo_open(netdev);
+ return netdev->netdev_ops->ndo_open(netdev);
return 0;
}
bool is_vf;
u8 rss_ctx_id;
int vf;
+ bool dmac_filter;
+};
+
+enum dmac_req {
+ DMAC_ADDR_UPDATE,
+ DMAC_ADDR_DEL
};
static void otx2_clear_ntuple_flow_info(struct otx2_nic *pfvf, struct otx2_flow_config *flow_cfg)
if (!pf->mac_table)
return -ENOMEM;
+ otx2_dmacflt_get_max_cnt(pf);
+
+ /* DMAC filters are not allocated */
+ if (!pf->flow_cfg->dmacflt_max_flows)
+ return 0;
+
+ pf->flow_cfg->bmap_to_dmacindex =
+ devm_kzalloc(pf->dev, sizeof(u8) *
+ pf->flow_cfg->dmacflt_max_flows,
+ GFP_KERNEL);
+
+ if (!pf->flow_cfg->bmap_to_dmacindex)
+ return -ENOMEM;
+
+ pf->flags |= OTX2_FLAG_DMACFLTR_SUPPORT;
+
return 0;
}
{
struct otx2_nic *pf = netdev_priv(netdev);
+ if (bitmap_weight(&pf->flow_cfg->dmacflt_bmap,
+ pf->flow_cfg->dmacflt_max_flows))
+ netdev_warn(netdev,
+ "Add %pM to CGX/RPM DMAC filters list as well\n",
+ mac);
+
return otx2_do_add_macfilter(pf, mac);
}
list_add(&flow->list, head);
}
+static int otx2_get_maxflows(struct otx2_flow_config *flow_cfg)
+{
+ if (flow_cfg->nr_flows == flow_cfg->ntuple_max_flows ||
+ bitmap_weight(&flow_cfg->dmacflt_bmap,
+ flow_cfg->dmacflt_max_flows))
+ return flow_cfg->ntuple_max_flows + flow_cfg->dmacflt_max_flows;
+ else
+ return flow_cfg->ntuple_max_flows;
+}
+
int otx2_get_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc,
u32 location)
{
struct otx2_flow *iter;
- if (location >= pfvf->flow_cfg->ntuple_max_flows)
+ if (location >= otx2_get_maxflows(pfvf->flow_cfg))
return -EINVAL;
list_for_each_entry(iter, &pfvf->flow_cfg->flow_list, list) {
int idx = 0;
int err = 0;
- nfc->data = pfvf->flow_cfg->ntuple_max_flows;
+ nfc->data = otx2_get_maxflows(pfvf->flow_cfg);
while ((!err || err == -ENOENT) && idx < rule_cnt) {
err = otx2_get_flow(pfvf, nfc, location);
if (!err)
return 0;
}
+static int otx2_is_flow_rule_dmacfilter(struct otx2_nic *pfvf,
+ struct ethtool_rx_flow_spec *fsp)
+{
+ struct ethhdr *eth_mask = &fsp->m_u.ether_spec;
+ struct ethhdr *eth_hdr = &fsp->h_u.ether_spec;
+ u64 ring_cookie = fsp->ring_cookie;
+ u32 flow_type;
+
+ if (!(pfvf->flags & OTX2_FLAG_DMACFLTR_SUPPORT))
+ return false;
+
+ flow_type = fsp->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS);
+
+ /* CGX/RPM block dmac filtering configured for white listing
+ * check for action other than DROP
+ */
+ if (flow_type == ETHER_FLOW && ring_cookie != RX_CLS_FLOW_DISC &&
+ !ethtool_get_flow_spec_ring_vf(ring_cookie)) {
+ if (is_zero_ether_addr(eth_mask->h_dest) &&
+ is_valid_ether_addr(eth_hdr->h_dest))
+ return true;
+ }
+
+ return false;
+}
+
static int otx2_add_flow_msg(struct otx2_nic *pfvf, struct otx2_flow *flow)
{
u64 ring_cookie = flow->flow_spec.ring_cookie;
return err;
}
+static int otx2_add_flow_with_pfmac(struct otx2_nic *pfvf,
+ struct otx2_flow *flow)
+{
+ struct otx2_flow *pf_mac;
+ struct ethhdr *eth_hdr;
+
+ pf_mac = kzalloc(sizeof(*pf_mac), GFP_KERNEL);
+ if (!pf_mac)
+ return -ENOMEM;
+
+ pf_mac->entry = 0;
+ pf_mac->dmac_filter = true;
+ pf_mac->location = pfvf->flow_cfg->ntuple_max_flows;
+ memcpy(&pf_mac->flow_spec, &flow->flow_spec,
+ sizeof(struct ethtool_rx_flow_spec));
+ pf_mac->flow_spec.location = pf_mac->location;
+
+ /* Copy PF mac address */
+ eth_hdr = &pf_mac->flow_spec.h_u.ether_spec;
+ ether_addr_copy(eth_hdr->h_dest, pfvf->netdev->dev_addr);
+
+ /* Install DMAC filter with PF mac address */
+ otx2_dmacflt_add(pfvf, eth_hdr->h_dest, 0);
+
+ otx2_add_flow_to_list(pfvf, pf_mac);
+ pfvf->flow_cfg->nr_flows++;
+ set_bit(0, &pfvf->flow_cfg->dmacflt_bmap);
+
+ return 0;
+}
+
int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc)
{
struct otx2_flow_config *flow_cfg = pfvf->flow_cfg;
struct ethtool_rx_flow_spec *fsp = &nfc->fs;
struct otx2_flow *flow;
+ struct ethhdr *eth_hdr;
bool new = false;
+ int err = 0;
u32 ring;
- int err;
ring = ethtool_get_flow_spec_ring(fsp->ring_cookie);
if (!(pfvf->flags & OTX2_FLAG_NTUPLE_SUPPORT))
if (ring >= pfvf->hw.rx_queues && fsp->ring_cookie != RX_CLS_FLOW_DISC)
return -EINVAL;
- if (fsp->location >= flow_cfg->ntuple_max_flows)
+ if (fsp->location >= otx2_get_maxflows(flow_cfg))
return -EINVAL;
flow = otx2_find_flow(pfvf, fsp->location);
if (!flow) {
- flow = kzalloc(sizeof(*flow), GFP_ATOMIC);
+ flow = kzalloc(sizeof(*flow), GFP_KERNEL);
if (!flow)
return -ENOMEM;
flow->location = fsp->location;
- flow->entry = flow_cfg->flow_ent[flow->location];
new = true;
}
/* struct copy */
if (fsp->flow_type & FLOW_RSS)
flow->rss_ctx_id = nfc->rss_context;
- err = otx2_add_flow_msg(pfvf, flow);
+ if (otx2_is_flow_rule_dmacfilter(pfvf, &flow->flow_spec)) {
+ eth_hdr = &flow->flow_spec.h_u.ether_spec;
+
+ /* Sync dmac filter table with updated fields */
+ if (flow->dmac_filter)
+ return otx2_dmacflt_update(pfvf, eth_hdr->h_dest,
+ flow->entry);
+
+ if (bitmap_full(&flow_cfg->dmacflt_bmap,
+ flow_cfg->dmacflt_max_flows)) {
+ netdev_warn(pfvf->netdev,
+ "Can't insert the rule %d as max allowed dmac filters are %d\n",
+ flow->location +
+ flow_cfg->dmacflt_max_flows,
+ flow_cfg->dmacflt_max_flows);
+ err = -EINVAL;
+ if (new)
+ kfree(flow);
+ return err;
+ }
+
+ /* Install PF mac address to DMAC filter list */
+ if (!test_bit(0, &flow_cfg->dmacflt_bmap))
+ otx2_add_flow_with_pfmac(pfvf, flow);
+
+ flow->dmac_filter = true;
+ flow->entry = find_first_zero_bit(&flow_cfg->dmacflt_bmap,
+ flow_cfg->dmacflt_max_flows);
+ fsp->location = flow_cfg->ntuple_max_flows + flow->entry;
+ flow->flow_spec.location = fsp->location;
+ flow->location = fsp->location;
+
+ set_bit(flow->entry, &flow_cfg->dmacflt_bmap);
+ otx2_dmacflt_add(pfvf, eth_hdr->h_dest, flow->entry);
+
+ } else {
+ if (flow->location >= pfvf->flow_cfg->ntuple_max_flows) {
+ netdev_warn(pfvf->netdev,
+ "Can't insert non dmac ntuple rule at %d, allowed range %d-0\n",
+ flow->location,
+ flow_cfg->ntuple_max_flows - 1);
+ err = -EINVAL;
+ } else {
+ flow->entry = flow_cfg->flow_ent[flow->location];
+ err = otx2_add_flow_msg(pfvf, flow);
+ }
+ }
+
if (err) {
if (new)
kfree(flow);
return err;
}
+static void otx2_update_rem_pfmac(struct otx2_nic *pfvf, int req)
+{
+ struct otx2_flow *iter;
+ struct ethhdr *eth_hdr;
+ bool found = false;
+
+ list_for_each_entry(iter, &pfvf->flow_cfg->flow_list, list) {
+ if (iter->dmac_filter && iter->entry == 0) {
+ eth_hdr = &iter->flow_spec.h_u.ether_spec;
+ if (req == DMAC_ADDR_DEL) {
+ otx2_dmacflt_remove(pfvf, eth_hdr->h_dest,
+ 0);
+ clear_bit(0, &pfvf->flow_cfg->dmacflt_bmap);
+ found = true;
+ } else {
+ ether_addr_copy(eth_hdr->h_dest,
+ pfvf->netdev->dev_addr);
+ otx2_dmacflt_update(pfvf, eth_hdr->h_dest, 0);
+ }
+ break;
+ }
+ }
+
+ if (found) {
+ list_del(&iter->list);
+ kfree(iter);
+ pfvf->flow_cfg->nr_flows--;
+ }
+}
+
int otx2_remove_flow(struct otx2_nic *pfvf, u32 location)
{
struct otx2_flow_config *flow_cfg = pfvf->flow_cfg;
struct otx2_flow *flow;
int err;
- if (location >= flow_cfg->ntuple_max_flows)
+ if (location >= otx2_get_maxflows(flow_cfg))
return -EINVAL;
flow = otx2_find_flow(pfvf, location);
if (!flow)
return -ENOENT;
- err = otx2_remove_flow_msg(pfvf, flow->entry, false);
+ if (flow->dmac_filter) {
+ struct ethhdr *eth_hdr = &flow->flow_spec.h_u.ether_spec;
+
+ /* user not allowed to remove dmac filter with interface mac */
+ if (ether_addr_equal(pfvf->netdev->dev_addr, eth_hdr->h_dest))
+ return -EPERM;
+
+ err = otx2_dmacflt_remove(pfvf, eth_hdr->h_dest,
+ flow->entry);
+ clear_bit(flow->entry, &flow_cfg->dmacflt_bmap);
+ /* If all dmac filters are removed delete macfilter with
+ * interface mac address and configure CGX/RPM block in
+ * promiscuous mode
+ */
+ if (bitmap_weight(&flow_cfg->dmacflt_bmap,
+ flow_cfg->dmacflt_max_flows) == 1)
+ otx2_update_rem_pfmac(pfvf, DMAC_ADDR_DEL);
+ } else {
+ err = otx2_remove_flow_msg(pfvf, flow->entry, false);
+ }
+
if (err)
return err;
mutex_unlock(&pf->mbox.lock);
return rsp_hdr->rc;
}
+
+void otx2_dmacflt_reinstall_flows(struct otx2_nic *pf)
+{
+ struct otx2_flow *iter;
+ struct ethhdr *eth_hdr;
+
+ list_for_each_entry(iter, &pf->flow_cfg->flow_list, list) {
+ if (iter->dmac_filter) {
+ eth_hdr = &iter->flow_spec.h_u.ether_spec;
+ otx2_dmacflt_add(pf, eth_hdr->h_dest,
+ iter->entry);
+ }
+ }
+}
+
+void otx2_dmacflt_update_pfmac_flow(struct otx2_nic *pfvf)
+{
+ otx2_update_rem_pfmac(pfvf, DMAC_ADDR_UPDATE);
+}
struct msg_req *msg;
int err;
+ if (enable && bitmap_weight(&pf->flow_cfg->dmacflt_bmap,
+ pf->flow_cfg->dmacflt_max_flows))
+ netdev_warn(pf->netdev,
+ "CGX/RPM internal loopback might not work as DMAC filters are active\n");
+
mutex_lock(&pf->mbox.lock);
if (enable)
msg = otx2_mbox_alloc_msg_cgx_intlbk_enable(&pf->mbox);
if (test_bit(CN10K_LMTST, &pf->hw.cap_flag)) {
/* Reserve LMT lines for NPA AURA batch free */
- pf->hw.npa_lmt_base = (__force u64 *)pf->hw.lmt_base;
+ pf->hw.npa_lmt_base = pf->hw.lmt_base;
/* Reserve LMT lines for NIX TX */
- pf->hw.nix_lmt_base = (__force u64 *)((u64)pf->hw.npa_lmt_base +
- (NIX_LMTID_BASE * LMT_LINE_SIZE));
+ pf->hw.nix_lmt_base = (u64 *)((u64)pf->hw.npa_lmt_base +
+ (pf->npa_lmt_lines * LMT_LINE_SIZE));
}
err = otx2_init_hw_resources(pf);
/* Restore pause frame settings */
otx2_config_pause_frm(pf);
+ /* Install DMAC Filters */
+ if (pf->flags & OTX2_FLAG_DMACFLTR_SUPPORT)
+ otx2_dmacflt_reinstall_flows(pf);
+
err = otx2_rxtx_enable(pf, true);
if (err)
goto err_tx_stop_queues;
err_tx_stop_queues:
netif_tx_stop_all_queues(netdev);
netif_carrier_off(netdev);
+ pf->flags |= OTX2_FLAG_INTF_DOWN;
err_free_cints:
otx2_free_cints(pf, qidx);
vec = pci_irq_vector(pf->pdev,
struct otx2_rss_info *rss;
int qidx, vec, wrk;
+ /* If the DOWN flag is set resources are already freed */
+ if (pf->flags & OTX2_FLAG_INTF_DOWN)
+ return 0;
+
netif_carrier_off(netdev);
netif_tx_stop_all_queues(netdev);
if (err)
goto err_detach_rsrc;
- err = cn10k_pf_lmtst_init(pf);
+ err = cn10k_lmtst_init(pf);
if (err)
goto err_detach_rsrc;
err_ptp_destroy:
otx2_ptp_destroy(pf);
err_detach_rsrc:
- if (hw->lmt_base)
- iounmap(hw->lmt_base);
+ if (test_bit(CN10K_LMTST, &pf->hw.cap_flag))
+ qmem_free(pf->dev, pf->dync_lmt);
otx2_detach_resources(&pf->mbox);
err_disable_mbox_intr:
otx2_disable_mbox_intr(pf);
otx2_mcam_flow_del(pf);
otx2_shutdown_tc(pf);
otx2_detach_resources(&pf->mbox);
- if (pf->hw.lmt_base)
- iounmap(pf->hw.lmt_base);
-
+ if (test_bit(CN10K_LMTST, &pf->hw.cap_flag))
+ qmem_free(pf->dev, pf->dync_lmt);
otx2_disable_mbox_intr(pf);
otx2_pfaf_mbox_destroy(pf);
pci_free_irq_vectors(pf->pdev);
struct otx2_nic *priv;
u32 burst, mark = 0;
u8 nr_police = 0;
- bool pps;
+ bool pps = false;
u64 rate;
int i;
u16 num_sqbs;
u16 sqe_thresh;
u8 sqe_per_sqb;
+ u32 lmt_id;
u64 io_addr;
u64 *aura_fc_addr;
u64 *lmt_addr;
if (err)
goto err_detach_rsrc;
- err = cn10k_vf_lmtst_init(vf);
+ err = cn10k_lmtst_init(vf);
if (err)
goto err_detach_rsrc;
err_unreg_netdev:
unregister_netdev(netdev);
err_detach_rsrc:
- if (hw->lmt_base)
- iounmap(hw->lmt_base);
+ if (test_bit(CN10K_LMTST, &vf->hw.cap_flag))
+ qmem_free(vf->dev, vf->dync_lmt);
otx2_detach_resources(&vf->mbox);
err_disable_mbox_intr:
otx2vf_disable_mbox_intr(vf);
destroy_workqueue(vf->otx2_wq);
otx2vf_disable_mbox_intr(vf);
otx2_detach_resources(&vf->mbox);
-
- if (vf->hw.lmt_base)
- iounmap(vf->hw.lmt_base);
-
+ if (test_bit(CN10K_LMTST, &vf->hw.cap_flag))
+ qmem_free(vf->dev, vf->dync_lmt);
otx2vf_vfaf_mbox_destroy(vf);
pci_free_irq_vectors(vf->pdev);
pci_set_drvdata(pdev, NULL);
prestera_trap = &prestera_trap_items_arr[i];
devlink_traps_unregister(devlink, &prestera_trap->trap, 1);
}
+ devlink_trap_groups_unregister(devlink, prestera_trap_groups_arr,
+ groups_count);
err_groups_register:
kfree(trap_data->trap_items_arr);
err_trap_items_alloc:
if (!SRIOV_VALID_STATE(dev->flags)) {
mlx4_err(dev, "Invalid SRIOV state\n");
+ err = -EINVAL;
goto err_close;
}
}
return 1;
}
-/* This function is called with two flows:
- * 1. During initialization of mlx5_core_dev and we don't need to lock it.
- * 2. During LAG configure stage and caller holds &mlx5_intf_mutex.
- */
+/* Must be called with intf_mutex held */
struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev)
{
struct auxiliary_device *adev;
param->cq_period_mode = params->rx_cq_moderation.cq_period_mode;
}
+static u8 rq_end_pad_mode(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
+{
+ bool ro = pcie_relaxed_ordering_enabled(mdev->pdev) &&
+ MLX5_CAP_GEN(mdev, relaxed_ordering_write);
+
+ return ro && params->lro_en ?
+ MLX5_WQ_END_PAD_MODE_NONE : MLX5_WQ_END_PAD_MODE_ALIGN;
+}
+
int mlx5e_build_rq_param(struct mlx5_core_dev *mdev,
struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk,
}
MLX5_SET(wq, wq, wq_type, params->rq_wq_type);
- MLX5_SET(wq, wq, end_padding_mode, MLX5_WQ_END_PAD_MODE_ALIGN);
+ MLX5_SET(wq, wq, end_padding_mode, rq_end_pad_mode(mdev, params));
MLX5_SET(wq, wq, log_wq_stride,
mlx5e_get_rqwq_log_stride(params->rq_wq_type, ndsegs));
MLX5_SET(wq, wq, pd, mdev->mlx5e_res.hw_objs.pdn);
params->log_sq_size = orig->log_sq_size;
mlx5e_ptp_build_sq_param(c->mdev, params, &cparams->txq_sq_param);
}
- if (test_bit(MLX5E_PTP_STATE_RX, c->state))
+ /* RQ */
+ if (test_bit(MLX5E_PTP_STATE_RX, c->state)) {
+ params->vlan_strip_disable = orig->vlan_strip_disable;
mlx5e_ptp_build_rq_param(c->mdev, c->netdev, c->priv->q_counter, cparams);
+ }
}
static int mlx5e_init_ptp_rq(struct mlx5e_ptp *c, struct mlx5e_params *params,
int err;
rq->wq_type = params->rq_wq_type;
- rq->pdev = mdev->device;
+ rq->pdev = c->pdev;
rq->netdev = priv->netdev;
rq->priv = priv;
rq->clock = &mdev->clock;
struct mlx5e_priv *priv = t->priv;
rq->wq_type = params->rq_wq_type;
- rq->pdev = mdev->device;
+ rq->pdev = t->pdev;
rq->netdev = priv->netdev;
rq->priv = priv;
rq->clock = &mdev->clock;
static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd)
{
- int err = 0;
+ int err;
int i;
for (i = 0; i < chs->num; i++) {
if (err)
return err;
}
+ if (chs->ptp && test_bit(MLX5E_PTP_STATE_RX, chs->ptp->state))
+ return mlx5e_modify_rq_vsd(&chs->ptp->rq, vsd);
return 0;
}
return 0;
}
+static netdev_features_t mlx5e_fix_uplink_rep_features(struct net_device *netdev,
+ netdev_features_t features)
+{
+ features &= ~NETIF_F_HW_TLS_RX;
+ if (netdev->features & NETIF_F_HW_TLS_RX)
+ netdev_warn(netdev, "Disabling hw_tls_rx, not supported in switchdev mode\n");
+
+ features &= ~NETIF_F_HW_TLS_TX;
+ if (netdev->features & NETIF_F_HW_TLS_TX)
+ netdev_warn(netdev, "Disabling hw_tls_tx, not supported in switchdev mode\n");
+
+ features &= ~NETIF_F_NTUPLE;
+ if (netdev->features & NETIF_F_NTUPLE)
+ netdev_warn(netdev, "Disabling ntuple, not supported in switchdev mode\n");
+
+ return features;
+}
+
static netdev_features_t mlx5e_fix_features(struct net_device *netdev,
netdev_features_t features)
{
netdev_warn(netdev, "Disabling rxhash, not supported when CQE compress is active\n");
}
- if (mlx5e_is_uplink_rep(priv)) {
- features &= ~NETIF_F_HW_TLS_RX;
- if (netdev->features & NETIF_F_HW_TLS_RX)
- netdev_warn(netdev, "Disabling hw_tls_rx, not supported in switchdev mode\n");
-
- features &= ~NETIF_F_HW_TLS_TX;
- if (netdev->features & NETIF_F_HW_TLS_TX)
- netdev_warn(netdev, "Disabling hw_tls_tx, not supported in switchdev mode\n");
- }
+ if (mlx5e_is_uplink_rep(priv))
+ features = mlx5e_fix_uplink_rep_features(netdev, features);
mutex_unlock(&priv->state_lock);
if (MLX5_CAP_ETH(mdev, scatter_fcs))
netdev->hw_features |= NETIF_F_RXFCS;
+ if (mlx5_qos_is_supported(mdev))
+ netdev->hw_features |= NETIF_F_HW_TC;
+
netdev->features = netdev->hw_features;
/* Defaults */
netdev->hw_features |= NETIF_F_NTUPLE;
#endif
}
- if (mlx5_qos_is_supported(mdev))
- netdev->features |= NETIF_F_HW_TC;
netdev->features |= NETIF_F_HIGHDMA;
netdev->features |= NETIF_F_HW_VLAN_STAG_FILTER;
static
struct mlx5_core_dev *mlx5e_hairpin_get_mdev(struct net *net, int ifindex)
{
+ struct mlx5_core_dev *mdev;
struct net_device *netdev;
struct mlx5e_priv *priv;
- netdev = __dev_get_by_index(net, ifindex);
+ netdev = dev_get_by_index(net, ifindex);
+ if (!netdev)
+ return ERR_PTR(-ENODEV);
+
priv = netdev_priv(netdev);
- return priv->mdev;
+ mdev = priv->mdev;
+ dev_put(netdev);
+
+ /* Mirred tc action holds a refcount on the ifindex net_device (see
+ * net/sched/act_mirred.c:tcf_mirred_get_dev). So, it's okay to continue using mdev
+ * after dev_put(netdev), while we're in the context of adding a tc flow.
+ *
+ * The mdev pointer corresponds to the peer/out net_device of a hairpin. It is then
+ * stored in a hairpin object, which exists until all flows, that refer to it, get
+ * removed.
+ *
+ * On the other hand, after a hairpin object has been created, the peer net_device may
+ * be removed/unbound while there are still some hairpin flows that are using it. This
+ * case is handled by mlx5e_tc_hairpin_update_dead_peer, which is hooked to
+ * NETDEV_UNREGISTER event of the peer net_device.
+ */
+ return mdev;
}
static int mlx5e_hairpin_create_transport(struct mlx5e_hairpin *hp)
func_mdev = priv->mdev;
peer_mdev = mlx5e_hairpin_get_mdev(dev_net(priv->netdev), peer_ifindex);
+ if (IS_ERR(peer_mdev)) {
+ err = PTR_ERR(peer_mdev);
+ goto create_pair_err;
+ }
pair = mlx5_core_hairpin_create(func_mdev, peer_mdev, params);
if (IS_ERR(pair)) {
int err;
peer_mdev = mlx5e_hairpin_get_mdev(dev_net(priv->netdev), peer_ifindex);
+ if (IS_ERR(peer_mdev)) {
+ NL_SET_ERR_MSG_MOD(extack, "invalid ifindex of mirred device");
+ return PTR_ERR(peer_mdev);
+ }
+
if (!MLX5_CAP_GEN(priv->mdev, hairpin) || !MLX5_CAP_GEN(peer_mdev, hairpin)) {
NL_SET_ERR_MSG_MOD(extack, "hairpin is not supported");
return -EOPNOTSUPP;
};
struct mlx5_vport_tbl_attr {
- u16 chain;
+ u32 chain;
u16 prio;
u16 vport;
const struct esw_vport_tbl_namespace *vport_ns;
{
dest[dest_idx].type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
dest[dest_idx].vport.num = esw_attr->dests[attr_idx].rep->vport;
- dest[dest_idx].vport.vhca_id =
- MLX5_CAP_GEN(esw_attr->dests[attr_idx].mdev, vhca_id);
- if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+ if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) {
+ dest[dest_idx].vport.vhca_id =
+ MLX5_CAP_GEN(esw_attr->dests[attr_idx].mdev, vhca_id);
dest[dest_idx].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
+ }
if (esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP) {
if (pkt_reformat) {
flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
switch (event) {
case ESW_OFFLOADS_DEVCOM_PAIR:
+ if (mlx5_get_next_phys_dev(esw->dev) != peer_esw->dev)
+ break;
+
if (mlx5_eswitch_vport_match_metadata_enabled(esw) !=
mlx5_eswitch_vport_match_metadata_enabled(peer_esw))
break;
static int connect_flow_table(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft,
struct fs_prio *prio)
{
- struct mlx5_flow_table *next_ft;
+ struct mlx5_flow_table *next_ft, *first_ft;
int err = 0;
/* Connect_prev_fts and update_root_ft_create are mutually exclusive */
- if (list_empty(&prio->node.children)) {
+ first_ft = list_first_entry_or_null(&prio->node.children,
+ struct mlx5_flow_table, node.list);
+ if (!first_ft || first_ft->level > ft->level) {
err = connect_prev_fts(dev, ft, prio);
if (err)
return err;
- next_ft = find_next_chained_ft(prio);
+ next_ft = first_ft ? first_ft : find_next_chained_ft(prio);
err = connect_fwd_rules(dev, ft, next_ft);
if (err)
return err;
node.list) == ft))
return 0;
- next_ft = find_next_chained_ft(prio);
+ next_ft = find_next_ft(ft);
err = connect_fwd_rules(dev, next_ft, ft);
if (err)
return err;
}
fw_reporter_ctx.err_synd = health->synd;
fw_reporter_ctx.miss_counter = health->miss_counter;
- devlink_health_report(health->fw_fatal_reporter,
- "FW fatal error reported", &fw_reporter_ctx);
+ if (devlink_health_report(health->fw_fatal_reporter,
+ "FW fatal error reported", &fw_reporter_ctx) == -ECANCELED) {
+ /* If recovery wasn't performed, due to grace period,
+ * unload the driver. This ensures that the driver
+ * closes all its resources and it is not subjected to
+ * requests from the kernel.
+ */
+ mlx5_core_err(dev, "Driver is in error state. Unloading\n");
+ mlx5_unload_one(dev);
+ }
}
static const struct devlink_health_reporter_ops mlx5_fw_fatal_reporter_ops = {
tristate "Sparx5 switch driver"
depends on NET_SWITCHDEV
depends on HAS_IOMEM
+ depends on OF
+ depends on ARCH_SPARX5 || COMPILE_TEST
select PHYLINK
select PHY_SPARX5_SERDES
select RESET_CONTROLLER
*/
#define VSTAX 73
-static void ifh_encode_bitfield(void *ifh, u64 value, u32 pos, u32 width)
+#define ifh_encode_bitfield(ifh, value, pos, _width) \
+ ({ \
+ u32 width = (_width); \
+ \
+ /* Max width is 5 bytes - 40 bits. In worst case this will
+ * spread over 6 bytes - 48 bits
+ */ \
+ compiletime_assert(width <= 40, \
+ "Unsupported width, must be <= 40"); \
+ __ifh_encode_bitfield((ifh), (value), (pos), width); \
+ })
+
+static void __ifh_encode_bitfield(void *ifh, u64 value, u32 pos, u32 width)
{
u8 *ifh_hdr = ifh;
/* Calculate the Start IFH byte position of this IFH bit position */
u32 byte = (35 - (pos / 8));
/* Calculate the Start bit position in the Start IFH byte */
u32 bit = (pos % 8);
- u64 encode = GENMASK(bit + width - 1, bit) & (value << bit);
-
- /* Max width is 5 bytes - 40 bits. In worst case this will
- * spread over 6 bytes - 48 bits
- */
- compiletime_assert(width <= 40, "Unsupported width, must be <= 40");
+ u64 encode = GENMASK_ULL(bit + width - 1, bit) & (value << bit);
/* The b0-b7 goes into the start IFH byte */
if (encode & 0xFF)
SET_NETDEV_DEV(ndev, &pdev->dev);
ret = register_netdev(ndev);
- if (ret) {
- free_netdev(ndev);
+ if (ret)
goto init_fail;
- }
netdev_dbg(ndev, "%s: IRQ=%d address=%pM\n",
__func__, ndev->irq, ndev->dev_addr);
}
static int ocelot_netdevice_changeupper(struct net_device *dev,
+ struct net_device *brport_dev,
struct netdev_notifier_changeupper_info *info)
{
struct netlink_ext_ack *extack;
if (netif_is_bridge_master(info->upper_dev)) {
if (info->linking)
- err = ocelot_netdevice_bridge_join(dev, dev,
+ err = ocelot_netdevice_bridge_join(dev, brport_dev,
info->upper_dev,
extack);
else
- err = ocelot_netdevice_bridge_leave(dev, dev,
+ err = ocelot_netdevice_bridge_leave(dev, brport_dev,
info->upper_dev);
}
if (netif_is_lag_master(info->upper_dev)) {
if (ocelot_port->bond != dev)
return NOTIFY_OK;
- err = ocelot_netdevice_changeupper(lower, info);
+ err = ocelot_netdevice_changeupper(lower, dev, info);
if (err)
return notifier_from_errno(err);
}
struct netdev_notifier_changeupper_info *info = ptr;
if (ocelot_netdevice_dev_check(dev))
- return ocelot_netdevice_changeupper(dev, info);
+ return ocelot_netdevice_changeupper(dev, dev, info);
if (netif_is_lag_master(dev))
return ocelot_netdevice_lag_changeupper(dev, info);
printk(version);
#endif
- i = pci_enable_device(pdev);
+ i = pcim_enable_device(pdev);
if (i) return i;
/* natsemi has a non-standard PM control register
ioaddr = ioremap(iostart, iosize);
if (!ioaddr) {
i = -ENOMEM;
- goto err_ioremap;
+ goto err_pci_request_regions;
}
/* Work around the dropped serial bit. */
err_register_netdev:
iounmap(ioaddr);
- err_ioremap:
- pci_release_regions(pdev);
-
err_pci_request_regions:
free_netdev(dev);
return i;
NATSEMI_REMOVE_FILE(pdev, dspcfg_workaround);
unregister_netdev (dev);
- pci_release_regions (pdev);
iounmap(ioaddr);
free_netdev (dev);
}
kfree(vdev->vpaths);
- /* we are safe to free it now */
- free_netdev(dev);
-
vxge_debug_init(vdev->level_trace, "%s: ethernet device unregistered",
buf);
vxge_debug_entryexit(vdev->level_trace, "%s: %s:%d Exiting...", buf,
__func__, __LINE__);
+
+ /* we are safe to free it now */
+ free_netdev(dev);
}
/*
nfp_fl_ct_clean_flow_entry(ct_entry);
kfree(ct_map_ent);
- /* If this is the last pre_ct_rule it means that it is
- * very likely that the nft table will be cleaned up next,
- * as this happens on the removal of the last act_ct flow.
- * However we cannot deregister the callback on the removal
- * of the last nft flow as this runs into a deadlock situation.
- * So deregister the callback on removal of the last pre_ct flow
- * and remove any remaining nft flow entries. We also cannot
- * save this state and delete the callback later since the
- * nft table would already have been freed at that time.
- */
if (!zt->pre_ct_count) {
- nf_flow_table_offload_del_cb(zt->nft,
- nfp_fl_ct_handle_nft_flow,
- zt);
zt->nft = NULL;
nfp_fl_ct_clean_nft_entries(zt);
}
nfp_ct_map_params);
nfp_fl_ct_clean_flow_entry(ct_map_ent->ct_entry);
kfree(ct_map_ent);
+ break;
default:
break;
}
/* Init to unknowns */
ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
+ ethtool_link_ksettings_add_link_mode(cmd, supported, Pause);
+ ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause);
cmd->base.port = PORT_OTHER;
cmd->base.speed = SPEED_UNKNOWN;
cmd->base.duplex = DUPLEX_UNKNOWN;
*/
};
-static void ionic_lif_rx_mode(struct ionic_lif *lif, unsigned int rx_mode);
+static void ionic_lif_rx_mode(struct ionic_lif *lif);
static int ionic_lif_addr_add(struct ionic_lif *lif, const u8 *addr);
static int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr);
static void ionic_link_status_check(struct ionic_lif *lif);
cur_moder = net_dim_get_rx_moderation(dim->mode, dim->profile_ix);
qcq = container_of(dim, struct ionic_qcq, dim);
new_coal = ionic_coal_usec_to_hw(qcq->q.lif->ionic, cur_moder.usec);
- qcq->intr.dim_coal_hw = new_coal ? new_coal : 1;
+ new_coal = new_coal ? new_coal : 1;
+
+ if (qcq->intr.dim_coal_hw != new_coal) {
+ unsigned int qi = qcq->cq.bound_q->index;
+ struct ionic_lif *lif = qcq->q.lif;
+
+ qcq->intr.dim_coal_hw = new_coal;
+
+ ionic_intr_coal_init(lif->ionic->idev.intr_ctrl,
+ lif->rxqcqs[qi]->intr.index,
+ qcq->intr.dim_coal_hw);
+ }
+
dim->state = DIM_START_MEASURE;
}
switch (w->type) {
case IONIC_DW_TYPE_RX_MODE:
- ionic_lif_rx_mode(lif, w->rx_mode);
+ ionic_lif_rx_mode(lif);
break;
case IONIC_DW_TYPE_RX_ADDR_ADD:
ionic_lif_addr_add(lif, w->addr);
return 0;
}
-static int ionic_lif_addr(struct ionic_lif *lif, const u8 *addr, bool add,
- bool can_sleep)
+static int ionic_lif_addr(struct ionic_lif *lif, const u8 *addr, bool add)
{
- struct ionic_deferred_work *work;
unsigned int nmfilters;
unsigned int nufilters;
lif->nucast--;
}
- if (!can_sleep) {
- work = kzalloc(sizeof(*work), GFP_ATOMIC);
- if (!work)
- return -ENOMEM;
- work->type = add ? IONIC_DW_TYPE_RX_ADDR_ADD :
- IONIC_DW_TYPE_RX_ADDR_DEL;
- memcpy(work->addr, addr, ETH_ALEN);
- netdev_dbg(lif->netdev, "deferred: rx_filter %s %pM\n",
- add ? "add" : "del", addr);
- ionic_lif_deferred_enqueue(&lif->deferred, work);
- } else {
- netdev_dbg(lif->netdev, "rx_filter %s %pM\n",
- add ? "add" : "del", addr);
- if (add)
- return ionic_lif_addr_add(lif, addr);
- else
- return ionic_lif_addr_del(lif, addr);
- }
+ netdev_dbg(lif->netdev, "rx_filter %s %pM\n",
+ add ? "add" : "del", addr);
+ if (add)
+ return ionic_lif_addr_add(lif, addr);
+ else
+ return ionic_lif_addr_del(lif, addr);
return 0;
}
static int ionic_addr_add(struct net_device *netdev, const u8 *addr)
{
- return ionic_lif_addr(netdev_priv(netdev), addr, ADD_ADDR, CAN_SLEEP);
-}
-
-static int ionic_ndo_addr_add(struct net_device *netdev, const u8 *addr)
-{
- return ionic_lif_addr(netdev_priv(netdev), addr, ADD_ADDR, CAN_NOT_SLEEP);
+ return ionic_lif_addr(netdev_priv(netdev), addr, ADD_ADDR);
}
static int ionic_addr_del(struct net_device *netdev, const u8 *addr)
{
- return ionic_lif_addr(netdev_priv(netdev), addr, DEL_ADDR, CAN_SLEEP);
+ return ionic_lif_addr(netdev_priv(netdev), addr, DEL_ADDR);
}
-static int ionic_ndo_addr_del(struct net_device *netdev, const u8 *addr)
+static void ionic_lif_rx_mode(struct ionic_lif *lif)
{
- return ionic_lif_addr(netdev_priv(netdev), addr, DEL_ADDR, CAN_NOT_SLEEP);
-}
-
-static void ionic_lif_rx_mode(struct ionic_lif *lif, unsigned int rx_mode)
-{
- struct ionic_admin_ctx ctx = {
- .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work),
- .cmd.rx_mode_set = {
- .opcode = IONIC_CMD_RX_MODE_SET,
- .lif_index = cpu_to_le16(lif->index),
- .rx_mode = cpu_to_le16(rx_mode),
- },
- };
+ struct net_device *netdev = lif->netdev;
+ unsigned int nfilters;
+ unsigned int nd_flags;
char buf[128];
- int err;
+ u16 rx_mode;
int i;
#define REMAIN(__x) (sizeof(buf) - (__x))
- i = scnprintf(buf, sizeof(buf), "rx_mode 0x%04x -> 0x%04x:",
- lif->rx_mode, rx_mode);
- if (rx_mode & IONIC_RX_MODE_F_UNICAST)
- i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_UNICAST");
- if (rx_mode & IONIC_RX_MODE_F_MULTICAST)
- i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_MULTICAST");
- if (rx_mode & IONIC_RX_MODE_F_BROADCAST)
- i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_BROADCAST");
- if (rx_mode & IONIC_RX_MODE_F_PROMISC)
- i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_PROMISC");
- if (rx_mode & IONIC_RX_MODE_F_ALLMULTI)
- i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_ALLMULTI");
- netdev_dbg(lif->netdev, "lif%d %s\n", lif->index, buf);
-
- err = ionic_adminq_post_wait(lif, &ctx);
- if (err)
- netdev_warn(lif->netdev, "set rx_mode 0x%04x failed: %d\n",
- rx_mode, err);
- else
- lif->rx_mode = rx_mode;
-}
+ mutex_lock(&lif->config_lock);
-static void ionic_set_rx_mode(struct net_device *netdev, bool can_sleep)
-{
- struct ionic_lif *lif = netdev_priv(netdev);
- struct ionic_deferred_work *work;
- unsigned int nfilters;
- unsigned int rx_mode;
+ /* grab the flags once for local use */
+ nd_flags = netdev->flags;
rx_mode = IONIC_RX_MODE_F_UNICAST;
- rx_mode |= (netdev->flags & IFF_MULTICAST) ? IONIC_RX_MODE_F_MULTICAST : 0;
- rx_mode |= (netdev->flags & IFF_BROADCAST) ? IONIC_RX_MODE_F_BROADCAST : 0;
- rx_mode |= (netdev->flags & IFF_PROMISC) ? IONIC_RX_MODE_F_PROMISC : 0;
- rx_mode |= (netdev->flags & IFF_ALLMULTI) ? IONIC_RX_MODE_F_ALLMULTI : 0;
+ rx_mode |= (nd_flags & IFF_MULTICAST) ? IONIC_RX_MODE_F_MULTICAST : 0;
+ rx_mode |= (nd_flags & IFF_BROADCAST) ? IONIC_RX_MODE_F_BROADCAST : 0;
+ rx_mode |= (nd_flags & IFF_PROMISC) ? IONIC_RX_MODE_F_PROMISC : 0;
+ rx_mode |= (nd_flags & IFF_ALLMULTI) ? IONIC_RX_MODE_F_ALLMULTI : 0;
/* sync unicast addresses
* next check to see if we're in an overflow state
* we remove our overflow flag and check the netdev flags
* to see if we can disable NIC PROMISC
*/
- if (can_sleep)
- __dev_uc_sync(netdev, ionic_addr_add, ionic_addr_del);
- else
- __dev_uc_sync(netdev, ionic_ndo_addr_add, ionic_ndo_addr_del);
+ __dev_uc_sync(netdev, ionic_addr_add, ionic_addr_del);
nfilters = le32_to_cpu(lif->identity->eth.max_ucast_filters);
if (netdev_uc_count(netdev) + 1 > nfilters) {
rx_mode |= IONIC_RX_MODE_F_PROMISC;
lif->uc_overflow = true;
} else if (lif->uc_overflow) {
lif->uc_overflow = false;
- if (!(netdev->flags & IFF_PROMISC))
+ if (!(nd_flags & IFF_PROMISC))
rx_mode &= ~IONIC_RX_MODE_F_PROMISC;
}
/* same for multicast */
- if (can_sleep)
- __dev_mc_sync(netdev, ionic_addr_add, ionic_addr_del);
- else
- __dev_mc_sync(netdev, ionic_ndo_addr_add, ionic_ndo_addr_del);
+ __dev_mc_sync(netdev, ionic_addr_add, ionic_addr_del);
nfilters = le32_to_cpu(lif->identity->eth.max_mcast_filters);
if (netdev_mc_count(netdev) > nfilters) {
rx_mode |= IONIC_RX_MODE_F_ALLMULTI;
lif->mc_overflow = true;
} else if (lif->mc_overflow) {
lif->mc_overflow = false;
- if (!(netdev->flags & IFF_ALLMULTI))
+ if (!(nd_flags & IFF_ALLMULTI))
rx_mode &= ~IONIC_RX_MODE_F_ALLMULTI;
}
+ i = scnprintf(buf, sizeof(buf), "rx_mode 0x%04x -> 0x%04x:",
+ lif->rx_mode, rx_mode);
+ if (rx_mode & IONIC_RX_MODE_F_UNICAST)
+ i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_UNICAST");
+ if (rx_mode & IONIC_RX_MODE_F_MULTICAST)
+ i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_MULTICAST");
+ if (rx_mode & IONIC_RX_MODE_F_BROADCAST)
+ i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_BROADCAST");
+ if (rx_mode & IONIC_RX_MODE_F_PROMISC)
+ i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_PROMISC");
+ if (rx_mode & IONIC_RX_MODE_F_ALLMULTI)
+ i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_ALLMULTI");
+ if (rx_mode & IONIC_RX_MODE_F_RDMA_SNIFFER)
+ i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_RDMA_SNIFFER");
+ netdev_dbg(netdev, "lif%d %s\n", lif->index, buf);
+
if (lif->rx_mode != rx_mode) {
- if (!can_sleep) {
- work = kzalloc(sizeof(*work), GFP_ATOMIC);
- if (!work) {
- netdev_err(lif->netdev, "rxmode change dropped\n");
- return;
- }
- work->type = IONIC_DW_TYPE_RX_MODE;
- work->rx_mode = rx_mode;
- netdev_dbg(lif->netdev, "deferred: rx_mode\n");
- ionic_lif_deferred_enqueue(&lif->deferred, work);
- } else {
- ionic_lif_rx_mode(lif, rx_mode);
+ struct ionic_admin_ctx ctx = {
+ .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work),
+ .cmd.rx_mode_set = {
+ .opcode = IONIC_CMD_RX_MODE_SET,
+ .lif_index = cpu_to_le16(lif->index),
+ },
+ };
+ int err;
+
+ ctx.cmd.rx_mode_set.rx_mode = cpu_to_le16(rx_mode);
+ err = ionic_adminq_post_wait(lif, &ctx);
+ if (err)
+ netdev_warn(netdev, "set rx_mode 0x%04x failed: %d\n",
+ rx_mode, err);
+ else
+ lif->rx_mode = rx_mode;
+ }
+
+ mutex_unlock(&lif->config_lock);
+}
+
+static void ionic_set_rx_mode(struct net_device *netdev, bool can_sleep)
+{
+ struct ionic_lif *lif = netdev_priv(netdev);
+ struct ionic_deferred_work *work;
+
+ if (!can_sleep) {
+ work = kzalloc(sizeof(*work), GFP_ATOMIC);
+ if (!work) {
+ netdev_err(lif->netdev, "rxmode change dropped\n");
+ return;
}
+ work->type = IONIC_DW_TYPE_RX_MODE;
+ netdev_dbg(lif->netdev, "deferred: rx_mode\n");
+ ionic_lif_deferred_enqueue(&lif->deferred, work);
+ } else {
+ ionic_lif_rx_mode(lif);
}
}
ionic_lif_qcq_deinit(lif, lif->notifyqcq);
ionic_lif_qcq_deinit(lif, lif->adminqcq);
+ mutex_destroy(&lif->config_lock);
mutex_destroy(&lif->queue_lock);
ionic_lif_reset(lif);
}
*/
if (!ether_addr_equal(ctx.comp.lif_getattr.mac,
netdev->dev_addr))
- ionic_lif_addr(lif, netdev->dev_addr, ADD_ADDR, CAN_SLEEP);
+ ionic_lif_addr(lif, netdev->dev_addr, ADD_ADDR);
} else {
/* Update the netdev mac with the device's mac */
memcpy(addr.sa_data, ctx.comp.lif_getattr.mac, netdev->addr_len);
netdev_dbg(lif->netdev, "adding station MAC addr %pM\n",
netdev->dev_addr);
- ionic_lif_addr(lif, netdev->dev_addr, ADD_ADDR, CAN_SLEEP);
+ ionic_lif_addr(lif, netdev->dev_addr, ADD_ADDR);
return 0;
}
lif->hw_index = le16_to_cpu(comp.hw_index);
mutex_init(&lif->queue_lock);
+ mutex_init(&lif->config_lock);
/* now that we have the hw_index we can figure out our doorbell page */
lif->dbid_count = le32_to_cpu(lif->ionic->ident.dev.ndbpgs_per_lif);
struct list_head list;
enum ionic_deferred_work_type type;
union {
- unsigned int rx_mode;
u8 addr[ETH_ALEN];
u8 fw_status;
};
unsigned int index;
unsigned int hw_index;
struct mutex queue_lock; /* lock for queue structures */
+ struct mutex config_lock; /* lock for config actions */
spinlock_t adminq_lock; /* lock for AdminQ operations */
struct ionic_qcq *adminqcq;
struct ionic_qcq *notifyqcq;
unsigned int nrxq_descs;
u32 rx_copybreak;
u64 rxq_features;
- unsigned int rx_mode;
+ u16 rx_mode;
u64 hw_features;
bool registered;
bool mc_overflow;
int ionic_lif_size(struct ionic *ionic);
#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
-int ionic_lif_hwstamp_replay(struct ionic_lif *lif);
+void ionic_lif_hwstamp_replay(struct ionic_lif *lif);
int ionic_lif_hwstamp_set(struct ionic_lif *lif, struct ifreq *ifr);
int ionic_lif_hwstamp_get(struct ionic_lif *lif, struct ifreq *ifr);
ktime_t ionic_lif_phc_ktime(struct ionic_lif *lif, u64 counter);
void ionic_lif_alloc_phc(struct ionic_lif *lif);
void ionic_lif_free_phc(struct ionic_lif *lif);
#else
-static inline int ionic_lif_hwstamp_replay(struct ionic_lif *lif)
-{
- return -EOPNOTSUPP;
-}
+static inline void ionic_lif_hwstamp_replay(struct ionic_lif *lif) {}
static inline int ionic_lif_hwstamp_set(struct ionic_lif *lif, struct ifreq *ifr)
{
struct hwtstamp_config config;
int err;
+ if (!lif->phc || !lif->phc->ptp)
+ return -EOPNOTSUPP;
+
if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
return -EFAULT;
return 0;
}
-int ionic_lif_hwstamp_replay(struct ionic_lif *lif)
+void ionic_lif_hwstamp_replay(struct ionic_lif *lif)
{
int err;
+ if (!lif->phc || !lif->phc->ptp)
+ return;
+
err = ionic_lif_hwstamp_set_ts_config(lif, NULL);
if (err)
netdev_info(lif->netdev, "hwstamp replay failed: %d\n", err);
-
- return err;
}
int ionic_lif_hwstamp_get(struct ionic_lif *lif, struct ifreq *ifr)
}
}
- if (likely(netdev->features & NETIF_F_RXCSUM)) {
- if (comp->csum_flags & IONIC_RXQ_COMP_CSUM_F_CALC) {
- skb->ip_summed = CHECKSUM_COMPLETE;
- skb->csum = (__force __wsum)le16_to_cpu(comp->csum);
- stats->csum_complete++;
- }
+ if (likely(netdev->features & NETIF_F_RXCSUM) &&
+ (comp->csum_flags & IONIC_RXQ_COMP_CSUM_F_CALC)) {
+ skb->ip_summed = CHECKSUM_COMPLETE;
+ skb->csum = (__force __wsum)le16_to_cpu(comp->csum);
+ stats->csum_complete++;
} else {
stats->csum_none++;
}
q->tail_idx = 0;
}
-static void ionic_dim_update(struct ionic_qcq *qcq)
+static void ionic_dim_update(struct ionic_qcq *qcq, int napi_mode)
{
struct dim_sample dim_sample;
struct ionic_lif *lif;
unsigned int qi;
+ u64 pkts, bytes;
if (!qcq->intr.dim_coal_hw)
return;
lif = qcq->q.lif;
qi = qcq->cq.bound_q->index;
- ionic_intr_coal_init(lif->ionic->idev.intr_ctrl,
- lif->rxqcqs[qi]->intr.index,
- qcq->intr.dim_coal_hw);
+ switch (napi_mode) {
+ case IONIC_LIF_F_TX_DIM_INTR:
+ pkts = lif->txqstats[qi].pkts;
+ bytes = lif->txqstats[qi].bytes;
+ break;
+ case IONIC_LIF_F_RX_DIM_INTR:
+ pkts = lif->rxqstats[qi].pkts;
+ bytes = lif->rxqstats[qi].bytes;
+ break;
+ default:
+ pkts = lif->txqstats[qi].pkts + lif->rxqstats[qi].pkts;
+ bytes = lif->txqstats[qi].bytes + lif->rxqstats[qi].bytes;
+ break;
+ }
dim_update_sample(qcq->cq.bound_intr->rearm_count,
- lif->txqstats[qi].pkts,
- lif->txqstats[qi].bytes,
- &dim_sample);
+ pkts, bytes, &dim_sample);
net_dim(&qcq->dim, dim_sample);
}
ionic_tx_service, NULL, NULL);
if (work_done < budget && napi_complete_done(napi, work_done)) {
- ionic_dim_update(qcq);
+ ionic_dim_update(qcq, IONIC_LIF_F_TX_DIM_INTR);
flags |= IONIC_INTR_CRED_UNMASK;
cq->bound_intr->rearm_count++;
}
ionic_rx_fill(cq->bound_q);
if (work_done < budget && napi_complete_done(napi, work_done)) {
- ionic_dim_update(qcq);
+ ionic_dim_update(qcq, IONIC_LIF_F_RX_DIM_INTR);
flags |= IONIC_INTR_CRED_UNMASK;
cq->bound_intr->rearm_count++;
}
ionic_rx_fill(rxcq->bound_q);
if (rx_work_done < budget && napi_complete_done(napi, rx_work_done)) {
- ionic_dim_update(qcq);
+ ionic_dim_update(qcq, 0);
flags |= IONIC_INTR_CRED_UNMASK;
rxcq->bound_intr->rearm_count++;
}
#define QEDE_SP_HW_ERR 4
#define QEDE_SP_ARFS_CONFIG 5
#define QEDE_SP_AER 7
+#define QEDE_SP_DISABLE 8
#ifdef CONFIG_RFS_ACCEL
int qede_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
int qede_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid)
{
struct qede_dev *edev = netdev_priv(dev);
- struct qede_vlan *vlan = NULL;
+ struct qede_vlan *vlan;
int rc = 0;
DP_VERBOSE(edev, NETIF_MSG_IFDOWN, "Removing vlan 0x%04x\n", vid);
if (vlan->vid == vid)
break;
- if (!vlan || (vlan->vid != vid)) {
+ if (list_entry_is_head(vlan, &edev->vlan_list, list)) {
DP_VERBOSE(edev, (NETIF_MSG_IFUP | NETIF_MSG_IFDOWN),
"Vlan isn't configured\n");
goto out;
struct qede_dev *edev = container_of(work, struct qede_dev,
sp_task.work);
+ /* Disable execution of this deferred work once
+ * qede removal is in progress, this stop any future
+ * scheduling of sp_task.
+ */
+ if (test_bit(QEDE_SP_DISABLE, &edev->sp_flags))
+ return;
+
/* The locking scheme depends on the specific flag:
* In case of QEDE_SP_RECOVERY, acquiring the RTNL lock is required to
* ensure that ongoing flows are ended and new ones are not started.
qede_rdma_dev_remove(edev, (mode == QEDE_REMOVE_RECOVERY));
if (mode != QEDE_REMOVE_RECOVERY) {
+ set_bit(QEDE_SP_DISABLE, &edev->sp_flags);
unregister_netdev(ndev);
cancel_delayed_work_sync(&edev->sp_task);
"driver lock acquired\n");
return 1;
}
- ssleep(1);
+ mdelay(1000);
} while (++i < 10);
netdev_err(qdev->ndev, "Timed out waiting for driver lock...\n");
if ((value & ISP_CONTROL_SR) == 0)
break;
- ssleep(1);
+ mdelay(1000);
} while ((--max_wait_time));
/*
ispControlStatus);
if ((value & ISP_CONTROL_FSR) == 0)
break;
- ssleep(1);
+ mdelay(1000);
} while ((--max_wait_time));
}
if (max_wait_time == 0)
put_device(&adpt->phydev->mdio.dev);
mdiobus_unregister(adpt->mii_bus);
- free_netdev(netdev);
if (adpt->phy.digital)
iounmap(adpt->phy.digital);
iounmap(adpt->phy.base);
+ free_netdev(netdev);
+
return 0;
}
new_bus->priv = tp;
new_bus->parent = &pdev->dev;
new_bus->irq[0] = PHY_MAC_INTERRUPT;
- snprintf(new_bus->id, MII_BUS_ID_SIZE, "r8169-%x", pci_dev_id(pdev));
+ snprintf(new_bus->id, MII_BUS_ID_SIZE, "r8169-%x-%x",
+ pci_domain_nr(pdev->bus), pci_dev_id(pdev));
new_bus->read = r8169_mdio_read_reg;
new_bus->write = r8169_mdio_write_reg;
/* The Ethernet AVB descriptor definitions. */
struct ravb_desc {
- __le16 ds; /* Descriptor size */
+ __le16 ds; /* Descriptor size */
u8 cc; /* Content control MSBs (reserved) */
u8 die_dt; /* Descriptor interrupt enable and type */
__le32 dptr; /* Descriptor pointer */
if (ravb_rx(ndev, "a, q))
goto out;
- /* Processing RX Descriptor Ring */
+ /* Processing TX Descriptor Ring */
spin_lock_irqsave(&priv->lock, flags);
/* Clear TX interrupt */
ravb_write(ndev, ~(mask | TIS_RESERVED), TIS);
* maximum size.
*/
tx_per_ev = EFX_MAX_EVQ_SIZE / EFX_TXQ_MAX_ENT(efx);
+ tx_per_ev = min(tx_per_ev, EFX_MAX_TXQ_PER_CHANNEL);
n_xdp_tx = num_possible_cpus();
n_xdp_ev = DIV_ROUND_UP(n_xdp_tx, tx_per_ev);
netif_err(efx, drv, efx->net_dev,
"Insufficient resources for %d XDP event queues (%d other channels, max %d)\n",
n_xdp_ev, n_channels, max_channels);
+ netif_err(efx, drv, efx->net_dev,
+ "XDP_TX and XDP_REDIRECT will not work on this interface");
efx->n_xdp_channels = 0;
efx->xdp_tx_per_channel = 0;
efx->xdp_tx_queue_count = 0;
netif_err(efx, drv, efx->net_dev,
"Insufficient resources for %d XDP TX queues (%d other channels, max VIs %d)\n",
n_xdp_tx, n_channels, efx->max_vis);
+ netif_err(efx, drv, efx->net_dev,
+ "XDP_TX and XDP_REDIRECT will not work on this interface");
efx->n_xdp_channels = 0;
efx->xdp_tx_per_channel = 0;
efx->xdp_tx_queue_count = 0;
} else {
efx->n_xdp_channels = n_xdp_ev;
- efx->xdp_tx_per_channel = EFX_MAX_TXQ_PER_CHANNEL;
+ efx->xdp_tx_per_channel = tx_per_ev;
efx->xdp_tx_queue_count = n_xdp_tx;
n_channels += n_xdp_ev;
netif_dbg(efx, drv, efx->net_dev,
if (efx_channel_is_xdp_tx(channel)) {
efx_for_each_channel_tx_queue(tx_queue, channel) {
tx_queue->queue = next_queue++;
- netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is XDP %u, HW %u\n",
- channel->channel, tx_queue->label,
- xdp_queue_number, tx_queue->queue);
+
/* We may have a few left-over XDP TX
* queues owing to xdp_tx_queue_count
* not dividing evenly by EFX_MAX_TXQ_PER_CHANNEL.
* We still allocate and probe those
* TXQs, but never use them.
*/
- if (xdp_queue_number < efx->xdp_tx_queue_count)
+ if (xdp_queue_number < efx->xdp_tx_queue_count) {
+ netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is XDP %u, HW %u\n",
+ channel->channel, tx_queue->label,
+ xdp_queue_number, tx_queue->queue);
efx->xdp_tx_queues[xdp_queue_number] = tx_queue;
- xdp_queue_number++;
+ xdp_queue_number++;
+ }
}
} else {
efx_for_each_channel_tx_queue(tx_queue, channel) {
}
}
}
- if (xdp_queue_number)
- efx->xdp_tx_queue_count = xdp_queue_number;
+ WARN_ON(xdp_queue_number != efx->xdp_tx_queue_count);
rc = netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels);
if (rc)
#endif
/* setup various bits in PCI command register */
- ret = pci_enable_device(pci_dev);
+ ret = pcim_enable_device(pci_dev);
if(ret) return ret;
i = dma_set_mask(&pci_dev->dev, DMA_BIT_MASK(32));
ioaddr = pci_iomap(pci_dev, 0, 0);
if (!ioaddr) {
ret = -ENOMEM;
- goto err_out_cleardev;
+ goto err_out;
}
sis_priv = netdev_priv(net_dev);
sis_priv->tx_ring_dma);
err_out_unmap:
pci_iounmap(pci_dev, ioaddr);
-err_out_cleardev:
- pci_release_regions(pci_dev);
err_out:
free_netdev(net_dev);
return ret;
sis_priv->tx_ring_dma);
pci_iounmap(pci_dev, sis_priv->ioaddr);
free_netdev(net_dev);
- pci_release_regions(pci_dev);
}
static int __maybe_unused sis900_suspend(struct device *dev)
{
struct plat_stmmacenet_data *plat;
struct stmmac_resources res;
- bool mdio = false;
- int ret, i;
struct device_node *np;
+ int ret, i, phy_mode;
+ bool mdio = false;
np = dev_of_node(&pdev->dev);
if (plat->bus_id < 0)
plat->bus_id = pci_dev_id(pdev);
- plat->phy_interface = device_get_phy_mode(&pdev->dev);
- if (plat->phy_interface < 0)
+ phy_mode = device_get_phy_mode(&pdev->dev);
+ if (phy_mode < 0)
dev_err(&pdev->dev, "phy_mode not found\n");
+ plat->phy_interface = phy_mode;
plat->interface = PHY_INTERFACE_MODE_GMII;
pci_set_master(pdev);
.config_l3_filter = dwmac4_config_l3_filter,
.config_l4_filter = dwmac4_config_l4_filter,
.est_configure = dwmac5_est_configure,
+ .est_irq_status = dwmac5_est_irq_status,
.fpe_configure = dwmac5_fpe_configure,
.fpe_send_mpacket = dwmac5_fpe_send_mpacket,
.fpe_irq_status = dwmac5_fpe_irq_status,
.config_l3_filter = dwmac4_config_l3_filter,
.config_l4_filter = dwmac4_config_l4_filter,
.est_configure = dwmac5_est_configure,
+ .est_irq_status = dwmac5_est_irq_status,
.fpe_configure = dwmac5_fpe_configure,
.fpe_send_mpacket = dwmac5_fpe_send_mpacket,
.fpe_irq_status = dwmac5_fpe_irq_status,
void stmmac_disable_tx_queue(struct stmmac_priv *priv, u32 queue);
void stmmac_enable_tx_queue(struct stmmac_priv *priv, u32 queue);
int stmmac_xsk_wakeup(struct net_device *dev, u32 queue, u32 flags);
+struct timespec64 stmmac_calc_tas_basetime(ktime_t old_base_time,
+ ktime_t current_time,
+ u64 cycle_time);
#if IS_ENABLED(CONFIG_STMMAC_SELFTESTS)
void stmmac_selftest_run(struct net_device *dev,
priv->plat->rx_queues_to_use, false);
stmmac_fpe_handshake(priv, false);
+ stmmac_fpe_stop_wq(priv);
}
priv->speed = SPEED_UNKNOWN;
struct device_node *np = pdev->dev.of_node;
struct plat_stmmacenet_data *plat;
struct stmmac_dma_cfg *dma_cfg;
+ int phy_mode;
void *ret;
int rc;
eth_zero_addr(mac);
}
- plat->phy_interface = device_get_phy_mode(&pdev->dev);
- if (plat->phy_interface < 0)
- return ERR_PTR(plat->phy_interface);
+ phy_mode = device_get_phy_mode(&pdev->dev);
+ if (phy_mode < 0)
+ return ERR_PTR(phy_mode);
+ plat->phy_interface = phy_mode;
plat->interface = stmmac_of_get_mac_mode(np);
if (plat->interface < 0)
plat->interface = plat->phy_interface;
u32 sec, nsec;
u32 quotient, reminder;
int neg_adj = 0;
- bool xmac;
+ bool xmac, est_rst = false;
+ int ret;
xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac;
sec = quotient;
nsec = reminder;
+ /* If EST is enabled, disabled it before adjust ptp time. */
+ if (priv->plat->est && priv->plat->est->enable) {
+ est_rst = true;
+ mutex_lock(&priv->plat->est->lock);
+ priv->plat->est->enable = false;
+ stmmac_est_configure(priv, priv->ioaddr, priv->plat->est,
+ priv->plat->clk_ptp_rate);
+ mutex_unlock(&priv->plat->est->lock);
+ }
+
spin_lock_irqsave(&priv->ptp_lock, flags);
stmmac_adjust_systime(priv, priv->ptpaddr, sec, nsec, neg_adj, xmac);
spin_unlock_irqrestore(&priv->ptp_lock, flags);
+ /* Caculate new basetime and re-configured EST after PTP time adjust. */
+ if (est_rst) {
+ struct timespec64 current_time, time;
+ ktime_t current_time_ns, basetime;
+ u64 cycle_time;
+
+ mutex_lock(&priv->plat->est->lock);
+ priv->ptp_clock_ops.gettime64(&priv->ptp_clock_ops, ¤t_time);
+ current_time_ns = timespec64_to_ktime(current_time);
+ time.tv_nsec = priv->plat->est->btr_reserve[0];
+ time.tv_sec = priv->plat->est->btr_reserve[1];
+ basetime = timespec64_to_ktime(time);
+ cycle_time = priv->plat->est->ctr[1] * NSEC_PER_SEC +
+ priv->plat->est->ctr[0];
+ time = stmmac_calc_tas_basetime(basetime,
+ current_time_ns,
+ cycle_time);
+
+ priv->plat->est->btr[0] = (u32)time.tv_nsec;
+ priv->plat->est->btr[1] = (u32)time.tv_sec;
+ priv->plat->est->enable = true;
+ ret = stmmac_est_configure(priv, priv->ioaddr, priv->plat->est,
+ priv->plat->clk_ptp_rate);
+ mutex_unlock(&priv->plat->est->lock);
+ if (ret)
+ netdev_err(priv->dev, "failed to configure EST\n");
+ }
+
return 0;
}
return ret;
}
+struct timespec64 stmmac_calc_tas_basetime(ktime_t old_base_time,
+ ktime_t current_time,
+ u64 cycle_time)
+{
+ struct timespec64 time;
+
+ if (ktime_after(old_base_time, current_time)) {
+ time = ktime_to_timespec64(old_base_time);
+ } else {
+ s64 n;
+ ktime_t base_time;
+
+ n = div64_s64(ktime_sub_ns(current_time, old_base_time),
+ cycle_time);
+ base_time = ktime_add_ns(old_base_time,
+ (n + 1) * cycle_time);
+
+ time = ktime_to_timespec64(base_time);
+ }
+
+ return time;
+}
+
static int tc_setup_taprio(struct stmmac_priv *priv,
struct tc_taprio_qopt_offload *qopt)
{
u32 size, wid = priv->dma_cap.estwid, dep = priv->dma_cap.estdep;
struct plat_stmmacenet_data *plat = priv->plat;
- struct timespec64 time, current_time;
+ struct timespec64 time, current_time, qopt_time;
ktime_t current_time_ns;
bool fpe = false;
int i, ret = 0;
GFP_KERNEL);
if (!plat->est)
return -ENOMEM;
+
+ mutex_init(&priv->plat->est->lock);
} else {
memset(plat->est, 0, sizeof(*plat->est));
}
size = qopt->num_entries;
+ mutex_lock(&priv->plat->est->lock);
priv->plat->est->gcl_size = size;
priv->plat->est->enable = qopt->enable;
+ mutex_unlock(&priv->plat->est->lock);
for (i = 0; i < size; i++) {
s64 delta_ns = qopt->entries[i].interval;
priv->plat->est->gcl[i] = delta_ns | (gates << wid);
}
+ mutex_lock(&priv->plat->est->lock);
/* Adjust for real system time */
priv->ptp_clock_ops.gettime64(&priv->ptp_clock_ops, ¤t_time);
current_time_ns = timespec64_to_ktime(current_time);
- if (ktime_after(qopt->base_time, current_time_ns)) {
- time = ktime_to_timespec64(qopt->base_time);
- } else {
- ktime_t base_time;
- s64 n;
-
- n = div64_s64(ktime_sub_ns(current_time_ns, qopt->base_time),
- qopt->cycle_time);
- base_time = ktime_add_ns(qopt->base_time,
- (n + 1) * qopt->cycle_time);
-
- time = ktime_to_timespec64(base_time);
- }
+ time = stmmac_calc_tas_basetime(qopt->base_time, current_time_ns,
+ qopt->cycle_time);
priv->plat->est->btr[0] = (u32)time.tv_nsec;
priv->plat->est->btr[1] = (u32)time.tv_sec;
+ qopt_time = ktime_to_timespec64(qopt->base_time);
+ priv->plat->est->btr_reserve[0] = (u32)qopt_time.tv_nsec;
+ priv->plat->est->btr_reserve[1] = (u32)qopt_time.tv_sec;
+
ctr = qopt->cycle_time;
priv->plat->est->ctr[0] = do_div(ctr, NSEC_PER_SEC);
priv->plat->est->ctr[1] = (u32)ctr;
- if (fpe && !priv->dma_cap.fpesel)
+ if (fpe && !priv->dma_cap.fpesel) {
+ mutex_unlock(&priv->plat->est->lock);
return -EOPNOTSUPP;
+ }
/* Actual FPE register configuration will be done after FPE handshake
* is success.
ret = stmmac_est_configure(priv, priv->ioaddr, priv->plat->est,
priv->plat->clk_ptp_rate);
+ mutex_unlock(&priv->plat->est->lock);
if (ret) {
netdev_err(priv->dev, "failed to configure EST\n");
goto disable;
return 0;
disable:
+ mutex_lock(&priv->plat->est->lock);
priv->plat->est->enable = false;
stmmac_est_configure(priv, priv->ioaddr, priv->plat->est,
priv->plat->clk_ptp_rate);
+ mutex_unlock(&priv->plat->est->lock);
priv->plat->fpe_cfg->enable = false;
stmmac_fpe_configure(priv, priv->ioaddr,
err = niu_pci_vpd_scan_props(np, here, end);
if (err < 0)
return err;
+ /* ret == 1 is not an error */
if (err == 1)
- return -EINVAL;
+ return 0;
}
return 0;
}
for (i = 1; i <= common->port_num; i++) {
struct am65_cpsw_port *port = am65_common_get_port(common, i);
- struct am65_cpsw_ndev_priv *priv = am65_ndev_to_priv(port->ndev);
+ struct am65_cpsw_ndev_priv *priv;
+ if (!port->ndev)
+ continue;
+
+ priv = am65_ndev_to_priv(port->ndev);
priv->offload_fwd_mark = set_val;
}
}
pci_release_regions(pdev);
#endif
- free_netdev(dev);
-
cancel_work_sync(&priv->tlan_tqueue);
+ free_netdev(dev);
}
static void tlan_start(struct net_device *dev)
#include <linux/kernel.h>
#include <linux/ptp_clock_kernel.h>
#include <linux/soc/ixp4xx/cpu.h>
+#include <linux/module.h>
+#include <mach/ixp4xx-regs.h>
#include "ixp46x_ts.h"
release_mem_region(start, len);
err_out_kfree:
- free_netdev(dev);
-
pr_err("%s: initialization failure, aborting!\n", fp->name);
+ free_netdev(dev);
return ret;
}
u64_stats_init(&mhi_netdev->stats.tx_syncp);
/* Start MHI channels */
- err = mhi_prepare_for_transfer(mhi_dev);
+ err = mhi_prepare_for_transfer(mhi_dev, 0);
if (err)
goto out_err;
u32 *mykey, u32 *mysalt)
{
const char aes_gcm_name[] = "rfc4106(gcm(aes))";
- struct net_device *dev = xs->xso.dev;
+ struct net_device *dev = xs->xso.real_dev;
unsigned char *key_data;
char *alg_name = NULL;
int key_len;
u16 sa_idx;
int ret;
- dev = xs->xso.dev;
+ dev = xs->xso.real_dev;
ns = netdev_priv(dev);
ipsec = &ns->ipsec;
static void nsim_ipsec_del_sa(struct xfrm_state *xs)
{
- struct netdevsim *ns = netdev_priv(xs->xso.dev);
+ struct netdevsim *ns = netdev_priv(xs->xso.real_dev);
struct nsim_ipsec *ipsec = &ns->ipsec;
u16 sa_idx;
static bool nsim_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
{
- struct netdevsim *ns = netdev_priv(xs->xso.dev);
+ struct netdevsim *ns = netdev_priv(xs->xso.real_dev);
struct nsim_ipsec *ipsec = &ns->ipsec;
ipsec->ok++;
if (phydev->dev_flags & PHY_BRCM_DIS_TXCRXC_NOENRGY) {
if (BRCM_PHY_MODEL(phydev) == PHY_ID_BCM54210E ||
BRCM_PHY_MODEL(phydev) == PHY_ID_BCM54810 ||
- BRCM_PHY_MODEL(phydev) == PHY_ID_BCM54210E)
+ BRCM_PHY_MODEL(phydev) == PHY_ID_BCM54811)
val |= BCM54XX_SHD_SCR3_RXCTXC_DIS;
else
val |= BCM54XX_SHD_SCR3_TRDDAPD;
/* Temperature read register (88E2110 only) */
MV_PCS_TEMP = 0x8042,
+ /* Number of ports on the device */
+ MV_PCS_PORT_INFO = 0xd00d,
+ MV_PCS_PORT_INFO_NPORTS_MASK = 0x0380,
+ MV_PCS_PORT_INFO_NPORTS_SHIFT = 7,
+
/* These registers appear at 0x800X and 0xa00X - the 0xa00X control
* registers appear to set themselves to the 0x800X when AN is
* restarted, but status registers appear readable from either.
#endif
};
+static int mv3310_get_number_of_ports(struct phy_device *phydev)
+{
+ int ret;
+
+ ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MV_PCS_PORT_INFO);
+ if (ret < 0)
+ return ret;
+
+ ret &= MV_PCS_PORT_INFO_NPORTS_MASK;
+ ret >>= MV_PCS_PORT_INFO_NPORTS_SHIFT;
+
+ return ret + 1;
+}
+
+static int mv3310_match_phy_device(struct phy_device *phydev)
+{
+ return mv3310_get_number_of_ports(phydev) == 1;
+}
+
+static int mv3340_match_phy_device(struct phy_device *phydev)
+{
+ return mv3310_get_number_of_ports(phydev) == 4;
+}
+
static int mv211x_match_phy_device(struct phy_device *phydev, bool has_5g)
{
int val;
static struct phy_driver mv3310_drivers[] = {
{
.phy_id = MARVELL_PHY_ID_88X3310,
- .phy_id_mask = MARVELL_PHY_ID_88X33X0_MASK,
+ .phy_id_mask = MARVELL_PHY_ID_MASK,
+ .match_phy_device = mv3310_match_phy_device,
.name = "mv88x3310",
.driver_data = &mv3310_type,
.get_features = mv3310_get_features,
.set_loopback = genphy_c45_loopback,
},
{
- .phy_id = MARVELL_PHY_ID_88X3340,
- .phy_id_mask = MARVELL_PHY_ID_88X33X0_MASK,
+ .phy_id = MARVELL_PHY_ID_88X3310,
+ .phy_id_mask = MARVELL_PHY_ID_MASK,
+ .match_phy_device = mv3340_match_phy_device,
.name = "mv88x3340",
.driver_data = &mv3340_type,
.get_features = mv3310_get_features,
module_phy_driver(mv3310_drivers);
static struct mdio_device_id __maybe_unused mv3310_tbl[] = {
- { MARVELL_PHY_ID_88X3310, MARVELL_PHY_ID_88X33X0_MASK },
- { MARVELL_PHY_ID_88X3340, MARVELL_PHY_ID_88X33X0_MASK },
+ { MARVELL_PHY_ID_88X3310, MARVELL_PHY_ID_MASK },
{ MARVELL_PHY_ID_88E2110, MARVELL_PHY_ID_MASK },
{ },
};
}
static int ksz8051_ksz8795_match_phy_device(struct phy_device *phydev,
- const u32 ksz_phy_id)
+ const bool ksz_8051)
{
int ret;
- if ((phydev->phy_id & MICREL_PHY_ID_MASK) != ksz_phy_id)
+ if ((phydev->phy_id & MICREL_PHY_ID_MASK) != PHY_ID_KSZ8051)
return 0;
ret = phy_read(phydev, MII_BMSR);
* the switch does not.
*/
ret &= BMSR_ERCAP;
- if (ksz_phy_id == PHY_ID_KSZ8051)
+ if (ksz_8051)
return ret;
else
return !ret;
static int ksz8051_match_phy_device(struct phy_device *phydev)
{
- return ksz8051_ksz8795_match_phy_device(phydev, PHY_ID_KSZ8051);
+ return ksz8051_ksz8795_match_phy_device(phydev, true);
}
static int ksz8081_config_init(struct phy_device *phydev)
static int ksz8795_match_phy_device(struct phy_device *phydev)
{
- return ksz8051_ksz8795_match_phy_device(phydev, PHY_ID_KSZ87XX);
+ return ksz8051_ksz8795_match_phy_device(phydev, false);
}
static int ksz9021_load_values_from_of(struct phy_device *phydev,
return ret;
}
+ phy_suspend(priv->phydev);
priv->phydev->mac_managed_pm = 1;
phy_attached_info(priv->phydev);
hso_net_init);
if (!net) {
dev_err(&interface->dev, "Unable to create ethernet device\n");
- goto exit;
+ goto err_hso_dev;
}
hso_net = netdev_priv(net);
USB_DIR_IN);
if (!hso_net->in_endp) {
dev_err(&interface->dev, "Can't find BULK IN endpoint\n");
- goto exit;
+ goto err_net;
}
hso_net->out_endp = hso_get_ep(interface, USB_ENDPOINT_XFER_BULK,
USB_DIR_OUT);
if (!hso_net->out_endp) {
dev_err(&interface->dev, "Can't find BULK OUT endpoint\n");
- goto exit;
+ goto err_net;
}
SET_NETDEV_DEV(net, &interface->dev);
SET_NETDEV_DEVTYPE(net, &hso_type);
for (i = 0; i < MUX_BULK_RX_BUF_COUNT; i++) {
hso_net->mux_bulk_rx_urb_pool[i] = usb_alloc_urb(0, GFP_KERNEL);
if (!hso_net->mux_bulk_rx_urb_pool[i])
- goto exit;
+ goto err_mux_bulk_rx;
hso_net->mux_bulk_rx_buf_pool[i] = kzalloc(MUX_BULK_RX_BUF_SIZE,
GFP_KERNEL);
if (!hso_net->mux_bulk_rx_buf_pool[i])
- goto exit;
+ goto err_mux_bulk_rx;
}
hso_net->mux_bulk_tx_urb = usb_alloc_urb(0, GFP_KERNEL);
if (!hso_net->mux_bulk_tx_urb)
- goto exit;
+ goto err_mux_bulk_rx;
hso_net->mux_bulk_tx_buf = kzalloc(MUX_BULK_TX_BUF_SIZE, GFP_KERNEL);
if (!hso_net->mux_bulk_tx_buf)
- goto exit;
+ goto err_free_tx_urb;
add_net_device(hso_dev);
result = register_netdev(net);
if (result) {
dev_err(&interface->dev, "Failed to register device\n");
- goto exit;
+ goto err_free_tx_buf;
}
hso_log_port(hso_dev);
hso_create_rfkill(hso_dev, interface);
return hso_dev;
-exit:
- hso_free_net_device(hso_dev, true);
+
+err_free_tx_buf:
+ remove_net_device(hso_dev);
+ kfree(hso_net->mux_bulk_tx_buf);
+err_free_tx_urb:
+ usb_free_urb(hso_net->mux_bulk_tx_urb);
+err_mux_bulk_rx:
+ for (i = 0; i < MUX_BULK_RX_BUF_COUNT; i++) {
+ usb_free_urb(hso_net->mux_bulk_rx_urb_pool[i]);
+ kfree(hso_net->mux_bulk_rx_buf_pool[i]);
+ }
+err_net:
+ free_netdev(net);
+err_hso_dev:
+ kfree(hso_dev);
return NULL;
}
{
struct phy_device *phydev = dev->net->phydev;
struct ethtool_link_ksettings ecmd;
- int ladv, radv, ret;
+ int ladv, radv, ret, link;
u32 buf;
/* clear LAN78xx interrupt status */
if (unlikely(ret < 0))
return -EIO;
+ mutex_lock(&phydev->lock);
phy_read_status(phydev);
+ link = phydev->link;
+ mutex_unlock(&phydev->lock);
- if (!phydev->link && dev->link_on) {
+ if (!link && dev->link_on) {
dev->link_on = false;
/* reset MAC */
return -EIO;
del_timer(&dev->stat_monitor);
- } else if (phydev->link && !dev->link_on) {
+ } else if (link && !dev->link_on) {
dev->link_on = true;
phy_ethtool_ksettings_get(phydev, &ecmd);
static u32 lan78xx_get_link(struct net_device *net)
{
+ u32 link;
+
+ mutex_lock(&net->phydev->lock);
phy_read_status(net->phydev);
+ link = net->phydev->link;
+ mutex_unlock(&net->phydev->lock);
- return net->phydev->link;
+ return link;
}
static void lan78xx_get_drvinfo(struct net_device *net,
// SPDX-License-Identifier: GPL-2.0-only
/*
- * Copyright (c) 1999-2013 Petko Manolov (petkan@nucleusys.com)
+ * Copyright (c) 1999-2021 Petko Manolov (petkan@nucleusys.com)
*
- * ChangeLog:
- * .... Most of the time spent on reading sources & docs.
- * v0.2.x First official release for the Linux kernel.
- * v0.3.0 Beutified and structured, some bugs fixed.
- * v0.3.x URBifying bulk requests and bugfixing. First relatively
- * stable release. Still can touch device's registers only
- * from top-halves.
- * v0.4.0 Control messages remained unurbified are now URBs.
- * Now we can touch the HW at any time.
- * v0.4.9 Control urbs again use process context to wait. Argh...
- * Some long standing bugs (enable_net_traffic) fixed.
- * Also nasty trick about resubmiting control urb from
- * interrupt context used. Please let me know how it
- * behaves. Pegasus II support added since this version.
- * TODO: suppressing HCD warnings spewage on disconnect.
- * v0.4.13 Ethernet address is now set at probe(), not at open()
- * time as this seems to break dhcpd.
- * v0.5.0 branch to 2.5.x kernels
- * v0.5.1 ethtool support added
- * v0.5.5 rx socket buffers are in a pool and the their allocation
- * is out of the interrupt routine.
- * ...
- * v0.9.3 simplified [get|set]_register(s), async update registers
- * logic revisited, receive skb_pool removed.
*/
#include <linux/sched.h>
/*
* Version Information
*/
-#define DRIVER_VERSION "v0.9.3 (2013/04/25)"
#define DRIVER_AUTHOR "Petko Manolov <petkan@nucleusys.com>"
#define DRIVER_DESC "Pegasus/Pegasus II USB Ethernet driver"
static int set_registers(pegasus_t *pegasus, __u16 indx, __u16 size,
const void *data)
{
- return usb_control_msg_send(pegasus->usb, 0, PEGASUS_REQ_SET_REGS,
+ int ret;
+
+ ret = usb_control_msg_send(pegasus->usb, 0, PEGASUS_REQ_SET_REGS,
PEGASUS_REQT_WRITE, 0, indx, data, size,
1000, GFP_NOIO);
+ if (ret < 0)
+ netif_dbg(pegasus, drv, pegasus->net, "%s failed with %d\n", __func__, ret);
+
+ return ret;
}
/*
static int set_register(pegasus_t *pegasus, __u16 indx, __u8 data)
{
void *buf = &data;
+ int ret;
- return usb_control_msg_send(pegasus->usb, 0, PEGASUS_REQ_SET_REG,
+ ret = usb_control_msg_send(pegasus->usb, 0, PEGASUS_REQ_SET_REG,
PEGASUS_REQT_WRITE, data, indx, buf, 1,
1000, GFP_NOIO);
+ if (ret < 0)
+ netif_dbg(pegasus, drv, pegasus->net, "%s failed with %d\n", __func__, ret);
+
+ return ret;
}
static int update_eth_regs_async(pegasus_t *pegasus)
static int __mii_op(pegasus_t *p, __u8 phy, __u8 indx, __u16 *regd, __u8 cmd)
{
- int i;
- __u8 data[4] = { phy, 0, 0, indx };
+ int i, ret;
__le16 regdi;
- int ret = -ETIMEDOUT;
+ __u8 data[4] = { phy, 0, 0, indx };
if (cmd & PHY_WRITE) {
__le16 *t = (__le16 *) & data[1];
if (data[0] & PHY_DONE)
break;
}
- if (i >= REG_TIMEOUT)
+ if (i >= REG_TIMEOUT) {
+ ret = -ETIMEDOUT;
goto fail;
+ }
if (cmd & PHY_READ) {
ret = get_registers(p, PhyData, 2, ®di);
+ if (ret < 0)
+ goto fail;
*regd = le16_to_cpu(regdi);
- return ret;
}
return 0;
fail:
static int mdio_read(struct net_device *dev, int phy_id, int loc)
{
pegasus_t *pegasus = netdev_priv(dev);
+ int ret;
u16 res;
- read_mii_word(pegasus, phy_id, loc, &res);
+ ret = read_mii_word(pegasus, phy_id, loc, &res);
+ if (ret < 0)
+ return ret;
+
return (int)res;
}
static int read_eprom_word(pegasus_t *pegasus, __u8 index, __u16 *retdata)
{
- int i;
- __u8 tmp = 0;
+ int ret, i;
__le16 retdatai;
- int ret;
+ __u8 tmp = 0;
set_register(pegasus, EpromCtrl, 0);
set_register(pegasus, EpromOffset, index);
for (i = 0; i < REG_TIMEOUT; i++) {
ret = get_registers(pegasus, EpromCtrl, 1, &tmp);
+ if (ret < 0)
+ goto fail;
if (tmp & EPROM_DONE)
break;
- if (ret == -ESHUTDOWN)
- goto fail;
}
- if (i >= REG_TIMEOUT)
+ if (i >= REG_TIMEOUT) {
+ ret = -ETIMEDOUT;
goto fail;
+ }
ret = get_registers(pegasus, EpromData, 2, &retdatai);
+ if (ret < 0)
+ goto fail;
*retdata = le16_to_cpu(retdatai);
return ret;
fail:
- netif_warn(pegasus, drv, pegasus->net, "%s failed\n", __func__);
- return -ETIMEDOUT;
+ netif_dbg(pegasus, drv, pegasus->net, "%s failed\n", __func__);
+ return ret;
}
#ifdef PEGASUS_WRITE_EEPROM
return ret;
fail:
- netif_warn(pegasus, drv, pegasus->net, "%s failed\n", __func__);
+ netif_dbg(pegasus, drv, pegasus->net, "%s failed\n", __func__);
return -ETIMEDOUT;
}
-#endif /* PEGASUS_WRITE_EEPROM */
+#endif /* PEGASUS_WRITE_EEPROM */
static inline int get_node_id(pegasus_t *pegasus, u8 *id)
{
return;
err:
eth_hw_addr_random(pegasus->net);
- dev_info(&pegasus->intf->dev, "software assigned MAC address.\n");
+ netif_dbg(pegasus, drv, pegasus->net, "software assigned MAC address.\n");
return;
}
static inline int reset_mac(pegasus_t *pegasus)
{
+ int ret, i;
__u8 data = 0x8;
- int i;
set_register(pegasus, EthCtrl1, data);
for (i = 0; i < REG_TIMEOUT; i++) {
- get_registers(pegasus, EthCtrl1, 1, &data);
+ ret = get_registers(pegasus, EthCtrl1, 1, &data);
+ if (ret < 0)
+ goto fail;
if (~data & 0x08) {
if (loopback)
break;
}
if (usb_dev_id[pegasus->dev_index].vendor == VENDOR_ELCON) {
__u16 auxmode;
- read_mii_word(pegasus, 3, 0x1b, &auxmode);
+ ret = read_mii_word(pegasus, 3, 0x1b, &auxmode);
+ if (ret < 0)
+ goto fail;
auxmode |= 4;
write_mii_word(pegasus, 3, 0x1b, &auxmode);
}
return 0;
+fail:
+ netif_dbg(pegasus, drv, pegasus->net, "%s failed\n", __func__);
+ return ret;
}
static int enable_net_traffic(struct net_device *dev, struct usb_device *usb)
{
- __u16 linkpart;
- __u8 data[4];
pegasus_t *pegasus = netdev_priv(dev);
int ret;
+ __u16 linkpart;
+ __u8 data[4];
- read_mii_word(pegasus, pegasus->phy, MII_LPA, &linkpart);
+ ret = read_mii_word(pegasus, pegasus->phy, MII_LPA, &linkpart);
+ if (ret < 0)
+ goto fail;
data[0] = 0xc8; /* TX & RX enable, append status, no CRC */
data[1] = 0;
if (linkpart & (ADVERTISE_100FULL | ADVERTISE_10FULL))
usb_dev_id[pegasus->dev_index].vendor == VENDOR_LINKSYS2 ||
usb_dev_id[pegasus->dev_index].vendor == VENDOR_DLINK) {
u16 auxmode;
- read_mii_word(pegasus, 0, 0x1b, &auxmode);
+ ret = read_mii_word(pegasus, 0, 0x1b, &auxmode);
+ if (ret < 0)
+ goto fail;
auxmode |= 4;
write_mii_word(pegasus, 0, 0x1b, &auxmode);
}
+ return 0;
+fail:
+ netif_dbg(pegasus, drv, pegasus->net, "%s failed\n", __func__);
return ret;
}
{
pegasus_t *pegasus = urb->context;
struct net_device *net;
+ u8 *buf = urb->transfer_buffer;
int rx_status, count = urb->actual_length;
int status = urb->status;
- u8 *buf = urb->transfer_buffer;
__u16 pkt_len;
if (!pegasus)
set_registers(pegasus, EthCtrl0, sizeof(tmp), &tmp);
}
-static inline void get_interrupt_interval(pegasus_t *pegasus)
+static inline int get_interrupt_interval(pegasus_t *pegasus)
{
u16 data;
u8 interval;
+ int ret;
+
+ ret = read_eprom_word(pegasus, 4, &data);
+ if (ret < 0)
+ return ret;
- read_eprom_word(pegasus, 4, &data);
interval = data >> 8;
if (pegasus->usb->speed != USB_SPEED_HIGH) {
if (interval < 0x80) {
}
}
pegasus->intr_interval = interval;
+
+ return 0;
}
static void set_carrier(struct net_device *net)
pegasus_t *pegasus = netdev_priv(dev);
strlcpy(info->driver, driver_name, sizeof(info->driver));
- strlcpy(info->version, DRIVER_VERSION, sizeof(info->version));
usb_make_path(pegasus->usb, info->bus_info, sizeof(info->bus_info));
}
data[0] = pegasus->phy;
fallthrough;
case SIOCDEVPRIVATE + 1:
- read_mii_word(pegasus, data[0], data[1] & 0x1f, &data[3]);
- res = 0;
+ res = read_mii_word(pegasus, data[0], data[1] & 0x1f, &data[3]);
break;
case SIOCDEVPRIVATE + 2:
if (!capable(CAP_NET_ADMIN))
static __u8 mii_phy_probe(pegasus_t *pegasus)
{
- int i;
+ int i, ret;
__u16 tmp;
for (i = 0; i < 32; i++) {
- read_mii_word(pegasus, i, MII_BMSR, &tmp);
+ ret = read_mii_word(pegasus, i, MII_BMSR, &tmp);
+ if (ret < 0)
+ goto fail;
if (tmp == 0 || tmp == 0xffff || (tmp & BMSR_MEDIA) == 0)
continue;
else
return i;
}
-
+fail:
return 0xff;
}
static inline void setup_pegasus_II(pegasus_t *pegasus)
{
+ int ret;
__u8 data = 0xa5;
set_register(pegasus, Reg1d, 0);
set_register(pegasus, Reg7b, 2);
set_register(pegasus, 0x83, data);
- get_registers(pegasus, 0x83, 1, &data);
+ ret = get_registers(pegasus, 0x83, 1, &data);
+ if (ret < 0)
+ goto fail;
if (data == 0xa5)
pegasus->chip = 0x8513;
set_register(pegasus, Reg81, 6);
else
set_register(pegasus, Reg81, 2);
+
+ return;
+fail:
+ netif_dbg(pegasus, drv, pegasus->net, "%s failed\n", __func__);
}
static void check_carrier(struct work_struct *work)
| NETIF_MSG_PROBE | NETIF_MSG_LINK);
pegasus->features = usb_dev_id[dev_index].private;
- get_interrupt_interval(pegasus);
+ res = get_interrupt_interval(pegasus);
+ if (res)
+ goto out2;
if (reset_mac(pegasus)) {
dev_err(&intf->dev, "can't reset MAC\n");
res = -EIO;
static int __init pegasus_init(void)
{
- pr_info("%s: %s, " DRIVER_DESC "\n", driver_name, DRIVER_VERSION);
+ pr_info("%s: " DRIVER_DESC "\n", driver_name);
if (devid)
parse_id(devid);
return usb_register(&pegasus_driver);
rtl8152_set_speed(struct r8152 *tp, u8 autoneg, u32 speed, u8 duplex,
u32 advertising);
-static int rtl8152_set_mac_address(struct net_device *netdev, void *p)
+static int __rtl8152_set_mac_address(struct net_device *netdev, void *p,
+ bool in_resume)
{
struct r8152 *tp = netdev_priv(netdev);
struct sockaddr *addr = p;
if (!is_valid_ether_addr(addr->sa_data))
goto out1;
- ret = usb_autopm_get_interface(tp->intf);
- if (ret < 0)
- goto out1;
+ if (!in_resume) {
+ ret = usb_autopm_get_interface(tp->intf);
+ if (ret < 0)
+ goto out1;
+ }
mutex_lock(&tp->control);
mutex_unlock(&tp->control);
- usb_autopm_put_interface(tp->intf);
+ if (!in_resume)
+ usb_autopm_put_interface(tp->intf);
out1:
return ret;
}
+static int rtl8152_set_mac_address(struct net_device *netdev, void *p)
+{
+ return __rtl8152_set_mac_address(netdev, p, false);
+}
+
/* Devices containing proper chips can support a persistent
* host system provided MAC address.
* Examples of this are Dell TB15 and Dell WD15 docks
return ret;
}
-static int set_ethernet_addr(struct r8152 *tp)
+static int set_ethernet_addr(struct r8152 *tp, bool in_resume)
{
struct net_device *dev = tp->netdev;
struct sockaddr sa;
if (tp->version == RTL_VER_01)
ether_addr_copy(dev->dev_addr, sa.sa_data);
else
- ret = rtl8152_set_mac_address(dev, &sa);
+ ret = __rtl8152_set_mac_address(dev, &sa, in_resume);
return ret;
}
tp->rtl_ops.down(tp);
mutex_unlock(&tp->control);
+ }
+ if (!res)
usb_autopm_put_interface(tp->intf);
- }
free_all_mem(tp);
clear_bit(SELECTIVE_SUSPEND, &tp->flags);
tp->rtl_ops.init(tp);
queue_delayed_work(system_long_wq, &tp->hw_phy_work, 0);
- set_ethernet_addr(tp);
+ set_ethernet_addr(tp, true);
return rtl8152_resume(intf);
}
tp->rtl_fw.retry = true;
#endif
queue_delayed_work(system_long_wq, &tp->hw_phy_work, 0);
- set_ethernet_addr(tp);
+ set_ethernet_addr(tp, false);
usb_set_intfdata(intf, tp);
{
struct scatterlist *sgs[4], hdr, stat;
unsigned out_num = 0, tmp;
+ int ret;
/* Caller should know better */
BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ));
sgs[out_num] = &stat;
BUG_ON(out_num + 1 > ARRAY_SIZE(sgs));
- virtqueue_add_sgs(vi->cvq, sgs, out_num, 1, vi, GFP_ATOMIC);
+ ret = virtqueue_add_sgs(vi->cvq, sgs, out_num, 1, vi, GFP_ATOMIC);
+ if (ret < 0) {
+ dev_warn(&vi->vdev->dev,
+ "Failed to add sgs for command vq: %d\n.", ret);
+ return false;
+ }
if (unlikely(!virtqueue_kick(vi->cvq)))
return vi->ctrl->status == VIRTIO_NET_OK;
/*
* Linux driver for VMware's vmxnet3 ethernet NIC.
*
- * Copyright (C) 2008-2020, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2021, VMware, Inc. All Rights Reserved.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the
#include "vmxnet3_int.h"
+#include <net/vxlan.h>
+#include <net/geneve.h>
+
+#define VXLAN_UDP_PORT 8472
struct vmxnet3_stat_desc {
char desc[ETH_GSTRING_LEN];
if (VMXNET3_VERSION_GE_4(adapter) &&
skb->encapsulation && skb->ip_summed == CHECKSUM_PARTIAL) {
u8 l4_proto = 0;
+ u16 port;
+ struct udphdr *udph;
switch (vlan_get_protocol(skb)) {
case htons(ETH_P_IP):
return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
}
- if (l4_proto != IPPROTO_UDP)
+ switch (l4_proto) {
+ case IPPROTO_UDP:
+ udph = udp_hdr(skb);
+ port = be16_to_cpu(udph->dest);
+ /* Check if offloaded port is supported */
+ if (port != GENEVE_UDP_PORT &&
+ port != IANA_VXLAN_UDP_PORT &&
+ port != VXLAN_UDP_PORT) {
+ return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
+ }
+ break;
+ default:
return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
+ }
}
return features;
}
return -EINVAL;
}
-static int __init mod_init(void)
+static int __init hdlc_cisco_init(void)
{
register_hdlc_protocol(&proto);
return 0;
}
-static void __exit mod_exit(void)
+static void __exit hdlc_cisco_exit(void)
{
unregister_hdlc_protocol(&proto);
}
-module_init(mod_init);
-module_exit(mod_exit);
+module_init(hdlc_cisco_init);
+module_exit(hdlc_cisco_exit);
MODULE_AUTHOR("Krzysztof Halasa <khc@pm.waw.pl>");
MODULE_DESCRIPTION("Cisco HDLC protocol support for generic HDLC");
return -EINVAL;
}
-static int __init mod_init(void)
+static int __init hdlc_fr_init(void)
{
register_hdlc_protocol(&proto);
return 0;
}
-static void __exit mod_exit(void)
+static void __exit hdlc_fr_exit(void)
{
unregister_hdlc_protocol(&proto);
}
-module_init(mod_init);
-module_exit(mod_exit);
+module_init(hdlc_fr_init);
+module_exit(hdlc_fr_exit);
MODULE_AUTHOR("Krzysztof Halasa <khc@pm.waw.pl>");
MODULE_DESCRIPTION("Frame-Relay protocol support for generic HDLC");
return -EINVAL;
}
-static int __init mod_init(void)
+static int __init hdlc_ppp_init(void)
{
skb_queue_head_init(&tx_queue);
register_hdlc_protocol(&proto);
return 0;
}
-static void __exit mod_exit(void)
+static void __exit hdlc_ppp_exit(void)
{
unregister_hdlc_protocol(&proto);
}
-module_init(mod_init);
-module_exit(mod_exit);
+module_init(hdlc_ppp_init);
+module_exit(hdlc_ppp_exit);
MODULE_AUTHOR("Krzysztof Halasa <khc@pm.waw.pl>");
MODULE_DESCRIPTION("PPP protocol support for generic HDLC");
}
-static int __init mod_init(void)
+static int __init hdlc_raw_init(void)
{
register_hdlc_protocol(&proto);
return 0;
-static void __exit mod_exit(void)
+static void __exit hdlc_raw_exit(void)
{
unregister_hdlc_protocol(&proto);
}
-module_init(mod_init);
-module_exit(mod_exit);
+module_init(hdlc_raw_init);
+module_exit(hdlc_raw_exit);
MODULE_AUTHOR("Krzysztof Halasa <khc@pm.waw.pl>");
MODULE_DESCRIPTION("Raw HDLC protocol support for generic HDLC");
}
-static int __init mod_init(void)
+static int __init hdlc_eth_init(void)
{
register_hdlc_protocol(&proto);
return 0;
-static void __exit mod_exit(void)
+static void __exit hdlc_eth_exit(void)
{
unregister_hdlc_protocol(&proto);
}
-module_init(mod_init);
-module_exit(mod_exit);
+module_init(hdlc_eth_init);
+module_exit(hdlc_eth_exit);
MODULE_AUTHOR("Krzysztof Halasa <khc@pm.waw.pl>");
MODULE_DESCRIPTION("Ethernet encapsulation support for generic HDLC");
return -EINVAL;
}
-static int __init mod_init(void)
+static int __init hdlc_x25_init(void)
{
register_hdlc_protocol(&proto);
return 0;
}
-static void __exit mod_exit(void)
+static void __exit hdlc_x25_exit(void)
{
unregister_hdlc_protocol(&proto);
}
-module_init(mod_init);
-module_exit(mod_exit);
+module_init(hdlc_x25_init);
+module_exit(hdlc_x25_exit);
MODULE_AUTHOR("Krzysztof Halasa <khc@pm.waw.pl>");
MODULE_DESCRIPTION("X.25 protocol support for generic HDLC");
case WLAN_CIPHER_SUITE_WEP104:
if (!mvif->wep_sta)
return -EOPNOTSUPP;
+ break;
case WLAN_CIPHER_SUITE_TKIP:
case WLAN_CIPHER_SUITE_CCMP:
case WLAN_CIPHER_SUITE_CCMP_256:
ret = mt76_get_field(dev, MT_CONN_ON_MISC, MT_TOP_MISC2_FW_N9_RDY);
if (ret) {
dev_dbg(dev->mt76.dev, "Firmware is already download\n");
- return -EIO;
+ goto fw_loaded;
}
ret = mt7921_load_patch(dev);
return -EIO;
}
+fw_loaded:
mt76_queue_tx_cleanup(dev, dev->mt76.q_mcu[MT_MCUQ_FWDL], false);
#ifdef CONFIG_PM
/* Assigned at module init. Guaranteed locally-administered and unicast. */
static u8 fake_router_bssid[ETH_ALEN] __ro_after_init = {};
+static void virt_wifi_inform_bss(struct wiphy *wiphy)
+{
+ u64 tsf = div_u64(ktime_get_boottime_ns(), 1000);
+ struct cfg80211_bss *informed_bss;
+ static const struct {
+ u8 tag;
+ u8 len;
+ u8 ssid[8];
+ } __packed ssid = {
+ .tag = WLAN_EID_SSID,
+ .len = 8,
+ .ssid = "VirtWifi",
+ };
+
+ informed_bss = cfg80211_inform_bss(wiphy, &channel_5ghz,
+ CFG80211_BSS_FTYPE_PRESP,
+ fake_router_bssid, tsf,
+ WLAN_CAPABILITY_ESS, 0,
+ (void *)&ssid, sizeof(ssid),
+ DBM_TO_MBM(-50), GFP_KERNEL);
+ cfg80211_put_bss(wiphy, informed_bss);
+}
+
/* Called with the rtnl lock held. */
static int virt_wifi_scan(struct wiphy *wiphy,
struct cfg80211_scan_request *request)
/* Acquires and releases the rdev BSS lock. */
static void virt_wifi_scan_result(struct work_struct *work)
{
- struct {
- u8 tag;
- u8 len;
- u8 ssid[8];
- } __packed ssid = {
- .tag = WLAN_EID_SSID, .len = 8, .ssid = "VirtWifi",
- };
- struct cfg80211_bss *informed_bss;
struct virt_wifi_wiphy_priv *priv =
container_of(work, struct virt_wifi_wiphy_priv,
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, tsf,
- WLAN_CAPABILITY_ESS, 0,
- (void *)&ssid, sizeof(ssid),
- DBM_TO_MBM(-50), GFP_KERNEL);
- cfg80211_put_bss(wiphy, informed_bss);
+ virt_wifi_inform_bss(wiphy);
/* Schedules work which acquires and releases the rtnl lock. */
cfg80211_scan_done(priv->scan_request, &scan_info);
if (!could_schedule)
return -EBUSY;
- if (sme->bssid)
+ if (sme->bssid) {
ether_addr_copy(priv->connect_requested_bss, sme->bssid);
- else
+ } else {
+ virt_wifi_inform_bss(wiphy);
eth_zero_addr(priv->connect_requested_bss);
+ }
wiphy_debug(wiphy, "connect\n");
struct virt_wifi_netdev_priv *priv =
container_of(work, struct virt_wifi_netdev_priv, connect.work);
u8 *requested_bss = priv->connect_requested_bss;
- bool has_addr = !is_zero_ether_addr(requested_bss);
bool right_addr = ether_addr_equal(requested_bss, fake_router_bssid);
u16 status = WLAN_STATUS_SUCCESS;
- if (!priv->is_up || (has_addr && !right_addr))
+ if (is_zero_ether_addr(requested_bss))
+ requested_bss = NULL;
+
+ if (!priv->is_up || (requested_bss && !right_addr))
status = WLAN_STATUS_UNSPECIFIED_FAILURE;
else
priv->is_connected = true;
return -EIO;
}
- /* check for the interafce id
- * if if_id 1 to 8 then create IP MUX channel sessions.
- * To start MUX session from 0 as network interface id would start
- * from 1 so map it to if_id = if_id - 1
- */
- if (if_id >= IP_MUX_SESSION_START && if_id <= IP_MUX_SESSION_END)
- return ipc_mux_open_session(ipc_imem->mux, if_id - 1);
-
- return -EINVAL;
+ return ipc_mux_open_session(ipc_imem->mux, if_id);
}
/* Release a net link to CP. */
{
if (ipc_imem->mux && if_id >= IP_MUX_SESSION_START &&
if_id <= IP_MUX_SESSION_END)
- ipc_mux_close_session(ipc_imem->mux, if_id - 1);
+ ipc_mux_close_session(ipc_imem->mux, if_id);
}
/* Tasklet call to do uplink transfer. */
goto out;
}
- if (if_id >= IP_MUX_SESSION_START && if_id <= IP_MUX_SESSION_END)
- /* Route the UL packet through IP MUX Layer */
- ret = ipc_mux_ul_trigger_encode(ipc_imem->mux,
- if_id - 1, skb);
- else
- dev_err(ipc_imem->dev,
- "invalid if_id %d: ", if_id);
+ /* Route the UL packet through IP MUX Layer */
+ ret = ipc_mux_ul_trigger_encode(ipc_imem->mux, if_id, skb);
out:
return ret;
}
#define BOOT_CHECK_DEFAULT_TIMEOUT 400
/* IP MUX channel range */
-#define IP_MUX_SESSION_START 1
-#define IP_MUX_SESSION_END 8
+#define IP_MUX_SESSION_START 0
+#define IP_MUX_SESSION_END 7
/* Default IP MUX channel */
-#define IP_MUX_SESSION_DEFAULT 1
+#define IP_MUX_SESSION_DEFAULT 0
/**
* ipc_imem_sys_port_open - Open a port link to CP.
#define IOSM_CP_VERSION 0x0100UL
/* DL dir Aggregation support mask */
-#define DL_AGGR BIT(23)
+#define DL_AGGR BIT(9)
/* UL dir Aggregation support mask */
-#define UL_AGGR BIT(22)
+#define UL_AGGR BIT(8)
/* UL flow credit support mask */
#define UL_FLOW_CREDIT BIT(21)
/* Pass the packet to the netif layer. */
dest_skb->priority = service_class;
- return ipc_wwan_receive(wwan, dest_skb, false, if_id + 1);
+ return ipc_wwan_receive(wwan, dest_skb, false, if_id);
}
/* Decode Flow Credit Table in the block */
return;
}
- ul_credits = fct->vfl.nr_of_bytes;
+ ul_credits = le32_to_cpu(fct->vfl.nr_of_bytes);
dev_dbg(ipc_mux->dev, "Flow_Credit:: if_id[%d] Old: %d Grants: %d",
if_id, ipc_mux->session[if_id].ul_flow_credits, ul_credits);
qlt->reserved[0] = 0;
qlt->reserved[1] = 0;
- qlt->vfl.nr_of_bytes = session->ul_list.qlen;
+ qlt->vfl.nr_of_bytes = cpu_to_le32(session->ul_list.qlen);
/* Add QLT to the transfer list. */
skb_queue_tail(&ipc_mux->channel->ul_list,
* @nr_of_bytes: Number of bytes available to transmit in the queue.
*/
struct mux_lite_vfl {
- u32 nr_of_bytes;
+ __le32 nr_of_bytes;
};
/**
}
if (p_td->buffer.address != IPC_CB(skb)->mapping) {
- dev_err(ipc_protocol->dev, "invalid buf=%p or skb=%p",
- (void *)p_td->buffer.address, skb->data);
+ dev_err(ipc_protocol->dev, "invalid buf=%llx or skb=%p",
+ (unsigned long long)p_td->buffer.address, skb->data);
ipc_pcie_kfree_skb(ipc_protocol->pcie, skb);
skb = NULL;
goto ret;
/* Store the device and event information */
info->dev = dev;
- snprintf(info->uevent, MAX_UEVENT_LEN, "%s: %s", dev_name(dev), uevent);
+ snprintf(info->uevent, MAX_UEVENT_LEN, "IOSM_EVENT=%s", uevent);
/* Schedule uevent in process context using work queue */
schedule_work(&info->work);
{
struct iosm_netdev_priv *priv = wwan_netdev_drvpriv(netdev);
struct iosm_wwan *ipc_wwan = priv->ipc_wwan;
+ unsigned int len = skb->len;
int if_id = priv->if_id;
int ret;
/* Return code of zero is success */
if (ret == 0) {
+ netdev->stats.tx_packets++;
+ netdev->stats.tx_bytes += len;
ret = NETDEV_TX_OK;
} else if (ret == -EBUSY) {
ret = NETDEV_TX_BUSY;
ret);
dev_kfree_skb_any(skb);
- return ret;
+ netdev->stats.tx_dropped++;
+ return NETDEV_TX_OK;
}
/* Ops structure for wwan net link */
iosm_dev->priv_flags |= IFF_NO_QUEUE;
iosm_dev->type = ARPHRD_NONE;
+ iosm_dev->mtu = ETH_DATA_LEN;
iosm_dev->min_mtu = ETH_MIN_MTU;
iosm_dev->max_mtu = ETH_MAX_MTU;
RCU_INIT_POINTER(ipc_wwan->sub_netlist[if_id], NULL);
/* unregistering includes synchronize_net() */
- unregister_netdevice(dev);
+ unregister_netdevice_queue(dev, head);
unlock:
mutex_unlock(&ipc_wwan->if_mutex);
skb->pkt_type = PACKET_HOST;
- if (if_id < (IP_MUX_SESSION_START - 1) ||
- if_id > (IP_MUX_SESSION_END - 1)) {
+ if (if_id < IP_MUX_SESSION_START ||
+ if_id > IP_MUX_SESSION_END) {
ret = -EINVAL;
goto free;
}
int ret;
/* Start mhi device's channel(s) */
- ret = mhi_prepare_for_transfer(mhiwwan->mhi_dev);
+ ret = mhi_prepare_for_transfer(mhiwwan->mhi_dev, 0);
if (ret)
return ret;
goto unlock;
}
+ rtnl_configure_link(dev, NULL); /* Link initialized, notify new link */
+
unlock:
rtnl_unlock();
if (!IS_ERR(skb))
dev_kfree_skb(skb);
-
- skb = ERR_PTR(-ENODEV);
+ return;
}
dev->cb(dev->nfc_digital_dev, dev->arg, skb);
if (IS_ERR(tfm)) {
ret = PTR_ERR(tfm);
dev_err(&fw_info->ndev->nfc_dev->dev,
- "Cannot allocate shash (code=%d)\n", ret);
+ "Cannot allocate shash (code=%pe)\n", tfm);
goto out;
}
cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
cmnd->write_zeroes.length =
cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
- cmnd->write_zeroes.control = 0;
+ if (nvme_ns_has_pi(ns))
+ cmnd->write_zeroes.control = cpu_to_le16(NVME_RW_PRINFO_PRACT);
+ else
+ cmnd->write_zeroes.control = 0;
return BLK_STS_OK;
}
static void nvme_ns_remove(struct nvme_ns *ns)
{
+ bool last_path = false;
+
if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags))
return;
mutex_lock(&ns->ctrl->subsys->lock);
list_del_rcu(&ns->siblings);
- if (list_empty(&ns->head->list))
- list_del_init(&ns->head->entry);
mutex_unlock(&ns->ctrl->subsys->lock);
synchronize_rcu(); /* guarantee not available in head->list */
list_del_init(&ns->list);
up_write(&ns->ctrl->namespaces_rwsem);
- nvme_mpath_check_last_path(ns);
+ /* Synchronize with nvme_init_ns_head() */
+ mutex_lock(&ns->head->subsys->lock);
+ if (list_empty(&ns->head->list)) {
+ list_del_init(&ns->head->entry);
+ last_path = true;
+ }
+ mutex_unlock(&ns->head->subsys->lock);
+ if (last_path)
+ nvme_mpath_shutdown_disk(ns->head);
nvme_put_ns(ns);
}
#endif
}
-void nvme_mpath_remove_disk(struct nvme_ns_head *head)
+void nvme_mpath_shutdown_disk(struct nvme_ns_head *head)
{
if (!head->disk)
return;
+ kblockd_schedule_work(&head->requeue_work);
if (head->disk->flags & GENHD_FL_UP) {
nvme_cdev_del(&head->cdev, &head->cdev_device);
del_gendisk(head->disk);
}
+}
+
+void nvme_mpath_remove_disk(struct nvme_ns_head *head)
+{
+ if (!head->disk)
+ return;
blk_set_queue_dying(head->disk->queue);
/* make sure all pending bios are cleaned up */
kblockd_schedule_work(&head->requeue_work);
void nvme_mpath_stop(struct nvme_ctrl *ctrl);
bool nvme_mpath_clear_current_path(struct nvme_ns *ns);
void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl);
-
-static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
-{
- struct nvme_ns_head *head = ns->head;
-
- if (head->disk && list_empty(&head->list))
- kblockd_schedule_work(&head->requeue_work);
-}
+void nvme_mpath_shutdown_disk(struct nvme_ns_head *head);
static inline void nvme_trace_bio_complete(struct request *req)
{
static inline void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
{
}
-static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
+static inline void nvme_mpath_shutdown_disk(struct nvme_ns_head *head)
{
}
static inline void nvme_trace_bio_complete(struct request *req)
wmb(); /* ensure the first interrupt sees the initialization */
}
+/*
+ * Try getting shutdown_lock while setting up IO queues.
+ */
+static int nvme_setup_io_queues_trylock(struct nvme_dev *dev)
+{
+ /*
+ * Give up if the lock is being held by nvme_dev_disable.
+ */
+ if (!mutex_trylock(&dev->shutdown_lock))
+ return -ENODEV;
+
+ /*
+ * Controller is in wrong state, fail early.
+ */
+ if (dev->ctrl.state != NVME_CTRL_CONNECTING) {
+ mutex_unlock(&dev->shutdown_lock);
+ return -ENODEV;
+ }
+
+ return 0;
+}
+
static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled)
{
struct nvme_dev *dev = nvmeq->dev;
goto release_cq;
nvmeq->cq_vector = vector;
- nvme_init_queue(nvmeq, qid);
+ result = nvme_setup_io_queues_trylock(dev);
+ if (result)
+ return result;
+ nvme_init_queue(nvmeq, qid);
if (!polled) {
result = queue_request_irq(nvmeq);
if (result < 0)
}
set_bit(NVMEQ_ENABLED, &nvmeq->flags);
+ mutex_unlock(&dev->shutdown_lock);
return result;
release_sq:
dev->online_queues--;
+ mutex_unlock(&dev->shutdown_lock);
adapter_delete_sq(dev, qid);
release_cq:
adapter_delete_cq(dev, qid);
if (nr_io_queues == 0)
return 0;
- clear_bit(NVMEQ_ENABLED, &adminq->flags);
+ /*
+ * Free IRQ resources as soon as NVMEQ_ENABLED bit transitions
+ * from set to unset. If there is a window to it is truely freed,
+ * pci_free_irq_vectors() jumping into this window will crash.
+ * And take lock to avoid racing with pci_free_irq_vectors() in
+ * nvme_dev_disable() path.
+ */
+ result = nvme_setup_io_queues_trylock(dev);
+ if (result)
+ return result;
+ if (test_and_clear_bit(NVMEQ_ENABLED, &adminq->flags))
+ pci_free_irq(pdev, 0, adminq);
if (dev->cmb_use_sqes) {
result = nvme_cmb_qdepth(dev, nr_io_queues,
result = nvme_remap_bar(dev, size);
if (!result)
break;
- if (!--nr_io_queues)
- return -ENOMEM;
+ if (!--nr_io_queues) {
+ result = -ENOMEM;
+ goto out_unlock;
+ }
} while (1);
adminq->q_db = dev->dbs;
retry:
/* Deregister the admin queue's interrupt */
- pci_free_irq(pdev, 0, adminq);
+ if (test_and_clear_bit(NVMEQ_ENABLED, &adminq->flags))
+ pci_free_irq(pdev, 0, adminq);
/*
* If we enable msix early due to not intx, disable it again before
pci_free_irq_vectors(pdev);
result = nvme_setup_irqs(dev, nr_io_queues);
- if (result <= 0)
- return -EIO;
+ if (result <= 0) {
+ result = -EIO;
+ goto out_unlock;
+ }
dev->num_vecs = result;
result = max(result - 1, 1);
*/
result = queue_request_irq(adminq);
if (result)
- return result;
+ goto out_unlock;
set_bit(NVMEQ_ENABLED, &adminq->flags);
+ mutex_unlock(&dev->shutdown_lock);
result = nvme_create_io_queues(dev);
if (result || dev->online_queues < 2)
if (dev->online_queues - 1 < dev->max_qid) {
nr_io_queues = dev->online_queues - 1;
nvme_disable_io_queues(dev);
+ result = nvme_setup_io_queues_trylock(dev);
+ if (result)
+ return result;
nvme_suspend_io_queues(dev);
goto retry;
}
dev->io_queues[HCTX_TYPE_READ],
dev->io_queues[HCTX_TYPE_POLL]);
return 0;
+out_unlock:
+ mutex_unlock(&dev->shutdown_lock);
+ return result;
}
static void nvme_del_queue_end(struct request *req, blk_status_t error)
bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL);
int result;
- if (WARN_ON(dev->ctrl.state != NVME_CTRL_RESETTING)) {
+ if (dev->ctrl.state != NVME_CTRL_RESETTING) {
+ dev_warn(dev->ctrl.device, "ctrl state %d is not RESETTING\n",
+ dev->ctrl.state);
result = -ENODEV;
goto out;
}
if (!pci_device_is_present(pdev)) {
nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DEAD);
nvme_dev_disable(dev, true);
- nvme_dev_remove_admin(dev);
}
flush_work(&dev->ctrl.reset_work);
struct blk_mq_tag_set admin_tag_set;
struct sockaddr_storage addr;
struct sockaddr_storage src_addr;
- struct net_device *ndev;
struct nvme_ctrl ctrl;
struct work_struct err_work;
}
if (opts->mask & NVMF_OPT_HOST_IFACE) {
- ctrl->ndev = dev_get_by_name(&init_net, opts->host_iface);
- if (!ctrl->ndev) {
+ if (!__dev_get_by_name(&init_net, opts->host_iface)) {
pr_err("invalid interface passed: %s\n",
opts->host_iface);
ret = -ENODEV;
__field(u8, fctype)
__field(u16, cid)
__field(u32, nsid)
- __field(u64, metadata)
+ __field(bool, metadata)
__array(u8, cdw10, 24)
),
TP_fast_assign(
__entry->flags = cmd->common.flags;
__entry->cid = cmd->common.command_id;
__entry->nsid = le32_to_cpu(cmd->common.nsid);
- __entry->metadata = le64_to_cpu(cmd->common.metadata);
+ __entry->metadata = !!blk_integrity_rq(req);
__entry->fctype = cmd->fabrics.fctype;
__assign_disk_name(__entry->disk, req->rq_disk);
memcpy(__entry->cdw10, &cmd->common.cdw10,
sizeof(__entry->cdw10));
),
- TP_printk("nvme%d: %sqid=%d, cmdid=%u, nsid=%u, flags=0x%x, meta=0x%llx, cmd=(%s %s)",
+ TP_printk("nvme%d: %sqid=%d, cmdid=%u, nsid=%u, flags=0x%x, meta=0x%x, cmd=(%s %s)",
__entry->ctrl_id, __print_disk_name(__entry->disk),
__entry->qid, __entry->cid, __entry->nsid,
__entry->flags, __entry->metadata,
return 0;
}
-static int ixp4xx_pci_read(struct ixp4xx_pci *p, u32 addr, u32 cmd, u32 *data)
+static int ixp4xx_pci_read_indirect(struct ixp4xx_pci *p, u32 addr, u32 cmd, u32 *data)
{
ixp4xx_writel(p, IXP4XX_PCI_NP_AD, addr);
return ixp4xx_pci_check_master_abort(p);
}
-static int ixp4xx_pci_write(struct ixp4xx_pci *p, u32 addr, u32 cmd, u32 data)
+static int ixp4xx_pci_write_indirect(struct ixp4xx_pci *p, u32 addr, u32 cmd, u32 data)
{
ixp4xx_writel(p, IXP4XX_PCI_NP_AD, addr);
dev_dbg(p->dev, "read_config from %d size %d dev %d:%d:%d address: %08x cmd: %08x\n",
where, size, bus_num, PCI_SLOT(devfn), PCI_FUNC(devfn), addr, cmd);
- ret = ixp4xx_pci_read(p, addr, cmd, &val);
+ ret = ixp4xx_pci_read_indirect(p, addr, cmd, &val);
if (ret)
return PCIBIOS_DEVICE_NOT_FOUND;
dev_dbg(p->dev, "write_config_byte %#x to %d size %d dev %d:%d:%d addr: %08x cmd %08x\n",
value, where, size, bus_num, PCI_SLOT(devfn), PCI_FUNC(devfn), addr, cmd);
- ret = ixp4xx_pci_write(p, addr, cmd, val);
+ ret = ixp4xx_pci_write_indirect(p, addr, cmd, val);
if (ret)
return PCIBIOS_DEVICE_NOT_FOUND;
break;
}
/* If arch decided it can't, fall through... */
-#endif /* HAVE_PCI_MMAP */
fallthrough;
+#endif /* HAVE_PCI_MMAP */
default:
ret = -EINVAL;
break;
for (i = 0; i < socket_count; i++) {
sockets[i].card_state = 1; /* 1 = present but empty */
sockets[i].io_base = pci_resource_start(dev, 0);
+ sockets[i].dev = dev;
sockets[i].socket.features |= SS_CAP_PCCARD;
sockets[i].socket.map_size = 0x1000;
sockets[i].socket.irq_mask = 0;
#define AMD_PMC_RESULT_CMD_UNKNOWN 0xFE
#define AMD_PMC_RESULT_FAILED 0xFF
+/* FCH SSC Registers */
+#define FCH_S0I3_ENTRY_TIME_L_OFFSET 0x30
+#define FCH_S0I3_ENTRY_TIME_H_OFFSET 0x34
+#define FCH_S0I3_EXIT_TIME_L_OFFSET 0x38
+#define FCH_S0I3_EXIT_TIME_H_OFFSET 0x3C
+#define FCH_SSC_MAPPING_SIZE 0x800
+#define FCH_BASE_PHY_ADDR_LOW 0xFED81100
+#define FCH_BASE_PHY_ADDR_HIGH 0x00000000
+
+/* SMU Message Definations */
+#define SMU_MSG_GETSMUVERSION 0x02
+#define SMU_MSG_LOG_GETDRAM_ADDR_HI 0x04
+#define SMU_MSG_LOG_GETDRAM_ADDR_LO 0x05
+#define SMU_MSG_LOG_START 0x06
+#define SMU_MSG_LOG_RESET 0x07
+#define SMU_MSG_LOG_DUMP_DATA 0x08
+#define SMU_MSG_GET_SUP_CONSTRAINTS 0x09
/* List of supported CPU ids */
#define AMD_CPU_ID_RV 0x15D0
#define AMD_CPU_ID_RN 0x1630
#define AMD_CPU_ID_PCO AMD_CPU_ID_RV
#define AMD_CPU_ID_CZN AMD_CPU_ID_RN
+#define AMD_CPU_ID_YC 0x14B5
-#define AMD_SMU_FW_VERSION 0x0
#define PMC_MSG_DELAY_MIN_US 100
#define RESPONSE_REGISTER_LOOP_MAX 200
+#define SOC_SUBSYSTEM_IP_MAX 12
+#define DELAY_MIN_US 2000
+#define DELAY_MAX_US 3000
enum amd_pmc_def {
MSG_TEST = 0x01,
MSG_OS_HINT_PCO,
MSG_OS_HINT_RN,
};
+struct amd_pmc_bit_map {
+ const char *name;
+ u32 bit_mask;
+};
+
+static const struct amd_pmc_bit_map soc15_ip_blk[] = {
+ {"DISPLAY", BIT(0)},
+ {"CPU", BIT(1)},
+ {"GFX", BIT(2)},
+ {"VDD", BIT(3)},
+ {"ACP", BIT(4)},
+ {"VCN", BIT(5)},
+ {"ISP", BIT(6)},
+ {"NBIO", BIT(7)},
+ {"DF", BIT(8)},
+ {"USB0", BIT(9)},
+ {"USB1", BIT(10)},
+ {"LAPIC", BIT(11)},
+ {}
+};
+
struct amd_pmc_dev {
void __iomem *regbase;
- void __iomem *smu_base;
+ void __iomem *smu_virt_addr;
+ void __iomem *fch_virt_addr;
u32 base_addr;
u32 cpu_id;
+ u32 active_ips;
struct device *dev;
+ struct mutex lock; /* generic mutex lock */
#if IS_ENABLED(CONFIG_DEBUG_FS)
struct dentry *dbgfs_dir;
#endif /* CONFIG_DEBUG_FS */
};
static struct amd_pmc_dev pmc;
+static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set, u32 *data, u8 msg, bool ret);
static inline u32 amd_pmc_reg_read(struct amd_pmc_dev *dev, int reg_offset)
{
iowrite32(val, dev->regbase + reg_offset);
}
+struct smu_metrics {
+ u32 table_version;
+ u32 hint_count;
+ u32 s0i3_cyclecount;
+ u32 timein_s0i2;
+ u64 timeentering_s0i3_lastcapture;
+ u64 timeentering_s0i3_totaltime;
+ u64 timeto_resume_to_os_lastcapture;
+ u64 timeto_resume_to_os_totaltime;
+ u64 timein_s0i3_lastcapture;
+ u64 timein_s0i3_totaltime;
+ u64 timein_swdrips_lastcapture;
+ u64 timein_swdrips_totaltime;
+ u64 timecondition_notmet_lastcapture[SOC_SUBSYSTEM_IP_MAX];
+ u64 timecondition_notmet_totaltime[SOC_SUBSYSTEM_IP_MAX];
+} __packed;
+
#ifdef CONFIG_DEBUG_FS
static int smu_fw_info_show(struct seq_file *s, void *unused)
{
struct amd_pmc_dev *dev = s->private;
- u32 value;
+ struct smu_metrics table;
+ int idx;
+
+ if (dev->cpu_id == AMD_CPU_ID_PCO)
+ return -EINVAL;
+
+ memcpy_fromio(&table, dev->smu_virt_addr, sizeof(struct smu_metrics));
+
+ seq_puts(s, "\n=== SMU Statistics ===\n");
+ seq_printf(s, "Table Version: %d\n", table.table_version);
+ seq_printf(s, "Hint Count: %d\n", table.hint_count);
+ seq_printf(s, "S0i3 Cycle Count: %d\n", table.s0i3_cyclecount);
+ seq_printf(s, "Time (in us) to S0i3: %lld\n", table.timeentering_s0i3_lastcapture);
+ seq_printf(s, "Time (in us) in S0i3: %lld\n", table.timein_s0i3_lastcapture);
+
+ seq_puts(s, "\n=== Active time (in us) ===\n");
+ for (idx = 0 ; idx < SOC_SUBSYSTEM_IP_MAX ; idx++) {
+ if (soc15_ip_blk[idx].bit_mask & dev->active_ips)
+ seq_printf(s, "%-8s : %lld\n", soc15_ip_blk[idx].name,
+ table.timecondition_notmet_lastcapture[idx]);
+ }
- value = ioread32(dev->smu_base + AMD_SMU_FW_VERSION);
- seq_printf(s, "SMU FW Info: %x\n", value);
return 0;
}
DEFINE_SHOW_ATTRIBUTE(smu_fw_info);
+static int s0ix_stats_show(struct seq_file *s, void *unused)
+{
+ struct amd_pmc_dev *dev = s->private;
+ u64 entry_time, exit_time, residency;
+
+ entry_time = ioread32(dev->fch_virt_addr + FCH_S0I3_ENTRY_TIME_H_OFFSET);
+ entry_time = entry_time << 32 | ioread32(dev->fch_virt_addr + FCH_S0I3_ENTRY_TIME_L_OFFSET);
+
+ exit_time = ioread32(dev->fch_virt_addr + FCH_S0I3_EXIT_TIME_H_OFFSET);
+ exit_time = exit_time << 32 | ioread32(dev->fch_virt_addr + FCH_S0I3_EXIT_TIME_L_OFFSET);
+
+ /* It's in 48MHz. We need to convert it */
+ residency = exit_time - entry_time;
+ do_div(residency, 48);
+
+ seq_puts(s, "=== S0ix statistics ===\n");
+ seq_printf(s, "S0ix Entry Time: %lld\n", entry_time);
+ seq_printf(s, "S0ix Exit Time: %lld\n", exit_time);
+ seq_printf(s, "Residency Time: %lld\n", residency);
+
+ return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(s0ix_stats);
+
static void amd_pmc_dbgfs_unregister(struct amd_pmc_dev *dev)
{
debugfs_remove_recursive(dev->dbgfs_dir);
dev->dbgfs_dir = debugfs_create_dir("amd_pmc", NULL);
debugfs_create_file("smu_fw_info", 0644, dev->dbgfs_dir, dev,
&smu_fw_info_fops);
+ debugfs_create_file("s0ix_stats", 0644, dev->dbgfs_dir, dev,
+ &s0ix_stats_fops);
}
#else
static inline void amd_pmc_dbgfs_register(struct amd_pmc_dev *dev)
}
#endif /* CONFIG_DEBUG_FS */
+static int amd_pmc_setup_smu_logging(struct amd_pmc_dev *dev)
+{
+ u32 phys_addr_low, phys_addr_hi;
+ u64 smu_phys_addr;
+
+ if (dev->cpu_id == AMD_CPU_ID_PCO)
+ return -EINVAL;
+
+ /* Get Active devices list from SMU */
+ amd_pmc_send_cmd(dev, 0, &dev->active_ips, SMU_MSG_GET_SUP_CONSTRAINTS, 1);
+
+ /* Get dram address */
+ amd_pmc_send_cmd(dev, 0, &phys_addr_low, SMU_MSG_LOG_GETDRAM_ADDR_LO, 1);
+ amd_pmc_send_cmd(dev, 0, &phys_addr_hi, SMU_MSG_LOG_GETDRAM_ADDR_HI, 1);
+ smu_phys_addr = ((u64)phys_addr_hi << 32 | phys_addr_low);
+
+ dev->smu_virt_addr = devm_ioremap(dev->dev, smu_phys_addr, sizeof(struct smu_metrics));
+ if (!dev->smu_virt_addr)
+ return -ENOMEM;
+
+ /* Start the logging */
+ amd_pmc_send_cmd(dev, 0, NULL, SMU_MSG_LOG_START, 0);
+
+ return 0;
+}
+
static void amd_pmc_dump_registers(struct amd_pmc_dev *dev)
{
u32 value;
dev_dbg(dev->dev, "AMD_PMC_REGISTER_MESSAGE:%x\n", value);
}
-static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set)
+static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set, u32 *data, u8 msg, bool ret)
{
int rc;
- u8 msg;
u32 val;
+ mutex_lock(&dev->lock);
/* Wait until we get a valid response */
rc = readx_poll_timeout(ioread32, dev->regbase + AMD_PMC_REGISTER_RESPONSE,
- val, val > 0, PMC_MSG_DELAY_MIN_US,
+ val, val != 0, PMC_MSG_DELAY_MIN_US,
PMC_MSG_DELAY_MIN_US * RESPONSE_REGISTER_LOOP_MAX);
if (rc) {
dev_err(dev->dev, "failed to talk to SMU\n");
- return rc;
+ goto out_unlock;
}
/* Write zero to response register */
amd_pmc_reg_write(dev, AMD_PMC_REGISTER_ARGUMENT, set);
/* Write message ID to message ID register */
- msg = (dev->cpu_id == AMD_CPU_ID_RN) ? MSG_OS_HINT_RN : MSG_OS_HINT_PCO;
amd_pmc_reg_write(dev, AMD_PMC_REGISTER_MESSAGE, msg);
- return 0;
+
+ /* Wait until we get a valid response */
+ rc = readx_poll_timeout(ioread32, dev->regbase + AMD_PMC_REGISTER_RESPONSE,
+ val, val != 0, PMC_MSG_DELAY_MIN_US,
+ PMC_MSG_DELAY_MIN_US * RESPONSE_REGISTER_LOOP_MAX);
+ if (rc) {
+ dev_err(dev->dev, "SMU response timed out\n");
+ goto out_unlock;
+ }
+
+ switch (val) {
+ case AMD_PMC_RESULT_OK:
+ if (ret) {
+ /* PMFW may take longer time to return back the data */
+ usleep_range(DELAY_MIN_US, 10 * DELAY_MAX_US);
+ *data = amd_pmc_reg_read(dev, AMD_PMC_REGISTER_ARGUMENT);
+ }
+ break;
+ case AMD_PMC_RESULT_CMD_REJECT_BUSY:
+ dev_err(dev->dev, "SMU not ready. err: 0x%x\n", val);
+ rc = -EBUSY;
+ goto out_unlock;
+ case AMD_PMC_RESULT_CMD_UNKNOWN:
+ dev_err(dev->dev, "SMU cmd unknown. err: 0x%x\n", val);
+ rc = -EINVAL;
+ goto out_unlock;
+ case AMD_PMC_RESULT_CMD_REJECT_PREREQ:
+ case AMD_PMC_RESULT_FAILED:
+ default:
+ dev_err(dev->dev, "SMU cmd failed. err: 0x%x\n", val);
+ rc = -EIO;
+ goto out_unlock;
+ }
+
+out_unlock:
+ mutex_unlock(&dev->lock);
+ amd_pmc_dump_registers(dev);
+ return rc;
+}
+
+static int amd_pmc_get_os_hint(struct amd_pmc_dev *dev)
+{
+ switch (dev->cpu_id) {
+ case AMD_CPU_ID_PCO:
+ return MSG_OS_HINT_PCO;
+ case AMD_CPU_ID_RN:
+ case AMD_CPU_ID_YC:
+ return MSG_OS_HINT_RN;
+ }
+ return -EINVAL;
}
static int __maybe_unused amd_pmc_suspend(struct device *dev)
{
struct amd_pmc_dev *pdev = dev_get_drvdata(dev);
int rc;
+ u8 msg;
+
+ /* Reset and Start SMU logging - to monitor the s0i3 stats */
+ amd_pmc_send_cmd(pdev, 0, NULL, SMU_MSG_LOG_RESET, 0);
+ amd_pmc_send_cmd(pdev, 0, NULL, SMU_MSG_LOG_START, 0);
- rc = amd_pmc_send_cmd(pdev, 1);
+ msg = amd_pmc_get_os_hint(pdev);
+ rc = amd_pmc_send_cmd(pdev, 1, NULL, msg, 0);
if (rc)
dev_err(pdev->dev, "suspend failed\n");
- amd_pmc_dump_registers(pdev);
- return 0;
+ return rc;
}
static int __maybe_unused amd_pmc_resume(struct device *dev)
{
struct amd_pmc_dev *pdev = dev_get_drvdata(dev);
int rc;
+ u8 msg;
+
+ /* Let SMU know that we are looking for stats */
+ amd_pmc_send_cmd(pdev, 0, NULL, SMU_MSG_LOG_DUMP_DATA, 0);
- rc = amd_pmc_send_cmd(pdev, 0);
+ msg = amd_pmc_get_os_hint(pdev);
+ rc = amd_pmc_send_cmd(pdev, 0, NULL, msg, 0);
if (rc)
dev_err(pdev->dev, "resume failed\n");
- amd_pmc_dump_registers(pdev);
return 0;
}
};
static const struct pci_device_id pmc_pci_ids[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_YC) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_CZN) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_RN) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_PCO) },
{
struct amd_pmc_dev *dev = &pmc;
struct pci_dev *rdev;
- u32 base_addr_lo;
- u32 base_addr_hi;
- u64 base_addr;
+ u32 base_addr_lo, base_addr_hi;
+ u64 base_addr, fch_phys_addr;
int err;
u32 val;
pci_dev_put(rdev);
base_addr = ((u64)base_addr_hi << 32 | base_addr_lo);
- dev->smu_base = devm_ioremap(dev->dev, base_addr, AMD_PMC_MAPPING_SIZE);
- if (!dev->smu_base)
- return -ENOMEM;
-
dev->regbase = devm_ioremap(dev->dev, base_addr + AMD_PMC_BASE_ADDR_OFFSET,
AMD_PMC_MAPPING_SIZE);
if (!dev->regbase)
return -ENOMEM;
- amd_pmc_dump_registers(dev);
+ mutex_init(&dev->lock);
+
+ /* Use FCH registers to get the S0ix stats */
+ base_addr_lo = FCH_BASE_PHY_ADDR_LOW;
+ base_addr_hi = FCH_BASE_PHY_ADDR_HIGH;
+ fch_phys_addr = ((u64)base_addr_hi << 32 | base_addr_lo);
+ dev->fch_virt_addr = devm_ioremap(dev->dev, fch_phys_addr, FCH_SSC_MAPPING_SIZE);
+ if (!dev->fch_virt_addr)
+ return -ENOMEM;
+
+ /* Use SMU to get the s0i3 debug stats */
+ err = amd_pmc_setup_smu_logging(dev);
+ if (err)
+ dev_err(dev->dev, "SMU debugging info not supported on this platform\n");
platform_set_drvdata(pdev, dev);
amd_pmc_dbgfs_register(dev);
struct amd_pmc_dev *dev = platform_get_drvdata(pdev);
amd_pmc_dbgfs_unregister(dev);
+ mutex_destroy(&dev->lock);
return 0;
}
static const struct acpi_device_id amd_pmc_acpi_ids[] = {
{"AMDI0005", 0},
+ {"AMDI0006", 0},
+ {"AMDI0007", 0},
{"AMD0004", 0},
{ }
};
static const struct dmi_system_id gigabyte_wmi_known_working_platforms[] = {
DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE"),
+ DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE V2"),
DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 GAMING X V2"),
DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550M AORUS PRO-P"),
DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550M DS3H"),
{"INT33D5", 0},
{"INTC1051", 0},
{"INTC1054", 0},
+ {"INTC1070", 0},
{"", 0},
};
MODULE_DEVICE_TABLE(acpi, intel_hid_ids);
else
ret = tlmi_save_bios_settings("");
+ if (!ret && !tlmi_priv.pending_changes) {
+ tlmi_priv.pending_changes = true;
+ /* let userland know it may need to check reboot pending again */
+ kobject_uevent(&tlmi_priv.class_dev->kobj, KOBJ_CHANGE);
+ }
out:
kfree(auth_str);
kfree(set_str);
.sysfs_ops = &tlmi_kobj_sysfs_ops,
};
+static ssize_t pending_reboot_show(struct kobject *kobj, struct kobj_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "%d\n", tlmi_priv.pending_changes);
+}
+
+static struct kobj_attribute pending_reboot = __ATTR_RO(pending_reboot);
+
/* ---- Initialisation --------------------------------------------------------- */
static void tlmi_release_attr(void)
{
kobject_put(&tlmi_priv.setting[i]->kobj);
}
}
+ sysfs_remove_file(&tlmi_priv.attribute_kset->kobj, &pending_reboot.attr);
kset_unregister(tlmi_priv.attribute_kset);
/* Authentication structures */
/* Build attribute */
tlmi_priv.setting[i]->kobj.kset = tlmi_priv.attribute_kset;
- ret = kobject_init_and_add(&tlmi_priv.setting[i]->kobj, &tlmi_attr_setting_ktype,
- NULL, "%s", tlmi_priv.setting[i]->display_name);
+ ret = kobject_add(&tlmi_priv.setting[i]->kobj, NULL,
+ "%s", tlmi_priv.setting[i]->display_name);
if (ret)
goto fail_create_attr;
goto fail_create_attr;
}
+ ret = sysfs_create_file(&tlmi_priv.attribute_kset->kobj, &pending_reboot.attr);
+ if (ret)
+ goto fail_create_attr;
+
/* Create authentication entries */
tlmi_priv.authentication_kset = kset_create_and_add("authentication", NULL,
&tlmi_priv.class_dev->kobj);
goto fail_create_attr;
}
tlmi_priv.pwd_admin->kobj.kset = tlmi_priv.authentication_kset;
- ret = kobject_init_and_add(&tlmi_priv.pwd_admin->kobj, &tlmi_pwd_setting_ktype,
- NULL, "%s", "Admin");
+ ret = kobject_add(&tlmi_priv.pwd_admin->kobj, NULL, "%s", "Admin");
if (ret)
goto fail_create_attr;
goto fail_create_attr;
tlmi_priv.pwd_power->kobj.kset = tlmi_priv.authentication_kset;
- ret = kobject_init_and_add(&tlmi_priv.pwd_power->kobj, &tlmi_pwd_setting_ktype,
- NULL, "%s", "System");
+ ret = kobject_add(&tlmi_priv.pwd_power->kobj, NULL, "%s", "System");
if (ret)
goto fail_create_attr;
pr_info("Error retrieving possible values for %d : %s\n",
i, setting->display_name);
}
+ kobject_init(&setting->kobj, &tlmi_attr_setting_ktype);
tlmi_priv.setting[i] = setting;
tlmi_priv.settings_count++;
kfree(item);
if (pwdcfg.password_state & TLMI_PAP_PWD)
tlmi_priv.pwd_admin->valid = true;
+ kobject_init(&tlmi_priv.pwd_admin->kobj, &tlmi_pwd_setting_ktype);
+
tlmi_priv.pwd_power = kzalloc(sizeof(struct tlmi_pwd_setting), GFP_KERNEL);
if (!tlmi_priv.pwd_power) {
ret = -ENOMEM;
- goto fail_clear_attr;
+ goto fail_free_pwd_admin;
}
strscpy(tlmi_priv.pwd_power->kbdlang, "us", TLMI_LANG_MAXLEN);
tlmi_priv.pwd_power->encoding = TLMI_ENCODING_ASCII;
if (pwdcfg.password_state & TLMI_POP_PWD)
tlmi_priv.pwd_power->valid = true;
+ kobject_init(&tlmi_priv.pwd_power->kobj, &tlmi_pwd_setting_ktype);
+
return 0;
+fail_free_pwd_admin:
+ kfree(tlmi_priv.pwd_admin);
fail_clear_attr:
- for (i = 0; i < TLMI_SETTINGS_COUNT; ++i)
- kfree(tlmi_priv.setting[i]);
+ for (i = 0; i < TLMI_SETTINGS_COUNT; ++i) {
+ if (tlmi_priv.setting[i]) {
+ kfree(tlmi_priv.setting[i]->possible_values);
+ kfree(tlmi_priv.setting[i]);
+ }
+ }
return ret;
}
bool can_get_bios_selections;
bool can_set_bios_password;
bool can_get_password_settings;
+ bool pending_changes;
struct tlmi_attr_setting *setting[TLMI_SETTINGS_COUNT];
struct device *class_dev;
err = wireless_input_setup();
if (err)
- pr_err("Failed to setup hp wireless hotkeys\n");
+ pr_err("Failed to setup wireless hotkeys\n");
return err;
}
break;
case AB8500_FG_CALIB_WAIT:
dev_dbg(di->dev, "Calibration WFI\n");
+ break;
default:
break;
}
queue_work(di->fg_wq, &di->fg_work);
break;
}
+ break;
default:
break;
}
default:
break;
}
+ break;
default:
break;
}
# Makefile for PTP 1588 clock support.
#
-ptp-y := ptp_clock.o ptp_chardev.o ptp_sysfs.o
+ptp-y := ptp_clock.o ptp_chardev.o ptp_sysfs.o ptp_vclock.o
ptp_kvm-$(CONFIG_X86) := ptp_kvm_x86.o ptp_kvm_common.o
ptp_kvm-$(CONFIG_HAVE_ARM_SMCCC) := ptp_kvm_arm.o ptp_kvm_common.o
obj-$(CONFIG_PTP_1588_CLOCK) += ptp.o
#define PTP_PPS_EVENT PPS_CAPTUREASSERT
#define PTP_PPS_MODE (PTP_PPS_DEFAULTS | PPS_CANWAIT | PPS_TSFMT_TSPEC)
+struct class *ptp_class;
+
/* private globals */
static dev_t ptp_devt;
-static struct class *ptp_class;
static DEFINE_IDA(ptp_clocks_map);
{
struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
+ if (ptp_vclock_in_use(ptp)) {
+ pr_err("ptp: virtual clock in use\n");
+ return -EBUSY;
+ }
+
return ptp->info->settime64(ptp->info, tp);
}
struct ptp_clock_info *ops;
int err = -EOPNOTSUPP;
+ if (ptp_vclock_in_use(ptp)) {
+ pr_err("ptp: virtual clock in use\n");
+ return -EBUSY;
+ }
+
ops = ptp->info;
if (tx->modes & ADJ_SETOFFSET) {
ptp_cleanup_pin_groups(ptp);
mutex_destroy(&ptp->tsevq_mux);
mutex_destroy(&ptp->pincfg_mux);
+ mutex_destroy(&ptp->n_vclocks_mux);
ida_simple_remove(&ptp_clocks_map, ptp->index);
kfree(ptp);
}
{
struct ptp_clock *ptp;
int err = 0, index, major = MAJOR(ptp_devt);
+ size_t size;
if (info->n_alarm > PTP_MAX_ALARMS)
return ERR_PTR(-EINVAL);
spin_lock_init(&ptp->tsevq.lock);
mutex_init(&ptp->tsevq_mux);
mutex_init(&ptp->pincfg_mux);
+ mutex_init(&ptp->n_vclocks_mux);
init_waitqueue_head(&ptp->tsev_wq);
if (ptp->info->do_aux_work) {
pr_err("failed to create ptp aux_worker %d\n", err);
goto kworker_err;
}
- ptp->pps_source->lookup_cookie = ptp;
+ }
+
+ /* PTP virtual clock is being registered under physical clock */
+ if (parent && parent->class && parent->class->name &&
+ strcmp(parent->class->name, "ptp") == 0)
+ ptp->is_virtual_clock = true;
+
+ if (!ptp->is_virtual_clock) {
+ ptp->max_vclocks = PTP_DEFAULT_MAX_VCLOCKS;
+
+ size = sizeof(int) * ptp->max_vclocks;
+ ptp->vclock_index = kzalloc(size, GFP_KERNEL);
+ if (!ptp->vclock_index) {
+ err = -ENOMEM;
+ goto no_mem_for_vclocks;
+ }
}
err = ptp_populate_pin_groups(ptp);
pr_err("failed to register pps source\n");
goto no_pps;
}
+ ptp->pps_source->lookup_cookie = ptp;
}
/* Initialize a new device of our class in our clock structure. */
no_pps:
ptp_cleanup_pin_groups(ptp);
no_pin_groups:
+ kfree(ptp->vclock_index);
+no_mem_for_vclocks:
if (ptp->kworker)
kthread_destroy_worker(ptp->kworker);
kworker_err:
mutex_destroy(&ptp->tsevq_mux);
mutex_destroy(&ptp->pincfg_mux);
+ mutex_destroy(&ptp->n_vclocks_mux);
ida_simple_remove(&ptp_clocks_map, index);
no_slot:
kfree(ptp);
int ptp_clock_unregister(struct ptp_clock *ptp)
{
+ if (ptp_vclock_in_use(ptp)) {
+ pr_err("ptp: virtual clock in use\n");
+ return -EBUSY;
+ }
+
ptp->defunct = 1;
wake_up_interruptible(&ptp->tsev_wq);
+ kfree(ptp->vclock_index);
+
if (ptp->kworker) {
kthread_cancel_delayed_work_sync(&ptp->aux_work);
kthread_destroy_worker(ptp->kworker);
#define PTP_MAX_TIMESTAMPS 128
#define PTP_BUF_TIMESTAMPS 30
+#define PTP_DEFAULT_MAX_VCLOCKS 20
struct timestamp_event_queue {
struct ptp_extts_event buf[PTP_MAX_TIMESTAMPS];
const struct attribute_group *pin_attr_groups[2];
struct kthread_worker *kworker;
struct kthread_delayed_work aux_work;
+ unsigned int max_vclocks;
+ unsigned int n_vclocks;
+ int *vclock_index;
+ struct mutex n_vclocks_mux; /* protect concurrent n_vclocks access */
+ bool is_virtual_clock;
+};
+
+#define info_to_vclock(d) container_of((d), struct ptp_vclock, info)
+#define cc_to_vclock(d) container_of((d), struct ptp_vclock, cc)
+#define dw_to_vclock(d) container_of((d), struct ptp_vclock, refresh_work)
+
+struct ptp_vclock {
+ struct ptp_clock *pclock;
+ struct ptp_clock_info info;
+ struct ptp_clock *clock;
+ struct cyclecounter cc;
+ struct timecounter tc;
+ spinlock_t lock; /* protects tc/cc */
};
/*
return cnt < 0 ? PTP_MAX_TIMESTAMPS + cnt : cnt;
}
+/* Check if ptp virtual clock is in use */
+static inline bool ptp_vclock_in_use(struct ptp_clock *ptp)
+{
+ bool in_use = false;
+
+ if (mutex_lock_interruptible(&ptp->n_vclocks_mux))
+ return true;
+
+ if (!ptp->is_virtual_clock && ptp->n_vclocks)
+ in_use = true;
+
+ mutex_unlock(&ptp->n_vclocks_mux);
+
+ return in_use;
+}
+
+extern struct class *ptp_class;
+
/*
* see ptp_chardev.c
*/
int ptp_populate_pin_groups(struct ptp_clock *ptp);
void ptp_cleanup_pin_groups(struct ptp_clock *ptp);
+struct ptp_vclock *ptp_vclock_register(struct ptp_clock *pclock);
+void ptp_vclock_unregister(struct ptp_vclock *vclock);
#endif
* PTP 1588 clock support - sysfs interface.
*
* Copyright (C) 2010 OMICRON electronics GmbH
+ * Copyright 2021 NXP
*/
#include <linux/capability.h>
#include <linux/slab.h>
}
static DEVICE_ATTR(pps_enable, 0220, NULL, pps_enable_store);
+static int unregister_vclock(struct device *dev, void *data)
+{
+ struct ptp_clock *ptp = dev_get_drvdata(dev);
+ struct ptp_clock_info *info = ptp->info;
+ struct ptp_vclock *vclock;
+ u8 *num = data;
+
+ vclock = info_to_vclock(info);
+ dev_info(dev->parent, "delete virtual clock ptp%d\n",
+ vclock->clock->index);
+
+ ptp_vclock_unregister(vclock);
+ (*num)--;
+
+ /* For break. Not error. */
+ if (*num == 0)
+ return -EINVAL;
+
+ return 0;
+}
+
+static ssize_t n_vclocks_show(struct device *dev,
+ struct device_attribute *attr, char *page)
+{
+ struct ptp_clock *ptp = dev_get_drvdata(dev);
+ ssize_t size;
+
+ if (mutex_lock_interruptible(&ptp->n_vclocks_mux))
+ return -ERESTARTSYS;
+
+ size = snprintf(page, PAGE_SIZE - 1, "%u\n", ptp->n_vclocks);
+
+ mutex_unlock(&ptp->n_vclocks_mux);
+
+ return size;
+}
+
+static ssize_t n_vclocks_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct ptp_clock *ptp = dev_get_drvdata(dev);
+ struct ptp_vclock *vclock;
+ int err = -EINVAL;
+ u32 num, i;
+
+ if (kstrtou32(buf, 0, &num))
+ return err;
+
+ if (mutex_lock_interruptible(&ptp->n_vclocks_mux))
+ return -ERESTARTSYS;
+
+ if (num > ptp->max_vclocks) {
+ dev_err(dev, "max value is %d\n", ptp->max_vclocks);
+ goto out;
+ }
+
+ /* Need to create more vclocks */
+ if (num > ptp->n_vclocks) {
+ for (i = 0; i < num - ptp->n_vclocks; i++) {
+ vclock = ptp_vclock_register(ptp);
+ if (!vclock)
+ goto out;
+
+ *(ptp->vclock_index + ptp->n_vclocks + i) =
+ vclock->clock->index;
+
+ dev_info(dev, "new virtual clock ptp%d\n",
+ vclock->clock->index);
+ }
+ }
+
+ /* Need to delete vclocks */
+ if (num < ptp->n_vclocks) {
+ i = ptp->n_vclocks - num;
+ device_for_each_child_reverse(dev, &i,
+ unregister_vclock);
+
+ for (i = 1; i <= ptp->n_vclocks - num; i++)
+ *(ptp->vclock_index + ptp->n_vclocks - i) = -1;
+ }
+
+ if (num == 0)
+ dev_info(dev, "only physical clock in use now\n");
+ else
+ dev_info(dev, "guarantee physical clock free running\n");
+
+ ptp->n_vclocks = num;
+ mutex_unlock(&ptp->n_vclocks_mux);
+
+ return count;
+out:
+ mutex_unlock(&ptp->n_vclocks_mux);
+ return err;
+}
+static DEVICE_ATTR_RW(n_vclocks);
+
+static ssize_t max_vclocks_show(struct device *dev,
+ struct device_attribute *attr, char *page)
+{
+ struct ptp_clock *ptp = dev_get_drvdata(dev);
+ ssize_t size;
+
+ size = snprintf(page, PAGE_SIZE - 1, "%u\n", ptp->max_vclocks);
+
+ return size;
+}
+
+static ssize_t max_vclocks_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct ptp_clock *ptp = dev_get_drvdata(dev);
+ unsigned int *vclock_index;
+ int err = -EINVAL;
+ size_t size;
+ u32 max;
+
+ if (kstrtou32(buf, 0, &max) || max == 0)
+ return -EINVAL;
+
+ if (max == ptp->max_vclocks)
+ return count;
+
+ if (mutex_lock_interruptible(&ptp->n_vclocks_mux))
+ return -ERESTARTSYS;
+
+ if (max < ptp->n_vclocks)
+ goto out;
+
+ size = sizeof(int) * max;
+ vclock_index = kzalloc(size, GFP_KERNEL);
+ if (!vclock_index) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ size = sizeof(int) * ptp->n_vclocks;
+ memcpy(vclock_index, ptp->vclock_index, size);
+
+ kfree(ptp->vclock_index);
+ ptp->vclock_index = vclock_index;
+ ptp->max_vclocks = max;
+
+ mutex_unlock(&ptp->n_vclocks_mux);
+
+ return count;
+out:
+ mutex_unlock(&ptp->n_vclocks_mux);
+ return err;
+}
+static DEVICE_ATTR_RW(max_vclocks);
+
static struct attribute *ptp_attrs[] = {
&dev_attr_clock_name.attr,
&dev_attr_fifo.attr,
&dev_attr_period.attr,
&dev_attr_pps_enable.attr,
+ &dev_attr_n_vclocks.attr,
+ &dev_attr_max_vclocks.attr,
NULL
};
} else if (attr == &dev_attr_pps_enable.attr) {
if (!info->pps)
mode = 0;
+ } else if (attr == &dev_attr_n_vclocks.attr ||
+ attr == &dev_attr_max_vclocks.attr) {
+ if (ptp->is_virtual_clock)
+ mode = 0;
}
return mode;
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * PTP virtual clock driver
+ *
+ * Copyright 2021 NXP
+ */
+#include <linux/slab.h>
+#include "ptp_private.h"
+
+#define PTP_VCLOCK_CC_SHIFT 31
+#define PTP_VCLOCK_CC_MULT (1 << PTP_VCLOCK_CC_SHIFT)
+#define PTP_VCLOCK_FADJ_SHIFT 9
+#define PTP_VCLOCK_FADJ_DENOMINATOR 15625ULL
+#define PTP_VCLOCK_REFRESH_INTERVAL (HZ * 2)
+
+static int ptp_vclock_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
+{
+ struct ptp_vclock *vclock = info_to_vclock(ptp);
+ unsigned long flags;
+ s64 adj;
+
+ adj = (s64)scaled_ppm << PTP_VCLOCK_FADJ_SHIFT;
+ adj = div_s64(adj, PTP_VCLOCK_FADJ_DENOMINATOR);
+
+ spin_lock_irqsave(&vclock->lock, flags);
+ timecounter_read(&vclock->tc);
+ vclock->cc.mult = PTP_VCLOCK_CC_MULT + adj;
+ spin_unlock_irqrestore(&vclock->lock, flags);
+
+ return 0;
+}
+
+static int ptp_vclock_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+ struct ptp_vclock *vclock = info_to_vclock(ptp);
+ unsigned long flags;
+
+ spin_lock_irqsave(&vclock->lock, flags);
+ timecounter_adjtime(&vclock->tc, delta);
+ spin_unlock_irqrestore(&vclock->lock, flags);
+
+ return 0;
+}
+
+static int ptp_vclock_gettime(struct ptp_clock_info *ptp,
+ struct timespec64 *ts)
+{
+ struct ptp_vclock *vclock = info_to_vclock(ptp);
+ unsigned long flags;
+ u64 ns;
+
+ spin_lock_irqsave(&vclock->lock, flags);
+ ns = timecounter_read(&vclock->tc);
+ spin_unlock_irqrestore(&vclock->lock, flags);
+ *ts = ns_to_timespec64(ns);
+
+ return 0;
+}
+
+static int ptp_vclock_settime(struct ptp_clock_info *ptp,
+ const struct timespec64 *ts)
+{
+ struct ptp_vclock *vclock = info_to_vclock(ptp);
+ u64 ns = timespec64_to_ns(ts);
+ unsigned long flags;
+
+ spin_lock_irqsave(&vclock->lock, flags);
+ timecounter_init(&vclock->tc, &vclock->cc, ns);
+ spin_unlock_irqrestore(&vclock->lock, flags);
+
+ return 0;
+}
+
+static long ptp_vclock_refresh(struct ptp_clock_info *ptp)
+{
+ struct ptp_vclock *vclock = info_to_vclock(ptp);
+ struct timespec64 ts;
+
+ ptp_vclock_gettime(&vclock->info, &ts);
+
+ return PTP_VCLOCK_REFRESH_INTERVAL;
+}
+
+static const struct ptp_clock_info ptp_vclock_info = {
+ .owner = THIS_MODULE,
+ .name = "ptp virtual clock",
+ /* The maximum ppb value that long scaled_ppm can support */
+ .max_adj = 32767999,
+ .adjfine = ptp_vclock_adjfine,
+ .adjtime = ptp_vclock_adjtime,
+ .gettime64 = ptp_vclock_gettime,
+ .settime64 = ptp_vclock_settime,
+ .do_aux_work = ptp_vclock_refresh,
+};
+
+static u64 ptp_vclock_read(const struct cyclecounter *cc)
+{
+ struct ptp_vclock *vclock = cc_to_vclock(cc);
+ struct ptp_clock *ptp = vclock->pclock;
+ struct timespec64 ts = {};
+
+ if (ptp->info->gettimex64)
+ ptp->info->gettimex64(ptp->info, &ts, NULL);
+ else
+ ptp->info->gettime64(ptp->info, &ts);
+
+ return timespec64_to_ns(&ts);
+}
+
+static const struct cyclecounter ptp_vclock_cc = {
+ .read = ptp_vclock_read,
+ .mask = CYCLECOUNTER_MASK(32),
+ .mult = PTP_VCLOCK_CC_MULT,
+ .shift = PTP_VCLOCK_CC_SHIFT,
+};
+
+struct ptp_vclock *ptp_vclock_register(struct ptp_clock *pclock)
+{
+ struct ptp_vclock *vclock;
+
+ vclock = kzalloc(sizeof(*vclock), GFP_KERNEL);
+ if (!vclock)
+ return NULL;
+
+ vclock->pclock = pclock;
+ vclock->info = ptp_vclock_info;
+ vclock->cc = ptp_vclock_cc;
+
+ snprintf(vclock->info.name, PTP_CLOCK_NAME_LEN, "ptp%d_virt",
+ pclock->index);
+
+ spin_lock_init(&vclock->lock);
+
+ vclock->clock = ptp_clock_register(&vclock->info, &pclock->dev);
+ if (IS_ERR_OR_NULL(vclock->clock)) {
+ kfree(vclock);
+ return NULL;
+ }
+
+ timecounter_init(&vclock->tc, &vclock->cc, 0);
+ ptp_schedule_worker(vclock->clock, PTP_VCLOCK_REFRESH_INTERVAL);
+
+ return vclock;
+}
+
+void ptp_vclock_unregister(struct ptp_vclock *vclock)
+{
+ ptp_clock_unregister(vclock->clock);
+ kfree(vclock);
+}
+
+int ptp_get_vclocks_index(int pclock_index, int **vclock_index)
+{
+ char name[PTP_CLOCK_NAME_LEN] = "";
+ struct ptp_clock *ptp;
+ struct device *dev;
+ int num = 0;
+
+ if (pclock_index < 0)
+ return num;
+
+ snprintf(name, PTP_CLOCK_NAME_LEN, "ptp%d", pclock_index);
+ dev = class_find_device_by_name(ptp_class, name);
+ if (!dev)
+ return num;
+
+ ptp = dev_get_drvdata(dev);
+
+ if (mutex_lock_interruptible(&ptp->n_vclocks_mux)) {
+ put_device(dev);
+ return num;
+ }
+
+ *vclock_index = kzalloc(sizeof(int) * ptp->n_vclocks, GFP_KERNEL);
+ if (!(*vclock_index))
+ goto out;
+
+ memcpy(*vclock_index, ptp->vclock_index, sizeof(int) * ptp->n_vclocks);
+ num = ptp->n_vclocks;
+out:
+ mutex_unlock(&ptp->n_vclocks_mux);
+ put_device(dev);
+ return num;
+}
+EXPORT_SYMBOL(ptp_get_vclocks_index);
+
+void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps,
+ int vclock_index)
+{
+ char name[PTP_CLOCK_NAME_LEN] = "";
+ struct ptp_vclock *vclock;
+ struct ptp_clock *ptp;
+ unsigned long flags;
+ struct device *dev;
+ u64 ns;
+
+ snprintf(name, PTP_CLOCK_NAME_LEN, "ptp%d", vclock_index);
+ dev = class_find_device_by_name(ptp_class, name);
+ if (!dev)
+ return;
+
+ ptp = dev_get_drvdata(dev);
+ if (!ptp->is_virtual_clock) {
+ put_device(dev);
+ return;
+ }
+
+ vclock = info_to_vclock(ptp->info);
+
+ ns = ktime_to_ns(hwtstamps->hwtstamp);
+
+ spin_lock_irqsave(&vclock->lock, flags);
+ ns = timecounter_cyc2time(&vclock->tc, ns);
+ spin_unlock_irqrestore(&vclock->lock, flags);
+
+ put_device(dev);
+ hwtstamps->hwtstamp = ns_to_ktime(ns);
+}
+EXPORT_SYMBOL(ptp_convert_timestamp);
return 0;
}
- if (state->period != pwm->state.period ||
- state->duty_cycle != pwm->state.duty_cycle) {
- err = berlin_pwm_config(chip, pwm, state->duty_cycle, state->period);
- if (err)
- return err;
- }
+ err = berlin_pwm_config(chip, pwm, state->duty_cycle, state->period);
+ if (err)
+ return err;
if (!enabled)
return berlin_pwm_enable(chip, pwm);
int ret;
struct ep93xx_pwm *ep93xx_pwm = to_ep93xx_pwm(chip);
bool enabled = state->enabled;
+ void __iomem *base = ep93xx_pwm->base;
+ unsigned long long c;
+ unsigned long period_cycles;
+ unsigned long duty_cycles;
+ unsigned long term;
if (state->polarity != pwm->state.polarity) {
if (enabled) {
return 0;
}
- if (state->period != pwm->state.period ||
- state->duty_cycle != pwm->state.duty_cycle) {
- struct ep93xx_pwm *ep93xx_pwm = to_ep93xx_pwm(chip);
- void __iomem *base = ep93xx_pwm->base;
- unsigned long long c;
- unsigned long period_cycles;
- unsigned long duty_cycles;
- unsigned long term;
+ /*
+ * The clock needs to be enabled to access the PWM registers.
+ * Configuration can be changed at any time.
+ */
+ if (!pwm_is_enabled(pwm)) {
+ ret = clk_prepare_enable(ep93xx_pwm->clk);
+ if (ret)
+ return ret;
+ }
- /*
- * The clock needs to be enabled to access the PWM registers.
- * Configuration can be changed at any time.
- */
- if (!pwm_is_enabled(pwm)) {
- ret = clk_prepare_enable(ep93xx_pwm->clk);
- if (ret)
- return ret;
- }
+ c = clk_get_rate(ep93xx_pwm->clk);
+ c *= state->period;
+ do_div(c, 1000000000);
+ period_cycles = c;
+
+ c = period_cycles;
+ c *= state->duty_cycle;
+ do_div(c, state->period);
+ duty_cycles = c;
- c = clk_get_rate(ep93xx_pwm->clk);
- c *= state->period;
- do_div(c, 1000000000);
- period_cycles = c;
-
- c = period_cycles;
- c *= state->duty_cycle;
- do_div(c, state->period);
- duty_cycles = c;
-
- if (period_cycles < 0x10000 && duty_cycles < 0x10000) {
- term = readw(base + EP93XX_PWMx_TERM_COUNT);
-
- /* Order is important if PWM is running */
- if (period_cycles > term) {
- writew(period_cycles, base + EP93XX_PWMx_TERM_COUNT);
- writew(duty_cycles, base + EP93XX_PWMx_DUTY_CYCLE);
- } else {
- writew(duty_cycles, base + EP93XX_PWMx_DUTY_CYCLE);
- writew(period_cycles, base + EP93XX_PWMx_TERM_COUNT);
- }
- ret = 0;
+ if (period_cycles < 0x10000 && duty_cycles < 0x10000) {
+ term = readw(base + EP93XX_PWMx_TERM_COUNT);
+
+ /* Order is important if PWM is running */
+ if (period_cycles > term) {
+ writew(period_cycles, base + EP93XX_PWMx_TERM_COUNT);
+ writew(duty_cycles, base + EP93XX_PWMx_DUTY_CYCLE);
} else {
- ret = -EINVAL;
+ writew(duty_cycles, base + EP93XX_PWMx_DUTY_CYCLE);
+ writew(period_cycles, base + EP93XX_PWMx_TERM_COUNT);
}
+ ret = 0;
+ } else {
+ ret = -EINVAL;
+ }
- if (!pwm_is_enabled(pwm))
- clk_disable_unprepare(ep93xx_pwm->clk);
+ if (!pwm_is_enabled(pwm))
+ clk_disable_unprepare(ep93xx_pwm->clk);
- if (ret)
- return ret;
- }
+ if (ret)
+ return ret;
if (!enabled) {
ret = clk_prepare_enable(ep93xx_pwm->clk);
return 0;
}
- if (state->period != pwm->state.period ||
- state->duty_cycle != pwm->state.duty_cycle) {
- err = spear_pwm_config(chip, pwm, state->duty_cycle, state->period);
- if (err)
- return err;
- }
+ err = spear_pwm_config(chip, pwm, state->duty_cycle, state->period);
+ if (err)
+ return err;
if (!pwm->state.enabled)
return spear_pwm_enable(chip, pwm);
}
}
- if (state->period != cstate->period ||
- state->duty_cycle != cstate->duty_cycle) {
- ret = sprd_pwm_config(spc, pwm, state->duty_cycle,
- state->period);
- if (ret)
- return ret;
- }
+ ret = sprd_pwm_config(spc, pwm, state->duty_cycle,
+ state->period);
+ if (ret)
+ return ret;
sprd_pwm_write(spc, pwm->hwpwm, SPRD_PWM_ENABLE, 1);
} else if (cstate->enabled) {
return 0;
}
- if (state->period != pwm->state.period ||
- state->duty_cycle != pwm->state.duty_cycle) {
- if (state->period > NSEC_PER_SEC)
- return -ERANGE;
+ if (state->period > NSEC_PER_SEC)
+ return -ERANGE;
- err = ecap_pwm_config(chip, pwm, state->duty_cycle,
- state->period, enabled);
- if (err)
- return err;
- }
+ err = ecap_pwm_config(chip, pwm, state->duty_cycle,
+ state->period, enabled);
+ if (err)
+ return err;
if (!enabled)
return ecap_pwm_enable(chip, pwm);
struct bd957x_regulator_data *r)
{
if ((severity == REGULATOR_SEVERITY_ERR &&
- r->ovd_notif != REGULATOR_EVENT_OVER_TEMP) ||
+ r->temp_notif != REGULATOR_EVENT_OVER_TEMP) ||
(severity == REGULATOR_SEVERITY_WARN &&
- r->ovd_notif != REGULATOR_EVENT_OVER_TEMP_WARN)) {
+ r->temp_notif != REGULATOR_EVENT_OVER_TEMP_WARN)) {
dev_warn(rdev_get_dev(rdev),
"Can't support both thermal WARN and ERR\n");
if (severity == REGULATOR_SEVERITY_WARN)
static int hi6421_regulator_enable(struct regulator_dev *rdev)
{
- struct hi6421_regulator_pdata *pdata;
+ struct hi6421_regulator_pdata *pdata = rdev_get_drvdata(rdev);
- pdata = dev_get_drvdata(rdev->dev.parent);
/* hi6421 spec requires regulator enablement must be serialized:
* - Because when BUCK, LDO switching from off to on, it will have
* a huge instantaneous current; so you can not turn on two or
static unsigned int hi6421_regulator_ldo_get_mode(struct regulator_dev *rdev)
{
- struct hi6421_regulator_info *info = rdev_get_drvdata(rdev);
+ struct hi6421_regulator_info *info;
unsigned int reg_val;
+ info = container_of(rdev->desc, struct hi6421_regulator_info, desc);
regmap_read(rdev->regmap, rdev->desc->enable_reg, ®_val);
if (reg_val & info->mode_mask)
return REGULATOR_MODE_IDLE;
static unsigned int hi6421_regulator_buck_get_mode(struct regulator_dev *rdev)
{
- struct hi6421_regulator_info *info = rdev_get_drvdata(rdev);
+ struct hi6421_regulator_info *info;
unsigned int reg_val;
+ info = container_of(rdev->desc, struct hi6421_regulator_info, desc);
regmap_read(rdev->regmap, rdev->desc->enable_reg, ®_val);
if (reg_val & info->mode_mask)
return REGULATOR_MODE_STANDBY;
static int hi6421_regulator_ldo_set_mode(struct regulator_dev *rdev,
unsigned int mode)
{
- struct hi6421_regulator_info *info = rdev_get_drvdata(rdev);
+ struct hi6421_regulator_info *info;
unsigned int new_mode;
+ info = container_of(rdev->desc, struct hi6421_regulator_info, desc);
switch (mode) {
case REGULATOR_MODE_NORMAL:
new_mode = 0;
static int hi6421_regulator_buck_set_mode(struct regulator_dev *rdev,
unsigned int mode)
{
- struct hi6421_regulator_info *info = rdev_get_drvdata(rdev);
+ struct hi6421_regulator_info *info;
unsigned int new_mode;
+ info = container_of(rdev->desc, struct hi6421_regulator_info, desc);
switch (mode) {
case REGULATOR_MODE_NORMAL:
new_mode = 0;
hi6421_regulator_ldo_get_optimum_mode(struct regulator_dev *rdev,
int input_uV, int output_uV, int load_uA)
{
- struct hi6421_regulator_info *info = rdev_get_drvdata(rdev);
+ struct hi6421_regulator_info *info;
+
+ info = container_of(rdev->desc, struct hi6421_regulator_info, desc);
if (load_uA > info->eco_microamp)
return REGULATOR_MODE_NORMAL;
if (!pdata)
return -ENOMEM;
mutex_init(&pdata->lock);
- platform_set_drvdata(pdev, pdata);
for (i = 0; i < ARRAY_SIZE(hi6421_regulator_info); i++) {
/* assign per-regulator data */
info = &hi6421_regulator_info[i];
config.dev = pdev->dev.parent;
- config.driver_data = info;
+ config.driver_data = pdata;
config.regmap = pmic->regmap;
rdev = devm_regulator_register(&pdev->dev, &info->desc,
static int hi6421_spmi_regulator_enable(struct regulator_dev *rdev)
{
- struct hi6421_spmi_reg_priv *priv;
+ struct hi6421_spmi_reg_priv *priv = rdev_get_drvdata(rdev);
int ret;
- priv = dev_get_drvdata(rdev->dev.parent);
/* cannot enable more than one regulator at one time */
mutex_lock(&priv->enable_mutex);
static unsigned int hi6421_spmi_regulator_get_mode(struct regulator_dev *rdev)
{
- struct hi6421_spmi_reg_info *sreg = rdev_get_drvdata(rdev);
+ struct hi6421_spmi_reg_info *sreg;
unsigned int reg_val;
+ sreg = container_of(rdev->desc, struct hi6421_spmi_reg_info, desc);
regmap_read(rdev->regmap, rdev->desc->enable_reg, ®_val);
if (reg_val & sreg->eco_mode_mask)
static int hi6421_spmi_regulator_set_mode(struct regulator_dev *rdev,
unsigned int mode)
{
- struct hi6421_spmi_reg_info *sreg = rdev_get_drvdata(rdev);
+ struct hi6421_spmi_reg_info *sreg;
unsigned int val;
+ sreg = container_of(rdev->desc, struct hi6421_spmi_reg_info, desc);
switch (mode) {
case REGULATOR_MODE_NORMAL:
val = 0;
int input_uV, int output_uV,
int load_uA)
{
- struct hi6421_spmi_reg_info *sreg = rdev_get_drvdata(rdev);
+ struct hi6421_spmi_reg_info *sreg;
+
+ sreg = container_of(rdev->desc, struct hi6421_spmi_reg_info, desc);
if (!sreg->eco_uA || ((unsigned int)load_uA > sreg->eco_uA))
return REGULATOR_MODE_NORMAL;
return -ENOMEM;
mutex_init(&priv->enable_mutex);
- platform_set_drvdata(pdev, priv);
for (i = 0; i < ARRAY_SIZE(regulator_info); i++) {
info = ®ulator_info[i];
config.dev = pdev->dev.parent;
- config.driver_data = info;
+ config.driver_data = priv;
config.regmap = pmic->regmap;
rdev = devm_regulator_register(dev, &info->desc, &config);
for (i = 0; i < regulator_init_data->size; i++) {
config.dev = dev->parent;
config.driver_data = (mt_regulators + i);
- rdev = devm_regulator_register(dev->parent,
- &(mt_regulators + i)->desc,
+ rdev = devm_regulator_register(dev, &(mt_regulators + i)->desc,
&config);
if (IS_ERR(rdev)) {
dev_err(dev, "failed to register %s\n",
#define RTMV20_WIDTH2_MASK GENMASK(7, 0)
#define RTMV20_LBPLVL_MASK GENMASK(3, 0)
#define RTMV20_LBPEN_MASK BIT(7)
-#define RTMV20_STROBEPOL_MASK BIT(1)
+#define RTMV20_STROBEPOL_MASK BIT(0)
#define RTMV20_VSYNPOL_MASK BIT(1)
#define RTMV20_FSINEN_MASK BIT(7)
#define RTMV20_ESEN_MASK BIT(6)
static void dasd_eckd_store_conf_data(struct dasd_device *device,
struct dasd_conf_data *conf_data, int chp)
{
+ struct dasd_eckd_private *private = device->private;
struct channel_path_desc_fmt0 *chp_desc;
struct subchannel_id sch_id;
+ void *cdp;
- ccw_device_get_schid(device->cdev, &sch_id);
/*
* path handling and read_conf allocate data
* free it before replacing the pointer
+ * also replace the old private->conf_data pointer
+ * with the new one if this points to the same data
*/
- kfree(device->path[chp].conf_data);
+ cdp = device->path[chp].conf_data;
+ if (private->conf_data == cdp) {
+ private->conf_data = (void *)conf_data;
+ dasd_eckd_identify_conf_parts(private);
+ }
+ ccw_device_get_schid(device->cdev, &sch_id);
device->path[chp].conf_data = conf_data;
device->path[chp].cssid = sch_id.cssid;
device->path[chp].ssid = sch_id.ssid;
if (chp_desc)
device->path[chp].chpid = chp_desc->chpid;
kfree(chp_desc);
+ kfree(cdp);
}
static void dasd_eckd_clear_conf_data(struct dasd_device *device)
case MTSEEK:
if (device->required_tapemarks)
tape_std_terminate_write(device);
- default:
- ;
}
rc = tape_mtop(device, op.mt_op, op.mt_count);
get_ccwdev_lock(ch->cdev), saveflags);
if (rc != 0)
ctcm_ccw_check_rc(ch, rc, "normal RX");
+ break;
default:
break;
}
if (qeth_is_ipafunc_supported(card, prot,
IPA_OSA_MC_ROUTER))
return 0;
+ goto out_inval;
default:
goto out_inval;
}
if (0 == (status & ZFCP_STATUS_COMMON_OPEN) ||
0 == (status & ZFCP_STATUS_COMMON_UNBLOCKED) ||
0 == (status & ZFCP_STATUS_PORT_PHYS_OPEN) ||
+ 0 != (status & ZFCP_STATUS_PORT_LINK_TEST) ||
0 != (status & ZFCP_STATUS_COMMON_ERP_FAILED) ||
0 != (status & ZFCP_STATUS_COMMON_ACCESS_BOXED))
i = sprintf(buf, "unknown\n");
//#endif
clear_bit(SCpnt->device->id * 8 +
(u8)(SCpnt->device->lun & 0x7), host->busyluns);
+ fallthrough;
/*
* We found the command, and cleared it out. Either
case IS_COMPLETE:
break;
}
+ break;
default:
break;
"request sense complete, result=0x%04x%02x%02x",
result, SCpnt->SCp.Message, SCpnt->SCp.Status);
- if (result != DID_OK || SCpnt->SCp.Status != GOOD)
+ if (result != DID_OK || SCpnt->SCp.Status != SAM_STAT_GOOD)
/*
* Something went wrong. Make sure that we don't
* have valid data in the sense buffer that could
if (!h->ctlr)
err = SCSI_DH_RES_TEMP_UNAVAIL;
else {
- list_add_rcu(&h->node, &h->ctlr->dh_list);
h->sdev = sdev;
+ list_add_rcu(&h->node, &h->ctlr->dh_list);
}
spin_unlock(&list_lock);
err = SCSI_DH_OK;
spin_lock(&list_lock);
if (h->ctlr) {
list_del_rcu(&h->node);
- h->sdev = NULL;
kref_put(&h->ctlr->kref, release_controller);
}
spin_unlock(&list_lock);
sdev->handler_data = NULL;
+ synchronize_rcu();
kfree(h);
}
shost_printk(KERN_WARNING, shost,
"error handler thread failed to spawn, error = %ld\n",
PTR_ERR(shost->ehandler));
+ shost->ehandler = NULL;
goto fail;
}
for (i = 0; i < size; ++i) {
struct ibmvfc_event *evt = &pool->events[i];
+ /*
+ * evt->active states
+ * 1 = in flight
+ * 0 = being completed
+ * -1 = free/freed
+ */
+ atomic_set(&evt->active, -1);
atomic_set(&evt->free, 1);
evt->crq.valid = 0x80;
evt->crq.ioba = cpu_to_be64(pool->iu_token + (sizeof(*evt->xfer_iu) * i));
BUG_ON(!ibmvfc_valid_event(pool, evt));
BUG_ON(atomic_inc_return(&evt->free) != 1);
+ BUG_ON(atomic_dec_and_test(&evt->active));
spin_lock_irqsave(&evt->queue->l_lock, flags);
list_add_tail(&evt->queue_list, &evt->queue->free);
**/
static void ibmvfc_fail_request(struct ibmvfc_event *evt, int error_code)
{
+ /*
+ * Anything we are failing should still be active. Otherwise, it
+ * implies we already got a response for the command and are doing
+ * something bad like double completing it.
+ */
+ BUG_ON(!atomic_dec_and_test(&evt->active));
if (evt->cmnd) {
evt->cmnd->result = (error_code << 16);
evt->done = ibmvfc_scsi_eh_done;
evt->done(evt);
} else {
+ atomic_set(&evt->active, 1);
spin_unlock_irqrestore(&evt->queue->l_lock, flags);
ibmvfc_trc_start(evt);
}
return;
}
- if (unlikely(atomic_read(&evt->free))) {
+ if (unlikely(atomic_dec_if_positive(&evt->active))) {
dev_err(vhost->dev, "Received duplicate correlation_token 0x%08llx!\n",
crq->ioba);
return;
return;
}
- if (unlikely(atomic_read(&evt->free))) {
+ if (unlikely(atomic_dec_if_positive(&evt->active))) {
dev_err(vhost->dev, "Received duplicate correlation_token 0x%08llx!\n",
crq->ioba);
return;
struct ibmvfc_target *tgt;
struct scsi_cmnd *cmnd;
atomic_t free;
+ atomic_t active;
union ibmvfc_iu *xfer_iu;
void (*done)(struct ibmvfc_event *evt);
void (*_done)(struct ibmvfc_event *evt);
break;
#else
pr_notice("ATA device seen but CONFIG_SCSI_SAS_ATA=N so cannot attach\n");
- /* Fall through */
+ fallthrough;
#endif
/* Fall through - only for the #else condition above. */
default:
mimd_t mimd;
uint32_t adapno;
int iterator;
-
+ bool is_found;
if (copy_from_user(&mimd, umimd, sizeof(mimd_t))) {
*rval = -EFAULT;
adapter = NULL;
iterator = 0;
+ is_found = false;
list_for_each_entry(adapter, &adapters_list_g, list) {
- if (iterator++ == adapno) break;
+ if (iterator++ == adapno) {
+ is_found = true;
+ break;
+ }
}
- if (!adapter) {
+ if (!is_found) {
*rval = -ENODEV;
return NULL;
}
uint32_t adapno;
int iterator;
mraid_mmadp_t* adapter;
+ bool is_found;
/*
* When the kioc returns from driver, make sure it still doesn't
iterator = 0;
adapter = NULL;
adapno = kioc->adapno;
+ is_found = false;
con_log(CL_ANN, ( KERN_WARNING "megaraid cmm: completed "
"ioctl that was timedout before\n"));
list_for_each_entry(adapter, &adapters_list_g, list) {
- if (iterator++ == adapno) break;
+ if (iterator++ == adapno) {
+ is_found = true;
+ break;
+ }
}
kioc->timedout = 0;
- if (adapter) {
+ if (is_found)
mraid_mm_dealloc_kioc( adapter, kioc );
- }
+
}
else {
wake_up(&wait_q);
goto out;
}
drv_info->information_length = cpu_to_le32(data_len);
- strncpy(drv_info->driver_signature, "Broadcom", sizeof(drv_info->driver_signature));
- strncpy(drv_info->os_name, utsname()->sysname, sizeof(drv_info->os_name));
- drv_info->os_name[sizeof(drv_info->os_name) - 1] = 0;
- strncpy(drv_info->os_version, utsname()->release, sizeof(drv_info->os_version));
- drv_info->os_version[sizeof(drv_info->os_version) - 1] = 0;
- strncpy(drv_info->driver_name, MPI3MR_DRIVER_NAME, sizeof(drv_info->driver_name));
- strncpy(drv_info->driver_version, MPI3MR_DRIVER_VERSION, sizeof(drv_info->driver_version));
- strncpy(drv_info->driver_release_date, MPI3MR_DRIVER_RELDATE, sizeof(drv_info->driver_release_date));
+ strscpy(drv_info->driver_signature, "Broadcom", sizeof(drv_info->driver_signature));
+ strscpy(drv_info->os_name, utsname()->sysname, sizeof(drv_info->os_name));
+ strscpy(drv_info->os_version, utsname()->release, sizeof(drv_info->os_version));
+ strscpy(drv_info->driver_name, MPI3MR_DRIVER_NAME, sizeof(drv_info->driver_name));
+ strscpy(drv_info->driver_version, MPI3MR_DRIVER_VERSION, sizeof(drv_info->driver_version));
+ strscpy(drv_info->driver_release_date, MPI3MR_DRIVER_RELDATE,
+ sizeof(drv_info->driver_release_date));
drv_info->driver_capabilities = 0;
memcpy((u8 *)&mrioc->driver_info, (u8 *)drv_info,
sizeof(mrioc->driver_info));
}
/**
- * _base_free_irq - free irq
+ * mpt3sas_base_free_irq - free irq
* @ioc: per adapter object
*
* Freeing respective reply_queue from the list.
*/
-static void
-_base_free_irq(struct MPT3SAS_ADAPTER *ioc)
+void
+mpt3sas_base_free_irq(struct MPT3SAS_ADAPTER *ioc)
{
struct adapter_reply_queue *reply_q, *next;
}
/**
- * _base_disable_msix - disables msix
+ * mpt3sas_base_disable_msix - disables msix
* @ioc: per adapter object
*
*/
-static void
-_base_disable_msix(struct MPT3SAS_ADAPTER *ioc)
+void
+mpt3sas_base_disable_msix(struct MPT3SAS_ADAPTER *ioc)
{
if (!ioc->msix_enable)
return;
for (i = 0; i < ioc->reply_queue_count; i++) {
r = _base_request_irq(ioc, i);
if (r) {
- _base_free_irq(ioc);
- _base_disable_msix(ioc);
+ mpt3sas_base_free_irq(ioc);
+ mpt3sas_base_disable_msix(ioc);
goto try_ioapic;
}
}
dexitprintk(ioc, ioc_info(ioc, "%s\n", __func__));
- _base_free_irq(ioc);
- _base_disable_msix(ioc);
+ mpt3sas_base_free_irq(ioc);
+ mpt3sas_base_disable_msix(ioc);
kfree(ioc->replyPostRegisterIndex);
ioc->replyPostRegisterIndex = NULL;
}
/**
- * _base_make_ioc_ready - put controller in READY state
+ * mpt3sas_base_make_ioc_ready - put controller in READY state
* @ioc: per adapter object
* @type: FORCE_BIG_HAMMER or SOFT_RESET
*
* Return: 0 for success, non-zero for failure.
*/
-static int
-_base_make_ioc_ready(struct MPT3SAS_ADAPTER *ioc, enum reset_type type)
+int
+mpt3sas_base_make_ioc_ready(struct MPT3SAS_ADAPTER *ioc, enum reset_type type)
{
u32 ioc_state;
int rc;
if (ioc->chip_phys && ioc->chip) {
mpt3sas_base_mask_interrupts(ioc);
ioc->shost_recovery = 1;
- _base_make_ioc_ready(ioc, SOFT_RESET);
+ mpt3sas_base_make_ioc_ready(ioc, SOFT_RESET);
ioc->shost_recovery = 0;
}
ioc->build_sg_mpi = &_base_build_sg;
ioc->build_zero_len_sge_mpi = &_base_build_zero_len_sge;
- r = _base_make_ioc_ready(ioc, SOFT_RESET);
+ r = mpt3sas_base_make_ioc_ready(ioc, SOFT_RESET);
if (r)
goto out_free_resources;
_base_pre_reset_handler(ioc);
mpt3sas_wait_for_commands_to_complete(ioc);
mpt3sas_base_mask_interrupts(ioc);
- r = _base_make_ioc_ready(ioc, type);
+ r = mpt3sas_base_make_ioc_ready(ioc, type);
if (r)
goto out;
_base_clear_outstanding_commands(ioc);
status, mpi_request, sz); } while (0)
int mpt3sas_wait_for_ioc(struct MPT3SAS_ADAPTER *ioc, int wait_count);
+int
+mpt3sas_base_make_ioc_ready(struct MPT3SAS_ADAPTER *ioc, enum reset_type type);
+void mpt3sas_base_free_irq(struct MPT3SAS_ADAPTER *ioc);
+void mpt3sas_base_disable_msix(struct MPT3SAS_ADAPTER *ioc);
/* scsih shared API */
struct scsi_cmnd *mpt3sas_scsih_scsi_lookup_get(struct MPT3SAS_ADAPTER *ioc,
_scsih_ir_shutdown(ioc);
_scsih_nvme_shutdown(ioc);
- mpt3sas_base_detach(ioc);
+ mpt3sas_base_mask_interrupts(ioc);
+ ioc->shost_recovery = 1;
+ mpt3sas_base_make_ioc_ready(ioc, SOFT_RESET);
+ ioc->shost_recovery = 0;
+ mpt3sas_base_free_irq(ioc);
+ mpt3sas_base_disable_msix(ioc);
}
* @attr: device attribute (unused)
* @buf: the buffer returned
*
- * A sysfs 'read only' shost attribute.
+ * A sysfs 'read-only' shost attribute.
*/
static ssize_t controller_fatal_error_show(struct device *cdev,
struct device_attribute *attr, char *buf)
static DEVICE_ATTR(ila_version, 0444, pm8001_ctl_ila_version_show, NULL);
/**
- * pm8001_ctl_inactive_fw_version_show - Inacative firmware version number
+ * pm8001_ctl_inactive_fw_version_show - Inactive firmware version number
* @cdev: pointer to embedded class device
* @attr: device attribute (unused)
* @buf: the buffer returned
* @cdev:pointer to embedded class device
* @attr: device attribute (unused)
* @buf: the buffer returned
+ *
* A sysfs 'read-only' shost attribute.
*/
static ssize_t pm8001_ctl_ib_queue_log_show(struct device *cdev,
* @cdev:pointer to embedded class device
* @attr: device attribute (unused)
* @buf: the buffer returned
+ *
* A sysfs 'read-only' shost attribute.
*/
* @cdev:pointer to embedded class device
* @attr: device attribute (unused)
* @buf:the buffer returned
+ *
* A sysfs 'read-only' shost attribute.
*/
static ssize_t pm8001_ctl_bios_version_show(struct device *cdev,
static DEVICE_ATTR(iop_log, S_IRUGO, pm8001_ctl_iop_log_show, NULL);
/**
- ** pm8001_ctl_fatal_log_show - fatal error logging
- ** @cdev:pointer to embedded class device
- ** @attr: device attribute
- ** @buf: the buffer returned
- **
- ** A sysfs 'read-only' shost attribute.
- **/
+ * pm8001_ctl_fatal_log_show - fatal error logging
+ * @cdev:pointer to embedded class device
+ * @attr: device attribute
+ * @buf: the buffer returned
+ *
+ * A sysfs 'read-only' shost attribute.
+ */
static ssize_t pm8001_ctl_fatal_log_show(struct device *cdev,
struct device_attribute *attr, char *buf)
static DEVICE_ATTR(fatal_log, S_IRUGO, pm8001_ctl_fatal_log_show, NULL);
/**
- ** non_fatal_log_show - non fatal error logging
- ** @cdev:pointer to embedded class device
- ** @attr: device attribute
- ** @buf: the buffer returned
- **
- ** A sysfs 'read-only' shost attribute.
- **/
+ * non_fatal_log_show - non fatal error logging
+ * @cdev:pointer to embedded class device
+ * @attr: device attribute
+ * @buf: the buffer returned
+ *
+ * A sysfs 'read-only' shost attribute.
+ */
static ssize_t non_fatal_log_show(struct device *cdev,
struct device_attribute *attr, char *buf)
{
static DEVICE_ATTR_RW(non_fatal_count);
/**
- ** pm8001_ctl_gsm_log_show - gsm dump collection
- ** @cdev:pointer to embedded class device
- ** @attr: device attribute (unused)
- ** @buf: the buffer returned
- ** A sysfs 'read-only' shost attribute.
- **/
+ * pm8001_ctl_gsm_log_show - gsm dump collection
+ * @cdev:pointer to embedded class device
+ * @attr: device attribute (unused)
+ * @buf: the buffer returned
+ *
+ * A sysfs 'read-only' shost attribute.
+ */
static ssize_t pm8001_ctl_gsm_log_show(struct device *cdev,
struct device_attribute *attr, char *buf)
{
/**
* pm8001_bar4_shift - function is called to shift BAR base address
- * @pm8001_ha : our hba card infomation
+ * @pm8001_ha : our hba card information
* @shiftValue : shifting value in memory bar.
*/
int pm8001_bar4_shift(struct pm8001_hba_info *pm8001_ha, u32 shiftValue)
}
/**
- * pm8001_chip_iounmap - which maped when initialized.
+ * pm8001_chip_iounmap - which mapped when initialized.
* @pm8001_ha: our hba card information
*/
void pm8001_chip_iounmap(struct pm8001_hba_info *pm8001_ha)
pm8001_cw32(pm8001_ha, 0, MSGU_ODCR, ODCR_CLEAR_ALL);
}
- /**
- * pm8001_chip_intx_interrupt_disable- disable PM8001 chip interrupt
- * @pm8001_ha: our hba card information
- */
+/**
+ * pm8001_chip_intx_interrupt_disable - disable PM8001 chip interrupt
+ * @pm8001_ha: our hba card information
+ */
static void
pm8001_chip_intx_interrupt_disable(struct pm8001_hba_info *pm8001_ha)
{
* @piomb: the message contents of this outbound message.
*
* When FW has completed a ssp request for example a IO request, after it has
- * filled the SG data with the data, it will trigger this event represent
- * that he has finished the job,please check the coresponding buffer.
+ * filled the SG data with the data, it will trigger this event representing
+ * that he has finished the job; please check the corresponding buffer.
* So we will tell the caller who maybe waiting the result to tell upper layer
* that the task has been finished.
*/
*
* when sas layer find a device it will notify LLDD, then the driver register
* the domain device to FW, this event is the return device ID which the FW
- * has assigned, from now,inter-communication with FW is no longer using the
+ * has assigned, from now, inter-communication with FW is no longer using the
* SAS address, use device ID which FW assigned.
*/
int pm8001_mpi_reg_resp(struct pm8001_hba_info *pm8001_ha, void *piomb)
/**
* pm8001_interrupt_handler_intx - main INTx interrupt handler.
* @irq: interrupt number
- * @dev_id: sas_ha structure. The HBA is retrieved from sas_has structure.
+ * @dev_id: sas_ha structure. The HBA is retrieved from sas_ha structure.
*/
static irqreturn_t pm8001_interrupt_handler_intx(int irq, void *dev_id)
}
/**
- * pm8001_ioremap - remap the pci high physical address to kernal virtual
+ * pm8001_ioremap - remap the pci high physical address to kernel virtual
* address so that we can access them.
- * @pm8001_ha:our hba structure.
+ * @pm8001_ha: our hba structure.
*/
static int pm8001_ioremap(struct pm8001_hba_info *pm8001_ha)
{
* pm8001_init_sas_add - initialize sas address
* @pm8001_ha: our ha struct.
*
- * Currently we just set the fixed SAS address to our HBA,for manufacture,
+ * Currently we just set the fixed SAS address to our HBA, for manufacture,
* it should read from the EEPROM
*/
static void pm8001_init_sas_add(struct pm8001_hba_info *pm8001_ha)
};
/**
- * pm8001_get_internal_phy_settings : Retrieves the internal PHY settings
+ * pm8001_get_internal_phy_settings - Retrieves the internal PHY settings
* @pm8001_ha : our adapter
* @phycfg : PHY config page to populate
*/
}
/**
- * pm8001_get_external_phy_settings : Retrieves the external PHY settings
+ * pm8001_get_external_phy_settings - Retrieves the external PHY settings
* @pm8001_ha : our adapter
* @phycfg : PHY config page to populate
*/
}
/**
- * pm8001_get_phy_mask : Retrieves the mask that denotes if a PHY is int/ext
+ * pm8001_get_phy_mask - Retrieves the mask that denotes if a PHY is int/ext
* @pm8001_ha : our adapter
* @phymask : The PHY mask
*/
}
/**
- * pm8001_set_phy_settings_ven_117c_12G() : Configure ATTO 12Gb PHY settings
+ * pm8001_set_phy_settings_ven_117c_12G() - Configure ATTO 12Gb PHY settings
* @pm8001_ha : our adapter
*/
static
}
/**
- * pm8001_configure_phy_settings : Configures PHY settings based on vendor ID.
+ * pm8001_configure_phy_settings - Configures PHY settings based on vendor ID.
* @pm8001_ha : our hba.
*/
static int pm8001_configure_phy_settings(struct pm8001_hba_info *pm8001_ha)
* @ent: pci device id
*
* This function is the main initialization function, when register a new
- * pci driver it is invoked, all struct an hardware initilization should be done
- * here, also, register interrupt
+ * pci driver it is invoked, all struct and hardware initialization should be
+ * done here, also, register interrupt.
*/
static int pm8001_pci_probe(struct pci_dev *pdev,
const struct pci_device_id *ent)
return rc;
}
-/*
+/**
* pm8001_init_ccb_tag - allocate memory to CCB and tag.
* @pm8001_ha: our hba card information.
* @shost: scsi host which has been allocated outside.
+ * @pdev: pci device.
*/
static int
pm8001_init_ccb_tag(struct pm8001_hba_info *pm8001_ha, struct Scsi_Host *shost,
* pm8001_pci_suspend - power management suspend main entry point
* @dev: Device struct
*
- * Returns 0 success, anything else error.
+ * Return: 0 on success, anything else on error.
*/
static int __maybe_unused pm8001_pci_suspend(struct device *dev)
{
* pm8001_pci_resume - power management resume main entry point
* @dev: Device struct
*
- * Returns 0 success, anything else error.
+ * Return: 0 on success, anything else on error.
*/
static int __maybe_unused pm8001_pci_resume(struct device *dev)
{
pm8001_tag_free(pm8001_ha, i);
}
- /**
- * pm8001_mem_alloc - allocate memory for pm8001.
- * @pdev: pci device.
- * @virt_addr: the allocated virtual address
- * @pphys_addr_hi: the physical address high byte address.
- * @pphys_addr_lo: the physical address low byte address.
- * @mem_size: memory size.
- */
+/**
+ * pm8001_mem_alloc - allocate memory for pm8001.
+ * @pdev: pci device.
+ * @virt_addr: the allocated virtual address
+ * @pphys_addr: DMA address for this device
+ * @pphys_addr_hi: the physical address high byte address.
+ * @pphys_addr_lo: the physical address low byte address.
+ * @mem_size: memory size.
+ * @align: requested byte alignment
+ */
int pm8001_mem_alloc(struct pci_dev *pdev, void **virt_addr,
dma_addr_t *pphys_addr, u32 *pphys_addr_hi,
u32 *pphys_addr_lo, u32 mem_size, u32 align)
}
/**
- * pm8001_task_prep_ssp - the dispatcher function,prepare ssp data for ssp task
+ * pm8001_task_prep_ssp - the dispatcher function, prepare ssp data for ssp task
* @pm8001_ha: our hba card information
* @ccb: the ccb which attached to ssp task
*/
pm8001_tag_free(pm8001_ha, ccb_idx);
}
- /**
- * pm8001_alloc_dev - find a empty pm8001_device
- * @pm8001_ha: our hba card information
- */
+/**
+ * pm8001_alloc_dev - find a empty pm8001_device
+ * @pm8001_ha: our hba card information
+ */
static struct pm8001_device *pm8001_alloc_dev(struct pm8001_hba_info *pm8001_ha)
{
u32 dev;
void pm8001_task_done(struct sas_task *task)
{
- if (!del_timer(&task->slow_task->timer))
- return;
+ del_timer(&task->slow_task->timer);
complete(&task->slow_task->completion);
}
{
struct sas_task_slow *slow = from_timer(slow, t, timer);
struct sas_task *task = slow->task;
+ unsigned long flags;
- task->task_state_flags |= SAS_TASK_STATE_ABORTED;
- complete(&task->slow_task->completion);
+ spin_lock_irqsave(&task->task_state_lock, flags);
+ if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) {
+ task->task_state_flags |= SAS_TASK_STATE_ABORTED;
+ complete(&task->slow_task->completion);
+ }
+ spin_unlock_irqrestore(&task->task_state_lock, flags);
}
#define PM8001_TASK_TIMEOUT 20
* @parameter: ssp task parameter.
*
* when errors or exception happened, we may want to do something, for example
- * abort the issued task which result in this execption, it is done by calling
+ * abort the issued task which result in this exception, it is done by calling
* this function, note it is also with the task execute interface.
*/
static int pm8001_exec_internal_tmf_task(struct domain_device *dev,
}
res = -TMF_RESP_FUNC_FAILED;
/* Even TMF timed out, return direct. */
- if ((task->task_state_flags & SAS_TASK_STATE_ABORTED)) {
- if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) {
- pm8001_dbg(pm8001_ha, FAIL,
- "TMF task[%x]timeout.\n",
- tmf->tmf);
- goto ex_err;
- }
+ if (task->task_state_flags & SAS_TASK_STATE_ABORTED) {
+ pm8001_dbg(pm8001_ha, FAIL, "TMF task[%x]timeout.\n",
+ tmf->tmf);
+ goto ex_err;
}
if (task->task_status.resp == SAS_TASK_COMPLETE &&
wait_for_completion(&task->slow_task->completion);
res = TMF_RESP_FUNC_FAILED;
/* Even TMF timed out, return direct. */
- if ((task->task_state_flags & SAS_TASK_STATE_ABORTED)) {
- if (!(task->task_state_flags & SAS_TASK_STATE_DONE)) {
- pm8001_dbg(pm8001_ha, FAIL,
- "TMF task timeout.\n");
- goto ex_err;
- }
+ if (task->task_state_flags & SAS_TASK_STATE_ABORTED) {
+ pm8001_dbg(pm8001_ha, FAIL, "TMF task timeout.\n");
+ goto ex_err;
}
if (task->task_status.resp == SAS_TASK_COMPLETE &&
}
/**
- * pm8001_I_T_nexus_reset()
- * Standard mandates link reset for ATA (type 0) and hard reset for
- * SSP (type 1) , only for RECOVERY
- * @dev: the device structure for the device to reset.
- */
+ * pm8001_I_T_nexus_reset() - reset the initiator/target connection
+ * @dev: the device structure for the device to reset.
+ *
+ * Standard mandates link reset for ATA (type 0) and hard reset for
+ * SSP (type 1), only for RECOVERY
+ */
int pm8001_I_T_nexus_reset(struct domain_device *dev)
{
int rc = TMF_RESP_FUNC_FAILED;
pm8001_ha->fatal_bar_loc = 0;
}
- /* Read until accum_len is retrived */
+ /* Read until accum_len is retrieved */
accum_len = pm8001_mr32(fatal_table_address,
MPI_FATAL_EDUMP_TABLE_ACCUM_LEN);
/* Determine length of data between previously stored transfer length
value);
return -EBUSY;
}
- /* check the MPI-State for initialization upto 100ms*/
+ /* check the MPI-State for initialization up to 100ms*/
max_wait_count = 5;/* 100 msec */
do {
msleep(FW_READY_INTERVAL);
value = pm8001_cr32(pm8001_ha, 0, MSGU_SCRATCH_PAD_0);
- /**
+ /*
* lower 26 bits of SCRATCHPAD0 register describes offset within the
* PCIe BAR where the MPI configuration table is present
*/
pm8001_dbg(pm8001_ha, DEV, "Scratchpad 0 Offset: 0x%x value 0x%x\n",
offset, value);
- /**
+ /*
* Upper 6 bits describe the offset within PCI config space where BAR
* is located.
*/
pcibar = get_pci_bar_index(pcilogic);
pm8001_dbg(pm8001_ha, INIT, "Scratchpad 0 PCI BAR: %d\n", pcibar);
- /**
+ /*
* Make sure the offset falls inside the ioremapped PCI BAR
*/
if (offset > pm8001_ha->io_mem[pcibar].memsize) {
pm8001_ha->main_cfg_tbl_addr = base_addr =
pm8001_ha->io_mem[pcibar].memvirtaddr + offset;
- /**
+ /*
* Validate main configuration table address: first DWord should read
* "PMCS"
*/
}
/**
- * pm80xx_encrypt_update - update flash with encryption informtion
+ * pm80xx_encrypt_update - update flash with encryption information
* @pm8001_ha: our hba card information.
*/
static int pm80xx_encrypt_update(struct pm8001_hba_info *pm8001_ha)
}
/**
- * pm80xx_chip_init - the main init function that initialize whole PM8001 chip.
+ * pm80xx_chip_init - the main init function that initializes whole PM8001 chip.
* @pm8001_ha: our hba card information
*/
static int pm80xx_chip_init(struct pm8001_hba_info *pm8001_ha)
}
/**
- * pm80xx_fatal_errors - returns non zero *ONLY* when fatal errors
+ * pm80xx_fatal_errors - returns non-zero *ONLY* when fatal errors
* @pm8001_ha: our hba card information
*
* Fatal errors are recoverable only after a host reboot.
}
/**
- * pm80xx_chip_soft_rst - soft reset the PM8001 chip, so that the clear all
- * the FW register status to the originated status.
+ * pm80xx_chip_soft_rst - soft reset the PM8001 chip, so that all
+ * FW register status are reset to the originated status.
* @pm8001_ha: our hba card information
*/
}
/**
- * mpi_ssp_completion- process the event that FW response to the SSP request.
+ * mpi_ssp_completion - process the event that FW response to the SSP request.
* @pm8001_ha: our hba card information
* @piomb: the message contents of this outbound message.
*
* When FW has completed a ssp request for example a IO request, after it has
- * filled the SG data with the data, it will trigger this event represent
- * that he has finished the job,please check the coresponding buffer.
+ * filled the SG data with the data, it will trigger this event representing
+ * that he has finished the job; please check the corresponding buffer.
* So we will tell the caller who maybe waiting the result to tell upper layer
* that the task has been finished.
*/
}
/**
- * pm80xx_hw_event_ack_req- For PM8001,some events need to acknowage to FW.
+ * pm80xx_hw_event_ack_req- For PM8001, some events need to acknowledge to FW.
* @pm8001_ha: our hba card information
* @Qnum: the outbound queue message number.
* @SEA: source of event to ack
}
/**
- * hw_event_sas_phy_up -FW tells me a SAS phy up event.
+ * hw_event_sas_phy_up - FW tells me a SAS phy up event.
* @pm8001_ha: our hba card information
* @piomb: IO message buffer
*/
}
/**
- * hw_event_sata_phy_up -FW tells me a SATA phy up event.
+ * hw_event_sata_phy_up - FW tells me a SATA phy up event.
* @pm8001_ha: our hba card information
* @piomb: IO message buffer
*/
}
/**
- * hw_event_phy_down -we should notify the libsas the phy is down.
+ * hw_event_phy_down - we should notify the libsas the phy is down.
* @pm8001_ha: our hba card information
* @piomb: IO message buffer
*/
}
/**
- * mpi_thermal_hw_event -The hw event has come.
+ * mpi_thermal_hw_event - a thermal hw event has come.
* @pm8001_ha: our hba card information
* @piomb: IO message buffer
*/
}
/**
- * mpi_hw_event -The hw event has come.
+ * mpi_hw_event - The hw event has come.
* @pm8001_ha: our hba card information
* @piomb: IO message buffer
*/
case OPC_OUB_SET_DEV_INFO:
pm8001_dbg(pm8001_ha, MSG, "OPC_OUB_SET_DEV_INFO\n");
break;
- /* spcv specifc commands */
+ /* spcv specific commands */
case OPC_OUB_PHY_START_RESP:
pm8001_dbg(pm8001_ha, MSG,
"OPC_OUB_PHY_START_RESP opcode:%x\n", opc);
}
/**
- * pm80xx_chip_smp_req - send a SMP task to FW
+ * pm80xx_chip_smp_req - send an SMP task to FW
* @pm8001_ha: our hba card information.
* @ccb: the ccb information this request used.
*/
}
/**
- * pm80xx_chip_ssp_io_req - send a SSP task to FW
+ * pm80xx_chip_ssp_io_req - send an SSP task to FW
* @pm8001_ha: our hba card information.
* @ccb: the ccb information this request used.
*/
payload.ase_sh_lm_slr_phyid = cpu_to_le32(SPINHOLD_DISABLE |
LINKMODE_AUTO | pm8001_ha->link_rate | phy_id);
/* SSC Disable and SAS Analog ST configuration */
- /**
+ /*
payload.ase_sh_lm_slr_phyid =
cpu_to_le32(SSC_DISABLE_30 | SAS_ASE | SPINHOLD_DISABLE |
LINKMODE_AUTO | LINKRATE_15 | LINKRATE_30 | LINKRATE_60 |
phy_id);
Have to add "SAS PHY Analog Setup SPASTI 1 Byte" Based on need
- **/
+ */
payload.sas_identify.dev_type = SAS_END_DEVICE;
payload.sas_identify.initiator_bits = SAS_PROTOCOL_ALL;
* @bufflen: len of buffer
* @sense: optional sense buffer
* @sshdr: optional decoded sense header
- * @timeout: request timeout in seconds
+ * @timeout: request timeout in HZ
* @retries: number of times to retry request
* @flags: flags for ->cmd_flags
* @rq_flags: flags for ->rq_flags
error = shost->hostt->target_alloc(starget);
if(error) {
- dev_printk(KERN_ERR, dev, "target allocation failed, error %d\n", error);
+ if (error != -ENXIO)
+ dev_err(dev, "target allocation failed, error %d\n", error);
/* don't want scsi_target_reap to do the final
* put because it will be under the host lock */
scsi_target_destroy(starget);
mutex_lock(&sdev->state_mutex);
ret = scsi_device_set_state(sdev, state);
/*
- * If the device state changes to SDEV_RUNNING, we need to run
- * the queue to avoid I/O hang.
+ * If the device state changes to SDEV_RUNNING, we need to
+ * rescan the device to revalidate it, and run the queue to
+ * avoid I/O hang.
*/
- if (ret == 0 && state == SDEV_RUNNING)
+ if (ret == 0 && state == SDEV_RUNNING) {
+ scsi_rescan_device(dev);
blk_mq_run_hw_queues(sdev->request_queue, true);
+ }
mutex_unlock(&sdev->state_mutex);
return ret == 0 ? count : -EINVAL;
struct device *dev = container_of(kobj, struct device, kobj);
struct iscsi_iface *iface = iscsi_dev_to_iface(dev);
struct iscsi_transport *t = iface->transport;
- int param;
- int param_type;
+ int param = -1;
if (attr == &dev_attr_iface_enabled.attr)
param = ISCSI_NET_PARAM_IFACE_ENABLE;
- else if (attr == &dev_attr_iface_vlan_id.attr)
- param = ISCSI_NET_PARAM_VLAN_ID;
- else if (attr == &dev_attr_iface_vlan_priority.attr)
- param = ISCSI_NET_PARAM_VLAN_PRIORITY;
- else if (attr == &dev_attr_iface_vlan_enabled.attr)
- param = ISCSI_NET_PARAM_VLAN_ENABLED;
- else if (attr == &dev_attr_iface_mtu.attr)
- param = ISCSI_NET_PARAM_MTU;
- else if (attr == &dev_attr_iface_port.attr)
- param = ISCSI_NET_PARAM_PORT;
- else if (attr == &dev_attr_iface_ipaddress_state.attr)
- param = ISCSI_NET_PARAM_IPADDR_STATE;
- else if (attr == &dev_attr_iface_delayed_ack_en.attr)
- param = ISCSI_NET_PARAM_DELAYED_ACK_EN;
- else if (attr == &dev_attr_iface_tcp_nagle_disable.attr)
- param = ISCSI_NET_PARAM_TCP_NAGLE_DISABLE;
- else if (attr == &dev_attr_iface_tcp_wsf_disable.attr)
- param = ISCSI_NET_PARAM_TCP_WSF_DISABLE;
- else if (attr == &dev_attr_iface_tcp_wsf.attr)
- param = ISCSI_NET_PARAM_TCP_WSF;
- else if (attr == &dev_attr_iface_tcp_timer_scale.attr)
- param = ISCSI_NET_PARAM_TCP_TIMER_SCALE;
- else if (attr == &dev_attr_iface_tcp_timestamp_en.attr)
- param = ISCSI_NET_PARAM_TCP_TIMESTAMP_EN;
- else if (attr == &dev_attr_iface_cache_id.attr)
- param = ISCSI_NET_PARAM_CACHE_ID;
- else if (attr == &dev_attr_iface_redirect_en.attr)
- param = ISCSI_NET_PARAM_REDIRECT_EN;
else if (attr == &dev_attr_iface_def_taskmgmt_tmo.attr)
param = ISCSI_IFACE_PARAM_DEF_TASKMGMT_TMO;
else if (attr == &dev_attr_iface_header_digest.attr)
param = ISCSI_IFACE_PARAM_STRICT_LOGIN_COMP_EN;
else if (attr == &dev_attr_iface_initiator_name.attr)
param = ISCSI_IFACE_PARAM_INITIATOR_NAME;
+
+ if (param != -1)
+ return t->attr_is_visible(ISCSI_IFACE_PARAM, param);
+
+ if (attr == &dev_attr_iface_vlan_id.attr)
+ param = ISCSI_NET_PARAM_VLAN_ID;
+ else if (attr == &dev_attr_iface_vlan_priority.attr)
+ param = ISCSI_NET_PARAM_VLAN_PRIORITY;
+ else if (attr == &dev_attr_iface_vlan_enabled.attr)
+ param = ISCSI_NET_PARAM_VLAN_ENABLED;
+ else if (attr == &dev_attr_iface_mtu.attr)
+ param = ISCSI_NET_PARAM_MTU;
+ else if (attr == &dev_attr_iface_port.attr)
+ param = ISCSI_NET_PARAM_PORT;
+ else if (attr == &dev_attr_iface_ipaddress_state.attr)
+ param = ISCSI_NET_PARAM_IPADDR_STATE;
+ else if (attr == &dev_attr_iface_delayed_ack_en.attr)
+ param = ISCSI_NET_PARAM_DELAYED_ACK_EN;
+ else if (attr == &dev_attr_iface_tcp_nagle_disable.attr)
+ param = ISCSI_NET_PARAM_TCP_NAGLE_DISABLE;
+ else if (attr == &dev_attr_iface_tcp_wsf_disable.attr)
+ param = ISCSI_NET_PARAM_TCP_WSF_DISABLE;
+ else if (attr == &dev_attr_iface_tcp_wsf.attr)
+ param = ISCSI_NET_PARAM_TCP_WSF;
+ else if (attr == &dev_attr_iface_tcp_timer_scale.attr)
+ param = ISCSI_NET_PARAM_TCP_TIMER_SCALE;
+ else if (attr == &dev_attr_iface_tcp_timestamp_en.attr)
+ param = ISCSI_NET_PARAM_TCP_TIMESTAMP_EN;
+ else if (attr == &dev_attr_iface_cache_id.attr)
+ param = ISCSI_NET_PARAM_CACHE_ID;
+ else if (attr == &dev_attr_iface_redirect_en.attr)
+ param = ISCSI_NET_PARAM_REDIRECT_EN;
else if (iface->iface_type == ISCSI_IFACE_TYPE_IPV4) {
if (attr == &dev_attr_ipv4_iface_ipaddress.attr)
param = ISCSI_NET_PARAM_IPV4_ADDR;
return 0;
}
- switch (param) {
- case ISCSI_IFACE_PARAM_DEF_TASKMGMT_TMO:
- case ISCSI_IFACE_PARAM_HDRDGST_EN:
- case ISCSI_IFACE_PARAM_DATADGST_EN:
- case ISCSI_IFACE_PARAM_IMM_DATA_EN:
- case ISCSI_IFACE_PARAM_INITIAL_R2T_EN:
- case ISCSI_IFACE_PARAM_DATASEQ_INORDER_EN:
- case ISCSI_IFACE_PARAM_PDU_INORDER_EN:
- case ISCSI_IFACE_PARAM_ERL:
- case ISCSI_IFACE_PARAM_MAX_RECV_DLENGTH:
- case ISCSI_IFACE_PARAM_FIRST_BURST:
- case ISCSI_IFACE_PARAM_MAX_R2T:
- case ISCSI_IFACE_PARAM_MAX_BURST:
- case ISCSI_IFACE_PARAM_CHAP_AUTH_EN:
- case ISCSI_IFACE_PARAM_BIDI_CHAP_EN:
- case ISCSI_IFACE_PARAM_DISCOVERY_AUTH_OPTIONAL:
- case ISCSI_IFACE_PARAM_DISCOVERY_LOGOUT_EN:
- case ISCSI_IFACE_PARAM_STRICT_LOGIN_COMP_EN:
- case ISCSI_IFACE_PARAM_INITIATOR_NAME:
- param_type = ISCSI_IFACE_PARAM;
- break;
- default:
- param_type = ISCSI_NET_PARAM;
- }
-
- return t->attr_is_visible(param_type, param);
+ return t->attr_is_visible(ISCSI_NET_PARAM, param);
}
static struct attribute *iscsi_iface_attrs[] = {
MODULE_ALIAS_SCSI_DEVICE(TYPE_RBC);
MODULE_ALIAS_SCSI_DEVICE(TYPE_ZBC);
-#if !defined(CONFIG_DEBUG_BLOCK_EXT_DEVT)
#define SD_MINORS 16
-#else
-#define SD_MINORS 0
-#endif
static void sd_config_discard(struct scsi_disk *, unsigned int);
static void sd_config_write_same(struct scsi_disk *);
else if (med->media_event_code == 2)
return DISK_EVENT_MEDIA_CHANGE;
else if (med->media_event_code == 3)
- return DISK_EVENT_EJECT_REQUEST;
+ return DISK_EVENT_MEDIA_CHANGE;
return 0;
}
static inline void ufshcd_vops_setup_xfer_req(struct ufs_hba *hba, int tag,
bool is_scsi_cmd)
{
- if (hba->vops && hba->vops->setup_xfer_req)
- return hba->vops->setup_xfer_req(hba, tag, is_scsi_cmd);
+ if (hba->vops && hba->vops->setup_xfer_req) {
+ unsigned long flags;
+
+ spin_lock_irqsave(hba->host->host_lock, flags);
+ hba->vops->setup_xfer_req(hba, tag, is_scsi_cmd);
+ spin_unlock_irqrestore(hba->host->host_lock, flags);
+ }
}
static inline void ufshcd_vops_setup_task_mgmt(struct ufs_hba *hba,
obj-y += fsl/
obj-$(CONFIG_ARCH_GEMINI) += gemini/
obj-y += imx/
-obj-$(CONFIG_ARCH_IXP4XX) += ixp4xx/
+obj-y += ixp4xx/
obj-$(CONFIG_SOC_XWAY) += lantiq/
obj-$(CONFIG_LITEX_SOC_CONTROLLER) += litex/
obj-y += mediatek/
#include <linux/signal.h>
#include <linux/device.h>
#include <linux/spinlock.h>
+#include <linux/platform_device.h>
#include <asm/irq.h>
#include <asm/io.h>
#include <soc/fsl/qe/qe.h>
struct irq_chip hc_irq;
/* VIRQ numbers of QE high/low irqs */
- unsigned int virq_high;
- unsigned int virq_low;
+ int virq_high;
+ int virq_low;
};
/*
chip->irq_eoi(&desc->irq_data);
}
-static void __init qe_ic_init(struct device_node *node)
+static int qe_ic_init(struct platform_device *pdev)
{
+ struct device *dev = &pdev->dev;
void (*low_handler)(struct irq_desc *desc);
void (*high_handler)(struct irq_desc *desc);
struct qe_ic *qe_ic;
- struct resource res;
- u32 ret;
+ struct resource *res;
+ struct device_node *node = pdev->dev.of_node;
- ret = of_address_to_resource(node, 0, &res);
- if (ret)
- return;
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (res == NULL) {
+ dev_err(dev, "no memory resource defined\n");
+ return -ENODEV;
+ }
- qe_ic = kzalloc(sizeof(*qe_ic), GFP_KERNEL);
+ qe_ic = devm_kzalloc(dev, sizeof(*qe_ic), GFP_KERNEL);
if (qe_ic == NULL)
- return;
+ return -ENOMEM;
- qe_ic->irqhost = irq_domain_add_linear(node, NR_QE_IC_INTS,
- &qe_ic_host_ops, qe_ic);
- if (qe_ic->irqhost == NULL) {
- kfree(qe_ic);
- return;
+ qe_ic->regs = devm_ioremap(dev, res->start, resource_size(res));
+ if (qe_ic->regs == NULL) {
+ dev_err(dev, "failed to ioremap() registers\n");
+ return -ENODEV;
}
- qe_ic->regs = ioremap(res.start, resource_size(&res));
-
qe_ic->hc_irq = qe_ic_irq_chip;
- qe_ic->virq_high = irq_of_parse_and_map(node, 0);
- qe_ic->virq_low = irq_of_parse_and_map(node, 1);
+ qe_ic->virq_high = platform_get_irq(pdev, 0);
+ qe_ic->virq_low = platform_get_irq(pdev, 1);
- if (!qe_ic->virq_low) {
- printk(KERN_ERR "Failed to map QE_IC low IRQ\n");
- kfree(qe_ic);
- return;
- }
- if (qe_ic->virq_high != qe_ic->virq_low) {
+ if (qe_ic->virq_low <= 0)
+ return -ENODEV;
+
+ if (qe_ic->virq_high > 0 && qe_ic->virq_high != qe_ic->virq_low) {
low_handler = qe_ic_cascade_low;
high_handler = qe_ic_cascade_high;
} else {
high_handler = NULL;
}
+ qe_ic->irqhost = irq_domain_add_linear(node, NR_QE_IC_INTS,
+ &qe_ic_host_ops, qe_ic);
+ if (qe_ic->irqhost == NULL) {
+ dev_err(dev, "failed to add irq domain\n");
+ return -ENODEV;
+ }
+
qe_ic_write(qe_ic->regs, QEIC_CICR, 0);
irq_set_handler_data(qe_ic->virq_low, qe_ic);
irq_set_chained_handler(qe_ic->virq_low, low_handler);
- if (qe_ic->virq_high && qe_ic->virq_high != qe_ic->virq_low) {
+ if (high_handler) {
irq_set_handler_data(qe_ic->virq_high, qe_ic);
irq_set_chained_handler(qe_ic->virq_high, high_handler);
}
+ return 0;
}
+static const struct of_device_id qe_ic_ids[] = {
+ { .compatible = "fsl,qe-ic"},
+ { .type = "qeic"},
+ {},
+};
-static int __init qe_ic_of_init(void)
+static struct platform_driver qe_ic_driver =
{
- struct device_node *np;
+ .driver = {
+ .name = "qe-ic",
+ .of_match_table = qe_ic_ids,
+ },
+ .probe = qe_ic_init,
+};
- np = of_find_compatible_node(NULL, NULL, "fsl,qe-ic");
- if (!np) {
- np = of_find_node_by_type(NULL, "qeic");
- if (!np)
- return -ENODEV;
- }
- qe_ic_init(np);
- of_node_put(np);
+static int __init qe_ic_of_init(void)
+{
+ platform_driver_register(&qe_ic_driver);
return 0;
}
subsys_initcall(qe_ic_of_init);
#include <linux/init.h>
#include <linux/io.h>
-#include <linux/module.h>
-#include <linux/nvmem-consumer.h>
#include <linux/of_address.h>
#include <linux/slab.h>
#include <linux/sys_soc.h>
struct imx8_soc_data {
char *name;
- u32 (*soc_revision)(struct device *dev);
+ u32 (*soc_revision)(void);
};
static u64 soc_uid;
static inline u32 imx8mq_soc_revision_from_atf(void) { return 0; };
#endif
-static u32 __init imx8mq_soc_revision(struct device *dev)
+static u32 __init imx8mq_soc_revision(void)
{
struct device_node *np;
void __iomem *ocotp_base;
rev = REV_B1;
}
- if (dev) {
- int ret;
-
- ret = nvmem_cell_read_u64(dev, "soc_unique_id", &soc_uid);
- if (ret) {
- iounmap(ocotp_base);
- of_node_put(np);
- return ret;
- }
- } else {
- soc_uid = readl_relaxed(ocotp_base + OCOTP_UID_HIGH);
- soc_uid <<= 32;
- soc_uid |= readl_relaxed(ocotp_base + OCOTP_UID_LOW);
- }
+ soc_uid = readl_relaxed(ocotp_base + OCOTP_UID_HIGH);
+ soc_uid <<= 32;
+ soc_uid |= readl_relaxed(ocotp_base + OCOTP_UID_LOW);
iounmap(ocotp_base);
of_node_put(np);
of_node_put(np);
}
-static u32 __init imx8mm_soc_revision(struct device *dev)
+static u32 __init imx8mm_soc_revision(void)
{
struct device_node *np;
void __iomem *anatop_base;
iounmap(anatop_base);
of_node_put(np);
- if (dev) {
- int ret;
-
- ret = nvmem_cell_read_u64(dev, "soc_unique_id", &soc_uid);
- if (ret)
- return ret;
- } else {
- imx8mm_soc_uid();
- }
+ imx8mm_soc_uid();
return rev;
}
.soc_revision = imx8mm_soc_revision,
};
-static __maybe_unused const struct of_device_id imx8_machine_match[] = {
+static __maybe_unused const struct of_device_id imx8_soc_match[] = {
{ .compatible = "fsl,imx8mq", .data = &imx8mq_soc_data, },
{ .compatible = "fsl,imx8mm", .data = &imx8mm_soc_data, },
{ .compatible = "fsl,imx8mn", .data = &imx8mn_soc_data, },
{ }
};
-static __maybe_unused const struct of_device_id imx8_soc_match[] = {
- { .compatible = "fsl,imx8mq-soc", .data = &imx8mq_soc_data, },
- { .compatible = "fsl,imx8mm-soc", .data = &imx8mm_soc_data, },
- { .compatible = "fsl,imx8mn-soc", .data = &imx8mn_soc_data, },
- { .compatible = "fsl,imx8mp-soc", .data = &imx8mp_soc_data, },
- { }
-};
-
#define imx8_revision(soc_rev) \
soc_rev ? \
kasprintf(GFP_KERNEL, "%d.%d", (soc_rev >> 4) & 0xf, soc_rev & 0xf) : \
"unknown"
-static int imx8_soc_info(struct platform_device *pdev)
+static int __init imx8_soc_init(void)
{
struct soc_device_attribute *soc_dev_attr;
struct soc_device *soc_dev;
if (ret)
goto free_soc;
- if (pdev)
- id = of_match_node(imx8_soc_match, pdev->dev.of_node);
- else
- id = of_match_node(imx8_machine_match, of_root);
+ id = of_match_node(imx8_soc_match, of_root);
if (!id) {
ret = -ENODEV;
goto free_soc;
data = id->data;
if (data) {
soc_dev_attr->soc_id = data->name;
- if (data->soc_revision) {
- if (pdev) {
- soc_rev = data->soc_revision(&pdev->dev);
- ret = soc_rev;
- if (ret < 0)
- goto free_soc;
- } else {
- soc_rev = data->soc_revision(NULL);
- }
- }
+ if (data->soc_revision)
+ soc_rev = data->soc_revision();
}
soc_dev_attr->revision = imx8_revision(soc_rev);
kfree(soc_dev_attr);
return ret;
}
-
-/* Retain device_initcall is for backward compatibility with DTS. */
-static int __init imx8_soc_init(void)
-{
- if (of_find_matching_node_and_match(NULL, imx8_soc_match, NULL))
- return 0;
-
- return imx8_soc_info(NULL);
-}
device_initcall(imx8_soc_init);
-
-static struct platform_driver imx8_soc_info_driver = {
- .probe = imx8_soc_info,
- .driver = {
- .name = "imx8_soc_info",
- .of_match_table = imx8_soc_match,
- },
-};
-
-module_platform_driver(imx8_soc_info_driver);
-MODULE_LICENSE("GPL v2");
#include <linux/of_platform.h>
#include <linux/platform_device.h>
#include <linux/soc/ixp4xx/npe.h>
-#include <mach/hardware.h>
#include <linux/soc/ixp4xx/cpu.h>
#define DEBUG_MSG 0
if (!(ixp4xx_read_feature_bits() &
(IXP4XX_FEATURE_RESET_NPEA << i))) {
- dev_info(dev, "NPE%d at 0x%08x-0x%08x not available\n",
- i, res->start, res->end);
+ dev_info(dev, "NPE%d at %pR not available\n",
+ i, res);
continue; /* NPE already disabled or not present */
}
npe->regs = devm_ioremap_resource(dev, res);
return PTR_ERR(npe->regs);
if (npe_reset(npe)) {
- dev_info(dev, "NPE%d at 0x%08x-0x%08x does not reset\n",
- i, res->start, res->end);
+ dev_info(dev, "NPE%d at %pR does not reset\n",
+ i, res);
continue;
}
npe->valid = 1;
- dev_info(dev, "NPE%d at 0x%08x-0x%08x registered\n",
- i, res->start, res->end);
+ dev_info(dev, "NPE%d at %pR registered\n", i, res);
found++;
}
#include <linux/of.h>
#include <linux/platform_device.h>
#include <linux/soc/ixp4xx/qmgr.h>
-#include <mach/hardware.h>
#include <linux/soc/ixp4xx/cpu.h>
static struct qmgr_regs __iomem *qmgr_regs;
/* ACK - it may clear any bits so don't rely on it */
__raw_writel(0xFFFFFFFF, &qmgr_regs->irqstat[0]);
- en_bitmap = qmgr_regs->irqen[0];
+ en_bitmap = __raw_readl(&qmgr_regs->irqen[0]);
while (en_bitmap) {
i = __fls(en_bitmap); /* number of the last "low" queue */
en_bitmap &= ~BIT(i);
- src = qmgr_regs->irqsrc[i >> 3];
- stat = qmgr_regs->stat1[i >> 3];
+ src = __raw_readl(&qmgr_regs->irqsrc[i >> 3]);
+ stat = __raw_readl(&qmgr_regs->stat1[i >> 3]);
if (src & 4) /* the IRQ condition is inverted */
stat = ~stat;
if (stat & BIT(src & 3)) {
/* ACK - it may clear any bits so don't rely on it */
__raw_writel(0xFFFFFFFF, &qmgr_regs->irqstat[1]);
- req_bitmap = qmgr_regs->irqen[1] & qmgr_regs->statne_h;
+ req_bitmap = __raw_readl(&qmgr_regs->irqen[1]) &
+ __raw_readl(&qmgr_regs->statne_h);
while (req_bitmap) {
i = __fls(req_bitmap); /* number of the last "high" queue */
req_bitmap &= ~BIT(i);
select PL310_ERRATA_769419 if CACHE_L2X0
select SOC_TEGRA_FLOWCTRL
select SOC_TEGRA_PMC
- select SOC_TEGRA20_VOLTAGE_COUPLER
+ select SOC_TEGRA20_VOLTAGE_COUPLER if REGULATOR
select TEGRA_TIMER
help
Support for NVIDIA Tegra AP20 and T20 processors, based on the
select PL310_ERRATA_769419 if CACHE_L2X0
select SOC_TEGRA_FLOWCTRL
select SOC_TEGRA_PMC
- select SOC_TEGRA30_VOLTAGE_COUPLER
+ select SOC_TEGRA30_VOLTAGE_COUPLER if REGULATOR
select TEGRA_TIMER
help
Support for NVIDIA Tegra T30 processor family, based on the
config SOC_TEGRA20_VOLTAGE_COUPLER
bool "Voltage scaling support for Tegra20 SoCs"
depends on ARCH_TEGRA_2x_SOC || COMPILE_TEST
+ depends on REGULATOR
config SOC_TEGRA30_VOLTAGE_COUPLER
bool "Voltage scaling support for Tegra30 SoCs"
depends on ARCH_TEGRA_3x_SOC || COMPILE_TEST
+ depends on REGULATOR
}
mr = spi_readl(as, MR);
- if (spi->cs_gpiod)
- gpiod_set_value(spi->cs_gpiod, 1);
} else {
u32 cpol = (spi->mode & SPI_CPOL) ? SPI_BIT(CPOL) : 0;
int i;
mr = spi_readl(as, MR);
mr = SPI_BFINS(PCS, ~(1 << chip_select), mr);
- if (spi->cs_gpiod)
- gpiod_set_value(spi->cs_gpiod, 1);
spi_writel(as, MR, mr);
}
if (!spi->cs_gpiod)
spi_writel(as, CR, SPI_BIT(LASTXFER));
- else
- gpiod_set_value(spi->cs_gpiod, 0);
}
static void atmel_spi_lock(struct atmel_spi *as) __acquires(&as->lock)
master->bus_num = pdev->id;
master->num_chipselect = 4;
master->setup = atmel_spi_setup;
- master->flags = (SPI_MASTER_MUST_RX | SPI_MASTER_MUST_TX);
+ master->flags = (SPI_MASTER_MUST_RX | SPI_MASTER_MUST_TX |
+ SPI_MASTER_GPIO_SS);
master->transfer_one = atmel_spi_one_transfer;
master->set_cs = atmel_spi_set_cs;
master->cleanup = atmel_spi_cleanup;
* struct bcm2835_spi - BCM2835 SPI controller
* @regs: base address of register map
* @clk: core clock, divided to calculate serial clock
+ * @clk_hz: core clock cached speed
* @irq: interrupt, signals TX FIFO empty or RX FIFO ¾ full
* @tfr: SPI transfer currently processed
* @ctlr: SPI controller reverse lookup
struct bcm2835_spi {
void __iomem *regs;
struct clk *clk;
+ unsigned long clk_hz;
int irq;
struct spi_transfer *tfr;
struct spi_controller *ctlr;
{
struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
struct bcm2835_spidev *slv = spi_get_ctldata(spi);
- unsigned long spi_hz, clk_hz, cdiv;
+ unsigned long spi_hz, cdiv;
unsigned long hz_per_byte, byte_limit;
u32 cs = slv->prepare_cs;
/* set clock */
spi_hz = tfr->speed_hz;
- clk_hz = clk_get_rate(bs->clk);
- if (spi_hz >= clk_hz / 2) {
+ if (spi_hz >= bs->clk_hz / 2) {
cdiv = 2; /* clk_hz/2 is the fastest we can go */
} else if (spi_hz) {
/* CDIV must be a multiple of two */
- cdiv = DIV_ROUND_UP(clk_hz, spi_hz);
+ cdiv = DIV_ROUND_UP(bs->clk_hz, spi_hz);
cdiv += (cdiv % 2);
if (cdiv >= 65536)
} else {
cdiv = 0; /* 0 is the slowest we can go */
}
- tfr->effective_speed_hz = cdiv ? (clk_hz / cdiv) : (clk_hz / 65536);
+ tfr->effective_speed_hz = cdiv ? (bs->clk_hz / cdiv) : (bs->clk_hz / 65536);
bcm2835_wr(bs, BCM2835_SPI_CLK, cdiv);
/* handle all the 3-wire mode */
return bs->irq ? bs->irq : -ENODEV;
clk_prepare_enable(bs->clk);
+ bs->clk_hz = clk_get_rate(bs->clk);
err = bcm2835_dma_init(ctlr, &pdev->dev, bs);
if (err)
{
unsigned int dummy_clk;
+ if (!op->dummy.nbytes)
+ return 0;
+
dummy_clk = op->dummy.nbytes * (8 / op->dummy.buswidth);
if (dtr)
dummy_clk /= 2;
f_pdata->inst_width = CQSPI_INST_TYPE_SINGLE;
f_pdata->addr_width = CQSPI_INST_TYPE_SINGLE;
f_pdata->data_width = CQSPI_INST_TYPE_SINGLE;
- f_pdata->dtr = op->data.dtr && op->cmd.dtr && op->addr.dtr;
+
+ /*
+ * For an op to be DTR, cmd phase along with every other non-empty
+ * phase should have dtr field set to 1. If an op phase has zero
+ * nbytes, ignore its dtr field; otherwise, check its dtr field.
+ */
+ f_pdata->dtr = op->cmd.dtr &&
+ (!op->addr.nbytes || op->addr.dtr) &&
+ (!op->data.nbytes || op->data.dtr);
switch (op->data.buswidth) {
case 0:
reg = cqspi_calc_rdreg(f_pdata);
writel(reg, reg_base + CQSPI_REG_RD_INSTR);
- if (f_pdata->dtr) {
- /*
- * Some flashes like the cypress Semper flash expect a 4-byte
- * dummy address with the Read SR command in DTR mode, but this
- * controller does not support sending address with the Read SR
- * command. So, disable write completion polling on the
- * controller's side. spi-nor will take care of polling the
- * status register.
- */
- reg = readl(reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
- reg |= CQSPI_REG_WR_DISABLE_AUTO_POLL;
- writel(reg, reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
- }
+ /*
+ * SPI NAND flashes require the address of the status register to be
+ * passed in the Read SR command. Also, some SPI NOR flashes like the
+ * cypress Semper flash expect a 4-byte dummy address in the Read SR
+ * command in DTR mode.
+ *
+ * But this controller does not support address phase in the Read SR
+ * command when doing auto-HW polling. So, disable write completion
+ * polling on the controller's side. spinand and spi-nor will take
+ * care of polling the status register.
+ */
+ reg = readl(reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
+ reg |= CQSPI_REG_WR_DISABLE_AUTO_POLL;
+ writel(reg, reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
reg = readl(reg_base + CQSPI_REG_SIZE);
reg &= ~CQSPI_REG_SIZE_ADDRESS_MASK;
{
bool all_true, all_false;
- all_true = op->cmd.dtr && op->addr.dtr && op->dummy.dtr &&
- op->data.dtr;
+ /*
+ * op->dummy.dtr is required for converting nbytes into ncycles.
+ * Also, don't check the dtr field of the op phase having zero nbytes.
+ */
+ all_true = op->cmd.dtr &&
+ (!op->addr.nbytes || op->addr.dtr) &&
+ (!op->dummy.nbytes || op->dummy.dtr) &&
+ (!op->data.nbytes || op->data.dtr);
+
all_false = !op->cmd.dtr && !op->addr.dtr && !op->dummy.dtr &&
!op->data.dtr;
goto clk_dis_apb;
}
+ pm_runtime_use_autosuspend(&pdev->dev);
+ pm_runtime_set_autosuspend_delay(&pdev->dev, SPI_AUTOSUSPEND_TIMEOUT);
+ pm_runtime_get_noresume(&pdev->dev);
+ pm_runtime_set_active(&pdev->dev);
+ pm_runtime_enable(&pdev->dev);
+
ret = of_property_read_u32(pdev->dev.of_node, "num-cs", &num_cs);
if (ret < 0)
master->num_chipselect = CDNS_SPI_DEFAULT_NUM_CS;
/* SPI controller initializations */
cdns_spi_init_hw(xspi);
- pm_runtime_set_active(&pdev->dev);
- pm_runtime_enable(&pdev->dev);
- pm_runtime_use_autosuspend(&pdev->dev);
- pm_runtime_set_autosuspend_delay(&pdev->dev, SPI_AUTOSUSPEND_TIMEOUT);
-
irq = platform_get_irq(pdev, 0);
if (irq <= 0) {
ret = -ENXIO;
master->bits_per_word_mask = SPI_BPW_MASK(8);
+ pm_runtime_mark_last_busy(&pdev->dev);
+ pm_runtime_put_autosuspend(&pdev->dev);
+
ret = spi_register_master(master);
if (ret) {
dev_err(&pdev->dev, "spi_register_master failed\n");
struct spi_message *msg)
{
struct spi_device *spi = msg->spi;
+ struct spi_transfer *xfer;
u32 ctrl = MX51_ECSPI_CTRL_ENABLE;
- u32 testreg;
+ u32 min_speed_hz = ~0U;
+ u32 testreg, delay;
u32 cfg = readl(spi_imx->base + MX51_ECSPI_CONFIG);
/* set Master or Slave mode */
writel(cfg, spi_imx->base + MX51_ECSPI_CONFIG);
+ /*
+ * Wait until the changes in the configuration register CONFIGREG
+ * propagate into the hardware. It takes exactly one tick of the
+ * SCLK clock, but we will wait two SCLK clock just to be sure. The
+ * effect of the delay it takes for the hardware to apply changes
+ * is noticable if the SCLK clock run very slow. In such a case, if
+ * the polarity of SCLK should be inverted, the GPIO ChipSelect might
+ * be asserted before the SCLK polarity changes, which would disrupt
+ * the SPI communication as the device on the other end would consider
+ * the change of SCLK polarity as a clock tick already.
+ *
+ * Because spi_imx->spi_bus_clk is only set in bitbang prepare_message
+ * callback, iterate over all the transfers in spi_message, find the
+ * one with lowest bus frequency, and use that bus frequency for the
+ * delay calculation. In case all transfers have speed_hz == 0, then
+ * min_speed_hz is ~0 and the resulting delay is zero.
+ */
+ list_for_each_entry(xfer, &msg->transfers, transfer_list) {
+ if (!xfer->speed_hz)
+ continue;
+ min_speed_hz = min(xfer->speed_hz, min_speed_hz);
+ }
+
+ delay = (2 * 1000000) / min_speed_hz;
+ if (likely(delay < 10)) /* SCLK is faster than 200 kHz */
+ udelay(delay);
+ else /* SCLK is _very_ slow */
+ usleep_range(delay, delay + 10);
+
return 0;
}
struct spi_device *spi)
{
u32 ctrl = readl(spi_imx->base + MX51_ECSPI_CTRL);
- u32 clk, delay;
+ u32 clk;
/* Clear BL field and set the right value */
ctrl &= ~MX51_ECSPI_CTRL_BL_MASK;
writel(ctrl, spi_imx->base + MX51_ECSPI_CTRL);
- /*
- * Wait until the changes in the configuration register CONFIGREG
- * propagate into the hardware. It takes exactly one tick of the
- * SCLK clock, but we will wait two SCLK clock just to be sure. The
- * effect of the delay it takes for the hardware to apply changes
- * is noticable if the SCLK clock run very slow. In such a case, if
- * the polarity of SCLK should be inverted, the GPIO ChipSelect might
- * be asserted before the SCLK polarity changes, which would disrupt
- * the SPI communication as the device on the other end would consider
- * the change of SCLK polarity as a clock tick already.
- */
- delay = (2 * 1000000) / clk;
- if (likely(delay < 10)) /* SCLK is faster than 100 kHz */
- udelay(delay);
- else /* SCLK is _very_ slow */
- usleep_range(delay, delay + 10);
-
return 0;
}
clk_disable_unprepare(spicc->core);
clk_disable_unprepare(spicc->pclk);
+ spi_master_put(spicc->master);
+
return 0;
}
mtk_spi_prepare_transfer(master, xfer);
mtk_spi_setup_packet(master);
- cnt = xfer->len / 4;
- iowrite32_rep(mdata->base + SPI_TX_DATA_REG, xfer->tx_buf, cnt);
-
- remainder = xfer->len % 4;
- if (remainder > 0) {
- reg_val = 0;
- memcpy(®_val, xfer->tx_buf + (cnt * 4), remainder);
- writel(reg_val, mdata->base + SPI_TX_DATA_REG);
+ if (xfer->tx_buf) {
+ cnt = xfer->len / 4;
+ iowrite32_rep(mdata->base + SPI_TX_DATA_REG, xfer->tx_buf, cnt);
+ remainder = xfer->len % 4;
+ if (remainder > 0) {
+ reg_val = 0;
+ memcpy(®_val, xfer->tx_buf + (cnt * 4), remainder);
+ writel(reg_val, mdata->base + SPI_TX_DATA_REG);
+ }
}
mtk_spi_enable_transfer(master);
pm_runtime_enable(&pdev->dev);
- ret = devm_spi_register_master(&pdev->dev, master);
- if (ret) {
- dev_err(&pdev->dev, "failed to register master (%d)\n", ret);
- goto err_disable_runtime_pm;
- }
-
if (mdata->dev_comp->need_pad_sel) {
if (mdata->pad_num != master->num_chipselect) {
dev_err(&pdev->dev,
dev_notice(&pdev->dev, "SPI dma_set_mask(%d) failed, ret:%d\n",
addr_bits, ret);
+ ret = devm_spi_register_master(&pdev->dev, master);
+ if (ret) {
+ dev_err(&pdev->dev, "failed to register master (%d)\n", ret);
+ goto err_disable_runtime_pm;
+ }
+
return 0;
err_disable_runtime_pm:
return ret;
}
+static const struct spi_device_id spi_mux_id[] = {
+ { "spi-mux" },
+ { }
+};
+MODULE_DEVICE_TABLE(spi, spi_mux_id);
+
static const struct of_device_id spi_mux_of_match[] = {
{ .compatible = "spi-mux" },
{ }
};
+MODULE_DEVICE_TABLE(of, spi_mux_of_match);
static struct spi_driver spi_mux_driver = {
.probe = spi_mux_probe,
.name = "spi-mux",
.of_match_table = spi_mux_of_match,
},
+ .id_table = spi_mux_id,
};
module_spi_driver(spi_mux_driver);
ier = readl_relaxed(spi->base + STM32H7_SPI_IER);
mask = ier;
- /* EOTIE is triggered on EOT, SUSP and TXC events. */
+ /*
+ * EOTIE enables irq from EOT, SUSP and TXC events. We need to set
+ * SUSP to acknowledge it later. TXC is automatically cleared
+ */
+
mask |= STM32H7_SPI_SR_SUSP;
/*
- * When TXTF is set, DXPIE and TXPIE are cleared. So in case of
- * Full-Duplex, need to poll RXP event to know if there are remaining
- * data, before disabling SPI.
+ * DXPIE is set in Full-Duplex, one IT will be raised if TXP and RXP
+ * are set. So in case of Full-Duplex, need to poll TXP and RXP event.
*/
- if (spi->rx_buf && !spi->cur_usedma)
- mask |= STM32H7_SPI_SR_RXP;
+ if ((spi->cur_comm == SPI_FULL_DUPLEX) && !spi->cur_usedma)
+ mask |= STM32H7_SPI_SR_TXP | STM32H7_SPI_SR_RXP;
if (!(sr & mask)) {
dev_warn(spi->dev, "spurious IT (sr=0x%08x, ier=0x%08x)\n",
master->can_dma = stm32_spi_can_dma;
pm_runtime_set_active(&pdev->dev);
+ pm_runtime_get_noresume(&pdev->dev);
pm_runtime_enable(&pdev->dev);
ret = spi_register_master(master);
err_pm_disable:
pm_runtime_disable(&pdev->dev);
+ pm_runtime_put_noidle(&pdev->dev);
+ pm_runtime_set_suspended(&pdev->dev);
err_dma_release:
if (spi->dma_tx)
dma_release_channel(spi->dma_tx);
struct spi_master *master = platform_get_drvdata(pdev);
struct stm32_spi *spi = spi_master_get_devdata(master);
+ pm_runtime_get_sync(&pdev->dev);
+
spi_unregister_master(master);
spi->cfg->disable(spi);
+ pm_runtime_disable(&pdev->dev);
+ pm_runtime_put_noidle(&pdev->dev);
+ pm_runtime_set_suspended(&pdev->dev);
if (master->dma_tx)
dma_release_channel(master->dma_tx);
if (master->dma_rx)
clk_disable_unprepare(spi->clk);
- pm_runtime_disable(&pdev->dev);
pinctrl_pm_select_sleep_state(&pdev->dev);
const struct spi_device *spi = to_spi_device(dev);
int len;
+ len = of_device_modalias(dev, buf, PAGE_SIZE);
+ if (len != -ENODEV)
+ return len;
+
len = acpi_device_modalias(dev, buf, PAGE_SIZE - 1);
if (len != -ENODEV)
return len;
dev_err(dev, "pcie%d no card, disable it (RST & CLK)\n",
slot);
mt7621_control_assert(port);
- clk_disable_unprepare(port->clk);
port->enabled = false;
if (slot == 0) {
#define FWBUFF_ALIGN_SZ 512
#define MAX_DUMP_FWSZ (48 * 1024)
+static void rtl871x_load_fw_fail(struct _adapter *adapter)
+{
+ struct usb_device *udev = adapter->dvobjpriv.pusbdev;
+ struct device *dev = &udev->dev;
+ struct device *parent = dev->parent;
+
+ complete(&adapter->rtl8712_fw_ready);
+
+ dev_err(&udev->dev, "r8712u: Firmware request failed\n");
+
+ if (parent)
+ device_lock(parent);
+
+ device_release_driver(dev);
+
+ if (parent)
+ device_unlock(parent);
+}
+
static void rtl871x_load_fw_cb(const struct firmware *firmware, void *context)
{
struct _adapter *adapter = context;
if (!firmware) {
- struct usb_device *udev = adapter->dvobjpriv.pusbdev;
- struct usb_interface *usb_intf = adapter->pusb_intf;
-
- dev_err(&udev->dev, "r8712u: Firmware request failed\n");
- usb_put_dev(udev);
- usb_set_intfdata(usb_intf, NULL);
- r8712_free_drv_sw(adapter);
- adapter->dvobj_deinit(adapter);
- complete(&adapter->rtl8712_fw_ready);
- free_netdev(adapter->pnetdev);
+ rtl871x_load_fw_fail(adapter);
return;
}
adapter->fw = firmware;
break;
}
}
+
+void r8712_flush_led_works(struct _adapter *padapter)
+{
+ struct led_priv *pledpriv = &padapter->ledpriv;
+
+ flush_work(&pledpriv->SwLed0.BlinkWorkItem);
+ flush_work(&pledpriv->SwLed1.BlinkWorkItem);
+}
void r8712_InitSwLeds(struct _adapter *padapter);
void r8712_DeInitSwLeds(struct _adapter *padapter);
void LedControl871x(struct _adapter *padapter, enum LED_CTL_MODE LedAction);
+void r8712_flush_led_works(struct _adapter *padapter);
#endif
}
mutex_unlock(&pwrctrl->mutex_lock);
}
+
+void r8712_flush_rwctrl_works(struct _adapter *padapter)
+{
+ struct pwrctrl_priv *pwrctrl = &padapter->pwrctrlpriv;
+
+ flush_work(&pwrctrl->SetPSModeWorkItem);
+ flush_work(&pwrctrl->rpwm_workitem);
+}
void r8712_set_ps_mode(struct _adapter *padapter, uint ps_mode,
uint smart_ps);
void r8712_set_rpwm(struct _adapter *padapter, u8 val8);
+void r8712_flush_rwctrl_works(struct _adapter *padapter);
#endif /* __RTL871X_PWRCTRL_H_ */
{
struct net_device *pnetdev = usb_get_intfdata(pusb_intf);
struct usb_device *udev = interface_to_usbdev(pusb_intf);
+ struct _adapter *padapter = netdev_priv(pnetdev);
+
+ /* never exit with a firmware callback pending */
+ wait_for_completion(&padapter->rtl8712_fw_ready);
+ usb_set_intfdata(pusb_intf, NULL);
+ release_firmware(padapter->fw);
+ if (drvpriv.drv_registered)
+ padapter->surprise_removed = true;
+ if (pnetdev->reg_state != NETREG_UNINITIALIZED)
+ unregister_netdev(pnetdev); /* will call netdev_close() */
+ r8712_flush_rwctrl_works(padapter);
+ r8712_flush_led_works(padapter);
+ udelay(1);
+ /* Stop driver mlme relation timer */
+ r8712_stop_drv_timers(padapter);
+ r871x_dev_unload(padapter);
+ r8712_free_drv_sw(padapter);
+ free_netdev(pnetdev);
+
+ /* decrease the reference count of the usb device structure
+ * when disconnect
+ */
+ usb_put_dev(udev);
- if (pnetdev) {
- struct _adapter *padapter = netdev_priv(pnetdev);
-
- /* never exit with a firmware callback pending */
- wait_for_completion(&padapter->rtl8712_fw_ready);
- pnetdev = usb_get_intfdata(pusb_intf);
- usb_set_intfdata(pusb_intf, NULL);
- if (!pnetdev)
- goto firmware_load_fail;
- release_firmware(padapter->fw);
- if (drvpriv.drv_registered)
- padapter->surprise_removed = true;
- if (pnetdev->reg_state != NETREG_UNINITIALIZED)
- unregister_netdev(pnetdev); /* will call netdev_close() */
- flush_scheduled_work();
- udelay(1);
- /* Stop driver mlme relation timer */
- r8712_stop_drv_timers(padapter);
- r871x_dev_unload(padapter);
- r8712_free_drv_sw(padapter);
- free_netdev(pnetdev);
-
- /* decrease the reference count of the usb device structure
- * when disconnect
- */
- usb_put_dev(udev);
- }
-firmware_load_fail:
/* If we didn't unplug usb dongle and remove/insert module, driver
* fails on sitesurvey for the first time when device is up.
* Reset usb port for sitesurvey fail issue.
depends on m
select WIRELESS_EXT
select WEXT_PRIV
+ select CRYPTO_LIB_ARC4
help
This option enables support for RTL8723BS SDIO drivers, such as
the wifi found on the 1st gen Intel Compute Stick, the CHIP
} else {
rtw_c2h_wk_cmd(adapter, (u8 *)c2h_evt);
}
+ } else {
+ kfree(c2h_evt);
}
} else {
/* Error handling for malloc fail */
#include "target_core_alua.h"
static sense_reason_t
-sbc_check_prot(struct se_device *, struct se_cmd *, unsigned char *, u32, bool);
+sbc_check_prot(struct se_device *, struct se_cmd *, unsigned char, u32, bool);
static sense_reason_t sbc_execute_unmap(struct se_cmd *cmd);
static sense_reason_t
}
static sense_reason_t
-sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *ops)
+sbc_setup_write_same(struct se_cmd *cmd, unsigned char flags, struct sbc_ops *ops)
{
struct se_device *dev = cmd->se_dev;
sector_t end_lba = dev->transport->get_blocks(dev) + 1;
unsigned int sectors = sbc_get_write_same_sectors(cmd);
sense_reason_t ret;
- if ((flags[0] & 0x04) || (flags[0] & 0x02)) {
+ if ((flags & 0x04) || (flags & 0x02)) {
pr_err("WRITE_SAME PBDATA and LBDATA"
" bits not supported for Block Discard"
" Emulation\n");
}
/* We always have ANC_SUP == 0 so setting ANCHOR is always an error */
- if (flags[0] & 0x10) {
+ if (flags & 0x10) {
pr_warn("WRITE SAME with ANCHOR not supported\n");
return TCM_INVALID_CDB_FIELD;
}
* Special case for WRITE_SAME w/ UNMAP=1 that ends up getting
* translated into block discard requests within backend code.
*/
- if (flags[0] & 0x08) {
+ if (flags & 0x08) {
if (!ops->execute_unmap)
return TCM_UNSUPPORTED_SCSI_OPCODE;
if (!ops->execute_write_same)
return TCM_UNSUPPORTED_SCSI_OPCODE;
- ret = sbc_check_prot(dev, cmd, &cmd->t_task_cdb[0], sectors, true);
+ ret = sbc_check_prot(dev, cmd, flags >> 5, sectors, true);
if (ret)
return ret;
}
static sense_reason_t
-sbc_check_prot(struct se_device *dev, struct se_cmd *cmd, unsigned char *cdb,
+sbc_check_prot(struct se_device *dev, struct se_cmd *cmd, unsigned char protect,
u32 sectors, bool is_write)
{
- u8 protect = cdb[1] >> 5;
int sp_ops = cmd->se_sess->sup_prot_ops;
int pi_prot_type = dev->dev_attrib.pi_prot_type;
bool fabric_prot = false;
fallthrough;
default:
pr_err("Unable to determine pi_prot_type for CDB: 0x%02x "
- "PROTECT: 0x%02x\n", cdb[0], protect);
+ "PROTECT: 0x%02x\n", cmd->t_task_cdb[0], protect);
return TCM_INVALID_CDB_FIELD;
}
if (sbc_check_dpofua(dev, cmd, cdb))
return TCM_INVALID_CDB_FIELD;
- ret = sbc_check_prot(dev, cmd, cdb, sectors, false);
+ ret = sbc_check_prot(dev, cmd, cdb[1] >> 5, sectors, false);
if (ret)
return ret;
if (sbc_check_dpofua(dev, cmd, cdb))
return TCM_INVALID_CDB_FIELD;
- ret = sbc_check_prot(dev, cmd, cdb, sectors, false);
+ ret = sbc_check_prot(dev, cmd, cdb[1] >> 5, sectors, false);
if (ret)
return ret;
if (sbc_check_dpofua(dev, cmd, cdb))
return TCM_INVALID_CDB_FIELD;
- ret = sbc_check_prot(dev, cmd, cdb, sectors, false);
+ ret = sbc_check_prot(dev, cmd, cdb[1] >> 5, sectors, false);
if (ret)
return ret;
if (sbc_check_dpofua(dev, cmd, cdb))
return TCM_INVALID_CDB_FIELD;
- ret = sbc_check_prot(dev, cmd, cdb, sectors, true);
+ ret = sbc_check_prot(dev, cmd, cdb[1] >> 5, sectors, true);
if (ret)
return ret;
if (sbc_check_dpofua(dev, cmd, cdb))
return TCM_INVALID_CDB_FIELD;
- ret = sbc_check_prot(dev, cmd, cdb, sectors, true);
+ ret = sbc_check_prot(dev, cmd, cdb[1] >> 5, sectors, true);
if (ret)
return ret;
if (sbc_check_dpofua(dev, cmd, cdb))
return TCM_INVALID_CDB_FIELD;
- ret = sbc_check_prot(dev, cmd, cdb, sectors, true);
+ ret = sbc_check_prot(dev, cmd, cdb[1] >> 5, sectors, true);
if (ret)
return ret;
size = sbc_get_size(cmd, 1);
cmd->t_task_lba = get_unaligned_be64(&cdb[12]);
- ret = sbc_setup_write_same(cmd, &cdb[10], ops);
+ ret = sbc_setup_write_same(cmd, cdb[10], ops);
if (ret)
return ret;
break;
size = sbc_get_size(cmd, 1);
cmd->t_task_lba = get_unaligned_be64(&cdb[2]);
- ret = sbc_setup_write_same(cmd, &cdb[1], ops);
+ ret = sbc_setup_write_same(cmd, cdb[1], ops);
if (ret)
return ret;
break;
* Follow sbcr26 with WRITE_SAME (10) and check for the existence
* of byte 1 bit 3 UNMAP instead of original reserved field
*/
- ret = sbc_setup_write_same(cmd, &cdb[1], ops);
+ ret = sbc_setup_write_same(cmd, cdb[1], ops);
if (ret)
return ret;
break;
INIT_WORK(&cmd->work, success ? target_complete_ok_work :
target_complete_failure_work);
- if (wwn->cmd_compl_affinity == SE_COMPL_AFFINITY_CPUID)
+ if (!wwn || wwn->cmd_compl_affinity == SE_COMPL_AFFINITY_CPUID)
cpu = cmd->cpuid;
else
cpu = wwn->cmd_compl_affinity;
struct optee_msg_arg *ma;
shm = tee_shm_alloc(ctx, OPTEE_MSG_GET_ARG_SIZE(num_params),
- TEE_SHM_MAPPED);
+ TEE_SHM_MAPPED | TEE_SHM_PRIV);
if (IS_ERR(shm))
return shm;
}
/**
- * optee_disable_shm_cache() - Disables caching of some shared memory allocation
- * in OP-TEE
+ * __optee_disable_shm_cache() - Disables caching of some shared memory
+ * allocation in OP-TEE
* @optee: main service struct
+ * @is_mapped: true if the cached shared memory addresses were mapped by this
+ * kernel, are safe to dereference, and should be freed
*/
-void optee_disable_shm_cache(struct optee *optee)
+static void __optee_disable_shm_cache(struct optee *optee, bool is_mapped)
{
struct optee_call_waiter w;
if (res.result.status == OPTEE_SMC_RETURN_OK) {
struct tee_shm *shm;
+ /*
+ * Shared memory references that were not mapped by
+ * this kernel must be ignored to prevent a crash.
+ */
+ if (!is_mapped)
+ continue;
+
shm = reg_pair_to_ptr(res.result.shm_upper32,
res.result.shm_lower32);
tee_shm_free(shm);
optee_cq_wait_final(&optee->call_queue, &w);
}
+/**
+ * optee_disable_shm_cache() - Disables caching of mapped shared memory
+ * allocations in OP-TEE
+ * @optee: main service struct
+ */
+void optee_disable_shm_cache(struct optee *optee)
+{
+ return __optee_disable_shm_cache(optee, true);
+}
+
+/**
+ * optee_disable_unmapped_shm_cache() - Disables caching of shared memory
+ * allocations in OP-TEE which are not
+ * currently mapped
+ * @optee: main service struct
+ */
+void optee_disable_unmapped_shm_cache(struct optee *optee)
+{
+ return __optee_disable_shm_cache(optee, false);
+}
+
#define PAGELIST_ENTRIES_PER_PAGE \
((OPTEE_MSG_NONCONTIG_PAGE_SIZE / sizeof(u64)) - 1)
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/arm-smccc.h>
+#include <linux/crash_dump.h>
#include <linux/errno.h>
#include <linux/io.h>
#include <linux/module.h>
if (!ctxdata)
return;
- shm = tee_shm_alloc(ctx, sizeof(struct optee_msg_arg), TEE_SHM_MAPPED);
+ shm = tee_shm_alloc(ctx, sizeof(struct optee_msg_arg),
+ TEE_SHM_MAPPED | TEE_SHM_PRIV);
if (!IS_ERR(shm)) {
arg = tee_shm_get_va(shm, 0);
/*
return ERR_PTR(-EINVAL);
}
+/* optee_remove - Device Removal Routine
+ * @pdev: platform device information struct
+ *
+ * optee_remove is called by platform subsystem to alert the driver
+ * that it should release the device
+ */
+
static int optee_remove(struct platform_device *pdev)
{
struct optee *optee = platform_get_drvdata(pdev);
return 0;
}
+/* optee_shutdown - Device Removal Routine
+ * @pdev: platform device information struct
+ *
+ * platform_shutdown is called by the platform subsystem to alert
+ * the driver that a shutdown, reboot, or kexec is happening and
+ * device must be disabled.
+ */
+static void optee_shutdown(struct platform_device *pdev)
+{
+ optee_disable_shm_cache(platform_get_drvdata(pdev));
+}
+
static int optee_probe(struct platform_device *pdev)
{
optee_invoke_fn *invoke_fn;
u32 sec_caps;
int rc;
+ /*
+ * The kernel may have crashed at the same time that all available
+ * secure world threads were suspended and we cannot reschedule the
+ * suspended threads without access to the crashed kernel's wait_queue.
+ * Therefore, we cannot reliably initialize the OP-TEE driver in the
+ * kdump kernel.
+ */
+ if (is_kdump_kernel())
+ return -ENODEV;
+
invoke_fn = get_invoke_func(&pdev->dev);
if (IS_ERR(invoke_fn))
return PTR_ERR(invoke_fn);
optee->memremaped_shm = memremaped_shm;
optee->pool = pool;
+ /*
+ * Ensure that there are no pre-existing shm objects before enabling
+ * the shm cache so that there's no chance of receiving an invalid
+ * address during shutdown. This could occur, for example, if we're
+ * kexec booting from an older kernel that did not properly cleanup the
+ * shm cache.
+ */
+ optee_disable_unmapped_shm_cache(optee);
+
optee_enable_shm_cache(optee);
if (optee->sec_caps & OPTEE_SMC_SEC_CAP_DYNAMIC_SHM)
static struct platform_driver optee_driver = {
.probe = optee_probe,
.remove = optee_remove,
+ .shutdown = optee_shutdown,
.driver = {
.name = "optee",
.of_match_table = optee_dt_match,
void optee_enable_shm_cache(struct optee *optee);
void optee_disable_shm_cache(struct optee *optee);
+void optee_disable_unmapped_shm_cache(struct optee *optee);
int optee_shm_register(struct tee_context *ctx, struct tee_shm *shm,
struct page **pages, size_t num_pages,
shm = cmd_alloc_suppl(ctx, sz);
break;
case OPTEE_RPC_SHM_TYPE_KERNEL:
- shm = tee_shm_alloc(ctx, sz, TEE_SHM_MAPPED);
+ shm = tee_shm_alloc(ctx, sz, TEE_SHM_MAPPED | TEE_SHM_PRIV);
break;
default:
arg->ret = TEEC_ERROR_BAD_PARAMETERS;
switch (OPTEE_SMC_RETURN_GET_RPC_FUNC(param->a0)) {
case OPTEE_SMC_RPC_FUNC_ALLOC:
- shm = tee_shm_alloc(ctx, param->a1, TEE_SHM_MAPPED);
+ shm = tee_shm_alloc(ctx, param->a1,
+ TEE_SHM_MAPPED | TEE_SHM_PRIV);
if (!IS_ERR(shm) && !tee_shm_get_pa(shm, 0, &pa)) {
reg_pair_from_64(¶m->a1, ¶m->a2, pa);
reg_pair_from_64(¶m->a4, ¶m->a5,
shm->paddr = page_to_phys(page);
shm->size = PAGE_SIZE << order;
- if (shm->flags & TEE_SHM_DMA_BUF) {
+ /*
+ * Shared memory private to the OP-TEE driver doesn't need
+ * to be registered with OP-TEE.
+ */
+ if (!(shm->flags & TEE_SHM_PRIV)) {
unsigned int nr_pages = 1 << order, i;
struct page **pages;
pages = kcalloc(nr_pages, sizeof(pages), GFP_KERNEL);
- if (!pages)
- return -ENOMEM;
+ if (!pages) {
+ rc = -ENOMEM;
+ goto err;
+ }
for (i = 0; i < nr_pages; i++) {
pages[i] = page;
rc = optee_shm_register(shm->ctx, shm, pages, nr_pages,
(unsigned long)shm->kaddr);
kfree(pages);
+ if (rc)
+ goto err;
}
+ return 0;
+
+err:
+ __free_pages(page, order);
return rc;
}
static void pool_op_free(struct tee_shm_pool_mgr *poolm,
struct tee_shm *shm)
{
- if (shm->flags & TEE_SHM_DMA_BUF)
+ if (!(shm->flags & TEE_SHM_PRIV))
optee_shm_unregister(shm->ctx, shm);
free_pages((unsigned long)shm->kaddr, get_order(shm->size));
return ERR_PTR(-EINVAL);
}
- if ((flags & ~(TEE_SHM_MAPPED | TEE_SHM_DMA_BUF))) {
+ if ((flags & ~(TEE_SHM_MAPPED | TEE_SHM_DMA_BUF | TEE_SHM_PRIV))) {
dev_err(teedev->dev.parent, "invalid shm flags 0x%x", flags);
return ERR_PTR(-EINVAL);
}
}
EXPORT_SYMBOL_GPL(tee_shm_alloc);
+/**
+ * tee_shm_alloc_kernel_buf() - Allocate shared memory for kernel buffer
+ * @ctx: Context that allocates the shared memory
+ * @size: Requested size of shared memory
+ *
+ * The returned memory registered in secure world and is suitable to be
+ * passed as a memory buffer in parameter argument to
+ * tee_client_invoke_func(). The memory allocated is later freed with a
+ * call to tee_shm_free().
+ *
+ * @returns a pointer to 'struct tee_shm'
+ */
+struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size)
+{
+ return tee_shm_alloc(ctx, size, TEE_SHM_MAPPED);
+}
+EXPORT_SYMBOL_GPL(tee_shm_alloc_kernel_buf);
+
struct tee_shm *tee_shm_register(struct tee_context *ctx, unsigned long addr,
size_t length, u32 flags)
{
NULL,
};
-static bool has_port(const struct tb_switch *sw, enum tb_port_type type)
-{
- const struct tb_port *port;
-
- tb_switch_for_each_port(sw, port) {
- if (!port->disabled && port->config.type == type)
- return true;
- }
-
- return false;
-}
-
static umode_t switch_attr_is_visible(struct kobject *kobj,
struct attribute *attr, int n)
{
if (attr == &dev_attr_authorized.attr) {
if (sw->tb->security_level == TB_SECURITY_NOPCIE ||
- sw->tb->security_level == TB_SECURITY_DPONLY ||
- !has_port(sw, TB_TYPE_PCIE_UP))
+ sw->tb->security_level == TB_SECURITY_DPONLY)
return 0;
} else if (attr == &dev_attr_device.attr) {
if (!sw->device)
{
struct uart_8250_port *up = up_to_u8250p(port);
unsigned int iir, lsr;
+ unsigned long flags;
unsigned int space, count;
iir = serial_port_in(port, UART_IIR);
if (iir & UART_IIR_NO_INT)
return 0;
- spin_lock(&port->lock);
+ spin_lock_irqsave(&port->lock, flags);
lsr = serial_port_in(port, UART_LSR);
if (lsr & UART_LSR_THRE)
serial8250_tx_chars(up);
- uart_unlock_and_check_sysrq(port);
+ uart_unlock_and_check_sysrq_irqrestore(port, flags);
return 1;
}
int fsl8250_handle_irq(struct uart_port *port)
{
unsigned char lsr, orig_lsr;
+ unsigned long flags;
unsigned int iir;
struct uart_8250_port *up = up_to_u8250p(port);
- spin_lock(&up->port.lock);
+ spin_lock_irqsave(&up->port.lock, flags);
iir = port->serial_in(port, UART_IIR);
if (iir & UART_IIR_NO_INT) {
up->lsr_saved_flags = orig_lsr;
- uart_unlock_and_check_sysrq(&up->port);
+ uart_unlock_and_check_sysrq_irqrestore(&up->port, flags);
return 1;
}
struct dma_tx_state state;
int copied, total, cnt;
unsigned char *ptr;
+ unsigned long flags;
if (data->rx_status == DMA_RX_SHUTDOWN)
return;
+ spin_lock_irqsave(&up->port.lock, flags);
+
dmaengine_tx_status(dma->rxchan, dma->rx_cookie, &state);
total = dma->rx_size - state.residue;
cnt = total;
tty_flip_buffer_push(tty_port);
mtk8250_rx_dma(up);
+
+ spin_unlock_irqrestore(&up->port.lock, flags);
}
static void mtk8250_rx_dma(struct uart_8250_port *up)
{ PCI_VDEVICE(INTEL, 0x0f0c), },
{ PCI_VDEVICE(INTEL, 0x228a), },
{ PCI_VDEVICE(INTEL, 0x228c), },
+ { PCI_VDEVICE(INTEL, 0x4b96), },
+ { PCI_VDEVICE(INTEL, 0x4b97), },
+ { PCI_VDEVICE(INTEL, 0x4b98), },
+ { PCI_VDEVICE(INTEL, 0x4b99), },
+ { PCI_VDEVICE(INTEL, 0x4b9a), },
+ { PCI_VDEVICE(INTEL, 0x4b9b), },
{ PCI_VDEVICE(INTEL, 0x9ce3), },
{ PCI_VDEVICE(INTEL, 0x9ce4), },
if (pci_match_id(pci_use_msi, dev)) {
dev_dbg(&dev->dev, "Using MSI(-X) interrupts\n");
pci_set_master(dev);
+ uart.port.flags &= ~UPF_SHARE_IRQ;
rc = pci_alloc_irq_vectors(dev, 1, 1, PCI_IRQ_ALL_TYPES);
} else {
dev_dbg(&dev->dev, "Using legacy interrupts\n");
/* Uart divisor latch read */
static int default_serial_dl_read(struct uart_8250_port *up)
{
- return serial_in(up, UART_DLL) | serial_in(up, UART_DLM) << 8;
+ /* Assign these in pieces to truncate any bits above 7. */
+ unsigned char dll = serial_in(up, UART_DLL);
+ unsigned char dlm = serial_in(up, UART_DLM);
+
+ return dll | dlm << 8;
}
/* Uart divisor latch write */
serial_out(up, UART_LCR, 0);
serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO);
- scratch = serial_in(up, UART_IIR) >> 6;
- switch (scratch) {
+ /* Assign this as it is to truncate any bits above 7. */
+ scratch = serial_in(up, UART_IIR);
+
+ switch (scratch >> 6) {
case 0:
autoconfig_8250(up);
break;
unsigned char status;
struct uart_8250_port *up = up_to_u8250p(port);
bool skip_rx = false;
+ unsigned long flags;
if (iir & UART_IIR_NO_INT)
return 0;
- spin_lock(&port->lock);
+ spin_lock_irqsave(&port->lock, flags);
status = serial_port_in(port, UART_LSR);
(up->ier & UART_IER_THRI))
serial8250_tx_chars(up);
- uart_unlock_and_check_sysrq(port);
+ uart_unlock_and_check_sysrq_irqrestore(port, flags);
return 1;
}
static unsigned int lpuart32_get_mctrl(struct uart_port *port)
{
- unsigned int mctrl = 0;
+ unsigned int mctrl = TIOCM_CAR | TIOCM_DSR | TIOCM_CTS;
u32 reg;
reg = lpuart32_read(port, UARTCTRL);
freq = uartclk;
if (freq == 0) {
dev_err(dev, "Cannot get clock rate\n");
- return -EINVAL;
+ ret = -EINVAL;
+ goto out_clk;
}
if (xtal) {
if (tup->cdata->fifo_mode_enable_status) {
ret = tegra_uart_wait_fifo_mode_enabled(tup);
- dev_err(tup->uport.dev, "FIFO mode not enabled\n");
- if (ret < 0)
+ if (ret < 0) {
+ dev_err(tup->uport.dev,
+ "Failed to enable FIFO mode: %d\n", ret);
return ret;
+ }
} else {
/*
* For all tegra devices (up to t210), there is a hardware
request->actual = 0;
priv_dev->status_completion_no_call = true;
priv_dev->pending_status_request = request;
+ usb_gadget_set_state(&priv_dev->gadget, USB_STATE_CONFIGURED);
spin_unlock_irqrestore(&priv_dev->lock, flags);
/*
pdev->gadget.name = "cdnsp-gadget";
pdev->gadget.speed = USB_SPEED_UNKNOWN;
pdev->gadget.sg_supported = 1;
- pdev->gadget.max_speed = USB_SPEED_SUPER_PLUS;
+ pdev->gadget.max_speed = max_speed;
pdev->gadget.lpm_capable = 1;
pdev->setup_buf = kzalloc(CDNSP_EP0_SETUP_SIZE, GFP_KERNEL);
#define IMAN_IE BIT(1)
#define IMAN_IP BIT(0)
/* bits 2:31 need to be preserved */
-#define IMAN_IE_SET(p) (((p) & IMAN_IE) | 0x2)
-#define IMAN_IE_CLEAR(p) (((p) & IMAN_IE) & ~(0x2))
+#define IMAN_IE_SET(p) ((p) | IMAN_IE)
+#define IMAN_IE_CLEAR(p) ((p) & ~IMAN_IE)
/* IMOD - Interrupter Moderation Register - irq_control bitmasks. */
/*
}
if (enqd_len + trb_buff_len >= full_len) {
- if (need_zero_pkt && zero_len_trb) {
- zero_len_trb = true;
- } else {
- field &= ~TRB_CHAIN;
- field |= TRB_IOC;
- more_trbs_coming = false;
- need_zero_pkt = false;
- preq->td.last_trb = ring->enqueue;
- }
+ if (need_zero_pkt)
+ zero_len_trb = !zero_len_trb;
+
+ field &= ~TRB_CHAIN;
+ field |= TRB_IOC;
+ more_trbs_coming = false;
+ preq->td.last_trb = ring->enqueue;
}
/* Only set interrupt on short packet for OUT endpoints. */
length_field = TRB_LEN(trb_buff_len) | TRB_TD_SIZE(remainder) |
TRB_INTR_TARGET(0);
- cdnsp_queue_trb(pdev, ring, more_trbs_coming | need_zero_pkt,
+ cdnsp_queue_trb(pdev, ring, more_trbs_coming | zero_len_trb,
lower_32_bits(send_addr),
upper_32_bits(send_addr),
length_field,
};
/* --- WWAN framework integration --- */
-#ifdef CONFIG_WWAN
+#ifdef CONFIG_WWAN_CORE
static int wdm_wwan_port_start(struct wwan_port *port)
{
struct wdm_device *desc = wwan_port_get_drvdata(port);
/* inbuf has been copied, it is safe to check for outstanding data */
schedule_work(&desc->service_outs_intr);
}
-#else /* CONFIG_WWAN */
+#else /* CONFIG_WWAN_CORE */
static void wdm_wwan_init(struct wdm_device *desc) {}
static void wdm_wwan_deinit(struct wdm_device *desc) {}
static void wdm_wwan_rx(struct wdm_device *desc, int length) {}
-#endif /* CONFIG_WWAN */
+#endif /* CONFIG_WWAN_CORE */
/* --- error handling --- */
static void wdm_rxwork(struct work_struct *work)
dev_err(dev, "overflow with length %d, actual length is %d\n",
data->iin_wMaxPacketSize, urb->actual_length);
fallthrough;
- case -ECONNRESET:
- case -ENOENT:
- case -ESHUTDOWN:
- case -EILSEQ:
- case -ETIME:
- case -EPIPE:
+ default:
/* urb terminated, clean up */
dev_dbg(dev, "urb terminated, status: %d\n", status);
return;
- default:
- dev_err(dev, "unknown status received: %d\n", status);
}
exit:
rv = usb_submit_urb(urb, GFP_ATOMIC);
if (!fsm->host_req_flag)
return;
- INIT_DELAYED_WORK(&fsm->hnp_polling_work, otg_hnp_polling_work);
+ if (!fsm->hnp_work_inited) {
+ INIT_DELAYED_WORK(&fsm->hnp_polling_work, otg_hnp_polling_work);
+ fsm->hnp_work_inited = true;
+ }
+
schedule_delayed_work(&fsm->hnp_polling_work,
msecs_to_jiffies(T_HOST_REQ_POLL));
}
"wIndex=%04x wLength=%04x\n",
ctrl->bRequestType, ctrl->bRequest, ctrl->wValue,
ctrl->wIndex, ctrl->wLength);
- if (ctrl->bRequestType & 0x80) {
+ if ((ctrl->bRequestType & USB_DIR_IN) && ctrl->wLength) {
pipe = usb_rcvctrlpipe(dev, 0);
snoop_urb(dev, NULL, pipe, ctrl->wLength, tmo, SUBMIT, NULL, 0);
#define USB_TP_TRANSMISSION_DELAY 40 /* ns */
#define USB_TP_TRANSMISSION_DELAY_MAX 65535 /* ns */
+#define USB_PING_RESPONSE_TIME 400 /* ns */
/* Protect struct usb_device->state and ->children members
* Note: Both are also protected by ->dev.sem, except that ->state can
}
/*
- * Set the Maximum Exit Latency (MEL) for the host to initiate a transition from
- * either U1 or U2.
+ * Set the Maximum Exit Latency (MEL) for the host to wakup up the path from
+ * U1/U2, send a PING to the device and receive a PING_RESPONSE.
+ * See USB 3.1 section C.1.5.2
*/
static void usb_set_lpm_mel(struct usb_device *udev,
struct usb3_lpm_parameters *udev_lpm_params,
unsigned int hub_exit_latency)
{
unsigned int total_mel;
- unsigned int device_mel;
- unsigned int hub_mel;
/*
- * Calculate the time it takes to transition all links from the roothub
- * to the parent hub into U0. The parent hub must then decode the
- * packet (hub header decode latency) to figure out which port it was
- * bound for.
- *
- * The Hub Header decode latency is expressed in 0.1us intervals (0x1
- * means 0.1us). Multiply that by 100 to get nanoseconds.
+ * tMEL1. time to transition path from host to device into U0.
+ * MEL for parent already contains the delay up to parent, so only add
+ * the exit latency for the last link (pick the slower exit latency),
+ * and the hub header decode latency. See USB 3.1 section C 2.2.1
+ * Store MEL in nanoseconds
*/
total_mel = hub_lpm_params->mel +
- (hub->descriptor->u.ss.bHubHdrDecLat * 100);
+ max(udev_exit_latency, hub_exit_latency) * 1000 +
+ hub->descriptor->u.ss.bHubHdrDecLat * 100;
/*
- * How long will it take to transition the downstream hub's port into
- * U0? The greater of either the hub exit latency or the device exit
- * latency.
- *
- * The BOS U1/U2 exit latencies are expressed in 1us intervals.
- * Multiply that by 1000 to get nanoseconds.
+ * tMEL2. Time to submit PING packet. Sum of tTPTransmissionDelay for
+ * each link + wHubDelay for each hub. Add only for last link.
+ * tMEL4, the time for PING_RESPONSE to traverse upstream is similar.
+ * Multiply by 2 to include it as well.
*/
- device_mel = udev_exit_latency * 1000;
- hub_mel = hub_exit_latency * 1000;
- if (device_mel > hub_mel)
- total_mel += device_mel;
- else
- total_mel += hub_mel;
+ total_mel += (__le16_to_cpu(hub->descriptor->u.ss.wHubDelay) +
+ USB_TP_TRANSMISSION_DELAY) * 2;
+
+ /*
+ * tMEL3, tPingResponse. Time taken by device to generate PING_RESPONSE
+ * after receiving PING. Also add 2100ns as stated in USB 3.1 C 1.5.2.4
+ * to cover the delay if the PING_RESPONSE is queued behind a Max Packet
+ * Size DP.
+ * Note these delays should be added only once for the entire path, so
+ * add them to the MEL of the device connected to the roothub.
+ */
+ if (!hub->hdev->parent)
+ total_mel += USB_PING_RESPONSE_TIME + 2100;
udev_lpm_params->mel = total_mel;
}
}
/*
+ * Don't allow device intiated U1/U2 if the system exit latency + one bus
+ * interval is greater than the minimum service interval of any active
+ * periodic endpoint. See USB 3.2 section 9.4.9
+ */
+static bool usb_device_may_initiate_lpm(struct usb_device *udev,
+ enum usb3_link_state state)
+{
+ unsigned int sel; /* us */
+ int i, j;
+
+ if (state == USB3_LPM_U1)
+ sel = DIV_ROUND_UP(udev->u1_params.sel, 1000);
+ else if (state == USB3_LPM_U2)
+ sel = DIV_ROUND_UP(udev->u2_params.sel, 1000);
+ else
+ return false;
+
+ for (i = 0; i < udev->actconfig->desc.bNumInterfaces; i++) {
+ struct usb_interface *intf;
+ struct usb_endpoint_descriptor *desc;
+ unsigned int interval;
+
+ intf = udev->actconfig->interface[i];
+ if (!intf)
+ continue;
+
+ for (j = 0; j < intf->cur_altsetting->desc.bNumEndpoints; j++) {
+ desc = &intf->cur_altsetting->endpoint[j].desc;
+
+ if (usb_endpoint_xfer_int(desc) ||
+ usb_endpoint_xfer_isoc(desc)) {
+ interval = (1 << (desc->bInterval - 1)) * 125;
+ if (sel + 125 > interval)
+ return false;
+ }
+ }
+ }
+ return true;
+}
+
+/*
* Enable the hub-initiated U1/U2 idle timeouts, and enable device-initiated
* U1/U2 entry.
*
* U1/U2_ENABLE
*/
if (udev->actconfig &&
- usb_set_device_initiated_lpm(udev, state, true) == 0) {
- if (state == USB3_LPM_U1)
- udev->usb3_lpm_u1_enabled = 1;
- else if (state == USB3_LPM_U2)
- udev->usb3_lpm_u2_enabled = 1;
- } else {
- /* Don't request U1/U2 entry if the device
- * cannot transition to U1/U2.
- */
- usb_set_lpm_timeout(udev, state, 0);
- hcd->driver->disable_usb3_lpm_timeout(hcd, udev, state);
+ usb_device_may_initiate_lpm(udev, state)) {
+ if (usb_set_device_initiated_lpm(udev, state, true)) {
+ /*
+ * Request to enable device initiated U1/U2 failed,
+ * better to turn off lpm in this case.
+ */
+ usb_set_lpm_timeout(udev, state, 0);
+ hcd->driver->disable_usb3_lpm_timeout(hcd, udev, state);
+ return;
+ }
}
-}
+ if (state == USB3_LPM_U1)
+ udev->usb3_lpm_u1_enabled = 1;
+ else if (state == USB3_LPM_U2)
+ udev->usb3_lpm_u2_enabled = 1;
+}
/*
* Disable the hub-initiated U1/U2 idle timeouts, and disable device-initiated
* U1/U2 entry.
/* 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 },
* 0 - No (default)
* 1 - Partial power down
* 2 - Hibernation
+ * @no_clock_gating: Specifies whether to avoid clock gating feature.
+ * 0 - No (use clock gating)
+ * 1 - Yes (avoid it)
* @lpm: Enable LPM support.
* 0 - No
* 1 - Yes
#define DWC2_POWER_DOWN_PARAM_NONE 0
#define DWC2_POWER_DOWN_PARAM_PARTIAL 1
#define DWC2_POWER_DOWN_PARAM_HIBERNATION 2
+ bool no_clock_gating;
bool lpm;
bool lpm_clock_gating;
* If neither hibernation nor partial power down are supported,
* clock gating is used to save power.
*/
- dwc2_gadget_enter_clock_gating(hsotg);
+ if (!hsotg->params.no_clock_gating)
+ dwc2_gadget_enter_clock_gating(hsotg);
}
/*
return;
}
- /* Zlp for all endpoints, for ep0 only in DATA IN stage */
+ /* Zlp for all endpoints in non DDMA, for ep0 only in DATA IN stage */
if (hs_ep->send_zlp) {
- dwc2_hsotg_program_zlp(hsotg, hs_ep);
hs_ep->send_zlp = 0;
- /* transfer will be completed on next complete interrupt */
- return;
+ if (!using_desc_dma(hsotg)) {
+ dwc2_hsotg_program_zlp(hsotg, hs_ep);
+ /* transfer will be completed on next complete interrupt */
+ return;
+ }
}
if (hs_ep->index == 0 && hsotg->ep0_state == DWC2_EP0_DATA_IN) {
__func__);
}
} else {
+ /* Mask GINTSTS_GOUTNAKEFF interrupt */
+ dwc2_hsotg_disable_gsint(hsotg, GINTSTS_GOUTNAKEFF);
+
if (!(dwc2_readl(hsotg, GINTSTS) & GINTSTS_GOUTNAKEFF))
dwc2_set_bit(hsotg, DCTL, DCTL_SGOUTNAK);
+ if (!using_dma(hsotg)) {
+ /* Wait for GINTSTS_RXFLVL interrupt */
+ if (dwc2_hsotg_wait_bit_set(hsotg, GINTSTS,
+ GINTSTS_RXFLVL, 100)) {
+ dev_warn(hsotg->dev, "%s: timeout GINTSTS.RXFLVL\n",
+ __func__);
+ } else {
+ /*
+ * Pop GLOBAL OUT NAK status packet from RxFIFO
+ * to assert GOUTNAKEFF interrupt
+ */
+ dwc2_readl(hsotg, GRXSTSP);
+ }
+ }
+
/* Wait for global nak to take effect */
if (dwc2_hsotg_wait_bit_set(hsotg, GINTSTS,
GINTSTS_GOUTNAKEFF, 100))
epctl = dwc2_readl(hs, epreg);
if (value) {
+ /* Unmask GOUTNAKEFF interrupt */
+ dwc2_hsotg_en_gsint(hs, GINTSTS_GOUTNAKEFF);
+
if (!(dwc2_readl(hs, GINTSTS) & GINTSTS_GOUTNAKEFF))
dwc2_set_bit(hs, DCTL, DCTL_SGOUTNAK);
// STALL bit will be set in GOUTNAKEFF interrupt handler
* If not hibernation nor partial power down are supported,
* clock gating is used to save power.
*/
- dwc2_host_enter_clock_gating(hsotg);
+ if (!hsotg->params.no_clock_gating)
+ dwc2_host_enter_clock_gating(hsotg);
break;
}
* If not hibernation nor partial power down are supported,
* clock gating is used to save power.
*/
- dwc2_host_enter_clock_gating(hsotg);
+ if (!hsotg->params.no_clock_gating)
+ dwc2_host_enter_clock_gating(hsotg);
/* After entering suspend, hardware is not accessible */
clear_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags);
struct dwc2_core_params *p = &hsotg->params;
p->power_down = DWC2_POWER_DOWN_PARAM_NONE;
+ p->no_clock_gating = true;
p->phy_utmi_width = 8;
}
unsigned dis_metastability_quirk:1;
unsigned dis_split_quirk:1;
+ unsigned async_callbacks:1;
u16 imod_interval;
};
static int dwc3_ep0_delegate_req(struct dwc3 *dwc, struct usb_ctrlrequest *ctrl)
{
- int ret;
+ int ret = -EINVAL;
- spin_unlock(&dwc->lock);
- ret = dwc->gadget_driver->setup(dwc->gadget, ctrl);
- spin_lock(&dwc->lock);
+ if (dwc->async_callbacks) {
+ spin_unlock(&dwc->lock);
+ ret = dwc->gadget_driver->setup(dwc->gadget, ctrl);
+ spin_lock(&dwc->lock);
+ }
return ret;
}
{
struct dwc3_request *req;
struct dwc3_request *tmp;
+ struct list_head local;
struct dwc3 *dwc = dep->dwc;
- list_for_each_entry_safe(req, tmp, &dep->cancelled_list, list) {
+restart:
+ list_replace_init(&dep->cancelled_list, &local);
+
+ list_for_each_entry_safe(req, tmp, &local, list) {
dwc3_gadget_ep_skip_trbs(dep, req);
switch (req->status) {
case DWC3_REQUEST_STATUS_DISCONNECTED:
break;
}
}
+
+ if (!list_empty(&dep->cancelled_list))
+ goto restart;
}
static int dwc3_gadget_ep_dequeue(struct usb_ep *ep,
}
/*
+ * Avoid issuing a runtime resume if the device is already in the
+ * suspended state during gadget disconnect. DWC3 gadget was already
+ * halted/stopped during runtime suspend.
+ */
+ if (!is_on) {
+ pm_runtime_barrier(dwc->dev);
+ if (pm_runtime_suspended(dwc->dev))
+ return 0;
+ }
+
+ /*
* Check the return value for successful resume, or error. For a
* successful resume, the DWC3 runtime PM resume routine will handle
* the run stop sequence, so avoid duplicate operations here.
return ret;
}
+static void dwc3_gadget_async_callbacks(struct usb_gadget *g, bool enable)
+{
+ struct dwc3 *dwc = gadget_to_dwc(g);
+ unsigned long flags;
+
+ spin_lock_irqsave(&dwc->lock, flags);
+ dwc->async_callbacks = enable;
+ spin_unlock_irqrestore(&dwc->lock, flags);
+}
+
static const struct usb_gadget_ops dwc3_gadget_ops = {
.get_frame = dwc3_gadget_get_frame,
.wakeup = dwc3_gadget_wakeup,
.udc_set_ssp_rate = dwc3_gadget_set_ssp_rate,
.get_config_params = dwc3_gadget_config_params,
.vbus_draw = dwc3_gadget_vbus_draw,
+ .udc_async_callbacks = dwc3_gadget_async_callbacks,
};
/* -------------------------------------------------------------------------- */
{
struct dwc3_request *req;
struct dwc3_request *tmp;
+ struct list_head local;
- list_for_each_entry_safe(req, tmp, &dep->started_list, list) {
+restart:
+ list_replace_init(&dep->started_list, &local);
+
+ list_for_each_entry_safe(req, tmp, &local, list) {
int ret;
ret = dwc3_gadget_ep_cleanup_completed_request(dep, event,
if (ret)
break;
}
+
+ if (!list_empty(&dep->started_list))
+ goto restart;
}
static bool dwc3_gadget_ep_should_continue(struct dwc3_ep *dep)
static void dwc3_disconnect_gadget(struct dwc3 *dwc)
{
- if (dwc->gadget_driver && dwc->gadget_driver->disconnect) {
+ if (dwc->async_callbacks && dwc->gadget_driver->disconnect) {
spin_unlock(&dwc->lock);
dwc->gadget_driver->disconnect(dwc->gadget);
spin_lock(&dwc->lock);
static void dwc3_suspend_gadget(struct dwc3 *dwc)
{
- if (dwc->gadget_driver && dwc->gadget_driver->suspend) {
+ if (dwc->async_callbacks && dwc->gadget_driver->suspend) {
spin_unlock(&dwc->lock);
dwc->gadget_driver->suspend(dwc->gadget);
spin_lock(&dwc->lock);
static void dwc3_resume_gadget(struct dwc3 *dwc)
{
- if (dwc->gadget_driver && dwc->gadget_driver->resume) {
+ if (dwc->async_callbacks && dwc->gadget_driver->resume) {
spin_unlock(&dwc->lock);
dwc->gadget_driver->resume(dwc->gadget);
spin_lock(&dwc->lock);
if (!dwc->gadget_driver)
return;
- if (dwc->gadget->speed != USB_SPEED_UNKNOWN) {
+ if (dwc->async_callbacks && dwc->gadget->speed != USB_SPEED_UNKNOWN) {
spin_unlock(&dwc->lock);
usb_gadget_udc_reset(dwc->gadget, dwc->gadget_driver);
spin_lock(&dwc->lock);
* implemented.
*/
- if (dwc->gadget_driver && dwc->gadget_driver->resume) {
+ if (dwc->async_callbacks && dwc->gadget_driver->resume) {
spin_unlock(&dwc->lock);
dwc->gadget_driver->resume(dwc->gadget);
spin_lock(&dwc->lock);
unsigned char bInterfaceSubClass;
unsigned char bInterfaceProtocol;
unsigned char protocol;
+ unsigned char idle;
unsigned short report_desc_length;
char *report_desc;
unsigned short report_length;
spin_lock_irqsave(&hidg->write_spinlock, flags);
+ if (!hidg->req) {
+ spin_unlock_irqrestore(&hidg->write_spinlock, flags);
+ return -ESHUTDOWN;
+ }
+
#define WRITE_COND (!hidg->write_pending)
try_again:
/* write queue */
count = min_t(unsigned, count, hidg->report_length);
spin_unlock_irqrestore(&hidg->write_spinlock, flags);
- status = copy_from_user(req->buf, buffer, count);
+ if (!req) {
+ ERROR(hidg->func.config->cdev, "hidg->req is NULL\n");
+ status = -ESHUTDOWN;
+ goto release_write_pending;
+ }
+
+ status = copy_from_user(req->buf, buffer, count);
if (status != 0) {
ERROR(hidg->func.config->cdev,
"copy_from_user error\n");
spin_unlock_irqrestore(&hidg->write_spinlock, flags);
+ if (!hidg->in_ep->enabled) {
+ ERROR(hidg->func.config->cdev, "in_ep is disabled\n");
+ status = -ESHUTDOWN;
+ goto release_write_pending;
+ }
+
status = usb_ep_queue(hidg->in_ep, req, GFP_ATOMIC);
- if (status < 0) {
- ERROR(hidg->func.config->cdev,
- "usb_ep_queue error on int endpoint %zd\n", status);
+ if (status < 0)
goto release_write_pending;
- } else {
+ else
status = count;
- }
return status;
release_write_pending:
goto respond;
break;
+ case ((USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_INTERFACE) << 8
+ | HID_REQ_GET_IDLE):
+ VDBG(cdev, "get_idle\n");
+ length = min_t(unsigned int, length, 1);
+ ((u8 *) req->buf)[0] = hidg->idle;
+ goto respond;
+ break;
+
case ((USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE) << 8
| HID_REQ_SET_REPORT):
VDBG(cdev, "set_report | wLength=%d\n", ctrl->wLength);
goto stall;
break;
+ case ((USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE) << 8
+ | HID_REQ_SET_IDLE):
+ VDBG(cdev, "set_idle\n");
+ length = 0;
+ hidg->idle = value >> 8;
+ goto respond;
+ break;
+
case ((USB_DIR_IN | USB_TYPE_STANDARD | USB_RECIP_INTERFACE) << 8
| USB_REQ_GET_DESCRIPTOR):
switch (value >> 8) {
hidg_interface_desc.bInterfaceSubClass = hidg->bInterfaceSubClass;
hidg_interface_desc.bInterfaceProtocol = hidg->bInterfaceProtocol;
hidg->protocol = HID_REPORT_PROTOCOL;
+ hidg->idle = 1;
hidg_ss_in_ep_desc.wMaxPacketSize = cpu_to_le16(hidg->report_length);
hidg_ss_in_comp_desc.wBytesPerInterval =
cpu_to_le16(hidg->report_length);
struct gs_port *port;
mutex_lock(&ports[port_num].lock);
- if (WARN_ON(!ports[port_num].port)) {
+ if (!ports[port_num].port) {
mutex_unlock(&ports[port_num].lock);
return;
}
case USB_SPEED_FULL:
if (max <= 1023)
break;
+ fallthrough;
default:
goto en_done;
}
err = devm_request_irq(&spi->dev, irq, max3420_irq_handler, 0,
"max3420", udc);
if (err < 0)
- return err;
+ goto del_gadget;
udc->thread_task = kthread_create(max3420_thread, udc,
"max3420-thread");
- if (IS_ERR(udc->thread_task))
- return PTR_ERR(udc->thread_task);
+ if (IS_ERR(udc->thread_task)) {
+ err = PTR_ERR(udc->thread_task);
+ goto del_gadget;
+ }
irq = of_irq_get_byname(spi->dev.of_node, "vbus");
if (irq <= 0) { /* no vbus irq implies self-powered design */
err = devm_request_irq(&spi->dev, irq,
max3420_vbus_handler, 0, "vbus", udc);
if (err < 0)
- return err;
+ goto del_gadget;
}
return 0;
+
+del_gadget:
+ usb_del_gadget_udc(&udc->gadget);
+ return err;
}
static int max3420_remove(struct spi_device *spi)
return 0;
free_eps:
+ pm_runtime_disable(&pdev->dev);
tegra_xudc_free_eps(xudc);
free_event_ring:
tegra_xudc_free_event_ring(xudc);
static irqreturn_t ehci_irq (struct usb_hcd *hcd)
{
struct ehci_hcd *ehci = hcd_to_ehci (hcd);
- u32 status, masked_status, pcd_status = 0, cmd;
+ u32 status, current_status, masked_status, pcd_status = 0;
+ u32 cmd;
int bh;
spin_lock(&ehci->lock);
- status = ehci_readl(ehci, &ehci->regs->status);
+ status = 0;
+ current_status = ehci_readl(ehci, &ehci->regs->status);
+restart:
/* e.g. cardbus physical eject */
- if (status == ~(u32) 0) {
+ if (current_status == ~(u32) 0) {
ehci_dbg (ehci, "device removed\n");
goto dead;
}
+ status |= current_status;
/*
* We don't use STS_FLR, but some controllers don't like it to
* remain on, so mask it out along with the other status bits.
*/
- masked_status = status & (INTR_MASK | STS_FLR);
+ masked_status = current_status & (INTR_MASK | STS_FLR);
/* Shared IRQ? */
if (!masked_status || unlikely(ehci->rh_state == EHCI_RH_HALTED)) {
/* clear (just) interrupts */
ehci_writel(ehci, masked_status, &ehci->regs->status);
+
+ /* For edge interrupts, don't race with an interrupt bit being raised */
+ current_status = ehci_readl(ehci, &ehci->regs->status);
+ if (current_status & INTR_MASK)
+ goto restart;
+
cmd = ehci_readl(ehci, &ehci->regs->command);
bh = 0;
*/
struct urb *curr_urb;
enum scheduling_pass sched_pass;
- struct usb_device *loaded_dev; /* dev that's loaded into the chip */
- int loaded_epnum; /* epnum whose toggles are loaded */
int urb_done; /* > 0 -> no errors, < 0: errno */
size_t curr_len;
u8 hien;
* Caller must NOT hold HCD spinlock.
*/
static void
-max3421_set_address(struct usb_hcd *hcd, struct usb_device *dev, int epnum,
- int force_toggles)
+max3421_set_address(struct usb_hcd *hcd, struct usb_device *dev, int epnum)
{
- struct max3421_hcd *max3421_hcd = hcd_to_max3421(hcd);
- int old_epnum, same_ep, rcvtog, sndtog;
- struct usb_device *old_dev;
+ int rcvtog, sndtog;
u8 hctl;
- old_dev = max3421_hcd->loaded_dev;
- old_epnum = max3421_hcd->loaded_epnum;
-
- same_ep = (dev == old_dev && epnum == old_epnum);
- if (same_ep && !force_toggles)
- return;
-
- if (old_dev && !same_ep) {
- /* save the old end-points toggles: */
- u8 hrsl = spi_rd8(hcd, MAX3421_REG_HRSL);
-
- rcvtog = (hrsl >> MAX3421_HRSL_RCVTOGRD_BIT) & 1;
- sndtog = (hrsl >> MAX3421_HRSL_SNDTOGRD_BIT) & 1;
-
- /* no locking: HCD (i.e., we) own toggles, don't we? */
- usb_settoggle(old_dev, old_epnum, 0, rcvtog);
- usb_settoggle(old_dev, old_epnum, 1, sndtog);
- }
/* setup new endpoint's toggle bits: */
rcvtog = usb_gettoggle(dev, epnum, 0);
sndtog = usb_gettoggle(dev, epnum, 1);
hctl = (BIT(rcvtog + MAX3421_HCTL_RCVTOG0_BIT) |
BIT(sndtog + MAX3421_HCTL_SNDTOG0_BIT));
- max3421_hcd->loaded_epnum = epnum;
spi_wr8(hcd, MAX3421_REG_HCTL, hctl);
/*
* address-assignment so it's best to just always load the
* address whenever the end-point changed/was forced.
*/
- max3421_hcd->loaded_dev = dev;
spi_wr8(hcd, MAX3421_REG_PERADDR, dev->devnum);
}
struct max3421_hcd *max3421_hcd = hcd_to_max3421(hcd);
struct urb *urb, *curr_urb = NULL;
struct max3421_ep *max3421_ep;
- int epnum, force_toggles = 0;
+ int epnum;
struct usb_host_endpoint *ep;
struct list_head *pos;
unsigned long flags;
usb_settoggle(urb->dev, epnum, 0, 1);
usb_settoggle(urb->dev, epnum, 1, 1);
max3421_ep->pkt_state = PKT_STATE_SETUP;
- force_toggles = 1;
} else
max3421_ep->pkt_state = PKT_STATE_TRANSFER;
}
spin_unlock_irqrestore(&max3421_hcd->lock, flags);
max3421_ep->last_active = max3421_hcd->frame_number;
- max3421_set_address(hcd, urb->dev, epnum, force_toggles);
+ max3421_set_address(hcd, urb->dev, epnum);
max3421_set_speed(hcd, urb->dev);
max3421_next_transfer(hcd, 0);
return 1;
status = 0;
urb = max3421_hcd->curr_urb;
if (urb) {
+ /* save the old end-points toggles: */
+ u8 hrsl = spi_rd8(hcd, MAX3421_REG_HRSL);
+ int rcvtog = (hrsl >> MAX3421_HRSL_RCVTOGRD_BIT) & 1;
+ int sndtog = (hrsl >> MAX3421_HRSL_SNDTOGRD_BIT) & 1;
+ int epnum = usb_endpoint_num(&urb->ep->desc);
+
+ /* no locking: HCD (i.e., we) own toggles, don't we? */
+ usb_settoggle(urb->dev, epnum, 0, rcvtog);
+ usb_settoggle(urb->dev, epnum, 1, sndtog);
+
max3421_hcd->curr_urb = NULL;
spin_lock_irqsave(&max3421_hcd->lock, flags);
usb_hcd_unlink_urb_from_ep(hcd, urb);
if (ohci_at91->wakeup)
enable_irq_wake(hcd->irq);
- ohci_at91_port_suspend(ohci_at91->sfr_regmap, 1);
-
ret = ohci_suspend(hcd, ohci_at91->wakeup);
if (ret) {
if (ohci_at91->wakeup)
/* flush the writes */
(void) ohci_readl (ohci, &ohci->regs->control);
msleep(1);
+ ohci_at91_port_suspend(ohci_at91->sfr_regmap, 1);
at91_stop_clock(ohci_at91);
+ } else {
+ ohci_at91_port_suspend(ohci_at91->sfr_regmap, 1);
}
return ret;
struct usb_hcd *hcd = dev_get_drvdata(dev);
struct ohci_at91_priv *ohci_at91 = hcd_to_ohci_at91_priv(hcd);
+ ohci_at91_port_suspend(ohci_at91->sfr_regmap, 0);
+
if (ohci_at91->wakeup)
disable_irq_wake(hcd->irq);
else
ohci_resume(hcd, false);
- ohci_at91_port_suspend(ohci_at91->sfr_regmap, 0);
-
return 0;
}
* Inform the usbcore about resume-in-progress by returning
* a non-zero value even if there are no status changes.
*/
+ spin_lock_irqsave(&xhci->lock, flags);
+
status = bus_state->resuming_ports;
mask = PORT_CSC | PORT_PEC | PORT_OCC | PORT_PLC | PORT_WRC | PORT_CEC;
- spin_lock_irqsave(&xhci->lock, flags);
/* For each port, did anything change? If so, set that bit in buf. */
for (i = 0; i < max_ports; i++) {
temp = readl(ports[i]->addr);
return 0;
case RENESAS_ROM_STATUS_NO_RESULT: /* No result yet */
- dev_dbg(&pdev->dev, "Unknown ROM status ...\n");
- break;
+ return 0;
case RENESAS_ROM_STATUS_ERROR: /* Error State */
default: /* All other states are marked as "Reserved states" */
u8 fw_state;
int err;
- /*
- * Only if device has ROM and loaded FW we can skip loading and
- * return success. Otherwise (even unknown state), attempt to load FW.
- */
- if (renesas_check_rom(pdev) && !renesas_check_rom_state(pdev))
- return 0;
+ /* Check if device has ROM and loaded, if so skip everything */
+ err = renesas_check_rom(pdev);
+ if (err) { /* we have rom */
+ err = renesas_check_rom_state(pdev);
+ if (!err)
+ return err;
+ }
/*
* Test if the device is actually needing the firmware. As most
{ /* end: all zeroes */ }
};
MODULE_DEVICE_TABLE(pci, pci_ids);
+
+/*
+ * Without CONFIG_USB_XHCI_PCI_RENESAS renesas_xhci_check_request_fw() won't
+ * load firmware, so don't encumber the xhci-pci driver with it.
+ */
+#if IS_ENABLED(CONFIG_USB_XHCI_PCI_RENESAS)
MODULE_FIRMWARE("renesas_usb_fw.mem");
+#endif
/* pci driver glue; this is a "new style" PCI driver module */
static struct pci_driver xhci_pci_driver = {
struct device *control_otghs;
unsigned int is_runtime_suspended:1;
unsigned int needs_resume:1;
+ unsigned int phy_suspended:1;
};
#define glue_to_musb(g) platform_get_drvdata(g->musb)
omap2430_low_level_exit(musb);
- phy_power_off(musb->phy);
- phy_exit(musb->phy);
+ if (!glue->phy_suspended) {
+ phy_power_off(musb->phy);
+ phy_exit(musb->phy);
+ }
glue->is_runtime_suspended = 1;
if (!musb)
return 0;
- phy_init(musb->phy);
- phy_power_on(musb->phy);
+ if (!glue->phy_suspended) {
+ phy_init(musb->phy);
+ phy_power_on(musb->phy);
+ }
omap2430_low_level_init(musb);
musb_writel(musb->mregs, OTG_INTERFSEL,
return 0;
}
+/* I2C and SPI PHYs need to be suspended before the glue layer */
static int omap2430_suspend(struct device *dev)
{
struct omap2430_glue *glue = dev_get_drvdata(dev);
+ struct musb *musb = glue_to_musb(glue);
+
+ phy_power_off(musb->phy);
+ phy_exit(musb->phy);
+ glue->phy_suspended = 1;
+
+ return 0;
+}
+
+/* Glue layer needs to be suspended after musb_suspend() */
+static int omap2430_suspend_late(struct device *dev)
+{
+ struct omap2430_glue *glue = dev_get_drvdata(dev);
if (glue->is_runtime_suspended)
return 0;
return omap2430_runtime_suspend(dev);
}
-static int omap2430_resume(struct device *dev)
+static int omap2430_resume_early(struct device *dev)
{
struct omap2430_glue *glue = dev_get_drvdata(dev);
return omap2430_runtime_resume(dev);
}
+static int omap2430_resume(struct device *dev)
+{
+ struct omap2430_glue *glue = dev_get_drvdata(dev);
+ struct musb *musb = glue_to_musb(glue);
+
+ phy_init(musb->phy);
+ phy_power_on(musb->phy);
+ glue->phy_suspended = 0;
+
+ return 0;
+}
+
static const struct dev_pm_ops omap2430_pm_ops = {
.runtime_suspend = omap2430_runtime_suspend,
.runtime_resume = omap2430_runtime_resume,
.suspend = omap2430_suspend,
+ .suspend_late = omap2430_suspend_late,
+ .resume_early = omap2430_resume_early,
.resume = omap2430_resume,
};
list_for_each_entry(usb_phy, &phy_list, head) {
if (usb_phy->dev == dev)
- break;
+ return usb_phy;
}
- return usb_phy;
+ return NULL;
}
static void usb_phy_set_default_current(struct usb_phy *usb_phy)
struct usb_phy *usb_phy;
char uchger_state[50] = { 0 };
char uchger_type[50] = { 0 };
+ unsigned long flags;
+ spin_lock_irqsave(&phy_lock, flags);
usb_phy = __device_to_usb_phy(dev);
+ spin_unlock_irqrestore(&phy_lock, flags);
+
+ if (!usb_phy)
+ return -ENODEV;
snprintf(uchger_state, ARRAY_SIZE(uchger_state),
"USB_CHARGER_STATE=%s", usb_chger_state[usb_phy->chg_state]);
#define usbhsf_dma_map(p) __usbhsf_dma_map_ctrl(p, 1)
#define usbhsf_dma_unmap(p) __usbhsf_dma_map_ctrl(p, 0)
static int __usbhsf_dma_map_ctrl(struct usbhs_pkt *pkt, int map);
+static void usbhsf_tx_irq_ctrl(struct usbhs_pipe *pipe, int enable);
+static void usbhsf_rx_irq_ctrl(struct usbhs_pipe *pipe, int enable);
struct usbhs_pkt *usbhs_pkt_pop(struct usbhs_pipe *pipe, struct usbhs_pkt *pkt)
{
struct usbhs_priv *priv = usbhs_pipe_to_priv(pipe);
if (chan) {
dmaengine_terminate_all(chan);
usbhsf_dma_unmap(pkt);
+ } else {
+ if (usbhs_pipe_is_dir_in(pipe))
+ usbhsf_rx_irq_ctrl(pipe, 0);
+ else
+ usbhsf_tx_irq_ctrl(pipe, 0);
}
usbhs_pipe_clear_without_sequence(pipe, 0, 0);
.owner = THIS_MODULE,
.name = "ch341-uart",
},
+ .bulk_in_size = 512,
.id_table = id_table,
.num_ports = 1,
.open = ch341_open,
{ USB_DEVICE(0x10C4, 0x89A4) }, /* CESINEL FTBC Flexible Thyristor Bridge Controller */
{ USB_DEVICE(0x10C4, 0x89FB) }, /* Qivicon ZigBee USB Radio Stick */
{ USB_DEVICE(0x10C4, 0x8A2A) }, /* HubZ dual ZigBee and Z-Wave dongle */
+ { USB_DEVICE(0x10C4, 0x8A5B) }, /* CEL EM3588 ZigBee USB Stick */
{ USB_DEVICE(0x10C4, 0x8A5E) }, /* CEL EM3588 ZigBee USB Stick Long Range */
{ USB_DEVICE(0x10C4, 0x8B34) }, /* Qivicon ZigBee USB Radio Stick */
{ USB_DEVICE(0x10C4, 0xEA60) }, /* Silicon Labs factory default */
{ 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(0x1901, 0x0197) }, /* GE CS1000 M.2 Key E serial interface */
+ { USB_DEVICE(0x1901, 0x0198) }, /* GE CS1000 Display 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 */
{ USB_DEVICE(FTDI_VID, FTDI_MTXORB_6_PID) },
{ USB_DEVICE(FTDI_VID, FTDI_R2000KU_TRUE_RNG) },
{ USB_DEVICE(FTDI_VID, FTDI_VARDAAN_PID) },
+ { USB_DEVICE(FTDI_VID, FTDI_AUTO_M3_OP_COM_V2_PID) },
{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_0100_PID) },
{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_0101_PID) },
{ USB_DEVICE(MTXORB_VID, MTXORB_FTDI_RANGE_0102_PID) },
/* Vardaan Enterprises Serial Interface VEUSB422R3 */
#define FTDI_VARDAAN_PID 0xF070
+/* Auto-M3 Ltd. - OP-COM USB V2 - OBD interface Adapter */
+#define FTDI_AUTO_M3_OP_COM_V2_PID 0x4f50
+
/*
* Xsens Technologies BV products (http://www.xsens.com).
*/
#define QUECTEL_PRODUCT_UC15 0x9090
/* These u-blox products use Qualcomm's vendor ID */
#define UBLOX_PRODUCT_R410M 0x90b2
+#define UBLOX_PRODUCT_R6XX 0x90fa
/* These Yuga products use Qualcomm's vendor ID */
#define YUGA_PRODUCT_CLM920_NC5 0x9625
/* u-blox products using Qualcomm vendor ID */
{ USB_DEVICE(QUALCOMM_VENDOR_ID, UBLOX_PRODUCT_R410M),
.driver_info = RSVD(1) | RSVD(3) },
+ { USB_DEVICE(QUALCOMM_VENDOR_ID, UBLOX_PRODUCT_R6XX),
+ .driver_info = RSVD(3) },
/* Quectel products using Quectel vendor ID */
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21, 0xff, 0xff, 0xff),
.driver_info = NUMEP2 },
.driver_info = NCTRL(2) | RSVD(3) },
{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1055, 0xff), /* Telit FN980 (PCIe) */
.driver_info = NCTRL(0) | RSVD(1) },
+ { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1056, 0xff), /* Telit FD980 */
+ .driver_info = NCTRL(2) | RSVD(3) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910),
.driver_info = NCTRL(0) | RSVD(1) | RSVD(3) },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM),
bcdDevice = le16_to_cpu(desc->bcdDevice);
bcdUSB = le16_to_cpu(desc->bcdUSB);
- switch (bcdDevice) {
- case 0x100:
- /*
- * Assume it's an HXN-type if the device doesn't support the old read
- * request value.
- */
- if (bcdUSB == 0x200 && !pl2303_supports_hx_status(serial))
- return TYPE_HXN;
+ switch (bcdUSB) {
+ case 0x110:
+ switch (bcdDevice) {
+ case 0x300:
+ return TYPE_HX;
+ case 0x400:
+ return TYPE_HXD;
+ default:
+ return TYPE_HX;
+ }
break;
- case 0x300:
- if (bcdUSB == 0x200)
+ case 0x200:
+ switch (bcdDevice) {
+ case 0x100:
+ case 0x305:
+ /*
+ * Assume it's an HXN-type if the device doesn't
+ * support the old read request value.
+ */
+ if (!pl2303_supports_hx_status(serial))
+ return TYPE_HXN;
+ break;
+ case 0x300:
return TYPE_TA;
-
- return TYPE_HX;
- case 0x400:
- return TYPE_HXD;
- case 0x500:
- return TYPE_TB;
+ case 0x500:
+ return TYPE_TB;
+ }
+ break;
}
dev_err(&serial->interface->dev,
USB_SC_DEVICE, USB_PR_DEVICE, NULL,
US_FL_NO_REPORT_OPCODES | US_FL_NO_SAME),
+/* Reported-by: Julian Sikorski <belegdol@gmail.com> */
+UNUSUAL_DEV(0x059f, 0x1061, 0x0000, 0x9999,
+ "LaCie",
+ "Rugged USB3-FW",
+ USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+ US_FL_IGNORE_UAS),
+
/*
* Apricorn USB3 dongle sometimes returns "USBSUSBSUSBS" in response to SCSI
* commands in UAS mode. Observed with the 1.28 firmware; are there others?
return -ENODEV;
/*
+ * This fwnode has a "compatible" property, but is never populated as a
+ * struct device. Instead we simply parse it to read the properties.
+ * This it breaks fw_devlink=on. To maintain backward compatibility
+ * with existing DT files, we work around this by deleting any
+ * fwnode_links to/from this fwnode.
+ */
+ fw_devlink_purge_absent_suppliers(fwnode);
+
+ /*
* When both VDD and VSYS power supplies are present, the low power
* supply VSYS is selected when VSYS voltage is above 3.1 V.
* Otherwise VDD is selected.
typec_set_pwr_opmode(chip->port, chip->pwr_opmode);
if (client->irq) {
- ret = stusb160x_irq_init(chip, client->irq);
- if (ret)
- goto port_unregister;
-
chip->role_sw = fwnode_usb_role_switch_get(fwnode);
if (IS_ERR(chip->role_sw)) {
ret = PTR_ERR(chip->role_sw);
ret);
goto port_unregister;
}
+
+ ret = stusb160x_irq_init(chip, client->irq);
+ if (ret)
+ goto role_sw_put;
} else {
/*
* If Source or Dual power role, need to enable VDD supply
return 0;
+role_sw_put:
+ if (chip->role_sw)
+ usb_role_switch_put(chip->role_sw);
port_unregister:
typec_unregister_port(chip->port);
all_reg_disable:
void tcpm_sink_frs(struct tcpm_port *port)
{
spin_lock(&port->pd_event_lock);
- port->pd_events = TCPM_FRS_EVENT;
+ port->pd_events |= TCPM_FRS_EVENT;
spin_unlock(&port->pd_event_lock);
kthread_queue_work(port->wq, &port->event_work);
}
void tcpm_sourcing_vbus(struct tcpm_port *port)
{
spin_lock(&port->pd_event_lock);
- port->pd_events = TCPM_SOURCING_VBUS;
+ port->pd_events |= TCPM_SOURCING_VBUS;
spin_unlock(&port->pd_event_lock);
kthread_queue_work(port->wq, &port->event_work);
}
if (!fwnode)
return -ENODEV;
+ /*
+ * This fwnode has a "compatible" property, but is never populated as a
+ * struct device. Instead we simply parse it to read the properties.
+ * This breaks fw_devlink=on. To maintain backward compatibility
+ * with existing DT files, we work around this by deleting any
+ * fwnode_links to/from this fwnode.
+ */
+ fw_devlink_purge_absent_suppliers(fwnode);
+
tps->role_sw = fwnode_usb_role_switch_get(fwnode);
if (IS_ERR(tps->role_sw)) {
ret = PTR_ERR(tps->role_sw);
fb_var_to_videomode(&mode2, &info->var);
/* make sure we don't delete the videomode of current var */
ret = fb_mode_is_equal(&mode1, &mode2);
-
- if (!ret)
- fbcon_mode_deleted(info, &mode1);
-
- if (!ret)
- fb_delete_videomode(&mode1, &info->modelist);
-
+ if (!ret) {
+ ret = fbcon_mode_deleted(info, &mode1);
+ if (!ret)
+ fb_delete_videomode(&mode1, &info->modelist);
+ }
return ret ? -EINVAL : 0;
}
case FB_BLANK_POWERDOWN:
/* turn off panel */
xilinx_fb_out32(drvdata, REG_CTRL, 0);
+ break;
+
default:
break;
}
test_and_set_bit(ACRN_VM_FLAG_DESTROYED, &vm->flags))
return 0;
+ ret = hcall_destroy_vm(vm->vmid);
+ if (ret < 0) {
+ dev_err(acrn_dev.this_device,
+ "Failed to destroy VM %u\n", vm->vmid);
+ clear_bit(ACRN_VM_FLAG_DESTROYED, &vm->flags);
+ return ret;
+ }
+
/* Remove from global VM list */
write_lock_bh(&acrn_vm_list_lock);
list_del_init(&vm->list);
vm->monitor_page = NULL;
}
- ret = hcall_destroy_vm(vm->vmid);
- if (ret < 0) {
- dev_err(acrn_dev.this_device,
- "Failed to destroy VM %u\n", vm->vmid);
- clear_bit(ACRN_VM_FLAG_DESTROYED, &vm->flags);
- return ret;
- }
-
acrn_vm_all_ram_unmap(vm);
dev_dbg(acrn_dev.this_device, "VM %u destroyed.\n", vm->vmid);
with v4 shared libraries freely available from Compaq. If you're
going to use shared libraries from Tru64 version 5.0 or later, say N.
-config BINFMT_EM86
- tristate "Kernel support for Linux/Intel ELF binaries"
- depends on ALPHA
- help
- Say Y here if you want to be able to execute Linux/Intel ELF
- binaries just like native Alpha binaries on your Alpha machine. For
- this to work, you need to have the emulator /usr/bin/em86 in place.
-
- You can get the same functionality by saying N here and saying Y to
- "Kernel support for MISC binaries".
-
- You may answer M to compile the emulation support as a module and
- later load the module when you want to use a Linux/Intel binary. The
- module will be called binfmt_em86. If unsure, say Y.
-
config BINFMT_MISC
tristate "Kernel support for MISC binaries"
help
obj-$(CONFIG_FS_VERITY) += verity/
obj-$(CONFIG_FILE_LOCKING) += locks.o
obj-$(CONFIG_BINFMT_AOUT) += binfmt_aout.o
-obj-$(CONFIG_BINFMT_EM86) += binfmt_em86.o
obj-$(CONFIG_BINFMT_MISC) += binfmt_misc.o
obj-$(CONFIG_BINFMT_SCRIPT) += binfmt_script.o
obj-$(CONFIG_BINFMT_ELF) += binfmt_elf.o
static int afs_deliver_yfs_cb_callback(struct afs_call *);
-#define CM_NAME(name) \
- char afs_SRXCB##name##_name[] __tracepoint_string = \
- "CB." #name
-
/*
* CB.CallBack operation type
*/
-static CM_NAME(CallBack);
static const struct afs_call_type afs_SRXCBCallBack = {
- .name = afs_SRXCBCallBack_name,
+ .name = "CB.CallBack",
.deliver = afs_deliver_cb_callback,
.destructor = afs_cm_destructor,
.work = SRXAFSCB_CallBack,
/*
* CB.InitCallBackState operation type
*/
-static CM_NAME(InitCallBackState);
static const struct afs_call_type afs_SRXCBInitCallBackState = {
- .name = afs_SRXCBInitCallBackState_name,
+ .name = "CB.InitCallBackState",
.deliver = afs_deliver_cb_init_call_back_state,
.destructor = afs_cm_destructor,
.work = SRXAFSCB_InitCallBackState,
/*
* CB.InitCallBackState3 operation type
*/
-static CM_NAME(InitCallBackState3);
static const struct afs_call_type afs_SRXCBInitCallBackState3 = {
- .name = afs_SRXCBInitCallBackState3_name,
+ .name = "CB.InitCallBackState3",
.deliver = afs_deliver_cb_init_call_back_state3,
.destructor = afs_cm_destructor,
.work = SRXAFSCB_InitCallBackState,
/*
* CB.Probe operation type
*/
-static CM_NAME(Probe);
static const struct afs_call_type afs_SRXCBProbe = {
- .name = afs_SRXCBProbe_name,
+ .name = "CB.Probe",
.deliver = afs_deliver_cb_probe,
.destructor = afs_cm_destructor,
.work = SRXAFSCB_Probe,
/*
* CB.ProbeUuid operation type
*/
-static CM_NAME(ProbeUuid);
static const struct afs_call_type afs_SRXCBProbeUuid = {
- .name = afs_SRXCBProbeUuid_name,
+ .name = "CB.ProbeUuid",
.deliver = afs_deliver_cb_probe_uuid,
.destructor = afs_cm_destructor,
.work = SRXAFSCB_ProbeUuid,
/*
* CB.TellMeAboutYourself operation type
*/
-static CM_NAME(TellMeAboutYourself);
static const struct afs_call_type afs_SRXCBTellMeAboutYourself = {
- .name = afs_SRXCBTellMeAboutYourself_name,
+ .name = "CB.TellMeAboutYourself",
.deliver = afs_deliver_cb_tell_me_about_yourself,
.destructor = afs_cm_destructor,
.work = SRXAFSCB_TellMeAboutYourself,
/*
* YFS CB.CallBack operation type
*/
-static CM_NAME(YFS_CallBack);
static const struct afs_call_type afs_SRXYFSCB_CallBack = {
- .name = afs_SRXCBYFS_CallBack_name,
+ .name = "YFSCB.CallBack",
.deliver = afs_deliver_yfs_cb_callback,
.destructor = afs_cm_destructor,
.work = SRXAFSCB_CallBack,
return ret;
}
- ret = -ENOENT;
if (!cookie.found) {
_leave(" = -ENOENT [not found]");
return -ENOENT;
if (d_count(new_dentry) > 2) {
/* copy the target dentry's name */
- ret = -ENOMEM;
op->rename.tmp = d_alloc(new_dentry->d_parent,
&new_dentry->d_name);
- if (!op->rename.tmp)
+ if (!op->rename.tmp) {
+ op->error = -ENOMEM;
goto error;
+ }
ret = afs_sillyrename(new_dvnode,
AFS_FS_I(d_inode(new_dentry)),
new_dentry, op->key);
- if (ret)
+ if (ret) {
+ op->error = ret;
goto error;
+ }
op->dentry_2 = op->rename.tmp;
op->rename.rehash = NULL;
if (wbc->range_cyclic) {
start = mapping->writeback_index * PAGE_SIZE;
ret = afs_writepages_region(mapping, wbc, start, LLONG_MAX, &next);
- if (start > 0 && wbc->nr_to_write > 0 && ret == 0)
- ret = afs_writepages_region(mapping, wbc, 0, start,
- &next);
- mapping->writeback_index = next / PAGE_SIZE;
+ if (ret == 0) {
+ mapping->writeback_index = next / PAGE_SIZE;
+ if (start > 0 && wbc->nr_to_write > 0) {
+ ret = afs_writepages_region(mapping, wbc, 0,
+ start, &next);
+ if (ret == 0)
+ mapping->writeback_index =
+ next / PAGE_SIZE;
+ }
+ }
} else if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) {
ret = afs_writepages_region(mapping, wbc, 0, LLONG_MAX, &next);
- if (wbc->nr_to_write > 0)
- mapping->writeback_index = next;
+ if (wbc->nr_to_write > 0 && ret == 0)
+ mapping->writeback_index = next / PAGE_SIZE;
} else {
ret = afs_writepages_region(mapping, wbc,
wbc->range_start, wbc->range_end, &next);
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/fs/binfmt_em86.c
- *
- * Based on linux/fs/binfmt_script.c
- * Copyright (C) 1996 Martin von Löwis
- * original #!-checking implemented by tytso.
- *
- * em86 changes Copyright (C) 1997 Jim Paradis
- */
-
-#include <linux/module.h>
-#include <linux/string.h>
-#include <linux/stat.h>
-#include <linux/binfmts.h>
-#include <linux/elf.h>
-#include <linux/init.h>
-#include <linux/fs.h>
-#include <linux/file.h>
-#include <linux/errno.h>
-
-
-#define EM86_INTERP "/usr/bin/em86"
-#define EM86_I_NAME "em86"
-
-static int load_em86(struct linux_binprm *bprm)
-{
- const char *i_name, *i_arg;
- char *interp;
- struct file * file;
- int retval;
- struct elfhdr elf_ex;
-
- /* Make sure this is a Linux/Intel ELF executable... */
- elf_ex = *((struct elfhdr *)bprm->buf);
-
- if (memcmp(elf_ex.e_ident, ELFMAG, SELFMAG) != 0)
- return -ENOEXEC;
-
- /* First of all, some simple consistency checks */
- if ((elf_ex.e_type != ET_EXEC && elf_ex.e_type != ET_DYN) ||
- (!((elf_ex.e_machine == EM_386) || (elf_ex.e_machine == EM_486))) ||
- !bprm->file->f_op->mmap) {
- return -ENOEXEC;
- }
-
- /* Need to be able to load the file after exec */
- if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
- return -ENOENT;
-
- /* Unlike in the script case, we don't have to do any hairy
- * parsing to find our interpreter... it's hardcoded!
- */
- interp = EM86_INTERP;
- i_name = EM86_I_NAME;
- i_arg = NULL; /* We reserve the right to add an arg later */
-
- /*
- * Splice in (1) the interpreter's name for argv[0]
- * (2) (optional) argument to interpreter
- * (3) filename of emulated file (replace argv[0])
- *
- * This is done in reverse order, because of how the
- * user environment and arguments are stored.
- */
- remove_arg_zero(bprm);
- retval = copy_string_kernel(bprm->filename, bprm);
- if (retval < 0) return retval;
- bprm->argc++;
- if (i_arg) {
- retval = copy_string_kernel(i_arg, bprm);
- if (retval < 0) return retval;
- bprm->argc++;
- }
- retval = copy_string_kernel(i_name, bprm);
- if (retval < 0) return retval;
- bprm->argc++;
-
- /*
- * OK, now restart the process with the interpreter's inode.
- * Note that we use open_exec() as the name is now in kernel
- * space, and we don't need to copy it.
- */
- file = open_exec(interp);
- if (IS_ERR(file))
- return PTR_ERR(file);
-
- bprm->interpreter = file;
- return 0;
-}
-
-static struct linux_binfmt em86_format = {
- .module = THIS_MODULE,
- .load_binary = load_em86,
-};
-
-static int __init init_em86_binfmt(void)
-{
- register_binfmt(&em86_format);
- return 0;
-}
-
-static void __exit exit_em86_binfmt(void)
-{
- unregister_binfmt(&em86_format);
-}
-
-core_initcall(init_em86_binfmt);
-module_exit(exit_em86_binfmt);
-MODULE_LICENSE("GPL");
free_percpu(bdev->bd_stats);
kfree(bdev->bd_meta_info);
+ if (!bdev_is_partition(bdev))
+ kfree(bdev->bd_disk);
kmem_cache_free(bdev_cachep, BDEV_I(inode));
}
int btrfs_find_all_roots(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info, u64 bytenr,
u64 time_seq, struct ulist **roots,
- bool ignore_offset)
+ bool ignore_offset, bool skip_commit_root_sem)
{
int ret;
- if (!trans)
+ if (!trans && !skip_commit_root_sem)
down_read(&fs_info->commit_root_sem);
ret = btrfs_find_all_roots_safe(trans, fs_info, bytenr,
time_seq, roots, ignore_offset);
- if (!trans)
+ if (!trans && !skip_commit_root_sem)
up_read(&fs_info->commit_root_sem);
return ret;
}
const u64 *extent_item_pos, bool ignore_offset);
int btrfs_find_all_roots(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info, u64 bytenr,
- u64 time_seq, struct ulist **roots, bool ignore_offset);
+ u64 time_seq, struct ulist **roots, bool ignore_offset,
+ bool skip_commit_root_sem);
char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
u32 name_len, unsigned long name_off,
struct extent_buffer *eb_in, u64 parent,
if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_BALANCE))
return;
- mutex_lock(&fs_info->reclaim_bgs_lock);
+ /*
+ * Long running balances can keep us blocked here for eternity, so
+ * simply skip reclaim if we're unable to get the mutex.
+ */
+ if (!mutex_trylock(&fs_info->reclaim_bgs_lock)) {
+ btrfs_exclop_finish(fs_info);
+ return;
+ }
+
spin_lock(&fs_info->unused_bgs_lock);
while (!list_empty(&fs_info->reclaim_bgs)) {
+ u64 zone_unusable;
int ret = 0;
bg = list_first_entry(&fs_info->reclaim_bgs,
goto next;
}
+ /*
+ * Cache the zone_unusable value before turning the block group
+ * to read only. As soon as the blog group is read only it's
+ * zone_unusable value gets moved to the block group's read-only
+ * bytes and isn't available for calculations anymore.
+ */
+ zone_unusable = bg->zone_unusable;
ret = inc_block_group_ro(bg, 0);
up_write(&space_info->groups_sem);
if (ret < 0)
goto next;
- btrfs_info(fs_info, "reclaiming chunk %llu with %llu%% used",
- bg->start, div_u64(bg->used * 100, bg->length));
+ btrfs_info(fs_info,
+ "reclaiming chunk %llu with %llu%% used %llu%% unusable",
+ bg->start, div_u64(bg->used * 100, bg->length),
+ div64_u64(zone_unusable * 100, bg->length));
trace_btrfs_reclaim_block_group(bg);
ret = btrfs_relocate_chunk(fs_info, bg->start);
if (ret)
return ret;
}
+/*
+ * This function, insert_block_group_item(), belongs to the phase 2 of chunk
+ * allocation.
+ *
+ * See the comment at btrfs_chunk_alloc() for details about the chunk allocation
+ * phases.
+ */
static int insert_block_group_item(struct btrfs_trans_handle *trans,
struct btrfs_block_group *block_group)
{
return btrfs_insert_item(trans, root, &key, &bgi, sizeof(bgi));
}
+/*
+ * This function, btrfs_create_pending_block_groups(), belongs to the phase 2 of
+ * chunk allocation.
+ *
+ * See the comment at btrfs_chunk_alloc() for details about the chunk allocation
+ * phases.
+ */
void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_block_group *block_group;
int ret = 0;
- if (!trans->can_flush_pending_bgs)
- return;
-
while (!list_empty(&trans->new_bgs)) {
int index;
ret = insert_block_group_item(trans, block_group);
if (ret)
btrfs_abort_transaction(trans, ret);
+ if (!block_group->chunk_item_inserted) {
+ mutex_lock(&fs_info->chunk_mutex);
+ ret = btrfs_chunk_alloc_add_chunk_item(trans, block_group);
+ mutex_unlock(&fs_info->chunk_mutex);
+ if (ret)
+ btrfs_abort_transaction(trans, ret);
+ }
ret = btrfs_finish_chunk_alloc(trans, block_group->start,
block_group->length);
if (ret)
btrfs_trans_release_chunk_metadata(trans);
}
-int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
- u64 type, u64 chunk_offset, u64 size)
+struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *trans,
+ u64 bytes_used, u64 type,
+ u64 chunk_offset, u64 size)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_block_group *cache;
cache = btrfs_create_block_group_cache(fs_info, chunk_offset);
if (!cache)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
cache->length = size;
set_free_space_tree_thresholds(cache);
ret = btrfs_load_block_group_zone_info(cache, true);
if (ret) {
btrfs_put_block_group(cache);
- return ret;
+ return ERR_PTR(ret);
}
ret = exclude_super_stripes(cache);
/* We may have excluded something, so call this just in case */
btrfs_free_excluded_extents(cache);
btrfs_put_block_group(cache);
- return ret;
+ return ERR_PTR(ret);
}
add_new_free_space(cache, chunk_offset, chunk_offset + size);
if (ret) {
btrfs_remove_free_space_cache(cache);
btrfs_put_block_group(cache);
- return ret;
+ return ERR_PTR(ret);
}
/*
btrfs_update_delayed_refs_rsv(trans);
set_avail_alloc_bits(fs_info, type);
- return 0;
+ return cache;
}
/*
return btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE);
}
+static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags)
+{
+ struct btrfs_block_group *bg;
+ int ret;
+
+ /*
+ * Check if we have enough space in the system space info because we
+ * will need to update device items in the chunk btree and insert a new
+ * chunk item in the chunk btree as well. This will allocate a new
+ * system block group if needed.
+ */
+ check_system_chunk(trans, flags);
+
+ bg = btrfs_alloc_chunk(trans, flags);
+ if (IS_ERR(bg)) {
+ ret = PTR_ERR(bg);
+ goto out;
+ }
+
+ /*
+ * If this is a system chunk allocation then stop right here and do not
+ * add the chunk item to the chunk btree. This is to prevent a deadlock
+ * because this system chunk allocation can be triggered while COWing
+ * some extent buffer of the chunk btree and while holding a lock on a
+ * parent extent buffer, in which case attempting to insert the chunk
+ * item (or update the device item) would result in a deadlock on that
+ * parent extent buffer. In this case defer the chunk btree updates to
+ * the second phase of chunk allocation and keep our reservation until
+ * the second phase completes.
+ *
+ * This is a rare case and can only be triggered by the very few cases
+ * we have where we need to touch the chunk btree outside chunk allocation
+ * and chunk removal. These cases are basically adding a device, removing
+ * a device or resizing a device.
+ */
+ if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
+ return 0;
+
+ ret = btrfs_chunk_alloc_add_chunk_item(trans, bg);
+ /*
+ * Normally we are not expected to fail with -ENOSPC here, since we have
+ * previously reserved space in the system space_info and allocated one
+ * new system chunk if necessary. However there are two exceptions:
+ *
+ * 1) We may have enough free space in the system space_info but all the
+ * existing system block groups have a profile which can not be used
+ * for extent allocation.
+ *
+ * This happens when mounting in degraded mode. For example we have a
+ * RAID1 filesystem with 2 devices, lose one device and mount the fs
+ * using the other device in degraded mode. If we then allocate a chunk,
+ * we may have enough free space in the existing system space_info, but
+ * none of the block groups can be used for extent allocation since they
+ * have a RAID1 profile, and because we are in degraded mode with a
+ * single device, we are forced to allocate a new system chunk with a
+ * SINGLE profile. Making check_system_chunk() iterate over all system
+ * block groups and check if they have a usable profile and enough space
+ * can be slow on very large filesystems, so we tolerate the -ENOSPC and
+ * try again after forcing allocation of a new system chunk. Like this
+ * we avoid paying the cost of that search in normal circumstances, when
+ * we were not mounted in degraded mode;
+ *
+ * 2) We had enough free space info the system space_info, and one suitable
+ * block group to allocate from when we called check_system_chunk()
+ * above. However right after we called it, the only system block group
+ * with enough free space got turned into RO mode by a running scrub,
+ * and in this case we have to allocate a new one and retry. We only
+ * need do this allocate and retry once, since we have a transaction
+ * handle and scrub uses the commit root to search for block groups.
+ */
+ if (ret == -ENOSPC) {
+ const u64 sys_flags = btrfs_system_alloc_profile(trans->fs_info);
+ struct btrfs_block_group *sys_bg;
+
+ sys_bg = btrfs_alloc_chunk(trans, sys_flags);
+ if (IS_ERR(sys_bg)) {
+ ret = PTR_ERR(sys_bg);
+ btrfs_abort_transaction(trans, ret);
+ goto out;
+ }
+
+ ret = btrfs_chunk_alloc_add_chunk_item(trans, sys_bg);
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ goto out;
+ }
+
+ ret = btrfs_chunk_alloc_add_chunk_item(trans, bg);
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ goto out;
+ }
+ } else if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ goto out;
+ }
+out:
+ btrfs_trans_release_chunk_metadata(trans);
+
+ return ret;
+}
+
/*
- * If force is CHUNK_ALLOC_FORCE:
+ * Chunk allocation is done in 2 phases:
+ *
+ * 1) Phase 1 - through btrfs_chunk_alloc() we allocate device extents for
+ * the chunk, the chunk mapping, create its block group and add the items
+ * that belong in the chunk btree to it - more specifically, we need to
+ * update device items in the chunk btree and add a new chunk item to it.
+ *
+ * 2) Phase 2 - through btrfs_create_pending_block_groups(), we add the block
+ * group item to the extent btree and the device extent items to the devices
+ * btree.
+ *
+ * This is done to prevent deadlocks. For example when COWing a node from the
+ * extent btree we are holding a write lock on the node's parent and if we
+ * trigger chunk allocation and attempted to insert the new block group item
+ * in the extent btree right way, we could deadlock because the path for the
+ * insertion can include that parent node. At first glance it seems impossible
+ * to trigger chunk allocation after starting a transaction since tasks should
+ * reserve enough transaction units (metadata space), however while that is true
+ * most of the time, chunk allocation may still be triggered for several reasons:
+ *
+ * 1) When reserving metadata, we check if there is enough free space in the
+ * metadata space_info and therefore don't trigger allocation of a new chunk.
+ * However later when the task actually tries to COW an extent buffer from
+ * the extent btree or from the device btree for example, it is forced to
+ * allocate a new block group (chunk) because the only one that had enough
+ * free space was just turned to RO mode by a running scrub for example (or
+ * device replace, block group reclaim thread, etc), so we can not use it
+ * for allocating an extent and end up being forced to allocate a new one;
+ *
+ * 2) Because we only check that the metadata space_info has enough free bytes,
+ * we end up not allocating a new metadata chunk in that case. However if
+ * the filesystem was mounted in degraded mode, none of the existing block
+ * groups might be suitable for extent allocation due to their incompatible
+ * profile (for e.g. mounting a 2 devices filesystem, where all block groups
+ * use a RAID1 profile, in degraded mode using a single device). In this case
+ * when the task attempts to COW some extent buffer of the extent btree for
+ * example, it will trigger allocation of a new metadata block group with a
+ * suitable profile (SINGLE profile in the example of the degraded mount of
+ * the RAID1 filesystem);
+ *
+ * 3) The task has reserved enough transaction units / metadata space, but when
+ * it attempts to COW an extent buffer from the extent or device btree for
+ * example, it does not find any free extent in any metadata block group,
+ * therefore forced to try to allocate a new metadata block group.
+ * This is because some other task allocated all available extents in the
+ * meanwhile - this typically happens with tasks that don't reserve space
+ * properly, either intentionally or as a bug. One example where this is
+ * done intentionally is fsync, as it does not reserve any transaction units
+ * and ends up allocating a variable number of metadata extents for log
+ * tree extent buffers.
+ *
+ * We also need this 2 phases setup when adding a device to a filesystem with
+ * a seed device - we must create new metadata and system chunks without adding
+ * any of the block group items to the chunk, extent and device btrees. If we
+ * did not do it this way, we would get ENOSPC when attempting to update those
+ * btrees, since all the chunks from the seed device are read-only.
+ *
+ * Phase 1 does the updates and insertions to the chunk btree because if we had
+ * it done in phase 2 and have a thundering herd of tasks allocating chunks in
+ * parallel, we risk having too many system chunks allocated by many tasks if
+ * many tasks reach phase 1 without the previous ones completing phase 2. In the
+ * extreme case this leads to exhaustion of the system chunk array in the
+ * superblock. This is easier to trigger if using a btree node/leaf size of 64K
+ * and with RAID filesystems (so we have more device items in the chunk btree).
+ * This has happened before and commit eafa4fd0ad0607 ("btrfs: fix exhaustion of
+ * the system chunk array due to concurrent allocations") provides more details.
+ *
+ * For allocation of system chunks, we defer the updates and insertions into the
+ * chunk btree to phase 2. This is to prevent deadlocks on extent buffers because
+ * if the chunk allocation is triggered while COWing an extent buffer of the
+ * chunk btree, we are holding a lock on the parent of that extent buffer and
+ * doing the chunk btree updates and insertions can require locking that parent.
+ * This is for the very few and rare cases where we update the chunk btree that
+ * are not chunk allocation or chunk removal: adding a device, removing a device
+ * or resizing a device.
+ *
+ * The reservation of system space, done through check_system_chunk(), as well
+ * as all the updates and insertions into the chunk btree must be done while
+ * holding fs_info->chunk_mutex. This is important to guarantee that while COWing
+ * an extent buffer from the chunks btree we never trigger allocation of a new
+ * system chunk, which would result in a deadlock (trying to lock twice an
+ * extent buffer of the chunk btree, first time before triggering the chunk
+ * allocation and the second time during chunk allocation while attempting to
+ * update the chunks btree). The system chunk array is also updated while holding
+ * that mutex. The same logic applies to removing chunks - we must reserve system
+ * space, update the chunk btree and the system chunk array in the superblock
+ * while holding fs_info->chunk_mutex.
+ *
+ * This function, btrfs_chunk_alloc(), belongs to phase 1.
+ *
+ * If @force is CHUNK_ALLOC_FORCE:
* - return 1 if it successfully allocates a chunk,
* - return errors including -ENOSPC otherwise.
- * If force is NOT CHUNK_ALLOC_FORCE:
+ * If @force is NOT CHUNK_ALLOC_FORCE:
* - return 0 if it doesn't need to allocate a new chunk,
* - return 1 if it successfully allocates a chunk,
* - return errors including -ENOSPC otherwise.
/* Don't re-enter if we're already allocating a chunk */
if (trans->allocating_chunk)
return -ENOSPC;
+ /*
+ * If we are removing a chunk, don't re-enter or we would deadlock.
+ * System space reservation and system chunk allocation is done by the
+ * chunk remove operation (btrfs_remove_chunk()).
+ */
+ if (trans->removing_chunk)
+ return -ENOSPC;
space_info = btrfs_find_space_info(fs_info, flags);
ASSERT(space_info);
force_metadata_allocation(fs_info);
}
- /*
- * Check if we have enough space in SYSTEM chunk because we may need
- * to update devices.
- */
- check_system_chunk(trans, flags);
-
- ret = btrfs_alloc_chunk(trans, flags);
+ ret = do_chunk_alloc(trans, flags);
trans->allocating_chunk = false;
spin_lock(&space_info->lock);
space_info->chunk_alloc = 0;
spin_unlock(&space_info->lock);
mutex_unlock(&fs_info->chunk_mutex);
- /*
- * When we allocate a new chunk we reserve space in the chunk block
- * reserve to make sure we can COW nodes/leafs in the chunk tree or
- * add new nodes/leafs to it if we end up needing to do it when
- * inserting the chunk item and updating device items as part of the
- * second phase of chunk allocation, performed by
- * btrfs_finish_chunk_alloc(). So make sure we don't accumulate a
- * large number of new block groups to create in our transaction
- * handle's new_bgs list to avoid exhausting the chunk block reserve
- * in extreme cases - like having a single transaction create many new
- * block groups when starting to write out the free space caches of all
- * the block groups that were made dirty during the lifetime of the
- * transaction.
- */
- if (trans->chunk_bytes_reserved >= (u64)SZ_2M)
- btrfs_create_pending_block_groups(trans);
return ret;
}
*/
void check_system_chunk(struct btrfs_trans_handle *trans, u64 type)
{
- struct btrfs_transaction *cur_trans = trans->transaction;
struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_space_info *info;
u64 left;
lockdep_assert_held(&fs_info->chunk_mutex);
info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_SYSTEM);
-again:
spin_lock(&info->lock);
left = info->total_bytes - btrfs_space_info_used(info, true);
spin_unlock(&info->lock);
if (left < thresh) {
u64 flags = btrfs_system_alloc_profile(fs_info);
- u64 reserved = atomic64_read(&cur_trans->chunk_bytes_reserved);
-
- /*
- * If there's not available space for the chunk tree (system
- * space) and there are other tasks that reserved space for
- * creating a new system block group, wait for them to complete
- * the creation of their system block group and release excess
- * reserved space. We do this because:
- *
- * *) We can end up allocating more system chunks than necessary
- * when there are multiple tasks that are concurrently
- * allocating block groups, which can lead to exhaustion of
- * the system array in the superblock;
- *
- * *) If we allocate extra and unnecessary system block groups,
- * despite being empty for a long time, and possibly forever,
- * they end not being added to the list of unused block groups
- * because that typically happens only when deallocating the
- * last extent from a block group - which never happens since
- * we never allocate from them in the first place. The few
- * exceptions are when mounting a filesystem or running scrub,
- * which add unused block groups to the list of unused block
- * groups, to be deleted by the cleaner kthread.
- * And even when they are added to the list of unused block
- * groups, it can take a long time until they get deleted,
- * since the cleaner kthread might be sleeping or busy with
- * other work (deleting subvolumes, running delayed iputs,
- * defrag scheduling, etc);
- *
- * This is rare in practice, but can happen when too many tasks
- * are allocating blocks groups in parallel (via fallocate())
- * and before the one that reserved space for a new system block
- * group finishes the block group creation and releases the space
- * reserved in excess (at btrfs_create_pending_block_groups()),
- * other tasks end up here and see free system space temporarily
- * not enough for updating the chunk tree.
- *
- * We unlock the chunk mutex before waiting for such tasks and
- * lock it again after the wait, otherwise we would deadlock.
- * It is safe to do so because allocating a system chunk is the
- * first thing done while allocating a new block group.
- */
- if (reserved > trans->chunk_bytes_reserved) {
- const u64 min_needed = reserved - thresh;
-
- mutex_unlock(&fs_info->chunk_mutex);
- wait_event(cur_trans->chunk_reserve_wait,
- atomic64_read(&cur_trans->chunk_bytes_reserved) <=
- min_needed);
- mutex_lock(&fs_info->chunk_mutex);
- goto again;
- }
+ struct btrfs_block_group *bg;
/*
* Ignore failure to create system chunk. We might end up not
* needing it, as we might not need to COW all nodes/leafs from
* the paths we visit in the chunk tree (they were already COWed
* or created in the current transaction for example).
+ *
+ * Also, if our caller is allocating a system chunk, do not
+ * attempt to insert the chunk item in the chunk btree, as we
+ * could deadlock on an extent buffer since our caller may be
+ * COWing an extent buffer from the chunk btree.
*/
- ret = btrfs_alloc_chunk(trans, flags);
+ bg = btrfs_alloc_chunk(trans, flags);
+ if (IS_ERR(bg)) {
+ ret = PTR_ERR(bg);
+ } else if (!(type & BTRFS_BLOCK_GROUP_SYSTEM)) {
+ /*
+ * If we fail to add the chunk item here, we end up
+ * trying again at phase 2 of chunk allocation, at
+ * btrfs_create_pending_block_groups(). So ignore
+ * any error here.
+ */
+ btrfs_chunk_alloc_add_chunk_item(trans, bg);
+ }
}
if (!ret) {
ret = btrfs_block_rsv_add(fs_info->chunk_root,
&fs_info->chunk_block_rsv,
thresh, BTRFS_RESERVE_NO_FLUSH);
- if (!ret) {
- atomic64_add(thresh, &cur_trans->chunk_bytes_reserved);
+ if (!ret)
trans->chunk_bytes_reserved += thresh;
- }
}
}
unsigned int removed:1;
unsigned int to_copy:1;
unsigned int relocating_repair:1;
+ unsigned int chunk_item_inserted:1;
int disk_cache_state;
void btrfs_reclaim_bgs(struct btrfs_fs_info *fs_info);
void btrfs_mark_bg_to_reclaim(struct btrfs_block_group *bg);
int btrfs_read_block_groups(struct btrfs_fs_info *info);
-int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
- u64 type, u64 chunk_offset, u64 size);
+struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *trans,
+ u64 bytes_used, u64 type,
+ u64 chunk_offset, u64 size);
void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans);
int btrfs_inc_block_group_ro(struct btrfs_block_group *cache,
bool do_chunk_alloc);
btrfs_record_physical_zoned(inode, cb->start, bio);
btrfs_writepage_endio_finish_ordered(BTRFS_I(inode), NULL,
cb->start, cb->start + cb->len - 1,
- bio->bi_status == BLK_STS_OK);
+ !cb->errors);
end_compressed_writeback(inode, cb);
/* note, our inode could be gone now */
return 0;
}
-static struct extent_buffer *alloc_tree_block_no_bg_flush(
- struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
- u64 parent_start,
- const struct btrfs_disk_key *disk_key,
- int level,
- u64 hint,
- u64 empty_size,
- enum btrfs_lock_nesting nest)
-{
- struct btrfs_fs_info *fs_info = root->fs_info;
- struct extent_buffer *ret;
-
- /*
- * If we are COWing a node/leaf from the extent, chunk, device or free
- * space trees, make sure that we do not finish block group creation of
- * pending block groups. We do this to avoid a deadlock.
- * COWing can result in allocation of a new chunk, and flushing pending
- * block groups (btrfs_create_pending_block_groups()) can be triggered
- * when finishing allocation of a new chunk. Creation of a pending block
- * group modifies the extent, chunk, device and free space trees,
- * therefore we could deadlock with ourselves since we are holding a
- * lock on an extent buffer that btrfs_create_pending_block_groups() may
- * try to COW later.
- * For similar reasons, we also need to delay flushing pending block
- * groups when splitting a leaf or node, from one of those trees, since
- * we are holding a write lock on it and its parent or when inserting a
- * new root node for one of those trees.
- */
- if (root == fs_info->extent_root ||
- root == fs_info->chunk_root ||
- root == fs_info->dev_root ||
- root == fs_info->free_space_root)
- trans->can_flush_pending_bgs = false;
-
- ret = btrfs_alloc_tree_block(trans, root, parent_start,
- root->root_key.objectid, disk_key, level,
- hint, empty_size, nest);
- trans->can_flush_pending_bgs = true;
-
- return ret;
-}
-
/*
* does the dirty work in cow of a single block. The parent block (if
* supplied) is updated to point to the new cow copy. The new buffer is marked
if ((root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) && parent)
parent_start = parent->start;
- cow = alloc_tree_block_no_bg_flush(trans, root, parent_start, &disk_key,
- level, search_start, empty_size, nest);
+ cow = btrfs_alloc_tree_block(trans, root, parent_start,
+ root->root_key.objectid, &disk_key, level,
+ search_start, empty_size, nest);
if (IS_ERR(cow))
return PTR_ERR(cow);
else
btrfs_node_key(lower, &lower_key, 0);
- c = alloc_tree_block_no_bg_flush(trans, root, 0, &lower_key, level,
- root->node->start, 0,
- BTRFS_NESTING_NEW_ROOT);
+ c = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
+ &lower_key, level, root->node->start, 0,
+ BTRFS_NESTING_NEW_ROOT);
if (IS_ERR(c))
return PTR_ERR(c);
mid = (c_nritems + 1) / 2;
btrfs_node_key(c, &disk_key, mid);
- split = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, level,
- c->start, 0, BTRFS_NESTING_SPLIT);
+ split = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
+ &disk_key, level, c->start, 0,
+ BTRFS_NESTING_SPLIT);
if (IS_ERR(split))
return PTR_ERR(split);
* BTRFS_NESTING_SPLIT_THE_SPLITTENING if we need to, but for now just
* use BTRFS_NESTING_NEW_ROOT.
*/
- right = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, 0,
- l->start, 0, num_doubles ?
- BTRFS_NESTING_NEW_ROOT :
- BTRFS_NESTING_SPLIT);
+ right = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
+ &disk_key, 0, l->start, 0,
+ num_doubles ? BTRFS_NESTING_NEW_ROOT :
+ BTRFS_NESTING_SPLIT);
if (IS_ERR(right))
return PTR_ERR(right);
kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
if (qrecord_inserted)
- btrfs_qgroup_trace_extent_post(fs_info, record);
+ btrfs_qgroup_trace_extent_post(trans, record);
return 0;
}
if (qrecord_inserted)
- return btrfs_qgroup_trace_extent_post(fs_info, record);
+ return btrfs_qgroup_trace_extent_post(trans, record);
return 0;
}
static void csum_tree_block(struct extent_buffer *buf, u8 *result)
{
struct btrfs_fs_info *fs_info = buf->fs_info;
- const int num_pages = fs_info->nodesize >> PAGE_SHIFT;
+ const int num_pages = num_extent_pages(buf);
const int first_page_part = min_t(u32, PAGE_SIZE, fs_info->nodesize);
SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
char *kaddr;
mutex_lock(&fs_info->fs_devices->device_list_mutex);
devices = &fs_info->fs_devices->devices;
list_for_each_entry(device, devices, dev_list) {
+ if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state))
+ continue;
+
ret = btrfs_trim_free_extents(device, &group_trimmed);
if (ret) {
dev_failed++;
return btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0);
}
+/*
+ * Split an extent_map at [start, start + len]
+ *
+ * This function is intended to be used only for extract_ordered_extent().
+ */
+static int split_zoned_em(struct btrfs_inode *inode, u64 start, u64 len,
+ u64 pre, u64 post)
+{
+ struct extent_map_tree *em_tree = &inode->extent_tree;
+ struct extent_map *em;
+ struct extent_map *split_pre = NULL;
+ struct extent_map *split_mid = NULL;
+ struct extent_map *split_post = NULL;
+ int ret = 0;
+ int modified;
+ unsigned long flags;
+
+ /* Sanity check */
+ if (pre == 0 && post == 0)
+ return 0;
+
+ split_pre = alloc_extent_map();
+ if (pre)
+ split_mid = alloc_extent_map();
+ if (post)
+ split_post = alloc_extent_map();
+ if (!split_pre || (pre && !split_mid) || (post && !split_post)) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ ASSERT(pre + post < len);
+
+ lock_extent(&inode->io_tree, start, start + len - 1);
+ write_lock(&em_tree->lock);
+ em = lookup_extent_mapping(em_tree, start, len);
+ if (!em) {
+ ret = -EIO;
+ goto out_unlock;
+ }
+
+ ASSERT(em->len == len);
+ ASSERT(!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags));
+ ASSERT(em->block_start < EXTENT_MAP_LAST_BYTE);
+
+ flags = em->flags;
+ clear_bit(EXTENT_FLAG_PINNED, &em->flags);
+ clear_bit(EXTENT_FLAG_LOGGING, &flags);
+ modified = !list_empty(&em->list);
+
+ /* First, replace the em with a new extent_map starting from * em->start */
+ split_pre->start = em->start;
+ split_pre->len = (pre ? pre : em->len - post);
+ split_pre->orig_start = split_pre->start;
+ split_pre->block_start = em->block_start;
+ split_pre->block_len = split_pre->len;
+ split_pre->orig_block_len = split_pre->block_len;
+ split_pre->ram_bytes = split_pre->len;
+ split_pre->flags = flags;
+ split_pre->compress_type = em->compress_type;
+ split_pre->generation = em->generation;
+
+ replace_extent_mapping(em_tree, em, split_pre, modified);
+
+ /*
+ * Now we only have an extent_map at:
+ * [em->start, em->start + pre] if pre != 0
+ * [em->start, em->start + em->len - post] if pre == 0
+ */
+
+ if (pre) {
+ /* Insert the middle extent_map */
+ split_mid->start = em->start + pre;
+ split_mid->len = em->len - pre - post;
+ split_mid->orig_start = split_mid->start;
+ split_mid->block_start = em->block_start + pre;
+ split_mid->block_len = split_mid->len;
+ split_mid->orig_block_len = split_mid->block_len;
+ split_mid->ram_bytes = split_mid->len;
+ split_mid->flags = flags;
+ split_mid->compress_type = em->compress_type;
+ split_mid->generation = em->generation;
+ add_extent_mapping(em_tree, split_mid, modified);
+ }
+
+ if (post) {
+ split_post->start = em->start + em->len - post;
+ split_post->len = post;
+ split_post->orig_start = split_post->start;
+ split_post->block_start = em->block_start + em->len - post;
+ split_post->block_len = split_post->len;
+ split_post->orig_block_len = split_post->block_len;
+ split_post->ram_bytes = split_post->len;
+ split_post->flags = flags;
+ split_post->compress_type = em->compress_type;
+ split_post->generation = em->generation;
+ add_extent_mapping(em_tree, split_post, modified);
+ }
+
+ /* Once for us */
+ free_extent_map(em);
+ /* Once for the tree */
+ free_extent_map(em);
+
+out_unlock:
+ write_unlock(&em_tree->lock);
+ unlock_extent(&inode->io_tree, start, start + len - 1);
+out:
+ free_extent_map(split_pre);
+ free_extent_map(split_mid);
+ free_extent_map(split_post);
+
+ return ret;
+}
+
static blk_status_t extract_ordered_extent(struct btrfs_inode *inode,
struct bio *bio, loff_t file_offset)
{
struct btrfs_ordered_extent *ordered;
- struct extent_map *em = NULL, *em_new = NULL;
- struct extent_map_tree *em_tree = &inode->extent_tree;
u64 start = (u64)bio->bi_iter.bi_sector << SECTOR_SHIFT;
+ u64 file_len;
u64 len = bio->bi_iter.bi_size;
u64 end = start + len;
u64 ordered_end;
goto out;
}
+ file_len = ordered->num_bytes;
pre = start - ordered->disk_bytenr;
post = ordered_end - end;
ret = btrfs_split_ordered_extent(ordered, pre, post);
if (ret)
goto out;
-
- read_lock(&em_tree->lock);
- em = lookup_extent_mapping(em_tree, ordered->file_offset, len);
- if (!em) {
- read_unlock(&em_tree->lock);
- ret = -EIO;
- goto out;
- }
- read_unlock(&em_tree->lock);
-
- ASSERT(!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags));
- /*
- * We cannot reuse em_new here but have to create a new one, as
- * unpin_extent_cache() expects the start of the extent map to be the
- * logical offset of the file, which does not hold true anymore after
- * splitting.
- */
- em_new = create_io_em(inode, em->start + pre, len,
- em->start + pre, em->block_start + pre, len,
- len, len, BTRFS_COMPRESS_NONE,
- BTRFS_ORDERED_REGULAR);
- if (IS_ERR(em_new)) {
- ret = PTR_ERR(em_new);
- goto out;
- }
- free_extent_map(em_new);
+ ret = split_zoned_em(inode, file_offset, file_len, pre, post);
out:
- free_extent_map(em);
btrfs_put_ordered_extent(ordered);
return errno_to_blk_status(ret);
goto out;
}
- if (ordered_extent->disk)
+ if (ordered_extent->bdev)
btrfs_rewrite_logical_zoned(ordered_extent);
btrfs_free_io_failure_record(inode, start, end);
entry->truncated_len = (u64)-1;
entry->qgroup_rsv = ret;
entry->physical = (u64)-1;
- entry->disk = NULL;
- entry->partno = (u8)-1;
ASSERT(type == BTRFS_ORDERED_REGULAR ||
type == BTRFS_ORDERED_NOCOW ||
* command in a workqueue context
*/
u64 physical;
- struct gendisk *disk;
- u8 partno;
+ struct block_device *bdev;
};
/*
return 0;
}
-int btrfs_qgroup_trace_extent_post(struct btrfs_fs_info *fs_info,
+int btrfs_qgroup_trace_extent_post(struct btrfs_trans_handle *trans,
struct btrfs_qgroup_extent_record *qrecord)
{
struct ulist *old_root;
u64 bytenr = qrecord->bytenr;
int ret;
- ret = btrfs_find_all_roots(NULL, fs_info, bytenr, 0, &old_root, false);
+ /*
+ * We are always called in a context where we are already holding a
+ * transaction handle. Often we are called when adding a data delayed
+ * reference from btrfs_truncate_inode_items() (truncating or unlinking),
+ * in which case we will be holding a write lock on extent buffer from a
+ * subvolume tree. In this case we can't allow btrfs_find_all_roots() to
+ * acquire fs_info->commit_root_sem, because that is a higher level lock
+ * that must be acquired before locking any extent buffers.
+ *
+ * So we want btrfs_find_all_roots() to not acquire the commit_root_sem
+ * but we can't pass it a non-NULL transaction handle, because otherwise
+ * it would not use commit roots and would lock extent buffers, causing
+ * a deadlock if it ends up trying to read lock the same extent buffer
+ * that was previously write locked at btrfs_truncate_inode_items().
+ *
+ * So pass a NULL transaction handle to btrfs_find_all_roots() and
+ * explicitly tell it to not acquire the commit_root_sem - if we are
+ * holding a transaction handle we don't need its protection.
+ */
+ ASSERT(trans != NULL);
+
+ ret = btrfs_find_all_roots(NULL, trans->fs_info, bytenr, 0, &old_root,
+ false, true);
if (ret < 0) {
- fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
- btrfs_warn(fs_info,
+ trans->fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
+ btrfs_warn(trans->fs_info,
"error accounting new delayed refs extent (err code: %d), quota inconsistent",
ret);
return 0;
kfree(record);
return 0;
}
- return btrfs_qgroup_trace_extent_post(fs_info, record);
+ return btrfs_qgroup_trace_extent_post(trans, record);
}
int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans,
/* Search commit root to find old_roots */
ret = btrfs_find_all_roots(NULL, fs_info,
record->bytenr, 0,
- &record->old_roots, false);
+ &record->old_roots, false, false);
if (ret < 0)
goto cleanup;
}
* current root. It's safe inside commit_transaction().
*/
ret = btrfs_find_all_roots(trans, fs_info,
- record->bytenr, BTRFS_SEQ_LAST, &new_roots, false);
+ record->bytenr, BTRFS_SEQ_LAST, &new_roots, false, false);
if (ret < 0)
goto cleanup;
if (qgroup_to_skip) {
num_bytes = found.offset;
ret = btrfs_find_all_roots(NULL, fs_info, found.objectid, 0,
- &roots, false);
+ &roots, false, false);
if (ret < 0)
goto out;
/* For rescan, just pass old_roots as NULL */
* using current root, then we can move all expensive backref walk out of
* transaction committing, but not now as qgroup accounting will be wrong again.
*/
-int btrfs_qgroup_trace_extent_post(struct btrfs_fs_info *fs_info,
+int btrfs_qgroup_trace_extent_post(struct btrfs_trans_handle *trans,
struct btrfs_qgroup_extent_record *qrecord);
/*
* quota.
*/
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots,
- false);
+ false, false);
if (ret) {
ulist_free(old_roots);
test_err("couldn't find old roots: %d", ret);
return ret;
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots,
- false);
+ false, false);
if (ret) {
ulist_free(old_roots);
ulist_free(new_roots);
new_roots = NULL;
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots,
- false);
+ false, false);
if (ret) {
ulist_free(old_roots);
test_err("couldn't find old roots: %d", ret);
return -EINVAL;
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots,
- false);
+ false, false);
if (ret) {
ulist_free(old_roots);
ulist_free(new_roots);
}
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots,
- false);
+ false, false);
if (ret) {
ulist_free(old_roots);
test_err("couldn't find old roots: %d", ret);
return ret;
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots,
- false);
+ false, false);
if (ret) {
ulist_free(old_roots);
ulist_free(new_roots);
}
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots,
- false);
+ false, false);
if (ret) {
ulist_free(old_roots);
test_err("couldn't find old roots: %d", ret);
return ret;
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots,
- false);
+ false, false);
if (ret) {
ulist_free(old_roots);
ulist_free(new_roots);
}
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots,
- false);
+ false, false);
if (ret) {
ulist_free(old_roots);
test_err("couldn't find old roots: %d", ret);
return ret;
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots,
- false);
+ false, false);
if (ret) {
ulist_free(old_roots);
ulist_free(new_roots);
}
/*
- * To be called after all the new block groups attached to the transaction
- * handle have been created (btrfs_create_pending_block_groups()).
+ * To be called after doing the chunk btree updates right after allocating a new
+ * chunk (after btrfs_chunk_alloc_add_chunk_item() is called), when removing a
+ * chunk after all chunk btree updates and after finishing the second phase of
+ * chunk allocation (btrfs_create_pending_block_groups()) in case some block
+ * group had its chunk item insertion delayed to the second phase.
*/
void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
- struct btrfs_transaction *cur_trans = trans->transaction;
if (!trans->chunk_bytes_reserved)
return;
- WARN_ON_ONCE(!list_empty(&trans->new_bgs));
-
btrfs_block_rsv_release(fs_info, &fs_info->chunk_block_rsv,
trans->chunk_bytes_reserved, NULL);
- atomic64_sub(trans->chunk_bytes_reserved, &cur_trans->chunk_bytes_reserved);
- cond_wake_up(&cur_trans->chunk_reserve_wait);
trans->chunk_bytes_reserved = 0;
}
spin_lock_init(&cur_trans->dropped_roots_lock);
INIT_LIST_HEAD(&cur_trans->releasing_ebs);
spin_lock_init(&cur_trans->releasing_ebs_lock);
- atomic64_set(&cur_trans->chunk_bytes_reserved, 0);
- init_waitqueue_head(&cur_trans->chunk_reserve_wait);
list_add_tail(&cur_trans->list, &fs_info->trans_list);
extent_io_tree_init(fs_info, &cur_trans->dirty_pages,
IO_TREE_TRANS_DIRTY_PAGES, fs_info->btree_inode);
h->fs_info = root->fs_info;
h->type = type;
- h->can_flush_pending_bgs = true;
INIT_LIST_HEAD(&h->new_bgs);
smp_mb();
spinlock_t releasing_ebs_lock;
struct list_head releasing_ebs;
-
- /*
- * The number of bytes currently reserved, by all transaction handles
- * attached to this transaction, for metadata extents of the chunk tree.
- */
- atomic64_t chunk_bytes_reserved;
- wait_queue_head_t chunk_reserve_wait;
};
#define __TRANS_FREEZABLE (1U << 0)
short aborted;
bool adding_csums;
bool allocating_chunk;
- bool can_flush_pending_bgs;
+ bool removing_chunk;
bool reloc_reserved;
bool in_fsync;
struct btrfs_root *root;
if (!log_root_tree->node) {
ret = btrfs_alloc_log_tree_node(trans, log_root_tree);
if (ret) {
- mutex_unlock(&fs_info->tree_log_mutex);
+ mutex_unlock(&fs_info->tree_root->log_mutex);
goto out;
}
}
spin_lock(&inode->lock);
inode->logged_trans = trans->transid;
/*
- * Don't update last_log_commit if we logged that an inode exists
- * after it was loaded to memory (full_sync bit set).
- * This is to prevent data loss when we do a write to the inode,
- * then the inode gets evicted after all delalloc was flushed,
- * then we log it exists (due to a rename for example) and then
- * fsync it. This last fsync would do nothing (not logging the
- * extents previously written).
+ * Don't update last_log_commit if we logged that an inode exists.
+ * We do this for two reasons:
+ *
+ * 1) We might have had buffered writes to this inode that were
+ * flushed and had their ordered extents completed in this
+ * transaction, but we did not previously log the inode with
+ * LOG_INODE_ALL. Later the inode was evicted and after that
+ * it was loaded again and this LOG_INODE_EXISTS log operation
+ * happened. We must make sure that if an explicit fsync against
+ * the inode is performed later, it logs the new extents, an
+ * updated inode item, etc, and syncs the log. The same logic
+ * applies to direct IO writes instead of buffered writes.
+ *
+ * 2) When we log the inode with LOG_INODE_EXISTS, its inode item
+ * is logged with an i_size of 0 or whatever value was logged
+ * before. If later the i_size of the inode is increased by a
+ * truncate operation, the log is synced through an fsync of
+ * some other inode and then finally an explicit fsync against
+ * this inode is made, we must make sure this fsync logs the
+ * inode with the new i_size, the hole between old i_size and
+ * the new i_size, and syncs the log.
*/
- if (inode_only != LOG_INODE_EXISTS ||
- !test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags))
+ if (inode_only != LOG_INODE_EXISTS)
inode->last_log_commit = inode->last_sub_trans;
spin_unlock(&inode->lock);
}
* if this inode hasn't been logged and directory we're renaming it
* from hasn't been logged, we don't need to log it
*/
- if (inode->logged_trans < trans->transid &&
- (!old_dir || old_dir->logged_trans < trans->transid))
+ if (!inode_logged(trans, inode) &&
+ (!old_dir || !inode_logged(trans, old_dir)))
return;
/*
if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
list_del_init(&device->dev_alloc_list);
clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
+ fs_devices->rw_devices--;
}
list_del_init(&device->dev_list);
fs_devices->num_devices--;
extent = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_dev_extent);
} else {
- btrfs_handle_fs_error(fs_info, ret, "Slot search failed");
goto out;
}
*dev_extent_len = btrfs_dev_extent_length(leaf, extent);
ret = btrfs_del_item(trans, root, path);
- if (ret) {
- btrfs_handle_fs_error(fs_info, ret,
- "Failed to remove dev extent item");
- } else {
+ if (ret == 0)
set_bit(BTRFS_TRANS_HAVE_FREE_BGS, &trans->transaction->flags);
- }
out:
btrfs_free_path(path);
return ret;
u32 cur;
struct btrfs_key key;
- mutex_lock(&fs_info->chunk_mutex);
+ lockdep_assert_held(&fs_info->chunk_mutex);
array_size = btrfs_super_sys_array_size(super_copy);
ptr = super_copy->sys_chunk_array;
cur += len;
}
}
- mutex_unlock(&fs_info->chunk_mutex);
return ret;
}
return em;
}
+static int remove_chunk_item(struct btrfs_trans_handle *trans,
+ struct map_lookup *map, u64 chunk_offset)
+{
+ int i;
+
+ /*
+ * Removing chunk items and updating the device items in the chunks btree
+ * requires holding the chunk_mutex.
+ * See the comment at btrfs_chunk_alloc() for the details.
+ */
+ lockdep_assert_held(&trans->fs_info->chunk_mutex);
+
+ for (i = 0; i < map->num_stripes; i++) {
+ int ret;
+
+ ret = btrfs_update_device(trans, map->stripes[i].dev);
+ if (ret)
+ return ret;
+ }
+
+ return btrfs_free_chunk(trans, chunk_offset);
+}
+
int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
return PTR_ERR(em);
}
map = em->map_lookup;
- mutex_lock(&fs_info->chunk_mutex);
- check_system_chunk(trans, map->type);
- mutex_unlock(&fs_info->chunk_mutex);
/*
- * Take the device list mutex to prevent races with the final phase of
- * a device replace operation that replaces the device object associated
- * with map stripes (dev-replace.c:btrfs_dev_replace_finishing()).
+ * First delete the device extent items from the devices btree.
+ * We take the device_list_mutex to avoid racing with the finishing phase
+ * of a device replace operation. See the comment below before acquiring
+ * fs_info->chunk_mutex. Note that here we do not acquire the chunk_mutex
+ * because that can result in a deadlock when deleting the device extent
+ * items from the devices btree - COWing an extent buffer from the btree
+ * may result in allocating a new metadata chunk, which would attempt to
+ * lock again fs_info->chunk_mutex.
*/
mutex_lock(&fs_devices->device_list_mutex);
for (i = 0; i < map->num_stripes; i++) {
btrfs_clear_space_info_full(fs_info);
mutex_unlock(&fs_info->chunk_mutex);
}
+ }
+ mutex_unlock(&fs_devices->device_list_mutex);
- ret = btrfs_update_device(trans, device);
+ /*
+ * We acquire fs_info->chunk_mutex for 2 reasons:
+ *
+ * 1) Just like with the first phase of the chunk allocation, we must
+ * reserve system space, do all chunk btree updates and deletions, and
+ * update the system chunk array in the superblock while holding this
+ * mutex. This is for similar reasons as explained on the comment at
+ * the top of btrfs_chunk_alloc();
+ *
+ * 2) Prevent races with the final phase of a device replace operation
+ * that replaces the device object associated with the map's stripes,
+ * because the device object's id can change at any time during that
+ * final phase of the device replace operation
+ * (dev-replace.c:btrfs_dev_replace_finishing()), so we could grab the
+ * replaced device and then see it with an ID of
+ * BTRFS_DEV_REPLACE_DEVID, which would cause a failure when updating
+ * the device item, which does not exists on the chunk btree.
+ * The finishing phase of device replace acquires both the
+ * device_list_mutex and the chunk_mutex, in that order, so we are
+ * safe by just acquiring the chunk_mutex.
+ */
+ trans->removing_chunk = true;
+ mutex_lock(&fs_info->chunk_mutex);
+
+ check_system_chunk(trans, map->type);
+
+ ret = remove_chunk_item(trans, map, chunk_offset);
+ /*
+ * Normally we should not get -ENOSPC since we reserved space before
+ * through the call to check_system_chunk().
+ *
+ * Despite our system space_info having enough free space, we may not
+ * be able to allocate extents from its block groups, because all have
+ * an incompatible profile, which will force us to allocate a new system
+ * block group with the right profile, or right after we called
+ * check_system_space() above, a scrub turned the only system block group
+ * with enough free space into RO mode.
+ * This is explained with more detail at do_chunk_alloc().
+ *
+ * So if we get -ENOSPC, allocate a new system chunk and retry once.
+ */
+ if (ret == -ENOSPC) {
+ const u64 sys_flags = btrfs_system_alloc_profile(fs_info);
+ struct btrfs_block_group *sys_bg;
+
+ sys_bg = btrfs_alloc_chunk(trans, sys_flags);
+ if (IS_ERR(sys_bg)) {
+ ret = PTR_ERR(sys_bg);
+ btrfs_abort_transaction(trans, ret);
+ goto out;
+ }
+
+ ret = btrfs_chunk_alloc_add_chunk_item(trans, sys_bg);
if (ret) {
- mutex_unlock(&fs_devices->device_list_mutex);
btrfs_abort_transaction(trans, ret);
goto out;
}
- }
- mutex_unlock(&fs_devices->device_list_mutex);
- ret = btrfs_free_chunk(trans, chunk_offset);
- if (ret) {
+ ret = remove_chunk_item(trans, map, chunk_offset);
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ goto out;
+ }
+ } else if (ret) {
btrfs_abort_transaction(trans, ret);
goto out;
}
}
}
+ mutex_unlock(&fs_info->chunk_mutex);
+ trans->removing_chunk = false;
+
+ /*
+ * We are done with chunk btree updates and deletions, so release the
+ * system space we previously reserved (with check_system_chunk()).
+ */
+ btrfs_trans_release_chunk_metadata(trans);
+
ret = btrfs_remove_block_group(trans, chunk_offset, em);
if (ret) {
btrfs_abort_transaction(trans, ret);
}
out:
+ if (trans->removing_chunk) {
+ mutex_unlock(&fs_info->chunk_mutex);
+ trans->removing_chunk = false;
+ }
/* once for us */
free_extent_map(em);
return ret;
u32 array_size;
u8 *ptr;
- mutex_lock(&fs_info->chunk_mutex);
+ lockdep_assert_held(&fs_info->chunk_mutex);
+
array_size = btrfs_super_sys_array_size(super_copy);
if (array_size + item_size + sizeof(disk_key)
- > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) {
- mutex_unlock(&fs_info->chunk_mutex);
+ > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE)
return -EFBIG;
- }
ptr = super_copy->sys_chunk_array + array_size;
btrfs_cpu_key_to_disk(&disk_key, key);
memcpy(ptr, chunk, item_size);
item_size += sizeof(disk_key);
btrfs_set_super_sys_array_size(super_copy, array_size + item_size);
- mutex_unlock(&fs_info->chunk_mutex);
return 0;
}
}
}
-static int create_chunk(struct btrfs_trans_handle *trans,
+static struct btrfs_block_group *create_chunk(struct btrfs_trans_handle *trans,
struct alloc_chunk_ctl *ctl,
struct btrfs_device_info *devices_info)
{
struct btrfs_fs_info *info = trans->fs_info;
struct map_lookup *map = NULL;
struct extent_map_tree *em_tree;
+ struct btrfs_block_group *block_group;
struct extent_map *em;
u64 start = ctl->start;
u64 type = ctl->type;
map = kmalloc(map_lookup_size(ctl->num_stripes), GFP_NOFS);
if (!map)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
map->num_stripes = ctl->num_stripes;
for (i = 0; i < ctl->ndevs; ++i) {
em = alloc_extent_map();
if (!em) {
kfree(map);
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
}
set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
em->map_lookup = map;
if (ret) {
write_unlock(&em_tree->lock);
free_extent_map(em);
- return ret;
+ return ERR_PTR(ret);
}
write_unlock(&em_tree->lock);
- ret = btrfs_make_block_group(trans, 0, type, start, ctl->chunk_size);
- if (ret)
+ block_group = btrfs_make_block_group(trans, 0, type, start, ctl->chunk_size);
+ if (IS_ERR(block_group))
goto error_del_extent;
for (i = 0; i < map->num_stripes; i++) {
check_raid56_incompat_flag(info, type);
check_raid1c34_incompat_flag(info, type);
- return 0;
+ return block_group;
error_del_extent:
write_lock(&em_tree->lock);
/* One for the tree reference */
free_extent_map(em);
- return ret;
+ return block_group;
}
-int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type)
+struct btrfs_block_group *btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
+ u64 type)
{
struct btrfs_fs_info *info = trans->fs_info;
struct btrfs_fs_devices *fs_devices = info->fs_devices;
struct btrfs_device_info *devices_info = NULL;
struct alloc_chunk_ctl ctl;
+ struct btrfs_block_group *block_group;
int ret;
lockdep_assert_held(&info->chunk_mutex);
if (!alloc_profile_is_valid(type, 0)) {
ASSERT(0);
- return -EINVAL;
+ return ERR_PTR(-EINVAL);
}
if (list_empty(&fs_devices->alloc_list)) {
if (btrfs_test_opt(info, ENOSPC_DEBUG))
btrfs_debug(info, "%s: no writable device", __func__);
- return -ENOSPC;
+ return ERR_PTR(-ENOSPC);
}
if (!(type & BTRFS_BLOCK_GROUP_TYPE_MASK)) {
btrfs_err(info, "invalid chunk type 0x%llx requested", type);
ASSERT(0);
- return -EINVAL;
+ return ERR_PTR(-EINVAL);
}
ctl.start = find_next_chunk(info);
devices_info = kcalloc(fs_devices->rw_devices, sizeof(*devices_info),
GFP_NOFS);
if (!devices_info)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
ret = gather_device_info(fs_devices, &ctl, devices_info);
- if (ret < 0)
+ if (ret < 0) {
+ block_group = ERR_PTR(ret);
goto out;
+ }
ret = decide_stripe_size(fs_devices, &ctl, devices_info);
- if (ret < 0)
+ if (ret < 0) {
+ block_group = ERR_PTR(ret);
goto out;
+ }
- ret = create_chunk(trans, &ctl, devices_info);
+ block_group = create_chunk(trans, &ctl, devices_info);
out:
kfree(devices_info);
- return ret;
+ return block_group;
}
/*
- * Chunk allocation falls into two parts. The first part does work
- * that makes the new allocated chunk usable, but does not do any operation
- * that modifies the chunk tree. The second part does the work that
- * requires modifying the chunk tree. This division is important for the
- * bootstrap process of adding storage to a seed btrfs.
+ * This function, btrfs_finish_chunk_alloc(), belongs to phase 2.
+ *
+ * See the comment at btrfs_chunk_alloc() for details about the chunk allocation
+ * phases.
*/
int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
u64 chunk_offset, u64 chunk_size)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
- struct btrfs_root *extent_root = fs_info->extent_root;
- struct btrfs_root *chunk_root = fs_info->chunk_root;
- struct btrfs_key key;
struct btrfs_device *device;
- struct btrfs_chunk *chunk;
- struct btrfs_stripe *stripe;
struct extent_map *em;
struct map_lookup *map;
- size_t item_size;
u64 dev_offset;
u64 stripe_size;
- int i = 0;
+ int i;
int ret = 0;
em = btrfs_get_chunk_map(fs_info, chunk_offset, chunk_size);
return PTR_ERR(em);
map = em->map_lookup;
- item_size = btrfs_chunk_item_size(map->num_stripes);
stripe_size = em->orig_block_len;
- chunk = kzalloc(item_size, GFP_NOFS);
- if (!chunk) {
- ret = -ENOMEM;
- goto out;
- }
-
/*
* Take the device list mutex to prevent races with the final phase of
* a device replace operation that replaces the device object associated
* with the map's stripes, because the device object's id can change
* at any time during that final phase of the device replace operation
- * (dev-replace.c:btrfs_dev_replace_finishing()).
+ * (dev-replace.c:btrfs_dev_replace_finishing()), so we could grab the
+ * replaced device and then see it with an ID of BTRFS_DEV_REPLACE_DEVID,
+ * resulting in persisting a device extent item with such ID.
*/
mutex_lock(&fs_info->fs_devices->device_list_mutex);
for (i = 0; i < map->num_stripes; i++) {
device = map->stripes[i].dev;
dev_offset = map->stripes[i].physical;
- ret = btrfs_update_device(trans, device);
- if (ret)
- break;
ret = btrfs_alloc_dev_extent(trans, device, chunk_offset,
dev_offset, stripe_size);
if (ret)
break;
}
- if (ret) {
- mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+ mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+
+ free_extent_map(em);
+ return ret;
+}
+
+/*
+ * This function, btrfs_chunk_alloc_add_chunk_item(), typically belongs to the
+ * phase 1 of chunk allocation. It belongs to phase 2 only when allocating system
+ * chunks.
+ *
+ * See the comment at btrfs_chunk_alloc() for details about the chunk allocation
+ * phases.
+ */
+int btrfs_chunk_alloc_add_chunk_item(struct btrfs_trans_handle *trans,
+ struct btrfs_block_group *bg)
+{
+ struct btrfs_fs_info *fs_info = trans->fs_info;
+ struct btrfs_root *extent_root = fs_info->extent_root;
+ struct btrfs_root *chunk_root = fs_info->chunk_root;
+ struct btrfs_key key;
+ struct btrfs_chunk *chunk;
+ struct btrfs_stripe *stripe;
+ struct extent_map *em;
+ struct map_lookup *map;
+ size_t item_size;
+ int i;
+ int ret;
+
+ /*
+ * We take the chunk_mutex for 2 reasons:
+ *
+ * 1) Updates and insertions in the chunk btree must be done while holding
+ * the chunk_mutex, as well as updating the system chunk array in the
+ * superblock. See the comment on top of btrfs_chunk_alloc() for the
+ * details;
+ *
+ * 2) To prevent races with the final phase of a device replace operation
+ * that replaces the device object associated with the map's stripes,
+ * because the device object's id can change at any time during that
+ * final phase of the device replace operation
+ * (dev-replace.c:btrfs_dev_replace_finishing()), so we could grab the
+ * replaced device and then see it with an ID of BTRFS_DEV_REPLACE_DEVID,
+ * which would cause a failure when updating the device item, which does
+ * not exists, or persisting a stripe of the chunk item with such ID.
+ * Here we can't use the device_list_mutex because our caller already
+ * has locked the chunk_mutex, and the final phase of device replace
+ * acquires both mutexes - first the device_list_mutex and then the
+ * chunk_mutex. Using any of those two mutexes protects us from a
+ * concurrent device replace.
+ */
+ lockdep_assert_held(&fs_info->chunk_mutex);
+
+ em = btrfs_get_chunk_map(fs_info, bg->start, bg->length);
+ if (IS_ERR(em)) {
+ ret = PTR_ERR(em);
+ btrfs_abort_transaction(trans, ret);
+ return ret;
+ }
+
+ map = em->map_lookup;
+ item_size = btrfs_chunk_item_size(map->num_stripes);
+
+ chunk = kzalloc(item_size, GFP_NOFS);
+ if (!chunk) {
+ ret = -ENOMEM;
+ btrfs_abort_transaction(trans, ret);
goto out;
}
+ for (i = 0; i < map->num_stripes; i++) {
+ struct btrfs_device *device = map->stripes[i].dev;
+
+ ret = btrfs_update_device(trans, device);
+ if (ret)
+ goto out;
+ }
+
stripe = &chunk->stripe;
for (i = 0; i < map->num_stripes; i++) {
- device = map->stripes[i].dev;
- dev_offset = map->stripes[i].physical;
+ struct btrfs_device *device = map->stripes[i].dev;
+ const u64 dev_offset = map->stripes[i].physical;
btrfs_set_stack_stripe_devid(stripe, device->devid);
btrfs_set_stack_stripe_offset(stripe, dev_offset);
memcpy(stripe->dev_uuid, device->uuid, BTRFS_UUID_SIZE);
stripe++;
}
- mutex_unlock(&fs_info->fs_devices->device_list_mutex);
- btrfs_set_stack_chunk_length(chunk, chunk_size);
+ btrfs_set_stack_chunk_length(chunk, bg->length);
btrfs_set_stack_chunk_owner(chunk, extent_root->root_key.objectid);
btrfs_set_stack_chunk_stripe_len(chunk, map->stripe_len);
btrfs_set_stack_chunk_type(chunk, map->type);
key.objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID;
key.type = BTRFS_CHUNK_ITEM_KEY;
- key.offset = chunk_offset;
+ key.offset = bg->start;
ret = btrfs_insert_item(trans, chunk_root, &key, chunk, item_size);
- if (ret == 0 && map->type & BTRFS_BLOCK_GROUP_SYSTEM) {
- /*
- * TODO: Cleanup of inserted chunk root in case of
- * failure.
- */
+ if (ret)
+ goto out;
+
+ bg->chunk_item_inserted = 1;
+
+ if (map->type & BTRFS_BLOCK_GROUP_SYSTEM) {
ret = btrfs_add_system_chunk(fs_info, &key, chunk, item_size);
+ if (ret)
+ goto out;
}
out:
{
struct btrfs_fs_info *fs_info = trans->fs_info;
u64 alloc_profile;
- int ret;
+ struct btrfs_block_group *meta_bg;
+ struct btrfs_block_group *sys_bg;
+
+ /*
+ * When adding a new device for sprouting, the seed device is read-only
+ * so we must first allocate a metadata and a system chunk. But before
+ * adding the block group items to the extent, device and chunk btrees,
+ * we must first:
+ *
+ * 1) Create both chunks without doing any changes to the btrees, as
+ * otherwise we would get -ENOSPC since the block groups from the
+ * seed device are read-only;
+ *
+ * 2) Add the device item for the new sprout device - finishing the setup
+ * of a new block group requires updating the device item in the chunk
+ * btree, so it must exist when we attempt to do it. The previous step
+ * ensures this does not fail with -ENOSPC.
+ *
+ * After that we can add the block group items to their btrees:
+ * update existing device item in the chunk btree, add a new block group
+ * item to the extent btree, add a new chunk item to the chunk btree and
+ * finally add the new device extent items to the devices btree.
+ */
alloc_profile = btrfs_metadata_alloc_profile(fs_info);
- ret = btrfs_alloc_chunk(trans, alloc_profile);
- if (ret)
- return ret;
+ meta_bg = btrfs_alloc_chunk(trans, alloc_profile);
+ if (IS_ERR(meta_bg))
+ return PTR_ERR(meta_bg);
alloc_profile = btrfs_system_alloc_profile(fs_info);
- ret = btrfs_alloc_chunk(trans, alloc_profile);
- return ret;
+ sys_bg = btrfs_alloc_chunk(trans, alloc_profile);
+ if (IS_ERR(sys_bg))
+ return PTR_ERR(sys_bg);
+
+ return 0;
}
static inline int btrfs_chunk_max_errors(struct map_lookup *map)
total_dev++;
} else if (found_key.type == BTRFS_CHUNK_ITEM_KEY) {
struct btrfs_chunk *chunk;
+
+ /*
+ * We are only called at mount time, so no need to take
+ * fs_info->chunk_mutex. Plus, to avoid lockdep warnings,
+ * we always lock first fs_info->chunk_mutex before
+ * acquiring any locks on the chunk tree. This is a
+ * requirement for chunk allocation, see the comment on
+ * top of btrfs_chunk_alloc() for details.
+ */
+ ASSERT(!test_bit(BTRFS_FS_OPEN, &fs_info->flags));
chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk);
- mutex_lock(&fs_info->chunk_mutex);
ret = read_one_chunk(&found_key, leaf, chunk);
- mutex_unlock(&fs_info->chunk_mutex);
if (ret)
goto error;
}
struct btrfs_io_geometry *io_geom);
int btrfs_read_sys_array(struct btrfs_fs_info *fs_info);
int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info);
-int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type);
+struct btrfs_block_group *btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
+ u64 type);
void btrfs_mapping_tree_free(struct extent_map_tree *tree);
blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
int mirror_num);
u64 logical);
int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
u64 chunk_offset, u64 chunk_size);
+int btrfs_chunk_alloc_add_chunk_item(struct btrfs_trans_handle *trans,
+ struct btrfs_block_group *bg);
int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset);
struct extent_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info,
u64 logical, u64 length);
return;
ordered->physical = physical;
- ordered->disk = bio->bi_bdev->bd_disk;
- ordered->partno = bio->bi_bdev->bd_partno;
+ ordered->bdev = bio->bi_bdev;
btrfs_put_ordered_extent(ordered);
}
struct extent_map_tree *em_tree;
struct extent_map *em;
struct btrfs_ordered_sum *sum;
- struct block_device *bdev;
u64 orig_logical = ordered->disk_bytenr;
u64 *logical = NULL;
int nr, stripe_len;
/* Zoned devices should not have partitions. So, we can assume it is 0 */
- ASSERT(ordered->partno == 0);
- bdev = bdgrab(ordered->disk->part0);
- if (WARN_ON(!bdev))
+ ASSERT(!bdev_is_partition(ordered->bdev));
+ if (WARN_ON(!ordered->bdev))
return;
- if (WARN_ON(btrfs_rmap_block(fs_info, orig_logical, bdev,
+ if (WARN_ON(btrfs_rmap_block(fs_info, orig_logical, ordered->bdev,
ordered->physical, &logical, &nr,
&stripe_len)))
goto out;
out:
kfree(logical);
- bdput(bdev);
}
bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info,
break;
case CEPH_MDS_SESSION_CLOSING:
/* Should never reach this when we're unmounting */
- WARN_ON_ONCE(true);
+ WARN_ON_ONCE(s->s_ttl);
fallthrough;
case CEPH_MDS_SESSION_NEW:
case CEPH_MDS_SESSION_RESTARTING:
}
}
- rc = dns_resolve_server_name_to_ip(name, &srvIP);
+ rc = dns_resolve_server_name_to_ip(name, &srvIP, NULL);
if (rc < 0) {
cifs_dbg(FYI, "%s: Failed to resolve server part of %s to IP: %d\n",
__func__, name, rc);
else
noff = tkn_e - (sb_mountdata + off) + 1;
+ if (strncasecmp(sb_mountdata + off, "cruid=", 6) == 0) {
+ off += noff;
+ continue;
+ }
if (strncasecmp(sb_mountdata + off, "unc=", 4) == 0) {
off += noff;
continue;
#define SMB_ECHO_INTERVAL_MAX 600
#define SMB_ECHO_INTERVAL_DEFAULT 60
+/* dns resolution interval in seconds */
+#define SMB_DNS_RESOLVE_INTERVAL_DEFAULT 600
+
/* maximum number of PDUs in one compound */
#define MAX_COMPOUND 5
/* point to the SMBD connection if RDMA is used instead of socket */
struct smbd_connection *smbd_conn;
struct delayed_work echo; /* echo ping workqueue job */
+ struct delayed_work resolve; /* dns resolution workqueue job */
char *smallbuf; /* pointer to current "small" buffer */
char *bigbuf; /* pointer to current "big" buffer */
/* Total size of this PDU. Only valid from cifs_demultiplex_thread */
bool use_swn_dstaddr;
struct sockaddr_storage swn_dstaddr;
#endif
+#ifdef CONFIG_CIFS_DFS_UPCALL
+ bool is_dfs_conn; /* if a dfs connection */
+#endif
};
struct cifs_credits {
InformationLevel) - 4;
offset = param_offset + params;
- /* Setup pointer to Request Data (inode type) */
- pRqD = (struct unlink_psx_rq *)(((char *)&pSMB->hdr.Protocol) + offset);
+ /* Setup pointer to Request Data (inode type).
+ * Note that SMB offsets are from the beginning of SMB which is 4 bytes
+ * in, after RFC1001 field
+ */
+ pRqD = (struct unlink_psx_rq *)((char *)(pSMB) + offset + 4);
pRqD->type = cpu_to_le16(type);
pSMB->ParameterOffset = cpu_to_le16(param_offset);
pSMB->DataOffset = cpu_to_le16(offset);
param_offset = offsetof(struct smb_com_transaction2_spi_req,
InformationLevel) - 4;
offset = param_offset + params;
- pdata = (OPEN_PSX_REQ *)(((char *)&pSMB->hdr.Protocol) + offset);
+ /* SMB offsets are from the beginning of SMB which is 4 bytes in, after RFC1001 field */
+ pdata = (OPEN_PSX_REQ *)((char *)(pSMB) + offset + 4);
pdata->Level = cpu_to_le16(SMB_QUERY_FILE_UNIX_BASIC);
pdata->Permissions = cpu_to_le64(mode);
pdata->PosixOpenFlags = cpu_to_le32(posix_flags);
int rc;
int len;
char *unc, *ipaddr = NULL;
+ time64_t expiry, now;
+ unsigned long ttl = SMB_DNS_RESOLVE_INTERVAL_DEFAULT;
if (!server->hostname)
return -EINVAL;
}
scnprintf(unc, len, "\\\\%s", server->hostname);
- rc = dns_resolve_server_name_to_ip(unc, &ipaddr);
+ rc = dns_resolve_server_name_to_ip(unc, &ipaddr, &expiry);
kfree(unc);
if (rc < 0) {
cifs_dbg(FYI, "%s: failed to resolve server part of %s to IP: %d\n",
__func__, server->hostname, rc);
- return rc;
+ goto requeue_resolve;
}
spin_lock(&cifs_tcp_ses_lock);
spin_unlock(&cifs_tcp_ses_lock);
kfree(ipaddr);
- return !rc ? -1 : 0;
+ /* rc == 1 means success here */
+ if (rc) {
+ now = ktime_get_real_seconds();
+ if (expiry && expiry > now)
+ /*
+ * To make sure we don't use the cached entry, retry 1s
+ * after expiry.
+ */
+ ttl = (expiry - now + 1);
+ }
+ rc = !rc ? -1 : 0;
+
+requeue_resolve:
+ cifs_dbg(FYI, "%s: next dns resolution scheduled for %lu seconds in the future\n",
+ __func__, ttl);
+ mod_delayed_work(cifsiod_wq, &server->resolve, (ttl * HZ));
+
+ return rc;
+}
+
+
+static void cifs_resolve_server(struct work_struct *work)
+{
+ int rc;
+ struct TCP_Server_Info *server = container_of(work,
+ struct TCP_Server_Info, resolve.work);
+
+ mutex_lock(&server->srv_mutex);
+
+ /*
+ * 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);
+ }
+
+ mutex_unlock(&server->srv_mutex);
}
#ifdef CONFIG_CIFS_DFS_UPCALL
#ifdef CONFIG_CIFS_DFS_UPCALL
struct super_block *sb = NULL;
struct cifs_sb_info *cifs_sb = NULL;
- struct dfs_cache_tgt_list tgt_list = {0};
+ struct dfs_cache_tgt_list tgt_list = DFS_CACHE_TGT_LIST_INIT(tgt_list);
struct dfs_cache_tgt_iterator *tgt_it = NULL;
#endif
spin_unlock(&cifs_tcp_ses_lock);
cancel_delayed_work_sync(&server->echo);
+ cancel_delayed_work_sync(&server->resolve);
spin_lock(&GlobalMid_Lock);
server->tcpStatus = CifsExiting;
spin_lock(&cifs_tcp_ses_lock);
list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) {
+#ifdef CONFIG_CIFS_DFS_UPCALL
+ /*
+ * DFS failover implementation in cifs_reconnect() requires unique tcp sessions for
+ * DFS connections to do failover properly, so avoid sharing them with regular
+ * shares or even links that may connect to same server but having completely
+ * different failover targets.
+ */
+ if (server->is_dfs_conn)
+ continue;
+#endif
/*
* Skip ses channels since they're only handled in lower layers
* (e.g. cifs_send_recv).
return;
}
+ /* srv_count can never go negative */
+ WARN_ON(server->srv_count < 0);
+
put_net(cifs_net_ns(server));
list_del_init(&server->tcp_ses_list);
spin_unlock(&cifs_tcp_ses_lock);
cancel_delayed_work_sync(&server->echo);
+ cancel_delayed_work_sync(&server->resolve);
if (from_reconnect)
/*
INIT_LIST_HEAD(&tcp_ses->tcp_ses_list);
INIT_LIST_HEAD(&tcp_ses->smb_ses_list);
INIT_DELAYED_WORK(&tcp_ses->echo, cifs_echo_request);
+ INIT_DELAYED_WORK(&tcp_ses->resolve, cifs_resolve_server);
INIT_DELAYED_WORK(&tcp_ses->reconnect, smb2_reconnect_server);
mutex_init(&tcp_ses->reconnect_mutex);
memcpy(&tcp_ses->srcaddr, &ctx->srcaddr,
/* queue echo request delayed work */
queue_delayed_work(cifsiod_wq, &tcp_ses->echo, tcp_ses->echo_interval);
+ /* queue dns resolution delayed work */
+ cifs_dbg(FYI, "%s: next dns resolution scheduled for %d seconds in the future\n",
+ __func__, SMB_DNS_RESOLVE_INTERVAL_DEFAULT);
+
+ queue_delayed_work(cifsiod_wq, &tcp_ses->resolve, (SMB_DNS_RESOLVE_INTERVAL_DEFAULT * HZ));
+
return tcp_ses;
out_err_crypto_release:
}
spin_unlock(&cifs_tcp_ses_lock);
+ /* ses_count can never go negative */
+ WARN_ON(ses->ses_count < 0);
+
spin_lock(&GlobalMid_Lock);
if (ses->status == CifsGood)
ses->status = CifsExiting;
return;
}
+ /* tc_count can never go negative */
+ WARN_ON(tcon->tc_count < 0);
+
if (tcon->use_witness) {
int rc;
}
#ifdef CONFIG_CIFS_DFS_UPCALL
+static int mount_get_dfs_conns(struct smb3_fs_context *ctx, struct cifs_sb_info *cifs_sb,
+ unsigned int *xid, struct TCP_Server_Info **nserver,
+ struct cifs_ses **nses, struct cifs_tcon **ntcon)
+{
+ int rc;
+
+ ctx->nosharesock = true;
+ rc = mount_get_conns(ctx, cifs_sb, xid, nserver, nses, ntcon);
+ if (*nserver) {
+ cifs_dbg(FYI, "%s: marking tcp session as a dfs connection\n", __func__);
+ spin_lock(&cifs_tcp_ses_lock);
+ (*nserver)->is_dfs_conn = true;
+ spin_unlock(&cifs_tcp_ses_lock);
+ }
+ return rc;
+}
+
/*
* cifs_build_path_to_root returns full path to root when we do not have an
* existing connection (tcon)
{
int rc;
char *npath = NULL;
- struct dfs_cache_tgt_list tgt_list = {0};
+ struct dfs_cache_tgt_list tgt_list = DFS_CACHE_TGT_LIST_INIT(tgt_list);
struct dfs_cache_tgt_iterator *tgt_it = NULL;
struct smb3_fs_context tmp_ctx = {NULL};
tmp_ctx.prepath);
mount_put_conns(cifs_sb, *xid, *server, *ses, *tcon);
- rc = mount_get_conns(&tmp_ctx, cifs_sb, xid, server, ses, tcon);
+ rc = mount_get_dfs_conns(&tmp_ctx, cifs_sb, xid, server, ses, tcon);
if (!rc || (*server && *ses)) {
/*
* We were able to connect to new target server. Update current context with
goto error;
}
- ctx->nosharesock = true;
+ mount_put_conns(cifs_sb, xid, server, ses, tcon);
+ /*
+ * Ignore error check here because we may failover to other targets from cached a
+ * referral.
+ */
+ (void)mount_get_dfs_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon);
/* Get path of DFS root */
ref_path = build_unc_path_to_root(ctx, cifs_sb, false);
/* Connect to new DFS target only if we were redirected */
if (oldmnt != cifs_sb->ctx->mount_options) {
mount_put_conns(cifs_sb, xid, server, ses, tcon);
- rc = mount_get_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon);
+ rc = mount_get_dfs_conns(ctx, cifs_sb, &xid, &server, &ses, &tcon);
}
if (rc && !server && !ses) {
/* Failed to connect. Try to connect to other targets in the referral. */
rc = -ELOOP;
} while (rc == -EREMOTE);
- if (rc || !tcon)
+ if (rc || !tcon || !ses)
goto error;
kfree(ref_path);
if (!tree)
return -ENOMEM;
- if (!tcon->dfs_path) {
+ /* If it is not dfs or there was no cached dfs referral, then reconnect to same share */
+ if (!tcon->dfs_path || dfs_cache_noreq_find(tcon->dfs_path + 1, &ref, &tl)) {
if (tcon->ipc) {
scnprintf(tree, MAX_TREE_SIZE, "\\\\%s\\IPC$", server->hostname);
rc = ops->tree_connect(xid, tcon->ses, tree, tcon, nlsc);
goto out;
}
- rc = dfs_cache_noreq_find(tcon->dfs_path + 1, &ref, &tl);
- if (rc)
- goto out;
isroot = ref.server_type == DFS_TYPE_ROOT;
free_dfs_info_param(&ref);
#include "cifs_debug.h"
#include "cifs_unicode.h"
#include "smb2glob.h"
+#include "dns_resolve.h"
#include "dfs_cache.h"
err_free_it:
list_for_each_entry_safe(it, nit, head, it_list) {
+ list_del(&it->it_list);
kfree(it->it_name);
kfree(it);
}
return 0;
}
+static bool target_share_equal(struct TCP_Server_Info *server, const char *s1, const char *s2)
+{
+ char unc[sizeof("\\\\") + SERVER_NAME_LENGTH] = {0};
+ const char *host;
+ size_t hostlen;
+ char *ip = NULL;
+ struct sockaddr sa;
+ bool match;
+ int rc;
+
+ if (strcasecmp(s1, s2))
+ return false;
+
+ /*
+ * Resolve share's hostname and check if server address matches. Otherwise just ignore it
+ * as we could not have upcall to resolve hostname or failed to convert ip address.
+ */
+ match = true;
+ extract_unc_hostname(s1, &host, &hostlen);
+ scnprintf(unc, sizeof(unc), "\\\\%.*s", (int)hostlen, host);
+
+ rc = dns_resolve_server_name_to_ip(unc, &ip, NULL);
+ if (rc < 0) {
+ cifs_dbg(FYI, "%s: could not resolve %.*s. assuming server address matches.\n",
+ __func__, (int)hostlen, host);
+ return true;
+ }
+
+ if (!cifs_convert_address(&sa, ip, strlen(ip))) {
+ cifs_dbg(VFS, "%s: failed to convert address \'%s\'. skip address matching.\n",
+ __func__, ip);
+ } else {
+ mutex_lock(&server->srv_mutex);
+ match = cifs_match_ipaddr((struct sockaddr *)&server->dstaddr, &sa);
+ mutex_unlock(&server->srv_mutex);
+ }
+
+ kfree(ip);
+ return match;
+}
+
+/*
+ * Mark dfs tcon for reconnecting when the currently connected tcon does not match any of the new
+ * target shares in @refs.
+ */
+static void mark_for_reconnect_if_needed(struct cifs_tcon *tcon, struct dfs_cache_tgt_list *tl,
+ const struct dfs_info3_param *refs, int numrefs)
+{
+ struct dfs_cache_tgt_iterator *it;
+ int i;
+
+ for (it = dfs_cache_get_tgt_iterator(tl); it; it = dfs_cache_get_next_tgt(tl, it)) {
+ for (i = 0; i < numrefs; i++) {
+ if (target_share_equal(tcon->ses->server, dfs_cache_get_tgt_name(it),
+ refs[i].node_name))
+ return;
+ }
+ }
+
+ cifs_dbg(FYI, "%s: no cached or matched targets. mark dfs share for reconnect.\n", __func__);
+ for (i = 0; i < tcon->ses->chan_count; i++) {
+ spin_lock(&GlobalMid_Lock);
+ if (tcon->ses->chans[i].server->tcpStatus != CifsExiting)
+ tcon->ses->chans[i].server->tcpStatus = CifsNeedReconnect;
+ spin_unlock(&GlobalMid_Lock);
+ }
+}
+
+/* Refresh dfs referral of tcon and mark it for reconnect if needed */
+static int refresh_tcon(struct cifs_ses **sessions, struct cifs_tcon *tcon, bool force_refresh)
+{
+ const char *path = tcon->dfs_path + 1;
+ struct cifs_ses *ses;
+ struct cache_entry *ce;
+ struct dfs_info3_param *refs = NULL;
+ int numrefs = 0;
+ bool needs_refresh = false;
+ struct dfs_cache_tgt_list tl = DFS_CACHE_TGT_LIST_INIT(tl);
+ int rc = 0;
+ unsigned int xid;
+
+ ses = find_ipc_from_server_path(sessions, path);
+ if (IS_ERR(ses)) {
+ cifs_dbg(FYI, "%s: could not find ipc session\n", __func__);
+ return PTR_ERR(ses);
+ }
+
+ down_read(&htable_rw_lock);
+ ce = lookup_cache_entry(path);
+ needs_refresh = force_refresh || IS_ERR(ce) || cache_entry_expired(ce);
+ if (!IS_ERR(ce)) {
+ rc = get_targets(ce, &tl);
+ if (rc)
+ cifs_dbg(FYI, "%s: could not get dfs targets: %d\n", __func__, rc);
+ }
+ up_read(&htable_rw_lock);
+
+ if (!needs_refresh) {
+ rc = 0;
+ goto out;
+ }
+
+ xid = get_xid();
+ rc = get_dfs_referral(xid, ses, path, &refs, &numrefs);
+ free_xid(xid);
+
+ /* Create or update a cache entry with the new referral */
+ if (!rc) {
+ dump_refs(refs, numrefs);
+
+ down_write(&htable_rw_lock);
+ ce = lookup_cache_entry(path);
+ if (IS_ERR(ce))
+ add_cache_entry_locked(refs, numrefs);
+ else if (force_refresh || cache_entry_expired(ce))
+ update_cache_entry_locked(ce, refs, numrefs);
+ up_write(&htable_rw_lock);
+
+ mark_for_reconnect_if_needed(tcon, &tl, refs, numrefs);
+ }
+
+out:
+ dfs_cache_free_tgts(&tl);
+ free_dfs_info_array(refs, numrefs);
+ return rc;
+}
+
+/**
+ * dfs_cache_remount_fs - remount a DFS share
+ *
+ * Reconfigure dfs mount by forcing a new DFS referral and if the currently cached targets do not
+ * match any of the new targets, mark it for reconnect.
+ *
+ * @cifs_sb: cifs superblock.
+ *
+ * Return zero if remounted, otherwise non-zero.
+ */
+int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb)
+{
+ struct cifs_tcon *tcon;
+ struct mount_group *mg;
+ struct cifs_ses *sessions[CACHE_MAX_ENTRIES + 1] = {NULL};
+ int rc;
+
+ if (!cifs_sb || !cifs_sb->master_tlink)
+ return -EINVAL;
+
+ tcon = cifs_sb_master_tcon(cifs_sb);
+ if (!tcon->dfs_path) {
+ cifs_dbg(FYI, "%s: not a dfs tcon\n", __func__);
+ return 0;
+ }
+
+ if (uuid_is_null(&cifs_sb->dfs_mount_id)) {
+ cifs_dbg(FYI, "%s: tcon has no dfs mount group id\n", __func__);
+ return -EINVAL;
+ }
+
+ mutex_lock(&mount_group_list_lock);
+ mg = find_mount_group_locked(&cifs_sb->dfs_mount_id);
+ if (IS_ERR(mg)) {
+ mutex_unlock(&mount_group_list_lock);
+ cifs_dbg(FYI, "%s: tcon has ipc session to refresh referral\n", __func__);
+ return PTR_ERR(mg);
+ }
+ kref_get(&mg->refcount);
+ mutex_unlock(&mount_group_list_lock);
+
+ spin_lock(&mg->lock);
+ memcpy(&sessions, mg->sessions, mg->num_sessions * sizeof(mg->sessions[0]));
+ spin_unlock(&mg->lock);
+
+ /*
+ * After reconnecting to a different server, unique ids won't match anymore, so we disable
+ * serverino. This prevents dentry revalidation to think the dentry are stale (ESTALE).
+ */
+ cifs_autodisable_serverino(cifs_sb);
+ /*
+ * Force the use of prefix path to support failover on DFS paths that resolve to targets
+ * that have different prefix paths.
+ */
+ cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH;
+ rc = refresh_tcon(sessions, tcon, true);
+
+ kref_put(&mg->refcount, mount_group_release);
+ return rc;
+}
+
/*
* Refresh all active dfs mounts regardless of whether they are in cache or not.
* (cache can be cleared)
struct cifs_ses *ses;
struct cifs_tcon *tcon, *ntcon;
struct list_head tcons;
- unsigned int xid;
INIT_LIST_HEAD(&tcons);
spin_unlock(&cifs_tcp_ses_lock);
list_for_each_entry_safe(tcon, ntcon, &tcons, ulist) {
- const char *path = tcon->dfs_path + 1;
- struct cache_entry *ce;
- struct dfs_info3_param *refs = NULL;
- int numrefs = 0;
- bool needs_refresh = false;
- int rc = 0;
-
list_del_init(&tcon->ulist);
-
- ses = find_ipc_from_server_path(sessions, path);
- if (IS_ERR(ses))
- goto next_tcon;
-
- down_read(&htable_rw_lock);
- ce = lookup_cache_entry(path);
- needs_refresh = IS_ERR(ce) || cache_entry_expired(ce);
- up_read(&htable_rw_lock);
-
- if (!needs_refresh)
- goto next_tcon;
-
- xid = get_xid();
- rc = get_dfs_referral(xid, ses, path, &refs, &numrefs);
- free_xid(xid);
-
- /* Create or update a cache entry with the new referral */
- if (!rc) {
- down_write(&htable_rw_lock);
- ce = lookup_cache_entry(path);
- if (IS_ERR(ce))
- add_cache_entry_locked(refs, numrefs);
- else if (cache_entry_expired(ce))
- update_cache_entry_locked(ce, refs, numrefs);
- up_write(&htable_rw_lock);
- }
-
-next_tcon:
- free_dfs_info_array(refs, numrefs);
+ refresh_tcon(sessions, tcon, false);
cifs_put_tcon(tcon);
}
}
#include <linux/uuid.h>
#include "cifsglob.h"
+#define DFS_CACHE_TGT_LIST_INIT(var) { .tl_numtgts = 0, .tl_list = LIST_HEAD_INIT((var).tl_list), }
+
struct dfs_cache_tgt_list {
int tl_numtgts;
struct list_head tl_list;
void dfs_cache_put_refsrv_sessions(const uuid_t *mount_id);
void dfs_cache_add_refsrv_session(const uuid_t *mount_id, struct cifs_ses *ses);
char *dfs_cache_canonical_path(const char *path, const struct nls_table *cp, int remap);
+int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb);
static inline struct dfs_cache_tgt_iterator *
dfs_cache_get_next_tgt(struct dfs_cache_tgt_list *tl,
* dns_resolve_server_name_to_ip - Resolve UNC server name to ip address.
* @unc: UNC path specifying the server (with '/' as delimiter)
* @ip_addr: Where to return the IP address.
+ * @expiry: Where to return the expiry time for the dns record.
*
* The IP address will be returned in string form, and the caller is
* responsible for freeing it.
* Returns length of result on success, -ve on error.
*/
int
-dns_resolve_server_name_to_ip(const char *unc, char **ip_addr)
+dns_resolve_server_name_to_ip(const char *unc, char **ip_addr, time64_t *expiry)
{
struct sockaddr_storage ss;
const char *hostname, *sep;
/* Perform the upcall */
rc = dns_query(current->nsproxy->net_ns, NULL, hostname, len,
- NULL, ip_addr, NULL, false);
+ NULL, ip_addr, expiry, false);
if (rc < 0)
cifs_dbg(FYI, "%s: unable to resolve: %*.*s\n",
__func__, len, len, hostname);
else
- cifs_dbg(FYI, "%s: resolved: %*.*s to %s\n",
- __func__, len, len, hostname, *ip_addr);
+ cifs_dbg(FYI, "%s: resolved: %*.*s to %s expiry %llu\n",
+ __func__, len, len, hostname, *ip_addr,
+ expiry ? (*expiry) : 0);
return rc;
name_is_IP_address:
#define _DNS_RESOLVE_H
#ifdef __KERNEL__
-extern int dns_resolve_server_name_to_ip(const char *unc, char **ip_addr);
+extern int dns_resolve_server_name_to_ip(const char *unc, char **ip_addr, time64_t *expiry);
#endif /* KERNEL */
#endif /* _DNS_RESOLVE_H */
static int cifs_readpage(struct file *file, struct page *page)
{
- loff_t offset = (loff_t)page->index << PAGE_SHIFT;
+ loff_t offset = page_file_offset(page);
int rc = -EACCES;
unsigned int xid;
#include <linux/magic.h>
#include <linux/security.h>
#include <net/net_namespace.h>
+#ifdef CONFIG_CIFS_DFS_UPCALL
+#include "dfs_cache.h"
+#endif
*/
#include <linux/ctype.h>
smb3_cleanup_fs_context_contents(cifs_sb->ctx);
rc = smb3_fs_context_dup(cifs_sb->ctx, ctx);
smb3_update_mnt_flags(cifs_sb);
+#ifdef CONFIG_CIFS_DFS_UPCALL
+ if (!rc)
+ rc = dfs_cache_remount_fs(cifs_sb);
+#endif
return rc;
}
ctx->cred_uid = uid;
ctx->cruid_specified = true;
break;
+ case Opt_backupuid:
+ uid = make_kuid(current_user_ns(), result.uint_32);
+ if (!uid_valid(uid))
+ goto cifs_parse_mount_err;
+ ctx->backupuid = uid;
+ ctx->backupuid_specified = true;
+ break;
case Opt_backupgid:
gid = make_kgid(current_user_ns(), result.uint_32);
if (!gid_valid(gid))
cifs_dbg(FYI, "%s: target name: %s\n", __func__, target + 2);
- rc = dns_resolve_server_name_to_ip(target, &tip);
+ rc = dns_resolve_server_name_to_ip(target, &tip, NULL);
if (rc < 0)
goto out;
p = buf;
while (bytes_left >= sizeof(*p)) {
info->speed = le64_to_cpu(p->LinkSpeed);
- info->rdma_capable = le32_to_cpu(p->Capability & RDMA_CAPABLE);
- info->rss_capable = le32_to_cpu(p->Capability & RSS_CAPABLE);
+ info->rdma_capable = le32_to_cpu(p->Capability & RDMA_CAPABLE) ? 1 : 0;
+ info->rss_capable = le32_to_cpu(p->Capability & RSS_CAPABLE) ? 1 : 0;
cifs_dbg(FYI, "%s: adding iface %zu\n", __func__, *iface_count);
cifs_dbg(FYI, "%s: speed %zu bps\n", __func__, info->speed);
/* ipc tcons are not refcounted */
spin_lock(&cifs_tcp_ses_lock);
tcon->tc_count--;
+ /* tc_count can never go negative */
+ WARN_ON(tcon->tc_count < 0);
spin_unlock(&cifs_tcp_ses_lock);
}
kfree(utf16_path);
{
struct cifs_io_parms io_parms = {0};
int nbytes;
+ int rc = 0;
struct kvec iov[2];
io_parms.netfid = cfile->fid.netfid;
io_parms.tcon = tcon;
io_parms.persistent_fid = cfile->fid.persistent_fid;
io_parms.volatile_fid = cfile->fid.volatile_fid;
- io_parms.offset = off;
- io_parms.length = len;
- /* iov[0] is reserved for smb header */
- iov[1].iov_base = buf;
- iov[1].iov_len = io_parms.length;
- return SMB2_write(xid, &io_parms, &nbytes, iov, 1);
+ while (len) {
+ io_parms.offset = off;
+ io_parms.length = len;
+ if (io_parms.length > SMB2_MAX_BUFFER_SIZE)
+ io_parms.length = SMB2_MAX_BUFFER_SIZE;
+ /* iov[0] is reserved for smb header */
+ iov[1].iov_base = buf;
+ iov[1].iov_len = io_parms.length;
+ rc = SMB2_write(xid, &io_parms, &nbytes, iov, 1);
+ if (rc)
+ break;
+ if (nbytes > len)
+ return -EINVAL;
+ buf += nbytes;
+ off += nbytes;
+ len -= nbytes;
+ }
+ return rc;
}
static int smb3_simple_fallocate_range(unsigned int xid,
(char **)&out_data, &out_data_len);
if (rc)
goto out;
- /*
- * It is already all allocated
- */
- if (out_data_len == 0)
- goto out;
buf = kzalloc(1024 * 1024, GFP_KERNEL);
if (buf == NULL) {
goto out;
}
+ if (keep_size == true) {
+ /*
+ * We can not preallocate pages beyond the end of the file
+ * in SMB2
+ */
+ if (off >= i_size_read(inode)) {
+ rc = 0;
+ goto out;
+ }
+ /*
+ * For fallocates that are partially beyond the end of file,
+ * clamp len so we only fallocate up to the end of file.
+ */
+ if (off + len > i_size_read(inode)) {
+ len = i_size_read(inode) - off;
+ }
+ }
+
if ((keep_size == true) || (i_size_read(inode) >= off + len)) {
/*
* At this point, we are trying to fallocate an internal
__u16 Padding;
__u32 Flags;
__le16 CompressionAlgorithms[3];
+ __u16 Pad; /* Some servers require pad to DataLen multiple of 8 */
/* Check if pad needed */
} __packed;
}
pr_debug("%s: count = %zd, pos = %lld, buf = %s\n",
__func__, iov_iter_count(to), iocb->ki_pos, buffer->page);
- retval = copy_to_iter(buffer->page, buffer->count, to);
+ if (iocb->ki_pos >= buffer->count)
+ goto out;
+ retval = copy_to_iter(buffer->page + iocb->ki_pos,
+ buffer->count - iocb->ki_pos, to);
iocb->ki_pos += retval;
if (retval == 0)
retval = -EFAULT;
buffer->needs_read_fill = 0;
}
- retval = copy_to_iter(buffer->bin_buffer, buffer->bin_buffer_size, to);
+ if (iocb->ki_pos >= buffer->bin_buffer_size)
+ goto out;
+ retval = copy_to_iter(buffer->bin_buffer + iocb->ki_pos,
+ buffer->bin_buffer_size - iocb->ki_pos, to);
iocb->ki_pos += retval;
if (retval == 0)
retval = -EFAULT;
return retval;
}
-static int fill_write_buffer(struct configfs_buffer *buffer,
+/* Fill [buffer, buffer + pos) with data coming from @from. */
+static int fill_write_buffer(struct configfs_buffer *buffer, loff_t pos,
struct iov_iter *from)
{
+ loff_t to_copy;
int copied;
+ u8 *to;
if (!buffer->page)
buffer->page = (char *)__get_free_pages(GFP_KERNEL, 0);
if (!buffer->page)
return -ENOMEM;
- copied = copy_from_iter(buffer->page, SIMPLE_ATTR_SIZE - 1, from);
+ to_copy = SIMPLE_ATTR_SIZE - 1 - pos;
+ if (to_copy <= 0)
+ return 0;
+ to = buffer->page + pos;
+ copied = copy_from_iter(to, to_copy, from);
buffer->needs_read_fill = 1;
/* if buf is assumed to contain a string, terminate it by \0,
* so e.g. sscanf() can scan the string easily */
- buffer->page[copied] = 0;
+ to[copied] = 0;
return copied ? : -EFAULT;
}
ssize_t len;
mutex_lock(&buffer->mutex);
- len = fill_write_buffer(buffer, from);
+ len = fill_write_buffer(buffer, iocb->ki_pos, from);
if (len > 0)
len = flush_write_buffer(file, buffer, len);
if (len > 0)
buffer->bin_buffer_size = end_offset;
}
- len = copy_from_iter(buffer->bin_buffer, buffer->bin_buffer_size, from);
+ len = copy_from_iter(buffer->bin_buffer + iocb->ki_pos,
+ buffer->bin_buffer_size - iocb->ki_pos, from);
+ iocb->ki_pos += len;
out:
mutex_unlock(&buffer->mutex);
return len ? : -EFAULT;
return err;
}
-static bool ext2_check_page(struct page *page, int quiet)
+static bool ext2_check_page(struct page *page, int quiet, char *kaddr)
{
struct inode *dir = page->mapping->host;
struct super_block *sb = dir->i_sb;
unsigned chunk_size = ext2_chunk_size(dir);
- char *kaddr = page_address(page);
u32 max_inumber = le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count);
unsigned offs, rec_len;
unsigned limit = PAGE_SIZE;
if (!IS_ERR(page)) {
*page_addr = kmap_local_page(page);
if (unlikely(!PageChecked(page))) {
- if (PageError(page) || !ext2_check_page(page, quiet))
+ if (PageError(page) || !ext2_check_page(page, quiet,
+ *page_addr))
goto fail;
}
}
* ext2_delete_entry deletes a directory entry by merging it with the
* previous entry. Page is up-to-date.
*/
-int ext2_delete_entry (struct ext2_dir_entry_2 * dir, struct page * page )
+int ext2_delete_entry (struct ext2_dir_entry_2 *dir, struct page *page,
+ char *kaddr)
{
struct inode *inode = page->mapping->host;
- char *kaddr = page_address(page);
unsigned from = ((char*)dir - kaddr) & ~(ext2_chunk_size(inode)-1);
unsigned to = ((char *)dir - kaddr) +
ext2_rec_len_from_disk(dir->rec_len);
de = ext2_next_entry(de);
}
if (pde)
- from = (char*)pde - (char*)page_address(page);
+ from = (char *)pde - kaddr;
pos = page_offset(page) + from;
lock_page(page);
err = ext2_prepare_chunk(page, pos, to - from);
extern int ext2_make_empty(struct inode *, struct inode *);
extern struct ext2_dir_entry_2 *ext2_find_entry(struct inode *, const struct qstr *,
struct page **, void **res_page_addr);
-extern int ext2_delete_entry (struct ext2_dir_entry_2 *, struct page *);
+extern int ext2_delete_entry(struct ext2_dir_entry_2 *dir, struct page *page,
+ char *kaddr);
extern int ext2_empty_dir (struct inode *);
extern struct ext2_dir_entry_2 *ext2_dotdot(struct inode *dir, struct page **p, void **pa);
extern void ext2_set_link(struct inode *, struct ext2_dir_entry_2 *, struct page *, void *,
goto out;
}
- err = ext2_delete_entry (de, page);
+ err = ext2_delete_entry (de, page, page_addr);
ext2_put_page(page, page_addr);
if (err)
goto out;
old_inode->i_ctime = current_time(old_inode);
mark_inode_dirty(old_inode);
- ext2_delete_entry(old_de, old_page);
+ ext2_delete_entry(old_de, old_page, old_page_addr);
if (dir_de) {
if (old_dir != new_dir)
* "bh" may be NULL: a metadata block may have been freed from memory
* but there may still be a record of it in the journal, and that record
* still needs to be revoked.
- *
- * If the handle isn't valid we're not journaling, but we still need to
- * call into ext4_journal_revoke() to put the buffer head.
*/
int __ext4_forget(const char *where, unsigned int line, handle_t *handle,
int is_metadata, struct inode *inode,
unsigned mmp_check_interval;
unsigned long last_update_time;
unsigned long diff;
- int retval;
+ int retval = 0;
mmp_block = le64_to_cpu(es->s_mmp_block);
mmp = (struct mmp_struct *)(bh->b_data);
goto journal_error;
err = ext4_handle_dirty_dx_node(handle, dir,
frame->bh);
- if (err)
+ if (restart || err)
goto journal_error;
} else {
struct dx_root *dxroot;
/* 32-bit arches must use fcntl64() */
case F_OFD_SETLK:
case F_OFD_SETLKW:
-#endif
fallthrough;
+#endif
case F_SETLK:
case F_SETLKW:
if (copy_from_user(&flock, argp, sizeof(flock)))
*/
smp_mb();
+ if (IS_DAX(inode))
+ return false;
+
/* while holding I_WB_SWITCH, no one else can update the association */
spin_lock(&inode->i_lock);
if (!(inode->i_sb->s_flags & SB_ACTIVE) ||
}
/**
+ * vfs_parse_fs_param_source - Handle setting "source" via parameter
+ * @fc: The filesystem context to modify
+ * @param: The parameter
+ *
+ * This is a simple helper for filesystems to verify that the "source" they
+ * accept is sane.
+ *
+ * Returns 0 on success, -ENOPARAM if this is not "source" parameter, and
+ * -EINVAL otherwise. In the event of failure, supplementary error information
+ * is logged.
+ */
+int vfs_parse_fs_param_source(struct fs_context *fc, struct fs_parameter *param)
+{
+ if (strcmp(param->key, "source") != 0)
+ return -ENOPARAM;
+
+ if (param->type != fs_value_is_string)
+ return invalf(fc, "Non-string source");
+
+ if (fc->source)
+ return invalf(fc, "Multiple sources");
+
+ fc->source = param->string;
+ param->string = NULL;
+ return 0;
+}
+EXPORT_SYMBOL(vfs_parse_fs_param_source);
+
+/**
* vfs_parse_fs_param - Add a single parameter to a superblock config
* @fc: The filesystem context to modify
* @param: The parameter
/* If the filesystem doesn't take any arguments, give it the
* default handling of source.
*/
- if (strcmp(param->key, "source") == 0) {
- if (param->type != fs_value_is_string)
- return invalf(fc, "VFS: Non-string source");
- if (fc->source)
- return invalf(fc, "VFS: Multiple sources");
- fc->source = param->string;
- param->string = NULL;
- return 0;
- }
+ ret = vfs_parse_fs_param_source(fc, param);
+ if (ret != -ENOPARAM)
+ return ret;
return invalf(fc, "%s: Unknown parameter '%s'",
fc->fs_type->name, param->key);
struct legacy_fs_context *ctx = fc->fs_private;
unsigned int size = ctx->data_size;
size_t len = 0;
+ int ret;
- if (strcmp(param->key, "source") == 0) {
- if (param->type != fs_value_is_string)
- return invalf(fc, "VFS: Legacy: Non-string source");
- if (fc->source)
- return invalf(fc, "VFS: Legacy: Multiple sources");
- fc->source = param->string;
- param->string = NULL;
- return 0;
- }
+ ret = vfs_parse_fs_param_source(fc, param);
+ if (ret != -ENOPARAM)
+ return ret;
if (ctx->param_type == LEGACY_FS_MONOLITHIC_PARAMS)
return invalf(fc, "VFS: Legacy: Can't mix monolithic and individual options");
fd->key = ptr + tree->max_key_len + 2;
hfs_dbg(BNODE_REFS, "find_init: %d (%p)\n",
tree->cnid, __builtin_return_address(0));
- mutex_lock(&tree->tree_lock);
+ switch (tree->cnid) {
+ case HFS_CAT_CNID:
+ mutex_lock_nested(&tree->tree_lock, CATALOG_BTREE_MUTEX);
+ break;
+ case HFS_EXT_CNID:
+ mutex_lock_nested(&tree->tree_lock, EXTENTS_BTREE_MUTEX);
+ break;
+ case HFS_ATTR_CNID:
+ mutex_lock_nested(&tree->tree_lock, ATTR_BTREE_MUTEX);
+ break;
+ default:
+ return -EINVAL;
+ }
return 0;
}
#include "btree.h"
-void hfs_bnode_read(struct hfs_bnode *node, void *buf,
- int off, int len)
+void hfs_bnode_read(struct hfs_bnode *node, void *buf, int off, int len)
{
struct page *page;
+ int pagenum;
+ int bytes_read;
+ int bytes_to_read;
+ void *vaddr;
off += node->page_offset;
- page = node->page[0];
+ pagenum = off >> PAGE_SHIFT;
+ off &= ~PAGE_MASK; /* compute page offset for the first page */
- memcpy(buf, kmap(page) + off, len);
- kunmap(page);
+ for (bytes_read = 0; bytes_read < len; bytes_read += bytes_to_read) {
+ if (pagenum >= node->tree->pages_per_bnode)
+ break;
+ page = node->page[pagenum];
+ bytes_to_read = min_t(int, len - bytes_read, PAGE_SIZE - off);
+
+ vaddr = kmap_atomic(page);
+ memcpy(buf + bytes_read, vaddr + off, bytes_to_read);
+ kunmap_atomic(vaddr);
+
+ pagenum++;
+ off = 0; /* page offset only applies to the first page */
+ }
}
u16 hfs_bnode_read_u16(struct hfs_bnode *node, int off)
#define NODE_HASH_SIZE 256
+/* B-tree mutex nested subclasses */
+enum hfs_btree_mutex_classes {
+ CATALOG_BTREE_MUTEX,
+ EXTENTS_BTREE_MUTEX,
+ ATTR_BTREE_MUTEX,
+};
+
/* A HFS BTree held in memory */
struct hfs_btree {
struct super_block *sb;
if (!res) {
if (fd.entrylength > sizeof(rec) || fd.entrylength < 0) {
res = -EIO;
- goto bail;
+ goto bail_hfs_find;
}
hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, fd.entrylength);
}
- if (res) {
- hfs_find_exit(&fd);
- goto bail_no_root;
- }
+ if (res)
+ goto bail_hfs_find;
res = -EINVAL;
root_inode = hfs_iget(sb, &fd.search_key->cat, &rec);
hfs_find_exit(&fd);
/* everything's okay */
return 0;
+bail_hfs_find:
+ hfs_find_exit(&fd);
bail_no_root:
pr_err("get root inode failed\n");
bail:
static const struct fs_parameter_spec hugetlb_fs_parameters[] = {
fsparam_u32 ("gid", Opt_gid),
fsparam_string("min_size", Opt_min_size),
- fsparam_u32 ("mode", Opt_mode),
+ fsparam_u32oct("mode", Opt_mode),
fsparam_string("nr_inodes", Opt_nr_inodes),
fsparam_string("pagesize", Opt_pagesize),
fsparam_string("size", Opt_size),
*/
extern const struct fs_context_operations legacy_fs_context_ops;
extern int parse_monolithic_mount_data(struct fs_context *, void *);
-extern void fc_drop_locked(struct fs_context *);
extern void vfs_clean_context(struct fs_context *fc);
extern int finish_clean_context(struct fs_context *fc);
};
static void create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index);
+static void io_wqe_dec_running(struct io_worker *worker);
static bool io_worker_get(struct io_worker *worker)
{
{
struct io_wqe *wqe = worker->wqe;
struct io_wqe_acct *acct = io_wqe_get_acct(worker);
- unsigned flags;
if (refcount_dec_and_test(&worker->ref))
complete(&worker->ref_done);
wait_for_completion(&worker->ref_done);
- preempt_disable();
- current->flags &= ~PF_IO_WORKER;
- flags = worker->flags;
- worker->flags = 0;
- if (flags & IO_WORKER_F_RUNNING)
- atomic_dec(&acct->nr_running);
- worker->flags = 0;
- preempt_enable();
-
raw_spin_lock_irq(&wqe->lock);
- if (flags & IO_WORKER_F_FREE)
+ if (worker->flags & IO_WORKER_F_FREE)
hlist_nulls_del_rcu(&worker->nulls_node);
list_del_rcu(&worker->all_list);
acct->nr_workers--;
+ preempt_disable();
+ io_wqe_dec_running(worker);
+ worker->flags = 0;
+ current->flags &= ~PF_IO_WORKER;
+ preempt_enable();
raw_spin_unlock_irq(&wqe->lock);
kfree_rcu(worker, rcu);
struct hlist_nulls_node *n;
struct io_worker *worker;
- n = rcu_dereference(hlist_nulls_first_rcu(&wqe->free_list));
- if (is_a_nulls(n))
- return false;
-
- worker = hlist_nulls_entry(n, struct io_worker, nulls_node);
- if (io_worker_get(worker)) {
- wake_up_process(worker->task);
+ /*
+ * Iterate free_list and see if we can find an idle worker to
+ * activate. If a given worker is on the free_list but in the process
+ * of exiting, keep trying.
+ */
+ hlist_nulls_for_each_entry_rcu(worker, n, &wqe->free_list, nulls_node) {
+ if (!io_worker_get(worker))
+ continue;
+ if (wake_up_process(worker->task)) {
+ io_worker_release(worker);
+ return true;
+ }
io_worker_release(worker);
- return true;
}
return false;
ret = io_wqe_activate_free_worker(wqe);
rcu_read_unlock();
- if (!ret && acct->nr_workers < acct->max_workers) {
- atomic_inc(&acct->nr_running);
- atomic_inc(&wqe->wq->worker_refs);
- create_io_worker(wqe->wq, wqe, acct->index);
+ if (!ret) {
+ bool do_create = false;
+
+ raw_spin_lock_irq(&wqe->lock);
+ if (acct->nr_workers < acct->max_workers) {
+ atomic_inc(&acct->nr_running);
+ atomic_inc(&wqe->wq->worker_refs);
+ acct->nr_workers++;
+ do_create = true;
+ }
+ raw_spin_unlock_irq(&wqe->lock);
+ if (do_create)
+ create_io_worker(wqe->wq, wqe, acct->index);
}
}
{
struct create_worker_data *cwd;
struct io_wq *wq;
+ struct io_wqe *wqe;
+ struct io_wqe_acct *acct;
cwd = container_of(cb, struct create_worker_data, work);
- wq = cwd->wqe->wq;
+ wqe = cwd->wqe;
+ wq = wqe->wq;
+ acct = &wqe->acct[cwd->index];
+ raw_spin_lock_irq(&wqe->lock);
+ if (acct->nr_workers < acct->max_workers)
+ acct->nr_workers++;
+ raw_spin_unlock_irq(&wqe->lock);
create_io_worker(wq, cwd->wqe, cwd->index);
kfree(cwd);
}
kfree(worker);
fail:
atomic_dec(&acct->nr_running);
+ raw_spin_lock_irq(&wqe->lock);
+ acct->nr_workers--;
+ raw_spin_unlock_irq(&wqe->lock);
io_worker_ref_put(wq);
return;
}
worker->flags |= IO_WORKER_F_FREE;
if (index == IO_WQ_ACCT_BOUND)
worker->flags |= IO_WORKER_F_BOUND;
- if (!acct->nr_workers && (worker->flags & IO_WORKER_F_BOUND))
+ if ((acct->nr_workers == 1) && (worker->flags & IO_WORKER_F_BOUND))
worker->flags |= IO_WORKER_F_FIXED;
- acct->nr_workers++;
raw_spin_unlock_irq(&wqe->lock);
wake_up_new_task(tsk);
}
int work_flags;
unsigned long flags;
- if (test_bit(IO_WQ_BIT_EXIT, &wqe->wq->state)) {
+ /*
+ * If io-wq is exiting for this task, or if the request has explicitly
+ * been marked as one that should not get executed, cancel it here.
+ */
+ if (test_bit(IO_WQ_BIT_EXIT, &wqe->wq->state) ||
+ (work->flags & IO_WQ_WORK_CANCEL)) {
io_run_cancel(work, wqe);
return;
}
{
struct io_kiocb *cur;
- io_for_each_link(cur, req)
- io_prep_async_work(cur);
+ if (req->flags & REQ_F_LINK_TIMEOUT) {
+ struct io_ring_ctx *ctx = req->ctx;
+
+ spin_lock_irq(&ctx->completion_lock);
+ io_for_each_link(cur, req)
+ io_prep_async_work(cur);
+ spin_unlock_irq(&ctx->completion_lock);
+ } else {
+ io_for_each_link(cur, req)
+ io_prep_async_work(cur);
+ }
}
static void io_queue_async_work(struct io_kiocb *req)
/* init ->work of the whole link before punting */
io_prep_async_link(req);
+
+ /*
+ * Not expected to happen, but if we do have a bug where this _can_
+ * happen, catch it here and ensure the request is marked as
+ * canceled. That will make io-wq go through the usual work cancel
+ * procedure rather than attempt to run this request (or create a new
+ * worker for it).
+ */
+ if (WARN_ON_ONCE(!same_thread_group(req->task, current)))
+ req->work.flags |= IO_WQ_WORK_CANCEL;
+
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);
node = next;
}
if (wq_list_empty(&tctx->task_list)) {
+ spin_lock_irq(&tctx->task_lock);
clear_bit(0, &tctx->task_state);
- if (wq_list_empty(&tctx->task_list))
+ if (wq_list_empty(&tctx->task_list)) {
+ spin_unlock_irq(&tctx->task_lock);
break;
+ }
+ spin_unlock_irq(&tctx->task_lock);
/* another tctx_task_work() is enqueued, yield */
if (test_and_set_bit(0, &tctx->task_state))
break;
/* ctx stays valid until unlock, even if we drop all ours ctx->refs */
mutex_lock(&ctx->uring_lock);
- if (!(current->flags & PF_EXITING) && !current->in_execve)
+ if (!(req->task->flags & PF_EXITING) && !req->task->in_execve)
__io_queue_sqe(req);
else
io_req_complete_failed(req, -EFAULT);
io_req_task_work_add(req);
}
+static void io_req_task_queue_reissue(struct io_kiocb *req)
+{
+ req->io_task_work.func = io_queue_async_work;
+ io_req_task_work_add(req);
+}
+
static inline void io_queue_next(struct io_kiocb *req)
{
struct io_kiocb *nxt = io_req_find_next(req);
* Find and free completed poll iocbs
*/
static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
- struct list_head *done)
+ struct list_head *done, bool resubmit)
{
struct req_batch rb;
struct io_kiocb *req;
req = list_first_entry(done, struct io_kiocb, inflight_entry);
list_del(&req->inflight_entry);
- if (READ_ONCE(req->result) == -EAGAIN &&
+ if (READ_ONCE(req->result) == -EAGAIN && resubmit &&
!(req->flags & REQ_F_DONT_REISSUE)) {
req->iopoll_completed = 0;
req_ref_get(req);
- io_queue_async_work(req);
+ io_req_task_queue_reissue(req);
continue;
}
}
static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
- long min)
+ long min, bool resubmit)
{
struct io_kiocb *req, *tmp;
LIST_HEAD(done);
}
if (!list_empty(&done))
- io_iopoll_complete(ctx, nr_events, &done);
+ io_iopoll_complete(ctx, nr_events, &done, resubmit);
return ret;
}
while (!list_empty(&ctx->iopoll_list)) {
unsigned int nr_events = 0;
- io_do_iopoll(ctx, &nr_events, 0);
+ io_do_iopoll(ctx, &nr_events, 0, false);
/* let it sleep and repeat later if can't complete a request */
if (nr_events == 0)
list_empty(&ctx->iopoll_list))
break;
}
- ret = io_do_iopoll(ctx, &nr_events, min);
+ ret = io_do_iopoll(ctx, &nr_events, min, true);
} while (!ret && nr_events < min && !need_resched());
out:
mutex_unlock(&ctx->uring_lock);
*/
if (percpu_ref_is_dying(&ctx->refs))
return false;
+ /*
+ * Play it safe and assume not safe to re-import and reissue if we're
+ * not in the original thread group (or in task context).
+ */
+ if (!same_thread_group(req->task, current) || !in_task())
+ return false;
return true;
}
#else
req->flags &= ~REQ_F_REISSUE;
if (io_resubmit_prep(req)) {
req_ref_get(req);
- io_queue_async_work(req);
+ io_req_task_queue_reissue(req);
} else {
int cflags = 0;
struct io_poll_table {
struct poll_table_struct pt;
struct io_kiocb *req;
+ int nr_entries;
int error;
};
if (req->poll.events & EPOLLONESHOT)
flags = 0;
if (!io_cqring_fill_event(ctx, req->user_data, error, flags)) {
- io_poll_remove_waitqs(req);
req->poll.done = true;
flags = 0;
}
done = io_poll_complete(req, req->result);
if (done) {
+ io_poll_remove_double(req);
hash_del(&req->hash_node);
} else {
req->result = 0;
struct io_kiocb *req = pt->req;
/*
- * If poll->head is already set, it's because the file being polled
- * uses multiple waitqueues for poll handling (eg one for read, one
- * for write). Setup a separate io_poll_iocb if this happens.
+ * The file being polled uses multiple waitqueues for poll handling
+ * (e.g. one for read, one for write). Setup a separate io_poll_iocb
+ * if this happens.
*/
- if (unlikely(poll->head)) {
+ if (unlikely(pt->nr_entries)) {
struct io_poll_iocb *poll_one = poll;
/* already have a 2nd entry, fail a third attempt */
*poll_ptr = poll;
}
- pt->error = 0;
+ pt->nr_entries++;
poll->head = head;
if (poll->events & EPOLLEXCLUSIVE)
ipt->pt._key = mask;
ipt->req = req;
- ipt->error = -EINVAL;
+ ipt->error = 0;
+ ipt->nr_entries = 0;
mask = vfs_poll(req->file, &ipt->pt) & poll->events;
+ if (unlikely(!ipt->nr_entries) && !ipt->error)
+ ipt->error = -EINVAL;
spin_lock_irq(&ctx->completion_lock);
+ if (ipt->error || (mask && (poll->events & EPOLLONESHOT)))
+ io_poll_remove_double(req);
if (likely(poll->head)) {
spin_lock(&poll->head->lock);
if (unlikely(list_empty(&poll->wait.entry))) {
ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask,
io_async_wake);
if (ret || ipt.error) {
- io_poll_remove_double(req);
spin_unlock_irq(&ctx->completion_lock);
if (ret)
return IO_APOLL_READY;
ret = io_req_prep_async(req);
if (ret)
- return ret;
+ goto fail;
io_prep_async_link(req);
de = kmalloc(sizeof(*de), GFP_KERNEL);
if (!de) {
- io_req_complete_failed(req, -ENOMEM);
+ ret = -ENOMEM;
+fail:
+ io_req_complete_failed(req, ret);
return true;
}
mutex_lock(&ctx->uring_lock);
if (!list_empty(&ctx->iopoll_list))
- io_do_iopoll(ctx, &nr_events, 0);
+ io_do_iopoll(ctx, &nr_events, 0, true);
/*
* Don't submit if refs are dying, good for io_uring_register(),
struct io_wq_data data;
unsigned int concurrency;
+ mutex_lock(&ctx->uring_lock);
hash = ctx->hash_map;
if (!hash) {
hash = kzalloc(sizeof(*hash), GFP_KERNEL);
- if (!hash)
+ if (!hash) {
+ mutex_unlock(&ctx->uring_lock);
return ERR_PTR(-ENOMEM);
+ }
refcount_set(&hash->refs, 1);
init_waitqueue_head(&hash->wait);
ctx->hash_map = hash;
}
+ mutex_unlock(&ctx->uring_lock);
data.hash = hash;
data.task = task;
f = fdget(p->wq_fd);
if (!f.file)
return -ENXIO;
- fdput(f);
- if (f.file->f_op != &io_uring_fops)
+ if (f.file->f_op != &io_uring_fops) {
+ fdput(f);
return -EINVAL;
+ }
+ fdput(f);
}
if (ctx->flags & IORING_SETUP_SQPOLL) {
struct task_struct *tsk;
if (PageUptodate(page))
return;
+ BUG_ON(page_has_private(page));
BUG_ON(page->index);
BUG_ON(size > PAGE_SIZE - offset_in_page(iomap->inline_data));
{
struct iomap_readpage_ctx *ctx = data;
struct page *page = ctx->cur_page;
- struct iomap_page *iop = iomap_page_create(inode, page);
+ struct iomap_page *iop;
bool same_page = false, is_contig = false;
loff_t orig_pos = pos;
unsigned poff, plen;
}
/* zero post-eof blocks as the page may be mapped */
+ iop = iomap_page_create(inode, page);
iomap_adjust_read_range(inode, iop, &pos, length, &poff, &plen);
if (plen == 0)
goto done;
block_commit_write(page, 0, length);
} else {
WARN_ON_ONCE(!PageUptodate(page));
- iomap_page_create(inode, page);
set_page_dirty(page);
}
struct writeback_control *wbc, struct inode *inode,
struct page *page, u64 end_offset)
{
- struct iomap_page *iop = to_iomap_page(page);
+ struct iomap_page *iop = iomap_page_create(inode, page);
struct iomap_ioend *ioend, *next;
unsigned len = i_blocksize(inode);
u64 file_offset; /* file offset of page */
int error = 0, count = 0, i;
LIST_HEAD(submit_list);
- WARN_ON_ONCE(i_blocks_per_page(inode, page) > 1 && !iop);
WARN_ON_ONCE(iop && atomic_read(&iop->write_bytes_pending) != 0);
/*
iomap_seek_hole(struct inode *inode, loff_t offset, const struct iomap_ops *ops)
{
loff_t size = i_size_read(inode);
- loff_t length = size - offset;
loff_t ret;
/* Nothing to be found before or beyond the end of the file. */
if (offset < 0 || offset >= size)
return -ENXIO;
- while (length > 0) {
- ret = iomap_apply(inode, offset, length, IOMAP_REPORT, ops,
- &offset, iomap_seek_hole_actor);
+ while (offset < size) {
+ ret = iomap_apply(inode, offset, size - offset, IOMAP_REPORT,
+ ops, &offset, iomap_seek_hole_actor);
if (ret < 0)
return ret;
if (ret == 0)
break;
-
offset += ret;
- length -= ret;
}
return offset;
iomap_seek_data(struct inode *inode, loff_t offset, const struct iomap_ops *ops)
{
loff_t size = i_size_read(inode);
- loff_t length = size - offset;
loff_t ret;
/* Nothing to be found before or beyond the end of the file. */
if (offset < 0 || offset >= size)
return -ENXIO;
- while (length > 0) {
- ret = iomap_apply(inode, offset, length, IOMAP_REPORT, ops,
- &offset, iomap_seek_data_actor);
+ while (offset < size) {
+ ret = iomap_apply(inode, offset, size - offset, IOMAP_REPORT,
+ ops, &offset, iomap_seek_data_actor);
if (ret < 0)
return ret;
if (ret == 0)
- break;
-
+ return offset;
offset += ret;
- length -= ret;
}
- if (length <= 0)
- return -ENXIO;
- return offset;
+ /* We've reached the end of the file without finding data */
+ return -ENXIO;
}
EXPORT_SYMBOL_GPL(iomap_seek_data);
}
}
+/*
+ * zero out partial blocks of one cluster.
+ *
+ * start: file offset where zero starts, will be made upper block aligned.
+ * len: it will be trimmed to the end of current cluster if "start + len"
+ * is bigger than it.
+ */
+static int ocfs2_zeroout_partial_cluster(struct inode *inode,
+ u64 start, u64 len)
+{
+ int ret;
+ u64 start_block, end_block, nr_blocks;
+ u64 p_block, offset;
+ u32 cluster, p_cluster, nr_clusters;
+ struct super_block *sb = inode->i_sb;
+ u64 end = ocfs2_align_bytes_to_clusters(sb, start);
+
+ if (start + len < end)
+ end = start + len;
+
+ start_block = ocfs2_blocks_for_bytes(sb, start);
+ end_block = ocfs2_blocks_for_bytes(sb, end);
+ nr_blocks = end_block - start_block;
+ if (!nr_blocks)
+ return 0;
+
+ cluster = ocfs2_bytes_to_clusters(sb, start);
+ ret = ocfs2_get_clusters(inode, cluster, &p_cluster,
+ &nr_clusters, NULL);
+ if (ret)
+ return ret;
+ if (!p_cluster)
+ return 0;
+
+ offset = start_block - ocfs2_clusters_to_blocks(sb, cluster);
+ p_block = ocfs2_clusters_to_blocks(sb, p_cluster) + offset;
+ return sb_issue_zeroout(sb, p_block, nr_blocks, GFP_NOFS);
+}
+
static int ocfs2_zero_partial_clusters(struct inode *inode,
u64 start, u64 len)
{
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
unsigned int csize = osb->s_clustersize;
handle_t *handle;
+ loff_t isize = i_size_read(inode);
/*
* The "start" and "end" values are NOT necessarily part of
if ((start & (csize - 1)) == 0 && (end & (csize - 1)) == 0)
goto out;
+ /* No page cache for EOF blocks, issue zero out to disk. */
+ if (end > isize) {
+ /*
+ * zeroout eof blocks in last cluster starting from
+ * "isize" even "start" > "isize" because it is
+ * complicated to zeroout just at "start" as "start"
+ * may be not aligned with block size, buffer write
+ * would be required to do that, but out of eof buffer
+ * write is not supported.
+ */
+ ret = ocfs2_zeroout_partial_cluster(inode, isize,
+ end - isize);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+ if (start >= isize)
+ goto out;
+ end = isize;
+ }
handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
}
/*
- * zero out partial blocks of one cluster.
- *
- * start: file offset where zero starts, will be made upper block aligned.
- * len: it will be trimmed to the end of current cluster if "start + len"
- * is bigger than it.
- */
-static int ocfs2_zeroout_partial_cluster(struct inode *inode,
- u64 start, u64 len)
-{
- int ret;
- u64 start_block, end_block, nr_blocks;
- u64 p_block, offset;
- u32 cluster, p_cluster, nr_clusters;
- struct super_block *sb = inode->i_sb;
- u64 end = ocfs2_align_bytes_to_clusters(sb, start);
-
- if (start + len < end)
- end = start + len;
-
- start_block = ocfs2_blocks_for_bytes(sb, start);
- end_block = ocfs2_blocks_for_bytes(sb, end);
- nr_blocks = end_block - start_block;
- if (!nr_blocks)
- return 0;
-
- cluster = ocfs2_bytes_to_clusters(sb, start);
- ret = ocfs2_get_clusters(inode, cluster, &p_cluster,
- &nr_clusters, NULL);
- if (ret)
- return ret;
- if (!p_cluster)
- return 0;
-
- offset = start_block - ocfs2_clusters_to_blocks(sb, cluster);
- p_block = ocfs2_clusters_to_blocks(sb, p_cluster) + offset;
- return sb_issue_zeroout(sb, p_block, nr_blocks, GFP_NOFS);
-}
-
-/*
* Parts of this function taken from xfs_change_file_space()
*/
static int __ocfs2_change_file_space(struct file *file, struct inode *inode,
goto out_inode_unlock;
}
- orig_isize = i_size_read(inode);
switch (sr->l_whence) {
case 0: /*SEEK_SET*/
break;
sr->l_start += f_pos;
break;
case 2: /*SEEK_END*/
- sr->l_start += orig_isize;
+ sr->l_start += i_size_read(inode);
break;
default:
ret = -EINVAL;
ret = -EINVAL;
}
+ orig_isize = i_size_read(inode);
/* zeroout eof blocks in the cluster. */
if (!ret && change_size && orig_isize < size) {
ret = ocfs2_zeroout_partial_cluster(inode, orig_isize,
#include "internal.h"
/*
+ * New pipe buffers will be restricted to this size while the user is exceeding
+ * their pipe buffer quota. The general pipe use case needs at least two
+ * buffers: one for data yet to be read, and one for new data. If this is less
+ * than two, then a write to a non-empty pipe may block even if the pipe is not
+ * full. This can occur with GNU make jobserver or similar uses of pipes as
+ * semaphores: multiple processes may be waiting to write tokens back to the
+ * pipe before reading tokens: https://lore.kernel.org/lkml/1628086770.5rn8p04n6j.none@localhost/.
+ *
+ * Users can reduce their pipe buffers with F_SETPIPE_SZ below this at their
+ * own risk, namely: pipe writes to non-full pipes may block until the pipe is
+ * emptied.
+ */
+#define PIPE_MIN_DEF_BUFFERS 2
+
+/*
* The max size that a non-root user is allowed to grow the pipe. Can
* be set by root in /proc/sys/fs/pipe-max-size
*/
#endif
/*
- * Only wake up if the pipe started out empty, since
- * otherwise there should be no readers waiting.
+ * Epoll nonsensically wants a wakeup whether the pipe
+ * was already empty or not.
*
* If it wasn't empty we try to merge new data into
* the last buffer.
*
* That naturally merges small writes, but it also
- * page-aligs the rest of the writes for large writes
+ * page-aligns the rest of the writes for large writes
* spanning multiple pages.
*/
head = pipe->head;
- was_empty = pipe_empty(head, pipe->tail);
+ was_empty = true;
chars = total_len & (PAGE_SIZE-1);
- if (chars && !was_empty) {
+ if (chars && !pipe_empty(head, pipe->tail)) {
unsigned int mask = pipe->ring_size - 1;
struct pipe_buffer *buf = &pipe->bufs[(head - 1) & mask];
int offset = buf->offset + buf->len;
user_bufs = account_pipe_buffers(user, 0, pipe_bufs);
if (too_many_pipe_buffers_soft(user_bufs) && pipe_is_unprivileged_user()) {
- user_bufs = account_pipe_buffers(user, pipe_bufs, 1);
- pipe_bufs = 1;
+ user_bufs = account_pipe_buffers(user, pipe_bufs, PIPE_MIN_DEF_BUFFERS);
+ pipe_bufs = PIPE_MIN_DEF_BUFFERS;
}
if (too_many_pipe_buffers_hard(user_bufs) && pipe_is_unprivileged_user())
search_path->path_length = ILLEGAL_PATH_ELEMENT_OFFSET;
}
+static int has_valid_deh_location(struct buffer_head *bh, struct item_head *ih)
+{
+ struct reiserfs_de_head *deh;
+ int i;
+
+ deh = B_I_DEH(bh, ih);
+ for (i = 0; i < ih_entry_count(ih); i++) {
+ if (deh_location(&deh[i]) > ih_item_len(ih)) {
+ reiserfs_warning(NULL, "reiserfs-5094",
+ "directory entry location seems wrong %h",
+ &deh[i]);
+ return 0;
+ }
+ }
+
+ return 1;
+}
+
static int is_leaf(char *buf, int blocksize, struct buffer_head *bh)
{
struct block_head *blkh;
"(second one): %h", ih);
return 0;
}
- if (is_direntry_le_ih(ih) && (ih_item_len(ih) < (ih_entry_count(ih) * IH_SIZE))) {
- reiserfs_warning(NULL, "reiserfs-5093",
- "item entry count seems wrong %h",
- ih);
- return 0;
+ if (is_direntry_le_ih(ih)) {
+ if (ih_item_len(ih) < (ih_entry_count(ih) * IH_SIZE)) {
+ reiserfs_warning(NULL, "reiserfs-5093",
+ "item entry count seems wrong %h",
+ ih);
+ return 0;
+ }
+ return has_valid_deh_location(bh, ih);
}
prev_location = ih_location(ih);
}
unlock_new_inode(root_inode);
}
+ if (!S_ISDIR(root_inode->i_mode) || !inode_get_bytes(root_inode) ||
+ !root_inode->i_size) {
+ SWARN(silent, s, "", "corrupt root inode, run fsck");
+ iput(root_inode);
+ errval = -EUCLEAN;
+ goto error;
+ }
+
s->s_root = d_make_root(root_inode);
if (!s->s_root)
goto error;
static void *seq_buf_alloc(unsigned long size)
{
+ if (unlikely(size > MAX_RW_COUNT))
+ return NULL;
+
return kvmalloc(size, GFP_KERNEL_ACCOUNT);
}
}
static __always_inline int validate_range(struct mm_struct *mm,
- __u64 *start, __u64 len)
+ __u64 start, __u64 len)
{
__u64 task_size = mm->task_size;
- *start = untagged_addr(*start);
-
- if (*start & ~PAGE_MASK)
+ if (start & ~PAGE_MASK)
return -EINVAL;
if (len & ~PAGE_MASK)
return -EINVAL;
if (!len)
return -EINVAL;
- if (*start < mmap_min_addr)
+ if (start < mmap_min_addr)
return -EINVAL;
- if (*start >= task_size)
+ if (start >= task_size)
return -EINVAL;
- if (len > task_size - *start)
+ if (len > task_size - start)
return -EINVAL;
return 0;
}
vm_flags |= VM_UFFD_MINOR;
}
- ret = validate_range(mm, &uffdio_register.range.start,
+ ret = validate_range(mm, uffdio_register.range.start,
uffdio_register.range.len);
if (ret)
goto out;
if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister)))
goto out;
- ret = validate_range(mm, &uffdio_unregister.start,
+ ret = validate_range(mm, uffdio_unregister.start,
uffdio_unregister.len);
if (ret)
goto out;
if (copy_from_user(&uffdio_wake, buf, sizeof(uffdio_wake)))
goto out;
- ret = validate_range(ctx->mm, &uffdio_wake.start, uffdio_wake.len);
+ ret = validate_range(ctx->mm, uffdio_wake.start, uffdio_wake.len);
if (ret)
goto out;
sizeof(uffdio_copy)-sizeof(__s64)))
goto out;
- ret = validate_range(ctx->mm, &uffdio_copy.dst, uffdio_copy.len);
+ ret = validate_range(ctx->mm, uffdio_copy.dst, uffdio_copy.len);
if (ret)
goto out;
/*
sizeof(uffdio_zeropage)-sizeof(__s64)))
goto out;
- ret = validate_range(ctx->mm, &uffdio_zeropage.range.start,
+ ret = validate_range(ctx->mm, uffdio_zeropage.range.start,
uffdio_zeropage.range.len);
if (ret)
goto out;
sizeof(struct uffdio_writeprotect)))
return -EFAULT;
- ret = validate_range(ctx->mm, &uffdio_wp.range.start,
+ ret = validate_range(ctx->mm, uffdio_wp.range.start,
uffdio_wp.range.len);
if (ret)
return ret;
sizeof(uffdio_continue) - (sizeof(__s64))))
goto out;
- ret = validate_range(ctx->mm, &uffdio_continue.range.start,
+ ret = validate_range(ctx->mm, uffdio_continue.range.start,
uffdio_continue.range.len);
if (ret)
goto out;
}
static int vboxsf_dir_create(struct inode *parent, struct dentry *dentry,
- umode_t mode, int is_dir)
+ umode_t mode, bool is_dir, bool excl, u64 *handle_ret)
{
struct vboxsf_inode *sf_parent_i = VBOXSF_I(parent);
struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb);
int err;
params.handle = SHFL_HANDLE_NIL;
- params.create_flags = SHFL_CF_ACT_CREATE_IF_NEW |
- SHFL_CF_ACT_FAIL_IF_EXISTS |
- SHFL_CF_ACCESS_READWRITE |
- (is_dir ? SHFL_CF_DIRECTORY : 0);
+ params.create_flags = SHFL_CF_ACT_CREATE_IF_NEW | SHFL_CF_ACCESS_READWRITE;
+ if (is_dir)
+ params.create_flags |= SHFL_CF_DIRECTORY;
+ if (excl)
+ params.create_flags |= SHFL_CF_ACT_FAIL_IF_EXISTS;
+
params.info.attr.mode = (mode & 0777) |
(is_dir ? SHFL_TYPE_DIRECTORY : SHFL_TYPE_FILE);
params.info.attr.additional = SHFLFSOBJATTRADD_NOTHING;
if (params.result != SHFL_FILE_CREATED)
return -EPERM;
- vboxsf_close(sbi->root, params.handle);
-
err = vboxsf_dir_instantiate(parent, dentry, ¶ms.info);
if (err)
- return err;
+ goto out;
/* parent directory access/change time changed */
sf_parent_i->force_restat = 1;
- return 0;
+out:
+ if (err == 0 && handle_ret)
+ *handle_ret = params.handle;
+ else
+ vboxsf_close(sbi->root, params.handle);
+
+ return err;
}
static int vboxsf_dir_mkfile(struct user_namespace *mnt_userns,
struct inode *parent, struct dentry *dentry,
umode_t mode, bool excl)
{
- return vboxsf_dir_create(parent, dentry, mode, 0);
+ return vboxsf_dir_create(parent, dentry, mode, false, excl, NULL);
}
static int vboxsf_dir_mkdir(struct user_namespace *mnt_userns,
struct inode *parent, struct dentry *dentry,
umode_t mode)
{
- return vboxsf_dir_create(parent, dentry, mode, 1);
+ return vboxsf_dir_create(parent, dentry, mode, true, true, NULL);
+}
+
+static int vboxsf_dir_atomic_open(struct inode *parent, struct dentry *dentry,
+ struct file *file, unsigned int flags, umode_t mode)
+{
+ struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb);
+ struct vboxsf_handle *sf_handle;
+ struct dentry *res = NULL;
+ u64 handle;
+ int err;
+
+ if (d_in_lookup(dentry)) {
+ res = vboxsf_dir_lookup(parent, dentry, 0);
+ if (IS_ERR(res))
+ return PTR_ERR(res);
+
+ if (res)
+ dentry = res;
+ }
+
+ /* Only creates */
+ if (!(flags & O_CREAT) || d_really_is_positive(dentry))
+ return finish_no_open(file, res);
+
+ err = vboxsf_dir_create(parent, dentry, mode, false, flags & O_EXCL, &handle);
+ if (err)
+ goto out;
+
+ sf_handle = vboxsf_create_sf_handle(d_inode(dentry), handle, SHFL_CF_ACCESS_READWRITE);
+ if (IS_ERR(sf_handle)) {
+ vboxsf_close(sbi->root, handle);
+ err = PTR_ERR(sf_handle);
+ goto out;
+ }
+
+ err = finish_open(file, dentry, generic_file_open);
+ if (err) {
+ /* This also closes the handle passed to vboxsf_create_sf_handle() */
+ vboxsf_release_sf_handle(d_inode(dentry), sf_handle);
+ goto out;
+ }
+
+ file->private_data = sf_handle;
+ file->f_mode |= FMODE_CREATED;
+out:
+ dput(res);
+ return err;
}
static int vboxsf_dir_unlink(struct inode *parent, struct dentry *dentry)
.lookup = vboxsf_dir_lookup,
.create = vboxsf_dir_mkfile,
.mkdir = vboxsf_dir_mkdir,
+ .atomic_open = vboxsf_dir_atomic_open,
.rmdir = vboxsf_dir_unlink,
.unlink = vboxsf_dir_unlink,
.rename = vboxsf_dir_rename,
struct list_head head;
};
-static int vboxsf_file_open(struct inode *inode, struct file *file)
+struct vboxsf_handle *vboxsf_create_sf_handle(struct inode *inode,
+ u64 handle, u32 access_flags)
{
struct vboxsf_inode *sf_i = VBOXSF_I(inode);
- struct shfl_createparms params = {};
struct vboxsf_handle *sf_handle;
- u32 access_flags = 0;
- int err;
sf_handle = kmalloc(sizeof(*sf_handle), GFP_KERNEL);
if (!sf_handle)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
+
+ /* the host may have given us different attr then requested */
+ sf_i->force_restat = 1;
+
+ /* init our handle struct and add it to the inode's handles list */
+ sf_handle->handle = handle;
+ sf_handle->root = VBOXSF_SBI(inode->i_sb)->root;
+ sf_handle->access_flags = access_flags;
+ kref_init(&sf_handle->refcount);
+
+ mutex_lock(&sf_i->handle_list_mutex);
+ list_add(&sf_handle->head, &sf_i->handle_list);
+ mutex_unlock(&sf_i->handle_list_mutex);
+
+ return sf_handle;
+}
+
+static int vboxsf_file_open(struct inode *inode, struct file *file)
+{
+ struct vboxsf_sbi *sbi = VBOXSF_SBI(inode->i_sb);
+ struct shfl_createparms params = {};
+ struct vboxsf_handle *sf_handle;
+ u32 access_flags = 0;
+ int err;
/*
* We check the value of params.handle afterwards to find out if
err = vboxsf_create_at_dentry(file_dentry(file), ¶ms);
if (err == 0 && params.handle == SHFL_HANDLE_NIL)
err = (params.result == SHFL_FILE_EXISTS) ? -EEXIST : -ENOENT;
- if (err) {
- kfree(sf_handle);
+ if (err)
return err;
- }
-
- /* the host may have given us different attr then requested */
- sf_i->force_restat = 1;
- /* init our handle struct and add it to the inode's handles list */
- sf_handle->handle = params.handle;
- sf_handle->root = VBOXSF_SBI(inode->i_sb)->root;
- sf_handle->access_flags = access_flags;
- kref_init(&sf_handle->refcount);
-
- mutex_lock(&sf_i->handle_list_mutex);
- list_add(&sf_handle->head, &sf_i->handle_list);
- mutex_unlock(&sf_i->handle_list_mutex);
+ sf_handle = vboxsf_create_sf_handle(inode, params.handle, access_flags);
+ if (IS_ERR(sf_handle)) {
+ vboxsf_close(sbi->root, params.handle);
+ return PTR_ERR(sf_handle);
+ }
file->private_data = sf_handle;
return 0;
kfree(sf_handle);
}
-static int vboxsf_file_release(struct inode *inode, struct file *file)
+void vboxsf_release_sf_handle(struct inode *inode, struct vboxsf_handle *sf_handle)
{
struct vboxsf_inode *sf_i = VBOXSF_I(inode);
- struct vboxsf_handle *sf_handle = file->private_data;
+ mutex_lock(&sf_i->handle_list_mutex);
+ list_del(&sf_handle->head);
+ mutex_unlock(&sf_i->handle_list_mutex);
+
+ kref_put(&sf_handle->refcount, vboxsf_handle_release);
+}
+
+static int vboxsf_file_release(struct inode *inode, struct file *file)
+{
/*
* When a file is closed on our (the guest) side, we want any subsequent
* accesses done on the host side to see all changes done from our side.
*/
filemap_write_and_wait(inode->i_mapping);
- mutex_lock(&sf_i->handle_list_mutex);
- list_del(&sf_handle->head);
- mutex_unlock(&sf_i->handle_list_mutex);
-
- kref_put(&sf_handle->refcount, vboxsf_handle_release);
+ vboxsf_release_sf_handle(inode, file->private_data);
return 0;
}
#define VBOXSF_SBI(sb) ((struct vboxsf_sbi *)(sb)->s_fs_info)
#define VBOXSF_I(i) container_of(i, struct vboxsf_inode, vfs_inode)
+struct vboxsf_handle;
+
struct vboxsf_options {
unsigned long ttl;
kuid_t uid;
extern const struct address_space_operations vboxsf_reg_aops;
extern const struct dentry_operations vboxsf_dentry_ops;
+/* from file.c */
+struct vboxsf_handle *vboxsf_create_sf_handle(struct inode *inode,
+ u64 handle, u32 access_flags);
+void vboxsf_release_sf_handle(struct inode *inode, struct vboxsf_handle *sf_handle);
+
/* from utils.c */
struct inode *vboxsf_new_inode(struct super_block *sb);
int vboxsf_init_inode(struct vboxsf_sbi *sbi, struct inode *inode,
args.fsbno = XFS_AGB_TO_FSB(mp, agno, aglen - delta);
/*
+ * Make sure that the last inode cluster cannot overlap with the new
+ * end of the AG, even if it's sparse.
+ */
+ error = xfs_ialloc_check_shrink(*tpp, agno, agibp, aglen - delta);
+ if (error)
+ return error;
+
+ /*
* Disable perag reservations so it doesn't cause the allocation request
* to fail. We'll reestablish reservation before we return.
*/
if (error)
return error;
- /* fallthrough */
+ fallthrough;
case XFS_DAS_RM_LBLK:
/* Set state in case xfs_attr_rmtval_remove returns -EAGAIN */
dac->dela_state = XFS_DAS_RM_LBLK;
return -EAGAIN;
}
- /* fallthrough */
+ fallthrough;
case XFS_DAS_RD_LEAF:
/*
* This is the last step for leaf format. Read the block with
return error;
}
- /* fallthrough */
+ fallthrough;
case XFS_DAS_ALLOC_NODE:
/*
* If there was an out-of-line value, allocate the blocks we
if (error)
return error;
- /* fallthrough */
+ fallthrough;
case XFS_DAS_RM_NBLK:
/* Set state in case xfs_attr_rmtval_remove returns -EAGAIN */
dac->dela_state = XFS_DAS_RM_NBLK;
return -EAGAIN;
}
- /* fallthrough */
+ fallthrough;
case XFS_DAS_CLR_FLAG:
/*
* The last state for node format. Look up the old attr and
state = dac->da_state;
}
- /* fallthrough */
+ fallthrough;
case XFS_DAS_RMTBLK:
dac->dela_state = XFS_DAS_RMTBLK;
return -EAGAIN;
}
- /* fallthrough */
+ fallthrough;
case XFS_DAS_RM_NAME:
/*
* If we came here fresh from a transaction roll, reattach all
return -EAGAIN;
}
- /* fallthrough */
+ fallthrough;
case XFS_DAS_RM_SHRINK:
/*
* If the result is small enough, push it all into the inode.
return XFS_AGINO_TO_INO(mp, 0, XFS_AGB_TO_AGINO(mp, first_bno));
}
+
+/*
+ * Ensure there are not sparse inode clusters that cross the new EOAG.
+ *
+ * This is a no-op for non-spinode filesystems since clusters are always fully
+ * allocated and checking the bnobt suffices. However, a spinode filesystem
+ * could have a record where the upper inodes are free blocks. If those blocks
+ * were removed from the filesystem, the inode record would extend beyond EOAG,
+ * which will be flagged as corruption.
+ */
+int
+xfs_ialloc_check_shrink(
+ struct xfs_trans *tp,
+ xfs_agnumber_t agno,
+ struct xfs_buf *agibp,
+ xfs_agblock_t new_length)
+{
+ struct xfs_inobt_rec_incore rec;
+ struct xfs_btree_cur *cur;
+ struct xfs_mount *mp = tp->t_mountp;
+ struct xfs_perag *pag;
+ xfs_agino_t agino = XFS_AGB_TO_AGINO(mp, new_length);
+ int has;
+ int error;
+
+ if (!xfs_sb_version_hassparseinodes(&mp->m_sb))
+ return 0;
+
+ pag = xfs_perag_get(mp, agno);
+ cur = xfs_inobt_init_cursor(mp, tp, agibp, pag, XFS_BTNUM_INO);
+
+ /* Look up the inobt record that would correspond to the new EOFS. */
+ error = xfs_inobt_lookup(cur, agino, XFS_LOOKUP_LE, &has);
+ if (error || !has)
+ goto out;
+
+ error = xfs_inobt_get_rec(cur, &rec, &has);
+ if (error)
+ goto out;
+
+ if (!has) {
+ error = -EFSCORRUPTED;
+ goto out;
+ }
+
+ /* If the record covers inodes that would be beyond EOFS, bail out. */
+ if (rec.ir_startino + XFS_INODES_PER_CHUNK > agino) {
+ error = -ENOSPC;
+ goto out;
+ }
+out:
+ xfs_btree_del_cursor(cur, error);
+ xfs_perag_put(pag);
+ return error;
+}
void xfs_ialloc_setup_geometry(struct xfs_mount *mp);
xfs_ino_t xfs_ialloc_calc_rootino(struct xfs_mount *mp, int sunit);
+int xfs_ialloc_check_shrink(struct xfs_trans *tp, xfs_agnumber_t agno,
+ struct xfs_buf *agibp, xfs_agblock_t new_length);
+
#endif /* __XFS_IALLOC_H__ */
/*
* This comment describes a historic gap in this verifier function.
*
- * On older kernels, the extent size hint verifier doesn't check that
- * the extent size hint is an integer multiple of the realtime extent
- * size on a directory with both RTINHERIT and EXTSZINHERIT flags set.
- * The verifier has always enforced the alignment rule for regular
- * files with the REALTIME flag set.
+ * For a directory with both RTINHERIT and EXTSZINHERIT flags set, this
+ * function has never checked that the extent size hint is an integer
+ * multiple of the realtime extent size. Since we allow users to set
+ * this combination on non-rt filesystems /and/ to change the rt
+ * extent size when adding a rt device to a filesystem, the net effect
+ * is that users can configure a filesystem anticipating one rt
+ * geometry and change their minds later. Directories do not use the
+ * extent size hint, so this is harmless for them.
*
* If a directory with a misaligned extent size hint is allowed to
* propagate that hint into a new regular realtime file, the result
* is that the inode cluster buffer verifier will trigger a corruption
- * shutdown the next time it is run.
+ * shutdown the next time it is run, because the verifier has always
+ * enforced the alignment rule for regular files.
*
- * Unfortunately, there could be filesystems with these misconfigured
- * directories in the wild, so we cannot add a check to this verifier
- * at this time because that will result a new source of directory
- * corruption errors when reading an existing filesystem. Instead, we
- * permit the misconfiguration to pass through the verifiers so that
- * callers of this function can correct and mitigate externally.
+ * Because we allow administrators to set a new rt extent size when
+ * adding a rt section, we cannot add a check to this verifier because
+ * that will result a new source of directory corruption errors when
+ * reading an existing filesystem. Instead, we rely on callers to
+ * decide when alignment checks are appropriate, and fix things up as
+ * needed.
*/
if (rt_flag)
/* start of the extended dinode, writable fields */
uint32_t di_crc; /* CRC of the inode */
uint64_t di_changecount; /* number of attribute changes */
- xfs_lsn_t di_lsn; /* flush sequence */
+
+ /*
+ * The LSN we write to this field during formatting is not a reflection
+ * of the current on-disk LSN. It should never be used for recovery
+ * sequencing, nor should it be recovered into the on-disk inode at all.
+ * See xlog_recover_inode_commit_pass2() and xfs_log_dinode_to_disk()
+ * for details.
+ */
+ xfs_lsn_t di_lsn;
+
uint64_t di_flags2; /* more random flags */
uint32_t di_cowextsize; /* basic cow extent size for file */
uint8_t di_pad2[12]; /* more padding for future expansion */
}
/*
- * Inode verifiers on older kernels don't check that the extent size
- * hint is an integer multiple of the rt extent size on a directory
- * with both rtinherit and extszinherit flags set. If we're logging a
- * directory that is misconfigured in this way, clear the hint.
+ * Inode verifiers do not check that the extent size hint is an integer
+ * multiple of the rt extent size on a directory with both rtinherit
+ * and extszinherit flags set. If we're logging a directory that is
+ * misconfigured in this way, clear the hint.
*/
if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) &&
(ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) &&
(ip->i_extsize % ip->i_mount->m_sb.sb_rextsize) > 0) {
- xfs_info_once(ip->i_mount,
- "Correcting misaligned extent size hint in inode 0x%llx.", ip->i_ino);
ip->i_diflags &= ~(XFS_DIFLAG_EXTSIZE |
XFS_DIFLAG_EXTSZINHERIT);
ip->i_extsize = 0;
uint16_t flags)
{
xfs_failaddr_t fa;
+ uint32_t value = be32_to_cpu(dip->di_extsize);
- fa = xfs_inode_validate_extsize(sc->mp, be32_to_cpu(dip->di_extsize),
- mode, flags);
+ fa = xfs_inode_validate_extsize(sc->mp, value, mode, flags);
if (fa)
xchk_ino_set_corrupt(sc, ino);
+
+ /*
+ * XFS allows a sysadmin to change the rt extent size when adding a rt
+ * section to a filesystem after formatting. If there are any
+ * directories with extszinherit and rtinherit set, the hint could
+ * become misaligned with the new rextsize. The verifier doesn't check
+ * this, because we allow rtinherit directories even without an rt
+ * device. Flag this as an administrative warning since we will clean
+ * this up eventually.
+ */
+ if ((flags & XFS_DIFLAG_RTINHERIT) &&
+ (flags & XFS_DIFLAG_EXTSZINHERIT) &&
+ value % sc->mp->m_sb.sb_rextsize > 0)
+ xchk_ino_set_warning(sc, ino);
}
/*
static xfs_lsn_t
xlog_recover_get_buf_lsn(
struct xfs_mount *mp,
- struct xfs_buf *bp)
+ struct xfs_buf *bp,
+ struct xfs_buf_log_format *buf_f)
{
uint32_t magic32;
uint16_t magic16;
void *blk = bp->b_addr;
uuid_t *uuid;
xfs_lsn_t lsn = -1;
+ uint16_t blft;
/* v4 filesystems always recover immediately */
if (!xfs_sb_version_hascrc(&mp->m_sb))
goto recover_immediately;
+ /*
+ * realtime bitmap and summary file blocks do not have magic numbers or
+ * UUIDs, so we must recover them immediately.
+ */
+ blft = xfs_blft_from_flags(buf_f);
+ if (blft == XFS_BLFT_RTBITMAP_BUF || blft == XFS_BLFT_RTSUMMARY_BUF)
+ goto recover_immediately;
+
magic32 = be32_to_cpu(*(__be32 *)blk);
switch (magic32) {
case XFS_ABTB_CRC_MAGIC:
switch (magicda) {
case XFS_DIR3_LEAF1_MAGIC:
case XFS_DIR3_LEAFN_MAGIC:
+ case XFS_ATTR3_LEAF_MAGIC:
case XFS_DA3_NODE_MAGIC:
lsn = be64_to_cpu(((struct xfs_da3_blkinfo *)blk)->lsn);
uuid = &((struct xfs_da3_blkinfo *)blk)->uuid;
* the verifier will be reset to match whatever recover turns that
* buffer into.
*/
- lsn = xlog_recover_get_buf_lsn(mp, bp);
+ lsn = xlog_recover_get_buf_lsn(mp, bp, buf_f);
if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) {
trace_xfs_log_recover_buf_skip(log, buf_f);
xlog_recover_validate_buf_type(mp, bp, buf_f, NULLCOMMITLSN);
error = xfs_droplink(tp, ip);
if (error)
goto out_trans_cancel;
+
+ /*
+ * Point the unlinked child directory's ".." entry to the root
+ * directory to eliminate back-references to inodes that may
+ * get freed before the child directory is closed. If the fs
+ * gets shrunk, this can lead to dirent inode validation errors.
+ */
+ if (dp->i_ino != tp->t_mountp->m_sb.sb_rootino) {
+ error = xfs_dir_replace(tp, ip, &xfs_name_dotdot,
+ tp->t_mountp->m_sb.sb_rootino, 0);
+ if (error)
+ return error;
+ }
} else {
/*
* When removing a non-directory we need to log the parent
STATIC void
xfs_log_dinode_to_disk(
struct xfs_log_dinode *from,
- struct xfs_dinode *to)
+ struct xfs_dinode *to,
+ xfs_lsn_t lsn)
{
to->di_magic = cpu_to_be16(from->di_magic);
to->di_mode = cpu_to_be16(from->di_mode);
to->di_flags2 = cpu_to_be64(from->di_flags2);
to->di_cowextsize = cpu_to_be32(from->di_cowextsize);
to->di_ino = cpu_to_be64(from->di_ino);
- to->di_lsn = cpu_to_be64(from->di_lsn);
+ to->di_lsn = cpu_to_be64(lsn);
memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
uuid_copy(&to->di_uuid, &from->di_uuid);
to->di_flushiter = 0;
}
/*
- * If the inode has an LSN in it, recover the inode only if it's less
- * than the lsn of the transaction we are replaying. Note: we still
- * need to replay an owner change even though the inode is more recent
- * than the transaction as there is no guarantee that all the btree
- * blocks are more recent than this transaction, too.
+ * If the inode has an LSN in it, recover the inode only if the on-disk
+ * inode's LSN is older than the lsn of the transaction we are
+ * replaying. We can have multiple checkpoints with the same start LSN,
+ * so the current LSN being equal to the on-disk LSN doesn't necessarily
+ * mean that the on-disk inode is more recent than the change being
+ * replayed.
+ *
+ * We must check the current_lsn against the on-disk inode
+ * here because the we can't trust the log dinode to contain a valid LSN
+ * (see comment below before replaying the log dinode for details).
+ *
+ * Note: we still need to replay an owner change even though the inode
+ * is more recent than the transaction as there is no guarantee that all
+ * the btree blocks are more recent than this transaction, too.
*/
if (dip->di_version >= 3) {
xfs_lsn_t lsn = be64_to_cpu(dip->di_lsn);
- if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) {
+ if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) > 0) {
trace_xfs_log_recover_inode_skip(log, in_f);
error = 0;
goto out_owner_change;
goto out_release;
}
- /* recover the log dinode inode into the on disk inode */
- xfs_log_dinode_to_disk(ldip, dip);
+ /*
+ * Recover the log dinode inode into the on disk inode.
+ *
+ * The LSN in the log dinode is garbage - it can be zero or reflect
+ * stale in-memory runtime state that isn't coherent with the changes
+ * logged in this transaction or the changes written to the on-disk
+ * inode. Hence we write the current lSN into the inode because that
+ * matches what xfs_iflush() would write inode the inode when flushing
+ * the changes in this transaction.
+ */
+ xfs_log_dinode_to_disk(ldip, dip, current_lsn);
fields = in_f->ilf_fields;
if (fields & XFS_ILOG_DEV)
fileattr_fill_xflags(fa, xfs_ip2xflags(ip));
- fa->fsx_extsize = XFS_FSB_TO_B(mp, ip->i_extsize);
+ if (ip->i_diflags & XFS_DIFLAG_EXTSIZE) {
+ fa->fsx_extsize = XFS_FSB_TO_B(mp, ip->i_extsize);
+ } else if (ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) {
+ /*
+ * Don't let a misaligned extent size hint on a directory
+ * escape to userspace if it won't pass the setattr checks
+ * later.
+ */
+ if ((ip->i_diflags & XFS_DIFLAG_RTINHERIT) &&
+ ip->i_extsize % mp->m_sb.sb_rextsize > 0) {
+ fa->fsx_xflags &= ~(FS_XFLAG_EXTSIZE |
+ FS_XFLAG_EXTSZINHERIT);
+ fa->fsx_extsize = 0;
+ } else {
+ fa->fsx_extsize = XFS_FSB_TO_B(mp, ip->i_extsize);
+ }
+ }
+
if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)
fa->fsx_cowextsize = XFS_FSB_TO_B(mp, ip->i_cowextsize);
fa->fsx_projid = ip->i_projid;
new_diflags = xfs_flags2diflags(ip, fa->fsx_xflags);
/*
- * Inode verifiers on older kernels don't check that the extent size
- * hint is an integer multiple of the rt extent size on a directory
- * with both rtinherit and extszinherit flags set. Don't let sysadmins
- * misconfigure directories.
+ * Inode verifiers do not check that the extent size hint is an integer
+ * multiple of the rt extent size on a directory with both rtinherit
+ * and extszinherit flags set. Don't let sysadmins misconfigure
+ * directories.
*/
if ((new_diflags & XFS_DIFLAG_RTINHERIT) &&
(new_diflags & XFS_DIFLAG_EXTSZINHERIT)) {
STATIC void
xlog_verify_tail_lsn(
struct xlog *log,
- struct xlog_in_core *iclog,
- xfs_lsn_t tail_lsn);
+ struct xlog_in_core *iclog);
#else
#define xlog_verify_dest_ptr(a,b)
#define xlog_verify_grant_tail(a)
#define xlog_verify_iclog(a,b,c)
-#define xlog_verify_tail_lsn(a,b,c)
+#define xlog_verify_tail_lsn(a,b)
#endif
STATIC int
return error;
}
-static bool
-__xlog_state_release_iclog(
- struct xlog *log,
- struct xlog_in_core *iclog)
-{
- lockdep_assert_held(&log->l_icloglock);
-
- if (iclog->ic_state == XLOG_STATE_WANT_SYNC) {
- /* update tail before writing to iclog */
- xfs_lsn_t tail_lsn = xlog_assign_tail_lsn(log->l_mp);
-
- iclog->ic_state = XLOG_STATE_SYNCING;
- iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn);
- xlog_verify_tail_lsn(log, iclog, tail_lsn);
- /* cycle incremented when incrementing curr_block */
- trace_xlog_iclog_syncing(iclog, _RET_IP_);
- return true;
- }
-
- ASSERT(iclog->ic_state == XLOG_STATE_ACTIVE);
- return false;
-}
-
/*
* Flush iclog to disk if this is the last reference to the given iclog and the
* it is in the WANT_SYNC state.
+ *
+ * If the caller passes in a non-zero @old_tail_lsn and the current log tail
+ * does not match, there may be metadata on disk that must be persisted before
+ * this iclog is written. To satisfy that requirement, set the
+ * XLOG_ICL_NEED_FLUSH flag as a condition for writing this iclog with the new
+ * log tail value.
+ *
+ * If XLOG_ICL_NEED_FUA is already set on the iclog, we need to ensure that the
+ * log tail is updated correctly. NEED_FUA indicates that the iclog will be
+ * written to stable storage, and implies that a commit record is contained
+ * within the iclog. We need to ensure that the log tail does not move beyond
+ * the tail that the first commit record in the iclog ordered against, otherwise
+ * correct recovery of that checkpoint becomes dependent on future operations
+ * performed on this iclog.
+ *
+ * Hence if NEED_FUA is set and the current iclog tail lsn is empty, write the
+ * current tail into iclog. Once the iclog tail is set, future operations must
+ * not modify it, otherwise they potentially violate ordering constraints for
+ * the checkpoint commit that wrote the initial tail lsn value. The tail lsn in
+ * the iclog will get zeroed on activation of the iclog after sync, so we
+ * always capture the tail lsn on the iclog on the first NEED_FUA release
+ * regardless of the number of active reference counts on this iclog.
*/
+
int
xlog_state_release_iclog(
struct xlog *log,
- struct xlog_in_core *iclog)
+ struct xlog_in_core *iclog,
+ xfs_lsn_t old_tail_lsn)
{
+ xfs_lsn_t tail_lsn;
lockdep_assert_held(&log->l_icloglock);
trace_xlog_iclog_release(iclog, _RET_IP_);
if (iclog->ic_state == XLOG_STATE_IOERROR)
return -EIO;
- if (atomic_dec_and_test(&iclog->ic_refcnt) &&
- __xlog_state_release_iclog(log, iclog)) {
- spin_unlock(&log->l_icloglock);
- xlog_sync(log, iclog);
- spin_lock(&log->l_icloglock);
+ /*
+ * Grabbing the current log tail needs to be atomic w.r.t. the writing
+ * of the tail LSN into the iclog so we guarantee that the log tail does
+ * not move between deciding if a cache flush is required and writing
+ * the LSN into the iclog below.
+ */
+ if (old_tail_lsn || iclog->ic_state == XLOG_STATE_WANT_SYNC) {
+ tail_lsn = xlog_assign_tail_lsn(log->l_mp);
+
+ if (old_tail_lsn && tail_lsn != old_tail_lsn)
+ iclog->ic_flags |= XLOG_ICL_NEED_FLUSH;
+
+ if ((iclog->ic_flags & XLOG_ICL_NEED_FUA) &&
+ !iclog->ic_header.h_tail_lsn)
+ iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn);
}
+ if (!atomic_dec_and_test(&iclog->ic_refcnt))
+ return 0;
+
+ if (iclog->ic_state != XLOG_STATE_WANT_SYNC) {
+ ASSERT(iclog->ic_state == XLOG_STATE_ACTIVE);
+ return 0;
+ }
+
+ iclog->ic_state = XLOG_STATE_SYNCING;
+ if (!iclog->ic_header.h_tail_lsn)
+ iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn);
+ xlog_verify_tail_lsn(log, iclog);
+ trace_xlog_iclog_syncing(iclog, _RET_IP_);
+
+ spin_unlock(&log->l_icloglock);
+ xlog_sync(log, iclog);
+ spin_lock(&log->l_icloglock);
return 0;
}
}
/*
+ * Flush out the iclog to disk ensuring that device caches are flushed and
+ * the iclog hits stable storage before any completion waiters are woken.
+ */
+static inline int
+xlog_force_iclog(
+ struct xlog_in_core *iclog)
+{
+ atomic_inc(&iclog->ic_refcnt);
+ iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA;
+ if (iclog->ic_state == XLOG_STATE_ACTIVE)
+ xlog_state_switch_iclogs(iclog->ic_log, iclog, 0);
+ return xlog_state_release_iclog(iclog->ic_log, iclog, 0);
+}
+
+/*
* Wait for the iclog and all prior iclogs to be written disk as required by the
* log force state machine. Waiting on ic_force_wait ensures iclog completions
* have been ordered and callbacks run before we are woken here, hence
/* account for space used by record data */
ticket->t_curr_res -= sizeof(ulf);
- /*
- * For external log devices, we need to flush the data device cache
- * first to ensure all metadata writeback is on stable storage before we
- * stamp the tail LSN into the unmount record.
- */
- if (log->l_targ != log->l_mp->m_ddev_targp)
- blkdev_issue_flush(log->l_targ->bt_bdev);
return xlog_write(log, &vec, ticket, NULL, NULL, XLOG_UNMOUNT_TRANS);
}
spin_lock(&log->l_icloglock);
iclog = log->l_iclog;
- atomic_inc(&iclog->ic_refcnt);
- if (iclog->ic_state == XLOG_STATE_ACTIVE)
- xlog_state_switch_iclogs(log, iclog, 0);
- else
- ASSERT(iclog->ic_state == XLOG_STATE_WANT_SYNC ||
- iclog->ic_state == XLOG_STATE_IOERROR);
- /*
- * Ensure the journal is fully flushed and on stable storage once the
- * iclog containing the unmount record is written.
- */
- iclog->ic_flags |= (XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA);
- error = xlog_state_release_iclog(log, iclog);
+ error = xlog_force_iclog(iclog);
xlog_wait_on_iclog(iclog);
if (tic) {
* metadata writeback and causing priority inversions.
*/
iclog->ic_bio.bi_opf = REQ_OP_WRITE | REQ_META | REQ_SYNC | REQ_IDLE;
- if (iclog->ic_flags & XLOG_ICL_NEED_FLUSH)
+ if (iclog->ic_flags & XLOG_ICL_NEED_FLUSH) {
iclog->ic_bio.bi_opf |= REQ_PREFLUSH;
+ /*
+ * For external log devices, we also need to flush the data
+ * device cache first to ensure all metadata writeback covered
+ * by the LSN in this iclog is on stable storage. This is slow,
+ * but it *must* complete before we issue the external log IO.
+ */
+ if (log->l_targ != log->l_mp->m_ddev_targp)
+ blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev);
+ }
if (iclog->ic_flags & XLOG_ICL_NEED_FUA)
iclog->ic_bio.bi_opf |= REQ_FUA;
+
iclog->ic_flags &= ~(XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA);
if (xlog_map_iclog_data(&iclog->ic_bio, iclog->ic_data, count)) {
return 0;
release_iclog:
- error = xlog_state_release_iclog(log, iclog);
+ error = xlog_state_release_iclog(log, iclog, 0);
spin_unlock(&log->l_icloglock);
return error;
}
ASSERT(optype & XLOG_COMMIT_TRANS);
*commit_iclog = iclog;
} else {
- error = xlog_state_release_iclog(log, iclog);
+ error = xlog_state_release_iclog(log, iclog, 0);
}
spin_unlock(&log->l_icloglock);
memset(iclog->ic_header.h_cycle_data, 0,
sizeof(iclog->ic_header.h_cycle_data));
iclog->ic_header.h_lsn = 0;
+ iclog->ic_header.h_tail_lsn = 0;
}
/*
* reference to the iclog.
*/
if (!atomic_add_unless(&iclog->ic_refcnt, -1, 1))
- error = xlog_state_release_iclog(log, iclog);
+ error = xlog_state_release_iclog(log, iclog, 0);
spin_unlock(&log->l_icloglock);
if (error)
return error;
}
/*
+ * Force the iclog to disk and check if the iclog has been completed before
+ * xlog_force_iclog() returns. This can happen on synchronous (e.g.
+ * pmem) or fast async storage because we drop the icloglock to issue the IO.
+ * If completion has already occurred, tell the caller so that it can avoid an
+ * unnecessary wait on the iclog.
+ */
+static int
+xlog_force_and_check_iclog(
+ struct xlog_in_core *iclog,
+ bool *completed)
+{
+ xfs_lsn_t lsn = be64_to_cpu(iclog->ic_header.h_lsn);
+ int error;
+
+ *completed = false;
+ error = xlog_force_iclog(iclog);
+ if (error)
+ return error;
+
+ /*
+ * If the iclog has already been completed and reused the header LSN
+ * will have been rewritten by completion
+ */
+ if (be64_to_cpu(iclog->ic_header.h_lsn) != lsn)
+ *completed = true;
+ return 0;
+}
+
+/*
* Write out all data in the in-core log as of this exact moment in time.
*
* Data may be written to the in-core log during this call. However,
{
struct xlog *log = mp->m_log;
struct xlog_in_core *iclog;
- xfs_lsn_t lsn;
XFS_STATS_INC(mp, xs_log_force);
trace_xfs_log_force(mp, 0, _RET_IP_);
iclog = iclog->ic_prev;
} else if (iclog->ic_state == XLOG_STATE_ACTIVE) {
if (atomic_read(&iclog->ic_refcnt) == 0) {
- /*
- * We are the only one with access to this iclog.
- *
- * Flush it out now. There should be a roundoff of zero
- * to show that someone has already taken care of the
- * roundoff from the previous sync.
- */
- atomic_inc(&iclog->ic_refcnt);
- lsn = be64_to_cpu(iclog->ic_header.h_lsn);
- xlog_state_switch_iclogs(log, iclog, 0);
- if (xlog_state_release_iclog(log, iclog))
+ /* We have exclusive access to this iclog. */
+ bool completed;
+
+ if (xlog_force_and_check_iclog(iclog, &completed))
goto out_error;
- if (be64_to_cpu(iclog->ic_header.h_lsn) != lsn)
+ if (completed)
goto out_unlock;
} else {
/*
- * Someone else is writing to this iclog.
- *
- * Use its call to flush out the data. However, the
- * other thread may not force out this LR, so we mark
- * it WANT_SYNC.
+ * Someone else is still writing to this iclog, so we
+ * need to ensure that when they release the iclog it
+ * gets synced immediately as we may be waiting on it.
*/
xlog_state_switch_iclogs(log, iclog, 0);
}
- } else {
- /*
- * If the head iclog is not active nor dirty, we just attach
- * ourselves to the head and go to sleep if necessary.
- */
- ;
}
+ /*
+ * The iclog we are about to wait on may contain the checkpoint pushed
+ * by the above xlog_cil_force() call, but it may not have been pushed
+ * to disk yet. Like the ACTIVE case above, we need to make sure caches
+ * are flushed when this iclog is written.
+ */
+ if (iclog->ic_state == XLOG_STATE_WANT_SYNC)
+ iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA;
+
if (flags & XFS_LOG_SYNC)
return xlog_wait_on_iclog(iclog);
out_unlock:
bool already_slept)
{
struct xlog_in_core *iclog;
+ bool completed;
spin_lock(&log->l_icloglock);
iclog = log->l_iclog;
goto out_unlock;
}
- if (iclog->ic_state == XLOG_STATE_ACTIVE) {
+ switch (iclog->ic_state) {
+ case XLOG_STATE_ACTIVE:
/*
* We sleep here if we haven't already slept (e.g. this is the
* first time we've looked at the correct iclog buf) and the
&log->l_icloglock);
return -EAGAIN;
}
- atomic_inc(&iclog->ic_refcnt);
- xlog_state_switch_iclogs(log, iclog, 0);
- if (xlog_state_release_iclog(log, iclog))
+ if (xlog_force_and_check_iclog(iclog, &completed))
goto out_error;
if (log_flushed)
*log_flushed = 1;
+ if (completed)
+ goto out_unlock;
+ break;
+ case XLOG_STATE_WANT_SYNC:
+ /*
+ * This iclog may contain the checkpoint pushed by the
+ * xlog_cil_force_seq() call, but there are other writers still
+ * accessing it so it hasn't been pushed to disk yet. Like the
+ * ACTIVE case above, we need to make sure caches are flushed
+ * when this iclog is written.
+ */
+ iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA;
+ break;
+ default:
+ /*
+ * The entire checkpoint was written by the CIL force and is on
+ * its way to disk already. It will be stable when it
+ * completes, so we don't need to manipulate caches here at all.
+ * We just need to wait for completion if necessary.
+ */
+ break;
}
if (flags & XFS_LOG_SYNC)
STATIC void
xlog_verify_tail_lsn(
struct xlog *log,
- struct xlog_in_core *iclog,
- xfs_lsn_t tail_lsn)
+ struct xlog_in_core *iclog)
{
- int blocks;
+ xfs_lsn_t tail_lsn = be64_to_cpu(iclog->ic_header.h_tail_lsn);
+ int blocks;
if (CYCLE_LSN(tail_lsn) == log->l_prev_cycle) {
blocks =
struct xfs_trans_header thdr;
struct xfs_log_iovec lhdr;
struct xfs_log_vec lvhdr = { NULL };
+ xfs_lsn_t preflush_tail_lsn;
xfs_lsn_t commit_lsn;
- xfs_lsn_t push_seq;
+ xfs_csn_t push_seq;
struct bio bio;
DECLARE_COMPLETION_ONSTACK(bdev_flush);
* because we hold the flush lock exclusively. Hence we can now issue
* a cache flush to ensure all the completed metadata in the journal we
* are about to overwrite is on stable storage.
+ *
+ * Because we are issuing this cache flush before we've written the
+ * tail lsn to the iclog, we can have metadata IO completions move the
+ * tail forwards between the completion of this flush and the iclog
+ * being written. In this case, we need to re-issue the cache flush
+ * before the iclog write. To detect whether the log tail moves, sample
+ * the tail LSN *before* we issue the flush.
*/
+ preflush_tail_lsn = atomic64_read(&log->l_tail_lsn);
xfs_flush_bdev_async(&bio, log->l_mp->m_ddev_targp->bt_bdev,
&bdev_flush);
* storage.
*/
commit_iclog->ic_flags |= XLOG_ICL_NEED_FUA;
- xlog_state_release_iclog(log, commit_iclog);
+ xlog_state_release_iclog(log, commit_iclog, preflush_tail_lsn);
spin_unlock(&log->l_icloglock);
return;
{ XLOG_STATE_DIRTY, "XLOG_STATE_DIRTY" }, \
{ XLOG_STATE_IOERROR, "XLOG_STATE_IOERROR" }
+/*
+ * In core log flags
+ */
+#define XLOG_ICL_NEED_FLUSH (1 << 0) /* iclog needs REQ_PREFLUSH */
+#define XLOG_ICL_NEED_FUA (1 << 1) /* iclog needs REQ_FUA */
+
+#define XLOG_ICL_STRINGS \
+ { XLOG_ICL_NEED_FLUSH, "XLOG_ICL_NEED_FLUSH" }, \
+ { XLOG_ICL_NEED_FUA, "XLOG_ICL_NEED_FUA" }
+
/*
* Log ticket flags
#define XLOG_COVER_OPS 5
-#define XLOG_ICL_NEED_FLUSH (1 << 0) /* iclog needs REQ_PREFLUSH */
-#define XLOG_ICL_NEED_FUA (1 << 1) /* iclog needs REQ_FUA */
-
/* Ticket reservation region accounting */
#define XLOG_TIC_LEN_MAX 15
void xfs_log_ticket_ungrant(struct xlog *log, struct xlog_ticket *ticket);
void xfs_log_ticket_regrant(struct xlog *log, struct xlog_ticket *ticket);
-int xlog_state_release_iclog(struct xlog *log, struct xlog_in_core *iclog);
+int xlog_state_release_iclog(struct xlog *log, struct xlog_in_core *iclog,
+ xfs_lsn_t log_tail_lsn);
/*
* When we crack an atomic LSN, we sample it first so that the value will not
uint8_t *rsum_cache; /* old summary cache */
sbp = &mp->m_sb;
- /*
- * Initial error checking.
- */
+
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- if (mp->m_rtdev_targp == NULL || mp->m_rbmip == NULL ||
- (nrblocks = in->newblocks) <= sbp->sb_rblocks ||
- (sbp->sb_rblocks && (in->extsize != sbp->sb_rextsize)))
+
+ /* Needs to have been mounted with an rt device. */
+ if (!XFS_IS_REALTIME_MOUNT(mp))
+ return -EINVAL;
+ /*
+ * Mount should fail if the rt bitmap/summary files don't load, but
+ * we'll check anyway.
+ */
+ if (!mp->m_rbmip || !mp->m_rsumip)
+ return -EINVAL;
+
+ /* Shrink not supported. */
+ if (in->newblocks <= sbp->sb_rblocks)
+ return -EINVAL;
+
+ /* Can only change rt extent size when adding rt volume. */
+ if (sbp->sb_rblocks > 0 && in->extsize != sbp->sb_rextsize)
+ return -EINVAL;
+
+ /* Range check the extent size. */
+ if (XFS_FSB_TO_B(mp, in->extsize) > XFS_MAX_RTEXTSIZE ||
+ XFS_FSB_TO_B(mp, in->extsize) < XFS_MIN_RTEXTSIZE)
return -EINVAL;
- if ((error = xfs_sb_validate_fsb_count(sbp, nrblocks)))
+
+ /* Unsupported realtime features. */
+ if (xfs_sb_version_hasrmapbt(&mp->m_sb) ||
+ xfs_sb_version_hasreflink(&mp->m_sb))
+ return -EOPNOTSUPP;
+
+ nrblocks = in->newblocks;
+ error = xfs_sb_validate_fsb_count(sbp, nrblocks);
+ if (error)
return error;
/*
* Read in the last block of the device, make sure it exists.
((sbp->sb_rextents & ((1 << mp->m_blkbit_log) - 1)) != 0);
bmbno < nrbmblocks;
bmbno++) {
- xfs_trans_t *tp;
+ struct xfs_trans *tp;
+ xfs_rfsblock_t nrblocks_step;
*nmp = *mp;
nsbp = &nmp->m_sb;
*/
nsbp->sb_rextsize = in->extsize;
nsbp->sb_rbmblocks = bmbno + 1;
- nsbp->sb_rblocks =
- XFS_RTMIN(nrblocks,
- nsbp->sb_rbmblocks * NBBY *
- nsbp->sb_blocksize * nsbp->sb_rextsize);
+ nrblocks_step = (bmbno + 1) * NBBY * nsbp->sb_blocksize *
+ nsbp->sb_rextsize;
+ nsbp->sb_rblocks = min(nrblocks, nrblocks_step);
nsbp->sb_rextents = nsbp->sb_rblocks;
do_div(nsbp->sb_rextents, nsbp->sb_rextsize);
ASSERT(nsbp->sb_rextents != 0);
__field(uint32_t, state)
__field(int32_t, refcount)
__field(uint32_t, offset)
+ __field(uint32_t, flags)
__field(unsigned long long, lsn)
__field(unsigned long, caller_ip)
),
__entry->state = iclog->ic_state;
__entry->refcount = atomic_read(&iclog->ic_refcnt);
__entry->offset = iclog->ic_offset;
+ __entry->flags = iclog->ic_flags;
__entry->lsn = be64_to_cpu(iclog->ic_header.h_lsn);
__entry->caller_ip = caller_ip;
),
- TP_printk("dev %d:%d state %s refcnt %d offset %u lsn 0x%llx caller %pS",
+ TP_printk("dev %d:%d state %s refcnt %d offset %u lsn 0x%llx flags %s caller %pS",
MAJOR(__entry->dev), MINOR(__entry->dev),
__print_symbolic(__entry->state, XLOG_STATE_STRINGS),
__entry->refcount,
__entry->offset,
__entry->lsn,
+ __print_flags(__entry->flags, "|", XLOG_ICL_STRINGS),
(char *)__entry->caller_ip)
);
return 0;
bio = bio_alloc(GFP_NOFS, nr_pages);
- if (!bio)
- return -ENOMEM;
-
bio_set_dev(bio, bdev);
bio->bi_iter.bi_sector = zi->i_zsector;
bio->bi_write_hint = iocb->ki_hint;
* @hrv: Hardware Revision of the device, pass -1 to not check _HRV
*
* The caller is responsible for invoking acpi_dev_put() on the returned device.
- *
- * FIXME: Due to above requirement there is a window that may invalidate @adev
- * and next iteration will use a dangling pointer, e.g. in the case of a
- * hotplug event. That said, the caller should ensure that this will never
- * happen.
*/
#define for_each_acpi_dev_match(adev, hid, uid, hrv) \
for (adev = acpi_dev_get_first_match_dev(hid, uid, hrv); \
static inline void acpi_dev_put(struct acpi_device *adev)
{
- put_device(&adev->dev);
+ if (adev)
+ put_device(&adev->dev);
}
struct acpi_device *acpi_bus_get_acpi_device(acpi_handle handle);
unsigned long arg);
#define DRM_IOCTL_NR(n) _IOC_NR(n)
+#define DRM_IOCTL_TYPE(n) _IOC_TYPE(n)
#define DRM_MAJOR 226
/**
#define R9A07G044_OSCCLK 21
/* R9A07G044 Module Clocks */
-#define R9A07G044_CLK_GIC600 0
-#define R9A07G044_CLK_IA55 1
-#define R9A07G044_CLK_SYC 2
-#define R9A07G044_CLK_DMAC 3
-#define R9A07G044_CLK_SYSC 4
-#define R9A07G044_CLK_MTU 5
-#define R9A07G044_CLK_GPT 6
-#define R9A07G044_CLK_ETH0 7
-#define R9A07G044_CLK_ETH1 8
-#define R9A07G044_CLK_I2C0 9
-#define R9A07G044_CLK_I2C1 10
-#define R9A07G044_CLK_I2C2 11
-#define R9A07G044_CLK_I2C3 12
-#define R9A07G044_CLK_SCIF0 13
-#define R9A07G044_CLK_SCIF1 14
-#define R9A07G044_CLK_SCIF2 15
-#define R9A07G044_CLK_SCIF3 16
-#define R9A07G044_CLK_SCIF4 17
-#define R9A07G044_CLK_SCI0 18
-#define R9A07G044_CLK_SCI1 19
-#define R9A07G044_CLK_GPIO 20
-#define R9A07G044_CLK_SDHI0 21
-#define R9A07G044_CLK_SDHI1 22
-#define R9A07G044_CLK_USB0 23
-#define R9A07G044_CLK_USB1 24
-#define R9A07G044_CLK_CANFD 25
-#define R9A07G044_CLK_SSI0 26
-#define R9A07G044_CLK_SSI1 27
-#define R9A07G044_CLK_SSI2 28
-#define R9A07G044_CLK_SSI3 29
-#define R9A07G044_CLK_MHU 30
-#define R9A07G044_CLK_OSTM0 31
-#define R9A07G044_CLK_OSTM1 32
-#define R9A07G044_CLK_OSTM2 33
-#define R9A07G044_CLK_WDT0 34
-#define R9A07G044_CLK_WDT1 35
-#define R9A07G044_CLK_WDT2 36
-#define R9A07G044_CLK_WDT_PON 37
-#define R9A07G044_CLK_GPU 38
-#define R9A07G044_CLK_ISU 39
-#define R9A07G044_CLK_H264 40
-#define R9A07G044_CLK_CRU 41
-#define R9A07G044_CLK_MIPI_DSI 42
-#define R9A07G044_CLK_LCDC 43
-#define R9A07G044_CLK_SRC 44
-#define R9A07G044_CLK_RSPI0 45
-#define R9A07G044_CLK_RSPI1 46
-#define R9A07G044_CLK_RSPI2 47
-#define R9A07G044_CLK_ADC 48
-#define R9A07G044_CLK_TSU_PCLK 49
-#define R9A07G044_CLK_SPI 50
-#define R9A07G044_CLK_MIPI_DSI_V 51
-#define R9A07G044_CLK_MIPI_DSI_PIN 52
+#define R9A07G044_CA55_SCLK 0
+#define R9A07G044_CA55_PCLK 1
+#define R9A07G044_CA55_ATCLK 2
+#define R9A07G044_CA55_GICCLK 3
+#define R9A07G044_CA55_PERICLK 4
+#define R9A07G044_CA55_ACLK 5
+#define R9A07G044_CA55_TSCLK 6
+#define R9A07G044_GIC600_GICCLK 7
+#define R9A07G044_IA55_CLK 8
+#define R9A07G044_IA55_PCLK 9
+#define R9A07G044_MHU_PCLK 10
+#define R9A07G044_SYC_CNT_CLK 11
+#define R9A07G044_DMAC_ACLK 12
+#define R9A07G044_DMAC_PCLK 13
+#define R9A07G044_OSTM0_PCLK 14
+#define R9A07G044_OSTM1_PCLK 15
+#define R9A07G044_OSTM2_PCLK 16
+#define R9A07G044_MTU_X_MCK_MTU3 17
+#define R9A07G044_POE3_CLKM_POE 18
+#define R9A07G044_GPT_PCLK 19
+#define R9A07G044_POEG_A_CLKP 20
+#define R9A07G044_POEG_B_CLKP 21
+#define R9A07G044_POEG_C_CLKP 22
+#define R9A07G044_POEG_D_CLKP 23
+#define R9A07G044_WDT0_PCLK 24
+#define R9A07G044_WDT0_CLK 25
+#define R9A07G044_WDT1_PCLK 26
+#define R9A07G044_WDT1_CLK 27
+#define R9A07G044_WDT2_PCLK 28
+#define R9A07G044_WDT2_CLK 29
+#define R9A07G044_SPI_CLK2 30
+#define R9A07G044_SPI_CLK 31
+#define R9A07G044_SDHI0_IMCLK 32
+#define R9A07G044_SDHI0_IMCLK2 33
+#define R9A07G044_SDHI0_CLK_HS 34
+#define R9A07G044_SDHI0_ACLK 35
+#define R9A07G044_SDHI1_IMCLK 36
+#define R9A07G044_SDHI1_IMCLK2 37
+#define R9A07G044_SDHI1_CLK_HS 38
+#define R9A07G044_SDHI1_ACLK 39
+#define R9A07G044_GPU_CLK 40
+#define R9A07G044_GPU_AXI_CLK 41
+#define R9A07G044_GPU_ACE_CLK 42
+#define R9A07G044_ISU_ACLK 43
+#define R9A07G044_ISU_PCLK 44
+#define R9A07G044_H264_CLK_A 45
+#define R9A07G044_H264_CLK_P 46
+#define R9A07G044_CRU_SYSCLK 47
+#define R9A07G044_CRU_VCLK 48
+#define R9A07G044_CRU_PCLK 49
+#define R9A07G044_CRU_ACLK 50
+#define R9A07G044_MIPI_DSI_PLLCLK 51
+#define R9A07G044_MIPI_DSI_SYSCLK 52
+#define R9A07G044_MIPI_DSI_ACLK 53
+#define R9A07G044_MIPI_DSI_PCLK 54
+#define R9A07G044_MIPI_DSI_VCLK 55
+#define R9A07G044_MIPI_DSI_LPCLK 56
+#define R9A07G044_LCDC_CLK_A 57
+#define R9A07G044_LCDC_CLK_P 58
+#define R9A07G044_LCDC_CLK_D 59
+#define R9A07G044_SSI0_PCLK2 60
+#define R9A07G044_SSI0_PCLK_SFR 61
+#define R9A07G044_SSI1_PCLK2 62
+#define R9A07G044_SSI1_PCLK_SFR 63
+#define R9A07G044_SSI2_PCLK2 64
+#define R9A07G044_SSI2_PCLK_SFR 65
+#define R9A07G044_SSI3_PCLK2 66
+#define R9A07G044_SSI3_PCLK_SFR 67
+#define R9A07G044_SRC_CLKP 68
+#define R9A07G044_USB_U2H0_HCLK 69
+#define R9A07G044_USB_U2H1_HCLK 70
+#define R9A07G044_USB_U2P_EXR_CPUCLK 71
+#define R9A07G044_USB_PCLK 72
+#define R9A07G044_ETH0_CLK_AXI 73
+#define R9A07G044_ETH0_CLK_CHI 74
+#define R9A07G044_ETH1_CLK_AXI 75
+#define R9A07G044_ETH1_CLK_CHI 76
+#define R9A07G044_I2C0_PCLK 77
+#define R9A07G044_I2C1_PCLK 78
+#define R9A07G044_I2C2_PCLK 79
+#define R9A07G044_I2C3_PCLK 80
+#define R9A07G044_SCIF0_CLK_PCK 81
+#define R9A07G044_SCIF1_CLK_PCK 82
+#define R9A07G044_SCIF2_CLK_PCK 83
+#define R9A07G044_SCIF3_CLK_PCK 84
+#define R9A07G044_SCIF4_CLK_PCK 85
+#define R9A07G044_SCI0_CLKP 86
+#define R9A07G044_SCI1_CLKP 87
+#define R9A07G044_IRDA_CLKP 88
+#define R9A07G044_RSPI0_CLKB 89
+#define R9A07G044_RSPI1_CLKB 90
+#define R9A07G044_RSPI2_CLKB 91
+#define R9A07G044_CANFD_PCLK 92
+#define R9A07G044_GPIO_HCLK 93
+#define R9A07G044_ADC_ADCLK 94
+#define R9A07G044_ADC_PCLK 95
+#define R9A07G044_TSU_PCLK 96
+
+/* R9A07G044 Resets */
+#define R9A07G044_CA55_RST_1_0 0
+#define R9A07G044_CA55_RST_1_1 1
+#define R9A07G044_CA55_RST_3_0 2
+#define R9A07G044_CA55_RST_3_1 3
+#define R9A07G044_CA55_RST_4 4
+#define R9A07G044_CA55_RST_5 5
+#define R9A07G044_CA55_RST_6 6
+#define R9A07G044_CA55_RST_7 7
+#define R9A07G044_CA55_RST_8 8
+#define R9A07G044_CA55_RST_9 9
+#define R9A07G044_CA55_RST_10 10
+#define R9A07G044_CA55_RST_11 11
+#define R9A07G044_CA55_RST_12 12
+#define R9A07G044_GIC600_GICRESET_N 13
+#define R9A07G044_GIC600_DBG_GICRESET_N 14
+#define R9A07G044_IA55_RESETN 15
+#define R9A07G044_MHU_RESETN 16
+#define R9A07G044_DMAC_ARESETN 17
+#define R9A07G044_DMAC_RST_ASYNC 18
+#define R9A07G044_SYC_RESETN 19
+#define R9A07G044_OSTM0_PRESETZ 20
+#define R9A07G044_OSTM1_PRESETZ 21
+#define R9A07G044_OSTM2_PRESETZ 22
+#define R9A07G044_MTU_X_PRESET_MTU3 23
+#define R9A07G044_POE3_RST_M_REG 24
+#define R9A07G044_GPT_RST_C 25
+#define R9A07G044_POEG_A_RST 26
+#define R9A07G044_POEG_B_RST 27
+#define R9A07G044_POEG_C_RST 28
+#define R9A07G044_POEG_D_RST 29
+#define R9A07G044_WDT0_PRESETN 30
+#define R9A07G044_WDT1_PRESETN 31
+#define R9A07G044_WDT2_PRESETN 32
+#define R9A07G044_SPI_RST 33
+#define R9A07G044_SDHI0_IXRST 34
+#define R9A07G044_SDHI1_IXRST 35
+#define R9A07G044_GPU_RESETN 36
+#define R9A07G044_GPU_AXI_RESETN 37
+#define R9A07G044_GPU_ACE_RESETN 38
+#define R9A07G044_ISU_ARESETN 39
+#define R9A07G044_ISU_PRESETN 40
+#define R9A07G044_H264_X_RESET_VCP 41
+#define R9A07G044_H264_CP_PRESET_P 42
+#define R9A07G044_CRU_CMN_RSTB 43
+#define R9A07G044_CRU_PRESETN 44
+#define R9A07G044_CRU_ARESETN 45
+#define R9A07G044_MIPI_DSI_CMN_RSTB 46
+#define R9A07G044_MIPI_DSI_ARESET_N 47
+#define R9A07G044_MIPI_DSI_PRESET_N 48
+#define R9A07G044_LCDC_RESET_N 49
+#define R9A07G044_SSI0_RST_M2_REG 50
+#define R9A07G044_SSI1_RST_M2_REG 51
+#define R9A07G044_SSI2_RST_M2_REG 52
+#define R9A07G044_SSI3_RST_M2_REG 53
+#define R9A07G044_SRC_RST 54
+#define R9A07G044_USB_U2H0_HRESETN 55
+#define R9A07G044_USB_U2H1_HRESETN 56
+#define R9A07G044_USB_U2P_EXL_SYSRST 57
+#define R9A07G044_USB_PRESETN 58
+#define R9A07G044_ETH0_RST_HW_N 59
+#define R9A07G044_ETH1_RST_HW_N 60
+#define R9A07G044_I2C0_MRST 61
+#define R9A07G044_I2C1_MRST 62
+#define R9A07G044_I2C2_MRST 63
+#define R9A07G044_I2C3_MRST 64
+#define R9A07G044_SCIF0_RST_SYSTEM_N 65
+#define R9A07G044_SCIF1_RST_SYSTEM_N 66
+#define R9A07G044_SCIF2_RST_SYSTEM_N 67
+#define R9A07G044_SCIF3_RST_SYSTEM_N 68
+#define R9A07G044_SCIF4_RST_SYSTEM_N 69
+#define R9A07G044_SCI0_RST 70
+#define R9A07G044_SCI1_RST 71
+#define R9A07G044_IRDA_RST 72
+#define R9A07G044_RSPI0_RST 73
+#define R9A07G044_RSPI1_RST 74
+#define R9A07G044_RSPI2_RST 75
+#define R9A07G044_CANFD_RSTP_N 76
+#define R9A07G044_CANFD_RSTC_N 77
+#define R9A07G044_GPIO_RSTN 78
+#define R9A07G044_GPIO_PORT_RESETN 79
+#define R9A07G044_GPIO_SPARE_RESETN 80
+#define R9A07G044_ADC_PRESETN 81
+#define R9A07G044_ADC_ADRST_N 82
+#define R9A07G044_TSU_PRESETN 83
#endif /* __DT_BINDINGS_CLOCK_R9A07G044_CPG_H__ */
* Maximum number of blkcg policies allowed to be registered concurrently.
* Defined here to simplify include dependency.
*/
-#define BLKCG_MAX_POLS 5
+#define BLKCG_MAX_POLS 6
typedef void (rq_end_io_fn)(struct request *, blk_status_t);
void *tailcall_target;
void *tailcall_bypass;
void *bypass_addr;
+ void *aux;
union {
struct {
struct bpf_map *map;
BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter)
#ifdef CONFIG_NET
BPF_LINK_TYPE(BPF_LINK_TYPE_NETNS, netns)
+BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp)
#endif
};
u64 map_key_state; /* constant (32 bit) key tracking for maps */
int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
- int sanitize_stack_off; /* stack slot to be cleared */
u32 seen; /* this insn was processed by the verifier at env->pass_cnt */
+ bool sanitize_stack_spill; /* subject to Spectre v4 sanitation */
bool zext_dst; /* this insn zero extends dst reg */
u8 alu_state; /* used in combination with alu_limit */
u32 used_map_cnt; /* number of used maps */
u32 used_btf_cnt; /* number of used BTF objects */
u32 id_gen; /* used to generate unique reg IDs */
+ bool explore_alu_limits;
bool allow_ptr_leaks;
bool allow_uninit_stack;
bool allow_ptr_to_map_access;
enum ethtool_link_mode_bit_indices link_mode);
/**
+ * ethtool_get_phc_vclocks - Derive phc vclocks information, and caller
+ * is responsible to free memory of vclock_index
+ * @dev: pointer to net_device structure
+ * @vclock_index: pointer to pointer of vclock index
+ *
+ * Return number of phc vclocks
+ */
+int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index);
+
+/**
* ethtool_sprintf - Write formatted string to ethtool string data
* @data: Pointer to start of string to update
* @fmt: Format of string to write
/* unused opcode to mark call to interpreter with arguments */
#define BPF_CALL_ARGS 0xe0
+/* unused opcode to mark speculation barrier for mitigating
+ * Speculative Store Bypass
+ */
+#define BPF_NOSPEC 0xc0
+
/* As per nm, we expose JITed images as text (code) section for
* kallsyms. That way, tools like perf can find it to match
* addresses.
.off = 0, \
.imm = 0 })
+/* Speculation barrier */
+
+#define BPF_ST_NOSPEC() \
+ ((struct bpf_insn) { \
+ .code = BPF_ST | BPF_NOSPEC, \
+ .dst_reg = 0, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = 0 })
+
/* Internal classic blocks for direct assignment */
#define __BPF_STMT(CODE, K) \
extern int generic_parse_monolithic(struct fs_context *fc, void *data);
extern int vfs_get_tree(struct fs_context *fc);
extern void put_fs_context(struct fs_context *fc);
+extern int vfs_parse_fs_param_source(struct fs_context *fc,
+ struct fs_parameter *param);
+extern void fc_drop_locked(struct fs_context *fc);
/*
* sget() wrappers to be called from the ->get_tree() op.
VM_BUG_ON(offset + len > PAGE_SIZE);
memcpy(to + offset, from, len);
+ flush_dcache_page(page);
kunmap_local(to);
}
static inline void memzero_page(struct page *page, size_t offset, size_t len)
{
- char *addr = kmap_atomic(page);
+ char *addr = kmap_local_page(page);
memset(addr + offset, 0, len);
- kunmap_atomic(addr);
+ flush_dcache_page(page);
+ kunmap_local(addr);
}
#endif /* _LINUX_HIGHMEM_H */
/* Get the device * from ishtp device instance */
struct device *ishtp_device(struct ishtp_cl_device *cl_device);
+/* wait for IPC resume */
+bool ishtp_wait_resume(struct ishtp_device *dev);
/* Trace interface for clients */
ishtp_print_log ishtp_trace_callback(struct ishtp_cl_device *cl_device);
/* Get device pointer of PCI device for DMA acces */
#define _LINUX_KASAN_H
#include <linux/bug.h>
+#include <linux/kernel.h>
#include <linux/static_key.h>
#include <linux/types.h>
#define MARVELL_PHY_ID_88E1545 0x01410ea0
#define MARVELL_PHY_ID_88E1548P 0x01410ec0
#define MARVELL_PHY_ID_88E3016 0x01410e60
+#define MARVELL_PHY_ID_88X3310 0x002b09a0
#define MARVELL_PHY_ID_88E2110 0x002b09b0
#define MARVELL_PHY_ID_88X2222 0x01410f10
-/* PHY IDs and mask for Alaska 10G PHYs */
-#define MARVELL_PHY_ID_88X33X0_MASK 0xfffffff8
-#define MARVELL_PHY_ID_88X3310 0x002b09a0
-#define MARVELL_PHY_ID_88X3340 0x002b09a8
-
/* Marvel 88E1111 in Finisar SFP module with modified PHY ID */
#define MARVELL_PHY_ID_88E1111_FINISAR 0x01ff0cc0
*/
#define for_each_mem_range(i, p_start, p_end) \
__for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, \
- MEMBLOCK_NONE, p_start, p_end, NULL)
+ MEMBLOCK_HOTPLUG, p_start, p_end, NULL)
/**
* for_each_mem_range_rev - reverse iterate through memblock areas from
*/
#define for_each_mem_range_rev(i, p_start, p_end) \
__for_each_mem_range_rev(i, &memblock.memory, NULL, NUMA_NO_NODE, \
- MEMBLOCK_NONE, p_start, p_end, NULL)
+ MEMBLOCK_HOTPLUG, p_start, p_end, NULL)
/**
* for_each_reserved_mem_range - iterate over all reserved memblock areas
#define RT5033_REGULATOR_BUCK_VOLTAGE_MIN 1000000U
#define RT5033_REGULATOR_BUCK_VOLTAGE_MAX 3000000U
#define RT5033_REGULATOR_BUCK_VOLTAGE_STEP 100000U
-#define RT5033_REGULATOR_BUCK_VOLTAGE_STEP_NUM 32
+#define RT5033_REGULATOR_BUCK_VOLTAGE_STEP_NUM 21
/* RT5033 regulator LDO output voltage uV */
#define RT5033_REGULATOR_LDO_VOLTAGE_MIN 1200000U
#define RT5033_REGULATOR_LDO_VOLTAGE_MAX 3000000U
#define RT5033_REGULATOR_LDO_VOLTAGE_STEP 100000U
-#define RT5033_REGULATOR_LDO_VOLTAGE_STEP_NUM 32
+#define RT5033_REGULATOR_LDO_VOLTAGE_STEP_NUM 19
/* RT5033 regulator SAFE LDO output voltage uV */
#define RT5033_REGULATOR_SAFE_LDO_VOLTAGE 4900000U
* host and device execution environments match and
* channels are in a DISABLED state.
* @mhi_dev: Device associated with the channels
+ * @flags: MHI channel flags
*/
-int mhi_prepare_for_transfer(struct mhi_device *mhi_dev);
+int mhi_prepare_for_transfer(struct mhi_device *mhi_dev,
+ unsigned int flags);
+
+/* Automatically allocate and queue inbound buffers */
+#define MHI_CH_INBOUND_ALLOC_BUFS BIT(0)
/**
* mhi_unprepare_from_transfer - Reset UL and DL channels for data transfer.
struct page *newpage, struct page *page);
extern int migrate_page_move_mapping(struct address_space *mapping,
struct page *newpage, struct page *page, int extra_count);
-extern void copy_huge_page(struct page *dst, struct page *src);
#else
static inline void putback_movable_pages(struct list_head *l) {}
{
return -ENOSYS;
}
-
-static inline void copy_huge_page(struct page *dst, struct page *src)
-{
-}
#endif /* CONFIG_MIGRATION */
#ifdef CONFIG_COMPACTION
void put_pages_list(struct list_head *pages);
void split_page(struct page *page, unsigned int order);
+void copy_huge_page(struct page *dst, struct page *src);
/*
* Compound pages have a destructor function. Provide a
}
#endif /* !__PAGETABLE_P4D_FOLDED */
-#ifndef __PAGETABLE_PUD_FOLDED
int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot);
-int pud_clear_huge(pud_t *pud);
-#else
-static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
-{
- return 0;
-}
-static inline int pud_clear_huge(pud_t *pud)
-{
- return 0;
-}
-#endif /* !__PAGETABLE_PUD_FOLDED */
-
-#ifndef __PAGETABLE_PMD_FOLDED
int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot);
+int pud_clear_huge(pud_t *pud);
int pmd_clear_huge(pmd_t *pmd);
-#else
-static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
-{
- return 0;
-}
-static inline int pmd_clear_huge(pmd_t *pmd)
-{
- return 0;
-}
-#endif /* !__PAGETABLE_PMD_FOLDED */
-
int p4d_free_pud_page(p4d_t *p4d, unsigned long addr);
int pud_free_pmd_page(pud_t *pud, unsigned long addr);
int pmd_free_pte_page(pmd_t *pmd, unsigned long addr);
#include <linux/device.h>
#include <linux/pps_kernel.h>
#include <linux/ptp_clock.h>
+#include <linux/timecounter.h>
+#include <linux/skbuff.h>
+#define PTP_CLOCK_NAME_LEN 32
/**
* struct ptp_clock_request - request PTP clock event
*
struct ptp_clock_info {
struct module *owner;
- char name[16];
+ char name[PTP_CLOCK_NAME_LEN];
s32 max_adj;
int n_alarm;
int n_ext_ts;
*/
void ptp_cancel_worker_sync(struct ptp_clock *ptp);
+/**
+ * ptp_get_vclocks_index() - get all vclocks index on pclock, and
+ * caller is responsible to free memory
+ * of vclock_index
+ *
+ * @pclock_index: phc index of ptp pclock.
+ * @vclock_index: pointer to pointer of vclock index.
+ *
+ * return number of vclocks.
+ */
+int ptp_get_vclocks_index(int pclock_index, int **vclock_index);
+
+/**
+ * ptp_convert_timestamp() - convert timestamp to a ptp vclock time
+ *
+ * @hwtstamps: skb_shared_hwtstamps structure pointer
+ * @vclock_index: phc index of ptp vclock.
+ */
+void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps,
+ int vclock_index);
+
#else
static inline struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info,
struct device *parent)
{ return -EOPNOTSUPP; }
static inline void ptp_cancel_worker_sync(struct ptp_clock *ptp)
{ }
+static inline int ptp_get_vclocks_index(int pclock_index, int **vclock_index)
+{ return 0; }
+static inline void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps,
+ int vclock_index)
+{ }
#endif
return 0;
}
-#define try_to_unmap(page, refs) false
+static inline void try_to_unmap(struct page *page, enum ttu_flags flags)
+{
+}
static inline int page_mkclean(struct page *page)
{
* to sustained performance level mapping
* @est_power_get: gets the estimated power cost for a given performance domain
* at a given frequency
+ * @fast_switch_possible: indicates if fast DVFS switching is possible or not
+ * for a given device
+ * @power_scale_mw_get: indicates if the power values provided are in milliWatts
+ * or in some other (abstract) scale
*/
struct scmi_perf_proto_ops {
int (*limits_set)(const struct scmi_protocol_handle *ph, u32 domain,
};
/**
- * scmi_sensor_reading - represent a timestamped read
+ * struct scmi_sensor_reading - represent a timestamped read
*
* Used by @reading_get_timestamped method.
*
};
/**
- * scmi_range_attrs - specifies a sensor or axis values' range
+ * struct scmi_range_attrs - specifies a sensor or axis values' range
* @min_range: The minimum value which can be represented by the sensor/axis.
* @max_range: The maximum value which can be represented by the sensor/axis.
*/
};
/**
- * scmi_sensor_axis_info - describes one sensor axes
+ * struct scmi_sensor_axis_info - describes one sensor axes
* @id: The axes ID.
* @type: Axes type. Chosen amongst one of @enum scmi_sensor_class.
* @scale: Power-of-10 multiplier applied to the axis unit.
};
/**
- * scmi_sensor_intervals_info - describes number and type of available update
- * intervals
+ * struct scmi_sensor_intervals_info - describes number and type of available
+ * update intervals
* @segmented: Flag for segmented intervals' representation. When True there
* will be exactly 3 intervals in @desc, with each entry
* representing a member of a segment in this order:
* OPP is an index to the list return by @dvfs_get_info
* @dvfs_get_info: returns the DVFS capabilities of the given power
* domain. It includes the OPP list and the latency information
+ * @device_domain_id: gets the scpi domain id for a given device
+ * @get_transition_latency: gets the DVFS transition latency for a given device
+ * @add_opps_to_device: adds all the OPPs for a given device
+ * @sensor_get_capability: get the list of capabilities for the sensors
+ * @sensor_get_info: get the information of the specified sensor
+ * @sensor_get_value: gets the current value of the sensor
+ * @device_get_power_state: gets the power state of a power domain
+ * @device_set_power_state: sets the power state of a power domain
*/
struct scpi_ops {
u32 (*get_version)(void);
if (sysrq_ch)
handle_sysrq(sysrq_ch);
}
+
+static inline void uart_unlock_and_check_sysrq_irqrestore(struct uart_port *port,
+ unsigned long flags)
+{
+ int sysrq_ch;
+
+ if (!port->has_sysrq) {
+ spin_unlock_irqrestore(&port->lock, flags);
+ return;
+ }
+
+ sysrq_ch = port->sysrq_ch;
+ port->sysrq_ch = 0;
+
+ spin_unlock_irqrestore(&port->lock, flags);
+
+ if (sysrq_ch)
+ handle_sysrq(sysrq_ch);
+}
#else /* CONFIG_MAGIC_SYSRQ_SERIAL */
static inline int uart_handle_sysrq_char(struct uart_port *port, unsigned int ch)
{
{
spin_unlock(&port->lock);
}
+static inline void uart_unlock_and_check_sysrq_irqrestore(struct uart_port *port,
+ unsigned long flags)
+{
+ spin_unlock_irqrestore(&port->lock, flags);
+}
#endif /* CONFIG_MAGIC_SYSRQ_SERIAL */
/*
return rcu_dereference_sk_user_data(sk);
}
+static inline void sk_psock_set_state(struct sk_psock *psock,
+ enum sk_psock_state_bits bit)
+{
+ set_bit(bit, &psock->state);
+}
+
+static inline void sk_psock_clear_state(struct sk_psock *psock,
+ enum sk_psock_state_bits bit)
+{
+ clear_bit(bit, &psock->state);
+}
+
+static inline bool sk_psock_test_state(const struct sk_psock *psock,
+ enum sk_psock_state_bits bit)
+{
+ return test_bit(bit, &psock->state);
+}
+
+static inline void sock_drop(struct sock *sk, struct sk_buff *skb)
+{
+ sk_drops_add(sk, skb);
+ kfree_skb(skb);
+}
+
+static inline void drop_sk_msg(struct sk_psock *psock, struct sk_msg *msg)
+{
+ if (msg->skb)
+ sock_drop(psock->sk, msg->skb);
+ kfree(msg);
+}
+
static inline void sk_psock_queue_msg(struct sk_psock *psock,
struct sk_msg *msg)
{
spin_lock_bh(&psock->ingress_lock);
- list_add_tail(&msg->list, &psock->ingress_msg);
+ if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
+ list_add_tail(&msg->list, &psock->ingress_msg);
+ else
+ drop_sk_msg(psock, msg);
spin_unlock_bh(&psock->ingress_lock);
}
psock->psock_update_sk_prot(sk, psock, true);
}
-static inline void sk_psock_set_state(struct sk_psock *psock,
- enum sk_psock_state_bits bit)
-{
- set_bit(bit, &psock->state);
-}
-
-static inline void sk_psock_clear_state(struct sk_psock *psock,
- enum sk_psock_state_bits bit)
-{
- clear_bit(bit, &psock->state);
-}
-
-static inline bool sk_psock_test_state(const struct sk_psock *psock,
- enum sk_psock_state_bits bit)
-{
- return test_bit(bit, &psock->state);
-}
-
static inline struct sk_psock *sk_psock_get(struct sock *sk)
{
struct sk_psock *psock;
#define EST_GCL 1024
struct stmmac_est {
+ struct mutex lock;
int enable;
+ u32 btr_reserve[2];
u32 btr_offset[2];
u32 btr[2];
u32 ctr[2];
#define TEE_SHM_USER_MAPPED BIT(4) /* Memory mapped in user space */
#define TEE_SHM_POOL BIT(5) /* Memory allocated from pool */
#define TEE_SHM_KERNEL_MAPPED BIT(6) /* Memory mapped in kernel space */
+#define TEE_SHM_PRIV BIT(7) /* Memory private to TEE driver */
struct device;
struct tee_device;
* @returns a pointer to 'struct tee_shm'
*/
struct tee_shm *tee_shm_alloc(struct tee_context *ctx, size_t size, u32 flags);
+struct tee_shm *tee_shm_alloc_kernel_buf(struct tee_context *ctx, size_t size);
/**
* tee_shm_register() - Register shared memory buffer
struct mutex lock;
u8 *host_req_flag;
struct delayed_work hnp_polling_work;
+ bool hnp_work_inited;
bool state_changed;
};
FP_SET_EXCEPTION(FP_EX_INVALID | FP_EX_INVALID_ISI); \
break; \
} \
- /* FALLTHRU */ \
+ fallthrough; \
\
case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NORMAL): \
case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_ZERO): \
void hci_free_dev(struct hci_dev *hdev);
int hci_register_dev(struct hci_dev *hdev);
void hci_unregister_dev(struct hci_dev *hdev);
+void hci_cleanup_dev(struct hci_dev *hdev);
int hci_suspend_dev(struct hci_dev *hdev);
int hci_resume_dev(struct hci_dev *hdev);
int hci_reset_dev(struct hci_dev *hdev);
*/
#define BOND_LINK_NOCHANGE -1
+struct bond_ipsec {
+ struct list_head list;
+ struct xfrm_state *xs;
+};
+
/*
* Here are the locking policies for the two bonding locks:
* Get rcu_read_lock when reading or RTNL when writing slave list.
#endif /* CONFIG_DEBUG_FS */
struct rtnl_link_stats64 bond_stats;
#ifdef CONFIG_XFRM_OFFLOAD
- struct xfrm_state *xs;
+ struct list_head ipsec_list;
+ /* protecting ipsec_list */
+ spinlock_t ipsec_lock;
#endif /* CONFIG_XFRM_OFFLOAD */
};
static inline bool sk_can_busy_loop(const struct sock *sk)
{
- return sk->sk_ll_usec && !signal_pending(current);
+ return READ_ONCE(sk->sk_ll_usec) && !signal_pending(current);
}
bool sk_busy_loop_end(void *p, unsigned long start_time);
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) ST-Ericsson AB 2010
- * Author: Daniel Martensson / daniel.martensson@stericsson.com
- * Dmitry.Tarnyagin / dmitry.tarnyagin@stericsson.com
- */
-
-#ifndef CAIF_HSI_H_
-#define CAIF_HSI_H_
-
-#include <net/caif/caif_layer.h>
-#include <net/caif/caif_device.h>
-#include <linux/atomic.h>
-
-/*
- * Maximum number of CAIF frames that can reside in the same HSI frame.
- */
-#define CFHSI_MAX_PKTS 15
-
-/*
- * Maximum number of bytes used for the frame that can be embedded in the
- * HSI descriptor.
- */
-#define CFHSI_MAX_EMB_FRM_SZ 96
-
-/*
- * Decides if HSI buffers should be prefilled with 0xFF pattern for easier
- * debugging. Both TX and RX buffers will be filled before the transfer.
- */
-#define CFHSI_DBG_PREFILL 0
-
-/* Structure describing a HSI packet descriptor. */
-#pragma pack(1) /* Byte alignment. */
-struct cfhsi_desc {
- u8 header;
- u8 offset;
- u16 cffrm_len[CFHSI_MAX_PKTS];
- u8 emb_frm[CFHSI_MAX_EMB_FRM_SZ];
-};
-#pragma pack() /* Default alignment. */
-
-/* Size of the complete HSI packet descriptor. */
-#define CFHSI_DESC_SZ (sizeof(struct cfhsi_desc))
-
-/*
- * Size of the complete HSI packet descriptor excluding the optional embedded
- * CAIF frame.
- */
-#define CFHSI_DESC_SHORT_SZ (CFHSI_DESC_SZ - CFHSI_MAX_EMB_FRM_SZ)
-
-/*
- * Maximum bytes transferred in one transfer.
- */
-#define CFHSI_MAX_CAIF_FRAME_SZ 4096
-
-#define CFHSI_MAX_PAYLOAD_SZ (CFHSI_MAX_PKTS * CFHSI_MAX_CAIF_FRAME_SZ)
-
-/* Size of the complete HSI TX buffer. */
-#define CFHSI_BUF_SZ_TX (CFHSI_DESC_SZ + CFHSI_MAX_PAYLOAD_SZ)
-
-/* Size of the complete HSI RX buffer. */
-#define CFHSI_BUF_SZ_RX ((2 * CFHSI_DESC_SZ) + CFHSI_MAX_PAYLOAD_SZ)
-
-/* Bitmasks for the HSI descriptor. */
-#define CFHSI_PIGGY_DESC (0x01 << 7)
-
-#define CFHSI_TX_STATE_IDLE 0
-#define CFHSI_TX_STATE_XFER 1
-
-#define CFHSI_RX_STATE_DESC 0
-#define CFHSI_RX_STATE_PAYLOAD 1
-
-/* Bitmasks for power management. */
-#define CFHSI_WAKE_UP 0
-#define CFHSI_WAKE_UP_ACK 1
-#define CFHSI_WAKE_DOWN_ACK 2
-#define CFHSI_AWAKE 3
-#define CFHSI_WAKELOCK_HELD 4
-#define CFHSI_SHUTDOWN 5
-#define CFHSI_FLUSH_FIFO 6
-
-#ifndef CFHSI_INACTIVITY_TOUT
-#define CFHSI_INACTIVITY_TOUT (1 * HZ)
-#endif /* CFHSI_INACTIVITY_TOUT */
-
-#ifndef CFHSI_WAKE_TOUT
-#define CFHSI_WAKE_TOUT (3 * HZ)
-#endif /* CFHSI_WAKE_TOUT */
-
-#ifndef CFHSI_MAX_RX_RETRIES
-#define CFHSI_MAX_RX_RETRIES (10 * HZ)
-#endif
-
-/* Structure implemented by the CAIF HSI driver. */
-struct cfhsi_cb_ops {
- void (*tx_done_cb) (struct cfhsi_cb_ops *drv);
- void (*rx_done_cb) (struct cfhsi_cb_ops *drv);
- void (*wake_up_cb) (struct cfhsi_cb_ops *drv);
- void (*wake_down_cb) (struct cfhsi_cb_ops *drv);
-};
-
-/* Structure implemented by HSI device. */
-struct cfhsi_ops {
- int (*cfhsi_up) (struct cfhsi_ops *dev);
- int (*cfhsi_down) (struct cfhsi_ops *dev);
- int (*cfhsi_tx) (u8 *ptr, int len, struct cfhsi_ops *dev);
- int (*cfhsi_rx) (u8 *ptr, int len, struct cfhsi_ops *dev);
- int (*cfhsi_wake_up) (struct cfhsi_ops *dev);
- int (*cfhsi_wake_down) (struct cfhsi_ops *dev);
- int (*cfhsi_get_peer_wake) (struct cfhsi_ops *dev, bool *status);
- int (*cfhsi_fifo_occupancy) (struct cfhsi_ops *dev, size_t *occupancy);
- int (*cfhsi_rx_cancel)(struct cfhsi_ops *dev);
- struct cfhsi_cb_ops *cb_ops;
-};
-
-/* Structure holds status of received CAIF frames processing */
-struct cfhsi_rx_state {
- int state;
- int nfrms;
- int pld_len;
- int retries;
- bool piggy_desc;
-};
-
-/* Priority mapping */
-enum {
- CFHSI_PRIO_CTL = 0,
- CFHSI_PRIO_VI,
- CFHSI_PRIO_VO,
- CFHSI_PRIO_BEBK,
- CFHSI_PRIO_LAST,
-};
-
-struct cfhsi_config {
- u32 inactivity_timeout;
- u32 aggregation_timeout;
- u32 head_align;
- u32 tail_align;
- u32 q_high_mark;
- u32 q_low_mark;
-};
-
-/* Structure implemented by CAIF HSI drivers. */
-struct cfhsi {
- struct caif_dev_common cfdev;
- struct net_device *ndev;
- struct platform_device *pdev;
- struct sk_buff_head qhead[CFHSI_PRIO_LAST];
- struct cfhsi_cb_ops cb_ops;
- struct cfhsi_ops *ops;
- int tx_state;
- struct cfhsi_rx_state rx_state;
- struct cfhsi_config cfg;
- int rx_len;
- u8 *rx_ptr;
- u8 *tx_buf;
- u8 *rx_buf;
- u8 *rx_flip_buf;
- spinlock_t lock;
- int flow_off_sent;
- struct list_head list;
- struct work_struct wake_up_work;
- struct work_struct wake_down_work;
- struct work_struct out_of_sync_work;
- struct workqueue_struct *wq;
- wait_queue_head_t wake_up_wait;
- wait_queue_head_t wake_down_wait;
- wait_queue_head_t flush_fifo_wait;
- struct timer_list inactivity_timer;
- struct timer_list rx_slowpath_timer;
-
- /* TX aggregation */
- int aggregation_len;
- struct timer_list aggregation_timer;
-
- unsigned long bits;
-};
-extern struct platform_driver cfhsi_driver;
-
-/**
- * enum ifla_caif_hsi - CAIF HSI NetlinkRT parameters.
- * @IFLA_CAIF_HSI_INACTIVITY_TOUT: Inactivity timeout before
- * taking the HSI wakeline down, in milliseconds.
- * When using RT Netlink to create, destroy or configure a CAIF HSI interface,
- * enum ifla_caif_hsi is used to specify the configuration attributes.
- */
-enum ifla_caif_hsi {
- __IFLA_CAIF_HSI_UNSPEC,
- __IFLA_CAIF_HSI_INACTIVITY_TOUT,
- __IFLA_CAIF_HSI_AGGREGATION_TOUT,
- __IFLA_CAIF_HSI_HEAD_ALIGN,
- __IFLA_CAIF_HSI_TAIL_ALIGN,
- __IFLA_CAIF_HSI_QHIGH_WATERMARK,
- __IFLA_CAIF_HSI_QLOW_WATERMARK,
- __IFLA_CAIF_HSI_MAX
-};
-
-struct cfhsi_ops *cfhsi_get_ops(void);
-
-#endif /* CAIF_HSI_H_ */
return &md_dst->u.tun_info;
dst = skb_dst(skb);
- if (dst && dst->lwtstate)
+ if (dst && dst->lwtstate &&
+ (dst->lwtstate->type == LWTUNNEL_ENCAP_IP ||
+ dst->lwtstate->type == LWTUNNEL_ENCAP_IP6))
return lwt_tun_info(dst->lwtstate);
return NULL;
}
/**
- * flow_action_has_one_action() - check if exactly one action is present
+ * flow_offload_has_one_action() - check if exactly one action is present
* @action: tc filter flow offload action
*
* Returns true if exactly one action is present.
int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
int (*output)(struct net *, struct sock *, struct sk_buff *));
-static inline int ip6_skb_dst_mtu(struct sk_buff *skb)
+static inline unsigned int ip6_skb_dst_mtu(struct sk_buff *skb)
{
- int mtu;
+ unsigned int mtu;
struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ?
inet6_sk(skb->sk) : NULL;
#include <linux/if_ether.h>
/* Lengths of frame formats */
-#define LLC_PDU_LEN_I 4 /* header and 2 control bytes */
-#define LLC_PDU_LEN_S 4
-#define LLC_PDU_LEN_U 3 /* header and 1 control byte */
+#define LLC_PDU_LEN_I 4 /* header and 2 control bytes */
+#define LLC_PDU_LEN_S 4
+#define LLC_PDU_LEN_U 3 /* header and 1 control byte */
+/* header and 1 control byte and XID info */
+#define LLC_PDU_LEN_U_XID (LLC_PDU_LEN_U + sizeof(struct llc_xid_info))
/* Known SAP addresses */
#define LLC_GLOBAL_SAP 0xFF
#define LLC_NULL_SAP 0x00 /* not network-layer visible */
#define LLC_PDU_TYPE_U_MASK 0x03 /* 8-bit control field */
#define LLC_PDU_TYPE_MASK 0x03
-#define LLC_PDU_TYPE_I 0 /* first bit */
-#define LLC_PDU_TYPE_S 1 /* first two bits */
-#define LLC_PDU_TYPE_U 3 /* first two bits */
+#define LLC_PDU_TYPE_I 0 /* first bit */
+#define LLC_PDU_TYPE_S 1 /* first two bits */
+#define LLC_PDU_TYPE_U 3 /* first two bits */
+#define LLC_PDU_TYPE_U_XID 4 /* private type for detecting XID commands */
#define LLC_PDU_TYPE_IS_I(pdu) \
((!(pdu->ctrl_1 & LLC_PDU_TYPE_I_MASK)) ? 1 : 0)
static inline void llc_pdu_header_init(struct sk_buff *skb, u8 type,
u8 ssap, u8 dsap, u8 cr)
{
- const int hlen = type == LLC_PDU_TYPE_U ? 3 : 4;
+ int hlen = 4; /* default value for I and S types */
struct llc_pdu_un *pdu;
+ switch (type) {
+ case LLC_PDU_TYPE_U:
+ hlen = 3;
+ break;
+ case LLC_PDU_TYPE_U_XID:
+ hlen = 6;
+ break;
+ }
+
skb_push(skb, hlen);
skb_reset_network_header(skb);
pdu = llc_pdu_un_hdr(skb);
xid_info->fmt_id = LLC_XID_FMT_ID; /* 0x81 */
xid_info->type = svcs_supported;
xid_info->rw = rx_window << 1; /* size of receive window */
- skb_put(skb, sizeof(struct llc_xid_info));
+
+ /* no need to push/put since llc_pdu_header_init() has already
+ * pushed 3 + 3 bytes
+ */
}
/**
bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
unsigned int *size, unsigned int remaining,
struct mptcp_out_options *opts);
-void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb);
+bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb);
void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
struct mptcp_out_options *opts);
return false;
}
-static inline void mptcp_incoming_options(struct sock *sk,
+static inline bool mptcp_incoming_options(struct sock *sk,
struct sk_buff *skb)
{
+ return true;
}
static inline void mptcp_skb_ext_move(struct sk_buff *to,
void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list);
void nf_conntrack_proto_pernet_init(struct net *net);
-void nf_conntrack_proto_pernet_fini(struct net *net);
int nf_conntrack_proto_init(void);
void nf_conntrack_proto_fini(void);
u8 tcp_loose;
u8 tcp_be_liberal;
u8 tcp_max_retrans;
+ u8 tcp_ignore_invalid_rst;
#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
unsigned int offload_timeout;
unsigned int offload_pickup;
#endif
spinlock_t xfrm_state_lock;
seqcount_spinlock_t xfrm_state_hash_generation;
+ seqcount_spinlock_t xfrm_policy_hash_generation;
spinlock_t xfrm_policy_lock;
struct mutex xfrm_cfg_mutex;
/**
* struct tcf_pkt_info - packet information
+ *
+ * @ptr: start of the pkt data
+ * @nexthdr: offset of the next header
*/
struct tcf_pkt_info {
unsigned char * ptr;
* @ops: the operations lookup table of the corresponding ematch module
* @datalen: length of the ematch specific configuration data
* @data: ematch specific data
+ * @net: the network namespace
*/
struct tcf_ematch {
struct tcf_ematch_ops * ops;
#define SCTP_SCOPE_POLICY_MAX SCTP_SCOPE_POLICY_LINK
/* Based on IPv4 scoping <draft-stewart-tsvwg-sctp-ipv4-00.txt>,
- * SCTP IPv4 unusable addresses: 0.0.0.0/8, 224.0.0.0/4, 198.18.0.0/24,
- * 192.88.99.0/24.
+ * SCTP IPv4 unusable addresses: 0.0.0.0/8, 224.0.0.0/4, 192.88.99.0/24.
* Also, RFC 8.4, non-unicast addresses are not considered valid SCTP
* addresses.
*/
((htonl(INADDR_BROADCAST) == a) || \
ipv4_is_multicast(a) || \
ipv4_is_zeronet(a) || \
- ipv4_is_test_198(a) || \
ipv4_is_anycast_6to4(a))
/* Flags used for the bind address copy functions. */
} cacc;
struct {
+ __u32 last_rtx_chunks;
__u16 pmtu;
__u16 probe_size;
__u16 probe_high;
void sctp_transport_immediate_rtx(struct sctp_transport *);
void sctp_transport_dst_release(struct sctp_transport *t);
void sctp_transport_dst_confirm(struct sctp_transport *t);
-void sctp_transport_pl_send(struct sctp_transport *t);
-void sctp_transport_pl_recv(struct sctp_transport *t);
+bool sctp_transport_pl_send(struct sctp_transport *t);
+bool sctp_transport_pl_recv(struct sctp_transport *t);
/* This is the structure we use to queue packets as they come into
* @sk_timer: sock cleanup timer
* @sk_stamp: time stamp of last packet received
* @sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only
- * @sk_tsflags: SO_TIMESTAMPING socket options
+ * @sk_tsflags: SO_TIMESTAMPING flags
+ * @sk_bind_phc: SO_TIMESTAMPING bind PHC index of PTP virtual clock
+ * for timestamping
* @sk_tskey: counter to disambiguate concurrent tstamp requests
* @sk_zckey: counter to order MSG_ZEROCOPY notifications
* @sk_socket: Identd and reporting IO signals
seqlock_t sk_stamp_seq;
#endif
u16 sk_tsflags;
+ int sk_bind_phc;
u8 sk_shutdown;
u32 sk_tskey;
atomic_t sk_zckey;
int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk);
void sock_set_timestamp(struct sock *sk, int optname, bool valbool);
-int sock_set_timestamping(struct sock *sk, int optname, int val);
+int sock_set_timestamping(struct sock *sk, int optname,
+ struct so_timestamping timestamping);
void sock_enable_timestamps(struct sock *sk);
void sock_no_linger(struct sock *sk);
static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
{
+ /* mptcp hooks are only on the slow path */
+ if (sk_is_mptcp((struct sock *)tp))
+ return;
+
tp->pred_flags = htonl((tp->tcp_header_len << 26) |
ntohl(TCP_FLAG_ACK) |
snd_wnd);
struct rcu_head rcu;
};
-extern unsigned int sysctl_tcp_fastopen_blackhole_timeout;
void tcp_fastopen_active_disable(struct sock *sk);
bool tcp_fastopen_active_should_disable(struct sock *sk);
void tcp_fastopen_active_disable_ofo_check(struct sock *sk);
#ifdef CONFIG_TEGRA_MC
struct tegra_mc *devm_tegra_memory_controller_get(struct device *dev);
+int tegra_mc_probe_device(struct tegra_mc *mc, struct device *dev);
#else
static inline struct tegra_mc *
devm_tegra_memory_controller_get(struct device *dev)
{
return ERR_PTR(-ENODEV);
}
-#endif
-int tegra_mc_probe_device(struct tegra_mc *mc, struct device *dev);
+static inline int
+tegra_mc_probe_device(struct tegra_mc *mc, struct device *dev)
+{
+ return -ENODEV;
+}
+#endif
#endif /* __SOC_TEGRA_MC_H__ */
/* Do not create a PCM for this DAI link (Backend link) */
unsigned int ignore:1;
+ /* This flag will reorder stop sequence. By enabling this flag
+ * DMA controller stop sequence will be invoked first followed by
+ * CPU DAI driver stop sequence
+ */
+ unsigned int stop_dma_first:1;
+
#ifdef CONFIG_SND_SOC_TOPOLOGY
struct snd_soc_dobj dobj; /* For topology */
#endif
afs_VL_GetCapabilities = 65537, /* AFS Get VL server capabilities */
};
+enum afs_cm_operation {
+ afs_CB_CallBack = 204, /* AFS break callback promises */
+ afs_CB_InitCallBackState = 205, /* AFS initialise callback state */
+ afs_CB_Probe = 206, /* AFS probe client */
+ afs_CB_GetLock = 207, /* AFS get contents of CM lock table */
+ afs_CB_GetCE = 208, /* AFS get cache file description */
+ afs_CB_GetXStatsVersion = 209, /* AFS get version of extended statistics */
+ afs_CB_GetXStats = 210, /* AFS get contents of extended statistics data */
+ afs_CB_InitCallBackState3 = 213, /* AFS initialise callback state, version 3 */
+ afs_CB_ProbeUuid = 214, /* AFS check the client hasn't rebooted */
+};
+
+enum yfs_cm_operation {
+ yfs_CB_Probe = 206, /* YFS probe client */
+ yfs_CB_GetLock = 207, /* YFS get contents of CM lock table */
+ yfs_CB_XStatsVersion = 209, /* YFS get version of extended statistics */
+ yfs_CB_GetXStats = 210, /* YFS get contents of extended statistics data */
+ yfs_CB_InitCallBackState3 = 213, /* YFS initialise callback state, version 3 */
+ yfs_CB_ProbeUuid = 214, /* YFS check the client hasn't rebooted */
+ yfs_CB_GetServerPrefs = 215,
+ yfs_CB_GetCellServDV = 216,
+ yfs_CB_GetLocalCell = 217,
+ yfs_CB_GetCacheConfig = 218,
+ yfs_CB_GetCellByNum = 65537,
+ yfs_CB_TellMeAboutYourself = 65538, /* get client capabilities */
+ yfs_CB_CallBack = 64204,
+};
+
enum afs_edit_dir_op {
afs_edit_dir_create,
afs_edit_dir_create_error,
EM(afs_YFSVL_GetCellName, "YFSVL.GetCellName") \
E_(afs_VL_GetCapabilities, "VL.GetCapabilities")
+#define afs_cm_operations \
+ EM(afs_CB_CallBack, "CB.CallBack") \
+ EM(afs_CB_InitCallBackState, "CB.InitCallBackState") \
+ EM(afs_CB_Probe, "CB.Probe") \
+ EM(afs_CB_GetLock, "CB.GetLock") \
+ EM(afs_CB_GetCE, "CB.GetCE") \
+ EM(afs_CB_GetXStatsVersion, "CB.GetXStatsVersion") \
+ EM(afs_CB_GetXStats, "CB.GetXStats") \
+ EM(afs_CB_InitCallBackState3, "CB.InitCallBackState3") \
+ E_(afs_CB_ProbeUuid, "CB.ProbeUuid")
+
+#define yfs_cm_operations \
+ EM(yfs_CB_Probe, "YFSCB.Probe") \
+ EM(yfs_CB_GetLock, "YFSCB.GetLock") \
+ EM(yfs_CB_XStatsVersion, "YFSCB.XStatsVersion") \
+ EM(yfs_CB_GetXStats, "YFSCB.GetXStats") \
+ EM(yfs_CB_InitCallBackState3, "YFSCB.InitCallBackState3") \
+ EM(yfs_CB_ProbeUuid, "YFSCB.ProbeUuid") \
+ EM(yfs_CB_GetServerPrefs, "YFSCB.GetServerPrefs") \
+ EM(yfs_CB_GetCellServDV, "YFSCB.GetCellServDV") \
+ EM(yfs_CB_GetLocalCell, "YFSCB.GetLocalCell") \
+ EM(yfs_CB_GetCacheConfig, "YFSCB.GetCacheConfig") \
+ EM(yfs_CB_GetCellByNum, "YFSCB.GetCellByNum") \
+ EM(yfs_CB_TellMeAboutYourself, "YFSCB.TellMeAboutYourself") \
+ E_(yfs_CB_CallBack, "YFSCB.CallBack")
+
#define afs_edit_dir_ops \
EM(afs_edit_dir_create, "create") \
EM(afs_edit_dir_create_error, "c_fail") \
afs_cell_traces;
afs_fs_operations;
afs_vl_operations;
+afs_cm_operations;
+yfs_cm_operations;
afs_edit_dir_ops;
afs_edit_dir_reasons;
afs_eproto_causes;
TP_STRUCT__entry(
__field(unsigned int, call )
- __field(const char *, name )
__field(u32, op )
+ __field(u16, service_id )
),
TP_fast_assign(
__entry->call = call->debug_id;
- __entry->name = call->type->name;
__entry->op = call->operation_ID;
+ __entry->service_id = call->service_id;
),
- TP_printk("c=%08x %s o=%u",
+ TP_printk("c=%08x %s",
__entry->call,
- __entry->name,
- __entry->op)
+ __entry->service_id == 2501 ?
+ __print_symbolic(__entry->op, yfs_cm_operations) :
+ __print_symbolic(__entry->op, afs_cm_operations))
);
TRACE_EVENT(afs_call,
__assign_str(name, skb->dev->name);
),
- TP_printk("dev=%s skbaddr=%p len=%u",
+ TP_printk("dev=%s skbaddr=%px len=%u",
__get_str(name), __entry->skbaddr, __entry->len)
)
__entry->txq_state = txq->state;
),
- TP_printk("dequeue ifindex=%d qdisc handle=0x%X parent=0x%X txq_state=0x%lX packets=%d skbaddr=%p",
+ TP_printk("dequeue ifindex=%d qdisc handle=0x%X parent=0x%X txq_state=0x%lX packets=%d skbaddr=%px",
__entry->ifindex, __entry->handle, __entry->parent,
__entry->txq_state, __entry->packets, __entry->skbaddr )
);
+TRACE_EVENT(qdisc_enqueue,
+
+ TP_PROTO(struct Qdisc *qdisc, const struct netdev_queue *txq, struct sk_buff *skb),
+
+ TP_ARGS(qdisc, txq, skb),
+
+ TP_STRUCT__entry(
+ __field(struct Qdisc *, qdisc)
+ __field(void *, skbaddr)
+ __field(int, ifindex)
+ __field(u32, handle)
+ __field(u32, parent)
+ ),
+
+ TP_fast_assign(
+ __entry->qdisc = qdisc;
+ __entry->skbaddr = skb;
+ __entry->ifindex = txq->dev ? txq->dev->ifindex : 0;
+ __entry->handle = qdisc->handle;
+ __entry->parent = qdisc->parent;
+ ),
+
+ TP_printk("enqueue ifindex=%d qdisc handle=0x%X parent=0x%X skbaddr=%px",
+ __entry->ifindex, __entry->handle, __entry->parent, __entry->skbaddr)
+);
+
TRACE_EVENT(qdisc_reset,
TP_PROTO(struct Qdisc *q),
ETHTOOL_MSG_FEC_SET,
ETHTOOL_MSG_MODULE_EEPROM_GET,
ETHTOOL_MSG_STATS_GET,
+ ETHTOOL_MSG_PHC_VCLOCKS_GET,
/* add new constants above here */
__ETHTOOL_MSG_USER_CNT,
ETHTOOL_MSG_FEC_NTF,
ETHTOOL_MSG_MODULE_EEPROM_GET_REPLY,
ETHTOOL_MSG_STATS_GET_REPLY,
+ ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY,
/* add new constants above here */
__ETHTOOL_MSG_KERNEL_CNT,
ETHTOOL_A_TSINFO_MAX = (__ETHTOOL_A_TSINFO_CNT - 1)
};
+/* PHC VCLOCKS */
+
+enum {
+ ETHTOOL_A_PHC_VCLOCKS_UNSPEC,
+ ETHTOOL_A_PHC_VCLOCKS_HEADER, /* nest - _A_HEADER_* */
+ ETHTOOL_A_PHC_VCLOCKS_NUM, /* u32 */
+ ETHTOOL_A_PHC_VCLOCKS_INDEX, /* array, s32 */
+
+ /* add new constants above here */
+ __ETHTOOL_A_PHC_VCLOCKS_CNT,
+ ETHTOOL_A_PHC_VCLOCKS_MAX = (__ETHTOOL_A_PHC_VCLOCKS_CNT - 1)
+};
+
/* CABLE TEST */
enum {
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* SPDX-License-Identifier: LGPL-2.1 WITH Linux-syscall-note */
/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */
#ifndef _USR_IDXD_H_
#define _USR_IDXD_H_
#include <linux/types.h>
#include <linux/socket.h> /* for SO_TIMESTAMPING */
-/* SO_TIMESTAMPING gets an integer bit field comprised of these values */
+/* SO_TIMESTAMPING flags */
enum {
SOF_TIMESTAMPING_TX_HARDWARE = (1<<0),
SOF_TIMESTAMPING_TX_SOFTWARE = (1<<1),
SOF_TIMESTAMPING_OPT_STATS = (1<<12),
SOF_TIMESTAMPING_OPT_PKTINFO = (1<<13),
SOF_TIMESTAMPING_OPT_TX_SWHW = (1<<14),
+ SOF_TIMESTAMPING_BIND_PHC = (1 << 15),
- SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_TX_SWHW,
+ SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_BIND_PHC,
SOF_TIMESTAMPING_MASK = (SOF_TIMESTAMPING_LAST - 1) |
SOF_TIMESTAMPING_LAST
};
SOF_TIMESTAMPING_TX_ACK)
/**
+ * struct so_timestamping - SO_TIMESTAMPING parameter
+ *
+ * @flags: SO_TIMESTAMPING flags
+ * @bind_phc: Index of PTP virtual clock bound to sock. This is available
+ * if flag SOF_TIMESTAMPING_BIND_PHC is set.
+ */
+struct so_timestamping {
+ int flags;
+ int bind_phc;
+};
+
+/**
* struct hwtstamp_config - %SIOCGHWTSTAMP and %SIOCSHWTSTAMP parameter
*
* @flags: no flags defined right now, must be zero for %SIOCSHWTSTAMP
NFULA_HWTYPE, /* hardware type */
NFULA_HWHEADER, /* hardware header */
NFULA_HWLEN, /* hardware header length */
- NFULA_CT, /* nf_conntrack_netlink.h */
+ NFULA_CT, /* nfnetlink_conntrack.h */
NFULA_CT_INFO, /* enum ip_conntrack_info */
NFULA_VLAN, /* nested attribute: packet vlan info */
NFULA_L2HDR, /* full L2 header */
NFQA_IFINDEX_PHYSOUTDEV, /* __u32 ifindex */
NFQA_HWADDR, /* nfqnl_msg_packet_hw */
NFQA_PAYLOAD, /* opaque data payload */
- NFQA_CT, /* nf_conntrack_netlink.h */
+ NFQA_CT, /* nfnetlink_conntrack.h */
NFQA_CT_INFO, /* enum ip_conntrack_info */
NFQA_CAP_LEN, /* __u32 length of captured packet */
NFQA_SKB_INFO, /* __u32 skb meta information */
- NFQA_EXP, /* nf_conntrack_netlink.h */
+ NFQA_EXP, /* nfnetlink_conntrack.h */
NFQA_UID, /* __u32 sk uid */
NFQA_GID, /* __u32 sk gid */
NFQA_SECCTX, /* security context string */
-/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
+/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB */
/*
* Copyright (c) 2006 - 2021 Intel Corporation. All rights reserved.
* Copyright (c) 2005 Topspin Communications. All rights reserved.
default y
bool "Enable SLUB debugging support" if EXPERT
depends on SLUB && SYSFS
- select STACKDEPOT if STACKTRACE_SUPPORT
help
SLUB has extensive debug support features. Disabling these can
result in significant savings in code size. This also disables
#include <linux/perf_event.h>
#include <linux/extable.h>
#include <linux/log2.h>
+
+#include <asm/barrier.h>
#include <asm/unaligned.h>
/* Registers */
/* Non-UAPI available opcodes. */
[BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS,
[BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL,
+ [BPF_ST | BPF_NOSPEC] = &&ST_NOSPEC,
[BPF_LDX | BPF_PROBE_MEM | BPF_B] = &&LDX_PROBE_MEM_B,
[BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H,
[BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W,
COND_JMP(s, JSGE, >=)
COND_JMP(s, JSLE, <=)
#undef COND_JMP
- /* STX and ST and LDX*/
+ /* ST, STX and LDX*/
+ ST_NOSPEC:
+ /* Speculation barrier for mitigating Speculative Store Bypass.
+ * In case of arm64, we rely on the firmware mitigation as
+ * controlled via the ssbd kernel parameter. Whenever the
+ * mitigation is enabled, it works for all of the kernel code
+ * with no need to provide any additional instructions here.
+ * In case of x86, we use 'lfence' insn for mitigation. We
+ * reuse preexisting logic from Spectre v1 mitigation that
+ * happens to produce the required code on x86 for v4 as well.
+ */
+#ifdef CONFIG_X86
+ barrier_nospec();
+#endif
+ CONT;
#define LDST(SIZEOP, SIZE) \
STX_MEM_##SIZEOP: \
*(SIZE *)(unsigned long) (DST + insn->off) = SRC; \
#endif
if (aux->dst_trampoline)
bpf_trampoline_put(aux->dst_trampoline);
- for (i = 0; i < aux->func_cnt; i++)
+ for (i = 0; i < aux->func_cnt; i++) {
+ /* We can just unlink the subprog poke descriptor table as
+ * it was originally linked to the main program and is also
+ * released along with it.
+ */
+ aux->func[i]->aux->poke_tab = NULL;
bpf_jit_free(aux->func[i]);
+ }
if (aux->func_cnt) {
kfree(aux->func);
bpf_prog_unlock_free(aux->prog);
if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
for (i = 0; i < map->max_entries; i++) {
- dst = READ_ONCE(dtab->netdev_map[i]);
+ dst = rcu_dereference_check(dtab->netdev_map[i],
+ rcu_read_lock_bh_held());
if (!is_valid_dst(dst, xdp, exclude_ifindex))
continue;
if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
for (i = 0; i < map->max_entries; i++) {
- dst = READ_ONCE(dtab->netdev_map[i]);
+ dst = rcu_dereference_check(dtab->netdev_map[i],
+ rcu_read_lock_bh_held());
if (!dst || dst->dev->ifindex == exclude_ifindex)
continue;
verbose(cbs->private_data, "BUG_%02x\n", insn->code);
}
} else if (class == BPF_ST) {
- if (BPF_MODE(insn->code) != BPF_MEM) {
+ if (BPF_MODE(insn->code) == BPF_MEM) {
+ verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = %d\n",
+ insn->code,
+ bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+ insn->dst_reg,
+ insn->off, insn->imm);
+ } else if (BPF_MODE(insn->code) == 0xc0 /* BPF_NOSPEC, no UAPI */) {
+ verbose(cbs->private_data, "(%02x) nospec\n", insn->code);
+ } else {
verbose(cbs->private_data, "BUG_st_%02x\n", insn->code);
- return;
}
- verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = %d\n",
- insn->code,
- bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
- insn->dst_reg,
- insn->off, insn->imm);
} else if (class == BPF_LDX) {
if (BPF_MODE(insn->code) != BPF_MEM) {
verbose(cbs->private_data, "BUG_ldx_%02x\n", insn->code);
cur = env->cur_state->frame[env->cur_state->curframe];
if (value_regno >= 0)
reg = &cur->regs[value_regno];
+ if (!env->bypass_spec_v4) {
+ bool sanitize = reg && is_spillable_regtype(reg->type);
+
+ for (i = 0; i < size; i++) {
+ if (state->stack[spi].slot_type[i] == STACK_INVALID) {
+ sanitize = true;
+ break;
+ }
+ }
+
+ if (sanitize)
+ env->insn_aux_data[insn_idx].sanitize_stack_spill = true;
+ }
if (reg && size == BPF_REG_SIZE && register_is_bounded(reg) &&
!register_is_null(reg) && env->bpf_capable) {
verbose(env, "invalid size of register spill\n");
return -EACCES;
}
-
if (state != cur && reg->type == PTR_TO_STACK) {
verbose(env, "cannot spill pointers to stack into stack frame of the caller\n");
return -EINVAL;
}
-
- if (!env->bypass_spec_v4) {
- bool sanitize = false;
-
- if (state->stack[spi].slot_type[0] == STACK_SPILL &&
- register_is_const(&state->stack[spi].spilled_ptr))
- sanitize = true;
- for (i = 0; i < BPF_REG_SIZE; i++)
- if (state->stack[spi].slot_type[i] == STACK_MISC) {
- sanitize = true;
- break;
- }
- if (sanitize) {
- int *poff = &env->insn_aux_data[insn_idx].sanitize_stack_off;
- int soff = (-spi - 1) * BPF_REG_SIZE;
-
- /* detected reuse of integer stack slot with a pointer
- * which means either llvm is reusing stack slot or
- * an attacker is trying to exploit CVE-2018-3639
- * (speculative store bypass)
- * Have to sanitize that slot with preemptive
- * store of zero.
- */
- if (*poff && *poff != soff) {
- /* disallow programs where single insn stores
- * into two different stack slots, since verifier
- * cannot sanitize them
- */
- verbose(env,
- "insn %d cannot access two stack slots fp%d and fp%d",
- insn_idx, *poff, soff);
- return -EINVAL;
- }
- *poff = soff;
- }
- }
save_register_state(state, spi, reg);
} else {
u8 type = STACK_MISC;
if (tail_call_reachable)
for (j = 0; j < frame; j++)
subprog[ret_prog[j]].tail_call_reachable = true;
+ if (subprog[0].tail_call_reachable)
+ env->prog->aux->tail_call_reachable = true;
/* end of for() loop means the last insn of the 'subprog'
* was reached. Doesn't matter whether it was JA or EXIT
alu_state |= off_is_imm ? BPF_ALU_IMMEDIATE : 0;
alu_state |= ptr_is_dst_reg ?
BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;
+
+ /* Limit pruning on unknown scalars to enable deep search for
+ * potential masking differences from other program paths.
+ */
+ if (!off_is_imm)
+ env->explore_alu_limits = true;
}
err = update_alu_sanitation_state(aux, alu_state, alu_limit);
}
/* Returns true if (rold safe implies rcur safe) */
-static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
- struct bpf_id_pair *idmap)
+static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
+ struct bpf_reg_state *rcur, struct bpf_id_pair *idmap)
{
bool equal;
return false;
switch (rold->type) {
case SCALAR_VALUE:
+ if (env->explore_alu_limits)
+ return false;
if (rcur->type == SCALAR_VALUE) {
if (!rold->precise && !rcur->precise)
return true;
return false;
}
-static bool stacksafe(struct bpf_func_state *old,
- struct bpf_func_state *cur,
- struct bpf_id_pair *idmap)
+static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
+ struct bpf_func_state *cur, struct bpf_id_pair *idmap)
{
int i, spi;
continue;
if (old->stack[spi].slot_type[0] != STACK_SPILL)
continue;
- if (!regsafe(&old->stack[spi].spilled_ptr,
- &cur->stack[spi].spilled_ptr,
- idmap))
+ if (!regsafe(env, &old->stack[spi].spilled_ptr,
+ &cur->stack[spi].spilled_ptr, idmap))
/* when explored and current stack slot are both storing
* spilled registers, check that stored pointers types
* are the same as well.
memset(env->idmap_scratch, 0, sizeof(env->idmap_scratch));
for (i = 0; i < MAX_BPF_REG; i++)
- if (!regsafe(&old->regs[i], &cur->regs[i], env->idmap_scratch))
+ if (!regsafe(env, &old->regs[i], &cur->regs[i],
+ env->idmap_scratch))
return false;
- if (!stacksafe(old, cur, env->idmap_scratch))
+ if (!stacksafe(env, old, cur, env->idmap_scratch))
return false;
if (!refsafe(old, cur))
for (i = 0; i < insn_cnt; i++, insn++) {
bpf_convert_ctx_access_t convert_ctx_access;
+ bool ctx_access;
if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_H) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_W) ||
- insn->code == (BPF_LDX | BPF_MEM | BPF_DW))
+ insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) {
type = BPF_READ;
- else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) ||
- insn->code == (BPF_STX | BPF_MEM | BPF_H) ||
- insn->code == (BPF_STX | BPF_MEM | BPF_W) ||
- insn->code == (BPF_STX | BPF_MEM | BPF_DW))
+ ctx_access = true;
+ } else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) ||
+ insn->code == (BPF_STX | BPF_MEM | BPF_H) ||
+ insn->code == (BPF_STX | BPF_MEM | BPF_W) ||
+ insn->code == (BPF_STX | BPF_MEM | BPF_DW) ||
+ insn->code == (BPF_ST | BPF_MEM | BPF_B) ||
+ insn->code == (BPF_ST | BPF_MEM | BPF_H) ||
+ insn->code == (BPF_ST | BPF_MEM | BPF_W) ||
+ insn->code == (BPF_ST | BPF_MEM | BPF_DW)) {
type = BPF_WRITE;
- else
+ ctx_access = BPF_CLASS(insn->code) == BPF_STX;
+ } else {
continue;
+ }
if (type == BPF_WRITE &&
- env->insn_aux_data[i + delta].sanitize_stack_off) {
+ env->insn_aux_data[i + delta].sanitize_stack_spill) {
struct bpf_insn patch[] = {
- /* Sanitize suspicious stack slot with zero.
- * There are no memory dependencies for this store,
- * since it's only using frame pointer and immediate
- * constant of zero
- */
- BPF_ST_MEM(BPF_DW, BPF_REG_FP,
- env->insn_aux_data[i + delta].sanitize_stack_off,
- 0),
- /* the original STX instruction will immediately
- * overwrite the same stack slot with appropriate value
- */
*insn,
+ BPF_ST_NOSPEC(),
};
cnt = ARRAY_SIZE(patch);
continue;
}
+ if (!ctx_access)
+ continue;
+
switch (env->insn_aux_data[i + delta].ptr_type) {
case PTR_TO_CTX:
if (!ops->convert_ctx_access)
goto out_free;
func[i]->is_func = 1;
func[i]->aux->func_idx = i;
- /* the btf and func_info will be freed only at prog->aux */
+ /* Below members will be freed only at prog->aux */
func[i]->aux->btf = prog->aux->btf;
func[i]->aux->func_info = prog->aux->func_info;
+ func[i]->aux->poke_tab = prog->aux->poke_tab;
+ func[i]->aux->size_poke_tab = prog->aux->size_poke_tab;
for (j = 0; j < prog->aux->size_poke_tab; j++) {
- u32 insn_idx = prog->aux->poke_tab[j].insn_idx;
- int ret;
+ struct bpf_jit_poke_descriptor *poke;
- if (!(insn_idx >= subprog_start &&
- insn_idx <= subprog_end))
- continue;
-
- ret = bpf_jit_add_poke_descriptor(func[i],
- &prog->aux->poke_tab[j]);
- if (ret < 0) {
- verbose(env, "adding tail call poke descriptor failed\n");
- goto out_free;
- }
-
- func[i]->insnsi[insn_idx - subprog_start].imm = ret + 1;
-
- map_ptr = func[i]->aux->poke_tab[ret].tail_call.map;
- ret = map_ptr->ops->map_poke_track(map_ptr, func[i]->aux);
- if (ret < 0) {
- verbose(env, "tracking tail call prog failed\n");
- goto out_free;
- }
+ poke = &prog->aux->poke_tab[j];
+ if (poke->insn_idx < subprog_end &&
+ poke->insn_idx >= subprog_start)
+ poke->aux = func[i]->aux;
}
/* Use bpf_prog_F_tag to indicate functions in stack traces.
cond_resched();
}
- /* Untrack main program's aux structs so that during map_poke_run()
- * we will not stumble upon the unfilled poke descriptors; each
- * of the main program's poke descs got distributed across subprogs
- * and got tracked onto map, so we are sure that none of them will
- * be missed after the operation below
- */
- for (i = 0; i < prog->aux->size_poke_tab; i++) {
- map_ptr = prog->aux->poke_tab[i].tail_call.map;
-
- map_ptr->ops->map_poke_untrack(map_ptr, prog->aux);
- }
-
/* at this point all bpf functions were successfully JITed
* now populate all bpf_calls with correct addresses and
* run last pass of JIT
bpf_prog_jit_attempt_done(prog);
return 0;
out_free:
+ /* We failed JIT'ing, so at this point we need to unregister poke
+ * descriptors from subprogs, so that kernel is not attempting to
+ * patch it anymore as we're freeing the subprog JIT memory.
+ */
+ for (i = 0; i < prog->aux->size_poke_tab; i++) {
+ map_ptr = prog->aux->poke_tab[i].tail_call.map;
+ map_ptr->ops->map_poke_untrack(map_ptr, prog->aux);
+ }
+ /* At this point we're guaranteed that poke descriptors are not
+ * live anymore. We can just unlink its descriptor table as it's
+ * released with the main prog.
+ */
for (i = 0; i < env->subprog_cnt; i++) {
if (!func[i])
continue;
-
- for (j = 0; j < func[i]->aux->size_poke_tab; j++) {
- map_ptr = func[i]->aux->poke_tab[j].tail_call.map;
- map_ptr->ops->map_poke_untrack(map_ptr, func[i]->aux);
- }
+ func[i]->aux->poke_tab = NULL;
bpf_jit_free(func[i]);
}
kfree(func);
}
}
-/* The verifier is using insn_aux_data[] to store temporary data during
- * verification and to store information for passes that run after the
- * verification like dead code sanitization. do_check_common() for subprogram N
- * may analyze many other subprograms. sanitize_insn_aux_data() clears all
- * temporary data after do_check_common() finds that subprogram N cannot be
- * verified independently. pass_cnt counts the number of times
- * do_check_common() was run and insn->aux->seen tells the pass number
- * insn_aux_data was touched. These variables are compared to clear temporary
- * data from failed pass. For testing and experiments do_check_common() can be
- * run multiple times even when prior attempt to verify is unsuccessful.
- *
- * Note that special handling is needed on !env->bypass_spec_v1 if this is
- * ever called outside of error path with subsequent program rejection.
- */
-static void sanitize_insn_aux_data(struct bpf_verifier_env *env)
-{
- struct bpf_insn *insn = env->prog->insnsi;
- struct bpf_insn_aux_data *aux;
- int i, class;
-
- for (i = 0; i < env->prog->len; i++) {
- class = BPF_CLASS(insn[i].code);
- if (class != BPF_LDX && class != BPF_STX)
- continue;
- aux = &env->insn_aux_data[i];
- if (aux->seen != env->pass_cnt)
- continue;
- memset(aux, 0, offsetof(typeof(*aux), orig_idx));
- }
-}
-
static int do_check_common(struct bpf_verifier_env *env, int subprog)
{
bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
if (!ret && pop_log)
bpf_vlog_reset(&env->log, 0);
free_states(env);
- if (ret)
- /* clean aux data in case subprog was rejected */
- sanitize_insn_aux_data(env);
return ret;
}
opt = fs_parse(fc, cgroup1_fs_parameters, param, &result);
if (opt == -ENOPARAM) {
- if (strcmp(param->key, "source") == 0) {
- if (fc->source)
- return invalf(fc, "Multiple sources not supported");
- fc->source = param->string;
- param->string = NULL;
- return 0;
- }
+ int ret;
+
+ ret = vfs_parse_fs_param_source(fc, param);
+ if (ret != -ENOPARAM)
+ return ret;
for_each_subsys(ss, i) {
if (strcmp(param->key, ss->legacy_name))
continue;
ret = cgroup_do_get_tree(fc);
if (!ret && percpu_ref_is_dying(&ctx->root->cgrp.self.refcnt)) {
- struct super_block *sb = fc->root->d_sb;
- dput(fc->root);
- deactivate_locked_super(sb);
+ fc_drop_locked(fc);
ret = 1;
}
gdb_cmd_detachkill(ks);
return DBG_PASS_EVENT;
}
-#endif
fallthrough;
+#endif
case 'C': /* Exception passing */
tmp = gdb_cmd_exception_pass(ks);
if (tmp > 0)
*/
#include <linux/dma-map-ops.h>
+static struct page *dma_common_vaddr_to_page(void *cpu_addr)
+{
+ if (is_vmalloc_addr(cpu_addr))
+ return vmalloc_to_page(cpu_addr);
+ return virt_to_page(cpu_addr);
+}
+
/*
* Create scatter-list for the already allocated DMA buffer.
*/
void *cpu_addr, dma_addr_t dma_addr, size_t size,
unsigned long attrs)
{
- struct page *page = virt_to_page(cpu_addr);
+ struct page *page = dma_common_vaddr_to_page(cpu_addr);
int ret;
ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
unsigned long user_count = vma_pages(vma);
unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
unsigned long off = vma->vm_pgoff;
+ struct page *page = dma_common_vaddr_to_page(cpu_addr);
int ret = -ENXIO;
vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs);
return -ENXIO;
return remap_pfn_range(vma, vma->vm_start,
- page_to_pfn(virt_to_page(cpu_addr)) + vma->vm_pgoff,
+ page_to_pfn(page) + vma->vm_pgoff,
user_count << PAGE_SHIFT, vma->vm_page_prot);
#else
return -ENXIO;
return gctx;
}
+static bool
+perf_check_permission(struct perf_event_attr *attr, struct task_struct *task)
+{
+ unsigned int ptrace_mode = PTRACE_MODE_READ_REALCREDS;
+ bool is_capable = perfmon_capable();
+
+ if (attr->sigtrap) {
+ /*
+ * perf_event_attr::sigtrap sends signals to the other task.
+ * Require the current task to also have CAP_KILL.
+ */
+ rcu_read_lock();
+ is_capable &= ns_capable(__task_cred(task)->user_ns, CAP_KILL);
+ rcu_read_unlock();
+
+ /*
+ * If the required capabilities aren't available, checks for
+ * ptrace permissions: upgrade to ATTACH, since sending signals
+ * can effectively change the target task.
+ */
+ ptrace_mode = PTRACE_MODE_ATTACH_REALCREDS;
+ }
+
+ /*
+ * Preserve ptrace permission check for backwards compatibility. The
+ * ptrace check also includes checks that the current task and other
+ * task have matching uids, and is therefore not done here explicitly.
+ */
+ return is_capable || ptrace_may_access(task, ptrace_mode);
+}
+
/**
* sys_perf_event_open - open a performance event, associate it to a task/cpu
*
goto err_file;
/*
- * Preserve ptrace permission check for backwards compatibility.
- *
* We must hold exec_update_lock across this and any potential
* perf_install_in_context() call for this new event to
* serialize against exec() altering our credentials (and the
* perf_event_exit_task() that could imply).
*/
err = -EACCES;
- if (!perfmon_capable() && !ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
+ if (!perf_check_permission(&attr, task))
goto err_cred;
}
s64 duration;
VERBOSE_SCALEOUT_BATCH("ref_scale_reader %ld: task started", me);
- set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
+ WARN_ON_ONCE(set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids)));
set_user_nice(current, MAX_NICE);
atomic_inc(&n_init);
if (holdoff)
schedule_timeout_interruptible(holdoff * HZ);
repeat:
- VERBOSE_SCALEOUT_BATCH("ref_scale_reader %ld: waiting to start next experiment on cpu %d", me, smp_processor_id());
+ VERBOSE_SCALEOUT_BATCH("ref_scale_reader %ld: waiting to start next experiment on cpu %d", me, raw_smp_processor_id());
// Wait for signal that this reader can start.
wait_event(rt->wq, (atomic_read(&nreaders_exp) && smp_load_acquire(&rt->start_reader)) ||
goto end;
// Make sure that the CPU is affinitized appropriately during testing.
- WARN_ON_ONCE(smp_processor_id() != me);
+ WARN_ON_ONCE(raw_smp_processor_id() != me);
WRITE_ONCE(rt->start_reader, 0);
if (!atomic_dec_return(&n_started))
in_qs = likely(!t->trc_reader_nesting);
}
- // Mark as checked. Because this is called from the grace-period
- // kthread, also remove the task from the holdout list.
+ // Mark as checked so that the grace-period kthread will
+ // remove it from the holdout list.
t->trc_reader_checked = true;
- trc_del_holdout(t);
if (in_qs)
return true; // Already in quiescent state, done!!!
// The current task had better be in a quiescent state.
if (t == current) {
t->trc_reader_checked = true;
- trc_del_holdout(t);
WARN_ON_ONCE(t->trc_reader_nesting);
return;
}
jr = j - data_race(rcu_state.gp_req_activity);
js = j - data_race(rcu_state.gp_start);
jw = j - data_race(rcu_state.gp_wake_time);
- pr_info("%s: wait state: %s(%d) ->state: %#lx ->rt_priority %u delta ->gp_start %lu ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_max %lu ->gp_flags %#x\n",
+ pr_info("%s: wait state: %s(%d) ->state: %#x ->rt_priority %u delta ->gp_start %lu ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_max %lu ->gp_flags %#x\n",
rcu_state.name, gp_state_getname(rcu_state.gp_state),
- rcu_state.gp_state, t ? t->__state : 0x1ffffL, t ? t->rt_priority : 0xffU,
+ rcu_state.gp_state, t ? t->__state : 0x1ffff, t ? t->rt_priority : 0xffU,
js, ja, jr, jw, (long)data_race(rcu_state.gp_wake_seq),
(long)data_race(rcu_state.gp_seq),
(long)data_race(rcu_get_root()->gp_seq_needed),
VERBOSE_SCFTORTOUT("scftorture_invoker %d: task started", scfp->cpu);
cpu = scfp->cpu % nr_cpu_ids;
- set_cpus_allowed_ptr(current, cpumask_of(cpu));
+ WARN_ON_ONCE(set_cpus_allowed_ptr(current, cpumask_of(cpu)));
set_user_nice(current, MAX_NICE);
if (holdoff)
schedule_timeout_interruptible(holdoff * HZ);
- VERBOSE_SCFTORTOUT("scftorture_invoker %d: Waiting for all SCF torturers from cpu %d", scfp->cpu, smp_processor_id());
+ VERBOSE_SCFTORTOUT("scftorture_invoker %d: Waiting for all SCF torturers from cpu %d", scfp->cpu, raw_smp_processor_id());
// Make sure that the CPU is affinitized appropriately during testing.
- curcpu = smp_processor_id();
+ curcpu = raw_smp_processor_id();
WARN_ONCE(curcpu != scfp->cpu % nr_cpu_ids,
"%s: Wanted CPU %d, running on %d, nr_cpu_ids = %d\n",
__func__, scfp->cpu, curcpu, nr_cpu_ids);
dequeue_task(rq, p, flags);
}
-/*
- * __normal_prio - return the priority that is based on the static prio
- */
-static inline int __normal_prio(struct task_struct *p)
+static inline int __normal_prio(int policy, int rt_prio, int nice)
{
- return p->static_prio;
+ int prio;
+
+ if (dl_policy(policy))
+ prio = MAX_DL_PRIO - 1;
+ else if (rt_policy(policy))
+ prio = MAX_RT_PRIO - 1 - rt_prio;
+ else
+ prio = NICE_TO_PRIO(nice);
+
+ return prio;
}
/*
*/
static inline int normal_prio(struct task_struct *p)
{
- int prio;
-
- if (task_has_dl_policy(p))
- prio = MAX_DL_PRIO-1;
- else if (task_has_rt_policy(p))
- prio = MAX_RT_PRIO-1 - p->rt_priority;
- else
- prio = __normal_prio(p);
- return prio;
+ return __normal_prio(p->policy, p->rt_priority, PRIO_TO_NICE(p->static_prio));
}
/*
} else if (PRIO_TO_NICE(p->static_prio) < 0)
p->static_prio = NICE_TO_PRIO(0);
- p->prio = p->normal_prio = __normal_prio(p);
+ p->prio = p->normal_prio = p->static_prio;
set_load_weight(p, false);
/*
}
EXPORT_SYMBOL(default_wake_function);
+static void __setscheduler_prio(struct task_struct *p, int prio)
+{
+ if (dl_prio(prio))
+ p->sched_class = &dl_sched_class;
+ else if (rt_prio(prio))
+ p->sched_class = &rt_sched_class;
+ else
+ p->sched_class = &fair_sched_class;
+
+ p->prio = prio;
+}
+
#ifdef CONFIG_RT_MUTEXES
static inline int __rt_effective_prio(struct task_struct *pi_task, int prio)
} else {
p->dl.pi_se = &p->dl;
}
- p->sched_class = &dl_sched_class;
} else if (rt_prio(prio)) {
if (dl_prio(oldprio))
p->dl.pi_se = &p->dl;
if (oldprio < prio)
queue_flag |= ENQUEUE_HEAD;
- p->sched_class = &rt_sched_class;
} else {
if (dl_prio(oldprio))
p->dl.pi_se = &p->dl;
if (rt_prio(oldprio))
p->rt.timeout = 0;
- p->sched_class = &fair_sched_class;
}
- p->prio = prio;
+ __setscheduler_prio(p, prio);
if (queued)
enqueue_task(rq, p, queue_flag);
set_load_weight(p, true);
}
-/* Actually do priority change: must hold pi & rq lock. */
-static void __setscheduler(struct rq *rq, struct task_struct *p,
- const struct sched_attr *attr, bool keep_boost)
-{
- /*
- * If params can't change scheduling class changes aren't allowed
- * either.
- */
- if (attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)
- return;
-
- __setscheduler_params(p, attr);
-
- /*
- * Keep a potential priority boosting if called from
- * sched_setscheduler().
- */
- p->prio = normal_prio(p);
- if (keep_boost)
- p->prio = rt_effective_prio(p, p->prio);
-
- if (dl_prio(p->prio))
- p->sched_class = &dl_sched_class;
- else if (rt_prio(p->prio))
- p->sched_class = &rt_sched_class;
- else
- p->sched_class = &fair_sched_class;
-}
-
/*
* Check the target process has a UID that matches the current process's:
*/
const struct sched_attr *attr,
bool user, bool pi)
{
- int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 :
- MAX_RT_PRIO - 1 - attr->sched_priority;
- int retval, oldprio, oldpolicy = -1, queued, running;
- int new_effective_prio, policy = attr->sched_policy;
+ int oldpolicy = -1, policy = attr->sched_policy;
+ int retval, oldprio, newprio, queued, running;
const struct sched_class *prev_class;
struct callback_head *head;
struct rq_flags rf;
p->sched_reset_on_fork = reset_on_fork;
oldprio = p->prio;
+ newprio = __normal_prio(policy, attr->sched_priority, attr->sched_nice);
if (pi) {
/*
* Take priority boosted tasks into account. If the new
* the runqueue. This will be done when the task deboost
* itself.
*/
- new_effective_prio = rt_effective_prio(p, newprio);
- if (new_effective_prio == oldprio)
+ newprio = rt_effective_prio(p, newprio);
+ if (newprio == oldprio)
queue_flags &= ~DEQUEUE_MOVE;
}
prev_class = p->sched_class;
- __setscheduler(rq, p, attr, pi);
+ if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) {
+ __setscheduler_params(p, attr);
+ __setscheduler_prio(p, newprio);
+ }
__setscheduler_uclamp(p, attr);
if (queued) {
*
* Creates the thread if it does not exist.
*/
-static inline void idle_init(unsigned int cpu)
+static __always_inline void idle_init(unsigned int cpu)
{
struct task_struct *tsk = per_cpu(idle_threads, cpu);
if (!p)
goto out;
+ /* Protect timer list r/w in arm_timer() */
+ sighand = lock_task_sighand(p, &flags);
+ if (unlikely(sighand == NULL))
+ goto out;
+
/*
* Fetch the current sample and update the timer's expiry time.
*/
bump_cpu_timer(timer, now);
- /* Protect timer list r/w in arm_timer() */
- sighand = lock_task_sighand(p, &flags);
- if (unlikely(sighand == NULL))
- goto out;
-
/*
* Now re-arm for the new expiry time.
*/
unsigned int cpu;
bool next_expiry_recalc;
bool is_idle;
+ bool timers_pending;
DECLARE_BITMAP(pending_map, WHEEL_SIZE);
struct hlist_head vectors[WHEEL_SIZE];
} ____cacheline_aligned;
* can reevaluate the wheel:
*/
base->next_expiry = bucket_expiry;
+ base->timers_pending = true;
base->next_expiry_recalc = false;
trigger_dyntick_cpu(base, timer);
}
static void timer_sync_wait_running(struct timer_base *base)
{
if (atomic_read(&base->timer_waiters)) {
+ raw_spin_unlock_irq(&base->lock);
spin_unlock(&base->expiry_lock);
spin_lock(&base->expiry_lock);
+ raw_spin_lock_irq(&base->lock);
}
}
if (timer->flags & TIMER_IRQSAFE) {
raw_spin_unlock(&base->lock);
call_timer_fn(timer, fn, baseclk);
- base->running_timer = NULL;
raw_spin_lock(&base->lock);
+ base->running_timer = NULL;
} else {
raw_spin_unlock_irq(&base->lock);
call_timer_fn(timer, fn, baseclk);
+ raw_spin_lock_irq(&base->lock);
base->running_timer = NULL;
timer_sync_wait_running(base);
- raw_spin_lock_irq(&base->lock);
}
}
}
}
base->next_expiry_recalc = false;
+ base->timers_pending = !(next == base->clk + NEXT_TIMER_MAX_DELTA);
return next;
}
struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
u64 expires = KTIME_MAX;
unsigned long nextevt;
- bool is_max_delta;
/*
* Pretend that there is no timer pending if the cpu is offline.
if (base->next_expiry_recalc)
base->next_expiry = __next_timer_interrupt(base);
nextevt = base->next_expiry;
- is_max_delta = (nextevt == base->clk + NEXT_TIMER_MAX_DELTA);
/*
* We have a fresh next event. Check whether we can forward the
expires = basem;
base->is_idle = false;
} else {
- if (!is_max_delta)
+ if (base->timers_pending)
expires = basem + (u64)(nextevt - basej) * TICK_NSEC;
/*
* If we expect to sleep more than a tick, mark the base idle.
base = per_cpu_ptr(&timer_bases[b], cpu);
base->clk = jiffies;
base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA;
+ base->timers_pending = false;
base->is_idle = false;
}
return 0;
* infrastructure to do the synchronization, thus we must do it
* ourselves.
*/
- synchronize_rcu_tasks_rude();
+ if (old_hash != EMPTY_HASH)
+ synchronize_rcu_tasks_rude();
free_ftrace_hash(old_hash);
}
*/
int register_ftrace_function(struct ftrace_ops *ops)
{
- int ret = -1;
+ int ret;
ftrace_ops_init(ops);
if (unlikely(!head))
return true;
- return reader->read == rb_page_commit(reader) &&
- (commit == reader ||
- (commit == head &&
- head->read == rb_page_commit(commit)));
+ /* Reader should exhaust content in reader page */
+ if (reader->read != rb_page_commit(reader))
+ return false;
+
+ /*
+ * If writers are committing on the reader page, knowing all
+ * committed content has been read, the ring buffer is empty.
+ */
+ if (commit == reader)
+ return true;
+
+ /*
+ * If writers are committing on a page other than reader page
+ * and head page, there should always be content to read.
+ */
+ if (commit != head)
+ return false;
+
+ /*
+ * Writers are committing on the head page, we just need
+ * to care about there're committed data, and the reader will
+ * swap reader page with head page when it is to read data.
+ */
+ return rb_page_commit(commit) == 0;
}
/**
"\t [:name=histname1]\n"
"\t [:<handler>.<action>]\n"
"\t [if <filter>]\n\n"
+ "\t Note, special fields can be used as well:\n"
+ "\t common_timestamp - to record current timestamp\n"
+ "\t common_cpu - to record the CPU the event happened on\n"
+ "\n"
"\t When a matching event is hit, an entry is added to a hash\n"
"\t table using the key(s) and value(s) named, and the value of a\n"
"\t sum called 'hitcount' is incremented. Keys and values\n"
return -EINVAL;
ret = event_trace_add_tracer(tr->dir, tr);
- if (ret)
+ if (ret) {
tracefs_remove(tr->dir);
+ return ret;
+ }
init_tracer_tracefs(tr, tr->dir);
__update_tracer_options(tr);
C(INVALID_SORT_MODIFIER,"Invalid sort modifier"), \
C(EMPTY_SORT_FIELD, "Empty sort field"), \
C(TOO_MANY_SORT_FIELDS, "Too many sort fields (Max = 2)"), \
- C(INVALID_SORT_FIELD, "Sort field must be a key or a val"),
+ C(INVALID_SORT_FIELD, "Sort field must be a key or a val"), \
+ C(INVALID_STR_OPERAND, "String type can not be an operand in expression"),
#undef C
#define C(a, b) HIST_ERR_##a
field->flags & HIST_FIELD_FL_ALIAS)
field_name = hist_field_name(field->operands[0], ++level);
else if (field->flags & HIST_FIELD_FL_CPU)
- field_name = "cpu";
+ field_name = "common_cpu";
else if (field->flags & HIST_FIELD_FL_EXPR ||
field->flags & HIST_FIELD_FL_VAR_REF) {
if (field->system) {
if (WARN_ON_ONCE(!field))
goto out;
- if (is_string_field(field)) {
+ /* Pointers to strings are just pointers and dangerous to dereference */
+ if (is_string_field(field) &&
+ (field->filter_type != FILTER_PTR_STRING)) {
flags |= HIST_FIELD_FL_STRING;
hist_field->size = MAX_FILTER_STR_VAL;
hist_data->enable_timestamps = true;
if (*flags & HIST_FIELD_FL_TIMESTAMP_USECS)
hist_data->attrs->ts_in_usecs = true;
- } else if (strcmp(field_name, "cpu") == 0)
+ } else if (strcmp(field_name, "common_cpu") == 0)
*flags |= HIST_FIELD_FL_CPU;
else {
field = trace_find_event_field(file->event_call, field_name);
if (!field || !field->size) {
- hist_err(tr, HIST_ERR_FIELD_NOT_FOUND, errpos(field_name));
- field = ERR_PTR(-EINVAL);
- goto out;
+ /*
+ * For backward compatibility, if field_name
+ * was "cpu", then we treat this the same as
+ * common_cpu.
+ */
+ if (strcmp(field_name, "cpu") == 0) {
+ *flags |= HIST_FIELD_FL_CPU;
+ } else {
+ hist_err(tr, HIST_ERR_FIELD_NOT_FOUND,
+ errpos(field_name));
+ field = ERR_PTR(-EINVAL);
+ goto out;
+ }
}
}
out:
ret = PTR_ERR(operand1);
goto free;
}
+ if (operand1->flags & HIST_FIELD_FL_STRING) {
+ /* String type can not be the operand of unary operator. */
+ hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(str));
+ destroy_hist_field(operand1, 0);
+ ret = -EINVAL;
+ goto free;
+ }
expr->flags |= operand1->flags &
(HIST_FIELD_FL_TIMESTAMP | HIST_FIELD_FL_TIMESTAMP_USECS);
operand1 = NULL;
goto free;
}
+ if (operand1->flags & HIST_FIELD_FL_STRING) {
+ hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(operand1_str));
+ ret = -EINVAL;
+ goto free;
+ }
/* rest of string could be another expression e.g. b+c in a+b+c */
operand_flags = 0;
operand2 = NULL;
goto free;
}
+ if (operand2->flags & HIST_FIELD_FL_STRING) {
+ hist_err(file->tr, HIST_ERR_INVALID_STR_OPERAND, errpos(str));
+ ret = -EINVAL;
+ goto free;
+ }
ret = check_expr_operands(file->tr, operand1, operand2);
if (ret)
expr->operands[0] = operand1;
expr->operands[1] = operand2;
+
+ /* The operand sizes should be the same, so just pick one */
+ expr->size = operand1->size;
+
expr->operator = field_op;
expr->name = expr_str(expr, 0);
expr->type = kstrdup(operand1->type, GFP_KERNEL);
field = key_field->field;
if (field->filter_type == FILTER_DYN_STRING)
size = *(u32 *)(rec + field->offset) >> 16;
- else if (field->filter_type == FILTER_PTR_STRING)
- size = strlen(key);
else if (field->filter_type == FILTER_STATIC_STRING)
size = field->size;
seq_printf(m, "%s=", hist_field->var.name);
if (hist_field->flags & HIST_FIELD_FL_CPU)
- seq_puts(m, "cpu");
+ seq_puts(m, "common_cpu");
else if (field_name) {
if (hist_field->flags & HIST_FIELD_FL_VAR_REF ||
hist_field->flags & HIST_FIELD_FL_ALIAS)
dyn_event_init(&event->devent, &synth_event_ops);
for (i = 0, j = 0; i < n_fields; i++) {
+ fields[i]->field_pos = i;
event->fields[i] = fields[i];
- if (fields[i]->is_dynamic) {
- event->dynamic_fields[j] = fields[i];
- event->dynamic_fields[j]->field_pos = i;
+ if (fields[i]->is_dynamic)
event->dynamic_fields[j++] = fields[i];
- event->n_dynamic_fields++;
- }
}
+ event->n_dynamic_fields = j;
event->n_fields = n_fields;
out:
return event;
get_online_cpus();
cpumask_and(current_mask, cpu_online_mask, tr->tracing_cpumask);
- next_cpu = cpumask_next(smp_processor_id(), current_mask);
+ next_cpu = cpumask_next(raw_smp_processor_id(), current_mask);
put_online_cpus();
if (next_cpu >= nr_cpu_ids)
char *name;
size_t size;
unsigned int offset;
+ unsigned int field_pos;
bool is_signed;
bool is_string;
bool is_dynamic;
- bool field_pos;
};
struct synth_event {
#include <linux/sched/task.h>
#include <linux/static_key.h>
+enum tp_func_state {
+ TP_FUNC_0,
+ TP_FUNC_1,
+ TP_FUNC_2,
+ TP_FUNC_N,
+};
+
extern tracepoint_ptr_t __start___tracepoints_ptrs[];
extern tracepoint_ptr_t __stop___tracepoints_ptrs[];
DEFINE_SRCU(tracepoint_srcu);
EXPORT_SYMBOL_GPL(tracepoint_srcu);
+enum tp_transition_sync {
+ TP_TRANSITION_SYNC_1_0_1,
+ TP_TRANSITION_SYNC_N_2_1,
+
+ _NR_TP_TRANSITION_SYNC,
+};
+
+struct tp_transition_snapshot {
+ unsigned long rcu;
+ unsigned long srcu;
+ bool ongoing;
+};
+
+/* Protected by tracepoints_mutex */
+static struct tp_transition_snapshot tp_transition_snapshot[_NR_TP_TRANSITION_SYNC];
+
+static void tp_rcu_get_state(enum tp_transition_sync sync)
+{
+ struct tp_transition_snapshot *snapshot = &tp_transition_snapshot[sync];
+
+ /* Keep the latest get_state snapshot. */
+ snapshot->rcu = get_state_synchronize_rcu();
+ snapshot->srcu = start_poll_synchronize_srcu(&tracepoint_srcu);
+ snapshot->ongoing = true;
+}
+
+static void tp_rcu_cond_sync(enum tp_transition_sync sync)
+{
+ struct tp_transition_snapshot *snapshot = &tp_transition_snapshot[sync];
+
+ if (!snapshot->ongoing)
+ return;
+ cond_synchronize_rcu(snapshot->rcu);
+ if (!poll_state_synchronize_srcu(&tracepoint_srcu, snapshot->srcu))
+ synchronize_srcu(&tracepoint_srcu);
+ snapshot->ongoing = false;
+}
+
/* Set to 1 to enable tracepoint debug output */
static const int tracepoint_debug;
return old;
}
-static void tracepoint_update_call(struct tracepoint *tp, struct tracepoint_func *tp_funcs, bool sync)
+/*
+ * Count the number of functions (enum tp_func_state) in a tp_funcs array.
+ */
+static enum tp_func_state nr_func_state(const struct tracepoint_func *tp_funcs)
+{
+ if (!tp_funcs)
+ return TP_FUNC_0;
+ if (!tp_funcs[1].func)
+ return TP_FUNC_1;
+ if (!tp_funcs[2].func)
+ return TP_FUNC_2;
+ return TP_FUNC_N; /* 3 or more */
+}
+
+static void tracepoint_update_call(struct tracepoint *tp, struct tracepoint_func *tp_funcs)
{
void *func = tp->iterator;
/* Synthetic events do not have static call sites */
if (!tp->static_call_key)
return;
-
- if (!tp_funcs[1].func) {
+ if (nr_func_state(tp_funcs) == TP_FUNC_1)
func = tp_funcs[0].func;
- /*
- * If going from the iterator back to a single caller,
- * we need to synchronize with __DO_TRACE to make sure
- * that the data passed to the callback is the one that
- * belongs to that callback.
- */
- if (sync)
- tracepoint_synchronize_unregister();
- }
-
__static_call_update(tp->static_call_key, tp->static_call_tramp, func);
}
* a pointer to it. This array is referenced by __DO_TRACE from
* include/linux/tracepoint.h using rcu_dereference_sched().
*/
- rcu_assign_pointer(tp->funcs, tp_funcs);
- tracepoint_update_call(tp, tp_funcs, false);
- static_key_enable(&tp->key);
+ switch (nr_func_state(tp_funcs)) {
+ case TP_FUNC_1: /* 0->1 */
+ /*
+ * Make sure new static func never uses old data after a
+ * 1->0->1 transition sequence.
+ */
+ tp_rcu_cond_sync(TP_TRANSITION_SYNC_1_0_1);
+ /* Set static call to first function */
+ tracepoint_update_call(tp, tp_funcs);
+ /* Both iterator and static call handle NULL tp->funcs */
+ rcu_assign_pointer(tp->funcs, tp_funcs);
+ static_key_enable(&tp->key);
+ break;
+ case TP_FUNC_2: /* 1->2 */
+ /* Set iterator static call */
+ tracepoint_update_call(tp, tp_funcs);
+ /*
+ * Iterator callback installed before updating tp->funcs.
+ * Requires ordering between RCU assign/dereference and
+ * static call update/call.
+ */
+ fallthrough;
+ case TP_FUNC_N: /* N->N+1 (N>1) */
+ rcu_assign_pointer(tp->funcs, tp_funcs);
+ /*
+ * Make sure static func never uses incorrect data after a
+ * N->...->2->1 (N>1) transition sequence.
+ */
+ if (tp_funcs[0].data != old[0].data)
+ tp_rcu_get_state(TP_TRANSITION_SYNC_N_2_1);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ break;
+ }
release_probes(old);
return 0;
/* Failed allocating new tp_funcs, replaced func with stub */
return 0;
- if (!tp_funcs) {
+ switch (nr_func_state(tp_funcs)) {
+ case TP_FUNC_0: /* 1->0 */
/* Removed last function */
if (tp->unregfunc && static_key_enabled(&tp->key))
tp->unregfunc();
static_key_disable(&tp->key);
+ /* Set iterator static call */
+ tracepoint_update_call(tp, tp_funcs);
+ /* Both iterator and static call handle NULL tp->funcs */
+ rcu_assign_pointer(tp->funcs, NULL);
+ /*
+ * Make sure new static func never uses old data after a
+ * 1->0->1 transition sequence.
+ */
+ tp_rcu_get_state(TP_TRANSITION_SYNC_1_0_1);
+ break;
+ case TP_FUNC_1: /* 2->1 */
rcu_assign_pointer(tp->funcs, tp_funcs);
- } else {
+ /*
+ * Make sure static func never uses incorrect data after a
+ * N->...->2->1 (N>2) transition sequence. If the first
+ * element's data has changed, then force the synchronization
+ * to prevent current readers that have loaded the old data
+ * from calling the new function.
+ */
+ if (tp_funcs[0].data != old[0].data)
+ tp_rcu_get_state(TP_TRANSITION_SYNC_N_2_1);
+ tp_rcu_cond_sync(TP_TRANSITION_SYNC_N_2_1);
+ /* Set static call to first function */
+ tracepoint_update_call(tp, tp_funcs);
+ break;
+ case TP_FUNC_2: /* N->N-1 (N>2) */
+ fallthrough;
+ case TP_FUNC_N:
rcu_assign_pointer(tp->funcs, tp_funcs);
- tracepoint_update_call(tp, tp_funcs,
- tp_funcs[0].func != old[0].func);
+ /*
+ * Make sure static func never uses incorrect data after a
+ * N->...->2->1 (N>2) transition sequence.
+ */
+ if (tp_funcs[0].data != old[0].data)
+ tp_rcu_get_state(TP_TRANSITION_SYNC_N_2_1);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ break;
}
release_probes(old);
return 0;
{
struct hlist_head *hashent = ucounts_hashentry(ns, uid);
struct ucounts *ucounts, *new;
+ long overflow;
spin_lock_irq(&ucounts_lock);
ucounts = find_ucounts(ns, uid, hashent);
return new;
}
}
+ overflow = atomic_add_negative(1, &ucounts->count);
spin_unlock_irq(&ucounts_lock);
- ucounts = get_ucounts(ucounts);
+ if (overflow) {
+ put_ucounts(ucounts);
+ return NULL;
+ }
return ucounts;
}
{
unsigned long flags;
- if (atomic_dec_and_test(&ucounts->count)) {
- spin_lock_irqsave(&ucounts_lock, flags);
+ if (atomic_dec_and_lock_irqsave(&ucounts->count, &ucounts_lock, flags)) {
hlist_del_init(&ucounts->node);
spin_unlock_irqrestore(&ucounts_lock, flags);
kfree(ucounts);
unbound_release_work);
struct workqueue_struct *wq = pwq->wq;
struct worker_pool *pool = pwq->pool;
- bool is_last;
+ bool is_last = false;
- if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)))
- return;
+ /*
+ * when @pwq is not linked, it doesn't hold any reference to the
+ * @wq, and @wq is invalid to access.
+ */
+ if (!list_empty(&pwq->pwqs_node)) {
+ if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)))
+ return;
- mutex_lock(&wq->mutex);
- list_del_rcu(&pwq->pwqs_node);
- is_last = list_empty(&wq->pwqs);
- mutex_unlock(&wq->mutex);
+ mutex_lock(&wq->mutex);
+ list_del_rcu(&pwq->pwqs_node);
+ is_last = list_empty(&wq->pwqs);
+ mutex_unlock(&wq->mutex);
+ }
mutex_lock(&wq_pool_mutex);
put_unbound_pool(pool);
config OBJAGG
tristate "objagg" if COMPILE_TEST
-config STRING_SELFTEST
- tristate "Test string functions"
-
endmenu
config GENERIC_IOREMAP
config TEST_HEXDUMP
tristate "Test functions located in the hexdump module at runtime"
+config STRING_SELFTEST
+ tristate "Test string functions at runtime"
+
config TEST_STRING_HELPERS
tristate "Test functions located in the string_helpers module at runtime"
for (pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); pfn++) {
void *entry;
- struct page *page;
entry = xa_load(&dmirror->pt, pfn);
- page = xa_untag_pointer(entry);
if (xa_pointer_tag(entry) == DPT_XA_TAG_ATOMIC)
return -EPERM;
}
blkcg_unpin_online(blkcg);
fprop_local_destroy_percpu(&wb->memcg_completions);
- percpu_ref_exit(&wb->refcnt);
spin_lock_irq(&cgwb_lock);
list_del(&wb->offline_node);
spin_unlock_irq(&cgwb_lock);
+ percpu_ref_exit(&wb->refcnt);
wb_exit(wb);
WARN_ON_ONCE(!list_empty(&wb->b_attached));
kfree_rcu(wb, rcu);
continue;
}
- refs = min3(pages_per_huge_page(h) - pfn_offset,
- (vma->vm_end - vaddr) >> PAGE_SHIFT, remainder);
+ /* vaddr may not be aligned to PAGE_SIZE */
+ refs = min3(pages_per_huge_page(h) - pfn_offset, remainder,
+ (vma->vm_end - ALIGN_DOWN(vaddr, PAGE_SIZE)) >> PAGE_SHIFT);
if (pages || vmas)
record_subpages_vmas(mem_map_offset(page, pfn_offset),
#ifdef CONFIG_KASAN_HW_TAGS
#include <linux/static_key.h>
+#include "../slab.h"
DECLARE_STATIC_KEY_FALSE(kasan_flag_stacktrace);
extern bool kasan_flag_async __ro_after_init;
if (WARN_ON((unsigned long)addr & KASAN_GRANULE_MASK))
return;
+ /*
+ * Explicitly initialize the memory with the precise object size to
+ * avoid overwriting the SLAB redzone. This disables initialization in
+ * the arch code and may thus lead to performance penalty. The penalty
+ * is accepted since SLAB redzones aren't enabled in production builds.
+ */
+ if (__slub_debug_enabled() &&
+ init && ((unsigned long)size & KASAN_GRANULE_MASK)) {
+ init = false;
+ memzero_explicit((void *)addr, size);
+ }
size = round_up(size, KASAN_GRANULE_SIZE);
hw_set_mem_tag_range((void *)addr, size, tag, init);
void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags)
{
/*
+ * Perform size check before switching kfence_allocation_gate, so that
+ * we don't disable KFENCE without making an allocation.
+ */
+ if (size > PAGE_SIZE)
+ return NULL;
+
+ /*
+ * Skip allocations from non-default zones, including DMA. We cannot
+ * guarantee that pages in the KFENCE pool will have the requested
+ * properties (e.g. reside in DMAable memory).
+ */
+ if ((flags & GFP_ZONEMASK) ||
+ (s->flags & (SLAB_CACHE_DMA | SLAB_CACHE_DMA32)))
+ return NULL;
+
+ /*
* allocation_gate only needs to become non-zero, so it doesn't make
* sense to continue writing to it and pay the associated contention
* cost, in case we have a large number of concurrent allocations.
if (!READ_ONCE(kfence_enabled))
return NULL;
- if (size > PAGE_SIZE)
- return NULL;
-
return kfence_guarded_alloc(s, size, flags);
}
tracepoint_synchronize_unregister();
}
-late_initcall(kfence_test_init);
+late_initcall_sync(kfence_test_init);
module_exit(kfence_test_exit);
MODULE_LICENSE("GPL v2");
return true;
/* skip hotpluggable memory regions if needed */
- if (movable_node_is_enabled() && memblock_is_hotpluggable(m))
+ if (movable_node_is_enabled() && memblock_is_hotpluggable(m) &&
+ !(flags & MEMBLOCK_HOTPLUG))
return true;
/* if we want mirror memory skip non-mirror memory regions */
unsigned long val;
if (mem_cgroup_is_root(memcg)) {
- cgroup_rstat_flush(memcg->css.cgroup);
+ /* mem_cgroup_threshold() calls here from irqsafe context */
+ cgroup_rstat_flush_irqsafe(memcg->css.cgroup);
val = memcg_page_state(memcg, NR_FILE_PAGES) +
memcg_page_state(memcg, NR_ANON_MAPPED);
if (swap)
return ret;
}
- if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd)))
+ if (vmf->prealloc_pte) {
+ vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
+ if (likely(pmd_none(*vmf->pmd))) {
+ mm_inc_nr_ptes(vma->vm_mm);
+ pmd_populate(vma->vm_mm, vmf->pmd, vmf->prealloc_pte);
+ vmf->prealloc_pte = NULL;
+ }
+ spin_unlock(vmf->ptl);
+ } else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) {
return VM_FAULT_OOM;
+ }
}
/* See comment in handle_pte_fault() */
}
/*
- * Gigantic pages are so large that we do not guarantee that page++ pointer
- * arithmetic will work across the entire page. We need something more
- * specialized.
- */
-static void __copy_gigantic_page(struct page *dst, struct page *src,
- int nr_pages)
-{
- int i;
- struct page *dst_base = dst;
- struct page *src_base = src;
-
- for (i = 0; i < nr_pages; ) {
- cond_resched();
- copy_highpage(dst, src);
-
- i++;
- dst = mem_map_next(dst, dst_base, i);
- src = mem_map_next(src, src_base, i);
- }
-}
-
-void copy_huge_page(struct page *dst, struct page *src)
-{
- int i;
- int nr_pages;
-
- if (PageHuge(src)) {
- /* hugetlbfs page */
- struct hstate *h = page_hstate(src);
- nr_pages = pages_per_huge_page(h);
-
- if (unlikely(nr_pages > MAX_ORDER_NR_PAGES)) {
- __copy_gigantic_page(dst, src, nr_pages);
- return;
- }
- } else {
- /* thp page */
- BUG_ON(!PageTransHuge(src));
- nr_pages = thp_nr_pages(src);
- }
-
- for (i = 0; i < nr_pages; i++) {
- cond_resched();
- copy_highpage(dst + i, src + i);
- }
-}
-
-/*
* Copy the page to its new location
*/
void migrate_page_states(struct page *newpage, struct page *page)
LIST_HEAD(migratepages);
new_page_t *new;
bool compound;
- unsigned int nr_pages = thp_nr_pages(page);
+ int nr_pages = thp_nr_pages(page);
/*
* PTE mapped THP or HugeTLB page can't reach here so the page could
#define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \
do { \
const char *memcg_path; \
- preempt_disable(); \
+ local_lock(&memcg_paths.lock); \
memcg_path = get_mm_memcg_path(mm); \
trace_mmap_lock_##type(mm, \
memcg_path != NULL ? memcg_path : "", \
##__VA_ARGS__); \
if (likely(memcg_path != NULL)) \
put_memcg_path_buf(); \
- preempt_enable(); \
+ local_unlock(&memcg_paths.lock); \
} while (0)
#else /* !CONFIG_MEMCG */
}
#endif
- if (_init_on_alloc_enabled_early) {
- if (page_poisoning_requested)
- pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, "
- "will take precedence over init_on_alloc\n");
- else
- static_branch_enable(&init_on_alloc);
- }
- if (_init_on_free_enabled_early) {
- if (page_poisoning_requested)
- pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, "
- "will take precedence over init_on_free\n");
- else
- static_branch_enable(&init_on_free);
+ if ((_init_on_alloc_enabled_early || _init_on_free_enabled_early) &&
+ page_poisoning_requested) {
+ pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, "
+ "will take precedence over init_on_alloc and init_on_free\n");
+ _init_on_alloc_enabled_early = false;
+ _init_on_free_enabled_early = false;
}
+ if (_init_on_alloc_enabled_early)
+ static_branch_enable(&init_on_alloc);
+ else
+ static_branch_disable(&init_on_alloc);
+
+ if (_init_on_free_enabled_early)
+ static_branch_enable(&init_on_free);
+ else
+ static_branch_disable(&init_on_free);
+
#ifdef CONFIG_DEBUG_PAGEALLOC
if (!debug_pagealloc_enabled())
return;
#endif /* CONFIG_FAIL_PAGE_ALLOC */
-static noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
+noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
{
return __should_fail_alloc_page(gfp_mask, order);
}
unsigned int alloc_flags = ALLOC_WMARK_LOW;
int nr_populated = 0, nr_account = 0;
- if (unlikely(nr_pages <= 0))
- return 0;
-
/*
* Skip populated array elements to determine if any pages need
* to be allocated before disabling IRQs.
while (page_array && nr_populated < nr_pages && page_array[nr_populated])
nr_populated++;
+ /* No pages requested? */
+ if (unlikely(nr_pages <= 0))
+ goto out;
+
/* Already populated array? */
if (unlikely(page_array && nr_pages - nr_populated == 0))
- return nr_populated;
+ goto out;
/* Use the single page allocator for one page. */
if (nr_pages - nr_populated == 1)
goto failed;
+#ifdef CONFIG_PAGE_OWNER
+ /*
+ * PAGE_OWNER may recurse into the allocator to allocate space to
+ * save the stack with pagesets.lock held. Releasing/reacquiring
+ * removes much of the performance benefit of bulk allocation so
+ * force the caller to allocate one page at a time as it'll have
+ * similar performance to added complexity to the bulk allocator.
+ */
+ if (static_branch_unlikely(&page_owner_inited))
+ goto failed;
+#endif
+
/* May set ALLOC_NOFRAGMENT, fragmentation will return 1 page. */
gfp &= gfp_allowed_mask;
alloc_gfp = gfp;
if (!prepare_alloc_pages(gfp, 0, preferred_nid, nodemask, &ac, &alloc_gfp, &alloc_flags))
- return 0;
+ goto out;
gfp = alloc_gfp;
/* Find an allowed local zone that meets the low watermark. */
__count_zid_vm_events(PGALLOC, zone_idx(zone), nr_account);
zone_statistics(ac.preferred_zoneref->zone, zone, nr_account);
+out:
return nr_populated;
failed_irq:
nr_populated++;
}
- return nr_populated;
+ goto out;
}
EXPORT_SYMBOL_GPL(__alloc_pages_bulk);
/*
* If the page is mlock()d, we cannot swap it out.
*/
- if (!(flags & TTU_IGNORE_MLOCK)) {
- if (vma->vm_flags & VM_LOCKED) {
- /* PTE-mapped THP are never marked as mlocked */
- if (!PageTransCompound(page) ||
- (PageHead(page) && !PageDoubleMap(page))) {
- /*
- * Holding pte lock, we do *not* need
- * mmap_lock here
- */
- mlock_vma_page(page);
- }
- ret = false;
- page_vma_mapped_walk_done(&pvmw);
- break;
- }
+ if (!(flags & TTU_IGNORE_MLOCK) &&
+ (vma->vm_flags & VM_LOCKED)) {
+ /*
+ * PTE-mapped THP are never marked as mlocked: so do
+ * not set it on a DoubleMap THP, nor on an Anon THP
+ * (which may still be PTE-mapped after DoubleMap was
+ * cleared). But stop unmapping even in those cases.
+ */
+ if (!PageTransCompound(page) || (PageHead(page) &&
+ !PageDoubleMap(page) && !PageAnon(page)))
+ mlock_vma_page(page);
+ page_vma_mapped_walk_done(&pvmw);
+ ret = false;
+ break;
}
/* Unexpected PMD-mapped THP? */
*/
if (vma->vm_flags & VM_LOCKED) {
/*
- * PTE-mapped THP are never marked as mlocked, but
- * this function is never called when PageDoubleMap().
+ * PTE-mapped THP are never marked as mlocked; but
+ * this function is never called on a DoubleMap THP,
+ * nor on an Anon THP (which may still be PTE-mapped
+ * after DoubleMap was cleared).
*/
mlock_vma_page(page);
/*
VM_BUG_ON_PAGE(!PageLocked(page) || PageLRU(page), page);
VM_BUG_ON_PAGE(PageCompound(page) && PageDoubleMap(page), page);
+ /* Anon THP are only marked as mlocked when singly mapped */
+ if (PageTransCompound(page) && PageAnon(page))
+ return;
+
rmap_walk(page, &rwc);
}
}
const struct address_space_operations secretmem_aops = {
+ .set_page_dirty = __set_page_dirty_no_writeback,
.freepage = secretmem_freepage,
.migratepage = secretmem_migratepage,
.isolate_page = secretmem_isolate_page,
#endif
extern void print_tracking(struct kmem_cache *s, void *object);
long validate_slab_cache(struct kmem_cache *s);
+static inline bool __slub_debug_enabled(void)
+{
+ return static_branch_unlikely(&slub_debug_enabled);
+}
#else
static inline void print_tracking(struct kmem_cache *s, void *object)
{
}
+static inline bool __slub_debug_enabled(void)
+{
+ return false;
+}
#endif
/*
*/
static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t flags)
{
-#ifdef CONFIG_SLUB_DEBUG
- VM_WARN_ON_ONCE(!(flags & SLAB_DEBUG_FLAGS));
- if (static_branch_unlikely(&slub_debug_enabled))
+ if (IS_ENABLED(CONFIG_SLUB_DEBUG))
+ VM_WARN_ON_ONCE(!(flags & SLAB_DEBUG_FLAGS));
+ if (__slub_debug_enabled())
return s->flags & flags;
-#endif
return false;
}
continue;
page = virt_to_head_page(p[i]);
- objcgs = page_objcgs(page);
+ objcgs = page_objcgs_check(page);
if (!objcgs)
continue;
#include <linux/cpuset.h>
#include <linux/mempolicy.h>
#include <linux/ctype.h>
-#include <linux/stackdepot.h>
#include <linux/debugobjects.h>
#include <linux/kallsyms.h>
#include <linux/kfence.h>
*/
#ifdef CONFIG_SLUB_DEBUG
-
#ifdef CONFIG_SLUB_DEBUG_ON
DEFINE_STATIC_KEY_TRUE(slub_debug_enabled);
#else
DEFINE_STATIC_KEY_FALSE(slub_debug_enabled);
#endif
-
-static inline bool __slub_debug_enabled(void)
-{
- return static_branch_unlikely(&slub_debug_enabled);
-}
-
-#else /* CONFIG_SLUB_DEBUG */
-
-static inline bool __slub_debug_enabled(void)
-{
- return false;
-}
-
#endif /* CONFIG_SLUB_DEBUG */
static inline bool kmem_cache_debug(struct kmem_cache *s)
#define TRACK_ADDRS_COUNT 16
struct track {
unsigned long addr; /* Called from address */
-#ifdef CONFIG_STACKDEPOT
- depot_stack_handle_t handle;
+#ifdef CONFIG_STACKTRACE
+ unsigned long addrs[TRACK_ADDRS_COUNT]; /* Called from address */
#endif
int cpu; /* Was running on cpu */
int pid; /* Pid context */
return kasan_reset_tag(p + alloc);
}
-#ifdef CONFIG_STACKDEPOT
-static depot_stack_handle_t save_stack_depot_trace(gfp_t flags)
-{
- unsigned long entries[TRACK_ADDRS_COUNT];
- depot_stack_handle_t handle;
- unsigned int nr_entries;
-
- nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 4);
- handle = stack_depot_save(entries, nr_entries, flags);
- return handle;
-}
-#endif
-
static void set_track(struct kmem_cache *s, void *object,
enum track_item alloc, unsigned long addr)
{
struct track *p = get_track(s, object, alloc);
if (addr) {
-#ifdef CONFIG_STACKDEPOT
- p->handle = save_stack_depot_trace(GFP_NOWAIT);
+#ifdef CONFIG_STACKTRACE
+ unsigned int nr_entries;
+
+ metadata_access_enable();
+ nr_entries = stack_trace_save(kasan_reset_tag(p->addrs),
+ TRACK_ADDRS_COUNT, 3);
+ metadata_access_disable();
+
+ if (nr_entries < TRACK_ADDRS_COUNT)
+ p->addrs[nr_entries] = 0;
#endif
p->addr = addr;
p->cpu = smp_processor_id();
pr_err("%s in %pS age=%lu cpu=%u pid=%d\n",
s, (void *)t->addr, pr_time - t->when, t->cpu, t->pid);
-#ifdef CONFIG_STACKDEPOT
+#ifdef CONFIG_STACKTRACE
{
- depot_stack_handle_t handle;
- unsigned long *entries;
- unsigned int nr_entries;
-
- handle = READ_ONCE(t->handle);
- if (!handle) {
- pr_err("object allocation/free stack trace missing\n");
- } else {
- nr_entries = stack_depot_fetch(handle, &entries);
- stack_trace_print(entries, nr_entries, 0);
- }
+ int i;
+ for (i = 0; i < TRACK_ADDRS_COUNT; i++)
+ if (t->addrs[i])
+ pr_err("\t%pS\n", (void *)t->addrs[i]);
+ else
+ break;
}
#endif
}
struct kmem_cache *s;
};
+static inline void free_nonslab_page(struct page *page)
+{
+ unsigned int order = compound_order(page);
+
+ VM_BUG_ON_PAGE(!PageCompound(page), page);
+ kfree_hook(page_address(page));
+ mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, -(PAGE_SIZE << order));
+ __free_pages(page, order);
+}
+
/*
* This function progressively scans the array with free objects (with
* a limited look ahead) and extract objects belonging to the same
if (!s) {
/* Handle kalloc'ed objects */
if (unlikely(!PageSlab(page))) {
- BUG_ON(!PageCompound(page));
- kfree_hook(object);
- __free_pages(page, compound_order(page));
+ free_nonslab_page(page);
p[size] = NULL; /* mark object processed */
return size;
}
objp = fixup_red_left(s, objp);
trackp = get_track(s, objp, TRACK_ALLOC);
kpp->kp_ret = (void *)trackp->addr;
-#ifdef CONFIG_STACKDEPOT
- {
- depot_stack_handle_t handle;
- unsigned long *entries;
- unsigned int nr_entries;
-
- handle = READ_ONCE(trackp->handle);
- if (handle) {
- nr_entries = stack_depot_fetch(handle, &entries);
- for (i = 0; i < KS_ADDRS_COUNT && i < nr_entries; i++)
- kpp->kp_stack[i] = (void *)entries[i];
- }
+#ifdef CONFIG_STACKTRACE
+ for (i = 0; i < KS_ADDRS_COUNT && i < TRACK_ADDRS_COUNT; i++) {
+ kpp->kp_stack[i] = (void *)trackp->addrs[i];
+ if (!kpp->kp_stack[i])
+ break;
+ }
- trackp = get_track(s, objp, TRACK_FREE);
- handle = READ_ONCE(trackp->handle);
- if (handle) {
- nr_entries = stack_depot_fetch(handle, &entries);
- for (i = 0; i < KS_ADDRS_COUNT && i < nr_entries; i++)
- kpp->kp_free_stack[i] = (void *)entries[i];
- }
+ trackp = get_track(s, objp, TRACK_FREE);
+ for (i = 0; i < KS_ADDRS_COUNT && i < TRACK_ADDRS_COUNT; i++) {
+ kpp->kp_free_stack[i] = (void *)trackp->addrs[i];
+ if (!kpp->kp_free_stack[i])
+ break;
}
#endif
#endif
page = virt_to_head_page(x);
if (unlikely(!PageSlab(page))) {
- unsigned int order = compound_order(page);
-
- BUG_ON(!PageCompound(page));
- kfree_hook(object);
- mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B,
- -(PAGE_SIZE << order));
- __free_pages(page, order);
+ free_nonslab_page(page);
return;
}
slab_free(page->slab_cache, page, object, NULL, 1, _RET_IP_);
}
EXPORT_SYMBOL_GPL(__page_mapcount);
+void copy_huge_page(struct page *dst, struct page *src)
+{
+ unsigned i, nr = compound_nr(src);
+
+ for (i = 0; i < nr; i++) {
+ cond_resched();
+ copy_highpage(nth_page(dst, i), nth_page(src, i));
+ }
+}
+
int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS;
int sysctl_overcommit_ratio __read_mostly = 50;
unsigned long sysctl_overcommit_kbytes __read_mostly;
kfree(attr);
}
+static void garp_attr_destroy_all(struct garp_applicant *app)
+{
+ struct rb_node *node, *next;
+ struct garp_attr *attr;
+
+ for (node = rb_first(&app->gid);
+ next = node ? rb_next(node) : NULL, node != NULL;
+ node = next) {
+ attr = rb_entry(node, struct garp_attr, node);
+ garp_attr_destroy(app, attr);
+ }
+}
+
static int garp_pdu_init(struct garp_applicant *app)
{
struct sk_buff *skb;
spin_lock_bh(&app->lock);
garp_gid_event(app, GARP_EVENT_TRANSMIT_PDU);
+ garp_attr_destroy_all(app);
garp_pdu_queue(app);
spin_unlock_bh(&app->lock);
kfree(attr);
}
+static void mrp_attr_destroy_all(struct mrp_applicant *app)
+{
+ struct rb_node *node, *next;
+ struct mrp_attr *attr;
+
+ for (node = rb_first(&app->mad);
+ next = node ? rb_next(node) : NULL, node != NULL;
+ node = next) {
+ attr = rb_entry(node, struct mrp_attr, node);
+ mrp_attr_destroy(app, attr);
+ }
+}
+
static int mrp_pdu_init(struct mrp_applicant *app)
{
struct sk_buff *skb;
spin_lock_bh(&app->lock);
mrp_mad_event(app, MRP_EVENT_TX);
+ mrp_attr_destroy_all(app);
mrp_pdu_queue(app);
spin_unlock_bh(&app->lock);
/* Unregister HCI device */
void hci_unregister_dev(struct hci_dev *hdev)
{
- int id;
-
BT_DBG("%p name %s bus %d", hdev, hdev->name, hdev->bus);
hci_dev_set_flag(hdev, HCI_UNREGISTER);
- id = hdev->id;
-
write_lock(&hci_dev_list_lock);
list_del(&hdev->list);
write_unlock(&hci_dev_list_lock);
}
device_del(&hdev->dev);
+ /* Actual cleanup is deferred until hci_cleanup_dev(). */
+ hci_dev_put(hdev);
+}
+EXPORT_SYMBOL(hci_unregister_dev);
+/* Cleanup HCI device */
+void hci_cleanup_dev(struct hci_dev *hdev)
+{
debugfs_remove_recursive(hdev->debugfs);
kfree_const(hdev->hw_info);
kfree_const(hdev->fw_info);
hci_blocked_keys_clear(hdev);
hci_dev_unlock(hdev);
- hci_dev_put(hdev);
-
- ida_simple_remove(&hci_index_ida, id);
+ ida_simple_remove(&hci_index_ida, hdev->id);
}
-EXPORT_SYMBOL(hci_unregister_dev);
/* Suspend HCI device */
int hci_suspend_dev(struct hci_dev *hdev)
char comm[TASK_COMM_LEN];
};
+static struct hci_dev *hci_hdev_from_sock(struct sock *sk)
+{
+ struct hci_dev *hdev = hci_pi(sk)->hdev;
+
+ if (!hdev)
+ return ERR_PTR(-EBADFD);
+ if (hci_dev_test_flag(hdev, HCI_UNREGISTER))
+ return ERR_PTR(-EPIPE);
+ return hdev;
+}
+
void hci_sock_set_flag(struct sock *sk, int nr)
{
set_bit(nr, &hci_pi(sk)->flags);
if (event == HCI_DEV_UNREG) {
struct sock *sk;
- /* Detach sockets from device */
+ /* Wake up sockets using this dead device */
read_lock(&hci_sk_list.lock);
sk_for_each(sk, &hci_sk_list.head) {
- lock_sock(sk);
if (hci_pi(sk)->hdev == hdev) {
- hci_pi(sk)->hdev = NULL;
sk->sk_err = EPIPE;
- sk->sk_state = BT_OPEN;
sk->sk_state_change(sk);
-
- hci_dev_put(hdev);
}
- release_sock(sk);
}
read_unlock(&hci_sk_list.lock);
}
static int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd,
unsigned long arg)
{
- struct hci_dev *hdev = hci_pi(sk)->hdev;
+ struct hci_dev *hdev = hci_hdev_from_sock(sk);
- if (!hdev)
- return -EBADFD;
+ if (IS_ERR(hdev))
+ return PTR_ERR(hdev);
if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL))
return -EBUSY;
lock_sock(sk);
+ /* Allow detaching from dead device and attaching to alive device, if
+ * the caller wants to re-bind (instead of close) this socket in
+ * response to hci_sock_dev_event(HCI_DEV_UNREG) notification.
+ */
+ hdev = hci_pi(sk)->hdev;
+ if (hdev && hci_dev_test_flag(hdev, HCI_UNREGISTER)) {
+ hci_pi(sk)->hdev = NULL;
+ sk->sk_state = BT_OPEN;
+ hci_dev_put(hdev);
+ }
+ hdev = NULL;
+
if (sk->sk_state == BT_BOUND) {
err = -EALREADY;
goto done;
lock_sock(sk);
- hdev = hci_pi(sk)->hdev;
- if (!hdev) {
- err = -EBADFD;
+ hdev = hci_hdev_from_sock(sk);
+ if (IS_ERR(hdev)) {
+ err = PTR_ERR(hdev);
goto done;
}
goto done;
}
- hdev = hci_pi(sk)->hdev;
- if (!hdev) {
- err = -EBADFD;
+ hdev = hci_hdev_from_sock(sk);
+ if (IS_ERR(hdev)) {
+ err = PTR_ERR(hdev);
goto done;
}
static void bt_host_release(struct device *dev)
{
struct hci_dev *hdev = to_hci_dev(dev);
+
+ if (hci_dev_test_flag(hdev, HCI_UNREGISTER))
+ hci_cleanup_dev(hdev);
kfree(hdev);
module_put(THIS_MODULE);
}
void *data;
int ret;
+ if (prog->expected_attach_type == BPF_XDP_DEVMAP ||
+ prog->expected_attach_type == BPF_XDP_CPUMAP)
+ return -EINVAL;
if (kattr->test.ctx_in || kattr->test.ctx_out)
return -EINVAL;
case SWITCHDEV_FDB_ADD_TO_BRIDGE:
fdb_info = ptr;
err = br_fdb_external_learn_add(br, p, fdb_info->addr,
- fdb_info->vid, false);
+ fdb_info->vid,
+ fdb_info->is_local, false);
if (err) {
err = notifier_from_errno(err);
break;
struct net_device *dst_dev;
dst_dev = dst ? dst->dev : br->dev;
- if (dst_dev != br_dev && dst_dev != dev)
+ if (dst_dev && dst_dev != dev)
continue;
err = br_fdb_replay_one(nb, fdb, dst_dev, action, ctx);
static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br,
struct net_bridge_port *p, const unsigned char *addr,
- u16 nlh_flags, u16 vid, struct nlattr *nfea_tb[])
+ u16 nlh_flags, u16 vid, struct nlattr *nfea_tb[],
+ struct netlink_ext_ack *extack)
{
int err = 0;
rcu_read_unlock();
local_bh_enable();
} else if (ndm->ndm_flags & NTF_EXT_LEARNED) {
- err = br_fdb_external_learn_add(br, p, addr, vid, true);
+ if (!p && !(ndm->ndm_state & NUD_PERMANENT)) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "FDB entry towards bridge must be permanent");
+ return -EINVAL;
+ }
+
+ err = br_fdb_external_learn_add(br, p, addr, vid,
+ ndm->ndm_state & NUD_PERMANENT,
+ true);
} else {
spin_lock_bh(&br->hash_lock);
err = fdb_add_entry(br, p, addr, ndm, nlh_flags, vid, nfea_tb);
}
/* VID was specified, so use it. */
- err = __br_fdb_add(ndm, br, p, addr, nlh_flags, vid, nfea_tb);
+ err = __br_fdb_add(ndm, br, p, addr, nlh_flags, vid, nfea_tb,
+ extack);
} else {
- err = __br_fdb_add(ndm, br, p, addr, nlh_flags, 0, nfea_tb);
+ err = __br_fdb_add(ndm, br, p, addr, nlh_flags, 0, nfea_tb,
+ extack);
if (err || !vg || !vg->num_vlans)
goto out;
if (!br_vlan_should_use(v))
continue;
err = __br_fdb_add(ndm, br, p, addr, nlh_flags, v->vid,
- nfea_tb);
+ nfea_tb, extack);
if (err)
goto out;
}
}
int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
- const unsigned char *addr, u16 vid,
+ const unsigned char *addr, u16 vid, bool is_local,
bool swdev_notify)
{
struct net_bridge_fdb_entry *fdb;
if (swdev_notify)
flags |= BIT(BR_FDB_ADDED_BY_USER);
+
+ if (is_local)
+ flags |= BIT(BR_FDB_LOCAL);
+
fdb = fdb_create(br, p, addr, vid, flags);
if (!fdb) {
err = -ENOMEM;
if (swdev_notify)
set_bit(BR_FDB_ADDED_BY_USER, &fdb->flags);
+ if (is_local)
+ set_bit(BR_FDB_LOCAL, &fdb->flags);
+
if (modified)
fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify);
}
struct net_bridge_port *p;
int err = 0;
unsigned br_hr, dev_hr;
- bool changed_addr;
+ bool changed_addr, fdb_synced = false;
/* Don't allow bridging non-ethernet like devices. */
if ((dev->flags & IFF_LOOPBACK) ||
list_add_rcu(&p->list, &br->port_list);
nbp_update_port_count(br);
+ if (!br_promisc_port(p) && (p->dev->priv_flags & IFF_UNICAST_FLT)) {
+ /* When updating the port count we also update all ports'
+ * promiscuous mode.
+ * A port leaving promiscuous mode normally gets the bridge's
+ * fdb synced to the unicast filter (if supported), however,
+ * `br_port_clear_promisc` does not distinguish between
+ * non-promiscuous ports and *new* ports, so we need to
+ * sync explicitly here.
+ */
+ fdb_synced = br_fdb_sync_static(br, p) == 0;
+ if (!fdb_synced)
+ netdev_err(dev, "failed to sync bridge static fdb addresses to this port\n");
+ }
netdev_update_features(br->dev);
return 0;
err7:
+ if (fdb_synced)
+ br_fdb_unsync_static(br, p);
list_del_rcu(&p->list);
br_fdb_delete_by_port(br, p, 0, 1);
nbp_update_port_count(br);
pim_hdr_type(pimhdr) != PIM_TYPE_HELLO)
return;
+ spin_lock(&br->multicast_lock);
br_ip4_multicast_mark_router(br, port);
+ spin_unlock(&br->multicast_lock);
}
static int br_ip4_multicast_mrd_rcv(struct net_bridge *br,
igmp_hdr(skb)->type != IGMP_MRDISC_ADV)
return -ENOMSG;
+ spin_lock(&br->multicast_lock);
br_ip4_multicast_mark_router(br, port);
+ spin_unlock(&br->multicast_lock);
return 0;
}
if (icmp6_hdr(skb)->icmp6_type != ICMPV6_MRDISC_ADV)
return;
+ spin_lock(&br->multicast_lock);
br_ip6_multicast_mark_router(br, port);
+ spin_unlock(&br->multicast_lock);
}
static int br_multicast_ipv6_rcv(struct net_bridge *br,
int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p);
void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p);
int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
- const unsigned char *addr, u16 vid,
+ const unsigned char *addr, u16 vid, bool is_local,
bool swdev_notify);
int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p,
const unsigned char *addr, u16 vid,
goto err;
ret = -EINVAL;
- if (unlikely(msg->msg_iter.iov->iov_base == NULL))
+ if (unlikely(msg->msg_iter.nr_segs == 0) ||
+ unlikely(msg->msg_iter.iov->iov_base == NULL))
goto err;
noblock = msg->msg_flags & MSG_DONTWAIT;
static bool j1939_session_deactivate(struct j1939_session *session)
{
+ struct j1939_priv *priv = session->priv;
bool active;
- j1939_session_list_lock(session->priv);
+ j1939_session_list_lock(priv);
+ /* This function should be called with a session ref-count of at
+ * least 2.
+ */
+ WARN_ON_ONCE(kref_read(&session->kref) < 2);
active = j1939_session_deactivate_locked(session);
- j1939_session_list_unlock(session->priv);
+ j1939_session_list_unlock(priv);
return active;
}
if (!session->transmission)
j1939_tp_schedule_txtimer(session, 0);
} else {
- j1939_tp_set_rxtimeout(session, 250);
+ j1939_tp_set_rxtimeout(session, 750);
}
session->last_cmd = 0xff;
consume_skb(se_skb);
return -EFAULT;
}
+ rtnl_lock();
lock_sock(sk);
- if (ro->bound && ro->ifindex)
+ if (ro->bound && ro->ifindex) {
dev = dev_get_by_index(sock_net(sk), ro->ifindex);
+ if (!dev) {
+ if (count > 1)
+ kfree(filter);
+ err = -ENODEV;
+ goto out_fil;
+ }
+ }
if (ro->bound) {
/* (try to) register the new filters */
dev_put(dev);
release_sock(sk);
+ rtnl_unlock();
break;
err_mask &= CAN_ERR_MASK;
+ rtnl_lock();
lock_sock(sk);
- if (ro->bound && ro->ifindex)
+ if (ro->bound && ro->ifindex) {
dev = dev_get_by_index(sock_net(sk), ro->ifindex);
+ if (!dev) {
+ err = -ENODEV;
+ goto out_err;
+ }
+ }
/* remove current error mask */
if (ro->bound) {
dev_put(dev);
release_sock(sk);
+ rtnl_unlock();
break;
#include <trace/events/napi.h>
#include <trace/events/net.h>
#include <trace/events/skb.h>
+#include <trace/events/qdisc.h>
#include <linux/inetdevice.h>
#include <linux/cpu_rmap.h>
#include <linux/static_key.h>
}
}
+static int dev_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *q,
+ struct sk_buff **to_free,
+ struct netdev_queue *txq)
+{
+ int rc;
+
+ rc = q->enqueue(skb, q, to_free) & NET_XMIT_MASK;
+ if (rc == NET_XMIT_SUCCESS)
+ trace_qdisc_enqueue(q, txq, skb);
+ return rc;
+}
+
static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
struct net_device *dev,
struct netdev_queue *txq)
* of q->seqlock to protect from racing with requeuing.
*/
if (unlikely(!nolock_qdisc_is_empty(q))) {
- rc = q->enqueue(skb, q, &to_free) &
- NET_XMIT_MASK;
+ rc = dev_qdisc_enqueue(skb, q, &to_free, txq);
__qdisc_run(q);
qdisc_run_end(q);
return NET_XMIT_SUCCESS;
}
- rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
+ rc = dev_qdisc_enqueue(skb, q, &to_free, txq);
qdisc_run(q);
no_lock_out:
qdisc_run_end(q);
rc = NET_XMIT_SUCCESS;
} else {
- rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
+ rc = dev_qdisc_enqueue(skb, q, &to_free, txq);
if (qdisc_run_begin(q)) {
if (unlikely(contended)) {
spin_unlock(&q->busylock);
diffs = memcmp(skb_mac_header(p),
skb_mac_header(skb),
maclen);
+
+ diffs |= skb_get_nfct(p) ^ skb_get_nfct(skb);
+#if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+ if (!diffs) {
+ struct tc_skb_ext *skb_ext = skb_ext_find(skb, TC_SKB_EXT);
+ struct tc_skb_ext *p_ext = skb_ext_find(p, TC_SKB_EXT);
+
+ diffs |= (!!p_ext) ^ (!!skb_ext);
+ if (!diffs && unlikely(skb_ext))
+ diffs |= p_ext->chain ^ skb_ext->chain;
+ }
+#endif
+
NAPI_GRO_CB(p)->same_flow = !diffs;
}
}
case GRO_MERGED_FREE:
if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD)
napi_skb_free_stolen_head(skb);
+ else if (skb->fclone != SKB_FCLONE_UNAVAILABLE)
+ __kfree_skb(skb);
else
__kfree_skb_defer(skb);
break;
skb_shinfo(skb)->gso_type = 0;
skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
skb_ext_reset(skb);
+ nf_reset_ct(skb);
napi->skb = skb;
}
struct net_device *dev;
int err, fd;
+ rtnl_lock();
dev = dev_get_by_index(net, attr->link_create.target_ifindex);
- if (!dev)
+ if (!dev) {
+ rtnl_unlock();
return -EINVAL;
+ }
link = kzalloc(sizeof(*link), GFP_USER);
if (!link) {
err = -ENOMEM;
- goto out_put_dev;
+ goto unlock;
}
bpf_link_init(&link->link, BPF_LINK_TYPE_XDP, &bpf_xdp_link_lops, prog);
err = bpf_link_prime(&link->link, &link_primer);
if (err) {
kfree(link);
- goto out_put_dev;
+ goto unlock;
}
- rtnl_lock();
err = dev_xdp_attach_link(dev, NULL, link);
rtnl_unlock();
if (err) {
+ link->dev = NULL;
bpf_link_cleanup(&link_primer);
goto out_put_dev;
}
dev_put(dev);
return fd;
+unlock:
+ rtnl_unlock();
+
out_put_dev:
dev_put(dev);
return err;
switch (attrs->flavour) {
case DEVLINK_PORT_FLAVOUR_PHYSICAL:
- case DEVLINK_PORT_FLAVOUR_VIRTUAL:
n = snprintf(name, len, "p%u", attrs->phys.port_number);
if (n < len && attrs->split)
n += snprintf(name + n, len - n, "s%u",
attrs->phys.split_subport_number);
- if (!attrs->split)
- n = snprintf(name, len, "p%u", attrs->phys.port_number);
- else
- n = snprintf(name, len, "p%us%u",
- attrs->phys.port_number,
- attrs->phys.split_subport_number);
-
break;
case DEVLINK_PORT_FLAVOUR_CPU:
case DEVLINK_PORT_FLAVOUR_DSA:
n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf,
attrs->pci_sf.sf);
break;
+ case DEVLINK_PORT_FLAVOUR_VIRTUAL:
+ return -EOPNOTSUPP;
}
if (n >= len)
}
EXPORT_SYMBOL(flow_get_u32_dst);
-/* Sort the source and destination IP (and the ports if the IP are the same),
+/* Sort the source and destination IP and the ports,
* to have consistent hash within the two directions
*/
static inline void __flow_hash_consistentify(struct flow_keys *keys)
case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
addr_diff = (__force u32)keys->addrs.v4addrs.dst -
(__force u32)keys->addrs.v4addrs.src;
- if ((addr_diff < 0) ||
- (addr_diff == 0 &&
- ((__force u16)keys->ports.dst <
- (__force u16)keys->ports.src))) {
+ if (addr_diff < 0)
swap(keys->addrs.v4addrs.src, keys->addrs.v4addrs.dst);
+
+ if ((__force u16)keys->ports.dst <
+ (__force u16)keys->ports.src) {
swap(keys->ports.src, keys->ports.dst);
}
break;
addr_diff = memcmp(&keys->addrs.v6addrs.dst,
&keys->addrs.v6addrs.src,
sizeof(keys->addrs.v6addrs.dst));
- if ((addr_diff < 0) ||
- (addr_diff == 0 &&
- ((__force u16)keys->ports.dst <
- (__force u16)keys->ports.src))) {
+ if (addr_diff < 0) {
for (i = 0; i < 4; i++)
swap(keys->addrs.v6addrs.src.s6_addr32[i],
keys->addrs.v6addrs.dst.s6_addr32[i]);
+ }
+ if ((__force u16)keys->ports.dst <
+ (__force u16)keys->ports.src) {
swap(keys->ports.src, keys->ports.dst);
}
break;
if (skb->cloned &&
atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1,
&shinfo->dataref))
- return;
+ goto exit;
skb_zcopy_clear(skb, true);
kfree_skb_list(shinfo->frag_list);
skb_free_head(skb);
+exit:
+ /* When we clone an SKB we copy the reycling bit. The pp_recycle
+ * bit is only set on the head though, so in order to avoid races
+ * while trying to recycle fragments on __skb_frag_unref() we need
+ * to make one SKB responsible for triggering the recycle path.
+ * So disable the recycling bit if an SKB is cloned and we have
+ * additional references to to the fragmented part of the SKB.
+ * Eventually the last SKB will have the recycling bit set and it's
+ * dataref set to 0, which will trigger the recycling
+ */
+ skb->pp_recycle = 0;
}
/*
void napi_skb_free_stolen_head(struct sk_buff *skb)
{
+ nf_reset_ct(skb);
skb_dst_drop(skb);
skb_ext_put(skb);
napi_skb_cache_put(skb);
if (!from->head_frag ||
skb_headlen(from) < L1_CACHE_BYTES ||
- skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS)
+ skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) {
hlen = skb_headlen(from);
+ if (!hlen)
+ hlen = from->len;
+ }
if (skb_has_frag_list(from))
hlen = from->len;
if (skb_linearize(skb))
return -EAGAIN;
num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len);
- if (unlikely(num_sge < 0)) {
- kfree(msg);
+ if (unlikely(num_sge < 0))
return num_sge;
- }
copied = skb->len;
msg->sg.start = 0;
{
struct sock *sk = psock->sk;
struct sk_msg *msg;
+ int err;
/* If we are receiving on the same sock skb->sk is already assigned,
* skip memory accounting and owner transition seeing it already set
* into user buffers.
*/
skb_set_owner_r(skb, sk);
- return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+ err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+ if (err < 0)
+ kfree(msg);
+ return err;
}
/* Puts an skb on the ingress queue of the socket already assigned to the
{
struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC);
struct sock *sk = psock->sk;
+ int err;
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);
+ err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+ if (err < 0)
+ kfree(msg);
+ return err;
}
static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
return sk_psock_skb_ingress(psock, skb);
}
-static void sock_drop(struct sock *sk, struct sk_buff *skb)
+static void sk_psock_skb_state(struct sk_psock *psock,
+ struct sk_psock_work_state *state,
+ struct sk_buff *skb,
+ int len, int off)
{
- sk_drops_add(sk, skb);
- kfree_skb(skb);
+ spin_lock_bh(&psock->ingress_lock);
+ if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
+ state->skb = skb;
+ state->len = len;
+ state->off = off;
+ } else {
+ sock_drop(psock->sk, skb);
+ }
+ spin_unlock_bh(&psock->ingress_lock);
}
static void sk_psock_backlog(struct work_struct *work)
{
struct sk_psock *psock = container_of(work, struct sk_psock, work);
struct sk_psock_work_state *state = &psock->work_state;
- struct sk_buff *skb;
+ struct sk_buff *skb = NULL;
bool ingress;
u32 len, off;
int ret;
mutex_lock(&psock->work_mutex);
- if (state->skb) {
+ if (unlikely(state->skb)) {
+ spin_lock_bh(&psock->ingress_lock);
skb = state->skb;
len = state->len;
off = state->off;
state->skb = NULL;
- goto start;
+ spin_unlock_bh(&psock->ingress_lock);
}
+ if (skb)
+ goto start;
while ((skb = skb_dequeue(&psock->ingress_skb))) {
len = skb->len;
len, ingress);
if (ret <= 0) {
if (ret == -EAGAIN) {
- state->skb = skb;
- state->len = len;
- state->off = off;
+ sk_psock_skb_state(psock, state, skb,
+ len, off);
goto end;
}
/* Hard errors break pipe and stop xmit. */
skb_bpf_redirect_clear(skb);
sock_drop(psock->sk, skb);
}
+ kfree_skb(psock->work_state.skb);
+ /* We null the skb here to ensure that calls to sk_psock_backlog
+ * do not pick up the free'd skb.
+ */
+ psock->work_state.skb = NULL;
__sk_psock_purge_ingress_msg(psock);
}
void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
{
- sk_psock_stop(psock, false);
-
write_lock_bh(&sk->sk_callback_lock);
sk_psock_restore_proto(sk, psock);
rcu_assign_sk_user_data(sk, NULL);
sk_psock_stop_verdict(sk, psock);
write_unlock_bh(&sk->sk_callback_lock);
+ sk_psock_stop(psock, false);
+
INIT_RCU_WORK(&psock->rwork, sk_psock_destroy);
queue_rcu_work(system_wq, &psock->rwork);
}
#include <net/tcp.h>
#include <net/busy_poll.h>
+#include <linux/ethtool.h>
+
static DEFINE_MUTEX(proto_list_mutex);
static LIST_HEAD(proto_list);
}
}
-int sock_set_timestamping(struct sock *sk, int optname, int val)
+static int sock_timestamping_bind_phc(struct sock *sk, int phc_index)
+{
+ struct net *net = sock_net(sk);
+ struct net_device *dev = NULL;
+ bool match = false;
+ int *vclock_index;
+ int i, num;
+
+ if (sk->sk_bound_dev_if)
+ dev = dev_get_by_index(net, sk->sk_bound_dev_if);
+
+ if (!dev) {
+ pr_err("%s: sock not bind to device\n", __func__);
+ return -EOPNOTSUPP;
+ }
+
+ num = ethtool_get_phc_vclocks(dev, &vclock_index);
+ for (i = 0; i < num; i++) {
+ if (*(vclock_index + i) == phc_index) {
+ match = true;
+ break;
+ }
+ }
+
+ if (num > 0)
+ kfree(vclock_index);
+
+ if (!match)
+ return -EINVAL;
+
+ sk->sk_bind_phc = phc_index;
+
+ return 0;
+}
+
+int sock_set_timestamping(struct sock *sk, int optname,
+ struct so_timestamping timestamping)
{
+ int val = timestamping.flags;
+ int ret;
+
if (val & ~SOF_TIMESTAMPING_MASK)
return -EINVAL;
!(val & SOF_TIMESTAMPING_OPT_TSONLY))
return -EINVAL;
+ if (val & SOF_TIMESTAMPING_BIND_PHC) {
+ ret = sock_timestamping_bind_phc(sk, timestamping.bind_phc);
+ if (ret)
+ return ret;
+ }
+
sk->sk_tsflags = val;
sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW);
int sock_setsockopt(struct socket *sock, int level, int optname,
sockptr_t optval, unsigned int optlen)
{
+ struct so_timestamping timestamping;
struct sock_txtime sk_txtime;
struct sock *sk = sock->sk;
int val;
case SO_TIMESTAMP_NEW:
case SO_TIMESTAMPNS_OLD:
case SO_TIMESTAMPNS_NEW:
- sock_set_timestamp(sk, valbool, optname);
+ sock_set_timestamp(sk, optname, valbool);
break;
case SO_TIMESTAMPING_NEW:
case SO_TIMESTAMPING_OLD:
- ret = sock_set_timestamping(sk, optname, val);
+ if (optlen == sizeof(timestamping)) {
+ if (copy_from_sockptr(×tamping, optval,
+ sizeof(timestamping))) {
+ ret = -EFAULT;
+ break;
+ }
+ } else {
+ memset(×tamping, 0, sizeof(timestamping));
+ timestamping.flags = val;
+ }
+ ret = sock_set_timestamping(sk, optname, timestamping);
break;
case SO_RCVLOWAT:
if (val < 0)
ret = -EINVAL;
else
- sk->sk_ll_usec = val;
+ WRITE_ONCE(sk->sk_ll_usec, val);
}
break;
case SO_PREFER_BUSY_POLL:
struct __kernel_old_timeval tm;
struct __kernel_sock_timeval stm;
struct sock_txtime txtime;
+ struct so_timestamping timestamping;
} v;
int lv = sizeof(int);
break;
case SO_TIMESTAMPING_OLD:
- v.val = sk->sk_tsflags;
+ lv = sizeof(v.timestamping);
+ v.timestamping.flags = sk->sk_tsflags;
+ v.timestamping.bind_phc = sk->sk_bind_phc;
break;
case SO_RCVTIMEO_OLD:
static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation)
{
struct dn_scp *scp = DN_SK(sk);
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
int err;
if (scp->state != DN_CR)
scp->segsize_loc = dst_metric_advmss(__sk_dst_get(sk));
dn_send_conn_conf(sk, allocation);
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ add_wait_queue(sk_sleep(sk), &wait);
for(;;) {
release_sock(sk);
if (scp->state == DN_CC)
- *timeo = schedule_timeout(*timeo);
+ *timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo);
lock_sock(sk);
err = 0;
if (scp->state == DN_RUN)
err = -EAGAIN;
if (!*timeo)
break;
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
if (err == 0) {
sk->sk_socket->state = SS_CONNECTED;
} else if (scp->state != DN_CC) {
static int dn_wait_run(struct sock *sk, long *timeo)
{
struct dn_scp *scp = DN_SK(sk);
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
int err = 0;
if (scp->state == DN_RUN)
if (!*timeo)
return -EALREADY;
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ add_wait_queue(sk_sleep(sk), &wait);
for(;;) {
release_sock(sk);
if (scp->state == DN_CI || scp->state == DN_CC)
- *timeo = schedule_timeout(*timeo);
+ *timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo);
lock_sock(sk);
err = 0;
if (scp->state == DN_RUN)
err = -ETIMEDOUT;
if (!*timeo)
break;
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
out:
if (err == 0) {
sk->sk_socket->state = SS_CONNECTED;
static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo)
{
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct sk_buff *skb = NULL;
int err = 0;
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ add_wait_queue(sk_sleep(sk), &wait);
for(;;) {
release_sock(sk);
skb = skb_dequeue(&sk->sk_receive_queue);
if (skb == NULL) {
- *timeo = schedule_timeout(*timeo);
+ *timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo);
skb = skb_dequeue(&sk->sk_receive_queue);
}
lock_sock(sk);
err = -EAGAIN;
if (!*timeo)
break;
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
return skb == NULL ? ERR_PTR(err) : skb;
}
struct dsa_slave_priv *p = netdev_priv(slave);
const struct dsa_port *cpu_dp = dp->cpu_dp;
struct net_device *master = cpu_dp->master;
+ const struct dsa_switch *ds = dp->ds;
slave->needed_headroom = cpu_dp->tag_ops->needed_headroom;
slave->needed_tailroom = cpu_dp->tag_ops->needed_tailroom;
slave->needed_tailroom += master->needed_tailroom;
p->xmit = cpu_dp->tag_ops->xmit;
+
+ slave->features = master->vlan_features | NETIF_F_HW_TC;
+ if (ds->ops->port_vlan_add && ds->ops->port_vlan_del)
+ slave->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+ slave->hw_features |= NETIF_F_HW_TC;
+ slave->features |= NETIF_F_LLTX;
+ if (slave->needed_tailroom)
+ slave->features &= ~(NETIF_F_SG | NETIF_F_FRAGLIST);
}
static struct lock_class_key dsa_slave_netdev_xmit_lock_key;
if (slave_dev == NULL)
return -ENOMEM;
- slave_dev->features = master->vlan_features | NETIF_F_HW_TC;
- if (ds->ops->port_vlan_add && ds->ops->port_vlan_del)
- slave_dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
- slave_dev->hw_features |= NETIF_F_HW_TC;
- slave_dev->features |= NETIF_F_LLTX;
slave_dev->ethtool_ops = &dsa_slave_ethtool_ops;
if (!is_zero_ether_addr(port->mac))
ether_addr_copy(slave_dev->dev_addr, port->mac);
int err, port;
if (dst->index == info->tree_index && ds->index == info->sw_index &&
- ds->ops->port_bridge_join)
+ ds->ops->port_bridge_leave)
ds->ops->port_bridge_leave(ds, info->port, info->br);
if ((dst->index != info->tree_index || ds->index != info->sw_index) &&
- ds->ops->crosschip_bridge_join)
+ ds->ops->crosschip_bridge_leave)
ds->ops->crosschip_bridge_leave(ds, info->tree_index,
info->sw_index, info->port,
info->br);
info->port, info->lag,
info->info);
- return 0;
+ return -EOPNOTSUPP;
}
static int dsa_switch_lag_leave(struct dsa_switch *ds,
return ds->ops->crosschip_lag_leave(ds, info->sw_index,
info->port, info->lag);
- return 0;
+ return -EOPNOTSUPP;
}
static int dsa_switch_mdb_add(struct dsa_switch *ds,
u8 *tag;
u8 *addr;
+ if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb))
+ return NULL;
+
/* Tag encoding */
tag = skb_put(skb, KSZ_INGRESS_TAG_LEN);
addr = skb_mac_header(skb);
u8 *addr;
u16 val;
+ if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb))
+ return NULL;
+
/* Tag encoding */
tag = skb_put(skb, KSZ9477_INGRESS_TAG_LEN);
addr = skb_mac_header(skb);
u8 *addr;
u8 *tag;
+ if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb))
+ return NULL;
+
/* Tag encoding */
tag = skb_put(skb, KSZ_INGRESS_TAG_LEN);
addr = skb_mac_header(skb);
ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o \
linkstate.o debug.o wol.o features.o privflags.o rings.o \
channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \
- tunnels.o fec.o eeprom.o stats.o
+ tunnels.o fec.o eeprom.o stats.o phc_vclocks.o
#include <linux/net_tstamp.h>
#include <linux/phy.h>
#include <linux/rtnetlink.h>
+#include <linux/ptp_clock_kernel.h>
#include "common.h"
[const_ilog2(SOF_TIMESTAMPING_OPT_STATS)] = "option-stats",
[const_ilog2(SOF_TIMESTAMPING_OPT_PKTINFO)] = "option-pktinfo",
[const_ilog2(SOF_TIMESTAMPING_OPT_TX_SWHW)] = "option-tx-swhw",
+ [const_ilog2(SOF_TIMESTAMPING_BIND_PHC)] = "bind-phc",
};
static_assert(ARRAY_SIZE(sof_timestamping_names) == __SOF_TIMESTAMPING_CNT);
return 0;
}
+int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index)
+{
+ struct ethtool_ts_info info = { };
+ int num = 0;
+
+ if (!__ethtool_get_ts_info(dev, &info))
+ num = ptp_get_vclocks_index(info.phc_index, vclock_index);
+
+ return num;
+}
+EXPORT_SYMBOL(ethtool_get_phc_vclocks);
+
const struct ethtool_phy_ops *ethtool_phy_ops;
void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops)
[ETHTOOL_MSG_TSINFO_GET] = ðnl_tsinfo_request_ops,
[ETHTOOL_MSG_MODULE_EEPROM_GET] = ðnl_module_eeprom_request_ops,
[ETHTOOL_MSG_STATS_GET] = ðnl_stats_request_ops,
+ [ETHTOOL_MSG_PHC_VCLOCKS_GET] = ðnl_phc_vclocks_request_ops,
};
static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb)
.policy = ethnl_stats_get_policy,
.maxattr = ARRAY_SIZE(ethnl_stats_get_policy) - 1,
},
+ {
+ .cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET,
+ .doit = ethnl_default_doit,
+ .start = ethnl_default_start,
+ .dumpit = ethnl_default_dumpit,
+ .done = ethnl_default_done,
+ .policy = ethnl_phc_vclocks_get_policy,
+ .maxattr = ARRAY_SIZE(ethnl_phc_vclocks_get_policy) - 1,
+ },
};
static const struct genl_multicast_group ethtool_nl_mcgrps[] = {
extern const struct ethnl_request_ops ethnl_fec_request_ops;
extern const struct ethnl_request_ops ethnl_module_eeprom_request_ops;
extern const struct ethnl_request_ops ethnl_stats_request_ops;
+extern const struct ethnl_request_ops ethnl_phc_vclocks_request_ops;
extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1];
extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1];
extern const struct nla_policy ethnl_fec_set_policy[ETHTOOL_A_FEC_AUTO + 1];
extern const struct nla_policy ethnl_module_eeprom_get_policy[ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS + 1];
extern const struct nla_policy ethnl_stats_get_policy[ETHTOOL_A_STATS_GROUPS + 1];
+extern const struct nla_policy ethnl_phc_vclocks_get_policy[ETHTOOL_A_PHC_VCLOCKS_HEADER + 1];
int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info);
int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2021 NXP
+ */
+#include "netlink.h"
+#include "common.h"
+
+struct phc_vclocks_req_info {
+ struct ethnl_req_info base;
+};
+
+struct phc_vclocks_reply_data {
+ struct ethnl_reply_data base;
+ int num;
+ int *index;
+};
+
+#define PHC_VCLOCKS_REPDATA(__reply_base) \
+ container_of(__reply_base, struct phc_vclocks_reply_data, base)
+
+const struct nla_policy ethnl_phc_vclocks_get_policy[] = {
+ [ETHTOOL_A_PHC_VCLOCKS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy),
+};
+
+static int phc_vclocks_prepare_data(const struct ethnl_req_info *req_base,
+ struct ethnl_reply_data *reply_base,
+ struct genl_info *info)
+{
+ struct phc_vclocks_reply_data *data = PHC_VCLOCKS_REPDATA(reply_base);
+ struct net_device *dev = reply_base->dev;
+ int ret;
+
+ ret = ethnl_ops_begin(dev);
+ if (ret < 0)
+ return ret;
+ data->num = ethtool_get_phc_vclocks(dev, &data->index);
+ ethnl_ops_complete(dev);
+
+ return ret;
+}
+
+static int phc_vclocks_reply_size(const struct ethnl_req_info *req_base,
+ const struct ethnl_reply_data *reply_base)
+{
+ const struct phc_vclocks_reply_data *data =
+ PHC_VCLOCKS_REPDATA(reply_base);
+ int len = 0;
+
+ if (data->num > 0) {
+ len += nla_total_size(sizeof(u32));
+ len += nla_total_size(sizeof(s32) * data->num);
+ }
+
+ return len;
+}
+
+static int phc_vclocks_fill_reply(struct sk_buff *skb,
+ const struct ethnl_req_info *req_base,
+ const struct ethnl_reply_data *reply_base)
+{
+ const struct phc_vclocks_reply_data *data =
+ PHC_VCLOCKS_REPDATA(reply_base);
+
+ if (data->num <= 0)
+ return 0;
+
+ if (nla_put_u32(skb, ETHTOOL_A_PHC_VCLOCKS_NUM, data->num) ||
+ nla_put(skb, ETHTOOL_A_PHC_VCLOCKS_INDEX,
+ sizeof(s32) * data->num, data->index))
+ return -EMSGSIZE;
+
+ return 0;
+}
+
+static void phc_vclocks_cleanup_data(struct ethnl_reply_data *reply_base)
+{
+ const struct phc_vclocks_reply_data *data =
+ PHC_VCLOCKS_REPDATA(reply_base);
+
+ kfree(data->index);
+}
+
+const struct ethnl_request_ops ethnl_phc_vclocks_request_ops = {
+ .request_cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET,
+ .reply_cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY,
+ .hdr_attr = ETHTOOL_A_PHC_VCLOCKS_HEADER,
+ .req_info_size = sizeof(struct phc_vclocks_req_info),
+ .reply_data_size = sizeof(struct phc_vclocks_reply_data),
+
+ .prepare_data = phc_vclocks_prepare_data,
+ .reply_size = phc_vclocks_reply_size,
+ .fill_reply = phc_vclocks_fill_reply,
+ .cleanup_data = phc_vclocks_cleanup_data,
+};
portid = NETLINK_CB(skb).portid; /* netlink portid */
NETLINK_CB(skb).portid = 0; /* from kernel */
NETLINK_CB(skb).dst_group = 0; /* unicast */
- netlink_unicast(net->ipv4.fibnl, skb, portid, MSG_DONTWAIT);
+ nlmsg_unicast(net->ipv4.fibnl, skb, portid);
}
static int __net_init nl_fib_lookup_init(struct net *net)
nlmsg_free(rep);
goto out;
}
- err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid,
- MSG_DONTWAIT);
- if (err > 0)
- err = 0;
+ err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid);
out:
if (sk)
}
dev->needed_headroom = t_hlen + hlen;
- mtu -= t_hlen;
+ mtu -= t_hlen + (dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0);
if (mtu < IPV4_MIN_MTU)
mtu = IPV4_MIN_MTU;
t_hlen = nt->hlen + sizeof(struct iphdr);
dev->min_mtu = ETH_MIN_MTU;
dev->max_mtu = IP_MAX_MTU - t_hlen;
+ if (dev->type == ARPHRD_ETHER)
+ dev->max_mtu -= dev->hard_header_len;
+
ip_tunnel_add(itn, nt);
return nt;
tunnel->i_seqno = ntohl(tpi->seq) + 1;
}
- skb_reset_network_header(skb);
+ skb_set_network_header(skb, (tunnel->dev->type == ARPHRD_ETHER) ? ETH_HLEN : 0);
err = IP_ECN_decapsulate(iph, skb);
if (unlikely(err)) {
tunnel_hlen = md ? tunnel_hlen : tunnel->hlen;
pkt_size = skb->len - tunnel_hlen;
+ pkt_size -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0;
- if (df)
+ if (df) {
mtu = dst_mtu(&rt->dst) - (sizeof(struct iphdr) + tunnel_hlen);
- else
+ mtu -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0;
+ } else {
mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
+ }
if (skb_valid_dst(skb))
skb_dst_update_pmtu_no_confirm(skb, mtu);
int t_hlen = tunnel->hlen + sizeof(struct iphdr);
int max_mtu = IP_MAX_MTU - t_hlen;
+ if (dev->type == ARPHRD_ETHER)
+ max_mtu -= dev->hard_header_len;
+
if (new_mtu < ETH_MIN_MTU)
return -EINVAL;
if (tb[IFLA_MTU]) {
unsigned int max = IP_MAX_MTU - (nt->hlen + sizeof(struct iphdr));
+ if (dev->type == ARPHRD_ETHER)
+ max -= dev->hard_header_len;
+
mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU, max);
}
raw_rcv(mroute_sk, skb);
return 0;
}
- }
+ }
}
/* already under rcu_read_lock() */
return err;
}
- err = netlink_unicast(net->diag_nlsk, rep,
- NETLINK_CB(in_skb).portid,
- MSG_DONTWAIT);
- if (err > 0)
- err = 0;
+ err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid);
+
return err;
}
}
pfrag->offset += copy;
} else {
+ if (!sk_wmem_schedule(sk, copy))
+ goto wait_for_space;
+
err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg);
if (err == -EMSGSIZE || err == -EEXIST) {
tcp_mark_push(tp, skb);
tcp_bpf_rebuild_protos(tcp_bpf_prots[TCP_BPF_IPV4], &tcp_prot);
return 0;
}
-core_initcall(tcp_bpf_v4_build_proto);
+late_initcall(tcp_bpf_v4_build_proto);
static int tcp_bpf_assert_proto_ops(struct proto *ops)
{
{
struct net *net = sock_net(sk);
+ if (!sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout)
+ return;
+
+ /* Paired with READ_ONCE() in tcp_fastopen_active_should_disable() */
+ WRITE_ONCE(net->ipv4.tfo_active_disable_stamp, jiffies);
+
+ /* Paired with smp_rmb() in tcp_fastopen_active_should_disable().
+ * We want net->ipv4.tfo_active_disable_stamp to be updated first.
+ */
+ smp_mb__before_atomic();
atomic_inc(&net->ipv4.tfo_active_disable_times);
- net->ipv4.tfo_active_disable_stamp = jiffies;
+
NET_INC_STATS(net, LINUX_MIB_TCPFASTOPENBLACKHOLE);
}
bool tcp_fastopen_active_should_disable(struct sock *sk)
{
unsigned int tfo_bh_timeout = sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout;
- int tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times);
unsigned long timeout;
+ int tfo_da_times;
int multiplier;
+ if (!tfo_bh_timeout)
+ return false;
+
+ tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times);
if (!tfo_da_times)
return false;
+ /* Paired with smp_mb__before_atomic() in tcp_fastopen_active_disable() */
+ smp_rmb();
+
/* Limit timeout to max: 2^6 * initial timeout */
multiplier = 1 << min(tfo_da_times - 1, 6);
- timeout = multiplier * tfo_bh_timeout * HZ;
- if (time_before(jiffies, sock_net(sk)->ipv4.tfo_active_disable_stamp + timeout))
+
+ /* Paired with the WRITE_ONCE() in tcp_fastopen_active_disable(). */
+ timeout = READ_ONCE(sock_net(sk)->ipv4.tfo_active_disable_stamp) +
+ multiplier * tfo_bh_timeout * HZ;
+ if (time_before(jiffies, timeout))
return true;
/* Mark check bit so we can check for successful active TFO
{
trace_tcp_receive_reset(sk);
+ /* mptcp can't tell us to ignore reset pkts,
+ * so just ignore the return value of mptcp_incoming_options().
+ */
if (sk_is_mptcp(sk))
mptcp_incoming_options(sk, skb);
bool fragstolen;
int eaten;
- if (sk_is_mptcp(sk))
- mptcp_incoming_options(sk, skb);
+ /* If a subflow has been reset, the packet should not continue
+ * to be processed, drop the packet.
+ */
+ if (sk_is_mptcp(sk) && !mptcp_incoming_options(sk, skb)) {
+ __kfree_skb(skb);
+ return;
+ }
if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) {
__kfree_skb(skb);
tp->snd_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk));
tp->snd_cwnd_stamp = tcp_jiffies32;
- icsk->icsk_ca_initialized = 0;
bpf_skops_established(sk, bpf_op, skb);
+ /* Initialize congestion control unless BPF initialized it already: */
if (!icsk->icsk_ca_initialized)
tcp_init_congestion_control(sk);
tcp_init_buffer_space(sk);
case TCP_CLOSING:
case TCP_LAST_ACK:
if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
- if (sk_is_mptcp(sk))
- mptcp_incoming_options(sk, skb);
+ /* If a subflow has been reset, the packet should not
+ * continue to be processed, drop the packet.
+ */
+ if (sk_is_mptcp(sk) && !mptcp_incoming_options(sk, skb))
+ goto discard;
break;
}
fallthrough;
if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
return;
- mtu = tcp_sk(sk)->mtu_info;
+ mtu = READ_ONCE(tcp_sk(sk)->mtu_info);
dst = inet_csk_update_pmtu(sk, mtu);
if (!dst)
return;
if (sk->sk_state == TCP_LISTEN)
goto out;
- tp->mtu_info = info;
+ WRITE_ONCE(tp->mtu_info, info);
if (!sock_owned_by_user(sk)) {
tcp_v4_mtu_reduced(sk);
} else {
net->ipv4.sysctl_tcp_comp_sack_nr = 44;
net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE;
spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock);
- net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 60 * 60;
+ net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 0;
atomic_set(&net->ipv4.tfo_active_disable_times, 0);
/* Reno is always built in */
if (th->cwr)
skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
+ if (skb->encapsulation)
+ skb->inner_transport_header = skb->transport_header;
+
return 0;
}
EXPORT_SYMBOL(tcp_gro_complete);
return __tcp_mtu_to_mss(sk, pmtu) -
(tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr));
}
+EXPORT_SYMBOL(tcp_mtu_to_mss);
/* Inverse of above */
int tcp_mss_to_mtu(struct sock *sk, int mss)
const struct iphdr *iph,
struct udphdr *uh,
struct udp_table *udptable,
+ struct sock *sk,
struct sk_buff *skb, u32 info)
{
+ int (*lookup)(struct sock *sk, struct sk_buff *skb);
int network_offset, transport_offset;
- struct sock *sk;
+ struct udp_sock *up;
network_offset = skb_network_offset(skb);
transport_offset = skb_transport_offset(skb);
/* Transport header needs to point to the UDP header */
skb_set_transport_header(skb, iph->ihl << 2);
+ if (sk) {
+ up = udp_sk(sk);
+
+ lookup = READ_ONCE(up->encap_err_lookup);
+ if (lookup && lookup(sk, skb))
+ sk = NULL;
+
+ goto out;
+ }
+
sk = __udp4_lib_lookup(net, iph->daddr, uh->source,
iph->saddr, uh->dest, skb->dev->ifindex, 0,
udptable, NULL);
if (sk) {
- int (*lookup)(struct sock *sk, struct sk_buff *skb);
- struct udp_sock *up = udp_sk(sk);
+ up = udp_sk(sk);
lookup = READ_ONCE(up->encap_err_lookup);
if (!lookup || lookup(sk, skb))
sk = NULL;
}
+out:
if (!sk)
sk = ERR_PTR(__udp4_lib_err_encap_no_sk(skb, info));
sk = __udp4_lib_lookup(net, iph->daddr, uh->dest,
iph->saddr, uh->source, skb->dev->ifindex,
inet_sdif(skb), udptable, NULL);
+
if (!sk || udp_sk(sk)->encap_type) {
/* No socket for error: try tunnels before discarding */
- sk = ERR_PTR(-ENOENT);
if (static_branch_unlikely(&udp_encap_needed_key)) {
- sk = __udp4_lib_err_encap(net, iph, uh, udptable, skb,
+ sk = __udp4_lib_err_encap(net, iph, uh, udptable, sk, skb,
info);
if (!sk)
return 0;
- }
+ } else
+ sk = ERR_PTR(-ENOENT);
if (IS_ERR(sk)) {
__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
}
ipcm_init_sk(&ipc, inet);
- ipc.gso_size = up->gso_size;
+ ipc.gso_size = READ_ONCE(up->gso_size);
if (msg->msg_controllen) {
err = udp_cmsg_send(sk, msg, &ipc.gso_size);
case UDP_SEGMENT:
if (val < 0 || val > USHRT_MAX)
return -EINVAL;
- up->gso_size = val;
+ WRITE_ONCE(up->gso_size, val);
break;
case UDP_GRO:
break;
case UDP_SEGMENT:
- val = up->gso_size;
+ val = READ_ONCE(up->gso_size);
break;
case UDP_GRO:
udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV4], &udp_prot);
return 0;
}
-core_initcall(udp_bpf_v4_build_proto);
+late_initcall(udp_bpf_v4_build_proto);
int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
{
kfree_skb(rep);
goto out;
}
- err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid,
- MSG_DONTWAIT);
- if (err > 0)
- err = 0;
+ err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid);
+
out:
if (sk)
sock_put(sk);
if ((!sk && (skb->dev->features & NETIF_F_GRO_UDP_FWD)) ||
(sk && udp_sk(sk)->gro_enabled) || NAPI_GRO_CB(skb)->is_flist)
- pp = call_gro_receive(udp_gro_receive_segment, head, skb);
- return pp;
+ return call_gro_receive(udp_gro_receive_segment, head, skb);
+
+ /* no GRO, be sure flush the current packet */
+ goto out;
}
if (NAPI_GRO_CB(skb)->encap_mark ||
skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_L4;
+
+ if (skb->encapsulation)
+ skb->inner_transport_header = skb->transport_header;
+
return 0;
}
{
struct dst_entry *dst = skb_dst(skb);
struct net_device *dev = dst->dev;
+ unsigned int hh_len = LL_RESERVED_SPACE(dev);
+ int delta = hh_len - skb_headroom(skb);
const struct in6_addr *nexthop;
struct neighbour *neigh;
int ret;
+ /* Be paranoid, rather than too clever. */
+ if (unlikely(delta > 0) && dev->header_ops) {
+ /* pskb_expand_head() might crash, if skb is shared */
+ if (skb_shared(skb)) {
+ struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
+
+ if (likely(nskb)) {
+ if (skb->sk)
+ skb_set_owner_w(nskb, skb->sk);
+ consume_skb(skb);
+ } else {
+ kfree_skb(skb);
+ }
+ skb = nskb;
+ }
+ if (skb &&
+ pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) {
+ kfree_skb(skb);
+ skb = NULL;
+ }
+ if (!skb) {
+ IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS);
+ return -ENOMEM;
+ }
+ }
+
if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) {
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
if (skb_warn_if_lro(skb))
goto drop;
- if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
+ if (!net->ipv6.devconf_all->disable_policy &&
+ !idev->cnf.disable_policy &&
+ !xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
goto drop;
}
if (net->ipv6.devconf_all->proxy_ndp &&
pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) {
int proxied = ip6_forward_proxy_check(skb);
- if (proxied > 0)
+ if (proxied > 0) {
+ hdr->hop_limit--;
return ip6_input(skb);
- else if (proxied < 0) {
+ } else if (proxied < 0) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
goto drop;
}
err = PTR_ERR(rt->fib6_metrics);
/* Do not leave garbage there. */
rt->fib6_metrics = (struct dst_metrics *)&dst_default_metrics;
- goto out;
+ goto out_free;
}
if (cfg->fc_flags & RTF_ADDRCONF)
static void tcp_v6_mtu_reduced(struct sock *sk)
{
struct dst_entry *dst;
+ u32 mtu;
if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
return;
- dst = inet6_csk_update_pmtu(sk, tcp_sk(sk)->mtu_info);
+ mtu = READ_ONCE(tcp_sk(sk)->mtu_info);
+
+ /* Drop requests trying to increase our current mss.
+ * Check done in __ip6_rt_update_pmtu() is too late.
+ */
+ if (tcp_mtu_to_mss(sk, mtu) >= tcp_sk(sk)->mss_cache)
+ return;
+
+ dst = inet6_csk_update_pmtu(sk, mtu);
if (!dst)
return;
}
if (type == ICMPV6_PKT_TOOBIG) {
+ u32 mtu = ntohl(info);
+
/* We are not interested in TCP_LISTEN and open_requests
* (SYN-ACKs send out by Linux are always <576bytes so
* they should go through unfragmented).
if (!ip6_sk_accept_pmtu(sk))
goto out;
- tp->mtu_info = ntohl(info);
+ if (mtu < IPV6_MIN_MTU)
+ goto out;
+
+ WRITE_ONCE(tp->mtu_info, mtu);
+
if (!sock_owned_by_user(sk))
tcp_v6_mtu_reduced(sk);
else if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED,
opt = ireq->ipv6_opt;
if (!opt)
opt = rcu_dereference(np->opt);
- err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt,
+ err = ip6_xmit(sk, skb, fl6, skb->mark ? : sk->sk_mark, opt,
tclass, sk->sk_priority);
rcu_read_unlock();
err = net_xmit_eval(err);
const struct ipv6hdr *hdr, int offset,
struct udphdr *uh,
struct udp_table *udptable,
+ struct sock *sk,
struct sk_buff *skb,
struct inet6_skb_parm *opt,
u8 type, u8 code, __be32 info)
{
+ int (*lookup)(struct sock *sk, struct sk_buff *skb);
int network_offset, transport_offset;
- struct sock *sk;
+ struct udp_sock *up;
network_offset = skb_network_offset(skb);
transport_offset = skb_transport_offset(skb);
/* Transport header needs to point to the UDP header */
skb_set_transport_header(skb, offset);
+ if (sk) {
+ up = udp_sk(sk);
+
+ lookup = READ_ONCE(up->encap_err_lookup);
+ if (lookup && lookup(sk, skb))
+ sk = NULL;
+
+ goto out;
+ }
+
sk = __udp6_lib_lookup(net, &hdr->daddr, uh->source,
&hdr->saddr, uh->dest,
inet6_iif(skb), 0, udptable, skb);
if (sk) {
- int (*lookup)(struct sock *sk, struct sk_buff *skb);
- struct udp_sock *up = udp_sk(sk);
+ up = udp_sk(sk);
lookup = READ_ONCE(up->encap_err_lookup);
if (!lookup || lookup(sk, skb))
sk = NULL;
}
+out:
if (!sk) {
sk = ERR_PTR(__udp6_lib_err_encap_no_sk(skb, opt, type, code,
offset, info));
sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source,
inet6_iif(skb), inet6_sdif(skb), udptable, NULL);
+
if (!sk || udp_sk(sk)->encap_type) {
/* No socket for error: try tunnels before discarding */
- sk = ERR_PTR(-ENOENT);
if (static_branch_unlikely(&udpv6_encap_needed_key)) {
sk = __udp6_lib_err_encap(net, hdr, offset, uh,
- udptable, skb,
+ udptable, sk, skb,
opt, type, code, info);
if (!sk)
return 0;
- }
+ } else
+ sk = ERR_PTR(-ENOENT);
if (IS_ERR(sk)) {
__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
ipcm6_init(&ipc6);
- ipc6.gso_size = up->gso_size;
+ ipc6.gso_size = READ_ONCE(up->gso_size);
ipc6.sockc.tsflags = sk->sk_tsflags;
ipc6.sockc.mark = sk->sk_mark;
{
struct dst_entry *dst = skb_dst(skb);
struct xfrm_state *x = dst->xfrm;
- int mtu;
+ unsigned int mtu;
bool toobig;
#ifdef CONFIG_NETFILTER
u8 iptype;
u32 ipmsgid;
u32 iptrgcls;
- union {
- u32 iprmmsg1_u32;
- u8 iprmmsg1[4];
- } ln1msg1;
- union {
- u32 ipbfln1f;
- u8 iprmmsg2[4];
- } ln1msg2;
+ struct {
+ union {
+ u32 iprmmsg1_u32;
+ u8 iprmmsg1[4];
+ } ln1msg1;
+ union {
+ u32 ipbfln1f;
+ u8 iprmmsg2[4];
+ } ln1msg2;
+ } rmmsg;
u32 res1[3];
u32 ipbfln2f;
u8 ippollfg;
msg.id = imp->ipmsgid;
msg.class = imp->iptrgcls;
if (imp->ipflags1 & IUCV_IPRMDATA) {
- memcpy(msg.rmmsg, imp->ln1msg1.iprmmsg1, 8);
+ memcpy(msg.rmmsg, &imp->rmmsg, 8);
msg.length = 8;
} else
- msg.length = imp->ln1msg2.ipbfln1f;
+ msg.length = imp->rmmsg.ln1msg2.ipbfln1f;
msg.reply_size = imp->ipbfln2f;
path->handler->message_pending(path, &msg);
}
{
u8 rc = LLC_PDU_LEN_U;
- if (addr->sllc_test || addr->sllc_xid)
+ if (addr->sllc_test)
rc = LLC_PDU_LEN_U;
+ else if (addr->sllc_xid)
+ /* We need to expand header to sizeof(struct llc_xid_info)
+ * since llc_pdu_init_as_xid_cmd() sets 4,5,6 bytes of LLC header
+ * as XID PDU. In llc_ui_sendmsg() we reserved header size and then
+ * filled all other space with user data. If we won't reserve this
+ * bytes, llc_pdu_init_as_xid_cmd() will overwrite user data
+ */
+ rc = LLC_PDU_LEN_U_XID;
else if (sk->sk_type == SOCK_STREAM)
rc = LLC_PDU_LEN_I;
return rc;
struct llc_sap_state_ev *ev = llc_sap_ev(skb);
int rc;
- llc_pdu_header_init(skb, LLC_PDU_TYPE_U, ev->saddr.lsap,
+ llc_pdu_header_init(skb, LLC_PDU_TYPE_U_XID, ev->saddr.lsap,
ev->daddr.lsap, LLC_PDU_CMD);
llc_pdu_init_as_xid_cmd(skb, LLC_XID_NULL_CLASS_2, 0);
rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac);
struct vif_params *params)
{
struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+ struct ieee80211_local *local = sdata->local;
+ struct sta_info *sta;
int ret;
ret = ieee80211_if_change_type(sdata, type);
RCU_INIT_POINTER(sdata->u.vlan.sta, NULL);
ieee80211_check_fast_rx_iface(sdata);
} else if (type == NL80211_IFTYPE_STATION && params->use_4addr >= 0) {
+ struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+
+ if (params->use_4addr == ifmgd->use_4addr)
+ return 0;
+
sdata->u.mgd.use_4addr = params->use_4addr;
+ if (!ifmgd->associated)
+ return 0;
+
+ mutex_lock(&local->sta_mtx);
+ sta = sta_info_get(sdata, ifmgd->bssid);
+ if (sta)
+ drv_sta_set_4addr(local, sdata, &sta->sta,
+ params->use_4addr);
+ mutex_unlock(&local->sta_mtx);
+
+ if (params->use_4addr)
+ ieee80211_send_4addr_nullfunc(local, sdata);
}
if (sdata->vif.type == NL80211_IFTYPE_MONITOR) {
void ieee80211_send_nullfunc(struct ieee80211_local *local,
struct ieee80211_sub_if_data *sdata,
bool powersave);
+void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata);
void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata,
struct ieee80211_hdr *hdr, bool ack, u16 tx_time);
ieee80211_tx_skb(sdata, skb);
}
-static void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local,
- struct ieee80211_sub_if_data *sdata)
+void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata)
{
struct sk_buff *skb;
struct ieee80211_hdr *nullfunc;
* Need to make a copy and possibly remove radiotap header
* and FCS from the original.
*/
- skb = skb_copy_expand(*origskb, needed_headroom, 0, GFP_ATOMIC);
+ skb = skb_copy_expand(*origskb, needed_headroom + NET_SKB_PAD,
+ 0, GFP_ATOMIC);
if (!skb)
return NULL;
return queued;
}
+static void
+ieee80211_aggr_check(struct ieee80211_sub_if_data *sdata,
+ struct sta_info *sta,
+ struct sk_buff *skb)
+{
+ struct rate_control_ref *ref = sdata->local->rate_ctrl;
+ u16 tid;
+
+ if (!ref || !(ref->ops->capa & RATE_CTRL_CAPA_AMPDU_TRIGGER))
+ return;
+
+ if (!sta || !sta->sta.ht_cap.ht_supported ||
+ !sta->sta.wme || skb_get_queue_mapping(skb) == IEEE80211_AC_VO ||
+ skb->protocol == sdata->control_port_protocol)
+ return;
+
+ tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;
+ if (likely(sta->ampdu_mlme.tid_tx[tid]))
+ return;
+
+ ieee80211_start_tx_ba_session(&sta->sta, tid, 0);
+}
+
/*
* initialises @tx
* pass %NULL for the station if unknown, a valid pointer if known
struct ieee80211_local *local = sdata->local;
struct ieee80211_hdr *hdr;
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+ bool aggr_check = false;
int tid;
memset(tx, 0, sizeof(*tx));
} else if (tx->sdata->control_port_protocol == tx->skb->protocol) {
tx->sta = sta_info_get_bss(sdata, hdr->addr1);
}
- if (!tx->sta && !is_multicast_ether_addr(hdr->addr1))
+ if (!tx->sta && !is_multicast_ether_addr(hdr->addr1)) {
tx->sta = sta_info_get(sdata, hdr->addr1);
+ aggr_check = true;
+ }
}
if (tx->sta && ieee80211_is_data_qos(hdr->frame_control) &&
struct tid_ampdu_tx *tid_tx;
tid = ieee80211_get_tid(hdr);
-
tid_tx = rcu_dereference(tx->sta->ampdu_mlme.tid_tx[tid]);
+ if (!tid_tx && aggr_check) {
+ ieee80211_aggr_check(sdata, tx->sta, skb);
+ tid_tx = rcu_dereference(tx->sta->ampdu_mlme.tid_tx[tid]);
+ }
+
if (tid_tx) {
bool queued;
}
EXPORT_SYMBOL(ieee80211_txq_schedule_start);
-static void
-ieee80211_aggr_check(struct ieee80211_sub_if_data *sdata,
- struct sta_info *sta,
- struct sk_buff *skb)
-{
- struct rate_control_ref *ref = sdata->local->rate_ctrl;
- u16 tid;
-
- if (!ref || !(ref->ops->capa & RATE_CTRL_CAPA_AMPDU_TRIGGER))
- return;
-
- if (!sta || !sta->sta.ht_cap.ht_supported ||
- !sta->sta.wme || skb_get_queue_mapping(skb) == IEEE80211_AC_VO ||
- skb->protocol == sdata->control_port_protocol)
- return;
-
- tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;
- if (likely(sta->ampdu_mlme.tid_tx[tid]))
- return;
-
- ieee80211_start_tx_ba_session(&sta->sta, tid, 0);
-}
-
void __ieee80211_subif_start_xmit(struct sk_buff *skb,
struct net_device *dev,
u32 info_flags,
SNMP_MIB_ITEM("RmSubflow", MPTCP_MIB_RMSUBFLOW),
SNMP_MIB_ITEM("MPPrioTx", MPTCP_MIB_MPPRIOTX),
SNMP_MIB_ITEM("MPPrioRx", MPTCP_MIB_MPPRIORX),
+ SNMP_MIB_ITEM("RcvPruned", MPTCP_MIB_RCVPRUNED),
SNMP_MIB_SENTINEL
};
MPTCP_MIB_RMSUBFLOW, /* Remove a subflow */
MPTCP_MIB_MPPRIOTX, /* Transmit a MP_PRIO */
MPTCP_MIB_MPPRIORX, /* Received a MP_PRIO */
+ MPTCP_MIB_RCVPRUNED, /* Incoming packet dropped due to memory limit */
__MPTCP_MIB_MAX
};
kfree_skb(rep);
goto out;
}
- err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid,
- MSG_DONTWAIT);
- if (err > 0)
- err = 0;
+ err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid);
+
out:
sock_put(sk);
return hmac == mp_opt->ahmac;
}
-void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
+/* Return false if a subflow has been reset, else return true */
+bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
__mptcp_check_push(subflow->conn, sk);
__mptcp_data_acked(subflow->conn);
mptcp_data_unlock(subflow->conn);
- return;
+ return true;
}
mptcp_get_options(sk, skb, &mp_opt);
+
+ /* The subflow can be in close state only if check_fully_established()
+ * just sent a reset. If so, tell the caller to ignore the current packet.
+ */
if (!check_fully_established(msk, sk, subflow, skb, &mp_opt))
- return;
+ return sk->sk_state != TCP_CLOSE;
if (mp_opt.fastclose &&
msk->local_key == mp_opt.rcvr_key) {
}
if (!mp_opt.dss)
- return;
+ return true;
/* we can't wait for recvmsg() to update the ack_seq, otherwise
* monodirectional flows will stuck
schedule_work(&msk->work))
sock_hold(subflow->conn);
- return;
+ return true;
}
mpext = skb_ext_add(skb, SKB_EXT_MPTCP);
if (!mpext)
- return;
+ return true;
memset(mpext, 0, sizeof(*mpext));
if (mpext->csum_reqd)
mpext->csum = mp_opt.csum;
}
+
+ return true;
}
static void mptcp_set_rwin(const struct tcp_sock *tp)
struct mptcp_addr_info addr;
u8 flags;
int ifindex;
- struct rcu_head rcu;
struct socket *lsk;
};
bool cleanup, rx_empty;
cleanup = (space > 0) && (space >= (old_space << 1));
- rx_empty = !atomic_read(&sk->sk_rmem_alloc);
+ rx_empty = !__mptcp_rmem(sk);
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
sk_rbuf = ssk_rbuf;
/* over limit? can't append more skbs to msk, Also, no need to wake-up*/
- if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf)
+ if (__mptcp_rmem(sk) > sk_rbuf) {
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
return;
+ }
/* Wake-up the reader only for in-sequence data */
mptcp_data_lock(sk);
if (!(flags & MSG_PEEK)) {
/* we will bulk release the skb memory later */
skb->destructor = NULL;
- msk->rmem_released += skb->truesize;
+ WRITE_ONCE(msk->rmem_released, msk->rmem_released + skb->truesize);
__skb_unlink(skb, &msk->receive_queue);
__kfree_skb(skb);
}
atomic_sub(msk->rmem_released, &sk->sk_rmem_alloc);
sk_mem_uncharge(sk, msk->rmem_released);
- msk->rmem_released = 0;
+ WRITE_ONCE(msk->rmem_released, 0);
}
static void __mptcp_splice_receive_queue(struct sock *sk)
msk->out_of_order_queue = RB_ROOT;
msk->first_pending = NULL;
msk->wmem_reserved = 0;
- msk->rmem_released = 0;
+ WRITE_ONCE(msk->rmem_released, 0);
msk->tx_pending_data = 0;
msk->first = NULL;
return (struct mptcp_sock *)sk;
}
+/* the msk socket don't use the backlog, also account for the bulk
+ * free memory
+ */
+static inline int __mptcp_rmem(const struct sock *sk)
+{
+ return atomic_read(&sk->sk_rmem_alloc) - READ_ONCE(mptcp_sk(sk)->rmem_released);
+}
+
static inline int __mptcp_space(const struct sock *sk)
{
- return tcp_space(sk) + READ_ONCE(mptcp_sk(sk)->rmem_released);
+ return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - __mptcp_rmem(sk));
}
static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk)
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
bool slow = lock_sock_fast(ssk);
- switch (optname) {
- case SO_TIMESTAMP_OLD:
- case SO_TIMESTAMP_NEW:
- case SO_TIMESTAMPNS_OLD:
- case SO_TIMESTAMPNS_NEW:
- sock_set_timestamp(sk, optname, !!val);
- break;
- case SO_TIMESTAMPING_NEW:
- case SO_TIMESTAMPING_OLD:
- sock_set_timestamping(sk, optname, val);
- break;
- }
-
+ sock_set_timestamp(sk, optname, !!val);
unlock_sock_fast(ssk, slow);
}
}
static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname,
- sockptr_t optval, unsigned int optlen)
+ sockptr_t optval,
+ unsigned int optlen)
{
int val, ret;
case SO_TIMESTAMP_NEW:
case SO_TIMESTAMPNS_OLD:
case SO_TIMESTAMPNS_NEW:
- case SO_TIMESTAMPING_OLD:
- case SO_TIMESTAMPING_NEW:
return mptcp_setsockopt_sol_socket_tstamp(msk, optname, val);
}
return -ENOPROTOOPT;
}
+static int mptcp_setsockopt_sol_socket_timestamping(struct mptcp_sock *msk,
+ int optname,
+ sockptr_t optval,
+ unsigned int optlen)
+{
+ struct mptcp_subflow_context *subflow;
+ struct sock *sk = (struct sock *)msk;
+ struct so_timestamping timestamping;
+ int ret;
+
+ if (optlen == sizeof(timestamping)) {
+ if (copy_from_sockptr(×tamping, optval,
+ sizeof(timestamping)))
+ return -EFAULT;
+ } else if (optlen == sizeof(int)) {
+ memset(×tamping, 0, sizeof(timestamping));
+
+ if (copy_from_sockptr(×tamping.flags, optval, sizeof(int)))
+ return -EFAULT;
+ } else {
+ return -EINVAL;
+ }
+
+ ret = sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname,
+ KERNEL_SOCKPTR(×tamping),
+ sizeof(timestamping));
+ if (ret)
+ return ret;
+
+ lock_sock(sk);
+
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ bool slow = lock_sock_fast(ssk);
+
+ sock_set_timestamping(sk, optname, timestamping);
+ unlock_sock_fast(ssk, slow);
+ }
+
+ release_sock(sk);
+
+ return 0;
+}
+
static int mptcp_setsockopt_sol_socket_linger(struct mptcp_sock *msk, sockptr_t optval,
unsigned int optlen)
{
case SO_TIMESTAMP_NEW:
case SO_TIMESTAMPNS_OLD:
case SO_TIMESTAMPNS_NEW:
+ return mptcp_setsockopt_sol_socket_int(msk, optname, optval,
+ optlen);
case SO_TIMESTAMPING_OLD:
case SO_TIMESTAMPING_NEW:
- return mptcp_setsockopt_sol_socket_int(msk, optname, optval, optlen);
+ return mptcp_setsockopt_sol_socket_timestamping(msk, optname,
+ optval, optlen);
case SO_LINGER:
return mptcp_setsockopt_sol_socket_linger(msk, optval, optlen);
case SO_RCVLOWAT:
ntohs(inet_sk(sk_listener)->inet_sport),
ntohs(inet_sk((struct sock *)subflow_req->msk)->inet_sport));
if (!mptcp_pm_sport_in_anno_list(subflow_req->msk, sk_listener)) {
- sock_put((struct sock *)subflow_req->msk);
- mptcp_token_destroy_request(req);
- tcp_request_sock_ops.destructor(req);
- subflow_req->msk = NULL;
- subflow_req->mp_join = 0;
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTSYNRX);
return -EPERM;
}
if (unlikely(req->syncookie)) {
if (mptcp_can_accept_new_subflow(subflow_req->msk))
subflow_init_req_cookie_join_save(subflow_req, skb);
+ else
+ return -EPERM;
}
pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token,
if (!mptcp_token_join_cookie_init_state(subflow_req, skb))
return -EINVAL;
- if (mptcp_can_accept_new_subflow(subflow_req->msk))
- subflow_req->mp_join = 1;
-
+ subflow_req->mp_join = 1;
subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq - 1;
}
static u32 mptcp_join_entry_hash(struct sk_buff *skb, struct net *net)
{
- u32 i = skb_get_hash(skb) ^ net_hash_mix(net);
+ static u32 mptcp_join_hash_secret __read_mostly;
+ struct tcphdr *th = tcp_hdr(skb);
+ u32 seq, i;
+
+ net_get_random_once(&mptcp_join_hash_secret,
+ sizeof(mptcp_join_hash_secret));
+
+ if (th->syn)
+ seq = TCP_SKB_CB(skb)->seq;
+ else
+ seq = TCP_SKB_CB(skb)->seq - 1;
+
+ i = jhash_3words(seq, net_hash_mix(net),
+ (__force __u32)th->source << 16 | (__force __u32)th->dest,
+ mptcp_join_hash_secret);
return i % ARRAY_SIZE(join_entries);
}
help
This allows to get MAC address from NCSI firmware and set them back to
controller.
+config NCSI_OEM_CMD_KEEP_PHY
+ bool "Keep PHY Link up"
+ depends on NET_NCSI
+ help
+ This allows to keep PHY link up and prevents any channel resets during
+ the host load.
/* OEM Vendor Manufacture ID */
#define NCSI_OEM_MFR_MLX_ID 0x8119
#define NCSI_OEM_MFR_BCM_ID 0x113d
+#define NCSI_OEM_MFR_INTEL_ID 0x157
+/* Intel specific OEM command */
+#define NCSI_OEM_INTEL_CMD_KEEP_PHY 0x20 /* CMD ID for Keep PHY up */
/* Broadcom specific OEM Command */
#define NCSI_OEM_BCM_CMD_GMA 0x01 /* CMD ID for Get MAC */
/* Mellanox specific OEM Command */
#define NCSI_OEM_MLX_CMD_SMAF 0x01 /* CMD ID for Set MC Affinity */
#define NCSI_OEM_MLX_CMD_SMAF_PARAM 0x07 /* Parameter for SMAF */
/* OEM Command payload lengths*/
+#define NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN 7
#define NCSI_OEM_BCM_CMD_GMA_LEN 12
#define NCSI_OEM_MLX_CMD_GMA_LEN 8
#define NCSI_OEM_MLX_CMD_SMAF_LEN 60
ncsi_dev_state_probe_mlx_gma,
ncsi_dev_state_probe_mlx_smaf,
ncsi_dev_state_probe_cis,
+ ncsi_dev_state_probe_keep_phy,
ncsi_dev_state_probe_gvi,
ncsi_dev_state_probe_gc,
ncsi_dev_state_probe_gls,
return 0;
}
+#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY)
+
+static int ncsi_oem_keep_phy_intel(struct ncsi_cmd_arg *nca)
+{
+ unsigned char data[NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN];
+ int ret = 0;
+
+ nca->payload = NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN;
+
+ memset(data, 0, NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN);
+ *(unsigned int *)data = ntohl((__force __be32)NCSI_OEM_MFR_INTEL_ID);
+
+ data[4] = NCSI_OEM_INTEL_CMD_KEEP_PHY;
+
+ /* PHY Link up attribute */
+ data[6] = 0x1;
+
+ nca->data = data;
+
+ ret = ncsi_xmit_cmd(nca);
+ if (ret)
+ netdev_err(nca->ndp->ndev.dev,
+ "NCSI: Failed to transmit cmd 0x%x during configure\n",
+ nca->type);
+ return ret;
+}
+
+#endif
+
#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC)
/* NCSI OEM Command APIs */
nca->payload = NCSI_OEM_BCM_CMD_GMA_LEN;
memset(data, 0, NCSI_OEM_BCM_CMD_GMA_LEN);
- *(unsigned int *)data = ntohl(NCSI_OEM_MFR_BCM_ID);
+ *(unsigned int *)data = ntohl((__force __be32)NCSI_OEM_MFR_BCM_ID);
data[5] = NCSI_OEM_BCM_CMD_GMA;
nca->data = data;
nca->payload = NCSI_OEM_MLX_CMD_GMA_LEN;
memset(&u, 0, sizeof(u));
- u.data_u32[0] = ntohl(NCSI_OEM_MFR_MLX_ID);
+ u.data_u32[0] = ntohl((__force __be32)NCSI_OEM_MFR_MLX_ID);
u.data_u8[5] = NCSI_OEM_MLX_CMD_GMA;
u.data_u8[6] = NCSI_OEM_MLX_CMD_GMA_PARAM;
int ret = 0;
memset(&u, 0, sizeof(u));
- u.data_u32[0] = ntohl(NCSI_OEM_MFR_MLX_ID);
+ u.data_u32[0] = ntohl((__force __be32)NCSI_OEM_MFR_MLX_ID);
u.data_u8[5] = NCSI_OEM_MLX_CMD_SMAF;
u.data_u8[6] = NCSI_OEM_MLX_CMD_SMAF_PARAM;
memcpy(&u.data_u8[MLX_SMAF_MAC_ADDR_OFFSET],
}
nd->state = ncsi_dev_state_probe_gvi;
+ if (IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY))
+ nd->state = ncsi_dev_state_probe_keep_phy;
+ break;
+#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY)
+ case ncsi_dev_state_probe_keep_phy:
+ ndp->pending_req_num = 1;
+
+ nca.type = NCSI_PKT_CMD_OEM;
+ nca.package = ndp->active_package->id;
+ nca.channel = 0;
+ ret = ncsi_oem_keep_phy_intel(&nca);
+ if (ret)
+ goto error;
+
+ nd->state = ncsi_dev_state_probe_gvi;
break;
+#endif /* CONFIG_NCSI_OEM_CMD_KEEP_PHY */
case ncsi_dev_state_probe_gvi:
case ncsi_dev_state_probe_gc:
case ncsi_dev_state_probe_gls:
/* Update to VLAN mode */
cmd = (struct ncsi_cmd_ev_pkt *)skb_network_header(nr->cmd);
ncm->enable = 1;
- ncm->data[0] = ntohl(cmd->mode);
+ ncm->data[0] = ntohl((__force __be32)cmd->mode);
return 0;
}
return 0;
}
+/* Response handler for Intel card */
+static int ncsi_rsp_handler_oem_intel(struct ncsi_request *nr)
+{
+ return 0;
+}
+
static struct ncsi_rsp_oem_handler {
unsigned int mfr_id;
int (*handler)(struct ncsi_request *nr);
} ncsi_rsp_oem_handlers[] = {
{ NCSI_OEM_MFR_MLX_ID, ncsi_rsp_handler_oem_mlx },
- { NCSI_OEM_MFR_BCM_ID, ncsi_rsp_handler_oem_bcm }
+ { NCSI_OEM_MFR_BCM_ID, ncsi_rsp_handler_oem_bcm },
+ { NCSI_OEM_MFR_INTEL_ID, ncsi_rsp_handler_oem_intel }
};
/* Response handler for OEM command */
spin_lock(&nf_conntrack_locks_all_lock);
- nf_conntrack_locks_all = true;
+ /* For nf_contrack_locks_all, only the latest time when another
+ * CPU will see an update is controlled, by the "release" of the
+ * spin_lock below.
+ * The earliest time is not controlled, an thus KCSAN could detect
+ * a race when nf_conntract_lock() reads the variable.
+ * WRITE_ONCE() is used to ensure the compiler will not
+ * optimize the write.
+ */
+ WRITE_ONCE(nf_conntrack_locks_all, true);
for (i = 0; i < CONNTRACK_LOCKS; i++) {
spin_lock(&nf_conntrack_locks[i]);
return false;
tstamp = nf_conn_tstamp_find(ct);
- if (tstamp && tstamp->stop == 0)
+ if (tstamp) {
+ s32 timeout = ct->timeout - nfct_time_stamp;
+
tstamp->stop = ktime_get_real_ns();
+ if (timeout < 0)
+ tstamp->stop -= jiffies_to_nsecs(-timeout);
+ }
if (nf_conntrack_event_report(IPCT_DESTROY, ct,
portid, report) < 0) {
}
list_for_each_entry(net, net_exit_list, exit_list) {
- nf_conntrack_proto_pernet_fini(net);
nf_conntrack_ecache_pernet_fini(net);
nf_conntrack_expect_pernet_fini(net);
free_percpu(net->ct.stat);
if (!help)
return 0;
+ rcu_read_lock();
helper = rcu_dereference(help->helper);
if (!helper)
goto out;
nla_nest_end(skb, nest_helper);
out:
+ rcu_read_unlock();
return 0;
nla_put_failure:
+ rcu_read_unlock();
return -1;
}
#endif
}
-void nf_conntrack_proto_pernet_fini(struct net *net)
-{
-#ifdef CONFIG_NF_CT_PROTO_GRE
- nf_ct_gre_keymap_flush(net);
-#endif
-}
-
module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint,
&nf_conntrack_htable_size, 0600);
return &net->ct.nf_ct_proto.gre;
}
-void nf_ct_gre_keymap_flush(struct net *net)
-{
- struct nf_gre_net *net_gre = gre_pernet(net);
- struct nf_ct_gre_keymap *km, *tmp;
-
- spin_lock_bh(&keymap_lock);
- list_for_each_entry_safe(km, tmp, &net_gre->keymap_list, list) {
- list_del_rcu(&km->list);
- kfree_rcu(km, rcu);
- }
- spin_unlock_bh(&keymap_lock);
-}
-
static inline int gre_key_cmpfn(const struct nf_ct_gre_keymap *km,
const struct nf_conntrack_tuple *t)
{
return true;
}
+static bool tcp_can_early_drop(const struct nf_conn *ct)
+{
+ switch (ct->proto.tcp.state) {
+ case TCP_CONNTRACK_FIN_WAIT:
+ case TCP_CONNTRACK_LAST_ACK:
+ case TCP_CONNTRACK_TIME_WAIT:
+ case TCP_CONNTRACK_CLOSE:
+ case TCP_CONNTRACK_CLOSE_WAIT:
+ return true;
+ default:
+ break;
+ }
+
+ return false;
+}
+
/* Returns verdict for packet, or -1 for invalid. */
int nf_conntrack_tcp_packet(struct nf_conn *ct,
struct sk_buff *skb,
if (index != TCP_RST_SET)
break;
- if (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) {
+ /* If we are closing, tuple might have been re-used already.
+ * last_index, last_ack, and all other ct fields used for
+ * sequence/window validation are outdated in that case.
+ *
+ * As the conntrack can already be expired by GC under pressure,
+ * just skip validation checks.
+ */
+ if (tcp_can_early_drop(ct))
+ goto in_window;
+
+ /* td_maxack might be outdated if we let a SYN through earlier */
+ if ((ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) &&
+ ct->proto.tcp.last_index != TCP_SYN_SET) {
u32 seq = ntohl(th->seq);
- if (before(seq, ct->proto.tcp.seen[!dir].td_maxack)) {
+ /* If we are not in established state and SEQ=0 this is most
+ * likely an answer to a SYN we let go through above (last_index
+ * can be updated due to out-of-order ACKs).
+ */
+ if (seq == 0 && !nf_conntrack_tcp_established(ct))
+ break;
+
+ if (before(seq, ct->proto.tcp.seen[!dir].td_maxack) &&
+ !tn->tcp_ignore_invalid_rst) {
/* Invalid RST */
spin_unlock_bh(&ct->lock);
nf_ct_l4proto_log_invalid(skb, ct, state, "invalid rst");
nf_ct_kill_acct(ct, ctinfo, skb);
return NF_ACCEPT;
}
+
+ if (index == TCP_SYN_SET && old_state == TCP_CONNTRACK_SYN_SENT) {
+ /* do not renew timeout on SYN retransmit.
+ *
+ * Else port reuse by client or NAT middlebox can keep
+ * entry alive indefinitely (including nat info).
+ */
+ return NF_ACCEPT;
+ }
+
/* ESTABLISHED without SEEN_REPLY, i.e. mid-connection
* pickup with loose=1. Avoid large ESTABLISHED timeout.
*/
return NF_ACCEPT;
}
-static bool tcp_can_early_drop(const struct nf_conn *ct)
-{
- switch (ct->proto.tcp.state) {
- case TCP_CONNTRACK_FIN_WAIT:
- case TCP_CONNTRACK_LAST_ACK:
- case TCP_CONNTRACK_TIME_WAIT:
- case TCP_CONNTRACK_CLOSE:
- case TCP_CONNTRACK_CLOSE_WAIT:
- return true;
- default:
- break;
- }
-
- return false;
-}
-
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
#include <linux/netfilter/nfnetlink.h>
*/
tn->tcp_be_liberal = 0;
+ /* If it's non-zero, we turn off RST sequence number check */
+ tn->tcp_ignore_invalid_rst = 0;
+
/* Max number of the retransmitted packets without receiving an (acceptable)
* ACK from the destination. If this number is reached, a shorter timer
* will be started.
#endif
NF_SYSCTL_CT_PROTO_TCP_LOOSE,
NF_SYSCTL_CT_PROTO_TCP_LIBERAL,
+ NF_SYSCTL_CT_PROTO_TCP_IGNORE_INVALID_RST,
NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS,
NF_SYSCTL_CT_PROTO_TIMEOUT_UDP,
NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
+ [NF_SYSCTL_CT_PROTO_TCP_IGNORE_INVALID_RST] = {
+ .procname = "nf_conntrack_tcp_ignore_invalid_rst",
+ .maxlen = sizeof(u8),
+ .mode = 0644,
+ .proc_handler = proc_dou8vec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
+ },
[NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS] = {
.procname = "nf_conntrack_tcp_max_retrans",
.maxlen = sizeof(u8),
XASSIGN(LOOSE, &tn->tcp_loose);
XASSIGN(LIBERAL, &tn->tcp_be_liberal);
XASSIGN(MAX_RETRANS, &tn->tcp_max_retrans);
+ XASSIGN(IGNORE_INVALID_RST, &tn->tcp_ignore_invalid_rst);
#undef XASSIGN
#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
void flow_offload_refresh(struct nf_flowtable *flow_table,
struct flow_offload *flow)
{
- flow->timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow);
+ u32 timeout;
+
+ timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow);
+ if (READ_ONCE(flow->timeout) != timeout)
+ WRITE_ONCE(flow->timeout, timeout);
if (likely(!nf_flowtable_hw_offload(flow_table)))
return;
return 0;
err_destroy_flow_rule:
- nft_flow_rule_destroy(flow);
+ if (flow)
+ nft_flow_rule_destroy(flow);
err_release_rule:
nf_tables_rule_release(&ctx, rule);
err_release_expr:
return 0;
}
+static void nf_tables_commit_audit_free(struct list_head *adl)
+{
+ struct nft_audit_data *adp, *adn;
+
+ list_for_each_entry_safe(adp, adn, adl, list) {
+ list_del(&adp->list);
+ kfree(adp);
+ }
+}
+
static void nf_tables_commit_audit_collect(struct list_head *adl,
struct nft_table *table, u32 op)
{
ret = nf_tables_commit_audit_alloc(&adl, trans->ctx.table);
if (ret) {
nf_tables_commit_chain_prepare_cancel(net);
+ nf_tables_commit_audit_free(&adl);
return ret;
}
if (trans->msg_type == NFT_MSG_NEWRULE ||
ret = nf_tables_commit_chain_prepare(net, chain);
if (ret < 0) {
nf_tables_commit_chain_prepare_cancel(net);
+ nf_tables_commit_audit_free(&adl);
return ret;
}
}
nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *dev)
{
const struct nf_hook_entries *hook_head = NULL;
+#ifdef CONFIG_NETFILTER_INGRESS
struct net_device *netdev;
+#endif
switch (pf) {
case NFPROTO_IPV4:
{
struct nft_last_priv *priv = nft_expr_priv(expr);
u64 last_jiffies;
+ u32 last_set = 0;
int err;
- if (tb[NFTA_LAST_MSECS]) {
+ if (tb[NFTA_LAST_SET]) {
+ last_set = ntohl(nla_get_be32(tb[NFTA_LAST_SET]));
+ if (last_set == 1)
+ priv->last_set = 1;
+ }
+
+ if (last_set && tb[NFTA_LAST_MSECS]) {
err = nf_msecs_to_jiffies64(tb[NFTA_LAST_MSECS], &last_jiffies);
if (err < 0)
return err;
- priv->last_jiffies = jiffies + (unsigned long)last_jiffies;
- priv->last_set = 1;
+ priv->last_jiffies = jiffies - (unsigned long)last_jiffies;
}
return 0;
{
struct nft_last_priv *priv = nft_expr_priv(expr);
- priv->last_jiffies = jiffies;
- priv->last_set = 1;
+ if (READ_ONCE(priv->last_jiffies) != jiffies)
+ WRITE_ONCE(priv->last_jiffies, jiffies);
+ if (READ_ONCE(priv->last_set) == 0)
+ WRITE_ONCE(priv->last_set, 1);
}
static int nft_last_dump(struct sk_buff *skb, const struct nft_expr *expr)
{
struct nft_last_priv *priv = nft_expr_priv(expr);
+ unsigned long last_jiffies = READ_ONCE(priv->last_jiffies);
+ u32 last_set = READ_ONCE(priv->last_set);
__be64 msecs;
- if (time_before(jiffies, priv->last_jiffies))
- priv->last_set = 0;
+ if (time_before(jiffies, last_jiffies)) {
+ WRITE_ONCE(priv->last_set, 0);
+ last_set = 0;
+ }
- if (priv->last_set)
- msecs = nf_jiffies64_to_msecs(jiffies - priv->last_jiffies);
+ if (last_set)
+ msecs = nf_jiffies64_to_msecs(jiffies - last_jiffies);
else
msecs = 0;
- if (nla_put_be32(skb, NFTA_LAST_SET, htonl(priv->last_set)) ||
+ if (nla_put_be32(skb, NFTA_LAST_SET, htonl(last_set)) ||
nla_put_be64(skb, NFTA_LAST_MSECS, msecs, NFTA_LAST_PAD))
goto nla_put_failure;
alen = sizeof_field(struct nf_nat_range, min_addr.ip6);
break;
default:
- return -EAFNOSUPPORT;
+ if (tb[NFTA_NAT_REG_ADDR_MIN])
+ return -EAFNOSUPPORT;
+ break;
}
priv->family = family;
nlmsg_end(skb, rep);
- netlink_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid, MSG_DONTWAIT);
+ nlmsg_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid);
}
EXPORT_SYMBOL(netlink_ack);
is accepted() it isn't 'dead' so doesn't get removed. */
if (sock_flag(sk, SOCK_DESTROY) ||
(sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) {
- sock_hold(sk);
bh_unlock_sock(sk);
nr_destroy_socket(sk);
- sock_put(sk);
- return;
+ goto out;
}
break;
nr_start_heartbeat(sk);
bh_unlock_sock(sk);
+out:
+ sock_put(sk);
}
static void nr_t2timer_expiry(struct timer_list *t)
nr_enquiry_response(sk);
}
bh_unlock_sock(sk);
+ sock_put(sk);
}
static void nr_t4timer_expiry(struct timer_list *t)
bh_lock_sock(sk);
nr_sk(sk)->condition &= ~NR_COND_PEER_RX_BUSY;
bh_unlock_sock(sk);
+ sock_put(sk);
}
static void nr_idletimer_expiry(struct timer_list *t)
sock_set_flag(sk, SOCK_DEAD);
}
bh_unlock_sock(sk);
+ sock_put(sk);
}
static void nr_t1timer_expiry(struct timer_list *t)
case NR_STATE_1:
if (nr->n2count == nr->n2) {
nr_disconnect(sk, ETIMEDOUT);
- bh_unlock_sock(sk);
- return;
+ goto out;
} else {
nr->n2count++;
nr_write_internal(sk, NR_CONNREQ);
case NR_STATE_2:
if (nr->n2count == nr->n2) {
nr_disconnect(sk, ETIMEDOUT);
- bh_unlock_sock(sk);
- return;
+ goto out;
} else {
nr->n2count++;
nr_write_internal(sk, NR_DISCREQ);
case NR_STATE_3:
if (nr->n2count == nr->n2) {
nr_disconnect(sk, ETIMEDOUT);
- bh_unlock_sock(sk);
- return;
+ goto out;
} else {
nr->n2count++;
nr_requeue_frames(sk);
}
nr_start_t1timer(sk);
+out:
bh_unlock_sock(sk);
+ sock_put(sk);
}
{
const long *cp1 = (const long *)((const u8 *)key1 + key_start);
const long *cp2 = (const long *)((const u8 *)key2 + key_start);
- long diffs = 0;
int i;
for (i = key_start; i < key_end; i += sizeof(long))
- diffs |= *cp1++ ^ *cp2++;
+ if (*cp1++ ^ *cp2++)
+ return false;
- return diffs == 0;
+ return true;
}
static bool flow_cmp_masked_key(const struct sw_flow *flow,
struct qrtr_endpoint ep;
struct mhi_device *mhi_dev;
struct device *dev;
+ struct completion ready;
};
/* From MHI to QRTR */
struct qrtr_mhi_dev *qdev = container_of(ep, struct qrtr_mhi_dev, ep);
int rc;
+ rc = wait_for_completion_interruptible(&qdev->ready);
+ if (rc)
+ goto free_skb;
+
if (skb->sk)
sock_hold(skb->sk);
int rc;
/* start channels */
- rc = mhi_prepare_for_transfer(mhi_dev);
+ rc = mhi_prepare_for_transfer(mhi_dev, 0);
if (rc)
return rc;
if (rc)
return rc;
+ /* start channels */
+ rc = mhi_prepare_for_transfer(mhi_dev, MHI_CH_INBOUND_ALLOC_BUFS);
+ if (rc) {
+ qrtr_endpoint_unregister(&qdev->ep);
+ dev_set_drvdata(&mhi_dev->dev, NULL);
+ return rc;
+ }
+
+ complete_all(&qdev->ready);
dev_dbg(qdev->dev, "Qualcomm MHI QRTR driver probed\n");
return 0;
if (!ipc)
goto err;
- if (sock_queue_rcv_skb(&ipc->sk, skb))
+ if (sock_queue_rcv_skb(&ipc->sk, skb)) {
+ qrtr_port_put(ipc);
goto err;
+ }
qrtr_port_put(ipc);
}
ipc = qrtr_port_lookup(to->sq_port);
if (!ipc || &ipc->sk == skb->sk) { /* do not send to self */
+ if (ipc)
+ qrtr_port_put(ipc);
kfree_skb(skb);
return -ENODEV;
}
static void tcf_ct_flow_table_cleanup_work(struct work_struct *work)
{
+ struct flow_block_cb *block_cb, *tmp_cb;
struct tcf_ct_flow_table *ct_ft;
+ struct flow_block *block;
ct_ft = container_of(to_rcu_work(work), struct tcf_ct_flow_table,
rwork);
nf_flow_table_free(&ct_ft->nf_ft);
+
+ /* Remove any remaining callbacks before cleanup */
+ block = &ct_ft->nf_ft.flow_block;
+ down_write(&ct_ft->nf_ft.flow_block_lock);
+ list_for_each_entry_safe(block_cb, tmp_cb, &block->cb_list, list) {
+ list_del(&block_cb->list);
+ flow_block_cb_free(block_cb);
+ }
+ up_write(&ct_ft->nf_ft.flow_block_lock);
kfree(ct_ft);
module_put(THIS_MODULE);
/* This will take care of sending queued events
* even if the connection is already confirmed.
*/
- nf_conntrack_confirm(skb);
+ if (nf_conntrack_confirm(skb) != NF_ACCEPT)
+ goto drop;
}
if (!skip_add)
*/
#include <linux/module.h>
+#include <linux/if_arp.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
tcf_lastuse_update(&d->tcf_tm);
bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb);
+ action = READ_ONCE(d->tcf_action);
+ if (unlikely(action == TC_ACT_SHOT))
+ goto drop;
+
+ if (!skb->dev || skb->dev->type != ARPHRD_ETHER)
+ return action;
+
/* XXX: if you are going to edit more fields beyond ethernet header
* (example when you add IP header replacement or vlan swap)
* then MAX_EDIT_LEN needs to change appropriately
if (unlikely(err)) /* best policy is to drop on the floor */
goto drop;
- action = READ_ONCE(d->tcf_action);
- if (unlikely(action == TC_ACT_SHOT))
- goto drop;
-
p = rcu_dereference_bh(d->skbmod_p);
flags = p->flags;
if (flags & SKBMOD_F_DMAC)
break;
case RTM_GETCHAIN:
err = tc_chain_notify(chain, skb, n->nlmsg_seq,
- n->nlmsg_seq, n->nlmsg_type, true);
+ n->nlmsg_flags, n->nlmsg_type, true);
if (err < 0)
NL_SET_ERR_MSG(extack, "Failed to send chain notify message");
break;
TCA_TCINDEX_POLICE);
}
+static void tcindex_free_perfect_hash(struct tcindex_data *cp);
+
static void tcindex_partial_destroy_work(struct work_struct *work)
{
struct tcindex_data *p = container_of(to_rcu_work(work),
rwork);
rtnl_lock();
- kfree(p->perfect);
+ if (p->perfect)
+ tcindex_free_perfect_hash(p);
kfree(p);
rtnl_unlock();
}
/* seqlock has the same scope of busylock, for NOLOCK qdisc */
spin_lock_init(&sch->seqlock);
- lockdep_set_class(&sch->busylock,
+ lockdep_set_class(&sch->seqlock,
dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
seqcount_init(&sch->running);
/* if there's no entry, it means that the schedule didn't
* start yet, so force all gates to be open, this is in
* accordance to IEEE 802.1Qbv-2015 Section 8.6.9.4.5
- * "AdminGateSates"
+ * "AdminGateStates"
*/
gate_mask = entry ? entry->gate_mask : TAPRIO_ALL_GATES_OPEN;
if (FULL_OFFLOAD_IS_ENABLED(q->flags)) {
qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
old = dev_graft_qdisc(qdisc->dev_queue, qdisc);
- if (ntx < dev->real_num_tx_queues)
- qdisc_hash_add(qdisc, false);
} else {
old = dev_graft_qdisc(qdisc->dev_queue, sch);
qdisc_refcount_inc(sch);
memcpy(key->data, &auth_key->sca_key[0], auth_key->sca_keylength);
cur_key->key = key;
- if (replace) {
- list_del_init(&shkey->key_list);
- sctp_auth_shkey_release(shkey);
+ if (!replace) {
+ list_add(&cur_key->key_list, sh_keys);
+ return 0;
}
+
+ list_del_init(&shkey->key_list);
+ sctp_auth_shkey_release(shkey);
list_add(&cur_key->key_list, sh_keys);
+ if (asoc && asoc->active_key_id == auth_key->sca_keynumber)
+ sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL);
+
return 0;
}
goto out;
}
- err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid,
- MSG_DONTWAIT);
- if (err > 0)
- err = 0;
+ err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid);
+
out:
return err;
}
if (unlikely(!af))
return NULL;
- if (af->from_addr_param(&paddr, param, peer_port, 0))
+ if (!af->from_addr_param(&paddr, param, peer_port, 0))
return NULL;
return __sctp_lookup_association(net, laddr, &paddr, transportp);
list_for_each_entry_safe(addr, temp,
&net->sctp.local_addr_list, list) {
if (addr->a.sa.sa_family == AF_INET6 &&
- ipv6_addr_equal(&addr->a.v6.sin6_addr,
- &ifa->addr)) {
+ ipv6_addr_equal(&addr->a.v6.sin6_addr,
+ &ifa->addr) &&
+ addr->a.v6.sin6_scope_id == ifa->idev->dev->ifindex) {
sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_DEL);
found = 1;
addr->valid = 0;
if (asoc->param_flags & SPP_PMTUD_ENABLE)
sctp_assoc_sync_pmtu(asoc);
} else if (!sctp_transport_pl_enabled(tp) &&
- !sctp_transport_pmtu_check(tp)) {
- if (asoc->param_flags & SPP_PMTUD_ENABLE)
+ asoc->param_flags & SPP_PMTUD_ENABLE) {
+ if (!sctp_transport_pmtu_check(tp))
sctp_assoc_sync_pmtu(asoc);
}
retval = SCTP_SCOPE_LINK;
} else if (ipv4_is_private_10(addr->v4.sin_addr.s_addr) ||
ipv4_is_private_172(addr->v4.sin_addr.s_addr) ||
- ipv4_is_private_192(addr->v4.sin_addr.s_addr)) {
+ ipv4_is_private_192(addr->v4.sin_addr.s_addr) ||
+ ipv4_is_test_198(addr->v4.sin_addr.s_addr)) {
retval = SCTP_SCOPE_PRIVATE;
} else {
retval = SCTP_SCOPE_GLOBAL;
const struct sctp_transport *transport,
__u32 probe_size)
{
- struct sctp_sender_hb_info hbinfo;
+ struct sctp_sender_hb_info hbinfo = {};
struct sctp_chunk *retval;
retval = sctp_make_control(asoc, SCTP_CID_HEARTBEAT, 0,
if (!sctp_transport_pl_enabled(transport))
return SCTP_DISPOSITION_CONSUME;
- sctp_transport_pl_send(transport);
-
- reply = sctp_make_heartbeat(asoc, transport, transport->pl.probe_size);
- if (!reply)
- return SCTP_DISPOSITION_NOMEM;
- sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply));
+ if (sctp_transport_pl_send(transport)) {
+ reply = sctp_make_heartbeat(asoc, transport, transport->pl.probe_size);
+ if (!reply)
+ return SCTP_DISPOSITION_NOMEM;
+ sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply));
+ }
sctp_add_cmd_sf(commands, SCTP_CMD_PROBE_TIMER_UPDATE,
SCTP_TRANSPORT(transport));
!sctp_transport_pl_enabled(link))
return SCTP_DISPOSITION_DISCARD;
- sctp_transport_pl_recv(link);
- if (link->pl.state == SCTP_PL_COMPLETE)
+ if (sctp_transport_pl_recv(link))
return SCTP_DISPOSITION_CONSUME;
return sctp_sf_send_probe(net, ep, asoc, type, link, commands);
}
if (optlen > 0) {
+ /* Trim it to the biggest size sctp sockopt may need if necessary */
+ optlen = min_t(unsigned int, optlen,
+ PAGE_ALIGN(USHRT_MAX +
+ sizeof(__u16) * sizeof(struct sctp_reset_streams)));
kopt = memdup_sockptr(optval, optlen);
if (IS_ERR(kopt))
return PTR_ERR(kopt);
sctp_transport_pl_update(transport);
}
-void sctp_transport_pl_send(struct sctp_transport *t)
+bool sctp_transport_pl_send(struct sctp_transport *t)
{
- pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n",
- __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high);
-
- if (t->pl.probe_count < SCTP_MAX_PROBES) {
- t->pl.probe_count++;
- return;
- }
+ if (t->pl.probe_count < SCTP_MAX_PROBES)
+ goto out;
+ t->pl.last_rtx_chunks = t->asoc->rtx_data_chunks;
+ t->pl.probe_count = 0;
if (t->pl.state == SCTP_PL_BASE) {
if (t->pl.probe_size == SCTP_BASE_PLPMTU) { /* BASE_PLPMTU Confirmation Failed */
t->pl.state = SCTP_PL_ERROR; /* Base -> Error */
sctp_assoc_sync_pmtu(t->asoc);
}
}
- t->pl.probe_count = 1;
+
+out:
+ if (t->pl.state == SCTP_PL_COMPLETE && t->pl.raise_count < 30 &&
+ !t->pl.probe_count && t->pl.last_rtx_chunks == t->asoc->rtx_data_chunks) {
+ t->pl.raise_count++;
+ return false;
+ }
+
+ pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n",
+ __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high);
+
+ t->pl.probe_count++;
+ return true;
}
-void sctp_transport_pl_recv(struct sctp_transport *t)
+bool sctp_transport_pl_recv(struct sctp_transport *t)
{
pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n",
__func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high);
+ t->pl.last_rtx_chunks = t->asoc->rtx_data_chunks;
t->pl.pmtu = t->pl.probe_size;
t->pl.probe_count = 0;
if (t->pl.state == SCTP_PL_BASE) {
if (!t->pl.probe_high) {
t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_BIG_STEP,
SCTP_MAX_PLPMTU);
- return;
+ return false;
}
t->pl.probe_size += SCTP_PL_MIN_STEP;
if (t->pl.probe_size >= t->pl.probe_high) {
t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
sctp_assoc_sync_pmtu(t->asoc);
}
- } else if (t->pl.state == SCTP_PL_COMPLETE && ++t->pl.raise_count == 30) {
+ } else if (t->pl.state == SCTP_PL_COMPLETE && t->pl.raise_count == 30) {
/* Raise probe_size again after 30 * interval in Search Complete */
t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */
t->pl.probe_size += SCTP_PL_MIN_STEP;
}
+
+ return t->pl.state == SCTP_PL_COMPLETE;
}
static bool sctp_transport_pl_toobig(struct sctp_transport *t, u32 pmtu)
#include <linux/sockios.h>
#include <net/busy_poll.h>
#include <linux/errqueue.h>
+#include <linux/ptp_clock_kernel.h>
#ifdef CONFIG_NET_RX_BUSY_POLL
unsigned int sysctl_net_busy_read __read_mostly;
empty = 0;
if (shhwtstamps &&
(sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) &&
- !skb_is_swtx_tstamp(skb, false_tstamp) &&
- ktime_to_timespec64_cond(shhwtstamps->hwtstamp, tss.ts + 2)) {
- empty = 0;
- if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) &&
- !skb_is_err_queue(skb))
- put_ts_pktinfo(msg, skb);
+ !skb_is_swtx_tstamp(skb, false_tstamp)) {
+ if (sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC)
+ ptp_convert_timestamp(shhwtstamps, sk->sk_bind_phc);
+
+ if (ktime_to_timespec64_cond(shhwtstamps->hwtstamp,
+ tss.ts + 2)) {
+ empty = 0;
+
+ if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) &&
+ !skb_is_err_queue(skb))
+ put_ts_pktinfo(msg, skb);
+ }
}
if (!empty) {
if (sock_flag(sk, SOCK_TSTAMP_NEW))
if (unlikely(!aead))
return -ENOKEY;
- /* Cow skb data if needed */
- if (likely(!skb_cloned(skb) &&
- (!skb_is_nonlinear(skb) || !skb_has_frag_list(skb)))) {
- nsg = 1 + skb_shinfo(skb)->nr_frags;
- } else {
- nsg = skb_cow_data(skb, 0, &unused);
- if (unlikely(nsg < 0)) {
- pr_err("RX: skb_cow_data() returned %d\n", nsg);
- return nsg;
- }
+ nsg = skb_cow_data(skb, 0, &unused);
+ if (unlikely(nsg < 0)) {
+ pr_err("RX: skb_cow_data() returned %d\n", nsg);
+ return nsg;
}
/* Allocate memory for the AEAD operation */
static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dsz);
static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz);
static void tipc_sk_push_backlog(struct tipc_sock *tsk, bool nagle_ack);
+static int tipc_wait_for_connect(struct socket *sock, long *timeo_p);
static const struct proto_ops packet_ops;
static const struct proto_ops stream_ops;
rc = 0;
}
- if (unlikely(syn && !rc))
+ if (unlikely(syn && !rc)) {
tipc_set_sk_state(sk, TIPC_CONNECTING);
+ if (timeout) {
+ timeout = msecs_to_jiffies(timeout);
+ tipc_wait_for_connect(sock, &timeout);
+ }
+ }
return rc ? rc : dlen;
}
return -EMSGSIZE;
/* Handle implicit connection setup */
- if (unlikely(dest)) {
+ if (unlikely(dest && sk->sk_state == TIPC_OPEN)) {
rc = __tipc_sendmsg(sock, m, dlen);
if (dlen && dlen == rc) {
tsk->peer_caps = tipc_node_get_capabilities(net, dnode);
static int tipc_wait_for_accept(struct socket *sock, long timeo)
{
struct sock *sk = sock->sk;
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
int err;
/* True wake-one mechanism for incoming connections: only
* anymore, the common case will execute the loop only once.
*/
for (;;) {
- prepare_to_wait_exclusive(sk_sleep(sk), &wait,
- TASK_INTERRUPTIBLE);
if (timeo && skb_queue_empty(&sk->sk_receive_queue)) {
+ add_wait_queue(sk_sleep(sk), &wait);
release_sock(sk);
- timeo = schedule_timeout(timeo);
+ timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo);
lock_sock(sk);
+ remove_wait_queue(sk_sleep(sk), &wait);
}
err = 0;
if (!skb_queue_empty(&sk->sk_receive_queue))
if (signal_pending(current))
break;
}
- finish_wait(sk_sleep(sk), &wait);
return err;
}
bool kern)
{
struct sock *new_sk, *sk = sock->sk;
- struct sk_buff *buf;
struct tipc_sock *new_tsock;
+ struct msghdr m = {NULL,};
struct tipc_msg *msg;
+ struct sk_buff *buf;
long timeo;
int res;
}
/*
- * Respond to 'SYN-' by discarding it & returning 'ACK'-.
- * Respond to 'SYN+' by queuing it on new socket.
+ * Respond to 'SYN-' by discarding it & returning 'ACK'.
+ * Respond to 'SYN+' by queuing it on new socket & returning 'ACK'.
*/
if (!msg_data_sz(msg)) {
- struct msghdr m = {NULL,};
-
tsk_advance_rx_queue(sk);
- __tipc_sendstream(new_sock, &m, 0);
} else {
__skb_dequeue(&sk->sk_receive_queue);
__skb_queue_head(&new_sk->sk_receive_queue, buf);
skb_set_owner_r(buf, new_sk);
}
+ __tipc_sendstream(new_sock, &m, 0);
release_sock(new_sk);
exit:
release_sock(sk);
return err;
}
+static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb)
+{
+ scm->fp = scm_fp_dup(UNIXCB(skb).fp);
+
+ /*
+ * Garbage collection of unix sockets starts by selecting a set of
+ * candidate sockets which have reference only from being in flight
+ * (total_refs == inflight_refs). This condition is checked once during
+ * the candidate collection phase, and candidates are marked as such, so
+ * that non-candidates can later be ignored. While inflight_refs is
+ * protected by unix_gc_lock, total_refs (file count) is not, hence this
+ * is an instantaneous decision.
+ *
+ * Once a candidate, however, the socket must not be reinstalled into a
+ * file descriptor while the garbage collection is in progress.
+ *
+ * If the above conditions are met, then the directed graph of
+ * candidates (*) does not change while unix_gc_lock is held.
+ *
+ * Any operations that changes the file count through file descriptors
+ * (dup, close, sendmsg) does not change the graph since candidates are
+ * not installed in fds.
+ *
+ * Dequeing a candidate via recvmsg would install it into an fd, but
+ * that takes unix_gc_lock to decrement the inflight count, so it's
+ * serialized with garbage collection.
+ *
+ * MSG_PEEK is special in that it does not change the inflight count,
+ * yet does install the socket into an fd. The following lock/unlock
+ * pair is to ensure serialization with garbage collection. It must be
+ * done between incrementing the file count and installing the file into
+ * an fd.
+ *
+ * If garbage collection starts after the barrier provided by the
+ * lock/unlock, then it will see the elevated refcount and not mark this
+ * as a candidate. If a garbage collection is already in progress
+ * before the file count was incremented, then the lock/unlock pair will
+ * ensure that garbage collection is finished before progressing to
+ * installing the fd.
+ *
+ * (*) A -> B where B is on the queue of A or B is on the queue of C
+ * which is on the queue of listening socket A.
+ */
+ spin_lock(&unix_gc_lock);
+ spin_unlock(&unix_gc_lock);
+}
+
static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds)
{
int err = 0;
sk_peek_offset_fwd(sk, size);
if (UNIXCB(skb).fp)
- scm.fp = scm_fp_dup(UNIXCB(skb).fp);
+ unix_peek_fds(&scm, skb);
}
err = (flags & MSG_TRUNC) ? skb->len - skip : size;
/* It is questionable, see note in unix_dgram_recvmsg.
*/
if (UNIXCB(skb).fp)
- scm.fp = scm_fp_dup(UNIXCB(skb).fp);
+ unix_peek_fds(&scm, skb);
sk_peek_offset_fwd(sk, chunk);
goto again;
}
- err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid,
- MSG_DONTWAIT);
- if (err > 0)
- err = 0;
+ err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid);
+
out:
if (sk)
sock_put(sk);
virtio_transport_recv_enqueue(vsk, pkt);
sk->sk_data_ready(sk);
return err;
+ case VIRTIO_VSOCK_OP_CREDIT_REQUEST:
+ virtio_transport_send_credit_update(vsk);
+ break;
case VIRTIO_VSOCK_OP_CREDIT_UPDATE:
sk->sk_write_space(sk);
break;
goto nla_put_failure;
for (band = state->band_start;
- band < NUM_NL80211_BANDS; band++) {
+ band < (state->split ?
+ NUM_NL80211_BANDS :
+ NL80211_BAND_60GHZ + 1);
+ band++) {
struct ieee80211_supported_band *sband;
/* omit higher bands for ancient software */
* be grouped with this beacon for updates ...
*/
if (!cfg80211_combine_bsses(rdev, new)) {
- kfree(new);
+ bss_ref_put(rdev, new);
goto drop;
}
}
if (rdev->bss_entries >= bss_entries_limit &&
!cfg80211_bss_expire_oldest(rdev)) {
- if (!list_empty(&new->hidden_list))
- list_del(&new->hidden_list);
- kfree(new);
+ bss_ref_put(rdev, new);
goto drop;
}
len = nlmsg_attrlen(nlh_src, xfrm_msg_min[type]);
nla_for_each_attr(nla, attrs, len, remaining) {
- int err = xfrm_xlate64_attr(dst, nla);
+ int err;
+ switch (type) {
+ case XFRM_MSG_NEWSPDINFO:
+ err = xfrm_nla_cpy(dst, nla, nla_len(nla));
+ break;
+ default:
+ err = xfrm_xlate64_attr(dst, nla);
+ break;
+ }
if (err)
return err;
}
/* Calculates len of translated 64-bit message. */
static size_t xfrm_user_rcv_calculate_len64(const struct nlmsghdr *src,
- struct nlattr *attrs[XFRMA_MAX+1])
+ struct nlattr *attrs[XFRMA_MAX + 1],
+ int maxtype)
{
size_t len = nlmsg_len(src);
case XFRM_MSG_POLEXPIRE:
len += 8;
break;
+ case XFRM_MSG_NEWSPDINFO:
+ /* attirbutes are xfrm_spdattr_type_t, not xfrm_attr_type_t */
+ return len;
default:
break;
}
+ /* Unexpected for anything, but XFRM_MSG_NEWSPDINFO, please
+ * correct both 64=>32-bit and 32=>64-bit translators to copy
+ * new attributes.
+ */
+ if (WARN_ON_ONCE(maxtype))
+ return len;
+
if (attrs[XFRMA_SA])
len += 4;
if (attrs[XFRMA_POLICY])
static int xfrm_xlate32(struct nlmsghdr *dst, const struct nlmsghdr *src,
struct nlattr *attrs[XFRMA_MAX+1],
- size_t size, u8 type, struct netlink_ext_ack *extack)
+ size_t size, u8 type, int maxtype,
+ struct netlink_ext_ack *extack)
{
size_t pos;
int i;
}
pos = dst->nlmsg_len;
+ if (maxtype) {
+ /* attirbutes are xfrm_spdattr_type_t, not xfrm_attr_type_t */
+ WARN_ON_ONCE(src->nlmsg_type != XFRM_MSG_NEWSPDINFO);
+
+ for (i = 1; i <= maxtype; i++) {
+ int err;
+
+ if (!attrs[i])
+ continue;
+
+ /* just copy - no need for translation */
+ err = xfrm_attr_cpy32(dst, &pos, attrs[i], size,
+ nla_len(attrs[i]), nla_len(attrs[i]));
+ if (err)
+ return err;
+ }
+ return 0;
+ }
+
for (i = 1; i < XFRMA_MAX + 1; i++) {
int err;
if (err < 0)
return ERR_PTR(err);
- len = xfrm_user_rcv_calculate_len64(h32, attrs);
+ len = xfrm_user_rcv_calculate_len64(h32, attrs, maxtype);
/* The message doesn't need translation */
if (len == nlmsg_len(h32))
return NULL;
if (!h64)
return ERR_PTR(-ENOMEM);
- err = xfrm_xlate32(h64, h32, attrs, len, type, extack);
+ err = xfrm_xlate32(h64, h32, attrs, len, type, maxtype, extack);
if (err < 0) {
kvfree(h64);
return ERR_PTR(err);
break;
}
- WARN_ON(!pos);
+ WARN_ON(list_entry_is_head(pos, &ipcomp_tfms_list, list));
if (--pos->users)
return;
__read_mostly;
static struct kmem_cache *xfrm_dst_cache __ro_after_init;
-static __read_mostly seqcount_mutex_t xfrm_policy_hash_generation;
static struct rhashtable xfrm_policy_inexact_table;
static const struct rhashtable_params xfrm_pol_inexact_params;
return;
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
- write_seqcount_begin(&xfrm_policy_hash_generation);
+ write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation);
odst = rcu_dereference_protected(net->xfrm.policy_bydst[dir].table,
lockdep_is_held(&net->xfrm.xfrm_policy_lock));
rcu_assign_pointer(net->xfrm.policy_bydst[dir].table, ndst);
net->xfrm.policy_bydst[dir].hmask = nhashmask;
- write_seqcount_end(&xfrm_policy_hash_generation);
+ write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation);
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
synchronize_rcu();
} while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq));
spin_lock_bh(&net->xfrm.xfrm_policy_lock);
- write_seqcount_begin(&xfrm_policy_hash_generation);
+ write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation);
/* make sure that we can insert the indirect policies again before
* we start with destructive action.
out_unlock:
__xfrm_policy_inexact_flush(net);
- write_seqcount_end(&xfrm_policy_hash_generation);
+ write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation);
spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
mutex_unlock(&hash_resize_mutex);
if (unlikely(!daddr || !saddr))
return NULL;
- retry:
- sequence = read_seqcount_begin(&xfrm_policy_hash_generation);
rcu_read_lock();
-
- chain = policy_hash_direct(net, daddr, saddr, family, dir);
- if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) {
- rcu_read_unlock();
- goto retry;
- }
+ retry:
+ do {
+ sequence = read_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation);
+ chain = policy_hash_direct(net, daddr, saddr, family, dir);
+ } while (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence));
ret = NULL;
hlist_for_each_entry_rcu(pol, chain, bydst) {
}
skip_inexact:
- if (read_seqcount_retry(&xfrm_policy_hash_generation, sequence)) {
- rcu_read_unlock();
+ if (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence))
goto retry;
- }
- if (ret && !xfrm_pol_hold_rcu(ret)) {
- rcu_read_unlock();
+ if (ret && !xfrm_pol_hold_rcu(ret))
goto retry;
- }
fail:
rcu_read_unlock();
/* Initialize the per-net locks here */
spin_lock_init(&net->xfrm.xfrm_state_lock);
spin_lock_init(&net->xfrm.xfrm_policy_lock);
+ seqcount_spinlock_init(&net->xfrm.xfrm_policy_hash_generation, &net->xfrm.xfrm_policy_lock);
mutex_init(&net->xfrm.xfrm_cfg_mutex);
rv = xfrm_statistics_init(net);
{
register_pernet_subsys(&xfrm_net_ops);
xfrm_dev_init();
- seqcount_mutex_init(&xfrm_policy_hash_generation, &hash_resize_mutex);
xfrm_input_init();
#ifdef CONFIG_XFRM_ESPINTCP
err = link->doit(skb, nlh, attrs);
+ /* We need to free skb allocated in xfrm_alloc_compat() before
+ * returning from this function, because consume_skb() won't take
+ * care of frag_list since netlink destructor sets
+ * sbk->head to NULL. (see netlink_skb_destructor())
+ */
+ if (skb_has_frag_list(skb)) {
+ kfree_skb(skb_shinfo(skb)->frag_list);
+ skb_shinfo(skb)->frag_list = NULL;
+ }
+
err:
kvfree(nlh64);
return err;
-Wno-gnu-variable-sized-type-not-at-end \
-Wno-address-of-packed-member -Wno-tautological-compare \
-Wno-unknown-warning-option $(CLANG_ARCH_ARGS) \
+ -fno-asynchronous-unwind-tables \
-I$(srctree)/samples/bpf/ -include asm_goto_workaround.h \
-O2 -emit-llvm -Xclang -disable-llvm-passes -c $< -o - | \
$(OPT) -O2 -mtriple=bpf-pc-linux | $(LLVM_DIS) | \
static int opt_timeout = 1000;
static bool opt_need_wakeup = true;
static u32 opt_num_xsks = 1;
+static u32 prog_id;
static bool opt_busy_poll;
static bool opt_reduced_cap;
return NULL;
}
+static void remove_xdp_program(void)
+{
+ u32 curr_prog_id = 0;
+
+ if (bpf_get_link_xdp_id(opt_ifindex, &curr_prog_id, opt_xdp_flags)) {
+ printf("bpf_get_link_xdp_id failed\n");
+ exit(EXIT_FAILURE);
+ }
+
+ if (prog_id == curr_prog_id)
+ bpf_set_link_xdp_fd(opt_ifindex, -1, opt_xdp_flags);
+ else if (!curr_prog_id)
+ printf("couldn't find a prog id on a given interface\n");
+ else
+ printf("program on interface changed, not removing\n");
+}
+
static void int_exit(int sig)
{
benchmark_done = true;
{
fprintf(stderr, "%s:%s:%i: errno: %d/\"%s\"\n", file, func,
line, error, strerror(error));
+
+ if (opt_num_xsks > 1)
+ remove_xdp_program();
exit(EXIT_FAILURE);
}
if (write(sock, &cmd, sizeof(int)) < 0)
exit_with_error(errno);
}
+
+ if (opt_num_xsks > 1)
+ remove_xdp_program();
}
static void swap_mac_addresses(void *data)
if (ret)
exit_with_error(-ret);
+ ret = bpf_get_link_xdp_id(opt_ifindex, &prog_id, opt_xdp_flags);
+ if (ret)
+ exit_with_error(-ret);
+
xsk->app_stats.rx_empty_polls = 0;
xsk->app_stats.fill_fail_polls = 0;
xsk->app_stats.copy_tx_sendtos = 0;
cmd_update_lto_symversions = \
rm -f $@.symversions \
$(foreach n, $(filter-out FORCE,$^), \
- $(if $(wildcard $(n).symversions), \
+ $(if $(shell test -s $(n).symversions && echo y), \
; cat $(n).symversions >> $@.symversions))
else
cmd_update_lto_symversions = echo >/dev/null
#! /usr/bin/env perl
# SPDX-License-Identifier: GPL-2.0
#
-# checkversion find uses of LINUX_VERSION_CODE or KERNEL_VERSION
-# without including <linux/version.h>, or cases of
-# including <linux/version.h> that don't need it.
-# Copyright (C) 2003, Randy Dunlap <rdunlap@xenotime.net>
+# checkversion finds uses of all macros in <linux/version.h>
+# where the source files do not #include <linux/version.h>; or cases
+# of including <linux/version.h> where it is not needed.
+# Copyright (C) 2003, Randy Dunlap <rdunlap@infradead.org>
use strict;
my $debugging;
foreach my $file (@ARGV) {
- next if $file =~ "include/linux/version\.h";
+ next if $file =~ "include/generated/uapi/linux/version\.h";
+ next if $file =~ "usr/include/linux/version\.h";
# Open this file.
open( my $f, '<', $file )
or die "Can't open $file: $!\n";
$iLinuxVersion = $. if m/^\s*#\s*include\s*<linux\/version\.h>/o;
}
- # Look for uses: LINUX_VERSION_CODE, KERNEL_VERSION, UTS_RELEASE
- if (($_ =~ /LINUX_VERSION_CODE/) || ($_ =~ /\WKERNEL_VERSION/)) {
+ # Look for uses: LINUX_VERSION_CODE, KERNEL_VERSION,
+ # LINUX_VERSION_MAJOR, LINUX_VERSION_PATCHLEVEL, LINUX_VERSION_SUBLEVEL
+ if (($_ =~ /LINUX_VERSION_CODE/) || ($_ =~ /\WKERNEL_VERSION/) ||
+ ($_ =~ /LINUX_VERSION_MAJOR/) || ($_ =~ /LINUX_VERSION_PATCHLEVEL/) ||
+ ($_ =~ /LINUX_VERSION_SUBLEVEL/)) {
$fUseVersion = 1;
last if $iLinuxVersion;
}
my $mcount_adjust; # Address adjustment to mcount offset
my $alignment; # The .align value to use for $mcount_section
my $section_type; # Section header plus possible alignment command
-my $can_use_local = 0; # If we can use local function references
-
-# Shut up recordmcount if user has older objcopy
-my $quiet_recordmcount = ".tmp_quiet_recordmcount";
-my $print_warning = 1;
-$print_warning = 0 if ( -f $quiet_recordmcount);
-
-##
-# check_objcopy - whether objcopy supports --globalize-symbols
-#
-# --globalize-symbols came out in 2.17, we must test the version
-# of objcopy, and if it is less than 2.17, then we can not
-# record local functions.
-sub check_objcopy
-{
- open (IN, "$objcopy --version |") or die "error running $objcopy";
- while (<IN>) {
- if (/objcopy.*\s(\d+)\.(\d+)/) {
- $can_use_local = 1 if ($1 > 2 || ($1 == 2 && $2 >= 17));
- last;
- }
- }
- close (IN);
-
- if (!$can_use_local && $print_warning) {
- print STDERR "WARNING: could not find objcopy version or version " .
- "is less than 2.17.\n" .
- "\tLocal function references are disabled.\n";
- open (QUIET, ">$quiet_recordmcount");
- printf QUIET "Disables the warning from recordmcount.pl\n";
- close QUIET;
- }
-}
if ($arch =~ /(x86(_64)?)|(i386)/) {
if ($bits == 64) {
my $mcount_s = $dirname . "/.tmp_mc_" . $prefix . ".s";
my $mcount_o = $dirname . "/.tmp_mc_" . $prefix . ".o";
-check_objcopy();
-
#
# Step 1: find all the local (static functions) and weak symbols.
# 't' is local, 'w/W' is weak
# is this function static? If so, note this fact.
if (defined $locals{$ref_func}) {
-
- # only use locals if objcopy supports globalize-symbols
- if (!$can_use_local) {
- return;
- }
$convert{$ref_func} = 1;
}
if test "$CONFIG_LOCALVERSION_AUTO" = "y"; then
# full scm version string
res="$res$(scm_version)"
-elif [ -z "${LOCALVERSION}" ]; then
- # append a plus sign if the repository is not in a clean
- # annotated or signed tagged state (as git describe only
- # looks at signed or annotated tags - git tag -a/-s) and
- # LOCALVERSION= is not specified
+elif [ "${LOCALVERSION+set}" != "set" ]; then
+ # If the variable LOCALVERSION is not set, append a plus
+ # sign if the repository is not in a clean annotated or
+ # signed tagged state (as git describe only looks at signed
+ # or annotated tags - git tag -a/-s).
+ #
+ # If the variable LOCALVERSION is set (including being set
+ # to an empty string), we don't want to append a plus sign.
scm=$(scm_version --short)
res="$res${scm:++}"
fi
continue
exception = None
- for l in open(el.path).readlines():
+ for l in open(el.path, encoding="utf-8").readlines():
if l.startswith('Valid-License-Identifier:'):
lid = l.split(':')[1].strip().upper()
if lid in spdx.licenses:
$ cat /sys/kernel/debug/tracing/trace_pipe > ~/raw_trace_func
Wait some times but not too much, the script is a bit slow.
Break the pipe (Ctrl + Z)
- $ scripts/draw_functrace.py < raw_trace_func > draw_functrace
+ $ scripts/tracing/draw_functrace.py < ~/raw_trace_func > draw_functrace
Then you have your drawn trace in draw_functrace
"""
line = line.strip()
if line.startswith("#"):
raise CommentLineException
- m = re.match("[^]]+?\\] +([0-9.]+): (\\w+) <-(\\w+)", line)
+ m = re.match("[^]]+?\\] +([a-z.]+) +([0-9.]+): (\\w+) <-(\\w+)", line)
if m is None:
raise BrokenLineException
- return (m.group(1), m.group(2), m.group(3))
+ return (m.group(2), m.group(3), m.group(4))
def main():
rc = sidtab_init(s);
if (rc) {
pr_err("SELinux: out of memory on SID table init\n");
- goto out;
+ return rc;
}
head = p->ocontexts[OCON_ISID];
if (sid == SECSID_NULL) {
pr_err("SELinux: SID 0 was assigned a context.\n");
sidtab_destroy(s);
- goto out;
+ return -EINVAL;
}
/* Ignore initial SIDs unused by this kernel. */
pr_err("SELinux: unable to load initial SID %s.\n",
name);
sidtab_destroy(s);
- goto out;
+ return rc;
}
}
- rc = 0;
-out:
- return rc;
+ return 0;
}
int policydb_class_isvalid(struct policydb *p, unsigned int class)
struct vm_area_struct *area)
{
return remap_pfn_range(area, area->vm_start,
- dmab->addr >> PAGE_SHIFT,
+ page_to_pfn(virt_to_page(dmab->area)),
area->vm_end - area->vm_start,
area->vm_page_prot);
}
if (!(substream->runtime->hw.info & SNDRV_PCM_INFO_MMAP))
return false;
- if (substream->ops->mmap ||
- (substream->dma_buffer.dev.type != SNDRV_DMA_TYPE_DEV &&
- substream->dma_buffer.dev.type != SNDRV_DMA_TYPE_DEV_UC))
+ if (substream->ops->mmap || substream->ops->page)
return true;
- return dma_can_mmap(substream->dma_buffer.dev.dev);
+ switch (substream->dma_buffer.dev.type) {
+ case SNDRV_DMA_TYPE_UNKNOWN:
+ return false;
+ case SNDRV_DMA_TYPE_CONTINUOUS:
+ case SNDRV_DMA_TYPE_VMALLOC:
+ return true;
+ default:
+ return dma_can_mmap(substream->dma_buffer.dev.dev);
+ }
}
static int constrain_mask_params(struct snd_pcm_substream *substream,
boundary = 0x7fffffff;
snd_pcm_stream_lock_irq(substream);
/* FIXME: we should consider the boundary for the sync from app */
- if (!(sflags & SNDRV_PCM_SYNC_PTR_APPL))
- control->appl_ptr = scontrol.appl_ptr;
- else
+ if (!(sflags & SNDRV_PCM_SYNC_PTR_APPL)) {
+ err = pcm_lib_apply_appl_ptr(substream,
+ scontrol.appl_ptr);
+ if (err < 0) {
+ snd_pcm_stream_unlock_irq(substream);
+ return err;
+ }
+ } else
scontrol.appl_ptr = control->appl_ptr % boundary;
if (!(sflags & SNDRV_PCM_SYNC_PTR_AVAIL_MIN))
control->avail_min = scontrol.avail_min;
return VM_FAULT_SIGBUS;
if (substream->ops->page)
page = substream->ops->page(substream, offset);
+ else if (!snd_pcm_get_dma_buf(substream))
+ page = virt_to_page(runtime->dma_area + offset);
else
page = snd_sgbuf_get_page(snd_pcm_get_dma_buf(substream), offset);
if (!page)
return err;
}
-static void delete_and_unsubscribe_port(struct snd_seq_client *client,
- struct snd_seq_client_port *port,
- struct snd_seq_subscribers *subs,
- bool is_src, bool ack)
+/* called with grp->list_mutex held */
+static void __delete_and_unsubscribe_port(struct snd_seq_client *client,
+ struct snd_seq_client_port *port,
+ struct snd_seq_subscribers *subs,
+ bool is_src, bool ack)
{
struct snd_seq_port_subs_info *grp;
struct list_head *list;
grp = is_src ? &port->c_src : &port->c_dest;
list = is_src ? &subs->src_list : &subs->dest_list;
- down_write(&grp->list_mutex);
write_lock_irq(&grp->list_lock);
empty = list_empty(list);
if (!empty)
if (!empty)
unsubscribe_port(client, port, grp, &subs->info, ack);
+}
+
+static void delete_and_unsubscribe_port(struct snd_seq_client *client,
+ struct snd_seq_client_port *port,
+ struct snd_seq_subscribers *subs,
+ bool is_src, bool ack)
+{
+ struct snd_seq_port_subs_info *grp;
+
+ grp = is_src ? &port->c_src : &port->c_dest;
+ down_write(&grp->list_mutex);
+ __delete_and_unsubscribe_port(client, port, subs, is_src, ack);
up_write(&grp->list_mutex);
}
struct snd_seq_client_port *dest_port,
struct snd_seq_port_subscribe *info)
{
- struct snd_seq_port_subs_info *src = &src_port->c_src;
+ struct snd_seq_port_subs_info *dest = &dest_port->c_dest;
struct snd_seq_subscribers *subs;
int err = -ENOENT;
- down_write(&src->list_mutex);
+ /* always start from deleting the dest port for avoiding concurrent
+ * deletions
+ */
+ down_write(&dest->list_mutex);
/* look for the connection */
- list_for_each_entry(subs, &src->list_head, src_list) {
+ list_for_each_entry(subs, &dest->list_head, dest_list) {
if (match_subs_info(info, &subs->info)) {
- atomic_dec(&subs->ref_count); /* mark as not ready */
+ __delete_and_unsubscribe_port(dest_client, dest_port,
+ subs, false,
+ connector->number != dest_client->number);
err = 0;
break;
}
}
- up_write(&src->list_mutex);
+ up_write(&dest->list_mutex);
if (err < 0)
return err;
delete_and_unsubscribe_port(src_client, src_port, subs, true,
connector->number != src_client->number);
- delete_and_unsubscribe_port(dest_client, dest_port, subs, false,
- connector->number != dest_client->number);
kfree(subs);
return 0;
}
.flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC,
.device = 0x4b55,
},
+ {
+ .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC,
+ .device = 0x4b58,
+ },
#endif
/* Alder Lake */
mixR = snd_sbmixer_read(p->chip, SB_DSP4_PCM_DEV + 1);
snd_sbmixer_write(p->chip, SB_DSP4_PCM_DEV, mixL & 0x7);
snd_sbmixer_write(p->chip, SB_DSP4_PCM_DEV + 1, mixR & 0x7);
+ spin_unlock_irqrestore(&p->chip->mixer_lock, flags);
spin_lock(&p->chip->reg_lock);
set_mode_register(p->chip, 0xc0); /* c0 = STOP */
spin_unlock(&p->chip->reg_lock);
/* restore PCM volume */
+ spin_lock_irqsave(&p->chip->mixer_lock, flags);
snd_sbmixer_write(p->chip, SB_DSP4_PCM_DEV, mixL);
snd_sbmixer_write(p->chip, SB_DSP4_PCM_DEV + 1, mixR);
spin_unlock_irqrestore(&p->chip->mixer_lock, flags);
mixR = snd_sbmixer_read(p->chip, SB_DSP4_PCM_DEV + 1);
snd_sbmixer_write(p->chip, SB_DSP4_PCM_DEV, mixL & 0x7);
snd_sbmixer_write(p->chip, SB_DSP4_PCM_DEV + 1, mixR & 0x7);
+ spin_unlock_irqrestore(&p->chip->mixer_lock, flags);
spin_lock(&p->chip->reg_lock);
if (p->running & SNDRV_SB_CSP_ST_QSOUND) {
spin_unlock(&p->chip->reg_lock);
/* restore PCM volume */
+ spin_lock_irqsave(&p->chip->mixer_lock, flags);
snd_sbmixer_write(p->chip, SB_DSP4_PCM_DEV, mixL);
snd_sbmixer_write(p->chip, SB_DSP4_PCM_DEV + 1, mixR);
spin_unlock_irqrestore(&p->chip->mixer_lock, flags);
static const struct snd_pci_quirk force_connect_list[] = {
SND_PCI_QUIRK(0x103c, 0x870f, "HP", 1),
SND_PCI_QUIRK(0x103c, 0x871a, "HP", 1),
+ SND_PCI_QUIRK(0x1462, 0xec94, "MS-7C94", 1),
+ SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", 1),
{}
};
SND_PCI_QUIRK(0x1025, 0x1290, "Acer Veriton Z4860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
SND_PCI_QUIRK(0x1025, 0x1291, "Acer Veriton Z4660G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
SND_PCI_QUIRK(0x1025, 0x129c, "Acer SWIFT SF314-55", ALC256_FIXUP_ACER_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1025, 0x1300, "Acer SWIFT SF314-56", ALC256_FIXUP_ACER_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1025, 0x1308, "Acer Aspire Z24-890", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
SND_PCI_QUIRK(0x1025, 0x132a, "Acer TravelMate B114-21", ALC233_FIXUP_ACER_HEADSET_MIC),
SND_PCI_QUIRK(0x1025, 0x1330, "Acer TravelMate X514-51T", ALC255_FIXUP_ACER_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1025, 0x142b, "Acer Swift SF314-42", ALC255_FIXUP_ACER_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1025, 0x1430, "Acer TravelMate B311R-31", ALC256_FIXUP_ACER_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1025, 0x1466, "Acer Aspire A515-56", ALC255_FIXUP_ACER_HEADPHONE_AND_MIC),
SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z),
SND_PCI_QUIRK(0x17aa, 0x3151, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x17aa, 0x3176, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x17aa, 0x3178, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
+ SND_PCI_QUIRK(0x17aa, 0x31af, "ThinkCentre Station", ALC623_FIXUP_LENOVO_THINKSTATION_P340),
SND_PCI_QUIRK(0x17aa, 0x3818, "Lenovo C940", ALC298_FIXUP_LENOVO_SPK_VOLUME),
SND_PCI_QUIRK(0x17aa, 0x3827, "Ideapad S740", ALC285_FIXUP_IDEAPAD_S740_COEF),
SND_PCI_QUIRK(0x17aa, 0x3843, "Yoga 9i", ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP),
| SND_SOC_DAIFMT_CBM_CFM,
.init = cz_rt5682_init,
.dpcm_playback = 1,
+ .stop_dma_first = 1,
.ops = &cz_rt5682_play_ops,
SND_SOC_DAILINK_REG(designware1, rt5682, platform),
},
.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF
| SND_SOC_DAIFMT_CBM_CFM,
.dpcm_capture = 1,
+ .stop_dma_first = 1,
.ops = &cz_rt5682_cap_ops,
SND_SOC_DAILINK_REG(designware2, rt5682, platform),
},
.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF
| SND_SOC_DAIFMT_CBM_CFM,
.dpcm_playback = 1,
+ .stop_dma_first = 1,
.ops = &cz_rt5682_max_play_ops,
SND_SOC_DAILINK_REG(designware3, mx, platform),
},
.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF
| SND_SOC_DAIFMT_CBM_CFM,
.dpcm_capture = 1,
+ .stop_dma_first = 1,
.ops = &cz_rt5682_dmic0_cap_ops,
SND_SOC_DAILINK_REG(designware3, adau, platform),
},
.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF
| SND_SOC_DAIFMT_CBM_CFM,
.dpcm_capture = 1,
+ .stop_dma_first = 1,
.ops = &cz_rt5682_dmic1_cap_ops,
SND_SOC_DAILINK_REG(designware2, adau, platform),
},
high-efficiency mono Class-D audio power amplifiers.
config SND_SOC_SSM2518
- tristate
+ tristate "Analog Devices SSM2518 Class-D Amplifier"
depends on I2C
config SND_SOC_SSM2602
Qualcomm SoCs like SDM845.
config SND_SOC_WCD938X
+ depends on SND_SOC_WCD938X_SDW
tristate
config SND_SOC_WCD938X_SDW
which consists of a Digital Signal Processor (DSP), several Digital
Audio Interfaces (DAIs), analog outputs, and a block of 14 GPIOs.
-config SND_SOC_ZX_AUD96P22
- tristate "ZTE ZX AUD96P22 CODEC"
- depends on I2C
- select REGMAP_I2C
-
# Amp
config SND_SOC_LM4857
tristate
.reg_defaults = rt5631_reg,
.num_reg_defaults = ARRAY_SIZE(rt5631_reg),
.cache_type = REGCACHE_RBTREE,
+ .use_single_read = true,
+ .use_single_write = true,
};
static int rt5631_i2c_probe(struct i2c_client *i2c,
rt5682_enable_push_button_irq(component, false);
snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1,
RT5682_TRIG_JD_MASK, RT5682_TRIG_JD_LOW);
- if (!snd_soc_dapm_get_pin_status(dapm, "MICBIAS"))
+ if (!snd_soc_dapm_get_pin_status(dapm, "MICBIAS") &&
+ !snd_soc_dapm_get_pin_status(dapm, "PLL1") &&
+ !snd_soc_dapm_get_pin_status(dapm, "PLL2B"))
snd_soc_component_update_bits(component,
RT5682_PWR_ANLG_1, RT5682_PWR_MB, 0);
- if (!snd_soc_dapm_get_pin_status(dapm, "Vref2"))
+ if (!snd_soc_dapm_get_pin_status(dapm, "Vref2") &&
+ !snd_soc_dapm_get_pin_status(dapm, "PLL1") &&
+ !snd_soc_dapm_get_pin_status(dapm, "PLL2B"))
snd_soc_component_update_bits(component,
RT5682_PWR_ANLG_1, RT5682_PWR_VREF2, 0);
snd_soc_component_update_bits(component, RT5682_PWR_ANLG_3,
ret);
return ret;
}
+ regcache_cache_only(aic31xx->regmap, true);
+
aic31xx->dev = &i2c->dev;
aic31xx->irq = i2c->irq;
#define AIC31XX_WORD_LEN_24BITS 0x02
#define AIC31XX_WORD_LEN_32BITS 0x03
#define AIC31XX_IFACE1_MASTER_MASK GENMASK(3, 2)
-#define AIC31XX_BCLK_MASTER BIT(2)
-#define AIC31XX_WCLK_MASTER BIT(3)
+#define AIC31XX_BCLK_MASTER BIT(3)
+#define AIC31XX_WCLK_MASTER BIT(2)
/* AIC31XX_DATA_OFFSET */
#define AIC31XX_DATA_OFFSET_MASK GENMASK(7, 0)
static DECLARE_TLV_DB_SCALE(tlv_driver_gain, -600, 100, 0);
/* -12dB min, 0.5dB steps */
static DECLARE_TLV_DB_SCALE(tlv_adc_vol, -1200, 50, 0);
-
-static DECLARE_TLV_DB_LINEAR(tlv_spk_vol, TLV_DB_GAIN_MUTE, 0);
+/* -6dB min, 1dB steps */
+static DECLARE_TLV_DB_SCALE(tlv_tas_driver_gain, -5850, 50, 0);
static DECLARE_TLV_DB_SCALE(tlv_amp_vol, 0, 600, 1);
static const char * const lo_cm_text[] = {
};
static const struct snd_kcontrol_new aic32x4_tas2505_snd_controls[] = {
- SOC_DOUBLE_R_S_TLV("PCM Playback Volume", AIC32X4_LDACVOL,
- AIC32X4_LDACVOL, 0, -0x7f, 0x30, 7, 0, tlv_pcm),
+ SOC_SINGLE_S8_TLV("PCM Playback Volume",
+ AIC32X4_LDACVOL, -0x7f, 0x30, tlv_pcm),
SOC_ENUM("DAC Playback PowerTune Switch", l_ptm_enum),
- SOC_DOUBLE_R_S_TLV("HP Driver Playback Volume", AIC32X4_HPLGAIN,
- AIC32X4_HPLGAIN, 0, -0x6, 0x1d, 5, 0,
- tlv_driver_gain),
- SOC_DOUBLE_R("HP DAC Playback Switch", AIC32X4_HPLGAIN,
- AIC32X4_HPLGAIN, 6, 0x01, 1),
- SOC_SINGLE("Auto-mute Switch", AIC32X4_DACMUTE, 4, 7, 0),
+ SOC_SINGLE_TLV("HP Driver Gain Volume",
+ AIC32X4_HPLGAIN, 0, 0x74, 1, tlv_tas_driver_gain),
+ SOC_SINGLE("HP DAC Playback Switch", AIC32X4_HPLGAIN, 6, 1, 1),
- SOC_SINGLE_RANGE_TLV("Speaker Driver Playback Volume", TAS2505_SPKVOL1,
- 0, 0, 117, 1, tlv_spk_vol),
- SOC_SINGLE_TLV("Speaker Amplifier Playback Volume", TAS2505_SPKVOL2,
- 4, 5, 0, tlv_amp_vol),
+ SOC_SINGLE_TLV("Speaker Driver Playback Volume",
+ TAS2505_SPKVOL1, 0, 0x74, 1, tlv_tas_driver_gain),
+ SOC_SINGLE_TLV("Speaker Amplifier Playback Volume",
+ TAS2505_SPKVOL2, 4, 5, 0, tlv_amp_vol),
+
+ SOC_SINGLE("Auto-mute Switch", AIC32X4_DACMUTE, 4, 7, 0),
};
static const struct snd_kcontrol_new hp_output_mixer_controls[] = {
(WCD938X_DIGITAL_INTR_LEVEL_0 + i), 0);
}
- ret = wcd938x_irq_init(wcd938x, component->dev);
- if (ret) {
- dev_err(component->dev, "%s: IRQ init failed: %d\n",
- __func__, ret);
- return ret;
- }
-
wcd938x->hphr_pdm_wd_int = regmap_irq_get_virq(wcd938x->irq_chip,
WCD938X_IRQ_HPHR_PDM_WD_INT);
wcd938x->hphl_pdm_wd_int = regmap_irq_get_virq(wcd938x->irq_chip,
}
wcd938x->sdw_priv[AIF1_PB] = dev_get_drvdata(wcd938x->rxdev);
wcd938x->sdw_priv[AIF1_PB]->wcd938x = wcd938x;
- wcd938x->sdw_priv[AIF1_PB]->slave_irq = wcd938x->virq;
wcd938x->txdev = wcd938x_sdw_device_get(wcd938x->txnode);
if (!wcd938x->txdev) {
}
wcd938x->sdw_priv[AIF1_CAP] = dev_get_drvdata(wcd938x->txdev);
wcd938x->sdw_priv[AIF1_CAP]->wcd938x = wcd938x;
- wcd938x->sdw_priv[AIF1_CAP]->slave_irq = wcd938x->virq;
wcd938x->tx_sdw_dev = dev_to_sdw_dev(wcd938x->txdev);
if (!wcd938x->tx_sdw_dev) {
dev_err(dev, "could not get txslave with matching of dev\n");
return PTR_ERR(wcd938x->regmap);
}
+ ret = wcd938x_irq_init(wcd938x, dev);
+ if (ret) {
+ dev_err(dev, "%s: IRQ init failed: %d\n", __func__, ret);
+ return ret;
+ }
+
+ wcd938x->sdw_priv[AIF1_PB]->slave_irq = wcd938x->virq;
+ wcd938x->sdw_priv[AIF1_CAP]->slave_irq = wcd938x->virq;
+
ret = wcd938x_set_micbias_data(wcd938x);
if (ret < 0) {
dev_err(dev, "%s: bad micbias pdata\n", __func__);
/*
* HALO_CCM_CORE_CONTROL
*/
+#define HALO_CORE_RESET 0x00000200
#define HALO_CORE_EN 0x00000001
/*
mutex_lock(&ctl->dsp->pwr_lock);
- ret = wm_coeff_read_ctrl_raw(ctl, ctl->cache, size);
+ ret = wm_coeff_read_ctrl(ctl, ctl->cache, size);
if (!ret && copy_to_user(bytes, ctl->cache, size))
ret = -EFAULT;
{
return regmap_update_bits(dsp->regmap,
dsp->base + HALO_CCM_CORE_CONTROL,
- HALO_CORE_EN, HALO_CORE_EN);
+ HALO_CORE_RESET | HALO_CORE_EN,
+ HALO_CORE_RESET | HALO_CORE_EN);
}
static void wm_halo_stop_core(struct wm_adsp *dsp)
return ret;
}
-static int max98373_sdw_trigger(struct snd_pcm_substream *substream, int cmd)
+static int mx8373_enable_spk_pin(struct snd_pcm_substream *substream, bool enable)
{
+ struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream);
+ struct snd_soc_dai *codec_dai;
+ struct snd_soc_dai *cpu_dai;
int ret;
+ int j;
- switch (cmd) {
- case SNDRV_PCM_TRIGGER_START:
- case SNDRV_PCM_TRIGGER_RESUME:
- case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
- /* enable max98373 first */
- ret = max_98373_trigger(substream, cmd);
- if (ret < 0)
- break;
-
- ret = sdw_trigger(substream, cmd);
- break;
- case SNDRV_PCM_TRIGGER_STOP:
- case SNDRV_PCM_TRIGGER_SUSPEND:
- case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
- ret = sdw_trigger(substream, cmd);
- if (ret < 0)
- break;
-
- ret = max_98373_trigger(substream, cmd);
- break;
- default:
- ret = -EINVAL;
- break;
+ /* set spk pin by playback only */
+ if (substream->stream == SNDRV_PCM_STREAM_CAPTURE)
+ return 0;
+
+ cpu_dai = asoc_rtd_to_cpu(rtd, 0);
+ for_each_rtd_codec_dais(rtd, j, codec_dai) {
+ struct snd_soc_dapm_context *dapm =
+ snd_soc_component_get_dapm(cpu_dai->component);
+ char pin_name[16];
+
+ snprintf(pin_name, ARRAY_SIZE(pin_name), "%s Spk",
+ codec_dai->component->name_prefix);
+
+ if (enable)
+ ret = snd_soc_dapm_enable_pin(dapm, pin_name);
+ else
+ ret = snd_soc_dapm_disable_pin(dapm, pin_name);
+
+ if (!ret)
+ snd_soc_dapm_sync(dapm);
}
- return ret;
+ return 0;
+}
+
+static int mx8373_sdw_prepare(struct snd_pcm_substream *substream)
+{
+ int ret = 0;
+
+ /* according to soc_pcm_prepare dai link prepare is called first */
+ ret = sdw_prepare(substream);
+ if (ret < 0)
+ return ret;
+
+ return mx8373_enable_spk_pin(substream, true);
+}
+
+static int mx8373_sdw_hw_free(struct snd_pcm_substream *substream)
+{
+ int ret = 0;
+
+ /* according to soc_pcm_hw_free dai link free is called first */
+ ret = sdw_hw_free(substream);
+ if (ret < 0)
+ return ret;
+
+ return mx8373_enable_spk_pin(substream, false);
}
static const struct snd_soc_ops max_98373_sdw_ops = {
.startup = sdw_startup,
- .prepare = sdw_prepare,
- .trigger = max98373_sdw_trigger,
- .hw_free = sdw_hw_free,
+ .prepare = mx8373_sdw_prepare,
+ .trigger = sdw_trigger,
+ .hw_free = mx8373_sdw_hw_free,
.shutdown = sdw_shutdown,
};
case MT8183_MTKAIF_PROTOCOL_1:
regmap_write(afe->regmap, AFE_AUD_PAD_TOP, 0x31);
regmap_write(afe->regmap, AFE_ADDA_MTKAIF_CFG0, 0x0);
+ break;
default:
break;
}
static int soc_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
{
+ struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream);
int ret = -EINVAL, _ret = 0;
int rollback = 0;
case SNDRV_PCM_TRIGGER_STOP:
case SNDRV_PCM_TRIGGER_SUSPEND:
case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
- ret = snd_soc_pcm_dai_trigger(substream, cmd, rollback);
- if (ret < 0)
- break;
+ if (rtd->dai_link->stop_dma_first) {
+ ret = snd_soc_pcm_component_trigger(substream, cmd, rollback);
+ if (ret < 0)
+ break;
- ret = snd_soc_pcm_component_trigger(substream, cmd, rollback);
- if (ret < 0)
- break;
+ ret = snd_soc_pcm_dai_trigger(substream, cmd, rollback);
+ if (ret < 0)
+ break;
+ } else {
+ ret = snd_soc_pcm_dai_trigger(substream, cmd, rollback);
+ if (ret < 0)
+ break;
+ ret = snd_soc_pcm_component_trigger(substream, cmd, rollback);
+ if (ret < 0)
+ break;
+ }
ret = snd_soc_link_trigger(substream, cmd, rollback);
break;
}
static const struct sof_dev_desc adl_desc = {
.machines = snd_soc_acpi_intel_adl_machines,
.alt_machines = snd_soc_acpi_intel_adl_sdw_machines,
+ .use_acpi_target_states = true,
.resindex_lpe_base = 0,
.resindex_pcicfg_base = -1,
.resindex_imr_base = -1,
}
EXPORT_SYMBOL_GPL(tegra_pcm_pointer);
-static int tegra_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, int stream,
+static int tegra_pcm_preallocate_dma_buffer(struct device *dev, struct snd_pcm *pcm, int stream,
size_t size)
{
struct snd_pcm_substream *substream = pcm->streams[stream].substream;
struct snd_dma_buffer *buf = &substream->dma_buffer;
- buf->area = dma_alloc_wc(pcm->card->dev, size, &buf->addr, GFP_KERNEL);
+ buf->area = dma_alloc_wc(dev, size, &buf->addr, GFP_KERNEL);
if (!buf->area)
return -ENOMEM;
buf->private_data = NULL;
buf->dev.type = SNDRV_DMA_TYPE_DEV;
- buf->dev.dev = pcm->card->dev;
+ buf->dev.dev = dev;
buf->bytes = size;
return 0;
if (!buf->area)
return;
- dma_free_wc(pcm->card->dev, buf->bytes, buf->area, buf->addr);
+ dma_free_wc(buf->dev.dev, buf->bytes, buf->area, buf->addr);
buf->area = NULL;
}
-static int tegra_pcm_dma_allocate(struct snd_soc_pcm_runtime *rtd,
+static int tegra_pcm_dma_allocate(struct device *dev, struct snd_soc_pcm_runtime *rtd,
size_t size)
{
- struct snd_card *card = rtd->card->snd_card;
struct snd_pcm *pcm = rtd->pcm;
int ret;
- ret = dma_set_mask_and_coherent(card->dev, DMA_BIT_MASK(32));
+ ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
if (ret < 0)
return ret;
if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) {
- ret = tegra_pcm_preallocate_dma_buffer(pcm,
- SNDRV_PCM_STREAM_PLAYBACK, size);
+ ret = tegra_pcm_preallocate_dma_buffer(dev, pcm, SNDRV_PCM_STREAM_PLAYBACK, size);
if (ret)
goto err;
}
if (pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream) {
- ret = tegra_pcm_preallocate_dma_buffer(pcm,
- SNDRV_PCM_STREAM_CAPTURE, size);
+ ret = tegra_pcm_preallocate_dma_buffer(dev, pcm, SNDRV_PCM_STREAM_CAPTURE, size);
if (ret)
goto err_free_play;
}
int tegra_pcm_construct(struct snd_soc_component *component,
struct snd_soc_pcm_runtime *rtd)
{
- return tegra_pcm_dma_allocate(rtd, tegra_pcm_hardware.buffer_bytes_max);
+ struct device *dev = component->dev;
+
+ /*
+ * Fallback for backwards-compatibility with older device trees that
+ * have the iommus property in the virtual, top-level "sound" node.
+ */
+ if (!of_get_property(dev->of_node, "iommus", NULL))
+ dev = rtd->card->snd_card->dev;
+
+ return tegra_pcm_dma_allocate(dev, rtd, tegra_pcm_hardware.buffer_bytes_max);
}
EXPORT_SYMBOL_GPL(tegra_pcm_construct);
return ret;
}
- if (priv->hsdiv_rates[domain->parent_clk_id] != scki) {
+ if (domain->parent_clk_id == -1 || priv->hsdiv_rates[domain->parent_clk_id] != scki) {
dev_dbg(priv->dev,
"%s configuration for %u Hz: %s, %dxFS (SCKI: %u Hz)\n",
audio_domain == J721E_AUDIO_DOMAIN_CPB ? "CPB" : "IVI",
j721e_rule_rate, &priv->rate_range,
SNDRV_PCM_HW_PARAM_RATE, -1);
- mutex_unlock(&priv->mutex);
if (ret)
- return ret;
+ goto out;
/* Reset TDM slots to 32 */
ret = snd_soc_dai_set_tdm_slot(cpu_dai, 0x3, 0x3, 2, 32);
if (ret && ret != -ENOTSUPP)
- return ret;
+ goto out;
for_each_rtd_codec_dais(rtd, i, codec_dai) {
ret = snd_soc_dai_set_tdm_slot(codec_dai, 0x3, 0x3, 2, 32);
if (ret && ret != -ENOTSUPP)
- return ret;
+ goto out;
}
- return 0;
+ if (ret == -ENOTSUPP)
+ ret = 0;
+out:
+ if (ret)
+ domain->active--;
+ mutex_unlock(&priv->mutex);
+
+ return ret;
}
static int j721e_audio_hw_params(struct snd_pcm_substream *substream,
}
}
- if (chip->quirk_type & QUIRK_SETUP_DISABLE_AUTOSUSPEND)
+ if (chip->quirk_type == QUIRK_SETUP_DISABLE_AUTOSUSPEND)
usb_enable_autosuspend(interface_to_usbdev(intf));
chip->num_interfaces--;
sources[ret - 1],
visited, validate);
if (ret > 0) {
+ /*
+ * For Samsung USBC Headset (AKG), setting clock selector again
+ * will result in incorrect default clock setting problems
+ */
+ if (chip->usb_id == USB_ID(0x04e8, 0xa051))
+ return ret;
err = uac_clock_selector_set_val(chip, entity_id, cur);
if (err < 0)
return err;
strlcat(name, " - Output Jack", name_size);
}
+/* get connector value to "wake up" the USB audio */
+static int connector_mixer_resume(struct usb_mixer_elem_list *list)
+{
+ struct usb_mixer_elem_info *cval = mixer_elem_list_to_info(list);
+
+ get_connector_value(cval, NULL, NULL);
+ return 0;
+}
+
/* Build a mixer control for a UAC connector control (jack-detect) */
static void build_connector_control(struct usb_mixer_interface *mixer,
const struct usbmix_name_map *imap,
if (!cval)
return;
snd_usb_mixer_elem_init_std(&cval->head, mixer, term->id);
+
+ /* set up a specific resume callback */
+ cval->head.resume = connector_mixer_resume;
+
/*
* UAC2: The first byte from reading the UAC2_TE_CONNECTOR control returns the
* number of channels connected.
{
struct usb_mixer_elem_info *cval = mixer_elem_list_to_info(list);
static const char * const val_types[] = {
- "BOOLEAN", "INV_BOOLEAN", "S8", "U8", "S16", "U16", "S32", "U32",
+ [USB_MIXER_BOOLEAN] = "BOOLEAN",
+ [USB_MIXER_INV_BOOLEAN] = "INV_BOOLEAN",
+ [USB_MIXER_S8] = "S8",
+ [USB_MIXER_U8] = "U8",
+ [USB_MIXER_S16] = "S16",
+ [USB_MIXER_U16] = "U16",
+ [USB_MIXER_S32] = "S32",
+ [USB_MIXER_U32] = "U32",
+ [USB_MIXER_BESPOKEN] = "BESPOKEN",
};
snd_iprintf(buffer, " Info: id=%i, control=%i, cmask=0x%x, "
"channels=%i, type=\"%s\"\n", cval->head.id,
return 0;
}
-static int default_mixer_resume(struct usb_mixer_elem_list *list)
-{
- struct usb_mixer_elem_info *cval = mixer_elem_list_to_info(list);
-
- /* get connector value to "wake up" the USB audio */
- if (cval->val_type == USB_MIXER_BOOLEAN && cval->channels == 1)
- get_connector_value(cval, NULL, NULL);
-
- return 0;
-}
-
static int default_mixer_reset_resume(struct usb_mixer_elem_list *list)
{
- int err = default_mixer_resume(list);
+ int err;
- if (err < 0)
- return err;
+ if (list->resume) {
+ err = list->resume(list);
+ if (err < 0)
+ return err;
+ }
return restore_mixer_value(list);
}
list->id = unitid;
list->dump = snd_usb_mixer_dump_cval;
#ifdef CONFIG_PM
- list->resume = default_mixer_resume;
+ list->resume = NULL;
list->reset_resume = default_mixer_reset_resume;
#endif
}
};
static const char *const scarlett2_dim_mute_names[SCARLETT2_DIM_MUTE_COUNT] = {
- "Mute", "Dim"
+ "Mute Playback Switch", "Dim Playback Switch"
};
/* Description of each hardware port type:
struct snd_ctl_elem_value *ucontrol)
{
struct usb_mixer_elem_info *elem = kctl->private_data;
- struct scarlett2_data *private = elem->head.mixer->private_data;
+ struct usb_mixer_interface *mixer = elem->head.mixer;
+ struct scarlett2_data *private = mixer->private_data;
int index = line_out_remap(private, elem->control);
+ mutex_lock(&private->data_mutex);
+ if (private->vol_updated)
+ scarlett2_update_volumes(mixer);
+ mutex_unlock(&private->data_mutex);
+
ucontrol->value.integer.value[0] = private->mute_switch[index];
return 0;
}
~SNDRV_CTL_ELEM_ACCESS_WRITE;
}
- /* Notify of write bit change */
- snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_INFO,
+ /* Notify of write bit and possible value change */
+ snd_ctl_notify(card,
+ SNDRV_CTL_EVENT_MASK_VALUE | SNDRV_CTL_EVENT_MASK_INFO,
&private->vol_ctls[index]->id);
- snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_INFO,
+ snd_ctl_notify(card,
+ SNDRV_CTL_EVENT_MASK_VALUE | SNDRV_CTL_EVENT_MASK_INFO,
&private->mute_ctls[index]->id);
}
{
struct scarlett2_data *private = mixer->private_data;
const struct scarlett2_device_info *info = private->info;
+ const char *s;
if (!info->direct_monitor)
return 0;
+ s = info->direct_monitor == 1
+ ? "Direct Monitor Playback Switch"
+ : "Direct Monitor Playback Enum";
+
return scarlett2_add_new_ctl(
mixer, &scarlett2_direct_monitor_ctl[info->direct_monitor - 1],
- 0, 1, "Direct Monitor Playback Switch",
- &private->direct_monitor_ctl);
+ 0, 1, s, &private->direct_monitor_ctl);
}
/*** Speaker Switching Control ***/
/* disable the line out SW/HW switch */
scarlett2_sw_hw_ctl_ro(private, i);
- snd_ctl_notify(card, SNDRV_CTL_EVENT_MASK_INFO,
+ snd_ctl_notify(card,
+ SNDRV_CTL_EVENT_MASK_VALUE |
+ SNDRV_CTL_EVENT_MASK_INFO,
&private->sw_hw_ctls[i]->id);
}
if (private->vol_sw_hw_switch[line_index]) {
private->mute_switch[line_index] = val;
snd_ctl_notify(mixer->chip->card,
- SNDRV_CTL_EVENT_MASK_INFO,
+ SNDRV_CTL_EVENT_MASK_VALUE,
&private->mute_ctls[i]->id);
}
}
/* Add MSD control */
return scarlett2_add_new_ctl(mixer, &scarlett2_msd_ctl,
- 0, 1, "MSD Mode", NULL);
+ 0, 1, "MSD Mode Switch", NULL);
}
/*** Cleanup/Suspend Callbacks ***/
REG_QUIRK_ENTRY(0x0951, 0x16d8, 2), /* Kingston HyperX AMP */
REG_QUIRK_ENTRY(0x0951, 0x16ed, 2), /* Kingston HyperX Cloud Alpha S */
REG_QUIRK_ENTRY(0x0951, 0x16ea, 2), /* Kingston HyperX Cloud Flight S */
+ REG_QUIRK_ENTRY(0x0ecb, 0x1f46, 2), /* JBL Quantum 600 */
+ REG_QUIRK_ENTRY(0x0ecb, 0x2039, 2), /* JBL Quantum 400 */
+ REG_QUIRK_ENTRY(0x0ecb, 0x203c, 2), /* JBL Quantum 600 */
+ REG_QUIRK_ENTRY(0x0ecb, 0x203e, 2), /* JBL Quantum 800 */
{ 0 } /* terminator */
};
#define __ARCH_WANT_SET_GET_RLIMIT
#define __ARCH_WANT_TIME32_SYSCALLS
#define __ARCH_WANT_SYS_CLONE3
+#define __ARCH_WANT_MEMFD_SECRET
#include <asm-generic/unistd.h>
$(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpf
$(Q)$(RM) -r -- $(OUTPUT)feature
-install: $(PROGS) bpftool_install runqslower_install
+install: $(PROGS) bpftool_install
$(call QUIET_INSTALL, bpf_jit_disasm)
$(Q)$(INSTALL) -m 0755 -d $(DESTDIR)$(prefix)/bin
$(Q)$(INSTALL) $(OUTPUT)bpf_jit_disasm $(DESTDIR)$(prefix)/bin/bpf_jit_disasm
runqslower:
$(call descend,runqslower)
-runqslower_install:
- $(call descend,runqslower,install)
-
runqslower_clean:
$(call descend,runqslower,clean)
$(call descend,resolve_btfids,clean)
.PHONY: all install clean bpftool bpftool_install bpftool_clean \
- runqslower runqslower_install runqslower_clean \
+ runqslower runqslower_clean \
resolve_btfids resolve_btfids_clean
int err = 0;
file = malloc(strlen(name) + 1);
+ if (!file) {
+ p_err("mem alloc failed");
+ return -1;
+ }
+
strcpy(file, name);
dir = dirname(file);
{
va_list ap;
char *s;
+ int err;
va_start(ap, fmt);
- if (vasprintf(&s, fmt, ap) < 0)
- return -1;
+ err = vasprintf(&s, fmt, ap);
va_end(ap);
+ if (err < 0)
+ return -1;
if (!oper_count) {
int i;
u32 pid;
/* ivcsw: treat like an enqueue event and store timestamp */
- if (prev->state == TASK_RUNNING)
+ if (prev->__state == TASK_RUNNING)
trace_enqueue(prev);
pid = next->pid;
/* CONFIG_CC_VERSION_TEXT (Do not delete this comment. See help in Kconfig) */
-#ifdef CONFIG_CPU_BIG_ENDIAN
-#define __BIG_ENDIAN 4321
-#else
-#define __LITTLE_ENDIAN 1234
-#endif
-
#define __ARG_PLACEHOLDER_1 0,
#define __take_second_arg(__ignored, val, ...) val
#define __NR_landlock_restrict_self 446
__SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self)
+#ifdef __ARCH_WANT_MEMFD_SECRET
+#define __NR_memfd_secret 447
+__SYSCALL(__NR_memfd_secret, sys_memfd_secret)
+#endif
+
#undef __NR_syscalls
-#define __NR_syscalls 447
+#define __NR_syscalls 448
/*
* 32 bit systems traditionally used different
err = unlink(link->pin_path);
if (err != 0)
- return libbpf_err_errno(err);
+ return -errno;
pr_debug("link fd=%d: unpinned from %s\n", link->fd, link->pin_path);
zfree(&link->pin_path);
cnt = epoll_wait(pb->epoll_fd, pb->events, pb->cpu_cnt, timeout_ms);
if (cnt < 0)
- return libbpf_err_errno(cnt);
+ return -errno;
for (i = 0; i < cnt; i++) {
struct perf_cpu_buf *cpu_buf = pb->events[i].data.ptr;
444 common landlock_create_ruleset sys_landlock_create_ruleset
445 common landlock_add_rule sys_landlock_add_rule
446 common landlock_restrict_self sys_landlock_restrict_self
+447 common memfd_secret sys_memfd_secret
#
# Due to a historical design error, certain syscalls are numbered differently
dso = machine__findnew_dso_id(machine, filename, id);
}
- if (dso)
+ if (dso) {
+ nsinfo__put(dso->nsinfo);
dso->nsinfo = nsi;
- else
+ } else
nsinfo__put(nsi);
thread__put(thread);
data.path = inject.input_name;
inject.session = perf_session__new(&data, inject.output.is_pipe, &inject.tool);
- if (IS_ERR(inject.session))
- return PTR_ERR(inject.session);
+ if (IS_ERR(inject.session)) {
+ ret = PTR_ERR(inject.session);
+ goto out_close_output;
+ }
if (zstd_init(&(inject.session->zstd_data), 0) < 0)
pr_warning("Decompression initialization failed.\n");
out_delete:
zstd_fini(&(inject.session->zstd_data));
perf_session__delete(inject.session);
+out_close_output:
+ perf_data__close(&inject.output);
free(inject.itrace_synth_opts.vm_tm_corr_args);
return ret;
}
.annotation_opts = annotation__default_options,
.skip_empty = true,
};
+ char *sort_order_help = sort_help("sort by key(s):");
+ char *field_order_help = sort_help("output field(s): overhead period sample ");
const struct option options[] = {
OPT_STRING('i', "input", &input_name, "file",
"input file name"),
OPT_BOOLEAN(0, "header-only", &report.header_only,
"Show only data header."),
OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
- sort_help("sort by key(s):")),
+ sort_order_help),
OPT_STRING('F', "fields", &field_order, "key[,keys...]",
- sort_help("output field(s): overhead period sample ")),
+ field_order_help),
OPT_BOOLEAN(0, "show-cpu-utilization", &symbol_conf.show_cpu_utilization,
"Show sample percentage for different cpu modes"),
OPT_BOOLEAN_FLAG(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
char sort_tmp[128];
if (ret < 0)
- return ret;
+ goto exit;
ret = perf_config(report__config, &report);
if (ret)
- return ret;
+ goto exit;
argc = parse_options(argc, argv, options, report_usage, 0);
if (argc) {
report.symbol_filter_str = argv[0];
}
- if (annotate_check_args(&report.annotation_opts) < 0)
- return -EINVAL;
+ if (annotate_check_args(&report.annotation_opts) < 0) {
+ ret = -EINVAL;
+ goto exit;
+ }
if (report.mmaps_mode)
report.tasks_mode = true;
if (symbol_conf.vmlinux_name &&
access(symbol_conf.vmlinux_name, R_OK)) {
pr_err("Invalid file: %s\n", symbol_conf.vmlinux_name);
- return -EINVAL;
+ ret = -EINVAL;
+ goto exit;
}
if (symbol_conf.kallsyms_name &&
access(symbol_conf.kallsyms_name, R_OK)) {
pr_err("Invalid file: %s\n", symbol_conf.kallsyms_name);
- return -EINVAL;
+ ret = -EINVAL;
+ goto exit;
}
if (report.inverted_callchain)
repeat:
session = perf_session__new(&data, false, &report.tool);
- if (IS_ERR(session))
- return PTR_ERR(session);
+ if (IS_ERR(session)) {
+ ret = PTR_ERR(session);
+ goto exit;
+ }
ret = evswitch__init(&report.evswitch, session->evlist, stderr);
if (ret)
- return ret;
+ goto exit;
if (zstd_init(&(session->zstd_data), 0) < 0)
pr_warning("Decompression initialization failed. Reported data may be incomplete.\n");
zstd_fini(&(session->zstd_data));
perf_session__delete(session);
+exit:
+ free(sort_order_help);
+ free(field_order_help);
return ret;
}
err = pthread_attr_init(&attr);
BUG_ON(err);
err = pthread_attr_setstacksize(&attr,
- (size_t) max(16 * 1024, PTHREAD_STACK_MIN));
+ (size_t) max(16 * 1024, (int)PTHREAD_STACK_MIN));
BUG_ON(err);
err = pthread_mutex_lock(&sched->start_work_mutex);
BUG_ON(err);
sort_dimension__add("pid", &sched->cmp_pid);
}
+static bool schedstat_events_exposed(void)
+{
+ /*
+ * Select "sched:sched_stat_wait" event to check
+ * whether schedstat tracepoints are exposed.
+ */
+ return IS_ERR(trace_event__tp_format("sched", "sched_stat_wait")) ?
+ false : true;
+}
+
static int __cmd_record(int argc, const char **argv)
{
unsigned int rec_argc, i, j;
"-m", "1024",
"-c", "1",
"-e", "sched:sched_switch",
- "-e", "sched:sched_stat_wait",
- "-e", "sched:sched_stat_sleep",
- "-e", "sched:sched_stat_iowait",
"-e", "sched:sched_stat_runtime",
"-e", "sched:sched_process_fork",
"-e", "sched:sched_wakeup_new",
"-e", "sched:sched_migrate_task",
};
+
+ /*
+ * The tracepoints trace_sched_stat_{wait, sleep, iowait}
+ * are not exposed to user if CONFIG_SCHEDSTATS is not set,
+ * to prevent "perf sched record" execution failure, determine
+ * whether to record schedstat events according to actual situation.
+ */
+ const char * const schedstat_args[] = {
+ "-e", "sched:sched_stat_wait",
+ "-e", "sched:sched_stat_sleep",
+ "-e", "sched:sched_stat_iowait",
+ };
+ unsigned int schedstat_argc = schedstat_events_exposed() ?
+ ARRAY_SIZE(schedstat_args) : 0;
+
struct tep_event *waking_event;
/*
* +2 for either "-e", "sched:sched_wakeup" or
* "-e", "sched:sched_waking"
*/
- rec_argc = ARRAY_SIZE(record_args) + 2 + argc - 1;
+ rec_argc = ARRAY_SIZE(record_args) + 2 + schedstat_argc + argc - 1;
rec_argv = calloc(rec_argc + 1, sizeof(char *));
if (rec_argv == NULL)
else
rec_argv[i++] = strdup("sched:sched_wakeup");
+ for (j = 0; j < schedstat_argc; j++)
+ rec_argv[i++] = strdup(schedstat_args[j]);
+
for (j = 1; j < (unsigned int)argc; j++, i++)
rec_argv[i] = argv[j];
}
}
+static void perf_script__exit(struct perf_script *script)
+{
+ perf_thread_map__put(script->threads);
+ perf_cpu_map__put(script->cpus);
+}
+
static int __cmd_script(struct perf_script *script)
{
int ret;
zfree(&script.ptime_range);
}
+ zstd_fini(&(session->zstd_data));
evlist__free_stats(session->evlist);
perf_session__delete(session);
+ perf_script__exit(&script);
if (script_started)
cleanup_scripting();
evlist__check_cpu_maps(evsel_list);
- if (perf_pmu__has_hybrid())
- stat_config.no_merge = true;
-
/*
* Initialize thread_map with comm names,
* so we could print it out on output.
return augmented_args;
}
+static void syscall__exit(struct syscall *sc)
+{
+ if (!sc)
+ return;
+
+ free(sc->arg_fmt);
+}
+
static int trace__sys_enter(struct trace *trace, struct evsel *evsel,
union perf_event *event __maybe_unused,
struct perf_sample *sample)
return evsel;
}
+static void evlist__free_syscall_tp_fields(struct evlist *evlist)
+{
+ struct evsel *evsel;
+
+ evlist__for_each_entry(evlist, evsel) {
+ struct evsel_trace *et = evsel->priv;
+
+ if (!et || !evsel->tp_format || strcmp(evsel->tp_format->system, "syscalls"))
+ continue;
+
+ free(et->fmt);
+ free(et);
+ }
+}
+
static void trace__handle_event(struct trace *trace, union perf_event *event, struct perf_sample *sample)
{
const u32 type = event->header.type;
out_delete_evlist:
trace__symbols__exit(trace);
-
+ evlist__free_syscall_tp_fields(evlist);
evlist__delete(evlist);
cgroup__put(trace->cgroup);
trace->evlist = NULL;
err = parse_events_option(&o, lists[0], 0);
}
out:
+ free(strace_groups_dir);
+ free(lists[0]);
+ free(lists[1]);
if (sep)
*sep = ',';
return err;
}
+static void trace__exit(struct trace *trace)
+{
+ int i;
+
+ strlist__delete(trace->ev_qualifier);
+ free(trace->ev_qualifier_ids.entries);
+ if (trace->syscalls.table) {
+ for (i = 0; i <= trace->sctbl->syscalls.max_id; i++)
+ syscall__exit(&trace->syscalls.table[i]);
+ free(trace->syscalls.table);
+ }
+ syscalltbl__delete(trace->sctbl);
+ zfree(&trace->perfconfig_events);
+}
+
int cmd_trace(int argc, const char **argv)
{
const char *trace_usage[] = {
if (output_name != NULL)
fclose(trace.output);
out:
- zfree(&trace.perfconfig_events);
+ trace__exit(&trace);
return err;
}
// SPDX-License-Identifier: GPL-2.0
#include <errno.h>
#include <stdio.h>
+#include <stdlib.h>
#include <sys/epoll.h>
#include <sys/types.h>
#include <sys/stat.h>
}
out:
+ free(obj_buf);
bpf__clear();
return ret;
}
struct evsel *evsel;
struct event_name tmp;
struct evlist *evlist = evlist__new_default();
+ char *unit = strdup("KRAVA");
TEST_ASSERT_VAL("failed to get evlist", evlist);
perf_evlist__id_add(&evlist->core, &evsel->core, 0, 0, 123);
- evsel->unit = strdup("KRAVA");
+ evsel->unit = unit;
TEST_ASSERT_VAL("failed to synthesize attr update unit",
!perf_event__synthesize_event_update_unit(NULL, evsel, process_event_unit));
TEST_ASSERT_VAL("failed to synthesize attr update cpus",
!perf_event__synthesize_event_update_cpus(&tmp.tool, evsel, process_event_cpus));
- perf_cpu_map__put(evsel->core.own_cpus);
+ free(unit);
+ evlist__delete(evlist);
return 0;
}
#include "tests.h"
#include "debug.h"
#include "pmu.h"
+#include "pmu-hybrid.h"
#include <errno.h>
#include <linux/kernel.h>
{
int err = 0, ret = 0;
- if (perf_pmu__has_hybrid())
+ if (perf_pmu__has_hybrid() && perf_pmu__hybrid_mounted("cpu_atom"))
return perf_evsel__name_array_test(evsel__hw_names, 2);
err = perf_evsel__name_array_test(evsel__hw_names, 1);
ret = check_maps(merged3, ARRAY_SIZE(merged3), &maps);
TEST_ASSERT_VAL("merge check failed", !ret);
+
+ maps__exit(&maps);
return TEST_OK;
}
#include "tests.h"
#include "debug.h"
#include "pmu.h"
+#include "pmu-hybrid.h"
#include <dirent.h>
#include <errno.h>
#include <sys/types.h>
{
struct evsel *evsel = evlist__first(evlist);
+ if (!perf_pmu__hybrid_mounted("cpu_atom")) {
+ TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries);
+ TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type);
+ TEST_ASSERT_VAL("wrong config", 0x1a == evsel->core.attr.config);
+ return 0;
+ }
+
TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries);
TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type);
TEST_ASSERT_VAL("wrong config", 0x1a == evsel->core.attr.config);
{
struct evsel *evsel = evlist__first(evlist);
- TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries);
+ TEST_ASSERT_VAL("wrong number of entries", 1 == evlist->core.nr_entries);
TEST_ASSERT_VAL("wrong type", PERF_TYPE_HW_CACHE == evsel->core.attr.type);
TEST_ASSERT_VAL("wrong config", 0x2 == (evsel->core.attr.config & 0xffffffff));
-
- evsel = evsel__next(evsel);
- TEST_ASSERT_VAL("wrong type", PERF_TYPE_HW_CACHE == evsel->core.attr.type);
- TEST_ASSERT_VAL("wrong config", 0x10002 == (evsel->core.attr.config & 0xffffffff));
return 0;
}
.id = 7,
},
{
- .name = "cpu_core/LLC-loads/,cpu_atom/LLC-load-misses/",
+ .name = "cpu_core/LLC-loads/",
.check = test__hybrid_cache_event,
.id = 8,
},
#include "mmap.h"
#include "tests.h"
#include "pmu.h"
+#include "pmu-hybrid.h"
#define CHECK__(x) { \
while ((x) < 0) { \
* For hybrid "cycles:u", it creates two events.
* Init the second evsel here.
*/
- if (perf_pmu__has_hybrid()) {
+ if (perf_pmu__has_hybrid() && perf_pmu__hybrid_mounted("cpu_atom")) {
evsel = evsel__next(evsel);
evsel->core.attr.comm = 1;
evsel->core.attr.disabled = 1;
TEST_ASSERT_VAL("failed to write header",
!perf_session__write_header(session, session->evlist, data.file.fd, true));
+ evlist__delete(session->evlist);
perf_session__delete(session);
return 0;
return 0;
}
+static void dump_queued_data(struct cs_etm_auxtrace *etm,
+ struct perf_record_auxtrace *event)
+{
+ struct auxtrace_buffer *buf;
+ unsigned int i;
+ /*
+ * Find all buffers with same reference in the queues and dump them.
+ * This is because the queues can contain multiple entries of the same
+ * buffer that were split on aux records.
+ */
+ for (i = 0; i < etm->queues.nr_queues; ++i)
+ list_for_each_entry(buf, &etm->queues.queue_array[i].head, list)
+ if (buf->reference == event->reference)
+ cs_etm__dump_event(etm, buf);
+}
+
static int cs_etm__process_auxtrace_event(struct perf_session *session,
union perf_event *event,
struct perf_tool *tool __maybe_unused)
cs_etm__dump_event(etm, buffer);
auxtrace_buffer__put_data(buffer);
}
- }
+ } else if (dump_trace)
+ dump_queued_data(etm, &event->auxtrace);
return 0;
}
return metadata;
}
+/**
+ * Puts a fragment of an auxtrace buffer into the auxtrace queues based
+ * on the bounds of aux_event, if it matches with the buffer that's at
+ * file_offset.
+ *
+ * Normally, whole auxtrace buffers would be added to the queue. But we
+ * want to reset the decoder for every PERF_RECORD_AUX event, and the decoder
+ * is reset across each buffer, so splitting the buffers up in advance has
+ * the same effect.
+ */
+static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_offset, size_t sz,
+ struct perf_record_aux *aux_event, struct perf_sample *sample)
+{
+ int err;
+ char buf[PERF_SAMPLE_MAX_SIZE];
+ union perf_event *auxtrace_event_union;
+ struct perf_record_auxtrace *auxtrace_event;
+ union perf_event auxtrace_fragment;
+ __u64 aux_offset, aux_size;
+
+ struct cs_etm_auxtrace *etm = container_of(session->auxtrace,
+ struct cs_etm_auxtrace,
+ auxtrace);
+
+ /*
+ * There should be a PERF_RECORD_AUXTRACE event at the file_offset that we got
+ * from looping through the auxtrace index.
+ */
+ err = perf_session__peek_event(session, file_offset, buf,
+ PERF_SAMPLE_MAX_SIZE, &auxtrace_event_union, NULL);
+ if (err)
+ return err;
+ auxtrace_event = &auxtrace_event_union->auxtrace;
+ if (auxtrace_event->header.type != PERF_RECORD_AUXTRACE)
+ return -EINVAL;
+
+ if (auxtrace_event->header.size < sizeof(struct perf_record_auxtrace) ||
+ auxtrace_event->header.size != sz) {
+ return -EINVAL;
+ }
+
+ /*
+ * In per-thread mode, CPU is set to -1, but TID will be set instead. See
+ * auxtrace_mmap_params__set_idx(). Return 'not found' if neither CPU nor TID match.
+ */
+ if ((auxtrace_event->cpu == (__u32) -1 && auxtrace_event->tid != sample->tid) ||
+ auxtrace_event->cpu != sample->cpu)
+ return 1;
+
+ if (aux_event->flags & PERF_AUX_FLAG_OVERWRITE) {
+ /*
+ * Clamp size in snapshot mode. The buffer size is clamped in
+ * __auxtrace_mmap__read() for snapshots, so the aux record size doesn't reflect
+ * the buffer size.
+ */
+ aux_size = min(aux_event->aux_size, auxtrace_event->size);
+
+ /*
+ * In this mode, the head also points to the end of the buffer so aux_offset
+ * needs to have the size subtracted so it points to the beginning as in normal mode
+ */
+ aux_offset = aux_event->aux_offset - aux_size;
+ } else {
+ aux_size = aux_event->aux_size;
+ aux_offset = aux_event->aux_offset;
+ }
+
+ if (aux_offset >= auxtrace_event->offset &&
+ aux_offset + aux_size <= auxtrace_event->offset + auxtrace_event->size) {
+ /*
+ * If this AUX event was inside this buffer somewhere, create a new auxtrace event
+ * based on the sizes of the aux event, and queue that fragment.
+ */
+ auxtrace_fragment.auxtrace = *auxtrace_event;
+ auxtrace_fragment.auxtrace.size = aux_size;
+ auxtrace_fragment.auxtrace.offset = aux_offset;
+ file_offset += aux_offset - auxtrace_event->offset + auxtrace_event->header.size;
+
+ pr_debug3("CS ETM: Queue buffer size: %#"PRI_lx64" offset: %#"PRI_lx64
+ " tid: %d cpu: %d\n", aux_size, aux_offset, sample->tid, sample->cpu);
+ return auxtrace_queues__add_event(&etm->queues, session, &auxtrace_fragment,
+ file_offset, NULL);
+ }
+
+ /* Wasn't inside this buffer, but there were no parse errors. 1 == 'not found' */
+ return 1;
+}
+
+static int cs_etm__queue_aux_records_cb(struct perf_session *session, union perf_event *event,
+ u64 offset __maybe_unused, void *data __maybe_unused)
+{
+ struct perf_sample sample;
+ int ret;
+ struct auxtrace_index_entry *ent;
+ struct auxtrace_index *auxtrace_index;
+ struct evsel *evsel;
+ size_t i;
+
+ /* Don't care about any other events, we're only queuing buffers for AUX events */
+ if (event->header.type != PERF_RECORD_AUX)
+ return 0;
+
+ if (event->header.size < sizeof(struct perf_record_aux))
+ return -EINVAL;
+
+ /* Truncated Aux records can have 0 size and shouldn't result in anything being queued. */
+ if (!event->aux.aux_size)
+ return 0;
+
+ /*
+ * Parse the sample, we need the sample_id_all data that comes after the event so that the
+ * CPU or PID can be matched to an AUXTRACE buffer's CPU or PID.
+ */
+ evsel = evlist__event2evsel(session->evlist, event);
+ if (!evsel)
+ return -EINVAL;
+ ret = evsel__parse_sample(evsel, event, &sample);
+ if (ret)
+ return ret;
+
+ /*
+ * Loop through the auxtrace index to find the buffer that matches up with this aux event.
+ */
+ list_for_each_entry(auxtrace_index, &session->auxtrace_index, list) {
+ for (i = 0; i < auxtrace_index->nr; i++) {
+ ent = &auxtrace_index->entries[i];
+ ret = cs_etm__queue_aux_fragment(session, ent->file_offset,
+ ent->sz, &event->aux, &sample);
+ /*
+ * Stop search on error or successful values. Continue search on
+ * 1 ('not found')
+ */
+ if (ret != 1)
+ return ret;
+ }
+ }
+
+ /*
+ * Couldn't find the buffer corresponding to this aux record, something went wrong. Warn but
+ * don't exit with an error because it will still be possible to decode other aux records.
+ */
+ pr_err("CS ETM: Couldn't find auxtrace buffer for aux_offset: %#"PRI_lx64
+ " tid: %d cpu: %d\n", event->aux.aux_offset, sample.tid, sample.cpu);
+ return 0;
+}
+
+static int cs_etm__queue_aux_records(struct perf_session *session)
+{
+ struct auxtrace_index *index = list_first_entry_or_null(&session->auxtrace_index,
+ struct auxtrace_index, list);
+ if (index && index->nr > 0)
+ return perf_session__peek_events(session, session->header.data_offset,
+ session->header.data_size,
+ cs_etm__queue_aux_records_cb, NULL);
+
+ /*
+ * We would get here if there are no entries in the index (either no auxtrace
+ * buffers or no index at all). Fail silently as there is the possibility of
+ * queueing them in cs_etm__process_auxtrace_event() if etm->data_queued is still
+ * false.
+ *
+ * In that scenario, buffers will not be split by AUX records.
+ */
+ return 0;
+}
+
int cs_etm__process_auxtrace_info(union perf_event *event,
struct perf_session *session)
{
if (dump_trace) {
cs_etm__print_auxtrace_info(auxtrace_info->priv, num_cpu);
- return 0;
}
err = cs_etm__synth_events(etm, session);
if (err)
goto err_delete_thread;
- err = auxtrace_queues__process_index(&etm->queues, session);
+ err = cs_etm__queue_aux_records(session);
if (err)
goto err_delete_thread;
static void close_dir(struct perf_data_file *files, int nr)
{
- while (--nr >= 1) {
+ while (--nr >= 0) {
close(files[nr].fd);
zfree(&files[nr].path);
}
struct map *map = NULL;
struct dso *dso = dso__new(name);
- if (dso)
+ if (dso) {
map = map__new2(0, dso);
+ dso__put(dso);
+ }
return map;
}
*
* Find a line number and file name for @addr in @cu_die.
*/
-int cu_find_lineinfo(Dwarf_Die *cu_die, unsigned long addr,
- const char **fname, int *lineno)
+int cu_find_lineinfo(Dwarf_Die *cu_die, Dwarf_Addr addr,
+ const char **fname, int *lineno)
{
Dwarf_Line *line;
Dwarf_Die die_mem;
Dwarf_Addr faddr;
- if (die_find_realfunc(cu_die, (Dwarf_Addr)addr, &die_mem)
+ if (die_find_realfunc(cu_die, addr, &die_mem)
&& die_entrypc(&die_mem, &faddr) == 0 &&
faddr == addr) {
*fname = dwarf_decl_file(&die_mem);
goto out;
}
- line = cu_getsrc_die(cu_die, (Dwarf_Addr)addr);
+ line = cu_getsrc_die(cu_die, addr);
if (line && dwarf_lineno(line, lineno) == 0) {
*fname = dwarf_linesrc(line, NULL, NULL);
if (!*fname)
const char *cu_get_comp_dir(Dwarf_Die *cu_die);
/* Get a line number and file name for given address */
-int cu_find_lineinfo(Dwarf_Die *cudie, unsigned long addr,
+int cu_find_lineinfo(Dwarf_Die *cudie, Dwarf_Addr addr,
const char **fname, int *lineno);
/* Walk on functions at given address */
zfree(&env->cpuid);
zfree(&env->cmdline);
zfree(&env->cmdline_argv);
+ zfree(&env->sibling_dies);
zfree(&env->sibling_cores);
zfree(&env->sibling_threads);
zfree(&env->pmu_mappings);
zfree(&env->cpu);
+ zfree(&env->cpu_pmu_caps);
zfree(&env->numa_map);
for (i = 0; i < env->nr_numa_nodes; i++)
if (ferror(infile)) {
pr_err("lzma: read error: %s\n", strerror(errno));
- goto err_fclose;
+ goto err_lzma_end;
}
if (feof(infile))
if (writen(output_fd, buf_out, write_size) != write_size) {
pr_err("lzma: write error: %s\n", strerror(errno));
- goto err_fclose;
+ goto err_lzma_end;
}
strm.next_out = buf_out;
break;
pr_err("lzma: failed %s\n", lzma_strerror(ret));
- goto err_fclose;
+ goto err_lzma_end;
}
}
err = 0;
+err_lzma_end:
+ lzma_end(&strm);
err_fclose:
fclose(infile);
return err;
grp_leader = evsel;
if (grp_evt > -1) {
- evsel->leader = grp_leader;
+ evsel__set_leader(evsel, grp_leader);
grp_leader->core.nr_members++;
grp_evt++;
}
return perf_pmu__find_map(NULL);
}
-static bool perf_pmu__valid_suffix(char *pmu_name, char *tok)
+/*
+ * Suffix must be in form tok_{digits}, or tok{digits}, or same as pmu_name
+ * to be valid.
+ */
+static bool perf_pmu__valid_suffix(const char *pmu_name, char *tok)
{
- char *p;
+ const char *p;
if (strncmp(pmu_name, tok, strlen(tok)))
return false;
if (*p == 0)
return true;
- if (*p != '_')
- return false;
+ if (*p == '_')
+ ++p;
- ++p;
- if (*p == 0 || !isdigit(*p))
- return false;
+ /* Ensure we end in a number */
+ while (1) {
+ if (!isdigit(*p))
+ return false;
+ if (*(++p) == 0)
+ break;
+ }
return true;
}
* match "socket" in "socketX_pmunameY" and then "pmuname" in
* "pmunameY".
*/
- for (; tok; name += strlen(tok), tok = strtok_r(NULL, ",", &tmp)) {
+ while (1) {
+ char *next_tok = strtok_r(NULL, ",", &tmp);
+
name = strstr(name, tok);
- if (!name || !perf_pmu__valid_suffix((char *)name, tok)) {
+ if (!name ||
+ (!next_tok && !perf_pmu__valid_suffix(name, tok))) {
res = false;
goto out;
}
+ if (!next_tok)
+ break;
+ tok = next_tok;
+ name += strlen(tok);
}
res = true;
LIST_HEAD(format);
LIST_HEAD(aliases);
__u32 type;
+ bool is_hybrid = perf_pmu__hybrid_mounted(name);
+
+ /*
+ * Check pmu name for hybrid and the pmu may be invalid in sysfs
+ */
+ if (!strncmp(name, "cpu_", 4) && !is_hybrid)
+ return NULL;
/*
* The pmu data we store & need consists of the pmu
pmu->is_uncore = pmu_is_uncore(name);
if (pmu->is_uncore)
pmu->id = pmu_id(name);
- pmu->is_hybrid = perf_pmu__hybrid_mounted(name);
+ pmu->is_hybrid = is_hybrid;
pmu->max_precise = pmu_max_precise(name);
pmu_add_cpu_aliases(&aliases, pmu);
pmu_add_sys_aliases(&aliases, pmu);
struct map *map;
map = dso__new_map(target);
- if (map && map->dso)
+ if (map && map->dso) {
+ nsinfo__put(map->dso->nsinfo);
map->dso->nsinfo = nsinfo__get(nsi);
+ }
return map;
} else {
return kernel_get_module_map(target);
clear_probe_trace_event(tevs + i);
}
-static bool kprobe_blacklist__listed(unsigned long address);
-static bool kprobe_warn_out_range(const char *symbol, unsigned long address)
+static bool kprobe_blacklist__listed(u64 address);
+static bool kprobe_warn_out_range(const char *symbol, u64 address)
{
struct map *map;
bool ret = false;
pr_debug("Symbol %s address found : %" PRIx64 "\n",
pp->function, address);
- ret = debuginfo__find_probe_point(dinfo, (unsigned long)address,
- result);
+ ret = debuginfo__find_probe_point(dinfo, address, result);
if (ret <= 0)
ret = (!ret) ? -ENOENT : ret;
else {
}
-static int get_text_start_address(const char *exec, unsigned long *address,
+static int get_text_start_address(const char *exec, u64 *address,
struct nsinfo *nsi)
{
Elf *elf;
bool is_kprobe)
{
struct debuginfo *dinfo = NULL;
- unsigned long stext = 0;
+ u64 stext = 0;
u64 addr = tp->address;
int ret = -ENOENT;
dinfo = debuginfo_cache__open(tp->module, verbose <= 0);
if (dinfo)
- ret = debuginfo__find_probe_point(dinfo,
- (unsigned long)addr, pp);
+ ret = debuginfo__find_probe_point(dinfo, addr, pp);
else
ret = -ENOENT;
/* Adjust symbol name and address */
static int post_process_probe_trace_point(struct probe_trace_point *tp,
- struct map *map, unsigned long offs)
+ struct map *map, u64 offs)
{
struct symbol *sym;
u64 addr = tp->address - offs;
int ntevs, const char *pathname)
{
struct map *map;
- unsigned long stext = 0;
+ u64 stext = 0;
int i, ret = 0;
/* Prepare a map for offline binary */
struct nsinfo *nsi)
{
int i, ret = 0;
- unsigned long stext = 0;
+ u64 stext = 0;
if (!exec)
return 0;
mod_name = find_module_name(module);
for (i = 0; i < ntevs; i++) {
ret = post_process_probe_trace_point(&tevs[i].point,
- map, (unsigned long)text_offs);
+ map, text_offs);
if (ret < 0)
break;
tevs[i].point.module =
* so tmp[1] should always valid (but could be '\0').
*/
if (tmp && !strncmp(tmp, "0x", 2)) {
- pp->abs_address = strtoul(pp->function, &tmp, 0);
+ pp->abs_address = strtoull(pp->function, &tmp, 0);
if (*tmp != '\0') {
semantic_error("Invalid absolute address.\n");
return -EINVAL;
argv[i] = NULL;
argc -= 1;
} else
- tp->address = strtoul(fmt1_str, NULL, 0);
+ tp->address = strtoull(fmt1_str, NULL, 0);
} else {
/* Only the symbol-based probe has offset */
tp->symbol = strdup(fmt1_str);
return -EINVAL;
/* Use the tp->address for uprobes */
- err = strbuf_addf(buf, "%s:0x%lx", tp->module, tp->address);
+ err = strbuf_addf(buf, "%s:0x%" PRIx64, tp->module, tp->address);
if (err >= 0 && tp->ref_ctr_offset) {
if (!uprobe_ref_ctr_is_supported())
{
if (!strncmp(tp->symbol, "0x", 2)) {
/* Absolute address. See try_to_find_absolute_address() */
- return strbuf_addf(buf, "%s%s0x%lx", tp->module ?: "",
+ return strbuf_addf(buf, "%s%s0x%" PRIx64, tp->module ?: "",
tp->module ? ":" : "", tp->address);
} else {
return strbuf_addf(buf, "%s%s%s+%lu", tp->module ?: "",
pp->function = strdup(tp->symbol);
pp->offset = tp->offset;
} else {
- ret = e_snprintf(buf, 128, "0x%" PRIx64, (u64)tp->address);
+ ret = e_snprintf(buf, 128, "0x%" PRIx64, tp->address);
if (ret < 0)
return ret;
pp->function = strdup(buf);
struct kprobe_blacklist_node {
struct list_head list;
- unsigned long start;
- unsigned long end;
+ u64 start;
+ u64 end;
char *symbol;
};
}
INIT_LIST_HEAD(&node->list);
list_add_tail(&node->list, blacklist);
- if (sscanf(buf, "0x%lx-0x%lx", &node->start, &node->end) != 2) {
+ if (sscanf(buf, "0x%" PRIx64 "-0x%" PRIx64, &node->start, &node->end) != 2) {
ret = -EINVAL;
break;
}
ret = -ENOMEM;
break;
}
- pr_debug2("Blacklist: 0x%lx-0x%lx, %s\n",
+ pr_debug2("Blacklist: 0x%" PRIx64 "-0x%" PRIx64 ", %s\n",
node->start, node->end, node->symbol);
ret++;
}
}
static struct kprobe_blacklist_node *
-kprobe_blacklist__find_by_address(struct list_head *blacklist,
- unsigned long address)
+kprobe_blacklist__find_by_address(struct list_head *blacklist, u64 address)
{
struct kprobe_blacklist_node *node;
kprobe_blacklist__delete(&kprobe_blacklist);
}
-static bool kprobe_blacklist__listed(unsigned long address)
+static bool kprobe_blacklist__listed(u64 address)
{
return !!kprobe_blacklist__find_by_address(&kprobe_blacklist, address);
}
* In __add_probe_trace_events, a NULL symbol is interpreted as
* invalid.
*/
- if (asprintf(&tp->symbol, "0x%lx", tp->address) < 0)
+ if (asprintf(&tp->symbol, "0x%" PRIx64, tp->address) < 0)
goto errout;
/* For kprobe, check range */
goto errout;
}
- if (asprintf(&tp->realname, "abs_%lx", tp->address) < 0)
+ if (asprintf(&tp->realname, "abs_%" PRIx64, tp->address) < 0)
goto errout;
if (pev->target) {
char *module; /* Module name */
unsigned long offset; /* Offset from symbol */
unsigned long ref_ctr_offset; /* SDT reference counter offset */
- unsigned long address; /* Actual address of the trace point */
+ u64 address; /* Actual address of the trace point */
bool retprobe; /* Return probe flag */
};
bool retprobe; /* Return probe flag */
char *lazy_line; /* Lazy matching pattern */
unsigned long offset; /* Offset from function entry */
- unsigned long abs_address; /* Absolute address of the point */
+ u64 abs_address; /* Absolute address of the point */
};
/* Perf probe probing argument field chain */
ret = probe_file__get_events(fd, filter, namelist);
if (ret < 0)
- return ret;
+ goto out;
ret = probe_file__del_strlist(fd, namelist);
+out:
strlist__delete(namelist);
-
return ret;
}
}
tp->offset = (unsigned long)(paddr - eaddr);
- tp->address = (unsigned long)paddr;
+ tp->address = paddr;
tp->symbol = strdup(symbol);
if (!tp->symbol)
return -ENOMEM;
}
/* Reverse search */
-int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
+int debuginfo__find_probe_point(struct debuginfo *dbg, u64 addr,
struct perf_probe_point *ppt)
{
Dwarf_Die cudie, spdie, indie;
addr += baseaddr;
/* Find cu die */
if (!dwarf_addrdie(dbg->dbg, (Dwarf_Addr)addr, &cudie)) {
- pr_warning("Failed to find debug information for address %lx\n",
+ pr_warning("Failed to find debug information for address %" PRIx64 "\n",
addr);
ret = -EINVAL;
goto end;
}
/* Find a corresponding line (filename and lineno) */
- cu_find_lineinfo(&cudie, addr, &fname, &lineno);
+ cu_find_lineinfo(&cudie, (Dwarf_Addr)addr, &fname, &lineno);
/* Don't care whether it failed or not */
/* Find a corresponding function (name, baseline and baseaddr) */
}
fname = dwarf_decl_file(&spdie);
- if (addr == (unsigned long)baseaddr) {
+ if (addr == baseaddr) {
/* Function entry - Relative line number is 0 */
lineno = baseline;
goto post;
if (lineno)
ppt->line = lineno - baseline;
else if (basefunc) {
- ppt->offset = addr - (unsigned long)baseaddr;
+ ppt->offset = addr - baseaddr;
func = basefunc;
}
}
static int line_range_walk_cb(const char *fname, int lineno,
- Dwarf_Addr addr __maybe_unused,
- void *data)
+ Dwarf_Addr addr, void *data)
{
struct line_finder *lf = data;
const char *__fname;
struct probe_trace_event **tevs);
/* Find a perf_probe_point from debuginfo */
-int debuginfo__find_probe_point(struct debuginfo *dbg, unsigned long addr,
+int debuginfo__find_probe_point(struct debuginfo *dbg, u64 addr,
struct perf_probe_point *ppt);
int debuginfo__get_text_offset(struct debuginfo *dbg, Dwarf_Addr *offs,
evlist__delete(session->evlist);
perf_data__close(session->data);
}
+ trace_event__cleanup(&session->tevent);
free(session);
}
add_key(sb, s[i].name, llen);
}
-const char *sort_help(const char *prefix)
+char *sort_help(const char *prefix)
{
struct strbuf sb;
char *s;
void sort__setup_elide(FILE *fp);
void perf_hpp__set_elide(int idx, bool elide);
-const char *sort_help(const char *prefix);
+char *sort_help(const char *prefix);
int report_parse_ignore_callees_opt(const struct option *opt, const char *arg, int unset);
}
}
+static bool is_uncore(struct evsel *evsel)
+{
+ struct perf_pmu *pmu = evsel__find_pmu(evsel);
+
+ return pmu && pmu->is_uncore;
+}
+
+static bool hybrid_uniquify(struct evsel *evsel)
+{
+ return perf_pmu__has_hybrid() && !is_uncore(evsel);
+}
+
static bool collect_data(struct perf_stat_config *config, struct evsel *counter,
void (*cb)(struct perf_stat_config *config, struct evsel *counter, void *data,
bool first),
if (counter->merged_stat)
return false;
cb(config, counter, data, true);
- if (config->no_merge)
+ if (config->no_merge || hybrid_uniquify(counter))
uniquify_event_name(counter);
else if (counter->auto_merge_stats)
collect_all_aliases(config, counter, cb, data);
import os
import time
+assert sys.version_info >= (3, 7), "Python version is too old"
+
from collections import namedtuple
from enum import Enum, auto
# Author: Felix Guo <felixguoxiuping@gmail.com>
# Author: Brendan Higgins <brendanhiggins@google.com>
-from __future__ import annotations
import importlib.util
import logging
import subprocess
import os
import shutil
import signal
-from typing import Iterator
-from typing import Optional
+from typing import Iterator, Optional, Tuple
from contextlib import ExitStack
raise ConfigError(arch + ' is not a valid arch')
def get_source_tree_ops_from_qemu_config(config_path: str,
- cross_compile: Optional[str]) -> tuple[
+ cross_compile: Optional[str]) -> Tuple[
str, LinuxSourceTreeOperations]:
# The module name/path has very little to do with where the actual file
# exists (I learned this through experimentation and could not find it
def parse_test_result(lines: LineStream) -> TestResult:
consume_non_diagnostic(lines)
if not lines or not parse_tap_header(lines):
- return TestResult(TestStatus.NO_TESTS, [], lines)
+ return TestResult(TestStatus.FAILURE_TO_PARSE_TESTS, [], lines)
expected_test_suite_num = parse_test_plan(lines)
- if not expected_test_suite_num:
+ if expected_test_suite_num == 0:
+ return TestResult(TestStatus.NO_TESTS, [], lines)
+ elif expected_test_suite_num is None:
return TestResult(TestStatus.FAILURE_TO_PARSE_TESTS, [], lines)
test_suites = []
for i in range(1, expected_test_suite_num + 1):
kunit_parser.TestStatus.FAILURE,
result.status)
+ def test_no_header(self):
+ empty_log = test_data_path('test_is_test_passed-no_tests_run_no_header.log')
+ with open(empty_log) as file:
+ result = kunit_parser.parse_run_tests(
+ kunit_parser.extract_tap_lines(file.readlines()))
+ self.assertEqual(0, len(result.suites))
+ self.assertEqual(
+ kunit_parser.TestStatus.FAILURE_TO_PARSE_TESTS,
+ result.status)
+
def test_no_tests(self):
- empty_log = test_data_path('test_is_test_passed-no_tests_run.log')
+ empty_log = test_data_path('test_is_test_passed-no_tests_run_with_header.log')
with open(empty_log) as file:
result = kunit_parser.parse_run_tests(
kunit_parser.extract_tap_lines(file.readlines()))
with open(crash_log) as file:
result = kunit_parser.parse_run_tests(
kunit_parser.extract_tap_lines(file.readlines()))
- print_mock.assert_any_call(StrContains('no tests run!'))
+ print_mock.assert_any_call(StrContains('could not parse test results!'))
print_mock.stop()
file.close()
result["sub_groups"][1]["test_cases"][0])
def test_no_tests_json(self):
- result = self._json_for('test_is_test_passed-no_tests_run.log')
+ result = self._json_for('test_is_test_passed-no_tests_run_with_header.log')
self.assertEqual(0, len(result['sub_groups']))
class StrContains(str):
--- /dev/null
+TAP version 14
+1..0
bpf_object__close(obj);
}
+#include "tailcall_bpf2bpf4.skel.h"
+
/* test_tailcall_bpf2bpf_4 checks that tailcall counter is correctly preserved
* across tailcalls combined with bpf2bpf calls. for making sure that tailcall
* counter behaves correctly, bpf program will go through following flow:
* the loop begins. At the end of the test make sure that the global counter is
* equal to 31, because tailcall counter includes the first two tailcalls
* whereas global counter is incremented only on loop presented on flow above.
+ *
+ * The noise parameter is used to insert bpf_map_update calls into the logic
+ * to force verifier to patch instructions. This allows us to ensure jump
+ * logic remains correct with instruction movement.
*/
-static void test_tailcall_bpf2bpf_4(void)
+static void test_tailcall_bpf2bpf_4(bool noise)
{
- int err, map_fd, prog_fd, main_fd, data_fd, i, val;
+ int err, map_fd, prog_fd, main_fd, data_fd, i;
+ struct tailcall_bpf2bpf4__bss val;
struct bpf_map *prog_array, *data_map;
struct bpf_program *prog;
struct bpf_object *obj;
goto out;
}
- err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0,
- &duration, &retval, NULL);
- CHECK(err || retval != sizeof(pkt_v4) * 3, "tailcall", "err %d errno %d retval %d\n",
- err, errno, retval);
-
data_map = bpf_object__find_map_by_name(obj, "tailcall.bss");
if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map)))
return;
return;
i = 0;
+ val.noise = noise;
+ val.count = 0;
+ err = bpf_map_update_elem(data_fd, &i, &val, BPF_ANY);
+ if (CHECK_FAIL(err))
+ goto out;
+
+ err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0,
+ &duration, &retval, NULL);
+ CHECK(err || retval != sizeof(pkt_v4) * 3, "tailcall", "err %d errno %d retval %d\n",
+ err, errno, retval);
+
+ i = 0;
err = bpf_map_lookup_elem(data_fd, &i, &val);
- CHECK(err || val != 31, "tailcall count", "err %d errno %d count %d\n",
- err, errno, val);
+ CHECK(err || val.count != 31, "tailcall count", "err %d errno %d count %d\n",
+ err, errno, val.count);
out:
bpf_object__close(obj);
if (test__start_subtest("tailcall_bpf2bpf_3"))
test_tailcall_bpf2bpf_3();
if (test__start_subtest("tailcall_bpf2bpf_4"))
- test_tailcall_bpf2bpf_4();
+ test_tailcall_bpf2bpf_4(false);
+ if (test__start_subtest("tailcall_bpf2bpf_5"))
+ test_tailcall_bpf2bpf_4(true);
}
#include <bpf/bpf_helpers.h>
struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 1);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(__u32));
+} nop_table SEC(".maps");
+
+struct {
__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
__uint(max_entries, 3);
__uint(key_size, sizeof(__u32));
} jmp_table SEC(".maps");
int count = 0;
+int noise = 0;
+
+__always_inline int subprog_noise(void)
+{
+ __u32 key = 0;
+
+ bpf_map_lookup_elem(&nop_table, &key);
+ return 0;
+}
__noinline
int subprog_tail_2(struct __sk_buff *skb)
{
+ if (noise)
+ subprog_noise();
bpf_tail_call_static(skb, &jmp_table, 2);
return skb->len * 3;
}
{
+ "map access: known scalar += value_ptr unknown vs const",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ 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_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ 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, 9),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_MOV64_IMM(BPF_REG_1, 3),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "map access: known scalar += value_ptr const vs unknown",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ 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_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ 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, 9),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2),
+ BPF_MOV64_IMM(BPF_REG_1, 3),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 3),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "map access: known scalar += value_ptr const vs const (ne)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ 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_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ 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, 7),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2),
+ BPF_MOV64_IMM(BPF_REG_1, 3),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_MOV64_IMM(BPF_REG_1, 5),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "map access: known scalar += value_ptr const vs const (eq)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ 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_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ 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, 7),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2),
+ BPF_MOV64_IMM(BPF_REG_1, 5),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_MOV64_IMM(BPF_REG_1, 5),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "map access: known scalar += value_ptr unknown vs unknown (eq)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ 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_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ 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, 11),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 3),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "map access: known scalar += value_ptr unknown vs unknown (lt)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ 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_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ 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, 11),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x3),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 3),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "map access: known scalar += value_ptr unknown vs unknown (gt)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ 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_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ 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, 11),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 3),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x3),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
"map access: known scalar += value_ptr from different maps",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
/x86_64/xen_vmcall_test
/x86_64/xss_msr_test
/x86_64/vmx_pmu_msrs_test
+/access_tracking_perf_test
/demand_paging_test
/dirty_log_test
/dirty_log_perf_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_msrs_test
TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test
TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test
+TEST_GEN_PROGS_x86_64 += access_tracking_perf_test
TEST_GEN_PROGS_x86_64 += demand_paging_test
TEST_GEN_PROGS_x86_64 += dirty_log_test
TEST_GEN_PROGS_x86_64 += dirty_log_perf_test
#define VREGS_SUBLIST \
{ "vregs", .regs = vregs, .regs_n = ARRAY_SIZE(vregs), }
#define PMU_SUBLIST \
- { "pmu", .regs = pmu_regs, .regs_n = ARRAY_SIZE(pmu_regs), }
+ { "pmu", .capability = KVM_CAP_ARM_PMU_V3, .feature = KVM_ARM_VCPU_PMU_V3, \
+ .regs = pmu_regs, .regs_n = ARRAY_SIZE(pmu_regs), }
#define SVE_SUBLIST \
{ "sve", .capability = KVM_CAP_ARM_SVE, .feature = KVM_ARM_VCPU_SVE, .finalize = true, \
.regs = sve_regs, .regs_n = ARRAY_SIZE(sve_regs), \
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * access_tracking_perf_test
+ *
+ * Copyright (C) 2021, Google, Inc.
+ *
+ * This test measures the performance effects of KVM's access tracking.
+ * Access tracking is driven by the MMU notifiers test_young, clear_young, and
+ * clear_flush_young. These notifiers do not have a direct userspace API,
+ * however the clear_young notifier can be triggered by marking a pages as idle
+ * in /sys/kernel/mm/page_idle/bitmap. This test leverages that mechanism to
+ * enable access tracking on guest memory.
+ *
+ * To measure performance this test runs a VM with a configurable number of
+ * vCPUs that each touch every page in disjoint regions of memory. Performance
+ * is measured in the time it takes all vCPUs to finish touching their
+ * predefined region.
+ *
+ * Note that a deterministic correctness test of access tracking is not possible
+ * by using page_idle as it exists today. This is for a few reasons:
+ *
+ * 1. page_idle only issues clear_young notifiers, which lack a TLB flush. This
+ * means subsequent guest accesses are not guaranteed to see page table
+ * updates made by KVM until some time in the future.
+ *
+ * 2. page_idle only operates on LRU pages. Newly allocated pages are not
+ * immediately allocated to LRU lists. Instead they are held in a "pagevec",
+ * which is drained to LRU lists some time in the future. There is no
+ * userspace API to force this drain to occur.
+ *
+ * These limitations are worked around in this test by using a large enough
+ * region of memory for each vCPU such that the number of translations cached in
+ * the TLB and the number of pages held in pagevecs are a small fraction of the
+ * overall workload. And if either of those conditions are not true this test
+ * will fail rather than silently passing.
+ */
+#include <inttypes.h>
+#include <limits.h>
+#include <pthread.h>
+#include <sys/mman.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+#include "kvm_util.h"
+#include "test_util.h"
+#include "perf_test_util.h"
+#include "guest_modes.h"
+
+/* Global variable used to synchronize all of the vCPU threads. */
+static int iteration = -1;
+
+/* Defines what vCPU threads should do during a given iteration. */
+static enum {
+ /* Run the vCPU to access all its memory. */
+ ITERATION_ACCESS_MEMORY,
+ /* Mark the vCPU's memory idle in page_idle. */
+ ITERATION_MARK_IDLE,
+} iteration_work;
+
+/* Set to true when vCPU threads should exit. */
+static bool done;
+
+/* The iteration that was last completed by each vCPU. */
+static int vcpu_last_completed_iteration[KVM_MAX_VCPUS];
+
+/* Whether to overlap the regions of memory vCPUs access. */
+static bool overlap_memory_access;
+
+struct test_params {
+ /* The backing source for the region of memory. */
+ enum vm_mem_backing_src_type backing_src;
+
+ /* The amount of memory to allocate for each vCPU. */
+ uint64_t vcpu_memory_bytes;
+
+ /* The number of vCPUs to create in the VM. */
+ int vcpus;
+};
+
+static uint64_t pread_uint64(int fd, const char *filename, uint64_t index)
+{
+ uint64_t value;
+ off_t offset = index * sizeof(value);
+
+ TEST_ASSERT(pread(fd, &value, sizeof(value), offset) == sizeof(value),
+ "pread from %s offset 0x%" PRIx64 " failed!",
+ filename, offset);
+
+ return value;
+
+}
+
+#define PAGEMAP_PRESENT (1ULL << 63)
+#define PAGEMAP_PFN_MASK ((1ULL << 55) - 1)
+
+static uint64_t lookup_pfn(int pagemap_fd, struct kvm_vm *vm, uint64_t gva)
+{
+ uint64_t hva = (uint64_t) addr_gva2hva(vm, gva);
+ uint64_t entry;
+ uint64_t pfn;
+
+ entry = pread_uint64(pagemap_fd, "pagemap", hva / getpagesize());
+ if (!(entry & PAGEMAP_PRESENT))
+ return 0;
+
+ pfn = entry & PAGEMAP_PFN_MASK;
+ if (!pfn) {
+ print_skip("Looking up PFNs requires CAP_SYS_ADMIN");
+ exit(KSFT_SKIP);
+ }
+
+ return pfn;
+}
+
+static bool is_page_idle(int page_idle_fd, uint64_t pfn)
+{
+ uint64_t bits = pread_uint64(page_idle_fd, "page_idle", pfn / 64);
+
+ return !!((bits >> (pfn % 64)) & 1);
+}
+
+static void mark_page_idle(int page_idle_fd, uint64_t pfn)
+{
+ uint64_t bits = 1ULL << (pfn % 64);
+
+ TEST_ASSERT(pwrite(page_idle_fd, &bits, 8, 8 * (pfn / 64)) == 8,
+ "Set page_idle bits for PFN 0x%" PRIx64, pfn);
+}
+
+static void mark_vcpu_memory_idle(struct kvm_vm *vm, int vcpu_id)
+{
+ uint64_t base_gva = perf_test_args.vcpu_args[vcpu_id].gva;
+ uint64_t pages = perf_test_args.vcpu_args[vcpu_id].pages;
+ uint64_t page;
+ uint64_t still_idle = 0;
+ uint64_t no_pfn = 0;
+ int page_idle_fd;
+ int pagemap_fd;
+
+ /* If vCPUs are using an overlapping region, let vCPU 0 mark it idle. */
+ if (overlap_memory_access && vcpu_id)
+ return;
+
+ page_idle_fd = open("/sys/kernel/mm/page_idle/bitmap", O_RDWR);
+ TEST_ASSERT(page_idle_fd > 0, "Failed to open page_idle.");
+
+ pagemap_fd = open("/proc/self/pagemap", O_RDONLY);
+ TEST_ASSERT(pagemap_fd > 0, "Failed to open pagemap.");
+
+ for (page = 0; page < pages; page++) {
+ uint64_t gva = base_gva + page * perf_test_args.guest_page_size;
+ uint64_t pfn = lookup_pfn(pagemap_fd, vm, gva);
+
+ if (!pfn) {
+ no_pfn++;
+ continue;
+ }
+
+ if (is_page_idle(page_idle_fd, pfn)) {
+ still_idle++;
+ continue;
+ }
+
+ mark_page_idle(page_idle_fd, pfn);
+ }
+
+ /*
+ * Assumption: Less than 1% of pages are going to be swapped out from
+ * under us during this test.
+ */
+ TEST_ASSERT(no_pfn < pages / 100,
+ "vCPU %d: No PFN for %" PRIu64 " out of %" PRIu64 " pages.",
+ vcpu_id, no_pfn, pages);
+
+ /*
+ * Test that at least 90% of memory has been marked idle (the rest might
+ * not be marked idle because the pages have not yet made it to an LRU
+ * list or the translations are still cached in the TLB). 90% is
+ * arbitrary; high enough that we ensure most memory access went through
+ * access tracking but low enough as to not make the test too brittle
+ * over time and across architectures.
+ */
+ TEST_ASSERT(still_idle < pages / 10,
+ "vCPU%d: Too many pages still idle (%"PRIu64 " out of %"
+ PRIu64 ").\n",
+ vcpu_id, still_idle, pages);
+
+ close(page_idle_fd);
+ close(pagemap_fd);
+}
+
+static void assert_ucall(struct kvm_vm *vm, uint32_t vcpu_id,
+ uint64_t expected_ucall)
+{
+ struct ucall uc;
+ uint64_t actual_ucall = get_ucall(vm, vcpu_id, &uc);
+
+ TEST_ASSERT(expected_ucall == actual_ucall,
+ "Guest exited unexpectedly (expected ucall %" PRIu64
+ ", got %" PRIu64 ")",
+ expected_ucall, actual_ucall);
+}
+
+static bool spin_wait_for_next_iteration(int *current_iteration)
+{
+ int last_iteration = *current_iteration;
+
+ do {
+ if (READ_ONCE(done))
+ return false;
+
+ *current_iteration = READ_ONCE(iteration);
+ } while (last_iteration == *current_iteration);
+
+ return true;
+}
+
+static void *vcpu_thread_main(void *arg)
+{
+ struct perf_test_vcpu_args *vcpu_args = arg;
+ struct kvm_vm *vm = perf_test_args.vm;
+ int vcpu_id = vcpu_args->vcpu_id;
+ int current_iteration = -1;
+
+ vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
+
+ while (spin_wait_for_next_iteration(¤t_iteration)) {
+ switch (READ_ONCE(iteration_work)) {
+ case ITERATION_ACCESS_MEMORY:
+ vcpu_run(vm, vcpu_id);
+ assert_ucall(vm, vcpu_id, UCALL_SYNC);
+ break;
+ case ITERATION_MARK_IDLE:
+ mark_vcpu_memory_idle(vm, vcpu_id);
+ break;
+ };
+
+ vcpu_last_completed_iteration[vcpu_id] = current_iteration;
+ }
+
+ return NULL;
+}
+
+static void spin_wait_for_vcpu(int vcpu_id, int target_iteration)
+{
+ while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) !=
+ target_iteration) {
+ continue;
+ }
+}
+
+/* The type of memory accesses to perform in the VM. */
+enum access_type {
+ ACCESS_READ,
+ ACCESS_WRITE,
+};
+
+static void run_iteration(struct kvm_vm *vm, int vcpus, const char *description)
+{
+ struct timespec ts_start;
+ struct timespec ts_elapsed;
+ int next_iteration;
+ int vcpu_id;
+
+ /* Kick off the vCPUs by incrementing iteration. */
+ next_iteration = ++iteration;
+
+ clock_gettime(CLOCK_MONOTONIC, &ts_start);
+
+ /* Wait for all vCPUs to finish the iteration. */
+ for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++)
+ spin_wait_for_vcpu(vcpu_id, next_iteration);
+
+ ts_elapsed = timespec_elapsed(ts_start);
+ pr_info("%-30s: %ld.%09lds\n",
+ description, ts_elapsed.tv_sec, ts_elapsed.tv_nsec);
+}
+
+static void access_memory(struct kvm_vm *vm, int vcpus, enum access_type access,
+ const char *description)
+{
+ perf_test_args.wr_fract = (access == ACCESS_READ) ? INT_MAX : 1;
+ sync_global_to_guest(vm, perf_test_args);
+ iteration_work = ITERATION_ACCESS_MEMORY;
+ run_iteration(vm, vcpus, description);
+}
+
+static void mark_memory_idle(struct kvm_vm *vm, int vcpus)
+{
+ /*
+ * Even though this parallelizes the work across vCPUs, this is still a
+ * very slow operation because page_idle forces the test to mark one pfn
+ * at a time and the clear_young notifier serializes on the KVM MMU
+ * lock.
+ */
+ pr_debug("Marking VM memory idle (slow)...\n");
+ iteration_work = ITERATION_MARK_IDLE;
+ run_iteration(vm, vcpus, "Mark memory idle");
+}
+
+static pthread_t *create_vcpu_threads(int vcpus)
+{
+ pthread_t *vcpu_threads;
+ int i;
+
+ vcpu_threads = malloc(vcpus * sizeof(vcpu_threads[0]));
+ TEST_ASSERT(vcpu_threads, "Failed to allocate vcpu_threads.");
+
+ for (i = 0; i < vcpus; i++) {
+ vcpu_last_completed_iteration[i] = iteration;
+ pthread_create(&vcpu_threads[i], NULL, vcpu_thread_main,
+ &perf_test_args.vcpu_args[i]);
+ }
+
+ return vcpu_threads;
+}
+
+static void terminate_vcpu_threads(pthread_t *vcpu_threads, int vcpus)
+{
+ int i;
+
+ /* Set done to signal the vCPU threads to exit */
+ done = true;
+
+ for (i = 0; i < vcpus; i++)
+ pthread_join(vcpu_threads[i], NULL);
+}
+
+static void run_test(enum vm_guest_mode mode, void *arg)
+{
+ struct test_params *params = arg;
+ struct kvm_vm *vm;
+ pthread_t *vcpu_threads;
+ int vcpus = params->vcpus;
+
+ vm = perf_test_create_vm(mode, vcpus, params->vcpu_memory_bytes,
+ params->backing_src);
+
+ perf_test_setup_vcpus(vm, vcpus, params->vcpu_memory_bytes,
+ !overlap_memory_access);
+
+ vcpu_threads = create_vcpu_threads(vcpus);
+
+ pr_info("\n");
+ access_memory(vm, vcpus, ACCESS_WRITE, "Populating memory");
+
+ /* As a control, read and write to the populated memory first. */
+ access_memory(vm, vcpus, ACCESS_WRITE, "Writing to populated memory");
+ access_memory(vm, vcpus, ACCESS_READ, "Reading from populated memory");
+
+ /* Repeat on memory that has been marked as idle. */
+ mark_memory_idle(vm, vcpus);
+ access_memory(vm, vcpus, ACCESS_WRITE, "Writing to idle memory");
+ mark_memory_idle(vm, vcpus);
+ access_memory(vm, vcpus, ACCESS_READ, "Reading from idle memory");
+
+ terminate_vcpu_threads(vcpu_threads, vcpus);
+ free(vcpu_threads);
+ perf_test_destroy_vm(vm);
+}
+
+static void help(char *name)
+{
+ puts("");
+ printf("usage: %s [-h] [-m mode] [-b vcpu_bytes] [-v vcpus] [-o] [-s mem_type]\n",
+ name);
+ puts("");
+ printf(" -h: Display this help message.");
+ guest_modes_help();
+ printf(" -b: specify the size of the memory region which should be\n"
+ " dirtied by each vCPU. e.g. 10M or 3G.\n"
+ " (default: 1G)\n");
+ printf(" -v: specify the number of vCPUs to run.\n");
+ printf(" -o: Overlap guest memory accesses instead of partitioning\n"
+ " them into a separate region of memory for each vCPU.\n");
+ printf(" -s: specify the type of memory that should be used to\n"
+ " back the guest data region.\n\n");
+ backing_src_help();
+ puts("");
+ exit(0);
+}
+
+int main(int argc, char *argv[])
+{
+ struct test_params params = {
+ .backing_src = VM_MEM_SRC_ANONYMOUS,
+ .vcpu_memory_bytes = DEFAULT_PER_VCPU_MEM_SIZE,
+ .vcpus = 1,
+ };
+ int page_idle_fd;
+ int opt;
+
+ guest_modes_append_default();
+
+ while ((opt = getopt(argc, argv, "hm:b:v:os:")) != -1) {
+ switch (opt) {
+ case 'm':
+ guest_modes_cmdline(optarg);
+ break;
+ case 'b':
+ params.vcpu_memory_bytes = parse_size(optarg);
+ break;
+ case 'v':
+ params.vcpus = atoi(optarg);
+ break;
+ case 'o':
+ overlap_memory_access = true;
+ break;
+ case 's':
+ params.backing_src = parse_backing_src_type(optarg);
+ break;
+ case 'h':
+ default:
+ help(argv[0]);
+ break;
+ }
+ }
+
+ page_idle_fd = open("/sys/kernel/mm/page_idle/bitmap", O_RDWR);
+ if (page_idle_fd < 0) {
+ print_skip("CONFIG_IDLE_PAGE_TRACKING is not enabled");
+ exit(KSFT_SKIP);
+ }
+ close(page_idle_fd);
+
+ for_each_guest_mode(run_test, ¶ms);
+
+ return 0;
+}
break;
case 'o':
p.partition_vcpu_memory_access = false;
+ break;
case 's':
p.backing_src = parse_backing_src_type(optarg);
break;
VM_MODE_P40V48_64K,
VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */
VM_MODE_P47V64_4K,
+ VM_MODE_P44V64_4K,
NUM_VM_MODES,
};
#elif defined(__s390x__)
-#define VM_MODE_DEFAULT VM_MODE_P47V64_4K
+#define VM_MODE_DEFAULT VM_MODE_P44V64_4K
#define MIN_PAGE_SHIFT 12U
#define ptes_per_page(page_size) ((page_size) / 16)
#define HV_X64_GUEST_DEBUGGING_AVAILABLE BIT(1)
#define HV_X64_PERF_MONITOR_AVAILABLE BIT(2)
#define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE BIT(3)
-#define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE BIT(4)
+#define HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE BIT(4)
#define HV_X64_GUEST_IDLE_STATE_AVAILABLE BIT(5)
#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE BIT(8)
#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(10)
#define HV_STATUS_INVALID_CONNECTION_ID 18
#define HV_STATUS_INSUFFICIENT_BUFFERS 19
+/* hypercall options */
+#define HV_HYPERCALL_FAST_BIT BIT(16)
+
#endif /* !SELFTEST_KVM_HYPERV_H */
void vm_init_descriptor_tables(struct kvm_vm *vm)
{
vm->handlers = vm_vaddr_alloc(vm, sizeof(struct handlers),
- vm->page_size, 0, 0);
+ vm->page_size);
*(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers;
}
}
}
#endif
+#ifdef __s390x__
+ {
+ int kvm_fd, vm_fd;
+ struct kvm_s390_vm_cpu_processor info;
+
+ kvm_fd = open_kvm_dev_path_or_exit();
+ vm_fd = ioctl(kvm_fd, KVM_CREATE_VM, 0);
+ kvm_device_access(vm_fd, KVM_S390_VM_CPU_MODEL,
+ KVM_S390_VM_CPU_PROCESSOR, &info, false);
+ close(vm_fd);
+ close(kvm_fd);
+ /* Starting with z13 we have 47bits of physical address */
+ if (info.ibc >= 0x30)
+ guest_mode_append(VM_MODE_P47V64_4K, true, true);
+ }
+#endif
}
void for_each_guest_mode(void (*func)(enum vm_guest_mode, void *), void *arg)
[VM_MODE_P40V48_64K] = "PA-bits:40, VA-bits:48, 64K pages",
[VM_MODE_PXXV48_4K] = "PA-bits:ANY, VA-bits:48, 4K pages",
[VM_MODE_P47V64_4K] = "PA-bits:47, VA-bits:64, 4K pages",
+ [VM_MODE_P44V64_4K] = "PA-bits:44, VA-bits:64, 4K pages",
};
_Static_assert(sizeof(strings)/sizeof(char *) == NUM_VM_MODES,
"Missing new mode strings?");
{ 40, 48, 0x10000, 16 },
{ 0, 0, 0x1000, 12 },
{ 47, 64, 0x1000, 12 },
+ { 44, 64, 0x1000, 12 },
};
_Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
"Missing new mode params?");
case VM_MODE_P47V64_4K:
vm->pgtable_levels = 5;
break;
+ case VM_MODE_P44V64_4K:
+ vm->pgtable_levels = 5;
+ break;
default:
TEST_FAIL("Unknown guest mode, mode: 0x%x", mode);
}
(max_mem_slots - 1), MEM_REGION_SIZE >> 10);
mem = mmap(NULL, (size_t)max_mem_slots * MEM_REGION_SIZE + alignment,
- PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE, -1, 0);
TEST_ASSERT(mem != MAP_FAILED, "Failed to mmap() host");
mem_aligned = (void *)(((size_t) mem + alignment - 1) & ~(alignment - 1));
run_delay = get_run_delay();
pthread_create(&thread, &attr, do_steal_time, NULL);
do
- pthread_yield();
+ sched_yield();
while (get_run_delay() - run_delay < MIN_RUN_DELAY_NS);
pthread_join(thread, NULL);
run_delay = get_run_delay() - run_delay;
vcpu_set_hv_cpuid(vm, VCPU_ID);
tsc_page_gva = vm_vaddr_alloc_page(vm);
- memset(addr_gpa2hva(vm, tsc_page_gva), 0x0, getpagesize());
+ memset(addr_gva2hva(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));
}
static int nr_gp;
+static int nr_ud;
static inline u64 hypercall(u64 control, vm_vaddr_t input_address,
vm_vaddr_t output_address)
regs->rip = (uint64_t)&wrmsr_end;
}
+static void guest_ud_handler(struct ex_regs *regs)
+{
+ nr_ud++;
+ regs->rip += 3;
+}
+
struct msr_data {
uint32_t idx;
bool available;
struct hcall_data {
uint64_t control;
uint64_t expect;
+ bool ud_expected;
};
static void guest_msr(struct msr_data *msr)
static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall)
{
int i = 0;
+ u64 res, input, output;
wrmsr(HV_X64_MSR_GUEST_OS_ID, LINUX_OS_ID);
wrmsr(HV_X64_MSR_HYPERCALL, pgs_gpa);
while (hcall->control) {
- GUEST_ASSERT(hypercall(hcall->control, pgs_gpa,
- pgs_gpa + 4096) == hcall->expect);
+ nr_ud = 0;
+ if (!(hcall->control & HV_HYPERCALL_FAST_BIT)) {
+ input = pgs_gpa;
+ output = pgs_gpa + 4096;
+ } else {
+ input = output = 0;
+ }
+
+ res = hypercall(hcall->control, input, output);
+ if (hcall->ud_expected)
+ GUEST_ASSERT(nr_ud == 1);
+ else
+ GUEST_ASSERT(res == hcall->expect);
+
GUEST_SYNC(i++);
}
recomm.ebx = 0xfff;
hcall->expect = HV_STATUS_SUCCESS;
break;
-
case 17:
+ /* XMM fast hypercall */
+ hcall->control = HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE | HV_HYPERCALL_FAST_BIT;
+ hcall->ud_expected = true;
+ break;
+ case 18:
+ feat.edx |= HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE;
+ hcall->ud_expected = false;
+ hcall->expect = HV_STATUS_SUCCESS;
+ break;
+
+ case 19:
/* END */
hcall->control = 0;
break;
vm_init_descriptor_tables(vm);
vcpu_init_descriptor_tables(vm, VCPU_ID);
- vm_handle_exception(vm, GP_VECTOR, guest_gp_handler);
+ vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler);
pr_info("Testing access to Hyper-V specific MSRs\n");
guest_test_msrs_access(vm, addr_gva2hva(vm, msr_gva),
/* Test hypercalls */
vm = vm_create_default(VCPU_ID, 0, guest_hcall);
+ vm_init_descriptor_tables(vm);
+ vcpu_init_descriptor_tables(vm, VCPU_ID);
+ vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler);
+
/* Hypercall input/output */
hcall_page = vm_vaddr_alloc_pages(vm, 2);
memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize());
/* Set up a #PF handler to eat the RSVD #PF and signal all done! */
vm_init_descriptor_tables(vm);
vcpu_init_descriptor_tables(vm, VCPU_ID);
- vm_handle_exception(vm, PF_VECTOR, guest_pf_handler);
+ vm_install_exception_handler(vm, PF_VECTOR, guest_pf_handler);
r = _vcpu_run(vm, VCPU_ID);
TEST_ASSERT(r == 0, "vcpu_run failed: %d\n", r);
: "+a" (phase));
}
-void self_smi(void)
+static void self_smi(void)
{
x2apic_write_reg(APIC_ICR,
APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_SMI);
}
-void guest_code(void *arg)
+static void l2_guest_code(void)
{
+ sync_with_host(8);
+
+ sync_with_host(10);
+
+ vmcall();
+}
+
+static void guest_code(void *arg)
+{
+ #define L2_GUEST_STACK_SIZE 64
+ unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
uint64_t apicbase = rdmsr(MSR_IA32_APICBASE);
+ struct svm_test_data *svm = arg;
+ struct vmx_pages *vmx_pages = arg;
sync_with_host(1);
sync_with_host(4);
if (arg) {
- if (cpu_has_svm())
- generic_svm_setup(arg, NULL, NULL);
- else
- GUEST_ASSERT(prepare_for_vmx_operation(arg));
+ if (cpu_has_svm()) {
+ generic_svm_setup(svm, l2_guest_code,
+ &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+ } else {
+ GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+ GUEST_ASSERT(load_vmcs(vmx_pages));
+ prepare_vmcs(vmx_pages, l2_guest_code,
+ &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+ }
sync_with_host(5);
self_smi();
sync_with_host(7);
+
+ if (cpu_has_svm()) {
+ run_guest(svm->vmcb, svm->vmcb_gpa);
+ svm->vmcb->save.rip += 3;
+ run_guest(svm->vmcb, svm->vmcb_gpa);
+ } else {
+ vmlaunch();
+ vmresume();
+ }
+
+ /* Stages 8-11 are eaten by SMM (SMRAM_STAGE reported instead) */
+ sync_with_host(12);
}
sync_with_host(DONE);
}
+void inject_smi(struct kvm_vm *vm)
+{
+ struct kvm_vcpu_events events;
+
+ vcpu_events_get(vm, VCPU_ID, &events);
+
+ events.smi.pending = 1;
+ events.flags |= KVM_VCPUEVENT_VALID_SMM;
+
+ vcpu_events_set(vm, VCPU_ID, &events);
+}
+
int main(int argc, char *argv[])
{
vm_vaddr_t nested_gva = 0;
"Unexpected stage: #%x, got %x",
stage, stage_reported);
+ /*
+ * Enter SMM during L2 execution and check that we correctly
+ * return from it. Do not perform save/restore while in SMM yet.
+ */
+ if (stage == 8) {
+ inject_smi(vm);
+ continue;
+ }
+
+ /*
+ * Perform save/restore while the guest is in SMM triggered
+ * during L2 execution.
+ */
+ if (stage == 10)
+ inject_smi(vm);
+
state = vcpu_save_state(vm, VCPU_ID);
kvm_vm_release(vm);
kvm_vm_restart(vm, O_RDWR);
#
echo $error > $NOTIFIER_ERR_INJECT_DIR/actions/MEM_GOING_OFFLINE/error
for memory in `hotpluggable_online_memory`; do
- offline_memory_expect_fail $memory
+ if [ $((RANDOM % 100)) -lt $ratio ]; then
+ offline_memory_expect_fail $memory
+ fi
done
echo 0 > $NOTIFIER_ERR_INJECT_DIR/actions/MEM_GOING_OFFLINE/error
fi
log_test $? 0 "IPv4: ${desc}"
- if [ "$with_redirect" = "yes" ]; then
+ # No PMTU info for test "redirect" and "mtu exception plus redirect"
+ if [ "$with_redirect" = "yes" ] && [ "$desc" != "redirect exception plus mtu" ]; then
ip -netns h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | \
- grep -q "${H2_N2_IP6} from :: via ${R2_LLADDR} dev br0.*${mtu}"
+ grep -v "mtu" | grep -q "${H2_N2_IP6} .*via ${R2_LLADDR} dev br0"
elif [ -n "${mtu}" ]; then
ip -netns h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | \
grep -q "${mtu}"
MONITOR_ACQUIRE,
EXPIRE_STATE,
EXPIRE_POLICY,
+ SPDINFO_ATTRS,
};
const char *desc_name[] = {
"create tunnel",
"alloc spi",
"monitor acquire",
"expire state",
- "expire policy"
+ "expire policy",
+ "spdinfo attributes",
+ ""
};
struct xfrm_desc {
enum desc_type type;
return ret;
}
+static int xfrm_spdinfo_set_thresh(int xfrm_sock, uint32_t *seq,
+ unsigned thresh4_l, unsigned thresh4_r,
+ unsigned thresh6_l, unsigned thresh6_r,
+ bool add_bad_attr)
+
+{
+ struct {
+ struct nlmsghdr nh;
+ union {
+ uint32_t unused;
+ int error;
+ };
+ char attrbuf[MAX_PAYLOAD];
+ } req;
+ struct xfrmu_spdhthresh thresh;
+
+ memset(&req, 0, sizeof(req));
+ req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(req.unused));
+ req.nh.nlmsg_type = XFRM_MSG_NEWSPDINFO;
+ req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+ req.nh.nlmsg_seq = (*seq)++;
+
+ thresh.lbits = thresh4_l;
+ thresh.rbits = thresh4_r;
+ if (rtattr_pack(&req.nh, sizeof(req), XFRMA_SPD_IPV4_HTHRESH, &thresh, sizeof(thresh)))
+ return -1;
+
+ thresh.lbits = thresh6_l;
+ thresh.rbits = thresh6_r;
+ if (rtattr_pack(&req.nh, sizeof(req), XFRMA_SPD_IPV6_HTHRESH, &thresh, sizeof(thresh)))
+ return -1;
+
+ if (add_bad_attr) {
+ BUILD_BUG_ON(XFRMA_IF_ID <= XFRMA_SPD_MAX + 1);
+ if (rtattr_pack(&req.nh, sizeof(req), XFRMA_IF_ID, NULL, 0)) {
+ pr_err("adding attribute failed: no space");
+ return -1;
+ }
+ }
+
+ if (send(xfrm_sock, &req, req.nh.nlmsg_len, 0) < 0) {
+ pr_err("send()");
+ return -1;
+ }
+
+ if (recv(xfrm_sock, &req, sizeof(req), 0) < 0) {
+ pr_err("recv()");
+ return -1;
+ } else if (req.nh.nlmsg_type != NLMSG_ERROR) {
+ printk("expected NLMSG_ERROR, got %d", (int)req.nh.nlmsg_type);
+ return -1;
+ }
+
+ if (req.error) {
+ printk("NLMSG_ERROR: %d: %s", req.error, strerror(-req.error));
+ return -1;
+ }
+
+ return 0;
+}
+
+static int xfrm_spdinfo_attrs(int xfrm_sock, uint32_t *seq)
+{
+ struct {
+ struct nlmsghdr nh;
+ union {
+ uint32_t unused;
+ int error;
+ };
+ char attrbuf[MAX_PAYLOAD];
+ } req;
+
+ if (xfrm_spdinfo_set_thresh(xfrm_sock, seq, 32, 31, 120, 16, false)) {
+ pr_err("Can't set SPD HTHRESH");
+ return KSFT_FAIL;
+ }
+
+ memset(&req, 0, sizeof(req));
+
+ req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(req.unused));
+ req.nh.nlmsg_type = XFRM_MSG_GETSPDINFO;
+ req.nh.nlmsg_flags = NLM_F_REQUEST;
+ req.nh.nlmsg_seq = (*seq)++;
+ if (send(xfrm_sock, &req, req.nh.nlmsg_len, 0) < 0) {
+ pr_err("send()");
+ return KSFT_FAIL;
+ }
+
+ if (recv(xfrm_sock, &req, sizeof(req), 0) < 0) {
+ pr_err("recv()");
+ return KSFT_FAIL;
+ } else if (req.nh.nlmsg_type == XFRM_MSG_NEWSPDINFO) {
+ size_t len = NLMSG_PAYLOAD(&req.nh, sizeof(req.unused));
+ struct rtattr *attr = (void *)req.attrbuf;
+ int got_thresh = 0;
+
+ for (; RTA_OK(attr, len); attr = RTA_NEXT(attr, len)) {
+ if (attr->rta_type == XFRMA_SPD_IPV4_HTHRESH) {
+ struct xfrmu_spdhthresh *t = RTA_DATA(attr);
+
+ got_thresh++;
+ if (t->lbits != 32 || t->rbits != 31) {
+ pr_err("thresh differ: %u, %u",
+ t->lbits, t->rbits);
+ return KSFT_FAIL;
+ }
+ }
+ if (attr->rta_type == XFRMA_SPD_IPV6_HTHRESH) {
+ struct xfrmu_spdhthresh *t = RTA_DATA(attr);
+
+ got_thresh++;
+ if (t->lbits != 120 || t->rbits != 16) {
+ pr_err("thresh differ: %u, %u",
+ t->lbits, t->rbits);
+ return KSFT_FAIL;
+ }
+ }
+ }
+ if (got_thresh != 2) {
+ pr_err("only %d thresh returned by XFRM_MSG_GETSPDINFO", got_thresh);
+ return KSFT_FAIL;
+ }
+ } else if (req.nh.nlmsg_type != NLMSG_ERROR) {
+ printk("expected NLMSG_ERROR, got %d", (int)req.nh.nlmsg_type);
+ return KSFT_FAIL;
+ } else {
+ printk("NLMSG_ERROR: %d: %s", req.error, strerror(-req.error));
+ return -1;
+ }
+
+ /* Restore the default */
+ if (xfrm_spdinfo_set_thresh(xfrm_sock, seq, 32, 32, 128, 128, false)) {
+ pr_err("Can't restore SPD HTHRESH");
+ return KSFT_FAIL;
+ }
+
+ /*
+ * At this moment xfrm uses nlmsg_parse_deprecated(), which
+ * implies NL_VALIDATE_LIBERAL - ignoring attributes with
+ * (type > maxtype). nla_parse_depricated_strict() would enforce
+ * it. Or even stricter nla_parse().
+ * Right now it's not expected to fail, but to be ignored.
+ */
+ if (xfrm_spdinfo_set_thresh(xfrm_sock, seq, 32, 32, 128, 128, true))
+ return KSFT_PASS;
+
+ return KSFT_PASS;
+}
+
static int child_serv(int xfrm_sock, uint32_t *seq,
unsigned int nr, int cmd_fd, void *buf, struct xfrm_desc *desc)
{
case EXPIRE_POLICY:
ret = xfrm_expire_policy(xfrm_sock, &seq, nr, &desc);
break;
+ case SPDINFO_ATTRS:
+ ret = xfrm_spdinfo_attrs(xfrm_sock, &seq);
+ break;
default:
printk("Unknown desc type %d", desc.type);
exit(KSFT_FAIL);
* sizeof(xfrm_user_polexpire) = 168 | sizeof(xfrm_user_polexpire) = 176
*
* Check the affected by the UABI difference structures.
+ * Also, check translation for xfrm_set_spdinfo: it has it's own attributes
+ * which needs to be correctly copied, but not translated.
*/
-const unsigned int compat_plan = 4;
+const unsigned int compat_plan = 5;
static int write_compat_struct_tests(int test_desc_fd)
{
struct xfrm_desc desc = {};
if (__write_desc(test_desc_fd, &desc))
return -1;
+ desc.type = SPDINFO_ATTRS;
+ if (__write_desc(test_desc_fd, &desc))
+ return -1;
+
return 0;
}
ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow
run_tests $ns1 $ns2 10.0.1.1
- chk_join_nr "subflows limited by server w cookies" 2 2 1
+ chk_join_nr "subflows limited by server w cookies" 2 1 1
# test signal address with cookies
reset_with_cookies
#include <sys/socket.h>
#include <sys/wait.h>
#include <linux/tcp.h>
+#include <linux/udp.h>
#include <arpa/inet.h>
#include <net/if.h>
#include <netinet/in.h>
+#include <netinet/ip.h>
#include <netdb.h>
#include <fcntl.h>
#include <libgen.h>
#include <time.h>
#include <errno.h>
+#include <linux/xfrm.h>
+#include <linux/ipsec.h>
+#include <linux/pfkeyv2.h>
+
#ifndef IPV6_UNICAST_IF
#define IPV6_UNICAST_IF 76
#endif
struct in_addr in;
struct in6_addr in6;
} expected_raddr;
+
+ /* ESP in UDP encap test */
+ int use_xfrm;
};
static int server_mode;
return 0;
}
+static int config_xfrm_policy(int sd, struct sock_args *args)
+{
+ struct xfrm_userpolicy_info policy = {};
+ int type = UDP_ENCAP_ESPINUDP;
+ int xfrm_af = IP_XFRM_POLICY;
+ int level = SOL_IP;
+
+ if (args->type != SOCK_DGRAM) {
+ log_error("Invalid socket type. Only DGRAM could be used for XFRM\n");
+ return 1;
+ }
+
+ policy.action = XFRM_POLICY_ALLOW;
+ policy.sel.family = args->version;
+ if (args->version == AF_INET6) {
+ xfrm_af = IPV6_XFRM_POLICY;
+ level = SOL_IPV6;
+ }
+
+ policy.dir = XFRM_POLICY_OUT;
+ if (setsockopt(sd, level, xfrm_af, &policy, sizeof(policy)) < 0)
+ return 1;
+
+ policy.dir = XFRM_POLICY_IN;
+ if (setsockopt(sd, level, xfrm_af, &policy, sizeof(policy)) < 0)
+ return 1;
+
+ if (setsockopt(sd, IPPROTO_UDP, UDP_ENCAP, &type, sizeof(type)) < 0) {
+ log_err_errno("Failed to set xfrm encap");
+ return 1;
+ }
+
+ return 0;
+}
+
static int lsock_init(struct sock_args *args)
{
long flags;
if (fcntl(sd, F_SETFD, FD_CLOEXEC) < 0)
log_err_errno("Failed to set close-on-exec flag");
+ if (args->use_xfrm && config_xfrm_policy(sd, args)) {
+ log_err_errno("Failed to set xfrm policy");
+ goto err;
+ }
+
out:
return sd;
return client_status;
}
-#define GETOPT_STR "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SCi6L:0:1:2:3:Fbq"
+#define GETOPT_STR "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SCi6xL:0:1:2:3:Fbq"
static void print_usage(char *prog)
{
" -D|R datagram (D) / raw (R) socket (default stream)\n"
" -l addr local address to bind to in server mode\n"
" -c addr local address to bind to in client mode\n"
+ " -x configure XFRM policy on socket\n"
"\n"
" -d dev bind socket to given device name\n"
" -I dev bind socket to given device name - server mode\n"
case 'q':
quiet = 1;
break;
+ case 'x':
+ args.use_xfrm = 1;
+ break;
default:
print_usage(argv[0]);
return 1;
# below for IPv6 doesn't apply here, because, on IPv4, administrative MTU
# changes alone won't affect PMTU
#
+# - pmtu_vti4_udp_exception
+# Same as pmtu_vti4_exception, but using ESP-in-UDP
+#
+# - pmtu_vti4_udp_routed_exception
+# Set up vti tunnel on top of veth connected through routing namespace and
+# add xfrm states and policies with ESP-in-UDP encapsulation. Check that
+# route exception is not created if link layer MTU is not exceeded, then
+# lower MTU on second part of routed environment and check that exception
+# is created with the expected PMTU.
+#
# - pmtu_vti6_exception
# Set up vti6 tunnel on top of veth, with xfrm states and policies, in two
# namespaces with matching endpoints. Check that route exception is
# decrease and increase MTU of tunnel, checking that route exception PMTU
# changes accordingly
#
+# - pmtu_vti6_udp_exception
+# Same as pmtu_vti6_exception, but using ESP-in-UDP
+#
+# - pmtu_vti6_udp_routed_exception
+# Same as pmtu_vti6_udp_routed_exception but with routing between vti
+# endpoints
+#
# - pmtu_vti4_default_mtu
# Set up vti4 tunnel on top of veth, in two namespaces with matching
# endpoints. Check that MTU assigned to vti interface is the MTU of the
pmtu_ipv6_ipv6_exception IPv6 over IPv6: PMTU exceptions 1
pmtu_vti6_exception vti6: PMTU exceptions 0
pmtu_vti4_exception vti4: PMTU exceptions 0
+ pmtu_vti6_udp_exception vti6: PMTU exceptions (ESP-in-UDP) 0
+ pmtu_vti4_udp_exception vti4: PMTU exceptions (ESP-in-UDP) 0
+ pmtu_vti6_udp_routed_exception vti6: PMTU exceptions, routed (ESP-in-UDP) 0
+ pmtu_vti4_udp_routed_exception vti4: PMTU exceptions, routed (ESP-in-UDP) 0
pmtu_vti4_default_mtu vti4: default MTU assignment 0
pmtu_vti6_default_mtu vti6: default MTU assignment 0
pmtu_vti4_link_add_mtu vti4: MTU setting on link creation 0
ns_c="ip netns exec ${NS_C}"
ns_r1="ip netns exec ${NS_R1}"
ns_r2="ip netns exec ${NS_R2}"
-
# Addressing and routing for tests with routers: four network segments, with
# index SEGMENT between 1 and 4, a common prefix (PREFIX4 or PREFIX6) and an
# identifier ID, which is 1 for hosts (A and B), 2 for routers (R1 and R2).
A ${prefix6}:${b_r2}::1 ${prefix6}:${a_r2}::2
B default ${prefix6}:${b_r1}::2
"
-
USE_NH="no"
# ns family nh id destination gateway
nexthops="
err_buf=
tcpdump_pids=
+nettest_pids=
err() {
err_buf="${err_buf}${1}
setup_vti 6 ${veth6_a_addr} ${veth6_b_addr} ${tunnel6_a_addr} ${tunnel6_b_addr} ${tunnel6_mask}
}
+setup_vti4routed() {
+ setup_vti 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 ${tunnel4_a_addr} ${tunnel4_b_addr} ${tunnel4_mask}
+}
+
+setup_vti6routed() {
+ setup_vti 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 ${tunnel6_a_addr} ${tunnel6_b_addr} ${tunnel6_mask}
+}
+
setup_vxlan_or_geneve() {
type="${1}"
a_addr="${2}"
proto=${1}
veth_a_addr="${2}"
veth_b_addr="${3}"
+ encap=${4}
- run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel || return 1
- run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
+ run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap} || return 1
+ run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap}
run_cmd ${ns_a} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel
run_cmd ${ns_a} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel
- run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
- run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
+ run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap}
+ run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap}
run_cmd ${ns_b} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel
run_cmd ${ns_b} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel
}
+setup_nettest_xfrm() {
+ which nettest >/dev/null
+ if [ $? -ne 0 ]; then
+ echo "'nettest' command not found; skipping tests"
+ return 1
+ fi
+
+ [ ${1} -eq 6 ] && proto="-6" || proto=""
+ port=${2}
+
+ run_cmd ${ns_a} nettest ${proto} -q -D -s -x -p ${port} -t 5 &
+ nettest_pids="${nettest_pids} $!"
+
+ run_cmd ${ns_b} nettest ${proto} -q -D -s -x -p ${port} -t 5 &
+ nettest_pids="${nettest_pids} $!"
+}
+
setup_xfrm4() {
setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr}
}
setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr}
}
+setup_xfrm4udp() {
+ setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} "encap espinudp 4500 4500 0.0.0.0"
+ setup_nettest_xfrm 4 4500
+}
+
+setup_xfrm6udp() {
+ setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} "encap espinudp 4500 4500 0.0.0.0"
+ setup_nettest_xfrm 6 4500
+}
+
+setup_xfrm4udprouted() {
+ setup_xfrm 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "encap espinudp 4500 4500 0.0.0.0"
+ setup_nettest_xfrm 4 4500
+}
+
+setup_xfrm6udprouted() {
+ setup_xfrm 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "encap espinudp 4500 4500 0.0.0.0"
+ setup_nettest_xfrm 6 4500
+}
+
setup_routing_old() {
for i in ${routes}; do
[ "${ns}" = "" ] && ns="${i}" && continue
done
tcpdump_pids=
+ for pid in ${nettest_pids}; do
+ kill ${pid}
+ done
+ nettest_pids=
+
for n in ${NS_A} ${NS_B} ${NS_C} ${NS_R1} ${NS_R2}; do
ip netns del ${n} 2> /dev/null
done
return ${fail}
}
+test_pmtu_vti4_udp_exception() {
+ setup namespaces veth vti4 xfrm4udp || return $ksft_skip
+ trace "${ns_a}" veth_a "${ns_b}" veth_b \
+ "${ns_a}" vti4_a "${ns_b}" vti4_b
+
+ veth_mtu=1500
+ vti_mtu=$((veth_mtu - 20))
+
+ # UDP SPI SN IV ICV pad length next header
+ esp_payload_rfc4106=$((vti_mtu - 8 - 4 - 4 - 8 - 16 - 1 - 1))
+ ping_payload=$((esp_payload_rfc4106 - 28))
+
+ mtu "${ns_a}" veth_a ${veth_mtu}
+ mtu "${ns_b}" veth_b ${veth_mtu}
+ mtu "${ns_a}" vti4_a ${vti_mtu}
+ mtu "${ns_b}" vti4_b ${vti_mtu}
+
+ # Send DF packet without exceeding link layer MTU, check that no
+ # exception is created
+ run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel4_b_addr}
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
+ check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1
+
+ # Now exceed link layer MTU by one byte, check that exception is created
+ # with the right PMTU value
+ run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((ping_payload + 1)) ${tunnel4_b_addr}
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
+ check_pmtu_value "${esp_payload_rfc4106}" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106 + 1)))"
+}
+
+test_pmtu_vti6_udp_exception() {
+ setup namespaces veth vti6 xfrm6udp || return $ksft_skip
+ trace "${ns_a}" veth_a "${ns_b}" veth_b \
+ "${ns_a}" vti6_a "${ns_b}" vti6_b
+ fail=0
+
+ # Create route exception by exceeding link layer MTU
+ mtu "${ns_a}" veth_a 4000
+ mtu "${ns_b}" veth_b 4000
+ mtu "${ns_a}" vti6_a 5000
+ mtu "${ns_b}" vti6_b 5000
+ run_cmd ${ns_a} ${ping6} -q -i 0.1 -w 1 -s 60000 ${tunnel6_b_addr}
+
+ # Check that exception was created
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+ check_pmtu_value any "${pmtu}" "creating tunnel exceeding link layer MTU" || return 1
+
+ # Decrease tunnel MTU, check for PMTU decrease in route exception
+ mtu "${ns_a}" vti6_a 3000
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+ check_pmtu_value "3000" "${pmtu}" "decreasing tunnel MTU" || fail=1
+
+ # Increase tunnel MTU, check for PMTU increase in route exception
+ mtu "${ns_a}" vti6_a 9000
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+ check_pmtu_value "9000" "${pmtu}" "increasing tunnel MTU" || fail=1
+
+ return ${fail}
+}
+
+test_pmtu_vti4_udp_routed_exception() {
+ setup namespaces routing vti4routed xfrm4udprouted || return $ksft_skip
+ trace "${ns_a}" veth_A-R1 "${ns_b}" veth_B-R1 \
+ "${ns_a}" vti4_a "${ns_b}" vti4_b
+
+ veth_mtu=1500
+ vti_mtu=$((veth_mtu - 20))
+
+ # UDP SPI SN IV ICV pad length next header
+ esp_payload_rfc4106=$((vti_mtu - 8 - 4 - 4 - 8 - 16 - 1 - 1))
+ ping_payload=$((esp_payload_rfc4106 - 28))
+
+ mtu "${ns_a}" veth_A-R1 ${veth_mtu}
+ mtu "${ns_r1}" veth_R1-A ${veth_mtu}
+ mtu "${ns_b}" veth_B-R1 ${veth_mtu}
+ mtu "${ns_r1}" veth_R1-B ${veth_mtu}
+
+ mtu "${ns_a}" vti4_a ${vti_mtu}
+ mtu "${ns_b}" vti4_b ${vti_mtu}
+
+ # Send DF packet without exceeding link layer MTU, check that no
+ # exception is created
+ run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel4_b_addr}
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
+ check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1
+
+ # Now decrease link layer MTU by 8 bytes on R1, check that exception is created
+ # with the right PMTU value
+ mtu "${ns_r1}" veth_R1-B $((veth_mtu - 8))
+ run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((ping_payload)) ${tunnel4_b_addr}
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
+ check_pmtu_value "$((esp_payload_rfc4106 - 8))" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106)))"
+}
+
+test_pmtu_vti6_udp_routed_exception() {
+ setup namespaces routing vti6routed xfrm6udprouted || return $ksft_skip
+ trace "${ns_a}" veth_A-R1 "${ns_b}" veth_B-R1 \
+ "${ns_a}" vti6_a "${ns_b}" vti6_b
+
+ veth_mtu=1500
+ vti_mtu=$((veth_mtu - 40))
+
+ # UDP SPI SN IV ICV pad length next header
+ esp_payload_rfc4106=$((vti_mtu - 8 - 4 - 4 - 8 - 16 - 1 - 1))
+ ping_payload=$((esp_payload_rfc4106 - 48))
+
+ mtu "${ns_a}" veth_A-R1 ${veth_mtu}
+ mtu "${ns_r1}" veth_R1-A ${veth_mtu}
+ mtu "${ns_b}" veth_B-R1 ${veth_mtu}
+ mtu "${ns_r1}" veth_R1-B ${veth_mtu}
+
+ # mtu "${ns_a}" vti6_a ${vti_mtu}
+ # mtu "${ns_b}" vti6_b ${vti_mtu}
+
+ run_cmd ${ns_a} ${ping6} -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel6_b_addr}
+
+ # Check that exception was not created
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+ check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1
+
+ # Now decrease link layer MTU by 8 bytes on R1, check that exception is created
+ # with the right PMTU value
+ mtu "${ns_r1}" veth_R1-B $((veth_mtu - 8))
+ run_cmd ${ns_a} ${ping6} -q -M want -i 0.1 -w 1 -s $((ping_payload)) ${tunnel6_b_addr}
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+ check_pmtu_value "$((esp_payload_rfc4106 - 8))" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106)))"
+
+}
+
test_pmtu_vti4_default_mtu() {
setup namespaces veth vti4 || return $ksft_skip
{
if (error)
printf("invalid option: %s\n", error);
- printf("timestamping interface option*\n\n"
+ printf("timestamping <interface> [bind_phc_index] [option]*\n\n"
"Options:\n"
" IP_MULTICAST_LOOP - looping outgoing multicasts\n"
" SO_TIMESTAMP - normal software time stamping, ms resolution\n"
" SOF_TIMESTAMPING_RX_SOFTWARE - software fallback for incoming packets\n"
" SOF_TIMESTAMPING_SOFTWARE - request reporting of software time stamps\n"
" SOF_TIMESTAMPING_RAW_HARDWARE - request reporting of raw HW time stamps\n"
+ " SOF_TIMESTAMPING_BIND_PHC - request to bind a PHC of PTP vclock\n"
" SIOCGSTAMP - check last socket time stamp\n"
" SIOCGSTAMPNS - more accurate socket time stamp\n"
" PTPV2 - use PTPv2 messages\n");
int main(int argc, char **argv)
{
- int so_timestamping_flags = 0;
int so_timestamp = 0;
int so_timestampns = 0;
int siocgstamp = 0;
struct ifreq device;
struct ifreq hwtstamp;
struct hwtstamp_config hwconfig, hwconfig_requested;
+ struct so_timestamping so_timestamping_get = { 0, -1 };
+ struct so_timestamping so_timestamping = { 0, -1 };
struct sockaddr_in addr;
struct ip_mreq imr;
struct in_addr iaddr;
exit(1);
}
- for (i = 2; i < argc; i++) {
+ if (argc >= 3 && sscanf(argv[2], "%d", &so_timestamping.bind_phc) == 1)
+ val = 3;
+ else
+ val = 2;
+
+ for (i = val; i < argc; i++) {
if (!strcasecmp(argv[i], "SO_TIMESTAMP"))
so_timestamp = 1;
else if (!strcasecmp(argv[i], "SO_TIMESTAMPNS"))
else if (!strcasecmp(argv[i], "PTPV2"))
ptpv2 = 1;
else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_HARDWARE"))
- so_timestamping_flags |= SOF_TIMESTAMPING_TX_HARDWARE;
+ so_timestamping.flags |= SOF_TIMESTAMPING_TX_HARDWARE;
else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_SOFTWARE"))
- so_timestamping_flags |= SOF_TIMESTAMPING_TX_SOFTWARE;
+ so_timestamping.flags |= SOF_TIMESTAMPING_TX_SOFTWARE;
else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RX_HARDWARE"))
- so_timestamping_flags |= SOF_TIMESTAMPING_RX_HARDWARE;
+ so_timestamping.flags |= SOF_TIMESTAMPING_RX_HARDWARE;
else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RX_SOFTWARE"))
- so_timestamping_flags |= SOF_TIMESTAMPING_RX_SOFTWARE;
+ so_timestamping.flags |= SOF_TIMESTAMPING_RX_SOFTWARE;
else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_SOFTWARE"))
- so_timestamping_flags |= SOF_TIMESTAMPING_SOFTWARE;
+ so_timestamping.flags |= SOF_TIMESTAMPING_SOFTWARE;
else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RAW_HARDWARE"))
- so_timestamping_flags |= SOF_TIMESTAMPING_RAW_HARDWARE;
+ so_timestamping.flags |= SOF_TIMESTAMPING_RAW_HARDWARE;
+ else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_BIND_PHC"))
+ so_timestamping.flags |= SOF_TIMESTAMPING_BIND_PHC;
else
usage(argv[i]);
}
hwtstamp.ifr_data = (void *)&hwconfig;
memset(&hwconfig, 0, sizeof(hwconfig));
hwconfig.tx_type =
- (so_timestamping_flags & SOF_TIMESTAMPING_TX_HARDWARE) ?
+ (so_timestamping.flags & SOF_TIMESTAMPING_TX_HARDWARE) ?
HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
hwconfig.rx_filter =
- (so_timestamping_flags & SOF_TIMESTAMPING_RX_HARDWARE) ?
+ (so_timestamping.flags & SOF_TIMESTAMPING_RX_HARDWARE) ?
ptpv2 ? HWTSTAMP_FILTER_PTP_V2_L4_SYNC :
HWTSTAMP_FILTER_PTP_V1_L4_SYNC : HWTSTAMP_FILTER_NONE;
hwconfig_requested = hwconfig;
sizeof(struct sockaddr_in)) < 0)
bail("bind");
+ if (setsockopt(sock, SOL_SOCKET, SO_BINDTODEVICE, interface, if_len))
+ bail("bind device");
+
/* set multicast group for outgoing packets */
inet_aton("224.0.1.130", &iaddr); /* alternate PTP domain 1 */
addr.sin_addr = iaddr;
&enabled, sizeof(enabled)) < 0)
bail("setsockopt SO_TIMESTAMPNS");
- if (so_timestamping_flags &&
- setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING,
- &so_timestamping_flags,
- sizeof(so_timestamping_flags)) < 0)
+ if (so_timestamping.flags &&
+ setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, &so_timestamping,
+ sizeof(so_timestamping)) < 0)
bail("setsockopt SO_TIMESTAMPING");
/* request IP_PKTINFO for debugging purposes */
else
printf("SO_TIMESTAMPNS %d\n", val);
- if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, &val, &len) < 0) {
+ len = sizeof(so_timestamping_get);
+ if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, &so_timestamping_get,
+ &len) < 0) {
printf("%s: %s\n", "getsockopt SO_TIMESTAMPING",
strerror(errno));
} else {
- printf("SO_TIMESTAMPING %d\n", val);
- if (val != so_timestamping_flags)
- printf(" not the expected value %d\n",
- so_timestamping_flags);
+ printf("SO_TIMESTAMPING flags %d, bind phc %d\n",
+ so_timestamping_get.flags, so_timestamping_get.bind_phc);
+ if (so_timestamping_get.flags != so_timestamping.flags ||
+ so_timestamping_get.bind_phc != so_timestamping.bind_phc)
+ printf(" not expected, flags %d, bind phc %d\n",
+ so_timestamping.flags, so_timestamping.bind_phc);
}
/* send packets forever every five seconds */
conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \
nft_concat_range.sh nft_conntrack_helper.sh \
nft_queue.sh nft_meta.sh nf_nat_edemux.sh \
- ipip-conntrack-mtu.sh
+ ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh
LDLIBS = -lmnl
TEST_GEN_FILES = nf-queue
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Check that UNREPLIED tcp conntrack will eventually timeout.
+#
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+ret=0
+
+waittime=20
+sfx=$(mktemp -u "XXXXXXXX")
+ns1="ns1-$sfx"
+ns2="ns2-$sfx"
+
+nft --version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without nft tool"
+ 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
+
+cleanup() {
+ ip netns pids $ns1 | xargs kill 2>/dev/null
+ ip netns pids $ns2 | xargs kill 2>/dev/null
+
+ ip netns del $ns1
+ ip netns del $ns2
+}
+
+ipv4() {
+ echo -n 192.168.$1.2
+}
+
+check_counter()
+{
+ ns=$1
+ name=$2
+ expect=$3
+ local lret=0
+
+ cnt=$(ip netns exec $ns2 nft list counter inet filter "$name" | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ echo "ERROR: counter $name in $ns2 has unexpected value (expected $expect)" 1>&2
+ ip netns exec $ns2 nft list counter inet filter "$name" 1>&2
+ lret=1
+ fi
+
+ return $lret
+}
+
+# Create test namespaces
+ip netns add $ns1 || exit 1
+
+trap cleanup EXIT
+
+ip netns add $ns2 || exit 1
+
+# Connect the namespace to the host using a veth pair
+ip -net $ns1 link add name veth1 type veth peer name veth2
+ip -net $ns1 link set netns $ns2 dev veth2
+
+ip -net $ns1 link set up dev lo
+ip -net $ns2 link set up dev lo
+ip -net $ns1 link set up dev veth1
+ip -net $ns2 link set up dev veth2
+
+ip -net $ns2 addr add 10.11.11.2/24 dev veth2
+ip -net $ns2 route add default via 10.11.11.1
+
+ip netns exec $ns2 sysctl -q net.ipv4.conf.veth2.forwarding=1
+
+# add a rule inside NS so we enable conntrack
+ip netns exec $ns1 iptables -A INPUT -m state --state established,related -j ACCEPT
+
+ip -net $ns1 addr add 10.11.11.1/24 dev veth1
+ip -net $ns1 route add 10.99.99.99 via 10.11.11.2
+
+# Check connectivity works
+ip netns exec $ns1 ping -q -c 2 10.11.11.2 >/dev/null || exit 1
+
+ip netns exec $ns2 nc -l -p 8080 < /dev/null &
+
+# however, conntrack entries are there
+
+ip netns exec $ns2 nft -f - <<EOF
+table inet filter {
+ counter connreq { }
+ counter redir { }
+ chain input {
+ type filter hook input priority 0; policy accept;
+ ct state new tcp flags syn ip daddr 10.99.99.99 tcp dport 80 counter name "connreq" accept
+ ct state new ct status dnat tcp dport 8080 counter name "redir" accept
+ }
+}
+EOF
+if [ $? -ne 0 ]; then
+ echo "ERROR: Could not load nft rules"
+ exit 1
+fi
+
+ip netns exec $ns2 sysctl -q net.netfilter.nf_conntrack_tcp_timeout_syn_sent=10
+
+echo "INFO: connect $ns1 -> $ns2 to the virtual ip"
+ip netns exec $ns1 bash -c 'while true ; do
+ nc -p 60000 10.99.99.99 80
+ sleep 1
+ done' &
+
+sleep 1
+
+ip netns exec $ns2 nft -f - <<EOF
+table inet nat {
+ chain prerouting {
+ type nat hook prerouting priority 0; policy accept;
+ ip daddr 10.99.99.99 tcp dport 80 redirect to :8080
+ }
+}
+EOF
+if [ $? -ne 0 ]; then
+ echo "ERROR: Could not load nat redirect"
+ exit 1
+fi
+
+count=$(ip netns exec $ns2 conntrack -L -p tcp --dport 80 2>/dev/null | wc -l)
+if [ $count -eq 0 ]; then
+ echo "ERROR: $ns2 did not pick up tcp connection from peer"
+ exit 1
+fi
+
+echo "INFO: NAT redirect added in ns $ns2, waiting for $waittime seconds for nat to take effect"
+for i in $(seq 1 $waittime); do
+ echo -n "."
+
+ sleep 1
+
+ count=$(ip netns exec $ns2 conntrack -L -p tcp --reply-port-src 8080 2>/dev/null | wc -l)
+ if [ $count -gt 0 ]; then
+ echo
+ echo "PASS: redirection took effect after $i seconds"
+ break
+ fi
+
+ m=$((i%20))
+ if [ $m -eq 0 ]; then
+ echo " waited for $i seconds"
+ fi
+done
+
+expect="packets 1 bytes 60"
+check_counter "$ns2" "redir" "$expect"
+if [ $? -ne 0 ]; then
+ ret=1
+fi
+
+if [ $ret -eq 0 ];then
+ echo "PASS: redirection counter has expected values"
+else
+ echo "ERROR: no tcp connection was redirected"
+fi
+
+exit $ret
static void anon_allocate_area(void **alloc_area)
{
- if (posix_memalign(alloc_area, page_size, nr_pages * page_size))
- err("posix_memalign() failed");
+ *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+ if (*alloc_area == MAP_FAILED)
+ err("mmap of anonymous memory failed");
}
static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset)
coalesced_mmio_in_range(dev, zone->addr, zone->size)) {
r = kvm_io_bus_unregister_dev(kvm,
zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS, &dev->dev);
- kvm_iodevice_destructor(&dev->dev);
/*
* On failure, unregister destroys all devices on the
*/
if (r)
break;
+ kvm_iodevice_destructor(&dev->dev);
}
}
static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
{
+ static DEFINE_MUTEX(kvm_debugfs_lock);
+ struct dentry *dent;
char dir_name[ITOA_MAX_LEN * 2];
struct kvm_stat_data *stat_data;
const struct _kvm_stats_desc *pdesc;
return 0;
snprintf(dir_name, sizeof(dir_name), "%d-%d", task_pid_nr(current), fd);
- kvm->debugfs_dentry = debugfs_create_dir(dir_name, kvm_debugfs_dir);
+ mutex_lock(&kvm_debugfs_lock);
+ dent = debugfs_lookup(dir_name, kvm_debugfs_dir);
+ if (dent) {
+ pr_warn_ratelimited("KVM: debugfs: duplicate directory %s\n", dir_name);
+ dput(dent);
+ mutex_unlock(&kvm_debugfs_lock);
+ return 0;
+ }
+ dent = debugfs_create_dir(dir_name, kvm_debugfs_dir);
+ mutex_unlock(&kvm_debugfs_lock);
+ if (IS_ERR(dent))
+ return 0;
+ kvm->debugfs_dentry = dent;
kvm->debugfs_stat_data = kcalloc(kvm_debugfs_num_entries,
sizeof(*kvm->debugfs_stat_data),
GFP_KERNEL_ACCOUNT);
stat_data->kvm = kvm;
stat_data->desc = pdesc;
stat_data->kind = KVM_STAT_VCPU;
- kvm->debugfs_stat_data[i] = stat_data;
+ kvm->debugfs_stat_data[i + kvm_vm_stats_header.num_desc] = stat_data;
debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
kvm->debugfs_dentry, stat_data,
&stat_fops_per_vm);
++vcpu->stat.generic.halt_poll_invalid;
goto out;
}
+ cpu_relax();
poll_end = cur = ktime_get();
} while (kvm_vcpu_can_poll(cur, stop));
}
};
};
+struct compat_kvm_clear_dirty_log {
+ __u32 slot;
+ __u32 num_pages;
+ __u64 first_page;
+ union {
+ compat_uptr_t dirty_bitmap; /* one bit per page */
+ __u64 padding2;
+ };
+};
+
static long kvm_vm_compat_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
if (kvm->mm != current->mm)
return -EIO;
switch (ioctl) {
+#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
+ case KVM_CLEAR_DIRTY_LOG: {
+ struct compat_kvm_clear_dirty_log compat_log;
+ struct kvm_clear_dirty_log log;
+
+ if (copy_from_user(&compat_log, (void __user *)arg,
+ sizeof(compat_log)))
+ return -EFAULT;
+ log.slot = compat_log.slot;
+ log.num_pages = compat_log.num_pages;
+ log.first_page = compat_log.first_page;
+ log.padding2 = compat_log.padding2;
+ log.dirty_bitmap = compat_ptr(compat_log.dirty_bitmap);
+
+ r = kvm_vm_ioctl_clear_dirty_log(kvm, &log);
+ break;
+ }
+#endif
case KVM_GET_DIRTY_LOG: {
struct compat_kvm_dirty_log compat_log;
struct kvm_dirty_log log;
}
add_uevent_var(env, "PID=%d", kvm->userspace_pid);
- if (!IS_ERR_OR_NULL(kvm->debugfs_dentry)) {
+ if (kvm->debugfs_dentry) {
char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL_ACCOUNT);
if (p) {