Greg Kroah-Hartman <greg@kroah.com>
Greg Kurz <groug@kaod.org> <gkurz@linux.vnet.ibm.com>
Gregory CLEMENT <gregory.clement@bootlin.com> <gregory.clement@free-electrons.com>
+Guo Ren <guoren@kernel.org> <guoren@linux.alibaba.com>
+Guo Ren <guoren@kernel.org> <ren_guo@c-sky.com>
Gustavo Padovan <gustavo@las.ic.unicamp.br>
Gustavo Padovan <padovan@profusion.mobi>
Hanjun Guo <guohanjun@huawei.com> <hanjun.guo@linaro.org>
:alt: disk-states-8.dot
:align: center
-.. kernel-figure:: node-states-8.dot
- :alt: node-states-8.dot
+.. kernel-figure:: peer-states-8.dot
+ :alt: peer-states-8.dot
:align: center
-digraph node_states {
- Secondary -> Primary [ label = "ioctl_set_state()" ]
- Primary -> Secondary [ label = "ioctl_set_state()" ]
-}
-
digraph peer_states {
Secondary -> Primary [ label = "recv state packet" ]
Primary -> Secondary [ label = "recv state packet" ]
html_static_path = ['sphinx-static']
-html_context = {
- 'css_files': [
- '_static/theme_overrides.css',
- ],
-}
+html_css_files = [
+ 'theme_overrides.css',
+]
+
+if major <= 1 and minor < 8:
+ html_context = {
+ 'css_files': [
+ '_static/theme_overrides.css',
+ ],
+ }
# Add any extra paths that contain custom files (such as robots.txt or
# .htaccess) here, relative to this directory. These files are copied
properties:
compatible:
- enum:
- - apple,t8103-i2c
- - apple,i2c
+ items:
+ - const: apple,t8103-i2c
+ - const: apple,i2c
reg:
maxItems: 1
examples:
- |
i2c@35010000 {
- compatible = "apple,t8103-i2c";
+ compatible = "apple,t8103-i2c", "apple,i2c";
reg = <0x35010000 0x4000>;
interrupt-parent = <&aic>;
interrupts = <0 627 4>;
samsung,syscon-phandle = <&pmu_system_controller>;
/* NTC thermistor is a hwmon device */
- ncp15wb473 {
+ thermistor {
compatible = "murata,ncp15wb473";
pullup-uv = <1800000>;
pullup-ohm = <47000>;
down {
label = "GPIO Key DOWN";
linux,code = <108>;
- interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>;
+ interrupts = <1 IRQ_TYPE_EDGE_FALLING>;
};
};
properties:
data-lanes:
+ description:
+ Note that 'fsl,imx7-mipi-csi2' only supports up to 2 data lines.
items:
minItems: 1
maxItems: 4
required:
- data-lanes
- allOf:
- - if:
- properties:
- compatible:
- contains:
- const: fsl,imx7-mipi-csi2
- then:
- properties:
- data-lanes:
- items:
- maxItems: 2
-
port@1:
$ref: /schemas/graph.yaml#/properties/port
description:
compensate for the board being designed with the lanes
swapped.
+ enet-phy-lane-no-swap:
+ $ref: /schemas/types.yaml#/definitions/flag
+ description:
+ If set, indicates that PHY will disable swap of the
+ TX/RX lanes. This property allows the PHY to work correcly after
+ e.g. wrong bootstrap configuration caused by issues in PCB
+ layout design.
+
eee-broken-100tx:
$ref: /schemas/types.yaml#/definitions/flag
description:
- PHY_TYPE_PCIE
- PHY_TYPE_SATA
- PHY_TYPE_SGMII
- - PHY_TYPE_USB
+ - PHY_TYPE_USB3
- description: The PHY instance
minimum: 0
maximum: 1 # for DP, SATA or USB
reg = <0x65>;
interrupt-parent = <&gpio1>;
interrupts = <16 IRQ_TYPE_EDGE_FALLING>;
- ti,watchdog-timer = <0>;
+ ti,watchdog-timeout-ms = <0>;
ti,sc-ocp-limit-microamp = <2000000>;
ti,sc-ovp-limit-microvolt = <17800000>;
monitored-battery = <&bat>;
clocks:
maxItems: 1
+ interrupts:
+ maxItems: 1
+
"#sound-dai-cells":
const: 0
- rockchip,rk3328-spi
- rockchip,rk3368-spi
- rockchip,rk3399-spi
+ - rockchip,rk3568-spi
- rockchip,rv1126-spi
- const: rockchip,rk3066-spi
spin_lock(&p->lock);
p->count += this_cpu_read(var2);
-On a non-PREEMPT_RT kernel migrate_disable() maps to preempt_disable()
-which makes the above code fully equivalent. On a PREEMPT_RT kernel
migrate_disable() ensures that the task is pinned on the current CPU which
in turn guarantees that the per-CPU access to var1 and var2 are staying on
-the same CPU.
+the same CPU while the task remains preemptible.
The migrate_disable() substitution is not valid for the following
scenario::
p = this_cpu_ptr(&var1);
p->val = func2();
-While correct on a non-PREEMPT_RT kernel, this breaks on PREEMPT_RT because
-here migrate_disable() does not protect against reentrancy from a
-preempting task. A correct substitution for this case is::
+This breaks because migrate_disable() does not protect against reentrancy from
+a preempting task. A correct substitution for this case is::
func()
{
a virtual function (VF), jumbo frames must first be enabled in the physical
function (PF). The VF MTU setting cannot be larger than the PF MTU.
+NBASE-T Support
+---------------
+The ixgbe driver supports NBASE-T on some devices. However, the advertisement
+of NBASE-T speeds is suppressed by default, to accommodate broken network
+switches which cannot cope with advertised NBASE-T speeds. Use the ethtool
+command to enable advertising NBASE-T speeds on devices which support it::
+
+ ethtool -s eth? advertise 0x1800000001028
+
+On Linux systems with INTERFACES(5), this can be specified as a pre-up command
+in /etc/network/interfaces so that the interface is always brought up with
+NBASE-T support, e.g.::
+
+ iface eth? inet dhcp
+ pre-up ethtool -s eth? advertise 0x1800000001028 || true
+
Generic Receive Offload, aka GRO
--------------------------------
The driver supports the in-kernel software implementation of GRO. GRO has
binutils 2.23 ld -v
flex 2.5.35 flex --version
bison 2.0 bison --version
+pahole 1.16 pahole --version
util-linux 2.10o fdformat --version
kmod 13 depmod -V
e2fsprogs 1.41.4 e2fsck -V
Since Linux 4.16, the build system generates parsers
during build. This requires bison 2.0 or later.
+pahole:
+-------
+
+Since Linux 5.2, if CONFIG_DEBUG_INFO_BTF is selected, the build system
+generates BTF (BPF Type Format) from DWARF in vmlinux, a bit later from kernel
+modules as well. This requires pahole v1.16 or later.
+
+It is found in the 'dwarves' or 'pahole' distro packages or from
+https://fedorapeople.org/~acme/dwarves/.
+
Perl
----
Documentation/process/submit-checklist.rst
for a list of items to check before submitting code. If you are submitting
a driver, also read Documentation/process/submitting-drivers.rst; for device
-tree binding patches, read Documentation/process/submitting-patches.rst.
+tree binding patches, read
+Documentation/devicetree/bindings/submitting-patches.rst.
This documentation assumes that you're using ``git`` to prepare your patches.
If you're unfamiliar with ``git``, you would be well-advised to learn how to
F: drivers/phy/qualcomm/phy-ath79-usb.c
ATHEROS ATH GENERIC UTILITIES
-M: Kalle Valo <kvalo@codeaurora.org>
+M: Kalle Valo <kvalo@kernel.org>
L: linux-wireless@vger.kernel.org
S: Supported
F: drivers/net/wireless/ath/*
F: drivers/net/wireless/ath/ath5k/
ATHEROS ATH6KL WIRELESS DRIVER
-M: Kalle Valo <kvalo@codeaurora.org>
+M: Kalle Valo <kvalo@kernel.org>
L: linux-wireless@vger.kernel.org
S: Supported
W: https://wireless.wiki.kernel.org/en/users/Drivers/ath6kl
F: drivers/iio/pressure/dps310.c
INFINIBAND SUBSYSTEM
-M: Doug Ledford <dledford@redhat.com>
M: Jason Gunthorpe <jgg@nvidia.com>
L: linux-rdma@vger.kernel.org
S: Supported
F: scripts/Makefile.kcsan
KDUMP
-M: Dave Young <dyoung@redhat.com>
M: Baoquan He <bhe@redhat.com>
R: Vivek Goyal <vgoyal@redhat.com>
+R: Dave Young <dyoung@redhat.com>
L: kexec@lists.infradead.org
S: Maintained
W: http://lse.sourceforge.net/kdump/
F: include/linux/mlx5/mlx5_ifc_fpga.h
MELLANOX ETHERNET SWITCH DRIVERS
-M: Jiri Pirko <jiri@nvidia.com>
M: Ido Schimmel <idosch@nvidia.com>
+M: Petr Machata <petrm@nvidia.com>
L: netdev@vger.kernel.org
S: Supported
W: http://www.mellanox.com
F: include/uapi/linux/netdevice.h
NETWORKING DRIVERS (WIRELESS)
-M: Kalle Valo <kvalo@codeaurora.org>
+M: Kalle Valo <kvalo@kernel.org>
L: linux-wireless@vger.kernel.org
S: Maintained
Q: http://patchwork.kernel.org/project/linux-wireless/list/
F: drivers/media/tuners/qt1010*
QUALCOMM ATHEROS ATH10K WIRELESS DRIVER
-M: Kalle Valo <kvalo@codeaurora.org>
+M: Kalle Valo <kvalo@kernel.org>
L: ath10k@lists.infradead.org
S: Supported
W: https://wireless.wiki.kernel.org/en/users/Drivers/ath10k
F: drivers/net/wireless/ath/ath10k/
QUALCOMM ATHEROS ATH11K WIRELESS DRIVER
-M: Kalle Valo <kvalo@codeaurora.org>
+M: Kalle Valo <kvalo@kernel.org>
L: ath11k@lists.infradead.org
S: Supported
T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvalo/ath.git
F: Documentation/devicetree/bindings/net/qcom,ethqos.txt
F: drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+QUALCOMM FASTRPC DRIVER
+M: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
+M: Amol Maheshwari <amahesh@qti.qualcomm.com>
+L: linux-arm-msm@vger.kernel.org
+S: Maintained
+F: Documentation/devicetree/bindings/misc/qcom,fastrpc.txt
+F: drivers/misc/fastrpc.c
+F: include/uapi/misc/fastrpc.h
+
QUALCOMM GENERIC INTERFACE I2C DRIVER
M: Akash Asthana <akashast@codeaurora.org>
M: Mukesh Savaliya <msavaliy@codeaurora.org>
F: drivers/media/platform/qcom/venus/
QUALCOMM WCN36XX WIRELESS DRIVER
-M: Kalle Valo <kvalo@codeaurora.org>
+M: Kalle Valo <kvalo@kernel.org>
L: wcn36xx@lists.infradead.org
S: Supported
W: https://wireless.wiki.kernel.org/en/users/Drivers/wcn36xx
F: drivers/iommu/s390-iommu.c
S390 IUCV NETWORK LAYER
-M: Julian Wiedmann <jwi@linux.ibm.com>
M: Alexandra Winter <wintera@linux.ibm.com>
M: Wenjia Zhang <wenjia@linux.ibm.com>
L: linux-s390@vger.kernel.org
F: net/iucv/
S390 NETWORK DRIVERS
-M: Julian Wiedmann <jwi@linux.ibm.com>
M: Alexandra Winter <wintera@linux.ibm.com>
M: Wenjia Zhang <wenjia@linux.ibm.com>
L: linux-s390@vger.kernel.org
F: arch/x86/kernel/cpu/zhaoxin.c
ZONEFS FILESYSTEM
-M: Damien Le Moal <damien.lemoal@wdc.com>
+M: Damien Le Moal <damien.lemoal@opensource.wdc.com>
M: Naohiro Aota <naohiro.aota@wdc.com>
R: Johannes Thumshirn <jth@kernel.org>
L: linux-fsdevel@vger.kernel.org
VERSION = 5
PATCHLEVEL = 16
SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc6
NAME = Gobble Gobble
# *DOCUMENTATION*
KBUILD_CFLAGS += $(stackp-flags-y)
KBUILD_CFLAGS-$(CONFIG_WERROR) += -Werror
-KBUILD_CFLAGS += $(KBUILD_CFLAGS-y) $(CONFIG_CC_IMPLICIT_FALLTHROUGH)
+KBUILD_CFLAGS += $(KBUILD_CFLAGS-y) $(CONFIG_CC_IMPLICIT_FALLTHROUGH:"%"=%)
ifdef CONFIG_CC_IS_CLANG
KBUILD_CPPFLAGS += -Qunused-arguments
ifneq ($(dtstree),)
-%.dtb: dt_binding_check include/config/kernel.release scripts_dtc
- $(Q)$(MAKE) $(build)=$(dtstree) $(dtstree)/$@ $(dtstree)/$*.dt.yaml
+%.dtb: include/config/kernel.release scripts_dtc
+ $(Q)$(MAKE) $(build)=$(dtstree) $(dtstree)/$@
-%.dtbo: dt_binding_check include/config/kernel.release scripts_dtc
- $(Q)$(MAKE) $(build)=$(dtstree) $(dtstree)/$@ $(dtstree)/$*.dt.yaml
+%.dtbo: include/config/kernel.release scripts_dtc
+ $(Q)$(MAKE) $(build)=$(dtstree) $(dtstree)/$@
PHONY += dtbs dtbs_install dtbs_check
dtbs: include/config/kernel.release scripts_dtc
$(Q)$(MAKE) $(build)=$(dtstree)
-ifneq ($(filter dtbs_check %.dtb %.dtbo, $(MAKECMDGOALS)),)
+ifneq ($(filter dtbs_check, $(MAKECMDGOALS)),)
export CHECK_DTBS=y
dtbs: dt_binding_check
endif
label = "cpu";
ethernet = <&fec>;
phy-mode = "rgmii-id";
+ rx-internal-delay-ps = <2000>;
+ tx-internal-delay-ps = <2000>;
fixed-link {
speed = <100>;
#define MX6ULL_PAD_CSI_DATA04__ESAI_TX_FS 0x01F4 0x0480 0x0000 0x9 0x0
#define MX6ULL_PAD_CSI_DATA05__ESAI_TX_CLK 0x01F8 0x0484 0x0000 0x9 0x0
#define MX6ULL_PAD_CSI_DATA06__ESAI_TX5_RX0 0x01FC 0x0488 0x0000 0x9 0x0
-#define MX6ULL_PAD_CSI_DATA07__ESAI_T0 0x0200 0x048C 0x0000 0x9 0x0
+#define MX6ULL_PAD_CSI_DATA07__ESAI_TX0 0x0200 0x048C 0x0000 0x9 0x0
#endif /* __DTS_IMX6ULL_PINFUNC_H */
/* Internal port connected to eth2 */
ethernet = <&enet2>;
phy-mode = "rgmii";
+ rx-internal-delay-ps = <0>;
+ tx-internal-delay-ps = <0>;
reg = <4>;
fixed-link {
flash0: n25q00@0 {
#address-cells = <1>;
#size-cells = <1>;
- compatible = "n25q00aa";
+ compatible = "micron,mt25qu02g", "jedec,spi-nor";
reg = <0>;
spi-max-frequency = <100000000>;
flash: flash@0 {
#address-cells = <1>;
#size-cells = <1>;
- compatible = "n25q256a";
+ compatible = "micron,n25q256a", "jedec,spi-nor";
reg = <0>;
spi-max-frequency = <100000000>;
flash0: n25q00@0 {
#address-cells = <1>;
#size-cells = <1>;
- compatible = "n25q00";
+ compatible = "micron,mt25qu02g", "jedec,spi-nor";
reg = <0>; /* chip select */
spi-max-frequency = <100000000>;
flash: flash@0 {
#address-cells = <1>;
#size-cells = <1>;
- compatible = "n25q00";
+ compatible = "micron,mt25qu02g", "jedec,spi-nor";
reg = <0>;
spi-max-frequency = <100000000>;
flash: flash@0 {
#address-cells = <1>;
#size-cells = <1>;
- compatible = "n25q256a";
+ compatible = "micron,n25q256a", "jedec,spi-nor";
reg = <0>;
spi-max-frequency = <100000000>;
m25p,fast-read;
flash0: n25q512a@0 {
#address-cells = <1>;
#size-cells = <1>;
- compatible = "n25q512a";
+ compatible = "micron,n25q512a", "jedec,spi-nor";
reg = <0>;
spi-max-frequency = <100000000>;
n25q128@0 {
#address-cells = <1>;
#size-cells = <1>;
- compatible = "n25q128";
+ compatible = "micron,n25q128", "jedec,spi-nor";
reg = <0>; /* chip select */
spi-max-frequency = <100000000>;
m25p,fast-read;
n25q00@1 {
#address-cells = <1>;
#size-cells = <1>;
- compatible = "n25q00";
+ compatible = "micron,mt25qu02g", "jedec,spi-nor";
reg = <1>; /* chip select */
spi-max-frequency = <100000000>;
m25p,fast-read;
rockchip_boot_fn = __pa_symbol(secondary_startup);
/* copy the trampoline to sram, that runs during startup of the core */
- memcpy(sram_base_addr, &rockchip_secondary_trampoline, trampoline_sz);
+ memcpy_toio(sram_base_addr, &rockchip_secondary_trampoline, trampoline_sz);
flush_cache_all();
outer_clean_range(0, trampoline_sz);
config ARCH_MESON
bool "Amlogic Platforms"
- select COMMON_CLK
help
This enables support for the arm64 based Amlogic SoCs
such as the s905, S905X/D, S912, A113X/D or S905X/D2
type = "critical";
};
};
- };
- cpu_cooling_maps: cooling-maps {
- map0 {
- trip = <&cpu_passive>;
- cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
- <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
- <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
- <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
- };
+ cpu_cooling_maps: cooling-maps {
+ map0 {
+ trip = <&cpu_passive>;
+ cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+ <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+ <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+ <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+ };
- map1 {
- trip = <&cpu_hot>;
- cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
- <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
- <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
- <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+ map1 {
+ trip = <&cpu_hot>;
+ cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+ <&cpu1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+ <&cpu2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>,
+ <&cpu3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
+ };
};
};
};
&port02 {
bus-range = <3 3>;
- ethernet0: pci@0,0 {
+ ethernet0: ethernet@0,0 {
reg = <0x30000 0x0 0x0 0x0 0x0>;
/* To be filled by the loader */
local-mac-address = [00 10 18 00 00 00];
* Copyright The Asahi Linux Contributors
*/
+#include <dt-bindings/gpio/gpio.h>
#include <dt-bindings/interrupt-controller/apple-aic.h>
#include <dt-bindings/interrupt-controller/irq.h>
#include <dt-bindings/pinctrl/apple.h>
apple,npins = <212>;
interrupt-controller;
+ #interrupt-cells = <2>;
interrupt-parent = <&aic>;
interrupts = <AIC_IRQ 190 IRQ_TYPE_LEVEL_HIGH>,
<AIC_IRQ 191 IRQ_TYPE_LEVEL_HIGH>,
apple,npins = <42>;
interrupt-controller;
+ #interrupt-cells = <2>;
interrupt-parent = <&aic>;
interrupts = <AIC_IRQ 268 IRQ_TYPE_LEVEL_HIGH>,
<AIC_IRQ 269 IRQ_TYPE_LEVEL_HIGH>,
apple,npins = <23>;
interrupt-controller;
+ #interrupt-cells = <2>;
interrupt-parent = <&aic>;
interrupts = <AIC_IRQ 330 IRQ_TYPE_LEVEL_HIGH>,
<AIC_IRQ 331 IRQ_TYPE_LEVEL_HIGH>,
apple,npins = <16>;
interrupt-controller;
+ #interrupt-cells = <2>;
interrupt-parent = <&aic>;
interrupts = <AIC_IRQ 391 IRQ_TYPE_LEVEL_HIGH>,
<AIC_IRQ 392 IRQ_TYPE_LEVEL_HIGH>,
port00: pci@0,0 {
device_type = "pci";
reg = <0x0 0x0 0x0 0x0 0x0>;
- reset-gpios = <&pinctrl_ap 152 0>;
+ reset-gpios = <&pinctrl_ap 152 GPIO_ACTIVE_LOW>;
max-link-speed = <2>;
#address-cells = <3>;
port01: pci@1,0 {
device_type = "pci";
reg = <0x800 0x0 0x0 0x0 0x0>;
- reset-gpios = <&pinctrl_ap 153 0>;
+ reset-gpios = <&pinctrl_ap 153 GPIO_ACTIVE_LOW>;
max-link-speed = <2>;
#address-cells = <3>;
port02: pci@2,0 {
device_type = "pci";
reg = <0x1000 0x0 0x0 0x0 0x0>;
- reset-gpios = <&pinctrl_ap 33 0>;
+ reset-gpios = <&pinctrl_ap 33 GPIO_ACTIVE_LOW>;
max-link-speed = <1>;
#address-cells = <3>;
powerdn {
label = "External Power Down";
gpios = <&gpio1 17 GPIO_ACTIVE_LOW>;
- interrupts = <&gpio1 17 IRQ_TYPE_EDGE_FALLING>;
linux,code = <KEY_POWER>;
};
admin {
label = "ADMIN button";
gpios = <&gpio3 8 GPIO_ACTIVE_HIGH>;
- interrupts = <&gpio3 8 IRQ_TYPE_EDGE_RISING>;
linux,code = <KEY_WPS_BUTTON>;
};
};
reg = <2>;
ethernet = <&dpmac17>;
phy-mode = "rgmii-id";
+ rx-internal-delay-ps = <2000>;
+ tx-internal-delay-ps = <2000>;
fixed-link {
speed = <1000>;
reg = <2>;
ethernet = <&dpmac18>;
phy-mode = "rgmii-id";
+ rx-internal-delay-ps = <2000>;
+ tx-internal-delay-ps = <2000>;
fixed-link {
speed = <1000>;
<&clk IMX8MQ_VIDEO_PLL1>,
<&clk IMX8MQ_VIDEO_PLL1_OUT>;
assigned-clock-rates = <0>, <0>, <0>, <594000000>;
- interconnects = <&noc IMX8MQ_ICM_LCDIF &noc IMX8MQ_ICS_DRAM>;
- interconnect-names = "dram";
status = "disabled";
port@0 {
regulator-max-microvolt = <3300000>;
regulator-always-on;
regulator-boot-on;
- vim-supply = <&vcc_io>;
+ vin-supply = <&vcc_io>;
};
vdd_core: vdd-core {
&sdhci {
bus-width = <8>;
mmc-hs400-1_8v;
- mmc-hs400-enhanced-strobe;
non-removable;
status = "okay";
};
clock-output-names = "xin32k", "rk808-clkout2";
pinctrl-names = "default";
pinctrl-0 = <&pmic_int_l>;
+ rockchip,system-power-controller;
vcc1-supply = <&vcc5v0_sys>;
vcc2-supply = <&vcc5v0_sys>;
vcc3-supply = <&vcc5v0_sys>;
regulator-boot-on;
regulator-min-microvolt = <3300000>;
regulator-max-microvolt = <3300000>;
- vim-supply = <&vcc3v3_sys>;
+ vin-supply = <&vcc3v3_sys>;
};
vcc3v3_sys: vcc3v3-sys {
status = "okay";
bt656-supply = <&vcc_3v0>;
- audio-supply = <&vcc_3v0>;
+ audio-supply = <&vcc1v8_codec>;
sdmmc-supply = <&vcc_sdio>;
gpio1830-supply = <&vcc_3v0>;
};
initrd_len, cmdline, 0);
if (!dtb) {
pr_err("Preparing for new dtb failed\n");
+ ret = -EINVAL;
goto out_err;
}
asmlinkage void do_trap_fpe(struct pt_regs *regs)
{
-#ifdef CONFIG_CPU_HAS_FP
+#ifdef CONFIG_CPU_HAS_FPU
return fpu_fpe(regs);
#else
do_trap_error(regs, SIGILL, ILL_ILLOPC, regs->pc,
asmlinkage void do_trap_priv(struct pt_regs *regs)
{
-#ifdef CONFIG_CPU_HAS_FP
+#ifdef CONFIG_CPU_HAS_FPU
if (user_mode(regs) && fpu_libc_helper(regs))
return;
#endif
#define PCI_IOSIZE SZ_64K
#define IO_SPACE_LIMIT (PCI_IOSIZE - 1)
+#define pci_remap_iospace pci_remap_iospace
+
#include <asm/mach-generic/spaces.h>
#endif
#include <linux/list.h>
#include <linux/of.h>
-#ifdef CONFIG_PCI_DRIVERS_GENERIC
-#define pci_remap_iospace pci_remap_iospace
-#endif
-
#ifdef CONFIG_PCI_DRIVERS_LEGACY
/*
#define emit(...) __emit(__VA_ARGS__)
/* Workaround for R10000 ll/sc errata */
-#ifdef CONFIG_WAR_R10000
+#ifdef CONFIG_WAR_R10000_LLSC
#define LLSC_beqz beqzl
#else
#define LLSC_beqz beqz
pci_read_bridge_bases(bus);
}
+#ifdef pci_remap_iospace
int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr)
{
unsigned long vaddr;
set_io_port_base(vaddr);
return 0;
}
+#endif
const char *name)
{
long reladdr;
+ func_desc_t desc;
+ int i;
if (is_mprofile_ftrace_call(name))
return create_ftrace_stub(entry, addr, me);
- memcpy(entry->jump, ppc64_stub_insns, sizeof(ppc64_stub_insns));
+ for (i = 0; i < sizeof(ppc64_stub_insns) / sizeof(u32); i++) {
+ if (patch_instruction(&entry->jump[i],
+ ppc_inst(ppc64_stub_insns[i])))
+ return 0;
+ }
/* Stub uses address relative to r2. */
reladdr = (unsigned long)entry - my_r2(sechdrs, me);
}
pr_debug("Stub %p get data from reladdr %li\n", entry, reladdr);
- entry->jump[0] |= PPC_HA(reladdr);
- entry->jump[1] |= PPC_LO(reladdr);
- entry->funcdata = func_desc(addr);
- entry->magic = STUB_MAGIC;
+ if (patch_instruction(&entry->jump[0],
+ ppc_inst(entry->jump[0] | PPC_HA(reladdr))))
+ return 0;
+
+ if (patch_instruction(&entry->jump[1],
+ ppc_inst(entry->jump[1] | PPC_LO(reladdr))))
+ return 0;
+
+ // func_desc_t is 8 bytes if ABIv2, else 16 bytes
+ desc = func_desc(addr);
+ for (i = 0; i < sizeof(func_desc_t) / sizeof(u32); i++) {
+ if (patch_instruction(((u32 *)&entry->funcdata) + i,
+ ppc_inst(((u32 *)(&desc))[i])))
+ return 0;
+ }
+
+ if (patch_instruction(&entry->magic, ppc_inst(STUB_MAGIC)))
+ return 0;
return 1;
}
me->name, *instruction, instruction);
return 0;
}
+
/* ld r2,R2_STACK_OFFSET(r1) */
- *instruction = PPC_INST_LD_TOC;
+ if (patch_instruction(instruction, ppc_inst(PPC_INST_LD_TOC)))
+ return 0;
+
return 1;
}
}
/* Only replace bits 2 through 26 */
- *(uint32_t *)location
- = (*(uint32_t *)location & ~0x03fffffc)
+ value = (*(uint32_t *)location & ~0x03fffffc)
| (value & 0x03fffffc);
+
+ if (patch_instruction((u32 *)location, ppc_inst(value)))
+ return -EFAULT;
+
break;
case R_PPC64_REL64:
local_irq_save(flags);
hard_irq_disable();
- if (qoriq_pm_ops)
+ if (qoriq_pm_ops && qoriq_pm_ops->cpu_up_prepare)
qoriq_pm_ops->cpu_up_prepare(cpu);
/* if cpu is not spinning, reset it */
booting_thread_hwid = cpu_thread_in_core(nr);
primary = cpu_first_thread_sibling(nr);
- if (qoriq_pm_ops)
+ if (qoriq_pm_ops && qoriq_pm_ops->cpu_up_prepare)
qoriq_pm_ops->cpu_up_prepare(nr);
/*
spi-max-frequency = <20000000>;
voltage-ranges = <3300 3300>;
disable-wp;
+ gpios = <&gpio 11 GPIO_ACTIVE_LOW>;
};
};
/* Copyright (c) 2020 SiFive, Inc */
#include "fu740-c000.dtsi"
+#include <dt-bindings/gpio/gpio.h>
#include <dt-bindings/interrupt-controller/irq.h>
/* Clock frequency (in Hz) of the PCB crystal for rtcclk */
temperature-sensor@4c {
compatible = "ti,tmp451";
reg = <0x4c>;
+ vcc-supply = <&vdd_bpro>;
interrupt-parent = <&gpio>;
interrupts = <6 IRQ_TYPE_LEVEL_LOW>;
};
+ eeprom@54 {
+ compatible = "microchip,24c02", "atmel,24c02";
+ reg = <0x54>;
+ vcc-supply = <&vdd_bpro>;
+ label = "board-id";
+ pagesize = <16>;
+ read-only;
+ size = <256>;
+ };
+
pmic@58 {
compatible = "dlg,da9063";
reg = <0x58>;
interrupts = <1 IRQ_TYPE_LEVEL_LOW>;
interrupt-controller;
- regulators {
- vdd_bcore1: bcore1 {
- regulator-min-microvolt = <900000>;
- regulator-max-microvolt = <900000>;
- regulator-min-microamp = <5000000>;
- regulator-max-microamp = <5000000>;
- regulator-always-on;
- };
+ onkey {
+ compatible = "dlg,da9063-onkey";
+ };
- vdd_bcore2: bcore2 {
- regulator-min-microvolt = <900000>;
- regulator-max-microvolt = <900000>;
- regulator-min-microamp = <5000000>;
- regulator-max-microamp = <5000000>;
+ rtc {
+ compatible = "dlg,da9063-rtc";
+ };
+
+ wdt {
+ compatible = "dlg,da9063-watchdog";
+ };
+
+ regulators {
+ vdd_bcore: bcores-merged {
+ regulator-min-microvolt = <1050000>;
+ regulator-max-microvolt = <1050000>;
+ regulator-min-microamp = <4800000>;
+ regulator-max-microamp = <4800000>;
regulator-always-on;
};
vdd_bpro: bpro {
regulator-min-microvolt = <1800000>;
regulator-max-microvolt = <1800000>;
- regulator-min-microamp = <2500000>;
- regulator-max-microamp = <2500000>;
+ regulator-min-microamp = <2400000>;
+ regulator-max-microamp = <2400000>;
regulator-always-on;
};
vdd_bperi: bperi {
- regulator-min-microvolt = <1050000>;
- regulator-max-microvolt = <1050000>;
+ regulator-min-microvolt = <1060000>;
+ regulator-max-microvolt = <1060000>;
regulator-min-microamp = <1500000>;
regulator-max-microamp = <1500000>;
regulator-always-on;
};
- vdd_bmem: bmem {
- regulator-min-microvolt = <1200000>;
- regulator-max-microvolt = <1200000>;
- regulator-min-microamp = <3000000>;
- regulator-max-microamp = <3000000>;
- regulator-always-on;
- };
-
- vdd_bio: bio {
+ vdd_bmem_bio: bmem-bio-merged {
regulator-min-microvolt = <1200000>;
regulator-max-microvolt = <1200000>;
regulator-min-microamp = <3000000>;
vdd_ldo1: ldo1 {
regulator-min-microvolt = <1800000>;
regulator-max-microvolt = <1800000>;
- regulator-min-microamp = <100000>;
- regulator-max-microamp = <100000>;
regulator-always-on;
};
vdd_ldo2: ldo2 {
regulator-min-microvolt = <1800000>;
regulator-max-microvolt = <1800000>;
- regulator-min-microamp = <200000>;
- regulator-max-microamp = <200000>;
regulator-always-on;
};
vdd_ldo3: ldo3 {
- regulator-min-microvolt = <1800000>;
- regulator-max-microvolt = <1800000>;
- regulator-min-microamp = <200000>;
- regulator-max-microamp = <200000>;
+ regulator-min-microvolt = <3300000>;
+ regulator-max-microvolt = <3300000>;
regulator-always-on;
};
vdd_ldo4: ldo4 {
- regulator-min-microvolt = <1800000>;
- regulator-max-microvolt = <1800000>;
- regulator-min-microamp = <200000>;
- regulator-max-microamp = <200000>;
+ regulator-min-microvolt = <2500000>;
+ regulator-max-microvolt = <2500000>;
regulator-always-on;
};
vdd_ldo5: ldo5 {
- regulator-min-microvolt = <1800000>;
- regulator-max-microvolt = <1800000>;
- regulator-min-microamp = <100000>;
- regulator-max-microamp = <100000>;
+ regulator-min-microvolt = <3300000>;
+ regulator-max-microvolt = <3300000>;
regulator-always-on;
};
vdd_ldo6: ldo6 {
- regulator-min-microvolt = <3300000>;
- regulator-max-microvolt = <3300000>;
- regulator-min-microamp = <200000>;
- regulator-max-microamp = <200000>;
+ regulator-min-microvolt = <1800000>;
+ regulator-max-microvolt = <1800000>;
regulator-always-on;
};
vdd_ldo7: ldo7 {
- regulator-min-microvolt = <1800000>;
- regulator-max-microvolt = <1800000>;
- regulator-min-microamp = <200000>;
- regulator-max-microamp = <200000>;
+ regulator-min-microvolt = <3300000>;
+ regulator-max-microvolt = <3300000>;
regulator-always-on;
};
vdd_ldo8: ldo8 {
- regulator-min-microvolt = <1800000>;
- regulator-max-microvolt = <1800000>;
- regulator-min-microamp = <200000>;
- regulator-max-microamp = <200000>;
+ regulator-min-microvolt = <3300000>;
+ regulator-max-microvolt = <3300000>;
regulator-always-on;
};
vdd_ld09: ldo9 {
regulator-min-microvolt = <1050000>;
regulator-max-microvolt = <1050000>;
- regulator-min-microamp = <200000>;
- regulator-max-microamp = <200000>;
+ regulator-always-on;
};
vdd_ldo10: ldo10 {
regulator-min-microvolt = <1000000>;
regulator-max-microvolt = <1000000>;
- regulator-min-microamp = <300000>;
- regulator-max-microamp = <300000>;
+ regulator-always-on;
};
vdd_ldo11: ldo11 {
regulator-min-microvolt = <2500000>;
regulator-max-microvolt = <2500000>;
- regulator-min-microamp = <300000>;
- regulator-max-microamp = <300000>;
regulator-always-on;
};
};
spi-max-frequency = <20000000>;
voltage-ranges = <3300 3300>;
disable-wp;
+ gpios = <&gpio 15 GPIO_ACTIVE_LOW>;
};
};
&gpio {
status = "okay";
+ gpio-line-names = "J29.1", "PMICNTB", "PMICSHDN", "J8.1", "J8.3",
+ "PCIe_PWREN", "THERM", "UBRDG_RSTN", "PCIe_PERSTN",
+ "ULPI_RSTN", "J8.2", "UHUB_RSTN", "GEMGXL_RST", "J8.4",
+ "EN_VDD_SD", "SD_CD";
};
CONFIG_UNIX_DIAG=m
CONFIG_XFRM_USER=m
CONFIG_NET_KEY=m
+CONFIG_NET_SWITCHDEV=y
CONFIG_SMC=m
CONFIG_SMC_DIAG=m
CONFIG_INET=y
CONFIG_MLX4_EN=m
CONFIG_MLX5_CORE=m
CONFIG_MLX5_CORE_EN=y
+CONFIG_MLX5_ESWITCH=y
# CONFIG_NET_VENDOR_MICREL is not set
# CONFIG_NET_VENDOR_MICROCHIP is not set
# CONFIG_NET_VENDOR_MICROSEMI is not set
CONFIG_UNIX_DIAG=m
CONFIG_XFRM_USER=m
CONFIG_NET_KEY=m
+CONFIG_NET_SWITCHDEV=y
CONFIG_SMC=m
CONFIG_SMC_DIAG=m
CONFIG_INET=y
CONFIG_MLX4_EN=m
CONFIG_MLX5_CORE=m
CONFIG_MLX5_CORE_EN=y
+CONFIG_MLX5_ESWITCH=y
# CONFIG_NET_VENDOR_MICREL is not set
# CONFIG_NET_VENDOR_MICROCHIP is not set
# CONFIG_NET_VENDOR_MICROSEMI is not set
return;
regs = ftrace_get_regs(fregs);
- preempt_disable_notrace();
p = get_kprobe((kprobe_opcode_t *)ip);
if (unlikely(!p) || kprobe_disabled(p))
goto out;
}
__this_cpu_write(current_kprobe, NULL);
out:
- preempt_enable_notrace();
ftrace_test_recursion_unlock(bit);
}
NOKPROBE_SYMBOL(kprobe_ftrace_handler);
struct pt_regs *old_regs = set_irq_regs(regs);
int from_idle;
- irq_enter();
+ irq_enter_rcu();
if (user_mode(regs)) {
update_timer_sys();
do_irq_async(regs, IO_INTERRUPT);
} while (MACHINE_IS_LPAR && irq_pending(regs));
- irq_exit();
+ irq_exit_rcu();
+
set_irq_regs(old_regs);
irqentry_exit(regs, state);
struct pt_regs *old_regs = set_irq_regs(regs);
int from_idle;
- irq_enter();
+ irq_enter_rcu();
if (user_mode(regs)) {
update_timer_sys();
do_irq_async(regs, EXT_INTERRUPT);
- irq_exit();
+ irq_exit_rcu();
set_irq_regs(old_regs);
irqentry_exit(regs, state);
* Author(s): Philipp Rudo <prudo@linux.vnet.ibm.com>
*/
+#define pr_fmt(fmt) "kexec: " fmt
+
#include <linux/elf.h>
#include <linux/errno.h>
#include <linux/kexec.h>
const Elf_Shdr *relsec,
const Elf_Shdr *symtab)
{
+ const char *strtab, *name, *shstrtab;
+ const Elf_Shdr *sechdrs;
Elf_Rela *relas;
int i, r_type;
+ int ret;
+
+ /* String & section header string table */
+ sechdrs = (void *)pi->ehdr + pi->ehdr->e_shoff;
+ strtab = (char *)pi->ehdr + sechdrs[symtab->sh_link].sh_offset;
+ shstrtab = (char *)pi->ehdr + sechdrs[pi->ehdr->e_shstrndx].sh_offset;
relas = (void *)pi->ehdr + relsec->sh_offset;
sym = (void *)pi->ehdr + symtab->sh_offset;
sym += ELF64_R_SYM(relas[i].r_info);
- if (sym->st_shndx == SHN_UNDEF)
+ if (sym->st_name)
+ name = strtab + sym->st_name;
+ else
+ name = shstrtab + sechdrs[sym->st_shndx].sh_name;
+
+ if (sym->st_shndx == SHN_UNDEF) {
+ pr_err("Undefined symbol: %s\n", name);
return -ENOEXEC;
+ }
- if (sym->st_shndx == SHN_COMMON)
+ if (sym->st_shndx == SHN_COMMON) {
+ pr_err("symbol '%s' in common section\n", name);
return -ENOEXEC;
+ }
if (sym->st_shndx >= pi->ehdr->e_shnum &&
- sym->st_shndx != SHN_ABS)
+ sym->st_shndx != SHN_ABS) {
+ pr_err("Invalid section %d for symbol %s\n",
+ sym->st_shndx, name);
return -ENOEXEC;
+ }
loc = pi->purgatory_buf;
loc += section->sh_offset;
addr = section->sh_addr + relas[i].r_offset;
r_type = ELF64_R_TYPE(relas[i].r_info);
- arch_kexec_do_relocs(r_type, loc, val, addr);
+
+ if (r_type == R_390_PLT32DBL)
+ r_type = R_390_PC32DBL;
+
+ ret = arch_kexec_do_relocs(r_type, loc, val, addr);
+ if (ret) {
+ pr_err("Unknown rela relocation: %d\n", r_type);
+ return -ENOEXEC;
+ }
}
return 0;
}
depends on ACPI
select UCS2_STRING
select EFI_RUNTIME_WRAPPERS
+ select ARCH_USE_MEMREMAP_PROT
help
This enables the kernel to use EFI runtime services that are
available (such as the EFI variable services).
KVM_ARCH_REQ_FLAGS(25, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_TLB_FLUSH_CURRENT KVM_ARCH_REQ(26)
#define KVM_REQ_TLB_FLUSH_GUEST \
- KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_NO_WAKEUP)
+ KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_APF_READY KVM_ARCH_REQ(28)
#define KVM_REQ_MSR_FILTER_CHANGED KVM_ARCH_REQ(29)
#define KVM_REQ_UPDATE_CPU_DIRTY_LOGGING \
{ NULL, },
};
+static struct sched_domain_topology_level x86_hybrid_topology[] = {
+#ifdef CONFIG_SCHED_SMT
+ { cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) },
+#endif
+#ifdef CONFIG_SCHED_MC
+ { cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC) },
+#endif
+ { cpu_cpu_mask, SD_INIT_NAME(DIE) },
+ { NULL, },
+};
+
static struct sched_domain_topology_level x86_topology[] = {
#ifdef CONFIG_SCHED_SMT
{ cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) },
calculate_max_logical_packages();
+ /* XXX for now assume numa-in-package and hybrid don't overlap */
if (x86_has_numa_in_package)
set_sched_topology(x86_numa_in_package_topology);
+ if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
+ set_sched_topology(x86_hybrid_topology);
nmi_selftest();
impress_friends();
all_cpus = send_ipi_ex.vp_set.format == HV_GENERIC_SET_ALL;
+ if (all_cpus)
+ goto check_and_send_ipi;
+
if (!sparse_banks_len)
goto ret_success;
- if (!all_cpus &&
- kvm_read_guest(kvm,
+ if (kvm_read_guest(kvm,
hc->ingpa + offsetof(struct hv_send_ipi_ex,
vp_set.bank_contents),
sparse_banks,
return HV_STATUS_INVALID_HYPERCALL_INPUT;
}
+check_and_send_ipi:
if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR))
return HV_STATUS_INVALID_HYPERCALL_INPUT;
static bool is_page_fault_stale(struct kvm_vcpu *vcpu,
struct kvm_page_fault *fault, int mmu_seq)
{
- if (is_obsolete_sp(vcpu->kvm, to_shadow_page(vcpu->arch.mmu->root_hpa)))
+ struct kvm_mmu_page *sp = to_shadow_page(vcpu->arch.mmu->root_hpa);
+
+ /* Special roots, e.g. pae_root, are not backed by shadow pages. */
+ if (sp && is_obsolete_sp(vcpu->kvm, sp))
+ return true;
+
+ /*
+ * Roots without an associated shadow page are considered invalid if
+ * there is a pending request to free obsolete roots. The request is
+ * only a hint that the current root _may_ be obsolete and needs to be
+ * reloaded, e.g. if the guest frees a PGD that KVM is tracking as a
+ * previous root, then __kvm_mmu_prepare_zap_page() signals all vCPUs
+ * to reload even if no vCPU is actively using the root.
+ */
+ if (!sp && kvm_test_request(KVM_REQ_MMU_RELOAD, vcpu))
return true;
return fault->slot &&
if (!loaded_vmcs->msr_bitmap)
goto out_vmcs;
memset(loaded_vmcs->msr_bitmap, 0xff, PAGE_SIZE);
-
- if (IS_ENABLED(CONFIG_HYPERV) &&
- static_branch_unlikely(&enable_evmcs) &&
- (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) {
- struct hv_enlightened_vmcs *evmcs =
- (struct hv_enlightened_vmcs *)loaded_vmcs->vmcs;
-
- evmcs->hv_enlightenments_control.msr_bitmap = 1;
- }
}
memset(&loaded_vmcs->host_state, 0, sizeof(struct vmcs_host_state));
if (err < 0)
goto free_pml;
+ /*
+ * Use Hyper-V 'Enlightened MSR Bitmap' feature when KVM runs as a
+ * nested (L1) hypervisor and Hyper-V in L0 supports it. Enable the
+ * feature only for vmcs01, KVM currently isn't equipped to realize any
+ * performance benefits from enabling it for vmcs02.
+ */
+ if (IS_ENABLED(CONFIG_HYPERV) && static_branch_unlikely(&enable_evmcs) &&
+ (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) {
+ struct hv_enlightened_vmcs *evmcs = (void *)vmx->vmcs01.vmcs;
+
+ evmcs->hv_enlightenments_control.msr_bitmap = 1;
+ }
+
/* The MSR bitmap starts with all ones */
bitmap_fill(vmx->shadow_msr_intercept.read, MAX_POSSIBLE_PASSTHROUGH_MSRS);
bitmap_fill(vmx->shadow_msr_intercept.write, MAX_POSSIBLE_PASSTHROUGH_MSRS);
!load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)))
return 1;
- if (!(cr0 & X86_CR0_PG) && kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE))
+ if (!(cr0 & X86_CR0_PG) &&
+ (is_64_bit_mode(vcpu) || kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)))
return 1;
static_call(kvm_x86_set_cr0)(vcpu, cr0);
if (!msr_info->host_initiated)
return 1;
- if (guest_cpuid_has(vcpu, X86_FEATURE_PDCM) && kvm_get_msr_feature(&msr_ent))
+ if (kvm_get_msr_feature(&msr_ent))
return 1;
if (data & ~msr_ent.data)
return 1;
unsigned short port, void *val, unsigned int count)
{
if (vcpu->arch.pio.count) {
- /* Complete previous iteration. */
+ /*
+ * Complete a previous iteration that required userspace I/O.
+ * Note, @count isn't guaranteed to match pio.count as userspace
+ * can modify ECX before rerunning the vCPU. Ignore any such
+ * shenanigans as KVM doesn't support modifying the rep count,
+ * and the emulator ensures @count doesn't overflow the buffer.
+ */
} else {
int r = __emulator_pio_in(vcpu, size, port, count);
if (!r)
/* Results already available, fall through. */
}
- WARN_ON(count != vcpu->arch.pio.count);
complete_emulator_pio_in(vcpu, val);
return 1;
}
if (PageReserved(page)) {
__ClearPageReserved(page);
- magic = (unsigned long)page->freelist;
+ magic = page->index;
if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) {
while (nr_pages--)
put_page_bootmem(page++);
case BPF_LDX | BPF_MEM | BPF_DW:
case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
if (BPF_MODE(insn->code) == BPF_PROBE_MEM) {
- /* test src_reg, src_reg */
- maybe_emit_mod(&prog, src_reg, src_reg, true); /* always 1 byte */
- EMIT2(0x85, add_2reg(0xC0, src_reg, src_reg));
- /* jne start_of_ldx */
- EMIT2(X86_JNE, 0);
+ /* Though the verifier prevents negative insn->off in BPF_PROBE_MEM
+ * add abs(insn->off) to the limit to make sure that negative
+ * offset won't be an issue.
+ * insn->off is s16, so it won't affect valid pointers.
+ */
+ u64 limit = TASK_SIZE_MAX + PAGE_SIZE + abs(insn->off);
+ u8 *end_of_jmp1, *end_of_jmp2;
+
+ /* Conservatively check that src_reg + insn->off is a kernel address:
+ * 1. src_reg + insn->off >= limit
+ * 2. src_reg + insn->off doesn't become small positive.
+ * Cannot do src_reg + insn->off >= limit in one branch,
+ * since it needs two spare registers, but JIT has only one.
+ */
+
+ /* movabsq r11, limit */
+ EMIT2(add_1mod(0x48, AUX_REG), add_1reg(0xB8, AUX_REG));
+ EMIT((u32)limit, 4);
+ EMIT(limit >> 32, 4);
+ /* cmp src_reg, r11 */
+ maybe_emit_mod(&prog, src_reg, AUX_REG, true);
+ EMIT2(0x39, add_2reg(0xC0, src_reg, AUX_REG));
+ /* if unsigned '<' goto end_of_jmp2 */
+ EMIT2(X86_JB, 0);
+ end_of_jmp1 = prog;
+
+ /* mov r11, src_reg */
+ emit_mov_reg(&prog, true, AUX_REG, src_reg);
+ /* add r11, insn->off */
+ maybe_emit_1mod(&prog, AUX_REG, true);
+ EMIT2_off32(0x81, add_1reg(0xC0, AUX_REG), insn->off);
+ /* jmp if not carry to start_of_ldx
+ * Otherwise ERR_PTR(-EINVAL) + 128 will be the user addr
+ * that has to be rejected.
+ */
+ EMIT2(0x73 /* JNC */, 0);
+ end_of_jmp2 = prog;
+
/* xor dst_reg, dst_reg */
emit_mov_imm32(&prog, false, dst_reg, 0);
/* jmp byte_after_ldx */
EMIT2(0xEB, 0);
- /* populate jmp_offset for JNE above */
- temp[4] = prog - temp - 5 /* sizeof(test + jne) */;
+ /* populate jmp_offset for JB above to jump to xor dst_reg */
+ end_of_jmp1[-1] = end_of_jmp2 - end_of_jmp1;
+ /* populate jmp_offset for JNC above to jump to start_of_ldx */
start_of_ldx = prog;
+ end_of_jmp2[-1] = start_of_ldx - end_of_jmp2;
}
emit_ldx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off);
if (BPF_MODE(insn->code) == BPF_PROBE_MEM) {
* End result: x86 insn "mov rbx, qword ptr [rax+0x14]"
* of 4 bytes will be ignored and rbx will be zero inited.
*/
- ex->fixup = (prog - temp) | (reg2pt_regs[dst_reg] << 8);
+ ex->fixup = (prog - start_of_ldx) | (reg2pt_regs[dst_reg] << 8);
}
break;
return;
}
- new = early_memremap(data.phys_map, data.size);
+ new = early_memremap_prot(data.phys_map, data.size,
+ pgprot_val(pgprot_encrypted(FIXMAP_PAGE_NORMAL)));
if (!new) {
pr_err("Failed to map new boot services memmap\n");
return;
hwm = current_hweight_max(iocg);
new_hwi = hweight_after_donation(iocg, old_hwi, hwm,
usage, &now);
- if (new_hwi < hwm) {
+ /*
+ * Donation calculation assumes hweight_after_donation
+ * to be positive, a condition that a donor w/ hwa < 2
+ * can't meet. Don't bother with donation if hwa is
+ * below 2. It's not gonna make a meaningful difference
+ * anyway.
+ */
+ if (new_hwi < hwm && hwa >= 2) {
iocg->hweight_donating = hwa;
iocg->hweight_after_donation = new_hwi;
list_add(&iocg->surplus_list, &surpluses);
#include <linux/falloc.h>
#include <linux/suspend.h>
#include <linux/fs.h>
+#include <linux/module.h>
#include "blk.h"
static inline struct inode *bdev_file_inode(struct file *file)
} else {
ret = bio_iov_iter_get_pages(bio, iter);
if (unlikely(ret)) {
- bio->bi_status = BLK_STS_IOERR;
- bio_endio(bio);
+ bio_put(bio);
return ret;
}
}
pgrp = task_pgrp(current);
else
pgrp = find_vpid(who);
+ read_lock(&tasklist_lock);
do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
tmpio = get_task_ioprio(p);
if (tmpio < 0)
else
ret = ioprio_best(ret, tmpio);
} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
+ read_unlock(&tasklist_lock);
+
break;
case IOPRIO_WHO_USER:
uid = make_kuid(current_user_ns(), who);
# SOC specific infrastructure drivers.
obj-y += soc/
-obj-$(CONFIG_VIRTIO) += virtio/
-obj-$(CONFIG_VIRTIO_PCI_LIB) += virtio/
+obj-y += virtio/
obj-$(CONFIG_VDPA) += vdpa/
obj-$(CONFIG_XEN) += xen/
__release(&t->lock);
/*
- * If this thread used poll, make sure we remove the waitqueue
- * from any epoll data structures holding it with POLLFREE.
- * waitqueue_active() is safe to use here because we're holding
- * the inner lock.
+ * If this thread used poll, make sure we remove the waitqueue from any
+ * poll data structures holding it.
*/
- if ((thread->looper & BINDER_LOOPER_STATE_POLL) &&
- waitqueue_active(&thread->wait)) {
- wake_up_poll(&thread->wait, EPOLLHUP | POLLFREE);
- }
+ if (thread->looper & BINDER_LOOPER_STATE_POLL)
+ wake_up_pollfree(&thread->wait);
binder_inner_proc_unlock(thread->proc);
/*
- * This is needed to avoid races between wake_up_poll() above and
- * and ep_remove_waitqueue() called for other reasons (eg the epoll file
- * descriptor being closed); ep_remove_waitqueue() holds an RCU read
- * lock, so we can be sure it's done after calling synchronize_rcu().
+ * This is needed to avoid races between wake_up_pollfree() above and
+ * someone else removing the last entry from the queue for other reasons
+ * (e.g. ep_remove_wait_queue() being called due to an epoll file
+ * descriptor being closed). Such other users hold an RCU read lock, so
+ * we can be sure they're done after we call synchronize_rcu().
*/
if (thread->looper & BINDER_LOOPER_STATE_POLL)
synchronize_rcu();
static unsigned int ceva_ahci_read_id(struct ata_device *dev,
struct ata_taskfile *tf, u16 *id)
{
+ __le16 *__id = (__le16 *)id;
u32 err_mask;
err_mask = ata_do_dev_read_id(dev, tf, id);
* Since CEVA controller does not support device sleep feature, we
* need to clear DEVSLP (bit 8) in word78 of the IDENTIFY DEVICE data.
*/
- id[ATA_ID_FEATURE_SUPP] &= cpu_to_le16(~(1 << 8));
+ __id[ATA_ID_FEATURE_SUPP] &= cpu_to_le16(~(1 << 8));
return 0;
}
{ "VRFDFC22048UCHC-TE*", NULL, ATA_HORKAGE_NODMA },
/* Odd clown on sil3726/4726 PMPs */
{ "Config Disk", NULL, ATA_HORKAGE_DISABLE },
+ /* Similar story with ASMedia 1092 */
+ { "ASMT109x- Config", NULL, ATA_HORKAGE_DISABLE },
/* Weird ATAPI devices */
{ "TORiSAN DVD-ROM DRD-N216", NULL, ATA_HORKAGE_MAX_SEC_128 },
goto invalid_fld;
}
- if (ata_is_ncq(tf->protocol) && (cdb[2 + cdb_offset] & 0x3) == 0)
- tf->protocol = ATA_PROT_NCQ_NODATA;
+ if ((cdb[2 + cdb_offset] & 0x3) == 0) {
+ /*
+ * When T_LENGTH is zero (No data is transferred), dir should
+ * be DMA_NONE.
+ */
+ if (scmd->sc_data_direction != DMA_NONE) {
+ fp = 2 + cdb_offset;
+ goto invalid_fld;
+ }
+
+ if (ata_is_ncq(tf->protocol))
+ tf->protocol = ATA_PROT_NCQ_NODATA;
+ }
/* enable LBA */
tf->flags |= ATA_TFLAG_LBA;
}
EXPORT_SYMBOL_GPL(mhi_pm_suspend);
-int mhi_pm_resume(struct mhi_controller *mhi_cntrl)
+static int __mhi_pm_resume(struct mhi_controller *mhi_cntrl, bool force)
{
struct mhi_chan *itr, *tmp;
struct device *dev = &mhi_cntrl->mhi_dev->dev;
if (MHI_PM_IN_ERROR_STATE(mhi_cntrl->pm_state))
return -EIO;
- if (mhi_get_mhi_state(mhi_cntrl) != MHI_STATE_M3)
- return -EINVAL;
+ if (mhi_get_mhi_state(mhi_cntrl) != MHI_STATE_M3) {
+ dev_warn(dev, "Resuming from non M3 state (%s)\n",
+ TO_MHI_STATE_STR(mhi_get_mhi_state(mhi_cntrl)));
+ if (!force)
+ return -EINVAL;
+ }
/* Notify clients about exiting LPM */
list_for_each_entry_safe(itr, tmp, &mhi_cntrl->lpm_chans, node) {
return 0;
}
+
+int mhi_pm_resume(struct mhi_controller *mhi_cntrl)
+{
+ return __mhi_pm_resume(mhi_cntrl, false);
+}
EXPORT_SYMBOL_GPL(mhi_pm_resume);
+int mhi_pm_resume_force(struct mhi_controller *mhi_cntrl)
+{
+ return __mhi_pm_resume(mhi_cntrl, true);
+}
+EXPORT_SYMBOL_GPL(mhi_pm_resume_force);
+
int __mhi_device_get_sync(struct mhi_controller *mhi_cntrl)
{
int ret;
#define MHI_PCI_DEFAULT_BAR_NUM 0
-#define MHI_POST_RESET_DELAY_MS 500
+#define MHI_POST_RESET_DELAY_MS 2000
#define HEALTH_CHECK_PERIOD (HZ * 2)
clk_prepare_lock();
+ /*
+ * Set hw->core after grabbing the prepare_lock to synchronize with
+ * callers of clk_core_fill_parent_index() where we treat hw->core
+ * being NULL as the clk not being registered yet. This is crucial so
+ * that clks aren't parented until their parent is fully registered.
+ */
+ core->hw->core = core;
+
ret = clk_pm_runtime_get(core);
if (ret)
goto unlock;
out:
clk_pm_runtime_put(core);
unlock:
- if (ret)
+ if (ret) {
hlist_del_init(&core->child_node);
+ core->hw->core = NULL;
+ }
clk_prepare_unlock();
core->num_parents = init->num_parents;
core->min_rate = 0;
core->max_rate = ULONG_MAX;
- hw->core = core;
ret = clk_core_populate_parent_map(core, init);
if (ret)
goto fail_create_clk;
}
- clk_core_link_consumer(hw->core, hw->clk);
+ clk_core_link_consumer(core, hw->clk);
ret = __clk_core_init(core);
if (!ret)
.probe = imx8qxp_lpcg_clk_probe,
};
-builtin_platform_driver(imx8qxp_lpcg_clk_driver);
+module_platform_driver(imx8qxp_lpcg_clk_driver);
MODULE_AUTHOR("Aisheng Dong <aisheng.dong@nxp.com>");
MODULE_DESCRIPTION("NXP i.MX8QXP LPCG clock driver");
},
.probe = imx8qxp_clk_probe,
};
-builtin_platform_driver(imx8qxp_clk_driver);
+module_platform_driver(imx8qxp_clk_driver);
MODULE_AUTHOR("Aisheng Dong <aisheng.dong@nxp.com>");
MODULE_DESCRIPTION("NXP i.MX8QXP clock driver");
void clk_trion_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
const struct alpha_pll_config *config)
{
+ /*
+ * If the bootloader left the PLL enabled it's likely that there are
+ * RCGs that will lock up if we disable the PLL below.
+ */
+ if (trion_pll_is_enabled(pll, regmap)) {
+ pr_debug("Trion PLL is already enabled, skipping configuration\n");
+ return;
+ }
+
clk_alpha_pll_write_config(regmap, PLL_L_VAL(pll), config->l);
regmap_write(regmap, PLL_CAL_L_VAL(pll), TRION_PLL_CAL_VAL);
clk_alpha_pll_write_config(regmap, PLL_ALPHA_VAL(pll), config->alpha);
val &= mask;
if (mux->parent_map)
- return qcom_find_src_index(hw, mux->parent_map, val);
+ return qcom_find_cfg_index(hw, mux->parent_map, val);
return val;
}
}
EXPORT_SYMBOL_GPL(qcom_find_src_index);
+int qcom_find_cfg_index(struct clk_hw *hw, const struct parent_map *map, u8 cfg)
+{
+ int i, num_parents = clk_hw_get_num_parents(hw);
+
+ for (i = 0; i < num_parents; i++)
+ if (cfg == map[i].cfg)
+ return i;
+
+ return -ENOENT;
+}
+EXPORT_SYMBOL_GPL(qcom_find_cfg_index);
+
struct regmap *
qcom_cc_map(struct platform_device *pdev, const struct qcom_cc_desc *desc)
{
qcom_pll_set_fsm_mode(struct regmap *m, u32 reg, u8 bias_count, u8 lock_count);
extern int qcom_find_src_index(struct clk_hw *hw, const struct parent_map *map,
u8 src);
+extern int qcom_find_cfg_index(struct clk_hw *hw, const struct parent_map *map,
+ u8 cfg);
extern int qcom_cc_register_board_clk(struct device *dev, const char *path,
const char *name, unsigned long rate);
.name = "gcc_sdcc1_apps_clk_src",
.parent_data = gcc_parent_data_1,
.num_parents = ARRAY_SIZE(gcc_parent_data_1),
- .ops = &clk_rcg2_ops,
+ .ops = &clk_rcg2_floor_ops,
},
};
.name = "gcc_sdcc1_ice_core_clk_src",
.parent_data = gcc_parent_data_0,
.num_parents = ARRAY_SIZE(gcc_parent_data_0),
- .ops = &clk_rcg2_floor_ops,
+ .ops = &clk_rcg2_ops,
},
};
regclk = icst_clk_setup(NULL, &icst_desc, name, parent_name, map, ctype);
if (IS_ERR(regclk)) {
- kfree(name);
pr_err("error setting up syscon ICST clock %s\n", name);
+ kfree(name);
return;
}
of_clk_add_provider(np, of_clk_src_simple_get, regclk);
static atomic_t timer_unstable_counter_workaround_in_use = ATOMIC_INIT(0);
-static void erratum_set_next_event_generic(const int access, unsigned long evt,
- struct clock_event_device *clk)
+/*
+ * Force the inlining of this function so that the register accesses
+ * can be themselves correctly inlined.
+ */
+static __always_inline
+void erratum_set_next_event_generic(const int access, unsigned long evt,
+ struct clock_event_device *clk)
{
unsigned long ctrl;
u64 cval;
pr_warn("pclk for %pOFn is present, but could not be activated\n",
np);
- if (!of_property_read_u32(np, "clock-freq", rate) &&
+ if (!of_property_read_u32(np, "clock-freq", rate) ||
!of_property_read_u32(np, "clock-frequency", rate))
return 0;
struct axi_dma_desc *first)
{
u32 priority = chan->chip->dw->hdata->priority[chan->id];
- struct axi_dma_chan_config config;
+ struct axi_dma_chan_config config = {};
u32 irq_mask;
u8 lms = 0; /* Select AXI0 master for LLI fetching */
config.tt_fc = DWAXIDMAC_TT_FC_MEM_TO_MEM_DMAC;
config.prior = priority;
config.hs_sel_dst = DWAXIDMAC_HS_SEL_HW;
- config.hs_sel_dst = DWAXIDMAC_HS_SEL_HW;
+ config.hs_sel_src = DWAXIDMAC_HS_SEL_HW;
switch (chan->direction) {
case DMA_MEM_TO_DEV:
dw_axi_dma_set_byte_halfword(chan, true);
/* DMA configuration */
err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
- if (!err) {
+ if (err) {
pci_err(pdev, "DMA mask 64 set failed\n");
return err;
- } else {
- pci_err(pdev, "DMA mask 64 set failed\n");
-
- err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
- if (err) {
- pci_err(pdev, "DMA mask 32 set failed\n");
- return err;
- }
}
/* Data structure allocation */
INIT_WORK(&idxd->work, idxd_device_reinit);
queue_work(idxd->wq, &idxd->work);
} else {
- spin_lock(&idxd->dev_lock);
idxd->state = IDXD_DEV_HALTED;
idxd_wqs_quiesce(idxd);
idxd_wqs_unmap_portal(idxd);
+ spin_lock(&idxd->dev_lock);
idxd_device_clear_state(idxd);
dev_err(&idxd->pdev->dev,
"idxd halted, need %s.\n",
{
struct idxd_desc *d, *t, *found = NULL;
struct llist_node *head;
+ LIST_HEAD(flist);
desc->completion->status = IDXD_COMP_DESC_ABORT;
/*
found = desc;
continue;
}
- list_add_tail(&desc->list, &ie->work_list);
+
+ if (d->completion->status)
+ list_add_tail(&d->list, &flist);
+ else
+ list_add_tail(&d->list, &ie->work_list);
}
}
if (found)
complete_desc(found, IDXD_COMPLETE_ABORT);
+
+ /*
+ * complete_desc() will return desc to allocator and the desc can be
+ * acquired by a different process and the desc->list can be modified.
+ * Delete desc from list so the list trasversing does not get corrupted
+ * by the other process.
+ */
+ list_for_each_entry_safe(d, t, &flist, list) {
+ list_del_init(&d->list);
+ complete_desc(d, IDXD_COMPLETE_NORMAL);
+ }
}
int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc)
MODULE_DESCRIPTION("STMicroelectronics FDMA engine driver");
MODULE_AUTHOR("Ludovic.barre <Ludovic.barre@st.com>");
MODULE_AUTHOR("Peter Griffin <peter.griffin@linaro.org>");
-MODULE_ALIAS("platform: " DRIVER_NAME);
+MODULE_ALIAS("platform:" DRIVER_NAME);
rm_res = tisci_rm->rm_ranges[RM_RANGE_TCHAN];
if (IS_ERR(rm_res)) {
bitmap_zero(ud->tchan_map, ud->tchan_cnt);
+ irq_res.sets = 1;
} else {
bitmap_fill(ud->tchan_map, ud->tchan_cnt);
for (i = 0; i < rm_res->sets; i++)
udma_mark_resource_ranges(ud, ud->tchan_map,
&rm_res->desc[i], "tchan");
+ irq_res.sets = rm_res->sets;
}
- irq_res.sets = rm_res->sets;
/* rchan and matching default flow ranges */
rm_res = tisci_rm->rm_ranges[RM_RANGE_RCHAN];
if (IS_ERR(rm_res)) {
bitmap_zero(ud->rchan_map, ud->rchan_cnt);
+ irq_res.sets++;
} else {
bitmap_fill(ud->rchan_map, ud->rchan_cnt);
for (i = 0; i < rm_res->sets; i++)
udma_mark_resource_ranges(ud, ud->rchan_map,
&rm_res->desc[i], "rchan");
+ irq_res.sets += rm_res->sets;
}
- irq_res.sets += rm_res->sets;
irq_res.desc = kcalloc(irq_res.sets, sizeof(*irq_res.desc), GFP_KERNEL);
+ if (!irq_res.desc)
+ return -ENOMEM;
rm_res = tisci_rm->rm_ranges[RM_RANGE_TCHAN];
- for (i = 0; i < rm_res->sets; i++) {
- irq_res.desc[i].start = rm_res->desc[i].start;
- irq_res.desc[i].num = rm_res->desc[i].num;
- irq_res.desc[i].start_sec = rm_res->desc[i].start_sec;
- irq_res.desc[i].num_sec = rm_res->desc[i].num_sec;
+ if (IS_ERR(rm_res)) {
+ irq_res.desc[0].start = 0;
+ irq_res.desc[0].num = ud->tchan_cnt;
+ i = 1;
+ } else {
+ for (i = 0; i < rm_res->sets; i++) {
+ irq_res.desc[i].start = rm_res->desc[i].start;
+ irq_res.desc[i].num = rm_res->desc[i].num;
+ irq_res.desc[i].start_sec = rm_res->desc[i].start_sec;
+ irq_res.desc[i].num_sec = rm_res->desc[i].num_sec;
+ }
}
rm_res = tisci_rm->rm_ranges[RM_RANGE_RCHAN];
- for (j = 0; j < rm_res->sets; j++, i++) {
- if (rm_res->desc[j].num) {
- irq_res.desc[i].start = rm_res->desc[j].start +
- ud->soc_data->oes.udma_rchan;
- irq_res.desc[i].num = rm_res->desc[j].num;
- }
- if (rm_res->desc[j].num_sec) {
- irq_res.desc[i].start_sec = rm_res->desc[j].start_sec +
- ud->soc_data->oes.udma_rchan;
- irq_res.desc[i].num_sec = rm_res->desc[j].num_sec;
+ if (IS_ERR(rm_res)) {
+ irq_res.desc[i].start = 0;
+ irq_res.desc[i].num = ud->rchan_cnt;
+ } else {
+ for (j = 0; j < rm_res->sets; j++, i++) {
+ if (rm_res->desc[j].num) {
+ irq_res.desc[i].start = rm_res->desc[j].start +
+ ud->soc_data->oes.udma_rchan;
+ irq_res.desc[i].num = rm_res->desc[j].num;
+ }
+ if (rm_res->desc[j].num_sec) {
+ irq_res.desc[i].start_sec = rm_res->desc[j].start_sec +
+ ud->soc_data->oes.udma_rchan;
+ irq_res.desc[i].num_sec = rm_res->desc[j].num_sec;
+ }
}
}
ret = ti_sci_inta_msi_domain_alloc_irqs(ud->dev, &irq_res);
rm_res = tisci_rm->rm_ranges[RM_RANGE_BCHAN];
if (IS_ERR(rm_res)) {
bitmap_zero(ud->bchan_map, ud->bchan_cnt);
+ irq_res.sets++;
} else {
bitmap_fill(ud->bchan_map, ud->bchan_cnt);
for (i = 0; i < rm_res->sets; i++)
udma_mark_resource_ranges(ud, ud->bchan_map,
&rm_res->desc[i],
"bchan");
+ irq_res.sets += rm_res->sets;
}
- irq_res.sets += rm_res->sets;
}
/* tchan ranges */
rm_res = tisci_rm->rm_ranges[RM_RANGE_TCHAN];
if (IS_ERR(rm_res)) {
bitmap_zero(ud->tchan_map, ud->tchan_cnt);
+ irq_res.sets += 2;
} else {
bitmap_fill(ud->tchan_map, ud->tchan_cnt);
for (i = 0; i < rm_res->sets; i++)
udma_mark_resource_ranges(ud, ud->tchan_map,
&rm_res->desc[i],
"tchan");
+ irq_res.sets += rm_res->sets * 2;
}
- irq_res.sets += rm_res->sets * 2;
}
/* rchan ranges */
rm_res = tisci_rm->rm_ranges[RM_RANGE_RCHAN];
if (IS_ERR(rm_res)) {
bitmap_zero(ud->rchan_map, ud->rchan_cnt);
+ irq_res.sets += 2;
} else {
bitmap_fill(ud->rchan_map, ud->rchan_cnt);
for (i = 0; i < rm_res->sets; i++)
udma_mark_resource_ranges(ud, ud->rchan_map,
&rm_res->desc[i],
"rchan");
+ irq_res.sets += rm_res->sets * 2;
}
- irq_res.sets += rm_res->sets * 2;
}
irq_res.desc = kcalloc(irq_res.sets, sizeof(*irq_res.desc), GFP_KERNEL);
+ if (!irq_res.desc)
+ return -ENOMEM;
if (ud->bchan_cnt) {
rm_res = tisci_rm->rm_ranges[RM_RANGE_BCHAN];
- for (i = 0; i < rm_res->sets; i++) {
- irq_res.desc[i].start = rm_res->desc[i].start +
- oes->bcdma_bchan_ring;
- irq_res.desc[i].num = rm_res->desc[i].num;
+ if (IS_ERR(rm_res)) {
+ irq_res.desc[0].start = oes->bcdma_bchan_ring;
+ irq_res.desc[0].num = ud->bchan_cnt;
+ i = 1;
+ } else {
+ for (i = 0; i < rm_res->sets; i++) {
+ irq_res.desc[i].start = rm_res->desc[i].start +
+ oes->bcdma_bchan_ring;
+ irq_res.desc[i].num = rm_res->desc[i].num;
+ }
}
}
if (ud->tchan_cnt) {
rm_res = tisci_rm->rm_ranges[RM_RANGE_TCHAN];
- for (j = 0; j < rm_res->sets; j++, i += 2) {
- irq_res.desc[i].start = rm_res->desc[j].start +
- oes->bcdma_tchan_data;
- irq_res.desc[i].num = rm_res->desc[j].num;
-
- irq_res.desc[i + 1].start = rm_res->desc[j].start +
- oes->bcdma_tchan_ring;
- irq_res.desc[i + 1].num = rm_res->desc[j].num;
+ if (IS_ERR(rm_res)) {
+ irq_res.desc[i].start = oes->bcdma_tchan_data;
+ irq_res.desc[i].num = ud->tchan_cnt;
+ irq_res.desc[i + 1].start = oes->bcdma_tchan_ring;
+ irq_res.desc[i + 1].num = ud->tchan_cnt;
+ i += 2;
+ } else {
+ for (j = 0; j < rm_res->sets; j++, i += 2) {
+ irq_res.desc[i].start = rm_res->desc[j].start +
+ oes->bcdma_tchan_data;
+ irq_res.desc[i].num = rm_res->desc[j].num;
+
+ irq_res.desc[i + 1].start = rm_res->desc[j].start +
+ oes->bcdma_tchan_ring;
+ irq_res.desc[i + 1].num = rm_res->desc[j].num;
+ }
}
}
if (ud->rchan_cnt) {
rm_res = tisci_rm->rm_ranges[RM_RANGE_RCHAN];
- for (j = 0; j < rm_res->sets; j++, i += 2) {
- irq_res.desc[i].start = rm_res->desc[j].start +
- oes->bcdma_rchan_data;
- irq_res.desc[i].num = rm_res->desc[j].num;
-
- irq_res.desc[i + 1].start = rm_res->desc[j].start +
- oes->bcdma_rchan_ring;
- irq_res.desc[i + 1].num = rm_res->desc[j].num;
+ if (IS_ERR(rm_res)) {
+ irq_res.desc[i].start = oes->bcdma_rchan_data;
+ irq_res.desc[i].num = ud->rchan_cnt;
+ irq_res.desc[i + 1].start = oes->bcdma_rchan_ring;
+ irq_res.desc[i + 1].num = ud->rchan_cnt;
+ i += 2;
+ } else {
+ for (j = 0; j < rm_res->sets; j++, i += 2) {
+ irq_res.desc[i].start = rm_res->desc[j].start +
+ oes->bcdma_rchan_data;
+ irq_res.desc[i].num = rm_res->desc[j].num;
+
+ irq_res.desc[i + 1].start = rm_res->desc[j].start +
+ oes->bcdma_rchan_ring;
+ irq_res.desc[i + 1].num = rm_res->desc[j].num;
+ }
}
}
if (IS_ERR(rm_res)) {
/* all rflows are assigned exclusively to Linux */
bitmap_zero(ud->rflow_in_use, ud->rflow_cnt);
+ irq_res.sets = 1;
} else {
bitmap_fill(ud->rflow_in_use, ud->rflow_cnt);
for (i = 0; i < rm_res->sets; i++)
udma_mark_resource_ranges(ud, ud->rflow_in_use,
&rm_res->desc[i], "rflow");
+ irq_res.sets = rm_res->sets;
}
- irq_res.sets = rm_res->sets;
/* tflow ranges */
rm_res = tisci_rm->rm_ranges[RM_RANGE_TFLOW];
if (IS_ERR(rm_res)) {
/* all tflows are assigned exclusively to Linux */
bitmap_zero(ud->tflow_map, ud->tflow_cnt);
+ irq_res.sets++;
} else {
bitmap_fill(ud->tflow_map, ud->tflow_cnt);
for (i = 0; i < rm_res->sets; i++)
udma_mark_resource_ranges(ud, ud->tflow_map,
&rm_res->desc[i], "tflow");
+ irq_res.sets += rm_res->sets;
}
- irq_res.sets += rm_res->sets;
irq_res.desc = kcalloc(irq_res.sets, sizeof(*irq_res.desc), GFP_KERNEL);
+ if (!irq_res.desc)
+ return -ENOMEM;
rm_res = tisci_rm->rm_ranges[RM_RANGE_TFLOW];
- for (i = 0; i < rm_res->sets; i++) {
- irq_res.desc[i].start = rm_res->desc[i].start +
- oes->pktdma_tchan_flow;
- irq_res.desc[i].num = rm_res->desc[i].num;
+ if (IS_ERR(rm_res)) {
+ irq_res.desc[0].start = oes->pktdma_tchan_flow;
+ irq_res.desc[0].num = ud->tflow_cnt;
+ i = 1;
+ } else {
+ for (i = 0; i < rm_res->sets; i++) {
+ irq_res.desc[i].start = rm_res->desc[i].start +
+ oes->pktdma_tchan_flow;
+ irq_res.desc[i].num = rm_res->desc[i].num;
+ }
}
rm_res = tisci_rm->rm_ranges[RM_RANGE_RFLOW];
- for (j = 0; j < rm_res->sets; j++, i++) {
- irq_res.desc[i].start = rm_res->desc[j].start +
- oes->pktdma_rchan_flow;
- irq_res.desc[i].num = rm_res->desc[j].num;
+ if (IS_ERR(rm_res)) {
+ irq_res.desc[i].start = oes->pktdma_rchan_flow;
+ irq_res.desc[i].num = ud->rflow_cnt;
+ } else {
+ for (j = 0; j < rm_res->sets; j++, i++) {
+ irq_res.desc[i].start = rm_res->desc[j].start +
+ oes->pktdma_rchan_flow;
+ irq_res.desc[i].num = rm_res->desc[j].num;
+ }
}
ret = ti_sci_inta_msi_domain_alloc_irqs(ud->dev, &irq_res);
kfree(irq_res.desc);
struct generic_pm_domain genpd;
struct scpi_ops *ops;
u32 domain;
- char name[30];
};
/*
scpi_pd->domain = i;
scpi_pd->ops = scpi_ops;
- sprintf(scpi_pd->name, "%pOFn.%d", np, i);
- scpi_pd->genpd.name = scpi_pd->name;
+ scpi_pd->genpd.name = devm_kasprintf(dev, GFP_KERNEL,
+ "%pOFn.%d", np, i);
+ if (!scpi_pd->genpd.name) {
+ dev_err(dev, "Failed to allocate genpd name:%pOFn.%d\n",
+ np, i);
+ continue;
+ }
scpi_pd->genpd.power_off = scpi_pd_power_off;
scpi_pd->genpd.power_on = scpi_pd_power_on;
const char *root_path, *filename = NULL;
char *root_path_buf;
size_t root_len;
+ size_t root_path_buf_len = 512;
- root_path_buf = kzalloc(512, GFP_KERNEL);
+ root_path_buf = kzalloc(root_path_buf_len, GFP_KERNEL);
if (!root_path_buf)
goto out;
root_path = dentry_path(bpmp->debugfs_mirror, root_path_buf,
- sizeof(root_path_buf));
+ root_path_buf_len);
if (IS_ERR(root_path))
goto out;
AMD_PG_SUPPORT_CP |
AMD_PG_SUPPORT_GDS |
AMD_PG_SUPPORT_RLC_SMU_HS)) {
- WREG32(mmRLC_JUMP_TABLE_RESTORE,
- adev->gfx.rlc.cp_table_gpu_addr >> 8);
+ WREG32_SOC15(GC, 0, mmRLC_JUMP_TABLE_RESTORE,
+ adev->gfx.rlc.cp_table_gpu_addr >> 8);
gfx_v9_0_init_gfx_power_gating(adev);
}
}
ENABLE_ADVANCED_DRIVER_MODEL, 1);
tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL,
SYSTEM_APERTURE_UNMAPPED_ACCESS, 0);
- tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0);
tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL,
MTYPE, MTYPE_UC);/* XXX for emulation. */
tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ATC_EN, 1);
ENABLE_ADVANCED_DRIVER_MODEL, 1);
tmp = REG_SET_FIELD(tmp, GCMC_VM_MX_L1_TLB_CNTL,
SYSTEM_APERTURE_UNMAPPED_ACCESS, 0);
- tmp = REG_SET_FIELD(tmp, GCMC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0);
tmp = REG_SET_FIELD(tmp, GCMC_VM_MX_L1_TLB_CNTL,
MTYPE, MTYPE_UC); /* UC, uncached */
ENABLE_ADVANCED_DRIVER_MODEL, 1);
tmp = REG_SET_FIELD(tmp, GCMC_VM_MX_L1_TLB_CNTL,
SYSTEM_APERTURE_UNMAPPED_ACCESS, 0);
- tmp = REG_SET_FIELD(tmp, GCMC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0);
tmp = REG_SET_FIELD(tmp, GCMC_VM_MX_L1_TLB_CNTL,
MTYPE, MTYPE_UC); /* UC, uncached */
return 0;
}
+ /*
+ * Pair the operations did in gmc_v9_0_hw_init and thus maintain
+ * a correct cached state for GMC. Otherwise, the "gate" again
+ * operation on S3 resuming will fail due to wrong cached state.
+ */
+ if (adev->mmhub.funcs->update_power_gating)
+ adev->mmhub.funcs->update_power_gating(adev, false);
+
amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0);
amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0);
ENABLE_ADVANCED_DRIVER_MODEL, 1);
tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL,
SYSTEM_APERTURE_UNMAPPED_ACCESS, 0);
- tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0);
tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL,
MTYPE, MTYPE_UC);/* XXX for emulation. */
tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ATC_EN, 1);
if (amdgpu_sriov_vf(adev))
return;
- if (enable && adev->pg_flags & AMD_PG_SUPPORT_MMHUB) {
- amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GMC, true);
-
- }
+ if (adev->pg_flags & AMD_PG_SUPPORT_MMHUB)
+ amdgpu_dpm_set_powergating_by_smu(adev,
+ AMD_IP_BLOCK_TYPE_GMC,
+ enable);
}
static int mmhub_v1_0_gart_enable(struct amdgpu_device *adev)
ENABLE_ADVANCED_DRIVER_MODEL, 1);
tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL,
SYSTEM_APERTURE_UNMAPPED_ACCESS, 0);
- tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0);
tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL,
MTYPE, MTYPE_UC);/* XXX for emulation. */
tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ATC_EN, 1);
ENABLE_ADVANCED_DRIVER_MODEL, 1);
tmp = REG_SET_FIELD(tmp, MMMC_VM_MX_L1_TLB_CNTL,
SYSTEM_APERTURE_UNMAPPED_ACCESS, 0);
- tmp = REG_SET_FIELD(tmp, MMMC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0);
tmp = REG_SET_FIELD(tmp, MMMC_VM_MX_L1_TLB_CNTL,
MTYPE, MTYPE_UC); /* UC, uncached */
ENABLE_ADVANCED_DRIVER_MODEL, 1);
tmp = REG_SET_FIELD(tmp, MMMC_VM_MX_L1_TLB_CNTL,
SYSTEM_APERTURE_UNMAPPED_ACCESS, 0);
- tmp = REG_SET_FIELD(tmp, MMMC_VM_MX_L1_TLB_CNTL, ECO_BITS, 0);
tmp = REG_SET_FIELD(tmp, MMMC_VM_MX_L1_TLB_CNTL,
MTYPE, MTYPE_UC); /* UC, uncached */
tmp = REG_SET_FIELD(tmp, VMSHAREDVC0_MC_VM_MX_L1_TLB_CNTL,
SYSTEM_APERTURE_UNMAPPED_ACCESS, 0);
tmp = REG_SET_FIELD(tmp, VMSHAREDVC0_MC_VM_MX_L1_TLB_CNTL,
- ECO_BITS, 0);
- tmp = REG_SET_FIELD(tmp, VMSHAREDVC0_MC_VM_MX_L1_TLB_CNTL,
MTYPE, MTYPE_UC);/* XXX for emulation. */
tmp = REG_SET_FIELD(tmp, VMSHAREDVC0_MC_VM_MX_L1_TLB_CNTL,
ATC_EN, 1);
return 0;
}
+ /* Reset DMCUB if it was previously running - before we overwrite its memory. */
+ status = dmub_srv_hw_reset(dmub_srv);
+ if (status != DMUB_STATUS_OK)
+ DRM_WARN("Error resetting DMUB HW: %d\n", status);
+
hdr = (const struct dmcub_firmware_header_v1_0 *)dmub_fw->data;
fw_inst_const = dmub_fw->data +
*/
link_enc_cfg_init(dm->dc, dc_state);
- amdgpu_dm_outbox_init(adev);
+ if (dc_enable_dmub_notifications(adev->dm.dc))
+ amdgpu_dm_outbox_init(adev);
r = dm_dmub_hw_init(adev);
if (r)
/* TODO: Remove dc_state->dccg, use dc->dccg directly. */
dc_resource_state_construct(dm->dc, dm_state->context);
+ /* Re-enable outbox interrupts for DPIA. */
+ if (dc_enable_dmub_notifications(adev->dm.dc))
+ amdgpu_dm_outbox_init(adev);
+
/* Before powering on DC we need to re-initialize DMUB. */
r = dm_dmub_hw_init(adev);
if (r)
*edp_num = 0;
for (i = 0; i < dc->link_count; i++) {
// report any eDP links, even unconnected DDI's
+ if (!dc->links[i])
+ continue;
if (dc->links[i]->connector_signal == SIGNAL_TYPE_EDP) {
edp_links[*edp_num] = dc->links[i];
if (++(*edp_num) == MAX_NUM_EDP)
.z10_restore = dcn31_z10_restore,
.z10_save_init = dcn31_z10_save_init,
.set_disp_pattern_generator = dcn30_set_disp_pattern_generator,
+ .exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state,
.update_visual_confirm_color = dcn20_update_visual_confirm_color,
};
pp_dpm_powergate_vce(handle, gate);
break;
case AMD_IP_BLOCK_TYPE_GMC:
- pp_dpm_powergate_mmhub(handle);
+ /*
+ * For now, this is only used on PICASSO.
+ * And only "gate" operation is supported.
+ */
+ if (gate)
+ pp_dpm_powergate_mmhub(handle);
break;
case AMD_IP_BLOCK_TYPE_GFX:
ret = pp_dpm_powergate_gfx(handle, gate);
kfree(smu_table->watermarks_table);
smu_table->watermarks_table = NULL;
+ kfree(smu_table->gpu_metrics_table);
+ smu_table->gpu_metrics_table = NULL;
+
return 0;
}
int smu_v13_0_check_fw_version(struct smu_context *smu)
{
+ struct amdgpu_device *adev = smu->adev;
uint32_t if_version = 0xff, smu_version = 0xff;
uint16_t smu_major;
uint8_t smu_minor, smu_debug;
smu_major = (smu_version >> 16) & 0xffff;
smu_minor = (smu_version >> 8) & 0xff;
smu_debug = (smu_version >> 0) & 0xff;
+ if (smu->is_apu)
+ adev->pm.fw_version = smu_version;
switch (smu->adev->ip_versions[MP1_HWIP][0]) {
case IP_VERSION(13, 0, 2):
if (crtc->state)
crtc->funcs->atomic_destroy_state(crtc, crtc->state);
- __drm_atomic_helper_crtc_reset(crtc, &ast_state->base);
+ if (ast_state)
+ __drm_atomic_helper_crtc_reset(crtc, &ast_state->base);
+ else
+ __drm_atomic_helper_crtc_reset(crtc, NULL);
}
static struct drm_crtc_state *
sizes->fb_width, sizes->fb_height);
info->par = fb_helper;
- snprintf(info->fix.id, sizeof(info->fix.id), "%s",
+ /*
+ * The DRM drivers fbdev emulation device name can be confusing if the
+ * driver name also has a "drm" suffix on it. Leading to names such as
+ * "simpledrmdrmfb" in /proc/fb. Unfortunately, it's an uAPI and can't
+ * be changed due user-space tools (e.g: pm-utils) matching against it.
+ */
+ snprintf(info->fix.id, sizeof(info->fix.id), "%sdrmfb",
fb_helper->dev->driver->name);
}
#include <linux/shmem_fs.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
+#include <linux/module.h>
#ifdef CONFIG_X86
#include <asm/set_memory.h>
if (*fence) {
ret = dma_fence_chain_find_seqno(fence, point);
- if (!ret)
+ if (!ret) {
+ /* If the requested seqno is already signaled
+ * drm_syncobj_find_fence may return a NULL
+ * fence. To make sure the recipient gets
+ * signalled, use a new fence instead.
+ */
+ if (!*fence)
+ *fence = dma_fence_get_stub();
+
goto out;
+ }
dma_fence_put(*fence);
} else {
ret = -EINVAL;
continue;
offset = readcount + dmc->dmc_info[id].dmc_offset * 4;
- if (fw->size - offset < 0) {
+ if (offset > fw->size) {
drm_err(&dev_priv->drm, "Reading beyond the fw_size\n");
continue;
}
out_fence = eb_requests_create(&eb, in_fence, out_fence_fd);
if (IS_ERR(out_fence)) {
err = PTR_ERR(out_fence);
+ out_fence = NULL;
if (eb.requests[0])
goto err_request;
else
#include <linux/slab.h> /* fault-inject.h is not standalone! */
#include <linux/fault-inject.h>
+#include <linux/sched/mm.h>
#include "gem/i915_gem_lmem.h"
#include "i915_trace.h"
GAMT_CHKN_BIT_REG,
GAMT_CHKN_DISABLE_L3_COH_PIPE);
+ /* Wa_1407352427:icl,ehl */
+ wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE2,
+ PSDUNIT_CLKGATE_DIS);
+
+ /* Wa_1406680159:icl,ehl */
+ wa_write_or(wal,
+ SUBSLICE_UNIT_LEVEL_CLKGATE,
+ GWUNIT_CLKGATE_DIS);
+
/* Wa_1607087056:icl,ehl,jsl */
if (IS_ICELAKE(i915) ||
IS_JSL_EHL_GT_STEP(i915, STEP_A0, STEP_B0))
wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE,
VSUNIT_CLKGATE_DIS | HSUNIT_CLKGATE_DIS);
- /* Wa_1407352427:icl,ehl */
- wa_write_or(wal, UNSLICE_UNIT_LEVEL_CLKGATE2,
- PSDUNIT_CLKGATE_DIS);
-
- /* Wa_1406680159:icl,ehl */
- wa_write_or(wal,
- SUBSLICE_UNIT_LEVEL_CLKGATE,
- GWUNIT_CLKGATE_DIS);
-
/*
* Wa_1408767742:icl[a2..forever],ehl[all]
* Wa_1605460711:icl[a0..c0]
#include <linux/sched.h>
#include <linux/sched/clock.h>
#include <linux/sched/signal.h>
+#include <linux/sched/mm.h>
#include "gem/i915_gem_context.h"
#include "gt/intel_breadcrumbs.h"
#include <linux/regulator/consumer.h>
#include <linux/reset.h>
#include <linux/clk.h>
+#include <linux/slab.h>
#include <linux/dma-mapping.h>
#include <linux/platform_device.h>
*/
#include <linux/vmalloc.h>
+#include <linux/sched/mm.h>
#include "msm_drv.h"
#include "msm_gem.h"
{
struct drm_display_mode mode = { SIMPLEDRM_MODE(width, height) };
- mode.clock = 60 /* Hz */ * mode.hdisplay * mode.vdisplay;
+ mode.clock = mode.hdisplay * mode.vdisplay * 60 / 1000 /* kHz */;
drm_mode_set_name(&mode);
return mode;
* as an indication that we're about to swap out.
*/
memset(&place, 0, sizeof(place));
- place.mem_type = TTM_PL_SYSTEM;
+ place.mem_type = bo->resource->mem_type;
if (!ttm_bo_evict_swapout_allowable(bo, ctx, &place, &locked, NULL))
return -EBUSY;
struct ttm_place hop;
memset(&hop, 0, sizeof(hop));
+ place.mem_type = TTM_PL_SYSTEM;
ret = ttm_resource_alloc(bo, &place, &evict_mem);
if (unlikely(ret))
goto out;
#include <linux/sched.h>
#include <linux/shmem_fs.h>
#include <linux/file.h>
+#include <linux/module.h>
#include <drm/drm_cache.h>
#include <drm/ttm/ttm_bo_driver.h>
config HID_CHICONY
tristate "Chicony devices"
- depends on HID
+ depends on USB_HID
default !EXPERT
help
Support for Chicony Tactical pad and special keys on Chicony keyboards.
config HID_CORSAIR
tristate "Corsair devices"
- depends on HID && USB && LEDS_CLASS
+ depends on USB_HID && LEDS_CLASS
help
Support for Corsair devices that are not fully compliant with the
HID standard.
config HID_PRODIKEYS
tristate "Prodikeys PC-MIDI Keyboard support"
- depends on HID && SND
+ depends on USB_HID && SND
select SND_RAWMIDI
help
Support for Prodikeys PC-MIDI Keyboard device support.
config HID_LOGITECH
tristate "Logitech devices"
- depends on HID
+ depends on USB_HID
depends on LEDS_CLASS
default !EXPERT
help
config HID_SAMSUNG
tristate "Samsung InfraRed remote control or keyboards"
- depends on HID
+ depends on USB_HID
help
Support for Samsung InfraRed remote control or keyboards.
if (drvdata->quirks & QUIRK_IS_MULTITOUCH)
drvdata->tp = &asus_i2c_tp;
- if ((drvdata->quirks & QUIRK_T100_KEYBOARD) &&
- hid_is_using_ll_driver(hdev, &usb_hid_driver)) {
+ if ((drvdata->quirks & QUIRK_T100_KEYBOARD) && hid_is_usb(hdev)) {
struct usb_interface *intf = to_usb_interface(hdev->dev.parent);
if (intf->altsetting->desc.bInterfaceNumber == T100_TPAD_INTF) {
drvdata->tp = &asus_t100chi_tp;
}
- if ((drvdata->quirks & QUIRK_MEDION_E1239T) &&
- hid_is_using_ll_driver(hdev, &usb_hid_driver)) {
+ if ((drvdata->quirks & QUIRK_MEDION_E1239T) && hid_is_usb(hdev)) {
struct usb_host_interface *alt =
to_usb_interface(hdev->dev.parent)->altsetting;
struct bigben_device, worker);
struct hid_field *report_field = bigben->report->field[0];
- if (bigben->removed)
+ if (bigben->removed || !report_field)
return;
if (bigben->work_led) {
{
int ret;
+ if (!hid_is_usb(hdev))
+ return -EINVAL;
+
hdev->quirks |= HID_QUIRK_INPUT_PER_APP;
ret = hid_parse(hdev);
if (ret) {
int ret;
unsigned long quirks = id->driver_data;
struct corsair_drvdata *drvdata;
- struct usb_interface *usbif = to_usb_interface(dev->dev.parent);
+ struct usb_interface *usbif;
+
+ if (!hid_is_usb(dev))
+ return -EINVAL;
+
+ usbif = to_usb_interface(dev->dev.parent);
drvdata = devm_kzalloc(&dev->dev, sizeof(struct corsair_drvdata),
GFP_KERNEL);
static int is_not_elan_touchpad(struct hid_device *hdev)
{
- if (hdev->bus == BUS_USB) {
+ if (hid_is_usb(hdev)) {
struct usb_interface *intf = to_usb_interface(hdev->dev.parent);
return (intf->altsetting->desc.bInterfaceNumber !=
int ret;
struct usb_device *udev;
+ if (!hid_is_usb(hdev))
+ return -EINVAL;
+
priv = kzalloc(sizeof(*priv), GFP_KERNEL);
if (!priv)
return -ENOMEM;
struct ft260_get_chip_version_report version;
int ret;
+ if (!hid_is_usb(hdev))
+ return -EINVAL;
+
dev = devm_kzalloc(&hdev->dev, sizeof(*dev), GFP_KERNEL);
if (!dev)
return -ENOMEM;
{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_DON) },
{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
+ USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_EEL) },
+ { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_HAMMER) },
{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_MAGNEMITE) },
static int holtek_kbd_probe(struct hid_device *hdev,
const struct hid_device_id *id)
{
- struct usb_interface *intf = to_usb_interface(hdev->dev.parent);
- int ret = hid_parse(hdev);
+ struct usb_interface *intf;
+ int ret;
+
+ if (!hid_is_usb(hdev))
+ return -EINVAL;
+ ret = hid_parse(hdev);
if (!ret)
ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
+ intf = to_usb_interface(hdev->dev.parent);
if (!ret && intf->cur_altsetting->desc.bInterfaceNumber == 1) {
struct hid_input *hidinput;
list_for_each_entry(hidinput, &hdev->inputs, list) {
return rdesc;
}
+static int holtek_mouse_probe(struct hid_device *hdev,
+ const struct hid_device_id *id)
+{
+ if (!hid_is_usb(hdev))
+ return -EINVAL;
+ return 0;
+}
+
static const struct hid_device_id holtek_mouse_devices[] = {
{ HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT,
USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A067) },
.name = "holtek_mouse",
.id_table = holtek_mouse_devices,
.report_fixup = holtek_mouse_report_fixup,
+ .probe = holtek_mouse_probe,
};
module_hid_driver(holtek_mouse_driver);
#define USB_DEVICE_ID_HP_X2_10_COVER 0x0755
#define I2C_DEVICE_ID_HP_ENVY_X360_15 0x2d05
#define I2C_DEVICE_ID_HP_SPECTRE_X360_15 0x2817
+#define USB_DEVICE_ID_ASUS_UX550VE_TOUCHSCREEN 0x2544
#define USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN 0x2706
#define I2C_DEVICE_ID_SURFACE_GO_TOUCHSCREEN 0x261A
#define USB_DEVICE_ID_GOOGLE_MAGNEMITE 0x503d
#define USB_DEVICE_ID_GOOGLE_MOONBALL 0x5044
#define USB_DEVICE_ID_GOOGLE_DON 0x5050
+#define USB_DEVICE_ID_GOOGLE_EEL 0x5057
#define USB_VENDOR_ID_GOTOP 0x08f2
#define USB_DEVICE_ID_SUPER_Q2 0x007f
#define USB_DEVICE_ID_MS_TOUCH_COVER_2 0x07a7
#define USB_DEVICE_ID_MS_TYPE_COVER_2 0x07a9
#define USB_DEVICE_ID_MS_POWER_COVER 0x07da
+#define USB_DEVICE_ID_MS_SURFACE3_COVER 0x07de
#define USB_DEVICE_ID_MS_XBOX_ONE_S_CONTROLLER 0x02fd
#define USB_DEVICE_ID_MS_PIXART_MOUSE 0x00cb
#define USB_DEVICE_ID_8BITDO_SN30_PRO_PLUS 0x02e0
HID_BATTERY_QUIRK_IGNORE },
{ HID_USB_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ASUS_UX550_TOUCHSCREEN),
HID_BATTERY_QUIRK_IGNORE },
+ { HID_USB_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_ASUS_UX550VE_TOUCHSCREEN),
+ HID_BATTERY_QUIRK_IGNORE },
{ HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_ENVY_X360_15),
HID_BATTERY_QUIRK_IGNORE },
{ HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, I2C_DEVICE_ID_HP_SPECTRE_X360_15),
static int lg_probe(struct hid_device *hdev, const struct hid_device_id *id)
{
- struct usb_interface *iface = to_usb_interface(hdev->dev.parent);
- __u8 iface_num = iface->cur_altsetting->desc.bInterfaceNumber;
+ struct usb_interface *iface;
+ __u8 iface_num;
unsigned int connect_mask = HID_CONNECT_DEFAULT;
struct lg_drv_data *drv_data;
int ret;
+ if (!hid_is_usb(hdev))
+ return -EINVAL;
+
+ iface = to_usb_interface(hdev->dev.parent);
+ iface_num = iface->cur_altsetting->desc.bInterfaceNumber;
+
/* G29 only work with the 1st interface */
if ((hdev->product == USB_DEVICE_ID_LOGITECH_G29_WHEEL) &&
(iface_num != 0)) {
case recvr_type_bluetooth: no_dj_interfaces = 2; break;
case recvr_type_dinovo: no_dj_interfaces = 2; break;
}
- if (hid_is_using_ll_driver(hdev, &usb_hid_driver)) {
+ if (hid_is_usb(hdev)) {
intf = to_usb_interface(hdev->dev.parent);
if (intf && intf->altsetting->desc.bInterfaceNumber >=
no_dj_interfaces) {
static int pk_probe(struct hid_device *hdev, const struct hid_device_id *id)
{
int ret;
- struct usb_interface *intf = to_usb_interface(hdev->dev.parent);
- unsigned short ifnum = intf->cur_altsetting->desc.bInterfaceNumber;
+ struct usb_interface *intf;
+ unsigned short ifnum;
unsigned long quirks = id->driver_data;
struct pk_device *pk;
struct pcmidi_snd *pm = NULL;
+ if (!hid_is_usb(hdev))
+ return -EINVAL;
+
+ intf = to_usb_interface(hdev->dev.parent);
+ ifnum = intf->cur_altsetting->desc.bInterfaceNumber;
+
pk = kzalloc(sizeof(*pk), GFP_KERNEL);
if (pk == NULL) {
hid_err(hdev, "can't alloc descriptor\n");
{ HID_USB_DEVICE(USB_VENDOR_ID_MCS, USB_DEVICE_ID_MCS_GAMEPADBLOCK), HID_QUIRK_MULTI_INPUT },
{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_PIXART_MOUSE), HID_QUIRK_ALWAYS_POLL },
{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_POWER_COVER), HID_QUIRK_NO_INIT_REPORTS },
+ { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_SURFACE3_COVER), HID_QUIRK_NO_INIT_REPORTS },
{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_SURFACE_PRO_2), HID_QUIRK_NO_INIT_REPORTS },
{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TOUCH_COVER_2), HID_QUIRK_NO_INIT_REPORTS },
{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_2), HID_QUIRK_NO_INIT_REPORTS },
{
int retval;
+ if (!hid_is_usb(hdev))
+ return -EINVAL;
+
retval = hid_parse(hdev);
if (retval) {
hid_err(hdev, "parse failed\n");
{
int retval;
+ if (!hid_is_usb(hdev))
+ return -EINVAL;
+
retval = hid_parse(hdev);
if (retval) {
hid_err(hdev, "parse failed\n");
{
int retval;
+ if (!hid_is_usb(hdev))
+ return -EINVAL;
+
retval = hid_parse(hdev);
if (retval) {
hid_err(hdev, "parse failed\n");
{
int retval;
+ if (!hid_is_usb(hdev))
+ return -EINVAL;
+
retval = hid_parse(hdev);
if (retval) {
hid_err(hdev, "parse failed\n");
{
int retval;
+ if (!hid_is_usb(hdev))
+ return -EINVAL;
+
retval = hid_parse(hdev);
if (retval) {
hid_err(hdev, "parse failed\n");
{
int retval;
+ if (!hid_is_usb(hdev))
+ return -EINVAL;
+
retval = hid_parse(hdev);
if (retval) {
hid_err(hdev, "parse failed\n");
{
int retval;
+ if (!hid_is_usb(hdev))
+ return -EINVAL;
+
retval = hid_parse(hdev);
if (retval) {
hid_err(hdev, "parse failed\n");
{
int retval;
+ if (!hid_is_usb(hdev))
+ return -EINVAL;
+
retval = hid_parse(hdev);
if (retval) {
hid_err(hdev, "parse failed\n");
{
int retval;
+ if (!hid_is_usb(hdev))
+ return -EINVAL;
+
retval = hid_parse(hdev);
if (retval) {
hid_err(hdev, "parse failed\n");
{
int retval;
+ if (!hid_is_usb(hdev))
+ return -EINVAL;
+
retval = hid_parse(hdev);
if (retval) {
hid_err(hdev, "parse failed\n");
int ret;
unsigned int cmask = HID_CONNECT_DEFAULT;
+ if (!hid_is_usb(hdev))
+ return -EINVAL;
+
ret = hid_parse(hdev);
if (ret) {
hid_err(hdev, "parse failed\n");
sc->quirks = quirks;
hid_set_drvdata(hdev, sc);
sc->hdev = hdev;
- usbdev = to_usb_device(sc->hdev->dev.parent->parent);
ret = hid_parse(hdev);
if (ret) {
*/
if (!(hdev->claimed & HID_CLAIMED_INPUT)) {
hid_err(hdev, "failed to claim input\n");
- hid_hw_stop(hdev);
- return -ENODEV;
+ ret = -ENODEV;
+ goto err;
}
if (sc->quirks & (GHL_GUITAR_PS3WIIU | GHL_GUITAR_PS4)) {
+ if (!hid_is_usb(hdev)) {
+ ret = -EINVAL;
+ goto err;
+ }
+
+ usbdev = to_usb_device(sc->hdev->dev.parent->parent);
+
sc->ghl_urb = usb_alloc_urb(0, GFP_ATOMIC);
- if (!sc->ghl_urb)
- return -ENOMEM;
+ if (!sc->ghl_urb) {
+ ret = -ENOMEM;
+ goto err;
+ }
if (sc->quirks & GHL_GUITAR_PS3WIIU)
ret = ghl_init_urb(sc, usbdev, ghl_ps3wiiu_magic_data,
ARRAY_SIZE(ghl_ps4_magic_data));
if (ret) {
hid_err(hdev, "error preparing URB\n");
- return ret;
+ goto err;
}
timer_setup(&sc->ghl_poke_timer, ghl_magic_poke, 0);
}
return ret;
+
+err:
+ hid_hw_stop(hdev);
+ return ret;
}
static void sony_remove(struct hid_device *hdev)
int ret = 0;
struct tm_wheel *tm_wheel = NULL;
+ if (!hid_is_usb(hdev))
+ return -EINVAL;
+
ret = hid_parse(hdev);
if (ret) {
hid_err(hdev, "parse failed with error %d\n", ret);
unsigned int minor;
int ret;
- if (!hid_is_using_ll_driver(hdev, &usb_hid_driver))
+ if (!hid_is_usb(hdev))
return -EINVAL;
dev = devm_kzalloc(&hdev->dev, sizeof(*dev), GFP_KERNEL);
struct uclogic_drvdata *drvdata = NULL;
bool params_initialized = false;
+ if (!hid_is_usb(hdev))
+ return -EINVAL;
+
/*
* libinput requires the pad interface to be on a different node
* than the pen, so use QUIRK_MULTI_INPUT for all tablets.
struct uclogic_params p = {0, };
/* Check arguments */
- if (params == NULL || hdev == NULL ||
- !hid_is_using_ll_driver(hdev, &usb_hid_driver)) {
+ if (params == NULL || hdev == NULL || !hid_is_usb(hdev)) {
rc = -EINVAL;
goto cleanup;
}
if (ish_should_leave_d0i3(pdev) && !dev->suspend_flag
&& IPC_IS_ISH_ILUP(fwsts)) {
- disable_irq_wake(pdev->irq);
+ if (device_may_wakeup(&pdev->dev))
+ disable_irq_wake(pdev->irq);
ish_set_host_ready(dev);
*/
pci_save_state(pdev);
- enable_irq_wake(pdev->irq);
+ if (device_may_wakeup(&pdev->dev))
+ enable_irq_wake(pdev->irq);
}
} else {
/*
* Skip the query for this type and modify defaults based on
* interface number.
*/
- if (features->type == WIRELESS) {
+ if (features->type == WIRELESS && intf) {
if (intf->cur_altsetting->desc.bInterfaceNumber == 0)
features->device_type = WACOM_DEVICETYPE_WL_MONITOR;
else
if ((features->type == HID_GENERIC) && !strcmp("Wacom HID", features->name)) {
char *product_name = wacom->hdev->name;
- if (hid_is_using_ll_driver(wacom->hdev, &usb_hid_driver)) {
+ if (hid_is_usb(wacom->hdev)) {
struct usb_interface *intf = to_usb_interface(wacom->hdev->dev.parent);
struct usb_device *dev = interface_to_usbdev(intf);
product_name = dev->product;
wacom_destroy_battery(wacom);
+ if (!usbdev)
+ return;
+
/* Stylus interface */
hdev1 = usb_get_intfdata(usbdev->config->interface[1]);
wacom1 = hid_get_drvdata(hdev1);
static int wacom_probe(struct hid_device *hdev,
const struct hid_device_id *id)
{
- struct usb_interface *intf = to_usb_interface(hdev->dev.parent);
- struct usb_device *dev = interface_to_usbdev(intf);
struct wacom *wacom;
struct wacom_wac *wacom_wac;
struct wacom_features *features;
wacom_wac->hid_data.inputmode = -1;
wacom_wac->mode_report = -1;
- wacom->usbdev = dev;
- wacom->intf = intf;
+ if (hid_is_usb(hdev)) {
+ struct usb_interface *intf = to_usb_interface(hdev->dev.parent);
+ struct usb_device *dev = interface_to_usbdev(intf);
+
+ wacom->usbdev = dev;
+ wacom->intf = intf;
+ }
+
mutex_init(&wacom->lock);
INIT_DELAYED_WORK(&wacom->init_work, wacom_init_work);
INIT_WORK(&wacom->wireless_work, wacom_wireless_work);
config HYPERV_UTILS
tristate "Microsoft Hyper-V Utilities driver"
depends on HYPERV && CONNECTOR && NLS
+ depends on PTP_1588_CLOCK_OPTIONAL
help
Select this option to enable the Hyper-V Utilities.
corsairpsu_check_cmd_support(priv);
priv->hwmon_dev = hwmon_device_register_with_info(&hdev->dev, "corsairpsu", priv,
- &corsairpsu_chip_info, 0);
+ &corsairpsu_chip_info, NULL);
if (IS_ERR(priv->hwmon_dev)) {
ret = PTR_ERR(priv->hwmon_dev);
{
struct dell_smm_data *data = dev_get_drvdata(dev);
- /* Register the proc entry */
- proc_create_data("i8k", 0, NULL, &i8k_proc_ops, data);
-
- devm_add_action_or_reset(dev, i8k_exit_procfs, NULL);
+ /* Only register exit function if creation was successful */
+ if (proc_create_data("i8k", 0, NULL, &i8k_proc_ops, data))
+ devm_add_action_or_reset(dev, i8k_exit_procfs, NULL);
}
#else
nct6775_wmi_set_bank(data, reg);
- err = nct6775_asuswmi_read(data->bank, reg, &tmp);
+ err = nct6775_asuswmi_read(data->bank, reg & 0xff, &tmp);
if (err)
return 0;
return ret;
}
- ctx->pwm_value = MAX_PWM;
-
pwm_init_state(ctx->pwm, &ctx->pwm_state);
/*
/*
* I2C command delays (in microseconds)
*/
-#define SHT4X_MEAS_DELAY 1000
+#define SHT4X_MEAS_DELAY_HPM 8200 /* see t_MEAS,h in datasheet */
#define SHT4X_DELAY_EXTRA 10000
/*
if (ret < 0)
goto unlock;
- usleep_range(SHT4X_MEAS_DELAY, SHT4X_MEAS_DELAY + SHT4X_DELAY_EXTRA);
+ usleep_range(SHT4X_MEAS_DELAY_HPM, SHT4X_MEAS_DELAY_HPM + SHT4X_DELAY_EXTRA);
ret = i2c_master_recv(client, raw_data, SHT4X_RESPONSE_LENGTH);
if (ret != SHT4X_RESPONSE_LENGTH) {
status = readb(i2c->base + MPC_I2C_SR);
if (status & CSR_MIF) {
/* Wait up to 100us for transfer to properly complete */
- readb_poll_timeout(i2c->base + MPC_I2C_SR, status, !(status & CSR_MCF), 0, 100);
+ readb_poll_timeout_atomic(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;
/**
* struct virtio_i2c - virtio I2C data
* @vdev: virtio device for this controller
- * @completion: completion of virtio I2C message
* @adap: I2C adapter for this controller
* @vq: the virtio virtqueue for communication
*/
struct virtio_i2c {
struct virtio_device *vdev;
- struct completion completion;
struct i2c_adapter adap;
struct virtqueue *vq;
};
/**
* struct virtio_i2c_req - the virtio I2C request structure
+ * @completion: completion of virtio I2C message
* @out_hdr: the OUT header of the virtio I2C message
* @buf: the buffer into which data is read, or from which it's written
* @in_hdr: the IN header of the virtio I2C message
*/
struct virtio_i2c_req {
+ struct completion completion;
struct virtio_i2c_out_hdr out_hdr ____cacheline_aligned;
uint8_t *buf ____cacheline_aligned;
struct virtio_i2c_in_hdr in_hdr ____cacheline_aligned;
static void virtio_i2c_msg_done(struct virtqueue *vq)
{
- struct virtio_i2c *vi = vq->vdev->priv;
+ struct virtio_i2c_req *req;
+ unsigned int len;
- complete(&vi->completion);
+ while ((req = virtqueue_get_buf(vq, &len)))
+ complete(&req->completion);
}
static int virtio_i2c_prepare_reqs(struct virtqueue *vq,
for (i = 0; i < num; i++) {
int outcnt = 0, incnt = 0;
+ init_completion(&reqs[i].completion);
+
/*
* Only 7-bit mode supported for this moment. For the address
* format, Please check the Virtio I2C Specification.
struct virtio_i2c_req *reqs,
struct i2c_msg *msgs, int num)
{
- struct virtio_i2c_req *req;
bool failed = false;
- unsigned int len;
int i, j = 0;
for (i = 0; i < num; i++) {
- /* Detach the ith request from the vq */
- req = virtqueue_get_buf(vq, &len);
+ struct virtio_i2c_req *req = &reqs[i];
- /*
- * Condition req == &reqs[i] should always meet since we have
- * total num requests in the vq. reqs[i] can never be NULL here.
- */
- if (!failed && (WARN_ON(req != &reqs[i]) ||
- req->in_hdr.status != VIRTIO_I2C_MSG_OK))
+ wait_for_completion(&req->completion);
+
+ if (!failed && req->in_hdr.status != VIRTIO_I2C_MSG_OK)
failed = true;
i2c_put_dma_safe_msg_buf(reqs[i].buf, &msgs[i], !failed);
* remote here to clear the virtqueue, so we can try another set of
* messages later on.
*/
-
- reinit_completion(&vi->completion);
virtqueue_kick(vq);
- wait_for_completion(&vi->completion);
-
count = virtio_i2c_complete_reqs(vq, reqs, msgs, count);
err_free:
vdev->priv = vi;
vi->vdev = vdev;
- init_completion(&vi->completion);
-
ret = virtio_i2c_setup_vqs(vi);
if (ret)
return ret;
return 0;
err_buffer_cleanup:
- if (data->dready_trig)
- iio_triggered_buffer_cleanup(indio_dev);
+ iio_triggered_buffer_cleanup(indio_dev);
err_trigger_unregister:
if (data->dready_trig)
iio_trigger_unregister(data->dready_trig);
pm_runtime_disable(&client->dev);
pm_runtime_set_suspended(&client->dev);
+ iio_triggered_buffer_cleanup(indio_dev);
if (data->dready_trig) {
- iio_triggered_buffer_cleanup(indio_dev);
iio_trigger_unregister(data->dready_trig);
iio_trigger_unregister(data->motion_trig);
}
hw_values.chan,
sizeof(hw_values.chan));
if (ret) {
- dev_err(st->dev,
- "error reading data\n");
- return ret;
+ dev_err(st->dev, "error reading data: %d\n", ret);
+ goto out;
}
iio_push_to_buffers_with_timestamp(indio_dev,
&hw_values,
iio_get_time_ns(indio_dev));
+out:
iio_trigger_notify_done(indio_dev->trig);
return IRQ_HANDLED;
if (ret)
return ret;
- indio_dev->trig = trig;
+ indio_dev->trig = iio_trigger_get(trig);
return 0;
}
config IMX8QXP_ADC
tristate "NXP IMX8QXP ADC driver"
- depends on ARCH_MXC_ARM64 || COMPILE_TEST
+ depends on ARCH_MXC || COMPILE_TEST
depends on HAS_IOMEM
help
Say yes here to build support for IMX8QXP ADC.
iio_push_to_buffers_with_timestamp(indio_dev, &st->data.scan,
iio_get_time_ns(indio_dev));
- iio_trigger_notify_done(indio_dev->trig);
err_unlock:
+ iio_trigger_notify_done(indio_dev->trig);
mutex_unlock(&st->lock);
return IRQ_HANDLED;
*val = st->conversion_value;
ret = at91_adc_adjust_val_osr(st, val);
if (chan->scan_type.sign == 's')
- *val = sign_extend32(*val, 11);
+ *val = sign_extend32(*val,
+ chan->scan_type.realbits - 1);
st->conversion_done = false;
}
struct iio_chan_spec const *chan, int *val)
{
struct axp20x_adc_iio *info = iio_priv(indio_dev);
- int size;
- /*
- * N.B.: Unlike the Chinese datasheets tell, the charging current is
- * stored on 12 bits, not 13 bits. Only discharging current is on 13
- * bits.
- */
- if (chan->type == IIO_CURRENT && chan->channel == AXP22X_BATT_DISCHRG_I)
- size = 13;
- else
- size = 12;
-
- *val = axp20x_read_variable_width(info->regmap, chan->address, size);
+ *val = axp20x_read_variable_width(info->regmap, chan->address, 12);
if (*val < 0)
return *val;
return IIO_VAL_INT_PLUS_MICRO;
case IIO_CURRENT:
- *val = 0;
- *val2 = 500000;
- return IIO_VAL_INT_PLUS_MICRO;
+ *val = 1;
+ return IIO_VAL_INT;
case IIO_TEMP:
*val = 100;
static int dln2_adc_read(struct dln2_adc *dln2, unsigned int channel)
{
int ret, i;
- struct iio_dev *indio_dev = platform_get_drvdata(dln2->pdev);
u16 conflict;
__le16 value;
int olen = sizeof(value);
.chan = channel,
};
- ret = iio_device_claim_direct_mode(indio_dev);
- if (ret < 0)
- return ret;
-
ret = dln2_adc_set_chan_enabled(dln2, channel, true);
if (ret < 0)
- goto release_direct;
+ return ret;
ret = dln2_adc_set_port_enabled(dln2, true, &conflict);
if (ret < 0) {
dln2_adc_set_port_enabled(dln2, false, NULL);
disable_chan:
dln2_adc_set_chan_enabled(dln2, channel, false);
-release_direct:
- iio_device_release_direct_mode(indio_dev);
return ret;
}
switch (mask) {
case IIO_CHAN_INFO_RAW:
+ ret = iio_device_claim_direct_mode(indio_dev);
+ if (ret < 0)
+ return ret;
+
mutex_lock(&dln2->mutex);
ret = dln2_adc_read(dln2, chan->channel);
mutex_unlock(&dln2->mutex);
+ iio_device_release_direct_mode(indio_dev);
+
if (ret < 0)
return ret;
return -ENOMEM;
}
iio_trigger_set_drvdata(dln2->trig, dln2);
- devm_iio_trigger_register(dev, dln2->trig);
+ ret = devm_iio_trigger_register(dev, dln2->trig);
+ if (ret) {
+ dev_err(dev, "failed to register trigger: %d\n", ret);
+ return ret;
+ }
iio_trigger_set_immutable(indio_dev, dln2->trig);
ret = devm_iio_triggered_buffer_setup(dev, indio_dev, NULL,
{
struct stm32_adc *adc = iio_priv(indio_dev);
+ stm32_adc_writel(adc, STM32H7_ADC_PCSEL, 0);
stm32h7_adc_disable(indio_dev);
stm32_adc_int_ch_disable(adc);
stm32h7_adc_enter_pwr_down(adc);
/* Get calibration data for vrefint channel */
ret = nvmem_cell_read_u16(&indio_dev->dev, "vrefint", &vrefint);
if (ret && ret != -ENOENT) {
- return dev_err_probe(&indio_dev->dev, ret,
+ return dev_err_probe(indio_dev->dev.parent, ret,
"nvmem access error\n");
}
if (ret == -ENOENT)
*/
#include <linux/bitfield.h>
+#include <linux/bitops.h>
#include <linux/delay.h>
#include <linux/device.h>
#include <linux/kernel.h>
goto err_unlock;
}
- *val = temp;
+ *val = sign_extend32(temp, 15);
err_unlock:
mutex_unlock(&st->lock);
}
/* extract lower 12 bits temperature reading */
- *val = temp & 0x0FFF;
+ *val = sign_extend32(temp, 11);
err_unlock:
mutex_unlock(&st->lock);
iio_push_to_buffers_with_timestamp(indio_dev, &scan, pf->timestamp);
+error_ret:
iio_trigger_notify_done(indio_dev->trig);
-error_ret:
return IRQ_HANDLED;
}
irq_modify_status(trig->subirq_base + i,
IRQ_NOREQUEST | IRQ_NOAUTOEN, IRQ_NOPROBE);
}
- get_device(&trig->dev);
return trig;
ret = regmap_bulk_read(data->regmap, LTR501_ALS_DATA1,
als_buf, sizeof(als_buf));
if (ret < 0)
- return ret;
+ goto done;
if (test_bit(0, indio_dev->active_scan_mask))
scan.channels[j++] = le16_to_cpu(als_buf[1]);
if (test_bit(1, indio_dev->active_scan_mask))
mutex_lock(&data->lock);
ret = regmap_field_read(data->reg_flag_nf, &dir);
if (ret < 0) {
- dev_err(&data->client->dev, "register read failed\n");
- mutex_unlock(&data->lock);
- return ret;
+ dev_err(&data->client->dev, "register read failed: %d\n", ret);
+ goto out;
}
event = IIO_UNMOD_EVENT_CODE(IIO_PROXIMITY, 1,
IIO_EV_TYPE_THRESH,
ret = regmap_field_write(data->reg_flag_psint, 0);
if (ret < 0)
dev_err(&data->client->dev, "failed to reset interrupts\n");
+out:
mutex_unlock(&data->lock);
return IRQ_HANDLED;
};
module_platform_driver(stm32_timer_trigger_driver);
-MODULE_ALIAS("platform: stm32-timer-trigger");
+MODULE_ALIAS("platform:stm32-timer-trigger");
MODULE_DESCRIPTION("STMicroelectronics STM32 Timer Trigger driver");
MODULE_LICENSE("GPL v2");
*/
static void __hfi1_rcd_eoi_intr(struct hfi1_ctxtdata *rcd)
{
+ if (!rcd->rcvhdrq)
+ return;
clear_recv_intr(rcd);
if (check_packet_present(rcd))
force_recv_intr(rcd);
struct hfi1_packet packet;
int skip_pkt = 0;
+ if (!rcd->rcvhdrq)
+ return RCV_PKT_OK;
/* Control context will always use the slow path interrupt handler */
needset = (rcd->ctxt == HFI1_CTRL_CTXT) ? 0 : 1;
rcd->fast_handler = get_dma_rtail_setting(rcd) ?
handle_receive_interrupt_dma_rtail :
handle_receive_interrupt_nodma_rtail;
- rcd->slow_handler = handle_receive_interrupt;
hfi1_set_seq_cnt(rcd, 1);
rcd->numa_id = numa;
rcd->rcv_array_groups = dd->rcv_entries.ngroups;
rcd->rhf_rcv_function_map = normal_rhf_rcv_functions;
+ rcd->slow_handler = handle_receive_interrupt;
+ rcd->do_interrupt = rcd->slow_handler;
rcd->msix_intr = CCE_NUM_MSIX_VECTORS;
mutex_init(&rcd->exp_mutex);
if (ret)
goto done;
- /* allocate dummy tail memory for all receive contexts */
- dd->rcvhdrtail_dummy_kvaddr = dma_alloc_coherent(&dd->pcidev->dev,
- sizeof(u64),
- &dd->rcvhdrtail_dummy_dma,
- GFP_KERNEL);
-
- if (!dd->rcvhdrtail_dummy_kvaddr) {
- dd_dev_err(dd, "cannot allocate dummy tail memory\n");
- ret = -ENOMEM;
- goto done;
- }
-
/* dd->rcd can be NULL if early initialization failed */
for (i = 0; dd->rcd && i < dd->first_dyn_alloc_ctxt; ++i) {
/*
if (!rcd)
continue;
- rcd->do_interrupt = &handle_receive_interrupt;
-
lastfail = hfi1_create_rcvhdrq(dd, rcd);
if (!lastfail)
lastfail = hfi1_setup_eagerbufs(rcd);
rcd->egrbufs.rcvtids = NULL;
for (e = 0; e < rcd->egrbufs.alloced; e++) {
- if (rcd->egrbufs.buffers[e].dma)
+ if (rcd->egrbufs.buffers[e].addr)
dma_free_coherent(&dd->pcidev->dev,
rcd->egrbufs.buffers[e].len,
rcd->egrbufs.buffers[e].addr,
dd->tx_opstats = NULL;
kfree(dd->comp_vect);
dd->comp_vect = NULL;
+ if (dd->rcvhdrtail_dummy_kvaddr)
+ dma_free_coherent(&dd->pcidev->dev, sizeof(u64),
+ (void *)dd->rcvhdrtail_dummy_kvaddr,
+ dd->rcvhdrtail_dummy_dma);
+ dd->rcvhdrtail_dummy_kvaddr = NULL;
sdma_clean(dd, dd->num_sdma);
rvt_dealloc_device(&dd->verbs_dev.rdi);
}
goto bail;
}
+ /* allocate dummy tail memory for all receive contexts */
+ dd->rcvhdrtail_dummy_kvaddr =
+ dma_alloc_coherent(&dd->pcidev->dev, sizeof(u64),
+ &dd->rcvhdrtail_dummy_dma, GFP_KERNEL);
+ if (!dd->rcvhdrtail_dummy_kvaddr) {
+ ret = -ENOMEM;
+ goto bail;
+ }
+
atomic_set(&dd->ipoib_rsm_usr_num, 0);
return dd;
free_credit_return(dd);
- if (dd->rcvhdrtail_dummy_kvaddr) {
- dma_free_coherent(&dd->pcidev->dev, sizeof(u64),
- (void *)dd->rcvhdrtail_dummy_kvaddr,
- dd->rcvhdrtail_dummy_dma);
- dd->rcvhdrtail_dummy_kvaddr = NULL;
- }
-
/*
* Free any resources still in use (usually just kernel contexts)
* at unload; we do for ctxtcnt, because that's what we allocate.
if (current->nr_cpus_allowed != 1)
goto out;
- cpu_id = smp_processor_id();
rcu_read_lock();
+ cpu_id = smp_processor_id();
rht_node = rhashtable_lookup(dd->sdma_rht, &cpu_id,
sdma_rht_params);
#include <linux/acpi.h>
#include <linux/etherdevice.h>
#include <linux/interrupt.h>
+#include <linux/iopoll.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <net/addrconf.h>
unsigned long instance_stage,
unsigned long reset_stage)
{
+#define HW_RESET_TIMEOUT_US 1000000
+#define HW_RESET_SLEEP_US 1000
+
struct hns_roce_v2_priv *priv = hr_dev->priv;
struct hnae3_handle *handle = priv->handle;
const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+ unsigned long val;
+ int ret;
/* When hardware reset is detected, we should stop sending mailbox&cmq&
* doorbell to hardware. If now in .init_instance() function, we should
* again.
*/
hr_dev->dis_db = true;
- if (!ops->get_hw_reset_stat(handle))
+
+ ret = read_poll_timeout(ops->ae_dev_reset_cnt, val,
+ val > hr_dev->reset_cnt, HW_RESET_SLEEP_US,
+ HW_RESET_TIMEOUT_US, false, handle);
+ if (!ret)
hr_dev->is_reset = true;
if (!hr_dev->is_reset || reset_stage == HNS_ROCE_STATE_RST_INIT ||
if (!hr_dev)
return 0;
- hr_dev->is_reset = true;
hr_dev->active = false;
hr_dev->dis_db = true;
-
hr_dev->state = HNS_ROCE_DEVICE_STATE_RST_DOWN;
return 0;
{
struct irdma_cq *cq = iwcq->back_cq;
+ if (!cq->user_mode)
+ cq->armed = false;
if (cq->ibcq.comp_handler)
cq->ibcq.comp_handler(&cq->ibcq, cq->ibcq.cq_context);
}
qp->flush_code = FLUSH_PROT_ERR;
break;
case IRDMA_AE_AMP_BAD_QP:
+ case IRDMA_AE_WQE_UNEXPECTED_OPCODE:
qp->flush_code = FLUSH_LOC_QP_OP_ERR;
break;
case IRDMA_AE_AMP_BAD_STAG_KEY:
case IRDMA_AE_PRIV_OPERATION_DENIED:
case IRDMA_AE_IB_INVALID_REQUEST:
case IRDMA_AE_IB_REMOTE_ACCESS_ERROR:
- case IRDMA_AE_IB_REMOTE_OP_ERROR:
qp->flush_code = FLUSH_REM_ACCESS_ERR;
qp->event_type = IRDMA_QP_EVENT_ACCESS_ERR;
break;
case IRDMA_AE_AMP_MWBIND_INVALID_BOUNDS:
qp->flush_code = FLUSH_MW_BIND_ERR;
break;
+ case IRDMA_AE_IB_REMOTE_OP_ERROR:
+ qp->flush_code = FLUSH_REM_OP_ERR;
+ break;
default:
qp->flush_code = FLUSH_FATAL_ERR;
break;
void (*callback_fcn)(struct irdma_cqp_request *cqp_request),
void *cb_param);
void irdma_gsi_ud_qp_ah_cb(struct irdma_cqp_request *cqp_request);
+bool irdma_cq_empty(struct irdma_cq *iwcq);
int irdma_inetaddr_event(struct notifier_block *notifier, unsigned long event,
void *ptr);
int irdma_inet6addr_event(struct notifier_block *notifier, unsigned long event,
list_del(&chunk->list);
if (chunk->type == PBLE_SD_PAGED)
irdma_pble_free_paged_mem(chunk);
- if (chunk->bitmapbuf)
- kfree(chunk->bitmapmem.va);
+ bitmap_free(chunk->bitmapbuf);
kfree(chunk->chunkmem.va);
}
}
"PBLE: next_fpm_addr = %llx chunk_size[%llu] = 0x%llx\n",
pble_rsrc->next_fpm_addr, chunk->size, chunk->size);
pble_rsrc->unallocated_pble -= (u32)(chunk->size >> 3);
- list_add(&chunk->list, &pble_rsrc->pinfo.clist);
sd_reg_val = (sd_entry_type == IRDMA_SD_TYPE_PAGED) ?
sd_entry->u.pd_table.pd_page_addr.pa :
sd_entry->u.bp.addr.pa;
goto error;
}
+ list_add(&chunk->list, &pble_rsrc->pinfo.clist);
sd_entry->valid = true;
return 0;
error:
- if (chunk->bitmapbuf)
- kfree(chunk->bitmapmem.va);
+ bitmap_free(chunk->bitmapbuf);
kfree(chunk->chunkmem.va);
return ret_code;
u32 pg_cnt;
enum irdma_alloc_type type;
struct irdma_sc_dev *dev;
- struct irdma_virt_mem bitmapmem;
struct irdma_virt_mem chunkmem;
};
sizeofbitmap = (u64)pchunk->size >> pprm->pble_shift;
- pchunk->bitmapmem.size = sizeofbitmap >> 3;
- pchunk->bitmapmem.va = kzalloc(pchunk->bitmapmem.size, GFP_KERNEL);
-
- if (!pchunk->bitmapmem.va)
+ pchunk->bitmapbuf = bitmap_zalloc(sizeofbitmap, GFP_KERNEL);
+ if (!pchunk->bitmapbuf)
return IRDMA_ERR_NO_MEMORY;
- pchunk->bitmapbuf = pchunk->bitmapmem.va;
- bitmap_zero(pchunk->bitmapbuf, sizeofbitmap);
-
pchunk->sizeofbitmap = sizeofbitmap;
/* each pble is 8 bytes hence shift by 3 */
pprm->total_pble_alloc += pchunk->size >> 3;
ibevent.element.qp = &iwqp->ibqp;
iwqp->ibqp.event_handler(&ibevent, iwqp->ibqp.qp_context);
}
+
+bool irdma_cq_empty(struct irdma_cq *iwcq)
+{
+ struct irdma_cq_uk *ukcq;
+ u64 qword3;
+ __le64 *cqe;
+ u8 polarity;
+
+ ukcq = &iwcq->sc_cq.cq_uk;
+ cqe = IRDMA_GET_CURRENT_CQ_ELEM(ukcq);
+ get_64bit_val(cqe, 24, &qword3);
+ polarity = (u8)FIELD_GET(IRDMA_CQ_VALID, qword3);
+
+ return polarity != ukcq->polarity;
+}
struct irdma_cq *iwcq;
struct irdma_cq_uk *ukcq;
unsigned long flags;
- enum irdma_cmpl_notify cq_notify = IRDMA_CQ_COMPL_EVENT;
+ enum irdma_cmpl_notify cq_notify;
+ bool promo_event = false;
+ int ret = 0;
+ cq_notify = notify_flags == IB_CQ_SOLICITED ?
+ IRDMA_CQ_COMPL_SOLICITED : IRDMA_CQ_COMPL_EVENT;
iwcq = to_iwcq(ibcq);
ukcq = &iwcq->sc_cq.cq_uk;
- if (notify_flags == IB_CQ_SOLICITED)
- cq_notify = IRDMA_CQ_COMPL_SOLICITED;
spin_lock_irqsave(&iwcq->lock, flags);
- irdma_uk_cq_request_notification(ukcq, cq_notify);
+ /* Only promote to arm the CQ for any event if the last arm event was solicited. */
+ if (iwcq->last_notify == IRDMA_CQ_COMPL_SOLICITED && notify_flags != IB_CQ_SOLICITED)
+ promo_event = true;
+
+ if (!iwcq->armed || promo_event) {
+ iwcq->armed = true;
+ iwcq->last_notify = cq_notify;
+ irdma_uk_cq_request_notification(ukcq, cq_notify);
+ }
+
+ if ((notify_flags & IB_CQ_REPORT_MISSED_EVENTS) && !irdma_cq_empty(iwcq))
+ ret = 1;
spin_unlock_irqrestore(&iwcq->lock, flags);
- return 0;
+ return ret;
}
static int irdma_roce_port_immutable(struct ib_device *ibdev, u32 port_num,
u16 cq_size;
u16 cq_num;
bool user_mode;
+ bool armed;
+ enum irdma_cmpl_notify last_notify;
u32 polled_cmpls;
u32 cq_mem_size;
struct irdma_dma_mem kmem;
/* User MR data */
struct mlx5_cache_ent *cache_ent;
- struct ib_umem *umem;
/* This is zero'd when the MR is allocated */
union {
struct list_head list;
};
- /* Used only by kernel MRs (umem == NULL) */
+ /* Used only by kernel MRs */
struct {
void *descs;
void *descs_alloc;
int data_length;
};
- /* Used only by User MRs (umem != NULL) */
+ /* Used only by User MRs */
struct {
+ struct ib_umem *umem;
unsigned int page_shift;
/* Current access_flags */
int access_flags;
return ret;
}
-static void
-mlx5_free_priv_descs(struct mlx5_ib_mr *mr)
+static void mlx5_free_priv_descs(struct mlx5_ib_mr *mr)
{
- if (!mr->umem && mr->descs) {
- struct ib_device *device = mr->ibmr.device;
- int size = mr->max_descs * mr->desc_size;
- struct mlx5_ib_dev *dev = to_mdev(device);
+ struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device);
+ int size = mr->max_descs * mr->desc_size;
- dma_unmap_single(&dev->mdev->pdev->dev, mr->desc_map, size,
- DMA_TO_DEVICE);
- kfree(mr->descs_alloc);
- mr->descs = NULL;
- }
+ if (!mr->descs)
+ return;
+
+ dma_unmap_single(&dev->mdev->pdev->dev, mr->desc_map, size,
+ DMA_TO_DEVICE);
+ kfree(mr->descs_alloc);
+ mr->descs = NULL;
}
int mlx5_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
if (mr->cache_ent) {
mlx5_mr_cache_free(dev, mr);
} else {
- mlx5_free_priv_descs(mr);
+ if (!udata)
+ mlx5_free_priv_descs(mr);
kfree(mr);
}
return 0;
if (err)
goto err_free_in;
- mr->umem = NULL;
kfree(in);
return mr;
}
mr->ibmr.device = pd->device;
- mr->umem = NULL;
switch (mr_type) {
case IB_MR_TYPE_MEM_REG:
err2:
rxe_queue_cleanup(qp->sq.queue);
+ qp->sq.queue = NULL;
err1:
qp->pd = NULL;
qp->rcq = NULL;
int cpu;
cpu = raw_smp_processor_id();
- s = this_cpu_ptr(stats->pcpu_stats);
+ s = get_cpu_ptr(stats->pcpu_stats);
if (con->cpu != cpu) {
s->cpu_migr.to++;
s = per_cpu_ptr(stats->pcpu_stats, con->cpu);
atomic_inc(&s->cpu_migr.from);
}
+ put_cpu_ptr(stats->pcpu_stats);
}
void rtrs_clt_inc_failover_cnt(struct rtrs_clt_stats *stats)
{
struct rtrs_clt_stats_pcpu *s;
- s = this_cpu_ptr(stats->pcpu_stats);
+ s = get_cpu_ptr(stats->pcpu_stats);
s->rdma.failover_cnt++;
+ put_cpu_ptr(stats->pcpu_stats);
}
int rtrs_clt_stats_migration_from_cnt_to_str(struct rtrs_clt_stats *stats, char *buf)
{
struct rtrs_clt_stats_pcpu *s;
- s = this_cpu_ptr(stats->pcpu_stats);
+ s = get_cpu_ptr(stats->pcpu_stats);
s->rdma.dir[d].cnt++;
s->rdma.dir[d].size_total += size;
+ put_cpu_ptr(stats->pcpu_stats);
}
void rtrs_clt_update_all_stats(struct rtrs_clt_io_req *req, int dir)
.free = aic_ipi_free,
};
-static int aic_init_smp(struct aic_irq_chip *irqc, struct device_node *node)
+static int __init aic_init_smp(struct aic_irq_chip *irqc, struct device_node *node)
{
struct irq_domain *ipi_domain;
int base_ipi;
int hwirq, i;
mutex_lock(&msi_used_lock);
+ hwirq = bitmap_find_free_region(msi_used, PCI_MSI_DOORBELL_NR,
+ order_base_2(nr_irqs));
+ mutex_unlock(&msi_used_lock);
- hwirq = bitmap_find_next_zero_area(msi_used, PCI_MSI_DOORBELL_NR,
- 0, nr_irqs, 0);
- if (hwirq >= PCI_MSI_DOORBELL_NR) {
- mutex_unlock(&msi_used_lock);
+ if (hwirq < 0)
return -ENOSPC;
- }
-
- bitmap_set(msi_used, hwirq, nr_irqs);
- mutex_unlock(&msi_used_lock);
for (i = 0; i < nr_irqs; i++) {
irq_domain_set_info(domain, virq + i, hwirq + i,
NULL, NULL);
}
- return hwirq;
+ return 0;
}
static void armada_370_xp_msi_free(struct irq_domain *domain,
struct irq_data *d = irq_domain_get_irq_data(domain, virq);
mutex_lock(&msi_used_lock);
- bitmap_clear(msi_used, d->hwirq, nr_irqs);
+ bitmap_release_region(msi_used, d->hwirq, order_base_2(nr_irqs));
mutex_unlock(&msi_used_lock);
}
generic_handle_domain_irq(scu_ic->irq_domain,
bit - scu_ic->irq_shift);
- regmap_update_bits(scu_ic->scu, scu_ic->reg, mask,
- BIT(bit + ASPEED_SCU_IC_STATUS_SHIFT));
+ regmap_write_bits(scu_ic->scu, scu_ic->reg, mask,
+ BIT(bit + ASPEED_SCU_IC_STATUS_SHIFT));
}
chained_irq_exit(chip, desc);
}
data->num_parent_irqs = platform_irq_count(pdev);
+ put_device(&pdev->dev);
if (data->num_parent_irqs <= 0) {
pr_err("invalid number of parent interrupts\n");
ret = -ENOMEM;
its_fixup_cmd(cmd);
- return NULL;
+ return desc->its_invall_cmd.col;
}
static struct its_vpe *its_build_vinvall_cmd(struct its_node *its,
#define pr_fmt(fmt) "irq-mips-gic: " fmt
+#include <linux/bitfield.h>
#include <linux/bitmap.h>
#include <linux/clocksource.h>
#include <linux/cpuhotplug.h>
mips_gic_base = ioremap(gic_base, gic_len);
gicconfig = read_gic_config();
- gic_shared_intrs = gicconfig & GIC_CONFIG_NUMINTERRUPTS;
- gic_shared_intrs >>= __ffs(GIC_CONFIG_NUMINTERRUPTS);
+ gic_shared_intrs = FIELD_GET(GIC_CONFIG_NUMINTERRUPTS, gicconfig);
gic_shared_intrs = (gic_shared_intrs + 1) * 8;
if (cpu_has_veic) {
#define NVIC_ISER 0x000
#define NVIC_ICER 0x080
-#define NVIC_IPR 0x300
+#define NVIC_IPR 0x400
#define NVIC_MAX_BANKS 16
/*
static void cached_dev_detach_finish(struct work_struct *w)
{
struct cached_dev *dc = container_of(w, struct cached_dev, detach);
+ struct cache_set *c = dc->disk.c;
BUG_ON(!test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags));
BUG_ON(refcount_read(&dc->count));
bcache_device_detach(&dc->disk);
list_move(&dc->list, &uncached_devices);
- calc_cached_dev_sectors(dc->disk.c);
+ calc_cached_dev_sectors(c);
clear_bit(BCACHE_DEV_DETACHING, &dc->disk.flags);
clear_bit(BCACHE_DEV_UNLINK_DONE, &dc->disk.flags);
n_sectors -= bv.bv_len >> SECTOR_SHIFT;
bio_advance_iter(bio, &bio->bi_iter, bv.bv_len);
retry_kmap:
- mem = bvec_kmap_local(&bv);
+ mem = kmap_local_page(bv.bv_page);
if (likely(dio->op == REQ_OP_WRITE))
flush_dcache_page(bv.bv_page);
if (!num_sectors || num_sectors > max_sectors)
num_sectors = max_sectors;
+ rdev->sb_start = sb_start;
}
sb = page_address(rdev->sb_page);
sb->data_size = cpu_to_le64(num_sectors);
spin_lock(&mddev->lock);
mddev->pers = NULL;
spin_unlock(&mddev->lock);
- pers->free(mddev, mddev->private);
+ if (mddev->private)
+ pers->free(mddev, mddev->private);
mddev->private = NULL;
if (pers->sync_request && mddev->to_remove == NULL)
mddev->to_remove = &md_redundancy_group;
memcpy(n, dm_block_data(child),
dm_bm_block_size(dm_tm_get_bm(info->tm)));
- dm_tm_unlock(info->tm, child);
dm_tm_dec(info->tm, dm_block_location(child));
+ dm_tm_unlock(info->tm, child);
return 0;
}
mutex_lock(&pcr->pcr_mutex);
rtsx_pci_power_off(pcr, HOST_ENTER_S3);
- free_irq(pcr->irq, (void *)pcr);
-
mutex_unlock(&pcr->pcr_mutex);
pcr->is_runtime_suspended = true;
mutex_lock(&pcr->pcr_mutex);
rtsx_pci_write_register(pcr, HOST_SLEEP_STATE, 0x03, 0x00);
- rtsx_pci_acquire_irq(pcr);
- synchronize_irq(pcr->irq);
if (pcr->ops->fetch_vendor_settings)
pcr->ops->fetch_vendor_settings(pcr);
static int at25_probe(struct spi_device *spi)
{
struct at25_data *at25 = NULL;
- struct spi_eeprom chip;
int err;
int sr;
u8 id[FM25_ID_LEN];
if (match && !strcmp(match->compatible, "cypress,fm25"))
is_fram = 1;
+ at25 = devm_kzalloc(&spi->dev, sizeof(struct at25_data), GFP_KERNEL);
+ if (!at25)
+ return -ENOMEM;
+
/* Chip description */
- if (!spi->dev.platform_data) {
- if (!is_fram) {
- err = at25_fw_to_chip(&spi->dev, &chip);
- if (err)
- return err;
- }
- } else
- chip = *(struct spi_eeprom *)spi->dev.platform_data;
+ if (spi->dev.platform_data) {
+ memcpy(&at25->chip, spi->dev.platform_data, sizeof(at25->chip));
+ } else if (!is_fram) {
+ err = at25_fw_to_chip(&spi->dev, &at25->chip);
+ if (err)
+ return err;
+ }
/* Ping the chip ... the status register is pretty portable,
* unlike probing manufacturer IDs. We do expect that system
return -ENXIO;
}
- at25 = devm_kzalloc(&spi->dev, sizeof(struct at25_data), GFP_KERNEL);
- if (!at25)
- return -ENOMEM;
-
mutex_init(&at25->lock);
- at25->chip = chip;
at25->spi = spi;
spi_set_drvdata(spi, at25);
dev_err(&spi->dev, "Error: unsupported size (id %02x)\n", id[7]);
return -ENODEV;
}
- chip.byte_len = int_pow(2, id[7] - 0x21 + 4) * 1024;
+ at25->chip.byte_len = int_pow(2, id[7] - 0x21 + 4) * 1024;
if (at25->chip.byte_len > 64 * 1024)
at25->chip.flags |= EE_ADDR3;
at25->nvmem_config.type = is_fram ? NVMEM_TYPE_FRAM : NVMEM_TYPE_EEPROM;
at25->nvmem_config.name = dev_name(&spi->dev);
at25->nvmem_config.dev = &spi->dev;
- at25->nvmem_config.read_only = chip.flags & EE_READONLY;
+ at25->nvmem_config.read_only = at25->chip.flags & EE_READONLY;
at25->nvmem_config.root_only = true;
at25->nvmem_config.owner = THIS_MODULE;
at25->nvmem_config.compat = true;
at25->nvmem_config.priv = at25;
at25->nvmem_config.stride = 1;
at25->nvmem_config.word_size = 1;
- at25->nvmem_config.size = chip.byte_len;
+ at25->nvmem_config.size = at25->chip.byte_len;
at25->nvmem = devm_nvmem_register(&spi->dev, &at25->nvmem_config);
if (IS_ERR(at25->nvmem))
return PTR_ERR(at25->nvmem);
dev_info(&spi->dev, "%d %s %s %s%s, pagesize %u\n",
- (chip.byte_len < 1024) ? chip.byte_len : (chip.byte_len / 1024),
- (chip.byte_len < 1024) ? "Byte" : "KByte",
+ (at25->chip.byte_len < 1024) ?
+ at25->chip.byte_len : (at25->chip.byte_len / 1024),
+ (at25->chip.byte_len < 1024) ? "Byte" : "KByte",
at25->chip.name, is_fram ? "fram" : "eeprom",
- (chip.flags & EE_READONLY) ? " (readonly)" : "",
+ (at25->chip.flags & EE_READONLY) ? " (readonly)" : "",
at25->chip.page_size);
return 0;
}
static u64 fastrpc_get_payload_size(struct fastrpc_invoke_ctx *ctx, int metalen)
{
u64 size = 0;
- int i;
+ int oix;
size = ALIGN(metalen, FASTRPC_ALIGN);
- for (i = 0; i < ctx->nscalars; i++) {
+ for (oix = 0; oix < ctx->nbufs; oix++) {
+ int i = ctx->olaps[oix].raix;
+
if (ctx->args[i].fd == 0 || ctx->args[i].fd == -1) {
- if (ctx->olaps[i].offset == 0)
+ if (ctx->olaps[oix].offset == 0)
size = ALIGN(size, FASTRPC_ALIGN);
- size += (ctx->olaps[i].mend - ctx->olaps[i].mstart);
+ size += (ctx->olaps[oix].mend - ctx->olaps[oix].mstart);
}
}
sdr_set_field(host->base + PAD_DS_TUNE,
PAD_DS_TUNE_DLY1, i);
ret = mmc_get_ext_csd(card, &ext_csd);
- if (!ret)
+ if (!ret) {
result_dly1 |= (1 << i);
+ kfree(ext_csd);
+ }
}
host->hs400_tuning = false;
/* Issue CMD19 twice for each tap */
for (i = 0; i < 2 * priv->tap_num; i++) {
- int cmd_error;
+ int cmd_error = 0;
/* Set sampling clock position */
sd_scc_write32(host, priv, SH_MOBILE_SDHI_SCC_TAPSET, i % priv->tap_num);
struct mtd_info mtd;
};
+static const struct spi_device_id dataflash_dev_ids[] = {
+ { "at45" },
+ { "dataflash" },
+ { },
+};
+MODULE_DEVICE_TABLE(spi, dataflash_dev_ids);
+
#ifdef CONFIG_OF
static const struct of_device_id dataflash_dt_ids[] = {
{ .compatible = "atmel,at45", },
.name = "mtd_dataflash",
.of_match_table = of_match_ptr(dataflash_dt_ids),
},
+ .id_table = dataflash_dev_ids,
.probe = dataflash_probe,
.remove = dataflash_remove,
config MTD_NAND_DENALI_DT
tristate "Denali NAND controller as a DT device"
select MTD_NAND_DENALI
- depends on HAS_DMA && HAVE_CLK && OF
+ depends on HAS_DMA && HAVE_CLK && OF && HAS_IOMEM
help
Enable the driver for NAND flash on platforms using a Denali NAND
controller as a DT device.
#include <linux/clk.h>
#include <linux/completion.h>
+#include <linux/delay.h>
#include <linux/dmaengine.h>
#include <linux/dma-direction.h>
#include <linux/dma-mapping.h>
#define FSMC_BUSY_WAIT_TIMEOUT (1 * HZ)
+/*
+ * According to SPEAr300 Reference Manual (RM0082)
+ * TOUDEL = 7ns (Output delay from the flip-flops to the board)
+ * TINDEL = 5ns (Input delay from the board to the flipflop)
+ */
+#define TOUTDEL 7000
+#define TINDEL 5000
+
struct fsmc_nand_timings {
u8 tclr;
u8 tar;
{
unsigned long hclk = clk_get_rate(host->clk);
unsigned long hclkn = NSEC_PER_SEC / hclk;
- u32 thiz, thold, twait, tset;
+ u32 thiz, thold, twait, tset, twait_min;
if (sdrt->tRC_min < 30000)
return -EOPNOTSUPP;
else if (tims->thold > FSMC_THOLD_MASK)
tims->thold = FSMC_THOLD_MASK;
- twait = max(sdrt->tRP_min, sdrt->tWP_min);
- tims->twait = DIV_ROUND_UP(twait / 1000, hclkn) - 1;
- if (tims->twait == 0)
- tims->twait = 1;
- else if (tims->twait > FSMC_TWAIT_MASK)
- tims->twait = FSMC_TWAIT_MASK;
-
tset = max(sdrt->tCS_min - sdrt->tWP_min,
sdrt->tCEA_max - sdrt->tREA_max);
tims->tset = DIV_ROUND_UP(tset / 1000, hclkn) - 1;
else if (tims->tset > FSMC_TSET_MASK)
tims->tset = FSMC_TSET_MASK;
+ /*
+ * According to SPEAr300 Reference Manual (RM0082) which gives more
+ * information related to FSMSC timings than the SPEAr600 one (RM0305),
+ * twait >= tCEA - (tset * TCLK) + TOUTDEL + TINDEL
+ */
+ twait_min = sdrt->tCEA_max - ((tims->tset + 1) * hclkn * 1000)
+ + TOUTDEL + TINDEL;
+ twait = max3(sdrt->tRP_min, sdrt->tWP_min, twait_min);
+
+ tims->twait = DIV_ROUND_UP(twait / 1000, hclkn) - 1;
+ if (tims->twait == 0)
+ tims->twait = 1;
+ else if (tims->twait > FSMC_TWAIT_MASK)
+ tims->twait = FSMC_TWAIT_MASK;
+
return 0;
}
instr->ctx.waitrdy.timeout_ms);
break;
}
+
+ if (instr->delay_ns)
+ ndelay(instr->delay_ns);
}
return ret;
struct nand_sdr_timings *spec_timings)
{
const struct nand_controller_ops *ops = chip->controller->ops;
- int best_mode = 0, mode, ret;
+ int best_mode = 0, mode, ret = -EOPNOTSUPP;
iface->type = NAND_SDR_IFACE;
struct nand_nvddr_timings *spec_timings)
{
const struct nand_controller_ops *ops = chip->controller->ops;
- int best_mode = 0, mode, ret;
+ int best_mode = 0, mode, ret = -EOPNOTSUPP;
iface->type = NAND_NVDDR_IFACE;
NAND_OP_CMD(NAND_CMD_ERASE1, 0),
NAND_OP_ADDR(2, addrs, 0),
NAND_OP_CMD(NAND_CMD_ERASE2,
- NAND_COMMON_TIMING_MS(conf, tWB_max)),
+ NAND_COMMON_TIMING_NS(conf, tWB_max)),
NAND_OP_WAIT_RDY(NAND_COMMON_TIMING_MS(conf, tBERS_max),
0),
};
struct slave *slave;
if (!bond_has_slaves(bond)) {
- bond_info->tx_rebalance_counter = 0;
+ atomic_set(&bond_info->tx_rebalance_counter, 0);
bond_info->lp_counter = 0;
goto re_arm;
}
rcu_read_lock();
- bond_info->tx_rebalance_counter++;
+ atomic_inc(&bond_info->tx_rebalance_counter);
bond_info->lp_counter++;
/* send learning packets */
}
/* rebalance tx traffic */
- if (bond_info->tx_rebalance_counter >= BOND_TLB_REBALANCE_TICKS) {
+ if (atomic_read(&bond_info->tx_rebalance_counter) >= BOND_TLB_REBALANCE_TICKS) {
bond_for_each_slave_rcu(bond, slave, iter) {
tlb_clear_slave(bond, slave, 1);
if (slave == rcu_access_pointer(bond->curr_active_slave)) {
bond_info->unbalanced_load = 0;
}
}
- bond_info->tx_rebalance_counter = 0;
+ atomic_set(&bond_info->tx_rebalance_counter, 0);
}
if (bond_info->rlb_enabled) {
tlb_init_slave(slave);
/* order a rebalance ASAP */
- bond->alb_info.tx_rebalance_counter = BOND_TLB_REBALANCE_TICKS;
+ atomic_set(&bond->alb_info.tx_rebalance_counter,
+ BOND_TLB_REBALANCE_TICKS);
if (bond->alb_info.rlb_enabled)
bond->alb_info.rlb_rebalance = 1;
rlb_clear_slave(bond, slave);
} else if (link == BOND_LINK_UP) {
/* order a rebalance ASAP */
- bond_info->tx_rebalance_counter = BOND_TLB_REBALANCE_TICKS;
+ atomic_set(&bond_info->tx_rebalance_counter,
+ BOND_TLB_REBALANCE_TICKS);
if (bond->alb_info.rlb_enabled) {
bond->alb_info.rlb_rebalance = 1;
/* If the updelay module parameter is smaller than the
#define KVASER_PCIEFD_SPACK_EWLR BIT(23)
#define KVASER_PCIEFD_SPACK_EPLR BIT(24)
+/* Kvaser KCAN_EPACK second word */
+#define KVASER_PCIEFD_EPACK_DIR_TX BIT(0)
+
struct kvaser_pciefd;
struct kvaser_pciefd_can {
can->err_rep_cnt++;
can->can.can_stats.bus_error++;
- stats->rx_errors++;
+ if (p->header[1] & KVASER_PCIEFD_EPACK_DIR_TX)
+ stats->tx_errors++;
+ else
+ stats->rx_errors++;
can->bec.txerr = bec.txerr;
can->bec.rxerr = bec.rxerr;
/* Interrupts for version 3.0.x */
#define IR_ERR_LEC_30X (IR_STE | IR_FOE | IR_ACKE | IR_BE | IR_CRCE)
-#define IR_ERR_BUS_30X (IR_ERR_LEC_30X | IR_WDI | IR_ELO | IR_BEU | \
- IR_BEC | IR_TOO | IR_MRAF | IR_TSW | IR_TEFL | \
- IR_RF1L | IR_RF0L)
+#define IR_ERR_BUS_30X (IR_ERR_LEC_30X | IR_WDI | IR_BEU | IR_BEC | \
+ IR_TOO | IR_MRAF | IR_TSW | IR_TEFL | IR_RF1L | \
+ IR_RF0L)
#define IR_ERR_ALL_30X (IR_ERR_STATE | IR_ERR_BUS_30X)
/* Interrupts for version >= 3.1.x */
#define IR_ERR_LEC_31X (IR_PED | IR_PEA)
-#define IR_ERR_BUS_31X (IR_ERR_LEC_31X | IR_WDI | IR_ELO | IR_BEU | \
- IR_BEC | IR_TOO | IR_MRAF | IR_TSW | IR_TEFL | \
- IR_RF1L | IR_RF0L)
+#define IR_ERR_BUS_31X (IR_ERR_LEC_31X | IR_WDI | IR_BEU | IR_BEC | \
+ IR_TOO | IR_MRAF | IR_TSW | IR_TEFL | IR_RF1L | \
+ IR_RF0L)
#define IR_ERR_ALL_31X (IR_ERR_STATE | IR_ERR_BUS_31X)
/* Interrupt Line Select (ILS) */
err = m_can_fifo_read(cdev, fgi, M_CAN_FIFO_DATA,
cf->data, DIV_ROUND_UP(cf->len, 4));
if (err)
- goto out_fail;
+ goto out_free_skb;
}
/* acknowledge rx fifo 0 */
return 0;
+out_free_skb:
+ kfree_skb(skb);
out_fail:
netdev_err(dev, "FIFO read returned %d\n", err);
return err;
{
if (irqstatus & IR_WDI)
netdev_err(dev, "Message RAM Watchdog event due to missing READY\n");
- if (irqstatus & IR_ELO)
- netdev_err(dev, "Error Logging Overflow\n");
if (irqstatus & IR_BEU)
netdev_err(dev, "Bit Error Uncorrected\n");
if (irqstatus & IR_BEC)
case 30:
/* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.0.x */
can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD_NON_ISO);
- cdev->can.bittiming_const = &m_can_bittiming_const_30X;
- cdev->can.data_bittiming_const = &m_can_data_bittiming_const_30X;
+ cdev->can.bittiming_const = cdev->bit_timing ?
+ cdev->bit_timing : &m_can_bittiming_const_30X;
+
+ cdev->can.data_bittiming_const = cdev->data_timing ?
+ cdev->data_timing :
+ &m_can_data_bittiming_const_30X;
break;
case 31:
/* CAN_CTRLMODE_FD_NON_ISO is fixed with M_CAN IP v3.1.x */
can_set_static_ctrlmode(dev, CAN_CTRLMODE_FD_NON_ISO);
- cdev->can.bittiming_const = &m_can_bittiming_const_31X;
- cdev->can.data_bittiming_const = &m_can_data_bittiming_const_31X;
+ cdev->can.bittiming_const = cdev->bit_timing ?
+ cdev->bit_timing : &m_can_bittiming_const_31X;
+
+ cdev->can.data_bittiming_const = cdev->data_timing ?
+ cdev->data_timing :
+ &m_can_data_bittiming_const_31X;
break;
case 32:
case 33:
/* Support both MCAN version v3.2.x and v3.3.0 */
- cdev->can.bittiming_const = &m_can_bittiming_const_31X;
- cdev->can.data_bittiming_const = &m_can_data_bittiming_const_31X;
+ cdev->can.bittiming_const = cdev->bit_timing ?
+ cdev->bit_timing : &m_can_bittiming_const_31X;
+
+ cdev->can.data_bittiming_const = cdev->data_timing ?
+ cdev->data_timing :
+ &m_can_data_bittiming_const_31X;
cdev->can.ctrlmode_supported |=
(m_can_niso_supported(cdev) ?
struct sk_buff *tx_skb;
struct phy *transceiver;
+ const struct can_bittiming_const *bit_timing;
+ const struct can_bittiming_const *data_timing;
+
struct m_can_ops *ops;
int version;
#define M_CAN_PCI_MMIO_BAR 0
-#define M_CAN_CLOCK_FREQ_EHL 100000000
#define CTL_CSR_INT_CTL_OFFSET 0x508
+struct m_can_pci_config {
+ const struct can_bittiming_const *bit_timing;
+ const struct can_bittiming_const *data_timing;
+ unsigned int clock_freq;
+};
+
struct m_can_pci_priv {
struct m_can_classdev cdev;
static int iomap_read_fifo(struct m_can_classdev *cdev, int offset, void *val, size_t val_count)
{
struct m_can_pci_priv *priv = cdev_to_priv(cdev);
+ void __iomem *src = priv->base + offset;
- ioread32_rep(priv->base + offset, val, val_count);
+ while (val_count--) {
+ *(unsigned int *)val = ioread32(src);
+ val += 4;
+ src += 4;
+ }
return 0;
}
const void *val, size_t val_count)
{
struct m_can_pci_priv *priv = cdev_to_priv(cdev);
+ void __iomem *dst = priv->base + offset;
- iowrite32_rep(priv->base + offset, val, val_count);
+ while (val_count--) {
+ iowrite32(*(unsigned int *)val, dst);
+ val += 4;
+ dst += 4;
+ }
return 0;
}
.read_fifo = iomap_read_fifo,
};
+static const struct can_bittiming_const m_can_bittiming_const_ehl = {
+ .name = KBUILD_MODNAME,
+ .tseg1_min = 2, /* Time segment 1 = prop_seg + phase_seg1 */
+ .tseg1_max = 64,
+ .tseg2_min = 1, /* Time segment 2 = phase_seg2 */
+ .tseg2_max = 128,
+ .sjw_max = 128,
+ .brp_min = 1,
+ .brp_max = 512,
+ .brp_inc = 1,
+};
+
+static const struct can_bittiming_const m_can_data_bittiming_const_ehl = {
+ .name = KBUILD_MODNAME,
+ .tseg1_min = 2, /* Time segment 1 = prop_seg + phase_seg1 */
+ .tseg1_max = 16,
+ .tseg2_min = 1, /* Time segment 2 = phase_seg2 */
+ .tseg2_max = 8,
+ .sjw_max = 4,
+ .brp_min = 1,
+ .brp_max = 32,
+ .brp_inc = 1,
+};
+
+static const struct m_can_pci_config m_can_pci_ehl = {
+ .bit_timing = &m_can_bittiming_const_ehl,
+ .data_timing = &m_can_data_bittiming_const_ehl,
+ .clock_freq = 200000000,
+};
+
static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id)
{
struct device *dev = &pci->dev;
+ const struct m_can_pci_config *cfg;
struct m_can_classdev *mcan_class;
struct m_can_pci_priv *priv;
void __iomem *base;
if (!mcan_class)
return -ENOMEM;
+ cfg = (const struct m_can_pci_config *)id->driver_data;
+
priv = cdev_to_priv(mcan_class);
priv->base = base;
mcan_class->dev = &pci->dev;
mcan_class->net->irq = pci_irq_vector(pci, 0);
mcan_class->pm_clock_support = 1;
- mcan_class->can.clock.freq = id->driver_data;
+ mcan_class->bit_timing = cfg->bit_timing;
+ mcan_class->data_timing = cfg->data_timing;
+ mcan_class->can.clock.freq = cfg->clock_freq;
mcan_class->ops = &m_can_pci_ops;
pci_set_drvdata(pci, mcan_class);
m_can_pci_suspend, m_can_pci_resume);
static const struct pci_device_id m_can_pci_id_table[] = {
- { PCI_VDEVICE(INTEL, 0x4bc1), M_CAN_CLOCK_FREQ_EHL, },
- { PCI_VDEVICE(INTEL, 0x4bc2), M_CAN_CLOCK_FREQ_EHL, },
+ { PCI_VDEVICE(INTEL, 0x4bc1), (kernel_ulong_t)&m_can_pci_ehl, },
+ { PCI_VDEVICE(INTEL, 0x4bc2), (kernel_ulong_t)&m_can_pci_ehl, },
{ } /* Terminating Entry */
};
MODULE_DEVICE_TABLE(pci, m_can_pci_id_table);
cf->data[i + 1] = data_reg >> 8;
}
- netif_receive_skb(skb);
rcv_pkts++;
stats->rx_packets++;
quota--;
stats->rx_bytes += cf->len;
+ netif_receive_skb(skb);
pch_fifo_thresh(priv, obj_num);
obj_num++;
free_sja1000dev(dev);
}
- err = request_irq(dev->irq, &ems_pcmcia_interrupt, IRQF_SHARED,
+ if (!card->channels) {
+ err = -ENODEV;
+ goto failure_cleanup;
+ }
+
+ err = request_irq(pdev->irq, &ems_pcmcia_interrupt, IRQF_SHARED,
DRV_NAME, card);
if (!err)
return 0;
#include "kvaser_usb.h"
-/* Forward declaration */
-static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg;
-
-#define CAN_USB_CLOCK 8000000
#define MAX_USBCAN_NET_DEVICES 2
/* Command header size */
#define CMD_LEAF_LOG_MESSAGE 106
+/* Leaf frequency options */
+#define KVASER_USB_LEAF_SWOPTION_FREQ_MASK 0x60
+#define KVASER_USB_LEAF_SWOPTION_FREQ_16_MHZ_CLK 0
+#define KVASER_USB_LEAF_SWOPTION_FREQ_32_MHZ_CLK BIT(5)
+#define KVASER_USB_LEAF_SWOPTION_FREQ_24_MHZ_CLK BIT(6)
+
/* error factors */
#define M16C_EF_ACKE BIT(0)
#define M16C_EF_CRCE BIT(1)
};
};
+static const struct can_bittiming_const kvaser_usb_leaf_bittiming_const = {
+ .name = "kvaser_usb",
+ .tseg1_min = KVASER_USB_TSEG1_MIN,
+ .tseg1_max = KVASER_USB_TSEG1_MAX,
+ .tseg2_min = KVASER_USB_TSEG2_MIN,
+ .tseg2_max = KVASER_USB_TSEG2_MAX,
+ .sjw_max = KVASER_USB_SJW_MAX,
+ .brp_min = KVASER_USB_BRP_MIN,
+ .brp_max = KVASER_USB_BRP_MAX,
+ .brp_inc = KVASER_USB_BRP_INC,
+};
+
+static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg_8mhz = {
+ .clock = {
+ .freq = 8000000,
+ },
+ .timestamp_freq = 1,
+ .bittiming_const = &kvaser_usb_leaf_bittiming_const,
+};
+
+static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg_16mhz = {
+ .clock = {
+ .freq = 16000000,
+ },
+ .timestamp_freq = 1,
+ .bittiming_const = &kvaser_usb_leaf_bittiming_const,
+};
+
+static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg_24mhz = {
+ .clock = {
+ .freq = 24000000,
+ },
+ .timestamp_freq = 1,
+ .bittiming_const = &kvaser_usb_leaf_bittiming_const,
+};
+
+static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg_32mhz = {
+ .clock = {
+ .freq = 32000000,
+ },
+ .timestamp_freq = 1,
+ .bittiming_const = &kvaser_usb_leaf_bittiming_const,
+};
+
static void *
kvaser_usb_leaf_frame_to_cmd(const struct kvaser_usb_net_priv *priv,
const struct sk_buff *skb, int *frame_len,
return rc;
}
+static void kvaser_usb_leaf_get_software_info_leaf(struct kvaser_usb *dev,
+ const struct leaf_cmd_softinfo *softinfo)
+{
+ u32 sw_options = le32_to_cpu(softinfo->sw_options);
+
+ dev->fw_version = le32_to_cpu(softinfo->fw_version);
+ dev->max_tx_urbs = le16_to_cpu(softinfo->max_outstanding_tx);
+
+ switch (sw_options & KVASER_USB_LEAF_SWOPTION_FREQ_MASK) {
+ case KVASER_USB_LEAF_SWOPTION_FREQ_16_MHZ_CLK:
+ dev->cfg = &kvaser_usb_leaf_dev_cfg_16mhz;
+ break;
+ case KVASER_USB_LEAF_SWOPTION_FREQ_24_MHZ_CLK:
+ dev->cfg = &kvaser_usb_leaf_dev_cfg_24mhz;
+ break;
+ case KVASER_USB_LEAF_SWOPTION_FREQ_32_MHZ_CLK:
+ dev->cfg = &kvaser_usb_leaf_dev_cfg_32mhz;
+ break;
+ }
+}
+
static int kvaser_usb_leaf_get_software_info_inner(struct kvaser_usb *dev)
{
struct kvaser_cmd cmd;
switch (dev->card_data.leaf.family) {
case KVASER_LEAF:
- dev->fw_version = le32_to_cpu(cmd.u.leaf.softinfo.fw_version);
- dev->max_tx_urbs =
- le16_to_cpu(cmd.u.leaf.softinfo.max_outstanding_tx);
+ kvaser_usb_leaf_get_software_info_leaf(dev, &cmd.u.leaf.softinfo);
break;
case KVASER_USBCAN:
dev->fw_version = le32_to_cpu(cmd.u.usbcan.softinfo.fw_version);
dev->max_tx_urbs =
le16_to_cpu(cmd.u.usbcan.softinfo.max_outstanding_tx);
+ dev->cfg = &kvaser_usb_leaf_dev_cfg_8mhz;
break;
}
{
struct kvaser_usb_dev_card_data *card_data = &dev->card_data;
- dev->cfg = &kvaser_usb_leaf_dev_cfg;
card_data->ctrlmode_supported |= CAN_CTRLMODE_3_SAMPLES;
return 0;
}
-static const struct can_bittiming_const kvaser_usb_leaf_bittiming_const = {
- .name = "kvaser_usb",
- .tseg1_min = KVASER_USB_TSEG1_MIN,
- .tseg1_max = KVASER_USB_TSEG1_MAX,
- .tseg2_min = KVASER_USB_TSEG2_MIN,
- .tseg2_max = KVASER_USB_TSEG2_MAX,
- .sjw_max = KVASER_USB_SJW_MAX,
- .brp_min = KVASER_USB_BRP_MIN,
- .brp_max = KVASER_USB_BRP_MAX,
- .brp_inc = KVASER_USB_BRP_INC,
-};
-
static int kvaser_usb_leaf_set_bittiming(struct net_device *netdev)
{
struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
.dev_read_bulk_callback = kvaser_usb_leaf_read_bulk_callback,
.dev_frame_to_cmd = kvaser_usb_leaf_frame_to_cmd,
};
-
-static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg = {
- .clock = {
- .freq = CAN_USB_CLOCK,
- },
- .timestamp_freq = 1,
- .bittiming_const = &kvaser_usb_leaf_bittiming_const,
-};
u16 reg;
int err;
+ /* The 88e6250 family does not have the PHY detect bit. Instead,
+ * report whether the port is internal.
+ */
+ if (chip->info->family == MV88E6XXX_FAMILY_6250)
+ return port < chip->info->num_internal_phys;
+
err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, ®);
if (err) {
dev_err(chip->dev,
{
struct mv88e6xxx_chip *chip = ds->priv;
struct mv88e6xxx_port *p;
- int err;
+ int err = 0;
p = &chip->ports[port];
- /* FIXME: is this the correct test? If we're in fixed mode on an
- * internal port, why should we process this any different from
- * PHY mode? On the other hand, the port may be automedia between
- * an internal PHY and the serdes...
- */
- if ((mode == MLO_AN_PHY) && mv88e6xxx_phy_is_internal(ds, port))
- return;
-
mv88e6xxx_reg_lock(chip);
- /* In inband mode, the link may come up at any time while the link
- * is not forced down. Force the link down while we reconfigure the
- * interface mode.
- */
- if (mode == MLO_AN_INBAND && p->interface != state->interface &&
- chip->info->ops->port_set_link)
- chip->info->ops->port_set_link(chip, port, LINK_FORCED_DOWN);
- err = mv88e6xxx_port_config_interface(chip, port, state->interface);
- if (err && err != -EOPNOTSUPP)
- goto err_unlock;
-
- err = mv88e6xxx_serdes_pcs_config(chip, port, mode, state->interface,
- state->advertising);
- /* FIXME: we should restart negotiation if something changed - which
- * is something we get if we convert to using phylinks PCS operations.
- */
- if (err > 0)
- err = 0;
+ if (mode != MLO_AN_PHY || !mv88e6xxx_phy_is_internal(ds, port)) {
+ /* In inband mode, the link may come up at any time while the
+ * link is not forced down. Force the link down while we
+ * reconfigure the interface mode.
+ */
+ if (mode == MLO_AN_INBAND &&
+ p->interface != state->interface &&
+ chip->info->ops->port_set_link)
+ chip->info->ops->port_set_link(chip, port,
+ LINK_FORCED_DOWN);
+
+ err = mv88e6xxx_port_config_interface(chip, port,
+ state->interface);
+ if (err && err != -EOPNOTSUPP)
+ goto err_unlock;
+
+ err = mv88e6xxx_serdes_pcs_config(chip, port, mode,
+ state->interface,
+ state->advertising);
+ /* FIXME: we should restart negotiation if something changed -
+ * which is something we get if we convert to using phylinks
+ * PCS operations.
+ */
+ if (err > 0)
+ err = 0;
+ }
/* Undo the forced down state above after completing configuration
- * irrespective of its state on entry, which allows the link to come up.
+ * irrespective of its state on entry, which allows the link to come
+ * up in the in-band case where there is no separate SERDES. Also
+ * ensure that the link can come up if the PPU is in use and we are
+ * in PHY mode (we treat the PPU as an effective in-band mechanism.)
*/
- if (mode == MLO_AN_INBAND && p->interface != state->interface &&
- chip->info->ops->port_set_link)
+ if (chip->info->ops->port_set_link &&
+ ((mode == MLO_AN_INBAND && p->interface != state->interface) ||
+ (mode == MLO_AN_PHY && mv88e6xxx_port_ppu_updates(chip, port))))
chip->info->ops->port_set_link(chip, port, LINK_UNFORCED);
p->interface = state->interface;
ops = chip->info->ops;
mv88e6xxx_reg_lock(chip);
- /* Internal PHYs propagate their configuration directly to the MAC.
- * External PHYs depend on whether the PPU is enabled for this port.
+ /* Force the link down if we know the port may not be automatically
+ * updated by the switch or if we are using fixed-link mode.
*/
- if (((!mv88e6xxx_phy_is_internal(ds, port) &&
- !mv88e6xxx_port_ppu_updates(chip, port)) ||
+ if ((!mv88e6xxx_port_ppu_updates(chip, port) ||
mode == MLO_AN_FIXED) && ops->port_sync_link)
err = ops->port_sync_link(chip, port, mode, false);
+
+ if (!err && ops->port_set_speed_duplex)
+ err = ops->port_set_speed_duplex(chip, port, SPEED_UNFORCED,
+ DUPLEX_UNFORCED);
mv88e6xxx_reg_unlock(chip);
if (err)
ops = chip->info->ops;
mv88e6xxx_reg_lock(chip);
- /* Internal PHYs propagate their configuration directly to the MAC.
- * External PHYs depend on whether the PPU is enabled for this port.
+ /* Configure and force the link up if we know that the port may not
+ * automatically updated by the switch or if we are using fixed-link
+ * mode.
*/
- if ((!mv88e6xxx_phy_is_internal(ds, port) &&
- !mv88e6xxx_port_ppu_updates(chip, port)) ||
+ if (!mv88e6xxx_port_ppu_updates(chip, port) ||
mode == MLO_AN_FIXED) {
/* FIXME: for an automedia port, should we force the link
* down here - what if the link comes up due to "other" media
if (err)
return err;
- if (speed)
+ if (speed != SPEED_UNFORCED)
dev_dbg(chip->dev, "p%d: Speed set to %d Mbps\n", port, speed);
else
dev_dbg(chip->dev, "p%d: Speed unforced\n", port);
if (err)
return err;
- if (speed)
+ if (speed != SPEED_UNFORCED)
dev_dbg(chip->dev, "p%d: Speed set to %d Mbps\n", port, speed);
else
dev_dbg(chip->dev, "p%d: Speed unforced\n", port);
bool up)
{
u8 cmode = chip->ports[port].cmode;
- int err = 0;
+ int err;
switch (cmode) {
case MV88E6XXX_PORT_STS_CMODE_SGMII:
case MV88E6XXX_PORT_STS_CMODE_RXAUI:
err = mv88e6390_serdes_power_10g(chip, lane, up);
break;
+ default:
+ err = -EINVAL;
+ break;
}
if (!err && up)
case MV88E6393X_PORT_STS_CMODE_10GBASER:
err = mv88e6390_serdes_power_10g(chip, lane, on);
break;
+ default:
+ err = -EINVAL;
+ break;
}
if (err)
}
}
- if (cpu < 0)
+ if (cpu < 0) {
+ kfree(tagging_rule);
+ kfree(redirect_rule);
return -EINVAL;
+ }
tagging_rule->key_type = OCELOT_VCAP_KEY_ETYPE;
*(__be16 *)tagging_rule->key.etype.etype.value = htons(ETH_P_1588);
priv->rxdescmem_busaddr = dma_res->start;
} else {
+ ret = -ENODEV;
goto err_free_netdev;
}
- if (!dma_set_mask(priv->device, DMA_BIT_MASK(priv->dmaops->dmamask)))
+ if (!dma_set_mask(priv->device, DMA_BIT_MASK(priv->dmaops->dmamask))) {
dma_set_coherent_mask(priv->device,
DMA_BIT_MASK(priv->dmaops->dmamask));
- else if (!dma_set_mask(priv->device, DMA_BIT_MASK(32)))
+ } else if (!dma_set_mask(priv->device, DMA_BIT_MASK(32))) {
dma_set_coherent_mask(priv->device, DMA_BIT_MASK(32));
- else
+ } else {
+ ret = -EIO;
goto err_free_netdev;
+ }
/* MAC address space */
ret = request_and_map(pdev, "control_port", &control_port,
enet->irq_tx = platform_get_irq_byname(pdev, "tx");
- dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
+ err = dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
+ if (err)
+ return err;
err = bcm4908_enet_dma_alloc(enet);
if (err)
struct bcm_sysport_priv *priv = netdev_priv(dev);
struct device *kdev = &priv->pdev->dev;
struct bcm_sysport_tx_ring *ring;
+ unsigned long flags, desc_flags;
struct bcm_sysport_cb *cb;
struct netdev_queue *txq;
u32 len_status, addr_lo;
unsigned int skb_len;
- unsigned long flags;
dma_addr_t mapping;
u16 queue;
int ret;
ring->desc_count--;
/* Ports are latched, so write upper address first */
+ spin_lock_irqsave(&priv->desc_lock, desc_flags);
tdma_writel(priv, len_status, TDMA_WRITE_PORT_HI(ring->index));
tdma_writel(priv, addr_lo, TDMA_WRITE_PORT_LO(ring->index));
+ spin_unlock_irqrestore(&priv->desc_lock, desc_flags);
/* Check ring space and update SW control flow */
if (ring->desc_count == 0)
}
/* Initialize both hardware and software ring */
+ spin_lock_init(&priv->desc_lock);
for (i = 0; i < dev->num_tx_queues; i++) {
ret = bcm_sysport_init_tx_ring(priv, i);
if (ret) {
int wol_irq;
/* Transmit rings */
+ spinlock_t desc_lock;
struct bcm_sysport_tx_ring *tx_rings;
/* Receive queue */
* Internal or external PHY with MDIO access
*/
phydev = phy_attach(priv->dev, phy_name, pd->phy_interface);
- if (!phydev) {
+ if (IS_ERR(phydev)) {
dev_err(kdev, "failed to register PHY device\n");
- return -ENODEV;
+ return PTR_ERR(phydev);
}
} else {
/*
__u64 bytes_per_cdan;
};
+#define DPAA2_ETH_CH_STATS 7
+
/* Maximum number of queues associated with a DPNI */
#define DPAA2_ETH_MAX_TCS 8
#define DPAA2_ETH_MAX_RX_QUEUES_PER_TC 16
/* Per-channel stats */
for (k = 0; k < priv->num_channels; k++) {
ch_stats = &priv->channel[k]->stats;
- for (j = 0; j < sizeof(*ch_stats) / sizeof(__u64) - 1; j++)
+ for (j = 0; j < DPAA2_ETH_CH_STATS; j++)
*((__u64 *)data + i + j) += *((__u64 *)ch_stats + j);
}
i += j;
#define FEC_ENET_WAKEUP ((uint)0x00020000) /* Wakeup request */
#define FEC_ENET_TXF (FEC_ENET_TXF_0 | FEC_ENET_TXF_1 | FEC_ENET_TXF_2)
#define FEC_ENET_RXF (FEC_ENET_RXF_0 | FEC_ENET_RXF_1 | FEC_ENET_RXF_2)
+#define FEC_ENET_RXF_GET(X) (((X) == 0) ? FEC_ENET_RXF_0 : \
+ (((X) == 1) ? FEC_ENET_RXF_1 : \
+ FEC_ENET_RXF_2))
#define FEC_ENET_TS_AVAIL ((uint)0x00010000)
#define FEC_ENET_TS_TIMER ((uint)0x00008000)
break;
pkt_received++;
- writel(FEC_ENET_RXF, fep->hwp + FEC_IEVENT);
+ writel(FEC_ENET_RXF_GET(queue_id), fep->hwp + FEC_IEVENT);
/* Check for errors. */
status ^= BD_ENET_RX_LAST;
set_protocol = ctx->curr_frag_cnt == ctx->expected_frag_cnt - 1;
} else {
skb = napi_alloc_skb(napi, len);
+
+ if (unlikely(!skb))
+ return NULL;
set_protocol = true;
}
__skb_put(skb, len);
u8 netdev_flags;
struct dentry *hnae3_dbgfs;
+ /* protects concurrent contention between debugfs commands */
+ struct mutex dbgfs_lock;
/* Network interface message level enabled bits */
u32 msg_enable;
if (ret)
return ret;
+ mutex_lock(&handle->dbgfs_lock);
save_buf = &hns3_dbg_cmd[index].buf;
if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) ||
read_buf = *save_buf;
} else {
read_buf = kvzalloc(hns3_dbg_cmd[index].buf_len, GFP_KERNEL);
- if (!read_buf)
- return -ENOMEM;
+ if (!read_buf) {
+ ret = -ENOMEM;
+ goto out;
+ }
/* save the buffer addr until the last read operation */
*save_buf = read_buf;
- }
- /* get data ready for the first time to read */
- if (!*ppos) {
+ /* get data ready for the first time to read */
ret = hns3_dbg_read_cmd(dbg_data, hns3_dbg_cmd[index].cmd,
read_buf, hns3_dbg_cmd[index].buf_len);
if (ret)
size = simple_read_from_buffer(buffer, count, ppos, read_buf,
strlen(read_buf));
- if (size > 0)
+ if (size > 0) {
+ mutex_unlock(&handle->dbgfs_lock);
return size;
+ }
out:
/* free the buffer for the last read operation */
*save_buf = NULL;
}
+ mutex_unlock(&handle->dbgfs_lock);
return ret;
}
debugfs_create_dir(hns3_dbg_dentry[i].name,
handle->hnae3_dbgfs);
+ mutex_init(&handle->dbgfs_lock);
+
for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++) {
if ((hns3_dbg_cmd[i].cmd == HNAE3_DBG_CMD_TM_NODES &&
ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2) ||
return 0;
out:
+ mutex_destroy(&handle->dbgfs_lock);
debugfs_remove_recursive(handle->hnae3_dbgfs);
handle->hnae3_dbgfs = NULL;
return ret;
hns3_dbg_cmd[i].buf = NULL;
}
+ mutex_destroy(&handle->dbgfs_lock);
debugfs_remove_recursive(handle->hnae3_dbgfs);
handle->hnae3_dbgfs = NULL;
}
memcpy(&req->msg, send_msg, sizeof(struct hclge_vf_to_pf_msg));
- trace_hclge_vf_mbx_send(hdev, req);
+ if (test_bit(HCLGEVF_STATE_NIC_REGISTERED, &hdev->state))
+ trace_hclge_vf_mbx_send(hdev, req);
/* synchronous send */
if (need_resp) {
#include <linux/interrupt.h>
#include <linux/etherdevice.h>
#include <linux/netdevice.h>
+#include <linux/module.h>
#include "hinic_hw_dev.h"
#include "hinic_dev.h"
dev_info(&pf->pdev->dev, "vsi %d not found\n", vsi_seid);
return;
}
+ if (vsi->type != I40E_VSI_MAIN &&
+ vsi->type != I40E_VSI_FDIR &&
+ vsi->type != I40E_VSI_VMDQ2) {
+ dev_info(&pf->pdev->dev,
+ "vsi %d type %d descriptor rings not available\n",
+ vsi_seid, vsi->type);
+ return;
+ }
if (type == RING_TYPE_XDP && !i40e_enabled_xdp_vsi(vsi)) {
dev_info(&pf->pdev->dev, "XDP not enabled on VSI %d\n", vsi_seid);
return;
}
/**
+ * i40e_sync_vf_state
+ * @vf: pointer to the VF info
+ * @state: VF state
+ *
+ * Called from a VF message to synchronize the service with a potential
+ * VF reset state
+ **/
+static bool i40e_sync_vf_state(struct i40e_vf *vf, enum i40e_vf_states state)
+{
+ int i;
+
+ /* When handling some messages, it needs VF state to be set.
+ * It is possible that this flag is cleared during VF reset,
+ * so there is a need to wait until the end of the reset to
+ * handle the request message correctly.
+ */
+ for (i = 0; i < I40E_VF_STATE_WAIT_COUNT; i++) {
+ if (test_bit(state, &vf->vf_states))
+ return true;
+ usleep_range(10000, 20000);
+ }
+
+ return test_bit(state, &vf->vf_states);
+}
+
+/**
* i40e_vc_get_version_msg
* @vf: pointer to the VF info
* @msg: pointer to the msg buffer
size_t len = 0;
int ret;
- if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) {
+ if (!i40e_sync_vf_state(vf, I40E_VF_STATE_INIT)) {
aq_ret = I40E_ERR_PARAM;
goto err;
}
bool allmulti = false;
bool alluni = false;
- if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+ if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
aq_ret = I40E_ERR_PARAM;
goto err_out;
}
struct i40e_vsi *vsi;
u16 num_qps_all = 0;
- if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+ if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
aq_ret = I40E_ERR_PARAM;
goto error_param;
}
i40e_status aq_ret = 0;
int i;
- if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+ if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
aq_ret = I40E_ERR_PARAM;
goto error_param;
}
struct i40e_pf *pf = vf->pf;
i40e_status aq_ret = 0;
- if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+ if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
aq_ret = I40E_ERR_PARAM;
goto error_param;
}
u8 cur_pairs = vf->num_queue_pairs;
struct i40e_pf *pf = vf->pf;
- if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states))
+ if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE))
return -EINVAL;
if (req_pairs > I40E_MAX_VF_QUEUES) {
memset(&stats, 0, sizeof(struct i40e_eth_stats));
- if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+ if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
aq_ret = I40E_ERR_PARAM;
goto error_param;
}
i40e_status ret = 0;
int i;
- if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
+ if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) ||
!i40e_vc_isvalid_vsi_id(vf, al->vsi_id)) {
ret = I40E_ERR_PARAM;
goto error_param;
i40e_status ret = 0;
int i;
- if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
+ if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) ||
!i40e_vc_isvalid_vsi_id(vf, al->vsi_id)) {
ret = I40E_ERR_PARAM;
goto error_param;
i40e_status aq_ret = 0;
int i;
- if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
+ if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) ||
!i40e_vc_isvalid_vsi_id(vf, vfl->vsi_id)) {
aq_ret = I40E_ERR_PARAM;
goto error_param;
struct i40e_vsi *vsi = NULL;
i40e_status aq_ret = 0;
- if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
+ if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) ||
!i40e_vc_isvalid_vsi_id(vf, vrk->vsi_id) ||
- (vrk->key_len != I40E_HKEY_ARRAY_SIZE)) {
+ vrk->key_len != I40E_HKEY_ARRAY_SIZE) {
aq_ret = I40E_ERR_PARAM;
goto err;
}
i40e_status aq_ret = 0;
u16 i;
- if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states) ||
+ if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE) ||
!i40e_vc_isvalid_vsi_id(vf, vrl->vsi_id) ||
- (vrl->lut_entries != I40E_VF_HLUT_ARRAY_SIZE)) {
+ vrl->lut_entries != I40E_VF_HLUT_ARRAY_SIZE) {
aq_ret = I40E_ERR_PARAM;
goto err;
}
i40e_status aq_ret = 0;
int len = 0;
- if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+ if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
aq_ret = I40E_ERR_PARAM;
goto err;
}
struct i40e_hw *hw = &pf->hw;
i40e_status aq_ret = 0;
- if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+ if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
aq_ret = I40E_ERR_PARAM;
goto err;
}
i40e_status aq_ret = 0;
struct i40e_vsi *vsi;
- if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+ if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
aq_ret = I40E_ERR_PARAM;
goto err;
}
i40e_status aq_ret = 0;
struct i40e_vsi *vsi;
- if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+ if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
aq_ret = I40E_ERR_PARAM;
goto err;
}
i40e_status aq_ret = 0;
int i, ret;
- if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+ if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
aq_ret = I40E_ERR_PARAM;
goto err;
}
i40e_status aq_ret = 0;
int i, ret;
- if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+ if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
aq_ret = I40E_ERR_PARAM;
goto err_out;
}
i40e_status aq_ret = 0;
u64 speed = 0;
- if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+ if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
aq_ret = I40E_ERR_PARAM;
goto err;
}
/* set this flag only after making sure all inputs are sane */
vf->adq_enabled = true;
- /* num_req_queues is set when user changes number of queues via ethtool
- * and this causes issue for default VSI(which depends on this variable)
- * when ADq is enabled, hence reset it.
- */
- vf->num_req_queues = 0;
/* reset the VF in order to allocate resources */
i40e_vc_reset_vf(vf, true);
struct i40e_pf *pf = vf->pf;
i40e_status aq_ret = 0;
- if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) {
+ if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) {
aq_ret = I40E_ERR_PARAM;
goto err;
}
#define I40E_MAX_VF_PROMISC_FLAGS 3
+#define I40E_VF_STATE_WAIT_COUNT 20
+
/* Various queue ctrls */
enum i40e_queue_ctrl {
I40E_QUEUE_CTRL_UNKNOWN = 0,
if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending))
return -EINVAL;
- new_tx_count = clamp_t(u32, ring->tx_pending,
- IAVF_MIN_TXD,
- IAVF_MAX_TXD);
- new_tx_count = ALIGN(new_tx_count, IAVF_REQ_DESCRIPTOR_MULTIPLE);
+ if (ring->tx_pending > IAVF_MAX_TXD ||
+ ring->tx_pending < IAVF_MIN_TXD ||
+ ring->rx_pending > IAVF_MAX_RXD ||
+ ring->rx_pending < IAVF_MIN_RXD) {
+ netdev_err(netdev, "Descriptors requested (Tx: %d / Rx: %d) out of range [%d-%d] (increment %d)\n",
+ ring->tx_pending, ring->rx_pending, IAVF_MIN_TXD,
+ IAVF_MAX_RXD, IAVF_REQ_DESCRIPTOR_MULTIPLE);
+ return -EINVAL;
+ }
- new_rx_count = clamp_t(u32, ring->rx_pending,
- IAVF_MIN_RXD,
- IAVF_MAX_RXD);
- new_rx_count = ALIGN(new_rx_count, IAVF_REQ_DESCRIPTOR_MULTIPLE);
+ new_tx_count = ALIGN(ring->tx_pending, IAVF_REQ_DESCRIPTOR_MULTIPLE);
+ if (new_tx_count != ring->tx_pending)
+ netdev_info(netdev, "Requested Tx descriptor count rounded up to %d\n",
+ new_tx_count);
+
+ new_rx_count = ALIGN(ring->rx_pending, IAVF_REQ_DESCRIPTOR_MULTIPLE);
+ if (new_rx_count != ring->rx_pending)
+ netdev_info(netdev, "Requested Rx descriptor count rounded up to %d\n",
+ new_rx_count);
/* if nothing to do return success */
if ((new_tx_count == adapter->tx_desc_count) &&
- (new_rx_count == adapter->rx_desc_count))
+ (new_rx_count == adapter->rx_desc_count)) {
+ netdev_dbg(netdev, "Nothing to change, descriptor count is same as requested\n");
return 0;
+ }
- adapter->tx_desc_count = new_tx_count;
- adapter->rx_desc_count = new_rx_count;
+ if (new_tx_count != adapter->tx_desc_count) {
+ netdev_dbg(netdev, "Changing Tx descriptor count from %d to %d\n",
+ adapter->tx_desc_count, new_tx_count);
+ adapter->tx_desc_count = new_tx_count;
+ }
+
+ if (new_rx_count != adapter->rx_desc_count) {
+ netdev_dbg(netdev, "Changing Rx descriptor count from %d to %d\n",
+ adapter->rx_desc_count, new_rx_count);
+ adapter->rx_desc_count = new_rx_count;
+ }
if (netif_running(netdev)) {
adapter->flags |= IAVF_FLAG_RESET_NEEDED;
}
adapter->aq_required = 0;
adapter->current_op = VIRTCHNL_OP_UNKNOWN;
+ mutex_unlock(&adapter->crit_lock);
queue_delayed_work(iavf_wq,
&adapter->watchdog_task,
msecs_to_jiffies(10));
iavf_detect_recover_hung(&adapter->vsi);
break;
case __IAVF_REMOVE:
- mutex_unlock(&adapter->crit_lock);
- return;
default:
+ mutex_unlock(&adapter->crit_lock);
return;
}
/* check for hw reset */
reg_val = rd32(hw, IAVF_VF_ARQLEN1) & IAVF_VF_ARQLEN1_ARQENABLE_MASK;
if (!reg_val) {
- iavf_change_state(adapter, __IAVF_RESETTING);
adapter->flags |= IAVF_FLAG_RESET_PENDING;
adapter->aq_required = 0;
adapter->current_op = VIRTCHNL_OP_UNKNOWN;
}
pci_set_master(adapter->pdev);
+ pci_restore_msi_state(adapter->pdev);
if (i == IAVF_RESET_WAIT_COMPLETE_COUNT) {
dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n",
new_cfg->etscfg.maxtcs = pf->hw.func_caps.common_cap.maxtc;
+ if (!bwcfg)
+ new_cfg->etscfg.tcbwtable[0] = 100;
+
if (!bwrec)
new_cfg->etsrec.tcbwtable[0] = 100;
if (mode == pf->dcbx_cap)
return ICE_DCB_NO_HW_CHG;
- pf->dcbx_cap = mode;
qos_cfg = &pf->hw.port_info->qos_cfg;
- if (mode & DCB_CAP_DCBX_VER_CEE) {
- if (qos_cfg->local_dcbx_cfg.pfc_mode == ICE_QOS_MODE_DSCP)
- return ICE_DCB_NO_HW_CHG;
+
+ /* DSCP configuration is not DCBx negotiated */
+ if (qos_cfg->local_dcbx_cfg.pfc_mode == ICE_QOS_MODE_DSCP)
+ return ICE_DCB_NO_HW_CHG;
+
+ pf->dcbx_cap = mode;
+
+ if (mode & DCB_CAP_DCBX_VER_CEE)
qos_cfg->local_dcbx_cfg.dcbx_mode = ICE_DCBX_MODE_CEE;
- } else {
+ else
qos_cfg->local_dcbx_cfg.dcbx_mode = ICE_DCBX_MODE_IEEE;
- }
dev_info(ice_pf_to_dev(pf), "DCBx mode = 0x%x\n", mode);
return ICE_DCB_HW_CHG_RST;
bool is_tun = tun == ICE_FD_HW_SEG_TUN;
int err;
- if (is_tun && !ice_get_open_tunnel_port(&pf->hw, &port_num))
+ if (is_tun && !ice_get_open_tunnel_port(&pf->hw, &port_num, TNL_ALL))
continue;
err = ice_fdir_write_fltr(pf, input, add, is_tun);
if (err)
}
/* return error if not an update and no available filters */
- fltrs_needed = ice_get_open_tunnel_port(hw, &tunnel_port) ? 2 : 1;
+ fltrs_needed = ice_get_open_tunnel_port(hw, &tunnel_port, TNL_ALL) ? 2 : 1;
if (!ice_fdir_find_fltr_by_idx(hw, fsp->location) &&
ice_fdir_num_avail_fltr(hw, pf->vsi[vsi->idx]) < fltrs_needed) {
dev_err(dev, "Failed to add filter. The maximum number of flow director filters has been reached.\n");
memcpy(pkt, ice_fdir_pkt[idx].pkt, ice_fdir_pkt[idx].pkt_len);
loc = pkt;
} else {
- if (!ice_get_open_tunnel_port(hw, &tnl_port))
+ if (!ice_get_open_tunnel_port(hw, &tnl_port, TNL_ALL))
return ICE_ERR_DOES_NOT_EXIST;
if (!ice_fdir_pkt[idx].tun_pkt)
return ICE_ERR_PARAM;
* ice_get_open_tunnel_port - retrieve an open tunnel port
* @hw: pointer to the HW structure
* @port: returns open port
+ * @type: type of tunnel, can be TNL_LAST if it doesn't matter
*/
bool
-ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port)
+ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port,
+ enum ice_tunnel_type type)
{
bool res = false;
u16 i;
mutex_lock(&hw->tnl_lock);
for (i = 0; i < hw->tnl.count && i < ICE_TUNNEL_MAX_ENTRIES; i++)
- if (hw->tnl.tbl[i].valid && hw->tnl.tbl[i].port) {
+ if (hw->tnl.tbl[i].valid && hw->tnl.tbl[i].port &&
+ (type == TNL_LAST || type == hw->tnl.tbl[i].type)) {
*port = hw->tnl.tbl[i].port;
res = true;
break;
ice_get_sw_fv_list(struct ice_hw *hw, u8 *prot_ids, u16 ids_cnt,
unsigned long *bm, struct list_head *fv_list);
bool
-ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port);
+ice_get_open_tunnel_port(struct ice_hw *hw, u16 *port,
+ enum ice_tunnel_type type);
int ice_udp_tunnel_set_port(struct net_device *netdev, unsigned int table,
unsigned int idx, struct udp_tunnel_info *ti);
int ice_udp_tunnel_unset_port(struct net_device *netdev, unsigned int table,
netif_carrier_on(vsi->netdev);
}
+ /* clear this now, and the first stats read will be used as baseline */
+ vsi->stat_offsets_loaded = false;
+
ice_service_task_schedule(pf);
return 0;
/**
* ice_update_vsi_tx_ring_stats - Update VSI Tx ring stats counters
* @vsi: the VSI to be updated
+ * @vsi_stats: the stats struct to be updated
* @rings: rings to work on
* @count: number of rings
*/
static void
-ice_update_vsi_tx_ring_stats(struct ice_vsi *vsi, struct ice_tx_ring **rings,
- u16 count)
+ice_update_vsi_tx_ring_stats(struct ice_vsi *vsi,
+ struct rtnl_link_stats64 *vsi_stats,
+ struct ice_tx_ring **rings, u16 count)
{
- struct rtnl_link_stats64 *vsi_stats = &vsi->net_stats;
u16 i;
for (i = 0; i < count; i++) {
*/
static void ice_update_vsi_ring_stats(struct ice_vsi *vsi)
{
- struct rtnl_link_stats64 *vsi_stats = &vsi->net_stats;
+ struct rtnl_link_stats64 *vsi_stats;
u64 pkts, bytes;
int i;
- /* reset netdev stats */
- vsi_stats->tx_packets = 0;
- vsi_stats->tx_bytes = 0;
- vsi_stats->rx_packets = 0;
- vsi_stats->rx_bytes = 0;
+ vsi_stats = kzalloc(sizeof(*vsi_stats), GFP_ATOMIC);
+ if (!vsi_stats)
+ return;
/* reset non-netdev (extended) stats */
vsi->tx_restart = 0;
rcu_read_lock();
/* update Tx rings counters */
- ice_update_vsi_tx_ring_stats(vsi, vsi->tx_rings, vsi->num_txq);
+ ice_update_vsi_tx_ring_stats(vsi, vsi_stats, vsi->tx_rings,
+ vsi->num_txq);
/* update Rx rings counters */
ice_for_each_rxq(vsi, i) {
/* update XDP Tx rings counters */
if (ice_is_xdp_ena_vsi(vsi))
- ice_update_vsi_tx_ring_stats(vsi, vsi->xdp_rings,
+ ice_update_vsi_tx_ring_stats(vsi, vsi_stats, vsi->xdp_rings,
vsi->num_xdp_txq);
rcu_read_unlock();
+
+ vsi->net_stats.tx_packets = vsi_stats->tx_packets;
+ vsi->net_stats.tx_bytes = vsi_stats->tx_bytes;
+ vsi->net_stats.rx_packets = vsi_stats->rx_packets;
+ vsi->net_stats.rx_bytes = vsi_stats->rx_bytes;
+
+ kfree(vsi_stats);
}
/**
scaled_ppm = -scaled_ppm;
}
- while ((u64)scaled_ppm > div_u64(U64_MAX, incval)) {
+ while ((u64)scaled_ppm > div64_u64(U64_MAX, incval)) {
/* handle overflow by scaling down the scaled_ppm and
* the divisor, losing some precision
*/
if (err)
continue;
- /* Check if the timestamp is valid */
- if (!(raw_tstamp & ICE_PTP_TS_VALID))
+ /* Check if the timestamp is invalid or stale */
+ if (!(raw_tstamp & ICE_PTP_TS_VALID) ||
+ raw_tstamp == tx->tstamps[idx].cached_tstamp)
continue;
- /* clear the timestamp register, so that it won't show valid
- * again when re-used.
- */
- ice_clear_phy_tstamp(hw, tx->quad, phy_idx);
-
/* The timestamp is valid, so we'll go ahead and clear this
* index and then send the timestamp up to the stack.
*/
spin_lock(&tx->lock);
+ tx->tstamps[idx].cached_tstamp = raw_tstamp;
clear_bit(idx, tx->in_use);
skb = tx->tstamps[idx].skb;
tx->tstamps[idx].skb = NULL;
* struct ice_tx_tstamp - Tracking for a single Tx timestamp
* @skb: pointer to the SKB for this timestamp request
* @start: jiffies when the timestamp was first requested
+ * @cached_tstamp: last read timestamp
*
* This structure tracks a single timestamp request. The SKB pointer is
* provided when initiating a request. The start time is used to ensure that
* we discard old requests that were not fulfilled within a 2 second time
* window.
+ * Timestamp values in the PHY are read only and do not get cleared except at
+ * hardware reset or when a new timestamp value is captured. The cached_tstamp
+ * field is used to detect the case where a new timestamp has not yet been
+ * captured, ensuring that we avoid sending stale timestamp data to the stack.
*/
struct ice_tx_tstamp {
struct sk_buff *skb;
unsigned long start;
+ u64 cached_tstamp;
};
/**
* ice_find_recp - find a recipe
* @hw: pointer to the hardware structure
* @lkup_exts: extension sequence to match
+ * @tun_type: type of recipe tunnel
*
* Returns index of matching recipe, or ICE_MAX_NUM_RECIPES if not found.
*/
-static u16 ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts)
+static u16
+ice_find_recp(struct ice_hw *hw, struct ice_prot_lkup_ext *lkup_exts,
+ enum ice_sw_tunnel_type tun_type)
{
bool refresh_required = true;
struct ice_sw_recipe *recp;
}
/* If for "i"th recipe the found was never set to false
* then it means we found our match
+ * Also tun type of recipe needs to be checked
*/
- if (found)
+ if (found && recp[i].tun_type == tun_type)
return i; /* Return the recipe ID */
}
}
}
/* Look for a recipe which matches our requested fv / mask list */
- *rid = ice_find_recp(hw, lkup_exts);
+ *rid = ice_find_recp(hw, lkup_exts, rinfo->tun_type);
if (*rid < ICE_MAX_NUM_RECIPES)
/* Success if found a recipe that match the existing criteria */
goto err_unroll;
+ rm->tun_type = rinfo->tun_type;
/* Recipe we need does not exist, add a recipe */
status = ice_add_sw_recipe(hw, rm, profiles);
if (status)
switch (tun_type) {
case ICE_SW_TUN_VXLAN:
+ if (!ice_get_open_tunnel_port(hw, &open_port, TNL_VXLAN))
+ return ICE_ERR_CFG;
+ break;
case ICE_SW_TUN_GENEVE:
- if (!ice_get_open_tunnel_port(hw, &open_port))
+ if (!ice_get_open_tunnel_port(hw, &open_port, TNL_GENEVE))
return ICE_ERR_CFG;
break;
-
default:
/* Nothing needs to be done for this tunnel type */
return 0;
if (status)
return status;
- rid = ice_find_recp(hw, &lkup_exts);
+ rid = ice_find_recp(hw, &lkup_exts, rinfo->tun_type);
/* If did not find a recipe that match the existing criteria */
if (rid == ICE_MAX_NUM_RECIPES)
return ICE_ERR_PARAM;
return inner ? ICE_IPV6_IL : ICE_IPV6_OFOS;
}
-static enum ice_protocol_type
-ice_proto_type_from_l4_port(bool inner, u16 ip_proto)
+static enum ice_protocol_type ice_proto_type_from_l4_port(u16 ip_proto)
{
- if (inner) {
- switch (ip_proto) {
- case IPPROTO_UDP:
- return ICE_UDP_ILOS;
- }
- } else {
- switch (ip_proto) {
- case IPPROTO_TCP:
- return ICE_TCP_IL;
- case IPPROTO_UDP:
- return ICE_UDP_OF;
- }
+ switch (ip_proto) {
+ case IPPROTO_TCP:
+ return ICE_TCP_IL;
+ case IPPROTO_UDP:
+ return ICE_UDP_ILOS;
}
return 0;
i++;
}
- if (flags & ICE_TC_FLWR_FIELD_ENC_DEST_L4_PORT) {
- list[i].type = ice_proto_type_from_l4_port(false, hdr->l3_key.ip_proto);
+ if ((flags & ICE_TC_FLWR_FIELD_ENC_DEST_L4_PORT) &&
+ hdr->l3_key.ip_proto == IPPROTO_UDP) {
+ list[i].type = ICE_UDP_OF;
list[i].h_u.l4_hdr.dst_port = hdr->l4_key.dst_port;
list[i].m_u.l4_hdr.dst_port = hdr->l4_mask.dst_port;
i++;
ICE_TC_FLWR_FIELD_SRC_L4_PORT)) {
struct ice_tc_l4_hdr *l4_key, *l4_mask;
- list[i].type = ice_proto_type_from_l4_port(inner, headers->l3_key.ip_proto);
+ list[i].type = ice_proto_type_from_l4_port(headers->l3_key.ip_proto);
l4_key = &headers->l4_key;
l4_mask = &headers->l4_mask;
headers->l3_mask.ttl = match.mask->ttl;
}
- if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS)) {
+ if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS) &&
+ fltr->tunnel_type != TNL_VXLAN && fltr->tunnel_type != TNL_GENEVE) {
struct flow_match_ports match;
flow_rule_match_enc_ports(rule, &match);
ice_vc_set_default_allowlist(vf);
ice_vf_fdir_exit(vf);
+ ice_vf_fdir_init(vf);
/* clean VF control VSI when resetting VFs since it should be
* setup only when VF creates its first FDIR rule.
*/
}
ice_vf_fdir_exit(vf);
+ ice_vf_fdir_init(vf);
/* clean VF control VSI when resetting VF since it should be setup
* only when VF creates its first FDIR rule.
*/
if (ret)
goto err_unroll_sriov;
+ /* rearm global interrupts */
+ if (test_and_clear_bit(ICE_OICR_INTR_DIS, pf->state))
+ ice_irq_dynamic_ena(hw, NULL, NULL);
+
return 0;
err_unroll_sriov:
struct vf_mac_filter *entry = NULL;
int ret = 0;
+ if ((vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) &&
+ !vf_data->trusted) {
+ dev_warn(&pdev->dev,
+ "VF %d requested MAC filter but is administratively denied\n",
+ vf);
+ return -EINVAL;
+ }
+ if (!is_valid_ether_addr(addr)) {
+ dev_warn(&pdev->dev,
+ "VF %d attempted to set invalid MAC filter\n",
+ vf);
+ return -EINVAL;
+ }
+
switch (info) {
case E1000_VF_MAC_FILTER_CLR:
/* remove all unicast MAC filters related to the current VF */
}
break;
case E1000_VF_MAC_FILTER_ADD:
- if ((vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) &&
- !vf_data->trusted) {
- dev_warn(&pdev->dev,
- "VF %d requested MAC filter but is administratively denied\n",
- vf);
- return -EINVAL;
- }
- if (!is_valid_ether_addr(addr)) {
- dev_warn(&pdev->dev,
- "VF %d attempted to set invalid MAC filter\n",
- vf);
- return -EINVAL;
- }
-
/* try to find empty slot in the list */
list_for_each(pos, &adapter->vf_macs.l) {
entry = list_entry(pos, struct vf_mac_filter, l);
return 0;
err_hw_init:
+ netif_napi_del(&adapter->rx_ring->napi);
kfree(adapter->tx_ring);
kfree(adapter->rx_ring);
err_sw_init:
ltrv = rd32(IGC_LTRMAXV);
if (ltr_max != (ltrv & IGC_LTRMAXV_LTRV_MASK)) {
ltrv = IGC_LTRMAXV_LSNP_REQ | ltr_max |
- (scale_min << IGC_LTRMAXV_SCALE_SHIFT);
+ (scale_max << IGC_LTRMAXV_SCALE_SHIFT);
wr32(IGC_LTRMAXV, ltrv);
}
}
if (!speed && hw->mac.ops.get_link_capabilities) {
ret = hw->mac.ops.get_link_capabilities(hw, &speed,
&autoneg);
+ /* remove NBASE-T speeds from default autonegotiation
+ * to accommodate broken network switches in the field
+ * which cannot cope with advertised NBASE-T speeds
+ */
speed &= ~(IXGBE_LINK_SPEED_5GB_FULL |
IXGBE_LINK_SPEED_2_5GB_FULL);
}
/* flush pending Tx transactions */
ixgbe_clear_tx_pending(hw);
+ /* set MDIO speed before talking to the PHY in case it's the 1st time */
+ ixgbe_set_mdio_speed(hw);
+
/* PHY ops must be identified and initialized prior to reset */
status = hw->phy.ops.init(hw);
if (status == IXGBE_ERR_SFP_NOT_SUPPORTED ||
mvpp2_rxq_status_update(port, rxq->id, 0, rxq->size);
if (priv->percpu_pools) {
- err = xdp_rxq_info_reg(&rxq->xdp_rxq_short, port->dev, rxq->id, 0);
+ err = xdp_rxq_info_reg(&rxq->xdp_rxq_short, port->dev, rxq->logic_rxq, 0);
if (err < 0)
goto err_free_dma;
- err = xdp_rxq_info_reg(&rxq->xdp_rxq_long, port->dev, rxq->id, 0);
+ err = xdp_rxq_info_reg(&rxq->xdp_rxq_long, port->dev, rxq->logic_rxq, 0);
if (err < 0)
goto err_unregister_rxq_short;
*
*/
+#include <linux/module.h>
+
#include "otx2_common.h"
#include "otx2_ptp.h"
u8 mac_profile;
int err;
- if (!mlxsw_sp_rif_mac_profile_is_shared(rif))
+ if (!mlxsw_sp_rif_mac_profile_is_shared(rif) &&
+ !mlxsw_sp_rif_mac_profile_find(mlxsw_sp, new_mac))
return mlxsw_sp_rif_mac_profile_edit(rif, new_mac);
err = mlxsw_sp_rif_mac_profile_get(mlxsw_sp, new_mac,
if (err)
goto out;
- err = mana_hwc_alloc_dma_buf(hwc, q_depth, max_msg_size,
- &hwc_wq->msg_buf);
- if (err)
- goto out;
-
hwc_wq->hwc = hwc;
hwc_wq->gdma_wq = queue;
hwc_wq->queue_depth = q_depth;
hwc_wq->hwc_cq = hwc_cq;
+ err = mana_hwc_alloc_dma_buf(hwc, q_depth, max_msg_size,
+ &hwc_wq->msg_buf);
+ if (err)
+ goto out;
+
*hwc_wq_ptr = hwc_wq;
return 0;
out:
return -ENOMEM;
cache = kzalloc(sizeof(*cache), GFP_KERNEL);
- if (!cache)
+ if (!cache) {
+ nfp_cpp_area_free(area);
return -ENOMEM;
+ }
cache->id = 0;
cache->addr = 0;
data_split = true;
}
} else {
+ if (unlikely(skb->len > ETH_TX_MAX_NON_LSO_PKT_LEN)) {
+ DP_ERR(edev, "Unexpected non LSO skb length = 0x%x\n", skb->len);
+ qede_free_failed_tx_pkt(txq, first_bd, 0, false);
+ qede_update_tx_producer(txq);
+ return NETDEV_TX_OK;
+ }
+
val |= ((skb->len & ETH_TX_DATA_1ST_BD_PKT_LEN_MASK) <<
ETH_TX_DATA_1ST_BD_PKT_LEN_SHIFT);
}
spin_lock_irqsave(&qdev->hw_lock, hw_flags);
- err = ql_wait_for_drvr_lock(qdev);
- if (err) {
- err = ql_adapter_initialize(qdev);
- if (err) {
- netdev_err(ndev, "Unable to initialize adapter\n");
- goto err_init;
- }
- netdev_err(ndev, "Releasing driver lock\n");
- ql_sem_unlock(qdev, QL_DRVR_SEM_MASK);
- } else {
+ if (!ql_wait_for_drvr_lock(qdev)) {
netdev_err(ndev, "Could not acquire driver lock\n");
+ err = -ENODEV;
goto err_lock;
}
+ err = ql_adapter_initialize(qdev);
+ if (err) {
+ netdev_err(ndev, "Unable to initialize adapter\n");
+ goto err_init;
+ }
+ ql_sem_unlock(qdev, QL_DRVR_SEM_MASK);
+
spin_unlock_irqrestore(&qdev->hw_lock, hw_flags);
set_bit(QL_ADAPTER_UP, &qdev->flags);
ef100_common_stat_mask(mask);
ef100_ethtool_stat_mask(mask);
+ if (!mc_stats)
+ return 0;
+
efx_nic_copy_stats(efx, mc_stats);
efx_nic_update_stats(ef100_stat_desc, EF100_STAT_COUNT, mask,
stats, mc_stats, false);
void (*set_rgmii_speed)(struct rk_priv_data *bsp_priv, int speed);
void (*set_rmii_speed)(struct rk_priv_data *bsp_priv, int speed);
void (*integrated_phy_powerup)(struct rk_priv_data *bsp_priv);
+ bool regs_valid;
u32 regs[];
};
.set_to_rmii = rk3568_set_to_rmii,
.set_rgmii_speed = rk3568_set_gmac_speed,
.set_rmii_speed = rk3568_set_gmac_speed,
+ .regs_valid = true,
.regs = {
0xfe2a0000, /* gmac0 */
0xfe010000, /* gmac1 */
* to be distinguished.
*/
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (res) {
+ if (res && ops->regs_valid) {
int i = 0;
while (ops->regs[i]) {
int is_l4;
};
+/* Rx Frame Steering */
+enum stmmac_rfs_type {
+ STMMAC_RFS_T_VLAN,
+ STMMAC_RFS_T_MAX,
+};
+
+struct stmmac_rfs_entry {
+ unsigned long cookie;
+ int in_use;
+ int type;
+ int tc;
+};
+
struct stmmac_priv {
/* Frequently used values are kept adjacent for cache effect */
u32 tx_coal_frames[MTL_MAX_TX_QUEUES];
struct stmmac_tc_entry *tc_entries;
unsigned int flow_entries_max;
struct stmmac_flow_entry *flow_entries;
+ unsigned int rfs_entries_max[STMMAC_RFS_T_MAX];
+ unsigned int rfs_entries_cnt[STMMAC_RFS_T_MAX];
+ unsigned int rfs_entries_total;
+ struct stmmac_rfs_entry *rfs_entries;
/* Pulse Per Second output */
struct stmmac_pps_cfg pps[STMMAC_PPS_MAX];
{
struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
struct stmmac_rx_buffer *buf = &rx_q->buf_pool[i];
+ gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN);
+
+ if (priv->dma_cap.addr64 <= 32)
+ gfp |= GFP_DMA32;
if (!buf->page) {
- buf->page = page_pool_dev_alloc_pages(rx_q->page_pool);
+ buf->page = page_pool_alloc_pages(rx_q->page_pool, gfp);
if (!buf->page)
return -ENOMEM;
buf->page_offset = stmmac_rx_offset(priv);
}
if (priv->sph && !buf->sec_page) {
- buf->sec_page = page_pool_dev_alloc_pages(rx_q->page_pool);
+ buf->sec_page = page_pool_alloc_pages(rx_q->page_pool, gfp);
if (!buf->sec_page)
return -ENOMEM;
struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
int dirty = stmmac_rx_dirty(priv, queue);
unsigned int entry = rx_q->dirty_rx;
+ gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN);
+
+ if (priv->dma_cap.addr64 <= 32)
+ gfp |= GFP_DMA32;
while (dirty-- > 0) {
struct stmmac_rx_buffer *buf = &rx_q->buf_pool[entry];
p = rx_q->dma_rx + entry;
if (!buf->page) {
- buf->page = page_pool_dev_alloc_pages(rx_q->page_pool);
+ buf->page = page_pool_alloc_pages(rx_q->page_pool, gfp);
if (!buf->page)
break;
}
if (priv->sph && !buf->sec_page) {
- buf->sec_page = page_pool_dev_alloc_pages(rx_q->page_pool);
+ buf->sec_page = page_pool_alloc_pages(rx_q->page_pool, gfp);
if (!buf->sec_page)
break;
}
}
+static int tc_rfs_init(struct stmmac_priv *priv)
+{
+ int i;
+
+ priv->rfs_entries_max[STMMAC_RFS_T_VLAN] = 8;
+
+ for (i = 0; i < STMMAC_RFS_T_MAX; i++)
+ priv->rfs_entries_total += priv->rfs_entries_max[i];
+
+ priv->rfs_entries = devm_kcalloc(priv->device,
+ priv->rfs_entries_total,
+ sizeof(*priv->rfs_entries),
+ GFP_KERNEL);
+ if (!priv->rfs_entries)
+ return -ENOMEM;
+
+ dev_info(priv->device, "Enabled RFS Flow TC (entries=%d)\n",
+ priv->rfs_entries_total);
+
+ return 0;
+}
+
static int tc_init(struct stmmac_priv *priv)
{
struct dma_features *dma_cap = &priv->dma_cap;
unsigned int count;
- int i;
+ int ret, i;
if (dma_cap->l3l4fnum) {
priv->flow_entries_max = dma_cap->l3l4fnum;
for (i = 0; i < priv->flow_entries_max; i++)
priv->flow_entries[i].idx = i;
- dev_info(priv->device, "Enabled Flow TC (entries=%d)\n",
+ dev_info(priv->device, "Enabled L3L4 Flow TC (entries=%d)\n",
priv->flow_entries_max);
}
+ ret = tc_rfs_init(priv);
+ if (ret)
+ return -ENOMEM;
+
if (!priv->plat->fpe_cfg) {
priv->plat->fpe_cfg = devm_kzalloc(priv->device,
sizeof(*priv->plat->fpe_cfg),
return ret;
}
+static struct stmmac_rfs_entry *tc_find_rfs(struct stmmac_priv *priv,
+ struct flow_cls_offload *cls,
+ bool get_free)
+{
+ int i;
+
+ for (i = 0; i < priv->rfs_entries_total; i++) {
+ struct stmmac_rfs_entry *entry = &priv->rfs_entries[i];
+
+ if (entry->cookie == cls->cookie)
+ return entry;
+ if (get_free && entry->in_use == false)
+ return entry;
+ }
+
+ return NULL;
+}
+
#define VLAN_PRIO_FULL_MASK (0x07)
static int tc_add_vlan_flow(struct stmmac_priv *priv,
struct flow_cls_offload *cls)
{
+ struct stmmac_rfs_entry *entry = tc_find_rfs(priv, cls, false);
struct flow_rule *rule = flow_cls_offload_flow_rule(cls);
struct flow_dissector *dissector = rule->match.dissector;
int tc = tc_classid_to_hwtc(priv->dev, cls->classid);
struct flow_match_vlan match;
+ if (!entry) {
+ entry = tc_find_rfs(priv, cls, true);
+ if (!entry)
+ return -ENOENT;
+ }
+
+ if (priv->rfs_entries_cnt[STMMAC_RFS_T_VLAN] >=
+ priv->rfs_entries_max[STMMAC_RFS_T_VLAN])
+ return -ENOENT;
+
/* Nothing to do here */
if (!dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_VLAN))
return -EINVAL;
prio = BIT(match.key->vlan_priority);
stmmac_rx_queue_prio(priv, priv->hw, prio, tc);
+
+ entry->in_use = true;
+ entry->cookie = cls->cookie;
+ entry->tc = tc;
+ entry->type = STMMAC_RFS_T_VLAN;
+ priv->rfs_entries_cnt[STMMAC_RFS_T_VLAN]++;
}
return 0;
static int tc_del_vlan_flow(struct stmmac_priv *priv,
struct flow_cls_offload *cls)
{
- struct flow_rule *rule = flow_cls_offload_flow_rule(cls);
- struct flow_dissector *dissector = rule->match.dissector;
- int tc = tc_classid_to_hwtc(priv->dev, cls->classid);
+ struct stmmac_rfs_entry *entry = tc_find_rfs(priv, cls, false);
- /* Nothing to do here */
- if (!dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_VLAN))
- return -EINVAL;
+ if (!entry || !entry->in_use || entry->type != STMMAC_RFS_T_VLAN)
+ return -ENOENT;
- if (tc < 0) {
- netdev_err(priv->dev, "Invalid traffic class\n");
- return -EINVAL;
- }
+ stmmac_rx_queue_prio(priv, priv->hw, 0, entry->tc);
+
+ entry->in_use = false;
+ entry->cookie = 0;
+ entry->tc = 0;
+ entry->type = 0;
- stmmac_rx_queue_prio(priv, priv->hw, 0, tc);
+ priv->rfs_entries_cnt[STMMAC_RFS_T_VLAN]--;
return 0;
}
if (ret < 0) {
dev_err(dev, "%pOF error reading port_id %d\n",
port_np, ret);
- return ret;
+ goto of_node_put;
}
if (!port_id || port_id > common->port_num) {
dev_err(dev, "%pOF has invalid port_id %u %s\n",
port_np, port_id, port_np->name);
- return -EINVAL;
+ ret = -EINVAL;
+ goto of_node_put;
}
port = am65_common_get_port(common, port_id);
(AM65_CPSW_NU_FRAM_PORT_OFFSET * (port_id - 1));
port->slave.mac_sl = cpsw_sl_get("am65", dev, port->port_base);
- if (IS_ERR(port->slave.mac_sl))
- return PTR_ERR(port->slave.mac_sl);
+ if (IS_ERR(port->slave.mac_sl)) {
+ ret = PTR_ERR(port->slave.mac_sl);
+ goto of_node_put;
+ }
port->disabled = !of_device_is_available(port_np);
if (port->disabled) {
ret = PTR_ERR(port->slave.ifphy);
dev_err(dev, "%pOF error retrieving port phy: %d\n",
port_np, ret);
- return ret;
+ goto of_node_put;
}
port->slave.mac_only =
/* get phy/link info */
if (of_phy_is_fixed_link(port_np)) {
ret = of_phy_register_fixed_link(port_np);
- if (ret)
- return dev_err_probe(dev, ret,
+ if (ret) {
+ ret = dev_err_probe(dev, ret,
"failed to register fixed-link phy %pOF\n",
port_np);
+ goto of_node_put;
+ }
port->slave.phy_node = of_node_get(port_np);
} else {
port->slave.phy_node =
if (!port->slave.phy_node) {
dev_err(dev,
"slave[%d] no phy found\n", port_id);
- return -ENODEV;
+ ret = -ENODEV;
+ goto of_node_put;
}
ret = of_get_phy_mode(port_np, &port->slave.phy_if);
if (ret) {
dev_err(dev, "%pOF read phy-mode err %d\n",
port_np, ret);
- return ret;
+ goto of_node_put;
}
ret = of_get_mac_address(port_np, port->slave.mac_addr);
}
return 0;
+
+of_node_put:
+ of_node_put(port_np);
+ of_node_put(node);
+ return ret;
}
static void am65_cpsw_pcpu_stats_free(void *data)
goto err_free;
key = nmap->entry[i].key;
*key = i;
+ memset(nmap->entry[i].value, 0, offmap->map.value_size);
}
}
{
struct netdevsim *ns = netdev_priv(dev);
- memcpy(&ns->ethtool.ring, ring, sizeof(ns->ethtool.ring));
+ ns->ethtool.ring.rx_pending = ring->rx_pending;
+ ns->ethtool.ring.rx_jumbo_pending = ring->rx_jumbo_pending;
+ ns->ethtool.ring.rx_mini_pending = ring->rx_mini_pending;
+ ns->ethtool.ring.tx_pending = ring->tx_pending;
return 0;
}
if (addr == mdiodev->addr) {
device_set_node(dev, of_fwnode_handle(child));
+ /* The refcount on "child" is passed to the mdio
+ * device. Do _not_ use of_node_put(child) here.
+ */
return;
}
}
* @mac_wol: true if the MAC needs to receive packets for Wake-on-Lan
*
* Handle a network device suspend event. There are several cases:
+ *
* - If Wake-on-Lan is not active, we can bring down the link between
* the MAC and PHY by calling phylink_stop().
* - If Wake-on-Lan is active, and being handled only by the PHY, we
min = ctx->max_datagram_size + ctx->max_ndp_size + sizeof(struct usb_cdc_ncm_nth32);
max = min_t(u32, CDC_NCM_NTB_MAX_SIZE_TX, le32_to_cpu(ctx->ncm_parm.dwNtbOutMaxSize));
+ if (max == 0)
+ max = CDC_NCM_NTB_MAX_SIZE_TX; /* dwNtbOutMaxSize not set */
/* some devices set dwNtbOutMaxSize too low for the above default */
min = min(min, max);
#define LAN7801_USB_PRODUCT_ID (0x7801)
#define LAN78XX_EEPROM_MAGIC (0x78A5)
#define LAN78XX_OTP_MAGIC (0x78F3)
+#define AT29M2AF_USB_VENDOR_ID (0x07C9)
+#define AT29M2AF_USB_PRODUCT_ID (0x0012)
#define MII_READ 1
#define MII_WRITE 0
/* LAN7801 USB Gigabit Ethernet Device */
USB_DEVICE(LAN78XX_USB_VENDOR_ID, LAN7801_USB_PRODUCT_ID),
},
+ {
+ /* ATM2-AF USB Gigabit Ethernet Device */
+ USB_DEVICE(AT29M2AF_USB_VENDOR_ID, AT29M2AF_USB_PRODUCT_ID),
+ },
{},
};
MODULE_DEVICE_TABLE(usb, products);
{QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)}, /* Telit LE922A */
{QMI_QUIRK_SET_DTR(0x1bc7, 0x1050, 2)}, /* Telit FN980 */
{QMI_QUIRK_SET_DTR(0x1bc7, 0x1060, 2)}, /* Telit LN920 */
+ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1070, 2)}, /* Telit FN990 */
{QMI_FIXED_INTF(0x1bc7, 0x1100, 3)}, /* Telit ME910 */
{QMI_FIXED_INTF(0x1bc7, 0x1101, 3)}, /* Telit ME910 dual modem */
{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */
pr_debug("%s: rx error: len %u exceeds max size %d\n",
dev->name, len, GOOD_PACKET_LEN);
dev->stats.rx_length_errors++;
- goto err_len;
+ goto err;
}
if (likely(!vi->xdp_enabled)) {
skip_xdp:
skb = build_skb(buf, buflen);
- if (!skb) {
- put_page(page);
+ if (!skb)
goto err;
- }
skb_reserve(skb, headroom - delta);
skb_put(skb, len);
if (!xdp_prog) {
if (metasize)
skb_metadata_set(skb, metasize);
-err:
return skb;
err_xdp:
rcu_read_unlock();
stats->xdp_drops++;
-err_len:
+err:
stats->drops++;
put_page(page);
xdp_xmit:
#ifdef CONFIG_PCI_MSI
if (adapter->intr.type == VMXNET3_IT_MSIX) {
- int i, nvec;
+ int i, nvec, nvec_allocated;
nvec = adapter->share_intr == VMXNET3_INTR_TXSHARE ?
1 : adapter->num_tx_queues;
for (i = 0; i < nvec; i++)
adapter->intr.msix_entries[i].entry = i;
- nvec = vmxnet3_acquire_msix_vectors(adapter, nvec);
- if (nvec < 0)
+ nvec_allocated = vmxnet3_acquire_msix_vectors(adapter, nvec);
+ if (nvec_allocated < 0)
goto msix_err;
/* If we cannot allocate one MSIx vector per queue
* then limit the number of rx queues to 1
*/
- if (nvec == VMXNET3_LINUX_MIN_MSIX_VECT) {
+ if (nvec_allocated == VMXNET3_LINUX_MIN_MSIX_VECT &&
+ nvec != VMXNET3_LINUX_MIN_MSIX_VECT) {
if (adapter->share_intr != VMXNET3_INTR_BUDDYSHARE
|| adapter->num_rx_queues != 1) {
adapter->share_intr = VMXNET3_INTR_TXSHARE;
}
}
- adapter->intr.num_intrs = nvec;
+ adapter->intr.num_intrs = nvec_allocated;
return;
msix_err:
/* If we cannot allocate MSIx vectors use only one rx queue */
dev_info(&adapter->pdev->dev,
"Failed to enable MSI-X, error %d. "
- "Limiting #rx queues to 1, try MSI.\n", nvec);
+ "Limiting #rx queues to 1, try MSI.\n", nvec_allocated);
adapter->intr.type = VMXNET3_IT_MSI;
}
skb->dev = vrf_dev;
- vrf_nf_set_untracked(skb);
-
err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk,
skb, NULL, vrf_dev, vrf_ip6_out_direct_finish);
if (rt6_need_strict(&ipv6_hdr(skb)->daddr))
return skb;
+ vrf_nf_set_untracked(skb);
+
if (qdisc_tx_is_default(vrf_dev) ||
IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED)
return vrf_ip6_out_direct(vrf_dev, sk, skb);
skb->dev = vrf_dev;
- vrf_nf_set_untracked(skb);
-
err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk,
skb, NULL, vrf_dev, vrf_ip_out_direct_finish);
ipv4_is_lbcast(ip_hdr(skb)->daddr))
return skb;
+ vrf_nf_set_untracked(skb);
+
if (qdisc_tx_is_default(vrf_dev) ||
IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED)
return vrf_ip_out_direct(vrf_dev, sk, skb);
ret = mhi_pm_suspend(ab_pci->mhi_ctrl);
break;
case ATH11K_MHI_RESUME:
- ret = mhi_pm_resume(ab_pci->mhi_ctrl);
+ /* Do force MHI resume as some devices like QCA6390, WCN6855
+ * are not in M3 state but they are functional. So just ignore
+ * the MHI state while resuming.
+ */
+ ret = mhi_pm_resume_force(ab_pci->mhi_ctrl);
break;
case ATH11K_MHI_TRIGGER_RDDM:
ret = mhi_force_rddm_mode(ab_pci->mhi_ctrl);
depends on MAC80211
depends on BCMA_POSSIBLE
select BCMA
- select NEW_LEDS if BCMA_DRIVER_GPIO
- select LEDS_CLASS if BCMA_DRIVER_GPIO
select BRCMUTIL
select FW_LOADER
select CORDIC
help
This module adds support for PCIe wireless adapters based on Broadcom
- IEEE802.11n SoftMAC chipsets. It also has WLAN led support, which will
- be available if you select BCMA_DRIVER_GPIO. If you choose to build a
- module, the driver will be called brcmsmac.ko.
+ IEEE802.11n SoftMAC chipsets. If you choose to build a module, the
+ driver will be called brcmsmac.ko.
+
+config BRCMSMAC_LEDS
+ def_bool BRCMSMAC && BCMA_DRIVER_GPIO && MAC80211_LEDS
+ help
+ The brcmsmac LED support depends on the presence of the
+ BCMA_DRIVER_GPIO driver, and it only works if LED support
+ is enabled and reachable from the driver module.
source "drivers/net/wireless/broadcom/brcm80211/brcmfmac/Kconfig"
brcms_trace_events.o \
debug.o
-brcmsmac-$(CONFIG_BCMA_DRIVER_GPIO) += led.o
+brcmsmac-$(CONFIG_BRCMSMAC_LEDS) += led.o
obj-$(CONFIG_BRCMSMAC) += brcmsmac.o
struct gpio_desc *gpiod;
};
-#ifdef CONFIG_BCMA_DRIVER_GPIO
+#ifdef CONFIG_BRCMSMAC_LEDS
void brcms_led_unregister(struct brcms_info *wl);
int brcms_led_register(struct brcms_info *wl);
#else
config IWLEGACY
tristate
select FW_LOADER
- select NEW_LEDS
- select LEDS_CLASS
select LEDS_TRIGGERS
select MAC80211_LEDS
config IWL4965
tristate "Intel Wireless WiFi 4965AGN (iwl4965)"
depends on PCI && MAC80211
+ depends on LEDS_CLASS=y || LEDS_CLASS=MAC80211
select IWLEGACY
help
This option enables support for
config IWL3945
tristate "Intel PRO/Wireless 3945ABG/BG Network Connection (iwl3945)"
depends on PCI && MAC80211
+ depends on LEDS_CLASS=y || LEDS_CLASS=MAC80211
select IWLEGACY
help
Select to build the driver supporting the:
config IWLWIFI_LEDS
bool
- depends on LEDS_CLASS=y || LEDS_CLASS=IWLWIFI
+ depends on LEDS_CLASS=y || LEDS_CLASS=MAC80211
depends on IWLMVM || IWLDVM
select LEDS_TRIGGERS
select MAC80211_LEDS
u8 rate_plcp;
u32 rate_flags = 0;
bool is_cck;
- struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
/* info->control is only relevant for non HW rate control */
if (!ieee80211_hw_check(mvm->hw, HAS_RATE_CONTROL)) {
+ struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
+
/* HT rate doesn't make sense for a non data frame */
WARN_ONCE(info->control.rates[0].flags & IEEE80211_TX_RC_MCS &&
!ieee80211_is_data(fc),
"Got a HT rate (flags:0x%x/mcs:%d/fc:0x%x/state:%d) for a non data frame\n",
info->control.rates[0].flags,
info->control.rates[0].idx,
- le16_to_cpu(fc), mvmsta->sta_state);
+ le16_to_cpu(fc), sta ? mvmsta->sta_state : -1);
rate_idx = info->control.rates[0].idx;
}
obj-$(CONFIG_MT7603E) += mt7603/
obj-$(CONFIG_MT7615_COMMON) += mt7615/
obj-$(CONFIG_MT7915E) += mt7915/
-obj-$(CONFIG_MT7921E) += mt7921/
+obj-$(CONFIG_MT7921_COMMON) += mt7921/
bool ipc_imem_ul_write_td(struct iosm_imem *ipc_imem)
{
struct ipc_mem_channel *channel;
+ bool hpda_ctrl_pending = false;
struct sk_buff_head *ul_list;
bool hpda_pending = false;
- bool forced_hpdu = false;
struct ipc_pipe *pipe;
int i;
ul_list = &channel->ul_list;
/* Fill the transfer descriptor with the uplink buffer info. */
- hpda_pending |= ipc_protocol_ul_td_send(ipc_imem->ipc_protocol,
+ if (!ipc_imem_check_wwan_ips(channel)) {
+ hpda_ctrl_pending |=
+ ipc_protocol_ul_td_send(ipc_imem->ipc_protocol,
pipe, ul_list);
-
- /* forced HP update needed for non data channels */
- if (hpda_pending && !ipc_imem_check_wwan_ips(channel))
- forced_hpdu = true;
+ } else {
+ hpda_pending |=
+ ipc_protocol_ul_td_send(ipc_imem->ipc_protocol,
+ pipe, ul_list);
+ }
}
- if (forced_hpdu) {
+ /* forced HP update needed for non data channels */
+ if (hpda_ctrl_pending) {
hpda_pending = false;
ipc_protocol_doorbell_trigger(ipc_imem->ipc_protocol,
IPC_HP_UL_WRITE_TD);
return;
}
+ if (test_and_clear_bit(IOSM_DEVLINK_INIT, &ipc_imem->flag))
+ ipc_devlink_deinit(ipc_imem->ipc_devlink);
+
if (!ipc_imem_setup_cp_mux_cap_init(ipc_imem, &mux_cfg))
ipc_imem->mux = ipc_mux_init(&mux_cfg, ipc_imem);
ipc_port_deinit(ipc_imem->ipc_port);
}
- if (ipc_imem->ipc_devlink)
+ if (test_and_clear_bit(IOSM_DEVLINK_INIT, &ipc_imem->flag))
ipc_devlink_deinit(ipc_imem->ipc_devlink);
ipc_imem_device_ipc_uninit(ipc_imem);
ipc_imem->pci_device_id = device_id;
- ipc_imem->ev_cdev_write_pending = false;
ipc_imem->cp_version = 0;
ipc_imem->device_sleep = IPC_HOST_SLEEP_ENTER_SLEEP;
if (ipc_flash_link_establish(ipc_imem))
goto devlink_channel_fail;
+
+ set_bit(IOSM_DEVLINK_INIT, &ipc_imem->flag);
}
return ipc_imem;
devlink_channel_fail:
#define IOSM_CHIP_INFO_SIZE_MAX 100
#define FULLY_FUNCTIONAL 0
+#define IOSM_DEVLINK_INIT 1
/* List of the supported UL/DL pipes. */
enum ipc_mem_pipes {
* process the irq actions.
* @flag: Flag to monitor the state of driver
* @td_update_timer_suspended: if true then td update timer suspend
- * @ev_cdev_write_pending: 0 means inform the IPC tasklet to pass
- * the accumulated uplink buffers to CP.
* @ev_mux_net_transmit_pending:0 means inform the IPC tasklet to pass
* @reset_det_n: Reset detect flag
* @pcie_wake_n: Pcie wake flag
u8 ev_irq_pending[IPC_IRQ_VECTORS];
unsigned long flag;
u8 td_update_timer_suspended:1,
- ev_cdev_write_pending:1,
ev_mux_net_transmit_pending:1,
reset_det_n:1,
pcie_wake_n:1;
static int ipc_imem_tq_cdev_write(struct iosm_imem *ipc_imem, int arg,
void *msg, size_t size)
{
- ipc_imem->ev_cdev_write_pending = false;
ipc_imem_ul_send(ipc_imem);
return 0;
/* Through tasklet to do sio write. */
static int ipc_imem_call_cdev_write(struct iosm_imem *ipc_imem)
{
- if (ipc_imem->ev_cdev_write_pending)
- return -1;
-
- ipc_imem->ev_cdev_write_pending = true;
-
return ipc_task_queue_send_task(ipc_imem, ipc_imem_tq_cdev_write, 0,
NULL, 0, false);
}
/* Release the pipe resources */
ipc_imem_pipe_cleanup(ipc_imem, &channel->ul_pipe);
ipc_imem_pipe_cleanup(ipc_imem, &channel->dl_pipe);
+ ipc_imem->nr_of_channels--;
}
void ipc_imem_sys_devlink_notify_rx(struct iosm_devlink *ipc_devlink,
struct request *rq)
{
if (ctrl->state != NVME_CTRL_DELETING_NOIO &&
+ ctrl->state != NVME_CTRL_DELETING &&
ctrl->state != NVME_CTRL_DEAD &&
!test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) &&
!blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
*/
if (WARN_ON_ONCE(!(id->flbas & NVME_NS_FLBAS_META_EXT)))
return -EINVAL;
- if (ctrl->max_integrity_segments)
- ns->features |=
- (NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS);
+
+ ns->features |= NVME_NS_EXT_LBAS;
+
+ /*
+ * The current fabrics transport drivers support namespace
+ * metadata formats only if nvme_ns_has_pi() returns true.
+ * Suppress support for all other formats so the namespace will
+ * have a 0 capacity and not be usable through the block stack.
+ *
+ * Note, this check will need to be modified if any drivers
+ * gain the ability to use other metadata formats.
+ */
+ if (ctrl->max_integrity_segments && nvme_ns_has_pi(ns))
+ ns->features |= NVME_NS_METADATA_SUPPORTED;
} else {
/*
* For PCIe controllers, we can't easily remap the separate
if (tmp->cntlid == ctrl->cntlid) {
dev_err(ctrl->device,
- "Duplicate cntlid %u with %s, rejecting\n",
- ctrl->cntlid, dev_name(tmp->device));
+ "Duplicate cntlid %u with %s, subsys %s, rejecting\n",
+ ctrl->cntlid, dev_name(tmp->device),
+ subsys->subnqn);
return false;
}
}
if (ana_log_size > ctrl->ana_log_size) {
nvme_mpath_stop(ctrl);
- kfree(ctrl->ana_log_buf);
+ nvme_mpath_uninit(ctrl);
ctrl->ana_log_buf = kmalloc(ana_log_size, GFP_KERNEL);
if (!ctrl->ana_log_buf)
return -ENOMEM;
{
kfree(ctrl->ana_log_buf);
ctrl->ana_log_buf = NULL;
+ ctrl->ana_log_size = 0;
}
return true;
if (ctrl->ops->flags & NVME_F_FABRICS &&
ctrl->state == NVME_CTRL_DELETING)
- return true;
+ return queue_live;
return __nvme_check_ready(ctrl, rq, queue_live);
}
int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
zone.len = ns->zsze;
zone.capacity = nvme_lba_to_sect(ns, le64_to_cpu(entry->zcap));
zone.start = nvme_lba_to_sect(ns, le64_to_cpu(entry->zslba));
- zone.wp = nvme_lba_to_sect(ns, le64_to_cpu(entry->wp));
+ if (zone.cond == BLK_ZONE_COND_FULL)
+ zone.wp = zone.start + zone.len;
+ else
+ zone.wp = nvme_lba_to_sect(ns, le64_to_cpu(entry->wp));
return cb(&zone, idx, data);
}
size_t data_len = le32_to_cpu(req->cmd->common.dptr.sgl.length);
int ret;
- if (!nvme_is_write(cmd->req.cmd) ||
+ /*
+ * This command has not been processed yet, hence we are trying to
+ * figure out if there is still pending data left to receive. If
+ * we don't, we can simply prepare for the next pdu and bail out,
+ * otherwise we will need to prepare a buffer and receive the
+ * stale data before continuing forward.
+ */
+ if (!nvme_is_write(cmd->req.cmd) || !data_len ||
data_len > cmd->req.port->inline_data_size) {
nvmet_prepare_receive_pdu(queue);
return;
}
EXPORT_SYMBOL_GPL(of_irq_find_parent);
+/*
+ * These interrupt controllers abuse interrupt-map for unspeakable
+ * reasons and rely on the core code to *ignore* it (the drivers do
+ * their own parsing of the property).
+ *
+ * If you think of adding to the list for something *new*, think
+ * again. There is a high chance that you will be sent back to the
+ * drawing board.
+ */
+static const char * const of_irq_imap_abusers[] = {
+ "CBEA,platform-spider-pic",
+ "sti,platform-spider-pic",
+ "realtek,rtl-intc",
+ "fsl,ls1021a-extirq",
+ "fsl,ls1043a-extirq",
+ "fsl,ls1088a-extirq",
+ "renesas,rza1-irqc",
+ NULL,
+};
+
/**
* of_irq_parse_raw - Low level interrupt tree parsing
* @addr: address specifier (start of "reg" property of the device) in be32 format
/*
* Now check if cursor is an interrupt-controller and
* if it is then we are done, unless there is an
- * interrupt-map which takes precedence.
+ * interrupt-map which takes precedence except on one
+ * of these broken platforms that want to parse
+ * interrupt-map themselves for $reason.
*/
bool intc = of_property_read_bool(ipar, "interrupt-controller");
imap = of_get_property(ipar, "interrupt-map", &imaplen);
- if (imap == NULL && intc) {
+ if (intc &&
+ (!imap || of_device_compatible_match(ipar, of_irq_imap_abusers))) {
pr_debug(" -> got it !\n");
return 0;
}
If unsure, say Y if you have an Apple Silicon system.
config PCIE_MT7621
- tristate "MediaTek MT7621 PCIe Controller"
- depends on (RALINK && SOC_MT7621) || (MIPS && COMPILE_TEST)
+ bool "MediaTek MT7621 PCIe Controller"
+ depends on SOC_MT7621 || (MIPS && COMPILE_TEST)
select PHY_MT7621_PCI
default SOC_MT7621
help
#include <linux/platform_device.h>
#include <linux/phy/phy.h>
#include <linux/regulator/consumer.h>
+#include <linux/module.h>
#include "pcie-designware.h"
#include <linux/pm_domain.h>
#include <linux/regmap.h>
#include <linux/reset.h>
+#include <linux/module.h>
#include "pcie-designware.h"
#define PCIE_CORE_DEV_ID_REG 0x0
#define PCIE_CORE_CMD_STATUS_REG 0x4
#define PCIE_CORE_DEV_REV_REG 0x8
-#define PCIE_CORE_EXP_ROM_BAR_REG 0x30
#define PCIE_CORE_PCIEXP_CAP 0xc0
#define PCIE_CORE_ERR_CAPCTL_REG 0x118
#define PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX BIT(5)
*value = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG);
return PCI_BRIDGE_EMUL_HANDLED;
- case PCI_ROM_ADDRESS1:
- *value = advk_readl(pcie, PCIE_CORE_EXP_ROM_BAR_REG);
- return PCI_BRIDGE_EMUL_HANDLED;
-
case PCI_INTERRUPT_LINE: {
/*
* From the whole 32bit register we support reading from HW only
advk_writel(pcie, new, PCIE_CORE_CMD_STATUS_REG);
break;
- case PCI_ROM_ADDRESS1:
- advk_writel(pcie, new, PCIE_CORE_EXP_ROM_BAR_REG);
- break;
-
case PCI_INTERRUPT_LINE:
if (mask & (PCI_BRIDGE_CTL_BUS_RESET << 16)) {
u32 val = advk_readl(pcie, PCIE_CORE_CTRL1_REG);
int ret, i;
reset = gpiod_get_from_of_node(np, "reset-gpios", 0,
- GPIOD_OUT_LOW, "#PERST");
+ GPIOD_OUT_LOW, "PERST#");
if (IS_ERR(reset))
return PTR_ERR(reset);
rmw_set(PORT_APPCLK_EN, port->base + PORT_APPCLK);
+ /* Assert PERST# before setting up the clock */
+ gpiod_set_value(reset, 1);
+
ret = apple_pcie_setup_refclk(pcie, port);
if (ret < 0)
return ret;
+ /* The minimal Tperst-clk value is 100us (PCIe CEM r5.0, 2.9.2) */
+ usleep_range(100, 200);
+
+ /* Deassert PERST# */
rmw_set(PORT_PERST_OFF, port->base + PORT_PERST);
- gpiod_set_value(reset, 1);
+ gpiod_set_value(reset, 0);
+
+ /* Wait for 100ms after PERST# deassertion (PCIe r5.0, 6.6.1) */
+ msleep(100);
ret = readl_relaxed_poll_timeout(port->base + PORT_STATUS, stat,
stat & PORT_STATUS_READY, 100, 250000);
goto out_disable;
}
- /* Ensure that all table entries are masked. */
- msix_mask_all(base, tsize);
-
ret = msix_setup_entries(dev, base, entries, nvec, affd);
if (ret)
goto out_disable;
/* Set MSI-X enabled bits and unmask the function */
pci_intx_for_msi(dev, 0);
dev->msix_enabled = 1;
+
+ /*
+ * Ensure that all table entries are masked to prevent
+ * stale entries from firing in a crash kernel.
+ *
+ * Done late to deal with a broken Marvell NVME device
+ * which takes the MSI-X mask bits into account even
+ * when MSI-X is disabled, which prevents MSI delivery.
+ */
+ msix_mask_all(base, tsize);
pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0);
pcibios_free_irq(dev);
free_msi_irqs(dev);
out_disable:
- pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
+ pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE, 0);
return ret;
}
return PTR_ERR(phy->sysctrl);
phy->pmctrl = syscon_regmap_lookup_by_compatible("hisilicon,hi3670-pmctrl");
- if (IS_ERR(phy->sysctrl))
- return PTR_ERR(phy->sysctrl);
+ if (IS_ERR(phy->pmctrl))
+ return PTR_ERR(phy->pmctrl);
/* clocks */
phy->phy_ref_clk = devm_clk_get(dev, "phy_ref");
* struct mvebu_cp110_utmi - PHY driver data
*
* @regs: PHY registers
- * @syscom: Regmap with system controller registers
+ * @syscon: Regmap with system controller registers
* @dev: device driver handle
- * @caps: PHY capabilities
+ * @ops: phy ops
*/
struct mvebu_cp110_utmi {
void __iomem *regs;
};
/**
- * Write register and read back masked value to confirm it is written
+ * usb_phy_write_readback() - Write register and read back masked value to
+ * confirm it is written
*
- * @base - QCOM DWC3 PHY base virtual address.
- * @offset - register offset.
- * @mask - register bitmask specifying what should be updated
- * @val - value to write.
+ * @phy_dwc3: QCOM DWC3 phy context
+ * @offset: register offset.
+ * @mask: register bitmask specifying what should be updated
+ * @val: value to write.
*/
static inline void usb_phy_write_readback(struct usb_phy *phy_dwc3,
u32 offset,
}
/**
- * Write SSPHY register
+ * usb_ss_write_phycreg() - Write SSPHY register
*
- * @base - QCOM DWC3 PHY base virtual address.
- * @addr - SSPHY address to write.
- * @val - value to write.
+ * @phy_dwc3: QCOM DWC3 phy context
+ * @addr: SSPHY address to write.
+ * @val: value to write.
*/
static int usb_ss_write_phycreg(struct usb_phy *phy_dwc3,
u32 addr, u32 val)
}
/**
- * Read SSPHY register.
+ * usb_ss_read_phycreg() - Read SSPHY register.
*
- * @base - QCOM DWC3 PHY base virtual address.
- * @addr - SSPHY address to read.
+ * @phy_dwc3: QCOM DWC3 phy context
+ * @addr: SSPHY address to read.
+ * @val: pointer in which read is store.
*/
static int usb_ss_read_phycreg(struct usb_phy *phy_dwc3,
u32 addr, u32 *val)
* @qmp: QMP phy to which this lane belongs
* @lane_rst: lane's reset controller
* @mode: current PHY mode
+ * @dp_aux_cfg: Display port aux config
+ * @dp_opts: Display port optional config
+ * @dp_clks: Display port clocks
*/
struct qmp_phy {
struct phy *phy;
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* Copyright (C) 2016 Linaro Ltd
*/
#include <linux/module.h>
if (!of_property_read_bool(np, "st,no-lsfs-fb-cap"))
usbphyc_phy->tune |= LFSCAPEN;
- if (of_property_read_bool(np, "st,slow-hs-slew-rate"))
+ if (of_property_read_bool(np, "st,decrease-hs-slew-rate"))
usbphyc_phy->tune |= HSDRVSLEW;
ret = of_property_read_u32(np, "st,tune-hs-dc-level", &val);
// SPDX-License-Identifier: GPL-2.0
-/**
+/*
* PCIe SERDES driver for AM654x SoC
*
* Copyright (C) 2018 - 2019 Texas Instruments Incorporated - http://www.ti.com/
// SPDX-License-Identifier: GPL-2.0
-/**
+/*
* Wrapper driver for SERDES used in J721E
*
* Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com/
}
/**
- * omap_usb2_set_comparator - links the comparator present in the system with
- * this phy
- * @comparator - the companion phy(comparator) for this phy
+ * omap_usb2_set_comparator() - links the comparator present in the system with this phy
+ *
+ * @comparator: the companion phy(comparator) for this phy
*
* The phy companion driver should call this API passing the phy_companion
* filled with set_vbus and start_srp to be used by usb phy.
// SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
* tusb1210.c - TUSB1210 USB ULPI PHY driver
*
* Copyright (C) 2015 Intel Corporation
#define AMD_CPU_ID_CZN AMD_CPU_ID_RN
#define AMD_CPU_ID_YC 0x14B5
-#define PMC_MSG_DELAY_MIN_US 100
+#define PMC_MSG_DELAY_MIN_US 50
#define RESPONSE_REGISTER_LOOP_MAX 20000
#define SOC_SUBSYSTEM_IP_MAX 12
DMI_MATCH(DMI_PRODUCT_FAMILY, "ThinkPad X1 Tablet Gen 2"),
},
},
+ {
+ .ident = "Microsoft Surface Go 3",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Surface Go 3"),
+ },
+ },
{ }
};
if (product && strlen(product) > 4)
switch (product[4]) {
case '5':
+ if (strlen(product) > 5)
+ switch (product[5]) {
+ case 'N':
+ year = 2021;
+ break;
+ case '0':
+ year = 2016;
+ break;
+ default:
+ year = 2022;
+ }
+ break;
case '6':
year = 2016;
break;
&dev_attr_hotkey_all_mask.attr,
&dev_attr_hotkey_adaptive_all_mask.attr,
&dev_attr_hotkey_recommended_mask.attr,
+ &dev_attr_hotkey_tablet_mode.attr,
+ &dev_attr_hotkey_radio_sw.attr,
#ifdef CONFIG_THINKPAD_ACPI_HOTKEY_POLL
&dev_attr_hotkey_source_mask.attr,
&dev_attr_hotkey_poll_freq.attr,
"tpacpi::standby",
"tpacpi::dock_status1",
"tpacpi::dock_status2",
- "tpacpi::unknown_led2",
+ "tpacpi::lid_logo_dot",
"tpacpi::unknown_led3",
"tpacpi::thinkvantage",
};
-#define TPACPI_SAFE_LEDS 0x1081U
+#define TPACPI_SAFE_LEDS 0x1481U
static inline bool tpacpi_is_led_restricted(const unsigned int led)
{
.properties = trekstor_primetab_t13b_props,
};
+static const struct property_entry trekstor_surftab_duo_w1_props[] = {
+ PROPERTY_ENTRY_BOOL("touchscreen-inverted-x"),
+ { }
+};
+
+static const struct ts_dmi_data trekstor_surftab_duo_w1_data = {
+ .acpi_name = "GDIX1001:00",
+ .properties = trekstor_surftab_duo_w1_props,
+};
+
static const struct property_entry trekstor_surftab_twin_10_1_props[] = {
PROPERTY_ENTRY_U32("touchscreen-min-x", 20),
PROPERTY_ENTRY_U32("touchscreen-min-y", 0),
},
},
{
+ /* TrekStor SurfTab duo W1 10.1 ST10432-10b */
+ .driver_data = (void *)&trekstor_surftab_duo_w1_data,
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "TrekStor"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "SurfTab duo W1 10.1 (VT4)"),
+ },
+ },
+ {
/* TrekStor SurfTab twin 10.1 ST10432-8 */
.driver_data = (void *)&trekstor_surftab_twin_10_1_data,
.matches = {
struct tegra_bpmp *bpmp = to_tegra_bpmp(rstc);
struct mrq_reset_request request;
struct tegra_bpmp_message msg;
- int err;
memset(&request, 0, sizeof(request));
request.cmd = command;
msg.tx.data = &request;
msg.tx.size = sizeof(request);
- err = tegra_bpmp_transfer(bpmp, &msg);
- if (err)
- return err;
- if (msg.rx.ret)
- return -EINVAL;
-
- return 0;
+ return tegra_bpmp_transfer(bpmp, &msg);
}
static int tegra_bpmp_reset_module(struct reset_controller_dev *rstc,
if (rc) {
pm8001_dbg(pm8001_ha, FAIL,
"pm8001_setup_irq failed [ret: %d]\n", rc);
- goto err_out_shost;
+ goto err_out;
}
/* Request Interrupt */
rc = pm8001_request_irq(pm8001_ha);
if (rc)
- goto err_out_shost;
+ goto err_out;
count = pm8001_ha->max_q_num;
/* Queues are chosen based on the number of cores/msix availability */
pm8001_tag_init(pm8001_ha);
return 0;
-err_out_shost:
- scsi_remove_host(pm8001_ha->shost);
err_out_nodev:
for (i = 0; i < pm8001_ha->max_memcnt; i++) {
if (pm8001_ha->memoryMap.region[i].virt_ptr != NULL) {
struct smp_completion_resp *psmpPayload;
struct task_status_struct *ts;
struct pm8001_device *pm8001_dev;
- char *pdma_respaddr = NULL;
psmpPayload = (struct smp_completion_resp *)(piomb + 4);
status = le32_to_cpu(psmpPayload->status);
if (pm8001_dev)
atomic_dec(&pm8001_dev->running_req);
if (pm8001_ha->smp_exp_mode == SMP_DIRECT) {
+ struct scatterlist *sg_resp = &t->smp_task.smp_resp;
+ u8 *payload;
+ void *to;
+
pm8001_dbg(pm8001_ha, IO,
"DIRECT RESPONSE Length:%d\n",
param);
- pdma_respaddr = (char *)(phys_to_virt(cpu_to_le64
- ((u64)sg_dma_address
- (&t->smp_task.smp_resp))));
+ to = kmap_atomic(sg_page(sg_resp));
+ payload = to + sg_resp->offset;
for (i = 0; i < param; i++) {
- *(pdma_respaddr+i) = psmpPayload->_r_a[i];
+ *(payload + i) = psmpPayload->_r_a[i];
pm8001_dbg(pm8001_ha, IO,
"SMP Byte%d DMA data 0x%x psmp 0x%x\n",
- i, *(pdma_respaddr + i),
+ i, *(payload + i),
psmpPayload->_r_a[i]);
}
+ kunmap_atomic(to);
}
break;
case IO_ABORTED:
struct sas_task *task = ccb->task;
struct domain_device *dev = task->dev;
struct pm8001_device *pm8001_dev = dev->lldd_dev;
- struct scatterlist *sg_req, *sg_resp;
+ struct scatterlist *sg_req, *sg_resp, *smp_req;
u32 req_len, resp_len;
struct smp_req smp_cmd;
u32 opc;
struct inbound_queue_table *circularQ;
- char *preq_dma_addr = NULL;
- __le64 tmp_addr;
u32 i, length;
+ u8 *payload;
+ u8 *to;
memset(&smp_cmd, 0, sizeof(smp_cmd));
/*
pm8001_ha->smp_exp_mode = SMP_INDIRECT;
- tmp_addr = cpu_to_le64((u64)sg_dma_address(&task->smp_task.smp_req));
- preq_dma_addr = (char *)phys_to_virt(tmp_addr);
+ smp_req = &task->smp_task.smp_req;
+ to = kmap_atomic(sg_page(smp_req));
+ payload = to + smp_req->offset;
/* INDIRECT MODE command settings. Use DMA */
if (pm8001_ha->smp_exp_mode == SMP_INDIRECT) {
/* for SPCv indirect mode. Place the top 4 bytes of
* SMP Request header here. */
for (i = 0; i < 4; i++)
- smp_cmd.smp_req16[i] = *(preq_dma_addr + i);
+ smp_cmd.smp_req16[i] = *(payload + i);
/* exclude top 4 bytes for SMP req header */
smp_cmd.long_smp_req.long_req_addr =
cpu_to_le64((u64)sg_dma_address
pm8001_dbg(pm8001_ha, IO, "SMP REQUEST DIRECT MODE\n");
for (i = 0; i < length; i++)
if (i < 16) {
- smp_cmd.smp_req16[i] = *(preq_dma_addr+i);
+ smp_cmd.smp_req16[i] = *(payload + i);
pm8001_dbg(pm8001_ha, IO,
"Byte[%d]:%x (DMA data:%x)\n",
i, smp_cmd.smp_req16[i],
- *(preq_dma_addr));
+ *(payload));
} else {
- smp_cmd.smp_req[i] = *(preq_dma_addr+i);
+ smp_cmd.smp_req[i] = *(payload + i);
pm8001_dbg(pm8001_ha, IO,
"Byte[%d]:%x (DMA data:%x)\n",
i, smp_cmd.smp_req[i],
- *(preq_dma_addr));
+ *(payload));
}
}
-
+ kunmap_atomic(to);
build_smp_cmd(pm8001_dev->device_id, smp_cmd.tag,
&smp_cmd, pm8001_ha->smp_exp_mode, length);
rc = pm8001_mpi_build_cmd(pm8001_ha, circularQ, opc, &smp_cmd,
{
struct qedi_work_map *work, *work_tmp;
u32 proto_itt = cqe->itid;
- itt_t protoitt = 0;
int found = 0;
struct qedi_cmd *qedi_cmd = NULL;
u32 iscsi_cid;
return;
check_cleanup_reqs:
- if (qedi_conn->cmd_cleanup_req > 0) {
- QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_TID,
+ if (atomic_inc_return(&qedi_conn->cmd_cleanup_cmpl) ==
+ qedi_conn->cmd_cleanup_req) {
+ QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
"Freeing tid=0x%x for cid=0x%x\n",
cqe->itid, qedi_conn->iscsi_conn_id);
- qedi_conn->cmd_cleanup_cmpl++;
wake_up(&qedi_conn->wait_queue);
- } else {
- QEDI_ERR(&qedi->dbg_ctx,
- "Delayed or untracked cleanup response, itt=0x%x, tid=0x%x, cid=0x%x\n",
- protoitt, cqe->itid, qedi_conn->iscsi_conn_id);
}
}
}
qedi_conn->cmd_cleanup_req = 0;
- qedi_conn->cmd_cleanup_cmpl = 0;
+ atomic_set(&qedi_conn->cmd_cleanup_cmpl, 0);
QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
"active_cmd_count=%d, cid=0x%x, in_recovery=%d, lun_reset=%d\n",
qedi_conn->iscsi_conn_id);
rval = wait_event_interruptible_timeout(qedi_conn->wait_queue,
- ((qedi_conn->cmd_cleanup_req ==
- qedi_conn->cmd_cleanup_cmpl) ||
- test_bit(QEDI_IN_RECOVERY,
- &qedi->flags)),
- 5 * HZ);
+ (qedi_conn->cmd_cleanup_req ==
+ atomic_read(&qedi_conn->cmd_cleanup_cmpl)) ||
+ test_bit(QEDI_IN_RECOVERY, &qedi->flags),
+ 5 * HZ);
if (rval) {
QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
"i/o cmd_cleanup_req=%d, equal to cmd_cleanup_cmpl=%d, cid=0x%x\n",
qedi_conn->cmd_cleanup_req,
- qedi_conn->cmd_cleanup_cmpl,
+ atomic_read(&qedi_conn->cmd_cleanup_cmpl),
qedi_conn->iscsi_conn_id);
return 0;
QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_SCSI_TM,
"i/o cmd_cleanup_req=%d, not equal to cmd_cleanup_cmpl=%d, cid=0x%x\n",
qedi_conn->cmd_cleanup_req,
- qedi_conn->cmd_cleanup_cmpl,
+ atomic_read(&qedi_conn->cmd_cleanup_cmpl),
qedi_conn->iscsi_conn_id);
iscsi_host_for_each_session(qedi->shost,
/* Enable IOs for all other sessions except current.*/
if (!wait_event_interruptible_timeout(qedi_conn->wait_queue,
- (qedi_conn->cmd_cleanup_req ==
- qedi_conn->cmd_cleanup_cmpl) ||
- test_bit(QEDI_IN_RECOVERY,
- &qedi->flags),
- 5 * HZ)) {
+ (qedi_conn->cmd_cleanup_req ==
+ atomic_read(&qedi_conn->cmd_cleanup_cmpl)) ||
+ test_bit(QEDI_IN_RECOVERY, &qedi->flags),
+ 5 * HZ)) {
iscsi_host_for_each_session(qedi->shost,
qedi_mark_device_available);
return -1;
qedi_ep = qedi_conn->ep;
qedi_conn->cmd_cleanup_req = 0;
- qedi_conn->cmd_cleanup_cmpl = 0;
+ atomic_set(&qedi_conn->cmd_cleanup_cmpl, 0);
if (!qedi_ep) {
QEDI_WARN(&qedi->dbg_ctx,
qedi_conn->iscsi_conn_id = qedi_ep->iscsi_cid;
qedi_conn->fw_cid = qedi_ep->fw_cid;
qedi_conn->cmd_cleanup_req = 0;
- qedi_conn->cmd_cleanup_cmpl = 0;
+ atomic_set(&qedi_conn->cmd_cleanup_cmpl, 0);
if (qedi_bind_conn_to_iscsi_cid(qedi, qedi_conn)) {
rc = -EINVAL;
spinlock_t list_lock; /* internal conn lock */
u32 active_cmd_count;
u32 cmd_cleanup_req;
- u32 cmd_cleanup_cmpl;
+ atomic_t cmd_cleanup_cmpl;
u32 iscsi_conn_id;
int itt;
struct va_format vaf;
char pbuf[64];
+ if (!ql_mask_match(level) && !trace_ql_dbg_log_enabled())
+ return;
+
va_start(va, fmt);
vaf.fmt = fmt;
rep_max_zones = min((alloc_len - 64) >> ilog2(RZONES_DESC_HD),
max_zones);
- arr = kcalloc(RZONES_DESC_HD, alloc_len, GFP_ATOMIC);
+ arr = kzalloc(alloc_len, GFP_ATOMIC);
if (!arr) {
mk_sense_buffer(scp, ILLEGAL_REQUEST, INSUFF_RES_ASC,
INSUFF_RES_ASCQ);
#define BLK_SFT_RSTN 0x0
#define BLK_CLK_EN 0x4
+#define BLK_MIPI_RESET_DIV 0x8 /* Mini/Nano DISPLAY_BLK_CTRL only */
struct imx8m_blk_ctrl_domain;
const char *gpc_name;
u32 rst_mask;
u32 clk_mask;
+
+ /*
+ * i.MX8M Mini and Nano have a third DISPLAY_BLK_CTRL register
+ * which is used to control the reset for the MIPI Phy.
+ * Since it's only present in certain circumstances,
+ * an if-statement should be used before setting and clearing this
+ * register.
+ */
+ u32 mipi_phy_rst_mask;
};
#define DOMAIN_MAX_CLKS 3
/* put devices into reset */
regmap_clear_bits(bc->regmap, BLK_SFT_RSTN, data->rst_mask);
+ if (data->mipi_phy_rst_mask)
+ regmap_clear_bits(bc->regmap, BLK_MIPI_RESET_DIV, data->mipi_phy_rst_mask);
/* enable upstream and blk-ctrl clocks to allow reset to propagate */
ret = clk_bulk_prepare_enable(data->num_clks, domain->clks);
/* release reset */
regmap_set_bits(bc->regmap, BLK_SFT_RSTN, data->rst_mask);
+ if (data->mipi_phy_rst_mask)
+ regmap_set_bits(bc->regmap, BLK_MIPI_RESET_DIV, data->mipi_phy_rst_mask);
/* disable upstream clocks */
clk_bulk_disable_unprepare(data->num_clks, domain->clks);
struct imx8m_blk_ctrl *bc = domain->bc;
/* put devices into reset and disable clocks */
+ if (data->mipi_phy_rst_mask)
+ regmap_clear_bits(bc->regmap, BLK_MIPI_RESET_DIV, data->mipi_phy_rst_mask);
+
regmap_clear_bits(bc->regmap, BLK_SFT_RSTN, data->rst_mask);
regmap_clear_bits(bc->regmap, BLK_CLK_EN, data->clk_mask);
.gpc_name = "mipi-dsi",
.rst_mask = BIT(5),
.clk_mask = BIT(8) | BIT(9),
+ .mipi_phy_rst_mask = BIT(17),
},
[IMX8MM_DISPBLK_PD_MIPI_CSI] = {
.name = "dispblk-mipi-csi",
.gpc_name = "mipi-csi",
.rst_mask = BIT(3) | BIT(4),
.clk_mask = BIT(10) | BIT(11),
+ .mipi_phy_rst_mask = BIT(16),
},
};
int ret;
int i;
+ /* Return early if this is running on devices with different SoCs */
+ if (!__mxc_cpu_type)
+ return 0;
+
if (of_machine_is_compatible("fsl,ls1021a"))
return 0;
};
builtin_platform_driver(tegra_fuse_driver);
-bool __init tegra_fuse_read_spare(unsigned int spare)
+u32 __init tegra_fuse_read_spare(unsigned int spare)
{
unsigned int offset = fuse->soc->info->spare + spare * 4;
void tegra_init_revision(void);
void tegra_init_apbmisc(void);
-bool __init tegra_fuse_read_spare(unsigned int spare);
+u32 __init tegra_fuse_read_spare(unsigned int spare);
u32 __init tegra_fuse_read_early(unsigned int offset);
u8 tegra_get_major_rev(void);
*ta_size = roundup(fw->size, PAGE_SIZE);
*ta = (void *)__get_free_pages(GFP_KERNEL, get_order(*ta_size));
- if (IS_ERR(*ta)) {
- pr_err("%s: get_free_pages failed 0x%llx\n", __func__,
- (u64)*ta);
+ if (!*ta) {
+ pr_err("%s: get_free_pages failed\n", __func__);
rc = -ENOMEM;
goto rel_fw;
}
};
static const struct mmio_reg tgl_fivr_mmio_regs[] = {
- { 0, 0x5A18, 3, 0x7, 12}, /* vco_ref_code_lo */
+ { 0, 0x5A18, 3, 0x7, 11}, /* vco_ref_code_lo */
{ 0, 0x5A18, 8, 0xFF, 16}, /* vco_ref_code_hi */
{ 0, 0x5A08, 8, 0xFF, 0}, /* spread_spectrum_pct */
{ 0, 0x5A08, 1, 0x1, 8}, /* spread_spectrum_clk_enable */
struct n_hdlc_buf_list rx_buf_list;
struct n_hdlc_buf_list tx_free_buf_list;
struct n_hdlc_buf_list rx_free_buf_list;
+ struct work_struct write_work;
+ struct tty_struct *tty_for_write_work;
};
/*
/* Local functions */
static struct n_hdlc *n_hdlc_alloc(void);
+static void n_hdlc_tty_write_work(struct work_struct *work);
/* max frame size for memory allocations */
static int maxframe = 4096;
wake_up_interruptible(&tty->read_wait);
wake_up_interruptible(&tty->write_wait);
+ cancel_work_sync(&n_hdlc->write_work);
+
n_hdlc_free_buf_list(&n_hdlc->rx_free_buf_list);
n_hdlc_free_buf_list(&n_hdlc->tx_free_buf_list);
n_hdlc_free_buf_list(&n_hdlc->rx_buf_list);
return -ENFILE;
}
+ INIT_WORK(&n_hdlc->write_work, n_hdlc_tty_write_work);
+ n_hdlc->tty_for_write_work = tty;
tty->disc_data = n_hdlc;
tty->receive_room = 65536;
} /* end of n_hdlc_send_frames() */
/**
+ * n_hdlc_tty_write_work - Asynchronous callback for transmit wakeup
+ * @work: pointer to work_struct
+ *
+ * Called when low level device driver can accept more send data.
+ */
+static void n_hdlc_tty_write_work(struct work_struct *work)
+{
+ struct n_hdlc *n_hdlc = container_of(work, struct n_hdlc, write_work);
+ struct tty_struct *tty = n_hdlc->tty_for_write_work;
+
+ n_hdlc_send_frames(n_hdlc, tty);
+} /* end of n_hdlc_tty_write_work() */
+
+/**
* n_hdlc_tty_wakeup - Callback for transmit wakeup
* @tty: pointer to associated tty instance data
*
{
struct n_hdlc *n_hdlc = tty->disc_data;
- n_hdlc_send_frames(n_hdlc, tty);
+ schedule_work(&n_hdlc->write_work);
} /* end of n_hdlc_tty_wakeup() */
/**
}
}
-static void fintek_8250_goto_highspeed(struct uart_8250_port *uart,
- struct fintek_8250 *pdata)
-{
- sio_write_reg(pdata, LDN, pdata->index);
-
- switch (pdata->pid) {
- case CHIP_ID_F81966:
- case CHIP_ID_F81866: /* set uart clock for high speed serial mode */
- sio_write_mask_reg(pdata, F81866_UART_CLK,
- F81866_UART_CLK_MASK,
- F81866_UART_CLK_14_769MHZ);
-
- uart->port.uartclk = 921600 * 16;
- break;
- default: /* leave clock speed untouched */
- break;
- }
-}
-
static void fintek_8250_set_termios(struct uart_port *port,
struct ktermios *termios,
struct ktermios *old)
fintek_8250_set_irq_mode(pdata, level_mode);
fintek_8250_set_max_fifo(pdata);
- fintek_8250_goto_highspeed(uart, pdata);
fintek_8250_exit_key(addr[i]);
{
struct cdnsp_device *pdev = gadget_to_cdnsp(gadget);
struct cdns *cdns = dev_get_drvdata(pdev->dev);
+ unsigned long flags;
trace_cdnsp_pullup(is_on);
+ /*
+ * Disable events handling while controller is being
+ * enabled/disabled.
+ */
+ disable_irq(cdns->dev_irq);
+ spin_lock_irqsave(&pdev->lock, flags);
+
if (!is_on) {
cdnsp_reset_device(pdev);
cdns_clear_vbus(cdns);
} else {
cdns_set_vbus(cdns);
}
+
+ spin_unlock_irqrestore(&pdev->lock, flags);
+ enable_irq(cdns->dev_irq);
+
return 0;
}
return;
}
+ *status = 0;
+
cdnsp_finish_td(pdev, td, event, pep, status);
}
spin_lock_irqsave(&pdev->lock, flags);
if (pdev->cdnsp_state & (CDNSP_STATE_HALTED | CDNSP_STATE_DYING)) {
- cdnsp_died(pdev);
+ /*
+ * While removing or stopping driver there may still be deferred
+ * not handled interrupt which should not be treated as error.
+ * Driver should simply ignore it.
+ */
+ if (pdev->gadget_driver)
+ cdnsp_died(pdev);
+
spin_unlock_irqrestore(&pdev->lock, flags);
return IRQ_HANDLED;
}
__entry->first_prime_det = pep->stream_info.first_prime_det;
__entry->drbls_count = pep->stream_info.drbls_count;
),
- TP_printk("%s: SID: %08x ep state: %x stream: enabled: %d num %d "
+ TP_printk("%s: SID: %08x, ep state: %x, stream: enabled: %d num %d "
"tds %d, first prime: %d drbls %d",
- __get_str(name), __entry->state, __entry->stream_id,
+ __get_str(name), __entry->stream_id, __entry->state,
__entry->enabled, __entry->num_streams, __entry->td_count,
__entry->first_prime_det, __entry->drbls_count)
);
*/
#include <linux/platform_device.h>
+#include <linux/slab.h>
#include "core.h"
#include "drd.h"
#include "host-export.h"
* the USB-2 spec requires such endpoints to have wMaxPacketSize = 0
* (see the end of section 5.6.3), so don't warn about them.
*/
- maxp = usb_endpoint_maxp(&endpoint->desc);
+ maxp = le16_to_cpu(endpoint->desc.wMaxPacketSize);
if (maxp == 0 && !(usb_endpoint_xfer_isoc(d) && asnum == 0)) {
dev_warn(ddev, "config %d interface %d altsetting %d endpoint 0x%X has invalid wMaxPacketSize 0\n",
cfgno, inum, asnum, d->bEndpointAddress);
maxpacket_maxes = full_speed_maxpacket_maxes;
break;
case USB_SPEED_HIGH:
- /* Bits 12..11 are allowed only for HS periodic endpoints */
+ /* Multiple-transactions bits are allowed only for HS periodic endpoints */
if (usb_endpoint_xfer_int(d) || usb_endpoint_xfer_isoc(d)) {
- i = maxp & (BIT(12) | BIT(11));
+ i = maxp & USB_EP_MAXP_MULT_MASK;
maxp &= ~i;
}
fallthrough;
{ USB_DEVICE(0x1532, 0x0116), .driver_info =
USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL },
+ /* Lenovo USB-C to Ethernet Adapter RTL8153-04 */
+ { USB_DEVICE(0x17ef, 0x720c), .driver_info = USB_QUIRK_NO_LPM },
+
/* Lenovo Powered USB-C Travel Hub (4X90S92381, RTL8153 GigE) */
{ USB_DEVICE(0x17ef, 0x721e), .driver_info = USB_QUIRK_NO_LPM },
ggpio |= GGPIO_STM32_OTG_GCCFG_IDEN;
ggpio |= GGPIO_STM32_OTG_GCCFG_VBDEN;
dwc2_writel(hsotg, ggpio, GGPIO);
+
+ /* ID/VBUS detection startup time */
+ usleep_range(5000, 7000);
}
retval = dwc2_drd_init(hsotg);
struct dwc3_qcom *qcom = platform_get_drvdata(pdev);
struct device_node *np = pdev->dev.of_node, *dwc3_np;
struct device *dev = &pdev->dev;
- struct property *prop;
int ret;
dwc3_np = of_get_compatible_child(np, "snps,dwc3");
return -ENODEV;
}
- prop = devm_kzalloc(dev, sizeof(*prop), GFP_KERNEL);
- if (!prop) {
- ret = -ENOMEM;
- dev_err(dev, "unable to allocate memory for property\n");
- goto node_put;
- }
-
- prop->name = "tx-fifo-resize";
- ret = of_add_property(dwc3_np, prop);
- if (ret) {
- dev_err(dev, "unable to add property\n");
- goto node_put;
- }
-
ret = of_platform_populate(np, NULL, NULL, dev);
if (ret) {
dev_err(dev, "failed to register dwc3 core - %d\n", ret);
#include <linux/pci_ids.h>
#include <linux/memblock.h>
#include <linux/io.h>
-#include <linux/iopoll.h>
#include <asm/pci-direct.h>
#include <asm/fixmap.h>
#include <linux/bcd.h>
{
u32 result;
- return readl_poll_timeout_atomic(ptr, result,
- ((result & mask) == done),
- delay, wait);
+ /* Can not use readl_poll_timeout_atomic() for early boot things */
+ do {
+ result = readl(ptr);
+ result &= mask;
+ if (result == done)
+ return 0;
+ udelay(delay);
+ wait -= delay;
+ } while (wait > 0);
+
+ return -ETIMEDOUT;
}
static void __init xdbc_bios_handoff(void)
struct usb_function *f = NULL;
u8 endp;
+ if (w_length > USB_COMP_EP0_BUFSIZ) {
+ if (ctrl->bRequestType & USB_DIR_IN) {
+ /* Cast away the const, we are going to overwrite on purpose. */
+ __le16 *temp = (__le16 *)&ctrl->wLength;
+
+ *temp = cpu_to_le16(USB_COMP_EP0_BUFSIZ);
+ w_length = USB_COMP_EP0_BUFSIZ;
+ } else {
+ goto done;
+ }
+ }
+
/* partial re-init of the response message; the function or the
* gadget might need to intercept e.g. a control-OUT completion
* when we delegate to it.
if (!cdev->req)
return -ENOMEM;
- cdev->req->buf = kmalloc(USB_COMP_EP0_BUFSIZ, GFP_KERNEL);
+ cdev->req->buf = kzalloc(USB_COMP_EP0_BUFSIZ, GFP_KERNEL);
if (!cdev->req->buf)
goto fail;
#include <linux/etherdevice.h>
#include <linux/ethtool.h>
#include <linux/if_vlan.h>
+#include <linux/etherdevice.h>
#include "u_ether.h"
{
struct eth_dev *dev;
struct usb_gadget *g;
- struct sockaddr sa;
int status;
if (!net->dev.parent)
return -EINVAL;
dev = netdev_priv(net);
g = dev->gadget;
+
+ net->addr_assign_type = NET_ADDR_RANDOM;
+ eth_hw_addr_set(net, dev->dev_mac);
+
status = register_netdev(net);
if (status < 0) {
dev_dbg(&g->dev, "register_netdev failed, %d\n", status);
return status;
} else {
INFO(dev, "HOST MAC %pM\n", dev->host_mac);
+ INFO(dev, "MAC %pM\n", dev->dev_mac);
/* two kinds of host-initiated state changes:
* - iff DATA transfer is active, carrier is "on"
*/
netif_carrier_off(net);
}
- sa.sa_family = net->type;
- memcpy(sa.sa_data, dev->dev_mac, ETH_ALEN);
- rtnl_lock();
- status = dev_set_mac_address(net, &sa, NULL);
- rtnl_unlock();
- if (status)
- pr_warn("cannot set self ethernet address: %d\n", status);
- else
- INFO(dev, "MAC %pM\n", dev->dev_mac);
return status;
}
goto fail_1;
}
- req->buf = kmalloc(DBGP_REQ_LEN, GFP_KERNEL);
+ req->buf = kzalloc(DBGP_REQ_LEN, GFP_KERNEL);
if (!req->buf) {
err = -ENOMEM;
stp = 2;
void *data = NULL;
u16 len = 0;
+ if (length > DBGP_REQ_LEN) {
+ if (ctrl->bRequestType & USB_DIR_IN) {
+ /* Cast away the const, we are going to overwrite on purpose. */
+ __le16 *temp = (__le16 *)&ctrl->wLength;
+
+ *temp = cpu_to_le16(DBGP_REQ_LEN);
+ length = DBGP_REQ_LEN;
+ } else {
+ return err;
+ }
+ }
+
+
if (request == USB_REQ_GET_DESCRIPTOR) {
switch (value>>8) {
case USB_DT_DEVICE:
/* enough for the whole queue: most events invalidate others */
#define N_EVENT 5
+#define RBUF_SIZE 256
+
struct dev_data {
spinlock_t lock;
refcount_t count;
struct dentry *dentry;
/* except this scratch i/o buffer for ep0 */
- u8 rbuf [256];
+ u8 rbuf[RBUF_SIZE];
};
static inline void get_dev (struct dev_data *data)
u16 w_value = le16_to_cpu(ctrl->wValue);
u16 w_length = le16_to_cpu(ctrl->wLength);
+ if (w_length > RBUF_SIZE) {
+ if (ctrl->bRequestType & USB_DIR_IN) {
+ /* Cast away the const, we are going to overwrite on purpose. */
+ __le16 *temp = (__le16 *)&ctrl->wLength;
+
+ *temp = cpu_to_le16(RBUF_SIZE);
+ w_length = RBUF_SIZE;
+ } else {
+ return value;
+ }
+ }
+
spin_lock (&dev->lock);
dev->setup_abort = 0;
if (dev->state == STATE_DEV_UNCONNECTED) {
continue;
retval = xhci_disable_slot(xhci, i);
+ xhci_free_virt_device(xhci, i);
if (retval)
xhci_err(xhci, "Failed to disable slot %d, %d. Enter test mode anyway\n",
i, retval);
ret = xhci_check_bandwidth(hcd, udev);
if (!ret)
- INIT_LIST_HEAD(&mtk->bw_ep_chk_list);
+ list_del_init(&mtk->bw_ep_chk_list);
return ret;
}
#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_4 0x161e
#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_5 0x15d6
#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_6 0x15d7
+#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_7 0x161c
+#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_8 0x161f
#define PCI_DEVICE_ID_ASMEDIA_1042_XHCI 0x1042
#define PCI_DEVICE_ID_ASMEDIA_1042A_XHCI 0x1142
pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_3 ||
pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_4 ||
pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_5 ||
- pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_6))
+ pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_6 ||
+ pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_7 ||
+ pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_8))
xhci->quirks |= XHCI_DEFAULT_PM_RUNTIME_ALLOW;
if (xhci->quirks & XHCI_RESET_ON_RESUME)
if (xhci->quirks & XHCI_EP_LIMIT_QUIRK)
/* Delete default control endpoint resources */
xhci_free_device_endpoint_resources(xhci, virt_dev, true);
- xhci_free_virt_device(xhci, slot_id);
}
static void xhci_handle_cmd_config_ep(struct xhci_hcd *xhci, int slot_id,
struct xhci_slot_ctx *slot_ctx;
int i, ret;
-#ifndef CONFIG_USB_DEFAULT_PERSIST
/*
* We called pm_runtime_get_noresume when the device was attached.
* Decrement the counter here to allow controller to runtime suspend
*/
if (xhci->quirks & XHCI_RESET_ON_RESUME)
pm_runtime_put_noidle(hcd->self.controller);
-#endif
ret = xhci_check_args(hcd, udev, NULL, 0, true, __func__);
/* If the host is halted due to driver unload, we still need to free the
del_timer_sync(&virt_dev->eps[i].stop_cmd_timer);
}
virt_dev->udev = NULL;
- ret = xhci_disable_slot(xhci, udev->slot_id);
- if (ret)
- xhci_free_virt_device(xhci, udev->slot_id);
+ xhci_disable_slot(xhci, udev->slot_id);
+ xhci_free_virt_device(xhci, udev->slot_id);
}
int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id)
u32 state;
int ret = 0;
- command = xhci_alloc_command(xhci, false, GFP_KERNEL);
+ command = xhci_alloc_command(xhci, true, GFP_KERNEL);
if (!command)
return -ENOMEM;
}
xhci_ring_cmd_db(xhci);
spin_unlock_irqrestore(&xhci->lock, flags);
+
+ wait_for_completion(command->completion);
+
+ if (command->status != COMP_SUCCESS)
+ xhci_warn(xhci, "Unsuccessful disable slot %u command, status %d\n",
+ slot_id, command->status);
+
+ xhci_free_command(xhci, command);
+
return ret;
}
xhci_debugfs_create_slot(xhci, slot_id);
-#ifndef CONFIG_USB_DEFAULT_PERSIST
/*
* If resetting upon resume, we can't put the controller into runtime
* suspend if there is a device attached.
*/
if (xhci->quirks & XHCI_RESET_ON_RESUME)
pm_runtime_get_noresume(hcd->self.controller);
-#endif
/* Is this a LS or FS device under a HS hub? */
/* Hub or peripherial? */
return 1;
disable_slot:
- ret = xhci_disable_slot(xhci, udev->slot_id);
- if (ret)
- xhci_free_virt_device(xhci, udev->slot_id);
+ xhci_disable_slot(xhci, udev->slot_id);
+ xhci_free_virt_device(xhci, udev->slot_id);
return 0;
}
mutex_unlock(&xhci->mutex);
ret = xhci_disable_slot(xhci, udev->slot_id);
+ xhci_free_virt_device(xhci, udev->slot_id);
if (!ret)
xhci_alloc_dev(hcd, udev);
kfree(command->completion);
/* 2 banks of GPIO - One for the pins taken from each serial port */
if (intf_num == 0) {
+ priv->gc.ngpio = 2;
+
if (mode.eci == CP210X_PIN_MODE_MODEM) {
/* mark all GPIOs of this interface as reserved */
priv->gpio_altfunc = 0xff;
priv->gpio_pushpull = (u8)((le16_to_cpu(config.gpio_mode) &
CP210X_ECI_GPIO_MODE_MASK) >>
CP210X_ECI_GPIO_MODE_OFFSET);
- priv->gc.ngpio = 2;
} else if (intf_num == 1) {
+ priv->gc.ngpio = 3;
+
if (mode.sci == CP210X_PIN_MODE_MODEM) {
/* mark all GPIOs of this interface as reserved */
priv->gpio_altfunc = 0xff;
priv->gpio_pushpull = (u8)((le16_to_cpu(config.gpio_mode) &
CP210X_SCI_GPIO_MODE_MASK) >>
CP210X_SCI_GPIO_MODE_OFFSET);
- priv->gc.ngpio = 3;
} else {
return -ENODEV;
}
.driver_info = NCTRL(2) | RSVD(3) },
{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1063, 0xff), /* Telit LN920 (ECM) */
.driver_info = NCTRL(0) | RSVD(1) },
+ { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1070, 0xff), /* Telit FN990 (rmnet) */
+ .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) },
+ { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1071, 0xff), /* Telit FN990 (MBIM) */
+ .driver_info = NCTRL(0) | RSVD(1) },
+ { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1072, 0xff), /* Telit FN990 (RNDIS) */
+ .driver_info = NCTRL(2) | RSVD(3) },
+ { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1073, 0xff), /* Telit FN990 (ECM) */
+ .driver_info = NCTRL(0) | RSVD(1) },
{ 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),
bool attached;
bool connected;
+ bool registered;
bool pd_supported;
enum typec_port_type port_type;
{
struct tcpm_port *port = container_of(timer, struct tcpm_port, state_machine_timer);
- kthread_queue_work(port->wq, &port->state_machine);
+ if (port->registered)
+ kthread_queue_work(port->wq, &port->state_machine);
return HRTIMER_NORESTART;
}
{
struct tcpm_port *port = container_of(timer, struct tcpm_port, vdm_state_machine_timer);
- kthread_queue_work(port->wq, &port->vdm_state_machine);
+ if (port->registered)
+ kthread_queue_work(port->wq, &port->vdm_state_machine);
return HRTIMER_NORESTART;
}
{
struct tcpm_port *port = container_of(timer, struct tcpm_port, enable_frs_timer);
- kthread_queue_work(port->wq, &port->enable_frs);
+ if (port->registered)
+ kthread_queue_work(port->wq, &port->enable_frs);
return HRTIMER_NORESTART;
}
{
struct tcpm_port *port = container_of(timer, struct tcpm_port, send_discover_timer);
- kthread_queue_work(port->wq, &port->send_discover_work);
+ if (port->registered)
+ kthread_queue_work(port->wq, &port->send_discover_work);
return HRTIMER_NORESTART;
}
typec_port_register_altmodes(port->typec_port,
&tcpm_altmode_ops, port,
port->port_altmode, ALTMODE_DISCOVERY_MAX);
+ port->registered = true;
mutex_lock(&port->lock);
tcpm_init(port);
{
int i;
+ port->registered = false;
+ kthread_destroy_worker(port->wq);
+
hrtimer_cancel(&port->send_discover_timer);
hrtimer_cancel(&port->enable_frs_timer);
hrtimer_cancel(&port->vdm_state_machine_timer);
typec_unregister_port(port->typec_port);
usb_role_switch_put(port->role_sw);
tcpm_debugfs_exit(port);
- kthread_destroy_worker(port->wq);
}
EXPORT_SYMBOL_GPL(tcpm_unregister_port);
goto msg_err;
while (mdev->id_table[i].device) {
- supported_classes |= BIT(mdev->id_table[i].device);
+ if (mdev->id_table[i].device <= 63)
+ supported_classes |= BIT_ULL(mdev->id_table[i].device);
i++;
}
{
struct vduse_dev *dev = vdpa_to_vduse(vdpa);
- if (len > dev->config_size - offset)
+ if (offset > dev->config_size ||
+ len > dev->config_size - offset)
return;
memcpy(buf, dev->config + offset, len);
break;
ret = -EINVAL;
- if (config.length == 0 ||
+ if (config.offset > dev->config_size ||
+ config.length == 0 ||
config.length > dev->config_size - config.offset)
break;
struct vdpa_device *vdpa = v->vdpa;
long size = vdpa->config->get_config_size(vdpa);
- if (c->len == 0)
+ if (c->len == 0 || c->off > size)
return -EINVAL;
if (c->len > size - c->off)
size_t max_segment_size = SIZE_MAX;
if (vring_use_dma_api(vdev))
- max_segment_size = dma_max_mapping_size(&vdev->dev);
+ max_segment_size = dma_max_mapping_size(vdev->dev.parent);
return max_segment_size;
}
if (atomic_inc_return(&vnode->cb_nr_mmap) == 1) {
down_write(&vnode->volume->cell->fs_open_mmaps_lock);
- list_add_tail(&vnode->cb_mmap_link,
- &vnode->volume->cell->fs_open_mmaps);
+ if (list_empty(&vnode->cb_mmap_link))
+ list_add_tail(&vnode->cb_mmap_link,
+ &vnode->volume->cell->fs_open_mmaps);
up_write(&vnode->volume->cell->fs_open_mmaps_lock);
}
INIT_LIST_HEAD(&vnode->pending_locks);
INIT_LIST_HEAD(&vnode->granted_locks);
INIT_DELAYED_WORK(&vnode->lock_work, afs_lock_work);
+ INIT_LIST_HEAD(&vnode->cb_mmap_link);
seqlock_init(&vnode->cb_lock);
}
struct file *file;
struct wait_queue_head *head;
__poll_t events;
- bool done;
bool cancelled;
+ bool work_scheduled;
+ bool work_need_resched;
struct wait_queue_entry wait;
struct work_struct work;
};
iocb_put(iocb);
}
+/*
+ * Safely lock the waitqueue which the request is on, synchronizing with the
+ * case where the ->poll() provider decides to free its waitqueue early.
+ *
+ * Returns true on success, meaning that req->head->lock was locked, req->wait
+ * is on req->head, and an RCU read lock was taken. Returns false if the
+ * request was already removed from its waitqueue (which might no longer exist).
+ */
+static bool poll_iocb_lock_wq(struct poll_iocb *req)
+{
+ wait_queue_head_t *head;
+
+ /*
+ * While we hold the waitqueue lock and the waitqueue is nonempty,
+ * wake_up_pollfree() will wait for us. However, taking the waitqueue
+ * lock in the first place can race with the waitqueue being freed.
+ *
+ * We solve this as eventpoll does: by taking advantage of the fact that
+ * all users of wake_up_pollfree() will RCU-delay the actual free. If
+ * we enter rcu_read_lock() and see that the pointer to the queue is
+ * non-NULL, we can then lock it without the memory being freed out from
+ * under us, then check whether the request is still on the queue.
+ *
+ * Keep holding rcu_read_lock() as long as we hold the queue lock, in
+ * case the caller deletes the entry from the queue, leaving it empty.
+ * In that case, only RCU prevents the queue memory from being freed.
+ */
+ rcu_read_lock();
+ head = smp_load_acquire(&req->head);
+ if (head) {
+ spin_lock(&head->lock);
+ if (!list_empty(&req->wait.entry))
+ return true;
+ spin_unlock(&head->lock);
+ }
+ rcu_read_unlock();
+ return false;
+}
+
+static void poll_iocb_unlock_wq(struct poll_iocb *req)
+{
+ spin_unlock(&req->head->lock);
+ rcu_read_unlock();
+}
+
static void aio_poll_complete_work(struct work_struct *work)
{
struct poll_iocb *req = container_of(work, struct poll_iocb, work);
* avoid further branches in the fast path.
*/
spin_lock_irq(&ctx->ctx_lock);
- if (!mask && !READ_ONCE(req->cancelled)) {
- add_wait_queue(req->head, &req->wait);
- spin_unlock_irq(&ctx->ctx_lock);
- return;
- }
+ if (poll_iocb_lock_wq(req)) {
+ if (!mask && !READ_ONCE(req->cancelled)) {
+ /*
+ * The request isn't actually ready to be completed yet.
+ * Reschedule completion if another wakeup came in.
+ */
+ if (req->work_need_resched) {
+ schedule_work(&req->work);
+ req->work_need_resched = false;
+ } else {
+ req->work_scheduled = false;
+ }
+ poll_iocb_unlock_wq(req);
+ spin_unlock_irq(&ctx->ctx_lock);
+ return;
+ }
+ list_del_init(&req->wait.entry);
+ poll_iocb_unlock_wq(req);
+ } /* else, POLLFREE has freed the waitqueue, so we must complete */
list_del_init(&iocb->ki_list);
iocb->ki_res.res = mangle_poll(mask);
- req->done = true;
spin_unlock_irq(&ctx->ctx_lock);
iocb_put(iocb);
struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw);
struct poll_iocb *req = &aiocb->poll;
- spin_lock(&req->head->lock);
- WRITE_ONCE(req->cancelled, true);
- if (!list_empty(&req->wait.entry)) {
- list_del_init(&req->wait.entry);
- schedule_work(&aiocb->poll.work);
- }
- spin_unlock(&req->head->lock);
+ if (poll_iocb_lock_wq(req)) {
+ WRITE_ONCE(req->cancelled, true);
+ if (!req->work_scheduled) {
+ schedule_work(&aiocb->poll.work);
+ req->work_scheduled = true;
+ }
+ poll_iocb_unlock_wq(req);
+ } /* else, the request was force-cancelled by POLLFREE already */
return 0;
}
if (mask && !(mask & req->events))
return 0;
- list_del_init(&req->wait.entry);
-
- if (mask && spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) {
+ /*
+ * Complete the request inline if possible. This requires that three
+ * conditions be met:
+ * 1. An event mask must have been passed. If a plain wakeup was done
+ * instead, then mask == 0 and we have to call vfs_poll() to get
+ * the events, so inline completion isn't possible.
+ * 2. The completion work must not have already been scheduled.
+ * 3. ctx_lock must not be busy. We have to use trylock because we
+ * already hold the waitqueue lock, so this inverts the normal
+ * locking order. Use irqsave/irqrestore because not all
+ * filesystems (e.g. fuse) call this function with IRQs disabled,
+ * yet IRQs have to be disabled before ctx_lock is obtained.
+ */
+ if (mask && !req->work_scheduled &&
+ spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) {
struct kioctx *ctx = iocb->ki_ctx;
- /*
- * Try to complete the iocb inline if we can. Use
- * irqsave/irqrestore because not all filesystems (e.g. fuse)
- * call this function with IRQs disabled and because IRQs
- * have to be disabled before ctx_lock is obtained.
- */
+ list_del_init(&req->wait.entry);
list_del(&iocb->ki_list);
iocb->ki_res.res = mangle_poll(mask);
- req->done = true;
- if (iocb->ki_eventfd && eventfd_signal_allowed()) {
+ if (iocb->ki_eventfd && !eventfd_signal_allowed()) {
iocb = NULL;
INIT_WORK(&req->work, aio_poll_put_work);
schedule_work(&req->work);
if (iocb)
iocb_put(iocb);
} else {
- schedule_work(&req->work);
+ /*
+ * Schedule the completion work if needed. If it was already
+ * scheduled, record that another wakeup came in.
+ *
+ * Don't remove the request from the waitqueue here, as it might
+ * not actually be complete yet (we won't know until vfs_poll()
+ * is called), and we must not miss any wakeups. POLLFREE is an
+ * exception to this; see below.
+ */
+ if (req->work_scheduled) {
+ req->work_need_resched = true;
+ } else {
+ schedule_work(&req->work);
+ req->work_scheduled = true;
+ }
+
+ /*
+ * If the waitqueue is being freed early but we can't complete
+ * the request inline, we have to tear down the request as best
+ * we can. That means immediately removing the request from its
+ * waitqueue and preventing all further accesses to the
+ * waitqueue via the request. We also need to schedule the
+ * completion work (done above). Also mark the request as
+ * cancelled, to potentially skip an unneeded call to ->poll().
+ */
+ if (mask & POLLFREE) {
+ WRITE_ONCE(req->cancelled, true);
+ list_del_init(&req->wait.entry);
+
+ /*
+ * Careful: this *must* be the last step, since as soon
+ * as req->head is NULL'ed out, the request can be
+ * completed and freed, since aio_poll_complete_work()
+ * will no longer need to take the waitqueue lock.
+ */
+ smp_store_release(&req->head, NULL);
+ }
}
return 1;
}
struct aio_poll_table {
struct poll_table_struct pt;
struct aio_kiocb *iocb;
+ bool queued;
int error;
};
struct aio_poll_table *pt = container_of(p, struct aio_poll_table, pt);
/* multiple wait queues per file are not supported */
- if (unlikely(pt->iocb->poll.head)) {
+ if (unlikely(pt->queued)) {
pt->error = -EINVAL;
return;
}
+ pt->queued = true;
pt->error = 0;
pt->iocb->poll.head = head;
add_wait_queue(head, &pt->iocb->poll.wait);
req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP;
req->head = NULL;
- req->done = false;
req->cancelled = false;
+ req->work_scheduled = false;
+ req->work_need_resched = false;
apt.pt._qproc = aio_poll_queue_proc;
apt.pt._key = req->events;
apt.iocb = aiocb;
+ apt.queued = false;
apt.error = -EINVAL; /* same as no support for IOCB_CMD_POLL */
/* initialized the list so that we can do list_empty checks */
mask = vfs_poll(req->file, &apt.pt) & req->events;
spin_lock_irq(&ctx->ctx_lock);
- if (likely(req->head)) {
- spin_lock(&req->head->lock);
- if (unlikely(list_empty(&req->wait.entry))) {
- if (apt.error)
+ if (likely(apt.queued)) {
+ bool on_queue = poll_iocb_lock_wq(req);
+
+ if (!on_queue || req->work_scheduled) {
+ /*
+ * aio_poll_wake() already either scheduled the async
+ * completion work, or completed the request inline.
+ */
+ if (apt.error) /* unsupported case: multiple queues */
cancel = true;
apt.error = 0;
mask = 0;
}
if (mask || apt.error) {
+ /* Steal to complete synchronously. */
list_del_init(&req->wait.entry);
} else if (cancel) {
+ /* Cancel if possible (may be too late though). */
WRITE_ONCE(req->cancelled, true);
- } else if (!req->done) { /* actually waiting for an event */
+ } else if (on_queue) {
+ /*
+ * Actually waiting for an event, so add the request to
+ * active_reqs so that it can be cancelled if needed.
+ */
list_add_tail(&aiocb->ki_list, &ctx->active_reqs);
aiocb->ki_cancel = aio_poll_cancel;
}
- spin_unlock(&req->head->lock);
+ if (on_queue)
+ poll_iocb_unlock_wq(req);
}
if (mask) { /* no async, we'd stolen it */
aiocb->ki_res.res = mangle_poll(mask);
BUG_ON(ret < 0);
rcu_assign_pointer(root->node, cow);
- btrfs_free_tree_block(trans, root, buf, parent_start,
- last_ref);
+ btrfs_free_tree_block(trans, btrfs_root_id(root), buf,
+ parent_start, last_ref);
free_extent_buffer(buf);
add_root_to_dirty_list(root);
} else {
return ret;
}
}
- btrfs_free_tree_block(trans, root, buf, parent_start,
- last_ref);
+ btrfs_free_tree_block(trans, btrfs_root_id(root), buf,
+ parent_start, last_ref);
}
if (unlock_orig)
btrfs_tree_unlock(buf);
free_extent_buffer(mid);
root_sub_used(root, mid->len);
- btrfs_free_tree_block(trans, root, mid, 0, 1);
+ btrfs_free_tree_block(trans, btrfs_root_id(root), mid, 0, 1);
/* once for the root ptr */
free_extent_buffer_stale(mid);
return 0;
btrfs_tree_unlock(right);
del_ptr(root, path, level + 1, pslot + 1);
root_sub_used(root, right->len);
- btrfs_free_tree_block(trans, root, right, 0, 1);
+ btrfs_free_tree_block(trans, btrfs_root_id(root), right,
+ 0, 1);
free_extent_buffer_stale(right);
right = NULL;
} else {
btrfs_tree_unlock(mid);
del_ptr(root, path, level + 1, pslot);
root_sub_used(root, mid->len);
- btrfs_free_tree_block(trans, root, mid, 0, 1);
+ btrfs_free_tree_block(trans, btrfs_root_id(root), mid, 0, 1);
free_extent_buffer_stale(mid);
mid = NULL;
} else {
root_sub_used(root, leaf->len);
atomic_inc(&leaf->refs);
- btrfs_free_tree_block(trans, root, leaf, 0, 1);
+ btrfs_free_tree_block(trans, btrfs_root_id(root), leaf, 0, 1);
free_extent_buffer_stale(leaf);
}
/*
return (root->root_item.flags & cpu_to_le64(BTRFS_ROOT_SUBVOL_DEAD)) != 0;
}
+static inline u64 btrfs_root_id(const struct btrfs_root *root)
+{
+ return root->root_key.objectid;
+}
+
/* struct btrfs_root_backup */
BTRFS_SETGET_STACK_FUNCS(backup_tree_root, struct btrfs_root_backup,
tree_root, 64);
u64 empty_size,
enum btrfs_lock_nesting nest);
void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
+ u64 root_id,
struct extent_buffer *buf,
u64 parent, int last_ref);
int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
/* Use new btrfs_qgroup_reserve_data to reserve precious data space. */
ret = btrfs_qgroup_reserve_data(inode, reserved, start, len);
- if (ret < 0)
+ if (ret < 0) {
btrfs_free_reserved_data_space_noquota(fs_info, len);
- else
+ extent_changeset_free(*reserved);
+ *reserved = NULL;
+ } else {
ret = 0;
+ }
return ret;
}
if (ret < 0)
return ret;
ret = btrfs_delalloc_reserve_metadata(inode, len);
- if (ret < 0)
+ if (ret < 0) {
btrfs_free_reserved_data_space(inode, *reserved, start, len);
+ extent_changeset_free(*reserved);
+ *reserved = NULL;
+ }
return ret;
}
}
return root;
fail:
+ /*
+ * If our caller provided us an anonymous device, then it's his
+ * responsability to free it in case we fail. So we have to set our
+ * root's anon_dev to 0 to avoid a double free, once by btrfs_put_root()
+ * and once again by our caller.
+ */
+ if (anon_dev)
+ root->anon_dev = 0;
btrfs_put_root(root);
return ERR_PTR(ret);
}
}
void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
+ u64 root_id,
struct extent_buffer *buf,
u64 parent, int last_ref)
{
- struct btrfs_fs_info *fs_info = root->fs_info;
+ struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_ref generic_ref = { 0 };
int ret;
btrfs_init_generic_ref(&generic_ref, BTRFS_DROP_DELAYED_REF,
buf->start, buf->len, parent);
btrfs_init_tree_ref(&generic_ref, btrfs_header_level(buf),
- root->root_key.objectid, 0, false);
+ root_id, 0, false);
- if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
+ if (root_id != BTRFS_TREE_LOG_OBJECTID) {
btrfs_ref_tree_mod(fs_info, &generic_ref);
ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, NULL);
BUG_ON(ret); /* -ENOMEM */
struct btrfs_block_group *cache;
bool must_pin = false;
- if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
+ if (root_id != BTRFS_TREE_LOG_OBJECTID) {
ret = check_ref_cleanup(trans, buf->start);
if (!ret) {
btrfs_redirty_list_add(trans->transaction, buf);
goto owner_mismatch;
}
- btrfs_free_tree_block(trans, root, eb, parent, wc->refs[level] == 1);
+ btrfs_free_tree_block(trans, btrfs_root_id(root), eb, parent,
+ wc->refs[level] == 1);
out:
wc->refs[level] = 0;
wc->flags[level] = 0;
int dev_ret = 0;
int ret = 0;
+ if (range->start == U64_MAX)
+ return -EINVAL;
+
/*
* Check range overflow if range->len is set.
* The default range->len is U64_MAX.
return;
/*
+ * A read may stumble upon this buffer later, make sure that it gets an
+ * error and knows there was an error.
+ */
+ clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
+
+ /*
+ * We need to set the mapping with the io error as well because a write
+ * error will flip the file system readonly, and then syncfs() will
+ * return a 0 because we are readonly if we don't modify the err seq for
+ * the superblock.
+ */
+ mapping_set_error(page->mapping, -EIO);
+
+ /*
* If we error out, we should add back the dirty_metadata_bytes
* to make it consistent.
*/
if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
return 0;
+ /*
+ * We could have had EXTENT_BUFFER_UPTODATE cleared by the write
+ * operation, which could potentially still be in flight. In this case
+ * we simply want to return an error.
+ */
+ if (unlikely(test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)))
+ return -EIO;
+
if (eb->fs_info->sectorsize < PAGE_SIZE)
return read_extent_buffer_subpage(eb, wait, mirror_num);
btrfs_tree_lock(free_space_root->node);
btrfs_clean_tree_block(free_space_root->node);
btrfs_tree_unlock(free_space_root->node);
- btrfs_free_tree_block(trans, free_space_root, free_space_root->node,
- 0, 1);
+ btrfs_free_tree_block(trans, btrfs_root_id(free_space_root),
+ free_space_root->node, 0, 1);
btrfs_put_root(free_space_root);
* Since we don't abort the transaction in this case, free the
* tree block so that we don't leak space and leave the
* filesystem in an inconsistent state (an extent item in the
- * extent tree without backreferences). Also no need to have
- * the tree block locked since it is not in any tree at this
- * point, so no other task can find it and use it.
+ * extent tree with a backreference for a root that does not
+ * exists).
*/
- btrfs_free_tree_block(trans, root, leaf, 0, 1);
+ btrfs_tree_lock(leaf);
+ btrfs_clean_tree_block(leaf);
+ btrfs_tree_unlock(leaf);
+ btrfs_free_tree_block(trans, objectid, leaf, 0, 1);
free_extent_buffer(leaf);
goto fail;
}
return -EPERM;
vol_args = memdup_user(arg, sizeof(*vol_args));
- if (IS_ERR(vol_args)) {
- ret = PTR_ERR(vol_args);
- goto out;
- }
+ if (IS_ERR(vol_args))
+ return PTR_ERR(vol_args);
if (vol_args->flags & ~BTRFS_DEVICE_REMOVE_ARGS_MASK) {
ret = -EOPNOTSUPP;
btrfs_tree_lock(quota_root->node);
btrfs_clean_tree_block(quota_root->node);
btrfs_tree_unlock(quota_root->node);
- btrfs_free_tree_block(trans, quota_root, quota_root->node, 0, 1);
+ btrfs_free_tree_block(trans, btrfs_root_id(quota_root),
+ quota_root->node, 0, 1);
btrfs_put_root(quota_root);
key.offset = ref_id;
again:
ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1);
- BUG_ON(ret < 0);
+ if (ret < 0)
+ goto out;
if (ret == 0) {
leaf = path->nodes[0];
ref = btrfs_item_ptr(leaf, path->slots[0],
parent_objectid, victim_name,
victim_name_len);
if (ret < 0) {
+ kfree(victim_name);
return ret;
} else if (!ret) {
ret = -ENOENT;
path->nodes[*level]->len);
if (ret)
return ret;
+ btrfs_redirty_list_add(trans->transaction,
+ next);
} else {
if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags))
clear_extent_buffer_dirty(next);
next->start, next->len);
if (ret)
goto out;
+ btrfs_redirty_list_add(trans->transaction, next);
} else {
if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags))
clear_extent_buffer_dirty(next);
EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT);
extent_io_tree_release(&log->log_csum_range);
- if (trans && log->node)
- btrfs_redirty_list_add(trans->transaction, log->node);
btrfs_put_root(log);
}
goto done;
}
if (btrfs_header_generation(path->nodes[0]) != trans->transid) {
+ ctx->last_dir_item_offset = min_key.offset;
ret = overwrite_item(trans, log, dst_path,
path->nodes[0], path->slots[0],
&min_key);
bytenr_orig = btrfs_sb_offset(0);
ret = btrfs_sb_log_location_bdev(bdev, 0, READ, &bytenr);
- if (ret)
- return ERR_PTR(ret);
+ if (ret) {
+ device = ERR_PTR(ret);
+ goto error_bdev_put;
+ }
disk_super = btrfs_read_disk_super(bdev, bytenr, bytenr_orig);
if (IS_ERR(disk_super)) {
block_group->alloc_offset = block_group->zone_capacity;
block_group->free_space_ctl->free_space = 0;
btrfs_clear_treelog_bg(block_group);
+ btrfs_clear_data_reloc_bg(block_group);
spin_unlock(&block_group->lock);
ret = blkdev_zone_mgmt(device->bdev, REQ_OP_ZONE_FINISH,
ASSERT(block_group->alloc_offset == block_group->zone_capacity);
ASSERT(block_group->free_space_ctl->free_space == 0);
btrfs_clear_treelog_bg(block_group);
+ btrfs_clear_data_reloc_bg(block_group);
spin_unlock(&block_group->lock);
map = block_group->physical_map;
{
struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(ci->vfs_inode.i_sb);
int bits = (fmode << 1) | 1;
- bool is_opened = false;
+ bool already_opened = false;
int i;
if (count == 1)
spin_lock(&ci->i_ceph_lock);
for (i = 0; i < CEPH_FILE_MODE_BITS; i++) {
- if (bits & (1 << i))
- ci->i_nr_by_mode[i] += count;
-
/*
- * If any of the mode ref is larger than 1,
+ * If any of the mode ref is larger than 0,
* that means it has been already opened by
* others. Just skip checking the PIN ref.
*/
- if (i && ci->i_nr_by_mode[i] > 1)
- is_opened = true;
+ if (i && ci->i_nr_by_mode[i])
+ already_opened = true;
+
+ if (bits & (1 << i))
+ ci->i_nr_by_mode[i] += count;
}
- if (!is_opened)
+ if (!already_opened)
percpu_counter_inc(&mdsc->metric.opened_inodes);
spin_unlock(&ci->i_ceph_lock);
}
in.cap.realm = cpu_to_le64(ci->i_snap_realm->ino);
in.cap.flags = CEPH_CAP_FLAG_AUTH;
in.ctime = in.mtime = in.atime = iinfo.btime;
- in.mode = cpu_to_le32((u32)mode);
in.truncate_seq = cpu_to_le32(1);
in.truncate_size = cpu_to_le64(-1ULL);
in.xattr_version = cpu_to_le64(1);
in.uid = cpu_to_le32(from_kuid(&init_user_ns, current_fsuid()));
- in.gid = cpu_to_le32(from_kgid(&init_user_ns, dir->i_mode & S_ISGID ?
- dir->i_gid : current_fsgid()));
+ if (dir->i_mode & S_ISGID) {
+ in.gid = cpu_to_le32(from_kgid(&init_user_ns, dir->i_gid));
+
+ /* Directories always inherit the setgid bit. */
+ if (S_ISDIR(mode))
+ mode |= S_ISGID;
+ else if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP) &&
+ !in_group_p(dir->i_gid) &&
+ !capable_wrt_inode_uidgid(&init_user_ns, dir, CAP_FSETID))
+ mode &= ~S_ISGID;
+ } else {
+ in.gid = cpu_to_le32(from_kgid(&init_user_ns, current_fsgid()));
+ }
+ in.mode = cpu_to_le32((u32)mode);
+
in.nlink = cpu_to_le32(1);
in.max_size = cpu_to_le64(lo->stripe_unit);
ssize_t ret;
u64 off = iocb->ki_pos;
u64 len = iov_iter_count(to);
- u64 i_size;
+ u64 i_size = i_size_read(inode);
dout("sync_read on file %p %llu~%u %s\n", file, off, (unsigned)len,
(file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
struct ceph_pagelist *pagelist = recon_state->pagelist;
struct dentry *dentry;
char *path;
- int pathlen, err;
+ int pathlen = 0, err;
u64 pathbase;
u64 snap_follows;
}
} else {
path = NULL;
- pathlen = 0;
pathbase = 0;
}
(cifs_sb->ctx->rsize > server->ops->negotiate_rsize(tcon, ctx)))
cifs_sb->ctx->rsize = server->ops->negotiate_rsize(tcon, ctx);
+ /*
+ * The cookie is initialized from volume info returned above.
+ * Inside cifs_fscache_get_super_cookie it checks
+ * that we do not get super cookie twice.
+ */
+ cifs_fscache_get_super_cookie(tcon);
+
out:
mnt_ctx->server = server;
mnt_ctx->ses = ses;
}
/*
+ * Remove duplicate path delimiters. Windows is supposed to do that
+ * but there are some bugs that prevent rename from working if there are
+ * multiple delimiters.
+ *
+ * Returns a sanitized duplicate of @path. The caller is responsible for
+ * cleaning up the original.
+ */
+#define IS_DELIM(c) ((c) == '/' || (c) == '\\')
+static char *sanitize_path(char *path)
+{
+ char *cursor1 = path, *cursor2 = path;
+
+ /* skip all prepended delimiters */
+ while (IS_DELIM(*cursor1))
+ cursor1++;
+
+ /* copy the first letter */
+ *cursor2 = *cursor1;
+
+ /* copy the remainder... */
+ while (*(cursor1++)) {
+ /* ... skipping all duplicated delimiters */
+ if (IS_DELIM(*cursor1) && IS_DELIM(*cursor2))
+ continue;
+ *(++cursor2) = *cursor1;
+ }
+
+ /* if the last character is a delimiter, skip it */
+ if (IS_DELIM(*(cursor2 - 1)))
+ cursor2--;
+
+ *(cursor2) = '\0';
+ return kstrdup(path, GFP_KERNEL);
+}
+
+/*
* Parse a devname into substrings and populate the ctx->UNC and ctx->prepath
* fields with the result. Returns 0 on success and an error otherwise
* (e.g. ENOMEM or EINVAL)
if (!*pos)
return 0;
- ctx->prepath = kstrdup(pos, GFP_KERNEL);
+ ctx->prepath = sanitize_path(pos);
if (!ctx->prepath)
return -ENOMEM;
goto out;
}
-#ifdef CONFIG_CIFS_FSCACHE
- /* populate tcon->resource_id */
- tcon->resource_id = CIFS_I(inode)->uniqueid;
-#endif
-
if (rc && tcon->pipe) {
cifs_dbg(FYI, "ipc connection - fake read inode\n");
spin_lock(&inode->i_lock);
iget_failed(inode);
inode = ERR_PTR(rc);
}
-
- /*
- * The cookie is initialized from volume info returned above.
- * Inside cifs_fscache_get_super_cookie it checks
- * that we do not get super cookie twice.
- */
- cifs_fscache_get_super_cookie(tcon);
-
out:
kfree(path);
free_xid(xid);
{
unsigned int tioffset; /* challenge message target info area */
unsigned int tilen; /* challenge message target info area length */
-
CHALLENGE_MESSAGE *pblob = (CHALLENGE_MESSAGE *)bcc_ptr;
+ __u32 server_flags;
if (blob_len < sizeof(CHALLENGE_MESSAGE)) {
cifs_dbg(VFS, "challenge blob len %d too small\n", blob_len);
return -EINVAL;
}
+ server_flags = le32_to_cpu(pblob->NegotiateFlags);
+ cifs_dbg(FYI, "%s: negotiate=0x%08x challenge=0x%08x\n", __func__,
+ ses->ntlmssp->client_flags, server_flags);
+
+ if ((ses->ntlmssp->client_flags & (NTLMSSP_NEGOTIATE_SEAL | NTLMSSP_NEGOTIATE_SIGN)) &&
+ (!(server_flags & NTLMSSP_NEGOTIATE_56) && !(server_flags & NTLMSSP_NEGOTIATE_128))) {
+ cifs_dbg(VFS, "%s: requested signing/encryption but server did not return either 56-bit or 128-bit session key size\n",
+ __func__);
+ return -EINVAL;
+ }
+ if (!(server_flags & NTLMSSP_NEGOTIATE_NTLM) && !(server_flags & NTLMSSP_NEGOTIATE_EXTENDED_SEC)) {
+ cifs_dbg(VFS, "%s: server does not seem to support either NTLMv1 or NTLMv2\n", __func__);
+ return -EINVAL;
+ }
+ if (ses->server->sign && !(server_flags & NTLMSSP_NEGOTIATE_SIGN)) {
+ cifs_dbg(VFS, "%s: forced packet signing but server does not seem to support it\n",
+ __func__);
+ return -EOPNOTSUPP;
+ }
+ if ((ses->ntlmssp->client_flags & NTLMSSP_NEGOTIATE_KEY_XCH) &&
+ !(server_flags & NTLMSSP_NEGOTIATE_KEY_XCH))
+ pr_warn_once("%s: authentication has been weakened as server does not support key exchange\n",
+ __func__);
+
+ ses->ntlmssp->server_flags = server_flags;
+
memcpy(ses->ntlmssp->cryptkey, pblob->Challenge, CIFS_CRYPTO_KEY_SIZE);
- /* BB we could decode pblob->NegotiateFlags; some may be useful */
/* In particular we can examine sign flags */
/* BB spec says that if AvId field of MsvAvTimestamp is populated then
we must set the MIC field of the AUTHENTICATE_MESSAGE */
- ses->ntlmssp->server_flags = le32_to_cpu(pblob->NegotiateFlags);
+
tioffset = le32_to_cpu(pblob->TargetInfoArray.BufferOffset);
tilen = le16_to_cpu(pblob->TargetInfoArray.Length);
if (tioffset > blob_len || tioffset + tilen > blob_len) {
flags = NTLMSSP_NEGOTIATE_56 | NTLMSSP_REQUEST_TARGET |
NTLMSSP_NEGOTIATE_128 | NTLMSSP_NEGOTIATE_UNICODE |
NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC |
- NTLMSSP_NEGOTIATE_SEAL;
- if (server->sign)
- flags |= NTLMSSP_NEGOTIATE_SIGN;
+ NTLMSSP_NEGOTIATE_ALWAYS_SIGN | NTLMSSP_NEGOTIATE_SEAL |
+ NTLMSSP_NEGOTIATE_SIGN;
if (!server->session_estab || ses->ntlmssp->sesskey_per_smbsess)
flags |= NTLMSSP_NEGOTIATE_KEY_XCH;
tmp = *pbuffer + sizeof(NEGOTIATE_MESSAGE);
+ ses->ntlmssp->client_flags = flags;
sec_blob->NegotiateFlags = cpu_to_le32(flags);
/* these fields should be null in negotiate phase MS-NLMP 3.1.5.1.1 */
memcpy(sec_blob->Signature, NTLMSSP_SIGNATURE, 8);
sec_blob->MessageType = NtLmAuthenticate;
- flags = NTLMSSP_NEGOTIATE_56 |
- NTLMSSP_REQUEST_TARGET | NTLMSSP_NEGOTIATE_TARGET_INFO |
- NTLMSSP_NEGOTIATE_128 | NTLMSSP_NEGOTIATE_UNICODE |
- NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC |
- NTLMSSP_NEGOTIATE_SEAL | NTLMSSP_NEGOTIATE_WORKSTATION_SUPPLIED;
- if (ses->server->sign)
- flags |= NTLMSSP_NEGOTIATE_SIGN;
- if (!ses->server->session_estab || ses->ntlmssp->sesskey_per_smbsess)
- flags |= NTLMSSP_NEGOTIATE_KEY_XCH;
+ flags = ses->ntlmssp->server_flags | NTLMSSP_REQUEST_TARGET |
+ NTLMSSP_NEGOTIATE_TARGET_INFO | NTLMSSP_NEGOTIATE_WORKSTATION_SUPPLIED;
tmp = *pbuffer + sizeof(AUTHENTICATE_MESSAGE);
sec_blob->NegotiateFlags = cpu_to_le32(flags);
*pbuffer, &tmp,
nls_cp);
- if (((ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_KEY_XCH) ||
- (ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_EXTENDED_SEC))
- && !calc_seckey(ses)) {
+ if ((ses->ntlmssp->server_flags & NTLMSSP_NEGOTIATE_KEY_XCH) &&
+ (!ses->server->session_estab || ses->ntlmssp->sesskey_per_smbsess) &&
+ !calc_seckey(ses)) {
memcpy(tmp, ses->ntlmssp->ciphertext, CIFS_CPHTXT_SIZE);
sec_blob->SessionKey.BufferOffset = cpu_to_le32(tmp - *pbuffer);
sec_blob->SessionKey.Length = cpu_to_le16(CIFS_CPHTXT_SIZE);
spin_unlock(&files->file_lock);
}
-static struct file *__fget_files(struct files_struct *files, unsigned int fd,
- fmode_t mask, unsigned int refs)
+static inline struct file *__fget_files_rcu(struct files_struct *files,
+ unsigned int fd, fmode_t mask, unsigned int refs)
{
- struct file *file;
+ for (;;) {
+ struct file *file;
+ struct fdtable *fdt = rcu_dereference_raw(files->fdt);
+ struct file __rcu **fdentry;
- rcu_read_lock();
-loop:
- file = files_lookup_fd_rcu(files, fd);
- if (file) {
- /* File object ref couldn't be taken.
- * dup2() atomicity guarantee is the reason
- * we loop to catch the new file (or NULL pointer)
+ if (unlikely(fd >= fdt->max_fds))
+ return NULL;
+
+ fdentry = fdt->fd + array_index_nospec(fd, fdt->max_fds);
+ file = rcu_dereference_raw(*fdentry);
+ if (unlikely(!file))
+ return NULL;
+
+ if (unlikely(file->f_mode & mask))
+ return NULL;
+
+ /*
+ * Ok, we have a file pointer. However, because we do
+ * this all locklessly under RCU, we may be racing with
+ * that file being closed.
+ *
+ * Such a race can take two forms:
+ *
+ * (a) the file ref already went down to zero,
+ * and get_file_rcu_many() fails. Just try
+ * again:
*/
- if (file->f_mode & mask)
- file = NULL;
- else if (!get_file_rcu_many(file, refs))
- goto loop;
- else if (files_lookup_fd_raw(files, fd) != file) {
+ if (unlikely(!get_file_rcu_many(file, refs)))
+ continue;
+
+ /*
+ * (b) the file table entry has changed under us.
+ * Note that we don't need to re-check the 'fdt->fd'
+ * pointer having changed, because it always goes
+ * hand-in-hand with 'fdt'.
+ *
+ * If so, we need to put our refs and try again.
+ */
+ if (unlikely(rcu_dereference_raw(files->fdt) != fdt) ||
+ unlikely(rcu_dereference_raw(*fdentry) != file)) {
fput_many(file, refs);
- goto loop;
+ continue;
}
+
+ /*
+ * Ok, we have a ref to the file, and checked that it
+ * still exists.
+ */
+ return file;
}
+}
+
+static struct file *__fget_files(struct files_struct *files, unsigned int fd,
+ fmode_t mask, unsigned int refs)
+{
+ struct file *file;
+
+ rcu_read_lock();
+ file = __fget_files_rcu(files, fd, mask, refs);
rcu_read_unlock();
return file;
struct io_wqe_acct *acct,
struct io_cb_cancel_data *match);
static void create_worker_cb(struct callback_head *cb);
+static void io_wq_cancel_tw_create(struct io_wq *wq);
static bool io_worker_get(struct io_worker *worker)
{
test_and_set_bit_lock(0, &worker->create_state))
goto fail_release;
+ atomic_inc(&wq->worker_refs);
init_task_work(&worker->create_work, func);
worker->create_index = acct->index;
if (!task_work_add(wq->task, &worker->create_work, TWA_SIGNAL)) {
- clear_bit_unlock(0, &worker->create_state);
+ /*
+ * EXIT may have been set after checking it above, check after
+ * adding the task_work and remove any creation item if it is
+ * now set. wq exit does that too, but we can have added this
+ * work item after we canceled in io_wq_exit_workers().
+ */
+ if (test_bit(IO_WQ_BIT_EXIT, &wq->state))
+ io_wq_cancel_tw_create(wq);
+ io_worker_ref_put(wq);
return true;
}
+ io_worker_ref_put(wq);
clear_bit_unlock(0, &worker->create_state);
fail_release:
io_worker_release(worker);
if (atomic_dec_and_test(&acct->nr_running) && io_acct_run_queue(acct)) {
atomic_inc(&acct->nr_running);
atomic_inc(&wqe->wq->worker_refs);
+ raw_spin_unlock(&wqe->lock);
io_queue_worker_create(worker, acct, create_worker_cb);
+ raw_spin_lock(&wqe->lock);
}
}
set_bit(IO_WQ_BIT_EXIT, &wq->state);
}
-static void io_wq_exit_workers(struct io_wq *wq)
+static void io_wq_cancel_tw_create(struct io_wq *wq)
{
struct callback_head *cb;
- int node;
-
- if (!wq->task)
- return;
while ((cb = task_work_cancel_match(wq->task, io_task_work_match, wq)) != NULL) {
struct io_worker *worker;
worker = container_of(cb, struct io_worker, create_work);
io_worker_cancel_cb(worker);
}
+}
+
+static void io_wq_exit_workers(struct io_wq *wq)
+{
+ int node;
+
+ if (!wq->task)
+ return;
+
+ io_wq_cancel_tw_create(wq);
rcu_read_lock();
for_each_node(node) {
/*
* Find any io_uring ctx that this task has registered or done IO on, and cancel
- * requests. @sqd should be not-null IIF it's an SQPOLL thread cancellation.
+ * requests. @sqd should be not-null IFF it's an SQPOLL thread cancellation.
*/
static __cold void io_uring_cancel_generic(bool cancel_all,
struct io_sq_data *sqd)
cancel_all);
}
- prepare_to_wait(&tctx->wait, &wait, TASK_UNINTERRUPTIBLE);
+ prepare_to_wait(&tctx->wait, &wait, TASK_INTERRUPTIBLE);
+ io_run_task_work();
io_uring_drop_tctx_refs(current);
+
/*
* If we've seen completions, retry without waiting. This
* avoids a race where a completion comes in before we did
netfs_rreq_do_write_to_cache(rreq);
}
-static void netfs_rreq_write_to_cache(struct netfs_read_request *rreq,
- bool was_async)
+static void netfs_rreq_write_to_cache(struct netfs_read_request *rreq)
{
- if (was_async) {
- rreq->work.func = netfs_rreq_write_to_cache_work;
- if (!queue_work(system_unbound_wq, &rreq->work))
- BUG();
- } else {
- netfs_rreq_do_write_to_cache(rreq);
- }
+ rreq->work.func = netfs_rreq_write_to_cache_work;
+ if (!queue_work(system_unbound_wq, &rreq->work))
+ BUG();
}
/*
wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS);
if (test_bit(NETFS_RREQ_WRITE_TO_CACHE, &rreq->flags))
- return netfs_rreq_write_to_cache(rreq, was_async);
+ return netfs_rreq_write_to_cache(rreq);
netfs_rreq_completed(rreq, was_async);
}
rreq = netfs_alloc_read_request(ops, netfs_priv, file);
if (!rreq) {
if (netfs_priv)
- ops->cleanup(netfs_priv, folio_file_mapping(folio));
+ ops->cleanup(folio_file_mapping(folio), netfs_priv);
folio_unlock(folio);
return -ENOMEM;
}
goto error;
have_folio_no_wait:
if (netfs_priv)
- ops->cleanup(netfs_priv, mapping);
+ ops->cleanup(mapping, netfs_priv);
*_folio = folio;
_leave(" = 0");
return 0;
folio_unlock(folio);
folio_put(folio);
if (netfs_priv)
- ops->cleanup(netfs_priv, mapping);
+ ops->cleanup(mapping, netfs_priv);
_leave(" = %d", ret);
return ret;
}
int
register_cld_notifier(void)
{
+ WARN_ON(!nfsd_net_id);
return rpc_pipefs_notifier_register(&nfsd4_cld_block);
}
return 0;
}
+static bool delegation_hashed(struct nfs4_delegation *dp)
+{
+ return !(list_empty(&dp->dl_perfile));
+}
+
static bool
unhash_delegation_locked(struct nfs4_delegation *dp)
{
lockdep_assert_held(&state_lock);
- if (list_empty(&dp->dl_perfile))
+ if (!delegation_hashed(dp))
return false;
dp->dl_stid.sc_type = NFS4_CLOSED_DELEG_STID;
* queued for a lease break. Don't queue it again.
*/
spin_lock(&state_lock);
- if (dp->dl_time == 0) {
+ if (delegation_hashed(dp) && dp->dl_time == 0) {
dp->dl_time = ktime_get_boottime_seconds();
list_add_tail(&dp->dl_recall_lru, &nn->del_recall_lru);
}
int retval;
printk(KERN_INFO "Installing knfsd (copyright (C) 1996 okir@monad.swb.de).\n");
- retval = register_cld_notifier();
- if (retval)
- return retval;
retval = nfsd4_init_slabs();
if (retval)
- goto out_unregister_notifier;
+ return retval;
retval = nfsd4_init_pnfs();
if (retval)
goto out_free_slabs;
goto out_free_exports;
retval = register_pernet_subsys(&nfsd_net_ops);
if (retval < 0)
+ goto out_free_filesystem;
+ retval = register_cld_notifier();
+ if (retval)
goto out_free_all;
return 0;
out_free_all:
+ unregister_pernet_subsys(&nfsd_net_ops);
+out_free_filesystem:
unregister_filesystem(&nfsd_fs_type);
out_free_exports:
remove_proc_entry("fs/nfs/exports", NULL);
nfsd4_exit_pnfs();
out_free_slabs:
nfsd4_free_slabs();
-out_unregister_notifier:
- unregister_cld_notifier();
return retval;
}
static void __exit exit_nfsd(void)
{
+ unregister_cld_notifier();
unregister_pernet_subsys(&nfsd_net_ops);
nfsd_drc_slab_free();
remove_proc_entry("fs/nfs/exports", NULL);
nfsd4_free_slabs();
nfsd4_exit_pnfs();
unregister_filesystem(&nfsd_fs_type);
- unregister_cld_notifier();
}
MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>");
void signalfd_cleanup(struct sighand_struct *sighand)
{
- wait_queue_head_t *wqh = &sighand->signalfd_wqh;
- /*
- * The lockless check can race with remove_wait_queue() in progress,
- * but in this case its caller should run under rcu_read_lock() and
- * sighand_cachep is SLAB_TYPESAFE_BY_RCU, we can safely return.
- */
- if (likely(!waitqueue_active(wqh)))
- return;
-
- /* wait_queue_entry_t->func(POLLFREE) should do remove_wait_queue() */
- wake_up_poll(wqh, EPOLLHUP | POLLFREE);
+ wake_up_pollfree(&sighand->signalfd_wqh);
}
struct signalfd_ctx {
ctx->y = y;
}
EXPORT_SYMBOL_GPL(cifs_arc4_crypt);
-
-static int __init
-init_smbfs_common(void)
-{
- return 0;
-}
-static void __init
-exit_smbfs_common(void)
-{
-}
-
-module_init(init_smbfs_common)
-module_exit(exit_smbfs_common)
struct tracefs_mount_opts mount_opts;
};
+static void change_gid(struct dentry *dentry, kgid_t gid)
+{
+ if (!dentry->d_inode)
+ return;
+ dentry->d_inode->i_gid = gid;
+}
+
+/*
+ * Taken from d_walk, but without he need for handling renames.
+ * Nothing can be renamed while walking the list, as tracefs
+ * does not support renames. This is only called when mounting
+ * or remounting the file system, to set all the files to
+ * the given gid.
+ */
+static void set_gid(struct dentry *parent, kgid_t gid)
+{
+ struct dentry *this_parent;
+ struct list_head *next;
+
+ this_parent = parent;
+ spin_lock(&this_parent->d_lock);
+
+ change_gid(this_parent, gid);
+repeat:
+ next = this_parent->d_subdirs.next;
+resume:
+ while (next != &this_parent->d_subdirs) {
+ struct list_head *tmp = next;
+ struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
+ next = tmp->next;
+
+ spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
+
+ change_gid(dentry, gid);
+
+ if (!list_empty(&dentry->d_subdirs)) {
+ spin_unlock(&this_parent->d_lock);
+ spin_release(&dentry->d_lock.dep_map, _RET_IP_);
+ this_parent = dentry;
+ spin_acquire(&this_parent->d_lock.dep_map, 0, 1, _RET_IP_);
+ goto repeat;
+ }
+ spin_unlock(&dentry->d_lock);
+ }
+ /*
+ * All done at this level ... ascend and resume the search.
+ */
+ rcu_read_lock();
+ascend:
+ if (this_parent != parent) {
+ struct dentry *child = this_parent;
+ this_parent = child->d_parent;
+
+ spin_unlock(&child->d_lock);
+ spin_lock(&this_parent->d_lock);
+
+ /* go into the first sibling still alive */
+ do {
+ next = child->d_child.next;
+ if (next == &this_parent->d_subdirs)
+ goto ascend;
+ child = list_entry(next, struct dentry, d_child);
+ } while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED));
+ rcu_read_unlock();
+ goto resume;
+ }
+ rcu_read_unlock();
+ spin_unlock(&this_parent->d_lock);
+ return;
+}
+
static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts)
{
substring_t args[MAX_OPT_ARGS];
if (!gid_valid(gid))
return -EINVAL;
opts->gid = gid;
+ set_gid(tracefs_mount->mnt_root, gid);
break;
case Opt_mode:
if (match_octal(&args[0], &option))
inode->i_mode = mode;
inode->i_fop = fops ? fops : &tracefs_file_operations;
inode->i_private = data;
+ inode->i_uid = d_inode(dentry->d_parent)->i_uid;
+ inode->i_gid = d_inode(dentry->d_parent)->i_gid;
d_instantiate(dentry, inode);
fsnotify_create(dentry->d_parent->d_inode, dentry);
return end_creating(dentry);
inode->i_mode = S_IFDIR | S_IRWXU | S_IRUSR| S_IRGRP | S_IXUSR | S_IXGRP;
inode->i_op = ops;
inode->i_fop = &simple_dir_operations;
+ inode->i_uid = d_inode(dentry->d_parent)->i_uid;
+ inode->i_gid = d_inode(dentry->d_parent)->i_gid;
/* directory inodes start off with i_nlink == 2 (for "." entry) */
inc_nlink(inode);
xfs_remount_ro(
struct xfs_mount *mp)
{
- int error;
+ struct xfs_icwalk icw = {
+ .icw_flags = XFS_ICWALK_FLAG_SYNC,
+ };
+ int error;
/*
* Cancel background eofb scanning so it cannot race with the final
*/
xfs_blockgc_stop(mp);
- /* Get rid of any leftover CoW reservations... */
- error = xfs_blockgc_free_space(mp, NULL);
+ /*
+ * Clear out all remaining COW staging extents and speculative post-EOF
+ * preallocations so that we don't leave inodes requiring inactivation
+ * cleanups during reclaim on a read-only mount. We must process every
+ * cached inode, so this requires a synchronous cache scan.
+ */
+ error = xfs_blockgc_free_space(mp, &icw);
if (error) {
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
return error;
MODULE_AUTHOR("Damien Le Moal");
MODULE_DESCRIPTION("Zone file system for zoned block devices");
MODULE_LICENSE("GPL");
+MODULE_ALIAS_FS("zonefs");
module_init(zonefs_init);
module_exit(zonefs_exit);
*/
static inline void free_bootmem_page(struct page *page)
{
- unsigned long magic = (unsigned long)page->freelist;
+ unsigned long magic = page->index;
/*
* The reserve_bootmem_region sets the reserved flag on bootmem
struct bpf_trampoline *bpf_trampoline_get(u64 key,
struct bpf_attach_target_info *tgt_info);
void bpf_trampoline_put(struct bpf_trampoline *tr);
+int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs);
#define BPF_DISPATCHER_INIT(_name) { \
.mutex = __MUTEX_INITIALIZER(_name.mutex), \
.func = &_name##_func, \
* kprobes, tracepoints) to prevent deadlocks on map operations as any of
* these events can happen inside a region which holds a map bucket lock
* and can deadlock on it.
- *
- * Use the preemption safe inc/dec variants on RT because migrate disable
- * is preemptible on RT and preemption in the middle of the RMW operation
- * might lead to inconsistent state. Use the raw variants for non RT
- * kernels as migrate_disable() maps to preempt_disable() so the slightly
- * more expensive save operation can be avoided.
*/
static inline void bpf_disable_instrumentation(void)
{
migrate_disable();
- if (IS_ENABLED(CONFIG_PREEMPT_RT))
- this_cpu_inc(bpf_prog_active);
- else
- __this_cpu_inc(bpf_prog_active);
+ this_cpu_inc(bpf_prog_active);
}
static inline void bpf_enable_instrumentation(void)
{
- if (IS_ENABLED(CONFIG_PREEMPT_RT))
- this_cpu_dec(bpf_prog_active);
- else
- __this_cpu_dec(bpf_prog_active);
+ this_cpu_dec(bpf_prog_active);
migrate_enable();
}
struct module *owner;
};
-struct kfunc_btf_id_list;
+struct kfunc_btf_id_list {
+ struct list_head list;
+ struct mutex mutex;
+};
#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
struct kfunc_btf_id_set *s);
bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id,
struct module *owner);
+
+extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list;
+extern struct kfunc_btf_id_list prog_test_kfunc_list;
#else
static inline void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
struct kfunc_btf_id_set *s)
{
return false;
}
+
+static struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list __maybe_unused;
+static struct kfunc_btf_id_list prog_test_kfunc_list __maybe_unused;
#endif
#define DEFINE_KFUNC_BTF_ID_SET(set, name) \
struct kfunc_btf_id_set name = { LIST_HEAD_INIT(name.list), (set), \
THIS_MODULE }
-extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list;
-extern struct kfunc_btf_id_list prog_test_kfunc_list;
-
#endif
#define _LINUX_CACHEINFO_H
#include <linux/bitops.h>
-#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/smp.h>
*/
#include <linux/math.h>
+#include <linux/sched.h>
extern unsigned long loops_per_jiffy;
void __attribute__((weak)) calibration_delay_done(void);
void msleep(unsigned int msecs);
unsigned long msleep_interruptible(unsigned int msecs);
-void usleep_range(unsigned long min, unsigned long max);
+void usleep_range_state(unsigned long min, unsigned long max,
+ unsigned int state);
+
+static inline void usleep_range(unsigned long min, unsigned long max)
+{
+ usleep_range_state(min, max, TASK_UNINTERRUPTIBLE);
+}
+
+static inline void usleep_idle_range(unsigned long min, unsigned long max)
+{
+ usleep_range_state(min, max, TASK_IDLE);
+}
static inline void ssleep(unsigned int seconds)
{
#include <linux/klist.h>
#include <linux/pm.h>
#include <linux/device/bus.h>
+#include <linux/module.h>
/**
* enum probe_type - device driver probe type to try
#define __LINUX_FILTER_H__
#include <linux/atomic.h>
+#include <linux/bpf.h>
#include <linux/refcount.h>
#include <linux/compat.h>
#include <linux/skbuff.h>
#include <asm/byteorder.h>
#include <uapi/linux/filter.h>
-#include <uapi/linux/bpf.h>
struct sk_buff;
struct sock;
* This uses migrate_disable/enable() explicitly to document that the
* invocation of a BPF program does not require reentrancy protection
* against a BPF program which is invoked from a preempting task.
- *
- * For non RT enabled kernels migrate_disable/enable() maps to
- * preempt_disable/enable(), i.e. it disables also preemption.
*/
static inline u32 bpf_prog_run_pin_on_cpu(const struct bpf_prog *prog,
const void *ctx)
return hdev->ll_driver == driver;
}
+static inline bool hid_is_usb(struct hid_device *hdev)
+{
+ return hid_is_using_ll_driver(hdev, &usb_hid_driver);
+}
+
#define PM_HINT_FULLON 1<<5
#define PM_HINT_NORMAL 1<<1
struct kmem_cache;
struct page;
+struct slab;
struct vm_struct;
struct task_struct;
return 0;
}
-void __kasan_poison_slab(struct page *page);
-static __always_inline void kasan_poison_slab(struct page *page)
+void __kasan_poison_slab(struct slab *slab);
+static __always_inline void kasan_poison_slab(struct slab *slab)
{
if (kasan_enabled())
- __kasan_poison_slab(page);
+ __kasan_poison_slab(slab);
}
void __kasan_unpoison_object_data(struct kmem_cache *cache, void *object);
slab_flags_t *flags) {}
static inline void kasan_cache_create_kmalloc(struct kmem_cache *cache) {}
static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; }
-static inline void kasan_poison_slab(struct page *page) {}
+static inline void kasan_poison_slab(struct slab *slab) {}
static inline void kasan_unpoison_object_data(struct kmem_cache *cache,
void *object) {}
static inline void kasan_poison_object_data(struct kmem_cache *cache,
return folio->memcg_data & MEMCG_DATA_KMEM;
}
-/*
- * page_objcgs - get the object cgroups vector associated with a page
- * @page: a pointer to the page struct
- *
- * Returns a pointer to the object cgroups vector associated with the page,
- * or NULL. This function assumes that the page is known to have an
- * associated object cgroups vector. It's not safe to call this function
- * against pages, which might have an associated memory cgroup: e.g.
- * kernel stack pages.
- */
-static inline struct obj_cgroup **page_objcgs(struct page *page)
-{
- unsigned long memcg_data = READ_ONCE(page->memcg_data);
-
- VM_BUG_ON_PAGE(memcg_data && !(memcg_data & MEMCG_DATA_OBJCGS), page);
- VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page);
-
- return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
-}
-
-/*
- * page_objcgs_check - get the object cgroups vector associated with a page
- * @page: a pointer to the page struct
- *
- * Returns a pointer to the object cgroups vector associated with the page,
- * or NULL. This function is safe to use if the page can be directly associated
- * with a memory cgroup.
- */
-static inline struct obj_cgroup **page_objcgs_check(struct page *page)
-{
- unsigned long memcg_data = READ_ONCE(page->memcg_data);
-
- if (!memcg_data || !(memcg_data & MEMCG_DATA_OBJCGS))
- return NULL;
-
- VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page);
-
- return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
-}
#else
static inline bool folio_memcg_kmem(struct folio *folio)
return false;
}
-static inline struct obj_cgroup **page_objcgs(struct page *page)
-{
- return NULL;
-}
-
-static inline struct obj_cgroup **page_objcgs_check(struct page *page)
-{
- return NULL;
-}
#endif
static inline bool PageMemcgKmem(struct page *page)
int mhi_pm_resume(struct mhi_controller *mhi_cntrl);
/**
+ * mhi_pm_resume_force - Force resume MHI from suspended state
+ * @mhi_cntrl: MHI controller
+ *
+ * Resume the device irrespective of its MHI state. As per the MHI spec, devices
+ * has to be in M3 state during resume. But some devices seem to be in a
+ * different MHI state other than M3 but they continue working fine if allowed.
+ * This API is intented to be used for such devices.
+ *
+ * Return: 0 if the resume succeeds, a negative error code otherwise
+ */
+int mhi_pm_resume_force(struct mhi_controller *mhi_cntrl);
+
+/**
* mhi_download_rddm_image - Download ramdump image from device for
* debugging purpose.
* @mhi_cntrl: MHI controller
return compound_head(page);
}
+static inline struct folio *virt_to_folio(const void *x)
+{
+ struct page *page = virt_to_page(x);
+
+ return page_folio(page);
+}
+
void __put_page(struct page *page);
void put_pages_list(struct list_head *pages);
#define page_address_init() do { } while(0)
#endif
+static inline void *folio_address(const struct folio *folio)
+{
+ return page_address(&folio->page);
+}
+
extern void *page_rmapping(struct page *page);
extern struct anon_vma *page_anon_vma(struct page *page);
extern pgoff_t __page_file_index(struct page *page);
* in each subpage, but you may need to restore some of their values
* afterwards.
*
- * SLUB uses cmpxchg_double() to atomically update its freelist and
- * counters. That requires that freelist & counters be adjacent and
- * double-word aligned. We align all struct pages to double-word
- * boundaries, and ensure that 'freelist' is aligned within the
- * struct.
+ * SLUB uses cmpxchg_double() to atomically update its freelist and counters.
+ * That requires that freelist & counters in struct slab be adjacent and
+ * double-word aligned. Because struct slab currently just reinterprets the
+ * bits of struct page, we align all struct pages to double-word boundaries,
+ * and ensure that 'freelist' is aligned within struct slab.
*/
#ifdef CONFIG_HAVE_ALIGNED_STRUCT_PAGE
#define _struct_page_alignment __aligned(2 * sizeof(unsigned long))
#define _LINUX_PERCPU_REFCOUNT_H
#include <linux/atomic.h>
-#include <linux/kernel.h>
#include <linux/percpu.h>
#include <linux/rcupdate.h>
+#include <linux/types.h>
#include <linux/gfp.h>
struct percpu_ref;
* @mac_managed_pm: Set true if MAC driver takes of suspending/resuming PHY
* @state: State of the PHY for management purposes
* @dev_flags: Device-specific flags used by the PHY driver.
- * Bits [15:0] are free to use by the PHY driver to communicate
- * driver specific behavior.
- * Bits [23:16] are currently reserved for future use.
- * Bits [31:24] are reserved for defining generic
- * PHY driver behavior.
+ *
+ * - Bits [15:0] are free to use by the PHY driver to communicate
+ * driver specific behavior.
+ * - Bits [23:16] are currently reserved for future use.
+ * - Bits [31:24] are reserved for defining generic
+ * PHY driver behavior.
* @irq: IRQ number of the PHY's interrupt (-1 if none)
* @phy_timer: The timer for handling the state machine
* @phylink: Pointer to phylink instance for this PHY
* pm_runtime_active - Check whether or not a device is runtime-active.
* @dev: Target device.
*
- * Return %true if runtime PM is enabled for @dev and its runtime PM status is
+ * Return %true if runtime PM is disabled for @dev or its runtime PM status is
* %RPM_ACTIVE, or %false otherwise.
*
* Note that the return value of this function can only be trusted if it is
* best to shut-down regulator(s) or reboot the SOC if error
* handling is repeatedly failing. If fatal_cnt is given the IRQ
* handling is aborted if it fails for fatal_cnt times and die()
- * callback (if populated) or BUG() is called to try to prevent
+ * callback (if populated) is called. If die() is not populated
+ * poweroff for the system is attempted in order to prevent any
* further damage.
* @reread_ms: The time which is waited before attempting to re-read status
* at the worker if IC reading fails. Immediate re-read is done
* @data: Driver private data pointer which will be passed as such to
* the renable, map_event and die callbacks in regulator_irq_data.
* @die: Protection callback. If IC status reading or recovery actions
- * fail fatal_cnt times this callback or BUG() is called. This
- * callback should implement a final protection attempt like
- * disabling the regulator. If protection succeeded this may
- * return 0. If anything else is returned the core assumes final
- * protection failed and calls BUG() as a last resort.
+ * fail fatal_cnt times this callback is called or system is
+ * powered off. This callback should implement a final protection
+ * attempt like disabling the regulator. If protection succeeded
+ * die() may return 0. If anything else is returned the core
+ * assumes final protection failed and attempts to perform a
+ * poweroff as a last resort.
* @map_event: Driver callback to map IRQ status into regulator devices with
* events / errors. NOTE: callback MUST initialize both the
* errors and notifs for all rdevs which it signals having
void kmem_dump_obj(void *object);
#endif
-#ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR
-void __check_heap_object(const void *ptr, unsigned long n, struct page *page,
- bool to_user);
-#else
-static inline void __check_heap_object(const void *ptr, unsigned long n,
- struct page *page, bool to_user) { }
-#endif
-
/*
* Some archs want to perform DMA into kmalloc caches and need a guaranteed
* alignment larger than the alignment of a 64-bit integer.
struct kmem_cache_node *node[MAX_NUMNODES];
};
-static inline void *nearest_obj(struct kmem_cache *cache, struct page *page,
+static inline void *nearest_obj(struct kmem_cache *cache, const struct slab *slab,
void *x)
{
- void *object = x - (x - page->s_mem) % cache->size;
- void *last_object = page->s_mem + (cache->num - 1) * cache->size;
+ void *object = x - (x - slab->s_mem) % cache->size;
+ void *last_object = slab->s_mem + (cache->num - 1) * cache->size;
if (unlikely(object > last_object))
return last_object;
* reciprocal_divide(offset, cache->reciprocal_buffer_size)
*/
static inline unsigned int obj_to_index(const struct kmem_cache *cache,
- const struct page *page, void *obj)
+ const struct slab *slab, void *obj)
{
- u32 offset = (obj - page->s_mem);
+ u32 offset = (obj - slab->s_mem);
return reciprocal_divide(offset, cache->reciprocal_buffer_size);
}
-static inline int objs_per_slab_page(const struct kmem_cache *cache,
- const struct page *page)
+static inline int objs_per_slab(const struct kmem_cache *cache,
+ const struct slab *slab)
{
- if (is_kfence_address(page_address(page)))
+ if (is_kfence_address(slab_address(slab)))
return 1;
return cache->num;
}
struct kmem_cache_cpu {
void **freelist; /* Pointer to next available object */
unsigned long tid; /* Globally unique transaction id */
- struct page *page; /* The slab from which we are allocating */
+ struct slab *slab; /* The slab from which we are allocating */
#ifdef CONFIG_SLUB_CPU_PARTIAL
- struct page *partial; /* Partially allocated frozen slabs */
+ struct slab *partial; /* Partially allocated frozen slabs */
#endif
local_lock_t lock; /* Protects the fields above */
#ifdef CONFIG_SLUB_STATS
#ifdef CONFIG_SLUB_CPU_PARTIAL
/* Number of per cpu partial objects to keep around */
unsigned int cpu_partial;
- /* Number of per cpu partial pages to keep around */
- unsigned int cpu_partial_pages;
+ /* Number of per cpu partial slabs to keep around */
+ unsigned int cpu_partial_slabs;
#endif
struct kmem_cache_order_objects oo;
}
#endif
-void object_err(struct kmem_cache *s, struct page *page,
- u8 *object, char *reason);
-
void *fixup_red_left(struct kmem_cache *s, void *p);
-static inline void *nearest_obj(struct kmem_cache *cache, struct page *page,
+static inline void *nearest_obj(struct kmem_cache *cache, const struct slab *slab,
void *x) {
- void *object = x - (x - page_address(page)) % cache->size;
- void *last_object = page_address(page) +
- (page->objects - 1) * cache->size;
+ void *object = x - (x - slab_address(slab)) % cache->size;
+ void *last_object = slab_address(slab) +
+ (slab->objects - 1) * cache->size;
void *result = (unlikely(object > last_object)) ? last_object : object;
result = fixup_red_left(cache, result);
}
static inline unsigned int obj_to_index(const struct kmem_cache *cache,
- const struct page *page, void *obj)
+ const struct slab *slab, void *obj)
{
if (is_kfence_address(obj))
return 0;
- return __obj_to_index(cache, page_address(page), obj);
+ return __obj_to_index(cache, slab_address(slab), obj);
}
-static inline int objs_per_slab_page(const struct kmem_cache *cache,
- const struct page *page)
+static inline int objs_per_slab(const struct kmem_cache *cache,
+ const struct slab *slab)
{
- return page->objects;
+ return slab->objects;
}
#endif /* _LINUX_SLUB_DEF_H */
void __wake_up_locked_sync_key(struct wait_queue_head *wq_head, unsigned int mode, void *key);
void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr);
void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode);
+void __wake_up_pollfree(struct wait_queue_head *wq_head);
#define wake_up(x) __wake_up(x, TASK_NORMAL, 1, NULL)
#define wake_up_nr(x, nr) __wake_up(x, TASK_NORMAL, nr, NULL)
#define wake_up_interruptible_sync_poll_locked(x, m) \
__wake_up_locked_sync_key((x), TASK_INTERRUPTIBLE, poll_to_key(m))
+/**
+ * wake_up_pollfree - signal that a polled waitqueue is going away
+ * @wq_head: the wait queue head
+ *
+ * In the very rare cases where a ->poll() implementation uses a waitqueue whose
+ * lifetime is tied to a task rather than to the 'struct file' being polled,
+ * this function must be called before the waitqueue is freed so that
+ * non-blocking polls (e.g. epoll) are notified that the queue is going away.
+ *
+ * The caller must also RCU-delay the freeing of the wait_queue_head, e.g. via
+ * an explicit synchronize_rcu() or call_rcu(), or via SLAB_TYPESAFE_BY_RCU.
+ */
+static inline void wake_up_pollfree(struct wait_queue_head *wq_head)
+{
+ /*
+ * For performance reasons, we don't always take the queue lock here.
+ * Therefore, we might race with someone removing the last entry from
+ * the queue, and proceed while they still hold the queue lock.
+ * However, rcu_read_lock() is required to be held in such cases, so we
+ * can safely proceed with an RCU-delayed free.
+ */
+ if (waitqueue_active(wq_head))
+ __wake_up_pollfree(wq_head);
+}
+
#define ___wait_cond_timeout(condition) \
({ \
bool __cond = (condition); \
struct alb_bond_info {
struct tlb_client_info *tx_hashtbl; /* Dynamically allocated */
u32 unbalanced_load;
- int tx_rebalance_counter;
+ atomic_t tx_rebalance_counter;
int lp_counter;
/* -------- rlb parameters -------- */
int rlb_enabled;
sk_rx_queue_update(sk, skb);
}
+/* Variant of sk_mark_napi_id() for passive flow setup,
+ * as sk->sk_napi_id and sk->sk_rx_queue_mapping content
+ * needs to be set.
+ */
+static inline void sk_mark_napi_id_set(struct sock *sk,
+ const struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+ WRITE_ONCE(sk->sk_napi_id, skb->napi_id);
+#endif
+ sk_rx_queue_set(sk, skb);
+}
+
static inline void __sk_mark_napi_id_once(struct sock *sk, unsigned int napi_id)
{
#ifdef CONFIG_NET_RX_BUSY_POLL
/* jiffies until ct expires, 0 if already expired */
static inline unsigned long nf_ct_expires(const struct nf_conn *ct)
{
- s32 timeout = ct->timeout - nfct_time_stamp;
+ s32 timeout = READ_ONCE(ct->timeout) - nfct_time_stamp;
return timeout > 0 ? timeout : 0;
}
static inline bool nf_ct_is_expired(const struct nf_conn *ct)
{
- return (__s32)(ct->timeout - nfct_time_stamp) <= 0;
+ return (__s32)(READ_ONCE(ct->timeout) - nfct_time_stamp) <= 0;
}
/* use after obtaining a reference count */
static inline void nf_ct_offload_timeout(struct nf_conn *ct)
{
if (nf_ct_expires(ct) < NF_CT_DAY / 2)
- ct->timeout = nfct_time_stamp + NF_CT_DAY;
+ WRITE_ONCE(ct->timeout, nfct_time_stamp + NF_CT_DAY);
}
struct kernel_param;
#define POLLRDHUP 0x2000
#endif
-#define POLLFREE (__force __poll_t)0x4000 /* currently only for epoll */
+#define POLLFREE (__force __poll_t)0x4000
#define POLL_BUSY_LOOP (__force __poll_t)0x8000
* MPTCP_EVENT_REMOVED: token, rem_id
* An address has been lost by the peer.
*
- * MPTCP_EVENT_SUB_ESTABLISHED: token, family, saddr4 | saddr6,
- * daddr4 | daddr6, sport, dport, backup,
- * if_idx [, error]
+ * MPTCP_EVENT_SUB_ESTABLISHED: token, family, loc_id, rem_id,
+ * saddr4 | saddr6, daddr4 | daddr6, sport,
+ * dport, backup, if_idx [, error]
* A new subflow has been established. 'error' should not be set.
*
- * MPTCP_EVENT_SUB_CLOSED: token, family, saddr4 | saddr6, daddr4 | daddr6,
- * sport, dport, backup, if_idx [, error]
+ * MPTCP_EVENT_SUB_CLOSED: token, family, loc_id, rem_id, saddr4 | saddr6,
+ * daddr4 | daddr6, sport, dport, backup, if_idx
+ * [, error]
* A subflow has been closed. An error (copy of sk_err) could be set if an
* error has been detected for this subflow.
*
- * MPTCP_EVENT_SUB_PRIORITY: token, family, saddr4 | saddr6, daddr4 | daddr6,
- * sport, dport, backup, if_idx [, error]
- * The priority of a subflow has changed. 'error' should not be set.
+ * MPTCP_EVENT_SUB_PRIORITY: token, family, loc_id, rem_id, saddr4 | saddr6,
+ * daddr4 | daddr6, sport, dport, backup, if_idx
+ * [, error]
+ * The priority of a subflow has changed. 'error' should not be set.
*/
enum mptcp_event_type {
MPTCP_EVENT_UNSPEC = 0,
#define _STK_LIM (8*1024*1024)
/*
- * GPG2 wants 64kB of mlocked memory, to make sure pass phrases
- * and other sensitive information are never written to disk.
+ * Limit the amount of locked memory by some sane default:
+ * root can always increase this limit if needed.
+ *
+ * The main use-cases are (1) preventing sensitive memory
+ * from being swapped; (2) real-time operations; (3) via
+ * IOURING_REGISTER_BUFFERS.
+ *
+ * The first two don't need much. The latter will take as
+ * much as it can get. 8MB is a reasonably sane default.
*/
-#define MLOCK_LIMIT ((PAGE_SIZE > 64*1024) ? PAGE_SIZE : 64*1024)
+#define MLOCK_LIMIT (8*1024*1024)
/*
* Due to binary compatibility, the actual resource numbers
{
int rc = 0;
struct sk_buff *skb;
- static unsigned int failed = 0;
+ unsigned int failed = 0;
/* NOTE: kauditd_thread takes care of all our locking, we just use
* the netlink info passed to us (e.g. sk and portid) */
continue;
}
+retry:
/* grab an extra skb reference in case of error */
skb_get(skb);
rc = netlink_unicast(sk, skb, portid, 0);
if (rc < 0) {
- /* fatal failure for our queue flush attempt? */
+ /* send failed - try a few times unless fatal error */
if (++failed >= retry_limit ||
rc == -ECONNREFUSED || rc == -EPERM) {
- /* yes - error processing for the queue */
sk = NULL;
if (err_hook)
(*err_hook)(skb);
- if (!skb_hook)
- goto out;
- /* keep processing with the skb_hook */
+ if (rc == -EAGAIN)
+ rc = 0;
+ /* continue to drain the queue */
continue;
} else
- /* no - requeue to preserve ordering */
- skb_queue_head(queue, skb);
+ goto retry;
} else {
- /* it worked - drop the extra reference and continue */
+ /* skb sent - drop the extra reference and continue */
consume_skb(skb);
failed = 0;
}
}
-out:
return (rc >= 0 ? 0 : rc);
}
audit_panic("cannot initialize netlink socket in namespace");
return -ENOMEM;
}
- aunet->sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT;
+ /* limit the timeout in case auditd is blocked/stopped */
+ aunet->sk->sk_sndtimeo = HZ / 10;
return 0;
}
/* BTF ID set registration API for modules */
-struct kfunc_btf_id_list {
- struct list_head list;
- struct mutex mutex;
-};
-
#ifdef CONFIG_DEBUG_INFO_BTF_MODULES
void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
{
struct kfunc_btf_id_set *s;
- if (!owner)
- return false;
mutex_lock(&klist->mutex);
list_for_each_entry(s, &klist->list, list) {
if (s->owner == owner && btf_id_set_contains(s->set, kfunc_id)) {
return false;
}
-#endif
-
#define DEFINE_KFUNC_BTF_ID_LIST(name) \
struct kfunc_btf_id_list name = { LIST_HEAD_INIT(name.list), \
__MUTEX_INITIALIZER(name.mutex) }; \
DEFINE_KFUNC_BTF_ID_LIST(bpf_tcp_ca_kfunc_list);
DEFINE_KFUNC_BTF_ID_LIST(prog_test_kfunc_list);
+
+#endif
reg->var_off = tnum_or(tnum_clear_subreg(var64_off), var32_off);
}
+static bool __reg32_bound_s64(s32 a)
+{
+ return a >= 0 && a <= S32_MAX;
+}
+
static void __reg_assign_32_into_64(struct bpf_reg_state *reg)
{
reg->umin_value = reg->u32_min_value;
reg->umax_value = reg->u32_max_value;
- /* Attempt to pull 32-bit signed bounds into 64-bit bounds
- * but must be positive otherwise set to worse case bounds
- * and refine later from tnum.
+
+ /* Attempt to pull 32-bit signed bounds into 64-bit bounds but must
+ * be positive otherwise set to worse case bounds and refine later
+ * from tnum.
*/
- if (reg->s32_min_value >= 0 && reg->s32_max_value >= 0)
- reg->smax_value = reg->s32_max_value;
- else
- reg->smax_value = U32_MAX;
- if (reg->s32_min_value >= 0)
+ if (__reg32_bound_s64(reg->s32_min_value) &&
+ __reg32_bound_s64(reg->s32_max_value)) {
reg->smin_value = reg->s32_min_value;
- else
+ reg->smax_value = reg->s32_max_value;
+ } else {
reg->smin_value = 0;
+ reg->smax_value = U32_MAX;
+ }
}
static void __reg_combine_32_into_64(struct bpf_reg_state *reg)
*/
if (insn->src_reg != BPF_REG_FP)
return 0;
- if (BPF_SIZE(insn->code) != BPF_DW)
- return 0;
/* dreg = *(u64 *)[fp - off] was a fill from the stack.
* that [fp - off] slot contains scalar that needs to be
/* scalars can only be spilled into stack */
if (insn->dst_reg != BPF_REG_FP)
return 0;
- if (BPF_SIZE(insn->code) != BPF_DW)
- return 0;
spi = (-insn->off - 1) / BPF_REG_SIZE;
if (spi >= 64) {
verbose(env, "BUG spi %d\n", spi);
if (insn->imm == BPF_CMPXCHG) {
/* Check comparison of R0 with memory location */
- err = check_reg_arg(env, BPF_REG_0, SRC_OP);
+ const u32 aux_reg = BPF_REG_0;
+
+ err = check_reg_arg(env, aux_reg, SRC_OP);
if (err)
return err;
+
+ if (is_pointer_value(env, aux_reg)) {
+ verbose(env, "R%d leaks addr into mem\n", aux_reg);
+ return -EACCES;
+ }
}
if (is_pointer_value(env, insn->src_reg)) {
load_reg = -1;
}
- /* check whether we can read the memory */
+ /* Check whether we can read the memory, with second call for fetch
+ * case to simulate the register fill.
+ */
err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
- BPF_SIZE(insn->code), BPF_READ, load_reg, true);
+ BPF_SIZE(insn->code), BPF_READ, -1, true);
+ if (!err && load_reg >= 0)
+ err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
+ BPF_SIZE(insn->code), BPF_READ, load_reg,
+ true);
if (err)
return err;
- /* check whether we can write into the same memory */
+ /* Check whether we can write into the same memory. */
err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_WRITE, -1, true);
if (err)
insn->dst_reg);
}
zext_32_to_64(dst_reg);
+
+ __update_reg_bounds(dst_reg);
+ __reg_deduce_bounds(dst_reg);
+ __reg_bound_offset(dst_reg);
}
} else {
/* case: R = imm
new_range = dst_reg->off;
if (range_right_open)
- new_range--;
+ new_range++;
/* Examples for register markings:
*
* - the VCPU on which owner runs is preempted
*/
if (!owner->on_cpu || need_resched() ||
- rt_mutex_waiter_is_top_waiter(lock, waiter) ||
+ !rt_mutex_waiter_is_top_waiter(lock, waiter) ||
vcpu_is_preempted(task_cpu(owner))) {
res = false;
break;
}
EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */
+void __wake_up_pollfree(struct wait_queue_head *wq_head)
+{
+ __wake_up(wq_head, TASK_NORMAL, 0, poll_to_key(EPOLLHUP | POLLFREE));
+ /* POLLFREE must have cleared the queue. */
+ WARN_ON_ONCE(waitqueue_active(wq_head));
+}
+
/*
* Note: we use "set_current_state()" _after_ the wait-queue add,
* because we need a memory barrier there on SMP, so that any
ss_mode != 0))
return -EINVAL;
+ /*
+ * Return before taking any locks if no actual
+ * sigaltstack changes were requested.
+ */
+ if (t->sas_ss_sp == (unsigned long)ss_sp &&
+ t->sas_ss_size == ss_size &&
+ t->sas_ss_flags == ss_flags)
+ return 0;
+
sigaltstack_lock();
if (ss_mode == SS_DISABLE) {
ss_size = 0;
timekeeping_forward_now(tk);
xt = tk_xtime(tk);
- ts_delta.tv_sec = ts->tv_sec - xt.tv_sec;
- ts_delta.tv_nsec = ts->tv_nsec - xt.tv_nsec;
+ ts_delta = timespec64_sub(*ts, xt);
if (timespec64_compare(&tk->wall_to_monotonic, &ts_delta) > 0) {
ret = -EINVAL;
EXPORT_SYMBOL(msleep_interruptible);
/**
- * usleep_range - Sleep for an approximate time
- * @min: Minimum time in usecs to sleep
- * @max: Maximum time in usecs to sleep
+ * usleep_range_state - Sleep for an approximate time in a given state
+ * @min: Minimum time in usecs to sleep
+ * @max: Maximum time in usecs to sleep
+ * @state: State of the current task that will be while sleeping
*
* In non-atomic context where the exact wakeup time is flexible, use
- * usleep_range() instead of udelay(). The sleep improves responsiveness
+ * usleep_range_state() instead of udelay(). The sleep improves responsiveness
* by avoiding the CPU-hogging busy-wait of udelay(), and the range reduces
* power usage by allowing hrtimers to take advantage of an already-
* scheduled interrupt instead of scheduling a new one just for this sleep.
*/
-void __sched usleep_range(unsigned long min, unsigned long max)
+void __sched usleep_range_state(unsigned long min, unsigned long max,
+ unsigned int state)
{
ktime_t exp = ktime_add_us(ktime_get(), min);
u64 delta = (u64)(max - min) * NSEC_PER_USEC;
for (;;) {
- __set_current_state(TASK_UNINTERRUPTIBLE);
+ __set_current_state(state);
/* Do not return before the requested sleep time has elapsed */
if (!schedule_hrtimeout_range(&exp, delta, HRTIMER_MODE_ABS))
break;
}
}
-EXPORT_SYMBOL(usleep_range);
+EXPORT_SYMBOL(usleep_range_state);
{
struct ftrace_direct_func *direct;
struct ftrace_func_entry *entry;
+ struct ftrace_hash *hash;
int ret = -ENODEV;
mutex_lock(&direct_mutex);
if (!entry)
goto out_unlock;
- if (direct_functions->count == 1)
+ hash = direct_ops.func_hash->filter_hash;
+ if (hash->count == 1)
unregister_ftrace_function(&direct_ops);
ret = ftrace_set_filter_ip(&direct_ops, ip, 1, 0);
err = unregister_ftrace_function(ops);
remove_direct_functions_hash(hash, addr);
mutex_unlock(&direct_mutex);
+
+ /* cleanup for possible another register call */
+ ops->func = NULL;
+ ops->trampoline = 0;
return err;
}
EXPORT_SYMBOL_GPL(unregister_ftrace_direct_multi);
argv + consumed, &consumed,
&field_version);
if (IS_ERR(field)) {
- argv_free(argv);
ret = PTR_ERR(field);
- goto err;
+ goto err_free_arg;
}
/*
if (cmd_version > 1 && n_fields_this_loop >= 1) {
synth_err(SYNTH_ERR_INVALID_CMD, errpos(field_str));
ret = -EINVAL;
- goto err;
+ goto err_free_arg;
}
fields[n_fields++] = field;
if (n_fields == SYNTH_FIELDS_MAX) {
synth_err(SYNTH_ERR_TOO_MANY_FIELDS, 0);
ret = -EINVAL;
- goto err;
+ goto err_free_arg;
}
n_fields_this_loop++;
}
+ argv_free(argv);
if (consumed < argc) {
synth_err(SYNTH_ERR_INVALID_CMD, 0);
goto err;
}
- argv_free(argv);
}
if (n_fields == 0) {
kfree(saved_fields);
return ret;
+ err_free_arg:
+ argv_free(argv);
err:
for (i = 0; i < n_fields; i++)
free_synth_field(fields[i]);
bool "Generate BTF typeinfo"
depends on !DEBUG_INFO_SPLIT && !DEBUG_INFO_REDUCED
depends on !GCC_PLUGIN_RANDSTRUCT || COMPILE_TEST
+ depends on BPF_SYSCALL
help
Generate deduplicated BTF type information from DWARF debug info.
Turning this on expects presence of pahole tool, which will convert
# UP and nommu archs use km based percpu allocator
#
config NEED_PER_CPU_KM
- depends on !SMP
+ depends on !SMP || !MMU
bool
default y
wb_shutdown(&bdi->wb);
cgwb_bdi_unregister(bdi);
+ /*
+ * If this BDI's min ratio has been set, use bdi_set_min_ratio() to
+ * update the global bdi_min_ratio.
+ */
+ if (bdi->min_ratio)
+ bdi_set_min_ratio(bdi, 0);
+
if (bdi->dev) {
bdi_debug_unregister(bdi);
device_unregister(bdi->dev);
void get_page_bootmem(unsigned long info, struct page *page, unsigned long type)
{
- page->freelist = (void *)type;
+ page->index = type;
SetPagePrivate(page);
set_page_private(page, info);
page_ref_inc(page);
void put_page_bootmem(struct page *page)
{
- unsigned long type;
+ unsigned long type = page->index;
- type = (unsigned long) page->freelist;
BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE);
if (page_ref_dec_return(page) == 1) {
- page->freelist = NULL;
+ page->index = 0;
ClearPagePrivate(page);
set_page_private(page, 0);
INIT_LIST_HEAD(&page->lru);
for (i = 0; i < nr_ids; i++) {
t = damon_new_target(ids[i]);
if (!t) {
- pr_err("Failed to alloc damon_target\n");
/* The caller should do cleanup of the ids itself */
damon_for_each_target_safe(t, next, ctx)
damon_destroy_target(t);
unsigned long aggr_int, unsigned long primitive_upd_int,
unsigned long min_nr_reg, unsigned long max_nr_reg)
{
- if (min_nr_reg < 3) {
- pr_err("min_nr_regions (%lu) must be at least 3\n",
- min_nr_reg);
+ if (min_nr_reg < 3)
return -EINVAL;
- }
- if (min_nr_reg > max_nr_reg) {
- pr_err("invalid nr_regions. min (%lu) > max (%lu)\n",
- min_nr_reg, max_nr_reg);
+ if (min_nr_reg > max_nr_reg)
return -EINVAL;
- }
ctx->sample_interval = sample_int;
ctx->aggr_interval = aggr_int;
static void kdamond_usleep(unsigned long usecs)
{
- if (usecs > 100 * 1000)
- schedule_timeout_interruptible(usecs_to_jiffies(usecs));
+ /* See Documentation/timers/timers-howto.rst for the thresholds */
+ if (usecs > 20 * USEC_PER_MSEC)
+ schedule_timeout_idle(usecs_to_jiffies(usecs));
else
- usleep_range(usecs, usecs + 1);
+ usleep_idle_range(usecs, usecs + 1);
}
/* Returns negative error code if it's not activated but should return */
ctx->callback.after_sampling(ctx))
done = true;
- usleep_range(ctx->sample_interval, ctx->sample_interval + 1);
+ kdamond_usleep(ctx->sample_interval);
if (ctx->primitive.check_accesses)
max_nr_accesses = ctx->primitive.check_accesses(ctx);
&wmarks.low, &parsed);
if (ret != 18)
break;
- if (!damos_action_valid(action)) {
- pr_err("wrong action %d\n", action);
+ if (!damos_action_valid(action))
goto fail;
- }
pos += parsed;
scheme = damon_new_scheme(min_sz, max_sz, min_nr_a, max_nr_a,
struct damon_addr_range *three_regions,
unsigned long *expected, int nr_expected)
{
- struct damon_ctx *ctx = damon_new_ctx();
struct damon_target *t;
struct damon_region *r;
int i;
r = damon_new_region(regions[i * 2], regions[i * 2 + 1]);
damon_add_region(r, t);
}
- damon_add_target(ctx, t);
damon_va_apply_three_regions(t, three_regions);
KUNIT_EXPECT_EQ(test, r->ar.start, expected[i * 2]);
KUNIT_EXPECT_EQ(test, r->ar.end, expected[i * 2 + 1]);
}
-
- damon_destroy_ctx(ctx);
}
/*
new_three_regions, expected, ARRAY_SIZE(expected));
}
-static void damon_test_split_evenly(struct kunit *test)
+static void damon_test_split_evenly_fail(struct kunit *test,
+ unsigned long start, unsigned long end, unsigned int nr_pieces)
{
- struct damon_ctx *c = damon_new_ctx();
- struct damon_target *t;
- struct damon_region *r;
- unsigned long i;
-
- KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(NULL, NULL, 5),
- -EINVAL);
-
- t = damon_new_target(42);
- r = damon_new_region(0, 100);
- KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 0), -EINVAL);
+ struct damon_target *t = damon_new_target(42);
+ struct damon_region *r = damon_new_region(start, end);
damon_add_region(r, t);
- KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 10), 0);
- KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 10u);
+ KUNIT_EXPECT_EQ(test,
+ damon_va_evenly_split_region(t, r, nr_pieces), -EINVAL);
+ KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 1u);
- i = 0;
damon_for_each_region(r, t) {
- KUNIT_EXPECT_EQ(test, r->ar.start, i++ * 10);
- KUNIT_EXPECT_EQ(test, r->ar.end, i * 10);
+ KUNIT_EXPECT_EQ(test, r->ar.start, start);
+ KUNIT_EXPECT_EQ(test, r->ar.end, end);
}
+
damon_free_target(t);
+}
+
+static void damon_test_split_evenly_succ(struct kunit *test,
+ unsigned long start, unsigned long end, unsigned int nr_pieces)
+{
+ struct damon_target *t = damon_new_target(42);
+ struct damon_region *r = damon_new_region(start, end);
+ unsigned long expected_width = (end - start) / nr_pieces;
+ unsigned long i = 0;
- t = damon_new_target(42);
- r = damon_new_region(5, 59);
damon_add_region(r, t);
- KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 5), 0);
- KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 5u);
+ KUNIT_EXPECT_EQ(test,
+ damon_va_evenly_split_region(t, r, nr_pieces), 0);
+ KUNIT_EXPECT_EQ(test, damon_nr_regions(t), nr_pieces);
- i = 0;
damon_for_each_region(r, t) {
- if (i == 4)
+ if (i == nr_pieces - 1)
break;
- KUNIT_EXPECT_EQ(test, r->ar.start, 5 + 10 * i++);
- KUNIT_EXPECT_EQ(test, r->ar.end, 5 + 10 * i);
+ KUNIT_EXPECT_EQ(test,
+ r->ar.start, start + i++ * expected_width);
+ KUNIT_EXPECT_EQ(test, r->ar.end, start + i * expected_width);
}
- KUNIT_EXPECT_EQ(test, r->ar.start, 5 + 10 * i);
- KUNIT_EXPECT_EQ(test, r->ar.end, 59ul);
+ KUNIT_EXPECT_EQ(test, r->ar.start, start + i * expected_width);
+ KUNIT_EXPECT_EQ(test, r->ar.end, end);
damon_free_target(t);
+}
- t = damon_new_target(42);
- r = damon_new_region(5, 6);
- damon_add_region(r, t);
- KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 2), -EINVAL);
- KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 1u);
+static void damon_test_split_evenly(struct kunit *test)
+{
+ KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(NULL, NULL, 5),
+ -EINVAL);
- damon_for_each_region(r, t) {
- KUNIT_EXPECT_EQ(test, r->ar.start, 5ul);
- KUNIT_EXPECT_EQ(test, r->ar.end, 6ul);
- }
- damon_free_target(t);
- damon_destroy_ctx(c);
+ damon_test_split_evenly_fail(test, 0, 100, 0);
+ damon_test_split_evenly_succ(test, 0, 100, 10);
+ damon_test_split_evenly_succ(test, 5, 59, 5);
+ damon_test_split_evenly_fail(test, 5, 6, 2);
}
static struct kunit_case damon_test_cases[] = {
#include <linux/mmu_notifier.h>
#include <linux/page_idle.h>
#include <linux/pagewalk.h>
+#include <linux/sched/mm.h>
#include "prmtv-common.h"
case DAMOS_STAT:
return 0;
default:
- pr_warn("Wrong action %d\n", scheme->action);
return -EINVAL;
}
goto skip;
if (!PageUptodate(page) || PageReadahead(page))
goto skip;
- if (PageHWPoison(page))
- goto skip;
if (!trylock_page(page))
goto skip;
if (page->mapping != mapping)
struct huge_bootmem_page *m = NULL; /* initialize for clang */
int nr_nodes, node;
- if (nid >= nr_online_nodes)
+ if (nid != NUMA_NO_NODE && nid >= nr_online_nodes)
return 0;
/* do node specific alloc */
if (nid != NUMA_NO_NODE) {
}
#endif
-void __kasan_poison_slab(struct page *page)
+void __kasan_poison_slab(struct slab *slab)
{
+ struct page *page = slab_page(slab);
unsigned long i;
for (i = 0; i < compound_nr(page); i++)
/* For caches that either have a constructor or SLAB_TYPESAFE_BY_RCU: */
#ifdef CONFIG_SLAB
/* For SLAB assign tags based on the object index in the freelist. */
- return (u8)obj_to_index(cache, virt_to_head_page(object), (void *)object);
+ return (u8)obj_to_index(cache, virt_to_slab(object), (void *)object);
#else
/*
* For SLUB assign a random tag during slab creation, otherwise reuse
if (is_kfence_address(object))
return false;
- if (unlikely(nearest_obj(cache, virt_to_head_page(object), object) !=
+ if (unlikely(nearest_obj(cache, virt_to_slab(object), object) !=
object)) {
kasan_report_invalid_free(tagged_object, ip);
return true;
void __kasan_slab_free_mempool(void *ptr, unsigned long ip)
{
- struct page *page;
+ struct folio *folio;
- page = virt_to_head_page(ptr);
+ folio = virt_to_folio(ptr);
/*
* Even though this function is only called for kmem_cache_alloc and
* !PageSlab() when the size provided to kmalloc is larger than
* KMALLOC_MAX_SIZE, and kmalloc falls back onto page_alloc.
*/
- if (unlikely(!PageSlab(page))) {
+ if (unlikely(!folio_test_slab(folio))) {
if (____kasan_kfree_large(ptr, ip))
return;
- kasan_poison(ptr, page_size(page), KASAN_FREE_PAGE, false);
+ kasan_poison(ptr, folio_size(folio), KASAN_FREE_PAGE, false);
} else {
- ____kasan_slab_free(page->slab_cache, ptr, ip, false, false);
+ struct slab *slab = folio_slab(folio);
+
+ ____kasan_slab_free(slab->slab_cache, ptr, ip, false, false);
}
}
void * __must_check __kasan_krealloc(const void *object, size_t size, gfp_t flags)
{
- struct page *page;
+ struct slab *slab;
if (unlikely(object == ZERO_SIZE_PTR))
return (void *)object;
*/
kasan_unpoison(object, size, false);
- page = virt_to_head_page(object);
+ slab = virt_to_slab(object);
/* Piggy-back on kmalloc() instrumentation to poison the redzone. */
- if (unlikely(!PageSlab(page)))
+ if (unlikely(!slab))
return __kasan_kmalloc_large(object, size, flags);
else
- return ____kasan_kmalloc(page->slab_cache, object, size, flags);
+ return ____kasan_kmalloc(slab->slab_cache, object, size, flags);
}
bool __kasan_check_byte(const void *address, unsigned long ip)
static void __kasan_record_aux_stack(void *addr, bool can_alloc)
{
- struct page *page = kasan_addr_to_page(addr);
+ struct slab *slab = kasan_addr_to_slab(addr);
struct kmem_cache *cache;
struct kasan_alloc_meta *alloc_meta;
void *object;
- if (is_kfence_address(addr) || !(page && PageSlab(page)))
+ if (is_kfence_address(addr) || !slab)
return;
- cache = page->slab_cache;
- object = nearest_obj(cache, page, addr);
+ cache = slab->slab_cache;
+ object = nearest_obj(cache, slab, addr);
alloc_meta = kasan_get_alloc_meta(cache, object);
if (!alloc_meta)
return;
void kasan_report_invalid_free(void *object, unsigned long ip);
struct page *kasan_addr_to_page(const void *addr);
+struct slab *kasan_addr_to_slab(const void *addr);
depot_stack_handle_t kasan_save_stack(gfp_t flags, bool can_alloc);
void kasan_set_track(struct kasan_track *track, gfp_t flags);
static struct kmem_cache *qlink_to_cache(struct qlist_node *qlink)
{
- return virt_to_head_page(qlink)->slab_cache;
+ return virt_to_slab(qlink)->slab_cache;
}
static void *qlink_to_object(struct qlist_node *qlink, struct kmem_cache *cache)
return NULL;
}
+struct slab *kasan_addr_to_slab(const void *addr)
+{
+ if ((addr >= (void *)PAGE_OFFSET) &&
+ (addr < high_memory))
+ return virt_to_slab(addr);
+ return NULL;
+}
+
static void describe_object_addr(struct kmem_cache *cache, void *object,
const void *addr)
{
pr_err("\n");
if (page && PageSlab(page)) {
- struct kmem_cache *cache = page->slab_cache;
- void *object = nearest_obj(cache, page, addr);
+ struct slab *slab = page_slab(page);
+ struct kmem_cache *cache = slab->slab_cache;
+ void *object = nearest_obj(cache, slab, addr);
describe_object(cache, object, addr, tag);
}
#ifdef CONFIG_KASAN_TAGS_IDENTIFY
struct kasan_alloc_meta *alloc_meta;
struct kmem_cache *cache;
- struct page *page;
+ struct slab *slab;
const void *addr;
void *object;
u8 tag;
tag = get_tag(info->access_addr);
addr = kasan_reset_tag(info->access_addr);
- page = kasan_addr_to_page(addr);
- if (page && PageSlab(page)) {
- cache = page->slab_cache;
- object = nearest_obj(cache, page, (void *)addr);
+ slab = kasan_addr_to_slab(addr);
+ if (slab) {
+ cache = slab->slab_cache;
+ object = nearest_obj(cache, slab, (void *)addr);
alloc_meta = kasan_get_alloc_meta(cache, object);
if (alloc_meta) {
{
struct kfence_metadata *meta = NULL;
unsigned long flags;
- struct page *page;
+ struct slab *slab;
void *addr;
/* Try to obtain a free object. */
alloc_covered_add(alloc_stack_hash, 1);
- /* Set required struct page fields. */
- page = virt_to_page(meta->addr);
- page->slab_cache = cache;
- if (IS_ENABLED(CONFIG_SLUB))
- page->objects = 1;
- if (IS_ENABLED(CONFIG_SLAB))
- page->s_mem = addr;
+ /* Set required slab fields. */
+ slab = virt_to_slab((void *)meta->addr);
+ slab->slab_cache = cache;
+#if defined(CONFIG_SLUB)
+ slab->objects = 1;
+#elif defined(CONFIG_SLAB)
+ slab->s_mem = addr;
+#endif
/* Memory initialization. */
for_each_canary(meta, set_canary_byte);
alloc = kmalloc(size, gfp);
if (is_kfence_address(alloc)) {
- struct page *page = virt_to_head_page(alloc);
+ struct slab *slab = virt_to_slab(alloc);
struct kmem_cache *s = test_cache ?:
kmalloc_caches[kmalloc_type(GFP_KERNEL)][__kmalloc_index(size, false)];
* even for KFENCE objects; these are required so that
* memcg accounting works correctly.
*/
- KUNIT_EXPECT_EQ(test, obj_to_index(s, page, alloc), 0U);
- KUNIT_EXPECT_EQ(test, objs_per_slab_page(s, page), 1);
+ KUNIT_EXPECT_EQ(test, obj_to_index(s, slab, alloc), 0U);
+ KUNIT_EXPECT_EQ(test, objs_per_slab(s, slab), 1);
if (policy == ALLOCATE_ANY)
return alloc;
rcu_read_unlock();
}
-/*
- * mod_objcg_mlstate() may be called with irq enabled, so
- * mod_memcg_lruvec_state() should be used.
- */
-static inline void mod_objcg_mlstate(struct obj_cgroup *objcg,
- struct pglist_data *pgdat,
- enum node_stat_item idx, int nr)
-{
- struct mem_cgroup *memcg;
- struct lruvec *lruvec;
-
- rcu_read_lock();
- memcg = obj_cgroup_memcg(objcg);
- lruvec = mem_cgroup_lruvec(memcg, pgdat);
- mod_memcg_lruvec_state(lruvec, idx, nr);
- rcu_read_unlock();
-}
-
/**
* __count_memcg_events - account VM events in a cgroup
* @memcg: the memory cgroup
}
#endif
-/*
- * Most kmem_cache_alloc() calls are from user context. The irq disable/enable
- * sequence used in this case to access content from object stock is slow.
- * To optimize for user context access, there are now two object stocks for
- * task context and interrupt context access respectively.
- *
- * The task context object stock can be accessed by disabling preemption only
- * which is cheap in non-preempt kernel. The interrupt context object stock
- * can only be accessed after disabling interrupt. User context code can
- * access interrupt object stock, but not vice versa.
- */
-static inline struct obj_stock *get_obj_stock(unsigned long *pflags)
-{
- struct memcg_stock_pcp *stock;
-
- if (likely(in_task())) {
- *pflags = 0UL;
- preempt_disable();
- stock = this_cpu_ptr(&memcg_stock);
- return &stock->task_obj;
- }
-
- local_irq_save(*pflags);
- stock = this_cpu_ptr(&memcg_stock);
- return &stock->irq_obj;
-}
-
-static inline void put_obj_stock(unsigned long flags)
-{
- if (likely(in_task()))
- preempt_enable();
- else
- local_irq_restore(flags);
-}
-
/**
* consume_stock: Try to consume stocked charge on this cpu.
* @memcg: memcg to consume from.
*/
#define OBJCGS_CLEAR_MASK (__GFP_DMA | __GFP_RECLAIMABLE | __GFP_ACCOUNT)
-int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
- gfp_t gfp, bool new_page)
+/*
+ * Most kmem_cache_alloc() calls are from user context. The irq disable/enable
+ * sequence used in this case to access content from object stock is slow.
+ * To optimize for user context access, there are now two object stocks for
+ * task context and interrupt context access respectively.
+ *
+ * The task context object stock can be accessed by disabling preemption only
+ * which is cheap in non-preempt kernel. The interrupt context object stock
+ * can only be accessed after disabling interrupt. User context code can
+ * access interrupt object stock, but not vice versa.
+ */
+static inline struct obj_stock *get_obj_stock(unsigned long *pflags)
+{
+ struct memcg_stock_pcp *stock;
+
+ if (likely(in_task())) {
+ *pflags = 0UL;
+ preempt_disable();
+ stock = this_cpu_ptr(&memcg_stock);
+ return &stock->task_obj;
+ }
+
+ local_irq_save(*pflags);
+ stock = this_cpu_ptr(&memcg_stock);
+ return &stock->irq_obj;
+}
+
+static inline void put_obj_stock(unsigned long flags)
{
- unsigned int objects = objs_per_slab_page(s, page);
+ if (likely(in_task()))
+ preempt_enable();
+ else
+ local_irq_restore(flags);
+}
+
+/*
+ * mod_objcg_mlstate() may be called with irq enabled, so
+ * mod_memcg_lruvec_state() should be used.
+ */
+static inline void mod_objcg_mlstate(struct obj_cgroup *objcg,
+ struct pglist_data *pgdat,
+ enum node_stat_item idx, int nr)
+{
+ struct mem_cgroup *memcg;
+ struct lruvec *lruvec;
+
+ rcu_read_lock();
+ memcg = obj_cgroup_memcg(objcg);
+ lruvec = mem_cgroup_lruvec(memcg, pgdat);
+ mod_memcg_lruvec_state(lruvec, idx, nr);
+ rcu_read_unlock();
+}
+
+int memcg_alloc_slab_cgroups(struct slab *slab, struct kmem_cache *s,
+ gfp_t gfp, bool new_slab)
+{
+ unsigned int objects = objs_per_slab(s, slab);
unsigned long memcg_data;
void *vec;
gfp &= ~OBJCGS_CLEAR_MASK;
vec = kcalloc_node(objects, sizeof(struct obj_cgroup *), gfp,
- page_to_nid(page));
+ slab_nid(slab));
if (!vec)
return -ENOMEM;
memcg_data = (unsigned long) vec | MEMCG_DATA_OBJCGS;
- if (new_page) {
+ if (new_slab) {
/*
- * If the slab page is brand new and nobody can yet access
- * it's memcg_data, no synchronization is required and
- * memcg_data can be simply assigned.
+ * If the slab is brand new and nobody can yet access its
+ * memcg_data, no synchronization is required and memcg_data can
+ * be simply assigned.
*/
- page->memcg_data = memcg_data;
- } else if (cmpxchg(&page->memcg_data, 0, memcg_data)) {
+ slab->memcg_data = memcg_data;
+ } else if (cmpxchg(&slab->memcg_data, 0, memcg_data)) {
/*
- * If the slab page is already in use, somebody can allocate
- * and assign obj_cgroups in parallel. In this case the existing
+ * If the slab is already in use, somebody can allocate and
+ * assign obj_cgroups in parallel. In this case the existing
* objcg vector should be reused.
*/
kfree(vec);
*/
struct mem_cgroup *mem_cgroup_from_obj(void *p)
{
- struct page *page;
+ struct folio *folio;
if (mem_cgroup_disabled())
return NULL;
- page = virt_to_head_page(p);
+ folio = virt_to_folio(p);
/*
* Slab objects are accounted individually, not per-page.
* Memcg membership data for each individual object is saved in
- * the page->obj_cgroups.
+ * slab->memcg_data.
*/
- if (page_objcgs_check(page)) {
- struct obj_cgroup *objcg;
+ if (folio_test_slab(folio)) {
+ struct obj_cgroup **objcgs;
+ struct slab *slab;
unsigned int off;
- off = obj_to_index(page->slab_cache, page, p);
- objcg = page_objcgs(page)[off];
- if (objcg)
- return obj_cgroup_memcg(objcg);
+ slab = folio_slab(folio);
+ objcgs = slab_objcgs(slab);
+ if (!objcgs)
+ return NULL;
+
+ off = obj_to_index(slab->slab_cache, slab, p);
+ if (objcgs[off])
+ return obj_cgroup_memcg(objcgs[off]);
return NULL;
}
/*
- * page_memcg_check() is used here, because page_has_obj_cgroups()
- * check above could fail because the object cgroups vector wasn't set
- * at that moment, but it can be set concurrently.
+ * page_memcg_check() is used here, because in theory we can encounter
+ * a folio where the slab flag has been cleared already, but
+ * slab->memcg_data has not been freed yet
* page_memcg_check(page) will guarantee that a proper memory
* cgroup pointer or NULL will be returned.
*/
- return page_memcg_check(page);
+ return page_memcg_check(folio_page(folio, 0));
}
__always_inline struct obj_cgroup *get_obj_cgroup_from_current(void)
#include <linux/memblock.h>
#include <linux/compaction.h>
#include <linux/rmap.h>
+#include <linux/module.h>
#include <asm/tlbflush.h>
static inline void fixup_objfreelist_debug(struct kmem_cache *cachep,
void **list);
static inline void fixup_slab_list(struct kmem_cache *cachep,
- struct kmem_cache_node *n, struct page *page,
+ struct kmem_cache_node *n, struct slab *slab,
void **list);
static int slab_early_init = 1;
static int slab_max_order = SLAB_MAX_ORDER_LO;
static bool slab_max_order_set __initdata;
-static inline void *index_to_obj(struct kmem_cache *cache, struct page *page,
- unsigned int idx)
+static inline void *index_to_obj(struct kmem_cache *cache,
+ const struct slab *slab, unsigned int idx)
{
- return page->s_mem + cache->size * idx;
+ return slab->s_mem + cache->size * idx;
}
#define BOOT_CPUCACHE_ENTRIES 1
}
static noinline void cache_free_pfmemalloc(struct kmem_cache *cachep,
- struct page *page, void *objp)
+ struct slab *slab, void *objp)
{
struct kmem_cache_node *n;
- int page_node;
+ int slab_node;
LIST_HEAD(list);
- page_node = page_to_nid(page);
- n = get_node(cachep, page_node);
+ slab_node = slab_nid(slab);
+ n = get_node(cachep, slab_node);
spin_lock(&n->list_lock);
- free_block(cachep, &objp, 1, page_node, &list);
+ free_block(cachep, &objp, 1, slab_node, &list);
spin_unlock(&n->list_lock);
slabs_destroy(cachep, &list);
}
static int __cache_free_alien(struct kmem_cache *cachep, void *objp,
- int node, int page_node)
+ int node, int slab_node)
{
struct kmem_cache_node *n;
struct alien_cache *alien = NULL;
n = get_node(cachep, node);
STATS_INC_NODEFREES(cachep);
- if (n->alien && n->alien[page_node]) {
- alien = n->alien[page_node];
+ if (n->alien && n->alien[slab_node]) {
+ alien = n->alien[slab_node];
ac = &alien->ac;
spin_lock(&alien->lock);
if (unlikely(ac->avail == ac->limit)) {
STATS_INC_ACOVERFLOW(cachep);
- __drain_alien_cache(cachep, ac, page_node, &list);
+ __drain_alien_cache(cachep, ac, slab_node, &list);
}
__free_one(ac, objp);
spin_unlock(&alien->lock);
slabs_destroy(cachep, &list);
} else {
- n = get_node(cachep, page_node);
+ n = get_node(cachep, slab_node);
spin_lock(&n->list_lock);
- free_block(cachep, &objp, 1, page_node, &list);
+ free_block(cachep, &objp, 1, slab_node, &list);
spin_unlock(&n->list_lock);
slabs_destroy(cachep, &list);
}
static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
{
- int page_node = page_to_nid(virt_to_page(objp));
+ int slab_node = slab_nid(virt_to_slab(objp));
int node = numa_mem_id();
/*
* Make sure we are not freeing a object from another node to the array
* cache on this cpu.
*/
- if (likely(node == page_node))
+ if (likely(node == slab_node))
return 0;
- return __cache_free_alien(cachep, objp, node, page_node);
+ return __cache_free_alien(cachep, objp, node, slab_node);
}
/*
* did not request dmaable memory, we might get it, but that
* would be relatively rare and ignorable.
*/
-static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags,
+static struct slab *kmem_getpages(struct kmem_cache *cachep, gfp_t flags,
int nodeid)
{
- struct page *page;
+ struct folio *folio;
+ struct slab *slab;
flags |= cachep->allocflags;
- page = __alloc_pages_node(nodeid, flags, cachep->gfporder);
- if (!page) {
+ folio = (struct folio *) __alloc_pages_node(nodeid, flags, cachep->gfporder);
+ if (!folio) {
slab_out_of_memory(cachep, flags, nodeid);
return NULL;
}
- account_slab_page(page, cachep->gfporder, cachep, flags);
- __SetPageSlab(page);
+ slab = folio_slab(folio);
+
+ account_slab(slab, cachep->gfporder, cachep, flags);
+ __folio_set_slab(folio);
/* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */
- if (sk_memalloc_socks() && page_is_pfmemalloc(page))
- SetPageSlabPfmemalloc(page);
+ if (sk_memalloc_socks() && page_is_pfmemalloc(folio_page(folio, 0)))
+ slab_set_pfmemalloc(slab);
- return page;
+ return slab;
}
/*
* Interface to system's page release.
*/
-static void kmem_freepages(struct kmem_cache *cachep, struct page *page)
+static void kmem_freepages(struct kmem_cache *cachep, struct slab *slab)
{
int order = cachep->gfporder;
+ struct folio *folio = slab_folio(slab);
- BUG_ON(!PageSlab(page));
- __ClearPageSlabPfmemalloc(page);
- __ClearPageSlab(page);
- page_mapcount_reset(page);
- /* In union with page->mapping where page allocator expects NULL */
- page->slab_cache = NULL;
+ BUG_ON(!folio_test_slab(folio));
+ __slab_clear_pfmemalloc(slab);
+ __folio_clear_slab(folio);
+ page_mapcount_reset(folio_page(folio, 0));
+ folio->mapping = NULL;
if (current->reclaim_state)
current->reclaim_state->reclaimed_slab += 1 << order;
- unaccount_slab_page(page, order, cachep);
- __free_pages(page, order);
+ unaccount_slab(slab, order, cachep);
+ __free_pages(folio_page(folio, 0), order);
}
static void kmem_rcu_free(struct rcu_head *head)
{
struct kmem_cache *cachep;
- struct page *page;
+ struct slab *slab;
- page = container_of(head, struct page, rcu_head);
- cachep = page->slab_cache;
+ slab = container_of(head, struct slab, rcu_head);
+ cachep = slab->slab_cache;
- kmem_freepages(cachep, page);
+ kmem_freepages(cachep, slab);
}
#if DEBUG
/* Print some data about the neighboring objects, if they
* exist:
*/
- struct page *page = virt_to_head_page(objp);
+ struct slab *slab = virt_to_slab(objp);
unsigned int objnr;
- objnr = obj_to_index(cachep, page, objp);
+ objnr = obj_to_index(cachep, slab, objp);
if (objnr) {
- objp = index_to_obj(cachep, page, objnr - 1);
+ objp = index_to_obj(cachep, slab, objnr - 1);
realobj = (char *)objp + obj_offset(cachep);
pr_err("Prev obj: start=%px, len=%d\n", realobj, size);
print_objinfo(cachep, objp, 2);
}
if (objnr + 1 < cachep->num) {
- objp = index_to_obj(cachep, page, objnr + 1);
+ objp = index_to_obj(cachep, slab, objnr + 1);
realobj = (char *)objp + obj_offset(cachep);
pr_err("Next obj: start=%px, len=%d\n", realobj, size);
print_objinfo(cachep, objp, 2);
#if DEBUG
static void slab_destroy_debugcheck(struct kmem_cache *cachep,
- struct page *page)
+ struct slab *slab)
{
int i;
if (OBJFREELIST_SLAB(cachep) && cachep->flags & SLAB_POISON) {
- poison_obj(cachep, page->freelist - obj_offset(cachep),
+ poison_obj(cachep, slab->freelist - obj_offset(cachep),
POISON_FREE);
}
for (i = 0; i < cachep->num; i++) {
- void *objp = index_to_obj(cachep, page, i);
+ void *objp = index_to_obj(cachep, slab, i);
if (cachep->flags & SLAB_POISON) {
check_poison_obj(cachep, objp);
}
#else
static void slab_destroy_debugcheck(struct kmem_cache *cachep,
- struct page *page)
+ struct slab *slab)
{
}
#endif
/**
* slab_destroy - destroy and release all objects in a slab
* @cachep: cache pointer being destroyed
- * @page: page pointer being destroyed
+ * @slab: slab being destroyed
*
- * Destroy all the objs in a slab page, and release the mem back to the system.
- * Before calling the slab page must have been unlinked from the cache. The
+ * Destroy all the objs in a slab, and release the mem back to the system.
+ * Before calling the slab must have been unlinked from the cache. The
* kmem_cache_node ->list_lock is not held/needed.
*/
-static void slab_destroy(struct kmem_cache *cachep, struct page *page)
+static void slab_destroy(struct kmem_cache *cachep, struct slab *slab)
{
void *freelist;
- freelist = page->freelist;
- slab_destroy_debugcheck(cachep, page);
+ freelist = slab->freelist;
+ slab_destroy_debugcheck(cachep, slab);
if (unlikely(cachep->flags & SLAB_TYPESAFE_BY_RCU))
- call_rcu(&page->rcu_head, kmem_rcu_free);
+ call_rcu(&slab->rcu_head, kmem_rcu_free);
else
- kmem_freepages(cachep, page);
+ kmem_freepages(cachep, slab);
/*
* From now on, we don't use freelist
*/
static void slabs_destroy(struct kmem_cache *cachep, struct list_head *list)
{
- struct page *page, *n;
+ struct slab *slab, *n;
- list_for_each_entry_safe(page, n, list, slab_list) {
- list_del(&page->slab_list);
- slab_destroy(cachep, page);
+ list_for_each_entry_safe(slab, n, list, slab_list) {
+ list_del(&slab->slab_list);
+ slab_destroy(cachep, slab);
}
}
{
struct list_head *p;
int nr_freed;
- struct page *page;
+ struct slab *slab;
nr_freed = 0;
while (nr_freed < tofree && !list_empty(&n->slabs_free)) {
goto out;
}
- page = list_entry(p, struct page, slab_list);
- list_del(&page->slab_list);
+ slab = list_entry(p, struct slab, slab_list);
+ list_del(&slab->slab_list);
n->free_slabs--;
n->total_slabs--;
/*
*/
n->free_objects -= cache->num;
spin_unlock_irq(&n->list_lock);
- slab_destroy(cache, page);
+ slab_destroy(cache, slab);
nr_freed++;
}
out:
* which are all initialized during kmem_cache_init().
*/
static void *alloc_slabmgmt(struct kmem_cache *cachep,
- struct page *page, int colour_off,
+ struct slab *slab, int colour_off,
gfp_t local_flags, int nodeid)
{
void *freelist;
- void *addr = page_address(page);
+ void *addr = slab_address(slab);
- page->s_mem = addr + colour_off;
- page->active = 0;
+ slab->s_mem = addr + colour_off;
+ slab->active = 0;
if (OBJFREELIST_SLAB(cachep))
freelist = NULL;
return freelist;
}
-static inline freelist_idx_t get_free_obj(struct page *page, unsigned int idx)
+static inline freelist_idx_t get_free_obj(struct slab *slab, unsigned int idx)
{
- return ((freelist_idx_t *)page->freelist)[idx];
+ return ((freelist_idx_t *) slab->freelist)[idx];
}
-static inline void set_free_obj(struct page *page,
+static inline void set_free_obj(struct slab *slab,
unsigned int idx, freelist_idx_t val)
{
- ((freelist_idx_t *)(page->freelist))[idx] = val;
+ ((freelist_idx_t *)(slab->freelist))[idx] = val;
}
-static void cache_init_objs_debug(struct kmem_cache *cachep, struct page *page)
+static void cache_init_objs_debug(struct kmem_cache *cachep, struct slab *slab)
{
#if DEBUG
int i;
for (i = 0; i < cachep->num; i++) {
- void *objp = index_to_obj(cachep, page, i);
+ void *objp = index_to_obj(cachep, slab, i);
if (cachep->flags & SLAB_STORE_USER)
*dbg_userword(cachep, objp) = NULL;
}
/* Swap two freelist entries */
-static void swap_free_obj(struct page *page, unsigned int a, unsigned int b)
+static void swap_free_obj(struct slab *slab, unsigned int a, unsigned int b)
{
- swap(((freelist_idx_t *)page->freelist)[a],
- ((freelist_idx_t *)page->freelist)[b]);
+ swap(((freelist_idx_t *) slab->freelist)[a],
+ ((freelist_idx_t *) slab->freelist)[b]);
}
/*
* Shuffle the freelist initialization state based on pre-computed lists.
* return true if the list was successfully shuffled, false otherwise.
*/
-static bool shuffle_freelist(struct kmem_cache *cachep, struct page *page)
+static bool shuffle_freelist(struct kmem_cache *cachep, struct slab *slab)
{
unsigned int objfreelist = 0, i, rand, count = cachep->num;
union freelist_init_state state;
objfreelist = count - 1;
else
objfreelist = next_random_slot(&state);
- page->freelist = index_to_obj(cachep, page, objfreelist) +
+ slab->freelist = index_to_obj(cachep, slab, objfreelist) +
obj_offset(cachep);
count--;
}
*/
if (!precomputed) {
for (i = 0; i < count; i++)
- set_free_obj(page, i, i);
+ set_free_obj(slab, i, i);
/* Fisher-Yates shuffle */
for (i = count - 1; i > 0; i--) {
rand = prandom_u32_state(&state.rnd_state);
rand %= (i + 1);
- swap_free_obj(page, i, rand);
+ swap_free_obj(slab, i, rand);
}
} else {
for (i = 0; i < count; i++)
- set_free_obj(page, i, next_random_slot(&state));
+ set_free_obj(slab, i, next_random_slot(&state));
}
if (OBJFREELIST_SLAB(cachep))
- set_free_obj(page, cachep->num - 1, objfreelist);
+ set_free_obj(slab, cachep->num - 1, objfreelist);
return true;
}
#else
static inline bool shuffle_freelist(struct kmem_cache *cachep,
- struct page *page)
+ struct slab *slab)
{
return false;
}
#endif /* CONFIG_SLAB_FREELIST_RANDOM */
static void cache_init_objs(struct kmem_cache *cachep,
- struct page *page)
+ struct slab *slab)
{
int i;
void *objp;
bool shuffled;
- cache_init_objs_debug(cachep, page);
+ cache_init_objs_debug(cachep, slab);
/* Try to randomize the freelist if enabled */
- shuffled = shuffle_freelist(cachep, page);
+ shuffled = shuffle_freelist(cachep, slab);
if (!shuffled && OBJFREELIST_SLAB(cachep)) {
- page->freelist = index_to_obj(cachep, page, cachep->num - 1) +
+ slab->freelist = index_to_obj(cachep, slab, cachep->num - 1) +
obj_offset(cachep);
}
for (i = 0; i < cachep->num; i++) {
- objp = index_to_obj(cachep, page, i);
+ objp = index_to_obj(cachep, slab, i);
objp = kasan_init_slab_obj(cachep, objp);
/* constructor could break poison info */
}
if (!shuffled)
- set_free_obj(page, i, i);
+ set_free_obj(slab, i, i);
}
}
-static void *slab_get_obj(struct kmem_cache *cachep, struct page *page)
+static void *slab_get_obj(struct kmem_cache *cachep, struct slab *slab)
{
void *objp;
- objp = index_to_obj(cachep, page, get_free_obj(page, page->active));
- page->active++;
+ objp = index_to_obj(cachep, slab, get_free_obj(slab, slab->active));
+ slab->active++;
return objp;
}
static void slab_put_obj(struct kmem_cache *cachep,
- struct page *page, void *objp)
+ struct slab *slab, void *objp)
{
- unsigned int objnr = obj_to_index(cachep, page, objp);
+ unsigned int objnr = obj_to_index(cachep, slab, objp);
#if DEBUG
unsigned int i;
/* Verify double free bug */
- for (i = page->active; i < cachep->num; i++) {
- if (get_free_obj(page, i) == objnr) {
+ for (i = slab->active; i < cachep->num; i++) {
+ if (get_free_obj(slab, i) == objnr) {
pr_err("slab: double free detected in cache '%s', objp %px\n",
cachep->name, objp);
BUG();
}
}
#endif
- page->active--;
- if (!page->freelist)
- page->freelist = objp + obj_offset(cachep);
-
- set_free_obj(page, page->active, objnr);
-}
+ slab->active--;
+ if (!slab->freelist)
+ slab->freelist = objp + obj_offset(cachep);
-/*
- * Map pages beginning at addr to the given cache and slab. This is required
- * for the slab allocator to be able to lookup the cache and slab of a
- * virtual address for kfree, ksize, and slab debugging.
- */
-static void slab_map_pages(struct kmem_cache *cache, struct page *page,
- void *freelist)
-{
- page->slab_cache = cache;
- page->freelist = freelist;
+ set_free_obj(slab, slab->active, objnr);
}
/*
* Grow (by 1) the number of slabs within a cache. This is called by
* kmem_cache_alloc() when there are no active objs left in a cache.
*/
-static struct page *cache_grow_begin(struct kmem_cache *cachep,
+static struct slab *cache_grow_begin(struct kmem_cache *cachep,
gfp_t flags, int nodeid)
{
void *freelist;
size_t offset;
gfp_t local_flags;
- int page_node;
+ int slab_node;
struct kmem_cache_node *n;
- struct page *page;
+ struct slab *slab;
/*
* Be lazy and only check for valid flags here, keeping it out of the
* Get mem for the objs. Attempt to allocate a physical page from
* 'nodeid'.
*/
- page = kmem_getpages(cachep, local_flags, nodeid);
- if (!page)
+ slab = kmem_getpages(cachep, local_flags, nodeid);
+ if (!slab)
goto failed;
- page_node = page_to_nid(page);
- n = get_node(cachep, page_node);
+ slab_node = slab_nid(slab);
+ n = get_node(cachep, slab_node);
/* Get colour for the slab, and cal the next value. */
n->colour_next++;
* page_address() in the latter returns a non-tagged pointer,
* as it should be for slab pages.
*/
- kasan_poison_slab(page);
+ kasan_poison_slab(slab);
/* Get slab management. */
- freelist = alloc_slabmgmt(cachep, page, offset,
- local_flags & ~GFP_CONSTRAINT_MASK, page_node);
+ freelist = alloc_slabmgmt(cachep, slab, offset,
+ local_flags & ~GFP_CONSTRAINT_MASK, slab_node);
if (OFF_SLAB(cachep) && !freelist)
goto opps1;
- slab_map_pages(cachep, page, freelist);
+ slab->slab_cache = cachep;
+ slab->freelist = freelist;
- cache_init_objs(cachep, page);
+ cache_init_objs(cachep, slab);
if (gfpflags_allow_blocking(local_flags))
local_irq_disable();
- return page;
+ return slab;
opps1:
- kmem_freepages(cachep, page);
+ kmem_freepages(cachep, slab);
failed:
if (gfpflags_allow_blocking(local_flags))
local_irq_disable();
return NULL;
}
-static void cache_grow_end(struct kmem_cache *cachep, struct page *page)
+static void cache_grow_end(struct kmem_cache *cachep, struct slab *slab)
{
struct kmem_cache_node *n;
void *list = NULL;
check_irq_off();
- if (!page)
+ if (!slab)
return;
- INIT_LIST_HEAD(&page->slab_list);
- n = get_node(cachep, page_to_nid(page));
+ INIT_LIST_HEAD(&slab->slab_list);
+ n = get_node(cachep, slab_nid(slab));
spin_lock(&n->list_lock);
n->total_slabs++;
- if (!page->active) {
- list_add_tail(&page->slab_list, &n->slabs_free);
+ if (!slab->active) {
+ list_add_tail(&slab->slab_list, &n->slabs_free);
n->free_slabs++;
} else
- fixup_slab_list(cachep, n, page, &list);
+ fixup_slab_list(cachep, n, slab, &list);
STATS_INC_GROWN(cachep);
- n->free_objects += cachep->num - page->active;
+ n->free_objects += cachep->num - slab->active;
spin_unlock(&n->list_lock);
fixup_objfreelist_debug(cachep, &list);
unsigned long caller)
{
unsigned int objnr;
- struct page *page;
+ struct slab *slab;
BUG_ON(virt_to_cache(objp) != cachep);
objp -= obj_offset(cachep);
kfree_debugcheck(objp);
- page = virt_to_head_page(objp);
+ slab = virt_to_slab(objp);
if (cachep->flags & SLAB_RED_ZONE) {
verify_redzone_free(cachep, objp);
if (cachep->flags & SLAB_STORE_USER)
*dbg_userword(cachep, objp) = (void *)caller;
- objnr = obj_to_index(cachep, page, objp);
+ objnr = obj_to_index(cachep, slab, objp);
BUG_ON(objnr >= cachep->num);
- BUG_ON(objp != index_to_obj(cachep, page, objnr));
+ BUG_ON(objp != index_to_obj(cachep, slab, objnr));
if (cachep->flags & SLAB_POISON) {
poison_obj(cachep, objp, POISON_FREE);
}
static inline void fixup_slab_list(struct kmem_cache *cachep,
- struct kmem_cache_node *n, struct page *page,
+ struct kmem_cache_node *n, struct slab *slab,
void **list)
{
/* move slabp to correct slabp list: */
- list_del(&page->slab_list);
- if (page->active == cachep->num) {
- list_add(&page->slab_list, &n->slabs_full);
+ list_del(&slab->slab_list);
+ if (slab->active == cachep->num) {
+ list_add(&slab->slab_list, &n->slabs_full);
if (OBJFREELIST_SLAB(cachep)) {
#if DEBUG
/* Poisoning will be done without holding the lock */
if (cachep->flags & SLAB_POISON) {
- void **objp = page->freelist;
+ void **objp = slab->freelist;
*objp = *list;
*list = objp;
}
#endif
- page->freelist = NULL;
+ slab->freelist = NULL;
}
} else
- list_add(&page->slab_list, &n->slabs_partial);
+ list_add(&slab->slab_list, &n->slabs_partial);
}
/* Try to find non-pfmemalloc slab if needed */
-static noinline struct page *get_valid_first_slab(struct kmem_cache_node *n,
- struct page *page, bool pfmemalloc)
+static noinline struct slab *get_valid_first_slab(struct kmem_cache_node *n,
+ struct slab *slab, bool pfmemalloc)
{
- if (!page)
+ if (!slab)
return NULL;
if (pfmemalloc)
- return page;
+ return slab;
- if (!PageSlabPfmemalloc(page))
- return page;
+ if (!slab_test_pfmemalloc(slab))
+ return slab;
/* No need to keep pfmemalloc slab if we have enough free objects */
if (n->free_objects > n->free_limit) {
- ClearPageSlabPfmemalloc(page);
- return page;
+ slab_clear_pfmemalloc(slab);
+ return slab;
}
/* Move pfmemalloc slab to the end of list to speed up next search */
- list_del(&page->slab_list);
- if (!page->active) {
- list_add_tail(&page->slab_list, &n->slabs_free);
+ list_del(&slab->slab_list);
+ if (!slab->active) {
+ list_add_tail(&slab->slab_list, &n->slabs_free);
n->free_slabs++;
} else
- list_add_tail(&page->slab_list, &n->slabs_partial);
+ list_add_tail(&slab->slab_list, &n->slabs_partial);
- list_for_each_entry(page, &n->slabs_partial, slab_list) {
- if (!PageSlabPfmemalloc(page))
- return page;
+ list_for_each_entry(slab, &n->slabs_partial, slab_list) {
+ if (!slab_test_pfmemalloc(slab))
+ return slab;
}
n->free_touched = 1;
- list_for_each_entry(page, &n->slabs_free, slab_list) {
- if (!PageSlabPfmemalloc(page)) {
+ list_for_each_entry(slab, &n->slabs_free, slab_list) {
+ if (!slab_test_pfmemalloc(slab)) {
n->free_slabs--;
- return page;
+ return slab;
}
}
return NULL;
}
-static struct page *get_first_slab(struct kmem_cache_node *n, bool pfmemalloc)
+static struct slab *get_first_slab(struct kmem_cache_node *n, bool pfmemalloc)
{
- struct page *page;
+ struct slab *slab;
assert_spin_locked(&n->list_lock);
- page = list_first_entry_or_null(&n->slabs_partial, struct page,
+ slab = list_first_entry_or_null(&n->slabs_partial, struct slab,
slab_list);
- if (!page) {
+ if (!slab) {
n->free_touched = 1;
- page = list_first_entry_or_null(&n->slabs_free, struct page,
+ slab = list_first_entry_or_null(&n->slabs_free, struct slab,
slab_list);
- if (page)
+ if (slab)
n->free_slabs--;
}
if (sk_memalloc_socks())
- page = get_valid_first_slab(n, page, pfmemalloc);
+ slab = get_valid_first_slab(n, slab, pfmemalloc);
- return page;
+ return slab;
}
static noinline void *cache_alloc_pfmemalloc(struct kmem_cache *cachep,
struct kmem_cache_node *n, gfp_t flags)
{
- struct page *page;
+ struct slab *slab;
void *obj;
void *list = NULL;
return NULL;
spin_lock(&n->list_lock);
- page = get_first_slab(n, true);
- if (!page) {
+ slab = get_first_slab(n, true);
+ if (!slab) {
spin_unlock(&n->list_lock);
return NULL;
}
- obj = slab_get_obj(cachep, page);
+ obj = slab_get_obj(cachep, slab);
n->free_objects--;
- fixup_slab_list(cachep, n, page, &list);
+ fixup_slab_list(cachep, n, slab, &list);
spin_unlock(&n->list_lock);
fixup_objfreelist_debug(cachep, &list);
* or cache_grow_end() for new slab
*/
static __always_inline int alloc_block(struct kmem_cache *cachep,
- struct array_cache *ac, struct page *page, int batchcount)
+ struct array_cache *ac, struct slab *slab, int batchcount)
{
/*
* There must be at least one object available for
* allocation.
*/
- BUG_ON(page->active >= cachep->num);
+ BUG_ON(slab->active >= cachep->num);
- while (page->active < cachep->num && batchcount--) {
+ while (slab->active < cachep->num && batchcount--) {
STATS_INC_ALLOCED(cachep);
STATS_INC_ACTIVE(cachep);
STATS_SET_HIGH(cachep);
- ac->entry[ac->avail++] = slab_get_obj(cachep, page);
+ ac->entry[ac->avail++] = slab_get_obj(cachep, slab);
}
return batchcount;
struct array_cache *ac, *shared;
int node;
void *list = NULL;
- struct page *page;
+ struct slab *slab;
check_irq_off();
node = numa_mem_id();
while (batchcount > 0) {
/* Get slab alloc is to come from. */
- page = get_first_slab(n, false);
- if (!page)
+ slab = get_first_slab(n, false);
+ if (!slab)
goto must_grow;
check_spinlock_acquired(cachep);
- batchcount = alloc_block(cachep, ac, page, batchcount);
- fixup_slab_list(cachep, n, page, &list);
+ batchcount = alloc_block(cachep, ac, slab, batchcount);
+ fixup_slab_list(cachep, n, slab, &list);
}
must_grow:
return obj;
}
- page = cache_grow_begin(cachep, gfp_exact_node(flags), node);
+ slab = cache_grow_begin(cachep, gfp_exact_node(flags), node);
/*
* cache_grow_begin() can reenable interrupts,
* then ac could change.
*/
ac = cpu_cache_get(cachep);
- if (!ac->avail && page)
- alloc_block(cachep, ac, page, batchcount);
- cache_grow_end(cachep, page);
+ if (!ac->avail && slab)
+ alloc_block(cachep, ac, slab, batchcount);
+ cache_grow_end(cachep, slab);
if (!ac->avail)
return NULL;
struct zone *zone;
enum zone_type highest_zoneidx = gfp_zone(flags);
void *obj = NULL;
- struct page *page;
+ struct slab *slab;
int nid;
unsigned int cpuset_mems_cookie;
* We may trigger various forms of reclaim on the allowed
* set and go into memory reserves if necessary.
*/
- page = cache_grow_begin(cache, flags, numa_mem_id());
- cache_grow_end(cache, page);
- if (page) {
- nid = page_to_nid(page);
+ slab = cache_grow_begin(cache, flags, numa_mem_id());
+ cache_grow_end(cache, slab);
+ if (slab) {
+ nid = slab_nid(slab);
obj = ____cache_alloc_node(cache,
gfp_exact_node(flags), nid);
static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
int nodeid)
{
- struct page *page;
+ struct slab *slab;
struct kmem_cache_node *n;
void *obj = NULL;
void *list = NULL;
check_irq_off();
spin_lock(&n->list_lock);
- page = get_first_slab(n, false);
- if (!page)
+ slab = get_first_slab(n, false);
+ if (!slab)
goto must_grow;
check_spinlock_acquired_node(cachep, nodeid);
STATS_INC_ACTIVE(cachep);
STATS_SET_HIGH(cachep);
- BUG_ON(page->active == cachep->num);
+ BUG_ON(slab->active == cachep->num);
- obj = slab_get_obj(cachep, page);
+ obj = slab_get_obj(cachep, slab);
n->free_objects--;
- fixup_slab_list(cachep, n, page, &list);
+ fixup_slab_list(cachep, n, slab, &list);
spin_unlock(&n->list_lock);
fixup_objfreelist_debug(cachep, &list);
must_grow:
spin_unlock(&n->list_lock);
- page = cache_grow_begin(cachep, gfp_exact_node(flags), nodeid);
- if (page) {
+ slab = cache_grow_begin(cachep, gfp_exact_node(flags), nodeid);
+ if (slab) {
/* This slab isn't counted yet so don't update free_objects */
- obj = slab_get_obj(cachep, page);
+ obj = slab_get_obj(cachep, slab);
}
- cache_grow_end(cachep, page);
+ cache_grow_end(cachep, slab);
return obj ? obj : fallback_alloc(cachep, flags);
}
{
int i;
struct kmem_cache_node *n = get_node(cachep, node);
- struct page *page;
+ struct slab *slab;
n->free_objects += nr_objects;
for (i = 0; i < nr_objects; i++) {
void *objp;
- struct page *page;
+ struct slab *slab;
objp = objpp[i];
- page = virt_to_head_page(objp);
- list_del(&page->slab_list);
+ slab = virt_to_slab(objp);
+ list_del(&slab->slab_list);
check_spinlock_acquired_node(cachep, node);
- slab_put_obj(cachep, page, objp);
+ slab_put_obj(cachep, slab, objp);
STATS_DEC_ACTIVE(cachep);
/* fixup slab chains */
- if (page->active == 0) {
- list_add(&page->slab_list, &n->slabs_free);
+ if (slab->active == 0) {
+ list_add(&slab->slab_list, &n->slabs_free);
n->free_slabs++;
} else {
/* Unconditionally move a slab to the end of the
* partial list on free - maximum time for the
* other objects to be freed, too.
*/
- list_add_tail(&page->slab_list, &n->slabs_partial);
+ list_add_tail(&slab->slab_list, &n->slabs_partial);
}
}
while (n->free_objects > n->free_limit && !list_empty(&n->slabs_free)) {
n->free_objects -= cachep->num;
- page = list_last_entry(&n->slabs_free, struct page, slab_list);
- list_move(&page->slab_list, list);
+ slab = list_last_entry(&n->slabs_free, struct slab, slab_list);
+ list_move(&slab->slab_list, list);
n->free_slabs--;
n->total_slabs--;
}
#if STATS
{
int i = 0;
- struct page *page;
+ struct slab *slab;
- list_for_each_entry(page, &n->slabs_free, slab_list) {
- BUG_ON(page->active);
+ list_for_each_entry(slab, &n->slabs_free, slab_list) {
+ BUG_ON(slab->active);
i++;
}
}
if (sk_memalloc_socks()) {
- struct page *page = virt_to_head_page(objp);
+ struct slab *slab = virt_to_slab(objp);
- if (unlikely(PageSlabPfmemalloc(page))) {
- cache_free_pfmemalloc(cachep, page, objp);
+ if (unlikely(slab_test_pfmemalloc(slab))) {
+ cache_free_pfmemalloc(cachep, slab, objp);
return;
}
}
#endif /* CONFIG_NUMA */
#ifdef CONFIG_PRINTK
-void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page)
+void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab)
{
struct kmem_cache *cachep;
unsigned int objnr;
void *objp;
kpp->kp_ptr = object;
- kpp->kp_page = page;
- cachep = page->slab_cache;
+ kpp->kp_slab = slab;
+ cachep = slab->slab_cache;
kpp->kp_slab_cache = cachep;
objp = object - obj_offset(cachep);
kpp->kp_data_offset = obj_offset(cachep);
- page = virt_to_head_page(objp);
- objnr = obj_to_index(cachep, page, objp);
- objp = index_to_obj(cachep, page, objnr);
+ slab = virt_to_slab(objp);
+ objnr = obj_to_index(cachep, slab, objp);
+ objp = index_to_obj(cachep, slab, objnr);
kpp->kp_objp = objp;
if (DEBUG && cachep->flags & SLAB_STORE_USER)
kpp->kp_ret = *dbg_userword(cachep, objp);
* Returns NULL if check passes, otherwise const char * to name of cache
* to indicate an error.
*/
-void __check_heap_object(const void *ptr, unsigned long n, struct page *page,
- bool to_user)
+void __check_heap_object(const void *ptr, unsigned long n,
+ const struct slab *slab, bool to_user)
{
struct kmem_cache *cachep;
unsigned int objnr;
ptr = kasan_reset_tag(ptr);
/* Find and validate object. */
- cachep = page->slab_cache;
- objnr = obj_to_index(cachep, page, (void *)ptr);
+ cachep = slab->slab_cache;
+ objnr = obj_to_index(cachep, slab, (void *)ptr);
BUG_ON(objnr >= cachep->num);
/* Find offset within object. */
if (is_kfence_address(ptr))
offset = ptr - kfence_object_start(ptr);
else
- offset = ptr - index_to_obj(cachep, page, objnr) - obj_offset(cachep);
+ offset = ptr - index_to_obj(cachep, slab, objnr) - obj_offset(cachep);
/* Allow address range falling entirely within usercopy region. */
if (offset >= cachep->useroffset &&
* Internal slab definitions
*/
+/* Reuses the bits in struct page */
+struct slab {
+ unsigned long __page_flags;
+
+#if defined(CONFIG_SLAB)
+
+ union {
+ struct list_head slab_list;
+ struct rcu_head rcu_head;
+ };
+ struct kmem_cache *slab_cache;
+ void *freelist; /* array of free object indexes */
+ void *s_mem; /* first object */
+ unsigned int active;
+
+#elif defined(CONFIG_SLUB)
+
+ union {
+ struct list_head slab_list;
+ struct rcu_head rcu_head;
+#ifdef CONFIG_SLUB_CPU_PARTIAL
+ struct {
+ struct slab *next;
+ int slabs; /* Nr of slabs left */
+ };
+#endif
+ };
+ struct kmem_cache *slab_cache;
+ /* Double-word boundary */
+ void *freelist; /* first free object */
+ union {
+ unsigned long counters;
+ struct {
+ unsigned inuse:16;
+ unsigned objects:15;
+ unsigned frozen:1;
+ };
+ };
+ unsigned int __unused;
+
+#elif defined(CONFIG_SLOB)
+
+ struct list_head slab_list;
+ void *__unused_1;
+ void *freelist; /* first free block */
+ long units;
+ unsigned int __unused_2;
+
+#else
+#error "Unexpected slab allocator configured"
+#endif
+
+ atomic_t __page_refcount;
+#ifdef CONFIG_MEMCG
+ unsigned long memcg_data;
+#endif
+};
+
+#define SLAB_MATCH(pg, sl) \
+ static_assert(offsetof(struct page, pg) == offsetof(struct slab, sl))
+SLAB_MATCH(flags, __page_flags);
+SLAB_MATCH(compound_head, slab_list); /* Ensure bit 0 is clear */
+SLAB_MATCH(slab_list, slab_list);
+#ifndef CONFIG_SLOB
+SLAB_MATCH(rcu_head, rcu_head);
+SLAB_MATCH(slab_cache, slab_cache);
+#endif
+#ifdef CONFIG_SLAB
+SLAB_MATCH(s_mem, s_mem);
+SLAB_MATCH(active, active);
+#endif
+SLAB_MATCH(_refcount, __page_refcount);
+#ifdef CONFIG_MEMCG
+SLAB_MATCH(memcg_data, memcg_data);
+#endif
+#undef SLAB_MATCH
+static_assert(sizeof(struct slab) <= sizeof(struct page));
+
+/**
+ * folio_slab - Converts from folio to slab.
+ * @folio: The folio.
+ *
+ * Currently struct slab is a different representation of a folio where
+ * folio_test_slab() is true.
+ *
+ * Return: The slab which contains this folio.
+ */
+#define folio_slab(folio) (_Generic((folio), \
+ const struct folio *: (const struct slab *)(folio), \
+ struct folio *: (struct slab *)(folio)))
+
+/**
+ * slab_folio - The folio allocated for a slab
+ * @slab: The slab.
+ *
+ * Slabs are allocated as folios that contain the individual objects and are
+ * using some fields in the first struct page of the folio - those fields are
+ * now accessed by struct slab. It is occasionally necessary to convert back to
+ * a folio in order to communicate with the rest of the mm. Please use this
+ * helper function instead of casting yourself, as the implementation may change
+ * in the future.
+ */
+#define slab_folio(s) (_Generic((s), \
+ const struct slab *: (const struct folio *)s, \
+ struct slab *: (struct folio *)s))
+
+/**
+ * page_slab - Converts from first struct page to slab.
+ * @p: The first (either head of compound or single) page of slab.
+ *
+ * A temporary wrapper to convert struct page to struct slab in situations where
+ * we know the page is the compound head, or single order-0 page.
+ *
+ * Long-term ideally everything would work with struct slab directly or go
+ * through folio to struct slab.
+ *
+ * Return: The slab which contains this page
+ */
+#define page_slab(p) (_Generic((p), \
+ const struct page *: (const struct slab *)(p), \
+ struct page *: (struct slab *)(p)))
+
+/**
+ * slab_page - The first struct page allocated for a slab
+ * @slab: The slab.
+ *
+ * A convenience wrapper for converting slab to the first struct page of the
+ * underlying folio, to communicate with code not yet converted to folio or
+ * struct slab.
+ */
+#define slab_page(s) folio_page(slab_folio(s), 0)
+
+/*
+ * If network-based swap is enabled, sl*b must keep track of whether pages
+ * were allocated from pfmemalloc reserves.
+ */
+static inline bool slab_test_pfmemalloc(const struct slab *slab)
+{
+ return folio_test_active((struct folio *)slab_folio(slab));
+}
+
+static inline void slab_set_pfmemalloc(struct slab *slab)
+{
+ folio_set_active(slab_folio(slab));
+}
+
+static inline void slab_clear_pfmemalloc(struct slab *slab)
+{
+ folio_clear_active(slab_folio(slab));
+}
+
+static inline void __slab_clear_pfmemalloc(struct slab *slab)
+{
+ __folio_clear_active(slab_folio(slab));
+}
+
+static inline void *slab_address(const struct slab *slab)
+{
+ return folio_address(slab_folio(slab));
+}
+
+static inline int slab_nid(const struct slab *slab)
+{
+ return folio_nid(slab_folio(slab));
+}
+
+static inline pg_data_t *slab_pgdat(const struct slab *slab)
+{
+ return folio_pgdat(slab_folio(slab));
+}
+
+static inline struct slab *virt_to_slab(const void *addr)
+{
+ struct folio *folio = virt_to_folio(addr);
+
+ if (!folio_test_slab(folio))
+ return NULL;
+
+ return folio_slab(folio);
+}
+
+static inline int slab_order(const struct slab *slab)
+{
+ return folio_order((struct folio *)slab_folio(slab));
+}
+
+static inline size_t slab_size(const struct slab *slab)
+{
+ return PAGE_SIZE << slab_order(slab);
+}
+
#ifdef CONFIG_SLOB
/*
* Common fields provided in kmem_cache by all slab allocators
}
#ifdef CONFIG_MEMCG_KMEM
-int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
- gfp_t gfp, bool new_page);
+/*
+ * slab_objcgs - get the object cgroups vector associated with a slab
+ * @slab: a pointer to the slab struct
+ *
+ * Returns a pointer to the object cgroups vector associated with the slab,
+ * or NULL if no such vector has been associated yet.
+ */
+static inline struct obj_cgroup **slab_objcgs(struct slab *slab)
+{
+ unsigned long memcg_data = READ_ONCE(slab->memcg_data);
+
+ VM_BUG_ON_PAGE(memcg_data && !(memcg_data & MEMCG_DATA_OBJCGS),
+ slab_page(slab));
+ VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, slab_page(slab));
+
+ return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
+}
+
+int memcg_alloc_slab_cgroups(struct slab *slab, struct kmem_cache *s,
+ gfp_t gfp, bool new_slab);
void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
enum node_stat_item idx, int nr);
-static inline void memcg_free_page_obj_cgroups(struct page *page)
+static inline void memcg_free_slab_cgroups(struct slab *slab)
{
- kfree(page_objcgs(page));
- page->memcg_data = 0;
+ kfree(slab_objcgs(slab));
+ slab->memcg_data = 0;
}
static inline size_t obj_full_size(struct kmem_cache *s)
gfp_t flags, size_t size,
void **p)
{
- struct page *page;
+ struct slab *slab;
unsigned long off;
size_t i;
for (i = 0; i < size; i++) {
if (likely(p[i])) {
- page = virt_to_head_page(p[i]);
+ slab = virt_to_slab(p[i]);
- if (!page_objcgs(page) &&
- memcg_alloc_page_obj_cgroups(page, s, flags,
+ if (!slab_objcgs(slab) &&
+ memcg_alloc_slab_cgroups(slab, s, flags,
false)) {
obj_cgroup_uncharge(objcg, obj_full_size(s));
continue;
}
- off = obj_to_index(s, page, p[i]);
+ off = obj_to_index(s, slab, p[i]);
obj_cgroup_get(objcg);
- page_objcgs(page)[off] = objcg;
- mod_objcg_state(objcg, page_pgdat(page),
+ slab_objcgs(slab)[off] = objcg;
+ mod_objcg_state(objcg, slab_pgdat(slab),
cache_vmstat_idx(s), obj_full_size(s));
} else {
obj_cgroup_uncharge(objcg, obj_full_size(s));
struct kmem_cache *s;
struct obj_cgroup **objcgs;
struct obj_cgroup *objcg;
- struct page *page;
+ struct slab *slab;
unsigned int off;
int i;
if (unlikely(!p[i]))
continue;
- page = virt_to_head_page(p[i]);
- objcgs = page_objcgs_check(page);
+ slab = virt_to_slab(p[i]);
+ /* we could be given a kmalloc_large() object, skip those */
+ if (!slab)
+ continue;
+
+ objcgs = slab_objcgs(slab);
if (!objcgs)
continue;
if (!s_orig)
- s = page->slab_cache;
+ s = slab->slab_cache;
else
s = s_orig;
- off = obj_to_index(s, page, p[i]);
+ off = obj_to_index(s, slab, p[i]);
objcg = objcgs[off];
if (!objcg)
continue;
objcgs[off] = NULL;
obj_cgroup_uncharge(objcg, obj_full_size(s));
- mod_objcg_state(objcg, page_pgdat(page), cache_vmstat_idx(s),
+ mod_objcg_state(objcg, slab_pgdat(slab), cache_vmstat_idx(s),
-obj_full_size(s));
obj_cgroup_put(objcg);
}
}
#else /* CONFIG_MEMCG_KMEM */
+static inline struct obj_cgroup **slab_objcgs(struct slab *slab)
+{
+ return NULL;
+}
+
static inline struct mem_cgroup *memcg_from_slab_obj(void *ptr)
{
return NULL;
}
-static inline int memcg_alloc_page_obj_cgroups(struct page *page,
+static inline int memcg_alloc_slab_cgroups(struct slab *slab,
struct kmem_cache *s, gfp_t gfp,
- bool new_page)
+ bool new_slab)
{
return 0;
}
-static inline void memcg_free_page_obj_cgroups(struct page *page)
+static inline void memcg_free_slab_cgroups(struct slab *slab)
{
}
}
#endif /* CONFIG_MEMCG_KMEM */
+#ifndef CONFIG_SLOB
static inline struct kmem_cache *virt_to_cache(const void *obj)
{
- struct page *page;
+ struct slab *slab;
- page = virt_to_head_page(obj);
- if (WARN_ONCE(!PageSlab(page), "%s: Object is not a Slab page!\n",
+ slab = virt_to_slab(obj);
+ if (WARN_ONCE(!slab, "%s: Object is not a Slab page!\n",
__func__))
return NULL;
- return page->slab_cache;
+ return slab->slab_cache;
}
-static __always_inline void account_slab_page(struct page *page, int order,
- struct kmem_cache *s,
- gfp_t gfp)
+static __always_inline void account_slab(struct slab *slab, int order,
+ struct kmem_cache *s, gfp_t gfp)
{
if (memcg_kmem_enabled() && (s->flags & SLAB_ACCOUNT))
- memcg_alloc_page_obj_cgroups(page, s, gfp, true);
+ memcg_alloc_slab_cgroups(slab, s, gfp, true);
- mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
+ mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s),
PAGE_SIZE << order);
}
-static __always_inline void unaccount_slab_page(struct page *page, int order,
- struct kmem_cache *s)
+static __always_inline void unaccount_slab(struct slab *slab, int order,
+ struct kmem_cache *s)
{
if (memcg_kmem_enabled())
- memcg_free_page_obj_cgroups(page);
+ memcg_free_slab_cgroups(slab);
- mod_node_page_state(page_pgdat(page), cache_vmstat_idx(s),
+ mod_node_page_state(slab_pgdat(slab), cache_vmstat_idx(s),
-(PAGE_SIZE << order));
}
print_tracking(cachep, x);
return cachep;
}
+#endif /* CONFIG_SLOB */
static inline size_t slab_ksize(const struct kmem_cache *s)
{
#define KS_ADDRS_COUNT 16
struct kmem_obj_info {
void *kp_ptr;
- struct page *kp_page;
+ struct slab *kp_slab;
void *kp_objp;
unsigned long kp_data_offset;
struct kmem_cache *kp_slab_cache;
void *kp_stack[KS_ADDRS_COUNT];
void *kp_free_stack[KS_ADDRS_COUNT];
};
-void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page);
+void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab);
+#endif
+
+#ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR
+void __check_heap_object(const void *ptr, unsigned long n,
+ const struct slab *slab, bool to_user);
+#else
+static inline
+void __check_heap_object(const void *ptr, unsigned long n,
+ const struct slab *slab, bool to_user)
+{
+}
#endif
#endif /* MM_SLAB_H */
*/
bool kmem_valid_obj(void *object)
{
- struct page *page;
+ struct folio *folio;
/* Some arches consider ZERO_SIZE_PTR to be a valid address. */
if (object < (void *)PAGE_SIZE || !virt_addr_valid(object))
return false;
- page = virt_to_head_page(object);
- return PageSlab(page);
+ folio = virt_to_folio(object);
+ return folio_test_slab(folio);
}
EXPORT_SYMBOL_GPL(kmem_valid_obj);
{
char *cp = IS_ENABLED(CONFIG_MMU) ? "" : "/vmalloc";
int i;
- struct page *page;
+ struct slab *slab;
unsigned long ptroffset;
struct kmem_obj_info kp = { };
if (WARN_ON_ONCE(!virt_addr_valid(object)))
return;
- page = virt_to_head_page(object);
- if (WARN_ON_ONCE(!PageSlab(page))) {
+ slab = virt_to_slab(object);
+ if (WARN_ON_ONCE(!slab)) {
pr_cont(" non-slab memory.\n");
return;
}
- kmem_obj_info(&kp, object, page);
+ kmem_obj_info(&kp, object, slab);
if (kp.kp_slab_cache)
pr_cont(" slab%s %s", cp, kp.kp_slab_cache->name);
else
* If kmalloc is asked for objects of PAGE_SIZE or larger, it calls
* alloc_pages() directly, allocating compound pages so the page order
* does not have to be separately tracked.
- * These objects are detected in kfree() because PageSlab()
+ * These objects are detected in kfree() because folio_test_slab()
* is false for them.
*
* SLAB is emulated on top of SLOB by simply calling constructors and
/*
* slob_page_free: true for pages on free_slob_pages list.
*/
-static inline int slob_page_free(struct page *sp)
+static inline int slob_page_free(struct slab *slab)
{
- return PageSlobFree(sp);
+ return PageSlobFree(slab_page(slab));
}
-static void set_slob_page_free(struct page *sp, struct list_head *list)
+static void set_slob_page_free(struct slab *slab, struct list_head *list)
{
- list_add(&sp->slab_list, list);
- __SetPageSlobFree(sp);
+ list_add(&slab->slab_list, list);
+ __SetPageSlobFree(slab_page(slab));
}
-static inline void clear_slob_page_free(struct page *sp)
+static inline void clear_slob_page_free(struct slab *slab)
{
- list_del(&sp->slab_list);
- __ClearPageSlobFree(sp);
+ list_del(&slab->slab_list);
+ __ClearPageSlobFree(slab_page(slab));
}
#define SLOB_UNIT sizeof(slob_t)
* freelist, in this case @page_removed_from_list will be set to
* true (set to false otherwise).
*/
-static void *slob_page_alloc(struct page *sp, size_t size, int align,
+static void *slob_page_alloc(struct slab *sp, size_t size, int align,
int align_offset, bool *page_removed_from_list)
{
slob_t *prev, *cur, *aligned = NULL;
static void *slob_alloc(size_t size, gfp_t gfp, int align, int node,
int align_offset)
{
- struct page *sp;
+ struct folio *folio;
+ struct slab *sp;
struct list_head *slob_list;
slob_t *b = NULL;
unsigned long flags;
* If there's a node specification, search for a partial
* page with a matching node id in the freelist.
*/
- if (node != NUMA_NO_NODE && page_to_nid(sp) != node)
+ if (node != NUMA_NO_NODE && slab_nid(sp) != node)
continue;
#endif
/* Enough room on this page? */
b = slob_new_pages(gfp & ~__GFP_ZERO, 0, node);
if (!b)
return NULL;
- sp = virt_to_page(b);
- __SetPageSlab(sp);
+ folio = virt_to_folio(b);
+ __folio_set_slab(folio);
+ sp = folio_slab(folio);
spin_lock_irqsave(&slob_lock, flags);
sp->units = SLOB_UNITS(PAGE_SIZE);
*/
static void slob_free(void *block, int size)
{
- struct page *sp;
+ struct slab *sp;
slob_t *prev, *next, *b = (slob_t *)block;
slobidx_t units;
unsigned long flags;
return;
BUG_ON(!size);
- sp = virt_to_page(block);
+ sp = virt_to_slab(block);
units = SLOB_UNITS(size);
spin_lock_irqsave(&slob_lock, flags);
if (slob_page_free(sp))
clear_slob_page_free(sp);
spin_unlock_irqrestore(&slob_lock, flags);
- __ClearPageSlab(sp);
- page_mapcount_reset(sp);
+ __folio_clear_slab(slab_folio(sp));
slob_free_pages(b, 0);
return;
}
}
#ifdef CONFIG_PRINTK
-void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page)
+void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab)
{
kpp->kp_ptr = object;
- kpp->kp_page = page;
+ kpp->kp_slab = slab;
}
#endif
void kfree(const void *block)
{
- struct page *sp;
+ struct folio *sp;
trace_kfree(_RET_IP_, block);
return;
kmemleak_free(block);
- sp = virt_to_page(block);
- if (PageSlab(sp)) {
+ sp = virt_to_folio(block);
+ if (folio_test_slab(sp)) {
int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
unsigned int *m = (unsigned int *)(block - align);
slob_free(m, *m + align);
} else {
- unsigned int order = compound_order(sp);
- mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE_B,
+ unsigned int order = folio_order(sp);
+
+ mod_node_page_state(folio_pgdat(sp), NR_SLAB_UNRECLAIMABLE_B,
-(PAGE_SIZE << order));
- __free_pages(sp, order);
+ __free_pages(folio_page(sp, 0), order);
}
}
/* can't use ksize for kmem_cache_alloc memory, only kmalloc */
size_t __ksize(const void *block)
{
- struct page *sp;
+ struct folio *folio;
int align;
unsigned int *m;
if (unlikely(block == ZERO_SIZE_PTR))
return 0;
- sp = virt_to_page(block);
- if (unlikely(!PageSlab(sp)))
- return page_size(sp);
+ folio = virt_to_folio(block);
+ if (unlikely(!folio_test_slab(folio)))
+ return folio_size(folio);
align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
m = (unsigned int *)(block - align);
* 1. slab_mutex (Global Mutex)
* 2. node->list_lock (Spinlock)
* 3. kmem_cache->cpu_slab->lock (Local lock)
- * 4. slab_lock(page) (Only on some arches or for debugging)
+ * 4. slab_lock(slab) (Only on some arches or for debugging)
* 5. object_map_lock (Only for debugging)
*
* slab_mutex
*
* The slab_lock is only used for debugging and on arches that do not
* have the ability to do a cmpxchg_double. It only protects:
- * A. page->freelist -> List of object free in a page
- * B. page->inuse -> Number of objects in use
- * C. page->objects -> Number of objects in page
- * D. page->frozen -> frozen state
+ * A. slab->freelist -> List of free objects in a slab
+ * B. slab->inuse -> Number of objects in use
+ * C. slab->objects -> Number of objects in slab
+ * D. slab->frozen -> frozen state
*
* Frozen slabs
*
* If a slab is frozen then it is exempt from list management. It is not
* on any list except per cpu partial list. The processor that froze the
- * slab is the one who can perform list operations on the page. Other
+ * slab is the one who can perform list operations on the slab. Other
* processors may put objects onto the freelist but the processor that
* froze the slab is the only one that can retrieve the objects from the
- * page's freelist.
+ * slab's freelist.
*
* list_lock
*
* minimal so we rely on the page allocators per cpu caches for
* fast frees and allocs.
*
- * page->frozen The slab is frozen and exempt from list processing.
+ * slab->frozen The slab is frozen and exempt from list processing.
* This means that the slab is dedicated to a purpose
* such as satisfying allocations for a specific
* processor. Objects may be freed in the slab while
#define OO_SHIFT 16
#define OO_MASK ((1 << OO_SHIFT) - 1)
-#define MAX_OBJS_PER_PAGE 32767 /* since page.objects is u15 */
+#define MAX_OBJS_PER_PAGE 32767 /* since slab.objects is u15 */
/* Internal SLUB flags */
/* Poison object */
#ifdef CONFIG_SLUB_CPU_PARTIAL
static void slub_set_cpu_partial(struct kmem_cache *s, unsigned int nr_objects)
{
- unsigned int nr_pages;
+ unsigned int nr_slabs;
s->cpu_partial = nr_objects;
/*
* We take the number of objects but actually limit the number of
- * pages on the per cpu partial list, in order to limit excessive
- * growth of the list. For simplicity we assume that the pages will
+ * slabs on the per cpu partial list, in order to limit excessive
+ * growth of the list. For simplicity we assume that the slabs will
* be half-full.
*/
- nr_pages = DIV_ROUND_UP(nr_objects * 2, oo_objects(s->oo));
- s->cpu_partial_pages = nr_pages;
+ nr_slabs = DIV_ROUND_UP(nr_objects * 2, oo_objects(s->oo));
+ s->cpu_partial_slabs = nr_slabs;
}
#else
static inline void
/*
* Per slab locking using the pagelock
*/
-static __always_inline void __slab_lock(struct page *page)
+static __always_inline void __slab_lock(struct slab *slab)
{
+ struct page *page = slab_page(slab);
+
VM_BUG_ON_PAGE(PageTail(page), page);
bit_spin_lock(PG_locked, &page->flags);
}
-static __always_inline void __slab_unlock(struct page *page)
+static __always_inline void __slab_unlock(struct slab *slab)
{
+ struct page *page = slab_page(slab);
+
VM_BUG_ON_PAGE(PageTail(page), page);
__bit_spin_unlock(PG_locked, &page->flags);
}
-static __always_inline void slab_lock(struct page *page, unsigned long *flags)
+static __always_inline void slab_lock(struct slab *slab, unsigned long *flags)
{
if (IS_ENABLED(CONFIG_PREEMPT_RT))
local_irq_save(*flags);
- __slab_lock(page);
+ __slab_lock(slab);
}
-static __always_inline void slab_unlock(struct page *page, unsigned long *flags)
+static __always_inline void slab_unlock(struct slab *slab, unsigned long *flags)
{
- __slab_unlock(page);
+ __slab_unlock(slab);
if (IS_ENABLED(CONFIG_PREEMPT_RT))
local_irq_restore(*flags);
}
* by an _irqsave() lock variant. Except on PREEMPT_RT where locks are different
* so we disable interrupts as part of slab_[un]lock().
*/
-static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct page *page,
+static inline bool __cmpxchg_double_slab(struct kmem_cache *s, struct slab *slab,
void *freelist_old, unsigned long counters_old,
void *freelist_new, unsigned long counters_new,
const char *n)
#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \
defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
if (s->flags & __CMPXCHG_DOUBLE) {
- if (cmpxchg_double(&page->freelist, &page->counters,
+ if (cmpxchg_double(&slab->freelist, &slab->counters,
freelist_old, counters_old,
freelist_new, counters_new))
return true;
/* init to 0 to prevent spurious warnings */
unsigned long flags = 0;
- slab_lock(page, &flags);
- if (page->freelist == freelist_old &&
- page->counters == counters_old) {
- page->freelist = freelist_new;
- page->counters = counters_new;
- slab_unlock(page, &flags);
+ slab_lock(slab, &flags);
+ if (slab->freelist == freelist_old &&
+ slab->counters == counters_old) {
+ slab->freelist = freelist_new;
+ slab->counters = counters_new;
+ slab_unlock(slab, &flags);
return true;
}
- slab_unlock(page, &flags);
+ slab_unlock(slab, &flags);
}
cpu_relax();
return false;
}
-static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page,
+static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct slab *slab,
void *freelist_old, unsigned long counters_old,
void *freelist_new, unsigned long counters_new,
const char *n)
#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \
defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
if (s->flags & __CMPXCHG_DOUBLE) {
- if (cmpxchg_double(&page->freelist, &page->counters,
+ if (cmpxchg_double(&slab->freelist, &slab->counters,
freelist_old, counters_old,
freelist_new, counters_new))
return true;
unsigned long flags;
local_irq_save(flags);
- __slab_lock(page);
- if (page->freelist == freelist_old &&
- page->counters == counters_old) {
- page->freelist = freelist_new;
- page->counters = counters_new;
- __slab_unlock(page);
+ __slab_lock(slab);
+ if (slab->freelist == freelist_old &&
+ slab->counters == counters_old) {
+ slab->freelist = freelist_new;
+ slab->counters = counters_new;
+ __slab_unlock(slab);
local_irq_restore(flags);
return true;
}
- __slab_unlock(page);
+ __slab_unlock(slab);
local_irq_restore(flags);
}
static DEFINE_RAW_SPINLOCK(object_map_lock);
static void __fill_map(unsigned long *obj_map, struct kmem_cache *s,
- struct page *page)
+ struct slab *slab)
{
- void *addr = page_address(page);
+ void *addr = slab_address(slab);
void *p;
- bitmap_zero(obj_map, page->objects);
+ bitmap_zero(obj_map, slab->objects);
- for (p = page->freelist; p; p = get_freepointer(s, p))
+ for (p = slab->freelist; p; p = get_freepointer(s, p))
set_bit(__obj_to_index(s, addr, p), obj_map);
}
#endif
/*
- * Determine a map of object in use on a page.
+ * Determine a map of objects in use in a slab.
*
- * Node listlock must be held to guarantee that the page does
+ * Node listlock must be held to guarantee that the slab does
* not vanish from under us.
*/
-static unsigned long *get_map(struct kmem_cache *s, struct page *page)
+static unsigned long *get_map(struct kmem_cache *s, struct slab *slab)
__acquires(&object_map_lock)
{
VM_BUG_ON(!irqs_disabled());
raw_spin_lock(&object_map_lock);
- __fill_map(object_map, s, page);
+ __fill_map(object_map, s, slab);
return object_map;
}
/* Verify that a pointer has an address that is valid within a slab page */
static inline int check_valid_pointer(struct kmem_cache *s,
- struct page *page, void *object)
+ struct slab *slab, void *object)
{
void *base;
if (!object)
return 1;
- base = page_address(page);
+ base = slab_address(slab);
object = kasan_reset_tag(object);
object = restore_red_left(s, object);
- if (object < base || object >= base + page->objects * s->size ||
+ if (object < base || object >= base + slab->objects * s->size ||
(object - base) % s->size) {
return 0;
}
print_track("Freed", get_track(s, object, TRACK_FREE), pr_time);
}
-static void print_page_info(struct page *page)
+static void print_slab_info(const struct slab *slab)
{
- pr_err("Slab 0x%p objects=%u used=%u fp=0x%p flags=%pGp\n",
- page, page->objects, page->inuse, page->freelist,
- &page->flags);
+ struct folio *folio = (struct folio *)slab_folio(slab);
+ pr_err("Slab 0x%p objects=%u used=%u fp=0x%p flags=%pGp\n",
+ slab, slab->objects, slab->inuse, slab->freelist,
+ folio_flags(folio, 0));
}
static void slab_bug(struct kmem_cache *s, char *fmt, ...)
va_end(args);
}
-static bool freelist_corrupted(struct kmem_cache *s, struct page *page,
- void **freelist, void *nextfree)
-{
- if ((s->flags & SLAB_CONSISTENCY_CHECKS) &&
- !check_valid_pointer(s, page, nextfree) && freelist) {
- object_err(s, page, *freelist, "Freechain corrupt");
- *freelist = NULL;
- slab_fix(s, "Isolate corrupted freechain");
- return true;
- }
-
- return false;
-}
-
-static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
+static void print_trailer(struct kmem_cache *s, struct slab *slab, u8 *p)
{
unsigned int off; /* Offset of last byte */
- u8 *addr = page_address(page);
+ u8 *addr = slab_address(slab);
print_tracking(s, p);
- print_page_info(page);
+ print_slab_info(slab);
pr_err("Object 0x%p @offset=%tu fp=0x%p\n\n",
p, p - addr, get_freepointer(s, p));
dump_stack();
}
-void object_err(struct kmem_cache *s, struct page *page,
+static void object_err(struct kmem_cache *s, struct slab *slab,
u8 *object, char *reason)
{
if (slab_add_kunit_errors())
return;
slab_bug(s, "%s", reason);
- print_trailer(s, page, object);
+ print_trailer(s, slab, object);
add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
}
-static __printf(3, 4) void slab_err(struct kmem_cache *s, struct page *page,
+static bool freelist_corrupted(struct kmem_cache *s, struct slab *slab,
+ void **freelist, void *nextfree)
+{
+ if ((s->flags & SLAB_CONSISTENCY_CHECKS) &&
+ !check_valid_pointer(s, slab, nextfree) && freelist) {
+ object_err(s, slab, *freelist, "Freechain corrupt");
+ *freelist = NULL;
+ slab_fix(s, "Isolate corrupted freechain");
+ return true;
+ }
+
+ return false;
+}
+
+static __printf(3, 4) void slab_err(struct kmem_cache *s, struct slab *slab,
const char *fmt, ...)
{
va_list args;
vsnprintf(buf, sizeof(buf), fmt, args);
va_end(args);
slab_bug(s, "%s", buf);
- print_page_info(page);
+ print_slab_info(slab);
dump_stack();
add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
}
memset(from, data, to - from);
}
-static int check_bytes_and_report(struct kmem_cache *s, struct page *page,
+static int check_bytes_and_report(struct kmem_cache *s, struct slab *slab,
u8 *object, char *what,
u8 *start, unsigned int value, unsigned int bytes)
{
u8 *fault;
u8 *end;
- u8 *addr = page_address(page);
+ u8 *addr = slab_address(slab);
metadata_access_enable();
fault = memchr_inv(kasan_reset_tag(start), value, bytes);
pr_err("0x%p-0x%p @offset=%tu. First byte 0x%x instead of 0x%x\n",
fault, end - 1, fault - addr,
fault[0], value);
- print_trailer(s, page, object);
+ print_trailer(s, slab, object);
add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
skip_bug_print:
* may be used with merged slabcaches.
*/
-static int check_pad_bytes(struct kmem_cache *s, struct page *page, u8 *p)
+static int check_pad_bytes(struct kmem_cache *s, struct slab *slab, u8 *p)
{
unsigned long off = get_info_end(s); /* The end of info */
if (size_from_object(s) == off)
return 1;
- return check_bytes_and_report(s, page, p, "Object padding",
+ return check_bytes_and_report(s, slab, p, "Object padding",
p + off, POISON_INUSE, size_from_object(s) - off);
}
/* Check the pad bytes at the end of a slab page */
-static int slab_pad_check(struct kmem_cache *s, struct page *page)
+static int slab_pad_check(struct kmem_cache *s, struct slab *slab)
{
u8 *start;
u8 *fault;
if (!(s->flags & SLAB_POISON))
return 1;
- start = page_address(page);
- length = page_size(page);
+ start = slab_address(slab);
+ length = slab_size(slab);
end = start + length;
remainder = length % s->size;
if (!remainder)
while (end > fault && end[-1] == POISON_INUSE)
end--;
- slab_err(s, page, "Padding overwritten. 0x%p-0x%p @offset=%tu",
+ slab_err(s, slab, "Padding overwritten. 0x%p-0x%p @offset=%tu",
fault, end - 1, fault - start);
print_section(KERN_ERR, "Padding ", pad, remainder);
return 0;
}
-static int check_object(struct kmem_cache *s, struct page *page,
+static int check_object(struct kmem_cache *s, struct slab *slab,
void *object, u8 val)
{
u8 *p = object;
u8 *endobject = object + s->object_size;
if (s->flags & SLAB_RED_ZONE) {
- if (!check_bytes_and_report(s, page, object, "Left Redzone",
+ if (!check_bytes_and_report(s, slab, object, "Left Redzone",
object - s->red_left_pad, val, s->red_left_pad))
return 0;
- if (!check_bytes_and_report(s, page, object, "Right Redzone",
+ if (!check_bytes_and_report(s, slab, object, "Right Redzone",
endobject, val, s->inuse - s->object_size))
return 0;
} else {
if ((s->flags & SLAB_POISON) && s->object_size < s->inuse) {
- check_bytes_and_report(s, page, p, "Alignment padding",
+ check_bytes_and_report(s, slab, p, "Alignment padding",
endobject, POISON_INUSE,
s->inuse - s->object_size);
}
if (s->flags & SLAB_POISON) {
if (val != SLUB_RED_ACTIVE && (s->flags & __OBJECT_POISON) &&
- (!check_bytes_and_report(s, page, p, "Poison", p,
+ (!check_bytes_and_report(s, slab, p, "Poison", p,
POISON_FREE, s->object_size - 1) ||
- !check_bytes_and_report(s, page, p, "End Poison",
+ !check_bytes_and_report(s, slab, p, "End Poison",
p + s->object_size - 1, POISON_END, 1)))
return 0;
/*
* check_pad_bytes cleans up on its own.
*/
- check_pad_bytes(s, page, p);
+ check_pad_bytes(s, slab, p);
}
if (!freeptr_outside_object(s) && val == SLUB_RED_ACTIVE)
return 1;
/* Check free pointer validity */
- if (!check_valid_pointer(s, page, get_freepointer(s, p))) {
- object_err(s, page, p, "Freepointer corrupt");
+ if (!check_valid_pointer(s, slab, get_freepointer(s, p))) {
+ object_err(s, slab, p, "Freepointer corrupt");
/*
* No choice but to zap it and thus lose the remainder
* of the free objects in this slab. May cause
return 1;
}
-static int check_slab(struct kmem_cache *s, struct page *page)
+static int check_slab(struct kmem_cache *s, struct slab *slab)
{
int maxobj;
- if (!PageSlab(page)) {
- slab_err(s, page, "Not a valid slab page");
+ if (!folio_test_slab(slab_folio(slab))) {
+ slab_err(s, slab, "Not a valid slab page");
return 0;
}
- maxobj = order_objects(compound_order(page), s->size);
- if (page->objects > maxobj) {
- slab_err(s, page, "objects %u > max %u",
- page->objects, maxobj);
+ maxobj = order_objects(slab_order(slab), s->size);
+ if (slab->objects > maxobj) {
+ slab_err(s, slab, "objects %u > max %u",
+ slab->objects, maxobj);
return 0;
}
- if (page->inuse > page->objects) {
- slab_err(s, page, "inuse %u > max %u",
- page->inuse, page->objects);
+ if (slab->inuse > slab->objects) {
+ slab_err(s, slab, "inuse %u > max %u",
+ slab->inuse, slab->objects);
return 0;
}
/* Slab_pad_check fixes things up after itself */
- slab_pad_check(s, page);
+ slab_pad_check(s, slab);
return 1;
}
/*
- * Determine if a certain object on a page is on the freelist. Must hold the
+ * Determine if a certain object in a slab is on the freelist. Must hold the
* slab lock to guarantee that the chains are in a consistent state.
*/
-static int on_freelist(struct kmem_cache *s, struct page *page, void *search)
+static int on_freelist(struct kmem_cache *s, struct slab *slab, void *search)
{
int nr = 0;
void *fp;
void *object = NULL;
int max_objects;
- fp = page->freelist;
- while (fp && nr <= page->objects) {
+ fp = slab->freelist;
+ while (fp && nr <= slab->objects) {
if (fp == search)
return 1;
- if (!check_valid_pointer(s, page, fp)) {
+ if (!check_valid_pointer(s, slab, fp)) {
if (object) {
- object_err(s, page, object,
+ object_err(s, slab, object,
"Freechain corrupt");
set_freepointer(s, object, NULL);
} else {
- slab_err(s, page, "Freepointer corrupt");
- page->freelist = NULL;
- page->inuse = page->objects;
+ slab_err(s, slab, "Freepointer corrupt");
+ slab->freelist = NULL;
+ slab->inuse = slab->objects;
slab_fix(s, "Freelist cleared");
return 0;
}
nr++;
}
- max_objects = order_objects(compound_order(page), s->size);
+ max_objects = order_objects(slab_order(slab), s->size);
if (max_objects > MAX_OBJS_PER_PAGE)
max_objects = MAX_OBJS_PER_PAGE;
- if (page->objects != max_objects) {
- slab_err(s, page, "Wrong number of objects. Found %d but should be %d",
- page->objects, max_objects);
- page->objects = max_objects;
+ if (slab->objects != max_objects) {
+ slab_err(s, slab, "Wrong number of objects. Found %d but should be %d",
+ slab->objects, max_objects);
+ slab->objects = max_objects;
slab_fix(s, "Number of objects adjusted");
}
- if (page->inuse != page->objects - nr) {
- slab_err(s, page, "Wrong object count. Counter is %d but counted were %d",
- page->inuse, page->objects - nr);
- page->inuse = page->objects - nr;
+ if (slab->inuse != slab->objects - nr) {
+ slab_err(s, slab, "Wrong object count. Counter is %d but counted were %d",
+ slab->inuse, slab->objects - nr);
+ slab->inuse = slab->objects - nr;
slab_fix(s, "Object count adjusted");
}
return search == NULL;
}
-static void trace(struct kmem_cache *s, struct page *page, void *object,
+static void trace(struct kmem_cache *s, struct slab *slab, void *object,
int alloc)
{
if (s->flags & SLAB_TRACE) {
pr_info("TRACE %s %s 0x%p inuse=%d fp=0x%p\n",
s->name,
alloc ? "alloc" : "free",
- object, page->inuse,
- page->freelist);
+ object, slab->inuse,
+ slab->freelist);
if (!alloc)
print_section(KERN_INFO, "Object ", (void *)object,
* Tracking of fully allocated slabs for debugging purposes.
*/
static void add_full(struct kmem_cache *s,
- struct kmem_cache_node *n, struct page *page)
+ struct kmem_cache_node *n, struct slab *slab)
{
if (!(s->flags & SLAB_STORE_USER))
return;
lockdep_assert_held(&n->list_lock);
- list_add(&page->slab_list, &n->full);
+ list_add(&slab->slab_list, &n->full);
}
-static void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, struct page *page)
+static void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, struct slab *slab)
{
if (!(s->flags & SLAB_STORE_USER))
return;
lockdep_assert_held(&n->list_lock);
- list_del(&page->slab_list);
+ list_del(&slab->slab_list);
}
/* Tracking of the number of slabs for debugging purposes */
}
/* Object debug checks for alloc/free paths */
-static void setup_object_debug(struct kmem_cache *s, struct page *page,
+static void setup_object_debug(struct kmem_cache *s, struct slab *slab,
void *object)
{
if (!kmem_cache_debug_flags(s, SLAB_STORE_USER|SLAB_RED_ZONE|__OBJECT_POISON))
}
static
-void setup_page_debug(struct kmem_cache *s, struct page *page, void *addr)
+void setup_slab_debug(struct kmem_cache *s, struct slab *slab, void *addr)
{
if (!kmem_cache_debug_flags(s, SLAB_POISON))
return;
metadata_access_enable();
- memset(kasan_reset_tag(addr), POISON_INUSE, page_size(page));
+ memset(kasan_reset_tag(addr), POISON_INUSE, slab_size(slab));
metadata_access_disable();
}
static inline int alloc_consistency_checks(struct kmem_cache *s,
- struct page *page, void *object)
+ struct slab *slab, void *object)
{
- if (!check_slab(s, page))
+ if (!check_slab(s, slab))
return 0;
- if (!check_valid_pointer(s, page, object)) {
- object_err(s, page, object, "Freelist Pointer check fails");
+ if (!check_valid_pointer(s, slab, object)) {
+ object_err(s, slab, object, "Freelist Pointer check fails");
return 0;
}
- if (!check_object(s, page, object, SLUB_RED_INACTIVE))
+ if (!check_object(s, slab, object, SLUB_RED_INACTIVE))
return 0;
return 1;
}
static noinline int alloc_debug_processing(struct kmem_cache *s,
- struct page *page,
+ struct slab *slab,
void *object, unsigned long addr)
{
if (s->flags & SLAB_CONSISTENCY_CHECKS) {
- if (!alloc_consistency_checks(s, page, object))
+ if (!alloc_consistency_checks(s, slab, object))
goto bad;
}
/* Success perform special debug activities for allocs */
if (s->flags & SLAB_STORE_USER)
set_track(s, object, TRACK_ALLOC, addr);
- trace(s, page, object, 1);
+ trace(s, slab, object, 1);
init_object(s, object, SLUB_RED_ACTIVE);
return 1;
bad:
- if (PageSlab(page)) {
+ if (folio_test_slab(slab_folio(slab))) {
/*
* If this is a slab page then lets do the best we can
* to avoid issues in the future. Marking all objects
* as used avoids touching the remaining objects.
*/
slab_fix(s, "Marking all objects used");
- page->inuse = page->objects;
- page->freelist = NULL;
+ slab->inuse = slab->objects;
+ slab->freelist = NULL;
}
return 0;
}
static inline int free_consistency_checks(struct kmem_cache *s,
- struct page *page, void *object, unsigned long addr)
+ struct slab *slab, void *object, unsigned long addr)
{
- if (!check_valid_pointer(s, page, object)) {
- slab_err(s, page, "Invalid object pointer 0x%p", object);
+ if (!check_valid_pointer(s, slab, object)) {
+ slab_err(s, slab, "Invalid object pointer 0x%p", object);
return 0;
}
- if (on_freelist(s, page, object)) {
- object_err(s, page, object, "Object already free");
+ if (on_freelist(s, slab, object)) {
+ object_err(s, slab, object, "Object already free");
return 0;
}
- if (!check_object(s, page, object, SLUB_RED_ACTIVE))
+ if (!check_object(s, slab, object, SLUB_RED_ACTIVE))
return 0;
- if (unlikely(s != page->slab_cache)) {
- if (!PageSlab(page)) {
- slab_err(s, page, "Attempt to free object(0x%p) outside of slab",
+ if (unlikely(s != slab->slab_cache)) {
+ if (!folio_test_slab(slab_folio(slab))) {
+ slab_err(s, slab, "Attempt to free object(0x%p) outside of slab",
object);
- } else if (!page->slab_cache) {
+ } else if (!slab->slab_cache) {
pr_err("SLUB <none>: no slab for object 0x%p.\n",
object);
dump_stack();
} else
- object_err(s, page, object,
+ object_err(s, slab, object,
"page slab pointer corrupt.");
return 0;
}
/* Supports checking bulk free of a constructed freelist */
static noinline int free_debug_processing(
- struct kmem_cache *s, struct page *page,
+ struct kmem_cache *s, struct slab *slab,
void *head, void *tail, int bulk_cnt,
unsigned long addr)
{
- struct kmem_cache_node *n = get_node(s, page_to_nid(page));
+ struct kmem_cache_node *n = get_node(s, slab_nid(slab));
void *object = head;
int cnt = 0;
unsigned long flags, flags2;
int ret = 0;
spin_lock_irqsave(&n->list_lock, flags);
- slab_lock(page, &flags2);
+ slab_lock(slab, &flags2);
if (s->flags & SLAB_CONSISTENCY_CHECKS) {
- if (!check_slab(s, page))
+ if (!check_slab(s, slab))
goto out;
}
cnt++;
if (s->flags & SLAB_CONSISTENCY_CHECKS) {
- if (!free_consistency_checks(s, page, object, addr))
+ if (!free_consistency_checks(s, slab, object, addr))
goto out;
}
if (s->flags & SLAB_STORE_USER)
set_track(s, object, TRACK_FREE, addr);
- trace(s, page, object, 0);
+ trace(s, slab, object, 0);
/* Freepointer not overwritten by init_object(), SLAB_POISON moved it */
init_object(s, object, SLUB_RED_INACTIVE);
out:
if (cnt != bulk_cnt)
- slab_err(s, page, "Bulk freelist count(%d) invalid(%d)\n",
+ slab_err(s, slab, "Bulk freelist count(%d) invalid(%d)\n",
bulk_cnt, cnt);
- slab_unlock(page, &flags2);
+ slab_unlock(slab, &flags2);
spin_unlock_irqrestore(&n->list_lock, flags);
if (!ret)
slab_fix(s, "Object at 0x%p not freed", object);
}
#else /* !CONFIG_SLUB_DEBUG */
static inline void setup_object_debug(struct kmem_cache *s,
- struct page *page, void *object) {}
+ struct slab *slab, void *object) {}
static inline
-void setup_page_debug(struct kmem_cache *s, struct page *page, void *addr) {}
+void setup_slab_debug(struct kmem_cache *s, struct slab *slab, void *addr) {}
static inline int alloc_debug_processing(struct kmem_cache *s,
- struct page *page, void *object, unsigned long addr) { return 0; }
+ struct slab *slab, void *object, unsigned long addr) { return 0; }
static inline int free_debug_processing(
- struct kmem_cache *s, struct page *page,
+ struct kmem_cache *s, struct slab *slab,
void *head, void *tail, int bulk_cnt,
unsigned long addr) { return 0; }
-static inline int slab_pad_check(struct kmem_cache *s, struct page *page)
+static inline int slab_pad_check(struct kmem_cache *s, struct slab *slab)
{ return 1; }
-static inline int check_object(struct kmem_cache *s, struct page *page,
+static inline int check_object(struct kmem_cache *s, struct slab *slab,
void *object, u8 val) { return 1; }
static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n,
- struct page *page) {}
+ struct slab *slab) {}
static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n,
- struct page *page) {}
+ struct slab *slab) {}
slab_flags_t kmem_cache_flags(unsigned int object_size,
slab_flags_t flags, const char *name)
{
static inline void dec_slabs_node(struct kmem_cache *s, int node,
int objects) {}
-static bool freelist_corrupted(struct kmem_cache *s, struct page *page,
+static bool freelist_corrupted(struct kmem_cache *s, struct slab *slab,
void **freelist, void *nextfree)
{
return false;
return *head != NULL;
}
-static void *setup_object(struct kmem_cache *s, struct page *page,
+static void *setup_object(struct kmem_cache *s, struct slab *slab,
void *object)
{
- setup_object_debug(s, page, object);
+ setup_object_debug(s, slab, object);
object = kasan_init_slab_obj(s, object);
if (unlikely(s->ctor)) {
kasan_unpoison_object_data(s, object);
/*
* Slab allocation and freeing
*/
-static inline struct page *alloc_slab_page(struct kmem_cache *s,
+static inline struct slab *alloc_slab_page(struct kmem_cache *s,
gfp_t flags, int node, struct kmem_cache_order_objects oo)
{
- struct page *page;
+ struct folio *folio;
+ struct slab *slab;
unsigned int order = oo_order(oo);
if (node == NUMA_NO_NODE)
- page = alloc_pages(flags, order);
+ folio = (struct folio *)alloc_pages(flags, order);
else
- page = __alloc_pages_node(node, flags, order);
+ folio = (struct folio *)__alloc_pages_node(node, flags, order);
+
+ if (!folio)
+ return NULL;
+
+ slab = folio_slab(folio);
+ __folio_set_slab(folio);
+ if (page_is_pfmemalloc(folio_page(folio, 0)))
+ slab_set_pfmemalloc(slab);
- return page;
+ return slab;
}
#ifdef CONFIG_SLAB_FREELIST_RANDOM
}
/* Get the next entry on the pre-computed freelist randomized */
-static void *next_freelist_entry(struct kmem_cache *s, struct page *page,
+static void *next_freelist_entry(struct kmem_cache *s, struct slab *slab,
unsigned long *pos, void *start,
unsigned long page_limit,
unsigned long freelist_count)
}
/* Shuffle the single linked freelist based on a random pre-computed sequence */
-static bool shuffle_freelist(struct kmem_cache *s, struct page *page)
+static bool shuffle_freelist(struct kmem_cache *s, struct slab *slab)
{
void *start;
void *cur;
void *next;
unsigned long idx, pos, page_limit, freelist_count;
- if (page->objects < 2 || !s->random_seq)
+ if (slab->objects < 2 || !s->random_seq)
return false;
freelist_count = oo_objects(s->oo);
pos = get_random_int() % freelist_count;
- page_limit = page->objects * s->size;
- start = fixup_red_left(s, page_address(page));
+ page_limit = slab->objects * s->size;
+ start = fixup_red_left(s, slab_address(slab));
/* First entry is used as the base of the freelist */
- cur = next_freelist_entry(s, page, &pos, start, page_limit,
+ cur = next_freelist_entry(s, slab, &pos, start, page_limit,
freelist_count);
- cur = setup_object(s, page, cur);
- page->freelist = cur;
+ cur = setup_object(s, slab, cur);
+ slab->freelist = cur;
- for (idx = 1; idx < page->objects; idx++) {
- next = next_freelist_entry(s, page, &pos, start, page_limit,
+ for (idx = 1; idx < slab->objects; idx++) {
+ next = next_freelist_entry(s, slab, &pos, start, page_limit,
freelist_count);
- next = setup_object(s, page, next);
+ next = setup_object(s, slab, next);
set_freepointer(s, cur, next);
cur = next;
}
return 0;
}
static inline void init_freelist_randomization(void) { }
-static inline bool shuffle_freelist(struct kmem_cache *s, struct page *page)
+static inline bool shuffle_freelist(struct kmem_cache *s, struct slab *slab)
{
return false;
}
#endif /* CONFIG_SLAB_FREELIST_RANDOM */
-static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
+static struct slab *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
{
- struct page *page;
+ struct slab *slab;
struct kmem_cache_order_objects oo = s->oo;
gfp_t alloc_gfp;
void *start, *p, *next;
if ((alloc_gfp & __GFP_DIRECT_RECLAIM) && oo_order(oo) > oo_order(s->min))
alloc_gfp = (alloc_gfp | __GFP_NOMEMALLOC) & ~(__GFP_RECLAIM|__GFP_NOFAIL);
- page = alloc_slab_page(s, alloc_gfp, node, oo);
- if (unlikely(!page)) {
+ slab = alloc_slab_page(s, alloc_gfp, node, oo);
+ if (unlikely(!slab)) {
oo = s->min;
alloc_gfp = flags;
/*
* Allocation may have failed due to fragmentation.
* Try a lower order alloc if possible
*/
- page = alloc_slab_page(s, alloc_gfp, node, oo);
- if (unlikely(!page))
+ slab = alloc_slab_page(s, alloc_gfp, node, oo);
+ if (unlikely(!slab))
goto out;
stat(s, ORDER_FALLBACK);
}
- page->objects = oo_objects(oo);
+ slab->objects = oo_objects(oo);
- account_slab_page(page, oo_order(oo), s, flags);
+ account_slab(slab, oo_order(oo), s, flags);
- page->slab_cache = s;
- __SetPageSlab(page);
- if (page_is_pfmemalloc(page))
- SetPageSlabPfmemalloc(page);
+ slab->slab_cache = s;
- kasan_poison_slab(page);
+ kasan_poison_slab(slab);
- start = page_address(page);
+ start = slab_address(slab);
- setup_page_debug(s, page, start);
+ setup_slab_debug(s, slab, start);
- shuffle = shuffle_freelist(s, page);
+ shuffle = shuffle_freelist(s, slab);
if (!shuffle) {
start = fixup_red_left(s, start);
- start = setup_object(s, page, start);
- page->freelist = start;
- for (idx = 0, p = start; idx < page->objects - 1; idx++) {
+ start = setup_object(s, slab, start);
+ slab->freelist = start;
+ for (idx = 0, p = start; idx < slab->objects - 1; idx++) {
next = p + s->size;
- next = setup_object(s, page, next);
+ next = setup_object(s, slab, next);
set_freepointer(s, p, next);
p = next;
}
set_freepointer(s, p, NULL);
}
- page->inuse = page->objects;
- page->frozen = 1;
+ slab->inuse = slab->objects;
+ slab->frozen = 1;
out:
- if (!page)
+ if (!slab)
return NULL;
- inc_slabs_node(s, page_to_nid(page), page->objects);
+ inc_slabs_node(s, slab_nid(slab), slab->objects);
- return page;
+ return slab;
}
-static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
+static struct slab *new_slab(struct kmem_cache *s, gfp_t flags, int node)
{
if (unlikely(flags & GFP_SLAB_BUG_MASK))
flags = kmalloc_fix_flags(flags);
flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK), node);
}
-static void __free_slab(struct kmem_cache *s, struct page *page)
+static void __free_slab(struct kmem_cache *s, struct slab *slab)
{
- int order = compound_order(page);
+ struct folio *folio = slab_folio(slab);
+ int order = folio_order(folio);
int pages = 1 << order;
if (kmem_cache_debug_flags(s, SLAB_CONSISTENCY_CHECKS)) {
void *p;
- slab_pad_check(s, page);
- for_each_object(p, s, page_address(page),
- page->objects)
- check_object(s, page, p, SLUB_RED_INACTIVE);
+ slab_pad_check(s, slab);
+ for_each_object(p, s, slab_address(slab), slab->objects)
+ check_object(s, slab, p, SLUB_RED_INACTIVE);
}
- __ClearPageSlabPfmemalloc(page);
- __ClearPageSlab(page);
- /* In union with page->mapping where page allocator expects NULL */
- page->slab_cache = NULL;
+ __slab_clear_pfmemalloc(slab);
+ __folio_clear_slab(folio);
+ folio->mapping = NULL;
if (current->reclaim_state)
current->reclaim_state->reclaimed_slab += pages;
- unaccount_slab_page(page, order, s);
- __free_pages(page, order);
+ unaccount_slab(slab, order, s);
+ __free_pages(folio_page(folio, 0), order);
}
static void rcu_free_slab(struct rcu_head *h)
{
- struct page *page = container_of(h, struct page, rcu_head);
+ struct slab *slab = container_of(h, struct slab, rcu_head);
- __free_slab(page->slab_cache, page);
+ __free_slab(slab->slab_cache, slab);
}
-static void free_slab(struct kmem_cache *s, struct page *page)
+static void free_slab(struct kmem_cache *s, struct slab *slab)
{
if (unlikely(s->flags & SLAB_TYPESAFE_BY_RCU)) {
- call_rcu(&page->rcu_head, rcu_free_slab);
+ call_rcu(&slab->rcu_head, rcu_free_slab);
} else
- __free_slab(s, page);
+ __free_slab(s, slab);
}
-static void discard_slab(struct kmem_cache *s, struct page *page)
+static void discard_slab(struct kmem_cache *s, struct slab *slab)
{
- dec_slabs_node(s, page_to_nid(page), page->objects);
- free_slab(s, page);
+ dec_slabs_node(s, slab_nid(slab), slab->objects);
+ free_slab(s, slab);
}
/*
* Management of partially allocated slabs.
*/
static inline void
-__add_partial(struct kmem_cache_node *n, struct page *page, int tail)
+__add_partial(struct kmem_cache_node *n, struct slab *slab, int tail)
{
n->nr_partial++;
if (tail == DEACTIVATE_TO_TAIL)
- list_add_tail(&page->slab_list, &n->partial);
+ list_add_tail(&slab->slab_list, &n->partial);
else
- list_add(&page->slab_list, &n->partial);
+ list_add(&slab->slab_list, &n->partial);
}
static inline void add_partial(struct kmem_cache_node *n,
- struct page *page, int tail)
+ struct slab *slab, int tail)
{
lockdep_assert_held(&n->list_lock);
- __add_partial(n, page, tail);
+ __add_partial(n, slab, tail);
}
static inline void remove_partial(struct kmem_cache_node *n,
- struct page *page)
+ struct slab *slab)
{
lockdep_assert_held(&n->list_lock);
- list_del(&page->slab_list);
+ list_del(&slab->slab_list);
n->nr_partial--;
}
* Returns a list of objects or NULL if it fails.
*/
static inline void *acquire_slab(struct kmem_cache *s,
- struct kmem_cache_node *n, struct page *page,
+ struct kmem_cache_node *n, struct slab *slab,
int mode)
{
void *freelist;
unsigned long counters;
- struct page new;
+ struct slab new;
lockdep_assert_held(&n->list_lock);
* The old freelist is the list of objects for the
* per cpu allocation list.
*/
- freelist = page->freelist;
- counters = page->counters;
+ freelist = slab->freelist;
+ counters = slab->counters;
new.counters = counters;
if (mode) {
- new.inuse = page->objects;
+ new.inuse = slab->objects;
new.freelist = NULL;
} else {
new.freelist = freelist;
VM_BUG_ON(new.frozen);
new.frozen = 1;
- if (!__cmpxchg_double_slab(s, page,
+ if (!__cmpxchg_double_slab(s, slab,
freelist, counters,
new.freelist, new.counters,
"acquire_slab"))
return NULL;
- remove_partial(n, page);
+ remove_partial(n, slab);
WARN_ON(!freelist);
return freelist;
}
#ifdef CONFIG_SLUB_CPU_PARTIAL
-static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain);
+static void put_cpu_partial(struct kmem_cache *s, struct slab *slab, int drain);
#else
-static inline void put_cpu_partial(struct kmem_cache *s, struct page *page,
+static inline void put_cpu_partial(struct kmem_cache *s, struct slab *slab,
int drain) { }
#endif
-static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags);
+static inline bool pfmemalloc_match(struct slab *slab, gfp_t gfpflags);
/*
* Try to allocate a partial slab from a specific node.
*/
static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
- struct page **ret_page, gfp_t gfpflags)
+ struct slab **ret_slab, gfp_t gfpflags)
{
- struct page *page, *page2;
+ struct slab *slab, *slab2;
void *object = NULL;
unsigned long flags;
- unsigned int partial_pages = 0;
+ unsigned int partial_slabs = 0;
/*
* Racy check. If we mistakenly see no partial slabs then we
return NULL;
spin_lock_irqsave(&n->list_lock, flags);
- list_for_each_entry_safe(page, page2, &n->partial, slab_list) {
+ list_for_each_entry_safe(slab, slab2, &n->partial, slab_list) {
void *t;
- if (!pfmemalloc_match(page, gfpflags))
+ if (!pfmemalloc_match(slab, gfpflags))
continue;
- t = acquire_slab(s, n, page, object == NULL);
+ t = acquire_slab(s, n, slab, object == NULL);
if (!t)
break;
if (!object) {
- *ret_page = page;
+ *ret_slab = slab;
stat(s, ALLOC_FROM_PARTIAL);
object = t;
} else {
- put_cpu_partial(s, page, 0);
+ put_cpu_partial(s, slab, 0);
stat(s, CPU_PARTIAL_NODE);
- partial_pages++;
+ partial_slabs++;
}
#ifdef CONFIG_SLUB_CPU_PARTIAL
if (!kmem_cache_has_cpu_partial(s)
- || partial_pages > s->cpu_partial_pages / 2)
+ || partial_slabs > s->cpu_partial_slabs / 2)
break;
#else
break;
}
/*
- * Get a page from somewhere. Search in increasing NUMA distances.
+ * Get a slab from somewhere. Search in increasing NUMA distances.
*/
static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
- struct page **ret_page)
+ struct slab **ret_slab)
{
#ifdef CONFIG_NUMA
struct zonelist *zonelist;
if (n && cpuset_zone_allowed(zone, flags) &&
n->nr_partial > s->min_partial) {
- object = get_partial_node(s, n, ret_page, flags);
+ object = get_partial_node(s, n, ret_slab, flags);
if (object) {
/*
* Don't check read_mems_allowed_retry()
}
/*
- * Get a partial page, lock it and return it.
+ * Get a partial slab, lock it and return it.
*/
static void *get_partial(struct kmem_cache *s, gfp_t flags, int node,
- struct page **ret_page)
+ struct slab **ret_slab)
{
void *object;
int searchnode = node;
if (node == NUMA_NO_NODE)
searchnode = numa_mem_id();
- object = get_partial_node(s, get_node(s, searchnode), ret_page, flags);
+ object = get_partial_node(s, get_node(s, searchnode), ret_slab, flags);
if (object || node != NUMA_NO_NODE)
return object;
- return get_any_partial(s, flags, ret_page);
+ return get_any_partial(s, flags, ret_slab);
}
#ifdef CONFIG_PREEMPTION
}
/*
- * Finishes removing the cpu slab. Merges cpu's freelist with page's freelist,
+ * Finishes removing the cpu slab. Merges cpu's freelist with slab's freelist,
* unfreezes the slabs and puts it on the proper list.
* Assumes the slab has been already safely taken away from kmem_cache_cpu
* by the caller.
*/
-static void deactivate_slab(struct kmem_cache *s, struct page *page,
+static void deactivate_slab(struct kmem_cache *s, struct slab *slab,
void *freelist)
{
enum slab_modes { M_NONE, M_PARTIAL, M_FULL, M_FREE };
- struct kmem_cache_node *n = get_node(s, page_to_nid(page));
+ struct kmem_cache_node *n = get_node(s, slab_nid(slab));
int lock = 0, free_delta = 0;
enum slab_modes l = M_NONE, m = M_NONE;
void *nextfree, *freelist_iter, *freelist_tail;
int tail = DEACTIVATE_TO_HEAD;
unsigned long flags = 0;
- struct page new;
- struct page old;
+ struct slab new;
+ struct slab old;
- if (page->freelist) {
+ if (slab->freelist) {
stat(s, DEACTIVATE_REMOTE_FREES);
tail = DEACTIVATE_TO_TAIL;
}
* 'freelist_iter' is already corrupted. So isolate all objects
* starting at 'freelist_iter' by skipping them.
*/
- if (freelist_corrupted(s, page, &freelist_iter, nextfree))
+ if (freelist_corrupted(s, slab, &freelist_iter, nextfree))
break;
freelist_tail = freelist_iter;
}
/*
- * Stage two: Unfreeze the page while splicing the per-cpu
- * freelist to the head of page's freelist.
+ * Stage two: Unfreeze the slab while splicing the per-cpu
+ * freelist to the head of slab's freelist.
*
- * Ensure that the page is unfrozen while the list presence
+ * Ensure that the slab is unfrozen while the list presence
* reflects the actual number of objects during unfreeze.
*
* We setup the list membership and then perform a cmpxchg
- * with the count. If there is a mismatch then the page
- * is not unfrozen but the page is on the wrong list.
+ * with the count. If there is a mismatch then the slab
+ * is not unfrozen but the slab is on the wrong list.
*
* Then we restart the process which may have to remove
- * the page from the list that we just put it on again
+ * the slab from the list that we just put it on again
* because the number of objects in the slab may have
* changed.
*/
redo:
- old.freelist = READ_ONCE(page->freelist);
- old.counters = READ_ONCE(page->counters);
+ old.freelist = READ_ONCE(slab->freelist);
+ old.counters = READ_ONCE(slab->counters);
VM_BUG_ON(!old.frozen);
/* Determine target state of the slab */
if (!lock) {
lock = 1;
/*
- * Taking the spinlock removes the possibility
- * that acquire_slab() will see a slab page that
- * is frozen
+ * Taking the spinlock removes the possibility that
+ * acquire_slab() will see a slab that is frozen
*/
spin_lock_irqsave(&n->list_lock, flags);
}
if (l != m) {
if (l == M_PARTIAL)
- remove_partial(n, page);
+ remove_partial(n, slab);
else if (l == M_FULL)
- remove_full(s, n, page);
+ remove_full(s, n, slab);
if (m == M_PARTIAL)
- add_partial(n, page, tail);
+ add_partial(n, slab, tail);
else if (m == M_FULL)
- add_full(s, n, page);
+ add_full(s, n, slab);
}
l = m;
- if (!cmpxchg_double_slab(s, page,
+ if (!cmpxchg_double_slab(s, slab,
old.freelist, old.counters,
new.freelist, new.counters,
"unfreezing slab"))
stat(s, DEACTIVATE_FULL);
else if (m == M_FREE) {
stat(s, DEACTIVATE_EMPTY);
- discard_slab(s, page);
+ discard_slab(s, slab);
stat(s, FREE_SLAB);
}
}
#ifdef CONFIG_SLUB_CPU_PARTIAL
-static void __unfreeze_partials(struct kmem_cache *s, struct page *partial_page)
+static void __unfreeze_partials(struct kmem_cache *s, struct slab *partial_slab)
{
struct kmem_cache_node *n = NULL, *n2 = NULL;
- struct page *page, *discard_page = NULL;
+ struct slab *slab, *slab_to_discard = NULL;
unsigned long flags = 0;
- while (partial_page) {
- struct page new;
- struct page old;
+ while (partial_slab) {
+ struct slab new;
+ struct slab old;
- page = partial_page;
- partial_page = page->next;
+ slab = partial_slab;
+ partial_slab = slab->next;
- n2 = get_node(s, page_to_nid(page));
+ n2 = get_node(s, slab_nid(slab));
if (n != n2) {
if (n)
spin_unlock_irqrestore(&n->list_lock, flags);
do {
- old.freelist = page->freelist;
- old.counters = page->counters;
+ old.freelist = slab->freelist;
+ old.counters = slab->counters;
VM_BUG_ON(!old.frozen);
new.counters = old.counters;
new.frozen = 0;
- } while (!__cmpxchg_double_slab(s, page,
+ } while (!__cmpxchg_double_slab(s, slab,
old.freelist, old.counters,
new.freelist, new.counters,
"unfreezing slab"));
if (unlikely(!new.inuse && n->nr_partial >= s->min_partial)) {
- page->next = discard_page;
- discard_page = page;
+ slab->next = slab_to_discard;
+ slab_to_discard = slab;
} else {
- add_partial(n, page, DEACTIVATE_TO_TAIL);
+ add_partial(n, slab, DEACTIVATE_TO_TAIL);
stat(s, FREE_ADD_PARTIAL);
}
}
if (n)
spin_unlock_irqrestore(&n->list_lock, flags);
- while (discard_page) {
- page = discard_page;
- discard_page = discard_page->next;
+ while (slab_to_discard) {
+ slab = slab_to_discard;
+ slab_to_discard = slab_to_discard->next;
stat(s, DEACTIVATE_EMPTY);
- discard_slab(s, page);
+ discard_slab(s, slab);
stat(s, FREE_SLAB);
}
}
*/
static void unfreeze_partials(struct kmem_cache *s)
{
- struct page *partial_page;
+ struct slab *partial_slab;
unsigned long flags;
local_lock_irqsave(&s->cpu_slab->lock, flags);
- partial_page = this_cpu_read(s->cpu_slab->partial);
+ partial_slab = this_cpu_read(s->cpu_slab->partial);
this_cpu_write(s->cpu_slab->partial, NULL);
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
- if (partial_page)
- __unfreeze_partials(s, partial_page);
+ if (partial_slab)
+ __unfreeze_partials(s, partial_slab);
}
static void unfreeze_partials_cpu(struct kmem_cache *s,
struct kmem_cache_cpu *c)
{
- struct page *partial_page;
+ struct slab *partial_slab;
- partial_page = slub_percpu_partial(c);
+ partial_slab = slub_percpu_partial(c);
c->partial = NULL;
- if (partial_page)
- __unfreeze_partials(s, partial_page);
+ if (partial_slab)
+ __unfreeze_partials(s, partial_slab);
}
/*
- * Put a page that was just frozen (in __slab_free|get_partial_node) into a
- * partial page slot if available.
+ * Put a slab that was just frozen (in __slab_free|get_partial_node) into a
+ * partial slab slot if available.
*
* If we did not find a slot then simply move all the partials to the
* per node partial list.
*/
-static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
+static void put_cpu_partial(struct kmem_cache *s, struct slab *slab, int drain)
{
- struct page *oldpage;
- struct page *page_to_unfreeze = NULL;
+ struct slab *oldslab;
+ struct slab *slab_to_unfreeze = NULL;
unsigned long flags;
- int pages = 0;
+ int slabs = 0;
local_lock_irqsave(&s->cpu_slab->lock, flags);
- oldpage = this_cpu_read(s->cpu_slab->partial);
+ oldslab = this_cpu_read(s->cpu_slab->partial);
- if (oldpage) {
- if (drain && oldpage->pages >= s->cpu_partial_pages) {
+ if (oldslab) {
+ if (drain && oldslab->slabs >= s->cpu_partial_slabs) {
/*
* Partial array is full. Move the existing set to the
* per node partial list. Postpone the actual unfreezing
* outside of the critical section.
*/
- page_to_unfreeze = oldpage;
- oldpage = NULL;
+ slab_to_unfreeze = oldslab;
+ oldslab = NULL;
} else {
- pages = oldpage->pages;
+ slabs = oldslab->slabs;
}
}
- pages++;
+ slabs++;
- page->pages = pages;
- page->next = oldpage;
+ slab->slabs = slabs;
+ slab->next = oldslab;
- this_cpu_write(s->cpu_slab->partial, page);
+ this_cpu_write(s->cpu_slab->partial, slab);
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
- if (page_to_unfreeze) {
- __unfreeze_partials(s, page_to_unfreeze);
+ if (slab_to_unfreeze) {
+ __unfreeze_partials(s, slab_to_unfreeze);
stat(s, CPU_PARTIAL_DRAIN);
}
}
static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
{
unsigned long flags;
- struct page *page;
+ struct slab *slab;
void *freelist;
local_lock_irqsave(&s->cpu_slab->lock, flags);
- page = c->page;
+ slab = c->slab;
freelist = c->freelist;
- c->page = NULL;
+ c->slab = NULL;
c->freelist = NULL;
c->tid = next_tid(c->tid);
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
- if (page) {
- deactivate_slab(s, page, freelist);
+ if (slab) {
+ deactivate_slab(s, slab, freelist);
stat(s, CPUSLAB_FLUSH);
}
}
{
struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
void *freelist = c->freelist;
- struct page *page = c->page;
+ struct slab *slab = c->slab;
- c->page = NULL;
+ c->slab = NULL;
c->freelist = NULL;
c->tid = next_tid(c->tid);
- if (page) {
- deactivate_slab(s, page, freelist);
+ if (slab) {
+ deactivate_slab(s, slab, freelist);
stat(s, CPUSLAB_FLUSH);
}
s = sfw->s;
c = this_cpu_ptr(s->cpu_slab);
- if (c->page)
+ if (c->slab)
flush_slab(s, c);
unfreeze_partials(s);
{
struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
- return c->page || slub_percpu_partial(c);
+ return c->slab || slub_percpu_partial(c);
}
static DEFINE_MUTEX(flush_lock);
* Check if the objects in a per cpu structure fit numa
* locality expectations.
*/
-static inline int node_match(struct page *page, int node)
+static inline int node_match(struct slab *slab, int node)
{
#ifdef CONFIG_NUMA
- if (node != NUMA_NO_NODE && page_to_nid(page) != node)
+ if (node != NUMA_NO_NODE && slab_nid(slab) != node)
return 0;
#endif
return 1;
}
#ifdef CONFIG_SLUB_DEBUG
-static int count_free(struct page *page)
+static int count_free(struct slab *slab)
{
- return page->objects - page->inuse;
+ return slab->objects - slab->inuse;
}
static inline unsigned long node_nr_objs(struct kmem_cache_node *n)
#if defined(CONFIG_SLUB_DEBUG) || defined(CONFIG_SYSFS)
static unsigned long count_partial(struct kmem_cache_node *n,
- int (*get_count)(struct page *))
+ int (*get_count)(struct slab *))
{
unsigned long flags;
unsigned long x = 0;
- struct page *page;
+ struct slab *slab;
spin_lock_irqsave(&n->list_lock, flags);
- list_for_each_entry(page, &n->partial, slab_list)
- x += get_count(page);
+ list_for_each_entry(slab, &n->partial, slab_list)
+ x += get_count(slab);
spin_unlock_irqrestore(&n->list_lock, flags);
return x;
}
#endif
}
-static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags)
-{
- if (unlikely(PageSlabPfmemalloc(page)))
- return gfp_pfmemalloc_allowed(gfpflags);
-
- return true;
-}
-
-/*
- * A variant of pfmemalloc_match() that tests page flags without asserting
- * PageSlab. Intended for opportunistic checks before taking a lock and
- * rechecking that nobody else freed the page under us.
- */
-static inline bool pfmemalloc_match_unsafe(struct page *page, gfp_t gfpflags)
+static inline bool pfmemalloc_match(struct slab *slab, gfp_t gfpflags)
{
- if (unlikely(__PageSlabPfmemalloc(page)))
+ if (unlikely(slab_test_pfmemalloc(slab)))
return gfp_pfmemalloc_allowed(gfpflags);
return true;
}
/*
- * Check the page->freelist of a page and either transfer the freelist to the
- * per cpu freelist or deactivate the page.
+ * Check the slab->freelist and either transfer the freelist to the
+ * per cpu freelist or deactivate the slab.
*
- * The page is still frozen if the return value is not NULL.
+ * The slab is still frozen if the return value is not NULL.
*
- * If this function returns NULL then the page has been unfrozen.
+ * If this function returns NULL then the slab has been unfrozen.
*/
-static inline void *get_freelist(struct kmem_cache *s, struct page *page)
+static inline void *get_freelist(struct kmem_cache *s, struct slab *slab)
{
- struct page new;
+ struct slab new;
unsigned long counters;
void *freelist;
lockdep_assert_held(this_cpu_ptr(&s->cpu_slab->lock));
do {
- freelist = page->freelist;
- counters = page->counters;
+ freelist = slab->freelist;
+ counters = slab->counters;
new.counters = counters;
VM_BUG_ON(!new.frozen);
- new.inuse = page->objects;
+ new.inuse = slab->objects;
new.frozen = freelist != NULL;
- } while (!__cmpxchg_double_slab(s, page,
+ } while (!__cmpxchg_double_slab(s, slab,
freelist, counters,
NULL, new.counters,
"get_freelist"));
unsigned long addr, struct kmem_cache_cpu *c)
{
void *freelist;
- struct page *page;
+ struct slab *slab;
unsigned long flags;
stat(s, ALLOC_SLOWPATH);
-reread_page:
+reread_slab:
- page = READ_ONCE(c->page);
- if (!page) {
+ slab = READ_ONCE(c->slab);
+ if (!slab) {
/*
* if the node is not online or has no normal memory, just
* ignore the node constraint
}
redo:
- if (unlikely(!node_match(page, node))) {
+ if (unlikely(!node_match(slab, node))) {
/*
* same as above but node_match() being false already
* implies node != NUMA_NO_NODE
* PFMEMALLOC but right now, we are losing the pfmemalloc
* information when the page leaves the per-cpu allocator
*/
- if (unlikely(!pfmemalloc_match_unsafe(page, gfpflags)))
+ if (unlikely(!pfmemalloc_match(slab, gfpflags)))
goto deactivate_slab;
- /* must check again c->page in case we got preempted and it changed */
+ /* must check again c->slab in case we got preempted and it changed */
local_lock_irqsave(&s->cpu_slab->lock, flags);
- if (unlikely(page != c->page)) {
+ if (unlikely(slab != c->slab)) {
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
- goto reread_page;
+ goto reread_slab;
}
freelist = c->freelist;
if (freelist)
goto load_freelist;
- freelist = get_freelist(s, page);
+ freelist = get_freelist(s, slab);
if (!freelist) {
- c->page = NULL;
+ c->slab = NULL;
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
stat(s, DEACTIVATE_BYPASS);
goto new_slab;
/*
* freelist is pointing to the list of objects to be used.
- * page is pointing to the page from which the objects are obtained.
- * That page must be frozen for per cpu allocations to work.
+ * slab is pointing to the slab from which the objects are obtained.
+ * That slab must be frozen for per cpu allocations to work.
*/
- VM_BUG_ON(!c->page->frozen);
+ VM_BUG_ON(!c->slab->frozen);
c->freelist = get_freepointer(s, freelist);
c->tid = next_tid(c->tid);
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
deactivate_slab:
local_lock_irqsave(&s->cpu_slab->lock, flags);
- if (page != c->page) {
+ if (slab != c->slab) {
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
- goto reread_page;
+ goto reread_slab;
}
freelist = c->freelist;
- c->page = NULL;
+ c->slab = NULL;
c->freelist = NULL;
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
- deactivate_slab(s, page, freelist);
+ deactivate_slab(s, slab, freelist);
new_slab:
if (slub_percpu_partial(c)) {
local_lock_irqsave(&s->cpu_slab->lock, flags);
- if (unlikely(c->page)) {
+ if (unlikely(c->slab)) {
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
- goto reread_page;
+ goto reread_slab;
}
if (unlikely(!slub_percpu_partial(c))) {
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
goto new_objects;
}
- page = c->page = slub_percpu_partial(c);
- slub_set_percpu_partial(c, page);
+ slab = c->slab = slub_percpu_partial(c);
+ slub_set_percpu_partial(c, slab);
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
stat(s, CPU_PARTIAL_ALLOC);
goto redo;
new_objects:
- freelist = get_partial(s, gfpflags, node, &page);
+ freelist = get_partial(s, gfpflags, node, &slab);
if (freelist)
- goto check_new_page;
+ goto check_new_slab;
slub_put_cpu_ptr(s->cpu_slab);
- page = new_slab(s, gfpflags, node);
+ slab = new_slab(s, gfpflags, node);
c = slub_get_cpu_ptr(s->cpu_slab);
- if (unlikely(!page)) {
+ if (unlikely(!slab)) {
slab_out_of_memory(s, gfpflags, node);
return NULL;
}
/*
- * No other reference to the page yet so we can
+ * No other reference to the slab yet so we can
* muck around with it freely without cmpxchg
*/
- freelist = page->freelist;
- page->freelist = NULL;
+ freelist = slab->freelist;
+ slab->freelist = NULL;
stat(s, ALLOC_SLAB);
-check_new_page:
+check_new_slab:
if (kmem_cache_debug(s)) {
- if (!alloc_debug_processing(s, page, freelist, addr)) {
+ if (!alloc_debug_processing(s, slab, freelist, addr)) {
/* Slab failed checks. Next slab needed */
goto new_slab;
} else {
}
}
- if (unlikely(!pfmemalloc_match(page, gfpflags)))
+ if (unlikely(!pfmemalloc_match(slab, gfpflags)))
/*
* For !pfmemalloc_match() case we don't load freelist so that
* we don't make further mismatched allocations easier.
*/
goto return_single;
-retry_load_page:
+retry_load_slab:
local_lock_irqsave(&s->cpu_slab->lock, flags);
- if (unlikely(c->page)) {
+ if (unlikely(c->slab)) {
void *flush_freelist = c->freelist;
- struct page *flush_page = c->page;
+ struct slab *flush_slab = c->slab;
- c->page = NULL;
+ c->slab = NULL;
c->freelist = NULL;
c->tid = next_tid(c->tid);
local_unlock_irqrestore(&s->cpu_slab->lock, flags);
- deactivate_slab(s, flush_page, flush_freelist);
+ deactivate_slab(s, flush_slab, flush_freelist);
stat(s, CPUSLAB_FLUSH);
- goto retry_load_page;
+ goto retry_load_slab;
}
- c->page = page;
+ c->slab = slab;
goto load_freelist;
return_single:
- deactivate_slab(s, page, get_freepointer(s, freelist));
+ deactivate_slab(s, slab, get_freepointer(s, freelist));
return freelist;
}
{
void *object;
struct kmem_cache_cpu *c;
- struct page *page;
+ struct slab *slab;
unsigned long tid;
struct obj_cgroup *objcg = NULL;
bool init = false;
/*
* Irqless object alloc/free algorithm used here depends on sequence
* of fetching cpu_slab's data. tid should be fetched before anything
- * on c to guarantee that object and page associated with previous tid
+ * on c to guarantee that object and slab associated with previous tid
* won't be used with current tid. If we fetch tid first, object and
- * page could be one associated with next tid and our alloc/free
+ * slab could be one associated with next tid and our alloc/free
* request will be failed. In this case, we will retry. So, no problem.
*/
barrier();
*/
object = c->freelist;
- page = c->page;
+ slab = c->slab;
/*
* We cannot use the lockless fastpath on PREEMPT_RT because if a
* slowpath has taken the local_lock_irqsave(), it is not protected
* there is a suitable cpu freelist.
*/
if (IS_ENABLED(CONFIG_PREEMPT_RT) ||
- unlikely(!object || !page || !node_match(page, node))) {
+ unlikely(!object || !slab || !node_match(slab, node))) {
object = __slab_alloc(s, gfpflags, node, addr, c);
} else {
void *next_object = get_freepointer_safe(s, object);
* have a longer lifetime than the cpu slabs in most processing loads.
*
* So we still attempt to reduce cache line usage. Just take the slab
- * lock and free the item. If there is no additional partial page
+ * lock and free the item. If there is no additional partial slab
* handling required then we can return immediately.
*/
-static void __slab_free(struct kmem_cache *s, struct page *page,
+static void __slab_free(struct kmem_cache *s, struct slab *slab,
void *head, void *tail, int cnt,
unsigned long addr)
{
void *prior;
int was_frozen;
- struct page new;
+ struct slab new;
unsigned long counters;
struct kmem_cache_node *n = NULL;
unsigned long flags;
return;
if (kmem_cache_debug(s) &&
- !free_debug_processing(s, page, head, tail, cnt, addr))
+ !free_debug_processing(s, slab, head, tail, cnt, addr))
return;
do {
spin_unlock_irqrestore(&n->list_lock, flags);
n = NULL;
}
- prior = page->freelist;
- counters = page->counters;
+ prior = slab->freelist;
+ counters = slab->counters;
set_freepointer(s, tail, prior);
new.counters = counters;
was_frozen = new.frozen;
} else { /* Needs to be taken off a list */
- n = get_node(s, page_to_nid(page));
+ n = get_node(s, slab_nid(slab));
/*
* Speculatively acquire the list_lock.
* If the cmpxchg does not succeed then we may
}
}
- } while (!cmpxchg_double_slab(s, page,
+ } while (!cmpxchg_double_slab(s, slab,
prior, counters,
head, new.counters,
"__slab_free"));
stat(s, FREE_FROZEN);
} else if (new.frozen) {
/*
- * If we just froze the page then put it onto the
+ * If we just froze the slab then put it onto the
* per cpu partial list.
*/
- put_cpu_partial(s, page, 1);
+ put_cpu_partial(s, slab, 1);
stat(s, CPU_PARTIAL_FREE);
}
* then add it.
*/
if (!kmem_cache_has_cpu_partial(s) && unlikely(!prior)) {
- remove_full(s, n, page);
- add_partial(n, page, DEACTIVATE_TO_TAIL);
+ remove_full(s, n, slab);
+ add_partial(n, slab, DEACTIVATE_TO_TAIL);
stat(s, FREE_ADD_PARTIAL);
}
spin_unlock_irqrestore(&n->list_lock, flags);
/*
* Slab on the partial list.
*/
- remove_partial(n, page);
+ remove_partial(n, slab);
stat(s, FREE_REMOVE_PARTIAL);
} else {
/* Slab must be on the full list */
- remove_full(s, n, page);
+ remove_full(s, n, slab);
}
spin_unlock_irqrestore(&n->list_lock, flags);
stat(s, FREE_SLAB);
- discard_slab(s, page);
+ discard_slab(s, slab);
}
/*
* with all sorts of special processing.
*
* Bulk free of a freelist with several objects (all pointing to the
- * same page) possible by specifying head and tail ptr, plus objects
+ * same slab) possible by specifying head and tail ptr, plus objects
* count (cnt). Bulk free indicated by tail pointer being set.
*/
static __always_inline void do_slab_free(struct kmem_cache *s,
- struct page *page, void *head, void *tail,
+ struct slab *slab, void *head, void *tail,
int cnt, unsigned long addr)
{
void *tail_obj = tail ? : head;
/* Same with comment on barrier() in slab_alloc_node() */
barrier();
- if (likely(page == c->page)) {
+ if (likely(slab == c->slab)) {
#ifndef CONFIG_PREEMPT_RT
void **freelist = READ_ONCE(c->freelist);
local_lock(&s->cpu_slab->lock);
c = this_cpu_ptr(s->cpu_slab);
- if (unlikely(page != c->page)) {
+ if (unlikely(slab != c->slab)) {
local_unlock(&s->cpu_slab->lock);
goto redo;
}
#endif
stat(s, FREE_FASTPATH);
} else
- __slab_free(s, page, head, tail_obj, cnt, addr);
+ __slab_free(s, slab, head, tail_obj, cnt, addr);
}
-static __always_inline void slab_free(struct kmem_cache *s, struct page *page,
+static __always_inline void slab_free(struct kmem_cache *s, struct slab *slab,
void *head, void *tail, int cnt,
unsigned long addr)
{
* to remove objects, whose reuse must be delayed.
*/
if (slab_free_freelist_hook(s, &head, &tail, &cnt))
- do_slab_free(s, page, head, tail, cnt, addr);
+ do_slab_free(s, slab, head, tail, cnt, addr);
}
#ifdef CONFIG_KASAN_GENERIC
void ___cache_free(struct kmem_cache *cache, void *x, unsigned long addr)
{
- do_slab_free(cache, virt_to_head_page(x), x, NULL, 1, addr);
+ do_slab_free(cache, virt_to_slab(x), x, NULL, 1, addr);
}
#endif
if (!s)
return;
trace_kmem_cache_free(_RET_IP_, x, s->name);
- slab_free(s, virt_to_head_page(x), x, NULL, 1, _RET_IP_);
+ slab_free(s, virt_to_slab(x), x, NULL, 1, _RET_IP_);
}
EXPORT_SYMBOL(kmem_cache_free);
struct detached_freelist {
- struct page *page;
+ struct slab *slab;
void *tail;
void *freelist;
int cnt;
struct kmem_cache *s;
};
-static inline void free_nonslab_page(struct page *page, void *object)
+static inline void free_large_kmalloc(struct folio *folio, void *object)
{
- unsigned int order = compound_order(page);
+ unsigned int order = folio_order(folio);
- if (WARN_ON_ONCE(!PageCompound(page)))
+ if (WARN_ON_ONCE(order == 0))
pr_warn_once("object pointer: 0x%p\n", object);
kfree_hook(object);
- mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, -(PAGE_SIZE << order));
- __free_pages(page, order);
+ mod_lruvec_page_state(folio_page(folio, 0), NR_SLAB_UNRECLAIMABLE_B,
+ -(PAGE_SIZE << order));
+ __free_pages(folio_page(folio, 0), order);
}
/*
* This function progressively scans the array with free objects (with
* a limited look ahead) and extract objects belonging to the same
- * page. It builds a detached freelist directly within the given
- * page/objects. This can happen without any need for
+ * slab. It builds a detached freelist directly within the given
+ * slab/objects. This can happen without any need for
* synchronization, because the objects are owned by running process.
* The freelist is build up as a single linked list in the objects.
* The idea is, that this detached freelist can then be bulk
size_t first_skipped_index = 0;
int lookahead = 3;
void *object;
- struct page *page;
+ struct folio *folio;
+ struct slab *slab;
/* Always re-init detached_freelist */
- df->page = NULL;
+ df->slab = NULL;
do {
object = p[--size];
if (!object)
return 0;
- page = virt_to_head_page(object);
+ folio = virt_to_folio(object);
if (!s) {
/* Handle kalloc'ed objects */
- if (unlikely(!PageSlab(page))) {
- free_nonslab_page(page, object);
+ if (unlikely(!folio_test_slab(folio))) {
+ free_large_kmalloc(folio, object);
p[size] = NULL; /* mark object processed */
return size;
}
/* Derive kmem_cache from object */
- df->s = page->slab_cache;
+ slab = folio_slab(folio);
+ df->s = slab->slab_cache;
} else {
+ slab = folio_slab(folio);
df->s = cache_from_obj(s, object); /* Support for memcg */
}
}
/* Start new detached freelist */
- df->page = page;
+ df->slab = slab;
set_freepointer(df->s, object, NULL);
df->tail = object;
df->freelist = object;
if (!object)
continue; /* Skip processed objects */
- /* df->page is always set at this point */
- if (df->page == virt_to_head_page(object)) {
+ /* df->slab is always set at this point */
+ if (df->slab == virt_to_slab(object)) {
/* Opportunity build freelist */
set_freepointer(df->s, object, df->freelist);
df->freelist = object;
struct detached_freelist df;
size = build_detached_freelist(s, size, p, &df);
- if (!df.page)
+ if (!df.slab)
continue;
- slab_free(df.s, df.page, df.freelist, df.tail, df.cnt, _RET_IP_);
+ slab_free(df.s, df.slab, df.freelist, df.tail, df.cnt, _RET_IP_);
} while (likely(size));
}
EXPORT_SYMBOL(kmem_cache_free_bulk);
* requested a higher minimum order then we start with that one instead of
* the smallest order which will fit the object.
*/
-static inline unsigned int slab_order(unsigned int size,
+static inline unsigned int calc_slab_order(unsigned int size,
unsigned int min_objects, unsigned int max_order,
unsigned int fract_leftover)
{
fraction = 16;
while (fraction >= 4) {
- order = slab_order(size, min_objects,
+ order = calc_slab_order(size, min_objects,
slub_max_order, fraction);
if (order <= slub_max_order)
return order;
* We were unable to place multiple objects in a slab. Now
* lets see if we can place a single object there.
*/
- order = slab_order(size, 1, slub_max_order, 1);
+ order = calc_slab_order(size, 1, slub_max_order, 1);
if (order <= slub_max_order)
return order;
/*
* Doh this slab cannot be placed using slub_max_order.
*/
- order = slab_order(size, 1, MAX_ORDER, 1);
+ order = calc_slab_order(size, 1, MAX_ORDER, 1);
if (order < MAX_ORDER)
return order;
return -ENOSYS;
*/
static void early_kmem_cache_node_alloc(int node)
{
- struct page *page;
+ struct slab *slab;
struct kmem_cache_node *n;
BUG_ON(kmem_cache_node->size < sizeof(struct kmem_cache_node));
- page = new_slab(kmem_cache_node, GFP_NOWAIT, node);
+ slab = new_slab(kmem_cache_node, GFP_NOWAIT, node);
- BUG_ON(!page);
- if (page_to_nid(page) != node) {
+ BUG_ON(!slab);
+ if (slab_nid(slab) != node) {
pr_err("SLUB: Unable to allocate memory from node %d\n", node);
pr_err("SLUB: Allocating a useless per node structure in order to be able to continue\n");
}
- n = page->freelist;
+ n = slab->freelist;
BUG_ON(!n);
#ifdef CONFIG_SLUB_DEBUG
init_object(kmem_cache_node, n, SLUB_RED_ACTIVE);
init_tracking(kmem_cache_node, n);
#endif
n = kasan_slab_alloc(kmem_cache_node, n, GFP_KERNEL, false);
- page->freelist = get_freepointer(kmem_cache_node, n);
- page->inuse = 1;
- page->frozen = 0;
+ slab->freelist = get_freepointer(kmem_cache_node, n);
+ slab->inuse = 1;
+ slab->frozen = 0;
kmem_cache_node->node[node] = n;
init_kmem_cache_node(n);
- inc_slabs_node(kmem_cache_node, node, page->objects);
+ inc_slabs_node(kmem_cache_node, node, slab->objects);
/*
* No locks need to be taken here as it has just been
* initialized and there is no concurrent access.
*/
- __add_partial(n, page, DEACTIVATE_TO_HEAD);
+ __add_partial(n, slab, DEACTIVATE_TO_HEAD);
}
static void free_kmem_cache_nodes(struct kmem_cache *s)
#endif
/*
- * The larger the object size is, the more pages we want on the partial
+ * The larger the object size is, the more slabs we want on the partial
* list to avoid pounding the page allocator excessively.
*/
set_min_partial(s, ilog2(s->size) / 2);
return -EINVAL;
}
-static void list_slab_objects(struct kmem_cache *s, struct page *page,
+static void list_slab_objects(struct kmem_cache *s, struct slab *slab,
const char *text)
{
#ifdef CONFIG_SLUB_DEBUG
- void *addr = page_address(page);
+ void *addr = slab_address(slab);
unsigned long flags;
unsigned long *map;
void *p;
- slab_err(s, page, text, s->name);
- slab_lock(page, &flags);
+ slab_err(s, slab, text, s->name);
+ slab_lock(slab, &flags);
- map = get_map(s, page);
- for_each_object(p, s, addr, page->objects) {
+ map = get_map(s, slab);
+ for_each_object(p, s, addr, slab->objects) {
if (!test_bit(__obj_to_index(s, addr, p), map)) {
pr_err("Object 0x%p @offset=%tu\n", p, p - addr);
}
}
put_map(map);
- slab_unlock(page, &flags);
+ slab_unlock(slab, &flags);
#endif
}
static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
{
LIST_HEAD(discard);
- struct page *page, *h;
+ struct slab *slab, *h;
BUG_ON(irqs_disabled());
spin_lock_irq(&n->list_lock);
- list_for_each_entry_safe(page, h, &n->partial, slab_list) {
- if (!page->inuse) {
- remove_partial(n, page);
- list_add(&page->slab_list, &discard);
+ list_for_each_entry_safe(slab, h, &n->partial, slab_list) {
+ if (!slab->inuse) {
+ remove_partial(n, slab);
+ list_add(&slab->slab_list, &discard);
} else {
- list_slab_objects(s, page,
+ list_slab_objects(s, slab,
"Objects remaining in %s on __kmem_cache_shutdown()");
}
}
spin_unlock_irq(&n->list_lock);
- list_for_each_entry_safe(page, h, &discard, slab_list)
- discard_slab(s, page);
+ list_for_each_entry_safe(slab, h, &discard, slab_list)
+ discard_slab(s, slab);
}
bool __kmem_cache_empty(struct kmem_cache *s)
}
#ifdef CONFIG_PRINTK
-void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page)
+void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab)
{
void *base;
int __maybe_unused i;
unsigned int objnr;
void *objp;
void *objp0;
- struct kmem_cache *s = page->slab_cache;
+ struct kmem_cache *s = slab->slab_cache;
struct track __maybe_unused *trackp;
kpp->kp_ptr = object;
- kpp->kp_page = page;
+ kpp->kp_slab = slab;
kpp->kp_slab_cache = s;
- base = page_address(page);
+ base = slab_address(slab);
objp0 = kasan_reset_tag(object);
#ifdef CONFIG_SLUB_DEBUG
objp = restore_red_left(s, objp0);
#else
objp = objp0;
#endif
- objnr = obj_to_index(s, page, objp);
+ objnr = obj_to_index(s, slab, objp);
kpp->kp_data_offset = (unsigned long)((char *)objp0 - (char *)objp);
objp = base + s->size * objnr;
kpp->kp_objp = objp;
- if (WARN_ON_ONCE(objp < base || objp >= base + page->objects * s->size || (objp - base) % s->size) ||
+ if (WARN_ON_ONCE(objp < base || objp >= base + slab->objects * s->size
+ || (objp - base) % s->size) ||
!(s->flags & SLAB_STORE_USER))
return;
#ifdef CONFIG_SLUB_DEBUG
* Returns NULL if check passes, otherwise const char * to name of cache
* to indicate an error.
*/
-void __check_heap_object(const void *ptr, unsigned long n, struct page *page,
- bool to_user)
+void __check_heap_object(const void *ptr, unsigned long n,
+ const struct slab *slab, bool to_user)
{
struct kmem_cache *s;
unsigned int offset;
ptr = kasan_reset_tag(ptr);
/* Find object and usable object size. */
- s = page->slab_cache;
+ s = slab->slab_cache;
/* Reject impossible pointers. */
- if (ptr < page_address(page))
+ if (ptr < slab_address(slab))
usercopy_abort("SLUB object not in SLUB page?!", NULL,
to_user, 0, n);
if (is_kfence)
offset = ptr - kfence_object_start(ptr);
else
- offset = (ptr - page_address(page)) % s->size;
+ offset = (ptr - slab_address(slab)) % s->size;
/* Adjust for redzone and reject if within the redzone. */
if (!is_kfence && kmem_cache_debug_flags(s, SLAB_RED_ZONE)) {
size_t __ksize(const void *object)
{
- struct page *page;
+ struct folio *folio;
if (unlikely(object == ZERO_SIZE_PTR))
return 0;
- page = virt_to_head_page(object);
+ folio = virt_to_folio(object);
- if (unlikely(!PageSlab(page))) {
- WARN_ON(!PageCompound(page));
- return page_size(page);
- }
+ if (unlikely(!folio_test_slab(folio)))
+ return folio_size(folio);
- return slab_ksize(page->slab_cache);
+ return slab_ksize(folio_slab(folio)->slab_cache);
}
EXPORT_SYMBOL(__ksize);
void kfree(const void *x)
{
- struct page *page;
+ struct folio *folio;
+ struct slab *slab;
void *object = (void *)x;
trace_kfree(_RET_IP_, x);
if (unlikely(ZERO_OR_NULL_PTR(x)))
return;
- page = virt_to_head_page(x);
- if (unlikely(!PageSlab(page))) {
- free_nonslab_page(page, object);
+ folio = virt_to_folio(x);
+ if (unlikely(!folio_test_slab(folio))) {
+ free_large_kmalloc(folio, object);
return;
}
- slab_free(page->slab_cache, page, object, NULL, 1, _RET_IP_);
+ slab = folio_slab(folio);
+ slab_free(slab->slab_cache, slab, object, NULL, 1, _RET_IP_);
}
EXPORT_SYMBOL(kfree);
int node;
int i;
struct kmem_cache_node *n;
- struct page *page;
- struct page *t;
+ struct slab *slab;
+ struct slab *t;
struct list_head discard;
struct list_head promote[SHRINK_PROMOTE_MAX];
unsigned long flags;
* Build lists of slabs to discard or promote.
*
* Note that concurrent frees may occur while we hold the
- * list_lock. page->inuse here is the upper limit.
+ * list_lock. slab->inuse here is the upper limit.
*/
- list_for_each_entry_safe(page, t, &n->partial, slab_list) {
- int free = page->objects - page->inuse;
+ list_for_each_entry_safe(slab, t, &n->partial, slab_list) {
+ int free = slab->objects - slab->inuse;
- /* Do not reread page->inuse */
+ /* Do not reread slab->inuse */
barrier();
/* We do not keep full slabs on the list */
BUG_ON(free <= 0);
- if (free == page->objects) {
- list_move(&page->slab_list, &discard);
+ if (free == slab->objects) {
+ list_move(&slab->slab_list, &discard);
n->nr_partial--;
} else if (free <= SHRINK_PROMOTE_MAX)
- list_move(&page->slab_list, promote + free - 1);
+ list_move(&slab->slab_list, promote + free - 1);
}
/*
spin_unlock_irqrestore(&n->list_lock, flags);
/* Release empty slabs */
- list_for_each_entry_safe(page, t, &discard, slab_list)
- discard_slab(s, page);
+ list_for_each_entry_safe(slab, t, &discard, slab_list)
+ discard_slab(s, slab);
if (slabs_node(s, node))
ret = 1;
*/
__flush_cpu_slab(s, smp_processor_id());
for_each_kmem_cache_node(s, node, n) {
- struct page *p;
+ struct slab *p;
list_for_each_entry(p, &n->partial, slab_list)
p->slab_cache = s;
#endif
#ifdef CONFIG_SYSFS
-static int count_inuse(struct page *page)
+static int count_inuse(struct slab *slab)
{
- return page->inuse;
+ return slab->inuse;
}
-static int count_total(struct page *page)
+static int count_total(struct slab *slab)
{
- return page->objects;
+ return slab->objects;
}
#endif
#ifdef CONFIG_SLUB_DEBUG
-static void validate_slab(struct kmem_cache *s, struct page *page,
+static void validate_slab(struct kmem_cache *s, struct slab *slab,
unsigned long *obj_map)
{
void *p;
- void *addr = page_address(page);
+ void *addr = slab_address(slab);
unsigned long flags;
- slab_lock(page, &flags);
+ slab_lock(slab, &flags);
- if (!check_slab(s, page) || !on_freelist(s, page, NULL))
+ if (!check_slab(s, slab) || !on_freelist(s, slab, NULL))
goto unlock;
/* Now we know that a valid freelist exists */
- __fill_map(obj_map, s, page);
- for_each_object(p, s, addr, page->objects) {
+ __fill_map(obj_map, s, slab);
+ for_each_object(p, s, addr, slab->objects) {
u8 val = test_bit(__obj_to_index(s, addr, p), obj_map) ?
SLUB_RED_INACTIVE : SLUB_RED_ACTIVE;
- if (!check_object(s, page, p, val))
+ if (!check_object(s, slab, p, val))
break;
}
unlock:
- slab_unlock(page, &flags);
+ slab_unlock(slab, &flags);
}
static int validate_slab_node(struct kmem_cache *s,
struct kmem_cache_node *n, unsigned long *obj_map)
{
unsigned long count = 0;
- struct page *page;
+ struct slab *slab;
unsigned long flags;
spin_lock_irqsave(&n->list_lock, flags);
- list_for_each_entry(page, &n->partial, slab_list) {
- validate_slab(s, page, obj_map);
+ list_for_each_entry(slab, &n->partial, slab_list) {
+ validate_slab(s, slab, obj_map);
count++;
}
if (count != n->nr_partial) {
if (!(s->flags & SLAB_STORE_USER))
goto out;
- list_for_each_entry(page, &n->full, slab_list) {
- validate_slab(s, page, obj_map);
+ list_for_each_entry(slab, &n->full, slab_list) {
+ validate_slab(s, slab, obj_map);
count++;
}
if (count != atomic_long_read(&n->nr_slabs)) {
unsigned long max;
unsigned long count;
struct location *loc;
+ loff_t idx;
};
static struct dentry *slab_debugfs_root;
}
static void process_slab(struct loc_track *t, struct kmem_cache *s,
- struct page *page, enum track_item alloc,
+ struct slab *slab, enum track_item alloc,
unsigned long *obj_map)
{
- void *addr = page_address(page);
+ void *addr = slab_address(slab);
void *p;
- __fill_map(obj_map, s, page);
+ __fill_map(obj_map, s, slab);
- for_each_object(p, s, addr, page->objects)
+ for_each_object(p, s, addr, slab->objects)
if (!test_bit(__obj_to_index(s, addr, p), obj_map))
add_location(t, s, get_track(s, p, alloc));
}
struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab,
cpu);
int node;
- struct page *page;
+ struct slab *slab;
- page = READ_ONCE(c->page);
- if (!page)
+ slab = READ_ONCE(c->slab);
+ if (!slab)
continue;
- node = page_to_nid(page);
+ node = slab_nid(slab);
if (flags & SO_TOTAL)
- x = page->objects;
+ x = slab->objects;
else if (flags & SO_OBJECTS)
- x = page->inuse;
+ x = slab->inuse;
else
x = 1;
total += x;
nodes[node] += x;
- page = slub_percpu_partial_read_once(c);
- if (page) {
- node = page_to_nid(page);
+#ifdef CONFIG_SLUB_CPU_PARTIAL
+ slab = slub_percpu_partial_read_once(c);
+ if (slab) {
+ node = slab_nid(slab);
if (flags & SO_TOTAL)
WARN_ON_ONCE(1);
else if (flags & SO_OBJECTS)
WARN_ON_ONCE(1);
else
- x = page->pages;
+ x = slab->slabs;
total += x;
nodes[node] += x;
}
+#endif
}
}
static ssize_t slabs_cpu_partial_show(struct kmem_cache *s, char *buf)
{
int objects = 0;
- int pages = 0;
- int cpu;
+ int slabs = 0;
+ int cpu __maybe_unused;
int len = 0;
+#ifdef CONFIG_SLUB_CPU_PARTIAL
for_each_online_cpu(cpu) {
- struct page *page;
+ struct slab *slab;
- page = slub_percpu_partial(per_cpu_ptr(s->cpu_slab, cpu));
+ slab = slub_percpu_partial(per_cpu_ptr(s->cpu_slab, cpu));
- if (page)
- pages += page->pages;
+ if (slab)
+ slabs += slab->slabs;
}
+#endif
- /* Approximate half-full pages , see slub_set_cpu_partial() */
- objects = (pages * oo_objects(s->oo)) / 2;
- len += sysfs_emit_at(buf, len, "%d(%d)", objects, pages);
+ /* Approximate half-full slabs, see slub_set_cpu_partial() */
+ objects = (slabs * oo_objects(s->oo)) / 2;
+ len += sysfs_emit_at(buf, len, "%d(%d)", objects, slabs);
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SLUB_CPU_PARTIAL) && defined(CONFIG_SMP)
for_each_online_cpu(cpu) {
- struct page *page;
+ struct slab *slab;
- page = slub_percpu_partial(per_cpu_ptr(s->cpu_slab, cpu));
- if (page) {
- pages = READ_ONCE(page->pages);
- objects = (pages * oo_objects(s->oo)) / 2;
+ slab = slub_percpu_partial(per_cpu_ptr(s->cpu_slab, cpu));
+ if (slab) {
+ slabs = READ_ONCE(slab->slabs);
+ objects = (slabs * oo_objects(s->oo)) / 2;
len += sysfs_emit_at(buf, len, " C%d=%d(%d)",
- cpu, objects, pages);
+ cpu, objects, slabs);
}
}
#endif
#if defined(CONFIG_SLUB_DEBUG) && defined(CONFIG_DEBUG_FS)
static int slab_debugfs_show(struct seq_file *seq, void *v)
{
-
- struct location *l;
- unsigned int idx = *(unsigned int *)v;
struct loc_track *t = seq->private;
+ struct location *l;
+ unsigned long idx;
+ idx = (unsigned long) t->idx;
if (idx < t->count) {
l = &t->loc[idx];
{
struct loc_track *t = seq->private;
- v = ppos;
- ++*ppos;
+ t->idx = ++(*ppos);
if (*ppos <= t->count)
- return v;
+ return ppos;
return NULL;
}
static void *slab_debugfs_start(struct seq_file *seq, loff_t *ppos)
{
+ struct loc_track *t = seq->private;
+
+ t->idx = *ppos;
return ppos;
}
for_each_kmem_cache_node(s, node, n) {
unsigned long flags;
- struct page *page;
+ struct slab *slab;
if (!atomic_long_read(&n->nr_slabs))
continue;
spin_lock_irqsave(&n->list_lock, flags);
- list_for_each_entry(page, &n->partial, slab_list)
- process_slab(t, s, page, alloc, obj_map);
- list_for_each_entry(page, &n->full, slab_list)
- process_slab(t, s, page, alloc, obj_map);
+ list_for_each_entry(slab, &n->partial, slab_list)
+ process_slab(t, s, slab, alloc, obj_map);
+ list_for_each_entry(slab, &n->full, slab_list)
+ process_slab(t, s, slab, alloc, obj_map);
spin_unlock_irqrestore(&n->list_lock, flags);
}
>> PAGE_SHIFT;
for (i = 0; i < nr_pages; i++, page++) {
- magic = (unsigned long) page->freelist;
+ magic = page->index;
BUG_ON(magic == NODE_INFO);
#include <linux/swap_slots.h>
#include <linux/cpu.h>
#include <linux/cpumask.h>
+#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/mutex.h>
#include <linux/mm.h>
#include <linux/atomic.h>
#include <linux/jump_label.h>
#include <asm/sections.h>
+#include "slab.h"
/*
* Checks if a given pointer and length is contained by the current
static inline void check_heap_object(const void *ptr, unsigned long n,
bool to_user)
{
- struct page *page;
+ struct folio *folio;
if (!virt_addr_valid(ptr))
return;
/*
* When CONFIG_HIGHMEM=y, kmap_to_page() will give either the
* highmem page or fallback to virt_to_page(). The following
- * is effectively a highmem-aware virt_to_head_page().
+ * is effectively a highmem-aware virt_to_slab().
*/
- page = compound_head(kmap_to_page((void *)ptr));
+ folio = page_folio(kmap_to_page((void *)ptr));
- if (PageSlab(page)) {
+ if (folio_test_slab(folio)) {
/* Check slab allocator for flags and size. */
- __check_heap_object(ptr, n, page, to_user);
+ __check_heap_object(ptr, n, folio_slab(folio), to_user);
} else {
/* Verify object does not incorrectly span multiple pages. */
- check_page_span(ptr, n, page, to_user);
+ check_page_span(ptr, n, folio_page(folio, 0), to_user);
}
}
*
* Usage of struct page fields:
* page->private: points to zspage
- * page->freelist(index): links together all component pages of a zspage
+ * page->index: links together all component pages of a zspage
* For the huge page, this is always 0, so we use this field
* to store handle.
- * page->units: first object offset in a subpage of zspage
+ * page->page_type: first object offset in a subpage of zspage
*
* Usage of struct page flags:
* PG_private: identifies the first component page
static inline int get_first_obj_offset(struct page *page)
{
- return page->units;
+ return page->page_type;
}
static inline void set_first_obj_offset(struct page *page, int offset)
{
- page->units = offset;
+ page->page_type = offset;
}
static inline unsigned int get_freeobj(struct zspage *zspage)
if (unlikely(PageHugeObject(page)))
return NULL;
- return page->freelist;
+ return (struct page *)page->index;
}
/**
set_page_private(page, 0);
page_mapcount_reset(page);
ClearPageHugeObject(page);
- page->freelist = NULL;
+ page->index = 0;
}
static int trylock_zspage(struct zspage *zspage)
/*
* Allocate individual pages and link them together as:
- * 1. all pages are linked together using page->freelist
+ * 1. all pages are linked together using page->index
* 2. each sub-page point to zspage using page->private
*
* we set PG_private to identify the first page (i.e. no other sub-page
for (i = 0; i < nr_pages; i++) {
page = pages[i];
set_page_private(page, (unsigned long)zspage);
- page->freelist = NULL;
+ page->index = 0;
if (i == 0) {
zspage->first_page = page;
SetPagePrivate(page);
class->pages_per_zspage == 1))
SetPageHugeObject(page);
} else {
- prev_page->freelist = page;
+ prev_page->index = (unsigned long)page;
}
prev_page = page;
}
return err;
}
- if (info->attrs[DEVLINK_ATTR_NETNS_PID] ||
- info->attrs[DEVLINK_ATTR_NETNS_FD] ||
- info->attrs[DEVLINK_ATTR_NETNS_ID]) {
- dest_net = devlink_netns_get(skb, info);
- if (IS_ERR(dest_net))
- return PTR_ERR(dest_net);
- }
-
if (info->attrs[DEVLINK_ATTR_RELOAD_ACTION])
action = nla_get_u8(info->attrs[DEVLINK_ATTR_RELOAD_ACTION]);
else
return -EINVAL;
}
}
+ if (info->attrs[DEVLINK_ATTR_NETNS_PID] ||
+ info->attrs[DEVLINK_ATTR_NETNS_FD] ||
+ info->attrs[DEVLINK_ATTR_NETNS_ID]) {
+ dest_net = devlink_netns_get(skb, info);
+ if (IS_ERR(dest_net))
+ return PTR_ERR(dest_net);
+ }
+
err = devlink_reload(devlink, dest_net, action, limit, &actions_performed, info->extack);
if (dest_net)
ASSERT_RTNL();
- n = kmalloc(sizeof(*n) + key_len, GFP_KERNEL);
+ n = kzalloc(sizeof(*n) + key_len, GFP_KERNEL);
if (!n)
goto out;
- n->protocol = 0;
write_pnet(&n->net, net);
memcpy(n->key, pkey, key_len);
n->dev = dev;
ntohs(skb->protocol), skb->pkt_type, skb->skb_iif);
if (dev)
- printk("%sdev name=%s feat=0x%pNF\n",
+ printk("%sdev name=%s feat=%pNF\n",
level, dev->name, &dev->features);
if (sk)
printk("%ssk family=%hu type=%u proto=%u\n",
void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock)
{
+ psock_set_prog(&psock->progs.stream_parser, NULL);
+
if (!psock->saved_data_ready)
return;
void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock)
{
+ psock_set_prog(&psock->progs.stream_verdict, NULL);
+ psock_set_prog(&psock->progs.skb_verdict, NULL);
+
if (!psock->saved_data_ready)
return;
write_lock_bh(&sk->sk_callback_lock);
if (strp_stop)
sk_psock_stop_strp(sk, psock);
- else
+ if (verdict_stop)
sk_psock_stop_verdict(sk, psock);
+
+ if (psock->psock_update_sk_prot)
+ psock->psock_update_sk_prot(sk, psock, false);
write_unlock_bh(&sk->sk_callback_lock);
}
}
if (msg_parser)
psock_set_prog(&psock->progs.msg_parser, msg_parser);
+ if (stream_parser)
+ psock_set_prog(&psock->progs.stream_parser, stream_parser);
+ if (stream_verdict)
+ psock_set_prog(&psock->progs.stream_verdict, stream_verdict);
+ if (skb_verdict)
+ psock_set_prog(&psock->progs.skb_verdict, skb_verdict);
ret = sock_map_init_proto(sk, psock);
if (ret < 0)
ret = sk_psock_init_strp(sk, psock);
if (ret)
goto out_unlock_drop;
- psock_set_prog(&psock->progs.stream_verdict, stream_verdict);
- psock_set_prog(&psock->progs.stream_parser, stream_parser);
sk_psock_start_strp(sk, psock);
} else if (!stream_parser && stream_verdict && !psock->saved_data_ready) {
- psock_set_prog(&psock->progs.stream_verdict, stream_verdict);
sk_psock_start_verdict(sk,psock);
} else if (!stream_verdict && skb_verdict && !psock->saved_data_ready) {
- psock_set_prog(&psock->progs.skb_verdict, skb_verdict);
sk_psock_start_verdict(sk, psock);
}
write_unlock_bh(&sk->sk_callback_lock);
if (dev->dev.parent)
pm_runtime_get_sync(dev->dev.parent);
- if (!netif_device_present(dev)) {
+ if (!netif_device_present(dev) ||
+ dev->reg_state == NETREG_UNREGISTERING) {
ret = -ENODEV;
goto err;
}
sk_node_init(&nreq_sk->sk_node);
nreq_sk->sk_tx_queue_mapping = req_sk->sk_tx_queue_mapping;
-#ifdef CONFIG_XPS
+#ifdef CONFIG_SOCK_RX_QUEUE_MAPPING
nreq_sk->sk_rx_queue_mapping = req_sk->sk_rx_queue_mapping;
#endif
nreq_sk->sk_incoming_cpu = req_sk->sk_incoming_cpu;
r->idiag_state = sk->sk_state;
r->idiag_timer = 0;
r->idiag_retrans = 0;
+ r->idiag_expires = 0;
if (inet_diag_msg_attrs_fill(sk, skb, r, ext,
sk_user_ns(NETLINK_CB(cb->skb).sk),
r->idiag_retrans = icsk->icsk_probes_out;
r->idiag_expires =
jiffies_delta_to_msecs(sk->sk_timer.expires - jiffies);
- } else {
- r->idiag_timer = 0;
- r->idiag_expires = 0;
}
if ((ext & (1 << (INET_DIAG_INFO - 1))) && handler->idiag_info_size) {
int ret = 0;
int state = child->sk_state;
- /* record NAPI ID of child */
- sk_mark_napi_id(child, skb);
+ /* record sk_napi_id and sk_rx_queue_mapping of child. */
+ sk_mark_napi_id_set(child, skb);
tcp_segs_in(tcp_sk(child), skb);
if (!sock_owned_by_user(child)) {
kfree_skb(skb);
return -EINVAL;
}
- if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) {
+ if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) {
kfree_skb(skb);
return -EINVAL;
}
hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb));
memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+
+ /* the control block has been erased, so we have to set the
+ * iif once again.
+ * We read the receiving interface index directly from the
+ * skb->skb_iif as it is done in the IPv4 receiving path (i.e.:
+ * ip_rcv_core(...)).
+ */
+ IP6CB(skb)->iif = skb->skb_iif;
}
hdr->nexthdr = NEXTHDR_ROUTING;
return 0;
err_reg_dev:
- ipip6_dev_free(sitn->fb_tunnel_dev);
free_netdev(sitn->fb_tunnel_dev);
err_alloc_dev:
return err;
* Copyright 2007, Michael Wu <flamingice@sourmilk.net>
* Copyright 2007-2010, Intel Corporation
* Copyright(c) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2020 Intel Corporation
+ * Copyright (C) 2018-2021 Intel Corporation
*/
/**
sband = ieee80211_get_sband(sdata);
if (!sband)
return;
- he_cap = ieee80211_get_he_iftype_cap(sband, sdata->vif.type);
+ he_cap = ieee80211_get_he_iftype_cap(sband,
+ ieee80211_vif_type_p2p(&sdata->vif));
if (!he_cap)
return;
* Copyright 2007, Michael Wu <flamingice@sourmilk.net>
* Copyright 2007-2010, Intel Corporation
* Copyright(c) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018 - 2020 Intel Corporation
+ * Copyright (C) 2018 - 2021 Intel Corporation
*/
#include <linux/ieee80211.h>
mgmt->u.action.u.addba_req.start_seq_num =
cpu_to_le16(start_seq_num << 4);
- ieee80211_tx_skb(sdata, skb);
+ ieee80211_tx_skb_tid(sdata, skb, tid);
}
void ieee80211_send_bar(struct ieee80211_vif *vif, u8 *ra, u16 tid, u16 ssn)
struct ieee80211_txq *txq = sta->sta.txq[tid];
struct txq_info *txqi;
+ lockdep_assert_held(&sta->ampdu_mlme.mtx);
+
if (!txq)
return;
ieee80211_assign_tid_tx(sta, tid, NULL);
ieee80211_agg_splice_finish(sta->sdata, tid);
- ieee80211_agg_start_txq(sta, tid, false);
kfree_rcu(tid_tx, rcu_head);
}
/* send AddBA request */
ieee80211_send_addba_request(sdata, sta->sta.addr, tid,
- tid_tx->dialog_token,
- sta->tid_seq[tid] >> 4,
+ tid_tx->dialog_token, tid_tx->ssn,
buf_size, tid_tx->timeout);
WARN_ON(test_and_set_bit(HT_AGG_STATE_SENT_ADDBA, &tid_tx->state));
params.ssn = sta->tid_seq[tid] >> 4;
ret = drv_ampdu_action(local, sdata, ¶ms);
+ tid_tx->ssn = params.ssn;
if (ret == IEEE80211_AMPDU_TX_START_DELAY_ADDBA) {
return;
} else if (ret == IEEE80211_AMPDU_TX_START_IMMEDIATE) {
{
struct ieee80211_sub_if_data *sdata = sta->sdata;
bool send_delba = false;
+ bool start_txq = false;
ht_dbg(sdata, "Stopping Tx BA session for %pM tid %d\n",
sta->sta.addr, tid);
send_delba = true;
ieee80211_remove_tid_tx(sta, tid);
+ start_txq = true;
unlock_sta:
spin_unlock_bh(&sta->lock);
+ if (start_txq)
+ ieee80211_agg_start_txq(sta, tid, false);
+
if (send_delba)
ieee80211_send_delba(sdata, sta->sta.addr, tid,
WLAN_BACK_INITIATOR, WLAN_REASON_QSTA_NOT_USE);
{
struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->txq.vif);
- if (local->in_reconfig)
+ /* In reconfig don't transmit now, but mark for waking later */
+ if (local->in_reconfig) {
+ set_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txq->flags);
return;
+ }
if (!check_sdata_in_driver(sdata))
return;
u16 tx_time)
{
struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
- u16 tid = ieee80211_get_tid(hdr);
- int ac = ieee80211_ac_from_tid(tid);
- struct ieee80211_sta_tx_tspec *tx_tspec = &ifmgd->tx_tspec[ac];
+ u16 tid;
+ int ac;
+ struct ieee80211_sta_tx_tspec *tx_tspec;
unsigned long now = jiffies;
+ if (!ieee80211_is_data_qos(hdr->frame_control))
+ return;
+
+ tid = ieee80211_get_tid(hdr);
+ ac = ieee80211_ac_from_tid(tid);
+ tx_tspec = &ifmgd->tx_tspec[ac];
+
if (likely(!tx_tspec->admitted_time))
return;
if (!fwd_skb)
goto out;
+ fwd_skb->dev = sdata->dev;
fwd_hdr = (struct ieee80211_hdr *) fwd_skb->data;
fwd_hdr->frame_control &= ~cpu_to_le16(IEEE80211_FCTL_RETRY);
info = IEEE80211_SKB_CB(fwd_skb);
/* check if STA exists already */
if (sta_info_get_bss(sdata, sta->sta.addr)) {
err = -EEXIST;
- goto out_err;
+ goto out_cleanup;
}
sinfo = kzalloc(sizeof(struct station_info), GFP_KERNEL);
if (!sinfo) {
err = -ENOMEM;
- goto out_err;
+ goto out_cleanup;
}
local->num_sta++;
list_add_tail_rcu(&sta->list, &local->sta_list);
+ /* update channel context before notifying the driver about state
+ * change, this enables driver using the updated channel context right away.
+ */
+ if (sta->sta_state >= IEEE80211_STA_ASSOC) {
+ ieee80211_recalc_min_chandef(sta->sdata);
+ if (!sta->sta.support_p2p_ps)
+ ieee80211_recalc_p2p_go_ps_allowed(sta->sdata);
+ }
+
/* notify driver */
err = sta_info_insert_drv_state(local, sdata, sta);
if (err)
set_sta_flag(sta, WLAN_STA_INSERTED);
- if (sta->sta_state >= IEEE80211_STA_ASSOC) {
- ieee80211_recalc_min_chandef(sta->sdata);
- if (!sta->sta.support_p2p_ps)
- ieee80211_recalc_p2p_go_ps_allowed(sta->sdata);
- }
-
/* accept BA sessions now */
clear_sta_flag(sta, WLAN_STA_BLOCK_BA);
out_drop_sta:
local->num_sta--;
synchronize_net();
+ out_cleanup:
cleanup_single_sta(sta);
- out_err:
mutex_unlock(&local->sta_mtx);
kfree(sinfo);
rcu_read_lock();
* @failed_bar_ssn: ssn of the last failed BAR tx attempt
* @bar_pending: BAR needs to be re-sent
* @amsdu: support A-MSDU withing A-MDPU
+ * @ssn: starting sequence number of the session
*
* This structure's lifetime is managed by RCU, assignments to
* the array holding it must hold the aggregation mutex.
u8 stop_initiator;
bool tx_stop;
u16 buf_size;
+ u16 ssn;
u16 failed_bar_ssn;
bool bar_pending;
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);
ieee80211_tx_result res = TX_CONTINUE;
+ if (!ieee80211_hw_check(&tx->local->hw, HAS_RATE_CONTROL))
+ CALL_TXH(ieee80211_tx_h_rate_ctrl);
+
if (unlikely(info->flags & IEEE80211_TX_INTFL_RETRANSMISSION)) {
__skb_queue_tail(&tx->skbs, tx->skb);
tx->skb = NULL;
goto txh_done;
}
- if (!ieee80211_hw_check(&tx->local->hw, HAS_RATE_CONTROL))
- CALL_TXH(ieee80211_tx_h_rate_ctrl);
-
CALL_TXH(ieee80211_tx_h_michael_mic_add);
CALL_TXH(ieee80211_tx_h_sequence);
CALL_TXH(ieee80211_tx_h_fragment);
ieee80211_aggr_check(sdata, sta, skb);
+ sk_pacing_shift_update(skb->sk, sdata->local->hw.tx_sk_pacing_shift);
+
if (sta) {
struct ieee80211_fast_tx *fast_tx;
- sk_pacing_shift_update(skb->sk, sdata->local->hw.tx_sk_pacing_shift);
-
fast_tx = rcu_dereference(sta->fast_tx);
if (fast_tx &&
struct ieee802_11_elems *elems)
{
const void *data = elem->data + 1;
- u8 len = elem->datalen - 1;
+ u8 len;
+
+ if (!elem->datalen)
+ return;
+
+ len = elem->datalen - 1;
switch (elem->data[0]) {
case WLAN_EID_EXT_HE_MU_EDCA:
chandef.chan = chan;
skb = ieee80211_probereq_get(&local->hw, src, ssid, ssid_len,
- 100 + ie_len);
+ local->scan_ies_len + ie_len);
if (!skb)
return NULL;
mutex_unlock(&local->sta_mtx);
}
+ /*
+ * If this is for hw restart things are still running.
+ * We may want to change that later, however.
+ */
+ if (local->open_count && (!suspended || reconfig_due_to_wowlan))
+ drv_reconfig_complete(local, IEEE80211_RECONFIG_TYPE_RESTART);
+
if (local->in_reconfig) {
local->in_reconfig = false;
barrier();
IEEE80211_QUEUE_STOP_REASON_SUSPEND,
false);
- /*
- * If this is for hw restart things are still running.
- * We may want to change that later, however.
- */
- if (local->open_count && (!suspended || reconfig_due_to_wowlan))
- drv_reconfig_complete(local, IEEE80211_RECONFIG_TYPE_RESTART);
-
if (!suspended)
return 0;
msk_owned_by_me(msk);
+ if (sk->sk_state == TCP_LISTEN)
+ return;
+
if (!rm_list->nr)
return;
int ret = 0;
prev_ssk = ssk;
- mptcp_flush_join_list(msk);
+ __mptcp_flush_join_list(msk);
ssk = mptcp_subflow_get_send(msk);
/* First check. If the ssk has changed since
*/
if (WARN_ON_ONCE(!new_mptcp_sock)) {
tcp_sk(newsk)->is_mptcp = 0;
- return newsk;
+ goto out;
}
/* acquire the 2nd reference for the owning socket */
MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
}
+out:
+ newsk->sk_kern_sock = kern;
return newsk;
}
case TCP_NODELAY:
case TCP_THIN_LINEAR_TIMEOUTS:
case TCP_CONGESTION:
- case TCP_ULP:
case TCP_CORK:
case TCP_KEEPIDLE:
case TCP_KEEPINTVL:
tstamp = nf_conn_tstamp_find(ct);
if (tstamp) {
- s32 timeout = ct->timeout - nfct_time_stamp;
+ s32 timeout = READ_ONCE(ct->timeout) - nfct_time_stamp;
tstamp->stop = ktime_get_real_ns();
if (timeout < 0)
}
/* We want the clashing entry to go away real soon: 1 second timeout. */
- loser_ct->timeout = nfct_time_stamp + HZ;
+ WRITE_ONCE(loser_ct->timeout, nfct_time_stamp + HZ);
/* IPS_NAT_CLASH removes the entry automatically on the first
* reply. Also prevents UDP tracker from moving the entry to
/* save hash for reusing when confirming */
*(unsigned long *)(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev) = hash;
ct->status = 0;
- ct->timeout = 0;
+ WRITE_ONCE(ct->timeout, 0);
write_pnet(&ct->ct_net, net);
memset(&ct->__nfct_init_offset, 0,
offsetof(struct nf_conn, proto) -
if (timeout > INT_MAX)
timeout = INT_MAX;
- ct->timeout = nfct_time_stamp + (u32)timeout;
+ WRITE_ONCE(ct->timeout, nfct_time_stamp + (u32)timeout);
if (test_bit(IPS_DYING_BIT, &ct->status))
return -ETIME;
if (timeout < 0)
timeout = 0;
- if (nf_flow_timeout_delta(ct->timeout) > (__s32)timeout)
- ct->timeout = nfct_time_stamp + timeout;
+ if (nf_flow_timeout_delta(READ_ONCE(ct->timeout)) > (__s32)timeout)
+ WRITE_ONCE(ct->timeout, nfct_time_stamp + timeout);
}
static void flow_offload_fixup_ct_state(struct nf_conn *ct)
struct net_device *indev;
struct net_device *outdev;
struct nf_conn *ct = NULL;
- enum ip_conntrack_info ctinfo;
+ enum ip_conntrack_info ctinfo = 0;
struct nfnl_ct_hook *nfnl_ct;
bool csum_verify;
char *secdata = NULL;
tcph = nft_tcp_header_pointer(pkt, sizeof(buff), buff, &tcphdr_len);
if (!tcph)
- return;
+ goto err;
opt = (u8 *)tcph;
for (i = sizeof(*tcph); i < tcphdr_len - 1; i += optl) {
continue;
if (i + optl > tcphdr_len || priv->len + priv->offset > optl)
- return;
+ goto err;
if (skb_ensure_writable(pkt->skb,
nft_thoff(pkt) + i + priv->len))
- return;
+ goto err;
tcph = nft_tcp_header_pointer(pkt, sizeof(buff), buff,
&tcphdr_len);
if (!tcph)
- return;
+ goto err;
offset = i + priv->offset;
return;
}
+ return;
+err:
+ regs->verdict.code = NFT_BREAK;
}
static void nft_exthdr_sctp_eval(const struct nft_expr *expr,
NFT_PIPAPO_AVX2_BUCKET_LOAD8(4, lt, 4, pkt[4], bsize);
NFT_PIPAPO_AVX2_AND(5, 0, 1);
- NFT_PIPAPO_AVX2_BUCKET_LOAD8(6, lt, 6, pkt[5], bsize);
+ NFT_PIPAPO_AVX2_BUCKET_LOAD8(6, lt, 5, pkt[5], bsize);
NFT_PIPAPO_AVX2_AND(7, 2, 3);
/* Stall */
{
struct class_dev_iter *iter = (struct class_dev_iter *) cb->args[0];
- nfc_device_iter_exit(iter);
- kfree(iter);
+ if (iter) {
+ nfc_device_iter_exit(iter);
+ kfree(iter);
+ }
return 0;
}
{
struct class_dev_iter *iter = (struct class_dev_iter *) cb->args[0];
- nfc_device_iter_exit(iter);
- kfree(iter);
+ if (iter) {
+ nfc_device_iter_exit(iter);
+ kfree(iter);
+ }
return 0;
}
}
out_free_pg_vec:
- bitmap_free(rx_owner_map);
- if (pg_vec)
+ if (pg_vec) {
+ bitmap_free(rx_owner_map);
free_pg_vec(pg_vec, order, req->tp_block_nr);
+ }
out:
return err;
}
err = pep_accept_conn(newsk, skb);
if (err) {
+ __sock_put(sk);
sock_put(newsk);
newsk = NULL;
goto drop;
* should end up here, but if it
* does, reset/destroy the connection.
*/
+ kfree(conn->c_path);
kmem_cache_free(rds_conn_slab, conn);
conn = ERR_PTR(-EOPNOTSUPP);
goto out;
entry->mpls_mangle.ttl = tcf_mpls_ttl(act);
break;
default:
+ err = -EOPNOTSUPP;
goto err_out_locked;
}
} else if (is_tcf_skbedit_ptype(act)) {
q->tins = kvcalloc(CAKE_MAX_TINS, sizeof(struct cake_tin_data),
GFP_KERNEL);
if (!q->tins)
- goto nomem;
+ return -ENOMEM;
for (i = 0; i < CAKE_MAX_TINS; i++) {
struct cake_tin_data *b = q->tins + i;
q->min_netlen = ~0;
q->min_adjlen = ~0;
return 0;
-
-nomem:
- cake_destroy(sch);
- return -ENOMEM;
}
static int cake_dump(struct Qdisc *sch, struct sk_buff *skb)
}
}
for (i = q->nbands; i < oldbands; i++) {
- qdisc_tree_flush_backlog(q->classes[i].qdisc);
- if (i >= q->nstrict)
+ if (i >= q->nstrict && q->classes[i].qdisc->q.qlen)
list_del(&q->classes[i].alist);
+ qdisc_tree_flush_backlog(q->classes[i].qdisc);
}
q->nstrict = nstrict;
memcpy(q->prio2band, priomap, sizeof(priomap));
struct fq_pie_sched_data *q = qdisc_priv(sch);
tcf_block_put(q->block);
+ q->p_params.tupdate = 0;
del_timer_sync(&q->adapt_timer);
kvfree(q->flows);
}
/* cleanup for a dangling non-blocking connect */
if (smc->connect_nonblock && sk->sk_state == SMC_INIT)
tcp_abort(smc->clcsock->sk, ECONNABORTED);
- flush_work(&smc->connect_work);
+
+ if (cancel_work_sync(&smc->connect_work))
+ sock_put(&smc->sk); /* sock_hold in smc_connect for passive closing */
if (sk->sk_state == SMC_LISTEN)
/* smc_close_non_accepted() is called and acquires
space_available = virtio_transport_space_update(sk, pkt);
/* Update CID in case it has changed after a transport reset event */
- vsk->local_addr.svm_cid = dst.svm_cid;
+ if (vsk->local_addr.svm_cid != VMADDR_CID_ANY)
+ vsk->local_addr.svm_cid = dst.svm_cid;
if (space_available)
sk->sk_write_space(sk);
static void restore_regulatory_settings(bool reset_user, bool cached);
static void print_regdomain(const struct ieee80211_regdomain *rd);
+static void reg_process_hint(struct regulatory_request *reg_request);
static const struct ieee80211_regdomain *get_cfg80211_regdom(void)
{
const struct firmware *fw;
void *db;
int err;
+ const struct ieee80211_regdomain *current_regdomain;
+ struct regulatory_request *request;
err = request_firmware(&fw, "regulatory.db", ®_pdev->dev);
if (err)
if (!IS_ERR_OR_NULL(regdb))
kfree(regdb);
regdb = db;
- rtnl_unlock();
+ /* reset regulatory domain */
+ current_regdomain = get_cfg80211_regdom();
+
+ request = kzalloc(sizeof(*request), GFP_KERNEL);
+ if (!request) {
+ err = -ENOMEM;
+ goto out_unlock;
+ }
+
+ request->wiphy_idx = WIPHY_IDX_INVALID;
+ request->alpha2[0] = current_regdomain->alpha2[0];
+ request->alpha2[1] = current_regdomain->alpha2[1];
+ request->initiator = NL80211_REGDOM_SET_BY_CORE;
+ request->user_reg_hint_type = NL80211_USER_REG_HINT_USER;
+
+ reg_process_hint(request);
+
+out_unlock:
+ rtnl_unlock();
out:
release_firmware(fw);
return err;
struct cfg80211_chan_def chandef = {};
struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
enum nl80211_iftype iftype;
+ bool ret;
wdev_lock(wdev);
iftype = wdev->iftype;
case NL80211_IFTYPE_AP:
case NL80211_IFTYPE_P2P_GO:
case NL80211_IFTYPE_ADHOC:
- return cfg80211_reg_can_beacon_relax(wiphy, &chandef, iftype);
+ wiphy_lock(wiphy);
+ ret = cfg80211_reg_can_beacon_relax(wiphy, &chandef, iftype);
+ wiphy_unlock(wiphy);
+
+ return ret;
case NL80211_IFTYPE_STATION:
case NL80211_IFTYPE_P2P_CLIENT:
return cfg80211_chandef_usable(wiphy, &chandef,
struct xdp_sock *xs = xdp_sk(sk);
struct xsk_buff_pool *pool;
- sock_poll_wait(file, sock, wait);
-
if (unlikely(!xsk_is_bound(xs)))
return mask;
else
/* Poll needs to drive Tx also in copy mode */
__xsk_sendmsg(sk);
+ } else {
+ sock_poll_wait(file, sock, wait);
}
if (xs->rx && !xskq_prod_is_empty(xs->rx))
obj-$(CONFIG_SAMPLE_FTRACE_DIRECT) += ftrace-direct-too.o
obj-$(CONFIG_SAMPLE_FTRACE_DIRECT) += ftrace-direct-modify.o
obj-$(CONFIG_SAMPLE_FTRACE_DIRECT_MULTI) += ftrace-direct-multi.o
+obj-$(CONFIG_SAMPLE_FTRACE_DIRECT_MULTI) += ftrace-direct-multi-modify.o
CFLAGS_sample-trace-array.o := -I$(src)
obj-$(CONFIG_SAMPLE_TRACE_ARRAY) += sample-trace-array.o
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/ftrace.h>
+#include <asm/asm-offsets.h>
+
+void my_direct_func1(unsigned long ip)
+{
+ trace_printk("my direct func1 ip %lx\n", ip);
+}
+
+void my_direct_func2(unsigned long ip)
+{
+ trace_printk("my direct func2 ip %lx\n", ip);
+}
+
+extern void my_tramp1(void *);
+extern void my_tramp2(void *);
+
+#ifdef CONFIG_X86_64
+
+asm (
+" .pushsection .text, \"ax\", @progbits\n"
+" .type my_tramp1, @function\n"
+" .globl my_tramp1\n"
+" my_tramp1:"
+" pushq %rbp\n"
+" movq %rsp, %rbp\n"
+" pushq %rdi\n"
+" movq 8(%rbp), %rdi\n"
+" call my_direct_func1\n"
+" popq %rdi\n"
+" leave\n"
+" ret\n"
+" .size my_tramp1, .-my_tramp1\n"
+" .type my_tramp2, @function\n"
+"\n"
+" .globl my_tramp2\n"
+" my_tramp2:"
+" pushq %rbp\n"
+" movq %rsp, %rbp\n"
+" pushq %rdi\n"
+" movq 8(%rbp), %rdi\n"
+" call my_direct_func2\n"
+" popq %rdi\n"
+" leave\n"
+" ret\n"
+" .size my_tramp2, .-my_tramp2\n"
+" .popsection\n"
+);
+
+#endif /* CONFIG_X86_64 */
+
+#ifdef CONFIG_S390
+
+asm (
+" .pushsection .text, \"ax\", @progbits\n"
+" .type my_tramp1, @function\n"
+" .globl my_tramp1\n"
+" my_tramp1:"
+" lgr %r1,%r15\n"
+" stmg %r0,%r5,"__stringify(__SF_GPRS)"(%r15)\n"
+" stg %r14,"__stringify(__SF_GPRS+8*8)"(%r15)\n"
+" aghi %r15,"__stringify(-STACK_FRAME_OVERHEAD)"\n"
+" stg %r1,"__stringify(__SF_BACKCHAIN)"(%r15)\n"
+" lgr %r2,%r0\n"
+" brasl %r14,my_direct_func1\n"
+" aghi %r15,"__stringify(STACK_FRAME_OVERHEAD)"\n"
+" lmg %r0,%r5,"__stringify(__SF_GPRS)"(%r15)\n"
+" lg %r14,"__stringify(__SF_GPRS+8*8)"(%r15)\n"
+" lgr %r1,%r0\n"
+" br %r1\n"
+" .size my_tramp1, .-my_tramp1\n"
+"\n"
+" .type my_tramp2, @function\n"
+" .globl my_tramp2\n"
+" my_tramp2:"
+" lgr %r1,%r15\n"
+" stmg %r0,%r5,"__stringify(__SF_GPRS)"(%r15)\n"
+" stg %r14,"__stringify(__SF_GPRS+8*8)"(%r15)\n"
+" aghi %r15,"__stringify(-STACK_FRAME_OVERHEAD)"\n"
+" stg %r1,"__stringify(__SF_BACKCHAIN)"(%r15)\n"
+" lgr %r2,%r0\n"
+" brasl %r14,my_direct_func2\n"
+" aghi %r15,"__stringify(STACK_FRAME_OVERHEAD)"\n"
+" lmg %r0,%r5,"__stringify(__SF_GPRS)"(%r15)\n"
+" lg %r14,"__stringify(__SF_GPRS+8*8)"(%r15)\n"
+" lgr %r1,%r0\n"
+" br %r1\n"
+" .size my_tramp2, .-my_tramp2\n"
+" .popsection\n"
+);
+
+#endif /* CONFIG_S390 */
+
+static unsigned long my_tramp = (unsigned long)my_tramp1;
+static unsigned long tramps[2] = {
+ (unsigned long)my_tramp1,
+ (unsigned long)my_tramp2,
+};
+
+static struct ftrace_ops direct;
+
+static int simple_thread(void *arg)
+{
+ static int t;
+ int ret = 0;
+
+ while (!kthread_should_stop()) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ schedule_timeout(2 * HZ);
+
+ if (ret)
+ continue;
+ t ^= 1;
+ ret = modify_ftrace_direct_multi(&direct, tramps[t]);
+ if (!ret)
+ my_tramp = tramps[t];
+ WARN_ON_ONCE(ret);
+ }
+
+ return 0;
+}
+
+static struct task_struct *simple_tsk;
+
+static int __init ftrace_direct_multi_init(void)
+{
+ int ret;
+
+ ftrace_set_filter_ip(&direct, (unsigned long) wake_up_process, 0, 0);
+ ftrace_set_filter_ip(&direct, (unsigned long) schedule, 0, 0);
+
+ ret = register_ftrace_direct_multi(&direct, my_tramp);
+
+ if (!ret)
+ simple_tsk = kthread_run(simple_thread, NULL, "event-sample-fn");
+ return ret;
+}
+
+static void __exit ftrace_direct_multi_exit(void)
+{
+ kthread_stop(simple_tsk);
+ unregister_ftrace_direct_multi(&direct, my_tramp);
+}
+
+module_init(ftrace_direct_multi_init);
+module_exit(ftrace_direct_multi_exit);
+
+MODULE_AUTHOR("Jiri Olsa");
+MODULE_DESCRIPTION("Example use case of using modify_ftrace_direct_multi()");
+MODULE_LICENSE("GPL");
} elsif ($arch eq "s390" && $bits == 64) {
if ($cc =~ /-DCC_USING_HOTPATCH/) {
- $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*c0 04 00 00 00 00\\s*brcl\\s*0,[0-9a-f]+ <([^\+]*)>\$";
+ $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*c0 04 00 00 00 00\\s*(bcrl\\s*0,|jgnop\\s*)[0-9a-f]+ <([^\+]*)>\$";
$mcount_adjust = 0;
}
$alignment = 8;
return 0;
}
-static int parse_sid(struct super_block *sb, const char *s, u32 *sid)
+static int parse_sid(struct super_block *sb, const char *s, u32 *sid,
+ gfp_t gfp)
{
int rc = security_context_str_to_sid(&selinux_state, s,
- sid, GFP_KERNEL);
+ sid, gfp);
if (rc)
pr_warn("SELinux: security_context_str_to_sid"
"(%s) failed for (dev %s, type %s) errno=%d\n",
*/
if (opts) {
if (opts->fscontext) {
- rc = parse_sid(sb, opts->fscontext, &fscontext_sid);
+ rc = parse_sid(sb, opts->fscontext, &fscontext_sid,
+ GFP_KERNEL);
if (rc)
goto out;
if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid,
sbsec->flags |= FSCONTEXT_MNT;
}
if (opts->context) {
- rc = parse_sid(sb, opts->context, &context_sid);
+ rc = parse_sid(sb, opts->context, &context_sid,
+ GFP_KERNEL);
if (rc)
goto out;
if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid,
sbsec->flags |= CONTEXT_MNT;
}
if (opts->rootcontext) {
- rc = parse_sid(sb, opts->rootcontext, &rootcontext_sid);
+ rc = parse_sid(sb, opts->rootcontext, &rootcontext_sid,
+ GFP_KERNEL);
if (rc)
goto out;
if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid,
sbsec->flags |= ROOTCONTEXT_MNT;
}
if (opts->defcontext) {
- rc = parse_sid(sb, opts->defcontext, &defcontext_sid);
+ rc = parse_sid(sb, opts->defcontext, &defcontext_sid,
+ GFP_KERNEL);
if (rc)
goto out;
if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid,
return (sbsec->flags & SE_MNTMASK) ? 1 : 0;
if (opts->fscontext) {
- rc = parse_sid(sb, opts->fscontext, &sid);
+ rc = parse_sid(sb, opts->fscontext, &sid, GFP_NOWAIT);
if (rc)
return 1;
if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, sid))
return 1;
}
if (opts->context) {
- rc = parse_sid(sb, opts->context, &sid);
+ rc = parse_sid(sb, opts->context, &sid, GFP_NOWAIT);
if (rc)
return 1;
if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid, sid))
struct inode_security_struct *root_isec;
root_isec = backing_inode_security(sb->s_root);
- rc = parse_sid(sb, opts->rootcontext, &sid);
+ rc = parse_sid(sb, opts->rootcontext, &sid, GFP_NOWAIT);
if (rc)
return 1;
if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid, sid))
return 1;
}
if (opts->defcontext) {
- rc = parse_sid(sb, opts->defcontext, &sid);
+ rc = parse_sid(sb, opts->defcontext, &sid, GFP_NOWAIT);
if (rc)
return 1;
if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid, sid))
return 0;
if (opts->fscontext) {
- rc = parse_sid(sb, opts->fscontext, &sid);
+ rc = parse_sid(sb, opts->fscontext, &sid, GFP_KERNEL);
if (rc)
return rc;
if (bad_option(sbsec, FSCONTEXT_MNT, sbsec->sid, sid))
goto out_bad_option;
}
if (opts->context) {
- rc = parse_sid(sb, opts->context, &sid);
+ rc = parse_sid(sb, opts->context, &sid, GFP_KERNEL);
if (rc)
return rc;
if (bad_option(sbsec, CONTEXT_MNT, sbsec->mntpoint_sid, sid))
if (opts->rootcontext) {
struct inode_security_struct *root_isec;
root_isec = backing_inode_security(sb->s_root);
- rc = parse_sid(sb, opts->rootcontext, &sid);
+ rc = parse_sid(sb, opts->rootcontext, &sid, GFP_KERNEL);
if (rc)
return rc;
if (bad_option(sbsec, ROOTCONTEXT_MNT, root_isec->sid, sid))
goto out_bad_option;
}
if (opts->defcontext) {
- rc = parse_sid(sb, opts->defcontext, &sid);
+ rc = parse_sid(sb, opts->defcontext, &sid, GFP_KERNEL);
if (rc)
return rc;
if (bad_option(sbsec, DEFCONTEXT_MNT, sbsec->def_sid, sid))
struct snd_ctl_elem_value *data,
int type, int count)
{
+ struct snd_ctl_elem_value32 __user *data32 = userdata;
int i, size;
if (type == SNDRV_CTL_ELEM_TYPE_BOOLEAN ||
if (copy_to_user(valuep, data->value.bytes.data, size))
return -EFAULT;
}
+ if (copy_to_user(&data32->id, &data->id, sizeof(data32->id)))
+ return -EFAULT;
return 0;
}
*
* Return the maximum value for field PAR.
*/
-static unsigned int
+static int
snd_pcm_hw_param_value_max(const struct snd_pcm_hw_params *params,
snd_pcm_hw_param_t var, int *dir)
{
struct snd_pcm_hw_params *oss_params,
struct snd_pcm_hw_params *slave_params)
{
- size_t s;
- size_t oss_buffer_size, oss_period_size, oss_periods;
- size_t min_period_size, max_period_size;
+ ssize_t s;
+ ssize_t oss_buffer_size;
+ ssize_t oss_period_size, oss_periods;
+ ssize_t min_period_size, max_period_size;
struct snd_pcm_runtime *runtime = substream->runtime;
size_t oss_frame_size;
oss_frame_size = snd_pcm_format_physical_width(params_format(oss_params)) *
params_channels(oss_params) / 8;
+ oss_buffer_size = snd_pcm_hw_param_value_max(slave_params,
+ SNDRV_PCM_HW_PARAM_BUFFER_SIZE,
+ NULL);
+ if (oss_buffer_size <= 0)
+ return -EINVAL;
oss_buffer_size = snd_pcm_plug_client_size(substream,
- snd_pcm_hw_param_value_max(slave_params, SNDRV_PCM_HW_PARAM_BUFFER_SIZE, NULL)) * oss_frame_size;
- if (!oss_buffer_size)
+ oss_buffer_size * oss_frame_size);
+ if (oss_buffer_size <= 0)
return -EINVAL;
oss_buffer_size = rounddown_pow_of_two(oss_buffer_size);
if (atomic_read(&substream->mmap_count)) {
min_period_size = snd_pcm_plug_client_size(substream,
snd_pcm_hw_param_value_min(slave_params, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, NULL));
- if (min_period_size) {
+ if (min_period_size > 0) {
min_period_size *= oss_frame_size;
min_period_size = roundup_pow_of_two(min_period_size);
if (oss_period_size < min_period_size)
max_period_size = snd_pcm_plug_client_size(substream,
snd_pcm_hw_param_value_max(slave_params, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, NULL));
- if (max_period_size) {
+ if (max_period_size > 0) {
max_period_size *= oss_frame_size;
max_period_size = rounddown_pow_of_two(max_period_size);
if (oss_period_size > max_period_size)
oss_periods = substream->oss.setup.periods;
s = snd_pcm_hw_param_value_max(slave_params, SNDRV_PCM_HW_PARAM_PERIODS, NULL);
- if (runtime->oss.maxfrags && s > runtime->oss.maxfrags)
+ if (s > 0 && runtime->oss.maxfrags && s > runtime->oss.maxfrags)
s = runtime->oss.maxfrags;
if (oss_periods > s)
oss_periods = s;
err = -EINVAL;
goto failure;
}
- choose_rate(substream, sparams, runtime->oss.rate);
- snd_pcm_hw_param_near(substream, sparams, SNDRV_PCM_HW_PARAM_CHANNELS, runtime->oss.channels, NULL);
+
+ err = choose_rate(substream, sparams, runtime->oss.rate);
+ if (err < 0)
+ goto failure;
+ err = snd_pcm_hw_param_near(substream, sparams,
+ SNDRV_PCM_HW_PARAM_CHANNELS,
+ runtime->oss.channels, NULL);
+ if (err < 0)
+ goto failure;
format = snd_pcm_oss_format_from(runtime->oss.format);
if (runtime->oss.subdivision || runtime->oss.fragshift)
return -EINVAL;
fragshift = val & 0xffff;
- if (fragshift >= 31)
+ if (fragshift >= 25) /* should be large enough */
return -EINVAL;
runtime->oss.fragshift = fragshift;
runtime->oss.maxfrags = (val >> 16) & 0xffff;
/* for alc285_fixup_ideapad_s740_coef() */
#include "ideapad_s740_helper.c"
-static void alc256_fixup_tongfang_reset_persistent_settings(struct hda_codec *codec,
- const struct hda_fixup *fix,
- int action)
+static const struct coef_fw alc256_fixup_set_coef_defaults_coefs[] = {
+ WRITE_COEF(0x10, 0x0020), WRITE_COEF(0x24, 0x0000),
+ WRITE_COEF(0x26, 0x0000), WRITE_COEF(0x29, 0x3000),
+ WRITE_COEF(0x37, 0xfe05), WRITE_COEF(0x45, 0x5089),
+ {}
+};
+
+static void alc256_fixup_set_coef_defaults(struct hda_codec *codec,
+ const struct hda_fixup *fix,
+ int action)
{
/*
- * A certain other OS sets these coeffs to different values. On at least one TongFang
- * barebone these settings might survive even a cold reboot. So to restore a clean slate the
- * values are explicitly reset to default here. Without this, the external microphone is
- * always in a plugged-in state, while the internal microphone is always in an unplugged
- * state, breaking the ability to use the internal microphone.
- */
- alc_write_coef_idx(codec, 0x24, 0x0000);
- alc_write_coef_idx(codec, 0x26, 0x0000);
- alc_write_coef_idx(codec, 0x29, 0x3000);
- alc_write_coef_idx(codec, 0x37, 0xfe05);
- alc_write_coef_idx(codec, 0x45, 0x5089);
+ * A certain other OS sets these coeffs to different values. On at least
+ * one TongFang barebone these settings might survive even a cold
+ * reboot. So to restore a clean slate the values are explicitly reset
+ * to default here. Without this, the external microphone is always in a
+ * plugged-in state, while the internal microphone is always in an
+ * unplugged state, breaking the ability to use the internal microphone.
+ */
+ alc_process_coef_fw(codec, alc256_fixup_set_coef_defaults_coefs);
}
static const struct coef_fw alc233_fixup_no_audio_jack_coefs[] = {
ALC287_FIXUP_LEGION_15IMHG05_AUTOMUTE,
ALC287_FIXUP_YOGA7_14ITL_SPEAKERS,
ALC287_FIXUP_13S_GEN2_SPEAKERS,
- ALC256_FIXUP_TONGFANG_RESET_PERSISTENT_SETTINGS,
+ ALC256_FIXUP_SET_COEF_DEFAULTS,
ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE,
ALC233_FIXUP_NO_AUDIO_JACK,
};
.chained = true,
.chain_id = ALC269_FIXUP_HEADSET_MODE,
},
- [ALC256_FIXUP_TONGFANG_RESET_PERSISTENT_SETTINGS] = {
+ [ALC256_FIXUP_SET_COEF_DEFAULTS] = {
.type = HDA_FIXUP_FUNC,
- .v.func = alc256_fixup_tongfang_reset_persistent_settings,
+ .v.func = alc256_fixup_set_coef_defaults,
},
[ALC245_FIXUP_HP_GPIO_LED] = {
.type = HDA_FIXUP_FUNC,
SND_PCI_QUIRK(0x1b7d, 0xa831, "Ordissimo EVE2 ", ALC269VB_FIXUP_ORDISSIMO_EVE2), /* Also known as Malata PC-B1303 */
SND_PCI_QUIRK(0x1c06, 0x2013, "Lemote A1802", ALC269_FIXUP_LEMOTE_A1802),
SND_PCI_QUIRK(0x1c06, 0x2015, "Lemote A190X", ALC269_FIXUP_LEMOTE_A190X),
- SND_PCI_QUIRK(0x1d05, 0x1132, "TongFang PHxTxX1", ALC256_FIXUP_TONGFANG_RESET_PERSISTENT_SETTINGS),
+ SND_PCI_QUIRK(0x1d05, 0x1132, "TongFang PHxTxX1", ALC256_FIXUP_SET_COEF_DEFAULTS),
SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC),
SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC),
}
}
+static void alc897_hp_automute_hook(struct hda_codec *codec,
+ struct hda_jack_callback *jack)
+{
+ struct alc_spec *spec = codec->spec;
+ int vref;
+
+ snd_hda_gen_hp_automute(codec, jack);
+ vref = spec->gen.hp_jack_present ? (PIN_HP | AC_PINCTL_VREF_100) : PIN_HP;
+ snd_hda_codec_write(codec, 0x1b, 0, AC_VERB_SET_PIN_WIDGET_CONTROL,
+ vref);
+}
+
+static void alc897_fixup_lenovo_headset_mic(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ struct alc_spec *spec = codec->spec;
+ if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+ spec->gen.hp_automute_hook = alc897_hp_automute_hook;
+ }
+}
+
static const struct coef_fw alc668_coefs[] = {
WRITE_COEF(0x01, 0xbebe), WRITE_COEF(0x02, 0xaaaa), WRITE_COEF(0x03, 0x0),
WRITE_COEF(0x04, 0x0180), WRITE_COEF(0x06, 0x0), WRITE_COEF(0x07, 0x0f80),
ALC668_FIXUP_ASUS_NO_HEADSET_MIC,
ALC668_FIXUP_HEADSET_MIC,
ALC668_FIXUP_MIC_DET_COEF,
+ ALC897_FIXUP_LENOVO_HEADSET_MIC,
+ ALC897_FIXUP_HEADSET_MIC_PIN,
};
static const struct hda_fixup alc662_fixups[] = {
{}
},
},
+ [ALC897_FIXUP_LENOVO_HEADSET_MIC] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc897_fixup_lenovo_headset_mic,
+ },
+ [ALC897_FIXUP_HEADSET_MIC_PIN] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x1a, 0x03a11050 },
+ { }
+ },
+ .chained = true,
+ .chain_id = ALC897_FIXUP_LENOVO_HEADSET_MIC
+ },
};
static const struct snd_pci_quirk alc662_fixup_tbl[] = {
SND_PCI_QUIRK(0x144d, 0xc051, "Samsung R720", ALC662_FIXUP_IDEAPAD),
SND_PCI_QUIRK(0x14cd, 0x5003, "USI", ALC662_FIXUP_USI_HEADSET_MODE),
SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC662_FIXUP_LENOVO_MULTI_CODECS),
+ SND_PCI_QUIRK(0x17aa, 0x32ca, "Lenovo ThinkCentre M80", ALC897_FIXUP_HEADSET_MIC_PIN),
+ SND_PCI_QUIRK(0x17aa, 0x32cb, "Lenovo ThinkCentre M70", ALC897_FIXUP_HEADSET_MIC_PIN),
+ SND_PCI_QUIRK(0x17aa, 0x32cf, "Lenovo ThinkCentre M950", ALC897_FIXUP_HEADSET_MIC_PIN),
+ SND_PCI_QUIRK(0x17aa, 0x32f7, "Lenovo ThinkCentre M90", ALC897_FIXUP_HEADSET_MIC_PIN),
SND_PCI_QUIRK(0x17aa, 0x38af, "Lenovo Ideapad Y550P", ALC662_FIXUP_IDEAPAD),
SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Ideapad Y550", ALC662_FIXUP_IDEAPAD),
SND_PCI_QUIRK(0x1849, 0x5892, "ASRock B150M", ALC892_FIXUP_ASROCK_MOBO),
{
struct acp6x_dev_data *adata;
struct platform_device_info pdevinfo[ACP6x_DEVS];
- int ret, index;
+ int index = 0;
int val = 0x00;
u32 addr;
unsigned int irqflags;
+ int ret;
irqflags = IRQF_SHARED;
/* Yellow Carp device check */
for (i = 0; i < RT5682_DAI_NUM_CLKS; ++i) {
struct clk_init_data init = { };
+ struct clk_parent_data parent_data;
+ const struct clk_hw *parent;
dai_clk_hw = &rt5682->dai_clks_hw[i];
case RT5682_DAI_WCLK_IDX:
/* Make MCLK the parent of WCLK */
if (rt5682->mclk) {
- init.parent_data = &(struct clk_parent_data){
+ parent_data = (struct clk_parent_data){
.fw_name = "mclk",
};
+ init.parent_data = &parent_data;
init.num_parents = 1;
}
break;
case RT5682_DAI_BCLK_IDX:
/* Make WCLK the parent of BCLK */
- init.parent_hws = &(const struct clk_hw *){
- &rt5682->dai_clks_hw[RT5682_DAI_WCLK_IDX]
- };
+ parent = &rt5682->dai_clks_hw[RT5682_DAI_WCLK_IDX];
+ init.parent_hws = &parent;
init.num_parents = 1;
break;
default:
for (i = 0; i < RT5682S_DAI_NUM_CLKS; ++i) {
struct clk_init_data init = { };
+ struct clk_parent_data parent_data;
+ const struct clk_hw *parent;
dai_clk_hw = &rt5682s->dai_clks_hw[i];
case RT5682S_DAI_WCLK_IDX:
/* Make MCLK the parent of WCLK */
if (rt5682s->mclk) {
- init.parent_data = &(struct clk_parent_data){
+ parent_data = (struct clk_parent_data){
.fw_name = "mclk",
};
+ init.parent_data = &parent_data;
init.num_parents = 1;
}
break;
case RT5682S_DAI_BCLK_IDX:
/* Make WCLK the parent of BCLK */
- init.parent_hws = &(const struct clk_hw *){
- &rt5682s->dai_clks_hw[RT5682S_DAI_WCLK_IDX]
- };
+ parent = &rt5682s->dai_clks_hw[RT5682S_DAI_WCLK_IDX];
+ init.parent_hws = &parent;
init.num_parents = 1;
break;
default:
int value = ucontrol->value.integer.value[0];
int sel;
+ if (wcd->comp_enabled[comp] == value)
+ return 0;
+
wcd->comp_enabled[comp] = value;
sel = value ? WCD934X_HPH_GAIN_SRC_SEL_COMPANDER :
WCD934X_HPH_GAIN_SRC_SEL_REGISTER;
case COMPANDER_8:
break;
default:
- break;
+ return 0;
}
- return 0;
+ return 1;
}
static int wcd934x_rx_hph_mode_get(struct snd_kcontrol *kc,
return 0;
}
+static int slim_rx_mux_to_dai_id(int mux)
+{
+ int aif_id;
+
+ switch (mux) {
+ case 1:
+ aif_id = AIF1_PB;
+ break;
+ case 2:
+ aif_id = AIF2_PB;
+ break;
+ case 3:
+ aif_id = AIF3_PB;
+ break;
+ case 4:
+ aif_id = AIF4_PB;
+ break;
+ default:
+ aif_id = -1;
+ break;
+ }
+
+ return aif_id;
+}
+
static int slim_rx_mux_put(struct snd_kcontrol *kc,
struct snd_ctl_elem_value *ucontrol)
{
struct wcd934x_codec *wcd = dev_get_drvdata(w->dapm->dev);
struct soc_enum *e = (struct soc_enum *)kc->private_value;
struct snd_soc_dapm_update *update = NULL;
+ struct wcd934x_slim_ch *ch, *c;
u32 port_id = w->shift;
+ bool found = false;
+ int mux_idx;
+ int prev_mux_idx = wcd->rx_port_value[port_id];
+ int aif_id;
- if (wcd->rx_port_value[port_id] == ucontrol->value.enumerated.item[0])
- return 0;
+ mux_idx = ucontrol->value.enumerated.item[0];
- wcd->rx_port_value[port_id] = ucontrol->value.enumerated.item[0];
+ if (mux_idx == prev_mux_idx)
+ return 0;
- switch (wcd->rx_port_value[port_id]) {
+ switch(mux_idx) {
case 0:
- list_del_init(&wcd->rx_chs[port_id].list);
- break;
- case 1:
- list_add_tail(&wcd->rx_chs[port_id].list,
- &wcd->dai[AIF1_PB].slim_ch_list);
- break;
- case 2:
- list_add_tail(&wcd->rx_chs[port_id].list,
- &wcd->dai[AIF2_PB].slim_ch_list);
- break;
- case 3:
- list_add_tail(&wcd->rx_chs[port_id].list,
- &wcd->dai[AIF3_PB].slim_ch_list);
+ aif_id = slim_rx_mux_to_dai_id(prev_mux_idx);
+ if (aif_id < 0)
+ return 0;
+
+ list_for_each_entry_safe(ch, c, &wcd->dai[aif_id].slim_ch_list, list) {
+ if (ch->port == port_id + WCD934X_RX_START) {
+ found = true;
+ list_del_init(&ch->list);
+ break;
+ }
+ }
+ if (!found)
+ return 0;
+
break;
- case 4:
- list_add_tail(&wcd->rx_chs[port_id].list,
- &wcd->dai[AIF4_PB].slim_ch_list);
+ case 1 ... 4:
+ aif_id = slim_rx_mux_to_dai_id(mux_idx);
+ if (aif_id < 0)
+ return 0;
+
+ if (list_empty(&wcd->rx_chs[port_id].list)) {
+ list_add_tail(&wcd->rx_chs[port_id].list,
+ &wcd->dai[aif_id].slim_ch_list);
+ } else {
+ dev_err(wcd->dev ,"SLIM_RX%d PORT is busy\n", port_id);
+ return 0;
+ }
break;
+
default:
- dev_err(wcd->dev, "Unknown AIF %d\n",
- wcd->rx_port_value[port_id]);
+ dev_err(wcd->dev, "Unknown AIF %d\n", mux_idx);
goto err;
}
+ wcd->rx_port_value[port_id] = mux_idx;
snd_soc_dapm_mux_update_power(w->dapm, kc, wcd->rx_port_value[port_id],
e, update);
- return 0;
+ return 1;
err:
return -EINVAL;
}
struct soc_mixer_control *mixer =
(struct soc_mixer_control *)kc->private_value;
int enable = ucontrol->value.integer.value[0];
+ struct wcd934x_slim_ch *ch, *c;
int dai_id = widget->shift;
int port_id = mixer->shift;
if (enable == wcd->tx_port_value[port_id])
return 0;
- wcd->tx_port_value[port_id] = enable;
-
- if (enable)
- list_add_tail(&wcd->tx_chs[port_id].list,
- &wcd->dai[dai_id].slim_ch_list);
- else
- list_del_init(&wcd->tx_chs[port_id].list);
+ if (enable) {
+ if (list_empty(&wcd->tx_chs[port_id].list)) {
+ list_add_tail(&wcd->tx_chs[port_id].list,
+ &wcd->dai[dai_id].slim_ch_list);
+ } else {
+ dev_err(wcd->dev ,"SLIM_TX%d PORT is busy\n", port_id);
+ return 0;
+ }
+ } else {
+ bool found = false;
+
+ list_for_each_entry_safe(ch, c, &wcd->dai[dai_id].slim_ch_list, list) {
+ if (ch->port == port_id) {
+ found = true;
+ list_del_init(&wcd->tx_chs[port_id].list);
+ break;
+ }
+ }
+ if (!found)
+ return 0;
+ }
+ wcd->tx_port_value[port_id] = enable;
snd_soc_dapm_mixer_update_power(widget->dapm, kc, enable, update);
- return 0;
+ return 1;
}
static const struct snd_kcontrol_new aif1_slim_cap_mixer[] = {
usleep_range(1000, 1010);
}
- return 0;
+
+ return 1;
}
static int wsa881x_get_port(struct snd_kcontrol *kcontrol,
(struct soc_mixer_control *)kcontrol->private_value;
int portidx = mixer->reg;
- if (ucontrol->value.integer.value[0])
+ if (ucontrol->value.integer.value[0]) {
+ if (data->port_enable[portidx])
+ return 0;
+
data->port_enable[portidx] = true;
- else
+ } else {
+ if (!data->port_enable[portidx])
+ return 0;
+
data->port_enable[portidx] = false;
+ }
if (portidx == WSA881X_PORT_BOOST) /* Boost Switch */
wsa881x_boost_ctrl(comp, data->port_enable[portidx]);
- return 0;
+ return 1;
}
static const char * const smart_boost_lvl_text[] = {
struct session_data *session = &data->sessions[session_id];
if (ucontrol->value.integer.value[0]) {
+ if (session->port_id == be_id)
+ return 0;
+
session->port_id = be_id;
snd_soc_dapm_mixer_update_power(dapm, kcontrol, 1, update);
} else {
- if (session->port_id == be_id) {
- session->port_id = -1;
+ if (session->port_id == -1 || session->port_id != be_id)
return 0;
- }
+ session->port_id = -1;
snd_soc_dapm_mixer_update_power(dapm, kcontrol, 0, update);
}
spinlock_t lock; /* xfer lock */
bool has_playback;
bool has_capture;
+ struct snd_soc_dai_driver *dai;
};
static int to_ch_num(unsigned int val)
{},
};
-static struct snd_soc_dai_driver i2s_tdm_dai = {
+static const struct snd_soc_dai_driver i2s_tdm_dai = {
.probe = rockchip_i2s_tdm_dai_probe,
- .playback = {
- .stream_name = "Playback",
- },
- .capture = {
- .stream_name = "Capture",
- },
.ops = &rockchip_i2s_tdm_dai_ops,
};
-static void rockchip_i2s_tdm_init_dai(struct rk_i2s_tdm_dev *i2s_tdm)
+static int rockchip_i2s_tdm_init_dai(struct rk_i2s_tdm_dev *i2s_tdm)
{
+ struct snd_soc_dai_driver *dai;
struct property *dma_names;
const char *dma_name;
u64 formats = (SNDRV_PCM_FMTBIT_S8 | SNDRV_PCM_FMTBIT_S16_LE |
i2s_tdm->has_capture = true;
}
+ dai = devm_kmemdup(i2s_tdm->dev, &i2s_tdm_dai,
+ sizeof(*dai), GFP_KERNEL);
+ if (!dai)
+ return -ENOMEM;
+
if (i2s_tdm->has_playback) {
- i2s_tdm_dai.playback.channels_min = 2;
- i2s_tdm_dai.playback.channels_max = 8;
- i2s_tdm_dai.playback.rates = SNDRV_PCM_RATE_8000_192000;
- i2s_tdm_dai.playback.formats = formats;
+ dai->playback.stream_name = "Playback";
+ dai->playback.channels_min = 2;
+ dai->playback.channels_max = 8;
+ dai->playback.rates = SNDRV_PCM_RATE_8000_192000;
+ dai->playback.formats = formats;
}
if (i2s_tdm->has_capture) {
- i2s_tdm_dai.capture.channels_min = 2;
- i2s_tdm_dai.capture.channels_max = 8;
- i2s_tdm_dai.capture.rates = SNDRV_PCM_RATE_8000_192000;
- i2s_tdm_dai.capture.formats = formats;
+ dai->capture.stream_name = "Capture";
+ dai->capture.channels_min = 2;
+ dai->capture.channels_max = 8;
+ dai->capture.rates = SNDRV_PCM_RATE_8000_192000;
+ dai->capture.formats = formats;
}
+
+ if (i2s_tdm->clk_trcm != TRCM_TXRX)
+ dai->symmetric_rate = 1;
+
+ i2s_tdm->dai = dai;
+
+ return 0;
}
static int rockchip_i2s_tdm_path_check(struct rk_i2s_tdm_dev *i2s_tdm,
spin_lock_init(&i2s_tdm->lock);
i2s_tdm->soc_data = (struct rk_i2s_soc_data *)of_id->data;
- rockchip_i2s_tdm_init_dai(i2s_tdm);
-
i2s_tdm->frame_width = 64;
i2s_tdm->clk_trcm = TRCM_TXRX;
}
i2s_tdm->clk_trcm = TRCM_RX;
}
- if (i2s_tdm->clk_trcm != TRCM_TXRX)
- i2s_tdm_dai.symmetric_rate = 1;
+
+ ret = rockchip_i2s_tdm_init_dai(i2s_tdm);
+ if (ret)
+ return ret;
i2s_tdm->grf = syscon_regmap_lookup_by_phandle(node, "rockchip,grf");
if (IS_ERR(i2s_tdm->grf))
ret = devm_snd_soc_register_component(&pdev->dev,
&rockchip_i2s_tdm_component,
- &i2s_tdm_dai, 1);
+ i2s_tdm->dai, 1);
if (ret) {
dev_err(&pdev->dev, "Could not register DAI\n");
#if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA_AUDIO_CODEC)
#define IDISP_VID_INTEL 0x80860000
+#define CODEC_PROBE_RETRIES 3
/* load the legacy HDA codec driver */
static int request_codec_module(struct hda_codec *codec)
u32 hda_cmd = (address << 28) | (AC_NODE_ROOT << 20) |
(AC_VERB_PARAMETERS << 8) | AC_PAR_VENDOR_ID;
u32 resp = -1;
- int ret;
+ int ret, retry = 0;
+
+ do {
+ mutex_lock(&hbus->core.cmd_mutex);
+ snd_hdac_bus_send_cmd(&hbus->core, hda_cmd);
+ snd_hdac_bus_get_response(&hbus->core, address, &resp);
+ mutex_unlock(&hbus->core.cmd_mutex);
+ } while (resp == -1 && retry++ < CODEC_PROBE_RETRIES);
- mutex_lock(&hbus->core.cmd_mutex);
- snd_hdac_bus_send_cmd(&hbus->core, hda_cmd);
- snd_hdac_bus_get_response(&hbus->core, address, &resp);
- mutex_unlock(&hbus->core.cmd_mutex);
if (resp == -1)
return -EIO;
dev_dbg(sdev->dev, "HDA codec #%d probed OK: response: %x\n",
static const struct dev_pm_ops tegra210_adx_pm_ops = {
SET_RUNTIME_PM_OPS(tegra210_adx_runtime_suspend,
tegra210_adx_runtime_resume, NULL)
- SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
- pm_runtime_force_resume)
+ SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+ pm_runtime_force_resume)
};
static struct platform_driver tegra210_adx_driver = {
static const struct dev_pm_ops tegra210_amx_pm_ops = {
SET_RUNTIME_PM_OPS(tegra210_amx_runtime_suspend,
tegra210_amx_runtime_resume, NULL)
- SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
- pm_runtime_force_resume)
+ SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+ pm_runtime_force_resume)
};
static struct platform_driver tegra210_amx_driver = {
static const struct dev_pm_ops tegra210_mixer_pm_ops = {
SET_RUNTIME_PM_OPS(tegra210_mixer_runtime_suspend,
tegra210_mixer_runtime_resume, NULL)
- SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
- pm_runtime_force_resume)
+ SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+ pm_runtime_force_resume)
};
static struct platform_driver tegra210_mixer_driver = {
if (err < 0)
goto end;
- return 1;
+ err = 1;
end:
pm_runtime_put(cmpnt->dev);
TEGRA210_MVC_VOLUME_SWITCH_MASK,
TEGRA210_MVC_VOLUME_SWITCH_TRIGGER);
- return 1;
+ err = 1;
end:
pm_runtime_put(cmpnt->dev);
static const struct dev_pm_ops tegra210_mvc_pm_ops = {
SET_RUNTIME_PM_OPS(tegra210_mvc_runtime_suspend,
tegra210_mvc_runtime_resume, NULL)
- SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
- pm_runtime_force_resume)
+ SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+ pm_runtime_force_resume)
};
static struct platform_driver tegra210_mvc_driver = {
static const struct dev_pm_ops tegra210_sfc_pm_ops = {
SET_RUNTIME_PM_OPS(tegra210_sfc_runtime_suspend,
tegra210_sfc_runtime_resume, NULL)
- SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
- pm_runtime_force_resume)
+ SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+ pm_runtime_force_resume)
};
static struct platform_driver tegra210_sfc_driver = {
static const struct snd_djm_device snd_djm_devices[] = {
- SND_DJM_DEVICE(250mk2),
- SND_DJM_DEVICE(750),
- SND_DJM_DEVICE(750mk2),
- SND_DJM_DEVICE(850),
- SND_DJM_DEVICE(900nxs2)
+ [SND_DJM_250MK2_IDX] = SND_DJM_DEVICE(250mk2),
+ [SND_DJM_750_IDX] = SND_DJM_DEVICE(750),
+ [SND_DJM_850_IDX] = SND_DJM_DEVICE(850),
+ [SND_DJM_900NXS2_IDX] = SND_DJM_DEVICE(900nxs2),
+ [SND_DJM_750MK2_IDX] = SND_DJM_DEVICE(750mk2),
};
int cnt;
};
int addr_cnt;
+ bool is_set;
Elf64_Addr addr[ADDR_CNT];
};
* in symbol's size, together with 'cnt' field hence
* that - 1.
*/
- if (id)
+ if (id) {
id->cnt = sym.st_size / sizeof(int) - 1;
+ id->is_set = true;
+ }
} else {
pr_err("FAILED unsupported prefix %s\n", prefix);
return -1;
int *ptr = data->d_buf;
int i;
- if (!id->id) {
+ if (!id->id && !id->is_set)
pr_err("WARN: resolve_btfids: unresolved symbol %s\n", id->name);
- }
for (i = 0; i < id->addr_cnt; i++) {
unsigned long addr = id->addr[i];
numa_num_possible_cpus \
libperl \
libpython \
- libpython-version \
libslang \
libslang-include-subdir \
libtraceevent \
test-numa_num_possible_cpus.bin \
test-libperl.bin \
test-libpython.bin \
- test-libpython-version.bin \
test-libslang.bin \
test-libslang-include-subdir.bin \
test-libtraceevent.bin \
$(OUTPUT)test-libpython.bin:
$(BUILD) $(FLAGS_PYTHON_EMBED)
-$(OUTPUT)test-libpython-version.bin:
- $(BUILD)
-
$(OUTPUT)test-libbfd.bin:
$(BUILD) -DPACKAGE='"perf"' -lbfd -ldl
# include "test-libpython.c"
#undef main
-#define main main_test_libpython_version
-# include "test-libpython-version.c"
-#undef main
-
#define main main_test_libperl
# include "test-libperl.c"
#undef main
int main(int argc, char *argv[])
{
main_test_libpython();
- main_test_libpython_version();
main_test_libperl();
main_test_hello();
main_test_libelf();
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0
-#include <Python.h>
-
-#if PY_VERSION_HEX >= 0x03000000
- #error
-#endif
-
-int main(void)
-{
- return 0;
-}
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LIBLOCKDEP_DEBUG_LOCKS_H_
-#define _LIBLOCKDEP_DEBUG_LOCKS_H_
-
-#include <stddef.h>
-#include <linux/compiler.h>
-#include <asm/bug.h>
-
-#define DEBUG_LOCKS_WARN_ON(x) WARN_ON(x)
-
-extern bool debug_locks;
-extern bool debug_locks_silent;
-
-#endif
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LIBLOCKDEP_LINUX_HARDIRQ_H_
-#define _LIBLOCKDEP_LINUX_HARDIRQ_H_
-
-#define SOFTIRQ_BITS 0UL
-#define HARDIRQ_BITS 0UL
-#define SOFTIRQ_SHIFT 0UL
-#define HARDIRQ_SHIFT 0UL
-#define hardirq_count() 0UL
-#define softirq_count() 0UL
-
-#endif
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_
-#define _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_
-
-# define lockdep_hardirq_context() 0
-# define lockdep_softirq_context(p) 0
-# define lockdep_hardirqs_enabled() 0
-# define lockdep_softirqs_enabled(p) 0
-# define lockdep_hardirq_enter() do { } while (0)
-# define lockdep_hardirq_exit() do { } while (0)
-# define lockdep_softirq_enter() do { } while (0)
-# define lockdep_softirq_exit() do { } while (0)
-# define INIT_TRACE_IRQFLAGS
-
-# define stop_critical_timings() do { } while (0)
-# define start_critical_timings() do { } while (0)
-
-#define raw_local_irq_disable() do { } while (0)
-#define raw_local_irq_enable() do { } while (0)
-#define raw_local_irq_save(flags) ((flags) = 0)
-#define raw_local_irq_restore(flags) ((void)(flags))
-#define raw_local_save_flags(flags) ((flags) = 0)
-#define raw_irqs_disabled_flags(flags) ((void)(flags))
-#define raw_irqs_disabled() 0
-#define raw_safe_halt()
-
-#define local_irq_enable() do { } while (0)
-#define local_irq_disable() do { } while (0)
-#define local_irq_save(flags) ((flags) = 0)
-#define local_irq_restore(flags) ((void)(flags))
-#define local_save_flags(flags) ((flags) = 0)
-#define irqs_disabled() (1)
-#define irqs_disabled_flags(flags) ((void)(flags), 0)
-#define safe_halt() do { } while (0)
-
-#define trace_lock_release(x, y)
-#define trace_lock_acquire(a, b, c, d, e, f, g)
-
-#endif
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LIBLOCKDEP_LOCKDEP_H_
-#define _LIBLOCKDEP_LOCKDEP_H_
-
-#include <sys/prctl.h>
-#include <sys/syscall.h>
-#include <string.h>
-#include <limits.h>
-#include <linux/utsname.h>
-#include <linux/compiler.h>
-#include <linux/export.h>
-#include <linux/kern_levels.h>
-#include <linux/err.h>
-#include <linux/rcu.h>
-#include <linux/list.h>
-#include <linux/hardirq.h>
-#include <unistd.h>
-
-#define MAX_LOCK_DEPTH 63UL
-
-#define asmlinkage
-#define __visible
-
-#include "../../../include/linux/lockdep.h"
-
-struct task_struct {
- u64 curr_chain_key;
- int lockdep_depth;
- unsigned int lockdep_recursion;
- struct held_lock held_locks[MAX_LOCK_DEPTH];
- gfp_t lockdep_reclaim_gfp;
- int pid;
- int state;
- char comm[17];
-};
-
-#define TASK_RUNNING 0
-
-extern struct task_struct *__curr(void);
-
-#define current (__curr())
-
-static inline int debug_locks_off(void)
-{
- return 1;
-}
-
-#define task_pid_nr(tsk) ((tsk)->pid)
-
-#define KSYM_NAME_LEN 128
-#define printk(...) dprintf(STDOUT_FILENO, __VA_ARGS__)
-#define pr_err(format, ...) fprintf (stderr, format, ## __VA_ARGS__)
-#define pr_warn pr_err
-#define pr_cont pr_err
-
-#define list_del_rcu list_del
-
-#define atomic_t unsigned long
-#define atomic_inc(x) ((*(x))++)
-
-#define print_tainted() ""
-#define static_obj(x) 1
-
-#define debug_show_all_locks()
-extern void debug_check_no_locks_held(void);
-
-static __used bool __is_kernel_percpu_address(unsigned long addr, void *can_addr)
-{
- return false;
-}
-
-#endif
+++ /dev/null
-#ifndef _TOOLS_INCLUDE_LINUX_PROC_FS_H
-#define _TOOLS_INCLUDE_LINUX_PROC_FS_H
-
-#endif /* _TOOLS_INCLUDE_LINUX_PROC_FS_H */
return true;
}
-#include <linux/lockdep.h>
-
#endif
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LIBLOCKDEP_LINUX_STACKTRACE_H_
-#define _LIBLOCKDEP_LINUX_STACKTRACE_H_
-
-#include <execinfo.h>
-
-struct stack_trace {
- unsigned int nr_entries, max_entries;
- unsigned long *entries;
- int skip;
-};
-
-static inline void print_stack_trace(struct stack_trace *trace, int spaces)
-{
- backtrace_symbols_fd((void **)trace->entries, trace->nr_entries, 1);
-}
-
-#define save_stack_trace(trace) \
- ((trace)->nr_entries = \
- backtrace((void **)(trace)->entries, (trace)->max_entries))
-
-static inline int dump_stack(void)
-{
- void *array[64];
- size_t size;
-
- size = backtrace(array, 64);
- backtrace_symbols_fd(array, size, 1);
-
- return 0;
-}
-
-#endif
FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
FEATURE_CHECK_LDFLAGS-libpython := $(PYTHON_EMBED_LDOPTS)
-FEATURE_CHECK_CFLAGS-libpython-version := $(PYTHON_EMBED_CCOPTS)
-FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
FEATURE_CHECK_LDFLAGS-libaio = -lrt
446 common landlock_restrict_self sys_landlock_restrict_self
# 447 reserved for memfd_secret
448 common process_mrelease sys_process_mrelease
+449 common futex_waitv sys_futex_waitv
446 common landlock_restrict_self sys_landlock_restrict_self sys_landlock_restrict_self
# 447 reserved for memfd_secret
448 common process_mrelease sys_process_mrelease sys_process_mrelease
+449 common futex_waitv sys_futex_waitv sys_futex_waitv
snd_ctx->out_fds[i] = fds[1];
if (!thread_mode)
close(fds[0]);
-
- free(ctx);
}
/* Now we have all the fds, fork the senders */
for (i = 0; i < num_fds; i++)
close(snd_ctx->out_fds[i]);
- free(snd_ctx);
-
/* Return number of children to reap */
return num_fds * 2;
}
return inject->itrace_synth_opts.vm_tm_corr_args ? 0 : -ENOMEM;
}
+static int output_fd(struct perf_inject *inject)
+{
+ return inject->in_place_update ? -1 : perf_data__fd(&inject->output);
+}
+
static int __cmd_inject(struct perf_inject *inject)
{
int ret = -EINVAL;
struct perf_session *session = inject->session;
- struct perf_data *data_out = &inject->output;
- int fd = inject->in_place_update ? -1 : perf_data__fd(data_out);
+ int fd = output_fd(inject);
u64 output_data_offset;
signal(SIGINT, sig_handler);
inject->tool.ordered_events = true;
inject->tool.ordering_requires_timestamps = true;
/* Allow space in the header for new attributes */
- output_data_offset = 4096;
+ output_data_offset = roundup(8192 + session->header.data_offset, 4096);
if (inject->strip)
strip_init(inject);
}
}
inject.session = __perf_session__new(&data, repipe,
- perf_data__fd(&inject.output),
+ output_fd(&inject),
&inject.tool);
if (IS_ERR(inject.session)) {
ret = PTR_ERR(inject.session);
zstd_fini(&(inject.session->zstd_data));
perf_session__delete(inject.session);
out_close_output:
- perf_data__close(&inject.output);
+ if (!inject.in_place_update)
+ perf_data__close(&inject.output);
free(inject.itrace_synth_opts.vm_tm_corr_args);
return ret;
}
TEST_ASSERT_VAL("#num_dies", expr__parse(&num_dies, ctx, "#num_dies") == 0);
TEST_ASSERT_VAL("#num_cores >= #num_dies", num_cores >= num_dies);
TEST_ASSERT_VAL("#num_packages", expr__parse(&num_packages, ctx, "#num_packages") == 0);
- TEST_ASSERT_VAL("#num_dies >= #num_packages", num_dies >= num_packages);
+
+ if (num_dies) // Some platforms do not have CPU die support, for example s390
+ TEST_ASSERT_VAL("#num_dies >= #num_packages", num_dies >= num_packages);
/*
* Source count returns the number of events aggregating in a leader
struct evsel *evsel;
u64 count;
+ perf_stat__reset_shadow_stats();
evlist__for_each_entry(evlist, evsel) {
count = find_value(evsel->name, vals);
perf_stat__update_shadow_stats(evsel, count, 0, st);
+++ /dev/null
-// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
-// Copyright (c) 2021 Facebook
-
-#ifndef __BPERF_STAT_H
-#define __BPERF_STAT_H
-
-typedef struct {
- __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
- __uint(key_size, sizeof(__u32));
- __uint(value_size, sizeof(struct bpf_perf_event_value));
- __uint(max_entries, 1);
-} reading_map;
-
-#endif /* __BPERF_STAT_H */
// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
// Copyright (c) 2021 Facebook
-#include <linux/bpf.h>
-#include <linux/perf_event.h>
+#include "vmlinux.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
-#include "bperf.h"
#include "bperf_u.h"
-reading_map diff_readings SEC(".maps");
-reading_map accum_readings SEC(".maps");
+struct {
+ __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(struct bpf_perf_event_value));
+ __uint(max_entries, 1);
+} diff_readings SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(struct bpf_perf_event_value));
+ __uint(max_entries, 1);
+} accum_readings SEC(".maps");
struct {
__uint(type, BPF_MAP_TYPE_HASH);
// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
// Copyright (c) 2021 Facebook
-#include <linux/bpf.h>
-#include <linux/perf_event.h>
+#include "vmlinux.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
-#include "bperf.h"
struct {
__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
__uint(map_flags, BPF_F_PRESERVE_ELEMS);
} events SEC(".maps");
-reading_map prev_readings SEC(".maps");
-reading_map diff_readings SEC(".maps");
+struct {
+ __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(struct bpf_perf_event_value));
+ __uint(max_entries, 1);
+} prev_readings SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(struct bpf_perf_event_value));
+ __uint(max_entries, 1);
+} diff_readings SEC(".maps");
SEC("raw_tp/sched_switch")
int BPF_PROG(on_switch)
// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
// Copyright (c) 2020 Facebook
-#include <linux/bpf.h>
+#include "vmlinux.h"
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
/* perf sample has 16 bits size limit */
#define PERF_SAMPLE_MAX_SIZE (1 << 16)
+/* number of register is bound by the number of bits in regs_dump::mask (64) */
+#define PERF_SAMPLE_REGS_CACHE_SIZE (8 * sizeof(u64))
+
struct regs_dump {
u64 abi;
u64 mask;
u64 *regs;
/* Cached values/mask filled by first register access. */
- u64 cache_regs[PERF_REGS_MAX];
+ u64 cache_regs[PERF_SAMPLE_REGS_CACHE_SIZE];
u64 cache_mask;
};
#include "expr-bison.h"
#include "expr-flex.h"
#include "smt.h"
+#include <linux/err.h>
#include <linux/kernel.h>
#include <linux/zalloc.h>
#include <ctype.h>
return NULL;
ctx->ids = hashmap__new(key_hash, key_equal, NULL);
+ if (IS_ERR(ctx->ids)) {
+ free(ctx);
+ return NULL;
+ }
ctx->runtime = 0;
return ctx;
#define FEAT_PROCESS_STR_FUN(__feat, __feat_env) \
static int process_##__feat(struct feat_fd *ff, void *data __maybe_unused) \
{\
+ free(ff->ph->env.__feat_env); \
ff->ph->env.__feat_env = do_read_string(ff); \
return ff->ph->env.__feat_env ? 0 : -ENOMEM; \
}
struct perf_record_header_feature *fe = (struct perf_record_header_feature *)event;
int type = fe->header.type;
u64 feat = fe->feat_id;
+ int ret = 0;
if (type < 0 || type >= PERF_RECORD_HEADER_MAX) {
pr_warning("invalid record type %d in pipe-mode\n", type);
ff.size = event->header.size - sizeof(*fe);
ff.ph = &session->header;
- if (feat_ops[feat].process(&ff, NULL))
- return -1;
+ if (feat_ops[feat].process(&ff, NULL)) {
+ ret = -1;
+ goto out;
+ }
if (!feat_ops[feat].print || !tool->show_feat_hdr)
- return 0;
+ goto out;
if (!feat_ops[feat].full_only ||
tool->show_feat_hdr >= SHOW_FEAT_HEADER_FULL_INFO) {
fprintf(stdout, "# %s info available, use -I to display\n",
feat_ops[feat].name);
}
-
- return 0;
+out:
+ free_event_desc(ff.events);
+ return ret;
}
size_t perf_event__fprintf_event_update(union perf_event *event, FILE *fp)
static bool intel_pt_fup_event(struct intel_pt_decoder *decoder)
{
+ enum intel_pt_sample_type type = decoder->state.type;
bool ret = false;
+ decoder->state.type &= ~INTEL_PT_BRANCH;
+
if (decoder->set_fup_tx_flags) {
decoder->set_fup_tx_flags = false;
decoder->tx_flags = decoder->fup_tx_flags;
- decoder->state.type = INTEL_PT_TRANSACTION;
+ decoder->state.type |= INTEL_PT_TRANSACTION;
if (decoder->fup_tx_flags & INTEL_PT_ABORT_TX)
decoder->state.type |= INTEL_PT_BRANCH;
- decoder->state.from_ip = decoder->ip;
- decoder->state.to_ip = 0;
decoder->state.flags = decoder->fup_tx_flags;
- return true;
+ ret = true;
}
if (decoder->set_fup_ptw) {
decoder->set_fup_ptw = false;
- decoder->state.type = INTEL_PT_PTW;
+ decoder->state.type |= INTEL_PT_PTW;
decoder->state.flags |= INTEL_PT_FUP_IP;
- decoder->state.from_ip = decoder->ip;
- decoder->state.to_ip = 0;
decoder->state.ptw_payload = decoder->fup_ptw_payload;
- return true;
+ ret = true;
}
if (decoder->set_fup_mwait) {
decoder->set_fup_mwait = false;
- decoder->state.type = INTEL_PT_MWAIT_OP;
- decoder->state.from_ip = decoder->ip;
- decoder->state.to_ip = 0;
+ decoder->state.type |= INTEL_PT_MWAIT_OP;
decoder->state.mwait_payload = decoder->fup_mwait_payload;
ret = true;
}
if (decoder->set_fup_pwre) {
decoder->set_fup_pwre = false;
decoder->state.type |= INTEL_PT_PWR_ENTRY;
- decoder->state.type &= ~INTEL_PT_BRANCH;
- decoder->state.from_ip = decoder->ip;
- decoder->state.to_ip = 0;
decoder->state.pwre_payload = decoder->fup_pwre_payload;
ret = true;
}
if (decoder->set_fup_exstop) {
decoder->set_fup_exstop = false;
decoder->state.type |= INTEL_PT_EX_STOP;
- decoder->state.type &= ~INTEL_PT_BRANCH;
decoder->state.flags |= INTEL_PT_FUP_IP;
- decoder->state.from_ip = decoder->ip;
- decoder->state.to_ip = 0;
ret = true;
}
if (decoder->set_fup_bep) {
decoder->set_fup_bep = false;
decoder->state.type |= INTEL_PT_BLK_ITEMS;
- decoder->state.type &= ~INTEL_PT_BRANCH;
+ ret = true;
+ }
+ if (decoder->overflow) {
+ decoder->overflow = false;
+ if (!ret && !decoder->pge) {
+ if (decoder->hop) {
+ decoder->state.type = 0;
+ decoder->pkt_state = INTEL_PT_STATE_RESAMPLE;
+ }
+ decoder->pge = true;
+ decoder->state.type |= INTEL_PT_BRANCH | INTEL_PT_TRACE_BEGIN;
+ decoder->state.from_ip = 0;
+ decoder->state.to_ip = decoder->ip;
+ return true;
+ }
+ }
+ if (ret) {
decoder->state.from_ip = decoder->ip;
decoder->state.to_ip = 0;
- ret = true;
+ } else {
+ decoder->state.type = type;
}
return ret;
}
intel_pt_clear_tx_flags(decoder);
intel_pt_set_nr(decoder);
decoder->timestamp_insn_cnt = 0;
- decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC;
+ decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
+ decoder->state.from_ip = decoder->ip;
+ decoder->ip = 0;
+ decoder->pge = false;
+ decoder->set_fup_tx_flags = false;
+ decoder->set_fup_ptw = false;
+ decoder->set_fup_mwait = false;
+ decoder->set_fup_pwre = false;
+ decoder->set_fup_exstop = false;
+ decoder->set_fup_bep = false;
decoder->overflow = true;
return -EOVERFLOW;
}
/* Hop mode: Ignore TNT, do not walk code, but get ip from FUPs and TIPs */
static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, int *err)
{
+ *err = 0;
+
/* Leap from PSB to PSB, getting ip from FUP within PSB+ */
if (decoder->leap && !decoder->in_psb && decoder->packet.type != INTEL_PT_PSB) {
*err = intel_pt_scan_for_psb(decoder);
return HOP_IGNORE;
case INTEL_PT_TIP_PGD:
+ decoder->pge = false;
if (!decoder->packet.count) {
intel_pt_set_nr(decoder);
return HOP_IGNORE;
if (!decoder->packet.count)
return HOP_IGNORE;
intel_pt_set_ip(decoder);
- if (intel_pt_fup_event(decoder))
- return HOP_RETURN;
- if (!decoder->branch_enable)
+ if (decoder->set_fup_mwait || decoder->set_fup_pwre)
+ *no_tip = true;
+ if (!decoder->branch_enable || !decoder->pge)
*no_tip = true;
if (*no_tip) {
decoder->state.type = INTEL_PT_INSTRUCTION;
decoder->state.from_ip = decoder->ip;
decoder->state.to_ip = 0;
+ intel_pt_fup_event(decoder);
return HOP_RETURN;
}
+ intel_pt_fup_event(decoder);
+ decoder->state.type |= INTEL_PT_INSTRUCTION | INTEL_PT_BRANCH;
*err = intel_pt_walk_fup_tip(decoder);
- if (!*err)
+ if (!*err && decoder->state.to_ip)
decoder->pkt_state = INTEL_PT_STATE_RESAMPLE;
return HOP_RETURN;
{
struct intel_pt_psb_info data = { .fup = false };
- if (!decoder->branch_enable || !decoder->pge)
+ if (!decoder->branch_enable)
return false;
intel_pt_pkt_lookahead(decoder, intel_pt_psb_lookahead_cb, &data);
if (err)
return err;
next:
+ err = 0;
if (decoder->cyc_threshold) {
if (decoder->sample_cyc && last_packet_type != INTEL_PT_CYC)
decoder->sample_cyc = false;
case INTEL_PT_TIP_PGE: {
decoder->pge = true;
+ decoder->overflow = false;
intel_pt_mtc_cyc_cnt_pge(decoder);
intel_pt_set_nr(decoder);
if (decoder->packet.count == 0) {
break;
}
intel_pt_set_last_ip(decoder);
- if (!decoder->branch_enable) {
+ if (!decoder->branch_enable || !decoder->pge) {
decoder->ip = decoder->last_ip;
if (intel_pt_fup_event(decoder))
return 0;
decoder->set_fup_pwre = false;
decoder->set_fup_exstop = false;
decoder->set_fup_bep = false;
+ decoder->overflow = false;
if (!decoder->branch_enable) {
decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
- decoder->overflow = false;
decoder->state.type = 0; /* Do not have a sample */
return 0;
}
decoder->pkt_state = INTEL_PT_STATE_RESAMPLE;
else
decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
- decoder->overflow = false;
decoder->state.from_ip = 0;
decoder->state.to_ip = decoder->ip;
}
decoder->have_last_ip = true;
- decoder->pkt_state = INTEL_PT_STATE_NO_IP;
+ decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
err = intel_pt_walk_psb(decoder);
if (err)
if (err) {
decoder->state.err = intel_pt_ext_err(err);
- decoder->state.from_ip = decoder->ip;
+ if (err != -EOVERFLOW)
+ decoder->state.from_ip = decoder->ip;
intel_pt_update_sample_time(decoder);
decoder->sample_tot_cyc_cnt = decoder->tot_cyc_cnt;
intel_pt_set_nr(decoder);
ptq->sync_switch = false;
intel_pt_next_tid(pt, ptq);
}
+ ptq->timestamp = state->est_timestamp;
if (pt->synth_opts.errors) {
err = intel_ptq_synth_error(ptq, state);
if (err)
int i, idx = 0;
u64 mask = regs->mask;
+ if ((u64)id >= PERF_SAMPLE_REGS_CACHE_SIZE)
+ return -EINVAL;
+
if (regs->cache_mask & (1ULL << id))
goto out;
struct tep_event *tp_format;
tp_format = trace_event__tp_format_id(evsel->core.attr.config);
- if (!tp_format)
+ if (IS_ERR_OR_NULL(tp_format))
return NULL;
evsel->tp_format = tp_format;
if (cached)
return cached_result;
- if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) > 0)
+ if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) >= 0)
goto done;
ncpu = sysconf(_SC_NPROCESSORS_CONF);
ACPICA_INCLUDE := $(srctree)/../../../drivers/acpi/acpica
CFLAGS += -D_LINUX -I$(KERNEL_INCLUDE) -I$(ACPICA_INCLUDE)
CFLAGS += $(WARNINGS)
+MKDIR = mkdir
ifeq ($(strip $(V)),false)
QUIET=@
$(objdir)%.o: %.c $(KERNEL_INCLUDE)
$(ECHO) " CC " $(subst $(OUTPUT),,$@)
+ $(QUIET) $(MKDIR) -p $(objdir) 2>/dev/null
$(QUIET) $(CC) -c $(CFLAGS) -o $@ $<
all: $(OUTPUT)$(TOOL)
return sum;
}
+__weak noinline struct file *bpf_testmod_return_ptr(int arg)
+{
+ static struct file f = {};
+
+ switch (arg) {
+ case 1: return (void *)EINVAL; /* user addr */
+ case 2: return (void *)0xcafe4a11; /* user addr */
+ case 3: return (void *)-EINVAL; /* canonical, but invalid */
+ case 4: return (void *)(1ull << 60); /* non-canonical and invalid */
+ case 5: return (void *)~(1ull << 30); /* trigger extable */
+ case 6: return &f; /* valid addr */
+ case 7: return (void *)((long)&f | 1); /* kernel tricks */
+ default: return NULL;
+ }
+}
+
noinline ssize_t
bpf_testmod_test_read(struct file *file, struct kobject *kobj,
struct bin_attribute *bin_attr,
.off = off,
.len = len,
};
+ int i = 1;
+
+ while (bpf_testmod_return_ptr(i))
+ i++;
/* This is always true. Use the check to make sure the compiler
* doesn't remove bpf_testmod_loop_test.
static void test_conn(void)
{
- int listen_fd = -1, cli_fd = -1, err;
+ int listen_fd = -1, cli_fd = -1, srv_fd = -1, err;
socklen_t addrlen = sizeof(srv_sa6);
int srv_port;
if (CHECK_FAIL(cli_fd == -1))
goto done;
+ srv_fd = accept(listen_fd, NULL, NULL);
+ if (CHECK_FAIL(srv_fd == -1))
+ goto done;
+
if (CHECK(skel->bss->listen_tp_sport != srv_port ||
skel->bss->req_sk_sport != srv_port,
"Unexpected sk src port",
close(listen_fd);
if (cli_fd != -1)
close(cli_fd);
+ if (srv_fd != -1)
+ close(srv_fd);
}
static void test_syncookie(void)
{
- int listen_fd = -1, cli_fd = -1, err;
+ int listen_fd = -1, cli_fd = -1, srv_fd = -1, err;
socklen_t addrlen = sizeof(srv_sa6);
int srv_port;
if (CHECK_FAIL(cli_fd == -1))
goto done;
+ srv_fd = accept(listen_fd, NULL, NULL);
+ if (CHECK_FAIL(srv_fd == -1))
+ goto done;
+
if (CHECK(skel->bss->listen_tp_sport != srv_port,
"Unexpected tp src port",
"listen_tp_sport:%u expected:%u\n",
close(listen_fd);
if (cli_fd != -1)
close(cli_fd);
+ if (srv_fd != -1)
+ close(srv_fd);
}
struct test {
return 0;
}
+SEC("fexit/bpf_testmod_return_ptr")
+int BPF_PROG(handle_fexit_ret, int arg, struct file *ret)
+{
+ long buf = 0;
+
+ bpf_probe_read_kernel(&buf, 8, ret);
+ bpf_probe_read_kernel(&buf, 8, (char *)ret + 256);
+ *(volatile long long *)ret;
+ *(volatile int *)&ret->f_mode;
+ return 0;
+}
+
__u32 fmod_ret_read_sz = 0;
SEC("fmod_ret/bpf_testmod_test_read")
#define MAX_INSNS BPF_MAXINSNS
#define MAX_TEST_INSNS 1000000
#define MAX_FIXUPS 8
-#define MAX_NR_MAPS 21
+#define MAX_NR_MAPS 22
#define MAX_TEST_RUNS 8
#define POINTER_VALUE 0xcafe4all
#define TEST_DATA_LEN 64
BPF_EXIT_INSN(),
},
.result = ACCEPT,
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R0 leaks addr into mem",
},
{
"Dest pointer in r0 - succeed",
BPF_EXIT_INSN(),
},
.result = ACCEPT,
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R0 leaks addr into mem",
+},
+{
+ "Dest pointer in r0 - succeed, check 2",
+ .insns = {
+ /* r0 = &val */
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_10),
+ /* val = r0; */
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+ /* r5 = &val */
+ BPF_MOV64_REG(BPF_REG_5, BPF_REG_10),
+ /* r0 = atomic_cmpxchg(&val, r0, r5); */
+ BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, BPF_REG_10, BPF_REG_5, -8),
+ /* r1 = *r0 */
+ BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8),
+ /* exit(0); */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R0 leaks addr into mem",
+},
+{
+ "Dest pointer in r0 - succeed, check 3",
+ .insns = {
+ /* r0 = &val */
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_10),
+ /* val = r0; */
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+ /* r5 = &val */
+ BPF_MOV64_REG(BPF_REG_5, BPF_REG_10),
+ /* r0 = atomic_cmpxchg(&val, r0, r5); */
+ BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, BPF_REG_10, BPF_REG_5, -8),
+ /* exit(0); */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = REJECT,
+ .errstr = "invalid size of register fill",
+ .errstr_unpriv = "R0 leaks addr into mem",
+},
+{
+ "Dest pointer in r0 - succeed, check 4",
+ .insns = {
+ /* r0 = &val */
+ BPF_MOV32_REG(BPF_REG_0, BPF_REG_10),
+ /* val = r0; */
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -8),
+ /* r5 = &val */
+ BPF_MOV32_REG(BPF_REG_5, BPF_REG_10),
+ /* r0 = atomic_cmpxchg(&val, r0, r5); */
+ BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, BPF_REG_10, BPF_REG_5, -8),
+ /* r1 = *r10 */
+ BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_10, -8),
+ /* exit(0); */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R10 partial copy of pointer",
+},
+{
+ "Dest pointer in r0 - succeed, check 5",
+ .insns = {
+ /* r0 = &val */
+ BPF_MOV32_REG(BPF_REG_0, BPF_REG_10),
+ /* val = r0; */
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -8),
+ /* r5 = &val */
+ BPF_MOV32_REG(BPF_REG_5, BPF_REG_10),
+ /* r0 = atomic_cmpxchg(&val, r0, r5); */
+ BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, BPF_REG_10, BPF_REG_5, -8),
+ /* r1 = *r0 */
+ BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, -8),
+ /* exit(0); */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = REJECT,
+ .errstr = "R0 invalid mem access",
+ .errstr_unpriv = "R10 partial copy of pointer",
},
+{
+ "atomic dw/fetch and address leakage of (map ptr & -1) via stack slot",
+ .insns = {
+ BPF_LD_IMM64(BPF_REG_1, -1),
+ BPF_LD_MAP_FD(BPF_REG_8, 0),
+ BPF_LD_MAP_FD(BPF_REG_9, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_9, 0),
+ BPF_ATOMIC_OP(BPF_DW, BPF_AND | BPF_FETCH, BPF_REG_2, BPF_REG_1, 0),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_2, 0),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_9, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 2, 4 },
+ .result = ACCEPT,
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "leaking pointer from stack off -8",
+},
+{
+ "atomic dw/fetch and address leakage of (map ptr & -1) via returned value",
+ .insns = {
+ BPF_LD_IMM64(BPF_REG_1, -1),
+ BPF_LD_MAP_FD(BPF_REG_8, 0),
+ BPF_LD_MAP_FD(BPF_REG_9, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_9, 0),
+ BPF_ATOMIC_OP(BPF_DW, BPF_AND | BPF_FETCH, BPF_REG_2, BPF_REG_1, 0),
+ BPF_MOV64_REG(BPF_REG_9, BPF_REG_1),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_9, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 2, 4 },
+ .result = ACCEPT,
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "leaking pointer from stack off -8",
+},
+{
+ "atomic w/fetch and address leakage of (map ptr & -1) via stack slot",
+ .insns = {
+ BPF_LD_IMM64(BPF_REG_1, -1),
+ BPF_LD_MAP_FD(BPF_REG_8, 0),
+ BPF_LD_MAP_FD(BPF_REG_9, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_9, 0),
+ BPF_ATOMIC_OP(BPF_W, BPF_AND | BPF_FETCH, BPF_REG_2, BPF_REG_1, 0),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_2, 0),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_9, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 2, 4 },
+ .result = REJECT,
+ .errstr = "invalid size of register fill",
+},
+{
+ "atomic w/fetch and address leakage of (map ptr & -1) via returned value",
+ .insns = {
+ BPF_LD_IMM64(BPF_REG_1, -1),
+ BPF_LD_MAP_FD(BPF_REG_8, 0),
+ BPF_LD_MAP_FD(BPF_REG_9, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_9, 0),
+ BPF_ATOMIC_OP(BPF_W, BPF_AND | BPF_FETCH, BPF_REG_2, BPF_REG_1, 0),
+ BPF_MOV64_REG(BPF_REG_9, BPF_REG_1),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_8),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_9, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 2, 4 },
+ .result = REJECT,
+ .errstr = "invalid size of register fill",
+},
#define __ATOMIC_FETCH_OP_TEST(src_reg, dst_reg, operand1, op, operand2, expect) \
{ \
"atomic fetch " #op ", src=" #dst_reg " dst=" #dst_reg, \
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
},
{
+ "precision tracking for u32 spill/fill",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_1),
+ BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
+ BPF_MOV32_IMM(BPF_REG_6, 32),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_MOV32_IMM(BPF_REG_6, 4),
+ /* Additional insns to introduce a pruning point. */
+ BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_MOV64_IMM(BPF_REG_3, 0),
+ /* u32 spill/fill */
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_6, -8),
+ BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_10, -8),
+ /* out-of-bound map value access for r6=32 */
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
+ 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, 2),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_8),
+ BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_8b = { 15 },
+ .result = REJECT,
+ .errstr = "R0 min value is outside of the allowed memory range",
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
+ "precision tracking for u32 spills, u64 fill",
+ .insns = {
+ BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+ BPF_MOV32_IMM(BPF_REG_7, 0xffffffff),
+ /* Additional insns to introduce a pruning point. */
+ BPF_MOV64_IMM(BPF_REG_3, 1),
+ BPF_MOV64_IMM(BPF_REG_3, 1),
+ BPF_MOV64_IMM(BPF_REG_3, 1),
+ BPF_MOV64_IMM(BPF_REG_3, 1),
+ BPF_EMIT_CALL(BPF_FUNC_get_prandom_u32),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_MOV64_IMM(BPF_REG_3, 1),
+ BPF_ALU32_IMM(BPF_DIV, BPF_REG_3, 0),
+ /* u32 spills, u64 fill */
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_6, -4),
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, -8),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_8, BPF_REG_10, -8),
+ /* if r8 != X goto pc+1 r8 known in fallthrough branch */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_8, 0xffffffff, 1),
+ BPF_MOV64_IMM(BPF_REG_3, 1),
+ /* if r8 == X goto pc+1 condition always true on first
+ * traversal, so starts backtracking to mark r8 as requiring
+ * precision. r7 marked as needing precision. r6 not marked
+ * since it's not tracked.
+ */
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_8, 0xffffffff, 1),
+ /* fails if r8 correctly marked unknown after fill. */
+ BPF_ALU32_IMM(BPF_DIV, BPF_REG_3, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = REJECT,
+ .errstr = "div by zero",
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+},
+{
"allocated_stack",
.insns = {
BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1),
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
},
{
+ "Spill u32 const scalars. Refill as u64. Offset to skb->data",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct __sk_buff, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct __sk_buff, data_end)),
+ /* r6 = 0 */
+ BPF_MOV32_IMM(BPF_REG_6, 0),
+ /* r7 = 20 */
+ BPF_MOV32_IMM(BPF_REG_7, 20),
+ /* *(u32 *)(r10 -4) = r6 */
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_6, -4),
+ /* *(u32 *)(r10 -8) = r7 */
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7, -8),
+ /* r4 = *(u64 *)(r10 -8) */
+ BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_10, -8),
+ /* r0 = r2 */
+ BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ /* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=65535 */
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4),
+ /* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv,umax=65535 */
+ BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+ /* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv20 */
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = REJECT,
+ .errstr = "invalid access to packet",
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+},
+{
"Spill a u32 const scalar. Refill as u16 from fp-6. Offset to skb->data",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
.errstr_unpriv = "R0 pointer -= pointer prohibited",
},
{
+ "map access: trying to leak tained dst reg",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_MOV32_IMM(BPF_REG_1, 0xFFFFFFFF),
+ BPF_MOV32_REG(BPF_REG_1, BPF_REG_1),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_2, BPF_REG_1),
+ BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_2, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_array_48b = { 4 },
+ .result = REJECT,
+ .errstr = "math between map_value pointer and 4294967295 is not allowed",
+},
+{
"32bit pkt_ptr -= scalar",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_8, BPF_REG_1,
.prog_type = BPF_PROG_TYPE_XDP,
},
{
- "XDP pkt read, pkt_data' > pkt_end, good access",
+ "XDP pkt read, pkt_data' > pkt_end, corner case, good access",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
+ "XDP pkt read, pkt_data' > pkt_end, corner case +1, good access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct xdp_md, data_end)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
+ BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+ "XDP pkt read, pkt_data' > pkt_end, corner case -1, bad access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct xdp_md, data_end)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+ BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R1 offset is outside of the packet",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
"XDP pkt read, pkt_end > pkt_data', good access",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
- "XDP pkt read, pkt_end > pkt_data', bad access 1",
+ "XDP pkt read, pkt_end > pkt_data', corner case -1, bad access",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
offsetof(struct xdp_md, data_end)),
BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
- BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
BPF_JMP_IMM(BPF_JA, 0, 0, 1),
- BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
+ "XDP pkt read, pkt_end > pkt_data', corner case, good access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct xdp_md, data_end)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+ BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+ "XDP pkt read, pkt_end > pkt_data', corner case +1, good access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct xdp_md, data_end)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+ BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
"XDP pkt read, pkt_data' < pkt_end, good access",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
- "XDP pkt read, pkt_data' < pkt_end, bad access 1",
+ "XDP pkt read, pkt_data' < pkt_end, corner case -1, bad access",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
offsetof(struct xdp_md, data_end)),
BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
- BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
BPF_JMP_IMM(BPF_JA, 0, 0, 1),
- BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
- "XDP pkt read, pkt_end < pkt_data', good access",
+ "XDP pkt read, pkt_data' < pkt_end, corner case, good access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct xdp_md, data_end)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+ BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+ "XDP pkt read, pkt_data' < pkt_end, corner case +1, good access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct xdp_md, data_end)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+ BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+ "XDP pkt read, pkt_end < pkt_data', corner case, good access",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
+ "XDP pkt read, pkt_end < pkt_data', corner case +1, good access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct xdp_md, data_end)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
+ BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+ "XDP pkt read, pkt_end < pkt_data', corner case -1, bad access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct xdp_md, data_end)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+ BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R1 offset is outside of the packet",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
"XDP pkt read, pkt_data' >= pkt_end, good access",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
- "XDP pkt read, pkt_data' >= pkt_end, bad access 1",
+ "XDP pkt read, pkt_data' >= pkt_end, corner case -1, bad access",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
offsetof(struct xdp_md, data_end)),
BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
- BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
- BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
- "XDP pkt read, pkt_end >= pkt_data', good access",
+ "XDP pkt read, pkt_data' >= pkt_end, corner case, good access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct xdp_md, data_end)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+ BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+ "XDP pkt read, pkt_data' >= pkt_end, corner case +1, good access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct xdp_md, data_end)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+ BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+ "XDP pkt read, pkt_end >= pkt_data', corner case, good access",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
- "XDP pkt read, pkt_data' <= pkt_end, good access",
+ "XDP pkt read, pkt_end >= pkt_data', corner case +1, good access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct xdp_md, data_end)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
+ BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+ "XDP pkt read, pkt_end >= pkt_data', corner case -1, bad access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct xdp_md, data_end)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+ BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R1 offset is outside of the packet",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+ "XDP pkt read, pkt_data' <= pkt_end, corner case, good access",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
+ "XDP pkt read, pkt_data' <= pkt_end, corner case +1, good access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct xdp_md, data_end)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
+ BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+ "XDP pkt read, pkt_data' <= pkt_end, corner case -1, bad access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct xdp_md, data_end)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+ BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R1 offset is outside of the packet",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
"XDP pkt read, pkt_end <= pkt_data', good access",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
- "XDP pkt read, pkt_end <= pkt_data', bad access 1",
+ "XDP pkt read, pkt_end <= pkt_data', corner case -1, bad access",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
offsetof(struct xdp_md, data_end)),
BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
- BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
- BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
- "XDP pkt read, pkt_meta' > pkt_data, good access",
+ "XDP pkt read, pkt_end <= pkt_data', corner case, good access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct xdp_md, data_end)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+ BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+ "XDP pkt read, pkt_end <= pkt_data', corner case +1, good access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ offsetof(struct xdp_md, data_end)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+ BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+ "XDP pkt read, pkt_meta' > pkt_data, corner case, good access",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
offsetof(struct xdp_md, data_meta)),
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
+ "XDP pkt read, pkt_meta' > pkt_data, corner case +1, good access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct xdp_md, data_meta)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
+ BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+ "XDP pkt read, pkt_meta' > pkt_data, corner case -1, bad access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct xdp_md, data_meta)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+ BPF_JMP_REG(BPF_JGT, BPF_REG_1, BPF_REG_3, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R1 offset is outside of the packet",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
"XDP pkt read, pkt_data > pkt_meta', good access",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
- "XDP pkt read, pkt_data > pkt_meta', bad access 1",
+ "XDP pkt read, pkt_data > pkt_meta', corner case -1, bad access",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
offsetof(struct xdp_md, data_meta)),
BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
- BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
BPF_JMP_IMM(BPF_JA, 0, 0, 1),
- BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
+ "XDP pkt read, pkt_data > pkt_meta', corner case, good access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct xdp_md, data_meta)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+ BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+ "XDP pkt read, pkt_data > pkt_meta', corner case +1, good access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct xdp_md, data_meta)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+ BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_1, 1),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
"XDP pkt read, pkt_meta' < pkt_data, good access",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
- "XDP pkt read, pkt_meta' < pkt_data, bad access 1",
+ "XDP pkt read, pkt_meta' < pkt_data, corner case -1, bad access",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
offsetof(struct xdp_md, data_meta)),
BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
- BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
BPF_JMP_IMM(BPF_JA, 0, 0, 1),
- BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
- "XDP pkt read, pkt_data < pkt_meta', good access",
+ "XDP pkt read, pkt_meta' < pkt_data, corner case, good access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct xdp_md, data_meta)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+ BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+ "XDP pkt read, pkt_meta' < pkt_data, corner case +1, good access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct xdp_md, data_meta)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+ BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 1),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+ "XDP pkt read, pkt_data < pkt_meta', corner case, good access",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
offsetof(struct xdp_md, data_meta)),
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
+ "XDP pkt read, pkt_data < pkt_meta', corner case +1, good access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct xdp_md, data_meta)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
+ BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+ "XDP pkt read, pkt_data < pkt_meta', corner case -1, bad access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct xdp_md, data_meta)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+ BPF_JMP_REG(BPF_JLT, BPF_REG_3, BPF_REG_1, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R1 offset is outside of the packet",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
"XDP pkt read, pkt_meta' >= pkt_data, good access",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
- "XDP pkt read, pkt_meta' >= pkt_data, bad access 1",
+ "XDP pkt read, pkt_meta' >= pkt_data, corner case -1, bad access",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
offsetof(struct xdp_md, data_meta)),
BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
- BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
- BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
- "XDP pkt read, pkt_data >= pkt_meta', good access",
+ "XDP pkt read, pkt_meta' >= pkt_data, corner case, good access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct xdp_md, data_meta)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+ BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+ "XDP pkt read, pkt_meta' >= pkt_data, corner case +1, good access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct xdp_md, data_meta)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+ BPF_JMP_REG(BPF_JGE, BPF_REG_1, BPF_REG_3, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+ "XDP pkt read, pkt_data >= pkt_meta', corner case, good access",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
offsetof(struct xdp_md, data_meta)),
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
- "XDP pkt read, pkt_meta' <= pkt_data, good access",
+ "XDP pkt read, pkt_data >= pkt_meta', corner case +1, good access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct xdp_md, data_meta)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
+ BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+ "XDP pkt read, pkt_data >= pkt_meta', corner case -1, bad access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct xdp_md, data_meta)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+ BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 1),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R1 offset is outside of the packet",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+ "XDP pkt read, pkt_meta' <= pkt_data, corner case, good access",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
offsetof(struct xdp_md, data_meta)),
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
+ "XDP pkt read, pkt_meta' <= pkt_data, corner case +1, good access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct xdp_md, data_meta)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 9),
+ BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -9),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+ "XDP pkt read, pkt_meta' <= pkt_data, corner case -1, bad access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct xdp_md, data_meta)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+ BPF_JMP_REG(BPF_JLE, BPF_REG_1, BPF_REG_3, 1),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R1 offset is outside of the packet",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
"XDP pkt read, pkt_data <= pkt_meta', good access",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
- "XDP pkt read, pkt_data <= pkt_meta', bad access 1",
+ "XDP pkt read, pkt_data <= pkt_meta', corner case -1, bad access",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
offsetof(struct xdp_md, data_meta)),
BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
- BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 6),
BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
- BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -6),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_XDP,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
+{
+ "XDP pkt read, pkt_data <= pkt_meta', corner case, good access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct xdp_md, data_meta)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 7),
+ BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -7),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
+{
+ "XDP pkt read, pkt_data <= pkt_meta', corner case +1, good access",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct xdp_md, data_meta)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, offsetof(struct xdp_md, data)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+ BPF_JMP_REG(BPF_JLE, BPF_REG_3, BPF_REG_1, 1),
+ BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_XDP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
+},
--- /dev/null
+# SPDX-License-Identifier: GPL-2.0-only
+huge_count_read_write
# SPDX-License-Identifier: GPL-2.0
# Makefile for damon selftests
-TEST_FILES = _chk_dependency.sh
-TEST_PROGS = debugfs_attrs.sh
+TEST_GEN_FILES += huge_count_read_write
+
+TEST_FILES = _chk_dependency.sh _debugfs_common.sh
+TEST_PROGS = debugfs_attrs.sh debugfs_schemes.sh debugfs_target_ids.sh
+TEST_PROGS += debugfs_empty_targets.sh debugfs_huge_count_read_write.sh
include ../lib.mk
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+test_write_result() {
+ file=$1
+ content=$2
+ orig_content=$3
+ expect_reason=$4
+ expected=$5
+
+ echo "$content" > "$file"
+ if [ $? -ne "$expected" ]
+ then
+ echo "writing $content to $file doesn't return $expected"
+ echo "expected because: $expect_reason"
+ echo "$orig_content" > "$file"
+ exit 1
+ fi
+}
+
+test_write_succ() {
+ test_write_result "$1" "$2" "$3" "$4" 0
+}
+
+test_write_fail() {
+ test_write_result "$1" "$2" "$3" "$4" 1
+}
+
+test_content() {
+ file=$1
+ orig_content=$2
+ expected=$3
+ expect_reason=$4
+
+ content=$(cat "$file")
+ if [ "$content" != "$expected" ]
+ then
+ echo "reading $file expected $expected but $content"
+ echo "expected because: $expect_reason"
+ echo "$orig_content" > "$file"
+ exit 1
+ fi
+}
+
+source ./_chk_dependency.sh
+
+damon_onoff="$DBGFS/monitor_on"
+if [ $(cat "$damon_onoff") = "on" ]
+then
+ echo "monitoring is on"
+ exit $ksft_skip
+fi
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
-test_write_result() {
- file=$1
- content=$2
- orig_content=$3
- expect_reason=$4
- expected=$5
-
- echo "$content" > "$file"
- if [ $? -ne "$expected" ]
- then
- echo "writing $content to $file doesn't return $expected"
- echo "expected because: $expect_reason"
- echo "$orig_content" > "$file"
- exit 1
- fi
-}
-
-test_write_succ() {
- test_write_result "$1" "$2" "$3" "$4" 0
-}
-
-test_write_fail() {
- test_write_result "$1" "$2" "$3" "$4" 1
-}
-
-test_content() {
- file=$1
- orig_content=$2
- expected=$3
- expect_reason=$4
-
- content=$(cat "$file")
- if [ "$content" != "$expected" ]
- then
- echo "reading $file expected $expected but $content"
- echo "expected because: $expect_reason"
- echo "$orig_content" > "$file"
- exit 1
- fi
-}
-
-source ./_chk_dependency.sh
+source _debugfs_common.sh
# Test attrs file
# ===============
"min_nr_regions > max_nr_regions"
test_content "$file" "$orig_content" "1 2 3 4 5" "successfully written"
echo "$orig_content" > "$file"
-
-# Test schemes file
-# =================
-
-file="$DBGFS/schemes"
-orig_content=$(cat "$file")
-
-test_write_succ "$file" "1 2 3 4 5 6 4 0 0 0 1 2 3 1 100 3 2 1" \
- "$orig_content" "valid input"
-test_write_fail "$file" "1 2
-3 4 5 6 3 0 0 0 1 2 3 1 100 3 2 1" "$orig_content" "multi lines"
-test_write_succ "$file" "" "$orig_content" "disabling"
-echo "$orig_content" > "$file"
-
-# Test target_ids file
-# ====================
-
-file="$DBGFS/target_ids"
-orig_content=$(cat "$file")
-
-test_write_succ "$file" "1 2 3 4" "$orig_content" "valid input"
-test_write_succ "$file" "1 2 abc 4" "$orig_content" "still valid input"
-test_content "$file" "$orig_content" "1 2" "non-integer was there"
-test_write_succ "$file" "abc 2 3" "$orig_content" "the file allows wrong input"
-test_content "$file" "$orig_content" "" "wrong input written"
-test_write_succ "$file" "" "$orig_content" "empty input"
-test_content "$file" "$orig_content" "" "empty input written"
-echo "$orig_content" > "$file"
-
-echo "PASS"
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source _debugfs_common.sh
+
+# Test empty targets case
+# =======================
+
+orig_target_ids=$(cat "$DBGFS/target_ids")
+echo "" > "$DBGFS/target_ids"
+orig_monitor_on=$(cat "$DBGFS/monitor_on")
+test_write_fail "$DBGFS/monitor_on" "on" "orig_monitor_on" "empty target ids"
+echo "$orig_target_ids" > "$DBGFS/target_ids"
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source _debugfs_common.sh
+
+# Test huge count read write
+# ==========================
+
+dmesg -C
+
+for file in "$DBGFS/"*
+do
+ ./huge_count_read_write "$file"
+done
+
+if dmesg | grep -q WARNING
+then
+ dmesg
+ exit 1
+else
+ exit 0
+fi
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source _debugfs_common.sh
+
+# Test schemes file
+# =================
+
+file="$DBGFS/schemes"
+orig_content=$(cat "$file")
+
+test_write_succ "$file" "1 2 3 4 5 6 4 0 0 0 1 2 3 1 100 3 2 1" \
+ "$orig_content" "valid input"
+test_write_fail "$file" "1 2
+3 4 5 6 3 0 0 0 1 2 3 1 100 3 2 1" "$orig_content" "multi lines"
+test_write_succ "$file" "" "$orig_content" "disabling"
+test_write_fail "$file" "2 1 2 1 10 1 3 10 1 1 1 1 1 1 1 1 2 3" \
+ "$orig_content" "wrong condition ranges"
+echo "$orig_content" > "$file"
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source _debugfs_common.sh
+
+# Test target_ids file
+# ====================
+
+file="$DBGFS/target_ids"
+orig_content=$(cat "$file")
+
+test_write_succ "$file" "1 2 3 4" "$orig_content" "valid input"
+test_write_succ "$file" "1 2 abc 4" "$orig_content" "still valid input"
+test_content "$file" "$orig_content" "1 2" "non-integer was there"
+test_write_succ "$file" "abc 2 3" "$orig_content" "the file allows wrong input"
+test_content "$file" "$orig_content" "" "wrong input written"
+test_write_succ "$file" "" "$orig_content" "empty input"
+test_content "$file" "$orig_content" "" "empty input written"
+echo "$orig_content" > "$file"
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Author: SeongJae Park <sj@kernel.org>
+ */
+
+#include <fcntl.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdio.h>
+
+void write_read_with_huge_count(char *file)
+{
+ int filedesc = open(file, O_RDWR);
+ char buf[25];
+ int ret;
+
+ printf("%s %s\n", __func__, file);
+ if (filedesc < 0) {
+ fprintf(stderr, "failed opening %s\n", file);
+ exit(1);
+ }
+
+ write(filedesc, "", 0xfffffffful);
+ perror("after write: ");
+ ret = read(filedesc, buf, 0xfffffffful);
+ perror("after read: ");
+ close(filedesc);
+}
+
+int main(int argc, char *argv[])
+{
+ if (argc != 2) {
+ fprintf(stderr, "Usage: %s <file>\n", argv[0]);
+ exit(1);
+ }
+ write_read_with_huge_count(argv[1]);
+
+ return 0;
+}
ip link set $h1.10 address $h1_10_mac
}
+rif_mac_profile_consolidation_test()
+{
+ local count=$1; shift
+ local h1_20_mac
+
+ RET=0
+
+ if [[ $count -eq 1 ]]; then
+ return
+ fi
+
+ h1_20_mac=$(mac_get $h1.20)
+
+ # Set the MAC of $h1.20 to that of $h1.10 and confirm that they are
+ # using the same MAC profile.
+ ip link set $h1.20 address 00:11:11:11:11:11
+ check_err $?
+
+ occ=$(devlink -j resource show $DEVLINK_DEV \
+ | jq '.[][][] | select(.name=="rif_mac_profiles") |.["occ"]')
+
+ [[ $occ -eq $((count - 1)) ]]
+ check_err $? "MAC profile occupancy did not decrease"
+
+ log_test "RIF MAC profile consolidation"
+
+ ip link set $h1.20 address $h1_20_mac
+}
+
rif_mac_profile_shared_replacement_test()
{
local count=$1; shift
create_max_rif_mac_profiles $count
rif_mac_profile_replacement_test
+ rif_mac_profile_consolidation_test $count
rif_mac_profile_shared_replacement_test $count
}
/x86_64/svm_int_ctl_test
/x86_64/sync_regs_test
/x86_64/tsc_msrs_test
+/x86_64/userspace_io_test
/x86_64/userspace_msr_exit_test
/x86_64/vmx_apic_access_test
/x86_64/vmx_close_while_nested_test
TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test
TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test
TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
+TEST_GEN_PROGS_x86_64 += x86_64/userspace_io_test
TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test
#endif
+#if defined(__x86_64__)
+unsigned long vm_compute_max_gfn(struct kvm_vm *vm);
+#else
+static inline unsigned long vm_compute_max_gfn(struct kvm_vm *vm)
+{
+ return ((1ULL << vm->pa_bits) >> vm->page_shift) - 1;
+}
+#endif
+
#define MIN_PAGE_SIZE (1U << MIN_PAGE_SHIFT)
#define PTES_PER_MIN_PAGE ptes_per_page(MIN_PAGE_SIZE)
(1ULL << (vm->va_bits - 1)) >> vm->page_shift);
/* Limit physical addresses to PA-bits. */
- vm->max_gfn = ((1ULL << vm->pa_bits) >> vm->page_shift) - 1;
+ vm->max_gfn = vm_compute_max_gfn(vm);
/* Allocate and setup memory for guest. */
vm->vpages_mapped = sparsebit_alloc();
return cpuid;
}
+
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx 0x68747541
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx 0x444d4163
+#define X86EMUL_CPUID_VENDOR_AuthenticAMD_edx 0x69746e65
+
+static inline unsigned x86_family(unsigned int eax)
+{
+ unsigned int x86;
+
+ x86 = (eax >> 8) & 0xf;
+
+ if (x86 == 0xf)
+ x86 += (eax >> 20) & 0xff;
+
+ return x86;
+}
+
+unsigned long vm_compute_max_gfn(struct kvm_vm *vm)
+{
+ const unsigned long num_ht_pages = 12 << (30 - vm->page_shift); /* 12 GiB */
+ unsigned long ht_gfn, max_gfn, max_pfn;
+ uint32_t eax, ebx, ecx, edx, max_ext_leaf;
+
+ max_gfn = (1ULL << (vm->pa_bits - vm->page_shift)) - 1;
+
+ /* Avoid reserved HyperTransport region on AMD processors. */
+ eax = ecx = 0;
+ cpuid(&eax, &ebx, &ecx, &edx);
+ if (ebx != X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx ||
+ ecx != X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx ||
+ edx != X86EMUL_CPUID_VENDOR_AuthenticAMD_edx)
+ return max_gfn;
+
+ /* On parts with <40 physical address bits, the area is fully hidden */
+ if (vm->pa_bits < 40)
+ return max_gfn;
+
+ /* Before family 17h, the HyperTransport area is just below 1T. */
+ ht_gfn = (1 << 28) - num_ht_pages;
+ eax = 1;
+ cpuid(&eax, &ebx, &ecx, &edx);
+ if (x86_family(eax) < 0x17)
+ goto done;
+
+ /*
+ * Otherwise it's at the top of the physical address space, possibly
+ * reduced due to SME by bits 11:6 of CPUID[0x8000001f].EBX. Use
+ * the old conservative value if MAXPHYADDR is not enumerated.
+ */
+ eax = 0x80000000;
+ cpuid(&eax, &ebx, &ecx, &edx);
+ max_ext_leaf = eax;
+ if (max_ext_leaf < 0x80000008)
+ goto done;
+
+ eax = 0x80000008;
+ cpuid(&eax, &ebx, &ecx, &edx);
+ max_pfn = (1ULL << ((eax & 0xff) - vm->page_shift)) - 1;
+ if (max_ext_leaf >= 0x8000001f) {
+ eax = 0x8000001f;
+ cpuid(&eax, &ebx, &ecx, &edx);
+ max_pfn >>= (ebx >> 6) & 0x3f;
+ }
+
+ ht_gfn = max_pfn - num_ht_pages;
+done:
+ return min(max_gfn, ht_gfn - 1);
+}
vmcb->control.int_ctl &= ~V_INTR_MASKING_MASK;
/* No intercepts for real and virtual interrupts */
- vmcb->control.intercept &= ~(1ULL << INTERCEPT_INTR | INTERCEPT_VINTR);
+ vmcb->control.intercept &= ~(BIT(INTERCEPT_INTR) | BIT(INTERCEPT_VINTR));
/* Make a virtual interrupt VINTR_IRQ_NUMBER pending */
vmcb->control.int_ctl |= V_IRQ_MASK | (0x1 << V_INTR_PRIO_SHIFT);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+
+#include "kvm_util.h"
+#include "processor.h"
+
+#define VCPU_ID 1
+
+static void guest_ins_port80(uint8_t *buffer, unsigned int count)
+{
+ unsigned long end;
+
+ if (count == 2)
+ end = (unsigned long)buffer + 1;
+ else
+ end = (unsigned long)buffer + 8192;
+
+ asm volatile("cld; rep; insb" : "+D"(buffer), "+c"(count) : "d"(0x80) : "memory");
+ GUEST_ASSERT_1(count == 0, count);
+ GUEST_ASSERT_2((unsigned long)buffer == end, buffer, end);
+}
+
+static void guest_code(void)
+{
+ uint8_t buffer[8192];
+ int i;
+
+ /*
+ * Special case tests. main() will adjust RCX 2 => 1 and 3 => 8192 to
+ * test that KVM doesn't explode when userspace modifies the "count" on
+ * a userspace I/O exit. KVM isn't required to play nice with the I/O
+ * itself as KVM doesn't support manipulating the count, it just needs
+ * to not explode or overflow a buffer.
+ */
+ guest_ins_port80(buffer, 2);
+ guest_ins_port80(buffer, 3);
+
+ /* Verify KVM fills the buffer correctly when not stuffing RCX. */
+ memset(buffer, 0, sizeof(buffer));
+ guest_ins_port80(buffer, 8192);
+ for (i = 0; i < 8192; i++)
+ GUEST_ASSERT_2(buffer[i] == 0xaa, i, buffer[i]);
+
+ GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+ struct kvm_regs regs;
+ struct kvm_run *run;
+ struct kvm_vm *vm;
+ struct ucall uc;
+ int rc;
+
+ /* Tell stdout not to buffer its content */
+ setbuf(stdout, NULL);
+
+ /* Create VM */
+ vm = vm_create_default(VCPU_ID, 0, guest_code);
+ run = vcpu_state(vm, VCPU_ID);
+
+ memset(®s, 0, sizeof(regs));
+
+ while (1) {
+ rc = _vcpu_run(vm, VCPU_ID);
+
+ TEST_ASSERT(rc == 0, "vcpu_run failed: %d\n", rc);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Unexpected exit reason: %u (%s),\n",
+ run->exit_reason,
+ exit_reason_str(run->exit_reason));
+
+ if (get_ucall(vm, VCPU_ID, &uc))
+ break;
+
+ TEST_ASSERT(run->io.port == 0x80,
+ "Expected I/O at port 0x80, got port 0x%x\n", run->io.port);
+
+ /*
+ * Modify the rep string count in RCX: 2 => 1 and 3 => 8192.
+ * Note, this abuses KVM's batching of rep string I/O to avoid
+ * getting stuck in an infinite loop. That behavior isn't in
+ * scope from a testing perspective as it's not ABI in any way,
+ * i.e. it really is abusing internal KVM knowledge.
+ */
+ vcpu_regs_get(vm, VCPU_ID, ®s);
+ if (regs.rcx == 2)
+ regs.rcx = 1;
+ if (regs.rcx == 3)
+ regs.rcx = 8192;
+ memset((void *)run + run->io.data_offset, 0xaa, 4096);
+ vcpu_regs_set(vm, VCPU_ID, ®s);
+ }
+
+ switch (uc.cmd) {
+ case UCALL_DONE:
+ break;
+ case UCALL_ABORT:
+ TEST_FAIL("%s at %s:%ld : argN+1 = 0x%lx, argN+2 = 0x%lx",
+ (const char *)uc.args[0], __FILE__, uc.args[1],
+ uc.args[2], uc.args[3]);
+ default:
+ TEST_FAIL("Unknown ucall %lu", uc.cmd);
+ }
+
+ kvm_vm_free(vm);
+ return 0;
+}
ret = _vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, PMU_CAP_LBR_FMT);
TEST_ASSERT(ret == 0, "Bad PERF_CAPABILITIES didn't fail.");
- /* testcase 4, set capabilities when we don't have PDCM bit */
- entry_1_0->ecx &= ~X86_FEATURE_PDCM;
- vcpu_set_cpuid(vm, VCPU_ID, cpuid);
- ret = _vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, host_cap.capabilities);
- TEST_ASSERT(ret == 0, "Bad PERF_CAPABILITIES didn't fail.");
-
- /* testcase 5, set capabilities when we don't have PMU version bits */
- entry_1_0->ecx |= X86_FEATURE_PDCM;
- eax.split.version_id = 0;
- entry_1_0->ecx = eax.full;
- vcpu_set_cpuid(vm, VCPU_ID, cpuid);
- ret = _vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, PMU_CAP_FW_WRITES);
- TEST_ASSERT(ret == 0, "Bad PERF_CAPABILITIES didn't fail.");
-
- vcpu_set_msr(vm, 0, MSR_IA32_PERF_CAPABILITIES, 0);
- ASSERT_EQ(vcpu_get_msr(vm, VCPU_ID, MSR_IA32_PERF_CAPABILITIES), 0);
-
kvm_vm_free(vm);
}
ip netns del ${NSC} >/dev/null 2>&1
}
+cleanup_vrf_dup()
+{
+ ip link del ${NSA_DEV2} >/dev/null 2>&1
+ ip netns pids ${NSC} | xargs kill 2>/dev/null
+ ip netns del ${NSC} >/dev/null 2>&1
+}
+
+setup_vrf_dup()
+{
+ # some VRF tests use ns-C which has the same config as
+ # ns-B but for a device NOT in the VRF
+ create_ns ${NSC} "-" "-"
+ connect_ns ${NSA} ${NSA_DEV2} ${NSA_IP}/24 ${NSA_IP6}/64 \
+ ${NSC} ${NSC_DEV} ${NSB_IP}/24 ${NSB_IP6}/64
+}
+
setup()
{
local with_vrf=${1}
ip -netns ${NSB} ro add ${VRF_IP}/32 via ${NSA_IP} dev ${NSB_DEV}
ip -netns ${NSB} -6 ro add ${VRF_IP6}/128 via ${NSA_IP6} dev ${NSB_DEV}
-
- # some VRF tests use ns-C which has the same config as
- # ns-B but for a device NOT in the VRF
- create_ns ${NSC} "-" "-"
- connect_ns ${NSA} ${NSA_DEV2} ${NSA_IP}/24 ${NSA_IP6}/64 \
- ${NSC} ${NSC_DEV} ${NSB_IP}/24 ${NSB_IP6}/64
else
ip -netns ${NSA} ro add ${NSB_LO_IP}/32 via ${NSB_IP} dev ${NSA_DEV}
ip -netns ${NSA} ro add ${NSB_LO_IP6}/128 via ${NSB_IP6} dev ${NSA_DEV}
log_test_addr ${a} $? 1 "Global server, local connection"
# run MD5 tests
+ setup_vrf_dup
ipv4_tcp_md5
+ cleanup_vrf_dup
#
# enable VRF global server
for a in ${NSA_IP} ${VRF_IP}
do
log_start
+ show_hint "Socket not bound to VRF, but address is in VRF"
run_cmd nettest -s -R -P icmp -l ${a} -b
- log_test_addr ${a} $? 0 "Raw socket bind to local address"
+ log_test_addr ${a} $? 1 "Raw socket bind to local address"
log_start
run_cmd nettest -s -R -P icmp -l ${a} -I ${NSA_DEV} -b
log_start
show_hint "Fails since VRF device does not support linklocal or multicast"
run_cmd ${ping6} -c1 -w1 ${a}
- log_test_addr ${a} $? 2 "ping out, VRF bind"
+ log_test_addr ${a} $? 1 "ping out, VRF bind"
done
for a in ${NSB_IP6} ${NSB_LO_IP6} ${NSB_LINKIP6}%${NSA_DEV} ${MCAST}%${NSA_DEV}
log_test_addr ${a} $? 1 "Global server, local connection"
# run MD5 tests
+ setup_vrf_dup
ipv6_tcp_md5
+ cleanup_vrf_dup
#
# enable VRF global server
run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b
log_test_addr ${a} $? 0 "TCP socket bind to local address after device bind"
+ # Sadly, the kernel allows binding a socket to a device and then
+ # binding to an address not on the device. So this test passes
+ # when it really should not
a=${NSA_LO_IP6}
log_start
- show_hint "Should fail with 'Cannot assign requested address'"
+ show_hint "Tecnically should fail since address is not on device but kernel allows"
run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b
- log_test_addr ${a} $? 1 "TCP socket bind to out of scope local address"
+ log_test_addr ${a} $? 0 "TCP socket bind to out of scope local address"
}
ipv6_addr_bind_vrf()
run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b
log_test_addr ${a} $? 0 "TCP socket bind to local address with device bind"
+ # Sadly, the kernel allows binding a socket to a device and then
+ # binding to an address not on the device. The only restriction
+ # is that the address is valid in the L3 domain. So this test
+ # passes when it really should not
a=${VRF_IP6}
log_start
+ show_hint "Tecnically should fail since address is not on device but kernel allows"
run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b
- log_test_addr ${a} $? 1 "TCP socket bind to VRF address with device bind"
+ log_test_addr ${a} $? 0 "TCP socket bind to VRF address with device bind"
a=${NSA_LO_IP6}
log_start
printf "\nTests passed: %3d\n" ${nsuccess}
printf "Tests failed: %3d\n" ${nfail}
+
+if [ $nfail -ne 0 ]; then
+ exit 1 # KSFT_FAIL
+elif [ $nsuccess -eq 0 ]; then
+ exit $ksft_skip
+fi
+
+exit 0 # KSFT_PASS
setup
set -e
+ ip netns add ns2
+ ip netns set ns2 auto
+
+ ip -netns ns2 link set dev lo up
+
+ $IP link add name veth1 type veth peer name veth2
+ $IP link set dev veth2 netns ns2
+ $IP address add 192.0.2.1/24 dev veth1
+ ip -netns ns2 address add 192.0.2.1/24 dev veth2
+ $IP link set dev veth1 up
+ ip -netns ns2 link set dev veth2 up
+
$IP link set dev lo address 52:54:00:6a:c7:5e
- $IP link set dummy0 address 52:54:00:6a:c7:5e
- $IP link add dummy1 type dummy
- $IP link set dummy1 address 52:54:00:6a:c7:5e
- $IP link set dev dummy1 up
+ $IP link set dev veth1 address 52:54:00:6a:c7:5e
+ ip -netns ns2 link set dev lo address 52:54:00:6a:c7:5e
+ ip -netns ns2 link set dev veth2 address 52:54:00:6a:c7:5e
+
+ # 1. (ns2) redirect lo's egress to veth2's egress
+ ip netns exec ns2 tc qdisc add dev lo parent root handle 1: fq_codel
+ ip netns exec ns2 tc filter add dev lo parent 1: protocol arp basic \
+ action mirred egress redirect dev veth2
+ ip netns exec ns2 tc filter add dev lo parent 1: protocol ip basic \
+ action mirred egress redirect dev veth2
+
+ # 2. (ns1) redirect veth1's ingress to lo's ingress
+ $NS_EXEC tc qdisc add dev veth1 ingress
+ $NS_EXEC tc filter add dev veth1 ingress protocol arp basic \
+ action mirred ingress redirect dev lo
+ $NS_EXEC tc filter add dev veth1 ingress protocol ip basic \
+ action mirred ingress redirect dev lo
+
+ # 3. (ns1) redirect lo's egress to veth1's egress
+ $NS_EXEC tc qdisc add dev lo parent root handle 1: fq_codel
+ $NS_EXEC tc filter add dev lo parent 1: protocol arp basic \
+ action mirred egress redirect dev veth1
+ $NS_EXEC tc filter add dev lo parent 1: protocol ip basic \
+ action mirred egress redirect dev veth1
+
+ # 4. (ns2) redirect veth2's ingress to lo's ingress
+ ip netns exec ns2 tc qdisc add dev veth2 ingress
+ ip netns exec ns2 tc filter add dev veth2 ingress protocol arp basic \
+ action mirred ingress redirect dev lo
+ ip netns exec ns2 tc filter add dev veth2 ingress protocol ip basic \
+ action mirred ingress redirect dev lo
+
$NS_EXEC sysctl -qw net.ipv4.conf.all.rp_filter=1
$NS_EXEC sysctl -qw net.ipv4.conf.all.accept_local=1
$NS_EXEC sysctl -qw net.ipv4.conf.all.route_localnet=1
-
- $NS_EXEC tc qd add dev dummy1 parent root handle 1: fq_codel
- $NS_EXEC tc filter add dev dummy1 parent 1: protocol arp basic action mirred egress redirect dev lo
- $NS_EXEC tc filter add dev dummy1 parent 1: protocol ip basic action mirred egress redirect dev lo
+ ip netns exec ns2 sysctl -qw net.ipv4.conf.all.rp_filter=1
+ ip netns exec ns2 sysctl -qw net.ipv4.conf.all.accept_local=1
+ ip netns exec ns2 sysctl -qw net.ipv4.conf.all.route_localnet=1
set +e
- run_cmd "ip netns exec ns1 ping -I dummy1 -w1 -c1 198.51.100.1"
+ run_cmd "ip netns exec ns2 ping -w1 -c1 192.0.2.1"
log_test $? 0 "rp_filter passes local packets"
- run_cmd "ip netns exec ns1 ping -I dummy1 -w1 -c1 127.0.0.1"
+ run_cmd "ip netns exec ns2 ping -w1 -c1 127.0.0.1"
log_test $? 0 "rp_filter passes loopback packets"
cleanup
NETIFS[p6]=veth5
NETIFS[p7]=veth6
NETIFS[p8]=veth7
+NETIFS[p9]=veth8
+NETIFS[p10]=veth9
# Port that does not have a cable connected.
NETIF_NO_CABLE=eth8
ip -netns h1 ro get ${H1_VRF_ARG} ${H2_N2_IP} | \
grep -E -v 'mtu|redirected' | grep -q "cache"
fi
- log_test $? 0 "IPv4: ${desc}"
+ log_test $? 0 "IPv4: ${desc}" 0
# No PMTU info for test "redirect" and "mtu exception plus redirect"
if [ "$with_redirect" = "yes" ] && [ "$desc" != "redirect exception plus mtu" ]; then
struct tls12_crypto_info_chacha20_poly1305 chacha20;
struct tls12_crypto_info_sm4_gcm sm4gcm;
struct tls12_crypto_info_sm4_ccm sm4ccm;
+ struct tls12_crypto_info_aes_ccm_128 aesccm128;
+ struct tls12_crypto_info_aes_gcm_256 aesgcm256;
};
size_t len;
};
tls12->sm4ccm.info.version = tls_version;
tls12->sm4ccm.info.cipher_type = cipher_type;
break;
+ case TLS_CIPHER_AES_CCM_128:
+ tls12->len = sizeof(struct tls12_crypto_info_aes_ccm_128);
+ tls12->aesccm128.info.version = tls_version;
+ tls12->aesccm128.info.cipher_type = cipher_type;
+ break;
+ case TLS_CIPHER_AES_GCM_256:
+ tls12->len = sizeof(struct tls12_crypto_info_aes_gcm_256);
+ tls12->aesgcm256.info.version = tls_version;
+ tls12->aesgcm256.info.cipher_type = cipher_type;
+ break;
default:
break;
}
.cipher_type = TLS_CIPHER_SM4_CCM,
};
+FIXTURE_VARIANT_ADD(tls, 12_aes_ccm)
+{
+ .tls_version = TLS_1_2_VERSION,
+ .cipher_type = TLS_CIPHER_AES_CCM_128,
+};
+
+FIXTURE_VARIANT_ADD(tls, 13_aes_ccm)
+{
+ .tls_version = TLS_1_3_VERSION,
+ .cipher_type = TLS_CIPHER_AES_CCM_128,
+};
+
+FIXTURE_VARIANT_ADD(tls, 12_aes_gcm_256)
+{
+ .tls_version = TLS_1_2_VERSION,
+ .cipher_type = TLS_CIPHER_AES_GCM_256,
+};
+
+FIXTURE_VARIANT_ADD(tls, 13_aes_gcm_256)
+{
+ .tls_version = TLS_1_3_VERSION,
+ .cipher_type = TLS_CIPHER_AES_GCM_256,
+};
+
FIXTURE_SETUP(tls)
{
struct tls_crypto_info_keys tls12;
bool have_toeplitz = false;
int index, c;
- while ((c = getopt_long(argc, argv, "46C:d:i:k:r:stT:u:v", long_options, &index)) != -1) {
+ while ((c = getopt_long(argc, argv, "46C:d:i:k:r:stT:uv", long_options, &index)) != -1) {
switch (c) {
case '4':
cfg_family = AF_INET;
# oifname is the vrf device.
test_masquerade_vrf()
{
+ local qdisc=$1
+
+ if [ "$qdisc" != "default" ]; then
+ tc -net $ns0 qdisc add dev tvrf root $qdisc
+ fi
+
ip netns exec $ns0 conntrack -F 2>/dev/null
ip netns exec $ns0 nft -f - <<EOF
flush ruleset
table ip nat {
+ chain rawout {
+ type filter hook output priority raw;
+
+ oif tvrf ct state untracked counter
+ }
+ chain postrouting2 {
+ type filter hook postrouting priority mangle;
+
+ oif tvrf ct state untracked counter
+ }
chain postrouting {
type nat hook postrouting priority 0;
# NB: masquerade should always be combined with 'oif(name) bla',
fi
# must also check that nat table was evaluated on second (lower device) iteration.
- ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2'
+ ip netns exec $ns0 nft list table ip nat |grep -q 'counter packets 2' &&
+ ip netns exec $ns0 nft list table ip nat |grep -q 'untracked counter packets [1-9]'
if [ $? -eq 0 ]; then
- echo "PASS: iperf3 connect with masquerade + sport rewrite on vrf device"
+ echo "PASS: iperf3 connect with masquerade + sport rewrite on vrf device ($qdisc qdisc)"
else
- echo "FAIL: vrf masq rule has unexpected counter value"
+ echo "FAIL: vrf rules have unexpected counter value"
ret=1
fi
+
+ if [ "$qdisc" != "default" ]; then
+ tc -net $ns0 qdisc del dev tvrf root
+ fi
}
# add masq rule that gets evaluated w. outif set to veth device.
}
test_ct_zone_in
-test_masquerade_vrf
+test_masquerade_vrf "default"
+test_masquerade_vrf "pfifo"
test_masquerade_veth
exit $ret
# Set types, defined by TYPE_ variables below
TYPES="net_port port_net net6_port port_proto net6_port_mac net6_port_mac_proto
- net_port_net net_mac net_mac_icmp net6_mac_icmp net6_port_net6_port
- net_port_mac_proto_net"
+ net_port_net net_mac mac_net net_mac_icmp net6_mac_icmp
+ net6_port_net6_port net_port_mac_proto_net"
# Reported bugs, also described by TYPE_ variables below
BUGS="flush_remove_add"
perf_proto ipv4
"
+TYPE_mac_net="
+display mac,net
+type_spec ether_addr . ipv4_addr
+chain_spec ether saddr . ip saddr
+dst
+src mac addr4
+start 1
+count 5
+src_delta 2000
+tools sendip nc bash
+proto udp
+
+race_repeat 0
+
+perf_duration 0
+"
+
TYPE_net_mac_icmp="
display net,mac - ICMP
type_spec ipv4_addr . ether_addr
fi
done
for f in ${src}; do
- __expr="${__expr} . "
+ [ "${__expr}" != "{ " ] && __expr="${__expr} . "
+
__start="$(eval format_"${f}" "${srcstart}")"
__end="$(eval format_"${f}" "${srcend}")"
ip netns del $ns
}
-ip netns add $ns
-if [ $? -ne 0 ];then
- echo "SKIP: Could not create net namespace $gw"
- exit $ksft_skip
-fi
+checktool (){
+ if ! $1 > /dev/null 2>&1; then
+ echo "SKIP: Could not $2"
+ exit $ksft_skip
+ fi
+}
+
+checktool "nft --version" "run test without nft tool"
+checktool "ip -Version" "run test without ip tool"
+checktool "socat -V" "run test without socat tool"
+checktool "ip netns add $ns" "create net namespace"
trap cleanup EXIT
local start=$(date +%s%3N)
i=$((i + 10000))
j=$((j + 1))
- dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" nc -w 1 -q 1 -u -p 12345 127.0.0.1 12345 > /dev/null
+ # nft rule in output places each packet in a different zone.
+ dd if=/dev/zero of=/dev/stdout bs=8k count=10000 2>/dev/null | ip netns exec "$ns" socat STDIN UDP:127.0.0.1:12345,sourceport=12345
if [ $? -ne 0 ] ;then
ret=1
break
CONFIG_NET_SCH_FIFO=y
CONFIG_NET_SCH_ETS=m
CONFIG_NET_SCH_RED=m
+CONFIG_NET_SCH_FQ_PIE=m
+CONFIG_NETDEVSIM=m
#
## Network testing
list_test_cases(alltests)
exit(0)
+ exit_code = 0 # KSFT_PASS
if len(alltests):
req_plugins = pm.get_required_plugins(alltests)
try:
print('The following plugins were not found:')
print('{}'.format(pde.missing_pg))
catresults = test_runner(pm, args, alltests)
+ if catresults.count_failures() != 0:
+ exit_code = 1 # KSFT_FAIL
if args.format == 'none':
print('Test results output suppression requested\n')
else:
gid=int(os.getenv('SUDO_GID')))
else:
print('No tests found\n')
+ exit_code = 4 # KSFT_SKIP
+ exit(exit_code)
def main():
"""
set_operation_mode(pm, parser, args, remaining)
- exit(0)
-
-
if __name__ == "__main__":
main()
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
+modprobe netdevsim
./tdc.py -c actions --nobuildebpf
./tdc.py -c qdisc
projects / platform / kernel / linux-starfive.git / commitdiff