Re: Linux 6.5.4

From: Greg Kroah-Hartman
Date: Tue Sep 19 2023 - 06:54:12 EST


diff --git a/Documentation/admin-guide/cgroup-v1/memory.rst b/Documentation/admin-guide/cgroup-v1/memory.rst
index fabaad3fd9c2..8d3afeede10e 100644
--- a/Documentation/admin-guide/cgroup-v1/memory.rst
+++ b/Documentation/admin-guide/cgroup-v1/memory.rst
@@ -92,8 +92,6 @@ Brief summary of control files.
memory.oom_control set/show oom controls.
memory.numa_stat show the number of memory usage per numa
node
- memory.kmem.limit_in_bytes This knob is deprecated and writing to
- it will return -ENOTSUPP.
memory.kmem.usage_in_bytes show current kernel memory allocation
memory.kmem.failcnt show the number of kernel memory usage
hits limits
diff --git a/Documentation/devicetree/bindings/clock/xlnx,versal-clk.yaml b/Documentation/devicetree/bindings/clock/xlnx,versal-clk.yaml
index 5cbb34d0b61b..d3dd9c2c3019 100644
--- a/Documentation/devicetree/bindings/clock/xlnx,versal-clk.yaml
+++ b/Documentation/devicetree/bindings/clock/xlnx,versal-clk.yaml
@@ -14,8 +14,6 @@ description: |
reads required input clock frequencies from the devicetree and acts as clock
provider for all clock consumers of PS clocks.

-select: false
-
properties:
compatible:
const: xlnx,versal-clk
diff --git a/Makefile b/Makefile
index 901cdfa5e7d3..beddccac3283 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
VERSION = 6
PATCHLEVEL = 5
-SUBLEVEL = 3
+SUBLEVEL = 4
EXTRAVERSION =
NAME = Hurr durr I'ma ninja sloth

@@ -1962,7 +1962,9 @@ quiet_cmd_depmod = DEPMOD $(MODLIB)

modules_install:
$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modinst
+ifndef modules_sign_only
$(call cmd,depmod)
+endif

else # CONFIG_MODULES

diff --git a/arch/arc/include/asm/atomic-llsc.h b/arch/arc/include/asm/atomic-llsc.h
index 1b0ffaeee16d..5258cb81a16b 100644
--- a/arch/arc/include/asm/atomic-llsc.h
+++ b/arch/arc/include/asm/atomic-llsc.h
@@ -18,7 +18,7 @@ static inline void arch_atomic_##op(int i, atomic_t *v) \
: [val] "=&r" (val) /* Early clobber to prevent reg reuse */ \
: [ctr] "r" (&v->counter), /* Not "m": llock only supports reg direct addr mode */ \
[i] "ir" (i) \
- : "cc"); \
+ : "cc", "memory"); \
} \

#define ATOMIC_OP_RETURN(op, asm_op) \
@@ -34,7 +34,7 @@ static inline int arch_atomic_##op##_return_relaxed(int i, atomic_t *v) \
: [val] "=&r" (val) \
: [ctr] "r" (&v->counter), \
[i] "ir" (i) \
- : "cc"); \
+ : "cc", "memory"); \
\
return val; \
}
@@ -56,7 +56,7 @@ static inline int arch_atomic_fetch_##op##_relaxed(int i, atomic_t *v) \
[orig] "=&r" (orig) \
: [ctr] "r" (&v->counter), \
[i] "ir" (i) \
- : "cc"); \
+ : "cc", "memory"); \
\
return orig; \
}
diff --git a/arch/arc/include/asm/atomic64-arcv2.h b/arch/arc/include/asm/atomic64-arcv2.h
index 6b6db981967a..9b5791b85471 100644
--- a/arch/arc/include/asm/atomic64-arcv2.h
+++ b/arch/arc/include/asm/atomic64-arcv2.h
@@ -60,7 +60,7 @@ static inline void arch_atomic64_##op(s64 a, atomic64_t *v) \
" bnz 1b \n" \
: "=&r"(val) \
: "r"(&v->counter), "ir"(a) \
- : "cc"); \
+ : "cc", "memory"); \
} \

#define ATOMIC64_OP_RETURN(op, op1, op2) \
@@ -77,7 +77,7 @@ static inline s64 arch_atomic64_##op##_return_relaxed(s64 a, atomic64_t *v) \
" bnz 1b \n" \
: [val] "=&r"(val) \
: "r"(&v->counter), "ir"(a) \
- : "cc"); /* memory clobber comes from smp_mb() */ \
+ : "cc", "memory"); \
\
return val; \
}
@@ -99,7 +99,7 @@ static inline s64 arch_atomic64_fetch_##op##_relaxed(s64 a, atomic64_t *v) \
" bnz 1b \n" \
: "=&r"(orig), "=&r"(val) \
: "r"(&v->counter), "ir"(a) \
- : "cc"); /* memory clobber comes from smp_mb() */ \
+ : "cc", "memory"); \
\
return orig; \
}
diff --git a/arch/arm/boot/dts/broadcom/bcm4708-linksys-ea6500-v2.dts b/arch/arm/boot/dts/broadcom/bcm4708-linksys-ea6500-v2.dts
index f1412ba83def..0454423fe166 100644
--- a/arch/arm/boot/dts/broadcom/bcm4708-linksys-ea6500-v2.dts
+++ b/arch/arm/boot/dts/broadcom/bcm4708-linksys-ea6500-v2.dts
@@ -19,7 +19,8 @@ chosen {

memory@0 {
device_type = "memory";
- reg = <0x00000000 0x08000000>;
+ reg = <0x00000000 0x08000000>,
+ <0x88000000 0x08000000>;
};

gpio-keys {
diff --git a/arch/arm/boot/dts/qcom/qcom-msm8974pro-sony-xperia-shinano-castor.dts b/arch/arm/boot/dts/qcom/qcom-msm8974pro-sony-xperia-shinano-castor.dts
index 154639d56f35..11468d1409f7 100644
--- a/arch/arm/boot/dts/qcom/qcom-msm8974pro-sony-xperia-shinano-castor.dts
+++ b/arch/arm/boot/dts/qcom/qcom-msm8974pro-sony-xperia-shinano-castor.dts
@@ -125,15 +125,15 @@ synaptics@2c {

syna,startup-delay-ms = <100>;

- rmi-f01@1 {
+ rmi4-f01@1 {
reg = <0x1>;
- syna,nosleep = <1>;
+ syna,nosleep-mode = <1>;
};

- rmi-f11@11 {
+ rmi4-f11@11 {
reg = <0x11>;
- syna,f11-flip-x = <1>;
syna,sensor-type = <1>;
+ touchscreen-inverted-x;
};
};
};
diff --git a/arch/arm/boot/dts/samsung/exynos4210-i9100.dts b/arch/arm/boot/dts/samsung/exynos4210-i9100.dts
index 37cd4dde53e4..a9ec1f6c1dea 100644
--- a/arch/arm/boot/dts/samsung/exynos4210-i9100.dts
+++ b/arch/arm/boot/dts/samsung/exynos4210-i9100.dts
@@ -207,8 +207,8 @@ lcd@0 {
power-on-delay = <10>;
reset-delay = <10>;

- panel-width-mm = <90>;
- panel-height-mm = <154>;
+ panel-width-mm = <56>;
+ panel-height-mm = <93>;

display-timings {
timing {
diff --git a/arch/arm64/boot/dts/nvidia/tegra186.dtsi b/arch/arm64/boot/dts/nvidia/tegra186.dtsi
index 7e4c496fd91c..2b3bb5d0af17 100644
--- a/arch/arm64/boot/dts/nvidia/tegra186.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra186.dtsi
@@ -135,7 +135,8 @@ tegra_ahub: ahub@2900800 {
clocks = <&bpmp TEGRA186_CLK_AHUB>;
clock-names = "ahub";
assigned-clocks = <&bpmp TEGRA186_CLK_AHUB>;
- assigned-clock-parents = <&bpmp TEGRA186_CLK_PLL_A_OUT0>;
+ assigned-clock-parents = <&bpmp TEGRA186_CLK_PLLP_OUT0>;
+ assigned-clock-rates = <81600000>;
#address-cells = <1>;
#size-cells = <1>;
ranges = <0x02900800 0x02900800 0x11800>;
diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
index 154fc8c0eb6d..33f92b77cd9d 100644
--- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
@@ -231,7 +231,8 @@ tegra_ahub: ahub@2900800 {
clocks = <&bpmp TEGRA194_CLK_AHUB>;
clock-names = "ahub";
assigned-clocks = <&bpmp TEGRA194_CLK_AHUB>;
- assigned-clock-parents = <&bpmp TEGRA194_CLK_PLLA_OUT0>;
+ assigned-clock-parents = <&bpmp TEGRA194_CLK_PLLP_OUT0>;
+ assigned-clock-rates = <81600000>;
status = "disabled";

#address-cells = <2>;
diff --git a/arch/arm64/boot/dts/nvidia/tegra210.dtsi b/arch/arm64/boot/dts/nvidia/tegra210.dtsi
index 617583ff2736..e7b4e3013964 100644
--- a/arch/arm64/boot/dts/nvidia/tegra210.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra210.dtsi
@@ -1386,7 +1386,8 @@ tegra_ahub: ahub@702d0800 {
clocks = <&tegra_car TEGRA210_CLK_D_AUDIO>;
clock-names = "ahub";
assigned-clocks = <&tegra_car TEGRA210_CLK_D_AUDIO>;
- assigned-clock-parents = <&tegra_car TEGRA210_CLK_PLL_A_OUT0>;
+ assigned-clock-parents = <&tegra_car TEGRA210_CLK_PLL_P>;
+ assigned-clock-rates = <81600000>;
#address-cells = <1>;
#size-cells = <1>;
ranges = <0x702d0000 0x702d0000 0x0000e400>;
diff --git a/arch/arm64/boot/dts/nvidia/tegra234.dtsi b/arch/arm64/boot/dts/nvidia/tegra234.dtsi
index f4974e81dd4b..0f12a8debd8a 100644
--- a/arch/arm64/boot/dts/nvidia/tegra234.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra234.dtsi
@@ -180,7 +180,8 @@ tegra_ahub: ahub@2900800 {
clocks = <&bpmp TEGRA234_CLK_AHUB>;
clock-names = "ahub";
assigned-clocks = <&bpmp TEGRA234_CLK_AHUB>;
- assigned-clock-parents = <&bpmp TEGRA234_CLK_PLLA_OUT0>;
+ assigned-clock-parents = <&bpmp TEGRA234_CLK_PLLP_OUT0>;
+ assigned-clock-rates = <81600000>;
status = "disabled";

#address-cells = <2>;
diff --git a/arch/arm64/boot/dts/qcom/msm8953-xiaomi-vince.dts b/arch/arm64/boot/dts/qcom/msm8953-xiaomi-vince.dts
index 0956c866d6cb..1a1d3f92a511 100644
--- a/arch/arm64/boot/dts/qcom/msm8953-xiaomi-vince.dts
+++ b/arch/arm64/boot/dts/qcom/msm8953-xiaomi-vince.dts
@@ -132,7 +132,6 @@ &i2c_3 {
touchscreen@20 {
reg = <0x20>;
compatible = "syna,rmi4-i2c";
- interrupts-parent = <&tlmm>;
interrupts-extended = <&tlmm 65 IRQ_TYPE_EDGE_FALLING>;

#address-cells = <1>;
diff --git a/arch/arm64/boot/dts/renesas/rzg2l-smarc-som.dtsi b/arch/arm64/boot/dts/renesas/rzg2l-smarc-som.dtsi
index fbbb4f03440b..d0515769e66d 100644
--- a/arch/arm64/boot/dts/renesas/rzg2l-smarc-som.dtsi
+++ b/arch/arm64/boot/dts/renesas/rzg2l-smarc-som.dtsi
@@ -100,7 +100,7 @@ phy0: ethernet-phy@7 {
rxc-skew-psec = <2400>;
txc-skew-psec = <2400>;
rxdv-skew-psec = <0>;
- txdv-skew-psec = <0>;
+ txen-skew-psec = <0>;
rxd0-skew-psec = <0>;
rxd1-skew-psec = <0>;
rxd2-skew-psec = <0>;
@@ -128,7 +128,7 @@ phy1: ethernet-phy@7 {
rxc-skew-psec = <2400>;
txc-skew-psec = <2400>;
rxdv-skew-psec = <0>;
- txdv-skew-psec = <0>;
+ txen-skew-psec = <0>;
rxd0-skew-psec = <0>;
rxd1-skew-psec = <0>;
rxd2-skew-psec = <0>;
diff --git a/arch/arm64/boot/dts/renesas/rzg2lc-smarc-som.dtsi b/arch/arm64/boot/dts/renesas/rzg2lc-smarc-som.dtsi
index 8a0d56872de7..79279ffb4099 100644
--- a/arch/arm64/boot/dts/renesas/rzg2lc-smarc-som.dtsi
+++ b/arch/arm64/boot/dts/renesas/rzg2lc-smarc-som.dtsi
@@ -77,7 +77,7 @@ phy0: ethernet-phy@7 {
rxc-skew-psec = <2400>;
txc-skew-psec = <2400>;
rxdv-skew-psec = <0>;
- txdv-skew-psec = <0>;
+ txen-skew-psec = <0>;
rxd0-skew-psec = <0>;
rxd1-skew-psec = <0>;
rxd2-skew-psec = <0>;
diff --git a/arch/arm64/boot/dts/renesas/rzg2ul-smarc-som.dtsi b/arch/arm64/boot/dts/renesas/rzg2ul-smarc-som.dtsi
index 49ecd33aeeb8..97cdad2a12e2 100644
--- a/arch/arm64/boot/dts/renesas/rzg2ul-smarc-som.dtsi
+++ b/arch/arm64/boot/dts/renesas/rzg2ul-smarc-som.dtsi
@@ -83,7 +83,7 @@ phy0: ethernet-phy@7 {
rxc-skew-psec = <2400>;
txc-skew-psec = <2400>;
rxdv-skew-psec = <0>;
- txdv-skew-psec = <0>;
+ txen-skew-psec = <0>;
rxd0-skew-psec = <0>;
rxd1-skew-psec = <0>;
rxd2-skew-psec = <0>;
@@ -112,7 +112,7 @@ phy1: ethernet-phy@7 {
rxc-skew-psec = <2400>;
txc-skew-psec = <2400>;
rxdv-skew-psec = <0>;
- txdv-skew-psec = <0>;
+ txen-skew-psec = <0>;
rxd0-skew-psec = <0>;
rxd1-skew-psec = <0>;
rxd2-skew-psec = <0>;
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index a47593d72f6f..d624b87c150d 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -299,8 +299,8 @@ ifdef CONFIG_64BIT
endif
endif

- ifeq ($(KBUILD_SYM32)$(call cc-option-yn,-msym32), yy)
- cflags-y += -msym32 -DKBUILD_64BIT_SYM32
+ ifeq ($(KBUILD_SYM32), y)
+ cflags-$(KBUILD_SYM32) += -msym32 -DKBUILD_64BIT_SYM32
else
ifeq ($(CONFIG_CPU_DADDI_WORKAROUNDS), y)
$(error CONFIG_CPU_DADDI_WORKAROUNDS unsupported without -msym32)
@@ -341,7 +341,7 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables

KBUILD_LDFLAGS += -m $(ld-emul)

-ifdef CONFIG_MIPS
+ifdef need-compiler
CHECKFLAGS += $(shell $(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) -dM -E -x c /dev/null | \
grep -E -vw '__GNUC_(MINOR_|PATCHLEVEL_)?_' | \
sed -e "s/^\#define /-D'/" -e "s/ /'='/" -e "s/$$/'/" -e 's/\$$/&&/g')
diff --git a/arch/parisc/include/asm/led.h b/arch/parisc/include/asm/led.h
index 6de13d08a388..b70b9094fb7c 100644
--- a/arch/parisc/include/asm/led.h
+++ b/arch/parisc/include/asm/led.h
@@ -11,8 +11,8 @@
#define LED1 0x02
#define LED0 0x01 /* bottom (or furthest left) LED */

-#define LED_LAN_TX LED0 /* for LAN transmit activity */
-#define LED_LAN_RCV LED1 /* for LAN receive activity */
+#define LED_LAN_RCV LED0 /* for LAN receive activity */
+#define LED_LAN_TX LED1 /* for LAN transmit activity */
#define LED_DISK_IO LED2 /* for disk activity */
#define LED_HEARTBEAT LED3 /* heartbeat */

diff --git a/arch/parisc/include/asm/mckinley.h b/arch/parisc/include/asm/mckinley.h
deleted file mode 100644
index 1314390b9034..000000000000
--- a/arch/parisc/include/asm/mckinley.h
+++ /dev/null
@@ -1,8 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ASM_PARISC_MCKINLEY_H
-#define ASM_PARISC_MCKINLEY_H
-
-/* declared in arch/parisc/kernel/setup.c */
-extern struct proc_dir_entry * proc_mckinley_root;
-
-#endif /*ASM_PARISC_MCKINLEY_H*/
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 5e9371fbf3d5..de2fb12120d2 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -2088,6 +2088,7 @@ struct bpf_tramp_jit {
*/
int r14_off; /* Offset of saved %r14 */
int run_ctx_off; /* Offset of struct bpf_tramp_run_ctx */
+ int tccnt_off; /* Offset of saved tailcall counter */
int do_fexit; /* do_fexit: label */
};

@@ -2258,12 +2259,16 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
tjit->r14_off = alloc_stack(tjit, sizeof(u64));
tjit->run_ctx_off = alloc_stack(tjit,
sizeof(struct bpf_tramp_run_ctx));
+ tjit->tccnt_off = alloc_stack(tjit, sizeof(u64));
/* The caller has already reserved STACK_FRAME_OVERHEAD bytes. */
tjit->stack_size -= STACK_FRAME_OVERHEAD;
tjit->orig_stack_args_off = tjit->stack_size + STACK_FRAME_OVERHEAD;

/* aghi %r15,-stack_size */
EMIT4_IMM(0xa70b0000, REG_15, -tjit->stack_size);
+ /* mvc tccnt_off(4,%r15),stack_size+STK_OFF_TCCNT(%r15) */
+ _EMIT6(0xd203f000 | tjit->tccnt_off,
+ 0xf000 | (tjit->stack_size + STK_OFF_TCCNT));
/* stmg %r2,%rN,fwd_reg_args_off(%r15) */
if (nr_reg_args)
EMIT6_DISP_LH(0xeb000000, 0x0024, REG_2,
@@ -2400,6 +2405,8 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
(nr_stack_args * sizeof(u64) - 1) << 16 |
tjit->stack_args_off,
0xf000 | tjit->orig_stack_args_off);
+ /* mvc STK_OFF_TCCNT(4,%r15),tccnt_off(%r15) */
+ _EMIT6(0xd203f000 | STK_OFF_TCCNT, 0xf000 | tjit->tccnt_off);
/* lgr %r1,%r8 */
EMIT4(0xb9040000, REG_1, REG_8);
/* %r1() */
@@ -2456,6 +2463,9 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
if (flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET))
EMIT6_DISP_LH(0xe3000000, 0x0004, REG_2, REG_0, REG_15,
tjit->retval_off);
+ /* mvc stack_size+STK_OFF_TCCNT(4,%r15),tccnt_off(%r15) */
+ _EMIT6(0xd203f000 | (tjit->stack_size + STK_OFF_TCCNT),
+ 0xf000 | tjit->tccnt_off);
/* aghi %r15,stack_size */
EMIT4_IMM(0xa70b0000, REG_15, tjit->stack_size);
/* Emit an expoline for the following indirect jump. */
diff --git a/arch/sh/boards/mach-ap325rxa/setup.c b/arch/sh/boards/mach-ap325rxa/setup.c
index 151792162152..645cccf3da88 100644
--- a/arch/sh/boards/mach-ap325rxa/setup.c
+++ b/arch/sh/boards/mach-ap325rxa/setup.c
@@ -531,7 +531,7 @@ static int __init ap325rxa_devices_setup(void)
device_initialize(&ap325rxa_ceu_device.dev);
dma_declare_coherent_memory(&ap325rxa_ceu_device.dev,
ceu_dma_membase, ceu_dma_membase,
- ceu_dma_membase + CEU_BUFFER_MEMORY_SIZE - 1);
+ CEU_BUFFER_MEMORY_SIZE);

platform_device_add(&ap325rxa_ceu_device);

diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c
index 674da7ebd8b7..7ec03d4a4edf 100644
--- a/arch/sh/boards/mach-ecovec24/setup.c
+++ b/arch/sh/boards/mach-ecovec24/setup.c
@@ -1454,15 +1454,13 @@ static int __init arch_setup(void)
device_initialize(&ecovec_ceu_devices[0]->dev);
dma_declare_coherent_memory(&ecovec_ceu_devices[0]->dev,
ceu0_dma_membase, ceu0_dma_membase,
- ceu0_dma_membase +
- CEU_BUFFER_MEMORY_SIZE - 1);
+ CEU_BUFFER_MEMORY_SIZE);
platform_device_add(ecovec_ceu_devices[0]);

device_initialize(&ecovec_ceu_devices[1]->dev);
dma_declare_coherent_memory(&ecovec_ceu_devices[1]->dev,
ceu1_dma_membase, ceu1_dma_membase,
- ceu1_dma_membase +
- CEU_BUFFER_MEMORY_SIZE - 1);
+ CEU_BUFFER_MEMORY_SIZE);
platform_device_add(ecovec_ceu_devices[1]);

gpiod_add_lookup_table(&cn12_power_gpiod_table);
diff --git a/arch/sh/boards/mach-kfr2r09/setup.c b/arch/sh/boards/mach-kfr2r09/setup.c
index 20f4db778ed6..c6d556dfbbbe 100644
--- a/arch/sh/boards/mach-kfr2r09/setup.c
+++ b/arch/sh/boards/mach-kfr2r09/setup.c
@@ -603,7 +603,7 @@ static int __init kfr2r09_devices_setup(void)
device_initialize(&kfr2r09_ceu_device.dev);
dma_declare_coherent_memory(&kfr2r09_ceu_device.dev,
ceu_dma_membase, ceu_dma_membase,
- ceu_dma_membase + CEU_BUFFER_MEMORY_SIZE - 1);
+ CEU_BUFFER_MEMORY_SIZE);

platform_device_add(&kfr2r09_ceu_device);

diff --git a/arch/sh/boards/mach-migor/setup.c b/arch/sh/boards/mach-migor/setup.c
index f60061283c48..773ee767d0c4 100644
--- a/arch/sh/boards/mach-migor/setup.c
+++ b/arch/sh/boards/mach-migor/setup.c
@@ -604,7 +604,7 @@ static int __init migor_devices_setup(void)
device_initialize(&migor_ceu_device.dev);
dma_declare_coherent_memory(&migor_ceu_device.dev,
ceu_dma_membase, ceu_dma_membase,
- ceu_dma_membase + CEU_BUFFER_MEMORY_SIZE - 1);
+ CEU_BUFFER_MEMORY_SIZE);

platform_device_add(&migor_ceu_device);

diff --git a/arch/sh/boards/mach-se/7724/setup.c b/arch/sh/boards/mach-se/7724/setup.c
index b60a2626e18b..6495f9354065 100644
--- a/arch/sh/boards/mach-se/7724/setup.c
+++ b/arch/sh/boards/mach-se/7724/setup.c
@@ -940,15 +940,13 @@ static int __init devices_setup(void)
device_initialize(&ms7724se_ceu_devices[0]->dev);
dma_declare_coherent_memory(&ms7724se_ceu_devices[0]->dev,
ceu0_dma_membase, ceu0_dma_membase,
- ceu0_dma_membase +
- CEU_BUFFER_MEMORY_SIZE - 1);
+ CEU_BUFFER_MEMORY_SIZE);
platform_device_add(ms7724se_ceu_devices[0]);

device_initialize(&ms7724se_ceu_devices[1]->dev);
dma_declare_coherent_memory(&ms7724se_ceu_devices[1]->dev,
ceu1_dma_membase, ceu1_dma_membase,
- ceu1_dma_membase +
- CEU_BUFFER_MEMORY_SIZE - 1);
+ CEU_BUFFER_MEMORY_SIZE);
platform_device_add(ms7724se_ceu_devices[1]);

return platform_add_devices(ms7724se_devices,
diff --git a/arch/sh/drivers/push-switch.c b/arch/sh/drivers/push-switch.c
index c95f48ff3f6f..6ecba5f521eb 100644
--- a/arch/sh/drivers/push-switch.c
+++ b/arch/sh/drivers/push-switch.c
@@ -101,8 +101,8 @@ static int switch_drv_remove(struct platform_device *pdev)
device_remove_file(&pdev->dev, &dev_attr_switch);

platform_set_drvdata(pdev, NULL);
- flush_work(&psw->work);
timer_shutdown_sync(&psw->debounce);
+ flush_work(&psw->work);
free_irq(irq, pdev);

kfree(psw);
diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index 3b12e6b99412..6c2e3ff3cb28 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -101,12 +101,6 @@ static inline int cpu_has_svm(const char **msg)
return 0;
}

- if (boot_cpu_data.extended_cpuid_level < SVM_CPUID_FUNC) {
- if (msg)
- *msg = "can't execute cpuid_8000000a";
- return 0;
- }
-
if (!boot_cpu_has(X86_FEATURE_SVM)) {
if (msg)
*msg = "svm not available";
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index cfc8ab773025..2092db892d7d 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -791,6 +791,7 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
int ret = 0;
unsigned long flags;
struct amd_svm_iommu_ir *ir;
+ u64 entry;

/**
* In some cases, the existing irte is updated and re-set,
@@ -824,6 +825,18 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
ir->data = pi->ir_data;

spin_lock_irqsave(&svm->ir_list_lock, flags);
+
+ /*
+ * Update the target pCPU for IOMMU doorbells if the vCPU is running.
+ * If the vCPU is NOT running, i.e. is blocking or scheduled out, KVM
+ * will update the pCPU info when the vCPU awkened and/or scheduled in.
+ * See also avic_vcpu_load().
+ */
+ entry = READ_ONCE(*(svm->avic_physical_id_cache));
+ if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)
+ amd_iommu_update_ga(entry & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK,
+ true, pi->ir_data);
+
list_add(&ir->node, &svm->ir_list);
spin_unlock_irqrestore(&svm->ir_list_lock, flags);
out:
@@ -986,10 +999,11 @@ static inline int
avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r)
{
int ret = 0;
- unsigned long flags;
struct amd_svm_iommu_ir *ir;
struct vcpu_svm *svm = to_svm(vcpu);

+ lockdep_assert_held(&svm->ir_list_lock);
+
if (!kvm_arch_has_assigned_device(vcpu->kvm))
return 0;

@@ -997,19 +1011,15 @@ avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r)
* Here, we go through the per-vcpu ir_list to update all existing
* interrupt remapping table entry targeting this vcpu.
*/
- spin_lock_irqsave(&svm->ir_list_lock, flags);
-
if (list_empty(&svm->ir_list))
- goto out;
+ return 0;

list_for_each_entry(ir, &svm->ir_list, node) {
ret = amd_iommu_update_ga(cpu, r, ir->data);
if (ret)
- break;
+ return ret;
}
-out:
- spin_unlock_irqrestore(&svm->ir_list_lock, flags);
- return ret;
+ return 0;
}

void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
@@ -1017,6 +1027,7 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
u64 entry;
int h_physical_id = kvm_cpu_get_apicid(cpu);
struct vcpu_svm *svm = to_svm(vcpu);
+ unsigned long flags;

lockdep_assert_preemption_disabled();

@@ -1033,6 +1044,15 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
if (kvm_vcpu_is_blocking(vcpu))
return;

+ /*
+ * Grab the per-vCPU interrupt remapping lock even if the VM doesn't
+ * _currently_ have assigned devices, as that can change. Holding
+ * ir_list_lock ensures that either svm_ir_list_add() will consume
+ * up-to-date entry information, or that this task will wait until
+ * svm_ir_list_add() completes to set the new target pCPU.
+ */
+ spin_lock_irqsave(&svm->ir_list_lock, flags);
+
entry = READ_ONCE(*(svm->avic_physical_id_cache));
WARN_ON_ONCE(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK);

@@ -1042,25 +1062,48 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)

WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, true);
+
+ spin_unlock_irqrestore(&svm->ir_list_lock, flags);
}

void avic_vcpu_put(struct kvm_vcpu *vcpu)
{
u64 entry;
struct vcpu_svm *svm = to_svm(vcpu);
+ unsigned long flags;

lockdep_assert_preemption_disabled();

+ /*
+ * Note, reading the Physical ID entry outside of ir_list_lock is safe
+ * as only the pCPU that has loaded (or is loading) the vCPU is allowed
+ * to modify the entry, and preemption is disabled. I.e. the vCPU
+ * can't be scheduled out and thus avic_vcpu_{put,load}() can't run
+ * recursively.
+ */
entry = READ_ONCE(*(svm->avic_physical_id_cache));

/* Nothing to do if IsRunning == '0' due to vCPU blocking. */
if (!(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK))
return;

+ /*
+ * Take and hold the per-vCPU interrupt remapping lock while updating
+ * the Physical ID entry even though the lock doesn't protect against
+ * multiple writers (see above). Holding ir_list_lock ensures that
+ * either svm_ir_list_add() will consume up-to-date entry information,
+ * or that this task will wait until svm_ir_list_add() completes to
+ * mark the vCPU as not running.
+ */
+ spin_lock_irqsave(&svm->ir_list_lock, flags);
+
avic_update_iommu_vcpu_affinity(vcpu, -1, 0);

entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
+
+ spin_unlock_irqrestore(&svm->ir_list_lock, flags);
+
}

void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 96936ddf1b3c..c66c823ae222 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -695,10 +695,9 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,

vmcb02->control.tsc_offset = vcpu->arch.tsc_offset;

- if (svm->tsc_ratio_msr != kvm_caps.default_tsc_scaling_ratio) {
- WARN_ON(!svm->tsc_scaling_enabled);
+ if (svm->tsc_scaling_enabled &&
+ svm->tsc_ratio_msr != kvm_caps.default_tsc_scaling_ratio)
nested_svm_update_tsc_ratio_msr(vcpu);
- }

vmcb02->control.int_ctl =
(svm->nested.ctl.int_ctl & int_ctl_vmcb12_bits) |
@@ -1101,8 +1100,8 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
vmcb_mark_dirty(vmcb01, VMCB_INTERCEPTS);
}

- if (svm->tsc_ratio_msr != kvm_caps.default_tsc_scaling_ratio) {
- WARN_ON(!svm->tsc_scaling_enabled);
+ if (kvm_caps.has_tsc_control &&
+ vcpu->arch.tsc_scaling_ratio != vcpu->arch.l1_tsc_scaling_ratio) {
vcpu->arch.tsc_scaling_ratio = vcpu->arch.l1_tsc_scaling_ratio;
__svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio);
}
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index d3aec1f2cad2..cefb67a8c668 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -1725,7 +1725,7 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm)
* Note, the source is not required to have the same number of
* vCPUs as the destination when migrating a vanilla SEV VM.
*/
- src_vcpu = kvm_get_vcpu(dst_kvm, i);
+ src_vcpu = kvm_get_vcpu(src_kvm, i);
src_svm = to_svm(src_vcpu);

/*
@@ -2881,7 +2881,10 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
svm->sev_es.ghcb_sa);
break;
case SVM_VMGEXIT_NMI_COMPLETE:
- ret = svm_invoke_exit_handler(vcpu, SVM_EXIT_IRET);
+ ++vcpu->stat.nmi_window_exits;
+ svm->nmi_masked = false;
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+ ret = 1;
break;
case SVM_VMGEXIT_AP_HLT_LOOP:
ret = kvm_emulate_ap_reset_hold(vcpu);
@@ -2952,9 +2955,12 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
/*
* An SEV-ES guest requires a VMSA area that is a separate from the
* VMCB page. Do not include the encryption mask on the VMSA physical
- * address since hardware will access it using the guest key.
+ * address since hardware will access it using the guest key. Note,
+ * the VMSA will be NULL if this vCPU is the destination for intrahost
+ * migration, and will be copied later.
*/
- svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
+ if (svm->sev_es.vmsa)
+ svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);

/* Can't intercept CR register access, HV can't modify CR registers */
svm_clr_intercept(svm, INTERCEPT_CR0_READ);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index d4bfdc607fe7..e3acccc12616 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -365,6 +365,8 @@ static void svm_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
svm->vmcb->control.int_state |= SVM_INTERRUPT_SHADOW_MASK;

}
+static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
+ void *insn, int insn_len);

static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu,
bool commit_side_effects)
@@ -385,6 +387,14 @@ static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu,
}

if (!svm->next_rip) {
+ /*
+ * FIXME: Drop this when kvm_emulate_instruction() does the
+ * right thing and treats "can't emulate" as outright failure
+ * for EMULTYPE_SKIP.
+ */
+ if (!svm_can_emulate_instruction(vcpu, EMULTYPE_SKIP, NULL, 0))
+ return 0;
+
if (unlikely(!commit_side_effects))
old_rflags = svm->vmcb->save.rflags;

@@ -2510,12 +2520,13 @@ static int iret_interception(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);

+ WARN_ON_ONCE(sev_es_guest(vcpu->kvm));
+
++vcpu->stat.nmi_window_exits;
svm->awaiting_iret_completion = true;

svm_clr_iret_intercept(svm);
- if (!sev_es_guest(vcpu->kvm))
- svm->nmi_iret_rip = kvm_rip_read(vcpu);
+ svm->nmi_iret_rip = kvm_rip_read(vcpu);

kvm_make_request(KVM_REQ_EVENT, vcpu);
return 1;
@@ -3918,12 +3929,11 @@ static void svm_complete_interrupts(struct kvm_vcpu *vcpu)
svm->soft_int_injected = false;

/*
- * If we've made progress since setting HF_IRET_MASK, we've
+ * If we've made progress since setting awaiting_iret_completion, we've
* executed an IRET and can allow NMI injection.
*/
if (svm->awaiting_iret_completion &&
- (sev_es_guest(vcpu->kvm) ||
- kvm_rip_read(vcpu) != svm->nmi_iret_rip)) {
+ kvm_rip_read(vcpu) != svm->nmi_iret_rip) {
svm->awaiting_iret_completion = false;
svm->nmi_masked = false;
kvm_make_request(KVM_REQ_EVENT, vcpu);
@@ -4651,16 +4661,25 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
* and cannot be decrypted by KVM, i.e. KVM would read cyphertext and
* decode garbage.
*
- * Inject #UD if KVM reached this point without an instruction buffer.
- * In practice, this path should never be hit by a well-behaved guest,
- * e.g. KVM doesn't intercept #UD or #GP for SEV guests, but this path
- * is still theoretically reachable, e.g. via unaccelerated fault-like
- * AVIC access, and needs to be handled by KVM to avoid putting the
- * guest into an infinite loop. Injecting #UD is somewhat arbitrary,
- * but its the least awful option given lack of insight into the guest.
+ * If KVM is NOT trying to simply skip an instruction, inject #UD if
+ * KVM reached this point without an instruction buffer. In practice,
+ * this path should never be hit by a well-behaved guest, e.g. KVM
+ * doesn't intercept #UD or #GP for SEV guests, but this path is still
+ * theoretically reachable, e.g. via unaccelerated fault-like AVIC
+ * access, and needs to be handled by KVM to avoid putting the guest
+ * into an infinite loop. Injecting #UD is somewhat arbitrary, but
+ * its the least awful option given lack of insight into the guest.
+ *
+ * If KVM is trying to skip an instruction, simply resume the guest.
+ * If a #NPF occurs while the guest is vectoring an INT3/INTO, then KVM
+ * will attempt to re-inject the INT3/INTO and skip the instruction.
+ * In that scenario, retrying the INT3/INTO and hoping the guest will
+ * make forward progress is the only option that has a chance of
+ * success (and in practice it will work the vast majority of the time).
*/
if (unlikely(!insn)) {
- kvm_queue_exception(vcpu, UD_VECTOR);
+ if (!(emul_type & EMULTYPE_SKIP))
+ kvm_queue_exception(vcpu, UD_VECTOR);
return false;
}

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index df461f387e20..f2fb67a9dc05 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -7243,13 +7243,20 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
flags);

vcpu->arch.cr2 = native_read_cr2();
+ vcpu->arch.regs_avail &= ~VMX_REGS_LAZY_LOAD_SET;
+
+ vmx->idt_vectoring_info = 0;

vmx_enable_fb_clear(vmx);

- if (unlikely(vmx->fail))
+ if (unlikely(vmx->fail)) {
vmx->exit_reason.full = 0xdead;
- else
- vmx->exit_reason.full = vmcs_read32(VM_EXIT_REASON);
+ goto out;
+ }
+
+ vmx->exit_reason.full = vmcs_read32(VM_EXIT_REASON);
+ if (likely(!vmx->exit_reason.failed_vmentry))
+ vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);

if ((u16)vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI &&
is_nmi(vmx_get_intr_info(vcpu))) {
@@ -7258,6 +7265,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
kvm_after_interrupt(vcpu);
}

+out:
guest_state_exit_irqoff();
}

@@ -7379,8 +7387,6 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
loadsegment(es, __USER_DS);
#endif

- vcpu->arch.regs_avail &= ~VMX_REGS_LAZY_LOAD_SET;
-
pt_guest_exit(vmx);

kvm_load_host_xsave_state(vcpu);
@@ -7397,17 +7403,12 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
vmx->nested.nested_run_pending = 0;
}

- vmx->idt_vectoring_info = 0;
-
if (unlikely(vmx->fail))
return EXIT_FASTPATH_NONE;

if (unlikely((u16)vmx->exit_reason.basic == EXIT_REASON_MCE_DURING_VMENTRY))
kvm_machine_check();

- if (likely(!vmx->exit_reason.failed_vmentry))
- vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
-
trace_kvm_exit(vcpu, KVM_ISA_VMX);

if (unlikely(vmx->exit_reason.failed_vmentry))
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 7397ff199d66..e78bc3b65ec8 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -697,11 +697,41 @@ static bool throtl_slice_used(struct throtl_grp *tg, bool rw)
return true;
}

+static unsigned int calculate_io_allowed(u32 iops_limit,
+ unsigned long jiffy_elapsed)
+{
+ unsigned int io_allowed;
+ u64 tmp;
+
+ /*
+ * jiffy_elapsed should not be a big value as minimum iops can be
+ * 1 then at max jiffy elapsed should be equivalent of 1 second as we
+ * will allow dispatch after 1 second and after that slice should
+ * have been trimmed.
+ */
+
+ tmp = (u64)iops_limit * jiffy_elapsed;
+ do_div(tmp, HZ);
+
+ if (tmp > UINT_MAX)
+ io_allowed = UINT_MAX;
+ else
+ io_allowed = tmp;
+
+ return io_allowed;
+}
+
+static u64 calculate_bytes_allowed(u64 bps_limit, unsigned long jiffy_elapsed)
+{
+ return mul_u64_u64_div_u64(bps_limit, (u64)jiffy_elapsed, (u64)HZ);
+}
+
/* Trim the used slices and adjust slice start accordingly */
static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)
{
- unsigned long nr_slices, time_elapsed, io_trim;
- u64 bytes_trim, tmp;
+ unsigned long time_elapsed;
+ long long bytes_trim;
+ int io_trim;

BUG_ON(time_before(tg->slice_end[rw], tg->slice_start[rw]));

@@ -723,67 +753,38 @@ static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)

throtl_set_slice_end(tg, rw, jiffies + tg->td->throtl_slice);

- time_elapsed = jiffies - tg->slice_start[rw];
-
- nr_slices = time_elapsed / tg->td->throtl_slice;
-
- if (!nr_slices)
+ time_elapsed = rounddown(jiffies - tg->slice_start[rw],
+ tg->td->throtl_slice);
+ if (!time_elapsed)
return;
- tmp = tg_bps_limit(tg, rw) * tg->td->throtl_slice * nr_slices;
- do_div(tmp, HZ);
- bytes_trim = tmp;

- io_trim = (tg_iops_limit(tg, rw) * tg->td->throtl_slice * nr_slices) /
- HZ;
-
- if (!bytes_trim && !io_trim)
+ bytes_trim = calculate_bytes_allowed(tg_bps_limit(tg, rw),
+ time_elapsed) +
+ tg->carryover_bytes[rw];
+ io_trim = calculate_io_allowed(tg_iops_limit(tg, rw), time_elapsed) +
+ tg->carryover_ios[rw];
+ if (bytes_trim <= 0 && io_trim <= 0)
return;

- if (tg->bytes_disp[rw] >= bytes_trim)
+ tg->carryover_bytes[rw] = 0;
+ if ((long long)tg->bytes_disp[rw] >= bytes_trim)
tg->bytes_disp[rw] -= bytes_trim;
else
tg->bytes_disp[rw] = 0;

- if (tg->io_disp[rw] >= io_trim)
+ tg->carryover_ios[rw] = 0;
+ if ((int)tg->io_disp[rw] >= io_trim)
tg->io_disp[rw] -= io_trim;
else
tg->io_disp[rw] = 0;

- tg->slice_start[rw] += nr_slices * tg->td->throtl_slice;
+ tg->slice_start[rw] += time_elapsed;

throtl_log(&tg->service_queue,
- "[%c] trim slice nr=%lu bytes=%llu io=%lu start=%lu end=%lu jiffies=%lu",
- rw == READ ? 'R' : 'W', nr_slices, bytes_trim, io_trim,
- tg->slice_start[rw], tg->slice_end[rw], jiffies);
-}
-
-static unsigned int calculate_io_allowed(u32 iops_limit,
- unsigned long jiffy_elapsed)
-{
- unsigned int io_allowed;
- u64 tmp;
-
- /*
- * jiffy_elapsed should not be a big value as minimum iops can be
- * 1 then at max jiffy elapsed should be equivalent of 1 second as we
- * will allow dispatch after 1 second and after that slice should
- * have been trimmed.
- */
-
- tmp = (u64)iops_limit * jiffy_elapsed;
- do_div(tmp, HZ);
-
- if (tmp > UINT_MAX)
- io_allowed = UINT_MAX;
- else
- io_allowed = tmp;
-
- return io_allowed;
-}
-
-static u64 calculate_bytes_allowed(u64 bps_limit, unsigned long jiffy_elapsed)
-{
- return mul_u64_u64_div_u64(bps_limit, (u64)jiffy_elapsed, (u64)HZ);
+ "[%c] trim slice nr=%lu bytes=%lld io=%d start=%lu end=%lu jiffies=%lu",
+ rw == READ ? 'R' : 'W', time_elapsed / tg->td->throtl_slice,
+ bytes_trim, io_trim, tg->slice_start[rw], tg->slice_end[rw],
+ jiffies);
}

static void __tg_update_carryover(struct throtl_grp *tg, bool rw)
diff --git a/drivers/accel/ivpu/ivpu_jsm_msg.c b/drivers/accel/ivpu/ivpu_jsm_msg.c
index 831bfd2b2d39..bdddef2c59ee 100644
--- a/drivers/accel/ivpu/ivpu_jsm_msg.c
+++ b/drivers/accel/ivpu/ivpu_jsm_msg.c
@@ -118,8 +118,7 @@ int ivpu_jsm_dyndbg_control(struct ivpu_device *vdev, char *command, size_t size
struct vpu_jsm_msg resp;
int ret;

- if (!strncpy(req.payload.dyndbg_control.dyndbg_cmd, command, VPU_DYNDBG_CMD_MAX_LEN - 1))
- return -ENOMEM;
+ strscpy(req.payload.dyndbg_control.dyndbg_cmd, command, VPU_DYNDBG_CMD_MAX_LEN);

ret = ivpu_ipc_send_receive(vdev, &req, VPU_JSM_MSG_DYNDBG_CONTROL_RSP, &resp,
VPU_IPC_CHAN_ASYNC_CMD, vdev->timeout.jsm);
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index addba109406b..c1e85e0ed43e 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -421,6 +421,8 @@ static const struct pci_device_id ahci_pci_tbl[] = {
{ PCI_VDEVICE(INTEL, 0x34d3), board_ahci_low_power }, /* Ice Lake LP AHCI */
{ PCI_VDEVICE(INTEL, 0x02d3), board_ahci_low_power }, /* Comet Lake PCH-U AHCI */
{ PCI_VDEVICE(INTEL, 0x02d7), board_ahci_low_power }, /* Comet Lake PCH RAID */
+ /* Elkhart Lake IDs 0x4b60 & 0x4b62 https://sata-io.org/product/8803 not tested yet */
+ { PCI_VDEVICE(INTEL, 0x4b63), board_ahci_low_power }, /* Elkhart Lake AHCI */

/* JMicron 360/1/3/5/6, match class to avoid IDE function */
{ PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
diff --git a/drivers/ata/pata_falcon.c b/drivers/ata/pata_falcon.c
index 996516e64f13..616064b02de6 100644
--- a/drivers/ata/pata_falcon.c
+++ b/drivers/ata/pata_falcon.c
@@ -123,8 +123,8 @@ static int __init pata_falcon_init_one(struct platform_device *pdev)
struct resource *base_res, *ctl_res, *irq_res;
struct ata_host *host;
struct ata_port *ap;
- void __iomem *base;
- int irq = 0;
+ void __iomem *base, *ctl_base;
+ int irq = 0, io_offset = 1, reg_shift = 2; /* Falcon defaults */

dev_info(&pdev->dev, "Atari Falcon and Q40/Q60 PATA controller\n");

@@ -165,26 +165,34 @@ static int __init pata_falcon_init_one(struct platform_device *pdev)
ap->pio_mask = ATA_PIO4;
ap->flags |= ATA_FLAG_SLAVE_POSS | ATA_FLAG_NO_IORDY;

- base = (void __iomem *)base_mem_res->start;
/* N.B. this assumes data_addr will be used for word-sized I/O only */
- ap->ioaddr.data_addr = base + 0 + 0 * 4;
- ap->ioaddr.error_addr = base + 1 + 1 * 4;
- ap->ioaddr.feature_addr = base + 1 + 1 * 4;
- ap->ioaddr.nsect_addr = base + 1 + 2 * 4;
- ap->ioaddr.lbal_addr = base + 1 + 3 * 4;
- ap->ioaddr.lbam_addr = base + 1 + 4 * 4;
- ap->ioaddr.lbah_addr = base + 1 + 5 * 4;
- ap->ioaddr.device_addr = base + 1 + 6 * 4;
- ap->ioaddr.status_addr = base + 1 + 7 * 4;
- ap->ioaddr.command_addr = base + 1 + 7 * 4;
-
- base = (void __iomem *)ctl_mem_res->start;
- ap->ioaddr.altstatus_addr = base + 1;
- ap->ioaddr.ctl_addr = base + 1;
-
- ata_port_desc(ap, "cmd 0x%lx ctl 0x%lx",
- (unsigned long)base_mem_res->start,
- (unsigned long)ctl_mem_res->start);
+ ap->ioaddr.data_addr = (void __iomem *)base_mem_res->start;
+
+ if (base_res) { /* only Q40 has IO resources */
+ io_offset = 0x10000;
+ reg_shift = 0;
+ base = (void __iomem *)base_res->start;
+ ctl_base = (void __iomem *)ctl_res->start;
+ } else {
+ base = (void __iomem *)base_mem_res->start;
+ ctl_base = (void __iomem *)ctl_mem_res->start;
+ }
+
+ ap->ioaddr.error_addr = base + io_offset + (1 << reg_shift);
+ ap->ioaddr.feature_addr = base + io_offset + (1 << reg_shift);
+ ap->ioaddr.nsect_addr = base + io_offset + (2 << reg_shift);
+ ap->ioaddr.lbal_addr = base + io_offset + (3 << reg_shift);
+ ap->ioaddr.lbam_addr = base + io_offset + (4 << reg_shift);
+ ap->ioaddr.lbah_addr = base + io_offset + (5 << reg_shift);
+ ap->ioaddr.device_addr = base + io_offset + (6 << reg_shift);
+ ap->ioaddr.status_addr = base + io_offset + (7 << reg_shift);
+ ap->ioaddr.command_addr = base + io_offset + (7 << reg_shift);
+
+ ap->ioaddr.altstatus_addr = ctl_base + io_offset;
+ ap->ioaddr.ctl_addr = ctl_base + io_offset;
+
+ ata_port_desc(ap, "cmd %px ctl %px data %px",
+ base, ctl_base, ap->ioaddr.data_addr);

irq_res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
if (irq_res && irq_res->start > 0) {
diff --git a/drivers/ata/pata_ftide010.c b/drivers/ata/pata_ftide010.c
index 6f6734c09b11..3ab8dca266cc 100644
--- a/drivers/ata/pata_ftide010.c
+++ b/drivers/ata/pata_ftide010.c
@@ -567,6 +567,7 @@ static struct platform_driver pata_ftide010_driver = {
};
module_platform_driver(pata_ftide010_driver);

+MODULE_DESCRIPTION("low level driver for Faraday Technology FTIDE010");
MODULE_AUTHOR("Linus Walleij <linus.walleij@xxxxxxxxxx>");
MODULE_LICENSE("GPL");
MODULE_ALIAS("platform:" DRV_NAME);
diff --git a/drivers/ata/sata_gemini.c b/drivers/ata/sata_gemini.c
index c42cc9bbbc4e..b52e4157443e 100644
--- a/drivers/ata/sata_gemini.c
+++ b/drivers/ata/sata_gemini.c
@@ -428,6 +428,7 @@ static struct platform_driver gemini_sata_driver = {
};
module_platform_driver(gemini_sata_driver);

+MODULE_DESCRIPTION("low level driver for Cortina Systems Gemini SATA bridge");
MODULE_AUTHOR("Linus Walleij <linus.walleij@xxxxxxxxxx>");
MODULE_LICENSE("GPL");
MODULE_ALIAS("platform:" DRV_NAME);
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index 864013019d6b..968090935eb2 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -1643,9 +1643,12 @@ static int null_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
struct nullb_queue *nq = hctx->driver_data;
LIST_HEAD(list);
int nr = 0;
+ struct request *rq;

spin_lock(&nq->poll_lock);
list_splice_init(&nq->poll_list, &list);
+ list_for_each_entry(rq, &list, queuelist)
+ blk_mq_set_request_complete(rq);
spin_unlock(&nq->poll_lock);

while (!list_empty(&list)) {
@@ -1671,16 +1674,21 @@ static enum blk_eh_timer_return null_timeout_rq(struct request *rq)
struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq);

- pr_info("rq %p timed out\n", rq);
-
if (hctx->type == HCTX_TYPE_POLL) {
struct nullb_queue *nq = hctx->driver_data;

spin_lock(&nq->poll_lock);
+ /* The request may have completed meanwhile. */
+ if (blk_mq_request_completed(rq)) {
+ spin_unlock(&nq->poll_lock);
+ return BLK_EH_DONE;
+ }
list_del_init(&rq->queuelist);
spin_unlock(&nq->poll_lock);
}

+ pr_info("rq %p timed out\n", rq);
+
/*
* If the device is marked as blocking (i.e. memory backed or zoned
* device), the submission path may be blocked waiting for resources
diff --git a/drivers/bus/mhi/host/pm.c b/drivers/bus/mhi/host/pm.c
index 083459028a4b..8a4362d75fc4 100644
--- a/drivers/bus/mhi/host/pm.c
+++ b/drivers/bus/mhi/host/pm.c
@@ -470,6 +470,10 @@ static void mhi_pm_disable_transition(struct mhi_controller *mhi_cntrl)

/* Trigger MHI RESET so that the device will not access host memory */
if (!MHI_PM_IN_FATAL_STATE(mhi_cntrl->pm_state)) {
+ /* Skip MHI RESET if in RDDM state */
+ if (mhi_cntrl->rddm_image && mhi_get_exec_env(mhi_cntrl) == MHI_EE_RDDM)
+ goto skip_mhi_reset;
+
dev_dbg(dev, "Triggering MHI Reset in device\n");
mhi_set_mhi_state(mhi_cntrl, MHI_STATE_RESET);

@@ -495,6 +499,7 @@ static void mhi_pm_disable_transition(struct mhi_controller *mhi_cntrl)
}
}

+skip_mhi_reset:
dev_dbg(dev,
"Waiting for all pending event ring processing to complete\n");
mhi_event = mhi_cntrl->mhi_event;
diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c
index a5dbebb1acfc..ea085b14ab7c 100644
--- a/drivers/char/tpm/tpm_crb.c
+++ b/drivers/char/tpm/tpm_crb.c
@@ -775,12 +775,13 @@ static int crb_acpi_add(struct acpi_device *device)
FW_BUG "TPM2 ACPI table has wrong size %u for start method type %d\n",
buf->header.length,
ACPI_TPM2_COMMAND_BUFFER_WITH_PLUTON);
- return -EINVAL;
+ rc = -EINVAL;
+ goto out;
}
crb_pluton = ACPI_ADD_PTR(struct tpm2_crb_pluton, buf, sizeof(*buf));
rc = crb_map_pluton(dev, priv, buf, crb_pluton);
if (rc)
- return rc;
+ goto out;
}

priv->sm = sm;
diff --git a/drivers/clk/imx/clk-pll14xx.c b/drivers/clk/imx/clk-pll14xx.c
index 7150c59bbfc9..0d58d85c375e 100644
--- a/drivers/clk/imx/clk-pll14xx.c
+++ b/drivers/clk/imx/clk-pll14xx.c
@@ -64,8 +64,6 @@ static const struct imx_pll14xx_rate_table imx_pll1443x_tbl[] = {
PLL_1443X_RATE(650000000U, 325, 3, 2, 0),
PLL_1443X_RATE(594000000U, 198, 2, 2, 0),
PLL_1443X_RATE(519750000U, 173, 2, 2, 16384),
- PLL_1443X_RATE(393216000U, 262, 2, 3, 9437),
- PLL_1443X_RATE(361267200U, 361, 3, 3, 17511),
};

struct imx_pll14xx_clk imx_1443x_pll = {
@@ -139,11 +137,10 @@ static void imx_pll14xx_calc_settings(struct clk_pll14xx *pll, unsigned long rat
/*
* Fractional PLL constrains:
*
- * a) 6MHz <= prate <= 25MHz
- * b) 1 <= p <= 63 (1 <= p <= 4 prate = 24MHz)
- * c) 64 <= m <= 1023
- * d) 0 <= s <= 6
- * e) -32768 <= k <= 32767
+ * a) 1 <= p <= 63
+ * b) 64 <= m <= 1023
+ * c) 0 <= s <= 6
+ * d) -32768 <= k <= 32767
*
* fvco = (m * 65536 + k) * prate / (p * 65536)
*/
@@ -186,7 +183,7 @@ static void imx_pll14xx_calc_settings(struct clk_pll14xx *pll, unsigned long rat
}

/* Finally calculate best values */
- for (pdiv = 1; pdiv <= 7; pdiv++) {
+ for (pdiv = 1; pdiv <= 63; pdiv++) {
for (sdiv = 0; sdiv <= 6; sdiv++) {
/* calc mdiv = round(rate * pdiv * 2^sdiv) / prate) */
mdiv = DIV_ROUND_CLOSEST(rate * (pdiv << sdiv), prate);
diff --git a/drivers/clk/qcom/camcc-sc7180.c b/drivers/clk/qcom/camcc-sc7180.c
index 8a4ba7a19ed1..6f56bdbf0204 100644
--- a/drivers/clk/qcom/camcc-sc7180.c
+++ b/drivers/clk/qcom/camcc-sc7180.c
@@ -1664,7 +1664,7 @@ static int cam_cc_sc7180_probe(struct platform_device *pdev)
return ret;
}

- ret = pm_runtime_get(&pdev->dev);
+ ret = pm_runtime_resume_and_get(&pdev->dev);
if (ret)
return ret;

diff --git a/drivers/clk/qcom/dispcc-sm8450.c b/drivers/clk/qcom/dispcc-sm8450.c
index adbfd30bfc96..84db4ff5485a 100644
--- a/drivers/clk/qcom/dispcc-sm8450.c
+++ b/drivers/clk/qcom/dispcc-sm8450.c
@@ -1776,8 +1776,10 @@ static int disp_cc_sm8450_probe(struct platform_device *pdev)
return ret;

regmap = qcom_cc_map(pdev, &disp_cc_sm8450_desc);
- if (IS_ERR(regmap))
- return PTR_ERR(regmap);
+ if (IS_ERR(regmap)) {
+ ret = PTR_ERR(regmap);
+ goto err_put_rpm;
+ }

clk_lucid_evo_pll_configure(&disp_cc_pll0, regmap, &disp_cc_pll0_config);
clk_lucid_evo_pll_configure(&disp_cc_pll1, regmap, &disp_cc_pll1_config);
@@ -1792,9 +1794,16 @@ static int disp_cc_sm8450_probe(struct platform_device *pdev)
regmap_update_bits(regmap, 0xe05c, BIT(0), BIT(0));

ret = qcom_cc_really_probe(pdev, &disp_cc_sm8450_desc, regmap);
+ if (ret)
+ goto err_put_rpm;

pm_runtime_put(&pdev->dev);

+ return 0;
+
+err_put_rpm:
+ pm_runtime_put_sync(&pdev->dev);
+
return ret;
}

diff --git a/drivers/clk/qcom/dispcc-sm8550.c b/drivers/clk/qcom/dispcc-sm8550.c
index 1e5a11081860..b2fae9001ff2 100644
--- a/drivers/clk/qcom/dispcc-sm8550.c
+++ b/drivers/clk/qcom/dispcc-sm8550.c
@@ -1761,8 +1761,10 @@ static int disp_cc_sm8550_probe(struct platform_device *pdev)
return ret;

regmap = qcom_cc_map(pdev, &disp_cc_sm8550_desc);
- if (IS_ERR(regmap))
- return PTR_ERR(regmap);
+ if (IS_ERR(regmap)) {
+ ret = PTR_ERR(regmap);
+ goto err_put_rpm;
+ }

clk_lucid_evo_pll_configure(&disp_cc_pll0, regmap, &disp_cc_pll0_config);
clk_lucid_evo_pll_configure(&disp_cc_pll1, regmap, &disp_cc_pll1_config);
@@ -1777,9 +1779,16 @@ static int disp_cc_sm8550_probe(struct platform_device *pdev)
regmap_update_bits(regmap, 0xe054, BIT(0), BIT(0));

ret = qcom_cc_really_probe(pdev, &disp_cc_sm8550_desc, regmap);
+ if (ret)
+ goto err_put_rpm;

pm_runtime_put(&pdev->dev);

+ return 0;
+
+err_put_rpm:
+ pm_runtime_put_sync(&pdev->dev);
+
return ret;
}

diff --git a/drivers/clk/qcom/gcc-mdm9615.c b/drivers/clk/qcom/gcc-mdm9615.c
index 8bed02a748ab..470a277603a9 100644
--- a/drivers/clk/qcom/gcc-mdm9615.c
+++ b/drivers/clk/qcom/gcc-mdm9615.c
@@ -58,7 +58,7 @@ static struct clk_regmap pll0_vote = {
.enable_mask = BIT(0),
.hw.init = &(struct clk_init_data){
.name = "pll0_vote",
- .parent_names = (const char *[]){ "pll8" },
+ .parent_names = (const char *[]){ "pll0" },
.num_parents = 1,
.ops = &clk_pll_vote_ops,
},
diff --git a/drivers/clk/qcom/lpasscc-sc7280.c b/drivers/clk/qcom/lpasscc-sc7280.c
index 0df2b29e95e3..e6b815aec46a 100644
--- a/drivers/clk/qcom/lpasscc-sc7280.c
+++ b/drivers/clk/qcom/lpasscc-sc7280.c
@@ -118,9 +118,13 @@ static int lpass_cc_sc7280_probe(struct platform_device *pdev)
ret = pm_clk_add(&pdev->dev, "iface");
if (ret < 0) {
dev_err(&pdev->dev, "failed to acquire iface clock\n");
- goto destroy_pm_clk;
+ goto err_destroy_pm_clk;
}

+ ret = pm_runtime_resume_and_get(&pdev->dev);
+ if (ret)
+ goto err_destroy_pm_clk;
+
if (!of_property_read_bool(pdev->dev.of_node, "qcom,adsp-pil-mode")) {
lpass_regmap_config.name = "qdsp6ss";
lpass_regmap_config.max_register = 0x3f;
@@ -128,7 +132,7 @@ static int lpass_cc_sc7280_probe(struct platform_device *pdev)

ret = qcom_cc_probe_by_index(pdev, 0, desc);
if (ret)
- goto destroy_pm_clk;
+ goto err_put_rpm;
}

lpass_regmap_config.name = "top_cc";
@@ -137,11 +141,15 @@ static int lpass_cc_sc7280_probe(struct platform_device *pdev)

ret = qcom_cc_probe_by_index(pdev, 1, desc);
if (ret)
- goto destroy_pm_clk;
+ goto err_put_rpm;
+
+ pm_runtime_put(&pdev->dev);

return 0;

-destroy_pm_clk:
+err_put_rpm:
+ pm_runtime_put_sync(&pdev->dev);
+err_destroy_pm_clk:
pm_clk_destroy(&pdev->dev);

return ret;
diff --git a/drivers/clk/qcom/mss-sc7180.c b/drivers/clk/qcom/mss-sc7180.c
index 5a1407440662..d106bc65470e 100644
--- a/drivers/clk/qcom/mss-sc7180.c
+++ b/drivers/clk/qcom/mss-sc7180.c
@@ -87,11 +87,22 @@ static int mss_sc7180_probe(struct platform_device *pdev)
return ret;
}

+ ret = pm_runtime_resume_and_get(&pdev->dev);
+ if (ret)
+ return ret;
+
ret = qcom_cc_probe(pdev, &mss_sc7180_desc);
if (ret < 0)
- return ret;
+ goto err_put_rpm;
+
+ pm_runtime_put(&pdev->dev);

return 0;
+
+err_put_rpm:
+ pm_runtime_put_sync(&pdev->dev);
+
+ return ret;
}

static const struct dev_pm_ops mss_sc7180_pm_ops = {
diff --git a/drivers/clk/qcom/q6sstop-qcs404.c b/drivers/clk/qcom/q6sstop-qcs404.c
index 780074e05841..26e2d63614ac 100644
--- a/drivers/clk/qcom/q6sstop-qcs404.c
+++ b/drivers/clk/qcom/q6sstop-qcs404.c
@@ -174,21 +174,32 @@ static int q6sstopcc_qcs404_probe(struct platform_device *pdev)
return ret;
}

+ ret = pm_runtime_resume_and_get(&pdev->dev);
+ if (ret)
+ return ret;
+
q6sstop_regmap_config.name = "q6sstop_tcsr";
desc = &tcsr_qcs404_desc;

ret = qcom_cc_probe_by_index(pdev, 1, desc);
if (ret)
- return ret;
+ goto err_put_rpm;

q6sstop_regmap_config.name = "q6sstop_cc";
desc = &q6sstop_qcs404_desc;

ret = qcom_cc_probe_by_index(pdev, 0, desc);
if (ret)
- return ret;
+ goto err_put_rpm;
+
+ pm_runtime_put(&pdev->dev);

return 0;
+
+err_put_rpm:
+ pm_runtime_put_sync(&pdev->dev);
+
+ return ret;
}

static const struct dev_pm_ops q6sstopcc_pm_ops = {
diff --git a/drivers/clk/qcom/turingcc-qcs404.c b/drivers/clk/qcom/turingcc-qcs404.c
index 43184459228f..2cd288d6c3e4 100644
--- a/drivers/clk/qcom/turingcc-qcs404.c
+++ b/drivers/clk/qcom/turingcc-qcs404.c
@@ -125,11 +125,22 @@ static int turingcc_probe(struct platform_device *pdev)
return ret;
}

+ ret = pm_runtime_resume_and_get(&pdev->dev);
+ if (ret)
+ return ret;
+
ret = qcom_cc_probe(pdev, &turingcc_desc);
if (ret < 0)
- return ret;
+ goto err_put_rpm;
+
+ pm_runtime_put(&pdev->dev);

return 0;
+
+err_put_rpm:
+ pm_runtime_put_sync(&pdev->dev);
+
+ return ret;
}

static const struct dev_pm_ops turingcc_pm_ops = {
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index e733a2a1927a..7dd2c615bce2 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -792,6 +792,13 @@ static __always_inline void set_next_event_mem(const int access, unsigned long e
u64 cnt;

ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk);
+
+ /* Timer must be disabled before programming CVAL */
+ if (ctrl & ARCH_TIMER_CTRL_ENABLE) {
+ ctrl &= ~ARCH_TIMER_CTRL_ENABLE;
+ arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
+ }
+
ctrl |= ARCH_TIMER_CTRL_ENABLE;
ctrl &= ~ARCH_TIMER_CTRL_IT_MASK;

diff --git a/drivers/dma/sh/rz-dmac.c b/drivers/dma/sh/rz-dmac.c
index 9479f29692d3..a5af6a666604 100644
--- a/drivers/dma/sh/rz-dmac.c
+++ b/drivers/dma/sh/rz-dmac.c
@@ -9,6 +9,7 @@
* Copyright 2012 Javier Martin, Vista Silicon <javier.martin@xxxxxxxxxxxxxxxxx>
*/

+#include <linux/bitfield.h>
#include <linux/dma-mapping.h>
#include <linux/dmaengine.h>
#include <linux/interrupt.h>
@@ -145,8 +146,8 @@ struct rz_dmac {
#define CHCFG_REQD BIT(3)
#define CHCFG_SEL(bits) ((bits) & 0x07)
#define CHCFG_MEM_COPY (0x80400008)
-#define CHCFG_FILL_DDS(a) (((a) << 16) & GENMASK(19, 16))
-#define CHCFG_FILL_SDS(a) (((a) << 12) & GENMASK(15, 12))
+#define CHCFG_FILL_DDS_MASK GENMASK(19, 16)
+#define CHCFG_FILL_SDS_MASK GENMASK(15, 12)
#define CHCFG_FILL_TM(a) (((a) & BIT(5)) << 22)
#define CHCFG_FILL_AM(a) (((a) & GENMASK(4, 2)) << 6)
#define CHCFG_FILL_LVL(a) (((a) & BIT(1)) << 5)
@@ -607,13 +608,15 @@ static int rz_dmac_config(struct dma_chan *chan,
if (val == CHCFG_DS_INVALID)
return -EINVAL;

- channel->chcfg |= CHCFG_FILL_DDS(val);
+ channel->chcfg &= ~CHCFG_FILL_DDS_MASK;
+ channel->chcfg |= FIELD_PREP(CHCFG_FILL_DDS_MASK, val);

val = rz_dmac_ds_to_val_mapping(config->src_addr_width);
if (val == CHCFG_DS_INVALID)
return -EINVAL;

- channel->chcfg |= CHCFG_FILL_SDS(val);
+ channel->chcfg &= ~CHCFG_FILL_SDS_MASK;
+ channel->chcfg |= FIELD_PREP(CHCFG_FILL_SDS_MASK, val);

return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index b702f499f5fb..923cbebcf520 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -38,6 +38,8 @@
#include <linux/pci.h>
#include <linux/pm_runtime.h>
#include <drm/drm_crtc_helper.h>
+#include <drm/drm_damage_helper.h>
+#include <drm/drm_drv.h>
#include <drm/drm_edid.h>
#include <drm/drm_fb_helper.h>
#include <drm/drm_gem_framebuffer_helper.h>
@@ -529,11 +531,29 @@ bool amdgpu_display_ddc_probe(struct amdgpu_connector *amdgpu_connector,
return true;
}

+static int amdgpu_dirtyfb(struct drm_framebuffer *fb, struct drm_file *file,
+ unsigned int flags, unsigned int color,
+ struct drm_clip_rect *clips, unsigned int num_clips)
+{
+
+ if (file)
+ return -ENOSYS;
+
+ return drm_atomic_helper_dirtyfb(fb, file, flags, color, clips,
+ num_clips);
+}
+
static const struct drm_framebuffer_funcs amdgpu_fb_funcs = {
.destroy = drm_gem_fb_destroy,
.create_handle = drm_gem_fb_create_handle,
};

+static const struct drm_framebuffer_funcs amdgpu_fb_funcs_atomic = {
+ .destroy = drm_gem_fb_destroy,
+ .create_handle = drm_gem_fb_create_handle,
+ .dirty = amdgpu_dirtyfb
+};
+
uint32_t amdgpu_display_supported_domains(struct amdgpu_device *adev,
uint64_t bo_flags)
{
@@ -1136,7 +1156,11 @@ static int amdgpu_display_gem_fb_verify_and_init(struct drm_device *dev,
if (ret)
goto err;

- ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs);
+ if (drm_drv_uses_atomic_modeset(dev))
+ ret = drm_framebuffer_init(dev, &rfb->base,
+ &amdgpu_fb_funcs_atomic);
+ else
+ ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs);

if (ret)
goto err;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
index 31fec5e70d13..23b30783dce3 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
@@ -437,6 +437,7 @@ struct mqd_manager *mqd_manager_init_v11(enum KFD_MQD_TYPE type,
mqd->is_occupied = kfd_is_occupied_cp;
mqd->mqd_size = sizeof(struct v11_compute_mqd);
mqd->get_wave_state = get_wave_state;
+ mqd->mqd_stride = kfd_mqd_stride;
#if defined(CONFIG_DEBUG_FS)
mqd->debugfs_show_mqd = debugfs_show_mqd;
#endif
@@ -452,6 +453,7 @@ struct mqd_manager *mqd_manager_init_v11(enum KFD_MQD_TYPE type,
mqd->destroy_mqd = kfd_destroy_mqd_cp;
mqd->is_occupied = kfd_is_occupied_cp;
mqd->mqd_size = sizeof(struct v11_compute_mqd);
+ mqd->mqd_stride = kfd_mqd_stride;
#if defined(CONFIG_DEBUG_FS)
mqd->debugfs_show_mqd = debugfs_show_mqd;
#endif
@@ -481,6 +483,7 @@ struct mqd_manager *mqd_manager_init_v11(enum KFD_MQD_TYPE type,
mqd->destroy_mqd = kfd_destroy_mqd_sdma;
mqd->is_occupied = kfd_is_occupied_sdma;
mqd->mqd_size = sizeof(struct v11_sdma_mqd);
+ mqd->mqd_stride = kfd_mqd_stride;
#if defined(CONFIG_DEBUG_FS)
mqd->debugfs_show_mqd = debugfs_show_mqd_sdma;
#endif
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 3a7e7d2ce847..3123ea2f4f30 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -5990,7 +5990,7 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,

if (recalculate_timing)
drm_mode_set_crtcinfo(&saved_mode, 0);
- else
+ else if (!old_stream)
drm_mode_set_crtcinfo(&mode, 0);

/*
@@ -7295,7 +7295,7 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm,
if (connector_type == DRM_MODE_CONNECTOR_HDMIA) {
if (!drm_mode_create_hdmi_colorspace_property(&aconnector->base, supported_colorspaces))
drm_connector_attach_colorspace_property(&aconnector->base);
- } else if (connector_type == DRM_MODE_CONNECTOR_DisplayPort ||
+ } else if ((connector_type == DRM_MODE_CONNECTOR_DisplayPort && !aconnector->mst_root) ||
connector_type == DRM_MODE_CONNECTOR_eDP) {
if (!drm_mode_create_dp_colorspace_property(&aconnector->base, supported_colorspaces))
drm_connector_attach_colorspace_property(&aconnector->base);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
index 322668973747..6c84ca2ae373 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
@@ -1260,6 +1260,13 @@ void amdgpu_dm_plane_handle_cursor_update(struct drm_plane *plane,
attributes.rotation_angle = 0;
attributes.attribute_flags.value = 0;

+ /* Enable cursor degamma ROM on DCN3+ for implicit sRGB degamma in DRM
+ * legacy gamma setup.
+ */
+ if (crtc_state->cm_is_degamma_srgb &&
+ adev->dm.dc->caps.color.dpp.gamma_corr)
+ attributes.attribute_flags.bits.ENABLE_CURSOR_DEGAMMA = 1;
+
attributes.pitch = afb->base.pitches[0] / afb->base.format->cpp[0];

if (crtc_state->stream) {
diff --git a/drivers/gpu/drm/amd/display/dc/Makefile b/drivers/gpu/drm/amd/display/dc/Makefile
index 69ffd4424dc7..1b8c2aef4633 100644
--- a/drivers/gpu/drm/amd/display/dc/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/Makefile
@@ -78,3 +78,4 @@ DC_EDID += dc_edid_parser.o
AMD_DISPLAY_DMUB = $(addprefix $(AMDDALPATH)/dc/,$(DC_DMUB))
AMD_DISPLAY_EDID = $(addprefix $(AMDDALPATH)/dc/,$(DC_EDID))
AMD_DISPLAY_FILES += $(AMD_DISPLAY_DMUB) $(AMD_DISPLAY_EDID)
+
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index d133e4186a52..1729fb727333 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -2061,12 +2061,12 @@ enum dc_status dc_commit_streams(struct dc *dc,
}
}

- /* Check for case where we are going from odm 2:1 to max
- * pipe scenario. For these cases, we will call
- * commit_minimal_transition_state() to exit out of odm 2:1
- * first before processing new streams
+ /* ODM Combine 2:1 power optimization is only applied for single stream
+ * scenario, it uses extra pipes than needed to reduce power consumption
+ * We need to switch off this feature to make room for new streams.
*/
- if (stream_count == dc->res_pool->pipe_count) {
+ if (stream_count > dc->current_state->stream_count &&
+ dc->current_state->stream_count == 1) {
for (i = 0; i < dc->res_pool->pipe_count; i++) {
pipe = &dc->current_state->res_ctx.pipe_ctx[i];
if (pipe->next_odm_pipe)
@@ -3589,6 +3589,45 @@ static void commit_planes_for_stream_fast(struct dc *dc,
top_pipe_to_program->stream->update_flags.raw = 0;
}

+static void wait_for_outstanding_hw_updates(struct dc *dc, const struct dc_state *dc_context)
+{
+/*
+ * This function calls HWSS to wait for any potentially double buffered
+ * operations to complete. It should be invoked as a pre-amble prior
+ * to full update programming before asserting any HW locks.
+ */
+ int pipe_idx;
+ int opp_inst;
+ int opp_count = dc->res_pool->pipe_count;
+ struct hubp *hubp;
+ int mpcc_inst;
+ const struct pipe_ctx *pipe_ctx;
+
+ for (pipe_idx = 0; pipe_idx < dc->res_pool->pipe_count; pipe_idx++) {
+ pipe_ctx = &dc_context->res_ctx.pipe_ctx[pipe_idx];
+
+ if (!pipe_ctx->stream)
+ continue;
+
+ if (pipe_ctx->stream_res.tg->funcs->wait_drr_doublebuffer_pending_clear)
+ pipe_ctx->stream_res.tg->funcs->wait_drr_doublebuffer_pending_clear(pipe_ctx->stream_res.tg);
+
+ hubp = pipe_ctx->plane_res.hubp;
+ if (!hubp)
+ continue;
+
+ mpcc_inst = hubp->inst;
+ // MPCC inst is equal to pipe index in practice
+ for (opp_inst = 0; opp_inst < opp_count; opp_inst++) {
+ if (dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst]) {
+ dc->res_pool->mpc->funcs->wait_for_idle(dc->res_pool->mpc, mpcc_inst);
+ dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst] = false;
+ break;
+ }
+ }
+ }
+}
+
static void commit_planes_for_stream(struct dc *dc,
struct dc_surface_update *srf_updates,
int surface_count,
@@ -3607,24 +3646,9 @@ static void commit_planes_for_stream(struct dc *dc,
// dc->current_state anymore, so we have to cache it before we apply
// the new SubVP context
subvp_prev_use = false;
-
-
dc_z10_restore(dc);
-
- if (update_type == UPDATE_TYPE_FULL) {
- /* wait for all double-buffer activity to clear on all pipes */
- int pipe_idx;
-
- for (pipe_idx = 0; pipe_idx < dc->res_pool->pipe_count; pipe_idx++) {
- struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[pipe_idx];
-
- if (!pipe_ctx->stream)
- continue;
-
- if (pipe_ctx->stream_res.tg->funcs->wait_drr_doublebuffer_pending_clear)
- pipe_ctx->stream_res.tg->funcs->wait_drr_doublebuffer_pending_clear(pipe_ctx->stream_res.tg);
- }
- }
+ if (update_type == UPDATE_TYPE_FULL)
+ wait_for_outstanding_hw_updates(dc, context);

if (update_type == UPDATE_TYPE_FULL) {
dc_allow_idle_optimizations(dc, false);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
index 8e9384094f6d..f2f55565e98a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
@@ -212,8 +212,9 @@ struct mpcc *mpc1_insert_plane(
/* check insert_above_mpcc exist in tree->opp_list */
struct mpcc *temp_mpcc = tree->opp_list;

- while (temp_mpcc && temp_mpcc->mpcc_bot != insert_above_mpcc)
- temp_mpcc = temp_mpcc->mpcc_bot;
+ if (temp_mpcc != insert_above_mpcc)
+ while (temp_mpcc && temp_mpcc->mpcc_bot != insert_above_mpcc)
+ temp_mpcc = temp_mpcc->mpcc_bot;
if (temp_mpcc == NULL)
return NULL;
}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index 5cfa37804d7c..7c344132a007 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -1580,17 +1580,6 @@ static void dcn20_update_dchubp_dpp(
|| plane_state->update_flags.bits.global_alpha_change
|| plane_state->update_flags.bits.per_pixel_alpha_change) {
// MPCC inst is equal to pipe index in practice
- int mpcc_inst = hubp->inst;
- int opp_inst;
- int opp_count = dc->res_pool->pipe_count;
-
- for (opp_inst = 0; opp_inst < opp_count; opp_inst++) {
- if (dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst]) {
- dc->res_pool->mpc->funcs->wait_for_idle(dc->res_pool->mpc, mpcc_inst);
- dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst] = false;
- break;
- }
- }
hws->funcs.update_mpcc(dc, pipe_ctx);
}

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
index 8ae5ddbd1b27..e6b9c2469a56 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
@@ -1099,6 +1099,11 @@ void dcn20_calculate_dlg_params(struct dc *dc,
context->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz =
pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000;
context->res_ctx.pipe_ctx[i].pipe_dlg_param = pipes[pipe_idx].pipe.dest;
+ if (dc->ctx->dce_version < DCN_VERSION_3_1 &&
+ context->res_ctx.pipe_ctx[i].stream->adaptive_sync_infopacket.valid)
+ dcn20_adjust_freesync_v_startup(
+ &context->res_ctx.pipe_ctx[i].stream->timing,
+ &context->res_ctx.pipe_ctx[i].pipe_dlg_param.vstartup_start);

pipe_idx++;
}
@@ -1927,7 +1932,6 @@ static bool dcn20_validate_bandwidth_internal(struct dc *dc, struct dc_state *co
int vlevel = 0;
int pipe_split_from[MAX_PIPES];
int pipe_cnt = 0;
- int i = 0;
display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_ATOMIC);
DC_LOGGER_INIT(dc->ctx->logger);

@@ -1951,15 +1955,6 @@ static bool dcn20_validate_bandwidth_internal(struct dc *dc, struct dc_state *co
dcn20_calculate_wm(dc, context, pipes, &pipe_cnt, pipe_split_from, vlevel, fast_validate);
dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel);

- for (i = 0; i < dc->res_pool->pipe_count; i++) {
- if (!context->res_ctx.pipe_ctx[i].stream)
- continue;
- if (context->res_ctx.pipe_ctx[i].stream->adaptive_sync_infopacket.valid)
- dcn20_adjust_freesync_v_startup(
- &context->res_ctx.pipe_ctx[i].stream->timing,
- &context->res_ctx.pipe_ctx[i].pipe_dlg_param.vstartup_start);
- }
-
BW_VAL_TRACE_END_WATERMARKS();

goto validate_out;
@@ -2232,7 +2227,6 @@ bool dcn21_validate_bandwidth_fp(struct dc *dc,
int vlevel = 0;
int pipe_split_from[MAX_PIPES];
int pipe_cnt = 0;
- int i = 0;
display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_ATOMIC);
DC_LOGGER_INIT(dc->ctx->logger);

@@ -2261,15 +2255,6 @@ bool dcn21_validate_bandwidth_fp(struct dc *dc,
dcn21_calculate_wm(dc, context, pipes, &pipe_cnt, pipe_split_from, vlevel, fast_validate);
dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel);

- for (i = 0; i < dc->res_pool->pipe_count; i++) {
- if (!context->res_ctx.pipe_ctx[i].stream)
- continue;
- if (context->res_ctx.pipe_ctx[i].stream->adaptive_sync_infopacket.valid)
- dcn20_adjust_freesync_v_startup(
- &context->res_ctx.pipe_ctx[i].stream->timing,
- &context->res_ctx.pipe_ctx[i].pipe_dlg_param.vstartup_start);
- }
-
BW_VAL_TRACE_END_WATERMARKS();

goto validate_out;
diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
index dbd60811f95d..ef3a67409021 100644
--- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
+++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
@@ -338,7 +338,9 @@ static void apply_below_the_range(struct core_freesync *core_freesync,
* - Delta for CEIL: delta_from_mid_point_in_us_1
* - Delta for FLOOR: delta_from_mid_point_in_us_2
*/
- if ((last_render_time_in_us / mid_point_frames_ceil) < in_out_vrr->min_duration_in_us) {
+ if (mid_point_frames_ceil &&
+ (last_render_time_in_us / mid_point_frames_ceil) <
+ in_out_vrr->min_duration_in_us) {
/* Check for out of range.
* If using CEIL produces a value that is out of range,
* then we are forced to use FLOOR.
@@ -385,8 +387,9 @@ static void apply_below_the_range(struct core_freesync *core_freesync,
/* Either we've calculated the number of frames to insert,
* or we need to insert min duration frames
*/
- if (last_render_time_in_us / frames_to_insert <
- in_out_vrr->min_duration_in_us){
+ if (frames_to_insert &&
+ (last_render_time_in_us / frames_to_insert) <
+ in_out_vrr->min_duration_in_us){
frames_to_insert -= (frames_to_insert > 1) ?
1 : 0;
}
diff --git a/drivers/gpu/drm/ast/ast_post.c b/drivers/gpu/drm/ast/ast_post.c
index a005aec18a02..0262aaafdb1c 100644
--- a/drivers/gpu/drm/ast/ast_post.c
+++ b/drivers/gpu/drm/ast/ast_post.c
@@ -291,7 +291,7 @@ static void ast_init_dram_reg(struct drm_device *dev)
;
} while (ast_read32(ast, 0x10100) != 0xa8);
} else {/* AST2100/1100 */
- if (ast->chip == AST2100 || ast->chip == 2200)
+ if (ast->chip == AST2100 || ast->chip == AST2200)
dram_reg_info = ast2100_dram_table_data;
else
dram_reg_info = ast1100_dram_table_data;
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index e99a6fa03d45..a7e677598004 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -58,6 +58,7 @@ struct i915_perf_group;

typedef u32 intel_engine_mask_t;
#define ALL_ENGINES ((intel_engine_mask_t)~0ul)
+#define VIRTUAL_ENGINES BIT(BITS_PER_TYPE(intel_engine_mask_t) - 1)

struct intel_hw_status_page {
struct list_head timelines;
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index a0e3ef1c65d2..b5b7f2fe8c78 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -5470,6 +5470,9 @@ guc_create_virtual(struct intel_engine_cs **siblings, unsigned int count,

ve->base.flags = I915_ENGINE_IS_VIRTUAL;

+ BUILD_BUG_ON(ilog2(VIRTUAL_ENGINES) < I915_NUM_ENGINES);
+ ve->base.mask = VIRTUAL_ENGINES;
+
intel_context_init(&ve->context, &ve->base);

for (n = 0; n < count; n++) {
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 4ec85308379a..ef5517ecd9a0 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -1174,6 +1174,7 @@ static int is_2MB_gtt_possible(struct intel_vgpu *vgpu,
{
const struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
kvm_pfn_t pfn;
+ int ret;

if (!HAS_PAGE_SIZES(vgpu->gvt->gt->i915, I915_GTT_PAGE_SIZE_2M))
return 0;
@@ -1183,7 +1184,13 @@ static int is_2MB_gtt_possible(struct intel_vgpu *vgpu,
pfn = gfn_to_pfn(vgpu->vfio_device.kvm, ops->get_pfn(entry));
if (is_error_noslot_pfn(pfn))
return -EINVAL;
- return PageTransHuge(pfn_to_page(pfn));
+
+ if (!pfn_valid(pfn))
+ return -EINVAL;
+
+ ret = PageTransHuge(pfn_to_page(pfn));
+ kvm_release_pfn_clean(pfn);
+ return ret;
}

static int split_2MB_gtt_entry(struct intel_vgpu *vgpu,
@@ -2875,24 +2882,6 @@ void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu, bool invalidate_old)
ggtt_invalidate(gvt->gt);
}

-/**
- * intel_vgpu_reset_gtt - reset the all GTT related status
- * @vgpu: a vGPU
- *
- * This function is called from vfio core to reset reset all
- * GTT related status, including GGTT, PPGTT, scratch page.
- *
- */
-void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu)
-{
- /* Shadow pages are only created when there is no page
- * table tracking data, so remove page tracking data after
- * removing the shadow pages.
- */
- intel_vgpu_destroy_all_ppgtt_mm(vgpu);
- intel_vgpu_reset_ggtt(vgpu, true);
-}
-
/**
* intel_gvt_restore_ggtt - restore all vGPU's ggtt entries
* @gvt: intel gvt device
diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h
index a3b0f59ec8bd..4cb183e06e95 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.h
+++ b/drivers/gpu/drm/i915/gvt/gtt.h
@@ -224,7 +224,6 @@ void intel_vgpu_reset_ggtt(struct intel_vgpu *vgpu, bool invalidate_old);
void intel_vgpu_invalidate_ppgtt(struct intel_vgpu *vgpu);

int intel_gvt_init_gtt(struct intel_gvt *gvt);
-void intel_vgpu_reset_gtt(struct intel_vgpu *vgpu);
void intel_gvt_clean_gtt(struct intel_gvt *gvt);

struct intel_vgpu_mm *intel_gvt_find_ppgtt_mm(struct intel_vgpu *vgpu,
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 833b73edefdb..eb2a3000ad66 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -134,9 +134,7 @@ static void i915_fence_release(struct dma_fence *fence)
i915_sw_fence_fini(&rq->semaphore);

/*
- * Keep one request on each engine for reserved use under mempressure
- * do not use with virtual engines as this really is only needed for
- * kernel contexts.
+ * Keep one request on each engine for reserved use under mempressure.
*
* We do not hold a reference to the engine here and so have to be
* very careful in what rq->engine we poke. The virtual engine is
@@ -166,8 +164,7 @@ static void i915_fence_release(struct dma_fence *fence)
* know that if the rq->execution_mask is a single bit, rq->engine
* can be a physical engine with the exact corresponding mask.
*/
- if (!intel_engine_is_virtual(rq->engine) &&
- is_power_of_2(rq->execution_mask) &&
+ if (is_power_of_2(rq->execution_mask) &&
!cmpxchg(&rq->engine->request_pool, NULL, rq))
return;

diff --git a/drivers/gpu/drm/mxsfb/mxsfb_kms.c b/drivers/gpu/drm/mxsfb/mxsfb_kms.c
index 3bcc9c0f2019..7ed2516b6de0 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_kms.c
+++ b/drivers/gpu/drm/mxsfb/mxsfb_kms.c
@@ -611,6 +611,14 @@ static void mxsfb_plane_overlay_atomic_update(struct drm_plane *plane,
writel(ctrl, mxsfb->base + LCDC_AS_CTRL);
}

+static void mxsfb_plane_overlay_atomic_disable(struct drm_plane *plane,
+ struct drm_atomic_state *state)
+{
+ struct mxsfb_drm_private *mxsfb = to_mxsfb_drm_private(plane->dev);
+
+ writel(0, mxsfb->base + LCDC_AS_CTRL);
+}
+
static bool mxsfb_format_mod_supported(struct drm_plane *plane,
uint32_t format,
uint64_t modifier)
@@ -626,6 +634,7 @@ static const struct drm_plane_helper_funcs mxsfb_plane_primary_helper_funcs = {
static const struct drm_plane_helper_funcs mxsfb_plane_overlay_helper_funcs = {
.atomic_check = mxsfb_plane_atomic_check,
.atomic_update = mxsfb_plane_overlay_atomic_update,
+ .atomic_disable = mxsfb_plane_overlay_atomic_disable,
};

static const struct drm_plane_funcs mxsfb_plane_funcs = {
diff --git a/drivers/gpu/drm/virtio/virtgpu_submit.c b/drivers/gpu/drm/virtio/virtgpu_submit.c
index cf3c04b16a7a..1d010c66910d 100644
--- a/drivers/gpu/drm/virtio/virtgpu_submit.c
+++ b/drivers/gpu/drm/virtio/virtgpu_submit.c
@@ -64,13 +64,9 @@ static int virtio_gpu_fence_event_create(struct drm_device *dev,
struct virtio_gpu_fence *fence,
u32 ring_idx)
{
- struct virtio_gpu_fpriv *vfpriv = file->driver_priv;
struct virtio_gpu_fence_event *e = NULL;
int ret;

- if (!(vfpriv->ring_idx_mask & BIT_ULL(ring_idx)))
- return 0;
-
e = kzalloc(sizeof(*e), GFP_KERNEL);
if (!e)
return -ENOMEM;
@@ -164,18 +160,30 @@ static int virtio_gpu_init_submit(struct virtio_gpu_submit *submit,
struct virtio_gpu_fpriv *vfpriv = file->driver_priv;
struct virtio_gpu_device *vgdev = dev->dev_private;
struct virtio_gpu_fence *out_fence;
+ bool drm_fence_event;
int err;

memset(submit, 0, sizeof(*submit));

- out_fence = virtio_gpu_fence_alloc(vgdev, fence_ctx, ring_idx);
- if (!out_fence)
- return -ENOMEM;
-
- err = virtio_gpu_fence_event_create(dev, file, out_fence, ring_idx);
- if (err) {
- dma_fence_put(&out_fence->f);
- return err;
+ if ((exbuf->flags & VIRTGPU_EXECBUF_RING_IDX) &&
+ (vfpriv->ring_idx_mask & BIT_ULL(ring_idx)))
+ drm_fence_event = true;
+ else
+ drm_fence_event = false;
+
+ if ((exbuf->flags & VIRTGPU_EXECBUF_FENCE_FD_OUT) ||
+ exbuf->num_bo_handles ||
+ drm_fence_event)
+ out_fence = virtio_gpu_fence_alloc(vgdev, fence_ctx, ring_idx);
+ else
+ out_fence = NULL;
+
+ if (drm_fence_event) {
+ err = virtio_gpu_fence_event_create(dev, file, out_fence, ring_idx);
+ if (err) {
+ dma_fence_put(&out_fence->f);
+ return err;
+ }
}

submit->out_fence = out_fence;
diff --git a/drivers/hwspinlock/qcom_hwspinlock.c b/drivers/hwspinlock/qcom_hwspinlock.c
index 9cf186362ae2..3f08cd4a5c28 100644
--- a/drivers/hwspinlock/qcom_hwspinlock.c
+++ b/drivers/hwspinlock/qcom_hwspinlock.c
@@ -69,9 +69,18 @@ static const struct hwspinlock_ops qcom_hwspinlock_ops = {
.unlock = qcom_hwspinlock_unlock,
};

+static const struct regmap_config sfpb_mutex_config = {
+ .reg_bits = 32,
+ .reg_stride = 4,
+ .val_bits = 32,
+ .max_register = 0x100,
+ .fast_io = true,
+};
+
static const struct qcom_hwspinlock_of_data of_sfpb_mutex = {
.offset = 0x4,
.stride = 0x4,
+ .regmap_config = &sfpb_mutex_config,
};

static const struct regmap_config tcsr_msm8226_mutex_config = {
diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c
index 2fefbe55c167..6c43992c8cf6 100644
--- a/drivers/i3c/master/svc-i3c-master.c
+++ b/drivers/i3c/master/svc-i3c-master.c
@@ -156,6 +156,7 @@ struct svc_i3c_regs_save {
* @base: I3C master controller
* @dev: Corresponding device
* @regs: Memory mapping
+ * @saved_regs: Volatile values for PM operations
* @free_slots: Bit array of available slots
* @addrs: Array containing the dynamic addresses of each attached device
* @descs: Array of descriptors, one per attached device
diff --git a/drivers/input/keyboard/tca6416-keypad.c b/drivers/input/keyboard/tca6416-keypad.c
index 2f745cabf4f2..d20cbddfae68 100644
--- a/drivers/input/keyboard/tca6416-keypad.c
+++ b/drivers/input/keyboard/tca6416-keypad.c
@@ -148,7 +148,7 @@ static int tca6416_keys_open(struct input_dev *dev)
if (chip->use_polling)
schedule_delayed_work(&chip->dwork, msecs_to_jiffies(100));
else
- enable_irq(chip->irqnum);
+ enable_irq(chip->client->irq);

return 0;
}
@@ -160,7 +160,7 @@ static void tca6416_keys_close(struct input_dev *dev)
if (chip->use_polling)
cancel_delayed_work_sync(&chip->dwork);
else
- disable_irq(chip->irqnum);
+ disable_irq(chip->client->irq);
}

static int tca6416_setup_registers(struct tca6416_keypad_chip *chip)
@@ -266,12 +266,7 @@ static int tca6416_keypad_probe(struct i2c_client *client)
goto fail1;

if (!chip->use_polling) {
- if (pdata->irq_is_gpio)
- chip->irqnum = gpio_to_irq(client->irq);
- else
- chip->irqnum = client->irq;
-
- error = request_threaded_irq(chip->irqnum, NULL,
+ error = request_threaded_irq(client->irq, NULL,
tca6416_keys_isr,
IRQF_TRIGGER_FALLING |
IRQF_ONESHOT | IRQF_NO_AUTOEN,
@@ -279,7 +274,7 @@ static int tca6416_keypad_probe(struct i2c_client *client)
if (error) {
dev_dbg(&client->dev,
"Unable to claim irq %d; error %d\n",
- chip->irqnum, error);
+ client->irq, error);
goto fail1;
}
}
@@ -297,10 +292,8 @@ static int tca6416_keypad_probe(struct i2c_client *client)
return 0;

fail2:
- if (!chip->use_polling) {
- free_irq(chip->irqnum, chip);
- enable_irq(chip->irqnum);
- }
+ if (!chip->use_polling)
+ free_irq(client->irq, chip);
fail1:
input_free_device(input);
kfree(chip);
@@ -311,10 +304,8 @@ static void tca6416_keypad_remove(struct i2c_client *client)
{
struct tca6416_keypad_chip *chip = i2c_get_clientdata(client);

- if (!chip->use_polling) {
- free_irq(chip->irqnum, chip);
- enable_irq(chip->irqnum);
- }
+ if (!chip->use_polling)
+ free_irq(client->irq, chip);

input_unregister_device(chip->input);
kfree(chip);
@@ -323,10 +314,9 @@ static void tca6416_keypad_remove(struct i2c_client *client)
static int tca6416_keypad_suspend(struct device *dev)
{
struct i2c_client *client = to_i2c_client(dev);
- struct tca6416_keypad_chip *chip = i2c_get_clientdata(client);

if (device_may_wakeup(dev))
- enable_irq_wake(chip->irqnum);
+ enable_irq_wake(client->irq);

return 0;
}
@@ -334,10 +324,9 @@ static int tca6416_keypad_suspend(struct device *dev)
static int tca6416_keypad_resume(struct device *dev)
{
struct i2c_client *client = to_i2c_client(dev);
- struct tca6416_keypad_chip *chip = i2c_get_clientdata(client);

if (device_may_wakeup(dev))
- disable_irq_wake(chip->irqnum);
+ disable_irq_wake(client->irq);

return 0;
}
diff --git a/drivers/input/misc/iqs7222.c b/drivers/input/misc/iqs7222.c
index 096b0925f41b..acb95048e823 100644
--- a/drivers/input/misc/iqs7222.c
+++ b/drivers/input/misc/iqs7222.c
@@ -1381,9 +1381,6 @@ static int iqs7222_ati_trigger(struct iqs7222_private *iqs7222)
if (error)
return error;

- sys_setup &= ~IQS7222_SYS_SETUP_INTF_MODE_MASK;
- sys_setup &= ~IQS7222_SYS_SETUP_PWR_MODE_MASK;
-
for (i = 0; i < IQS7222_NUM_RETRIES; i++) {
/*
* Trigger ATI from streaming and normal-power modes so that
@@ -1561,8 +1558,11 @@ static int iqs7222_dev_init(struct iqs7222_private *iqs7222, int dir)
return error;
}

- if (dir == READ)
+ if (dir == READ) {
+ iqs7222->sys_setup[0] &= ~IQS7222_SYS_SETUP_INTF_MODE_MASK;
+ iqs7222->sys_setup[0] &= ~IQS7222_SYS_SETUP_PWR_MODE_MASK;
return 0;
+ }

return iqs7222_ati_trigger(iqs7222);
}
diff --git a/drivers/mailbox/qcom-ipcc.c b/drivers/mailbox/qcom-ipcc.c
index 7e27acf6c0cc..f597a1bd5684 100644
--- a/drivers/mailbox/qcom-ipcc.c
+++ b/drivers/mailbox/qcom-ipcc.c
@@ -227,10 +227,8 @@ static int qcom_ipcc_setup_mbox(struct qcom_ipcc *ipcc,
ret = of_parse_phandle_with_args(client_dn, "mboxes",
"#mbox-cells", j, &curr_ph);
of_node_put(curr_ph.np);
- if (!ret && curr_ph.np == controller_dn) {
+ if (!ret && curr_ph.np == controller_dn)
ipcc->num_chans++;
- break;
- }
}
}

diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index 5a134fa8a174..42c4f603ec81 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -756,6 +756,7 @@ static int fastrpc_map_create(struct fastrpc_user *fl, int fd,
{
struct fastrpc_session_ctx *sess = fl->sctx;
struct fastrpc_map *map = NULL;
+ struct sg_table *table;
int err = 0;

if (!fastrpc_map_lookup(fl, fd, ppmap, true))
@@ -783,11 +784,12 @@ static int fastrpc_map_create(struct fastrpc_user *fl, int fd,
goto attach_err;
}

- map->table = dma_buf_map_attachment_unlocked(map->attach, DMA_BIDIRECTIONAL);
- if (IS_ERR(map->table)) {
- err = PTR_ERR(map->table);
+ table = dma_buf_map_attachment_unlocked(map->attach, DMA_BIDIRECTIONAL);
+ if (IS_ERR(table)) {
+ err = PTR_ERR(table);
goto map_err;
}
+ map->table = table;

if (attr & FASTRPC_ATTR_SECUREMAP) {
map->phys = sg_phys(map->table->sgl);
@@ -1871,7 +1873,11 @@ static int fastrpc_req_mmap(struct fastrpc_user *fl, char __user *argp)
return -EINVAL;
}

- err = fastrpc_buf_alloc(fl, fl->sctx->dev, req.size, &buf);
+ if (req.flags == ADSP_MMAP_REMOTE_HEAP_ADDR)
+ err = fastrpc_remote_heap_alloc(fl, dev, req.size, &buf);
+ else
+ err = fastrpc_buf_alloc(fl, dev, req.size, &buf);
+
if (err) {
dev_err(dev, "failed to allocate buffer\n");
return err;
@@ -1910,12 +1916,8 @@ static int fastrpc_req_mmap(struct fastrpc_user *fl, char __user *argp)

/* Add memory to static PD pool, protection thru hypervisor */
if (req.flags == ADSP_MMAP_REMOTE_HEAP_ADDR && fl->cctx->vmcount) {
- struct qcom_scm_vmperm perm;
-
- perm.vmid = QCOM_SCM_VMID_HLOS;
- perm.perm = QCOM_SCM_PERM_RWX;
- err = qcom_scm_assign_mem(buf->phys, buf->size,
- &fl->cctx->perms, &perm, 1);
+ err = qcom_scm_assign_mem(buf->phys, (u64)buf->size,
+ &fl->cctx->perms, fl->cctx->vmperms, fl->cctx->vmcount);
if (err) {
dev_err(fl->sctx->dev, "Failed to assign memory phys 0x%llx size 0x%llx err %d",
buf->phys, buf->size, err);
diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
index d8418d7fcc37..39661e23d7d4 100644
--- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c
+++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
@@ -272,6 +272,7 @@ struct brcmnand_controller {
const unsigned int *page_sizes;
unsigned int page_size_shift;
unsigned int max_oob;
+ u32 ecc_level_shift;
u32 features;

/* for low-power standby/resume only */
@@ -596,6 +597,34 @@ enum {
INTFC_CTLR_READY = BIT(31),
};

+/***********************************************************************
+ * NAND ACC CONTROL bitfield
+ *
+ * Some bits have remained constant throughout hardware revision, while
+ * others have shifted around.
+ ***********************************************************************/
+
+/* Constant for all versions (where supported) */
+enum {
+ /* See BRCMNAND_HAS_CACHE_MODE */
+ ACC_CONTROL_CACHE_MODE = BIT(22),
+
+ /* See BRCMNAND_HAS_PREFETCH */
+ ACC_CONTROL_PREFETCH = BIT(23),
+
+ ACC_CONTROL_PAGE_HIT = BIT(24),
+ ACC_CONTROL_WR_PREEMPT = BIT(25),
+ ACC_CONTROL_PARTIAL_PAGE = BIT(26),
+ ACC_CONTROL_RD_ERASED = BIT(27),
+ ACC_CONTROL_FAST_PGM_RDIN = BIT(28),
+ ACC_CONTROL_WR_ECC = BIT(30),
+ ACC_CONTROL_RD_ECC = BIT(31),
+};
+
+#define ACC_CONTROL_ECC_SHIFT 16
+/* Only for v7.2 */
+#define ACC_CONTROL_ECC_EXT_SHIFT 13
+
static inline bool brcmnand_non_mmio_ops(struct brcmnand_controller *ctrl)
{
#if IS_ENABLED(CONFIG_MTD_NAND_BRCMNAND_BCMA)
@@ -737,6 +766,12 @@ static int brcmnand_revision_init(struct brcmnand_controller *ctrl)
else if (of_property_read_bool(ctrl->dev->of_node, "brcm,nand-has-wp"))
ctrl->features |= BRCMNAND_HAS_WP;

+ /* v7.2 has different ecc level shift in the acc register */
+ if (ctrl->nand_version == 0x0702)
+ ctrl->ecc_level_shift = ACC_CONTROL_ECC_EXT_SHIFT;
+ else
+ ctrl->ecc_level_shift = ACC_CONTROL_ECC_SHIFT;
+
return 0;
}

@@ -931,30 +966,6 @@ static inline int brcmnand_cmd_shift(struct brcmnand_controller *ctrl)
return 0;
}

-/***********************************************************************
- * NAND ACC CONTROL bitfield
- *
- * Some bits have remained constant throughout hardware revision, while
- * others have shifted around.
- ***********************************************************************/
-
-/* Constant for all versions (where supported) */
-enum {
- /* See BRCMNAND_HAS_CACHE_MODE */
- ACC_CONTROL_CACHE_MODE = BIT(22),
-
- /* See BRCMNAND_HAS_PREFETCH */
- ACC_CONTROL_PREFETCH = BIT(23),
-
- ACC_CONTROL_PAGE_HIT = BIT(24),
- ACC_CONTROL_WR_PREEMPT = BIT(25),
- ACC_CONTROL_PARTIAL_PAGE = BIT(26),
- ACC_CONTROL_RD_ERASED = BIT(27),
- ACC_CONTROL_FAST_PGM_RDIN = BIT(28),
- ACC_CONTROL_WR_ECC = BIT(30),
- ACC_CONTROL_RD_ECC = BIT(31),
-};
-
static inline u32 brcmnand_spare_area_mask(struct brcmnand_controller *ctrl)
{
if (ctrl->nand_version == 0x0702)
@@ -967,18 +978,15 @@ static inline u32 brcmnand_spare_area_mask(struct brcmnand_controller *ctrl)
return GENMASK(4, 0);
}

-#define NAND_ACC_CONTROL_ECC_SHIFT 16
-#define NAND_ACC_CONTROL_ECC_EXT_SHIFT 13
-
static inline u32 brcmnand_ecc_level_mask(struct brcmnand_controller *ctrl)
{
u32 mask = (ctrl->nand_version >= 0x0600) ? 0x1f : 0x0f;

- mask <<= NAND_ACC_CONTROL_ECC_SHIFT;
+ mask <<= ACC_CONTROL_ECC_SHIFT;

/* v7.2 includes additional ECC levels */
- if (ctrl->nand_version >= 0x0702)
- mask |= 0x7 << NAND_ACC_CONTROL_ECC_EXT_SHIFT;
+ if (ctrl->nand_version == 0x0702)
+ mask |= 0x7 << ACC_CONTROL_ECC_EXT_SHIFT;

return mask;
}
@@ -992,8 +1000,8 @@ static void brcmnand_set_ecc_enabled(struct brcmnand_host *host, int en)

if (en) {
acc_control |= ecc_flags; /* enable RD/WR ECC */
- acc_control |= host->hwcfg.ecc_level
- << NAND_ACC_CONTROL_ECC_SHIFT;
+ acc_control &= ~brcmnand_ecc_level_mask(ctrl);
+ acc_control |= host->hwcfg.ecc_level << ctrl->ecc_level_shift;
} else {
acc_control &= ~ecc_flags; /* disable RD/WR ECC */
acc_control &= ~brcmnand_ecc_level_mask(ctrl);
@@ -1072,6 +1080,14 @@ static int bcmnand_ctrl_poll_status(struct brcmnand_controller *ctrl,
cpu_relax();
} while (time_after(limit, jiffies));

+ /*
+ * do a final check after time out in case the CPU was busy and the driver
+ * did not get enough time to perform the polling to avoid false alarms
+ */
+ val = brcmnand_read_reg(ctrl, BRCMNAND_INTFC_STATUS);
+ if ((val & mask) == expected_val)
+ return 0;
+
dev_warn(ctrl->dev, "timeout on status poll (expected %x got %x)\n",
expected_val, val & mask);

@@ -1461,19 +1477,33 @@ static int write_oob_to_regs(struct brcmnand_controller *ctrl, int i,
const u8 *oob, int sas, int sector_1k)
{
int tbytes = sas << sector_1k;
- int j;
+ int j, k = 0;
+ u32 last = 0xffffffff;
+ u8 *plast = (u8 *)&last;

/* Adjust OOB values for 1K sector size */
if (sector_1k && (i & 0x01))
tbytes = max(0, tbytes - (int)ctrl->max_oob);
tbytes = min_t(int, tbytes, ctrl->max_oob);

- for (j = 0; j < tbytes; j += 4)
+ /*
+ * tbytes may not be multiple of words. Make sure we don't read out of
+ * the boundary and stop at last word.
+ */
+ for (j = 0; (j + 3) < tbytes; j += 4)
oob_reg_write(ctrl, j,
(oob[j + 0] << 24) |
(oob[j + 1] << 16) |
(oob[j + 2] << 8) |
(oob[j + 3] << 0));
+
+ /* handle the remaing bytes */
+ while (j < tbytes)
+ plast[k++] = oob[j++];
+
+ if (tbytes & 0x3)
+ oob_reg_write(ctrl, (tbytes & ~0x3), (__force u32)cpu_to_be32(last));
+
return tbytes;
}

@@ -1592,7 +1622,17 @@ static void brcmnand_send_cmd(struct brcmnand_host *host, int cmd)

dev_dbg(ctrl->dev, "send native cmd %d addr 0x%llx\n", cmd, cmd_addr);

- BUG_ON(ctrl->cmd_pending != 0);
+ /*
+ * If we came here through _panic_write and there is a pending
+ * command, try to wait for it. If it times out, rather than
+ * hitting BUG_ON, just return so we don't crash while crashing.
+ */
+ if (oops_in_progress) {
+ if (ctrl->cmd_pending &&
+ bcmnand_ctrl_poll_status(ctrl, NAND_CTRL_RDY, NAND_CTRL_RDY, 0))
+ return;
+ } else
+ BUG_ON(ctrl->cmd_pending != 0);
ctrl->cmd_pending = cmd;

ret = bcmnand_ctrl_poll_status(ctrl, NAND_CTRL_RDY, NAND_CTRL_RDY, 0);
@@ -2561,7 +2601,7 @@ static int brcmnand_set_cfg(struct brcmnand_host *host,
tmp &= ~brcmnand_ecc_level_mask(ctrl);
tmp &= ~brcmnand_spare_area_mask(ctrl);
if (ctrl->nand_version >= 0x0302) {
- tmp |= cfg->ecc_level << NAND_ACC_CONTROL_ECC_SHIFT;
+ tmp |= cfg->ecc_level << ctrl->ecc_level_shift;
tmp |= cfg->spare_area_size;
}
nand_writereg(ctrl, acc_control_offs, tmp);
diff --git a/drivers/mtd/spi-nor/winbond.c b/drivers/mtd/spi-nor/winbond.c
index 834d6ba5ce70..63ba8e3a96f5 100644
--- a/drivers/mtd/spi-nor/winbond.c
+++ b/drivers/mtd/spi-nor/winbond.c
@@ -120,8 +120,9 @@ static const struct flash_info winbond_nor_parts[] = {
NO_SFDP_FLAGS(SECT_4K) },
{ "w25q80bl", INFO(0xef4014, 0, 64 * 1024, 16)
NO_SFDP_FLAGS(SECT_4K) },
- { "w25q128", INFO(0xef4018, 0, 64 * 1024, 256)
- NO_SFDP_FLAGS(SECT_4K) },
+ { "w25q128", INFO(0xef4018, 0, 0, 0)
+ PARSE_SFDP
+ FLAGS(SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB) },
{ "w25q256", INFO(0xef4019, 0, 64 * 1024, 512)
NO_SFDP_FLAGS(SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ)
.fixups = &w25q256_fixups },
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 6c0623f88654..d9d843efd111 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -2337,13 +2337,27 @@ static u32 ksz_get_phy_flags(struct dsa_switch *ds, int port)
{
struct ksz_device *dev = ds->priv;

- if (dev->chip_id == KSZ8830_CHIP_ID) {
+ switch (dev->chip_id) {
+ case KSZ8830_CHIP_ID:
/* Silicon Errata Sheet (DS80000830A):
* Port 1 does not work with LinkMD Cable-Testing.
* Port 1 does not respond to received PAUSE control frames.
*/
if (!port)
return MICREL_KSZ8_P1_ERRATA;
+ break;
+ case KSZ9477_CHIP_ID:
+ /* KSZ9477 Errata DS80000754C
+ *
+ * Module 4: Energy Efficient Ethernet (EEE) feature select must
+ * be manually disabled
+ * The EEE feature is enabled by default, but it is not fully
+ * operational. It must be manually disabled through register
+ * controls. If not disabled, the PHY ports can auto-negotiate
+ * to enable EEE, and this feature can cause link drops when
+ * linked to another device supporting EEE.
+ */
+ return MICREL_NO_EEE;
}

return 0;
diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h
index dee35ba924ad..8c66d3bf61f0 100644
--- a/drivers/net/dsa/sja1105/sja1105.h
+++ b/drivers/net/dsa/sja1105/sja1105.h
@@ -132,6 +132,8 @@ struct sja1105_info {
int max_frame_mem;
int num_ports;
bool multiple_cascade_ports;
+ /* Every {port, TXQ} has its own CBS shaper */
+ bool fixed_cbs_mapping;
enum dsa_tag_protocol tag_proto;
const struct sja1105_dynamic_table_ops *dyn_ops;
const struct sja1105_table_ops *static_ops;
@@ -264,6 +266,8 @@ struct sja1105_private {
* the switch doesn't confuse them with one another.
*/
struct mutex mgmt_lock;
+ /* Serializes accesses to the FDB */
+ struct mutex fdb_lock;
/* PTP two-step TX timestamp ID, and its serialization lock */
spinlock_t ts_id_lock;
u8 ts_id;
diff --git a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c
index 7729d3f8b7f5..984c0e604e8d 100644
--- a/drivers/net/dsa/sja1105/sja1105_dynamic_config.c
+++ b/drivers/net/dsa/sja1105/sja1105_dynamic_config.c
@@ -1175,18 +1175,15 @@ const struct sja1105_dynamic_table_ops sja1110_dyn_ops[BLK_IDX_MAX_DYN] = {

static int
sja1105_dynamic_config_poll_valid(struct sja1105_private *priv,
- struct sja1105_dyn_cmd *cmd,
- const struct sja1105_dynamic_table_ops *ops)
+ const struct sja1105_dynamic_table_ops *ops,
+ void *entry, bool check_valident,
+ bool check_errors)
{
u8 packed_buf[SJA1105_MAX_DYN_CMD_SIZE] = {};
+ struct sja1105_dyn_cmd cmd = {};
int rc;

- /* We don't _need_ to read the full entry, just the command area which
- * is a fixed SJA1105_SIZE_DYN_CMD. But our cmd_packing() API expects a
- * buffer that contains the full entry too. Additionally, our API
- * doesn't really know how many bytes into the buffer does the command
- * area really begin. So just read back the whole entry.
- */
+ /* Read back the whole entry + command structure. */
rc = sja1105_xfer_buf(priv, SPI_READ, ops->addr, packed_buf,
ops->packed_size);
if (rc)
@@ -1195,11 +1192,25 @@ sja1105_dynamic_config_poll_valid(struct sja1105_private *priv,
/* Unpack the command structure, and return it to the caller in case it
* needs to perform further checks on it (VALIDENT).
*/
- memset(cmd, 0, sizeof(*cmd));
- ops->cmd_packing(packed_buf, cmd, UNPACK);
+ ops->cmd_packing(packed_buf, &cmd, UNPACK);

/* Hardware hasn't cleared VALID => still working on it */
- return cmd->valid ? -EAGAIN : 0;
+ if (cmd.valid)
+ return -EAGAIN;
+
+ if (check_valident && !cmd.valident && !(ops->access & OP_VALID_ANYWAY))
+ return -ENOENT;
+
+ if (check_errors && cmd.errors)
+ return -EINVAL;
+
+ /* Don't dereference possibly NULL pointer - maybe caller
+ * only wanted to see whether the entry existed or not.
+ */
+ if (entry)
+ ops->entry_packing(packed_buf, entry, UNPACK);
+
+ return 0;
}

/* Poll the dynamic config entry's control area until the hardware has
@@ -1208,16 +1219,19 @@ sja1105_dynamic_config_poll_valid(struct sja1105_private *priv,
*/
static int
sja1105_dynamic_config_wait_complete(struct sja1105_private *priv,
- struct sja1105_dyn_cmd *cmd,
- const struct sja1105_dynamic_table_ops *ops)
+ const struct sja1105_dynamic_table_ops *ops,
+ void *entry, bool check_valident,
+ bool check_errors)
{
- int rc;
-
- return read_poll_timeout(sja1105_dynamic_config_poll_valid,
- rc, rc != -EAGAIN,
- SJA1105_DYNAMIC_CONFIG_SLEEP_US,
- SJA1105_DYNAMIC_CONFIG_TIMEOUT_US,
- false, priv, cmd, ops);
+ int err, rc;
+
+ err = read_poll_timeout(sja1105_dynamic_config_poll_valid,
+ rc, rc != -EAGAIN,
+ SJA1105_DYNAMIC_CONFIG_SLEEP_US,
+ SJA1105_DYNAMIC_CONFIG_TIMEOUT_US,
+ false, priv, ops, entry, check_valident,
+ check_errors);
+ return err < 0 ? err : rc;
}

/* Provides read access to the settings through the dynamic interface
@@ -1286,25 +1300,14 @@ int sja1105_dynamic_config_read(struct sja1105_private *priv,
mutex_lock(&priv->dynamic_config_lock);
rc = sja1105_xfer_buf(priv, SPI_WRITE, ops->addr, packed_buf,
ops->packed_size);
- if (rc < 0) {
- mutex_unlock(&priv->dynamic_config_lock);
- return rc;
- }
-
- rc = sja1105_dynamic_config_wait_complete(priv, &cmd, ops);
- mutex_unlock(&priv->dynamic_config_lock);
if (rc < 0)
- return rc;
+ goto out;

- if (!cmd.valident && !(ops->access & OP_VALID_ANYWAY))
- return -ENOENT;
+ rc = sja1105_dynamic_config_wait_complete(priv, ops, entry, true, false);
+out:
+ mutex_unlock(&priv->dynamic_config_lock);

- /* Don't dereference possibly NULL pointer - maybe caller
- * only wanted to see whether the entry existed or not.
- */
- if (entry)
- ops->entry_packing(packed_buf, entry, UNPACK);
- return 0;
+ return rc;
}

int sja1105_dynamic_config_write(struct sja1105_private *priv,
@@ -1356,22 +1359,14 @@ int sja1105_dynamic_config_write(struct sja1105_private *priv,
mutex_lock(&priv->dynamic_config_lock);
rc = sja1105_xfer_buf(priv, SPI_WRITE, ops->addr, packed_buf,
ops->packed_size);
- if (rc < 0) {
- mutex_unlock(&priv->dynamic_config_lock);
- return rc;
- }
-
- rc = sja1105_dynamic_config_wait_complete(priv, &cmd, ops);
- mutex_unlock(&priv->dynamic_config_lock);
if (rc < 0)
- return rc;
+ goto out;

- cmd = (struct sja1105_dyn_cmd) {0};
- ops->cmd_packing(packed_buf, &cmd, UNPACK);
- if (cmd.errors)
- return -EINVAL;
+ rc = sja1105_dynamic_config_wait_complete(priv, ops, NULL, false, true);
+out:
+ mutex_unlock(&priv->dynamic_config_lock);

- return 0;
+ return rc;
}

static u8 sja1105_crc8_add(u8 crc, u8 byte, u8 poly)
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index 3529a565b4aa..013976b0af9f 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -1805,6 +1805,7 @@ static int sja1105_fdb_add(struct dsa_switch *ds, int port,
struct dsa_db db)
{
struct sja1105_private *priv = ds->priv;
+ int rc;

if (!vid) {
switch (db.type) {
@@ -1819,12 +1820,16 @@ static int sja1105_fdb_add(struct dsa_switch *ds, int port,
}
}

- return priv->info->fdb_add_cmd(ds, port, addr, vid);
+ mutex_lock(&priv->fdb_lock);
+ rc = priv->info->fdb_add_cmd(ds, port, addr, vid);
+ mutex_unlock(&priv->fdb_lock);
+
+ return rc;
}

-static int sja1105_fdb_del(struct dsa_switch *ds, int port,
- const unsigned char *addr, u16 vid,
- struct dsa_db db)
+static int __sja1105_fdb_del(struct dsa_switch *ds, int port,
+ const unsigned char *addr, u16 vid,
+ struct dsa_db db)
{
struct sja1105_private *priv = ds->priv;

@@ -1844,6 +1849,20 @@ static int sja1105_fdb_del(struct dsa_switch *ds, int port,
return priv->info->fdb_del_cmd(ds, port, addr, vid);
}

+static int sja1105_fdb_del(struct dsa_switch *ds, int port,
+ const unsigned char *addr, u16 vid,
+ struct dsa_db db)
+{
+ struct sja1105_private *priv = ds->priv;
+ int rc;
+
+ mutex_lock(&priv->fdb_lock);
+ rc = __sja1105_fdb_del(ds, port, addr, vid, db);
+ mutex_unlock(&priv->fdb_lock);
+
+ return rc;
+}
+
static int sja1105_fdb_dump(struct dsa_switch *ds, int port,
dsa_fdb_dump_cb_t *cb, void *data)
{
@@ -1875,13 +1894,14 @@ static int sja1105_fdb_dump(struct dsa_switch *ds, int port,
if (!(l2_lookup.destports & BIT(port)))
continue;

- /* We need to hide the FDB entry for unknown multicast */
- if (l2_lookup.macaddr == SJA1105_UNKNOWN_MULTICAST &&
- l2_lookup.mask_macaddr == SJA1105_UNKNOWN_MULTICAST)
- continue;
-
u64_to_ether_addr(l2_lookup.macaddr, macaddr);

+ /* Hardware FDB is shared for fdb and mdb, "bridge fdb show"
+ * only wants to see unicast
+ */
+ if (is_multicast_ether_addr(macaddr))
+ continue;
+
/* We need to hide the dsa_8021q VLANs from the user. */
if (vid_is_dsa_8021q(l2_lookup.vlanid))
l2_lookup.vlanid = 0;
@@ -1905,6 +1925,8 @@ static void sja1105_fast_age(struct dsa_switch *ds, int port)
};
int i;

+ mutex_lock(&priv->fdb_lock);
+
for (i = 0; i < SJA1105_MAX_L2_LOOKUP_COUNT; i++) {
struct sja1105_l2_lookup_entry l2_lookup = {0};
u8 macaddr[ETH_ALEN];
@@ -1918,7 +1940,7 @@ static void sja1105_fast_age(struct dsa_switch *ds, int port)
if (rc) {
dev_err(ds->dev, "Failed to read FDB: %pe\n",
ERR_PTR(rc));
- return;
+ break;
}

if (!(l2_lookup.destports & BIT(port)))
@@ -1930,14 +1952,16 @@ static void sja1105_fast_age(struct dsa_switch *ds, int port)

u64_to_ether_addr(l2_lookup.macaddr, macaddr);

- rc = sja1105_fdb_del(ds, port, macaddr, l2_lookup.vlanid, db);
+ rc = __sja1105_fdb_del(ds, port, macaddr, l2_lookup.vlanid, db);
if (rc) {
dev_err(ds->dev,
"Failed to delete FDB entry %pM vid %lld: %pe\n",
macaddr, l2_lookup.vlanid, ERR_PTR(rc));
- return;
+ break;
}
}
+
+ mutex_unlock(&priv->fdb_lock);
}

static int sja1105_mdb_add(struct dsa_switch *ds, int port,
@@ -2122,11 +2146,36 @@ static void sja1105_bridge_leave(struct dsa_switch *ds, int port,
}

#define BYTES_PER_KBIT (1000LL / 8)
+/* Port 0 (the uC port) does not have CBS shapers */
+#define SJA1110_FIXED_CBS(port, prio) ((((port) - 1) * SJA1105_NUM_TC) + (prio))
+
+static int sja1105_find_cbs_shaper(struct sja1105_private *priv,
+ int port, int prio)
+{
+ int i;
+
+ if (priv->info->fixed_cbs_mapping) {
+ i = SJA1110_FIXED_CBS(port, prio);
+ if (i >= 0 && i < priv->info->num_cbs_shapers)
+ return i;
+
+ return -1;
+ }
+
+ for (i = 0; i < priv->info->num_cbs_shapers; i++)
+ if (priv->cbs[i].port == port && priv->cbs[i].prio == prio)
+ return i;
+
+ return -1;
+}

static int sja1105_find_unused_cbs_shaper(struct sja1105_private *priv)
{
int i;

+ if (priv->info->fixed_cbs_mapping)
+ return -1;
+
for (i = 0; i < priv->info->num_cbs_shapers; i++)
if (!priv->cbs[i].idle_slope && !priv->cbs[i].send_slope)
return i;
@@ -2157,14 +2206,20 @@ static int sja1105_setup_tc_cbs(struct dsa_switch *ds, int port,
{
struct sja1105_private *priv = ds->priv;
struct sja1105_cbs_entry *cbs;
+ s64 port_transmit_rate_kbps;
int index;

if (!offload->enable)
return sja1105_delete_cbs_shaper(priv, port, offload->queue);

- index = sja1105_find_unused_cbs_shaper(priv);
- if (index < 0)
- return -ENOSPC;
+ /* The user may be replacing an existing shaper */
+ index = sja1105_find_cbs_shaper(priv, port, offload->queue);
+ if (index < 0) {
+ /* That isn't the case - see if we can allocate a new one */
+ index = sja1105_find_unused_cbs_shaper(priv);
+ if (index < 0)
+ return -ENOSPC;
+ }

cbs = &priv->cbs[index];
cbs->port = port;
@@ -2174,9 +2229,17 @@ static int sja1105_setup_tc_cbs(struct dsa_switch *ds, int port,
*/
cbs->credit_hi = offload->hicredit;
cbs->credit_lo = abs(offload->locredit);
- /* User space is in kbits/sec, hardware in bytes/sec */
- cbs->idle_slope = offload->idleslope * BYTES_PER_KBIT;
- cbs->send_slope = abs(offload->sendslope * BYTES_PER_KBIT);
+ /* User space is in kbits/sec, while the hardware in bytes/sec times
+ * link speed. Since the given offload->sendslope is good only for the
+ * current link speed anyway, and user space is likely to reprogram it
+ * when that changes, don't even bother to track the port's link speed,
+ * but deduce the port transmit rate from idleslope - sendslope.
+ */
+ port_transmit_rate_kbps = offload->idleslope - offload->sendslope;
+ cbs->idle_slope = div_s64(offload->idleslope * BYTES_PER_KBIT,
+ port_transmit_rate_kbps);
+ cbs->send_slope = div_s64(abs(offload->sendslope * BYTES_PER_KBIT),
+ port_transmit_rate_kbps);
/* Convert the negative values from 64-bit 2's complement
* to 32-bit 2's complement (for the case of 0x80000000 whose
* negative is still negative).
@@ -2241,6 +2304,7 @@ int sja1105_static_config_reload(struct sja1105_private *priv,
int rc, i;
s64 now;

+ mutex_lock(&priv->fdb_lock);
mutex_lock(&priv->mgmt_lock);

mac = priv->static_config.tables[BLK_IDX_MAC_CONFIG].entries;
@@ -2353,6 +2417,7 @@ int sja1105_static_config_reload(struct sja1105_private *priv,
goto out;
out:
mutex_unlock(&priv->mgmt_lock);
+ mutex_unlock(&priv->fdb_lock);

return rc;
}
@@ -2922,7 +2987,9 @@ static int sja1105_port_mcast_flood(struct sja1105_private *priv, int to,
{
struct sja1105_l2_lookup_entry *l2_lookup;
struct sja1105_table *table;
- int match;
+ int match, rc;
+
+ mutex_lock(&priv->fdb_lock);

table = &priv->static_config.tables[BLK_IDX_L2_LOOKUP];
l2_lookup = table->entries;
@@ -2935,7 +3002,8 @@ static int sja1105_port_mcast_flood(struct sja1105_private *priv, int to,
if (match == table->entry_count) {
NL_SET_ERR_MSG_MOD(extack,
"Could not find FDB entry for unknown multicast");
- return -ENOSPC;
+ rc = -ENOSPC;
+ goto out;
}

if (flags.val & BR_MCAST_FLOOD)
@@ -2943,10 +3011,13 @@ static int sja1105_port_mcast_flood(struct sja1105_private *priv, int to,
else
l2_lookup[match].destports &= ~BIT(to);

- return sja1105_dynamic_config_write(priv, BLK_IDX_L2_LOOKUP,
- l2_lookup[match].index,
- &l2_lookup[match],
- true);
+ rc = sja1105_dynamic_config_write(priv, BLK_IDX_L2_LOOKUP,
+ l2_lookup[match].index,
+ &l2_lookup[match], true);
+out:
+ mutex_unlock(&priv->fdb_lock);
+
+ return rc;
}

static int sja1105_port_pre_bridge_flags(struct dsa_switch *ds, int port,
@@ -3316,6 +3387,7 @@ static int sja1105_probe(struct spi_device *spi)
mutex_init(&priv->ptp_data.lock);
mutex_init(&priv->dynamic_config_lock);
mutex_init(&priv->mgmt_lock);
+ mutex_init(&priv->fdb_lock);
spin_lock_init(&priv->ts_id_lock);

rc = sja1105_parse_dt(priv);
diff --git a/drivers/net/dsa/sja1105/sja1105_spi.c b/drivers/net/dsa/sja1105/sja1105_spi.c
index 5ce29c8057a4..834b5c1b4db0 100644
--- a/drivers/net/dsa/sja1105/sja1105_spi.c
+++ b/drivers/net/dsa/sja1105/sja1105_spi.c
@@ -781,6 +781,7 @@ const struct sja1105_info sja1110a_info = {
.tag_proto = DSA_TAG_PROTO_SJA1110,
.can_limit_mcast_flood = true,
.multiple_cascade_ports = true,
+ .fixed_cbs_mapping = true,
.ptp_ts_bits = 32,
.ptpegr_ts_bytes = 8,
.max_frame_mem = SJA1110_MAX_FRAME_MEMORY,
@@ -831,6 +832,7 @@ const struct sja1105_info sja1110b_info = {
.tag_proto = DSA_TAG_PROTO_SJA1110,
.can_limit_mcast_flood = true,
.multiple_cascade_ports = true,
+ .fixed_cbs_mapping = true,
.ptp_ts_bits = 32,
.ptpegr_ts_bytes = 8,
.max_frame_mem = SJA1110_MAX_FRAME_MEMORY,
@@ -881,6 +883,7 @@ const struct sja1105_info sja1110c_info = {
.tag_proto = DSA_TAG_PROTO_SJA1110,
.can_limit_mcast_flood = true,
.multiple_cascade_ports = true,
+ .fixed_cbs_mapping = true,
.ptp_ts_bits = 32,
.ptpegr_ts_bytes = 8,
.max_frame_mem = SJA1110_MAX_FRAME_MEMORY,
@@ -931,6 +934,7 @@ const struct sja1105_info sja1110d_info = {
.tag_proto = DSA_TAG_PROTO_SJA1110,
.can_limit_mcast_flood = true,
.multiple_cascade_ports = true,
+ .fixed_cbs_mapping = true,
.ptp_ts_bits = 32,
.ptpegr_ts_bytes = 8,
.max_frame_mem = SJA1110_MAX_FRAME_MEMORY,
diff --git a/drivers/net/ethernet/adi/adin1110.c b/drivers/net/ethernet/adi/adin1110.c
index f5c2d7a9abc1..ca66b747b7c5 100644
--- a/drivers/net/ethernet/adi/adin1110.c
+++ b/drivers/net/ethernet/adi/adin1110.c
@@ -739,7 +739,7 @@ static int adin1110_broadcasts_filter(struct adin1110_port_priv *port_priv,
u32 port_rules = 0;
u8 mask[ETH_ALEN];

- memset(mask, 0xFF, ETH_ALEN);
+ eth_broadcast_addr(mask);

if (accept_broadcast && port_priv->state == BR_STATE_FORWARDING)
port_rules = adin1110_port_rules(port_priv, true, true);
@@ -760,7 +760,7 @@ static int adin1110_set_mac_address(struct net_device *netdev,
return -EADDRNOTAVAIL;

eth_hw_addr_set(netdev, dev_addr);
- memset(mask, 0xFF, ETH_ALEN);
+ eth_broadcast_addr(mask);

mac_slot = (!port_priv->nr) ? ADIN_MAC_P1_ADDR_SLOT : ADIN_MAC_P2_ADDR_SLOT;
port_rules = adin1110_port_rules(port_priv, true, false);
@@ -1271,7 +1271,7 @@ static int adin1110_port_set_blocking_state(struct adin1110_port_priv *port_priv
goto out;

/* Allow only BPDUs to be passed to the CPU */
- memset(mask, 0xFF, ETH_ALEN);
+ eth_broadcast_addr(mask);
port_rules = adin1110_port_rules(port_priv, true, false);
ret = adin1110_write_mac_address(port_priv, mac_slot, mac,
mask, port_rules);
@@ -1385,8 +1385,8 @@ static int adin1110_fdb_add(struct adin1110_port_priv *port_priv,
return -ENOMEM;

other_port = priv->ports[!port_priv->nr];
- port_rules = adin1110_port_rules(port_priv, false, true);
- memset(mask, 0xFF, ETH_ALEN);
+ port_rules = adin1110_port_rules(other_port, false, true);
+ eth_broadcast_addr(mask);

return adin1110_write_mac_address(other_port, mac_nr, (u8 *)fdb->addr,
mask, port_rules);
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 82929ee76739..2d18acf3d5ea 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -757,8 +757,6 @@ static void macb_mac_link_up(struct phylink_config *config,
if (rx_pause)
ctrl |= MACB_BIT(PAE);

- macb_set_tx_clk(bp, speed);
-
/* Initialize rings & buffers as clearing MACB_BIT(TE) in link down
* cleared the pipeline and control registers.
*/
@@ -778,6 +776,9 @@ static void macb_mac_link_up(struct phylink_config *config,

spin_unlock_irqrestore(&bp->lock, flags);

+ if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC))
+ macb_set_tx_clk(bp, speed);
+
/* Enable Rx and Tx; Enable PTP unicast */
ctrl = macb_readl(bp, NCR);
if (gem_has_ptp(bp))
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index e0a4cb7e3f50..c153dc083aff 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -1402,7 +1402,7 @@ static void enetc_fixup_clear_rss_rfs(struct pci_dev *pdev)
return;

si = enetc_psi_create(pdev);
- if (si)
+ if (!IS_ERR(si))
enetc_psi_destroy(pdev);
}
DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_FREESCALE, ENETC_DEV_ID_PF,
diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
index e57b73eb70f6..ac041cc5714c 100644
--- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
@@ -492,7 +492,10 @@ static int gve_rx_append_frags(struct napi_struct *napi,
if (!skb)
return -1;

- skb_shinfo(rx->ctx.skb_tail)->frag_list = skb;
+ if (rx->ctx.skb_tail == rx->ctx.skb_head)
+ skb_shinfo(rx->ctx.skb_head)->frag_list = skb;
+ else
+ rx->ctx.skb_tail->next = skb;
rx->ctx.skb_tail = skb;
num_frags = 0;
}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index a4b43bcd2f0c..aaf1f42624a7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -814,6 +814,7 @@ struct hnae3_tc_info {
u8 max_tc; /* Total number of TCs */
u8 num_tc; /* Total number of enabled TCs */
bool mqprio_active;
+ bool dcb_ets_active;
};

#define HNAE3_MAX_DSCP 64
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index f276b5ecb431..26fb6fefcb9d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -1411,9 +1411,9 @@ int hns3_dbg_init(struct hnae3_handle *handle)
return 0;

out:
- mutex_destroy(&handle->dbgfs_lock);
debugfs_remove_recursive(handle->hnae3_dbgfs);
handle->hnae3_dbgfs = NULL;
+ mutex_destroy(&handle->dbgfs_lock);
return ret;
}

@@ -1421,6 +1421,9 @@ void hns3_dbg_uninit(struct hnae3_handle *handle)
{
u32 i;

+ debugfs_remove_recursive(handle->hnae3_dbgfs);
+ handle->hnae3_dbgfs = NULL;
+
for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++)
if (handle->dbgfs_buf[i]) {
kvfree(handle->dbgfs_buf[i]);
@@ -1428,8 +1431,6 @@ void hns3_dbg_uninit(struct hnae3_handle *handle)
}

mutex_destroy(&handle->dbgfs_lock);
- debugfs_remove_recursive(handle->hnae3_dbgfs);
- handle->hnae3_dbgfs = NULL;
}

void hns3_dbg_register_debugfs(const char *debugfs_dir_name)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index b7b51e56b030..613d0a779cef 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2102,8 +2102,12 @@ static void hns3_tx_doorbell(struct hns3_enet_ring *ring, int num,
*/
if (test_bit(HNS3_NIC_STATE_TX_PUSH_ENABLE, &priv->state) && num &&
!ring->pending_buf && num <= HNS3_MAX_PUSH_BD_NUM && doorbell) {
+ /* This smp_store_release() pairs with smp_load_aquire() in
+ * hns3_nic_reclaim_desc(). Ensure that the BD valid bit
+ * is updated.
+ */
+ smp_store_release(&ring->last_to_use, ring->next_to_use);
hns3_tx_push_bd(ring, num);
- WRITE_ONCE(ring->last_to_use, ring->next_to_use);
return;
}

@@ -2114,6 +2118,11 @@ static void hns3_tx_doorbell(struct hns3_enet_ring *ring, int num,
return;
}

+ /* This smp_store_release() pairs with smp_load_aquire() in
+ * hns3_nic_reclaim_desc(). Ensure that the BD valid bit is updated.
+ */
+ smp_store_release(&ring->last_to_use, ring->next_to_use);
+
if (ring->tqp->mem_base)
hns3_tx_mem_doorbell(ring);
else
@@ -2121,7 +2130,6 @@ static void hns3_tx_doorbell(struct hns3_enet_ring *ring, int num,
ring->tqp->io_base + HNS3_RING_TX_RING_TAIL_REG);

ring->pending_buf = 0;
- WRITE_ONCE(ring->last_to_use, ring->next_to_use);
}

static void hns3_tsyn(struct net_device *netdev, struct sk_buff *skb,
@@ -3307,8 +3315,6 @@ static void hns3_set_default_feature(struct net_device *netdev)

netdev->priv_flags |= IFF_UNICAST_FLT;

- netdev->gso_partial_features |= NETIF_F_GSO_GRE_CSUM;
-
netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER |
NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO |
@@ -3562,9 +3568,8 @@ static void hns3_reuse_buffer(struct hns3_enet_ring *ring, int i)
static bool hns3_nic_reclaim_desc(struct hns3_enet_ring *ring,
int *bytes, int *pkts, int budget)
{
- /* pair with ring->last_to_use update in hns3_tx_doorbell(),
- * smp_store_release() is not used in hns3_tx_doorbell() because
- * the doorbell operation already have the needed barrier operation.
+ /* This smp_load_acquire() pairs with smp_store_release() in
+ * hns3_tx_doorbell().
*/
int ltu = smp_load_acquire(&ring->last_to_use);
int ntc = ring->next_to_clean;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 407d30ee55d2..64858b3114ac 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -773,7 +773,9 @@ static int hns3_get_link_ksettings(struct net_device *netdev,
hns3_get_ksettings(h, cmd);
break;
case HNAE3_MEDIA_TYPE_FIBER:
- if (module_type == HNAE3_MODULE_TYPE_CR)
+ if (module_type == HNAE3_MODULE_TYPE_UNKNOWN)
+ cmd->base.port = PORT_OTHER;
+ else if (module_type == HNAE3_MODULE_TYPE_CR)
cmd->base.port = PORT_DA;
else
cmd->base.port = PORT_FIBRE;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
index fad5a5ff3cda..b98301e205f7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
@@ -259,7 +259,7 @@ static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets)
int ret;

if (!(hdev->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) ||
- hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE)
+ h->kinfo.tc_info.mqprio_active)
return -EINVAL;

ret = hclge_ets_validate(hdev, ets, &num_tc, &map_changed);
@@ -275,10 +275,7 @@ static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets)
}

hclge_tm_schd_info_update(hdev, num_tc);
- if (num_tc > 1)
- hdev->flag |= HCLGE_FLAG_DCB_ENABLE;
- else
- hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE;
+ h->kinfo.tc_info.dcb_ets_active = num_tc > 1;

ret = hclge_ieee_ets_to_tm_info(hdev, ets);
if (ret)
@@ -487,7 +484,7 @@ static u8 hclge_getdcbx(struct hnae3_handle *h)
struct hclge_vport *vport = hclge_get_vport(h);
struct hclge_dev *hdev = vport->back;

- if (hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE)
+ if (h->kinfo.tc_info.mqprio_active)
return 0;

return hdev->dcbx_cap;
@@ -611,7 +608,8 @@ static int hclge_setup_tc(struct hnae3_handle *h,
if (!test_bit(HCLGE_STATE_NIC_REGISTERED, &hdev->state))
return -EBUSY;

- if (hdev->flag & HCLGE_FLAG_DCB_ENABLE)
+ kinfo = &vport->nic.kinfo;
+ if (kinfo->tc_info.dcb_ets_active)
return -EINVAL;

ret = hclge_mqprio_qopt_check(hdev, mqprio_qopt);
@@ -625,7 +623,6 @@ static int hclge_setup_tc(struct hnae3_handle *h,
if (ret)
return ret;

- kinfo = &vport->nic.kinfo;
memcpy(&old_tc_info, &kinfo->tc_info, sizeof(old_tc_info));
hclge_sync_mqprio_qopt(&kinfo->tc_info, mqprio_qopt);
kinfo->tc_info.mqprio_active = tc > 0;
@@ -634,13 +631,6 @@ static int hclge_setup_tc(struct hnae3_handle *h,
if (ret)
goto err_out;

- hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE;
-
- if (tc > 1)
- hdev->flag |= HCLGE_FLAG_MQPRIO_ENABLE;
- else
- hdev->flag &= ~HCLGE_FLAG_MQPRIO_ENABLE;
-
return hclge_notify_init_up(hdev);

err_out:
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index f01a7a9ee02c..ff3f8f424ad9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -1519,7 +1519,7 @@ static int hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, bool sel_x,
struct hclge_desc desc[3];
int pos = 0;
int ret, i;
- u32 *req;
+ __le32 *req;

hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_FD_TCAM_OP, true);
desc[0].flag |= cpu_to_le16(HCLGE_COMM_CMD_FLAG_NEXT);
@@ -1544,22 +1544,22 @@ static int hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, bool sel_x,
tcam_msg.loc);

/* tcam_data0 ~ tcam_data1 */
- req = (u32 *)req1->tcam_data;
+ req = (__le32 *)req1->tcam_data;
for (i = 0; i < 2; i++)
pos += scnprintf(tcam_buf + pos, HCLGE_DBG_TCAM_BUF_SIZE - pos,
- "%08x\n", *req++);
+ "%08x\n", le32_to_cpu(*req++));

/* tcam_data2 ~ tcam_data7 */
- req = (u32 *)req2->tcam_data;
+ req = (__le32 *)req2->tcam_data;
for (i = 0; i < 6; i++)
pos += scnprintf(tcam_buf + pos, HCLGE_DBG_TCAM_BUF_SIZE - pos,
- "%08x\n", *req++);
+ "%08x\n", le32_to_cpu(*req++));

/* tcam_data8 ~ tcam_data12 */
- req = (u32 *)req3->tcam_data;
+ req = (__le32 *)req3->tcam_data;
for (i = 0; i < 5; i++)
pos += scnprintf(tcam_buf + pos, HCLGE_DBG_TCAM_BUF_SIZE - pos,
- "%08x\n", *req++);
+ "%08x\n", le32_to_cpu(*req++));

return ret;
}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 2d5a2e1ef664..ce6b658a930c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -11026,6 +11026,7 @@ static void hclge_get_mdix_mode(struct hnae3_handle *handle,

static void hclge_info_show(struct hclge_dev *hdev)
{
+ struct hnae3_handle *handle = &hdev->vport->nic;
struct device *dev = &hdev->pdev->dev;

dev_info(dev, "PF info begin:\n");
@@ -11042,9 +11043,9 @@ static void hclge_info_show(struct hclge_dev *hdev)
dev_info(dev, "This is %s PF\n",
hdev->flag & HCLGE_FLAG_MAIN ? "main" : "not main");
dev_info(dev, "DCB %s\n",
- hdev->flag & HCLGE_FLAG_DCB_ENABLE ? "enable" : "disable");
+ handle->kinfo.tc_info.dcb_ets_active ? "enable" : "disable");
dev_info(dev, "MQPRIO %s\n",
- hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE ? "enable" : "disable");
+ handle->kinfo.tc_info.mqprio_active ? "enable" : "disable");
dev_info(dev, "Default tx spare buffer size: %u\n",
hdev->tx_spare_buf_size);

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 8f76b568c1bf..70319ce49a1d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -919,8 +919,6 @@ struct hclge_dev {

#define HCLGE_FLAG_MAIN BIT(0)
#define HCLGE_FLAG_DCB_CAPABLE BIT(1)
-#define HCLGE_FLAG_DCB_ENABLE BIT(2)
-#define HCLGE_FLAG_MQPRIO_ENABLE BIT(3)
u32 flag;

u32 pkt_buf_size; /* Total pf buf size for tx/rx */
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 015b78144114..a2b759531cb7 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -34,11 +34,11 @@ struct igb_adapter;
/* TX/RX descriptor defines */
#define IGB_DEFAULT_TXD 256
#define IGB_DEFAULT_TX_WORK 128
-#define IGB_MIN_TXD 80
+#define IGB_MIN_TXD 64
#define IGB_MAX_TXD 4096

#define IGB_DEFAULT_RXD 256
-#define IGB_MIN_RXD 80
+#define IGB_MIN_RXD 64
#define IGB_MAX_RXD 4096

#define IGB_DEFAULT_ITR 3 /* dynamic */
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 08e3df37089f..12f106b3a878 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -3827,8 +3827,11 @@ static int igb_enable_sriov(struct pci_dev *pdev, int num_vfs, bool reinit)
}

/* only call pci_enable_sriov() if no VFs are allocated already */
- if (!old_vfs)
+ if (!old_vfs) {
err = pci_enable_sriov(pdev, adapter->vfs_allocated_count);
+ if (err)
+ goto err_out;
+ }

goto out;

@@ -3933,8 +3936,9 @@ static void igb_probe_vfs(struct igb_adapter *adapter)
struct pci_dev *pdev = adapter->pdev;
struct e1000_hw *hw = &adapter->hw;

- /* Virtualization features not supported on i210 family. */
- if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211))
+ /* Virtualization features not supported on i210 and 82580 family. */
+ if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211) ||
+ (hw->mac.type == e1000_82580))
return;

/* Of the below we really only want the effect of getting
diff --git a/drivers/net/ethernet/intel/igbvf/igbvf.h b/drivers/net/ethernet/intel/igbvf/igbvf.h
index 57d39ee00b58..7b83678ba83a 100644
--- a/drivers/net/ethernet/intel/igbvf/igbvf.h
+++ b/drivers/net/ethernet/intel/igbvf/igbvf.h
@@ -39,11 +39,11 @@ enum latency_range {
/* Tx/Rx descriptor defines */
#define IGBVF_DEFAULT_TXD 256
#define IGBVF_MAX_TXD 4096
-#define IGBVF_MIN_TXD 80
+#define IGBVF_MIN_TXD 64

#define IGBVF_DEFAULT_RXD 256
#define IGBVF_MAX_RXD 4096
-#define IGBVF_MIN_RXD 80
+#define IGBVF_MIN_RXD 64

#define IGBVF_MIN_ITR_USECS 10 /* 100000 irq/sec */
#define IGBVF_MAX_ITR_USECS 10000 /* 100 irq/sec */
diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index 38901d2a4680..b4077c3f62ed 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -368,11 +368,11 @@ static inline u32 igc_rss_type(const union igc_adv_rx_desc *rx_desc)
/* TX/RX descriptor defines */
#define IGC_DEFAULT_TXD 256
#define IGC_DEFAULT_TX_WORK 128
-#define IGC_MIN_TXD 80
+#define IGC_MIN_TXD 64
#define IGC_MAX_TXD 4096

#define IGC_DEFAULT_RXD 256
-#define IGC_MIN_RXD 80
+#define IGC_MIN_RXD 64
#define IGC_MAX_RXD 4096

/* Supported Rx Buffer Sizes */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
index 0310af851086..9339edbd9082 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
@@ -979,6 +979,7 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter,
u32 tsync_tx_ctl = IXGBE_TSYNCTXCTL_ENABLED;
u32 tsync_rx_ctl = IXGBE_TSYNCRXCTL_ENABLED;
u32 tsync_rx_mtrl = PTP_EV_PORT << 16;
+ u32 aflags = adapter->flags;
bool is_l2 = false;
u32 regval;

@@ -996,20 +997,20 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter,
case HWTSTAMP_FILTER_NONE:
tsync_rx_ctl = 0;
tsync_rx_mtrl = 0;
- adapter->flags &= ~(IXGBE_FLAG_RX_HWTSTAMP_ENABLED |
- IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER);
+ aflags &= ~(IXGBE_FLAG_RX_HWTSTAMP_ENABLED |
+ IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER);
break;
case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L4_V1;
tsync_rx_mtrl |= IXGBE_RXMTRL_V1_SYNC_MSG;
- adapter->flags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED |
- IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER);
+ aflags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED |
+ IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER);
break;
case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L4_V1;
tsync_rx_mtrl |= IXGBE_RXMTRL_V1_DELAY_REQ_MSG;
- adapter->flags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED |
- IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER);
+ aflags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED |
+ IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER);
break;
case HWTSTAMP_FILTER_PTP_V2_EVENT:
case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
@@ -1023,8 +1024,8 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter,
tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_EVENT_V2;
is_l2 = true;
config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
- adapter->flags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED |
- IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER);
+ aflags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED |
+ IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER);
break;
case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
case HWTSTAMP_FILTER_NTP_ALL:
@@ -1035,7 +1036,7 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter,
if (hw->mac.type >= ixgbe_mac_X550) {
tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_ALL;
config->rx_filter = HWTSTAMP_FILTER_ALL;
- adapter->flags |= IXGBE_FLAG_RX_HWTSTAMP_ENABLED;
+ aflags |= IXGBE_FLAG_RX_HWTSTAMP_ENABLED;
break;
}
fallthrough;
@@ -1046,8 +1047,6 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter,
* Delay_Req messages and hardware does not support
* timestamping all packets => return error
*/
- adapter->flags &= ~(IXGBE_FLAG_RX_HWTSTAMP_ENABLED |
- IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER);
config->rx_filter = HWTSTAMP_FILTER_NONE;
return -ERANGE;
}
@@ -1079,8 +1078,8 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter,
IXGBE_TSYNCRXCTL_TYPE_ALL |
IXGBE_TSYNCRXCTL_TSIP_UT_EN;
config->rx_filter = HWTSTAMP_FILTER_ALL;
- adapter->flags |= IXGBE_FLAG_RX_HWTSTAMP_ENABLED;
- adapter->flags &= ~IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER;
+ aflags |= IXGBE_FLAG_RX_HWTSTAMP_ENABLED;
+ aflags &= ~IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER;
is_l2 = true;
break;
default:
@@ -1113,6 +1112,9 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter,

IXGBE_WRITE_FLUSH(hw);

+ /* configure adapter flags only when HW is actually configured */
+ adapter->flags = aflags;
+
/* clear TX/RX time stamp registers, just to be sure */
ixgbe_ptp_clear_tx_timestamp(adapter);
IXGBE_READ_REG(hw, IXGBE_RXSTMPH);
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 1fec84b4c068..0129afa1210e 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -5586,6 +5586,11 @@ static int mvpp2_ethtool_get_rxnfc(struct net_device *dev,
break;
case ETHTOOL_GRXCLSRLALL:
for (i = 0; i < MVPP2_N_RFS_ENTRIES_PER_FLOW; i++) {
+ if (loc == info->rule_cnt) {
+ ret = -EMSGSIZE;
+ break;
+ }
+
if (port->rfs_rules[i])
rules[loc++] = i;
}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index c2f68678e947..23c2f2ed2fb8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -846,6 +846,21 @@ static int nix_aq_enqueue_wait(struct rvu *rvu, struct rvu_block *block,
return 0;
}

+static void nix_get_aq_req_smq(struct rvu *rvu, struct nix_aq_enq_req *req,
+ u16 *smq, u16 *smq_mask)
+{
+ struct nix_cn10k_aq_enq_req *aq_req;
+
+ if (!is_rvu_otx2(rvu)) {
+ aq_req = (struct nix_cn10k_aq_enq_req *)req;
+ *smq = aq_req->sq.smq;
+ *smq_mask = aq_req->sq_mask.smq;
+ } else {
+ *smq = req->sq.smq;
+ *smq_mask = req->sq_mask.smq;
+ }
+}
+
static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw,
struct nix_aq_enq_req *req,
struct nix_aq_enq_rsp *rsp)
@@ -857,6 +872,7 @@ static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw,
struct rvu_block *block;
struct admin_queue *aq;
struct rvu_pfvf *pfvf;
+ u16 smq, smq_mask;
void *ctx, *mask;
bool ena;
u64 cfg;
@@ -928,13 +944,14 @@ static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw,
if (rc)
return rc;

+ nix_get_aq_req_smq(rvu, req, &smq, &smq_mask);
/* Check if SQ pointed SMQ belongs to this PF/VF or not */
if (req->ctype == NIX_AQ_CTYPE_SQ &&
((req->op == NIX_AQ_INSTOP_INIT && req->sq.ena) ||
(req->op == NIX_AQ_INSTOP_WRITE &&
- req->sq_mask.ena && req->sq_mask.smq && req->sq.ena))) {
+ req->sq_mask.ena && req->sq.ena && smq_mask))) {
if (!is_valid_txschq(rvu, blkaddr, NIX_TXSCH_LVL_SMQ,
- pcifunc, req->sq.smq))
+ pcifunc, smq))
return NIX_AF_ERR_AQ_ENQUEUE;
}

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
index 826f691de259..a4a258da8dd5 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
@@ -107,12 +107,13 @@ int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura)
}

#define NPA_MAX_BURST 16
-void cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
+int cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
{
struct otx2_nic *pfvf = dev;
+ int cnt = cq->pool_ptrs;
u64 ptrs[NPA_MAX_BURST];
- int num_ptrs = 1;
dma_addr_t bufptr;
+ int num_ptrs = 1;

/* Refill pool with new buffers */
while (cq->pool_ptrs) {
@@ -131,6 +132,7 @@ void cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
num_ptrs = 1;
}
}
+ return cnt - cq->pool_ptrs;
}

void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h
index 8ae96815865e..c1861f7de254 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.h
@@ -24,7 +24,7 @@ static inline int mtu_to_dwrr_weight(struct otx2_nic *pfvf, int mtu)
return weight;
}

-void cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq);
+int cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq);
void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx);
int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura);
int cn10k_lmtst_init(struct otx2_nic *pfvf);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index b9712040a0bc..20ecc90d203e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -573,20 +573,8 @@ int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
int otx2_alloc_buffer(struct otx2_nic *pfvf, struct otx2_cq_queue *cq,
dma_addr_t *dma)
{
- if (unlikely(__otx2_alloc_rbuf(pfvf, cq->rbpool, dma))) {
- struct refill_work *work;
- struct delayed_work *dwork;
-
- work = &pfvf->refill_wrk[cq->cq_idx];
- dwork = &work->pool_refill_work;
- /* Schedule a task if no other task is running */
- if (!cq->refill_task_sched) {
- cq->refill_task_sched = true;
- schedule_delayed_work(dwork,
- msecs_to_jiffies(100));
- }
+ if (unlikely(__otx2_alloc_rbuf(pfvf, cq->rbpool, dma)))
return -ENOMEM;
- }
return 0;
}

@@ -1080,39 +1068,20 @@ static int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx)
static void otx2_pool_refill_task(struct work_struct *work)
{
struct otx2_cq_queue *cq;
- struct otx2_pool *rbpool;
struct refill_work *wrk;
- int qidx, free_ptrs = 0;
struct otx2_nic *pfvf;
- dma_addr_t bufptr;
+ int qidx;

wrk = container_of(work, struct refill_work, pool_refill_work.work);
pfvf = wrk->pf;
qidx = wrk - pfvf->refill_wrk;
cq = &pfvf->qset.cq[qidx];
- rbpool = cq->rbpool;
- free_ptrs = cq->pool_ptrs;

- while (cq->pool_ptrs) {
- if (otx2_alloc_rbuf(pfvf, rbpool, &bufptr)) {
- /* Schedule a WQ if we fails to free atleast half of the
- * pointers else enable napi for this RQ.
- */
- if (!((free_ptrs - cq->pool_ptrs) > free_ptrs / 2)) {
- struct delayed_work *dwork;
-
- dwork = &wrk->pool_refill_work;
- schedule_delayed_work(dwork,
- msecs_to_jiffies(100));
- } else {
- cq->refill_task_sched = false;
- }
- return;
- }
- pfvf->hw_ops->aura_freeptr(pfvf, qidx, bufptr + OTX2_HEAD_ROOM);
- cq->pool_ptrs--;
- }
cq->refill_task_sched = false;
+
+ local_bh_disable();
+ napi_schedule(wrk->napi);
+ local_bh_enable();
}

int otx2_config_nix_queues(struct otx2_nic *pfvf)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index ba8091131ec0..0e81849db353 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -301,6 +301,7 @@ struct flr_work {
struct refill_work {
struct delayed_work pool_refill_work;
struct otx2_nic *pf;
+ struct napi_struct *napi;
};

/* PTPv2 originTimestamp structure */
@@ -373,7 +374,7 @@ struct dev_hw_ops {
int (*sq_aq_init)(void *dev, u16 qidx, u16 sqb_aura);
void (*sqe_flush)(void *dev, struct otx2_snd_queue *sq,
int size, int qidx);
- void (*refill_pool_ptrs)(void *dev, struct otx2_cq_queue *cq);
+ int (*refill_pool_ptrs)(void *dev, struct otx2_cq_queue *cq);
void (*aura_freeptr)(void *dev, int aura, u64 buf);
};

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index 9551b422622a..9ded98bb1c89 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -1942,6 +1942,10 @@ int otx2_stop(struct net_device *netdev)

netif_tx_disable(netdev);

+ for (wrk = 0; wrk < pf->qset.cq_cnt; wrk++)
+ cancel_delayed_work_sync(&pf->refill_wrk[wrk].pool_refill_work);
+ devm_kfree(pf->dev, pf->refill_wrk);
+
otx2_free_hw_resources(pf);
otx2_free_cints(pf, pf->hw.cint_cnt);
otx2_disable_napi(pf);
@@ -1949,9 +1953,6 @@ int otx2_stop(struct net_device *netdev)
for (qidx = 0; qidx < netdev->num_tx_queues; qidx++)
netdev_tx_reset_queue(netdev_get_tx_queue(netdev, qidx));

- for (wrk = 0; wrk < pf->qset.cq_cnt; wrk++)
- cancel_delayed_work_sync(&pf->refill_wrk[wrk].pool_refill_work);
- devm_kfree(pf->dev, pf->refill_wrk);

kfree(qset->sq);
kfree(qset->cq);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index e369baf11530..e77d43848955 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -424,9 +424,10 @@ static int otx2_rx_napi_handler(struct otx2_nic *pfvf,
return processed_cqe;
}

-void otx2_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
+int otx2_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
{
struct otx2_nic *pfvf = dev;
+ int cnt = cq->pool_ptrs;
dma_addr_t bufptr;

while (cq->pool_ptrs) {
@@ -435,6 +436,8 @@ void otx2_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
otx2_aura_freeptr(pfvf, cq->cq_idx, bufptr + OTX2_HEAD_ROOM);
cq->pool_ptrs--;
}
+
+ return cnt - cq->pool_ptrs;
}

static int otx2_tx_napi_handler(struct otx2_nic *pfvf,
@@ -521,6 +524,7 @@ int otx2_napi_handler(struct napi_struct *napi, int budget)
struct otx2_cq_queue *cq;
struct otx2_qset *qset;
struct otx2_nic *pfvf;
+ int filled_cnt = -1;

cq_poll = container_of(napi, struct otx2_cq_poll, napi);
pfvf = (struct otx2_nic *)cq_poll->dev;
@@ -541,7 +545,7 @@ int otx2_napi_handler(struct napi_struct *napi, int budget)
}

if (rx_cq && rx_cq->pool_ptrs)
- pfvf->hw_ops->refill_pool_ptrs(pfvf, rx_cq);
+ filled_cnt = pfvf->hw_ops->refill_pool_ptrs(pfvf, rx_cq);
/* Clear the IRQ */
otx2_write64(pfvf, NIX_LF_CINTX_INT(cq_poll->cint_idx), BIT_ULL(0));

@@ -561,9 +565,25 @@ int otx2_napi_handler(struct napi_struct *napi, int budget)
otx2_config_irq_coalescing(pfvf, i);
}

- /* Re-enable interrupts */
- otx2_write64(pfvf, NIX_LF_CINTX_ENA_W1S(cq_poll->cint_idx),
- BIT_ULL(0));
+ if (unlikely(!filled_cnt)) {
+ struct refill_work *work;
+ struct delayed_work *dwork;
+
+ work = &pfvf->refill_wrk[cq->cq_idx];
+ dwork = &work->pool_refill_work;
+ /* Schedule a task if no other task is running */
+ if (!cq->refill_task_sched) {
+ work->napi = napi;
+ cq->refill_task_sched = true;
+ schedule_delayed_work(dwork,
+ msecs_to_jiffies(100));
+ }
+ } else {
+ /* Re-enable interrupts */
+ otx2_write64(pfvf,
+ NIX_LF_CINTX_ENA_W1S(cq_poll->cint_idx),
+ BIT_ULL(0));
+ }
}
return workdone;
}
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
index 9e3bfbe5c480..a82ffca8ce1b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
@@ -170,6 +170,6 @@ void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq,
int size, int qidx);
void otx2_sqe_flush(void *dev, struct otx2_snd_queue *sq,
int size, int qidx);
-void otx2_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq);
-void cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq);
+int otx2_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq);
+int cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq);
#endif /* OTX2_TXRX_H */
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 2d15342c260a..7f0807672071 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -2860,6 +2860,9 @@ static int mtk_hwlro_get_fdir_all(struct net_device *dev,
int i;

for (i = 0; i < MTK_MAX_LRO_IP_CNT; i++) {
+ if (cnt == cmd->rule_cnt)
+ return -EMSGSIZE;
+
if (mac->hwlro_ip[i]) {
rule_locs[cnt] = i;
cnt++;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c
index 92d3952dfa8b..feeb41693c17 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c
@@ -17,8 +17,10 @@ tc_act_parse_ct(struct mlx5e_tc_act_parse_state *parse_state,
if (err)
return err;

- if (mlx5e_is_eswitch_flow(parse_state->flow))
+ if (mlx5e_is_eswitch_flow(parse_state->flow)) {
attr->esw_attr->split_count = attr->esw_attr->out_count;
+ parse_state->if_count = 0;
+ }

attr->flags |= MLX5_ATTR_FLAG_CT;

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c
index 291193f7120d..f63402c48028 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c
@@ -294,6 +294,7 @@ parse_mirred_ovs_master(struct mlx5e_tc_act_parse_state *parse_state,
if (err)
return err;

+ parse_state->if_count = 0;
esw_attr->out_count++;
return 0;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c
index 3b272bbf4c53..368a95fa77d3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/pedit.c
@@ -98,8 +98,10 @@ tc_act_parse_pedit(struct mlx5e_tc_act_parse_state *parse_state,

attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;

- if (ns_type == MLX5_FLOW_NAMESPACE_FDB)
+ if (ns_type == MLX5_FLOW_NAMESPACE_FDB) {
esw_attr->split_count = esw_attr->out_count;
+ parse_state->if_count = 0;
+ }

return 0;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/redirect_ingress.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/redirect_ingress.c
index ad09a8a5f36e..2d1d4a04501b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/redirect_ingress.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/redirect_ingress.c
@@ -66,6 +66,7 @@ tc_act_parse_redirect_ingress(struct mlx5e_tc_act_parse_state *parse_state,
if (err)
return err;

+ parse_state->if_count = 0;
esw_attr->out_count++;

return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c
index c8a3eaf189f6..a13c5e707b83 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan.c
@@ -166,6 +166,7 @@ tc_act_parse_vlan(struct mlx5e_tc_act_parse_state *parse_state,
return err;

esw_attr->split_count = esw_attr->out_count;
+ parse_state->if_count = 0;

return 0;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan_mangle.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan_mangle.c
index 310b99230760..f17575b09788 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan_mangle.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/vlan_mangle.c
@@ -65,8 +65,10 @@ tc_act_parse_vlan_mangle(struct mlx5e_tc_act_parse_state *parse_state,
if (err)
return err;

- if (ns_type == MLX5_FLOW_NAMESPACE_FDB)
+ if (ns_type == MLX5_FLOW_NAMESPACE_FDB) {
attr->esw_attr->split_count = attr->esw_attr->out_count;
+ parse_state->if_count = 0;
+ }

return 0;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 31708d5aa608..4b22a91482ce 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -3939,6 +3939,7 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state,
}

i_split = i + 1;
+ parse_state->if_count = 0;
list_add(&attr->list, &flow->attrs);
}

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index fdf2be548e85..2170539461fa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -22,20 +22,17 @@ static bool mlx5_esw_devlink_port_supported(struct mlx5_eswitch *esw, u16 vport_
mlx5_core_is_ec_vf_vport(esw->dev, vport_num);
}

-static struct devlink_port *mlx5_esw_dl_port_alloc(struct mlx5_eswitch *esw, u16 vport_num)
+static void mlx5_esw_offloads_pf_vf_devlink_port_attrs_set(struct mlx5_eswitch *esw,
+ u16 vport_num,
+ struct devlink_port *dl_port)
{
struct mlx5_core_dev *dev = esw->dev;
struct devlink_port_attrs attrs = {};
struct netdev_phys_item_id ppid = {};
- struct devlink_port *dl_port;
u32 controller_num = 0;
bool external;
u16 pfnum;

- dl_port = kzalloc(sizeof(*dl_port), GFP_KERNEL);
- if (!dl_port)
- return NULL;
-
mlx5_esw_get_port_parent_id(dev, &ppid);
pfnum = mlx5_get_dev_index(dev);
external = mlx5_core_is_ecpf_esw_manager(dev);
@@ -63,12 +60,40 @@ static struct devlink_port *mlx5_esw_dl_port_alloc(struct mlx5_eswitch *esw, u16
devlink_port_attrs_pci_vf_set(dl_port, 0, pfnum,
vport_num - 1, false);
}
- return dl_port;
}

-static void mlx5_esw_dl_port_free(struct devlink_port *dl_port)
+int mlx5_esw_offloads_pf_vf_devlink_port_init(struct mlx5_eswitch *esw, u16 vport_num)
+{
+ struct devlink_port *dl_port;
+ struct mlx5_vport *vport;
+
+ if (!mlx5_esw_devlink_port_supported(esw, vport_num))
+ return 0;
+
+ vport = mlx5_eswitch_get_vport(esw, vport_num);
+ if (IS_ERR(vport))
+ return PTR_ERR(vport);
+
+ dl_port = kzalloc(sizeof(*dl_port), GFP_KERNEL);
+ if (!dl_port)
+ return -ENOMEM;
+
+ mlx5_esw_offloads_pf_vf_devlink_port_attrs_set(esw, vport_num, dl_port);
+
+ vport->dl_port = dl_port;
+ return 0;
+}
+
+void mlx5_esw_offloads_pf_vf_devlink_port_cleanup(struct mlx5_eswitch *esw, u16 vport_num)
{
- kfree(dl_port);
+ struct mlx5_vport *vport;
+
+ vport = mlx5_eswitch_get_vport(esw, vport_num);
+ if (IS_ERR(vport) || !vport->dl_port)
+ return;
+
+ kfree(vport->dl_port);
+ vport->dl_port = NULL;
}

static const struct devlink_port_ops mlx5_esw_dl_port_ops = {
@@ -89,35 +114,29 @@ int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_
struct devlink *devlink;
int err;

- if (!mlx5_esw_devlink_port_supported(esw, vport_num))
- return 0;
-
vport = mlx5_eswitch_get_vport(esw, vport_num);
if (IS_ERR(vport))
return PTR_ERR(vport);

- dl_port = mlx5_esw_dl_port_alloc(esw, vport_num);
+ dl_port = vport->dl_port;
if (!dl_port)
- return -ENOMEM;
+ return 0;

devlink = priv_to_devlink(dev);
dl_port_index = mlx5_esw_vport_to_devlink_port_index(dev, vport_num);
err = devl_port_register_with_ops(devlink, dl_port, dl_port_index,
&mlx5_esw_dl_port_ops);
if (err)
- goto reg_err;
+ return err;

err = devl_rate_leaf_create(dl_port, vport, NULL);
if (err)
goto rate_err;

- vport->dl_port = dl_port;
return 0;

rate_err:
devl_port_unregister(dl_port);
-reg_err:
- mlx5_esw_dl_port_free(dl_port);
return err;
}

@@ -125,11 +144,8 @@ void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, u16 vpo
{
struct mlx5_vport *vport;

- if (!mlx5_esw_devlink_port_supported(esw, vport_num))
- return;
-
vport = mlx5_eswitch_get_vport(esw, vport_num);
- if (IS_ERR(vport))
+ if (IS_ERR(vport) || !vport->dl_port)
return;

if (vport->dl_port->devlink_rate) {
@@ -138,8 +154,6 @@ void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, u16 vpo
}

devl_port_unregister(vport->dl_port);
- mlx5_esw_dl_port_free(vport->dl_port);
- vport->dl_port = NULL;
}

struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u16 vport_num)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 243c455f1029..6e9b1b183190 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1078,7 +1078,7 @@ int mlx5_eswitch_load_vport(struct mlx5_eswitch *esw, u16 vport_num,
if (err)
return err;

- err = esw_offloads_load_rep(esw, vport_num);
+ err = mlx5_esw_offloads_load_rep(esw, vport_num);
if (err)
goto err_rep;

@@ -1091,10 +1091,35 @@ int mlx5_eswitch_load_vport(struct mlx5_eswitch *esw, u16 vport_num,

void mlx5_eswitch_unload_vport(struct mlx5_eswitch *esw, u16 vport_num)
{
- esw_offloads_unload_rep(esw, vport_num);
+ mlx5_esw_offloads_unload_rep(esw, vport_num);
mlx5_esw_vport_disable(esw, vport_num);
}

+static int mlx5_eswitch_load_pf_vf_vport(struct mlx5_eswitch *esw, u16 vport_num,
+ enum mlx5_eswitch_vport_event enabled_events)
+{
+ int err;
+
+ err = mlx5_esw_offloads_init_pf_vf_rep(esw, vport_num);
+ if (err)
+ return err;
+
+ err = mlx5_eswitch_load_vport(esw, vport_num, enabled_events);
+ if (err)
+ goto err_load;
+ return 0;
+
+err_load:
+ mlx5_esw_offloads_cleanup_pf_vf_rep(esw, vport_num);
+ return err;
+}
+
+static void mlx5_eswitch_unload_pf_vf_vport(struct mlx5_eswitch *esw, u16 vport_num)
+{
+ mlx5_eswitch_unload_vport(esw, vport_num);
+ mlx5_esw_offloads_cleanup_pf_vf_rep(esw, vport_num);
+}
+
void mlx5_eswitch_unload_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs)
{
struct mlx5_vport *vport;
@@ -1103,7 +1128,7 @@ void mlx5_eswitch_unload_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs)
mlx5_esw_for_each_vf_vport(esw, i, vport, num_vfs) {
if (!vport->enabled)
continue;
- mlx5_eswitch_unload_vport(esw, vport->vport);
+ mlx5_eswitch_unload_pf_vf_vport(esw, vport->vport);
}
}

@@ -1116,7 +1141,7 @@ static void mlx5_eswitch_unload_ec_vf_vports(struct mlx5_eswitch *esw,
mlx5_esw_for_each_ec_vf_vport(esw, i, vport, num_ec_vfs) {
if (!vport->enabled)
continue;
- mlx5_eswitch_unload_vport(esw, vport->vport);
+ mlx5_eswitch_unload_pf_vf_vport(esw, vport->vport);
}
}

@@ -1128,7 +1153,7 @@ int mlx5_eswitch_load_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs,
int err;

mlx5_esw_for_each_vf_vport(esw, i, vport, num_vfs) {
- err = mlx5_eswitch_load_vport(esw, vport->vport, enabled_events);
+ err = mlx5_eswitch_load_pf_vf_vport(esw, vport->vport, enabled_events);
if (err)
goto vf_err;
}
@@ -1148,7 +1173,7 @@ static int mlx5_eswitch_load_ec_vf_vports(struct mlx5_eswitch *esw, u16 num_ec_v
int err;

mlx5_esw_for_each_ec_vf_vport(esw, i, vport, num_ec_vfs) {
- err = mlx5_eswitch_load_vport(esw, vport->vport, enabled_events);
+ err = mlx5_eswitch_load_pf_vf_vport(esw, vport->vport, enabled_events);
if (err)
goto vf_err;
}
@@ -1187,12 +1212,19 @@ int
mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw,
enum mlx5_eswitch_vport_event enabled_events)
{
+ bool pf_needed;
int ret;

+ pf_needed = mlx5_core_is_ecpf_esw_manager(esw->dev) ||
+ esw->mode == MLX5_ESWITCH_LEGACY;
+
/* Enable PF vport */
- ret = mlx5_eswitch_load_vport(esw, MLX5_VPORT_PF, enabled_events);
- if (ret)
- return ret;
+ if (pf_needed) {
+ ret = mlx5_eswitch_load_pf_vf_vport(esw, MLX5_VPORT_PF,
+ enabled_events);
+ if (ret)
+ return ret;
+ }

/* Enable external host PF HCA */
ret = host_pf_enable_hca(esw->dev);
@@ -1201,7 +1233,7 @@ mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw,

/* Enable ECPF vport */
if (mlx5_ecpf_vport_exists(esw->dev)) {
- ret = mlx5_eswitch_load_vport(esw, MLX5_VPORT_ECPF, enabled_events);
+ ret = mlx5_eswitch_load_pf_vf_vport(esw, MLX5_VPORT_ECPF, enabled_events);
if (ret)
goto ecpf_err;
if (mlx5_core_ec_sriov_enabled(esw->dev)) {
@@ -1224,11 +1256,12 @@ mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw,
mlx5_eswitch_unload_ec_vf_vports(esw, esw->esw_funcs.num_ec_vfs);
ec_vf_err:
if (mlx5_ecpf_vport_exists(esw->dev))
- mlx5_eswitch_unload_vport(esw, MLX5_VPORT_ECPF);
+ mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_ECPF);
ecpf_err:
host_pf_disable_hca(esw->dev);
pf_hca_err:
- mlx5_eswitch_unload_vport(esw, MLX5_VPORT_PF);
+ if (pf_needed)
+ mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_PF);
return ret;
}

@@ -1242,11 +1275,14 @@ void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw)
if (mlx5_ecpf_vport_exists(esw->dev)) {
if (mlx5_core_ec_sriov_enabled(esw->dev))
mlx5_eswitch_unload_ec_vf_vports(esw, esw->esw_funcs.num_vfs);
- mlx5_eswitch_unload_vport(esw, MLX5_VPORT_ECPF);
+ mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_ECPF);
}

host_pf_disable_hca(esw->dev);
- mlx5_eswitch_unload_vport(esw, MLX5_VPORT_PF);
+
+ if (mlx5_core_is_ecpf_esw_manager(esw->dev) ||
+ esw->mode == MLX5_ESWITCH_LEGACY)
+ mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_PF);
}

static void mlx5_eswitch_get_devlink_param(struct mlx5_eswitch *esw)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index ae0dc8a3060d..56d9a261a5c8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -725,8 +725,10 @@ void mlx5_esw_set_spec_source_port(struct mlx5_eswitch *esw,
u16 vport,
struct mlx5_flow_spec *spec);

-int esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num);
-void esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num);
+int mlx5_esw_offloads_init_pf_vf_rep(struct mlx5_eswitch *esw, u16 vport_num);
+void mlx5_esw_offloads_cleanup_pf_vf_rep(struct mlx5_eswitch *esw, u16 vport_num);
+int mlx5_esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num);
+void mlx5_esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num);

int mlx5_esw_offloads_rep_load(struct mlx5_eswitch *esw, u16 vport_num);
void mlx5_esw_offloads_rep_unload(struct mlx5_eswitch *esw, u16 vport_num);
@@ -739,6 +741,8 @@ int mlx5_eswitch_load_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs,
enum mlx5_eswitch_vport_event enabled_events);
void mlx5_eswitch_unload_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs);

+int mlx5_esw_offloads_pf_vf_devlink_port_init(struct mlx5_eswitch *esw, u16 vport_num);
+void mlx5_esw_offloads_pf_vf_devlink_port_cleanup(struct mlx5_eswitch *esw, u16 vport_num);
int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_num);
void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, u16 vport_num);
struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u16 vport_num);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index e59380ee1ead..1ad5a72dcc3f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2424,7 +2424,23 @@ void mlx5_esw_offloads_rep_unload(struct mlx5_eswitch *esw, u16 vport_num)
__esw_offloads_unload_rep(esw, rep, rep_type);
}

-int esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num)
+int mlx5_esw_offloads_init_pf_vf_rep(struct mlx5_eswitch *esw, u16 vport_num)
+{
+ if (esw->mode != MLX5_ESWITCH_OFFLOADS)
+ return 0;
+
+ return mlx5_esw_offloads_pf_vf_devlink_port_init(esw, vport_num);
+}
+
+void mlx5_esw_offloads_cleanup_pf_vf_rep(struct mlx5_eswitch *esw, u16 vport_num)
+{
+ if (esw->mode != MLX5_ESWITCH_OFFLOADS)
+ return;
+
+ mlx5_esw_offloads_pf_vf_devlink_port_cleanup(esw, vport_num);
+}
+
+int mlx5_esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num)
{
int err;

@@ -2448,7 +2464,7 @@ int esw_offloads_load_rep(struct mlx5_eswitch *esw, u16 vport_num)
return err;
}

-void esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num)
+void mlx5_esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num)
{
if (esw->mode != MLX5_ESWITCH_OFFLOADS)
return;
@@ -3076,26 +3092,47 @@ esw_vport_destroy_offloads_acl_tables(struct mlx5_eswitch *esw,
esw_acl_ingress_ofld_cleanup(esw, vport);
}

-static int esw_create_uplink_offloads_acl_tables(struct mlx5_eswitch *esw)
+static int esw_create_offloads_acl_tables(struct mlx5_eswitch *esw)
{
- struct mlx5_vport *vport;
+ struct mlx5_vport *uplink, *manager;
+ int ret;

- vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK);
- if (IS_ERR(vport))
- return PTR_ERR(vport);
+ uplink = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK);
+ if (IS_ERR(uplink))
+ return PTR_ERR(uplink);
+
+ ret = esw_vport_create_offloads_acl_tables(esw, uplink);
+ if (ret)
+ return ret;
+
+ manager = mlx5_eswitch_get_vport(esw, esw->manager_vport);
+ if (IS_ERR(manager)) {
+ ret = PTR_ERR(manager);
+ goto err_manager;
+ }
+
+ ret = esw_vport_create_offloads_acl_tables(esw, manager);
+ if (ret)
+ goto err_manager;

- return esw_vport_create_offloads_acl_tables(esw, vport);
+ return 0;
+
+err_manager:
+ esw_vport_destroy_offloads_acl_tables(esw, uplink);
+ return ret;
}

-static void esw_destroy_uplink_offloads_acl_tables(struct mlx5_eswitch *esw)
+static void esw_destroy_offloads_acl_tables(struct mlx5_eswitch *esw)
{
struct mlx5_vport *vport;

- vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK);
- if (IS_ERR(vport))
- return;
+ vport = mlx5_eswitch_get_vport(esw, esw->manager_vport);
+ if (!IS_ERR(vport))
+ esw_vport_destroy_offloads_acl_tables(esw, vport);

- esw_vport_destroy_offloads_acl_tables(esw, vport);
+ vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK);
+ if (!IS_ERR(vport))
+ esw_vport_destroy_offloads_acl_tables(esw, vport);
}

int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw)
@@ -3140,7 +3177,7 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw)
}
esw->fdb_table.offloads.indir = indir;

- err = esw_create_uplink_offloads_acl_tables(esw);
+ err = esw_create_offloads_acl_tables(esw);
if (err)
goto create_acl_err;

@@ -3181,7 +3218,7 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw)
create_restore_err:
esw_destroy_offloads_table(esw);
create_offloads_err:
- esw_destroy_uplink_offloads_acl_tables(esw);
+ esw_destroy_offloads_acl_tables(esw);
create_acl_err:
mlx5_esw_indir_table_destroy(esw->fdb_table.offloads.indir);
create_indir_err:
@@ -3197,7 +3234,7 @@ static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw)
esw_destroy_offloads_fdb_tables(esw);
esw_destroy_restore_table(esw);
esw_destroy_offloads_table(esw);
- esw_destroy_uplink_offloads_acl_tables(esw);
+ esw_destroy_offloads_acl_tables(esw);
mlx5_esw_indir_table_destroy(esw->fdb_table.offloads.indir);
mutex_destroy(&esw->fdb_table.offloads.vports.lock);
}
@@ -3355,7 +3392,7 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
vport->info.link_state = MLX5_VPORT_ADMIN_STATE_DOWN;

/* Uplink vport rep must load first. */
- err = esw_offloads_load_rep(esw, MLX5_VPORT_UPLINK);
+ err = mlx5_esw_offloads_load_rep(esw, MLX5_VPORT_UPLINK);
if (err)
goto err_uplink;

@@ -3366,7 +3403,7 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
return 0;

err_vports:
- esw_offloads_unload_rep(esw, MLX5_VPORT_UPLINK);
+ mlx5_esw_offloads_unload_rep(esw, MLX5_VPORT_UPLINK);
err_uplink:
esw_offloads_steering_cleanup(esw);
err_steering_init:
@@ -3404,7 +3441,7 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw,
void esw_offloads_disable(struct mlx5_eswitch *esw)
{
mlx5_eswitch_disable_pf_vf_vports(esw);
- esw_offloads_unload_rep(esw, MLX5_VPORT_UPLINK);
+ mlx5_esw_offloads_unload_rep(esw, MLX5_VPORT_UPLINK);
esw_set_passing_vport_metadata(esw, false);
esw_offloads_steering_cleanup(esw);
mapping_destroy(esw->offloads.reg_c0_obj_pool);
diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api.c b/drivers/net/ethernet/microchip/vcap/vcap_api.c
index a418ad8e8770..15a3a31b15d4 100644
--- a/drivers/net/ethernet/microchip/vcap/vcap_api.c
+++ b/drivers/net/ethernet/microchip/vcap/vcap_api.c
@@ -1021,18 +1021,32 @@ static struct vcap_rule_internal *vcap_dup_rule(struct vcap_rule_internal *ri,
list_for_each_entry(ckf, &ri->data.keyfields, ctrl.list) {
newckf = kmemdup(ckf, sizeof(*newckf), GFP_KERNEL);
if (!newckf)
- return ERR_PTR(-ENOMEM);
+ goto err;
list_add_tail(&newckf->ctrl.list, &duprule->data.keyfields);
}

list_for_each_entry(caf, &ri->data.actionfields, ctrl.list) {
newcaf = kmemdup(caf, sizeof(*newcaf), GFP_KERNEL);
if (!newcaf)
- return ERR_PTR(-ENOMEM);
+ goto err;
list_add_tail(&newcaf->ctrl.list, &duprule->data.actionfields);
}

return duprule;
+
+err:
+ list_for_each_entry_safe(ckf, newckf, &duprule->data.keyfields, ctrl.list) {
+ list_del(&ckf->ctrl.list);
+ kfree(ckf);
+ }
+
+ list_for_each_entry_safe(caf, newcaf, &duprule->data.actionfields, ctrl.list) {
+ list_del(&caf->ctrl.list);
+ kfree(caf);
+ }
+
+ kfree(duprule);
+ return ERR_PTR(-ENOMEM);
}

static void vcap_apply_width(u8 *dst, int width, int bytes)
diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c
index 4e412ac0965a..449ed1f5624c 100644
--- a/drivers/net/ethernet/renesas/rswitch.c
+++ b/drivers/net/ethernet/renesas/rswitch.c
@@ -816,10 +816,10 @@ static int rswitch_poll(struct napi_struct *napi, int budget)

netif_wake_subqueue(ndev, 0);

- napi_complete(napi);
-
- rswitch_enadis_data_irq(priv, rdev->tx_queue->index, true);
- rswitch_enadis_data_irq(priv, rdev->rx_queue->index, true);
+ if (napi_complete_done(napi, budget - quota)) {
+ rswitch_enadis_data_irq(priv, rdev->tx_queue->index, true);
+ rswitch_enadis_data_irq(priv, rdev->rx_queue->index, true);
+ }

out:
return budget - quota;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 4727f7be4f86..6931973028ae 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2703,9 +2703,7 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue)

/* We still have pending packets, let's call for a new scheduling */
if (tx_q->dirty_tx != tx_q->cur_tx)
- hrtimer_start(&tx_q->txtimer,
- STMMAC_COAL_TIMER(priv->tx_coal_timer[queue]),
- HRTIMER_MODE_REL);
+ stmmac_tx_timer_arm(priv, queue);

__netif_tx_unlock_bh(netdev_get_tx_queue(priv->dev, queue));

@@ -2986,9 +2984,13 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
static void stmmac_tx_timer_arm(struct stmmac_priv *priv, u32 queue)
{
struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue];
+ u32 tx_coal_timer = priv->tx_coal_timer[queue];
+
+ if (!tx_coal_timer)
+ return;

hrtimer_start(&tx_q->txtimer,
- STMMAC_COAL_TIMER(priv->tx_coal_timer[queue]),
+ STMMAC_COAL_TIMER(tx_coal_timer),
HRTIMER_MODE_REL);
}

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index b6d7981b2d1e..927d3d54658e 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -1800,9 +1800,6 @@ static const struct ksz9477_errata_write ksz9477_errata_writes[] = {
/* Transmit waveform amplitude can be improved (1000BASE-T, 100BASE-TX, 10BASE-Te) */
{0x1c, 0x04, 0x00d0},

- /* Energy Efficient Ethernet (EEE) feature select must be manually disabled */
- {0x07, 0x3c, 0x0000},
-
/* Register settings are required to meet data sheet supply current specifications */
{0x1c, 0x13, 0x6eff},
{0x1c, 0x14, 0xe6ff},
@@ -1847,6 +1844,12 @@ static int ksz9477_config_init(struct phy_device *phydev)
return err;
}

+ /* According to KSZ9477 Errata DS80000754C (Module 4) all EEE modes
+ * in this switch shall be regarded as broken.
+ */
+ if (phydev->dev_flags & MICREL_NO_EEE)
+ phydev->eee_broken_modes = -1;
+
err = genphy_restart_aneg(phydev);
if (err)
return err;
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 0738baa5b82e..e88bedca8f32 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -2629,6 +2629,9 @@ static int r8152_poll(struct napi_struct *napi, int budget)
struct r8152 *tp = container_of(napi, struct r8152, napi);
int work_done;

+ if (!budget)
+ return 0;
+
work_done = rx_bottom(tp, budget);

if (work_done < budget) {
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index ef8eacb596f7..fc0d0114d8c2 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -344,6 +344,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
struct veth_rq *rq = NULL;
+ int ret = NETDEV_TX_OK;
struct net_device *rcv;
int length = skb->len;
bool use_napi = false;
@@ -376,6 +377,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
} else {
drop:
atomic64_inc(&priv->dropped);
+ ret = NET_XMIT_DROP;
}

if (use_napi)
@@ -383,7 +385,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)

rcu_read_unlock();

- return NETDEV_TX_OK;
+ return ret;
}

static u64 veth_stats_tx(struct net_device *dev, u64 *packets, u64 *bytes)
@@ -1445,6 +1447,8 @@ static int veth_open(struct net_device *dev)
netif_carrier_on(peer);
}

+ veth_set_xdp_features(dev);
+
return 0;
}

diff --git a/drivers/parisc/led.c b/drivers/parisc/led.c
index 8bdc5e043831..3737c1021f88 100644
--- a/drivers/parisc/led.c
+++ b/drivers/parisc/led.c
@@ -56,8 +56,8 @@
static int led_type __read_mostly = -1;
static unsigned char lastleds; /* LED state from most recent update */
static unsigned int led_heartbeat __read_mostly = 1;
-static unsigned int led_diskio __read_mostly = 1;
-static unsigned int led_lanrxtx __read_mostly = 1;
+static unsigned int led_diskio __read_mostly;
+static unsigned int led_lanrxtx __read_mostly;
static char lcd_text[32] __read_mostly;
static char lcd_text_default[32] __read_mostly;
static int lcd_no_led_support __read_mostly = 0; /* KittyHawk doesn't support LED on its LCD */
diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c
index 8f28f8696bf3..b8e91cbb6056 100644
--- a/drivers/parisc/sba_iommu.c
+++ b/drivers/parisc/sba_iommu.c
@@ -46,8 +46,6 @@
#include <linux/module.h>

#include <asm/ropes.h>
-#include <asm/mckinley.h> /* for proc_mckinley_root */
-#include <asm/runway.h> /* for proc_runway_root */
#include <asm/page.h> /* for PAGE0 */
#include <asm/pdc.h> /* for PDC_MODEL_* */
#include <asm/pdcpat.h> /* for is_pdc_pat() */
@@ -122,7 +120,7 @@ MODULE_PARM_DESC(sba_reserve_agpgart, "Reserve half of IO pdir as AGPGART");
#endif

static struct proc_dir_entry *proc_runway_root __ro_after_init;
-struct proc_dir_entry *proc_mckinley_root __ro_after_init;
+static struct proc_dir_entry *proc_mckinley_root __ro_after_init;

/************************************
** SBA register read and write support
@@ -1899,9 +1897,7 @@ static int __init sba_driver_callback(struct parisc_device *dev)
int i;
char *version;
void __iomem *sba_addr = ioremap(dev->hpa.start, SBA_FUNC_SIZE);
-#ifdef CONFIG_PROC_FS
- struct proc_dir_entry *root;
-#endif
+ struct proc_dir_entry *root __maybe_unused;

sba_dump_ranges(sba_addr);

@@ -1967,7 +1963,6 @@ static int __init sba_driver_callback(struct parisc_device *dev)

hppa_dma_ops = &sba_ops;

-#ifdef CONFIG_PROC_FS
switch (dev->id.hversion) {
case PLUTO_MCKINLEY_PORT:
if (!proc_mckinley_root)
@@ -1985,7 +1980,6 @@ static int __init sba_driver_callback(struct parisc_device *dev)

proc_create_single("sba_iommu", 0, root, sba_proc_info);
proc_create_single("sba_iommu-bitmap", 0, root, sba_proc_bitmap_info);
-#endif
return 0;
}

diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c
index eee0f9bc3d32..4502bc849c87 100644
--- a/drivers/pinctrl/intel/pinctrl-cherryview.c
+++ b/drivers/pinctrl/intel/pinctrl-cherryview.c
@@ -1701,7 +1701,6 @@ static int chv_pinctrl_probe(struct platform_device *pdev)
struct intel_community_context *cctx;
struct intel_community *community;
struct device *dev = &pdev->dev;
- struct acpi_device *adev = ACPI_COMPANION(dev);
struct intel_pinctrl *pctrl;
acpi_status status;
unsigned int i;
@@ -1769,7 +1768,7 @@ static int chv_pinctrl_probe(struct platform_device *pdev)
if (ret)
return ret;

- status = acpi_install_address_space_handler(adev->handle,
+ status = acpi_install_address_space_handler(ACPI_HANDLE(dev),
community->acpi_space_id,
chv_pinctrl_mmio_access_handler,
NULL, pctrl);
@@ -1786,7 +1785,7 @@ static int chv_pinctrl_remove(struct platform_device *pdev)
struct intel_pinctrl *pctrl = platform_get_drvdata(pdev);
const struct intel_community *community = &pctrl->communities[0];

- acpi_remove_address_space_handler(ACPI_COMPANION(&pdev->dev),
+ acpi_remove_address_space_handler(ACPI_HANDLE(&pdev->dev),
community->acpi_space_id,
chv_pinctrl_mmio_access_handler);

diff --git a/drivers/platform/mellanox/Kconfig b/drivers/platform/mellanox/Kconfig
index 382793e73a60..30b50920b278 100644
--- a/drivers/platform/mellanox/Kconfig
+++ b/drivers/platform/mellanox/Kconfig
@@ -80,8 +80,8 @@ config MLXBF_PMC

config NVSW_SN2201
tristate "Nvidia SN2201 platform driver support"
- depends on HWMON
- depends on I2C
+ depends on HWMON && I2C
+ depends on ACPI || COMPILE_TEST
select REGMAP_I2C
help
This driver provides support for the Nvidia SN2201 platform.
diff --git a/drivers/platform/mellanox/mlxbf-pmc.c b/drivers/platform/mellanox/mlxbf-pmc.c
index be967d797c28..2d4bbe99959e 100644
--- a/drivers/platform/mellanox/mlxbf-pmc.c
+++ b/drivers/platform/mellanox/mlxbf-pmc.c
@@ -191,6 +191,7 @@ static const struct mlxbf_pmc_events mlxbf_pmc_smgen_events[] = {
};

static const struct mlxbf_pmc_events mlxbf_pmc_trio_events_1[] = {
+ { 0x0, "DISABLE" },
{ 0xa0, "TPIO_DATA_BEAT" },
{ 0xa1, "TDMA_DATA_BEAT" },
{ 0xa2, "MAP_DATA_BEAT" },
@@ -214,6 +215,7 @@ static const struct mlxbf_pmc_events mlxbf_pmc_trio_events_1[] = {
};

static const struct mlxbf_pmc_events mlxbf_pmc_trio_events_2[] = {
+ { 0x0, "DISABLE" },
{ 0xa0, "TPIO_DATA_BEAT" },
{ 0xa1, "TDMA_DATA_BEAT" },
{ 0xa2, "MAP_DATA_BEAT" },
@@ -246,6 +248,7 @@ static const struct mlxbf_pmc_events mlxbf_pmc_trio_events_2[] = {
};

static const struct mlxbf_pmc_events mlxbf_pmc_ecc_events[] = {
+ { 0x0, "DISABLE" },
{ 0x100, "ECC_SINGLE_ERROR_CNT" },
{ 0x104, "ECC_DOUBLE_ERROR_CNT" },
{ 0x114, "SERR_INJ" },
@@ -258,6 +261,7 @@ static const struct mlxbf_pmc_events mlxbf_pmc_ecc_events[] = {
};

static const struct mlxbf_pmc_events mlxbf_pmc_mss_events[] = {
+ { 0x0, "DISABLE" },
{ 0xc0, "RXREQ_MSS" },
{ 0xc1, "RXDAT_MSS" },
{ 0xc2, "TXRSP_MSS" },
@@ -265,6 +269,7 @@ static const struct mlxbf_pmc_events mlxbf_pmc_mss_events[] = {
};

static const struct mlxbf_pmc_events mlxbf_pmc_hnf_events[] = {
+ { 0x0, "DISABLE" },
{ 0x45, "HNF_REQUESTS" },
{ 0x46, "HNF_REJECTS" },
{ 0x47, "ALL_BUSY" },
@@ -323,6 +328,7 @@ static const struct mlxbf_pmc_events mlxbf_pmc_hnf_events[] = {
};

static const struct mlxbf_pmc_events mlxbf_pmc_hnfnet_events[] = {
+ { 0x0, "DISABLE" },
{ 0x12, "CDN_REQ" },
{ 0x13, "DDN_REQ" },
{ 0x14, "NDN_REQ" },
@@ -892,7 +898,7 @@ static int mlxbf_pmc_read_event(int blk_num, uint32_t cnt_num, bool is_l3,
uint64_t *result)
{
uint32_t perfcfg_offset, perfval_offset;
- uint64_t perfmon_cfg, perfevt, perfctl;
+ uint64_t perfmon_cfg, perfevt;

if (cnt_num >= pmc->block[blk_num].counters)
return -EINVAL;
@@ -904,25 +910,6 @@ static int mlxbf_pmc_read_event(int blk_num, uint32_t cnt_num, bool is_l3,
perfval_offset = perfcfg_offset +
pmc->block[blk_num].counters * MLXBF_PMC_REG_SIZE;

- /* Set counter in "read" mode */
- perfmon_cfg = FIELD_PREP(MLXBF_PMC_PERFMON_CONFIG_ADDR,
- MLXBF_PMC_PERFCTL);
- perfmon_cfg |= FIELD_PREP(MLXBF_PMC_PERFMON_CONFIG_STROBE, 1);
- perfmon_cfg |= FIELD_PREP(MLXBF_PMC_PERFMON_CONFIG_WR_R_B, 0);
-
- if (mlxbf_pmc_write(pmc->block[blk_num].mmio_base + perfcfg_offset,
- MLXBF_PMC_WRITE_REG_64, perfmon_cfg))
- return -EFAULT;
-
- /* Check if the counter is enabled */
-
- if (mlxbf_pmc_read(pmc->block[blk_num].mmio_base + perfval_offset,
- MLXBF_PMC_READ_REG_64, &perfctl))
- return -EFAULT;
-
- if (!FIELD_GET(MLXBF_PMC_PERFCTL_EN0, perfctl))
- return -EINVAL;
-
/* Set counter in "read" mode */
perfmon_cfg = FIELD_PREP(MLXBF_PMC_PERFMON_CONFIG_ADDR,
MLXBF_PMC_PERFEVT);
@@ -1008,7 +995,7 @@ static ssize_t mlxbf_pmc_counter_show(struct device *dev,
} else
return -EINVAL;

- return sprintf(buf, "0x%llx\n", value);
+ return sysfs_emit(buf, "0x%llx\n", value);
}

/* Store function for "counter" sysfs files */
@@ -1078,13 +1065,13 @@ static ssize_t mlxbf_pmc_event_show(struct device *dev,

err = mlxbf_pmc_read_event(blk_num, cnt_num, is_l3, &evt_num);
if (err)
- return sprintf(buf, "No event being monitored\n");
+ return sysfs_emit(buf, "No event being monitored\n");

evt_name = mlxbf_pmc_get_event_name(pmc->block_name[blk_num], evt_num);
if (!evt_name)
return -EINVAL;

- return sprintf(buf, "0x%llx: %s\n", evt_num, evt_name);
+ return sysfs_emit(buf, "0x%llx: %s\n", evt_num, evt_name);
}

/* Store function for "event" sysfs files */
@@ -1139,9 +1126,9 @@ static ssize_t mlxbf_pmc_event_list_show(struct device *dev,
return -EINVAL;

for (i = 0, buf[0] = '\0'; i < size; ++i) {
- len += sprintf(e_info, "0x%x: %s\n", events[i].evt_num,
- events[i].evt_name);
- if (len > PAGE_SIZE)
+ len += snprintf(e_info, sizeof(e_info), "0x%x: %s\n",
+ events[i].evt_num, events[i].evt_name);
+ if (len >= PAGE_SIZE)
break;
strcat(buf, e_info);
ret = len;
@@ -1168,7 +1155,7 @@ static ssize_t mlxbf_pmc_enable_show(struct device *dev,

value = FIELD_GET(MLXBF_PMC_L3C_PERF_CNT_CFG_EN, perfcnt_cfg);

- return sprintf(buf, "%d\n", value);
+ return sysfs_emit(buf, "%d\n", value);
}

/* Store function for "enable" sysfs files - only for l3cache */
diff --git a/drivers/platform/mellanox/mlxbf-tmfifo.c b/drivers/platform/mellanox/mlxbf-tmfifo.c
index b600b77d91ef..f3696a54a2bd 100644
--- a/drivers/platform/mellanox/mlxbf-tmfifo.c
+++ b/drivers/platform/mellanox/mlxbf-tmfifo.c
@@ -59,6 +59,7 @@ struct mlxbf_tmfifo;
* @vq: pointer to the virtio virtqueue
* @desc: current descriptor of the pending packet
* @desc_head: head descriptor of the pending packet
+ * @drop_desc: dummy desc for packet dropping
* @cur_len: processed length of the current descriptor
* @rem_len: remaining length of the pending packet
* @pkt_len: total length of the pending packet
@@ -75,6 +76,7 @@ struct mlxbf_tmfifo_vring {
struct virtqueue *vq;
struct vring_desc *desc;
struct vring_desc *desc_head;
+ struct vring_desc drop_desc;
int cur_len;
int rem_len;
u32 pkt_len;
@@ -86,6 +88,14 @@ struct mlxbf_tmfifo_vring {
struct mlxbf_tmfifo *fifo;
};

+/* Check whether vring is in drop mode. */
+#define IS_VRING_DROP(_r) ({ \
+ typeof(_r) (r) = (_r); \
+ (r->desc_head == &r->drop_desc ? true : false); })
+
+/* A stub length to drop maximum length packet. */
+#define VRING_DROP_DESC_MAX_LEN GENMASK(15, 0)
+
/* Interrupt types. */
enum {
MLXBF_TM_RX_LWM_IRQ,
@@ -214,7 +224,7 @@ static u8 mlxbf_tmfifo_net_default_mac[ETH_ALEN] = {
static efi_char16_t mlxbf_tmfifo_efi_name[] = L"RshimMacAddr";

/* Maximum L2 header length. */
-#define MLXBF_TMFIFO_NET_L2_OVERHEAD 36
+#define MLXBF_TMFIFO_NET_L2_OVERHEAD (ETH_HLEN + VLAN_HLEN)

/* Supported virtio-net features. */
#define MLXBF_TMFIFO_NET_FEATURES \
@@ -262,6 +272,7 @@ static int mlxbf_tmfifo_alloc_vrings(struct mlxbf_tmfifo *fifo,
vring->align = SMP_CACHE_BYTES;
vring->index = i;
vring->vdev_id = tm_vdev->vdev.id.device;
+ vring->drop_desc.len = VRING_DROP_DESC_MAX_LEN;
dev = &tm_vdev->vdev.dev;

size = vring_size(vring->num, vring->align);
@@ -367,7 +378,7 @@ static u32 mlxbf_tmfifo_get_pkt_len(struct mlxbf_tmfifo_vring *vring,
return len;
}

-static void mlxbf_tmfifo_release_pending_pkt(struct mlxbf_tmfifo_vring *vring)
+static void mlxbf_tmfifo_release_pkt(struct mlxbf_tmfifo_vring *vring)
{
struct vring_desc *desc_head;
u32 len = 0;
@@ -596,19 +607,25 @@ static void mlxbf_tmfifo_rxtx_word(struct mlxbf_tmfifo_vring *vring,

if (vring->cur_len + sizeof(u64) <= len) {
/* The whole word. */
- if (is_rx)
- memcpy(addr + vring->cur_len, &data, sizeof(u64));
- else
- memcpy(&data, addr + vring->cur_len, sizeof(u64));
+ if (!IS_VRING_DROP(vring)) {
+ if (is_rx)
+ memcpy(addr + vring->cur_len, &data,
+ sizeof(u64));
+ else
+ memcpy(&data, addr + vring->cur_len,
+ sizeof(u64));
+ }
vring->cur_len += sizeof(u64);
} else {
/* Leftover bytes. */
- if (is_rx)
- memcpy(addr + vring->cur_len, &data,
- len - vring->cur_len);
- else
- memcpy(&data, addr + vring->cur_len,
- len - vring->cur_len);
+ if (!IS_VRING_DROP(vring)) {
+ if (is_rx)
+ memcpy(addr + vring->cur_len, &data,
+ len - vring->cur_len);
+ else
+ memcpy(&data, addr + vring->cur_len,
+ len - vring->cur_len);
+ }
vring->cur_len = len;
}

@@ -625,13 +642,14 @@ static void mlxbf_tmfifo_rxtx_word(struct mlxbf_tmfifo_vring *vring,
* flag is set.
*/
static void mlxbf_tmfifo_rxtx_header(struct mlxbf_tmfifo_vring *vring,
- struct vring_desc *desc,
+ struct vring_desc **desc,
bool is_rx, bool *vring_change)
{
struct mlxbf_tmfifo *fifo = vring->fifo;
struct virtio_net_config *config;
struct mlxbf_tmfifo_msg_hdr hdr;
int vdev_id, hdr_len;
+ bool drop_rx = false;

/* Read/Write packet header. */
if (is_rx) {
@@ -651,8 +669,8 @@ static void mlxbf_tmfifo_rxtx_header(struct mlxbf_tmfifo_vring *vring,
if (ntohs(hdr.len) >
__virtio16_to_cpu(virtio_legacy_is_little_endian(),
config->mtu) +
- MLXBF_TMFIFO_NET_L2_OVERHEAD)
- return;
+ MLXBF_TMFIFO_NET_L2_OVERHEAD)
+ drop_rx = true;
} else {
vdev_id = VIRTIO_ID_CONSOLE;
hdr_len = 0;
@@ -667,16 +685,25 @@ static void mlxbf_tmfifo_rxtx_header(struct mlxbf_tmfifo_vring *vring,

if (!tm_dev2)
return;
- vring->desc = desc;
+ vring->desc = *desc;
vring = &tm_dev2->vrings[MLXBF_TMFIFO_VRING_RX];
*vring_change = true;
}
+
+ if (drop_rx && !IS_VRING_DROP(vring)) {
+ if (vring->desc_head)
+ mlxbf_tmfifo_release_pkt(vring);
+ *desc = &vring->drop_desc;
+ vring->desc_head = *desc;
+ vring->desc = *desc;
+ }
+
vring->pkt_len = ntohs(hdr.len) + hdr_len;
} else {
/* Network virtio has an extra header. */
hdr_len = (vring->vdev_id == VIRTIO_ID_NET) ?
sizeof(struct virtio_net_hdr) : 0;
- vring->pkt_len = mlxbf_tmfifo_get_pkt_len(vring, desc);
+ vring->pkt_len = mlxbf_tmfifo_get_pkt_len(vring, *desc);
hdr.type = (vring->vdev_id == VIRTIO_ID_NET) ?
VIRTIO_ID_NET : VIRTIO_ID_CONSOLE;
hdr.len = htons(vring->pkt_len - hdr_len);
@@ -709,15 +736,23 @@ static bool mlxbf_tmfifo_rxtx_one_desc(struct mlxbf_tmfifo_vring *vring,
/* Get the descriptor of the next packet. */
if (!vring->desc) {
desc = mlxbf_tmfifo_get_next_pkt(vring, is_rx);
- if (!desc)
- return false;
+ if (!desc) {
+ /* Drop next Rx packet to avoid stuck. */
+ if (is_rx) {
+ desc = &vring->drop_desc;
+ vring->desc_head = desc;
+ vring->desc = desc;
+ } else {
+ return false;
+ }
+ }
} else {
desc = vring->desc;
}

/* Beginning of a packet. Start to Rx/Tx packet header. */
if (vring->pkt_len == 0) {
- mlxbf_tmfifo_rxtx_header(vring, desc, is_rx, &vring_change);
+ mlxbf_tmfifo_rxtx_header(vring, &desc, is_rx, &vring_change);
(*avail)--;

/* Return if new packet is for another ring. */
@@ -743,17 +778,24 @@ static bool mlxbf_tmfifo_rxtx_one_desc(struct mlxbf_tmfifo_vring *vring,
vring->rem_len -= len;

/* Get the next desc on the chain. */
- if (vring->rem_len > 0 &&
+ if (!IS_VRING_DROP(vring) && vring->rem_len > 0 &&
(virtio16_to_cpu(vdev, desc->flags) & VRING_DESC_F_NEXT)) {
idx = virtio16_to_cpu(vdev, desc->next);
desc = &vr->desc[idx];
goto mlxbf_tmfifo_desc_done;
}

- /* Done and release the pending packet. */
- mlxbf_tmfifo_release_pending_pkt(vring);
+ /* Done and release the packet. */
desc = NULL;
fifo->vring[is_rx] = NULL;
+ if (!IS_VRING_DROP(vring)) {
+ mlxbf_tmfifo_release_pkt(vring);
+ } else {
+ vring->pkt_len = 0;
+ vring->desc_head = NULL;
+ vring->desc = NULL;
+ return false;
+ }

/*
* Make sure the load/store are in order before
@@ -933,7 +975,7 @@ static void mlxbf_tmfifo_virtio_del_vqs(struct virtio_device *vdev)

/* Release the pending packet. */
if (vring->desc)
- mlxbf_tmfifo_release_pending_pkt(vring);
+ mlxbf_tmfifo_release_pkt(vring);
vq = vring->vq;
if (vq) {
vring->vq = NULL;
diff --git a/drivers/pwm/pwm-atmel-tcb.c b/drivers/pwm/pwm-atmel-tcb.c
index 4a116dc44f6e..2826fc216d29 100644
--- a/drivers/pwm/pwm-atmel-tcb.c
+++ b/drivers/pwm/pwm-atmel-tcb.c
@@ -422,13 +422,14 @@ static int atmel_tcb_pwm_probe(struct platform_device *pdev)
struct atmel_tcb_pwm_chip *tcbpwm;
const struct atmel_tcb_config *config;
struct device_node *np = pdev->dev.of_node;
- struct regmap *regmap;
- struct clk *clk, *gclk = NULL;
- struct clk *slow_clk;
char clk_name[] = "t0_clk";
int err;
int channel;

+ tcbpwm = devm_kzalloc(&pdev->dev, sizeof(*tcbpwm), GFP_KERNEL);
+ if (tcbpwm == NULL)
+ return -ENOMEM;
+
err = of_property_read_u32(np, "reg", &channel);
if (err < 0) {
dev_err(&pdev->dev,
@@ -437,49 +438,43 @@ static int atmel_tcb_pwm_probe(struct platform_device *pdev)
return err;
}

- regmap = syscon_node_to_regmap(np->parent);
- if (IS_ERR(regmap))
- return PTR_ERR(regmap);
+ tcbpwm->regmap = syscon_node_to_regmap(np->parent);
+ if (IS_ERR(tcbpwm->regmap))
+ return PTR_ERR(tcbpwm->regmap);

- slow_clk = of_clk_get_by_name(np->parent, "slow_clk");
- if (IS_ERR(slow_clk))
- return PTR_ERR(slow_clk);
+ tcbpwm->slow_clk = of_clk_get_by_name(np->parent, "slow_clk");
+ if (IS_ERR(tcbpwm->slow_clk))
+ return PTR_ERR(tcbpwm->slow_clk);

clk_name[1] += channel;
- clk = of_clk_get_by_name(np->parent, clk_name);
- if (IS_ERR(clk))
- clk = of_clk_get_by_name(np->parent, "t0_clk");
- if (IS_ERR(clk))
- return PTR_ERR(clk);
+ tcbpwm->clk = of_clk_get_by_name(np->parent, clk_name);
+ if (IS_ERR(tcbpwm->clk))
+ tcbpwm->clk = of_clk_get_by_name(np->parent, "t0_clk");
+ if (IS_ERR(tcbpwm->clk)) {
+ err = PTR_ERR(tcbpwm->clk);
+ goto err_slow_clk;
+ }

match = of_match_node(atmel_tcb_of_match, np->parent);
config = match->data;

if (config->has_gclk) {
- gclk = of_clk_get_by_name(np->parent, "gclk");
- if (IS_ERR(gclk))
- return PTR_ERR(gclk);
- }
-
- tcbpwm = devm_kzalloc(&pdev->dev, sizeof(*tcbpwm), GFP_KERNEL);
- if (tcbpwm == NULL) {
- err = -ENOMEM;
- goto err_slow_clk;
+ tcbpwm->gclk = of_clk_get_by_name(np->parent, "gclk");
+ if (IS_ERR(tcbpwm->gclk)) {
+ err = PTR_ERR(tcbpwm->gclk);
+ goto err_clk;
+ }
}

tcbpwm->chip.dev = &pdev->dev;
tcbpwm->chip.ops = &atmel_tcb_pwm_ops;
tcbpwm->chip.npwm = NPWM;
tcbpwm->channel = channel;
- tcbpwm->regmap = regmap;
- tcbpwm->clk = clk;
- tcbpwm->gclk = gclk;
- tcbpwm->slow_clk = slow_clk;
tcbpwm->width = config->counter_width;

- err = clk_prepare_enable(slow_clk);
+ err = clk_prepare_enable(tcbpwm->slow_clk);
if (err)
- goto err_slow_clk;
+ goto err_gclk;

spin_lock_init(&tcbpwm->lock);

@@ -494,8 +489,14 @@ static int atmel_tcb_pwm_probe(struct platform_device *pdev)
err_disable_clk:
clk_disable_unprepare(tcbpwm->slow_clk);

+err_gclk:
+ clk_put(tcbpwm->gclk);
+
+err_clk:
+ clk_put(tcbpwm->clk);
+
err_slow_clk:
- clk_put(slow_clk);
+ clk_put(tcbpwm->slow_clk);

return err;
}
@@ -507,8 +508,9 @@ static void atmel_tcb_pwm_remove(struct platform_device *pdev)
pwmchip_remove(&tcbpwm->chip);

clk_disable_unprepare(tcbpwm->slow_clk);
- clk_put(tcbpwm->slow_clk);
+ clk_put(tcbpwm->gclk);
clk_put(tcbpwm->clk);
+ clk_put(tcbpwm->slow_clk);
}

static const struct of_device_id atmel_tcb_pwm_dt_ids[] = {
diff --git a/drivers/pwm/pwm-lpc32xx.c b/drivers/pwm/pwm-lpc32xx.c
index 86a0ea0f6955..806f0bb3ad6d 100644
--- a/drivers/pwm/pwm-lpc32xx.c
+++ b/drivers/pwm/pwm-lpc32xx.c
@@ -51,10 +51,10 @@ static int lpc32xx_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
if (duty_cycles > 255)
duty_cycles = 255;

- val = readl(lpc32xx->base + (pwm->hwpwm << 2));
+ val = readl(lpc32xx->base);
val &= ~0xFFFF;
val |= (period_cycles << 8) | duty_cycles;
- writel(val, lpc32xx->base + (pwm->hwpwm << 2));
+ writel(val, lpc32xx->base);

return 0;
}
@@ -69,9 +69,9 @@ static int lpc32xx_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm)
if (ret)
return ret;

- val = readl(lpc32xx->base + (pwm->hwpwm << 2));
+ val = readl(lpc32xx->base);
val |= PWM_ENABLE;
- writel(val, lpc32xx->base + (pwm->hwpwm << 2));
+ writel(val, lpc32xx->base);

return 0;
}
@@ -81,9 +81,9 @@ static void lpc32xx_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
struct lpc32xx_pwm_chip *lpc32xx = to_lpc32xx_pwm_chip(chip);
u32 val;

- val = readl(lpc32xx->base + (pwm->hwpwm << 2));
+ val = readl(lpc32xx->base);
val &= ~PWM_ENABLE;
- writel(val, lpc32xx->base + (pwm->hwpwm << 2));
+ writel(val, lpc32xx->base);

clk_disable_unprepare(lpc32xx->clk);
}
@@ -141,9 +141,9 @@ static int lpc32xx_pwm_probe(struct platform_device *pdev)
lpc32xx->chip.npwm = 1;

/* If PWM is disabled, configure the output to the default value */
- val = readl(lpc32xx->base + (lpc32xx->chip.pwms[0].hwpwm << 2));
+ val = readl(lpc32xx->base);
val &= ~PWM_PIN_LEVEL;
- writel(val, lpc32xx->base + (lpc32xx->chip.pwms[0].hwpwm << 2));
+ writel(val, lpc32xx->base);

ret = devm_pwmchip_add(&pdev->dev, &lpc32xx->chip);
if (ret < 0) {
diff --git a/drivers/regulator/raa215300.c b/drivers/regulator/raa215300.c
index 24a1c89f5dbc..253645696d0b 100644
--- a/drivers/regulator/raa215300.c
+++ b/drivers/regulator/raa215300.c
@@ -38,10 +38,6 @@
#define RAA215300_REG_BLOCK_EN_RTC_EN BIT(6)
#define RAA215300_RTC_DEFAULT_ADDR 0x6f

-const char *clkin_name = "clkin";
-const char *xin_name = "xin";
-static struct clk *clk;
-
static const struct regmap_config raa215300_regmap_config = {
.reg_bits = 8,
.val_bits = 8,
@@ -51,10 +47,6 @@ static const struct regmap_config raa215300_regmap_config = {
static void raa215300_rtc_unregister_device(void *data)
{
i2c_unregister_device(data);
- if (!clk) {
- clk_unregister_fixed_rate(clk);
- clk = NULL;
- }
}

static int raa215300_clk_present(struct i2c_client *client, const char *name)
@@ -71,8 +63,10 @@ static int raa215300_clk_present(struct i2c_client *client, const char *name)
static int raa215300_i2c_probe(struct i2c_client *client)
{
struct device *dev = &client->dev;
- const char *clk_name = xin_name;
+ const char *clkin_name = "clkin";
unsigned int pmic_version, val;
+ const char *xin_name = "xin";
+ const char *clk_name = NULL;
struct regmap *regmap;
int ret;

@@ -114,24 +108,32 @@ static int raa215300_i2c_probe(struct i2c_client *client)
ret = raa215300_clk_present(client, xin_name);
if (ret < 0) {
return ret;
- } else if (!ret) {
+ } else if (ret) {
+ clk_name = xin_name;
+ } else {
ret = raa215300_clk_present(client, clkin_name);
if (ret < 0)
return ret;
-
- clk_name = clkin_name;
+ if (ret)
+ clk_name = clkin_name;
}

- if (ret) {
+ if (clk_name) {
char *name = pmic_version >= 0x12 ? "isl1208" : "raa215300_a0";
struct device_node *np = client->dev.of_node;
u32 addr = RAA215300_RTC_DEFAULT_ADDR;
struct i2c_board_info info = {};
struct i2c_client *rtc_client;
+ struct clk_hw *hw;
ssize_t size;

- clk = clk_register_fixed_rate(NULL, clk_name, NULL, 0, 32000);
- clk_register_clkdev(clk, clk_name, NULL);
+ hw = devm_clk_hw_register_fixed_rate(dev, clk_name, NULL, 0, 32000);
+ if (IS_ERR(hw))
+ return PTR_ERR(hw);
+
+ ret = devm_clk_hw_register_clkdev(dev, hw, clk_name, NULL);
+ if (ret)
+ return dev_err_probe(dev, ret, "Failed to initialize clkdev\n");

if (np) {
int i;
diff --git a/drivers/regulator/tps6287x-regulator.c b/drivers/regulator/tps6287x-regulator.c
index b1c0963586ac..e45579a4498c 100644
--- a/drivers/regulator/tps6287x-regulator.c
+++ b/drivers/regulator/tps6287x-regulator.c
@@ -119,7 +119,7 @@ static struct regulator_desc tps6287x_reg = {
.ramp_mask = TPS6287X_CTRL1_VRAMP,
.ramp_delay_table = tps6287x_ramp_table,
.n_ramp_values = ARRAY_SIZE(tps6287x_ramp_table),
- .n_voltages = 256,
+ .n_voltages = 256 * ARRAY_SIZE(tps6287x_voltage_ranges),
.linear_ranges = tps6287x_voltage_ranges,
.n_linear_ranges = ARRAY_SIZE(tps6287x_voltage_ranges),
.linear_range_selectors = tps6287x_voltage_range_sel,
diff --git a/drivers/regulator/tps6594-regulator.c b/drivers/regulator/tps6594-regulator.c
index d5a574ec6d12..47c3b7efe145 100644
--- a/drivers/regulator/tps6594-regulator.c
+++ b/drivers/regulator/tps6594-regulator.c
@@ -384,21 +384,19 @@ static int tps6594_request_reg_irqs(struct platform_device *pdev,
if (irq < 0)
return -EINVAL;

- irq_data[*irq_idx + j].dev = tps->dev;
- irq_data[*irq_idx + j].type = irq_type;
- irq_data[*irq_idx + j].rdev = rdev;
+ irq_data[*irq_idx].dev = tps->dev;
+ irq_data[*irq_idx].type = irq_type;
+ irq_data[*irq_idx].rdev = rdev;

error = devm_request_threaded_irq(tps->dev, irq, NULL,
- tps6594_regulator_irq_handler,
- IRQF_ONESHOT,
- irq_type->irq_name,
- &irq_data[*irq_idx]);
- (*irq_idx)++;
+ tps6594_regulator_irq_handler, IRQF_ONESHOT,
+ irq_type->irq_name, &irq_data[*irq_idx]);
if (error) {
dev_err(tps->dev, "tps6594 failed to request %s IRQ %d: %d\n",
irq_type->irq_name, irq, error);
return error;
}
+ (*irq_idx)++;
}
return 0;
}
@@ -420,8 +418,8 @@ static int tps6594_regulator_probe(struct platform_device *pdev)
int error, i, irq, multi, delta;
int irq_idx = 0;
int buck_idx = 0;
- int ext_reg_irq_nb = 2;
-
+ size_t ext_reg_irq_nb = 2;
+ size_t reg_irq_nb;
enum {
MULTI_BUCK12,
MULTI_BUCK123,
@@ -484,15 +482,16 @@ static int tps6594_regulator_probe(struct platform_device *pdev)
}
}

- if (tps->chip_id == LP8764)
+ if (tps->chip_id == LP8764) {
/* There is only 4 buck on LP8764 */
buck_configured[4] = 1;
+ reg_irq_nb = size_mul(REGS_INT_NB, (BUCK_NB - 1));
+ } else {
+ reg_irq_nb = size_mul(REGS_INT_NB, (size_add(BUCK_NB, LDO_NB)));
+ }

- irq_data = devm_kmalloc_array(tps->dev,
- REGS_INT_NB * sizeof(struct tps6594_regulator_irq_data),
- ARRAY_SIZE(tps6594_bucks_irq_types) +
- ARRAY_SIZE(tps6594_ldos_irq_types),
- GFP_KERNEL);
+ irq_data = devm_kmalloc_array(tps->dev, reg_irq_nb,
+ sizeof(struct tps6594_regulator_irq_data), GFP_KERNEL);
if (!irq_data)
return -ENOMEM;

diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index 4b23c9f7f3e5..6b99f7dd0643 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -413,6 +413,7 @@ static int zcdn_create(const char *name)
ZCRYPT_NAME "_%d", (int)MINOR(devt));
nodename[sizeof(nodename) - 1] = '\0';
if (dev_set_name(&zcdndev->device, nodename)) {
+ kfree(zcdndev);
rc = -EINVAL;
goto unlockout;
}
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index b00222459607..44449c70a375 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -3093,8 +3093,6 @@ qla24xx_vport_create(struct fc_vport *fc_vport, bool disable)
vha->flags.difdix_supported = 1;
ql_dbg(ql_dbg_user, vha, 0x7082,
"Registered for DIF/DIX type 1 and 3 protection.\n");
- if (ql2xenabledif == 1)
- prot = SHOST_DIX_TYPE0_PROTECTION;
scsi_host_set_prot(vha->host,
prot | SHOST_DIF_TYPE1_PROTECTION
| SHOST_DIF_TYPE2_PROTECTION
diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c
index d7e8454304ce..ab637324262f 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.c
+++ b/drivers/scsi/qla2xxx/qla_dbg.c
@@ -18,7 +18,7 @@
* | Queue Command and IO tracing | 0x3074 | 0x300b |
* | | | 0x3027-0x3028 |
* | | | 0x303d-0x3041 |
- * | | | 0x302d,0x3033 |
+ * | | | 0x302e,0x3033 |
* | | | 0x3036,0x3038 |
* | | | 0x303a |
* | DPC Thread | 0x4023 | 0x4002,0x4013 |
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 4ae38305c15a..97852e5f7a87 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -466,6 +466,7 @@ static inline be_id_t port_id_to_be_id(port_id_t port_id)
}

struct tmf_arg {
+ struct list_head tmf_elem;
struct qla_qpair *qpair;
struct fc_port *fcport;
struct scsi_qla_host *vha;
@@ -2541,7 +2542,6 @@ enum rscn_addr_format {
typedef struct fc_port {
struct list_head list;
struct scsi_qla_host *vha;
- struct list_head tmf_pending;

unsigned int conf_compl_supported:1;
unsigned int deleted:2;
@@ -2562,9 +2562,6 @@ typedef struct fc_port {
unsigned int do_prli_nvme:1;

uint8_t nvme_flag;
- uint8_t active_tmf;
-#define MAX_ACTIVE_TMF 8
-
uint8_t node_name[WWN_SIZE];
uint8_t port_name[WWN_SIZE];
port_id_t d_id;
@@ -3745,6 +3742,16 @@ struct qla_fw_resources {
u16 pad;
};

+struct qla_fw_res {
+ u16 iocb_total;
+ u16 iocb_limit;
+ atomic_t iocb_used;
+
+ u16 exch_total;
+ u16 exch_limit;
+ atomic_t exch_used;
+};
+
#define QLA_IOCB_PCT_LIMIT 95

struct qla_buf_pool {
@@ -4387,7 +4394,6 @@ struct qla_hw_data {
uint8_t aen_mbx_count;
atomic_t num_pend_mbx_stage1;
atomic_t num_pend_mbx_stage2;
- atomic_t num_pend_mbx_stage3;
uint16_t frame_payload_size;

uint32_t login_retry_count;
@@ -4656,6 +4662,8 @@ struct qla_hw_data {
uint32_t flt_region_aux_img_status_sec;
};
uint8_t active_image;
+ uint8_t active_tmf;
+#define MAX_ACTIVE_TMF 8

/* Needed for BEACON */
uint16_t beacon_blink_led;
@@ -4670,6 +4678,8 @@ struct qla_hw_data {

struct qla_msix_entry *msix_entries;

+ struct list_head tmf_pending;
+ struct list_head tmf_active;
struct list_head vp_list; /* list of VP */
unsigned long vp_idx_map[(MAX_MULTI_ID_FABRIC / 8) /
sizeof(unsigned long)];
@@ -4799,6 +4809,7 @@ struct qla_hw_data {
struct els_reject elsrej;
u8 edif_post_stop_cnt_down;
struct qla_vp_map *vp_map;
+ struct qla_fw_res fwres ____cacheline_aligned;
};

#define RX_ELS_SIZE (roundup(sizeof(struct enode) + ELS_MAX_PAYLOAD, SMP_CACHE_BYTES))
diff --git a/drivers/scsi/qla2xxx/qla_dfs.c b/drivers/scsi/qla2xxx/qla_dfs.c
index 1925cc6897b6..f060e593685d 100644
--- a/drivers/scsi/qla2xxx/qla_dfs.c
+++ b/drivers/scsi/qla2xxx/qla_dfs.c
@@ -276,6 +276,16 @@ qla_dfs_fw_resource_cnt_show(struct seq_file *s, void *unused)

seq_printf(s, "estimate exchange used[%d] high water limit [%d] n",
exch_used, ha->base_qpair->fwres.exch_limit);
+
+ if (ql2xenforce_iocb_limit == 2) {
+ iocbs_used = atomic_read(&ha->fwres.iocb_used);
+ exch_used = atomic_read(&ha->fwres.exch_used);
+ seq_printf(s, " estimate iocb2 used [%d] high water limit [%d]\n",
+ iocbs_used, ha->fwres.iocb_limit);
+
+ seq_printf(s, " estimate exchange2 used[%d] high water limit [%d] \n",
+ exch_used, ha->fwres.exch_limit);
+ }
}

return 0;
diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
index ba7831f24734..33fba9d62969 100644
--- a/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/drivers/scsi/qla2xxx/qla_gbl.h
@@ -143,6 +143,7 @@ void qla_edif_sess_down(struct scsi_qla_host *vha, struct fc_port *sess);
void qla_edif_clear_appdata(struct scsi_qla_host *vha,
struct fc_port *fcport);
const char *sc_to_str(uint16_t cmd);
+void qla_adjust_iocb_limit(scsi_qla_host_t *vha);

/*
* Global Data in qla_os.c source file.
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 33d4914e19fa..0cd4f909f940 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -508,6 +508,7 @@ static
void qla24xx_handle_adisc_event(scsi_qla_host_t *vha, struct event_arg *ea)
{
struct fc_port *fcport = ea->fcport;
+ unsigned long flags;

ql_dbg(ql_dbg_disc, vha, 0x20d2,
"%s %8phC DS %d LS %d rc %d login %d|%d rscn %d|%d lid %d\n",
@@ -522,9 +523,15 @@ void qla24xx_handle_adisc_event(scsi_qla_host_t *vha, struct event_arg *ea)
ql_dbg(ql_dbg_disc, vha, 0x2066,
"%s %8phC: adisc fail: post delete\n",
__func__, ea->fcport->port_name);
+
+ spin_lock_irqsave(&vha->work_lock, flags);
/* deleted = 0 & logout_on_delete = force fw cleanup */
- fcport->deleted = 0;
+ if (fcport->deleted == QLA_SESS_DELETED)
+ fcport->deleted = 0;
+
fcport->logout_on_delete = 1;
+ spin_unlock_irqrestore(&vha->work_lock, flags);
+
qlt_schedule_sess_for_deletion(ea->fcport);
return;
}
@@ -1134,7 +1141,7 @@ int qla24xx_async_gnl(struct scsi_qla_host *vha, fc_port_t *fcport)
u16 *mb;

if (!vha->flags.online || (fcport->flags & FCF_ASYNC_SENT))
- return rval;
+ goto done;

ql_dbg(ql_dbg_disc, vha, 0x20d9,
"Async-gnlist WWPN %8phC \n", fcport->port_name);
@@ -1188,8 +1195,9 @@ int qla24xx_async_gnl(struct scsi_qla_host *vha, fc_port_t *fcport)
done_free_sp:
/* ref: INIT */
kref_put(&sp->cmd_kref, qla2x00_sp_release);
+ fcport->flags &= ~(FCF_ASYNC_SENT);
done:
- fcport->flags &= ~(FCF_ASYNC_ACTIVE | FCF_ASYNC_SENT);
+ fcport->flags &= ~(FCF_ASYNC_ACTIVE);
return rval;
}

@@ -1446,7 +1454,6 @@ void __qla24xx_handle_gpdb_event(scsi_qla_host_t *vha, struct event_arg *ea)

spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
ea->fcport->login_gen++;
- ea->fcport->deleted = 0;
ea->fcport->logout_on_delete = 1;

if (!ea->fcport->login_succ && !IS_SW_RESV_ADDR(ea->fcport->d_id)) {
@@ -1996,12 +2003,11 @@ qla2x00_tmf_iocb_timeout(void *data)
int rc, h;
unsigned long flags;

- if (sp->type == SRB_MARKER) {
- complete(&tmf->u.tmf.comp);
- return;
- }
+ if (sp->type == SRB_MARKER)
+ rc = QLA_FUNCTION_FAILED;
+ else
+ rc = qla24xx_async_abort_cmd(sp, false);

- rc = qla24xx_async_abort_cmd(sp, false);
if (rc) {
spin_lock_irqsave(sp->qpair->qp_lock_ptr, flags);
for (h = 1; h < sp->qpair->req->num_outstanding_cmds; h++) {
@@ -2032,10 +2038,14 @@ static void qla_marker_sp_done(srb_t *sp, int res)
complete(&tmf->u.tmf.comp);
}

-#define START_SP_W_RETRIES(_sp, _rval) \
+#define START_SP_W_RETRIES(_sp, _rval, _chip_gen, _login_gen) \
{\
int cnt = 5; \
do { \
+ if (_chip_gen != sp->vha->hw->chip_reset || _login_gen != sp->fcport->login_gen) {\
+ _rval = EINVAL; \
+ break; \
+ } \
_rval = qla2x00_start_sp(_sp); \
if (_rval == EAGAIN) \
msleep(1); \
@@ -2058,6 +2068,7 @@ qla26xx_marker(struct tmf_arg *arg)
srb_t *sp;
int rval = QLA_FUNCTION_FAILED;
fc_port_t *fcport = arg->fcport;
+ u32 chip_gen, login_gen;

if (TMF_NOT_READY(arg->fcport)) {
ql_dbg(ql_dbg_taskm, vha, 0x8039,
@@ -2067,6 +2078,9 @@ qla26xx_marker(struct tmf_arg *arg)
return QLA_SUSPENDED;
}

+ chip_gen = vha->hw->chip_reset;
+ login_gen = fcport->login_gen;
+
/* ref: INIT */
sp = qla2xxx_get_qpair_sp(vha, arg->qpair, fcport, GFP_KERNEL);
if (!sp)
@@ -2084,7 +2098,7 @@ qla26xx_marker(struct tmf_arg *arg)
tm_iocb->u.tmf.loop_id = fcport->loop_id;
tm_iocb->u.tmf.vp_index = vha->vp_idx;

- START_SP_W_RETRIES(sp, rval);
+ START_SP_W_RETRIES(sp, rval, chip_gen, login_gen);

ql_dbg(ql_dbg_taskm, vha, 0x8006,
"Async-marker hdl=%x loop-id=%x portid=%06x modifier=%x lun=%lld qp=%d rval %d.\n",
@@ -2123,6 +2137,17 @@ static void qla2x00_tmf_sp_done(srb_t *sp, int res)
complete(&tmf->u.tmf.comp);
}

+static int qla_tmf_wait(struct tmf_arg *arg)
+{
+ /* there are only 2 types of error handling that reaches here, lun or target reset */
+ if (arg->flags & (TCF_LUN_RESET | TCF_ABORT_TASK_SET | TCF_CLEAR_TASK_SET))
+ return qla2x00_eh_wait_for_pending_commands(arg->vha,
+ arg->fcport->d_id.b24, arg->lun, WAIT_LUN);
+ else
+ return qla2x00_eh_wait_for_pending_commands(arg->vha,
+ arg->fcport->d_id.b24, arg->lun, WAIT_TARGET);
+}
+
static int
__qla2x00_async_tm_cmd(struct tmf_arg *arg)
{
@@ -2130,8 +2155,9 @@ __qla2x00_async_tm_cmd(struct tmf_arg *arg)
struct srb_iocb *tm_iocb;
srb_t *sp;
int rval = QLA_FUNCTION_FAILED;
-
fc_port_t *fcport = arg->fcport;
+ u32 chip_gen, login_gen;
+ u64 jif;

if (TMF_NOT_READY(arg->fcport)) {
ql_dbg(ql_dbg_taskm, vha, 0x8032,
@@ -2141,6 +2167,9 @@ __qla2x00_async_tm_cmd(struct tmf_arg *arg)
return QLA_SUSPENDED;
}

+ chip_gen = vha->hw->chip_reset;
+ login_gen = fcport->login_gen;
+
/* ref: INIT */
sp = qla2xxx_get_qpair_sp(vha, arg->qpair, fcport, GFP_KERNEL);
if (!sp)
@@ -2158,7 +2187,7 @@ __qla2x00_async_tm_cmd(struct tmf_arg *arg)
tm_iocb->u.tmf.flags = arg->flags;
tm_iocb->u.tmf.lun = arg->lun;

- START_SP_W_RETRIES(sp, rval);
+ START_SP_W_RETRIES(sp, rval, chip_gen, login_gen);

ql_dbg(ql_dbg_taskm, vha, 0x802f,
"Async-tmf hdl=%x loop-id=%x portid=%06x ctrl=%x lun=%lld qp=%d rval=%x.\n",
@@ -2176,8 +2205,26 @@ __qla2x00_async_tm_cmd(struct tmf_arg *arg)
"TM IOCB failed (%x).\n", rval);
}

- if (!test_bit(UNLOADING, &vha->dpc_flags) && !IS_QLAFX00(vha->hw))
- rval = qla26xx_marker(arg);
+ if (!test_bit(UNLOADING, &vha->dpc_flags) && !IS_QLAFX00(vha->hw)) {
+ jif = jiffies;
+ if (qla_tmf_wait(arg)) {
+ ql_log(ql_log_info, vha, 0x803e,
+ "Waited %u ms Nexus=%ld:%06x:%llu.\n",
+ jiffies_to_msecs(jiffies - jif), vha->host_no,
+ fcport->d_id.b24, arg->lun);
+ }
+
+ if (chip_gen == vha->hw->chip_reset && login_gen == fcport->login_gen) {
+ rval = qla26xx_marker(arg);
+ } else {
+ ql_log(ql_log_info, vha, 0x803e,
+ "Skip Marker due to disruption. Nexus=%ld:%06x:%llu.\n",
+ vha->host_no, fcport->d_id.b24, arg->lun);
+ rval = QLA_FUNCTION_FAILED;
+ }
+ }
+ if (tm_iocb->u.tmf.data)
+ rval = tm_iocb->u.tmf.data;

done_free_sp:
/* ref: INIT */
@@ -2186,30 +2233,42 @@ __qla2x00_async_tm_cmd(struct tmf_arg *arg)
return rval;
}

-static void qla_put_tmf(fc_port_t *fcport)
+static void qla_put_tmf(struct tmf_arg *arg)
{
- struct scsi_qla_host *vha = fcport->vha;
+ struct scsi_qla_host *vha = arg->vha;
struct qla_hw_data *ha = vha->hw;
unsigned long flags;

spin_lock_irqsave(&ha->tgt.sess_lock, flags);
- fcport->active_tmf--;
+ ha->active_tmf--;
+ list_del(&arg->tmf_elem);
spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
}

static
-int qla_get_tmf(fc_port_t *fcport)
+int qla_get_tmf(struct tmf_arg *arg)
{
- struct scsi_qla_host *vha = fcport->vha;
+ struct scsi_qla_host *vha = arg->vha;
struct qla_hw_data *ha = vha->hw;
unsigned long flags;
+ fc_port_t *fcport = arg->fcport;
int rc = 0;
- LIST_HEAD(tmf_elem);
+ struct tmf_arg *t;

spin_lock_irqsave(&ha->tgt.sess_lock, flags);
- list_add_tail(&tmf_elem, &fcport->tmf_pending);
+ list_for_each_entry(t, &ha->tmf_active, tmf_elem) {
+ if (t->fcport == arg->fcport && t->lun == arg->lun) {
+ /* reject duplicate TMF */
+ ql_log(ql_log_warn, vha, 0x802c,
+ "found duplicate TMF. Nexus=%ld:%06x:%llu.\n",
+ vha->host_no, fcport->d_id.b24, arg->lun);
+ spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
+ return -EINVAL;
+ }
+ }

- while (fcport->active_tmf >= MAX_ACTIVE_TMF) {
+ list_add_tail(&arg->tmf_elem, &ha->tmf_pending);
+ while (ha->active_tmf >= MAX_ACTIVE_TMF) {
spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);

msleep(1);
@@ -2221,15 +2280,17 @@ int qla_get_tmf(fc_port_t *fcport)
rc = EIO;
break;
}
- if (fcport->active_tmf < MAX_ACTIVE_TMF &&
- list_is_first(&tmf_elem, &fcport->tmf_pending))
+ if (ha->active_tmf < MAX_ACTIVE_TMF &&
+ list_is_first(&arg->tmf_elem, &ha->tmf_pending))
break;
}

- list_del(&tmf_elem);
+ list_del(&arg->tmf_elem);

- if (!rc)
- fcport->active_tmf++;
+ if (!rc) {
+ ha->active_tmf++;
+ list_add_tail(&arg->tmf_elem, &ha->tmf_active);
+ }

spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);

@@ -2241,9 +2302,8 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint64_t lun,
uint32_t tag)
{
struct scsi_qla_host *vha = fcport->vha;
- struct qla_qpair *qpair;
struct tmf_arg a;
- int i, rval = QLA_SUCCESS;
+ int rval = QLA_SUCCESS;

if (TMF_NOT_READY(fcport))
return QLA_SUSPENDED;
@@ -2251,47 +2311,22 @@ qla2x00_async_tm_cmd(fc_port_t *fcport, uint32_t flags, uint64_t lun,
a.vha = fcport->vha;
a.fcport = fcport;
a.lun = lun;
+ a.flags = flags;
+ INIT_LIST_HEAD(&a.tmf_elem);
+
if (flags & (TCF_LUN_RESET|TCF_ABORT_TASK_SET|TCF_CLEAR_TASK_SET|TCF_CLEAR_ACA)) {
a.modifier = MK_SYNC_ID_LUN;
-
- if (qla_get_tmf(fcport))
- return QLA_FUNCTION_FAILED;
} else {
a.modifier = MK_SYNC_ID;
}

- if (vha->hw->mqenable) {
- for (i = 0; i < vha->hw->num_qpairs; i++) {
- qpair = vha->hw->queue_pair_map[i];
- if (!qpair)
- continue;
-
- if (TMF_NOT_READY(fcport)) {
- ql_log(ql_log_warn, vha, 0x8026,
- "Unable to send TM due to disruption.\n");
- rval = QLA_SUSPENDED;
- break;
- }
-
- a.qpair = qpair;
- a.flags = flags|TCF_NOTMCMD_TO_TARGET;
- rval = __qla2x00_async_tm_cmd(&a);
- if (rval)
- break;
- }
- }
-
- if (rval)
- goto bailout;
+ if (qla_get_tmf(&a))
+ return QLA_FUNCTION_FAILED;

a.qpair = vha->hw->base_qpair;
- a.flags = flags;
rval = __qla2x00_async_tm_cmd(&a);

-bailout:
- if (a.modifier == MK_SYNC_ID_LUN)
- qla_put_tmf(fcport);
-
+ qla_put_tmf(&a);
return rval;
}

@@ -4147,39 +4182,61 @@ qla24xx_detect_sfp(scsi_qla_host_t *vha)
return ha->flags.lr_detected;
}

-void qla_init_iocb_limit(scsi_qla_host_t *vha)
+static void __qla_adjust_iocb_limit(struct qla_qpair *qpair)
{
- u16 i, num_qps;
- u32 limit;
- struct qla_hw_data *ha = vha->hw;
+ u8 num_qps;
+ u16 limit;
+ struct qla_hw_data *ha = qpair->vha->hw;

num_qps = ha->num_qpairs + 1;
limit = (ha->orig_fw_iocb_count * QLA_IOCB_PCT_LIMIT) / 100;

- ha->base_qpair->fwres.iocbs_total = ha->orig_fw_iocb_count;
- ha->base_qpair->fwres.iocbs_limit = limit;
- ha->base_qpair->fwres.iocbs_qp_limit = limit / num_qps;
- ha->base_qpair->fwres.iocbs_used = 0;
+ qpair->fwres.iocbs_total = ha->orig_fw_iocb_count;
+ qpair->fwres.iocbs_limit = limit;
+ qpair->fwres.iocbs_qp_limit = limit / num_qps;
+
+ qpair->fwres.exch_total = ha->orig_fw_xcb_count;
+ qpair->fwres.exch_limit = (ha->orig_fw_xcb_count *
+ QLA_IOCB_PCT_LIMIT) / 100;
+}
+
+void qla_init_iocb_limit(scsi_qla_host_t *vha)
+{
+ u8 i;
+ struct qla_hw_data *ha = vha->hw;

- ha->base_qpair->fwres.exch_total = ha->orig_fw_xcb_count;
- ha->base_qpair->fwres.exch_limit = (ha->orig_fw_xcb_count *
- QLA_IOCB_PCT_LIMIT) / 100;
+ __qla_adjust_iocb_limit(ha->base_qpair);
+ ha->base_qpair->fwres.iocbs_used = 0;
ha->base_qpair->fwres.exch_used = 0;

for (i = 0; i < ha->max_qpairs; i++) {
if (ha->queue_pair_map[i]) {
- ha->queue_pair_map[i]->fwres.iocbs_total =
- ha->orig_fw_iocb_count;
- ha->queue_pair_map[i]->fwres.iocbs_limit = limit;
- ha->queue_pair_map[i]->fwres.iocbs_qp_limit =
- limit / num_qps;
+ __qla_adjust_iocb_limit(ha->queue_pair_map[i]);
ha->queue_pair_map[i]->fwres.iocbs_used = 0;
- ha->queue_pair_map[i]->fwres.exch_total = ha->orig_fw_xcb_count;
- ha->queue_pair_map[i]->fwres.exch_limit =
- (ha->orig_fw_xcb_count * QLA_IOCB_PCT_LIMIT) / 100;
ha->queue_pair_map[i]->fwres.exch_used = 0;
}
}
+
+ ha->fwres.iocb_total = ha->orig_fw_iocb_count;
+ ha->fwres.iocb_limit = (ha->orig_fw_iocb_count * QLA_IOCB_PCT_LIMIT) / 100;
+ ha->fwres.exch_total = ha->orig_fw_xcb_count;
+ ha->fwres.exch_limit = (ha->orig_fw_xcb_count * QLA_IOCB_PCT_LIMIT) / 100;
+
+ atomic_set(&ha->fwres.iocb_used, 0);
+ atomic_set(&ha->fwres.exch_used, 0);
+}
+
+void qla_adjust_iocb_limit(scsi_qla_host_t *vha)
+{
+ u8 i;
+ struct qla_hw_data *ha = vha->hw;
+
+ __qla_adjust_iocb_limit(ha->base_qpair);
+
+ for (i = 0; i < ha->max_qpairs; i++) {
+ if (ha->queue_pair_map[i])
+ __qla_adjust_iocb_limit(ha->queue_pair_map[i]);
+ }
}

/**
@@ -4777,15 +4834,16 @@ qla2x00_init_rings(scsi_qla_host_t *vha)
if (ha->flags.edif_enabled)
mid_init_cb->init_cb.frame_payload_size = cpu_to_le16(ELS_MAX_PAYLOAD);

+ QLA_FW_STARTED(ha);
rval = qla2x00_init_firmware(vha, ha->init_cb_size);
next_check:
if (rval) {
+ QLA_FW_STOPPED(ha);
ql_log(ql_log_fatal, vha, 0x00d2,
"Init Firmware **** FAILED ****.\n");
} else {
ql_dbg(ql_dbg_init, vha, 0x00d3,
"Init Firmware -- success.\n");
- QLA_FW_STARTED(ha);
vha->u_ql2xexchoffld = vha->u_ql2xiniexchg = 0;
}

@@ -5506,7 +5564,6 @@ qla2x00_alloc_fcport(scsi_qla_host_t *vha, gfp_t flags)
INIT_WORK(&fcport->reg_work, qla_register_fcport_fn);
INIT_LIST_HEAD(&fcport->gnl_entry);
INIT_LIST_HEAD(&fcport->list);
- INIT_LIST_HEAD(&fcport->tmf_pending);

INIT_LIST_HEAD(&fcport->sess_cmd_list);
spin_lock_init(&fcport->sess_cmd_lock);
@@ -6090,6 +6147,8 @@ qla2x00_reg_remote_port(scsi_qla_host_t *vha, fc_port_t *fcport)
void
qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport)
{
+ unsigned long flags;
+
if (IS_SW_RESV_ADDR(fcport->d_id))
return;

@@ -6099,7 +6158,11 @@ qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport)
qla2x00_set_fcport_disc_state(fcport, DSC_UPD_FCPORT);
fcport->login_retry = vha->hw->login_retry_count;
fcport->flags &= ~(FCF_LOGIN_NEEDED | FCF_ASYNC_SENT);
+
+ spin_lock_irqsave(&vha->work_lock, flags);
fcport->deleted = 0;
+ spin_unlock_irqrestore(&vha->work_lock, flags);
+
if (vha->hw->current_topology == ISP_CFG_NL)
fcport->logout_on_delete = 0;
else
@@ -7337,14 +7400,15 @@ qla2x00_abort_isp_cleanup(scsi_qla_host_t *vha)
}

/* purge MBox commands */
- if (atomic_read(&ha->num_pend_mbx_stage3)) {
+ spin_lock_irqsave(&ha->hardware_lock, flags);
+ if (test_bit(MBX_INTR_WAIT, &ha->mbx_cmd_flags)) {
clear_bit(MBX_INTR_WAIT, &ha->mbx_cmd_flags);
complete(&ha->mbx_intr_comp);
}
+ spin_unlock_irqrestore(&ha->hardware_lock, flags);

i = 0;
- while (atomic_read(&ha->num_pend_mbx_stage3) ||
- atomic_read(&ha->num_pend_mbx_stage2) ||
+ while (atomic_read(&ha->num_pend_mbx_stage2) ||
atomic_read(&ha->num_pend_mbx_stage1)) {
msleep(20);
i++;
diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h
index 0167e85ba058..0556969f6dc1 100644
--- a/drivers/scsi/qla2xxx/qla_inline.h
+++ b/drivers/scsi/qla2xxx/qla_inline.h
@@ -386,6 +386,7 @@ enum {
RESOURCE_IOCB = BIT_0,
RESOURCE_EXCH = BIT_1, /* exchange */
RESOURCE_FORCE = BIT_2,
+ RESOURCE_HA = BIT_3,
};

static inline int
@@ -393,7 +394,7 @@ qla_get_fw_resources(struct qla_qpair *qp, struct iocb_resource *iores)
{
u16 iocbs_used, i;
u16 exch_used;
- struct qla_hw_data *ha = qp->vha->hw;
+ struct qla_hw_data *ha = qp->hw;

if (!ql2xenforce_iocb_limit) {
iores->res_type = RESOURCE_NONE;
@@ -428,15 +429,69 @@ qla_get_fw_resources(struct qla_qpair *qp, struct iocb_resource *iores)
return -ENOSPC;
}
}
+
+ if (ql2xenforce_iocb_limit == 2) {
+ if ((iores->iocb_cnt + atomic_read(&ha->fwres.iocb_used)) >=
+ ha->fwres.iocb_limit) {
+ iores->res_type = RESOURCE_NONE;
+ return -ENOSPC;
+ }
+
+ if (iores->res_type & RESOURCE_EXCH) {
+ if ((iores->exch_cnt + atomic_read(&ha->fwres.exch_used)) >=
+ ha->fwres.exch_limit) {
+ iores->res_type = RESOURCE_NONE;
+ return -ENOSPC;
+ }
+ }
+ }
+
force:
qp->fwres.iocbs_used += iores->iocb_cnt;
qp->fwres.exch_used += iores->exch_cnt;
+ if (ql2xenforce_iocb_limit == 2) {
+ atomic_add(iores->iocb_cnt, &ha->fwres.iocb_used);
+ atomic_add(iores->exch_cnt, &ha->fwres.exch_used);
+ iores->res_type |= RESOURCE_HA;
+ }
return 0;
}

+/*
+ * decrement to zero. This routine will not decrement below zero
+ * @v: pointer of type atomic_t
+ * @amount: amount to decrement from v
+ */
+static void qla_atomic_dtz(atomic_t *v, int amount)
+{
+ int c, old, dec;
+
+ c = atomic_read(v);
+ for (;;) {
+ dec = c - amount;
+ if (unlikely(dec < 0))
+ dec = 0;
+
+ old = atomic_cmpxchg((v), c, dec);
+ if (likely(old == c))
+ break;
+ c = old;
+ }
+}
+
static inline void
qla_put_fw_resources(struct qla_qpair *qp, struct iocb_resource *iores)
{
+ struct qla_hw_data *ha = qp->hw;
+
+ if (iores->res_type & RESOURCE_HA) {
+ if (iores->res_type & RESOURCE_IOCB)
+ qla_atomic_dtz(&ha->fwres.iocb_used, iores->iocb_cnt);
+
+ if (iores->res_type & RESOURCE_EXCH)
+ qla_atomic_dtz(&ha->fwres.exch_used, iores->exch_cnt);
+ }
+
if (iores->res_type & RESOURCE_IOCB) {
if (qp->fwres.iocbs_used >= iores->iocb_cnt) {
qp->fwres.iocbs_used -= iores->iocb_cnt;
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index 730d8609276c..1ee9b7d5fc15 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -3882,6 +3882,7 @@ qla_marker_iocb(srb_t *sp, struct mrk_entry_24xx *mrk)
{
mrk->entry_type = MARKER_TYPE;
mrk->modifier = sp->u.iocb_cmd.u.tmf.modifier;
+ mrk->handle = make_handle(sp->qpair->req->id, sp->handle);
if (sp->u.iocb_cmd.u.tmf.modifier != MK_SYNC_ALL) {
mrk->nport_handle = cpu_to_le16(sp->u.iocb_cmd.u.tmf.loop_id);
int_to_scsilun(sp->u.iocb_cmd.u.tmf.lun, (struct scsi_lun *)&mrk->lun);
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 656700f79325..1f42a413b598 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -1121,8 +1121,12 @@ qla2x00_async_event(scsi_qla_host_t *vha, struct rsp_que *rsp, uint16_t *mb)
unsigned long flags;
fc_port_t *fcport = NULL;

- if (!vha->hw->flags.fw_started)
+ if (!vha->hw->flags.fw_started) {
+ ql_log(ql_log_warn, vha, 0x50ff,
+ "Dropping AEN - %04x %04x %04x %04x.\n",
+ mb[0], mb[1], mb[2], mb[3]);
return;
+ }

/* Setup to process RIO completion. */
handle_cnt = 0;
@@ -2539,7 +2543,6 @@ qla24xx_tm_iocb_entry(scsi_qla_host_t *vha, struct req_que *req, void *tsk)
case CS_PORT_BUSY:
case CS_INCOMPLETE:
case CS_PORT_UNAVAILABLE:
- case CS_TIMEOUT:
case CS_RESET:
if (atomic_read(&fcport->state) == FCS_ONLINE) {
ql_dbg(ql_dbg_disc, fcport->vha, 0x3021,
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 254fd4c64262..21ec32b4fb28 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -273,7 +273,6 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
spin_unlock_irqrestore(&ha->hardware_lock, flags);

wait_time = jiffies;
- atomic_inc(&ha->num_pend_mbx_stage3);
if (!wait_for_completion_timeout(&ha->mbx_intr_comp,
mcp->tov * HZ)) {
ql_dbg(ql_dbg_mbx, vha, 0x117a,
@@ -290,7 +289,6 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
spin_unlock_irqrestore(&ha->hardware_lock,
flags);
atomic_dec(&ha->num_pend_mbx_stage2);
- atomic_dec(&ha->num_pend_mbx_stage3);
rval = QLA_ABORTED;
goto premature_exit;
}
@@ -302,11 +300,9 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
ha->flags.mbox_busy = 0;
spin_unlock_irqrestore(&ha->hardware_lock, flags);
atomic_dec(&ha->num_pend_mbx_stage2);
- atomic_dec(&ha->num_pend_mbx_stage3);
rval = QLA_ABORTED;
goto premature_exit;
}
- atomic_dec(&ha->num_pend_mbx_stage3);

if (time_after(jiffies, wait_time + 5 * HZ))
ql_log(ql_log_warn, vha, 0x1015, "cmd=0x%x, waited %d msecs\n",
@@ -2213,6 +2209,9 @@ qla2x00_get_firmware_state(scsi_qla_host_t *vha, uint16_t *states)
ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x1054,
"Entered %s.\n", __func__);

+ if (!ha->flags.fw_started)
+ return QLA_FUNCTION_FAILED;
+
mcp->mb[0] = MBC_GET_FIRMWARE_STATE;
mcp->out_mb = MBX_0;
if (IS_FWI2_CAPABLE(vha->hw))
diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c
index 86e85f2f4782..9941b38eac93 100644
--- a/drivers/scsi/qla2xxx/qla_nvme.c
+++ b/drivers/scsi/qla2xxx/qla_nvme.c
@@ -132,6 +132,7 @@ static int qla_nvme_alloc_queue(struct nvme_fc_local_port *lport,
"Failed to allocate qpair\n");
return -EINVAL;
}
+ qla_adjust_iocb_limit(vha);
}
*handle = qpair;

@@ -667,7 +668,7 @@ static int qla_nvme_post_cmd(struct nvme_fc_local_port *lport,

rval = qla2x00_start_nvme_mq(sp);
if (rval != QLA_SUCCESS) {
- ql_log(ql_log_warn, vha, 0x212d,
+ ql_dbg(ql_dbg_io + ql_dbg_verbose, vha, 0x212d,
"qla2x00_start_nvme_mq failed = %d\n", rval);
sp->priv = NULL;
priv->sp = NULL;
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 877e4f446709..67176be79dff 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -44,10 +44,11 @@ module_param(ql2xfulldump_on_mpifail, int, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(ql2xfulldump_on_mpifail,
"Set this to take full dump on MPI hang.");

-int ql2xenforce_iocb_limit = 1;
+int ql2xenforce_iocb_limit = 2;
module_param(ql2xenforce_iocb_limit, int, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(ql2xenforce_iocb_limit,
- "Enforce IOCB throttling, to avoid FW congestion. (default: 1)");
+ "Enforce IOCB throttling, to avoid FW congestion. (default: 2) "
+ "1: track usage per queue, 2: track usage per adapter");

/*
* CT6 CTX allocation cache
@@ -1488,8 +1489,9 @@ qla2xxx_eh_device_reset(struct scsi_cmnd *cmd)
goto eh_reset_failed;
}
err = 3;
- if (qla2x00_eh_wait_for_pending_commands(vha, sdev->id,
- sdev->lun, WAIT_LUN) != QLA_SUCCESS) {
+ if (qla2x00_eh_wait_for_pending_commands(vha, fcport->d_id.b24,
+ cmd->device->lun,
+ WAIT_LUN) != QLA_SUCCESS) {
ql_log(ql_log_warn, vha, 0x800d,
"wait for pending cmds failed for cmd=%p.\n", cmd);
goto eh_reset_failed;
@@ -1555,8 +1557,8 @@ qla2xxx_eh_target_reset(struct scsi_cmnd *cmd)
goto eh_reset_failed;
}
err = 3;
- if (qla2x00_eh_wait_for_pending_commands(vha, sdev->id,
- 0, WAIT_TARGET) != QLA_SUCCESS) {
+ if (qla2x00_eh_wait_for_pending_commands(vha, fcport->d_id.b24, 0,
+ WAIT_TARGET) != QLA_SUCCESS) {
ql_log(ql_log_warn, vha, 0x800d,
"wait for pending cmds failed for cmd=%p.\n", cmd);
goto eh_reset_failed;
@@ -3006,9 +3008,10 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
ha->max_exchg = FW_MAX_EXCHANGES_CNT;
atomic_set(&ha->num_pend_mbx_stage1, 0);
atomic_set(&ha->num_pend_mbx_stage2, 0);
- atomic_set(&ha->num_pend_mbx_stage3, 0);
atomic_set(&ha->zio_threshold, DEFAULT_ZIO_THRESHOLD);
ha->last_zio_threshold = DEFAULT_ZIO_THRESHOLD;
+ INIT_LIST_HEAD(&ha->tmf_pending);
+ INIT_LIST_HEAD(&ha->tmf_active);

/* Assign ISP specific operations. */
if (IS_QLA2100(ha)) {
@@ -3285,6 +3288,13 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
host->max_id = ha->max_fibre_devices;
host->cmd_per_lun = 3;
host->unique_id = host->host_no;
+
+ if (ql2xenabledif && ql2xenabledif != 2) {
+ ql_log(ql_log_warn, base_vha, 0x302d,
+ "Invalid value for ql2xenabledif, resetting it to default (2)\n");
+ ql2xenabledif = 2;
+ }
+
if (IS_T10_PI_CAPABLE(ha) && ql2xenabledif)
host->max_cmd_len = 32;
else
@@ -3521,8 +3531,6 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
base_vha->flags.difdix_supported = 1;
ql_dbg(ql_dbg_init, base_vha, 0x00f1,
"Registering for DIF/DIX type 1 and 3 protection.\n");
- if (ql2xenabledif == 1)
- prot = SHOST_DIX_TYPE0_PROTECTION;
if (ql2xprotmask)
scsi_host_set_prot(host, ql2xprotmask);
else
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 5258b07687a9..2b815a9928ea 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -1068,10 +1068,6 @@ void qlt_free_session_done(struct work_struct *work)
(struct imm_ntfy_from_isp *)sess->iocb, SRB_NACK_LOGO);
}

- spin_lock_irqsave(&vha->work_lock, flags);
- sess->flags &= ~FCF_ASYNC_SENT;
- spin_unlock_irqrestore(&vha->work_lock, flags);
-
spin_lock_irqsave(&ha->tgt.sess_lock, flags);
if (sess->se_sess) {
sess->se_sess = NULL;
@@ -1081,7 +1077,6 @@ void qlt_free_session_done(struct work_struct *work)

qla2x00_set_fcport_disc_state(sess, DSC_DELETED);
sess->fw_login_state = DSC_LS_PORT_UNAVAIL;
- sess->deleted = QLA_SESS_DELETED;

if (sess->login_succ && !IS_SW_RESV_ADDR(sess->d_id)) {
vha->fcport_count--;
@@ -1133,10 +1128,15 @@ void qlt_free_session_done(struct work_struct *work)

sess->explicit_logout = 0;
spin_unlock_irqrestore(&ha->tgt.sess_lock, flags);
- sess->free_pending = 0;

qla2x00_dfs_remove_rport(vha, sess);

+ spin_lock_irqsave(&vha->work_lock, flags);
+ sess->flags &= ~FCF_ASYNC_SENT;
+ sess->deleted = QLA_SESS_DELETED;
+ sess->free_pending = 0;
+ spin_unlock_irqrestore(&vha->work_lock, flags);
+
ql_dbg(ql_dbg_disc, vha, 0xf001,
"Unregistration of sess %p %8phC finished fcp_cnt %d\n",
sess, sess->port_name, vha->fcport_count);
@@ -1185,12 +1185,12 @@ void qlt_unreg_sess(struct fc_port *sess)
* management from being sent.
*/
sess->flags |= FCF_ASYNC_SENT;
+ sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
spin_unlock_irqrestore(&sess->vha->work_lock, flags);

if (sess->se_sess)
vha->hw->tgt.tgt_ops->clear_nacl_from_fcport_map(sess);

- sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
qla2x00_set_fcport_disc_state(sess, DSC_DELETE_PEND);
sess->last_rscn_gen = sess->rscn_gen;
sess->last_login_gen = sess->login_gen;
diff --git a/drivers/soc/qcom/qmi_encdec.c b/drivers/soc/qcom/qmi_encdec.c
index b7158e3c3a0b..5c7161b18b72 100644
--- a/drivers/soc/qcom/qmi_encdec.c
+++ b/drivers/soc/qcom/qmi_encdec.c
@@ -534,8 +534,8 @@ static int qmi_decode_string_elem(const struct qmi_elem_info *ei_array,
decoded_bytes += rc;
}

- if (string_len > temp_ei->elem_len) {
- pr_err("%s: String len %d > Max Len %d\n",
+ if (string_len >= temp_ei->elem_len) {
+ pr_err("%s: String len %d >= Max Len %d\n",
__func__, string_len, temp_ei->elem_len);
return -ETOOSMALL;
} else if (string_len > tlv_len) {
diff --git a/drivers/ufs/core/ufs_bsg.c b/drivers/ufs/core/ufs_bsg.c
index 0d38e7fa34cc..97f4d86f8d90 100644
--- a/drivers/ufs/core/ufs_bsg.c
+++ b/drivers/ufs/core/ufs_bsg.c
@@ -76,8 +76,7 @@ static int ufs_bsg_exec_advanced_rpmb_req(struct ufs_hba *hba, struct bsg_job *j
int ret;
int data_len;

- if (hba->ufs_version < ufshci_version(4, 0) || !hba->dev_info.b_advanced_rpmb_en ||
- !(hba->capabilities & MASK_EHSLUTRD_SUPPORTED))
+ if (hba->ufs_version < ufshci_version(4, 0) || !hba->dev_info.b_advanced_rpmb_en)
return -EINVAL;

if (rpmb_request->ehs_req.length != 2 || rpmb_request->ehs_req.ehs_type != 1)
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index fa18806e80b6..9615a076735b 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -7296,7 +7296,15 @@ int ufshcd_advanced_rpmb_req_handler(struct ufs_hba *hba, struct utp_upiu_req *r
/* Advanced RPMB starts from UFS 4.0, so its command type is UTP_CMD_TYPE_UFS_STORAGE */
lrbp->command_type = UTP_CMD_TYPE_UFS_STORAGE;

- ufshcd_prepare_req_desc_hdr(lrbp, &upiu_flags, dir, 2);
+ /*
+ * According to UFSHCI 4.0 specification page 24, if EHSLUTRDS is 0, host controller takes
+ * EHS length from CMD UPIU, and SW driver use EHS Length field in CMD UPIU. if it is 1,
+ * HW controller takes EHS length from UTRD.
+ */
+ if (hba->capabilities & MASK_EHSLUTRD_SUPPORTED)
+ ufshcd_prepare_req_desc_hdr(lrbp, &upiu_flags, dir, 2);
+ else
+ ufshcd_prepare_req_desc_hdr(lrbp, &upiu_flags, dir, 0);

/* update the task tag and LUN in the request upiu */
req_upiu->header.dword_0 |= cpu_to_be32(upiu_flags << 16 | UFS_UPIU_RPMB_WLUN << 8 | tag);
diff --git a/drivers/video/backlight/gpio_backlight.c b/drivers/video/backlight/gpio_backlight.c
index 5c5c99f7979e..30ec5b684533 100644
--- a/drivers/video/backlight/gpio_backlight.c
+++ b/drivers/video/backlight/gpio_backlight.c
@@ -87,8 +87,7 @@ static int gpio_backlight_probe(struct platform_device *pdev)
/* Not booted with device tree or no phandle link to the node */
bl->props.power = def_value ? FB_BLANK_UNBLANK
: FB_BLANK_POWERDOWN;
- else if (gpiod_get_direction(gbl->gpiod) == 0 &&
- gpiod_get_value_cansleep(gbl->gpiod) == 0)
+ else if (gpiod_get_value_cansleep(gbl->gpiod) == 0)
bl->props.power = FB_BLANK_POWERDOWN;
else
bl->props.power = FB_BLANK_UNBLANK;
diff --git a/drivers/video/backlight/lp855x_bl.c b/drivers/video/backlight/lp855x_bl.c
index 1c9e921bca14..349ec324bc1e 100644
--- a/drivers/video/backlight/lp855x_bl.c
+++ b/drivers/video/backlight/lp855x_bl.c
@@ -71,6 +71,7 @@ struct lp855x {
struct device *dev;
struct lp855x_platform_data *pdata;
struct pwm_device *pwm;
+ bool needs_pwm_init;
struct regulator *supply; /* regulator for VDD input */
struct regulator *enable; /* regulator for EN/VDDIO input */
};
@@ -220,7 +221,15 @@ static void lp855x_pwm_ctrl(struct lp855x *lp, int br, int max_br)
{
struct pwm_state state;

- pwm_get_state(lp->pwm, &state);
+ if (lp->needs_pwm_init) {
+ pwm_init_state(lp->pwm, &state);
+ /* Legacy platform data compatibility */
+ if (lp->pdata->period_ns > 0)
+ state.period = lp->pdata->period_ns;
+ lp->needs_pwm_init = false;
+ } else {
+ pwm_get_state(lp->pwm, &state);
+ }

state.duty_cycle = div_u64(br * state.period, max_br);
state.enabled = state.duty_cycle;
@@ -387,7 +396,6 @@ static int lp855x_probe(struct i2c_client *cl)
const struct i2c_device_id *id = i2c_client_get_device_id(cl);
const struct acpi_device_id *acpi_id = NULL;
struct device *dev = &cl->dev;
- struct pwm_state pwmstate;
struct lp855x *lp;
int ret;

@@ -470,15 +478,11 @@ static int lp855x_probe(struct i2c_client *cl)
else
return dev_err_probe(dev, ret, "getting PWM\n");

+ lp->needs_pwm_init = false;
lp->mode = REGISTER_BASED;
dev_dbg(dev, "mode: register based\n");
} else {
- pwm_init_state(lp->pwm, &pwmstate);
- /* Legacy platform data compatibility */
- if (lp->pdata->period_ns > 0)
- pwmstate.period = lp->pdata->period_ns;
- pwm_apply_state(lp->pwm, &pwmstate);
-
+ lp->needs_pwm_init = true;
lp->mode = PWM_BASED;
dev_dbg(dev, "mode: PWM based\n");
}
diff --git a/drivers/video/fbdev/ep93xx-fb.c b/drivers/video/fbdev/ep93xx-fb.c
index 22158d9ca8dd..71f355d34a13 100644
--- a/drivers/video/fbdev/ep93xx-fb.c
+++ b/drivers/video/fbdev/ep93xx-fb.c
@@ -474,7 +474,6 @@ static int ep93xxfb_probe(struct platform_device *pdev)
if (!info)
return -ENOMEM;

- info->dev = &pdev->dev;
platform_set_drvdata(pdev, info);
fbi = info->par;
fbi->mach_info = mach_info;
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index ee97d89dfc11..2108283b438c 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -1075,6 +1075,8 @@ config ADVANTECH_WDT
config ADVANTECH_EC_WDT
tristate "Advantech Embedded Controller Watchdog Timer"
depends on X86
+ select ISA_BUS_API
+ select WATCHDOG_CORE
help
This driver supports Advantech products with ITE based Embedded Controller.
It does not support Advantech products with other ECs or without EC.
diff --git a/drivers/watchdog/intel-mid_wdt.c b/drivers/watchdog/intel-mid_wdt.c
index 9b2173f765c8..fb7fae750181 100644
--- a/drivers/watchdog/intel-mid_wdt.c
+++ b/drivers/watchdog/intel-mid_wdt.c
@@ -203,3 +203,4 @@ module_platform_driver(mid_wdt_driver);
MODULE_AUTHOR("David Cohen <david.a.cohen@xxxxxxxxxxxxxxx>");
MODULE_DESCRIPTION("Watchdog Driver for Intel MID platform");
MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:intel_mid_wdt");
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index a9a2c5446c18..4494883a19ab 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2384,11 +2384,10 @@ int btrfs_validate_super(struct btrfs_fs_info *fs_info,
ret = -EINVAL;
}

- if (memcmp(fs_info->fs_devices->fsid, fs_info->super_copy->fsid,
- BTRFS_FSID_SIZE)) {
+ if (memcmp(fs_info->fs_devices->fsid, sb->fsid, BTRFS_FSID_SIZE) != 0) {
btrfs_err(fs_info,
"superblock fsid doesn't match fsid of fs_devices: %pU != %pU",
- fs_info->super_copy->fsid, fs_info->fs_devices->fsid);
+ sb->fsid, fs_info->fs_devices->fsid);
ret = -EINVAL;
}

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index f396a9afa403..e5566827da17 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3709,7 +3709,8 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
fs_info->data_reloc_bg == 0);

if (block_group->ro ||
- test_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags)) {
+ (!ffe_ctl->for_data_reloc &&
+ test_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags))) {
ret = 1;
goto out;
}
@@ -3752,8 +3753,26 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
if (ffe_ctl->for_treelog && !fs_info->treelog_bg)
fs_info->treelog_bg = block_group->start;

- if (ffe_ctl->for_data_reloc && !fs_info->data_reloc_bg)
- fs_info->data_reloc_bg = block_group->start;
+ if (ffe_ctl->for_data_reloc) {
+ if (!fs_info->data_reloc_bg)
+ fs_info->data_reloc_bg = block_group->start;
+ /*
+ * Do not allow allocations from this block group, unless it is
+ * for data relocation. Compared to increasing the ->ro, setting
+ * the ->zoned_data_reloc_ongoing flag still allows nocow
+ * writers to come in. See btrfs_inc_nocow_writers().
+ *
+ * We need to disable an allocation to avoid an allocation of
+ * regular (non-relocation data) extent. With mix of relocation
+ * extents and regular extents, we can dispatch WRITE commands
+ * (for relocation extents) and ZONE APPEND commands (for
+ * regular extents) at the same time to the same zone, which
+ * easily break the write pointer.
+ *
+ * Also, this flag avoids this block group to be zone finished.
+ */
+ set_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags);
+ }

ffe_ctl->found_offset = start + block_group->alloc_offset;
block_group->alloc_offset += num_bytes;
@@ -3771,24 +3790,8 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
out:
if (ret && ffe_ctl->for_treelog)
fs_info->treelog_bg = 0;
- if (ret && ffe_ctl->for_data_reloc &&
- fs_info->data_reloc_bg == block_group->start) {
- /*
- * Do not allow further allocations from this block group.
- * Compared to increasing the ->ro, setting the
- * ->zoned_data_reloc_ongoing flag still allows nocow
- * writers to come in. See btrfs_inc_nocow_writers().
- *
- * We need to disable an allocation to avoid an allocation of
- * regular (non-relocation data) extent. With mix of relocation
- * extents and regular extents, we can dispatch WRITE commands
- * (for relocation extents) and ZONE APPEND commands (for
- * regular extents) at the same time to the same zone, which
- * easily break the write pointer.
- */
- set_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags);
+ if (ret && ffe_ctl->for_data_reloc)
fs_info->data_reloc_bg = 0;
- }
spin_unlock(&fs_info->relocation_bg_lock);
spin_unlock(&fs_info->treelog_bg_lock);
spin_unlock(&block_group->lock);
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 696bf695d8eb..1ce5dd154499 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -597,29 +597,37 @@ int btrfs_lookup_csums_list(struct btrfs_root *root, u64 start, u64 end,
* Each bit represents a sector. Thus caller should ensure @csum_buf passed
* in is large enough to contain all csums.
*/
-int btrfs_lookup_csums_bitmap(struct btrfs_root *root, u64 start, u64 end,
- u8 *csum_buf, unsigned long *csum_bitmap,
- bool search_commit)
+int btrfs_lookup_csums_bitmap(struct btrfs_root *root, struct btrfs_path *path,
+ u64 start, u64 end, u8 *csum_buf,
+ unsigned long *csum_bitmap)
{
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_key key;
- struct btrfs_path *path;
struct extent_buffer *leaf;
struct btrfs_csum_item *item;
const u64 orig_start = start;
+ bool free_path = false;
int ret;

ASSERT(IS_ALIGNED(start, fs_info->sectorsize) &&
IS_ALIGNED(end + 1, fs_info->sectorsize));

- path = btrfs_alloc_path();
- if (!path)
- return -ENOMEM;
+ if (!path) {
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+ free_path = true;
+ }

- if (search_commit) {
- path->skip_locking = 1;
- path->reada = READA_FORWARD;
- path->search_commit_root = 1;
+ /* Check if we can reuse the previous path. */
+ if (path->nodes[0]) {
+ btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+
+ if (key.objectid == BTRFS_EXTENT_CSUM_OBJECTID &&
+ key.type == BTRFS_EXTENT_CSUM_KEY &&
+ key.offset <= start)
+ goto search_forward;
+ btrfs_release_path(path);
}

key.objectid = BTRFS_EXTENT_CSUM_OBJECTID;
@@ -656,6 +664,7 @@ int btrfs_lookup_csums_bitmap(struct btrfs_root *root, u64 start, u64 end,
}
}

+search_forward:
while (start <= end) {
u64 csum_end;

@@ -712,7 +721,8 @@ int btrfs_lookup_csums_bitmap(struct btrfs_root *root, u64 start, u64 end,
}
ret = 0;
fail:
- btrfs_free_path(path);
+ if (free_path)
+ btrfs_free_path(path);
return ret;
}

diff --git a/fs/btrfs/file-item.h b/fs/btrfs/file-item.h
index 4ec669b69008..04bd2d34efb1 100644
--- a/fs/btrfs/file-item.h
+++ b/fs/btrfs/file-item.h
@@ -57,9 +57,9 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
int btrfs_lookup_csums_list(struct btrfs_root *root, u64 start, u64 end,
struct list_head *list, int search_commit,
bool nowait);
-int btrfs_lookup_csums_bitmap(struct btrfs_root *root, u64 start, u64 end,
- u8 *csum_buf, unsigned long *csum_bitmap,
- bool search_commit);
+int btrfs_lookup_csums_bitmap(struct btrfs_root *root, struct btrfs_path *path,
+ u64 start, u64 end, u8 *csum_buf,
+ unsigned long *csum_bitmap);
void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
const struct btrfs_path *path,
struct btrfs_file_extent_item *fi,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index aa090b0b5d29..db2b33a822fc 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3359,6 +3359,13 @@ int btrfs_finish_one_ordered(struct btrfs_ordered_extent *ordered_extent)
btrfs_free_reserved_extent(fs_info,
ordered_extent->disk_bytenr,
ordered_extent->disk_num_bytes, 1);
+ /*
+ * Actually free the qgroup rsv which was released when
+ * the ordered extent was created.
+ */
+ btrfs_qgroup_free_refroot(fs_info, inode->root->root_key.objectid,
+ ordered_extent->qgroup_rsv,
+ BTRFS_QGROUP_RSV_DATA);
}
}

diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 0249ea52bb80..3e388e0431e3 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -2112,8 +2112,8 @@ static void fill_data_csums(struct btrfs_raid_bio *rbio)
goto error;
}

- ret = btrfs_lookup_csums_bitmap(csum_root, start, start + len - 1,
- rbio->csum_buf, rbio->csum_bitmap, false);
+ ret = btrfs_lookup_csums_bitmap(csum_root, NULL, start, start + len - 1,
+ rbio->csum_buf, rbio->csum_bitmap);
if (ret < 0)
goto error;
if (bitmap_empty(rbio->csum_bitmap, len >> fs_info->sectorsize_bits))
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 46c3c1d57266..5f4ff7d5b5c1 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -3006,9 +3006,6 @@ static int relocate_one_page(struct inode *inode, struct file_ra_state *ra,
if (!page)
return -ENOMEM;
}
- ret = set_page_extent_mapped(page);
- if (ret < 0)
- goto release_page;

if (PageReadahead(page))
page_cache_async_readahead(inode->i_mapping, ra, NULL,
@@ -3024,6 +3021,15 @@ static int relocate_one_page(struct inode *inode, struct file_ra_state *ra,
}
}

+ /*
+ * We could have lost page private when we dropped the lock to read the
+ * page above, make sure we set_page_extent_mapped here so we have any
+ * of the subpage blocksize stuff we need in place.
+ */
+ ret = set_page_extent_mapped(page);
+ if (ret < 0)
+ goto release_page;
+
page_start = page_offset(page);
page_end = page_start + PAGE_SIZE - 1;

diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 7289f5bff397..cfbd6b1c4b7f 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -43,9 +43,20 @@ struct scrub_ctx;
/*
* The following value only influences the performance.
*
- * This determines the batch size for stripe submitted in one go.
+ * This detemines how many stripes would be submitted in one go,
+ * which is 512KiB (BTRFS_STRIPE_LEN * SCRUB_STRIPES_PER_GROUP).
*/
-#define SCRUB_STRIPES_PER_SCTX 8 /* That would be 8 64K stripe per-device. */
+#define SCRUB_STRIPES_PER_GROUP 8
+
+/*
+ * How many groups we have for each sctx.
+ *
+ * This would be 8M per device, the same value as the old scrub in-flight bios
+ * size limit.
+ */
+#define SCRUB_GROUPS_PER_SCTX 16
+
+#define SCRUB_TOTAL_STRIPES (SCRUB_GROUPS_PER_SCTX * SCRUB_STRIPES_PER_GROUP)

/*
* The following value times PAGE_SIZE needs to be large enough to match the
@@ -172,9 +183,11 @@ struct scrub_stripe {
};

struct scrub_ctx {
- struct scrub_stripe stripes[SCRUB_STRIPES_PER_SCTX];
+ struct scrub_stripe stripes[SCRUB_TOTAL_STRIPES];
struct scrub_stripe *raid56_data_stripes;
struct btrfs_fs_info *fs_info;
+ struct btrfs_path extent_path;
+ struct btrfs_path csum_path;
int first_free;
int cur_stripe;
atomic_t cancel_req;
@@ -315,10 +328,10 @@ static noinline_for_stack void scrub_free_ctx(struct scrub_ctx *sctx)
if (!sctx)
return;

- for (i = 0; i < SCRUB_STRIPES_PER_SCTX; i++)
+ for (i = 0; i < SCRUB_TOTAL_STRIPES; i++)
release_scrub_stripe(&sctx->stripes[i]);

- kfree(sctx);
+ kvfree(sctx);
}

static void scrub_put_ctx(struct scrub_ctx *sctx)
@@ -333,13 +346,20 @@ static noinline_for_stack struct scrub_ctx *scrub_setup_ctx(
struct scrub_ctx *sctx;
int i;

- sctx = kzalloc(sizeof(*sctx), GFP_KERNEL);
+ /* Since sctx has inline 128 stripes, it can go beyond 64K easily. Use
+ * kvzalloc().
+ */
+ sctx = kvzalloc(sizeof(*sctx), GFP_KERNEL);
if (!sctx)
goto nomem;
refcount_set(&sctx->refs, 1);
sctx->is_dev_replace = is_dev_replace;
sctx->fs_info = fs_info;
- for (i = 0; i < SCRUB_STRIPES_PER_SCTX; i++) {
+ sctx->extent_path.search_commit_root = 1;
+ sctx->extent_path.skip_locking = 1;
+ sctx->csum_path.search_commit_root = 1;
+ sctx->csum_path.skip_locking = 1;
+ for (i = 0; i < SCRUB_TOTAL_STRIPES; i++) {
int ret;

ret = init_scrub_stripe(fs_info, &sctx->stripes[i]);
@@ -1468,6 +1488,8 @@ static void scrub_stripe_reset_bitmaps(struct scrub_stripe *stripe)
* Return <0 for error.
*/
static int scrub_find_fill_first_stripe(struct btrfs_block_group *bg,
+ struct btrfs_path *extent_path,
+ struct btrfs_path *csum_path,
struct btrfs_device *dev, u64 physical,
int mirror_num, u64 logical_start,
u32 logical_len,
@@ -1477,7 +1499,6 @@ static int scrub_find_fill_first_stripe(struct btrfs_block_group *bg,
struct btrfs_root *extent_root = btrfs_extent_root(fs_info, bg->start);
struct btrfs_root *csum_root = btrfs_csum_root(fs_info, bg->start);
const u64 logical_end = logical_start + logical_len;
- struct btrfs_path path = { 0 };
u64 cur_logical = logical_start;
u64 stripe_end;
u64 extent_start;
@@ -1493,14 +1514,13 @@ static int scrub_find_fill_first_stripe(struct btrfs_block_group *bg,
/* The range must be inside the bg. */
ASSERT(logical_start >= bg->start && logical_end <= bg->start + bg->length);

- path.search_commit_root = 1;
- path.skip_locking = 1;
-
- ret = find_first_extent_item(extent_root, &path, logical_start, logical_len);
+ ret = find_first_extent_item(extent_root, extent_path, logical_start,
+ logical_len);
/* Either error or not found. */
if (ret)
goto out;
- get_extent_info(&path, &extent_start, &extent_len, &extent_flags, &extent_gen);
+ get_extent_info(extent_path, &extent_start, &extent_len, &extent_flags,
+ &extent_gen);
if (extent_flags & BTRFS_EXTENT_FLAG_TREE_BLOCK)
stripe->nr_meta_extents++;
if (extent_flags & BTRFS_EXTENT_FLAG_DATA)
@@ -1528,7 +1548,7 @@ static int scrub_find_fill_first_stripe(struct btrfs_block_group *bg,

/* Fill the extent info for the remaining sectors. */
while (cur_logical <= stripe_end) {
- ret = find_first_extent_item(extent_root, &path, cur_logical,
+ ret = find_first_extent_item(extent_root, extent_path, cur_logical,
stripe_end - cur_logical + 1);
if (ret < 0)
goto out;
@@ -1536,7 +1556,7 @@ static int scrub_find_fill_first_stripe(struct btrfs_block_group *bg,
ret = 0;
break;
}
- get_extent_info(&path, &extent_start, &extent_len,
+ get_extent_info(extent_path, &extent_start, &extent_len,
&extent_flags, &extent_gen);
if (extent_flags & BTRFS_EXTENT_FLAG_TREE_BLOCK)
stripe->nr_meta_extents++;
@@ -1561,9 +1581,9 @@ static int scrub_find_fill_first_stripe(struct btrfs_block_group *bg,
*/
ASSERT(BITS_PER_LONG >= BTRFS_STRIPE_LEN >> fs_info->sectorsize_bits);

- ret = btrfs_lookup_csums_bitmap(csum_root, stripe->logical,
- stripe_end, stripe->csums,
- &csum_bitmap, true);
+ ret = btrfs_lookup_csums_bitmap(csum_root, csum_path,
+ stripe->logical, stripe_end,
+ stripe->csums, &csum_bitmap);
if (ret < 0)
goto out;
if (ret > 0)
@@ -1576,7 +1596,6 @@ static int scrub_find_fill_first_stripe(struct btrfs_block_group *bg,
}
set_bit(SCRUB_STRIPE_FLAG_INITIALIZED, &stripe->state);
out:
- btrfs_release_path(&path);
return ret;
}

@@ -1654,6 +1673,28 @@ static bool stripe_has_metadata_error(struct scrub_stripe *stripe)
return false;
}

+static void submit_initial_group_read(struct scrub_ctx *sctx,
+ unsigned int first_slot,
+ unsigned int nr_stripes)
+{
+ struct blk_plug plug;
+
+ ASSERT(first_slot < SCRUB_TOTAL_STRIPES);
+ ASSERT(first_slot + nr_stripes <= SCRUB_TOTAL_STRIPES);
+
+ scrub_throttle_dev_io(sctx, sctx->stripes[0].dev,
+ btrfs_stripe_nr_to_offset(nr_stripes));
+ blk_start_plug(&plug);
+ for (int i = 0; i < nr_stripes; i++) {
+ struct scrub_stripe *stripe = &sctx->stripes[first_slot + i];
+
+ /* Those stripes should be initialized. */
+ ASSERT(test_bit(SCRUB_STRIPE_FLAG_INITIALIZED, &stripe->state));
+ scrub_submit_initial_read(sctx, stripe);
+ }
+ blk_finish_plug(&plug);
+}
+
static int flush_scrub_stripes(struct scrub_ctx *sctx)
{
struct btrfs_fs_info *fs_info = sctx->fs_info;
@@ -1666,11 +1707,11 @@ static int flush_scrub_stripes(struct scrub_ctx *sctx)

ASSERT(test_bit(SCRUB_STRIPE_FLAG_INITIALIZED, &sctx->stripes[0].state));

- scrub_throttle_dev_io(sctx, sctx->stripes[0].dev,
- btrfs_stripe_nr_to_offset(nr_stripes));
- for (int i = 0; i < nr_stripes; i++) {
- stripe = &sctx->stripes[i];
- scrub_submit_initial_read(sctx, stripe);
+ /* Submit the stripes which are populated but not submitted. */
+ if (nr_stripes % SCRUB_STRIPES_PER_GROUP) {
+ const int first_slot = round_down(nr_stripes, SCRUB_STRIPES_PER_GROUP);
+
+ submit_initial_group_read(sctx, first_slot, nr_stripes - first_slot);
}

for (int i = 0; i < nr_stripes; i++) {
@@ -1750,28 +1791,40 @@ static void raid56_scrub_wait_endio(struct bio *bio)

static int queue_scrub_stripe(struct scrub_ctx *sctx, struct btrfs_block_group *bg,
struct btrfs_device *dev, int mirror_num,
- u64 logical, u32 length, u64 physical)
+ u64 logical, u32 length, u64 physical,
+ u64 *found_logical_ret)
{
struct scrub_stripe *stripe;
int ret;

- /* No available slot, submit all stripes and wait for them. */
- if (sctx->cur_stripe >= SCRUB_STRIPES_PER_SCTX) {
- ret = flush_scrub_stripes(sctx);
- if (ret < 0)
- return ret;
- }
+ /*
+ * There should always be one slot left, as caller filling the last
+ * slot should flush them all.
+ */
+ ASSERT(sctx->cur_stripe < SCRUB_TOTAL_STRIPES);

stripe = &sctx->stripes[sctx->cur_stripe];
-
- /* We can queue one stripe using the remaining slot. */
scrub_reset_stripe(stripe);
- ret = scrub_find_fill_first_stripe(bg, dev, physical, mirror_num,
- logical, length, stripe);
+ ret = scrub_find_fill_first_stripe(bg, &sctx->extent_path,
+ &sctx->csum_path, dev, physical,
+ mirror_num, logical, length, stripe);
/* Either >0 as no more extents or <0 for error. */
if (ret)
return ret;
+ if (found_logical_ret)
+ *found_logical_ret = stripe->logical;
sctx->cur_stripe++;
+
+ /* We filled one group, submit it. */
+ if (sctx->cur_stripe % SCRUB_STRIPES_PER_GROUP == 0) {
+ const int first_slot = sctx->cur_stripe - SCRUB_STRIPES_PER_GROUP;
+
+ submit_initial_group_read(sctx, first_slot, SCRUB_STRIPES_PER_GROUP);
+ }
+
+ /* Last slot used, flush them all. */
+ if (sctx->cur_stripe == SCRUB_TOTAL_STRIPES)
+ return flush_scrub_stripes(sctx);
return 0;
}

@@ -1785,6 +1838,8 @@ static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx,
struct btrfs_fs_info *fs_info = sctx->fs_info;
struct btrfs_raid_bio *rbio;
struct btrfs_io_context *bioc = NULL;
+ struct btrfs_path extent_path = { 0 };
+ struct btrfs_path csum_path = { 0 };
struct bio *bio;
struct scrub_stripe *stripe;
bool all_empty = true;
@@ -1795,6 +1850,16 @@ static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx,

ASSERT(sctx->raid56_data_stripes);

+ /*
+ * For data stripe search, we cannot re-use the same extent/csum paths,
+ * as the data stripe bytenr may be smaller than previous extent. Thus
+ * we have to use our own extent/csum paths.
+ */
+ extent_path.search_commit_root = 1;
+ extent_path.skip_locking = 1;
+ csum_path.search_commit_root = 1;
+ csum_path.skip_locking = 1;
+
for (int i = 0; i < data_stripes; i++) {
int stripe_index;
int rot;
@@ -1809,7 +1874,7 @@ static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx,

scrub_reset_stripe(stripe);
set_bit(SCRUB_STRIPE_FLAG_NO_REPORT, &stripe->state);
- ret = scrub_find_fill_first_stripe(bg,
+ ret = scrub_find_fill_first_stripe(bg, &extent_path, &csum_path,
map->stripes[stripe_index].dev, physical, 1,
full_stripe_start + btrfs_stripe_nr_to_offset(i),
BTRFS_STRIPE_LEN, stripe);
@@ -1937,6 +2002,8 @@ static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx,
bio_put(bio);
btrfs_bio_counter_dec(fs_info);

+ btrfs_release_path(&extent_path);
+ btrfs_release_path(&csum_path);
out:
return ret;
}
@@ -1970,6 +2037,7 @@ static int scrub_simple_mirror(struct scrub_ctx *sctx,
path.skip_locking = 1;
/* Go through each extent items inside the logical range */
while (cur_logical < logical_end) {
+ u64 found_logical;
u64 cur_physical = physical + cur_logical - logical_start;

/* Canceled? */
@@ -1994,7 +2062,7 @@ static int scrub_simple_mirror(struct scrub_ctx *sctx,

ret = queue_scrub_stripe(sctx, bg, device, mirror_num,
cur_logical, logical_end - cur_logical,
- cur_physical);
+ cur_physical, &found_logical);
if (ret > 0) {
/* No more extent, just update the accounting */
sctx->stat.last_physical = physical + logical_length;
@@ -2004,9 +2072,7 @@ static int scrub_simple_mirror(struct scrub_ctx *sctx,
if (ret < 0)
break;

- ASSERT(sctx->cur_stripe > 0);
- cur_logical = sctx->stripes[sctx->cur_stripe - 1].logical
- + BTRFS_STRIPE_LEN;
+ cur_logical = found_logical + BTRFS_STRIPE_LEN;

/* Don't hold CPU for too long time */
cond_resched();
@@ -2109,6 +2175,9 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
u64 stripe_logical;
int stop_loop = 0;

+ /* Extent_path should be released by now. */
+ ASSERT(sctx->extent_path.nodes[0] == NULL);
+
scrub_blocked_if_needed(fs_info);

if (sctx->is_dev_replace &&
@@ -2227,6 +2296,9 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
ret2 = flush_scrub_stripes(sctx);
if (!ret)
ret = ret2;
+ btrfs_release_path(&sctx->extent_path);
+ btrfs_release_path(&sctx->csum_path);
+
if (sctx->raid56_data_stripes) {
for (int i = 0; i < nr_data_stripes(map); i++)
release_scrub_stripe(&sctx->raid56_data_stripes[i]);
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index 75e7fa337e66..ba5322fe34f5 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -389,11 +389,7 @@ int btrfs_can_overcommit(struct btrfs_fs_info *fs_info,
return 0;

used = btrfs_space_info_used(space_info, true);
- if (test_bit(BTRFS_FS_ACTIVE_ZONE_TRACKING, &fs_info->flags) &&
- (space_info->flags & BTRFS_BLOCK_GROUP_METADATA))
- avail = 0;
- else
- avail = calc_available_free_space(fs_info, space_info, flush);
+ avail = calc_available_free_space(fs_info, space_info, flush);

if (used + bytes < space_info->total_bytes + avail)
return 1;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 91b6c2fdc420..5bbd288b9cb5 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -292,10 +292,11 @@ static noinline int join_transaction(struct btrfs_fs_info *fs_info,
spin_unlock(&fs_info->trans_lock);

/*
- * If we are ATTACH, we just want to catch the current transaction,
- * and commit it. If there is no transaction, just return ENOENT.
+ * If we are ATTACH or TRANS_JOIN_NOSTART, we just want to catch the
+ * current transaction, and commit it. If there is no transaction, just
+ * return ENOENT.
*/
- if (type == TRANS_ATTACH)
+ if (type == TRANS_ATTACH || type == TRANS_JOIN_NOSTART)
return -ENOENT;

/*
@@ -591,8 +592,13 @@ start_transaction(struct btrfs_root *root, unsigned int num_items,
u64 delayed_refs_bytes = 0;

qgroup_reserved = num_items * fs_info->nodesize;
- ret = btrfs_qgroup_reserve_meta_pertrans(root, qgroup_reserved,
- enforce_qgroups);
+ /*
+ * Use prealloc for now, as there might be a currently running
+ * transaction that could free this reserved space prematurely
+ * by committing.
+ */
+ ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserved,
+ enforce_qgroups, false);
if (ret)
return ERR_PTR(ret);

@@ -705,6 +711,14 @@ start_transaction(struct btrfs_root *root, unsigned int num_items,
h->reloc_reserved = reloc_reserved;
}

+ /*
+ * Now that we have found a transaction to be a part of, convert the
+ * qgroup reservation from prealloc to pertrans. A different transaction
+ * can't race in and free our pertrans out from under us.
+ */
+ if (qgroup_reserved)
+ btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved);
+
got_it:
if (!current->journal_info)
current->journal_info = h;
@@ -752,7 +766,7 @@ start_transaction(struct btrfs_root *root, unsigned int num_items,
btrfs_block_rsv_release(fs_info, &fs_info->trans_block_rsv,
num_bytes, NULL);
reserve_fail:
- btrfs_qgroup_free_meta_pertrans(root, qgroup_reserved);
+ btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved);
return ERR_PTR(ret);
}

diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 249030135001..d9e6df2da272 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -2017,6 +2017,10 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ
* and block_group->meta_write_pointer for metadata.
*/
if (!fully_written) {
+ if (test_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags)) {
+ spin_unlock(&block_group->lock);
+ return -EAGAIN;
+ }
spin_unlock(&block_group->lock);

ret = btrfs_inc_block_group_ro(block_group, false);
@@ -2045,7 +2049,9 @@ static int do_zone_finish(struct btrfs_block_group *block_group, bool fully_writ
return 0;
}

- if (block_group->reserved) {
+ if (block_group->reserved ||
+ test_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC,
+ &block_group->runtime_flags)) {
spin_unlock(&block_group->lock);
btrfs_dec_block_group_ro(block_group);
return -EAGAIN;
@@ -2276,7 +2282,10 @@ void btrfs_zoned_release_data_reloc_bg(struct btrfs_fs_info *fs_info, u64 logica

/* All relocation extents are written. */
if (block_group->start + block_group->alloc_offset == logical + length) {
- /* Now, release this block group for further allocations. */
+ /*
+ * Now, release this block group for further allocations and
+ * zone finish.
+ */
clear_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC,
&block_group->runtime_flags);
}
@@ -2300,7 +2309,8 @@ int btrfs_zone_finish_one_bg(struct btrfs_fs_info *fs_info)

spin_lock(&block_group->lock);
if (block_group->reserved || block_group->alloc_offset == 0 ||
- (block_group->flags & BTRFS_BLOCK_GROUP_SYSTEM)) {
+ (block_group->flags & BTRFS_BLOCK_GROUP_SYSTEM) ||
+ test_bit(BLOCK_GROUP_FLAG_ZONED_DATA_RELOC, &block_group->runtime_flags)) {
spin_unlock(&block_group->lock);
continue;
}
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index 1f72f977c6db..79b20d6ae39e 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -913,11 +913,11 @@ unsigned long ext4_bg_num_gdb(struct super_block *sb, ext4_group_t group)
}

/*
- * This function returns the number of file system metadata clusters at
+ * This function returns the number of file system metadata blocks at
* the beginning of a block group, including the reserved gdt blocks.
*/
-static unsigned ext4_num_base_meta_clusters(struct super_block *sb,
- ext4_group_t block_group)
+unsigned int ext4_num_base_meta_blocks(struct super_block *sb,
+ ext4_group_t block_group)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
unsigned num;
@@ -935,8 +935,15 @@ static unsigned ext4_num_base_meta_clusters(struct super_block *sb,
} else { /* For META_BG_BLOCK_GROUPS */
num += ext4_bg_num_gdb_meta(sb, block_group);
}
- return EXT4_NUM_B2C(sbi, num);
+ return num;
}
+
+static unsigned int ext4_num_base_meta_clusters(struct super_block *sb,
+ ext4_group_t block_group)
+{
+ return EXT4_NUM_B2C(EXT4_SB(sb), ext4_num_base_meta_blocks(sb, block_group));
+}
+
/**
* ext4_inode_to_goal_block - return a hint for block allocation
* @inode: inode for block allocation
diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c
index 5504f72bbbbe..6fe3c941b565 100644
--- a/fs/ext4/block_validity.c
+++ b/fs/ext4/block_validity.c
@@ -215,7 +215,6 @@ int ext4_setup_system_zone(struct super_block *sb)
struct ext4_system_blocks *system_blks;
struct ext4_group_desc *gdp;
ext4_group_t i;
- int flex_size = ext4_flex_bg_size(sbi);
int ret;

system_blks = kzalloc(sizeof(*system_blks), GFP_KERNEL);
@@ -223,12 +222,13 @@ int ext4_setup_system_zone(struct super_block *sb)
return -ENOMEM;

for (i=0; i < ngroups; i++) {
+ unsigned int meta_blks = ext4_num_base_meta_blocks(sb, i);
+
cond_resched();
- if (ext4_bg_has_super(sb, i) &&
- ((i < 5) || ((i % flex_size) == 0))) {
+ if (meta_blks != 0) {
ret = add_system_zone(system_blks,
ext4_group_first_block_no(sb, i),
- ext4_bg_num_gdb(sb, i) + 1, 0);
+ meta_blks, 0);
if (ret)
goto err;
}
diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c
index e20ac0654b3f..453d4da5de52 100644
--- a/fs/ext4/crypto.c
+++ b/fs/ext4/crypto.c
@@ -33,6 +33,8 @@ int ext4_fname_setup_filename(struct inode *dir, const struct qstr *iname,

#if IS_ENABLED(CONFIG_UNICODE)
err = ext4_fname_setup_ci_filename(dir, iname, fname);
+ if (err)
+ ext4_fname_free_filename(fname);
#endif
return err;
}
@@ -51,6 +53,8 @@ int ext4_fname_prepare_lookup(struct inode *dir, struct dentry *dentry,

#if IS_ENABLED(CONFIG_UNICODE)
err = ext4_fname_setup_ci_filename(dir, &dentry->d_name, fname);
+ if (err)
+ ext4_fname_free_filename(fname);
#endif
return err;
}
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 0a2d55faa095..9653aab5e9f4 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -3084,6 +3084,8 @@ extern const char *ext4_decode_error(struct super_block *sb, int errno,
extern void ext4_mark_group_bitmap_corrupted(struct super_block *sb,
ext4_group_t block_group,
unsigned int flags);
+extern unsigned int ext4_num_base_meta_blocks(struct super_block *sb,
+ ext4_group_t block_group);

extern __printf(7, 8)
void __ext4_error(struct super_block *, const char *, unsigned int, bool,
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 9b5b8951afb4..6f7de14c0fa8 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -878,23 +878,29 @@ void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
err1 = __es_remove_extent(inode, lblk, end, NULL, es1);
if (err1 != 0)
goto error;
+ /* Free preallocated extent if it didn't get used. */
+ if (es1) {
+ if (!es1->es_len)
+ __es_free_extent(es1);
+ es1 = NULL;
+ }

err2 = __es_insert_extent(inode, &newes, es2);
if (err2 == -ENOMEM && !ext4_es_must_keep(&newes))
err2 = 0;
if (err2 != 0)
goto error;
+ /* Free preallocated extent if it didn't get used. */
+ if (es2) {
+ if (!es2->es_len)
+ __es_free_extent(es2);
+ es2 = NULL;
+ }

if (sbi->s_cluster_ratio > 1 && test_opt(inode->i_sb, DELALLOC) &&
(status & EXTENT_STATUS_WRITTEN ||
status & EXTENT_STATUS_UNWRITTEN))
__revise_pending(inode, lblk, len);
-
- /* es is pre-allocated but not used, free it. */
- if (es1 && !es1->es_len)
- __es_free_extent(es1);
- if (es2 && !es2->es_len)
- __es_free_extent(es2);
error:
write_unlock(&EXT4_I(inode)->i_es_lock);
if (err1 || err2)
@@ -1491,8 +1497,12 @@ void ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
*/
write_lock(&EXT4_I(inode)->i_es_lock);
err = __es_remove_extent(inode, lblk, end, &reserved, es);
- if (es && !es->es_len)
- __es_free_extent(es);
+ /* Free preallocated extent if it didn't get used. */
+ if (es) {
+ if (!es->es_len)
+ __es_free_extent(es);
+ es = NULL;
+ }
write_unlock(&EXT4_I(inode)->i_es_lock);
if (err)
goto retry;
@@ -2047,19 +2057,25 @@ void ext4_es_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk,
err1 = __es_remove_extent(inode, lblk, lblk, NULL, es1);
if (err1 != 0)
goto error;
+ /* Free preallocated extent if it didn't get used. */
+ if (es1) {
+ if (!es1->es_len)
+ __es_free_extent(es1);
+ es1 = NULL;
+ }

err2 = __es_insert_extent(inode, &newes, es2);
if (err2 != 0)
goto error;
+ /* Free preallocated extent if it didn't get used. */
+ if (es2) {
+ if (!es2->es_len)
+ __es_free_extent(es2);
+ es2 = NULL;
+ }

if (allocated)
__insert_pending(inode, lblk);
-
- /* es is pre-allocated but not used, free it. */
- if (es1 && !es1->es_len)
- __es_free_extent(es1);
- if (es2 && !es2->es_len)
- __es_free_extent(es2);
error:
write_unlock(&EXT4_I(inode)->i_es_lock);
if (err1 || err2)
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index c457c8517f0f..73a4b711be02 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -476,6 +476,11 @@ static ssize_t ext4_dio_write_checks(struct kiocb *iocb, struct iov_iter *from,
* required to change security info in file_modified(), for extending
* I/O, any form of non-overwrite I/O, and unaligned I/O to unwritten
* extents (as partial block zeroing may be required).
+ *
+ * Note that unaligned writes are allowed under shared lock so long as
+ * they are pure overwrites. Otherwise, concurrent unaligned writes risk
+ * data corruption due to partial block zeroing in the dio layer, and so
+ * the I/O must occur exclusively.
*/
if (*ilock_shared &&
((!IS_NOSEC(inode) || *extend || !overwrite ||
@@ -492,21 +497,12 @@ static ssize_t ext4_dio_write_checks(struct kiocb *iocb, struct iov_iter *from,

/*
* Now that locking is settled, determine dio flags and exclusivity
- * requirements. Unaligned writes are allowed under shared lock so long
- * as they are pure overwrites. Set the iomap overwrite only flag as an
- * added precaution in this case. Even though this is unnecessary, we
- * can detect and warn on unexpected -EAGAIN if an unsafe unaligned
- * write is ever submitted.
- *
- * Otherwise, concurrent unaligned writes risk data corruption due to
- * partial block zeroing in the dio layer, and so the I/O must occur
- * exclusively. The inode lock is already held exclusive if the write is
- * non-overwrite or extending, so drain all outstanding dio and set the
- * force wait dio flag.
+ * requirements. We don't use DIO_OVERWRITE_ONLY because we enforce
+ * behavior already. The inode lock is already held exclusive if the
+ * write is non-overwrite or extending, so drain all outstanding dio and
+ * set the force wait dio flag.
*/
- if (*ilock_shared && unaligned_io) {
- *dio_flags = IOMAP_DIO_OVERWRITE_ONLY;
- } else if (!*ilock_shared && (unaligned_io || *extend)) {
+ if (!*ilock_shared && (unaligned_io || *extend)) {
if (iocb->ki_flags & IOCB_NOWAIT) {
ret = -EAGAIN;
goto out;
@@ -608,7 +604,6 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
iomap_ops = &ext4_iomap_overwrite_ops;
ret = iomap_dio_rw(iocb, from, iomap_ops, &ext4_dio_write_ops,
dio_flags, NULL, 0);
- WARN_ON_ONCE(ret == -EAGAIN && !(iocb->ki_flags & IOCB_NOWAIT));
if (ret == -ENOTBLK)
ret = 0;

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 5882afe71d82..ecebc3a139be 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1389,18 +1389,14 @@ struct page *f2fs_get_lock_data_page(struct inode *inode, pgoff_t index,
{
struct address_space *mapping = inode->i_mapping;
struct page *page;
-repeat:
+
page = f2fs_get_read_data_page(inode, index, 0, for_write, NULL);
if (IS_ERR(page))
return page;

/* wait for read completion */
lock_page(page);
- if (unlikely(page->mapping != mapping)) {
- f2fs_put_page(page, 1);
- goto repeat;
- }
- if (unlikely(!PageUptodate(page))) {
+ if (unlikely(page->mapping != mapping || !PageUptodate(page))) {
f2fs_put_page(page, 1);
return ERR_PTR(-EIO);
}
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index c602ff2403b6..c0b7417f1d87 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -2122,15 +2122,6 @@ static inline int f2fs_down_read_trylock(struct f2fs_rwsem *sem)
return down_read_trylock(&sem->internal_rwsem);
}

-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-static inline void f2fs_down_read_nested(struct f2fs_rwsem *sem, int subclass)
-{
- down_read_nested(&sem->internal_rwsem, subclass);
-}
-#else
-#define f2fs_down_read_nested(sem, subclass) f2fs_down_read(sem)
-#endif
-
static inline void f2fs_up_read(struct f2fs_rwsem *sem)
{
up_read(&sem->internal_rwsem);
@@ -2141,6 +2132,21 @@ static inline void f2fs_down_write(struct f2fs_rwsem *sem)
down_write(&sem->internal_rwsem);
}

+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+static inline void f2fs_down_read_nested(struct f2fs_rwsem *sem, int subclass)
+{
+ down_read_nested(&sem->internal_rwsem, subclass);
+}
+
+static inline void f2fs_down_write_nested(struct f2fs_rwsem *sem, int subclass)
+{
+ down_write_nested(&sem->internal_rwsem, subclass);
+}
+#else
+#define f2fs_down_read_nested(sem, subclass) f2fs_down_read(sem)
+#define f2fs_down_write_nested(sem, subclass) f2fs_down_write(sem)
+#endif
+
static inline int f2fs_down_write_trylock(struct f2fs_rwsem *sem)
{
return down_write_trylock(&sem->internal_rwsem);
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 4638fee16a91..0d185ad5e469 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -641,7 +641,8 @@ int f2fs_add_inline_entry(struct inode *dir, const struct f2fs_filename *fname,
}

if (inode) {
- f2fs_down_write(&F2FS_I(inode)->i_sem);
+ f2fs_down_write_nested(&F2FS_I(inode)->i_sem,
+ SINGLE_DEPTH_NESTING);
page = f2fs_init_inode_metadata(inode, dir, fname, ipage);
if (IS_ERR(page)) {
err = PTR_ERR(page);
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index be08be6f4bfd..b38bf2b34490 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -205,6 +205,8 @@ void f2fs_abort_atomic_write(struct inode *inode, bool clean)
f2fs_i_size_write(inode, fi->original_i_size);
fi->original_i_size = 0;
}
+ /* avoid stale dirty inode during eviction */
+ sync_inode_metadata(inode, 0);
}

static int __replace_atomic_write_block(struct inode *inode, pgoff_t index,
diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c
index dc603479b30e..b3d498163f97 100644
--- a/fs/fuse/readdir.c
+++ b/fs/fuse/readdir.c
@@ -243,8 +243,16 @@ static int fuse_direntplus_link(struct file *file,
dput(dentry);
dentry = alias;
}
- if (IS_ERR(dentry))
+ if (IS_ERR(dentry)) {
+ if (!IS_ERR(inode)) {
+ struct fuse_inode *fi = get_fuse_inode(inode);
+
+ spin_lock(&fi->lock);
+ fi->nlookup--;
+ spin_unlock(&fi->lock);
+ }
return PTR_ERR(dentry);
+ }
}
if (fc->readdirplus_auto)
set_bit(FUSE_I_INIT_RDPLUS, &get_fuse_inode(inode)->state);
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index ae49256b7c8c..be2759a974f9 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -183,13 +183,13 @@ static int gfs2_writepages(struct address_space *mapping,
int ret;

/*
- * Even if we didn't write any pages here, we might still be holding
+ * Even if we didn't write enough pages here, we might still be holding
* dirty pages in the ail. We forcibly flush the ail because we don't
* want balance_dirty_pages() to loop indefinitely trying to write out
* pages held in the ail that it can't find.
*/
ret = iomap_writepages(mapping, wbc, &wpc, &gfs2_writeback_ops);
- if (ret == 0)
+ if (ret == 0 && wbc->nr_to_write > 0)
set_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags);
return ret;
}
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index aa568796207c..aaca22f2aa2d 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -1282,9 +1282,6 @@ static inline int gfs2_ail_flush_reqd(struct gfs2_sbd *sdp)
{
unsigned int used_blocks = sdp->sd_jdesc->jd_blocks - atomic_read(&sdp->sd_log_blks_free);

- if (test_and_clear_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags))
- return 1;
-
return used_blocks + atomic_read(&sdp->sd_log_blks_needed) >=
atomic_read(&sdp->sd_log_thresh2);
}
@@ -1301,7 +1298,6 @@ int gfs2_logd(void *data)
{
struct gfs2_sbd *sdp = data;
unsigned long t = 1;
- DEFINE_WAIT(wait);

while (!kthread_should_stop()) {

@@ -1326,7 +1322,9 @@ int gfs2_logd(void *data)
GFS2_LFC_LOGD_JFLUSH_REQD);
}

- if (gfs2_ail_flush_reqd(sdp)) {
+ if (test_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags) ||
+ gfs2_ail_flush_reqd(sdp)) {
+ clear_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags);
gfs2_ail1_start(sdp);
gfs2_ail1_wait(sdp);
gfs2_ail1_empty(sdp, 0);
@@ -1338,17 +1336,12 @@ int gfs2_logd(void *data)

try_to_freeze();

- do {
- prepare_to_wait(&sdp->sd_logd_waitq, &wait,
- TASK_INTERRUPTIBLE);
- if (!gfs2_ail_flush_reqd(sdp) &&
- !gfs2_jrnl_flush_reqd(sdp) &&
- !kthread_should_stop())
- t = schedule_timeout(t);
- } while(t && !gfs2_ail_flush_reqd(sdp) &&
- !gfs2_jrnl_flush_reqd(sdp) &&
- !kthread_should_stop());
- finish_wait(&sdp->sd_logd_waitq, &wait);
+ t = wait_event_interruptible_timeout(sdp->sd_logd_waitq,
+ test_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags) ||
+ gfs2_ail_flush_reqd(sdp) ||
+ gfs2_jrnl_flush_reqd(sdp) ||
+ kthread_should_stop(),
+ t);
}

return 0;
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 9ec91017a7f3..f033ac807013 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -349,6 +349,8 @@ int jbd2_cleanup_journal_tail(journal_t *journal)

/* Checkpoint list management */

+enum shrink_type {SHRINK_DESTROY, SHRINK_BUSY_STOP, SHRINK_BUSY_SKIP};
+
/*
* journal_shrink_one_cp_list
*
@@ -360,7 +362,8 @@ int jbd2_cleanup_journal_tail(journal_t *journal)
* Called with j_list_lock held.
*/
static unsigned long journal_shrink_one_cp_list(struct journal_head *jh,
- bool destroy, bool *released)
+ enum shrink_type type,
+ bool *released)
{
struct journal_head *last_jh;
struct journal_head *next_jh = jh;
@@ -376,12 +379,15 @@ static unsigned long journal_shrink_one_cp_list(struct journal_head *jh,
jh = next_jh;
next_jh = jh->b_cpnext;

- if (destroy) {
+ if (type == SHRINK_DESTROY) {
ret = __jbd2_journal_remove_checkpoint(jh);
} else {
ret = jbd2_journal_try_remove_checkpoint(jh);
- if (ret < 0)
- continue;
+ if (ret < 0) {
+ if (type == SHRINK_BUSY_SKIP)
+ continue;
+ break;
+ }
}

nr_freed++;
@@ -445,7 +451,7 @@ unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal,
tid = transaction->t_tid;

freed = journal_shrink_one_cp_list(transaction->t_checkpoint_list,
- false, &released);
+ SHRINK_BUSY_SKIP, &released);
nr_freed += freed;
(*nr_to_scan) -= min(*nr_to_scan, freed);
if (*nr_to_scan == 0)
@@ -485,19 +491,21 @@ unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal,
void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy)
{
transaction_t *transaction, *last_transaction, *next_transaction;
+ enum shrink_type type;
bool released;

transaction = journal->j_checkpoint_transactions;
if (!transaction)
return;

+ type = destroy ? SHRINK_DESTROY : SHRINK_BUSY_STOP;
last_transaction = transaction->t_cpprev;
next_transaction = transaction;
do {
transaction = next_transaction;
next_transaction = transaction->t_cpnext;
journal_shrink_one_cp_list(transaction->t_checkpoint_list,
- destroy, &released);
+ type, &released);
/*
* This function only frees up some memory if possible so we
* dont have an obligation to finish processing. Bail out if
@@ -631,6 +639,8 @@ int jbd2_journal_try_remove_checkpoint(struct journal_head *jh)
{
struct buffer_head *bh = jh2bh(jh);

+ if (jh->b_transaction)
+ return -EBUSY;
if (!trylock_buffer(bh))
return -EBUSY;
if (buffer_dirty(bh)) {
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 0184931d47f7..c269a7d29a46 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -230,12 +230,8 @@ static int count_tags(journal_t *journal, struct buffer_head *bh)
/* Make sure we wrap around the log correctly! */
#define wrap(journal, var) \
do { \
- unsigned long _wrap_last = \
- jbd2_has_feature_fast_commit(journal) ? \
- (journal)->j_fc_last : (journal)->j_last; \
- \
- if (var >= _wrap_last) \
- var -= (_wrap_last - (journal)->j_first); \
+ if (var >= (journal)->j_last) \
+ var -= ((journal)->j_last - (journal)->j_first); \
} while (0)

static int fc_do_one_pass(journal_t *journal,
@@ -524,9 +520,7 @@ static int do_one_pass(journal_t *journal,
break;

jbd2_debug(2, "Scanning for sequence ID %u at %lu/%lu\n",
- next_commit_ID, next_log_block,
- jbd2_has_feature_fast_commit(journal) ?
- journal->j_fc_last : journal->j_last);
+ next_commit_ID, next_log_block, journal->j_last);

/* Skip over each chunk of the transaction looking
* either the next descriptor block or the final commit
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 5a1a4af9d3d2..bf243015834e 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -383,9 +383,11 @@ static int kernfs_link_sibling(struct kernfs_node *kn)
rb_insert_color(&kn->rb, &kn->parent->dir.children);

/* successfully added, account subdir number */
+ down_write(&kernfs_root(kn)->kernfs_iattr_rwsem);
if (kernfs_type(kn) == KERNFS_DIR)
kn->parent->dir.subdirs++;
kernfs_inc_rev(kn->parent);
+ up_write(&kernfs_root(kn)->kernfs_iattr_rwsem);

return 0;
}
@@ -408,9 +410,11 @@ static bool kernfs_unlink_sibling(struct kernfs_node *kn)
if (RB_EMPTY_NODE(&kn->rb))
return false;

+ down_write(&kernfs_root(kn)->kernfs_iattr_rwsem);
if (kernfs_type(kn) == KERNFS_DIR)
kn->parent->dir.subdirs--;
kernfs_inc_rev(kn->parent);
+ up_write(&kernfs_root(kn)->kernfs_iattr_rwsem);

rb_erase(&kn->rb, &kn->parent->dir.children);
RB_CLEAR_NODE(&kn->rb);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index aaffaaa336cc..47d892a1d363 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -472,13 +472,31 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
return result;
}

+static void nfs_direct_add_page_head(struct list_head *list,
+ struct nfs_page *req)
+{
+ struct nfs_page *head = req->wb_head;
+
+ if (!list_empty(&head->wb_list) || !nfs_lock_request(head))
+ return;
+ if (!list_empty(&head->wb_list)) {
+ nfs_unlock_request(head);
+ return;
+ }
+ list_add(&head->wb_list, list);
+ kref_get(&head->wb_kref);
+ kref_get(&head->wb_kref);
+}
+
static void nfs_direct_join_group(struct list_head *list, struct inode *inode)
{
struct nfs_page *req, *subreq;

list_for_each_entry(req, list, wb_list) {
- if (req->wb_head != req)
+ if (req->wb_head != req) {
+ nfs_direct_add_page_head(&req->wb_list, req);
continue;
+ }
subreq = req->wb_this_page;
if (subreq == req)
continue;
diff --git a/fs/nfs/pnfs_dev.c b/fs/nfs/pnfs_dev.c
index ddbbf4fcda86..178001c90156 100644
--- a/fs/nfs/pnfs_dev.c
+++ b/fs/nfs/pnfs_dev.c
@@ -154,7 +154,7 @@ nfs4_get_device_info(struct nfs_server *server,
set_bit(NFS_DEVICEID_NOCACHE, &d->flags);

out_free_pages:
- for (i = 0; i < max_pages; i++)
+ while (--i >= 0)
__free_page(pages[i]);
kfree(pages);
out_free_pdev:
diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index fe483f163dbc..2d5e9a9d5b8b 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -218,7 +218,7 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon,
.tcon = tcon,
.path = path,
.create_options = cifs_create_options(cifs_sb, CREATE_NOT_FILE),
- .desired_access = FILE_READ_ATTRIBUTES,
+ .desired_access = FILE_READ_DATA | FILE_READ_ATTRIBUTES,
.disposition = FILE_OPEN,
.fid = pfid,
};
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 657dee4b2c8c..051f15b9d607 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -729,6 +729,7 @@ struct TCP_Server_Info {
*/
#define CIFS_SERVER_IS_CHAN(server) (!!(server)->primary_server)
struct TCP_Server_Info *primary_server;
+ __u16 channel_sequence_num; /* incremented on primary channel on each chan reconnect */

#ifdef CONFIG_CIFS_SWN_UPCALL
bool use_swn_dstaddr;
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 238538dde4e3..2456b5dd439c 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -1686,6 +1686,7 @@ cifs_get_tcp_session(struct smb3_fs_context *ctx,
ctx->target_rfc1001_name, RFC1001_NAME_LEN_WITH_NULL);
tcp_ses->session_estab = false;
tcp_ses->sequence_number = 0;
+ tcp_ses->channel_sequence_num = 0; /* only tracked for primary channel */
tcp_ses->reconnect_instance = 1;
tcp_ses->lstrp = jiffies;
tcp_ses->compress_algorithm = cpu_to_le16(ctx->compression);
diff --git a/fs/smb/client/fscache.c b/fs/smb/client/fscache.c
index 8f6909d633da..34e20c4cd507 100644
--- a/fs/smb/client/fscache.c
+++ b/fs/smb/client/fscache.c
@@ -48,7 +48,7 @@ int cifs_fscache_get_super_cookie(struct cifs_tcon *tcon)
sharename = extract_sharename(tcon->tree_name);
if (IS_ERR(sharename)) {
cifs_dbg(FYI, "%s: couldn't extract sharename\n", __func__);
- return -EINVAL;
+ return PTR_ERR(sharename);
}

slen = strlen(sharename);
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 0f62bc373ad0..dd6a423dc6e1 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -172,8 +172,17 @@ smb2_set_credits(struct TCP_Server_Info *server, const int val)

spin_lock(&server->req_lock);
server->credits = val;
- if (val == 1)
+ if (val == 1) {
server->reconnect_instance++;
+ /*
+ * ChannelSequence updated for all channels in primary channel so that consistent
+ * across SMB3 requests sent on any channel. See MS-SMB2 3.2.4.1 and 3.2.7.1
+ */
+ if (CIFS_SERVER_IS_CHAN(server))
+ server->primary_server->channel_sequence_num++;
+ else
+ server->channel_sequence_num++;
+ }
scredits = server->credits;
in_flight = server->in_flight;
spin_unlock(&server->req_lock);
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index a457f07f820d..9c7e46b7e7c7 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -88,9 +88,20 @@ smb2_hdr_assemble(struct smb2_hdr *shdr, __le16 smb2_cmd,
const struct cifs_tcon *tcon,
struct TCP_Server_Info *server)
{
+ struct smb3_hdr_req *smb3_hdr;
shdr->ProtocolId = SMB2_PROTO_NUMBER;
shdr->StructureSize = cpu_to_le16(64);
shdr->Command = smb2_cmd;
+ if (server->dialect >= SMB30_PROT_ID) {
+ /* After reconnect SMB3 must set ChannelSequence on subsequent reqs */
+ smb3_hdr = (struct smb3_hdr_req *)shdr;
+ /* if primary channel is not set yet, use default channel for chan sequence num */
+ if (CIFS_SERVER_IS_CHAN(server))
+ smb3_hdr->ChannelSequence =
+ cpu_to_le16(server->primary_server->channel_sequence_num);
+ else
+ smb3_hdr->ChannelSequence = cpu_to_le16(server->channel_sequence_num);
+ }
if (server) {
spin_lock(&server->req_lock);
/* Request up to 10 credits but don't go over the limit. */
diff --git a/fs/smb/common/smb2pdu.h b/fs/smb/common/smb2pdu.h
index bae590eec871..2680251b9aac 100644
--- a/fs/smb/common/smb2pdu.h
+++ b/fs/smb/common/smb2pdu.h
@@ -153,6 +153,28 @@ struct smb2_hdr {
__u8 Signature[16];
} __packed;

+struct smb3_hdr_req {
+ __le32 ProtocolId; /* 0xFE 'S' 'M' 'B' */
+ __le16 StructureSize; /* 64 */
+ __le16 CreditCharge; /* MBZ */
+ __le16 ChannelSequence; /* See MS-SMB2 3.2.4.1 and 3.2.7.1 */
+ __le16 Reserved;
+ __le16 Command;
+ __le16 CreditRequest; /* CreditResponse */
+ __le32 Flags;
+ __le32 NextCommand;
+ __le64 MessageId;
+ union {
+ struct {
+ __le32 ProcessId;
+ __le32 TreeId;
+ } __packed SyncId;
+ __le64 AsyncId;
+ } __packed Id;
+ __le64 SessionId;
+ __u8 Signature[16];
+} __packed;
+
struct smb2_pdu {
struct smb2_hdr hdr;
__le16 StructureSize2; /* size of wct area (varies, request specific) */
diff --git a/include/linux/audit.h b/include/linux/audit.h
index 6a3a9e122bb5..51b1b7054a23 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -117,6 +117,8 @@ enum audit_nfcfgop {
AUDIT_NFT_OP_OBJ_RESET,
AUDIT_NFT_OP_FLOWTABLE_REGISTER,
AUDIT_NFT_OP_FLOWTABLE_UNREGISTER,
+ AUDIT_NFT_OP_SETELEM_RESET,
+ AUDIT_NFT_OP_RULE_RESET,
AUDIT_NFT_OP_INVALID,
};

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f58895830ada..f316affcd2e1 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2619,6 +2619,18 @@ static inline void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr)
}
#endif /* CONFIG_BPF_SYSCALL */

+static __always_inline int
+bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr)
+{
+ int ret = -EFAULT;
+
+ if (IS_ENABLED(CONFIG_BPF_EVENTS))
+ ret = copy_from_kernel_nofault(dst, unsafe_ptr, size);
+ if (unlikely(ret < 0))
+ memset(dst, 0, size);
+ return ret;
+}
+
void __bpf_free_used_btfs(struct bpf_prog_aux *aux,
struct btf_mod_pair *used_btfs, u32 len);

diff --git a/include/linux/export-internal.h b/include/linux/export-internal.h
index 1c849db953a5..45fca09b2319 100644
--- a/include/linux/export-internal.h
+++ b/include/linux/export-internal.h
@@ -52,6 +52,8 @@

#ifdef CONFIG_IA64
#define KSYM_FUNC(name) @fptr(name)
+#elif defined(CONFIG_PARISC) && defined(CONFIG_64BIT)
+#define KSYM_FUNC(name) P%name
#else
#define KSYM_FUNC(name) name
#endif
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 660012997f54..644e69354cba 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -146,6 +146,7 @@ struct inet6_skb_parm {
#define IP6SKB_JUMBOGRAM 128
#define IP6SKB_SEG6 256
#define IP6SKB_FAKEJUMBO 512
+#define IP6SKB_MULTIPATH 1024
};

#if defined(CONFIG_NET_L3_MASTER_DEV)
diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h
index 8bef1ab62bba..4e27ca7c49de 100644
--- a/include/linux/micrel_phy.h
+++ b/include/linux/micrel_phy.h
@@ -41,9 +41,10 @@
#define PHY_ID_KSZ9477 0x00221631

/* struct phy_device dev_flags definitions */
-#define MICREL_PHY_50MHZ_CLK 0x00000001
-#define MICREL_PHY_FXEN 0x00000002
-#define MICREL_KSZ8_P1_ERRATA 0x00000003
+#define MICREL_PHY_50MHZ_CLK BIT(0)
+#define MICREL_PHY_FXEN BIT(1)
+#define MICREL_KSZ8_P1_ERRATA BIT(2)
+#define MICREL_NO_EEE BIT(3)

#define MICREL_KSZ9021_EXTREG_CTRL 0xB
#define MICREL_KSZ9021_EXTREG_DATA_WRITE 0xC
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 1817940a3418..4dff1eba425b 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -615,7 +615,7 @@ void pcs_get_state(struct phylink_pcs *pcs,
*
* The %neg_mode argument should be tested via the phylink_mode_*() family of
* functions, or for PCS that set pcs->neg_mode true, should be tested
- * against the %PHYLINK_PCS_NEG_* definitions.
+ * against the PHYLINK_PCS_NEG_* definitions.
*/
int pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode,
phy_interface_t interface, const unsigned long *advertising,
@@ -645,7 +645,7 @@ void pcs_an_restart(struct phylink_pcs *pcs);
*
* The %mode argument should be tested via the phylink_mode_*() family of
* functions, or for PCS that set pcs->neg_mode true, should be tested
- * against the %PHYLINK_PCS_NEG_* definitions.
+ * against the PHYLINK_PCS_NEG_* definitions.
*/
void pcs_link_up(struct phylink_pcs *pcs, unsigned int neg_mode,
phy_interface_t interface, int speed, int duplex);
diff --git a/include/linux/tca6416_keypad.h b/include/linux/tca6416_keypad.h
index b0d36a9934cc..5cf6f6f82aa7 100644
--- a/include/linux/tca6416_keypad.h
+++ b/include/linux/tca6416_keypad.h
@@ -25,7 +25,6 @@ struct tca6416_keys_platform_data {
unsigned int rep:1; /* enable input subsystem auto repeat */
uint16_t pinmask;
uint16_t invert;
- int irq_is_gpio;
int use_polling; /* use polling if Interrupt is not connected*/
};
#endif
diff --git a/include/net/ip.h b/include/net/ip.h
index 19adacd5ece0..3489a1cca5e7 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -57,6 +57,7 @@ struct inet_skb_parm {
#define IPSKB_FRAG_PMTU BIT(6)
#define IPSKB_L3SLAVE BIT(7)
#define IPSKB_NOPOLICY BIT(8)
+#define IPSKB_MULTIPATH BIT(9)

u16 frag_max_size;
};
@@ -94,7 +95,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
ipcm_init(ipcm);

ipcm->sockc.mark = READ_ONCE(inet->sk.sk_mark);
- ipcm->sockc.tsflags = inet->sk.sk_tsflags;
+ ipcm->sockc.tsflags = READ_ONCE(inet->sk.sk_tsflags);
ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if);
ipcm->addr = inet->inet_saddr;
ipcm->protocol = inet->inet_num;
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 05e6f756feaf..9ba6413fd2e3 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -604,7 +604,10 @@ static inline bool fib6_rules_early_flow_dissect(struct net *net,
if (!net->ipv6.fib6_rules_require_fldissect)
return false;

- skb_flow_dissect_flow_keys(skb, flkeys, flag);
+ memset(flkeys, 0, sizeof(*flkeys));
+ __skb_flow_dissect(net, skb, &flow_keys_dissector,
+ flkeys, NULL, 0, 0, 0, flag);
+
fl6->fl6_sport = flkeys->ports.src;
fl6->fl6_dport = flkeys->ports.dst;
fl6->flowi6_proto = flkeys->basic.ip_proto;
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index a378eff827c7..f0c13864180e 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -418,7 +418,10 @@ static inline bool fib4_rules_early_flow_dissect(struct net *net,
if (!net->ipv4.fib_rules_require_fldissect)
return false;

- skb_flow_dissect_flow_keys(skb, flkeys, flag);
+ memset(flkeys, 0, sizeof(*flkeys));
+ __skb_flow_dissect(net, skb, &flow_keys_dissector,
+ flkeys, NULL, 0, 0, 0, flag);
+
fl4->fl4_sport = flkeys->ports.src;
fl4->fl4_dport = flkeys->ports.dst;
fl4->flowi4_proto = flkeys->basic.ip_proto;
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index ed4b6ad3fcac..cd0e2744f66f 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -482,15 +482,14 @@ static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len)
u64_stats_inc(&tstats->tx_packets);
u64_stats_update_end(&tstats->syncp);
put_cpu_ptr(tstats);
+ return;
+ }
+
+ if (pkt_len < 0) {
+ DEV_STATS_INC(dev, tx_errors);
+ DEV_STATS_INC(dev, tx_aborted_errors);
} else {
- struct net_device_stats *err_stats = &dev->stats;
-
- if (pkt_len < 0) {
- err_stats->tx_errors++;
- err_stats->tx_aborted_errors++;
- } else {
- err_stats->tx_dropped++;
- }
+ DEV_STATS_INC(dev, tx_dropped);
}
}

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 2acc4c808d45..a14ac821fb36 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -784,6 +784,11 @@ static inline bool ipv6_addr_v4mapped(const struct in6_addr *a)
cpu_to_be32(0x0000ffff))) == 0UL;
}

+static inline bool ipv6_addr_v4mapped_any(const struct in6_addr *a)
+{
+ return ipv6_addr_v4mapped(a) && ipv4_is_zeronet(a->s6_addr32[3]);
+}
+
static inline bool ipv6_addr_v4mapped_loopback(const struct in6_addr *a)
{
return ipv6_addr_v4mapped(a) && ipv4_is_loopback(a->s6_addr32[3]);
@@ -1356,7 +1361,7 @@ static inline int __ip6_sock_set_addr_preferences(struct sock *sk, int val)
return 0;
}

-static inline int ip6_sock_set_addr_preferences(struct sock *sk, bool val)
+static inline int ip6_sock_set_addr_preferences(struct sock *sk, int val)
{
int ret;

diff --git a/include/net/scm.h b/include/net/scm.h
index c5bcdf65f55c..e8c76b4be2fe 100644
--- a/include/net/scm.h
+++ b/include/net/scm.h
@@ -9,6 +9,7 @@
#include <linux/pid.h>
#include <linux/nsproxy.h>
#include <linux/sched/signal.h>
+#include <net/compat.h>

/* Well, we should have at least one descriptor open
* to accept passed FDs 8)
@@ -123,14 +124,17 @@ static inline bool scm_has_secdata(struct socket *sock)
static __inline__ void scm_pidfd_recv(struct msghdr *msg, struct scm_cookie *scm)
{
struct file *pidfd_file = NULL;
- int pidfd;
+ int len, pidfd;

- /*
- * put_cmsg() doesn't return an error if CMSG is truncated,
+ /* put_cmsg() doesn't return an error if CMSG is truncated,
* that's why we need to opencode these checks here.
*/
- if ((msg->msg_controllen <= sizeof(struct cmsghdr)) ||
- (msg->msg_controllen - sizeof(struct cmsghdr)) < sizeof(int)) {
+ if (msg->msg_flags & MSG_CMSG_COMPAT)
+ len = sizeof(struct compat_cmsghdr) + sizeof(int);
+ else
+ len = sizeof(struct cmsghdr) + sizeof(int);
+
+ if (msg->msg_controllen < len) {
msg->msg_flags |= MSG_CTRUNC;
return;
}
diff --git a/include/net/sock.h b/include/net/sock.h
index e8927f2d47a3..4e787285fc66 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1053,6 +1053,12 @@ static inline void sk_wmem_queued_add(struct sock *sk, int val)
WRITE_ONCE(sk->sk_wmem_queued, sk->sk_wmem_queued + val);
}

+static inline void sk_forward_alloc_add(struct sock *sk, int val)
+{
+ /* Paired with lockless reads of sk->sk_forward_alloc */
+ WRITE_ONCE(sk->sk_forward_alloc, sk->sk_forward_alloc + val);
+}
+
void sk_stream_write_space(struct sock *sk);

/* OOB backlog add */
@@ -1377,7 +1383,7 @@ static inline int sk_forward_alloc_get(const struct sock *sk)
if (sk->sk_prot->forward_alloc_get)
return sk->sk_prot->forward_alloc_get(sk);
#endif
- return sk->sk_forward_alloc;
+ return READ_ONCE(sk->sk_forward_alloc);
}

static inline bool __sk_stream_memory_free(const struct sock *sk, int wake)
@@ -1673,14 +1679,14 @@ static inline void sk_mem_charge(struct sock *sk, int size)
{
if (!sk_has_account(sk))
return;
- sk->sk_forward_alloc -= size;
+ sk_forward_alloc_add(sk, -size);
}

static inline void sk_mem_uncharge(struct sock *sk, int size)
{
if (!sk_has_account(sk))
return;
- sk->sk_forward_alloc += size;
+ sk_forward_alloc_add(sk, size);
sk_mem_reclaim(sk);
}

@@ -1900,7 +1906,9 @@ struct sockcm_cookie {
static inline void sockcm_init(struct sockcm_cookie *sockc,
const struct sock *sk)
{
- *sockc = (struct sockcm_cookie) { .tsflags = sk->sk_tsflags };
+ *sockc = (struct sockcm_cookie) {
+ .tsflags = READ_ONCE(sk->sk_tsflags)
+ };
}

int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg,
@@ -2695,9 +2703,9 @@ void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk,
static inline void
sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
{
- ktime_t kt = skb->tstamp;
struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb);
-
+ u32 tsflags = READ_ONCE(sk->sk_tsflags);
+ ktime_t kt = skb->tstamp;
/*
* generate control messages if
* - receive time stamping in software requested
@@ -2705,10 +2713,10 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
* - hardware time stamps available and wanted
*/
if (sock_flag(sk, SOCK_RCVTSTAMP) ||
- (sk->sk_tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) ||
- (kt && sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) ||
+ (tsflags & SOF_TIMESTAMPING_RX_SOFTWARE) ||
+ (kt && tsflags & SOF_TIMESTAMPING_SOFTWARE) ||
(hwtstamps->hwtstamp &&
- (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE)))
+ (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE)))
__sock_recv_timestamp(msg, sk, skb);
else
sock_write_timestamp(sk, kt);
@@ -2730,7 +2738,8 @@ static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk,
#define TSFLAGS_ANY (SOF_TIMESTAMPING_SOFTWARE | \
SOF_TIMESTAMPING_RAW_HARDWARE)

- if (sk->sk_flags & FLAGS_RECV_CMSGS || sk->sk_tsflags & TSFLAGS_ANY)
+ if (sk->sk_flags & FLAGS_RECV_CMSGS ||
+ READ_ONCE(sk->sk_tsflags) & TSFLAGS_ANY)
__sock_recv_cmsgs(msg, sk, skb);
else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP)))
sock_write_timestamp(sk, skb->tstamp);
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 8dfd581cd554..eae5dfe9b9a0 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -143,6 +143,8 @@ static const struct audit_nfcfgop_tab audit_nfcfgs[] = {
{ AUDIT_NFT_OP_OBJ_RESET, "nft_reset_obj" },
{ AUDIT_NFT_OP_FLOWTABLE_REGISTER, "nft_register_flowtable" },
{ AUDIT_NFT_OP_FLOWTABLE_UNREGISTER, "nft_unregister_flowtable" },
+ { AUDIT_NFT_OP_SETELEM_RESET, "nft_reset_setelem" },
+ { AUDIT_NFT_OP_RULE_RESET, "nft_reset_rule" },
{ AUDIT_NFT_OP_INVALID, "nft_invalid" },
};

diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index b5149cfce7d4..146824cc9689 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -553,7 +553,7 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
void *value, u64 map_flags, gfp_t gfp_flags)
{
struct bpf_local_storage_data *old_sdata = NULL;
- struct bpf_local_storage_elem *selem = NULL;
+ struct bpf_local_storage_elem *alloc_selem, *selem = NULL;
struct bpf_local_storage *local_storage;
unsigned long flags;
int err;
@@ -607,11 +607,12 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
}
}

- if (gfp_flags == GFP_KERNEL) {
- selem = bpf_selem_alloc(smap, owner, value, true, gfp_flags);
- if (!selem)
- return ERR_PTR(-ENOMEM);
- }
+ /* A lookup has just been done before and concluded a new selem is
+ * needed. The chance of an unnecessary alloc is unlikely.
+ */
+ alloc_selem = selem = bpf_selem_alloc(smap, owner, value, true, gfp_flags);
+ if (!alloc_selem)
+ return ERR_PTR(-ENOMEM);

raw_spin_lock_irqsave(&local_storage->lock, flags);

@@ -623,13 +624,13 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
* simple.
*/
err = -EAGAIN;
- goto unlock_err;
+ goto unlock;
}

old_sdata = bpf_local_storage_lookup(local_storage, smap, false);
err = check_flags(old_sdata, map_flags);
if (err)
- goto unlock_err;
+ goto unlock;

if (old_sdata && (map_flags & BPF_F_LOCK)) {
copy_map_value_locked(&smap->map, old_sdata->data, value,
@@ -638,23 +639,7 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
goto unlock;
}

- if (gfp_flags != GFP_KERNEL) {
- /* local_storage->lock is held. Hence, we are sure
- * we can unlink and uncharge the old_sdata successfully
- * later. Hence, instead of charging the new selem now
- * and then uncharge the old selem later (which may cause
- * a potential but unnecessary charge failure), avoid taking
- * a charge at all here (the "!old_sdata" check) and the
- * old_sdata will not be uncharged later during
- * bpf_selem_unlink_storage_nolock().
- */
- selem = bpf_selem_alloc(smap, owner, value, !old_sdata, gfp_flags);
- if (!selem) {
- err = -ENOMEM;
- goto unlock_err;
- }
- }
-
+ alloc_selem = NULL;
/* First, link the new selem to the map */
bpf_selem_link_map(smap, selem);

@@ -665,20 +650,16 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
if (old_sdata) {
bpf_selem_unlink_map(SELEM(old_sdata));
bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata),
- false, false);
+ true, false);
}

unlock:
raw_spin_unlock_irqrestore(&local_storage->lock, flags);
- return SDATA(selem);
-
-unlock_err:
- raw_spin_unlock_irqrestore(&local_storage->lock, flags);
- if (selem) {
+ if (alloc_selem) {
mem_uncharge(smap, owner, smap->elem_size);
- bpf_selem_free(selem, smap, true);
+ bpf_selem_free(alloc_selem, smap, true);
}
- return ERR_PTR(err);
+ return err ? ERR_PTR(err) : SDATA(selem);
}

static u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache)
@@ -779,7 +760,7 @@ void bpf_local_storage_destroy(struct bpf_local_storage *local_storage)
* of the loop will set the free_cgroup_storage to true.
*/
free_storage = bpf_selem_unlink_storage_nolock(
- local_storage, selem, false, true);
+ local_storage, selem, true, true);
}
raw_spin_unlock_irqrestore(&local_storage->lock, flags);

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index dc85240a0134..e3e45b651cd4 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1635,12 +1635,6 @@ bool bpf_opcode_in_insntable(u8 code)
}

#ifndef CONFIG_BPF_JIT_ALWAYS_ON
-u64 __weak bpf_probe_read_kernel(void *dst, u32 size, const void *unsafe_ptr)
-{
- memset(dst, 0, size);
- return -EFAULT;
-}
-
/**
* ___bpf_prog_run - run eBPF program on a given context
* @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers
@@ -1931,8 +1925,8 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn)
DST = *(SIZE *)(unsigned long) (SRC + insn->off); \
CONT; \
LDX_PROBE_MEM_##SIZEOP: \
- bpf_probe_read_kernel(&DST, sizeof(SIZE), \
- (const void *)(long) (SRC + insn->off)); \
+ bpf_probe_read_kernel_common(&DST, sizeof(SIZE), \
+ (const void *)(long) (SRC + insn->off)); \
DST = *((SIZE *)&DST); \
CONT;

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a2aef900519c..1480b6cf12f0 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -5304,9 +5304,9 @@ int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size)
}

run_ctx.bpf_cookie = 0;
- run_ctx.saved_run_ctx = NULL;
if (!__bpf_prog_enter_sleepable_recur(prog, &run_ctx)) {
/* recursion detected */
+ __bpf_prog_exit_sleepable_recur(prog, 0, &run_ctx);
bpf_prog_put(prog);
return -EBUSY;
}
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 78acf28d4873..53ff50cac61e 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -926,13 +926,12 @@ u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog,
migrate_disable();
might_fault();

+ run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);
+
if (unlikely(this_cpu_inc_return(*(prog->active)) != 1)) {
bpf_prog_inc_misses_counter(prog);
return 0;
}
-
- run_ctx->saved_run_ctx = bpf_set_run_ctx(&run_ctx->run_ctx);
-
return bpf_prog_start_time();
}

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 30d8db47c1e2..abf287b2678a 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -223,17 +223,6 @@ const struct bpf_func_proto bpf_probe_read_user_str_proto = {
.arg3_type = ARG_ANYTHING,
};

-static __always_inline int
-bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr)
-{
- int ret;
-
- ret = copy_from_kernel_nofault(dst, unsafe_ptr, size);
- if (unlikely(ret < 0))
- memset(dst, 0, size);
- return ret;
-}
-
BPF_CALL_3(bpf_probe_read_kernel, void *, dst, u32, size,
const void *, unsafe_ptr)
{
diff --git a/lib/idr.c b/lib/idr.c
index 7ecdfdb5309e..13f2758c2377 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -100,7 +100,7 @@ EXPORT_SYMBOL_GPL(idr_alloc);
* @end: The maximum ID (exclusive).
* @gfp: Memory allocation flags.
*
- * Allocates an unused ID in the range specified by @nextid and @end. If
+ * Allocates an unused ID in the range specified by @start and @end. If
* @end is <= 0, it is treated as one larger than %INT_MAX. This allows
* callers to use @start + N as @end as long as N is within integer range.
* The search for an unused ID will start at the last ID allocated and will
diff --git a/lib/kunit/test.c b/lib/kunit/test.c
index 84e4666555c9..e8c9dd9d73a3 100644
--- a/lib/kunit/test.c
+++ b/lib/kunit/test.c
@@ -744,12 +744,13 @@ static int kunit_module_notify(struct notifier_block *nb, unsigned long val,

switch (val) {
case MODULE_STATE_LIVE:
- kunit_module_init(mod);
break;
case MODULE_STATE_GOING:
kunit_module_exit(mod);
break;
case MODULE_STATE_COMING:
+ kunit_module_init(mod);
+ break;
case MODULE_STATE_UNFORMED:
break;
}
diff --git a/lib/test_meminit.c b/lib/test_meminit.c
index 60e1984c060f..0ae35223d773 100644
--- a/lib/test_meminit.c
+++ b/lib/test_meminit.c
@@ -93,7 +93,7 @@ static int __init test_pages(int *total_failures)
int failures = 0, num_tests = 0;
int i;

- for (i = 0; i < 10; i++)
+ for (i = 0; i <= MAX_ORDER; i++)
num_tests += do_alloc_pages_order(i, &failures);

REPORT_FAILURES_IN_FN();
diff --git a/lib/test_scanf.c b/lib/test_scanf.c
index b620cf7de503..a2707af2951a 100644
--- a/lib/test_scanf.c
+++ b/lib/test_scanf.c
@@ -606,7 +606,7 @@ static void __init numbers_slice(void)
#define test_number_prefix(T, str, scan_fmt, expect0, expect1, n_args, fn) \
do { \
const T expect[2] = { expect0, expect1 }; \
- T result[2] = {~expect[0], ~expect[1]}; \
+ T result[2] = { (T)~expect[0], (T)~expect[1] }; \
\
_test(fn, &expect, str, scan_fmt, n_args, &result[0], &result[1]); \
} while (0)
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index c2007ef5e9b0..4b9734777f69 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -36,14 +36,22 @@ struct vmemmap_remap_walk {
struct list_head *vmemmap_pages;
};

-static int __split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start)
+static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start)
{
pmd_t __pmd;
int i;
unsigned long addr = start;
- struct page *page = pmd_page(*pmd);
- pte_t *pgtable = pte_alloc_one_kernel(&init_mm);
+ struct page *head;
+ pte_t *pgtable;
+
+ spin_lock(&init_mm.page_table_lock);
+ head = pmd_leaf(*pmd) ? pmd_page(*pmd) : NULL;
+ spin_unlock(&init_mm.page_table_lock);

+ if (!head)
+ return 0;
+
+ pgtable = pte_alloc_one_kernel(&init_mm);
if (!pgtable)
return -ENOMEM;

@@ -53,7 +61,7 @@ static int __split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start)
pte_t entry, *pte;
pgprot_t pgprot = PAGE_KERNEL;

- entry = mk_pte(page + i, pgprot);
+ entry = mk_pte(head + i, pgprot);
pte = pte_offset_kernel(&__pmd, addr);
set_pte_at(&init_mm, addr, pte, entry);
}
@@ -65,8 +73,8 @@ static int __split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start)
* be treated as indepdenent small pages (as they can be freed
* individually).
*/
- if (!PageReserved(page))
- split_page(page, get_order(PMD_SIZE));
+ if (!PageReserved(head))
+ split_page(head, get_order(PMD_SIZE));

/* Make pte visible before pmd. See comment in pmd_install(). */
smp_wmb();
@@ -80,20 +88,6 @@ static int __split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start)
return 0;
}

-static int split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start)
-{
- int leaf;
-
- spin_lock(&init_mm.page_table_lock);
- leaf = pmd_leaf(*pmd);
- spin_unlock(&init_mm.page_table_lock);
-
- if (!leaf)
- return 0;
-
- return __split_vmemmap_huge_pmd(pmd, start);
-}
-
static void vmemmap_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long end,
struct vmemmap_remap_walk *walk)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 315fd5f45e3c..e79267c1eee0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3871,10 +3871,6 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of,
case _MEMSWAP:
ret = mem_cgroup_resize_max(memcg, nr_pages, true);
break;
- case _KMEM:
- /* kmem.limit_in_bytes is deprecated. */
- ret = -EOPNOTSUPP;
- break;
case _TCP:
ret = memcg_update_tcp_max(memcg, nr_pages);
break;
@@ -5085,12 +5081,6 @@ static struct cftype mem_cgroup_legacy_files[] = {
.seq_show = memcg_numa_stat_show,
},
#endif
- {
- .name = "kmem.limit_in_bytes",
- .private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT),
- .write = mem_cgroup_write,
- .read_u64 = mem_cgroup_read_u64,
- },
{
.name = "kmem.usage_in_bytes",
.private = MEMFILE_PRIVATE(_KMEM, RES_USAGE),
@@ -5339,7 +5329,6 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
INIT_LIST_HEAD(&memcg->deferred_split_queue.split_queue);
memcg->deferred_split_queue.split_queue_len = 0;
#endif
- idr_replace(&mem_cgroup_idr, memcg, memcg->id.id);
lru_gen_init_memcg(memcg);
return memcg;
fail:
@@ -5411,14 +5400,27 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css)
if (alloc_shrinker_info(memcg))
goto offline_kmem;

- /* Online state pins memcg ID, memcg ID pins CSS */
- refcount_set(&memcg->id.ref, 1);
- css_get(css);
-
if (unlikely(mem_cgroup_is_root(memcg)))
queue_delayed_work(system_unbound_wq, &stats_flush_dwork,
FLUSH_TIME);
lru_gen_online_memcg(memcg);
+
+ /* Online state pins memcg ID, memcg ID pins CSS */
+ refcount_set(&memcg->id.ref, 1);
+ css_get(css);
+
+ /*
+ * Ensure mem_cgroup_from_id() works once we're fully online.
+ *
+ * We could do this earlier and require callers to filter with
+ * css_tryget_online(). But right now there are no users that
+ * need earlier access, and the workingset code relies on the
+ * cgroup tree linkage (mem_cgroup_get_nr_swap_pages()). So
+ * publish it here at the end of onlining. This matches the
+ * regular ID destruction during offlining.
+ */
+ idr_replace(&mem_cgroup_idr, memcg, memcg->id.id);
+
return 0;
offline_kmem:
memcg_offline_kmem(memcg);
diff --git a/mm/mremap.c b/mm/mremap.c
index 11e06e4ab33b..91f0173d396f 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -715,7 +715,7 @@ static unsigned long move_vma(struct vm_area_struct *vma,
}

vma_iter_init(&vmi, mm, old_addr);
- if (!do_vmi_munmap(&vmi, mm, old_addr, old_len, uf_unmap, false)) {
+ if (do_vmi_munmap(&vmi, mm, old_addr, old_len, uf_unmap, false) < 0) {
/* OOM: unable to split vma, just get accounts right */
if (vm_flags & VM_ACCOUNT && !(flags & MREMAP_DONTUNMAP))
vm_acct_memory(old_len >> PAGE_SHIFT);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 5be64834a852..da152407bc2b 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4440,7 +4440,7 @@ static void inc_max_seq(struct lruvec *lruvec, bool can_swap, bool force_scan)
int prev, next;
int type, zone;
struct lru_gen_folio *lrugen = &lruvec->lrugen;
-
+restart:
spin_lock_irq(&lruvec->lru_lock);

VM_WARN_ON_ONCE(!seq_is_valid(lruvec));
@@ -4451,11 +4451,12 @@ static void inc_max_seq(struct lruvec *lruvec, bool can_swap, bool force_scan)

VM_WARN_ON_ONCE(!force_scan && (type == LRU_GEN_FILE || can_swap));

- while (!inc_min_seq(lruvec, type, can_swap)) {
- spin_unlock_irq(&lruvec->lru_lock);
- cond_resched();
- spin_lock_irq(&lruvec->lru_lock);
- }
+ if (inc_min_seq(lruvec, type, can_swap))
+ continue;
+
+ spin_unlock_irq(&lruvec->lru_lock);
+ cond_resched();
+ goto restart;
}

/*
diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index feaec4ad6d16..b28c976f52a0 100644
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -974,6 +974,7 @@ static void __j1939_sk_errqueue(struct j1939_session *session, struct sock *sk,
struct sock_exterr_skb *serr;
struct sk_buff *skb;
char *state = "UNK";
+ u32 tsflags;
int err;

jsk = j1939_sk(sk);
@@ -981,13 +982,14 @@ static void __j1939_sk_errqueue(struct j1939_session *session, struct sock *sk,
if (!(jsk->state & J1939_SOCK_ERRQUEUE))
return;

+ tsflags = READ_ONCE(sk->sk_tsflags);
switch (type) {
case J1939_ERRQUEUE_TX_ACK:
- if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK))
+ if (!(tsflags & SOF_TIMESTAMPING_TX_ACK))
return;
break;
case J1939_ERRQUEUE_TX_SCHED:
- if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_SCHED))
+ if (!(tsflags & SOF_TIMESTAMPING_TX_SCHED))
return;
break;
case J1939_ERRQUEUE_TX_ABORT:
@@ -997,7 +999,7 @@ static void __j1939_sk_errqueue(struct j1939_session *session, struct sock *sk,
case J1939_ERRQUEUE_RX_DPO:
fallthrough;
case J1939_ERRQUEUE_RX_ABORT:
- if (!(sk->sk_tsflags & SOF_TIMESTAMPING_RX_SOFTWARE))
+ if (!(tsflags & SOF_TIMESTAMPING_RX_SOFTWARE))
return;
break;
default:
@@ -1054,7 +1056,7 @@ static void __j1939_sk_errqueue(struct j1939_session *session, struct sock *sk,
}

serr->opt_stats = true;
- if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
+ if (tsflags & SOF_TIMESTAMPING_OPT_ID)
serr->ee.ee_data = session->tskey;

netdev_dbg(session->priv->ndev, "%s: 0x%p tskey: %i, state: %s\n",
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 85a2d0d9bd39..6bed3992df81 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1780,8 +1780,7 @@ u32 __skb_get_hash_symmetric(const struct sk_buff *skb)

memset(&keys, 0, sizeof(keys));
__skb_flow_dissect(NULL, skb, &flow_keys_dissector_symmetric,
- &keys, NULL, 0, 0, 0,
- FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
+ &keys, NULL, 0, 0, 0, 0);

return __flow_hash_from_keys(&keys, &hashrnd);
}
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index acdf94bb54c8..7dfae58055c2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5149,7 +5149,7 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb,
serr->ee.ee_info = tstype;
serr->opt_stats = opt_stats;
serr->header.h4.iif = skb->dev ? skb->dev->ifindex : 0;
- if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) {
+ if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID) {
serr->ee.ee_data = skb_shinfo(skb)->tskey;
if (sk_is_tcp(sk))
serr->ee.ee_data -= atomic_read(&sk->sk_tskey);
@@ -5205,21 +5205,23 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
{
struct sk_buff *skb;
bool tsonly, opt_stats = false;
+ u32 tsflags;

if (!sk)
return;

- if (!hwtstamps && !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) &&
+ tsflags = READ_ONCE(sk->sk_tsflags);
+ if (!hwtstamps && !(tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) &&
skb_shinfo(orig_skb)->tx_flags & SKBTX_IN_PROGRESS)
return;

- tsonly = sk->sk_tsflags & SOF_TIMESTAMPING_OPT_TSONLY;
+ tsonly = tsflags & SOF_TIMESTAMPING_OPT_TSONLY;
if (!skb_may_tx_timestamp(sk, tsonly))
return;

if (tsonly) {
#ifdef CONFIG_INET
- if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_STATS) &&
+ if ((tsflags & SOF_TIMESTAMPING_OPT_STATS) &&
sk_is_tcp(sk)) {
skb = tcp_get_timestamping_opt_stats(sk, orig_skb,
ack_skb);
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index ef1a2eb6520b..a746dbc2f887 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -612,12 +612,18 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb
static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
u32 off, u32 len, bool ingress)
{
+ int err = 0;
+
if (!ingress) {
if (!sock_writeable(psock->sk))
return -EAGAIN;
return skb_send_sock(psock->sk, skb, off, len);
}
- return sk_psock_skb_ingress(psock, skb, off, len);
+ skb_get(skb);
+ err = sk_psock_skb_ingress(psock, skb, off, len);
+ if (err < 0)
+ kfree_skb(skb);
+ return err;
}

static void sk_psock_skb_state(struct sk_psock *psock,
@@ -685,9 +691,7 @@ static void sk_psock_backlog(struct work_struct *work)
} while (len);

skb = skb_dequeue(&psock->ingress_skb);
- if (!ingress) {
- kfree_skb(skb);
- }
+ kfree_skb(skb);
}
end:
mutex_unlock(&psock->work_mutex);
diff --git a/net/core/sock.c b/net/core/sock.c
index 1c5c01b116e6..29c6cb030818 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -765,7 +765,8 @@ bool sk_mc_loop(struct sock *sk)
return false;
if (!sk)
return true;
- switch (sk->sk_family) {
+ /* IPV6_ADDRFORM can change sk->sk_family under us. */
+ switch (READ_ONCE(sk->sk_family)) {
case AF_INET:
return inet_sk(sk)->mc_loop;
#if IS_ENABLED(CONFIG_IPV6)
@@ -893,7 +894,7 @@ static int sock_timestamping_bind_phc(struct sock *sk, int phc_index)
if (!match)
return -EINVAL;

- sk->sk_bind_phc = phc_index;
+ WRITE_ONCE(sk->sk_bind_phc, phc_index);

return 0;
}
@@ -936,7 +937,7 @@ int sock_set_timestamping(struct sock *sk, int optname,
return ret;
}

- sk->sk_tsflags = val;
+ WRITE_ONCE(sk->sk_tsflags, val);
sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW);

if (val & SOF_TIMESTAMPING_RX_SOFTWARE)
@@ -1044,7 +1045,7 @@ static int sock_reserve_memory(struct sock *sk, int bytes)
mem_cgroup_uncharge_skmem(sk->sk_memcg, pages);
return -ENOMEM;
}
- sk->sk_forward_alloc += pages << PAGE_SHIFT;
+ sk_forward_alloc_add(sk, pages << PAGE_SHIFT);

WRITE_ONCE(sk->sk_reserved_mem,
sk->sk_reserved_mem + (pages << PAGE_SHIFT));
@@ -1717,8 +1718,8 @@ int sk_getsockopt(struct sock *sk, int level, int optname,

case SO_TIMESTAMPING_OLD:
lv = sizeof(v.timestamping);
- v.timestamping.flags = sk->sk_tsflags;
- v.timestamping.bind_phc = sk->sk_bind_phc;
+ v.timestamping.flags = READ_ONCE(sk->sk_tsflags);
+ v.timestamping.bind_phc = READ_ONCE(sk->sk_bind_phc);
break;

case SO_RCVTIMEO_OLD:
@@ -2745,9 +2746,9 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo)
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
if (refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf))
break;
- if (sk->sk_shutdown & SEND_SHUTDOWN)
+ if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN)
break;
- if (sk->sk_err)
+ if (READ_ONCE(sk->sk_err))
break;
timeo = schedule_timeout(timeo);
}
@@ -2775,7 +2776,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
goto failure;

err = -EPIPE;
- if (sk->sk_shutdown & SEND_SHUTDOWN)
+ if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN)
goto failure;

if (sk_wmem_alloc_get(sk) < READ_ONCE(sk->sk_sndbuf))
@@ -3137,10 +3138,10 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind)
{
int ret, amt = sk_mem_pages(size);

- sk->sk_forward_alloc += amt << PAGE_SHIFT;
+ sk_forward_alloc_add(sk, amt << PAGE_SHIFT);
ret = __sk_mem_raise_allocated(sk, size, amt, kind);
if (!ret)
- sk->sk_forward_alloc -= amt << PAGE_SHIFT;
+ sk_forward_alloc_add(sk, -(amt << PAGE_SHIFT));
return ret;
}
EXPORT_SYMBOL(__sk_mem_schedule);
@@ -3172,7 +3173,7 @@ void __sk_mem_reduce_allocated(struct sock *sk, int amount)
void __sk_mem_reclaim(struct sock *sk, int amount)
{
amount >>= PAGE_SHIFT;
- sk->sk_forward_alloc -= amount << PAGE_SHIFT;
+ sk_forward_alloc_add(sk, -(amount << PAGE_SHIFT));
__sk_mem_reduce_allocated(sk, amount);
}
EXPORT_SYMBOL(__sk_mem_reclaim);
@@ -3741,7 +3742,7 @@ void sk_get_meminfo(const struct sock *sk, u32 *mem)
mem[SK_MEMINFO_RCVBUF] = READ_ONCE(sk->sk_rcvbuf);
mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk);
mem[SK_MEMINFO_SNDBUF] = READ_ONCE(sk->sk_sndbuf);
- mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
+ mem[SK_MEMINFO_FWD_ALLOC] = sk_forward_alloc_get(sk);
mem[SK_MEMINFO_WMEM_QUEUED] = READ_ONCE(sk->sk_wmem_queued);
mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len);
diff --git a/net/handshake/netlink.c b/net/handshake/netlink.c
index 1086653e1fad..d0bc1dd8e65a 100644
--- a/net/handshake/netlink.c
+++ b/net/handshake/netlink.c
@@ -157,26 +157,24 @@ int handshake_nl_accept_doit(struct sk_buff *skb, struct genl_info *info)
int handshake_nl_done_doit(struct sk_buff *skb, struct genl_info *info)
{
struct net *net = sock_net(skb->sk);
- struct handshake_req *req = NULL;
- struct socket *sock = NULL;
+ struct handshake_req *req;
+ struct socket *sock;
int fd, status, err;

if (GENL_REQ_ATTR_CHECK(info, HANDSHAKE_A_DONE_SOCKFD))
return -EINVAL;
fd = nla_get_u32(info->attrs[HANDSHAKE_A_DONE_SOCKFD]);

- err = 0;
sock = sockfd_lookup(fd, &err);
- if (err) {
- err = -EBADF;
- goto out_status;
- }
+ if (!sock)
+ return err;

req = handshake_req_hash_lookup(sock->sk);
if (!req) {
err = -EBUSY;
+ trace_handshake_cmd_done_err(net, req, sock->sk, err);
fput(sock->file);
- goto out_status;
+ return err;
}

trace_handshake_cmd_done(net, req, sock->sk, fd);
@@ -188,10 +186,6 @@ int handshake_nl_done_doit(struct sk_buff *skb, struct genl_info *info)
handshake_complete(req, status, info);
fput(sock->file);
return 0;
-
-out_status:
- trace_handshake_cmd_done_err(net, req, sock->sk, err);
- return err;
}

static unsigned int handshake_net_id;
diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c
index 629daacc9607..b71dab630a87 100644
--- a/net/hsr/hsr_forward.c
+++ b/net/hsr/hsr_forward.c
@@ -594,6 +594,7 @@ static int fill_frame_info(struct hsr_frame_info *frame,
proto = vlan_hdr->vlanhdr.h_vlan_encapsulated_proto;
/* FIXME: */
netdev_warn_once(skb->dev, "VLAN not yet supported");
+ return -EINVAL;
}

frame->is_from_san = false;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 5deac0517ef7..37be82496322 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -355,14 +355,14 @@ static void __inet_del_ifa(struct in_device *in_dev,
{
struct in_ifaddr *promote = NULL;
struct in_ifaddr *ifa, *ifa1;
- struct in_ifaddr *last_prim;
+ struct in_ifaddr __rcu **last_prim;
struct in_ifaddr *prev_prom = NULL;
int do_promote = IN_DEV_PROMOTE_SECONDARIES(in_dev);

ASSERT_RTNL();

ifa1 = rtnl_dereference(*ifap);
- last_prim = rtnl_dereference(in_dev->ifa_list);
+ last_prim = ifap;
if (in_dev->dead)
goto no_promotions;

@@ -376,7 +376,7 @@ static void __inet_del_ifa(struct in_device *in_dev,
while ((ifa = rtnl_dereference(*ifap1)) != NULL) {
if (!(ifa->ifa_flags & IFA_F_SECONDARY) &&
ifa1->ifa_scope <= ifa->ifa_scope)
- last_prim = ifa;
+ last_prim = &ifa->ifa_next;

if (!(ifa->ifa_flags & IFA_F_SECONDARY) ||
ifa1->ifa_mask != ifa->ifa_mask ||
@@ -440,9 +440,9 @@ static void __inet_del_ifa(struct in_device *in_dev,

rcu_assign_pointer(prev_prom->ifa_next, next_sec);

- last_sec = rtnl_dereference(last_prim->ifa_next);
+ last_sec = rtnl_dereference(*last_prim);
rcu_assign_pointer(promote->ifa_next, last_sec);
- rcu_assign_pointer(last_prim->ifa_next, promote);
+ rcu_assign_pointer(*last_prim, promote);
}

promote->ifa_flags &= ~IFA_F_SECONDARY;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 65ba18a91865..eafa4a033515 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -278,7 +278,8 @@ void fib_release_info(struct fib_info *fi)
hlist_del(&nexthop_nh->nh_hash);
} endfor_nexthops(fi)
}
- fi->fib_dead = 1;
+ /* Paired with READ_ONCE() from fib_table_lookup() */
+ WRITE_ONCE(fi->fib_dead, 1);
fib_info_put(fi);
}
spin_unlock_bh(&fib_info_lock);
@@ -1581,6 +1582,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
link_it:
ofi = fib_find_info(fi);
if (ofi) {
+ /* fib_table_lookup() should not see @fi yet. */
fi->fib_dead = 1;
free_fib_info(fi);
refcount_inc(&ofi->fib_treeref);
@@ -1619,6 +1621,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg,

failure:
if (fi) {
+ /* fib_table_lookup() should not see @fi yet. */
fi->fib_dead = 1;
free_fib_info(fi);
}
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 74d403dbd2b4..d13fb9e76b97 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1582,7 +1582,8 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp,
if (fa->fa_dscp &&
inet_dscp_to_dsfield(fa->fa_dscp) != flp->flowi4_tos)
continue;
- if (fi->fib_dead)
+ /* Paired with WRITE_ONCE() in fib_release_info() */
+ if (READ_ONCE(fi->fib_dead))
continue;
if (fa->fa_info->fib_scope < flp->flowi4_scope)
continue;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 0819d6001b9a..ae5e786a0598 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -795,41 +795,45 @@ static bool inet_bind2_bucket_match(const struct inet_bind2_bucket *tb,
const struct net *net, unsigned short port,
int l3mdev, const struct sock *sk)
{
+ if (!net_eq(ib2_net(tb), net) || tb->port != port ||
+ tb->l3mdev != l3mdev)
+ return false;
+
#if IS_ENABLED(CONFIG_IPV6)
- if (sk->sk_family != tb->family)
+ if (sk->sk_family != tb->family) {
+ if (sk->sk_family == AF_INET)
+ return ipv6_addr_v4mapped(&tb->v6_rcv_saddr) &&
+ tb->v6_rcv_saddr.s6_addr32[3] == sk->sk_rcv_saddr;
+
return false;
+ }

if (sk->sk_family == AF_INET6)
- return net_eq(ib2_net(tb), net) && tb->port == port &&
- tb->l3mdev == l3mdev &&
- ipv6_addr_equal(&tb->v6_rcv_saddr, &sk->sk_v6_rcv_saddr);
- else
+ return ipv6_addr_equal(&tb->v6_rcv_saddr, &sk->sk_v6_rcv_saddr);
#endif
- return net_eq(ib2_net(tb), net) && tb->port == port &&
- tb->l3mdev == l3mdev && tb->rcv_saddr == sk->sk_rcv_saddr;
+ return tb->rcv_saddr == sk->sk_rcv_saddr;
}

bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const struct net *net,
unsigned short port, int l3mdev, const struct sock *sk)
{
+ if (!net_eq(ib2_net(tb), net) || tb->port != port ||
+ tb->l3mdev != l3mdev)
+ return false;
+
#if IS_ENABLED(CONFIG_IPV6)
if (sk->sk_family != tb->family) {
if (sk->sk_family == AF_INET)
- return net_eq(ib2_net(tb), net) && tb->port == port &&
- tb->l3mdev == l3mdev &&
- ipv6_addr_any(&tb->v6_rcv_saddr);
+ return ipv6_addr_any(&tb->v6_rcv_saddr) ||
+ ipv6_addr_v4mapped_any(&tb->v6_rcv_saddr);

return false;
}

if (sk->sk_family == AF_INET6)
- return net_eq(ib2_net(tb), net) && tb->port == port &&
- tb->l3mdev == l3mdev &&
- ipv6_addr_any(&tb->v6_rcv_saddr);
- else
+ return ipv6_addr_any(&tb->v6_rcv_saddr);
#endif
- return net_eq(ib2_net(tb), net) && tb->port == port &&
- tb->l3mdev == l3mdev && tb->rcv_saddr == 0;
+ return tb->rcv_saddr == 0;
}

/* The socket's bhash2 hashbucket spinlock must be held when this is called */
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index fe9ead9ee863..5e9c8156656a 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -584,7 +584,8 @@ static void ip_sublist_rcv_finish(struct list_head *head)
static struct sk_buff *ip_extract_route_hint(const struct net *net,
struct sk_buff *skb, int rt_type)
{
- if (fib4_has_custom_rules(net) || rt_type == RTN_BROADCAST)
+ if (fib4_has_custom_rules(net) || rt_type == RTN_BROADCAST ||
+ IPCB(skb)->flags & IPSKB_MULTIPATH)
return NULL;

return skb;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index a6e4c82615d7..6935d07a60c3 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -982,7 +982,7 @@ static int __ip_append_data(struct sock *sk,
paged = !!cork->gso_size;

if (cork->tx_flags & SKBTX_ANY_TSTAMP &&
- sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
+ READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID)
tskey = atomic_inc_return(&sk->sk_tskey) - 1;

hh_len = LL_RESERVED_SPACE(rt->dst.dev);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index d41bce8927b2..d7006942fc2f 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -510,7 +510,7 @@ static bool ipv4_datagram_support_cmsg(const struct sock *sk,
* or without payload (SOF_TIMESTAMPING_OPT_TSONLY).
*/
info = PKTINFO_SKB_CB(skb);
- if (!(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_CMSG) ||
+ if (!(READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_CMSG) ||
!info->ipi_ifindex)
return false;

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 92fede388d52..33626619aee7 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2144,6 +2144,7 @@ static int ip_mkroute_input(struct sk_buff *skb,
int h = fib_multipath_hash(res->fi->fib_net, NULL, skb, hkeys);

fib_select_multipath(res, h);
+ IPCB(skb)->flags |= IPSKB_MULTIPATH;
}
#endif

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 8ed52e1e3c99..75f24b931a18 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2256,14 +2256,14 @@ void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
}
}

- if (sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE)
+ if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_SOFTWARE)
has_timestamping = true;
else
tss->ts[0] = (struct timespec64) {0};
}

if (tss->ts[2].tv_sec || tss->ts[2].tv_nsec) {
- if (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE)
+ if (READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_RAW_HARDWARE)
has_timestamping = true;
else
tss->ts[2] = (struct timespec64) {0};
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 51d8638d4b4c..9f9ca68c4702 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3459,7 +3459,7 @@ void sk_forced_mem_schedule(struct sock *sk, int size)
if (delta <= 0)
return;
amt = sk_mem_pages(delta);
- sk->sk_forward_alloc += amt << PAGE_SHIFT;
+ sk_forward_alloc_add(sk, amt << PAGE_SHIFT);
sk_memory_allocated_add(sk, amt);

if (mem_cgroup_sockets_enabled && sk->sk_memcg)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index b3aa68ea29de..4c847baf52d1 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1443,9 +1443,9 @@ static void udp_rmem_release(struct sock *sk, int size, int partial,
spin_lock(&sk_queue->lock);


- sk->sk_forward_alloc += size;
+ sk_forward_alloc_add(sk, size);
amt = (sk->sk_forward_alloc - partial) & ~(PAGE_SIZE - 1);
- sk->sk_forward_alloc -= amt;
+ sk_forward_alloc_add(sk, -amt);

if (amt)
__sk_mem_reduce_allocated(sk, amt >> PAGE_SHIFT);
@@ -1556,7 +1556,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
goto uncharge_drop;
}

- sk->sk_forward_alloc -= size;
+ sk_forward_alloc_add(sk, -size);

/* no need to setup a destructor, we will explicitly release the
* forward allocated memory on dequeue
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 94cec2075eee..c93a2b9a9172 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1368,7 +1368,7 @@ static int ipv6_create_tempaddr(struct inet6_ifaddr *ifp, bool block)
* idev->desync_factor if it's larger
*/
cnf_temp_preferred_lft = READ_ONCE(idev->cnf.temp_prefered_lft);
- max_desync_factor = min_t(__u32,
+ max_desync_factor = min_t(long,
idev->cnf.max_desync_factor,
cnf_temp_preferred_lft - regen_advance);

diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index d94041bb4287..b8378814532c 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -99,7 +99,8 @@ static bool ip6_can_use_hint(const struct sk_buff *skb,
static struct sk_buff *ip6_extract_route_hint(const struct net *net,
struct sk_buff *skb)
{
- if (fib6_routes_require_src(net) || fib6_has_custom_rules(net))
+ if (fib6_routes_require_src(net) || fib6_has_custom_rules(net) ||
+ IP6CB(skb)->flags & IP6SKB_MULTIPATH)
return NULL;

return skb;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 016b0a513259..9270ef7f8e98 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1502,7 +1502,7 @@ static int __ip6_append_data(struct sock *sk,
orig_mtu = mtu;

if (cork->tx_flags & SKBTX_ANY_TSTAMP &&
- sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
+ READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_OPT_ID)
tskey = atomic_inc_return(&sk->sk_tskey) - 1;

hh_len = LL_RESERVED_SPACE(rt->dst.dev);
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 1b2772834972..5831aaa53d75 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -119,7 +119,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
return -EINVAL;

ipcm6_init_sk(&ipc6, np);
- ipc6.sockc.tsflags = sk->sk_tsflags;
+ ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags);
ipc6.sockc.mark = READ_ONCE(sk->sk_mark);

fl6.flowi6_oif = oif;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index ea16734f5e1f..d52d5e34c12a 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -778,7 +778,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
fl6.flowi6_uid = sk->sk_uid;

ipcm6_init(&ipc6);
- ipc6.sockc.tsflags = sk->sk_tsflags;
+ ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags);
ipc6.sockc.mark = fl6.flowi6_mark;

if (sin6) {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 56a55585eb79..a02328c93a53 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -424,6 +424,9 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
if (match->nh && have_oif_match && res->nh)
return;

+ if (skb)
+ IP6CB(skb)->flags |= IP6SKB_MULTIPATH;
+
/* We might have already computed the hash for ICMPv6 errors. In such
* case it will always be non-zero. Otherwise now is the time to do it.
*/
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 3ffca158d3e1..24d3c5c79121 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1368,7 +1368,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)

ipcm6_init(&ipc6);
ipc6.gso_size = READ_ONCE(up->gso_size);
- ipc6.sockc.tsflags = sk->sk_tsflags;
+ ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags);
ipc6.sockc.mark = READ_ONCE(sk->sk_mark);

/* destination address check */
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 393f01b2a7e6..dd1d8ffd5f59 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -930,15 +930,18 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
out_error:
kcm_push(kcm);

- if (copied && sock->type == SOCK_SEQPACKET) {
+ if (sock->type == SOCK_SEQPACKET) {
/* Wrote some bytes before encountering an
* error, return partial success.
*/
- goto partial_message;
- }
-
- if (head != kcm->seq_skb)
+ if (copied)
+ goto partial_message;
+ if (head != kcm->seq_skb)
+ kfree_skb(head);
+ } else {
kfree_skb(head);
+ kcm->seq_skb = NULL;
+ }

err = sk_stream_error(sk, msg->msg_flags, err);

@@ -1859,6 +1862,8 @@ static __net_exit void kcm_exit_net(struct net *net)
* that all multiplexors and psocks have been destroyed.
*/
WARN_ON(!list_empty(&knet->mux_list));
+
+ mutex_destroy(&knet->mutex);
}

static struct pernet_operations kcm_net_ops = {
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 0efc52c640b5..40258d9f8c79 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -136,9 +136,15 @@ static void mptcp_drop(struct sock *sk, struct sk_buff *skb)
__kfree_skb(skb);
}

+static void mptcp_rmem_fwd_alloc_add(struct sock *sk, int size)
+{
+ WRITE_ONCE(mptcp_sk(sk)->rmem_fwd_alloc,
+ mptcp_sk(sk)->rmem_fwd_alloc + size);
+}
+
static void mptcp_rmem_charge(struct sock *sk, int size)
{
- mptcp_sk(sk)->rmem_fwd_alloc -= size;
+ mptcp_rmem_fwd_alloc_add(sk, -size);
}

static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to,
@@ -179,7 +185,7 @@ static bool mptcp_ooo_try_coalesce(struct mptcp_sock *msk, struct sk_buff *to,
static void __mptcp_rmem_reclaim(struct sock *sk, int amount)
{
amount >>= PAGE_SHIFT;
- mptcp_sk(sk)->rmem_fwd_alloc -= amount << PAGE_SHIFT;
+ mptcp_rmem_charge(sk, amount << PAGE_SHIFT);
__sk_mem_reduce_allocated(sk, amount);
}

@@ -188,7 +194,7 @@ static void mptcp_rmem_uncharge(struct sock *sk, int size)
struct mptcp_sock *msk = mptcp_sk(sk);
int reclaimable;

- msk->rmem_fwd_alloc += size;
+ mptcp_rmem_fwd_alloc_add(sk, size);
reclaimable = msk->rmem_fwd_alloc - sk_unused_reserved_mem(sk);

/* see sk_mem_uncharge() for the rationale behind the following schema */
@@ -343,7 +349,7 @@ static bool mptcp_rmem_schedule(struct sock *sk, struct sock *ssk, int size)
if (!__sk_mem_raise_allocated(sk, size, amt, SK_MEM_RECV))
return false;

- msk->rmem_fwd_alloc += amount;
+ mptcp_rmem_fwd_alloc_add(sk, amount);
return true;
}

@@ -1773,7 +1779,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
}

/* data successfully copied into the write queue */
- sk->sk_forward_alloc -= total_ts;
+ sk_forward_alloc_add(sk, -total_ts);
copied += psize;
dfrag->data_len += psize;
frag_truesize += psize;
@@ -3242,8 +3248,8 @@ void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags)
/* move all the rx fwd alloc into the sk_mem_reclaim_final in
* inet_sock_destruct() will dispose it
*/
- sk->sk_forward_alloc += msk->rmem_fwd_alloc;
- msk->rmem_fwd_alloc = 0;
+ sk_forward_alloc_add(sk, msk->rmem_fwd_alloc);
+ WRITE_ONCE(msk->rmem_fwd_alloc, 0);
mptcp_token_destroy(msk);
mptcp_pm_free_anno_list(msk);
mptcp_free_local_addr_list(msk);
@@ -3513,7 +3519,8 @@ static void mptcp_shutdown(struct sock *sk, int how)

static int mptcp_forward_alloc_get(const struct sock *sk)
{
- return sk->sk_forward_alloc + mptcp_sk(sk)->rmem_fwd_alloc;
+ return READ_ONCE(sk->sk_forward_alloc) +
+ READ_ONCE(mptcp_sk(sk)->rmem_fwd_alloc);
}

static int mptcp_ioctl_outq(const struct mptcp_sock *msk, u64 v)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index eb8b1167dced..a72934f00804 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -102,6 +102,7 @@ static const u8 nft2audit_op[NFT_MSG_MAX] = { // enum nf_tables_msg_types
[NFT_MSG_NEWFLOWTABLE] = AUDIT_NFT_OP_FLOWTABLE_REGISTER,
[NFT_MSG_GETFLOWTABLE] = AUDIT_NFT_OP_INVALID,
[NFT_MSG_DELFLOWTABLE] = AUDIT_NFT_OP_FLOWTABLE_UNREGISTER,
+ [NFT_MSG_GETSETELEM_RESET] = AUDIT_NFT_OP_SETELEM_RESET,
};

static void nft_validate_state_update(struct nft_table *table, u8 new_validate_state)
@@ -3421,6 +3422,18 @@ static void nf_tables_rule_notify(const struct nft_ctx *ctx,
nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS);
}

+static void audit_log_rule_reset(const struct nft_table *table,
+ unsigned int base_seq,
+ unsigned int nentries)
+{
+ char *buf = kasprintf(GFP_ATOMIC, "%s:%u",
+ table->name, base_seq);
+
+ audit_log_nfcfg(buf, table->family, nentries,
+ AUDIT_NFT_OP_RULE_RESET, GFP_ATOMIC);
+ kfree(buf);
+}
+
struct nft_rule_dump_ctx {
char *table;
char *chain;
@@ -3467,6 +3480,10 @@ static int __nf_tables_dump_rules(struct sk_buff *skb,
cont_skip:
(*idx)++;
}
+
+ if (reset && *idx)
+ audit_log_rule_reset(table, cb->seq, *idx);
+
return 0;
}

@@ -3634,6 +3651,9 @@ static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info,
if (err < 0)
goto err_fill_rule_info;

+ if (reset)
+ audit_log_rule_reset(table, nft_pernet(net)->base_seq, 1);
+
return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid);

err_fill_rule_info:
@@ -5621,13 +5641,25 @@ static int nf_tables_dump_setelem(const struct nft_ctx *ctx,
return nf_tables_fill_setelem(args->skb, set, elem, args->reset);
}

+static void audit_log_nft_set_reset(const struct nft_table *table,
+ unsigned int base_seq,
+ unsigned int nentries)
+{
+ char *buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, base_seq);
+
+ audit_log_nfcfg(buf, table->family, nentries,
+ AUDIT_NFT_OP_SETELEM_RESET, GFP_ATOMIC);
+ kfree(buf);
+}
+
struct nft_set_dump_ctx {
const struct nft_set *set;
struct nft_ctx ctx;
};

static int nft_set_catchall_dump(struct net *net, struct sk_buff *skb,
- const struct nft_set *set, bool reset)
+ const struct nft_set *set, bool reset,
+ unsigned int base_seq)
{
struct nft_set_elem_catchall *catchall;
u8 genmask = nft_genmask_cur(net);
@@ -5643,6 +5675,8 @@ static int nft_set_catchall_dump(struct net *net, struct sk_buff *skb,

elem.priv = catchall->elem;
ret = nf_tables_fill_setelem(skb, set, &elem, reset);
+ if (reset && !ret)
+ audit_log_nft_set_reset(set->table, base_seq, 1);
break;
}

@@ -5722,12 +5756,17 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
set->ops->walk(&dump_ctx->ctx, set, &args.iter);

if (!args.iter.err && args.iter.count == cb->args[0])
- args.iter.err = nft_set_catchall_dump(net, skb, set, reset);
- rcu_read_unlock();
-
+ args.iter.err = nft_set_catchall_dump(net, skb, set,
+ reset, cb->seq);
nla_nest_end(skb, nest);
nlmsg_end(skb, nlh);

+ if (reset && args.iter.count > args.iter.skip)
+ audit_log_nft_set_reset(table, cb->seq,
+ args.iter.count - args.iter.skip);
+
+ rcu_read_unlock();
+
if (args.iter.err && args.iter.err != -EMSGSIZE)
return args.iter.err;
if (args.iter.count == cb->args[0])
@@ -5952,13 +5991,13 @@ static int nf_tables_getsetelem(struct sk_buff *skb,
struct netlink_ext_ack *extack = info->extack;
u8 genmask = nft_genmask_cur(info->net);
u8 family = info->nfmsg->nfgen_family;
+ int rem, err = 0, nelems = 0;
struct net *net = info->net;
struct nft_table *table;
struct nft_set *set;
struct nlattr *attr;
struct nft_ctx ctx;
bool reset = false;
- int rem, err = 0;

table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family,
genmask, 0);
@@ -6001,8 +6040,13 @@ static int nf_tables_getsetelem(struct sk_buff *skb,
NL_SET_BAD_ATTR(extack, attr);
break;
}
+ nelems++;
}

+ if (reset)
+ audit_log_nft_set_reset(table, nft_pernet(net)->base_seq,
+ nelems);
+
return err;
}

diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c
index 8f1bfa6ccc2d..50723ba08289 100644
--- a/net/netfilter/nfnetlink_osf.c
+++ b/net/netfilter/nfnetlink_osf.c
@@ -315,6 +315,14 @@ static int nfnl_osf_add_callback(struct sk_buff *skb,

f = nla_data(osf_attrs[OSF_ATTR_FINGER]);

+ if (f->opt_num > ARRAY_SIZE(f->opt))
+ return -EINVAL;
+
+ if (!memchr(f->genre, 0, MAXGENRELEN) ||
+ !memchr(f->subtype, 0, MAXGENRELEN) ||
+ !memchr(f->version, 0, MAXGENRELEN))
+ return -EINVAL;
+
kf = kmalloc(sizeof(struct nf_osf_finger), GFP_KERNEL);
if (!kf)
return -ENOMEM;
diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index a9844eefedeb..3fbaa7bf41f9 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -35,6 +35,14 @@ static unsigned int optlen(const u8 *opt, unsigned int offset)
return opt[offset + 1];
}

+static int nft_skb_copy_to_reg(const struct sk_buff *skb, int offset, u32 *dest, unsigned int len)
+{
+ if (len % NFT_REG32_SIZE)
+ dest[len / NFT_REG32_SIZE] = 0;
+
+ return skb_copy_bits(skb, offset, dest, len);
+}
+
static void nft_exthdr_ipv6_eval(const struct nft_expr *expr,
struct nft_regs *regs,
const struct nft_pktinfo *pkt)
@@ -56,8 +64,7 @@ static void nft_exthdr_ipv6_eval(const struct nft_expr *expr,
}
offset += priv->offset;

- dest[priv->len / NFT_REG32_SIZE] = 0;
- if (skb_copy_bits(pkt->skb, offset, dest, priv->len) < 0)
+ if (nft_skb_copy_to_reg(pkt->skb, offset, dest, priv->len) < 0)
goto err;
return;
err:
@@ -153,8 +160,7 @@ static void nft_exthdr_ipv4_eval(const struct nft_expr *expr,
}
offset += priv->offset;

- dest[priv->len / NFT_REG32_SIZE] = 0;
- if (skb_copy_bits(pkt->skb, offset, dest, priv->len) < 0)
+ if (nft_skb_copy_to_reg(pkt->skb, offset, dest, priv->len) < 0)
goto err;
return;
err:
@@ -210,7 +216,8 @@ static void nft_exthdr_tcp_eval(const struct nft_expr *expr,
if (priv->flags & NFT_EXTHDR_F_PRESENT) {
*dest = 1;
} else {
- dest[priv->len / NFT_REG32_SIZE] = 0;
+ if (priv->len % NFT_REG32_SIZE)
+ dest[priv->len / NFT_REG32_SIZE] = 0;
memcpy(dest, opt + offset, priv->len);
}

@@ -388,9 +395,8 @@ static void nft_exthdr_sctp_eval(const struct nft_expr *expr,
offset + ntohs(sch->length) > pkt->skb->len)
break;

- dest[priv->len / NFT_REG32_SIZE] = 0;
- if (skb_copy_bits(pkt->skb, offset + priv->offset,
- dest, priv->len) < 0)
+ if (nft_skb_copy_to_reg(pkt->skb, offset + priv->offset,
+ dest, priv->len) < 0)
break;
return;
}
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index c6435e709231..f250b5399344 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -312,6 +312,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL;
struct rb_node *node, *next, *parent, **p, *first = NULL;
struct nft_rbtree *priv = nft_set_priv(set);
+ u8 cur_genmask = nft_genmask_cur(net);
u8 genmask = nft_genmask_next(net);
int d, err;

@@ -357,8 +358,11 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
if (!nft_set_elem_active(&rbe->ext, genmask))
continue;

- /* perform garbage collection to avoid bogus overlap reports. */
- if (nft_set_elem_expired(&rbe->ext)) {
+ /* perform garbage collection to avoid bogus overlap reports
+ * but skip new elements in this transaction.
+ */
+ if (nft_set_elem_expired(&rbe->ext) &&
+ nft_set_elem_active(&rbe->ext, cur_genmask)) {
err = nft_rbtree_gc_elem(set, priv, rbe, genmask);
if (err < 0)
return err;
diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c
index 591d87d5e5c0..68e6acd0f130 100644
--- a/net/sched/sch_fq_pie.c
+++ b/net/sched/sch_fq_pie.c
@@ -61,6 +61,7 @@ struct fq_pie_sched_data {
struct pie_params p_params;
u32 ecn_prob;
u32 flows_cnt;
+ u32 flows_cursor;
u32 quantum;
u32 memory_limit;
u32 new_flow_count;
@@ -375,22 +376,32 @@ static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt,
static void fq_pie_timer(struct timer_list *t)
{
struct fq_pie_sched_data *q = from_timer(q, t, adapt_timer);
+ unsigned long next, tupdate;
struct Qdisc *sch = q->sch;
spinlock_t *root_lock; /* to lock qdisc for probability calculations */
- u32 idx;
+ int max_cnt, i;

rcu_read_lock();
root_lock = qdisc_lock(qdisc_root_sleeping(sch));
spin_lock(root_lock);

- for (idx = 0; idx < q->flows_cnt; idx++)
- pie_calculate_probability(&q->p_params, &q->flows[idx].vars,
- q->flows[idx].backlog);
-
- /* reset the timer to fire after 'tupdate' jiffies. */
- if (q->p_params.tupdate)
- mod_timer(&q->adapt_timer, jiffies + q->p_params.tupdate);
+ /* Limit this expensive loop to 2048 flows per round. */
+ max_cnt = min_t(int, q->flows_cnt - q->flows_cursor, 2048);
+ for (i = 0; i < max_cnt; i++) {
+ pie_calculate_probability(&q->p_params,
+ &q->flows[q->flows_cursor].vars,
+ q->flows[q->flows_cursor].backlog);
+ q->flows_cursor++;
+ }

+ tupdate = q->p_params.tupdate;
+ next = 0;
+ if (q->flows_cursor >= q->flows_cnt) {
+ q->flows_cursor = 0;
+ next = tupdate;
+ }
+ if (tupdate)
+ mod_timer(&q->adapt_timer, jiffies + next);
spin_unlock(root_lock);
rcu_read_unlock();
}
diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c
index ea8c4a7174bb..35f49edf63db 100644
--- a/net/sched/sch_plug.c
+++ b/net/sched/sch_plug.c
@@ -207,7 +207,7 @@ static struct Qdisc_ops plug_qdisc_ops __read_mostly = {
.priv_size = sizeof(struct plug_sched_data),
.enqueue = plug_enqueue,
.dequeue = plug_dequeue,
- .peek = qdisc_peek_head,
+ .peek = qdisc_peek_dequeued,
.init = plug_init,
.change = plug_change,
.reset = qdisc_reset_queue,
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index befaf74b33ca..09d2955baab1 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -974,10 +974,13 @@ static void qfq_update_eligible(struct qfq_sched *q)
}

/* Dequeue head packet of the head class in the DRR queue of the aggregate. */
-static void agg_dequeue(struct qfq_aggregate *agg,
- struct qfq_class *cl, unsigned int len)
+static struct sk_buff *agg_dequeue(struct qfq_aggregate *agg,
+ struct qfq_class *cl, unsigned int len)
{
- qdisc_dequeue_peeked(cl->qdisc);
+ struct sk_buff *skb = qdisc_dequeue_peeked(cl->qdisc);
+
+ if (!skb)
+ return NULL;

cl->deficit -= (int) len;

@@ -987,6 +990,8 @@ static void agg_dequeue(struct qfq_aggregate *agg,
cl->deficit += agg->lmax;
list_move_tail(&cl->alist, &agg->active);
}
+
+ return skb;
}

static inline struct sk_buff *qfq_peek_skb(struct qfq_aggregate *agg,
@@ -1132,11 +1137,18 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch)
if (!skb)
return NULL;

- qdisc_qstats_backlog_dec(sch, skb);
sch->q.qlen--;
+
+ skb = agg_dequeue(in_serv_agg, cl, len);
+
+ if (!skb) {
+ sch->q.qlen++;
+ return NULL;
+ }
+
+ qdisc_qstats_backlog_dec(sch, skb);
qdisc_bstats_update(sch, skb);

- agg_dequeue(in_serv_agg, cl, len);
/* If lmax is lowered, through qfq_change_class, for a class
* owning pending packets with larger size than the new value
* of lmax, then the following condition may hold.
diff --git a/net/sctp/proc.c b/net/sctp/proc.c
index f13d6a34f32f..ec00ee75d59a 100644
--- a/net/sctp/proc.c
+++ b/net/sctp/proc.c
@@ -282,7 +282,7 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v)
assoc->init_retries, assoc->shutdown_retries,
assoc->rtx_data_chunks,
refcount_read(&sk->sk_wmem_alloc),
- sk->sk_wmem_queued,
+ READ_ONCE(sk->sk_wmem_queued),
sk->sk_sndbuf,
sk->sk_rcvbuf);
seq_printf(seq, "\n");
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 423dc400992b..7cf207706eb6 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -69,7 +69,7 @@
#include <net/sctp/stream_sched.h>

/* Forward declarations for internal helper functions. */
-static bool sctp_writeable(struct sock *sk);
+static bool sctp_writeable(const struct sock *sk);
static void sctp_wfree(struct sk_buff *skb);
static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p,
size_t msg_len);
@@ -140,7 +140,7 @@ static inline void sctp_set_owner_w(struct sctp_chunk *chunk)

refcount_add(sizeof(struct sctp_chunk), &sk->sk_wmem_alloc);
asoc->sndbuf_used += chunk->skb->truesize + sizeof(struct sctp_chunk);
- sk->sk_wmem_queued += chunk->skb->truesize + sizeof(struct sctp_chunk);
+ sk_wmem_queued_add(sk, chunk->skb->truesize + sizeof(struct sctp_chunk));
sk_mem_charge(sk, chunk->skb->truesize);
}

@@ -9144,7 +9144,7 @@ static void sctp_wfree(struct sk_buff *skb)
struct sock *sk = asoc->base.sk;

sk_mem_uncharge(sk, skb->truesize);
- sk->sk_wmem_queued -= skb->truesize + sizeof(struct sctp_chunk);
+ sk_wmem_queued_add(sk, -(skb->truesize + sizeof(struct sctp_chunk)));
asoc->sndbuf_used -= skb->truesize + sizeof(struct sctp_chunk);
WARN_ON(refcount_sub_and_test(sizeof(struct sctp_chunk),
&sk->sk_wmem_alloc));
@@ -9299,9 +9299,9 @@ void sctp_write_space(struct sock *sk)
* UDP-style sockets or TCP-style sockets, this code should work.
* - Daisy
*/
-static bool sctp_writeable(struct sock *sk)
+static bool sctp_writeable(const struct sock *sk)
{
- return sk->sk_sndbuf > sk->sk_wmem_queued;
+ return READ_ONCE(sk->sk_sndbuf) > READ_ONCE(sk->sk_wmem_queued);
}

/* Wait for an association to go into ESTABLISHED state. If timeout is 0,
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 6b78075404d7..3e89bb9b7c56 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1654,6 +1654,7 @@ void smcr_port_add(struct smc_ib_device *smcibdev, u8 ibport)
{
struct smc_link_group *lgr, *n;

+ spin_lock_bh(&smc_lgr_list.lock);
list_for_each_entry_safe(lgr, n, &smc_lgr_list.list, list) {
struct smc_link *link;

@@ -1669,6 +1670,7 @@ void smcr_port_add(struct smc_ib_device *smcibdev, u8 ibport)
if (link)
smc_llc_add_link_local(link);
}
+ spin_unlock_bh(&smc_lgr_list.lock);
}

/* link is down - switch connections to alternate link,
diff --git a/net/socket.c b/net/socket.c
index f49edb9b4918..b5639a650015 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -821,7 +821,7 @@ static bool skb_is_swtx_tstamp(const struct sk_buff *skb, int false_tstamp)

static ktime_t get_timestamp(struct sock *sk, struct sk_buff *skb, int *if_index)
{
- bool cycles = sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC;
+ bool cycles = READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_BIND_PHC;
struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb);
struct net_device *orig_dev;
ktime_t hwtstamp;
@@ -873,12 +873,12 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
int need_software_tstamp = sock_flag(sk, SOCK_RCVTSTAMP);
int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW);
struct scm_timestamping_internal tss;
-
int empty = 1, false_tstamp = 0;
struct skb_shared_hwtstamps *shhwtstamps =
skb_hwtstamps(skb);
int if_index;
ktime_t hwtstamp;
+ u32 tsflags;

/* Race occurred between timestamp enabling and packet
receiving. Fill in the current time for now. */
@@ -920,11 +920,12 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
}

memset(&tss, 0, sizeof(tss));
- if ((sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) &&
+ tsflags = READ_ONCE(sk->sk_tsflags);
+ if ((tsflags & SOF_TIMESTAMPING_SOFTWARE) &&
ktime_to_timespec64_cond(skb->tstamp, tss.ts + 0))
empty = 0;
if (shhwtstamps &&
- (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) &&
+ (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) &&
!skb_is_swtx_tstamp(skb, false_tstamp)) {
if_index = 0;
if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_NETDEV)
@@ -932,14 +933,14 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
else
hwtstamp = shhwtstamps->hwtstamp;

- if (sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC)
+ if (tsflags & SOF_TIMESTAMPING_BIND_PHC)
hwtstamp = ptp_convert_timestamp(&hwtstamp,
- sk->sk_bind_phc);
+ READ_ONCE(sk->sk_bind_phc));

if (ktime_to_timespec64_cond(hwtstamp, tss.ts + 2)) {
empty = 0;

- if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) &&
+ if ((tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) &&
!skb_is_err_queue(skb))
put_ts_pktinfo(msg, skb, if_index);
}
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 53f944e6d8ef..e047abc60089 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -817,7 +817,7 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,
psock = sk_psock_get(sk);
if (!psock || !policy) {
err = tls_push_record(sk, flags, record_type);
- if (err && sk->sk_err == EBADMSG) {
+ if (err && err != -EINPROGRESS && sk->sk_err == EBADMSG) {
*copied -= sk_msg_free(sk, msg);
tls_free_open_rec(sk);
err = -sk->sk_err;
@@ -846,7 +846,7 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk,
switch (psock->eval) {
case __SK_PASS:
err = tls_push_record(sk, flags, record_type);
- if (err && sk->sk_err == EBADMSG) {
+ if (err && err != -EINPROGRESS && sk->sk_err == EBADMSG) {
*copied -= sk_msg_free(sk, msg);
tls_free_open_rec(sk);
err = -sk->sk_err;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 86930a8ed012..3e8a04a13668 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -680,7 +680,7 @@ static void unix_release_sock(struct sock *sk, int embrion)
* What the above comment does talk about? --ANK(980817)
*/

- if (unix_tot_inflight)
+ if (READ_ONCE(unix_tot_inflight))
unix_gc(); /* Garbage collect fds */
}

diff --git a/net/unix/scm.c b/net/unix/scm.c
index f9152881d77f..033e21e5c4df 100644
--- a/net/unix/scm.c
+++ b/net/unix/scm.c
@@ -63,7 +63,7 @@ void unix_inflight(struct user_struct *user, struct file *fp)
/* Paired with READ_ONCE() in wait_for_unix_gc() */
WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + 1);
}
- user->unix_inflight++;
+ WRITE_ONCE(user->unix_inflight, user->unix_inflight + 1);
spin_unlock(&unix_gc_lock);
}

@@ -84,7 +84,7 @@ void unix_notinflight(struct user_struct *user, struct file *fp)
/* Paired with READ_ONCE() in wait_for_unix_gc() */
WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - 1);
}
- user->unix_inflight--;
+ WRITE_ONCE(user->unix_inflight, user->unix_inflight - 1);
spin_unlock(&unix_gc_lock);
}

@@ -98,7 +98,7 @@ static inline bool too_many_unix_fds(struct task_struct *p)
{
struct user_struct *user = current_user();

- if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE)))
+ if (unlikely(READ_ONCE(user->unix_inflight) > task_rlimit(p, RLIMIT_NOFILE)))
return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN);
return false;
}
diff --git a/net/xdp/xsk_diag.c b/net/xdp/xsk_diag.c
index c014217f5fa7..22b36c8143cf 100644
--- a/net/xdp/xsk_diag.c
+++ b/net/xdp/xsk_diag.c
@@ -111,6 +111,9 @@ static int xsk_diag_fill(struct sock *sk, struct sk_buff *nlskb,
sock_diag_save_cookie(sk, msg->xdiag_cookie);

mutex_lock(&xs->mutex);
+ if (READ_ONCE(xs->state) == XSK_UNBOUND)
+ goto out_nlmsg_trim;
+
if ((req->xdiag_show & XDP_SHOW_INFO) && xsk_diag_put_info(xs, nlskb))
goto out_nlmsg_trim;

diff --git a/scripts/dummy-tools/gcc b/scripts/dummy-tools/gcc
index 1db1889f6d81..07f6dc4c5cf6 100755
--- a/scripts/dummy-tools/gcc
+++ b/scripts/dummy-tools/gcc
@@ -85,8 +85,7 @@ if arg_contain -S "$@"; then
fi

# For arch/powerpc/tools/gcc-check-mprofile-kernel.sh
- if arg_contain -m64 "$@" && arg_contain -mlittle-endian "$@" &&
- arg_contain -mprofile-kernel "$@"; then
+ if arg_contain -m64 "$@" && arg_contain -mprofile-kernel "$@"; then
if ! test -t 0 && ! grep -q notrace; then
echo "_mcount"
fi
diff --git a/scripts/kconfig/preprocess.c b/scripts/kconfig/preprocess.c
index 748da578b418..d1f5bcff4b62 100644
--- a/scripts/kconfig/preprocess.c
+++ b/scripts/kconfig/preprocess.c
@@ -396,6 +396,9 @@ static char *eval_clause(const char *str, size_t len, int argc, char *argv[])

p++;
}
+
+ if (new_argc >= FUNCTION_MAX_ARGS)
+ pperror("too many function arguments");
new_argv[new_argc++] = prev;

/*
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index b29b29707f10..ba981f22908a 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -1226,6 +1226,15 @@ static void check_export_symbol(struct module *mod, struct elf_info *elf,
*/
s->is_func = (ELF_ST_TYPE(sym->st_info) == STT_FUNC);

+ /*
+ * For parisc64, symbols prefixed $$ from the library have the symbol type
+ * STT_LOPROC. They should be handled as functions too.
+ */
+ if (elf->hdr->e_ident[EI_CLASS] == ELFCLASS64 &&
+ elf->hdr->e_machine == EM_PARISC &&
+ ELF_ST_TYPE(sym->st_info) == STT_LOPROC)
+ s->is_func = true;
+
if (match(secname, PATTERNS(INIT_SECTIONS)))
warn("%s: %s: EXPORT_SYMBOL used for init symbol. Remove __init or EXPORT_SYMBOL.\n",
mod->name, name);
diff --git a/scripts/package/mkspec b/scripts/package/mkspec
index 8049f0e2c110..c9299f9c1f3e 100755
--- a/scripts/package/mkspec
+++ b/scripts/package/mkspec
@@ -57,7 +57,7 @@ $S BuildRequires: gcc make openssl openssl-devel perl python3 rsync

# $UTS_MACHINE as a fallback of _arch in case
# /usr/lib/rpm/platform/*/macros was not included.
- %define _arch %{?_arch:$UTS_MACHINE}
+ %{!?_arch: %define _arch $UTS_MACHINE}
%define __spec_install_post /usr/lib/rpm/brp-compress || :
%define debug_package %{nil}

diff --git a/sound/soc/tegra/tegra210_sfc.c b/sound/soc/tegra/tegra210_sfc.c
index e9df1ffc8a58..c2240babd601 100644
--- a/sound/soc/tegra/tegra210_sfc.c
+++ b/sound/soc/tegra/tegra210_sfc.c
@@ -2,7 +2,7 @@
//
// tegra210_sfc.c - Tegra210 SFC driver
//
-// Copyright (c) 2021 NVIDIA CORPORATION. All rights reserved.
+// Copyright (c) 2021-2023 NVIDIA CORPORATION. All rights reserved.

#include <linux/clk.h>
#include <linux/device.h>
@@ -42,6 +42,7 @@ static const int tegra210_sfc_rates[TEGRA210_SFC_NUM_RATES] = {
32000,
44100,
48000,
+ 64000,
88200,
96000,
176400,
@@ -2857,6 +2858,7 @@ static s32 *coef_addr_table[TEGRA210_SFC_NUM_RATES][TEGRA210_SFC_NUM_RATES] = {
coef_8to32,
coef_8to44,
coef_8to48,
+ UNSUPP_CONV,
coef_8to88,
coef_8to96,
UNSUPP_CONV,
@@ -2872,6 +2874,7 @@ static s32 *coef_addr_table[TEGRA210_SFC_NUM_RATES][TEGRA210_SFC_NUM_RATES] = {
coef_11to32,
coef_11to44,
coef_11to48,
+ UNSUPP_CONV,
coef_11to88,
coef_11to96,
UNSUPP_CONV,
@@ -2887,6 +2890,7 @@ static s32 *coef_addr_table[TEGRA210_SFC_NUM_RATES][TEGRA210_SFC_NUM_RATES] = {
coef_16to32,
coef_16to44,
coef_16to48,
+ UNSUPP_CONV,
coef_16to88,
coef_16to96,
coef_16to176,
@@ -2902,6 +2906,7 @@ static s32 *coef_addr_table[TEGRA210_SFC_NUM_RATES][TEGRA210_SFC_NUM_RATES] = {
coef_22to32,
coef_22to44,
coef_22to48,
+ UNSUPP_CONV,
coef_22to88,
coef_22to96,
coef_22to176,
@@ -2917,6 +2922,7 @@ static s32 *coef_addr_table[TEGRA210_SFC_NUM_RATES][TEGRA210_SFC_NUM_RATES] = {
coef_24to32,
coef_24to44,
coef_24to48,
+ UNSUPP_CONV,
coef_24to88,
coef_24to96,
coef_24to176,
@@ -2932,6 +2938,7 @@ static s32 *coef_addr_table[TEGRA210_SFC_NUM_RATES][TEGRA210_SFC_NUM_RATES] = {
BYPASS_CONV,
coef_32to44,
coef_32to48,
+ UNSUPP_CONV,
coef_32to88,
coef_32to96,
coef_32to176,
@@ -2947,6 +2954,7 @@ static s32 *coef_addr_table[TEGRA210_SFC_NUM_RATES][TEGRA210_SFC_NUM_RATES] = {
coef_44to32,
BYPASS_CONV,
coef_44to48,
+ UNSUPP_CONV,
coef_44to88,
coef_44to96,
coef_44to176,
@@ -2962,11 +2970,28 @@ static s32 *coef_addr_table[TEGRA210_SFC_NUM_RATES][TEGRA210_SFC_NUM_RATES] = {
coef_48to32,
coef_48to44,
BYPASS_CONV,
+ UNSUPP_CONV,
coef_48to88,
coef_48to96,
coef_48to176,
coef_48to192,
},
+ /* Convertions from 64 kHz */
+ {
+ UNSUPP_CONV,
+ UNSUPP_CONV,
+ UNSUPP_CONV,
+ UNSUPP_CONV,
+ UNSUPP_CONV,
+ UNSUPP_CONV,
+ UNSUPP_CONV,
+ UNSUPP_CONV,
+ UNSUPP_CONV,
+ UNSUPP_CONV,
+ UNSUPP_CONV,
+ UNSUPP_CONV,
+ UNSUPP_CONV,
+ },
/* Convertions from 88.2 kHz */
{
coef_88to8,
@@ -2977,6 +3002,7 @@ static s32 *coef_addr_table[TEGRA210_SFC_NUM_RATES][TEGRA210_SFC_NUM_RATES] = {
coef_88to32,
coef_88to44,
coef_88to48,
+ UNSUPP_CONV,
BYPASS_CONV,
coef_88to96,
coef_88to176,
@@ -2991,6 +3017,7 @@ static s32 *coef_addr_table[TEGRA210_SFC_NUM_RATES][TEGRA210_SFC_NUM_RATES] = {
coef_96to32,
coef_96to44,
coef_96to48,
+ UNSUPP_CONV,
coef_96to88,
BYPASS_CONV,
coef_96to176,
@@ -3006,6 +3033,7 @@ static s32 *coef_addr_table[TEGRA210_SFC_NUM_RATES][TEGRA210_SFC_NUM_RATES] = {
coef_176to32,
coef_176to44,
coef_176to48,
+ UNSUPP_CONV,
coef_176to88,
coef_176to96,
BYPASS_CONV,
@@ -3021,6 +3049,7 @@ static s32 *coef_addr_table[TEGRA210_SFC_NUM_RATES][TEGRA210_SFC_NUM_RATES] = {
coef_192to32,
coef_192to44,
coef_192to48,
+ UNSUPP_CONV,
coef_192to88,
coef_192to96,
coef_192to176,
diff --git a/sound/soc/tegra/tegra210_sfc.h b/sound/soc/tegra/tegra210_sfc.h
index 5a6b66e297d8..a4c993d79403 100644
--- a/sound/soc/tegra/tegra210_sfc.h
+++ b/sound/soc/tegra/tegra210_sfc.h
@@ -2,7 +2,7 @@
/*
* tegra210_sfc.h - Definitions for Tegra210 SFC driver
*
- * Copyright (c) 2021 NVIDIA CORPORATION. All rights reserved.
+ * Copyright (c) 2021-2023 NVIDIA CORPORATION. All rights reserved.
*
*/

@@ -47,7 +47,7 @@
#define TEGRA210_SFC_EN_SHIFT 0
#define TEGRA210_SFC_EN (1 << TEGRA210_SFC_EN_SHIFT)

-#define TEGRA210_SFC_NUM_RATES 12
+#define TEGRA210_SFC_NUM_RATES 13

/* Fields in TEGRA210_SFC_COEF_RAM */
#define TEGRA210_SFC_COEF_RAM_EN BIT(0)
diff --git a/tools/build/Makefile.build b/tools/build/Makefile.build
index 89430338a3d9..fac42486a8cf 100644
--- a/tools/build/Makefile.build
+++ b/tools/build/Makefile.build
@@ -117,6 +117,16 @@ $(OUTPUT)%.s: %.c FORCE
$(call rule_mkdir)
$(call if_changed_dep,cc_s_c)

+# bison and flex files are generated in the OUTPUT directory
+# so it needs a separate rule to depend on them properly
+$(OUTPUT)%-bison.o: $(OUTPUT)%-bison.c FORCE
+ $(call rule_mkdir)
+ $(call if_changed_dep,$(host)cc_o_c)
+
+$(OUTPUT)%-flex.o: $(OUTPUT)%-flex.c FORCE
+ $(call rule_mkdir)
+ $(call if_changed_dep,$(host)cc_o_c)
+
# Gather build data:
# obj-y - list of build objects
# subdir-y - list of directories to nest
diff --git a/tools/mm/Makefile b/tools/mm/Makefile
index 6c1da51f4177..1c5606cc3334 100644
--- a/tools/mm/Makefile
+++ b/tools/mm/Makefile
@@ -8,8 +8,8 @@ TARGETS=page-types slabinfo page_owner_sort
LIB_DIR = ../lib/api
LIBS = $(LIB_DIR)/libapi.a

-CFLAGS += -Wall -Wextra -I../lib/
-LDFLAGS += $(LIBS)
+CFLAGS += -Wall -Wextra -I../lib/ -pthread
+LDFLAGS += $(LIBS) -pthread

all: $(TARGETS)

diff --git a/tools/perf/Documentation/perf-dlfilter.txt b/tools/perf/Documentation/perf-dlfilter.txt
index fb22e3b31dc5..8887cc20a809 100644
--- a/tools/perf/Documentation/perf-dlfilter.txt
+++ b/tools/perf/Documentation/perf-dlfilter.txt
@@ -64,6 +64,12 @@ internal filtering.
If implemented, 'filter_description' should return a one-line description
of the filter, and optionally a longer description.

+Do not assume the 'sample' argument is valid (dereferenceable)
+after 'filter_event' and 'filter_event_early' return.
+
+Do not assume data referenced by pointers in struct perf_dlfilter_sample
+is valid (dereferenceable) after 'filter_event' and 'filter_event_early' return.
+
The perf_dlfilter_sample structure
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

@@ -150,7 +156,8 @@ struct perf_dlfilter_fns {
const char *(*srcline)(void *ctx, __u32 *line_number);
struct perf_event_attr *(*attr)(void *ctx);
__s32 (*object_code)(void *ctx, __u64 ip, void *buf, __u32 len);
- void *(*reserved[120])(void *);
+ void (*al_cleanup)(void *ctx, struct perf_dlfilter_al *al);
+ void *(*reserved[119])(void *);
};
----

@@ -161,7 +168,8 @@ struct perf_dlfilter_fns {
'args' returns arguments from --dlarg options.

'resolve_address' provides information about 'address'. al->size must be set
-before calling. Returns 0 on success, -1 otherwise.
+before calling. Returns 0 on success, -1 otherwise. Call al_cleanup() (if present,
+see below) when 'al' data is no longer needed.

'insn' returns instruction bytes and length.

@@ -171,6 +179,12 @@ before calling. Returns 0 on success, -1 otherwise.

'object_code' reads object code and returns the number of bytes read.

+'al_cleanup' must be called (if present, so check perf_dlfilter_fns.al_cleanup != NULL)
+after resolve_address() to free any associated resources.
+
+Do not assume pointers obtained via perf_dlfilter_fns are valid (dereferenceable)
+after 'filter_event' and 'filter_event_early' return.
+
The perf_dlfilter_al structure
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

@@ -197,9 +211,13 @@ struct perf_dlfilter_al {
/* Below members are only populated by resolve_ip() */
__u8 filtered; /* true if this sample event will be filtered out */
const char *comm;
+ void *priv; /* Private data. Do not change */
};
----

+Do not assume data referenced by pointers in struct perf_dlfilter_al
+is valid (dereferenceable) after 'filter_event' and 'filter_event_early' return.
+
perf_dlfilter_sample flags
~~~~~~~~~~~~~~~~~~~~~~~~~~

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 097316ef38e6..f178b36c6940 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -381,7 +381,7 @@ ifndef NO_JVMTI
PROGRAMS += $(OUTPUT)$(LIBJVMTI)
endif

-DLFILTERS := dlfilter-test-api-v0.so dlfilter-show-cycles.so
+DLFILTERS := dlfilter-test-api-v0.so dlfilter-test-api-v2.so dlfilter-show-cycles.so
DLFILTERS := $(patsubst %,$(OUTPUT)dlfilters/%,$(DLFILTERS))

# what 'all' will build and 'install' will install, in perfexecdir
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index c15386cb1033..0cf1c5a2e032 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -2052,6 +2052,7 @@ static int __cmd_contention(int argc, const char **argv)
if (IS_ERR(session)) {
pr_err("Initializing perf session failed\n");
err = PTR_ERR(session);
+ session = NULL;
goto out_delete;
}

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 200b3e7ea8da..517bf25750c8 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2199,6 +2199,17 @@ static void process_event(struct perf_script *script,
if (PRINT_FIELD(RETIRE_LAT))
fprintf(fp, "%16" PRIu16, sample->retire_lat);

+ if (PRINT_FIELD(CGROUP)) {
+ const char *cgrp_name;
+ struct cgroup *cgrp = cgroup__find(machine->env,
+ sample->cgroup);
+ if (cgrp != NULL)
+ cgrp_name = cgrp->name;
+ else
+ cgrp_name = "unknown";
+ fprintf(fp, " %s", cgrp_name);
+ }
+
if (PRINT_FIELD(IP)) {
struct callchain_cursor *cursor = NULL;

@@ -2243,17 +2254,6 @@ static void process_event(struct perf_script *script,
if (PRINT_FIELD(CODE_PAGE_SIZE))
fprintf(fp, " %s", get_page_size_name(sample->code_page_size, str));

- if (PRINT_FIELD(CGROUP)) {
- const char *cgrp_name;
- struct cgroup *cgrp = cgroup__find(machine->env,
- sample->cgroup);
- if (cgrp != NULL)
- cgrp_name = cgrp->name;
- else
- cgrp_name = "unknown";
- fprintf(fp, " %s", cgrp_name);
- }
-
perf_sample__fprintf_ipc(sample, attr, fp);

fprintf(fp, "\n");
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 1baa2acb3ced..ea8c7eca5eee 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1805,6 +1805,7 @@ int cmd_top(int argc, const char **argv)
top.session = perf_session__new(NULL, NULL);
if (IS_ERR(top.session)) {
status = PTR_ERR(top.session);
+ top.session = NULL;
goto out_delete_evlist;
}

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 6e73d0e95715..4aba576512a1 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -3136,13 +3136,8 @@ static void evlist__free_syscall_tp_fields(struct evlist *evlist)
struct evsel *evsel;

evlist__for_each_entry(evlist, evsel) {
- struct evsel_trace *et = evsel->priv;
-
- if (!et || !evsel->tp_format || strcmp(evsel->tp_format->system, "syscalls"))
- continue;
-
- zfree(&et->fmt);
- free(et);
+ evsel_trace__delete(evsel->priv);
+ evsel->priv = NULL;
}
}

diff --git a/tools/perf/dlfilters/dlfilter-test-api-v2.c b/tools/perf/dlfilters/dlfilter-test-api-v2.c
new file mode 100644
index 000000000000..38e593d92920
--- /dev/null
+++ b/tools/perf/dlfilters/dlfilter-test-api-v2.c
@@ -0,0 +1,377 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Test v2 API for perf --dlfilter shared object
+ * Copyright (c) 2023, Intel Corporation.
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stdbool.h>
+
+/*
+ * Copy v2 API instead of including current API
+ */
+#include <linux/perf_event.h>
+#include <linux/types.h>
+
+/*
+ * The following macro can be used to determine if this header defines
+ * perf_dlfilter_sample machine_pid and vcpu.
+ */
+#define PERF_DLFILTER_HAS_MACHINE_PID
+
+/* Definitions for perf_dlfilter_sample flags */
+enum {
+ PERF_DLFILTER_FLAG_BRANCH = 1ULL << 0,
+ PERF_DLFILTER_FLAG_CALL = 1ULL << 1,
+ PERF_DLFILTER_FLAG_RETURN = 1ULL << 2,
+ PERF_DLFILTER_FLAG_CONDITIONAL = 1ULL << 3,
+ PERF_DLFILTER_FLAG_SYSCALLRET = 1ULL << 4,
+ PERF_DLFILTER_FLAG_ASYNC = 1ULL << 5,
+ PERF_DLFILTER_FLAG_INTERRUPT = 1ULL << 6,
+ PERF_DLFILTER_FLAG_TX_ABORT = 1ULL << 7,
+ PERF_DLFILTER_FLAG_TRACE_BEGIN = 1ULL << 8,
+ PERF_DLFILTER_FLAG_TRACE_END = 1ULL << 9,
+ PERF_DLFILTER_FLAG_IN_TX = 1ULL << 10,
+ PERF_DLFILTER_FLAG_VMENTRY = 1ULL << 11,
+ PERF_DLFILTER_FLAG_VMEXIT = 1ULL << 12,
+};
+
+/*
+ * perf sample event information (as per perf script and <linux/perf_event.h>)
+ */
+struct perf_dlfilter_sample {
+ __u32 size; /* Size of this structure (for compatibility checking) */
+ __u16 ins_lat; /* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */
+ __u16 p_stage_cyc; /* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */
+ __u64 ip;
+ __s32 pid;
+ __s32 tid;
+ __u64 time;
+ __u64 addr;
+ __u64 id;
+ __u64 stream_id;
+ __u64 period;
+ __u64 weight; /* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */
+ __u64 transaction; /* Refer PERF_SAMPLE_TRANSACTION in <linux/perf_event.h> */
+ __u64 insn_cnt; /* For instructions-per-cycle (IPC) */
+ __u64 cyc_cnt; /* For instructions-per-cycle (IPC) */
+ __s32 cpu;
+ __u32 flags; /* Refer PERF_DLFILTER_FLAG_* above */
+ __u64 data_src; /* Refer PERF_SAMPLE_DATA_SRC in <linux/perf_event.h> */
+ __u64 phys_addr; /* Refer PERF_SAMPLE_PHYS_ADDR in <linux/perf_event.h> */
+ __u64 data_page_size; /* Refer PERF_SAMPLE_DATA_PAGE_SIZE in <linux/perf_event.h> */
+ __u64 code_page_size; /* Refer PERF_SAMPLE_CODE_PAGE_SIZE in <linux/perf_event.h> */
+ __u64 cgroup; /* Refer PERF_SAMPLE_CGROUP in <linux/perf_event.h> */
+ __u8 cpumode; /* Refer CPUMODE_MASK etc in <linux/perf_event.h> */
+ __u8 addr_correlates_sym; /* True => resolve_addr() can be called */
+ __u16 misc; /* Refer perf_event_header in <linux/perf_event.h> */
+ __u32 raw_size; /* Refer PERF_SAMPLE_RAW in <linux/perf_event.h> */
+ const void *raw_data; /* Refer PERF_SAMPLE_RAW in <linux/perf_event.h> */
+ __u64 brstack_nr; /* Number of brstack entries */
+ const struct perf_branch_entry *brstack; /* Refer <linux/perf_event.h> */
+ __u64 raw_callchain_nr; /* Number of raw_callchain entries */
+ const __u64 *raw_callchain; /* Refer <linux/perf_event.h> */
+ const char *event;
+ __s32 machine_pid;
+ __s32 vcpu;
+};
+
+/*
+ * Address location (as per perf script)
+ */
+struct perf_dlfilter_al {
+ __u32 size; /* Size of this structure (for compatibility checking) */
+ __u32 symoff;
+ const char *sym;
+ __u64 addr; /* Mapped address (from dso) */
+ __u64 sym_start;
+ __u64 sym_end;
+ const char *dso;
+ __u8 sym_binding; /* STB_LOCAL, STB_GLOBAL or STB_WEAK, refer <elf.h> */
+ __u8 is_64_bit; /* Only valid if dso is not NULL */
+ __u8 is_kernel_ip; /* True if in kernel space */
+ __u32 buildid_size;
+ __u8 *buildid;
+ /* Below members are only populated by resolve_ip() */
+ __u8 filtered; /* True if this sample event will be filtered out */
+ const char *comm;
+ void *priv; /* Private data (v2 API) */
+};
+
+struct perf_dlfilter_fns {
+ /* Return information about ip */
+ const struct perf_dlfilter_al *(*resolve_ip)(void *ctx);
+ /* Return information about addr (if addr_correlates_sym) */
+ const struct perf_dlfilter_al *(*resolve_addr)(void *ctx);
+ /* Return arguments from --dlarg option */
+ char **(*args)(void *ctx, int *dlargc);
+ /*
+ * Return information about address (al->size must be set before
+ * calling). Returns 0 on success, -1 otherwise. Call al_cleanup()
+ * when 'al' data is no longer needed.
+ */
+ __s32 (*resolve_address)(void *ctx, __u64 address, struct perf_dlfilter_al *al);
+ /* Return instruction bytes and length */
+ const __u8 *(*insn)(void *ctx, __u32 *length);
+ /* Return source file name and line number */
+ const char *(*srcline)(void *ctx, __u32 *line_number);
+ /* Return perf_event_attr, refer <linux/perf_event.h> */
+ struct perf_event_attr *(*attr)(void *ctx);
+ /* Read object code, return numbers of bytes read */
+ __s32 (*object_code)(void *ctx, __u64 ip, void *buf, __u32 len);
+ /*
+ * If present (i.e. must check al_cleanup != NULL), call after
+ * resolve_address() to free any associated resources. (v2 API)
+ */
+ void (*al_cleanup)(void *ctx, struct perf_dlfilter_al *al);
+ /* Reserved */
+ void *(*reserved[119])(void *);
+};
+
+struct perf_dlfilter_fns perf_dlfilter_fns;
+
+static int verbose;
+
+#define pr_debug(fmt, ...) do { \
+ if (verbose > 0) \
+ fprintf(stderr, fmt, ##__VA_ARGS__); \
+ } while (0)
+
+static int test_fail(const char *msg)
+{
+ pr_debug("%s\n", msg);
+ return -1;
+}
+
+#define CHECK(x) do { \
+ if (!(x)) \
+ return test_fail("Check '" #x "' failed\n"); \
+ } while (0)
+
+struct filter_data {
+ __u64 ip;
+ __u64 addr;
+ int do_early;
+ int early_filter_cnt;
+ int filter_cnt;
+};
+
+static struct filter_data *filt_dat;
+
+int start(void **data, void *ctx)
+{
+ int dlargc;
+ char **dlargv;
+ struct filter_data *d;
+ static bool called;
+
+ verbose = 1;
+
+ CHECK(!filt_dat && !called);
+ called = true;
+
+ d = calloc(1, sizeof(*d));
+ if (!d)
+ test_fail("Failed to allocate memory");
+ filt_dat = d;
+ *data = d;
+
+ dlargv = perf_dlfilter_fns.args(ctx, &dlargc);
+
+ CHECK(dlargc == 6);
+ CHECK(!strcmp(dlargv[0], "first"));
+ verbose = strtol(dlargv[1], NULL, 0);
+ d->ip = strtoull(dlargv[2], NULL, 0);
+ d->addr = strtoull(dlargv[3], NULL, 0);
+ d->do_early = strtol(dlargv[4], NULL, 0);
+ CHECK(!strcmp(dlargv[5], "last"));
+
+ pr_debug("%s API\n", __func__);
+
+ return 0;
+}
+
+#define CHECK_SAMPLE(x) do { \
+ if (sample->x != expected.x) \
+ return test_fail("'" #x "' not expected value\n"); \
+ } while (0)
+
+static int check_sample(struct filter_data *d, const struct perf_dlfilter_sample *sample)
+{
+ struct perf_dlfilter_sample expected = {
+ .ip = d->ip,
+ .pid = 12345,
+ .tid = 12346,
+ .time = 1234567890,
+ .addr = d->addr,
+ .id = 99,
+ .stream_id = 101,
+ .period = 543212345,
+ .cpu = 31,
+ .cpumode = PERF_RECORD_MISC_USER,
+ .addr_correlates_sym = 1,
+ .misc = PERF_RECORD_MISC_USER,
+ };
+
+ CHECK(sample->size >= sizeof(struct perf_dlfilter_sample));
+
+ CHECK_SAMPLE(ip);
+ CHECK_SAMPLE(pid);
+ CHECK_SAMPLE(tid);
+ CHECK_SAMPLE(time);
+ CHECK_SAMPLE(addr);
+ CHECK_SAMPLE(id);
+ CHECK_SAMPLE(stream_id);
+ CHECK_SAMPLE(period);
+ CHECK_SAMPLE(cpu);
+ CHECK_SAMPLE(cpumode);
+ CHECK_SAMPLE(addr_correlates_sym);
+ CHECK_SAMPLE(misc);
+
+ CHECK(!sample->raw_data);
+ CHECK_SAMPLE(brstack_nr);
+ CHECK(!sample->brstack);
+ CHECK_SAMPLE(raw_callchain_nr);
+ CHECK(!sample->raw_callchain);
+
+#define EVENT_NAME "branches:"
+ CHECK(!strncmp(sample->event, EVENT_NAME, strlen(EVENT_NAME)));
+
+ return 0;
+}
+
+static int check_al(void *ctx)
+{
+ const struct perf_dlfilter_al *al;
+
+ al = perf_dlfilter_fns.resolve_ip(ctx);
+ if (!al)
+ return test_fail("resolve_ip() failed");
+
+ CHECK(al->sym && !strcmp("foo", al->sym));
+ CHECK(!al->symoff);
+
+ return 0;
+}
+
+static int check_addr_al(void *ctx)
+{
+ const struct perf_dlfilter_al *addr_al;
+
+ addr_al = perf_dlfilter_fns.resolve_addr(ctx);
+ if (!addr_al)
+ return test_fail("resolve_addr() failed");
+
+ CHECK(addr_al->sym && !strcmp("bar", addr_al->sym));
+ CHECK(!addr_al->symoff);
+
+ return 0;
+}
+
+static int check_address_al(void *ctx, const struct perf_dlfilter_sample *sample)
+{
+ struct perf_dlfilter_al address_al;
+ const struct perf_dlfilter_al *al;
+
+ al = perf_dlfilter_fns.resolve_ip(ctx);
+ if (!al)
+ return test_fail("resolve_ip() failed");
+
+ address_al.size = sizeof(address_al);
+ if (perf_dlfilter_fns.resolve_address(ctx, sample->ip, &address_al))
+ return test_fail("resolve_address() failed");
+
+ CHECK(address_al.sym && al->sym);
+ CHECK(!strcmp(address_al.sym, al->sym));
+ CHECK(address_al.addr == al->addr);
+ CHECK(address_al.sym_start == al->sym_start);
+ CHECK(address_al.sym_end == al->sym_end);
+ CHECK(address_al.dso && al->dso);
+ CHECK(!strcmp(address_al.dso, al->dso));
+
+ /* al_cleanup() is v2 API so may not be present */
+ if (perf_dlfilter_fns.al_cleanup)
+ perf_dlfilter_fns.al_cleanup(ctx, &address_al);
+
+ return 0;
+}
+
+static int check_attr(void *ctx)
+{
+ struct perf_event_attr *attr = perf_dlfilter_fns.attr(ctx);
+
+ CHECK(attr);
+ CHECK(attr->type == PERF_TYPE_HARDWARE);
+ CHECK(attr->config == PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
+
+ return 0;
+}
+
+static int do_checks(void *data, const struct perf_dlfilter_sample *sample, void *ctx, bool early)
+{
+ struct filter_data *d = data;
+
+ CHECK(data && filt_dat == data);
+
+ if (early) {
+ CHECK(!d->early_filter_cnt);
+ d->early_filter_cnt += 1;
+ } else {
+ CHECK(!d->filter_cnt);
+ CHECK(d->early_filter_cnt);
+ CHECK(d->do_early != 2);
+ d->filter_cnt += 1;
+ }
+
+ if (check_sample(data, sample))
+ return -1;
+
+ if (check_attr(ctx))
+ return -1;
+
+ if (early && !d->do_early)
+ return 0;
+
+ if (check_al(ctx) || check_addr_al(ctx) || check_address_al(ctx, sample))
+ return -1;
+
+ if (early)
+ return d->do_early == 2;
+
+ return 1;
+}
+
+int filter_event_early(void *data, const struct perf_dlfilter_sample *sample, void *ctx)
+{
+ pr_debug("%s API\n", __func__);
+
+ return do_checks(data, sample, ctx, true);
+}
+
+int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx)
+{
+ pr_debug("%s API\n", __func__);
+
+ return do_checks(data, sample, ctx, false);
+}
+
+int stop(void *data, void *ctx)
+{
+ static bool called;
+
+ pr_debug("%s API\n", __func__);
+
+ CHECK(data && filt_dat == data && !called);
+ called = true;
+
+ free(data);
+ filt_dat = NULL;
+ return 0;
+}
+
+const char *filter_description(const char **long_description)
+{
+ *long_description = "Filter used by the 'dlfilter C API' perf test";
+ return "dlfilter to test v2 C API";
+}
diff --git a/tools/perf/include/perf/perf_dlfilter.h b/tools/perf/include/perf/perf_dlfilter.h
index a26e2f129f83..16fc4568ac53 100644
--- a/tools/perf/include/perf/perf_dlfilter.h
+++ b/tools/perf/include/perf/perf_dlfilter.h
@@ -91,6 +91,7 @@ struct perf_dlfilter_al {
/* Below members are only populated by resolve_ip() */
__u8 filtered; /* True if this sample event will be filtered out */
const char *comm;
+ void *priv; /* Private data. Do not change */
};

struct perf_dlfilter_fns {
@@ -102,7 +103,8 @@ struct perf_dlfilter_fns {
char **(*args)(void *ctx, int *dlargc);
/*
* Return information about address (al->size must be set before
- * calling). Returns 0 on success, -1 otherwise.
+ * calling). Returns 0 on success, -1 otherwise. Call al_cleanup()
+ * when 'al' data is no longer needed.
*/
__s32 (*resolve_address)(void *ctx, __u64 address, struct perf_dlfilter_al *al);
/* Return instruction bytes and length */
@@ -113,8 +115,13 @@ struct perf_dlfilter_fns {
struct perf_event_attr *(*attr)(void *ctx);
/* Read object code, return numbers of bytes read */
__s32 (*object_code)(void *ctx, __u64 ip, void *buf, __u32 len);
+ /*
+ * If present (i.e. must check al_cleanup != NULL), call after
+ * resolve_address() to free any associated resources.
+ */
+ void (*al_cleanup)(void *ctx, struct perf_dlfilter_al *al);
/* Reserved */
- void *(*reserved[120])(void *);
+ void *(*reserved[119])(void *);
};

/*
diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build
index 150765f2baee..1d18bb89402e 100644
--- a/tools/perf/pmu-events/Build
+++ b/tools/perf/pmu-events/Build
@@ -35,3 +35,9 @@ $(PMU_EVENTS_C): $(JSON) $(JSON_TEST) $(JEVENTS_PY) $(METRIC_PY) $(METRIC_TEST_L
$(call rule_mkdir)
$(Q)$(call echo-cmd,gen)$(PYTHON) $(JEVENTS_PY) $(JEVENTS_ARCH) $(JEVENTS_MODEL) pmu-events/arch $@
endif
+
+# pmu-events.c file is generated in the OUTPUT directory so it needs a
+# separate rule to depend on it properly
+$(OUTPUT)pmu-events/pmu-events.o: $(PMU_EVENTS_C)
+ $(call rule_mkdir)
+ $(call if_changed_dep,cc_o_c)
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/cache.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/cache.json
index fc0633054211..7a2b7b200f14 100644
--- a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/cache.json
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/cache.json
@@ -92,9 +92,6 @@
{
"ArchStdEvent": "L1D_CACHE_LMISS_RD"
},
- {
- "ArchStdEvent": "L1D_CACHE_LMISS"
- },
{
"ArchStdEvent": "L1I_CACHE_LMISS"
},
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/cache.json b/tools/perf/pmu-events/arch/powerpc/power10/cache.json
index 605be14f441c..839ae26945fb 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/cache.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/cache.json
@@ -1,53 +1,8 @@
[
- {
- "EventCode": "0x1003C",
- "EventName": "PM_EXEC_STALL_DMISS_L2L3",
- "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from either the local L2 or local L3."
- },
- {
- "EventCode": "0x1E054",
- "EventName": "PM_EXEC_STALL_DMISS_L21_L31",
- "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from another core's L2 or L3 on the same chip."
- },
- {
- "EventCode": "0x34054",
- "EventName": "PM_EXEC_STALL_DMISS_L2L3_NOCONFLICT",
- "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local L2 or local L3, without a dispatch conflict."
- },
- {
- "EventCode": "0x34056",
- "EventName": "PM_EXEC_STALL_LOAD_FINISH",
- "BriefDescription": "Cycles in which the oldest instruction in the pipeline was finishing a load after its data was reloaded from a data source beyond the local L1; cycles in which the LSU was processing an L1-hit; cycles in which the NTF instruction merged with another load in the LMQ; cycles in which the NTF instruction is waiting for a data reload for a load miss, but the data comes back with a non-NTF instruction."
- },
- {
- "EventCode": "0x3006C",
- "EventName": "PM_RUN_CYC_SMT2_MODE",
- "BriefDescription": "Cycles when this thread's run latch is set and the core is in SMT2 mode."
- },
{
"EventCode": "0x300F4",
"EventName": "PM_RUN_INST_CMPL_CONC",
- "BriefDescription": "PowerPC instructions completed by this thread when all threads in the core had the run-latch set."
- },
- {
- "EventCode": "0x4C016",
- "EventName": "PM_EXEC_STALL_DMISS_L2L3_CONFLICT",
- "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local L2 or local L3, with a dispatch conflict."
- },
- {
- "EventCode": "0x4D014",
- "EventName": "PM_EXEC_STALL_LOAD",
- "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a load instruction executing in the Load Store Unit."
- },
- {
- "EventCode": "0x4D016",
- "EventName": "PM_EXEC_STALL_PTESYNC",
- "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a PTESYNC instruction executing in the Load Store Unit."
- },
- {
- "EventCode": "0x401EA",
- "EventName": "PM_THRESH_EXC_128",
- "BriefDescription": "Threshold counter exceeded a value of 128."
+ "BriefDescription": "PowerPC instruction completed by this thread when all threads in the core had the run-latch set."
},
{
"EventCode": "0x400F6",
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json b/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json
index 54acb55e2c8c..e816cd10c129 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/floating_point.json
@@ -1,7 +1,67 @@
[
{
- "EventCode": "0x4016E",
- "EventName": "PM_THRESH_NOT_MET",
- "BriefDescription": "Threshold counter did not meet threshold."
+ "EventCode": "0x100F4",
+ "EventName": "PM_FLOP_CMPL",
+ "BriefDescription": "Floating Point Operations Completed. Includes any type. It counts once for each 1, 2, 4 or 8 flop instruction. Use PM_1|2|4|8_FLOP_CMPL events to count flops."
+ },
+ {
+ "EventCode": "0x45050",
+ "EventName": "PM_1FLOP_CMPL",
+ "BriefDescription": "One floating point instruction completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)."
+ },
+ {
+ "EventCode": "0x45052",
+ "EventName": "PM_4FLOP_CMPL",
+ "BriefDescription": "Four floating point instruction completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)."
+ },
+ {
+ "EventCode": "0x45054",
+ "EventName": "PM_FMA_CMPL",
+ "BriefDescription": "Two floating point instruction completed (FMA class of instructions: fmadd, fnmadd, fmsub, fnmsub). Scalar instructions only."
+ },
+ {
+ "EventCode": "0x45056",
+ "EventName": "PM_SCALAR_FLOP_CMPL",
+ "BriefDescription": "Scalar floating point instruction completed."
+ },
+ {
+ "EventCode": "0x4505A",
+ "EventName": "PM_SP_FLOP_CMPL",
+ "BriefDescription": "Single Precision floating point instruction completed."
+ },
+ {
+ "EventCode": "0x4505C",
+ "EventName": "PM_MATH_FLOP_CMPL",
+ "BriefDescription": "Math floating point instruction completed."
+ },
+ {
+ "EventCode": "0x4D052",
+ "EventName": "PM_2FLOP_CMPL",
+ "BriefDescription": "Double Precision vector version of fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg completed."
+ },
+ {
+ "EventCode": "0x4D054",
+ "EventName": "PM_8FLOP_CMPL",
+ "BriefDescription": "Four Double Precision vector instruction completed."
+ },
+ {
+ "EventCode": "0x4D056",
+ "EventName": "PM_NON_FMA_FLOP_CMPL",
+ "BriefDescription": "Non FMA instruction completed."
+ },
+ {
+ "EventCode": "0x4D058",
+ "EventName": "PM_VECTOR_FLOP_CMPL",
+ "BriefDescription": "Vector floating point instruction completed."
+ },
+ {
+ "EventCode": "0x4D05A",
+ "EventName": "PM_NON_MATH_FLOP_CMPL",
+ "BriefDescription": "Non Math instruction completed."
+ },
+ {
+ "EventCode": "0x4D05C",
+ "EventName": "PM_DPP_FLOP_CMPL",
+ "BriefDescription": "Double-Precision or Quad-Precision instruction completed."
}
]
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/frontend.json b/tools/perf/pmu-events/arch/powerpc/power10/frontend.json
index 558f9530f54e..dc0bb6c6338b 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/frontend.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/frontend.json
@@ -1,64 +1,9 @@
[
- {
- "EventCode": "0x10004",
- "EventName": "PM_EXEC_STALL_TRANSLATION",
- "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered a TLB miss or ERAT miss and waited for it to resolve."
- },
- {
- "EventCode": "0x10006",
- "EventName": "PM_DISP_STALL_HELD_OTHER_CYC",
- "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any other reason."
- },
- {
- "EventCode": "0x10010",
- "EventName": "PM_PMC4_OVERFLOW",
- "BriefDescription": "The event selected for PMC4 caused the event counter to overflow."
- },
- {
- "EventCode": "0x10020",
- "EventName": "PM_PMC4_REWIND",
- "BriefDescription": "The speculative event selected for PMC4 rewinds and the counter for PMC4 is not charged."
- },
- {
- "EventCode": "0x10038",
- "EventName": "PM_DISP_STALL_TRANSLATION",
- "BriefDescription": "Cycles when dispatch was stalled for this thread because the MMU was handling a translation miss."
- },
- {
- "EventCode": "0x1003A",
- "EventName": "PM_DISP_STALL_BR_MPRED_IC_L2",
- "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L2 after suffering a branch mispredict."
- },
- {
- "EventCode": "0x1D05E",
- "EventName": "PM_DISP_STALL_HELD_HALT_CYC",
- "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of power management."
- },
- {
- "EventCode": "0x1E050",
- "EventName": "PM_DISP_STALL_HELD_STF_MAPPER_CYC",
- "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the STF mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR."
- },
{
"EventCode": "0x1F054",
"EventName": "PM_DTLB_HIT",
"BriefDescription": "The PTE required by the instruction was resident in the TLB (data TLB access). When MMCR1[16]=0 this event counts only demand hits. When MMCR1[16]=1 this event includes demand and prefetch. Applies to both HPT and RPT."
},
- {
- "EventCode": "0x10064",
- "EventName": "PM_DISP_STALL_IC_L2",
- "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L2."
- },
- {
- "EventCode": "0x101E8",
- "EventName": "PM_THRESH_EXC_256",
- "BriefDescription": "Threshold counter exceeded a count of 256."
- },
- {
- "EventCode": "0x101EC",
- "EventName": "PM_THRESH_MET",
- "BriefDescription": "Threshold exceeded."
- },
{
"EventCode": "0x100F2",
"EventName": "PM_1PLUS_PPC_CMPL",
@@ -67,57 +12,7 @@
{
"EventCode": "0x100F6",
"EventName": "PM_IERAT_MISS",
- "BriefDescription": "IERAT Reloaded to satisfy an IERAT miss. All page sizes are counted by this event."
- },
- {
- "EventCode": "0x100F8",
- "EventName": "PM_DISP_STALL_CYC",
- "BriefDescription": "Cycles the ICT has no itags assigned to this thread (no instructions were dispatched during these cycles)."
- },
- {
- "EventCode": "0x20006",
- "EventName": "PM_DISP_STALL_HELD_ISSQ_FULL_CYC",
- "BriefDescription": "Cycles in which the NTC instruction is held at dispatch due to Issue queue full. Includes issue queue and branch queue."
- },
- {
- "EventCode": "0x20114",
- "EventName": "PM_MRK_L2_RC_DISP",
- "BriefDescription": "Marked instruction RC dispatched in L2."
- },
- {
- "EventCode": "0x2C010",
- "EventName": "PM_EXEC_STALL_LSU",
- "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the Load Store Unit. This does not include simple fixed point instructions."
- },
- {
- "EventCode": "0x2C016",
- "EventName": "PM_DISP_STALL_IERAT_ONLY_MISS",
- "BriefDescription": "Cycles when dispatch was stalled while waiting to resolve an instruction ERAT miss."
- },
- {
- "EventCode": "0x2C01E",
- "EventName": "PM_DISP_STALL_BR_MPRED_IC_L3",
- "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L3 after suffering a branch mispredict."
- },
- {
- "EventCode": "0x2D01A",
- "EventName": "PM_DISP_STALL_IC_MISS",
- "BriefDescription": "Cycles when dispatch was stalled for this thread due to an Icache Miss."
- },
- {
- "EventCode": "0x2E018",
- "EventName": "PM_DISP_STALL_FETCH",
- "BriefDescription": "Cycles when dispatch was stalled for this thread because Fetch was being held."
- },
- {
- "EventCode": "0x2E01A",
- "EventName": "PM_DISP_STALL_HELD_XVFC_MAPPER_CYC",
- "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the XVFC mapper/SRB was full."
- },
- {
- "EventCode": "0x2C142",
- "EventName": "PM_MRK_XFER_FROM_SRC_PMC2",
- "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[15:27]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
+ "BriefDescription": "IERAT Reloaded to satisfy an IERAT miss. All page sizes are counted by this event. This event only counts instruction demand access."
},
{
"EventCode": "0x24050",
@@ -134,11 +29,6 @@
"EventName": "PM_BR_TAKEN_CMPL",
"BriefDescription": "Branch Taken instruction completed."
},
- {
- "EventCode": "0x30004",
- "EventName": "PM_DISP_STALL_FLUSH",
- "BriefDescription": "Cycles when dispatch was stalled because of a flush that happened to an instruction(s) that was not yet NTC. PM_EXEC_STALL_NTC_FLUSH only includes instructions that were flushed after becoming NTC."
- },
{
"EventCode": "0x3000A",
"EventName": "PM_DISP_STALL_ITLB_MISS",
@@ -149,99 +39,29 @@
"EventName": "PM_FLUSH_COMPLETION",
"BriefDescription": "The instruction that was next to complete (oldest in the pipeline) did not complete because it suffered a flush."
},
- {
- "EventCode": "0x30014",
- "EventName": "PM_EXEC_STALL_STORE",
- "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a store instruction executing in the Load Store Unit."
- },
- {
- "EventCode": "0x30018",
- "EventName": "PM_DISP_STALL_HELD_SCOREBOARD_CYC",
- "BriefDescription": "Cycles in which the NTC instruction is held at dispatch while waiting on the Scoreboard. This event combines VSCR and FPSCR together."
- },
- {
- "EventCode": "0x30026",
- "EventName": "PM_EXEC_STALL_STORE_MISS",
- "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a store whose cache line was not resident in the L1 and was waiting for allocation of the missing line into the L1."
- },
- {
- "EventCode": "0x3012A",
- "EventName": "PM_MRK_L2_RC_DONE",
- "BriefDescription": "L2 RC machine completed the transaction for the marked instruction."
- },
{
"EventCode": "0x3F046",
"EventName": "PM_ITLB_HIT_1G",
"BriefDescription": "Instruction TLB hit (IERAT reload) page size 1G, which implies Radix Page Table translation is in use. When MMCR1[17]=0 this event counts only for demand misses. When MMCR1[17]=1 this event includes demand misses and prefetches."
},
- {
- "EventCode": "0x34058",
- "EventName": "PM_DISP_STALL_BR_MPRED_ICMISS",
- "BriefDescription": "Cycles when dispatch was stalled after a mispredicted branch resulted in an instruction cache miss."
- },
- {
- "EventCode": "0x3D05C",
- "EventName": "PM_DISP_STALL_HELD_RENAME_CYC",
- "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because the mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR and XVFC."
- },
- {
- "EventCode": "0x3E052",
- "EventName": "PM_DISP_STALL_IC_L3",
- "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L3."
- },
{
"EventCode": "0x3E054",
"EventName": "PM_LD_MISS_L1",
- "BriefDescription": "Load Missed L1, counted at execution time (can be greater than loads finished). LMQ merges are not included in this count. i.e. if a load instruction misses on an address that is already allocated on the LMQ, this event will not increment for that load). Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load."
- },
- {
- "EventCode": "0x301EA",
- "EventName": "PM_THRESH_EXC_1024",
- "BriefDescription": "Threshold counter exceeded a value of 1024."
+ "BriefDescription": "Load missed L1, counted at finish time. LMQ merges are not included in this count. i.e. if a load instruction misses on an address that is already allocated on the LMQ, this event will not increment for that load). Note that this count is per slice, so if a load spans multiple slices this event will increment multiple times for a single load."
},
{
"EventCode": "0x300FA",
"EventName": "PM_INST_FROM_L3MISS",
- "BriefDescription": "The processor's instruction cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss."
+ "BriefDescription": "The processor's instruction cache was reloaded from beyond the local core's L3 due to a demand miss."
},
{
"EventCode": "0x40006",
"EventName": "PM_ISSUE_KILL",
"BriefDescription": "Cycles in which an instruction or group of instructions were cancelled after being issued. This event increments once per occurrence, regardless of how many instructions are included in the issue group."
},
- {
- "EventCode": "0x40116",
- "EventName": "PM_MRK_LARX_FIN",
- "BriefDescription": "Marked load and reserve instruction (LARX) finished. LARX and STCX are instructions used to acquire a lock."
- },
- {
- "EventCode": "0x4C010",
- "EventName": "PM_DISP_STALL_BR_MPRED_IC_L3MISS",
- "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from sources beyond the local L3 after suffering a mispredicted branch."
- },
- {
- "EventCode": "0x4D01E",
- "EventName": "PM_DISP_STALL_BR_MPRED",
- "BriefDescription": "Cycles when dispatch was stalled for this thread due to a mispredicted branch."
- },
- {
- "EventCode": "0x4E010",
- "EventName": "PM_DISP_STALL_IC_L3MISS",
- "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from any source beyond the local L3."
- },
- {
- "EventCode": "0x4E01A",
- "EventName": "PM_DISP_STALL_HELD_CYC",
- "BriefDescription": "Cycles in which the NTC instruction is held at dispatch for any reason."
- },
- {
- "EventCode": "0x4003C",
- "EventName": "PM_DISP_STALL_HELD_SYNC_CYC",
- "BriefDescription": "Cycles in which the NTC instruction is held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch."
- },
{
"EventCode": "0x44056",
"EventName": "PM_VECTOR_ST_CMPL",
- "BriefDescription": "Vector store instructions completed."
+ "BriefDescription": "Vector store instruction completed."
}
]
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/marked.json b/tools/perf/pmu-events/arch/powerpc/power10/marked.json
index 58b5dfe3a273..913b6515b870 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/marked.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/marked.json
@@ -1,14 +1,29 @@
[
- {
- "EventCode": "0x1002C",
- "EventName": "PM_LD_PREFETCH_CACHE_LINE_MISS",
- "BriefDescription": "The L1 cache was reloaded with a line that fulfills a prefetch request."
- },
{
"EventCode": "0x10132",
"EventName": "PM_MRK_INST_ISSUED",
"BriefDescription": "Marked instruction issued. Note that stores always get issued twice, the address gets issued to the LSU and the data gets issued to the VSU. Also, issues can sometimes get killed/cancelled and cause multiple sequential issues for the same instruction."
},
+ {
+ "EventCode": "0x10134",
+ "EventName": "PM_MRK_ST_DONE_L2",
+ "BriefDescription": "Marked store completed in L2."
+ },
+ {
+ "EventCode": "0x1C142",
+ "EventName": "PM_MRK_XFER_FROM_SRC_PMC1",
+ "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[0:12]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
+ },
+ {
+ "EventCode": "0x1C144",
+ "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC1",
+ "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[0:12]."
+ },
+ {
+ "EventCode": "0x1F150",
+ "EventName": "PM_MRK_ST_L2_CYC",
+ "BriefDescription": "Cycles from L2 RC dispatch to L2 RC completion."
+ },
{
"EventCode": "0x101E0",
"EventName": "PM_MRK_INST_DISP",
@@ -20,14 +35,39 @@
"BriefDescription": "Marked Branch Taken instruction completed."
},
{
- "EventCode": "0x20112",
- "EventName": "PM_MRK_NTF_FIN",
- "BriefDescription": "The marked instruction became the oldest in the pipeline before it finished. It excludes instructions that finish at dispatch."
+ "EventCode": "0x101E4",
+ "EventName": "PM_MRK_L1_ICACHE_MISS",
+ "BriefDescription": "Marked instruction suffered an instruction cache miss."
+ },
+ {
+ "EventCode": "0x101EA",
+ "EventName": "PM_MRK_L1_RELOAD_VALID",
+ "BriefDescription": "Marked demand reload."
+ },
+ {
+ "EventCode": "0x20114",
+ "EventName": "PM_MRK_L2_RC_DISP",
+ "BriefDescription": "Marked instruction RC dispatched in L2."
},
{
- "EventCode": "0x2C01C",
- "EventName": "PM_EXEC_STALL_DMISS_OFF_CHIP",
- "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a remote chip."
+ "EventCode": "0x2011C",
+ "EventName": "PM_MRK_NTF_CYC",
+ "BriefDescription": "Cycles in which the marked instruction is the oldest in the pipeline (next-to-finish or next-to-complete)."
+ },
+ {
+ "EventCode": "0x20130",
+ "EventName": "PM_MRK_INST_DECODED",
+ "BriefDescription": "An instruction was marked at decode time. Random Instruction Sampling (RIS) only."
+ },
+ {
+ "EventCode": "0x20132",
+ "EventName": "PM_MRK_DFU_ISSUE",
+ "BriefDescription": "The marked instruction was a decimal floating point operation issued to the VSU. Measured at issue time."
+ },
+ {
+ "EventCode": "0x20134",
+ "EventName": "PM_MRK_FXU_ISSUE",
+ "BriefDescription": "The marked instruction was a fixed point operation issued to the VSU. Measured at issue time."
},
{
"EventCode": "0x20138",
@@ -39,6 +79,16 @@
"EventName": "PM_MRK_BRU_FIN",
"BriefDescription": "Marked Branch instruction finished."
},
+ {
+ "EventCode": "0x2013C",
+ "EventName": "PM_MRK_FX_LSU_FIN",
+ "BriefDescription": "The marked instruction was simple fixed point that was issued to the store unit. Measured at finish time."
+ },
+ {
+ "EventCode": "0x2C142",
+ "EventName": "PM_MRK_XFER_FROM_SRC_PMC2",
+ "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[15:27]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
+ },
{
"EventCode": "0x2C144",
"EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC2",
@@ -60,19 +110,49 @@
"BriefDescription": "A marked branch completed. All branches are included."
},
{
- "EventCode": "0x200FD",
- "EventName": "PM_L1_ICACHE_MISS",
- "BriefDescription": "Demand iCache Miss."
+ "EventCode": "0x2D154",
+ "EventName": "PM_MRK_DERAT_MISS_64K",
+ "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 64K for a marked instruction. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
+ },
+ {
+ "EventCode": "0x201E0",
+ "EventName": "PM_MRK_DATA_FROM_MEMORY",
+ "BriefDescription": "The processor's data cache was reloaded from local, remote, or distant memory due to a demand miss for a marked load."
+ },
+ {
+ "EventCode": "0x201E2",
+ "EventName": "PM_MRK_LD_MISS_L1",
+ "BriefDescription": "Marked demand data load miss counted at finish time."
},
{
- "EventCode": "0x30130",
- "EventName": "PM_MRK_INST_FIN",
- "BriefDescription": "marked instruction finished. Excludes instructions that finish at dispatch. Note that stores always finish twice since the address gets issued to the LSU and the data gets issued to the VSU."
+ "EventCode": "0x201E4",
+ "EventName": "PM_MRK_DATA_FROM_L3MISS",
+ "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss for a marked load."
+ },
+ {
+ "EventCode": "0x3012A",
+ "EventName": "PM_MRK_L2_RC_DONE",
+ "BriefDescription": "L2 RC machine completed the transaction for the marked instruction."
+ },
+ {
+ "EventCode": "0x30132",
+ "EventName": "PM_MRK_VSU_FIN",
+ "BriefDescription": "VSU marked instruction finished. Excludes simple FX instructions issued to the Store Unit."
},
{
"EventCode": "0x34146",
"EventName": "PM_MRK_LD_CMPL",
- "BriefDescription": "Marked loads completed."
+ "BriefDescription": "Marked load instruction completed."
+ },
+ {
+ "EventCode": "0x3C142",
+ "EventName": "PM_MRK_XFER_FROM_SRC_PMC3",
+ "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[30:42]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
+ },
+ {
+ "EventCode": "0x3C144",
+ "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC3",
+ "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[30:42]."
},
{
"EventCode": "0x3E158",
@@ -82,12 +162,22 @@
{
"EventCode": "0x3E15A",
"EventName": "PM_MRK_ST_FIN",
- "BriefDescription": "The marked instruction was a store of any kind."
+ "BriefDescription": "Marked store instruction finished."
},
{
- "EventCode": "0x30068",
- "EventName": "PM_L1_ICACHE_RELOADED_PREF",
- "BriefDescription": "Counts all Icache prefetch reloads ( includes demand turned into prefetch)."
+ "EventCode": "0x3F150",
+ "EventName": "PM_MRK_ST_DRAIN_CYC",
+ "BriefDescription": "Cycles in which the marked store drained from the core to the L2."
+ },
+ {
+ "EventCode": "0x30162",
+ "EventName": "PM_MRK_ISSUE_DEPENDENT_LOAD",
+ "BriefDescription": "The marked instruction was dependent on a load. It is eligible for issue kill."
+ },
+ {
+ "EventCode": "0x301E2",
+ "EventName": "PM_MRK_ST_CMPL",
+ "BriefDescription": "Marked store completed and sent to nest. Note that this count excludes cache-inhibited stores."
},
{
"EventCode": "0x301E4",
@@ -95,48 +185,58 @@
"BriefDescription": "Marked Branch Mispredicted. Includes direction and target."
},
{
- "EventCode": "0x300F6",
- "EventName": "PM_LD_DEMAND_MISS_L1",
- "BriefDescription": "The L1 cache was reloaded with a line that fulfills a demand miss request. Counted at reload time, before finish."
+ "EventCode": "0x40116",
+ "EventName": "PM_MRK_LARX_FIN",
+ "BriefDescription": "Marked load and reserve instruction (LARX) finished. LARX and STCX are instructions used to acquire a lock."
+ },
+ {
+ "EventCode": "0x40132",
+ "EventName": "PM_MRK_LSU_FIN",
+ "BriefDescription": "LSU marked instruction finish."
},
{
- "EventCode": "0x300FE",
- "EventName": "PM_DATA_FROM_L3MISS",
- "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss."
+ "EventCode": "0x44146",
+ "EventName": "PM_MRK_STCX_CORE_CYC",
+ "BriefDescription": "Cycles spent in the core portion of a marked STCX instruction. It starts counting when the instruction is decoded and stops counting when it drains into the L2."
},
{
- "EventCode": "0x40012",
- "EventName": "PM_L1_ICACHE_RELOADED_ALL",
- "BriefDescription": "Counts all Icache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch."
+ "EventCode": "0x4C142",
+ "EventName": "PM_MRK_XFER_FROM_SRC_PMC4",
+ "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[45:57]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
},
{
- "EventCode": "0x40134",
- "EventName": "PM_MRK_INST_TIMEO",
- "BriefDescription": "Marked instruction finish timeout (instruction was lost)."
+ "EventCode": "0x4C144",
+ "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC4",
+ "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[45:57]."
},
{
- "EventCode": "0x4505A",
- "EventName": "PM_SP_FLOP_CMPL",
- "BriefDescription": "Single Precision floating point instructions completed."
+ "EventCode": "0x4C15E",
+ "EventName": "PM_MRK_DTLB_MISS_64K",
+ "BriefDescription": "Marked Data TLB reload (after a miss) page size 64K. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
},
{
- "EventCode": "0x4D058",
- "EventName": "PM_VECTOR_FLOP_CMPL",
- "BriefDescription": "Vector floating point instructions completed."
+ "EventCode": "0x4E15E",
+ "EventName": "PM_MRK_INST_FLUSHED",
+ "BriefDescription": "The marked instruction was flushed."
},
{
- "EventCode": "0x4D05A",
- "EventName": "PM_NON_MATH_FLOP_CMPL",
- "BriefDescription": "Non Math instructions completed."
+ "EventCode": "0x40164",
+ "EventName": "PM_MRK_DERAT_MISS_2M",
+ "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 2M for a marked instruction. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
},
{
"EventCode": "0x401E0",
"EventName": "PM_MRK_INST_CMPL",
- "BriefDescription": "marked instruction completed."
+ "BriefDescription": "Marked instruction completed."
+ },
+ {
+ "EventCode": "0x401E6",
+ "EventName": "PM_MRK_INST_FROM_L3MISS",
+ "BriefDescription": "The processor's instruction cache was reloaded from beyond the local core's L3 due to a demand miss for a marked instruction."
},
{
- "EventCode": "0x400FE",
- "EventName": "PM_DATA_FROM_MEMORY",
- "BriefDescription": "The processor's data cache was reloaded from local, remote, or distant memory due to a demand miss."
+ "EventCode": "0x401E8",
+ "EventName": "PM_MRK_DATA_FROM_L2MISS",
+ "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L2 due to a demand miss for a marked instruction."
}
]
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/memory.json b/tools/perf/pmu-events/arch/powerpc/power10/memory.json
index 843b51f531e9..b95a547a704b 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/memory.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/memory.json
@@ -1,24 +1,9 @@
[
- {
- "EventCode": "0x1000A",
- "EventName": "PM_PMC3_REWIND",
- "BriefDescription": "The speculative event selected for PMC3 rewinds and the counter for PMC3 is not charged."
- },
{
"EventCode": "0x1C040",
"EventName": "PM_XFER_FROM_SRC_PMC1",
"BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[0:12]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
},
- {
- "EventCode": "0x1C142",
- "EventName": "PM_MRK_XFER_FROM_SRC_PMC1",
- "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[0:12]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
- },
- {
- "EventCode": "0x1C144",
- "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC1",
- "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[0:12]."
- },
{
"EventCode": "0x1C056",
"EventName": "PM_DERAT_MISS_4K",
@@ -34,25 +19,10 @@
"EventName": "PM_DTLB_MISS_2M",
"BriefDescription": "Data TLB reload (after a miss) page size 2M. Implies radix translation was used. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
},
- {
- "EventCode": "0x1E056",
- "EventName": "PM_EXEC_STALL_STORE_PIPE",
- "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the store unit. This does not include cycles spent handling store misses, PTESYNC instructions or TLBIE instructions."
- },
- {
- "EventCode": "0x1F150",
- "EventName": "PM_MRK_ST_L2_CYC",
- "BriefDescription": "Cycles from L2 RC dispatch to L2 RC completion."
- },
{
"EventCode": "0x10062",
"EventName": "PM_LD_L3MISS_PEND_CYC",
- "BriefDescription": "Cycles L3 miss was pending for this thread."
- },
- {
- "EventCode": "0x20010",
- "EventName": "PM_PMC1_OVERFLOW",
- "BriefDescription": "The event selected for PMC1 caused the event counter to overflow."
+ "BriefDescription": "Cycles in which an L3 miss was pending for this thread."
},
{
"EventCode": "0x2001A",
@@ -79,36 +49,16 @@
"EventName": "PM_DTLB_MISS_4K",
"BriefDescription": "Data TLB reload (after a miss) page size 4K. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
},
- {
- "EventCode": "0x2D154",
- "EventName": "PM_MRK_DERAT_MISS_64K",
- "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 64K for a marked instruction. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
- },
{
"EventCode": "0x200F6",
"EventName": "PM_DERAT_MISS",
"BriefDescription": "DERAT Reloaded to satisfy a DERAT miss. All page sizes are counted by this event. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
},
- {
- "EventCode": "0x30016",
- "EventName": "PM_EXEC_STALL_DERAT_DTLB_MISS",
- "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered a TLB miss and waited for it resolve."
- },
{
"EventCode": "0x3C040",
"EventName": "PM_XFER_FROM_SRC_PMC3",
"BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[30:42]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
},
- {
- "EventCode": "0x3C142",
- "EventName": "PM_MRK_XFER_FROM_SRC_PMC3",
- "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[30:42]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
- },
- {
- "EventCode": "0x3C144",
- "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC3",
- "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[30:42]."
- },
{
"EventCode": "0x3C054",
"EventName": "PM_DERAT_MISS_16M",
@@ -124,41 +74,21 @@
"EventName": "PM_LARX_FIN",
"BriefDescription": "Load and reserve instruction (LARX) finished. LARX and STCX are instructions used to acquire a lock."
},
- {
- "EventCode": "0x301E2",
- "EventName": "PM_MRK_ST_CMPL",
- "BriefDescription": "Marked store completed and sent to nest. Note that this count excludes cache-inhibited stores."
- },
{
"EventCode": "0x300FC",
"EventName": "PM_DTLB_MISS",
- "BriefDescription": "The DPTEG required for the load/store instruction in execution was missing from the TLB. It includes pages of all sizes for demand and prefetch activity."
- },
- {
- "EventCode": "0x4D02C",
- "EventName": "PM_PMC1_REWIND",
- "BriefDescription": "The speculative event selected for PMC1 rewinds and the counter for PMC1 is not charged."
+ "BriefDescription": "The DPTEG required for the load/store instruction in execution was missing from the TLB. This event only counts for demand misses."
},
{
"EventCode": "0x4003E",
"EventName": "PM_LD_CMPL",
- "BriefDescription": "Loads completed."
+ "BriefDescription": "Load instruction completed."
},
{
"EventCode": "0x4C040",
"EventName": "PM_XFER_FROM_SRC_PMC4",
"BriefDescription": "The processor's L1 data cache was reloaded from the source specified in MMCR3[45:57]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
},
- {
- "EventCode": "0x4C142",
- "EventName": "PM_MRK_XFER_FROM_SRC_PMC4",
- "BriefDescription": "For a marked data transfer instruction, the processor's L1 data cache was reloaded from the source specified in MMCR3[45:57]. If MMCR1[16|17] is 0 (default), this count includes only lines that were reloaded to satisfy a demand miss. If MMCR1[16|17] is 1, this count includes both demand misses and prefetch reloads."
- },
- {
- "EventCode": "0x4C144",
- "EventName": "PM_MRK_XFER_FROM_SRC_CYC_PMC4",
- "BriefDescription": "Cycles taken for a marked demand miss to reload a line from the source specified in MMCR3[45:57]."
- },
{
"EventCode": "0x4C056",
"EventName": "PM_DTLB_MISS_16M",
@@ -168,20 +98,5 @@
"EventCode": "0x4C05A",
"EventName": "PM_DTLB_MISS_1G",
"BriefDescription": "Data TLB reload (after a miss) page size 1G. Implies radix translation was used. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
- },
- {
- "EventCode": "0x4C15E",
- "EventName": "PM_MRK_DTLB_MISS_64K",
- "BriefDescription": "Marked Data TLB reload (after a miss) page size 64K. When MMCR1[16]=0 this event counts only for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
- },
- {
- "EventCode": "0x4D056",
- "EventName": "PM_NON_FMA_FLOP_CMPL",
- "BriefDescription": "Non FMA instruction completed."
- },
- {
- "EventCode": "0x40164",
- "EventName": "PM_MRK_DERAT_MISS_2M",
- "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 2M for a marked instruction. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
}
]
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/metrics.json b/tools/perf/pmu-events/arch/powerpc/power10/metrics.json
index 6f53583a0c62..182369076d95 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/metrics.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/metrics.json
@@ -16,133 +16,133 @@
"BriefDescription": "Average cycles per completed instruction when dispatch was stalled for any reason",
"MetricExpr": "PM_DISP_STALL_CYC / PM_RUN_INST_CMPL",
"MetricGroup": "CPI;CPI_STALL_RATIO",
- "MetricName": "DISPATCHED_CPI"
+ "MetricName": "DISPATCH_STALL_CPI"
},
{
"BriefDescription": "Average cycles per completed instruction when dispatch was stalled because there was a flush",
"MetricExpr": "PM_DISP_STALL_FLUSH / PM_RUN_INST_CMPL",
"MetricGroup": "CPI",
- "MetricName": "DISPATCHED_FLUSH_CPI"
+ "MetricName": "DISPATCH_STALL_FLUSH_CPI"
},
{
"BriefDescription": "Average cycles per completed instruction when dispatch was stalled because the MMU was handling a translation miss",
"MetricExpr": "PM_DISP_STALL_TRANSLATION / PM_RUN_INST_CMPL",
"MetricGroup": "CPI",
- "MetricName": "DISPATCHED_TRANSLATION_CPI"
+ "MetricName": "DISPATCH_STALL_TRANSLATION_CPI"
},
{
"BriefDescription": "Average cycles per completed instruction when dispatch was stalled waiting to resolve an instruction ERAT miss",
"MetricExpr": "PM_DISP_STALL_IERAT_ONLY_MISS / PM_RUN_INST_CMPL",
"MetricGroup": "CPI",
- "MetricName": "DISPATCHED_IERAT_ONLY_MISS_CPI"
+ "MetricName": "DISPATCH_STALL_IERAT_ONLY_MISS_CPI"
},
{
"BriefDescription": "Average cycles per completed instruction when dispatch was stalled waiting to resolve an instruction TLB miss",
"MetricExpr": "PM_DISP_STALL_ITLB_MISS / PM_RUN_INST_CMPL",
"MetricGroup": "CPI",
- "MetricName": "DISPATCHED_ITLB_MISS_CPI"
+ "MetricName": "DISPATCH_STALL_ITLB_MISS_CPI"
},
{
"BriefDescription": "Average cycles per completed instruction when dispatch was stalled due to an icache miss",
"MetricExpr": "PM_DISP_STALL_IC_MISS / PM_RUN_INST_CMPL",
"MetricGroup": "CPI",
- "MetricName": "DISPATCHED_IC_MISS_CPI"
+ "MetricName": "DISPATCH_STALL_IC_MISS_CPI"
},
{
"BriefDescription": "Average cycles per completed instruction when dispatch was stalled while the instruction was fetched from the local L2",
"MetricExpr": "PM_DISP_STALL_IC_L2 / PM_RUN_INST_CMPL",
"MetricGroup": "CPI",
- "MetricName": "DISPATCHED_IC_L2_CPI"
+ "MetricName": "DISPATCH_STALL_IC_L2_CPI"
},
{
"BriefDescription": "Average cycles per completed instruction when dispatch was stalled while the instruction was fetched from the local L3",
"MetricExpr": "PM_DISP_STALL_IC_L3 / PM_RUN_INST_CMPL",
"MetricGroup": "CPI",
- "MetricName": "DISPATCHED_IC_L3_CPI"
+ "MetricName": "DISPATCH_STALL_IC_L3_CPI"
},
{
"BriefDescription": "Average cycles per completed instruction when dispatch was stalled while the instruction was fetched from any source beyond the local L3",
"MetricExpr": "PM_DISP_STALL_IC_L3MISS / PM_RUN_INST_CMPL",
"MetricGroup": "CPI",
- "MetricName": "DISPATCHED_IC_L3MISS_CPI"
+ "MetricName": "DISPATCH_STALL_IC_L3MISS_CPI"
},
{
"BriefDescription": "Average cycles per completed instruction when dispatch was stalled due to an icache miss after a branch mispredict",
"MetricExpr": "PM_DISP_STALL_BR_MPRED_ICMISS / PM_RUN_INST_CMPL",
"MetricGroup": "CPI",
- "MetricName": "DISPATCHED_BR_MPRED_ICMISS_CPI"
+ "MetricName": "DISPATCH_STALL_BR_MPRED_ICMISS_CPI"
},
{
"BriefDescription": "Average cycles per completed instruction when dispatch was stalled while instruction was fetched from the local L2 after suffering a branch mispredict",
"MetricExpr": "PM_DISP_STALL_BR_MPRED_IC_L2 / PM_RUN_INST_CMPL",
"MetricGroup": "CPI",
- "MetricName": "DISPATCHED_BR_MPRED_IC_L2_CPI"
+ "MetricName": "DISPATCH_STALL_BR_MPRED_IC_L2_CPI"
},
{
"BriefDescription": "Average cycles per completed instruction when dispatch was stalled while instruction was fetched from the local L3 after suffering a branch mispredict",
"MetricExpr": "PM_DISP_STALL_BR_MPRED_IC_L3 / PM_RUN_INST_CMPL",
"MetricGroup": "CPI",
- "MetricName": "DISPATCHED_BR_MPRED_IC_L3_CPI"
+ "MetricName": "DISPATCH_STALL_BR_MPRED_IC_L3_CPI"
},
{
"BriefDescription": "Average cycles per completed instruction when dispatch was stalled while instruction was fetched from any source beyond the local L3 after suffering a branch mispredict",
"MetricExpr": "PM_DISP_STALL_BR_MPRED_IC_L3MISS / PM_RUN_INST_CMPL",
"MetricGroup": "CPI",
- "MetricName": "DISPATCHED_BR_MPRED_IC_L3MISS_CPI"
+ "MetricName": "DISPATCH_STALL_BR_MPRED_IC_L3MISS_CPI"
},
{
"BriefDescription": "Average cycles per completed instruction when dispatch was stalled due to a branch mispredict",
"MetricExpr": "PM_DISP_STALL_BR_MPRED / PM_RUN_INST_CMPL",
"MetricGroup": "CPI",
- "MetricName": "DISPATCHED_BR_MPRED_CPI"
+ "MetricName": "DISPATCH_STALL_BR_MPRED_CPI"
},
{
"BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch for any reason",
"MetricExpr": "PM_DISP_STALL_HELD_CYC / PM_RUN_INST_CMPL",
"MetricGroup": "CPI",
- "MetricName": "DISPATCHED_HELD_CPI"
+ "MetricName": "DISPATCH_STALL_HELD_CPI"
},
{
"BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch",
"MetricExpr": "PM_DISP_STALL_HELD_SYNC_CYC / PM_RUN_INST_CMPL",
"MetricGroup": "CPI",
- "MetricName": "DISP_HELD_STALL_SYNC_CPI"
+ "MetricName": "DISPATCH_STALL_HELD_SYNC_CPI"
},
{
"BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch while waiting on the scoreboard",
"MetricExpr": "PM_DISP_STALL_HELD_SCOREBOARD_CYC / PM_RUN_INST_CMPL",
"MetricGroup": "CPI",
- "MetricName": "DISP_HELD_STALL_SCOREBOARD_CPI"
+ "MetricName": "DISPATCH_STALL_HELD_SCOREBOARD_CPI"
},
{
"BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch due to issue queue full",
"MetricExpr": "PM_DISP_STALL_HELD_ISSQ_FULL_CYC / PM_RUN_INST_CMPL",
"MetricGroup": "CPI",
- "MetricName": "DISP_HELD_STALL_ISSQ_FULL_CPI"
+ "MetricName": "DISPATCH_STALL_HELD_ISSQ_FULL_CPI"
},
{
"BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because the mapper/SRB was full",
"MetricExpr": "PM_DISP_STALL_HELD_RENAME_CYC / PM_RUN_INST_CMPL",
"MetricGroup": "CPI",
- "MetricName": "DISPATCHED_HELD_RENAME_CPI"
+ "MetricName": "DISPATCH_STALL_HELD_RENAME_CPI"
},
{
"BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because the STF mapper/SRB was full",
"MetricExpr": "PM_DISP_STALL_HELD_STF_MAPPER_CYC / PM_RUN_INST_CMPL",
"MetricGroup": "CPI",
- "MetricName": "DISPATCHED_HELD_STF_MAPPER_CPI"
+ "MetricName": "DISPATCH_STALL_HELD_STF_MAPPER_CPI"
},
{
"BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because the XVFC mapper/SRB was full",
"MetricExpr": "PM_DISP_STALL_HELD_XVFC_MAPPER_CYC / PM_RUN_INST_CMPL",
"MetricGroup": "CPI",
- "MetricName": "DISPATCHED_HELD_XVFC_MAPPER_CPI"
+ "MetricName": "DISPATCH_STALL_HELD_XVFC_MAPPER_CPI"
},
{
"BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch for any other reason",
"MetricExpr": "PM_DISP_STALL_HELD_OTHER_CYC / PM_RUN_INST_CMPL",
"MetricGroup": "CPI",
- "MetricName": "DISPATCHED_HELD_OTHER_CPI"
+ "MetricName": "DISPATCH_STALL_HELD_OTHER_CPI"
},
{
"BriefDescription": "Average cycles per completed instruction when the NTC instruction has been dispatched but not issued for any reason",
@@ -352,13 +352,13 @@
"BriefDescription": "Average cycles per completed instruction when dispatch was stalled because fetch was being held, so there was nothing in the pipeline for this thread",
"MetricExpr": "PM_DISP_STALL_FETCH / PM_RUN_INST_CMPL",
"MetricGroup": "CPI",
- "MetricName": "DISPATCHED_FETCH_CPI"
+ "MetricName": "DISPATCH_STALL_FETCH_CPI"
},
{
"BriefDescription": "Average cycles per completed instruction when the NTC instruction was held at dispatch because of power management",
"MetricExpr": "PM_DISP_STALL_HELD_HALT_CYC / PM_RUN_INST_CMPL",
"MetricGroup": "CPI",
- "MetricName": "DISPATCHED_HELD_HALT_CPI"
+ "MetricName": "DISPATCH_STALL_HELD_HALT_CPI"
},
{
"BriefDescription": "Percentage of flushes per completed instruction",
@@ -453,12 +453,6 @@
"MetricGroup": "General",
"MetricName": "LOADS_PER_INST"
},
- {
- "BriefDescription": "Average number of finished stores per completed instruction",
- "MetricExpr": "PM_ST_FIN / PM_RUN_INST_CMPL",
- "MetricGroup": "General",
- "MetricName": "STORES_PER_INST"
- },
{
"BriefDescription": "Percentage of demand loads that reloaded from beyond the L2 per completed instruction",
"MetricExpr": "PM_DATA_FROM_L2MISS / PM_RUN_INST_CMPL * 100",
@@ -566,7 +560,7 @@
"BriefDescription": "Average number of STCX instructions finshed per completed instruction",
"MetricExpr": "PM_STCX_FIN / PM_RUN_INST_CMPL",
"MetricGroup": "General",
- "MetricName": "STXC_PER_INST"
+ "MetricName": "STCX_PER_INST"
},
{
"BriefDescription": "Average number of LARX instructions finshed per completed instruction",
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/others.json b/tools/perf/pmu-events/arch/powerpc/power10/others.json
index a771e4b6bec5..f09c00c89322 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/others.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/others.json
@@ -1,104 +1,39 @@
[
{
- "EventCode": "0x10016",
- "EventName": "PM_VSU0_ISSUE",
- "BriefDescription": "VSU instructions issued to VSU pipe 0."
- },
- {
- "EventCode": "0x1001C",
- "EventName": "PM_ULTRAVISOR_INST_CMPL",
- "BriefDescription": "PowerPC instructions that completed while the thread was in ultravisor state."
- },
- {
- "EventCode": "0x100F0",
- "EventName": "PM_CYC",
- "BriefDescription": "Processor cycles."
- },
- {
- "EventCode": "0x10134",
- "EventName": "PM_MRK_ST_DONE_L2",
- "BriefDescription": "Marked stores completed in L2 (RC machine done)."
+ "EventCode": "0x1002C",
+ "EventName": "PM_LD_PREFETCH_CACHE_LINE_MISS",
+ "BriefDescription": "The L1 cache was reloaded with a line that fulfills a prefetch request."
},
{
"EventCode": "0x1505E",
"EventName": "PM_LD_HIT_L1",
- "BriefDescription": "Loads that finished without experiencing an L1 miss."
+ "BriefDescription": "Load finished without experiencing an L1 miss."
},
{
"EventCode": "0x1F056",
"EventName": "PM_DISP_SS0_2_INSTR_CYC",
"BriefDescription": "Cycles in which Superslice 0 dispatches either 1 or 2 instructions."
},
- {
- "EventCode": "0x1F15C",
- "EventName": "PM_MRK_STCX_L2_CYC",
- "BriefDescription": "Cycles spent in the nest portion of a marked Stcx instruction. It starts counting when the operation starts to drain to the L2 and it stops counting when the instruction retires from the Instruction Completion Table (ICT) in the Instruction Sequencing Unit (ISU)."
- },
{
"EventCode": "0x10066",
"EventName": "PM_ADJUNCT_CYC",
"BriefDescription": "Cycles in which the thread is in Adjunct state. MSR[S HV PR] bits = 011."
},
- {
- "EventCode": "0x101E4",
- "EventName": "PM_MRK_L1_ICACHE_MISS",
- "BriefDescription": "Marked Instruction suffered an icache Miss."
- },
- {
- "EventCode": "0x101EA",
- "EventName": "PM_MRK_L1_RELOAD_VALID",
- "BriefDescription": "Marked demand reload."
- },
- {
- "EventCode": "0x100F4",
- "EventName": "PM_FLOP_CMPL",
- "BriefDescription": "Floating Point Operations Completed. Includes any type. It counts once for each 1, 2, 4 or 8 flop instruction. Use PM_1|2|4|8_FLOP_CMPL events to count flops."
- },
- {
- "EventCode": "0x100FA",
- "EventName": "PM_RUN_LATCH_ANY_THREAD_CYC",
- "BriefDescription": "Cycles when at least one thread has the run latch set."
- },
{
"EventCode": "0x100FC",
"EventName": "PM_LD_REF_L1",
"BriefDescription": "All L1 D cache load references counted at finish, gated by reject. In P9 and earlier this event counted only cacheable loads but in P10 both cacheable and non-cacheable loads are included."
},
- {
- "EventCode": "0x2000C",
- "EventName": "PM_RUN_LATCH_ALL_THREADS_CYC",
- "BriefDescription": "Cycles when the run latch is set for all threads."
- },
{
"EventCode": "0x2E010",
"EventName": "PM_ADJUNCT_INST_CMPL",
- "BriefDescription": "PowerPC instructions that completed while the thread is in Adjunct state."
+ "BriefDescription": "PowerPC instruction completed while the thread was in Adjunct state."
},
{
"EventCode": "0x2E014",
"EventName": "PM_STCX_FIN",
"BriefDescription": "Conditional store instruction (STCX) finished. LARX and STCX are instructions used to acquire a lock."
},
- {
- "EventCode": "0x20130",
- "EventName": "PM_MRK_INST_DECODED",
- "BriefDescription": "An instruction was marked at decode time. Random Instruction Sampling (RIS) only."
- },
- {
- "EventCode": "0x20132",
- "EventName": "PM_MRK_DFU_ISSUE",
- "BriefDescription": "The marked instruction was a decimal floating point operation issued to the VSU. Measured at issue time."
- },
- {
- "EventCode": "0x20134",
- "EventName": "PM_MRK_FXU_ISSUE",
- "BriefDescription": "The marked instruction was a fixed point operation issued to the VSU. Measured at issue time."
- },
- {
- "EventCode": "0x2505C",
- "EventName": "PM_VSU_ISSUE",
- "BriefDescription": "At least one VSU instruction was issued to one of the VSU pipes. Up to 4 per cycle. Includes fixed point operations."
- },
{
"EventCode": "0x2F054",
"EventName": "PM_DISP_SS1_2_INSTR_CYC",
@@ -109,40 +44,15 @@
"EventName": "PM_DISP_SS1_4_INSTR_CYC",
"BriefDescription": "Cycles in which Superslice 1 dispatches either 3 or 4 instructions."
},
- {
- "EventCode": "0x2006C",
- "EventName": "PM_RUN_CYC_SMT4_MODE",
- "BriefDescription": "Cycles when this thread's run latch is set and the core is in SMT4 mode."
- },
- {
- "EventCode": "0x201E0",
- "EventName": "PM_MRK_DATA_FROM_MEMORY",
- "BriefDescription": "The processor's data cache was reloaded from local, remote, or distant memory due to a demand miss for a marked load."
- },
- {
- "EventCode": "0x201E4",
- "EventName": "PM_MRK_DATA_FROM_L3MISS",
- "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss for a marked load."
- },
- {
- "EventCode": "0x201E8",
- "EventName": "PM_THRESH_EXC_512",
- "BriefDescription": "Threshold counter exceeded a value of 512."
- },
{
"EventCode": "0x200F2",
"EventName": "PM_INST_DISP",
- "BriefDescription": "PowerPC instructions dispatched."
- },
- {
- "EventCode": "0x30132",
- "EventName": "PM_MRK_VSU_FIN",
- "BriefDescription": "VSU marked instructions finished. Excludes simple FX instructions issued to the Store Unit."
+ "BriefDescription": "PowerPC instruction dispatched."
},
{
- "EventCode": "0x30038",
- "EventName": "PM_EXEC_STALL_DMISS_LMEM",
- "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local memory, local OpenCapp cache, or local OpenCapp memory."
+ "EventCode": "0x200FD",
+ "EventName": "PM_L1_ICACHE_MISS",
+ "BriefDescription": "Demand instruction cache miss."
},
{
"EventCode": "0x3F04A",
@@ -152,12 +62,7 @@
{
"EventCode": "0x3405A",
"EventName": "PM_PRIVILEGED_INST_CMPL",
- "BriefDescription": "PowerPC Instructions that completed while the thread is in Privileged state."
- },
- {
- "EventCode": "0x3F150",
- "EventName": "PM_MRK_ST_DRAIN_CYC",
- "BriefDescription": "cycles to drain st from core to L2."
+ "BriefDescription": "PowerPC instruction completed while the thread was in Privileged state."
},
{
"EventCode": "0x3F054",
@@ -170,103 +75,43 @@
"BriefDescription": "Cycles in which Superslice 0 dispatches either 5, 6, 7 or 8 instructions."
},
{
- "EventCode": "0x30162",
- "EventName": "PM_MRK_ISSUE_DEPENDENT_LOAD",
- "BriefDescription": "The marked instruction was dependent on a load. It is eligible for issue kill."
- },
- {
- "EventCode": "0x40114",
- "EventName": "PM_MRK_START_PROBE_NOP_DISP",
- "BriefDescription": "Marked Start probe nop dispatched. Instruction AND R0,R0,R0."
- },
- {
- "EventCode": "0x4001C",
- "EventName": "PM_VSU_FIN",
- "BriefDescription": "VSU instructions finished."
- },
- {
- "EventCode": "0x4C01A",
- "EventName": "PM_EXEC_STALL_DMISS_OFF_NODE",
- "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a distant chip."
- },
- {
- "EventCode": "0x4D012",
- "EventName": "PM_PMC3_SAVED",
- "BriefDescription": "The conditions for the speculative event selected for PMC3 are met and PMC3 is charged."
+ "EventCode": "0x30068",
+ "EventName": "PM_L1_ICACHE_RELOADED_PREF",
+ "BriefDescription": "Counts all instruction cache prefetch reloads (includes demand turned into prefetch)."
},
{
- "EventCode": "0x4D022",
- "EventName": "PM_HYPERVISOR_INST_CMPL",
- "BriefDescription": "PowerPC instructions that completed while the thread is in hypervisor state."
+ "EventCode": "0x300F6",
+ "EventName": "PM_LD_DEMAND_MISS_L1",
+ "BriefDescription": "The L1 cache was reloaded with a line that fulfills a demand miss request. Counted at reload time, before finish."
},
{
- "EventCode": "0x4D026",
- "EventName": "PM_ULTRAVISOR_CYC",
- "BriefDescription": "Cycles when the thread is in Ultravisor state. MSR[S HV PR]=110."
+ "EventCode": "0x300FE",
+ "EventName": "PM_DATA_FROM_L3MISS",
+ "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss."
},
{
- "EventCode": "0x4D028",
- "EventName": "PM_PRIVILEGED_CYC",
- "BriefDescription": "Cycles when the thread is in Privileged state. MSR[S HV PR]=x00."
- },
- {
- "EventCode": "0x40030",
- "EventName": "PM_INST_FIN",
- "BriefDescription": "Instructions finished."
- },
- {
- "EventCode": "0x44146",
- "EventName": "PM_MRK_STCX_CORE_CYC",
- "BriefDescription": "Cycles spent in the core portion of a marked Stcx instruction. It starts counting when the instruction is decoded and stops counting when it drains into the L2."
+ "EventCode": "0x40012",
+ "EventName": "PM_L1_ICACHE_RELOADED_ALL",
+ "BriefDescription": "Counts all instruction cache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch."
},
{
"EventCode": "0x44054",
"EventName": "PM_VECTOR_LD_CMPL",
- "BriefDescription": "Vector load instructions completed."
- },
- {
- "EventCode": "0x45054",
- "EventName": "PM_FMA_CMPL",
- "BriefDescription": "Two floating point instructions completed (FMA class of instructions: fmadd, fnmadd, fmsub, fnmsub). Scalar instructions only."
- },
- {
- "EventCode": "0x45056",
- "EventName": "PM_SCALAR_FLOP_CMPL",
- "BriefDescription": "Scalar floating point instructions completed."
- },
- {
- "EventCode": "0x4505C",
- "EventName": "PM_MATH_FLOP_CMPL",
- "BriefDescription": "Math floating point instructions completed."
+ "BriefDescription": "Vector load instruction completed."
},
{
"EventCode": "0x4D05E",
"EventName": "PM_BR_CMPL",
"BriefDescription": "A branch completed. All branches are included."
},
- {
- "EventCode": "0x4E15E",
- "EventName": "PM_MRK_INST_FLUSHED",
- "BriefDescription": "The marked instruction was flushed."
- },
- {
- "EventCode": "0x401E6",
- "EventName": "PM_MRK_INST_FROM_L3MISS",
- "BriefDescription": "The processor's instruction cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss for a marked instruction."
- },
- {
- "EventCode": "0x401E8",
- "EventName": "PM_MRK_DATA_FROM_L2MISS",
- "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1 or L2 due to a demand miss for a marked load."
- },
{
"EventCode": "0x400F0",
"EventName": "PM_LD_DEMAND_MISS_L1_FIN",
- "BriefDescription": "Load Missed L1, counted at finish time."
+ "BriefDescription": "Load missed L1, counted at finish time."
},
{
- "EventCode": "0x500FA",
- "EventName": "PM_RUN_INST_CMPL",
- "BriefDescription": "Completed PowerPC instructions gated by the run latch."
+ "EventCode": "0x400FE",
+ "EventName": "PM_DATA_FROM_MEMORY",
+ "BriefDescription": "The processor's data cache was reloaded from local, remote, or distant memory due to a demand miss."
}
]
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json b/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json
index b8aded6045fa..a8272a2f0517 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/pipeline.json
@@ -1,8 +1,13 @@
[
{
- "EventCode": "0x100FE",
- "EventName": "PM_INST_CMPL",
- "BriefDescription": "PowerPC instructions completed."
+ "EventCode": "0x10004",
+ "EventName": "PM_EXEC_STALL_TRANSLATION",
+ "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered a TLB miss or ERAT miss and waited for it to resolve."
+ },
+ {
+ "EventCode": "0x10006",
+ "EventName": "PM_DISP_STALL_HELD_OTHER_CYC",
+ "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch for any other reason."
},
{
"EventCode": "0x1000C",
@@ -12,7 +17,7 @@
{
"EventCode": "0x1000E",
"EventName": "PM_MMA_ISSUED",
- "BriefDescription": "MMA instructions issued."
+ "BriefDescription": "MMA instruction issued."
},
{
"EventCode": "0x10012",
@@ -30,14 +35,19 @@
"BriefDescription": "Cycles in which an instruction reload is pending to satisfy a demand miss."
},
{
- "EventCode": "0x10022",
- "EventName": "PM_PMC2_SAVED",
- "BriefDescription": "The conditions for the speculative event selected for PMC2 are met and PMC2 is charged."
+ "EventCode": "0x10038",
+ "EventName": "PM_DISP_STALL_TRANSLATION",
+ "BriefDescription": "Cycles when dispatch was stalled for this thread because the MMU was handling a translation miss."
},
{
- "EventCode": "0x10024",
- "EventName": "PM_PMC5_OVERFLOW",
- "BriefDescription": "The event selected for PMC5 caused the event counter to overflow."
+ "EventCode": "0x1003A",
+ "EventName": "PM_DISP_STALL_BR_MPRED_IC_L2",
+ "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L2 after suffering a branch mispredict."
+ },
+ {
+ "EventCode": "0x1003C",
+ "EventName": "PM_EXEC_STALL_DMISS_L2L3",
+ "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from either the local L2 or local L3."
},
{
"EventCode": "0x10058",
@@ -54,11 +64,36 @@
"EventName": "PM_DERAT_MISS_2M",
"BriefDescription": "Data ERAT Miss (Data TLB Access) page size 2M. Implies radix translation. When MMCR1[16]=0 this event counts only DERAT reloads for demand misses. When MMCR1[16]=1 this event includes demand misses and prefetches."
},
+ {
+ "EventCode": "0x1D05E",
+ "EventName": "PM_DISP_STALL_HELD_HALT_CYC",
+ "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because of power management."
+ },
+ {
+ "EventCode": "0x1E050",
+ "EventName": "PM_DISP_STALL_HELD_STF_MAPPER_CYC",
+ "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because the STF mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR."
+ },
+ {
+ "EventCode": "0x1E054",
+ "EventName": "PM_EXEC_STALL_DMISS_L21_L31",
+ "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from another core's L2 or L3 on the same chip."
+ },
+ {
+ "EventCode": "0x1E056",
+ "EventName": "PM_EXEC_STALL_STORE_PIPE",
+ "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the store unit. This does not include cycles spent handling store misses, PTESYNC instructions or TLBIE instructions."
+ },
{
"EventCode": "0x1E05A",
"EventName": "PM_CMPL_STALL_LWSYNC",
"BriefDescription": "Cycles in which the oldest instruction in the pipeline was a lwsync waiting to complete."
},
+ {
+ "EventCode": "0x10064",
+ "EventName": "PM_DISP_STALL_IC_L2",
+ "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L2."
+ },
{
"EventCode": "0x10068",
"EventName": "PM_BR_FIN",
@@ -70,9 +105,9 @@
"BriefDescription": "Simple fixed point instruction issued to the store unit. Measured at finish time."
},
{
- "EventCode": "0x1006C",
- "EventName": "PM_RUN_CYC_ST_MODE",
- "BriefDescription": "Cycles when the run latch is set and the core is in ST mode."
+ "EventCode": "0x100F8",
+ "EventName": "PM_DISP_STALL_CYC",
+ "BriefDescription": "Cycles the ICT has no itags assigned to this thread (no instructions were dispatched during these cycles)."
},
{
"EventCode": "0x20004",
@@ -80,54 +115,104 @@
"BriefDescription": "Cycles in which the oldest instruction in the pipeline was dispatched but not issued yet."
},
{
- "EventCode": "0x2000A",
- "EventName": "PM_HYPERVISOR_CYC",
- "BriefDescription": "Cycles when the thread is in Hypervisor state. MSR[S HV PR]=010."
+ "EventCode": "0x20006",
+ "EventName": "PM_DISP_STALL_HELD_ISSQ_FULL_CYC",
+ "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch due to Issue queue full. Includes issue queue and branch queue."
},
{
"EventCode": "0x2000E",
"EventName": "PM_LSU_LD1_FIN",
"BriefDescription": "LSU Finished an internal operation in LD1 port."
},
+ {
+ "EventCode": "0x2C010",
+ "EventName": "PM_EXEC_STALL_LSU",
+ "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the Load Store Unit. This does not include simple fixed point instructions."
+ },
{
"EventCode": "0x2C014",
"EventName": "PM_CMPL_STALL_SPECIAL",
"BriefDescription": "Cycles in which the oldest instruction in the pipeline required special handling before completing."
},
+ {
+ "EventCode": "0x2C016",
+ "EventName": "PM_DISP_STALL_IERAT_ONLY_MISS",
+ "BriefDescription": "Cycles when dispatch was stalled while waiting to resolve an instruction ERAT miss."
+ },
{
"EventCode": "0x2C018",
"EventName": "PM_EXEC_STALL_DMISS_L3MISS",
"BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a source beyond the local L2 or local L3."
},
+ {
+ "EventCode": "0x2C01C",
+ "EventName": "PM_EXEC_STALL_DMISS_OFF_CHIP",
+ "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a remote chip."
+ },
+ {
+ "EventCode": "0x2C01E",
+ "EventName": "PM_DISP_STALL_BR_MPRED_IC_L3",
+ "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L3 after suffering a branch mispredict."
+ },
{
"EventCode": "0x2D010",
"EventName": "PM_LSU_ST1_FIN",
"BriefDescription": "LSU Finished an internal operation in ST1 port."
},
+ {
+ "EventCode": "0x10016",
+ "EventName": "PM_VSU0_ISSUE",
+ "BriefDescription": "VSU instruction issued to VSU pipe 0."
+ },
{
"EventCode": "0x2D012",
"EventName": "PM_VSU1_ISSUE",
- "BriefDescription": "VSU instructions issued to VSU pipe 1."
+ "BriefDescription": "VSU instruction issued to VSU pipe 1."
+ },
+ {
+ "EventCode": "0x2505C",
+ "EventName": "PM_VSU_ISSUE",
+ "BriefDescription": "At least one VSU instruction was issued to one of the VSU pipes. Up to 4 per cycle. Includes fixed point operations."
+ },
+ {
+ "EventCode": "0x4001C",
+ "EventName": "PM_VSU_FIN",
+ "BriefDescription": "VSU instruction finished."
},
{
"EventCode": "0x2D018",
"EventName": "PM_EXEC_STALL_VSU",
"BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in the VSU (includes FXU, VSU, CRU)."
},
+ {
+ "EventCode": "0x2D01A",
+ "EventName": "PM_DISP_STALL_IC_MISS",
+ "BriefDescription": "Cycles when dispatch was stalled for this thread due to an instruction cache miss."
+ },
{
"EventCode": "0x2D01C",
"EventName": "PM_CMPL_STALL_STCX",
"BriefDescription": "Cycles in which the oldest instruction in the pipeline was a stcx waiting for resolution from the nest before completing."
},
{
- "EventCode": "0x2E01E",
- "EventName": "PM_EXEC_STALL_NTC_FLUSH",
- "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in any unit before it was flushed. Note that if the flush of the oldest instruction happens after finish, the cycles from dispatch to issue will be included in PM_DISP_STALL and the cycles from issue to finish will be included in PM_EXEC_STALL and its corresponding children. This event will also count cycles when the previous NTF instruction is still completing and the new NTF instruction is stalled at dispatch."
+ "EventCode": "0x2E018",
+ "EventName": "PM_DISP_STALL_FETCH",
+ "BriefDescription": "Cycles when dispatch was stalled for this thread because Fetch was being held."
+ },
+ {
+ "EventCode": "0x2E01A",
+ "EventName": "PM_DISP_STALL_HELD_XVFC_MAPPER_CYC",
+ "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because the XVFC mapper/SRB was full."
},
{
- "EventCode": "0x2013C",
- "EventName": "PM_MRK_FX_LSU_FIN",
- "BriefDescription": "The marked instruction was simple fixed point that was issued to the store unit. Measured at finish time."
+ "EventCode": "0x2E01C",
+ "EventName": "PM_EXEC_STALL_TLBIE",
+ "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a TLBIE instruction executing in the Load Store Unit."
+ },
+ {
+ "EventCode": "0x2E01E",
+ "EventName": "PM_EXEC_STALL_NTC_FLUSH",
+ "BriefDescription": "Cycles in which the oldest instruction in the pipeline was executing in any unit before it was flushed. Note that if the flush of the oldest instruction happens after finish, the cycles from dispatch to issue will be included in PM_DISP_STALL and the cycles from issue to finish will be included in PM_EXEC_STALL and its corresponding children. This event will also count cycles when the previous next-to-finish (NTF) instruction is still completing and the new NTF instruction is stalled at dispatch."
},
{
"EventCode": "0x2405A",
@@ -135,14 +220,9 @@
"BriefDescription": "Cycles in which the oldest instruction in the pipeline (NTC) finishes. Note that instructions can finish out of order, therefore not all the instructions that finish have a Next-to-complete status."
},
{
- "EventCode": "0x201E2",
- "EventName": "PM_MRK_LD_MISS_L1",
- "BriefDescription": "Marked DL1 Demand Miss counted at finish time."
- },
- {
- "EventCode": "0x200F4",
- "EventName": "PM_RUN_CYC",
- "BriefDescription": "Processor cycles gated by the run latch."
+ "EventCode": "0x30004",
+ "EventName": "PM_DISP_STALL_FLUSH",
+ "BriefDescription": "Cycles when dispatch was stalled because of a flush that happened to an instruction(s) that was not yet next-to-complete (NTC). PM_EXEC_STALL_NTC_FLUSH only includes instructions that were flushed after becoming NTC."
},
{
"EventCode": "0x30008",
@@ -150,35 +230,45 @@
"BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting to finish in one of the execution units (BRU, LSU, VSU). Only cycles between issue and finish are counted in this category."
},
{
- "EventCode": "0x3001A",
- "EventName": "PM_LSU_ST2_FIN",
- "BriefDescription": "LSU Finished an internal operation in ST2 port."
+ "EventCode": "0x30014",
+ "EventName": "PM_EXEC_STALL_STORE",
+ "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a store instruction executing in the Load Store Unit."
},
{
- "EventCode": "0x30020",
- "EventName": "PM_PMC2_REWIND",
- "BriefDescription": "The speculative event selected for PMC2 rewinds and the counter for PMC2 is not charged."
+ "EventCode": "0x30016",
+ "EventName": "PM_EXEC_STALL_DERAT_DTLB_MISS",
+ "BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered a TLB miss and waited for it resolve."
},
{
- "EventCode": "0x30022",
- "EventName": "PM_PMC4_SAVED",
- "BriefDescription": "The conditions for the speculative event selected for PMC4 are met and PMC4 is charged."
+ "EventCode": "0x30018",
+ "EventName": "PM_DISP_STALL_HELD_SCOREBOARD_CYC",
+ "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch while waiting on the Scoreboard. This event combines VSCR and FPSCR together."
+ },
+ {
+ "EventCode": "0x3001A",
+ "EventName": "PM_LSU_ST2_FIN",
+ "BriefDescription": "LSU Finished an internal operation in ST2 port."
},
{
- "EventCode": "0x30024",
- "EventName": "PM_PMC6_OVERFLOW",
- "BriefDescription": "The event selected for PMC6 caused the event counter to overflow."
+ "EventCode": "0x30026",
+ "EventName": "PM_EXEC_STALL_STORE_MISS",
+ "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a store whose cache line was not resident in the L1 and was waiting for allocation of the missing line into the L1."
},
{
"EventCode": "0x30028",
"EventName": "PM_CMPL_STALL_MEM_ECC",
- "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for the non-speculative finish of either a stcx waiting for its result or a load waiting for non-critical sectors of data and ECC."
+ "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for the non-speculative finish of either a STCX waiting for its result or a load waiting for non-critical sectors of data and ECC."
},
{
"EventCode": "0x30036",
"EventName": "PM_EXEC_STALL_SIMPLE_FX",
"BriefDescription": "Cycles in which the oldest instruction in the pipeline was a simple fixed point instruction executing in the Load Store Unit."
},
+ {
+ "EventCode": "0x30038",
+ "EventName": "PM_EXEC_STALL_DMISS_LMEM",
+ "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local memory, local OpenCAPI cache, or local OpenCAPI memory."
+ },
{
"EventCode": "0x3003A",
"EventName": "PM_CMPL_STALL_EXCEPTION",
@@ -187,17 +277,37 @@
{
"EventCode": "0x3F044",
"EventName": "PM_VSU2_ISSUE",
- "BriefDescription": "VSU instructions issued to VSU pipe 2."
+ "BriefDescription": "VSU instruction issued to VSU pipe 2."
},
{
"EventCode": "0x30058",
"EventName": "PM_TLBIE_FIN",
- "BriefDescription": "TLBIE instructions finished in the LSU. Two TLBIEs can finish each cycle. All will be counted."
+ "BriefDescription": "TLBIE instruction finished in the LSU. Two TLBIEs can finish each cycle. All will be counted."
+ },
+ {
+ "EventCode": "0x34054",
+ "EventName": "PM_EXEC_STALL_DMISS_L2L3_NOCONFLICT",
+ "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local L2 or local L3, without a dispatch conflict."
+ },
+ {
+ "EventCode": "0x34056",
+ "EventName": "PM_EXEC_STALL_LOAD_FINISH",
+ "BriefDescription": "Cycles in which the oldest instruction in the pipeline was finishing a load after its data was reloaded from a data source beyond the local L1; cycles in which the LSU was processing an L1-hit; cycles in which the next-to-finish (NTF) instruction merged with another load in the LMQ; cycles in which the NTF instruction is waiting for a data reload for a load miss, but the data comes back with a non-NTF instruction."
+ },
+ {
+ "EventCode": "0x34058",
+ "EventName": "PM_DISP_STALL_BR_MPRED_ICMISS",
+ "BriefDescription": "Cycles when dispatch was stalled after a mispredicted branch resulted in an instruction cache miss."
+ },
+ {
+ "EventCode": "0x3D05C",
+ "EventName": "PM_DISP_STALL_HELD_RENAME_CYC",
+ "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because the mapper/SRB was full. Includes GPR (count, link, tar), VSR, VMR, FPR and XVFC."
},
{
- "EventCode": "0x3D058",
- "EventName": "PM_SCALAR_FSQRT_FDIV_ISSUE",
- "BriefDescription": "Scalar versions of four floating point operations: fdiv,fsqrt (xvdivdp, xvdivsp, xvsqrtdp, xvsqrtsp)."
+ "EventCode": "0x3E052",
+ "EventName": "PM_DISP_STALL_IC_L3",
+ "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from the local L3."
},
{
"EventCode": "0x30066",
@@ -215,25 +325,45 @@
"BriefDescription": "Cycles in which both instructions in the ICT entry pair show as finished. These are the cycles between finish and completion for the oldest pair of instructions in the pipeline."
},
{
- "EventCode": "0x40010",
- "EventName": "PM_PMC3_OVERFLOW",
- "BriefDescription": "The event selected for PMC3 caused the event counter to overflow."
+ "EventCode": "0x4C010",
+ "EventName": "PM_DISP_STALL_BR_MPRED_IC_L3MISS",
+ "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from sources beyond the local L3 after suffering a mispredicted branch."
},
{
"EventCode": "0x4C012",
"EventName": "PM_EXEC_STALL_DERAT_ONLY_MISS",
"BriefDescription": "Cycles in which the oldest instruction in the pipeline suffered an ERAT miss and waited for it resolve."
},
+ {
+ "EventCode": "0x4C016",
+ "EventName": "PM_EXEC_STALL_DMISS_L2L3_CONFLICT",
+ "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from the local L2 or local L3, with a dispatch conflict."
+ },
{
"EventCode": "0x4C018",
"EventName": "PM_CMPL_STALL",
"BriefDescription": "Cycles in which the oldest instruction in the pipeline cannot complete because the thread was blocked for any reason."
},
+ {
+ "EventCode": "0x4C01A",
+ "EventName": "PM_EXEC_STALL_DMISS_OFF_NODE",
+ "BriefDescription": "Cycles in which the oldest instruction in the pipeline was waiting for a load miss to resolve from a distant chip."
+ },
{
"EventCode": "0x4C01E",
"EventName": "PM_LSU_ST3_FIN",
"BriefDescription": "LSU Finished an internal operation in ST3 port."
},
+ {
+ "EventCode": "0x4D014",
+ "EventName": "PM_EXEC_STALL_LOAD",
+ "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a load instruction executing in the Load Store Unit."
+ },
+ {
+ "EventCode": "0x4D016",
+ "EventName": "PM_EXEC_STALL_PTESYNC",
+ "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a PTESYNC instruction executing in the Load Store Unit."
+ },
{
"EventCode": "0x4D018",
"EventName": "PM_EXEC_STALL_BRU",
@@ -249,10 +379,25 @@
"EventName": "PM_EXEC_STALL_TLBIEL",
"BriefDescription": "Cycles in which the oldest instruction in the pipeline was a TLBIEL instruction executing in the Load Store Unit. TLBIEL instructions have lower overhead than TLBIE instructions because they don't get set to the nest."
},
+ {
+ "EventCode": "0x4D01E",
+ "EventName": "PM_DISP_STALL_BR_MPRED",
+ "BriefDescription": "Cycles when dispatch was stalled for this thread due to a mispredicted branch."
+ },
+ {
+ "EventCode": "0x4E010",
+ "EventName": "PM_DISP_STALL_IC_L3MISS",
+ "BriefDescription": "Cycles when dispatch was stalled while the instruction was fetched from any source beyond the local L3."
+ },
{
"EventCode": "0x4E012",
"EventName": "PM_EXEC_STALL_UNKNOWN",
- "BriefDescription": "Cycles in which the oldest instruction in the pipeline completed without an ntf_type pulse. The ntf_pulse was missed by the ISU because the NTF finishes and completions came too close together."
+ "BriefDescription": "Cycles in which the oldest instruction in the pipeline completed without an ntf_type pulse. The ntf_pulse was missed by the ISU because the next-to-finish (NTF) instruction finishes and completions came too close together."
+ },
+ {
+ "EventCode": "0x4E01A",
+ "EventName": "PM_DISP_STALL_HELD_CYC",
+ "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch for any reason."
},
{
"EventCode": "0x4D020",
@@ -260,24 +405,14 @@
"BriefDescription": "VSU instruction was issued to VSU pipe 3."
},
{
- "EventCode": "0x40132",
- "EventName": "PM_MRK_LSU_FIN",
- "BriefDescription": "LSU marked instruction finish."
+ "EventCode": "0x4003C",
+ "EventName": "PM_DISP_STALL_HELD_SYNC_CYC",
+ "BriefDescription": "Cycles in which the next-to-complete (NTC) instruction is held at dispatch because of a synchronizing instruction that requires the ICT to be empty before dispatch."
},
{
"EventCode": "0x45058",
"EventName": "PM_IC_MISS_CMPL",
- "BriefDescription": "Non-speculative icache miss, counted at completion."
- },
- {
- "EventCode": "0x4D050",
- "EventName": "PM_VSU_NON_FLOP_CMPL",
- "BriefDescription": "Non-floating point VSU instructions completed."
- },
- {
- "EventCode": "0x4D052",
- "EventName": "PM_2FLOP_CMPL",
- "BriefDescription": "Double Precision vector version of fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg completed."
+ "BriefDescription": "Non-speculative instruction cache miss, counted at completion."
},
{
"EventCode": "0x400F2",
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/pmc.json b/tools/perf/pmu-events/arch/powerpc/power10/pmc.json
index b5d1bd39cfb2..0a2bf56ee7c1 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/pmc.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/pmc.json
@@ -1,22 +1,197 @@
[
+ {
+ "EventCode": "0x100FE",
+ "EventName": "PM_INST_CMPL",
+ "BriefDescription": "PowerPC instruction completed."
+ },
+ {
+ "EventCode": "0x1000A",
+ "EventName": "PM_PMC3_REWIND",
+ "BriefDescription": "The speculative event selected for PMC3 rewinds and the counter for PMC3 is not charged."
+ },
+ {
+ "EventCode": "0x10010",
+ "EventName": "PM_PMC4_OVERFLOW",
+ "BriefDescription": "The event selected for PMC4 caused the event counter to overflow."
+ },
+ {
+ "EventCode": "0x1001C",
+ "EventName": "PM_ULTRAVISOR_INST_CMPL",
+ "BriefDescription": "PowerPC instruction completed while the thread was in ultravisor state."
+ },
+ {
+ "EventCode": "0x100F0",
+ "EventName": "PM_CYC",
+ "BriefDescription": "Processor cycles."
+ },
+ {
+ "EventCode": "0x10020",
+ "EventName": "PM_PMC4_REWIND",
+ "BriefDescription": "The speculative event selected for PMC4 rewinds and the counter for PMC4 is not charged."
+ },
+ {
+ "EventCode": "0x10022",
+ "EventName": "PM_PMC2_SAVED",
+ "BriefDescription": "The conditions for the speculative event selected for PMC2 are met and PMC2 is charged."
+ },
+ {
+ "EventCode": "0x10024",
+ "EventName": "PM_PMC5_OVERFLOW",
+ "BriefDescription": "The event selected for PMC5 caused the event counter to overflow."
+ },
+ {
+ "EventCode": "0x1F15E",
+ "EventName": "PM_MRK_START_PROBE_NOP_CMPL",
+ "BriefDescription": "Marked Start probe nop (AND R0,R0,R0) completed."
+ },
+ {
+ "EventCode": "0x1006C",
+ "EventName": "PM_RUN_CYC_ST_MODE",
+ "BriefDescription": "Cycles when the run latch is set and the core is in ST mode."
+ },
+ {
+ "EventCode": "0x101E8",
+ "EventName": "PM_THRESH_EXC_256",
+ "BriefDescription": "Threshold counter exceeded a count of 256."
+ },
+ {
+ "EventCode": "0x101EC",
+ "EventName": "PM_THRESH_MET",
+ "BriefDescription": "Threshold exceeded."
+ },
+ {
+ "EventCode": "0x100FA",
+ "EventName": "PM_RUN_LATCH_ANY_THREAD_CYC",
+ "BriefDescription": "Cycles when at least one thread has the run latch set."
+ },
+ {
+ "EventCode": "0x2000A",
+ "EventName": "PM_HYPERVISOR_CYC",
+ "BriefDescription": "Cycles when the thread is in Hypervisor state. MSR[S HV PR]=010."
+ },
+ {
+ "EventCode": "0x2000C",
+ "EventName": "PM_RUN_LATCH_ALL_THREADS_CYC",
+ "BriefDescription": "Cycles when the run latch is set for all threads."
+ },
+ {
+ "EventCode": "0x20010",
+ "EventName": "PM_PMC1_OVERFLOW",
+ "BriefDescription": "The event selected for PMC1 caused the event counter to overflow."
+ },
+ {
+ "EventCode": "0x2006C",
+ "EventName": "PM_RUN_CYC_SMT4_MODE",
+ "BriefDescription": "Cycles when this thread's run latch is set and the core is in SMT4 mode."
+ },
+ {
+ "EventCode": "0x201E6",
+ "EventName": "PM_THRESH_EXC_32",
+ "BriefDescription": "Threshold counter exceeded a value of 32."
+ },
+ {
+ "EventCode": "0x201E8",
+ "EventName": "PM_THRESH_EXC_512",
+ "BriefDescription": "Threshold counter exceeded a value of 512."
+ },
+ {
+ "EventCode": "0x200F4",
+ "EventName": "PM_RUN_CYC",
+ "BriefDescription": "Processor cycles gated by the run latch."
+ },
+ {
+ "EventCode": "0x30010",
+ "EventName": "PM_PMC2_OVERFLOW",
+ "BriefDescription": "The event selected for PMC2 caused the event counter to overflow."
+ },
+ {
+ "EventCode": "0x30020",
+ "EventName": "PM_PMC2_REWIND",
+ "BriefDescription": "The speculative event selected for PMC2 rewinds and the counter for PMC2 is not charged."
+ },
+ {
+ "EventCode": "0x30022",
+ "EventName": "PM_PMC4_SAVED",
+ "BriefDescription": "The conditions for the speculative event selected for PMC4 are met and PMC4 is charged."
+ },
+ {
+ "EventCode": "0x30024",
+ "EventName": "PM_PMC6_OVERFLOW",
+ "BriefDescription": "The event selected for PMC6 caused the event counter to overflow."
+ },
+ {
+ "EventCode": "0x3006C",
+ "EventName": "PM_RUN_CYC_SMT2_MODE",
+ "BriefDescription": "Cycles when this thread's run latch is set and the core is in SMT2 mode."
+ },
{
"EventCode": "0x301E8",
"EventName": "PM_THRESH_EXC_64",
"BriefDescription": "Threshold counter exceeded a value of 64."
},
{
- "EventCode": "0x45050",
- "EventName": "PM_1FLOP_CMPL",
- "BriefDescription": "One floating point instruction completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)."
+ "EventCode": "0x301EA",
+ "EventName": "PM_THRESH_EXC_1024",
+ "BriefDescription": "Threshold counter exceeded a value of 1024."
+ },
+ {
+ "EventCode": "0x40010",
+ "EventName": "PM_PMC3_OVERFLOW",
+ "BriefDescription": "The event selected for PMC3 caused the event counter to overflow."
+ },
+ {
+ "EventCode": "0x40114",
+ "EventName": "PM_MRK_START_PROBE_NOP_DISP",
+ "BriefDescription": "Marked Start probe nop dispatched. Instruction AND R0,R0,R0."
+ },
+ {
+ "EventCode": "0x4D010",
+ "EventName": "PM_PMC1_SAVED",
+ "BriefDescription": "The conditions for the speculative event selected for PMC1 are met and PMC1 is charged."
+ },
+ {
+ "EventCode": "0x4D012",
+ "EventName": "PM_PMC3_SAVED",
+ "BriefDescription": "The conditions for the speculative event selected for PMC3 are met and PMC3 is charged."
+ },
+ {
+ "EventCode": "0x4D022",
+ "EventName": "PM_HYPERVISOR_INST_CMPL",
+ "BriefDescription": "PowerPC instruction completed while the thread was in hypervisor state."
+ },
+ {
+ "EventCode": "0x4D026",
+ "EventName": "PM_ULTRAVISOR_CYC",
+ "BriefDescription": "Cycles when the thread is in Ultravisor state. MSR[S HV PR]=110."
+ },
+ {
+ "EventCode": "0x4D028",
+ "EventName": "PM_PRIVILEGED_CYC",
+ "BriefDescription": "Cycles when the thread is in Privileged state. MSR[S HV PR]=x00."
+ },
+ {
+ "EventCode": "0x4D02C",
+ "EventName": "PM_PMC1_REWIND",
+ "BriefDescription": "The speculative event selected for PMC1 rewinds and the counter for PMC1 is not charged."
+ },
+ {
+ "EventCode": "0x40030",
+ "EventName": "PM_INST_FIN",
+ "BriefDescription": "Instruction finished."
+ },
+ {
+ "EventCode": "0x40134",
+ "EventName": "PM_MRK_INST_TIMEO",
+ "BriefDescription": "Marked instruction finish timeout (instruction was lost)."
},
{
- "EventCode": "0x45052",
- "EventName": "PM_4FLOP_CMPL",
- "BriefDescription": "Four floating point instructions completed (fadd, fmul, fsub, fcmp, fsel, fabs, fnabs, fres, fsqrte, fneg)."
+ "EventCode": "0x401EA",
+ "EventName": "PM_THRESH_EXC_128",
+ "BriefDescription": "Threshold counter exceeded a value of 128."
},
{
- "EventCode": "0x4D054",
- "EventName": "PM_8FLOP_CMPL",
- "BriefDescription": "Four Double Precision vector instructions completed."
+ "EventCode": "0x400FA",
+ "EventName": "PM_RUN_INST_CMPL",
+ "BriefDescription": "PowerPC instruction completed while the run latch is set."
}
]
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/translation.json b/tools/perf/pmu-events/arch/powerpc/power10/translation.json
index db3766dca07c..170c9aeb30d8 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/translation.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/translation.json
@@ -1,34 +1,9 @@
[
- {
- "EventCode": "0x1F15E",
- "EventName": "PM_MRK_START_PROBE_NOP_CMPL",
- "BriefDescription": "Marked Start probe nop (AND R0,R0,R0) completed."
- },
- {
- "EventCode": "0x20016",
- "EventName": "PM_ST_FIN",
- "BriefDescription": "Store finish count. Includes speculative activity."
- },
{
"EventCode": "0x20018",
"EventName": "PM_ST_FWD",
"BriefDescription": "Store forwards that finished."
},
- {
- "EventCode": "0x2011C",
- "EventName": "PM_MRK_NTF_CYC",
- "BriefDescription": "Cycles during which the marked instruction is the oldest in the pipeline (NTF or NTC)."
- },
- {
- "EventCode": "0x2E01C",
- "EventName": "PM_EXEC_STALL_TLBIE",
- "BriefDescription": "Cycles in which the oldest instruction in the pipeline was a TLBIE instruction executing in the Load Store Unit."
- },
- {
- "EventCode": "0x201E6",
- "EventName": "PM_THRESH_EXC_32",
- "BriefDescription": "Threshold counter exceeded a value of 32."
- },
{
"EventCode": "0x200F0",
"EventName": "PM_ST_CMPL",
@@ -37,21 +12,6 @@
{
"EventCode": "0x200FE",
"EventName": "PM_DATA_FROM_L2MISS",
- "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1 or L2 due to a demand miss."
- },
- {
- "EventCode": "0x30010",
- "EventName": "PM_PMC2_OVERFLOW",
- "BriefDescription": "The event selected for PMC2 caused the event counter to overflow."
- },
- {
- "EventCode": "0x4D010",
- "EventName": "PM_PMC1_SAVED",
- "BriefDescription": "The conditions for the speculative event selected for PMC1 are met and PMC1 is charged."
- },
- {
- "EventCode": "0x4D05C",
- "EventName": "PM_DPP_FLOP_CMPL",
- "BriefDescription": "Double-Precision or Quad-Precision instructions completed."
+ "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L2 due to a demand miss."
}
]
diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py
index 12e80bb7939b..82c42c46d886 100755
--- a/tools/perf/pmu-events/jevents.py
+++ b/tools/perf/pmu-events/jevents.py
@@ -999,7 +999,7 @@ such as "arm/cortex-a34".''',
_args = ap.parse_args()

_args.output_file.write("""
-#include "pmu-events/pmu-events.h"
+#include <pmu-events/pmu-events.h>
#include "util/header.h"
#include "util/pmu.h"
#include <string.h>
diff --git a/tools/perf/tests/dlfilter-test.c b/tools/perf/tests/dlfilter-test.c
index 086fd2179e41..da3a9b50b1b1 100644
--- a/tools/perf/tests/dlfilter-test.c
+++ b/tools/perf/tests/dlfilter-test.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
/*
* Test dlfilter C API. A perf.data file is synthesized and then processed
- * by perf script with a dlfilter named dlfilter-test-api-v0.so. Also a C file
+ * by perf script with dlfilters named dlfilter-test-api-v*.so. Also a C file
* is compiled to provide a dso to match the synthesized perf.data file.
*/

@@ -37,6 +37,8 @@

#define MAP_START 0x400000

+#define DLFILTER_TEST_NAME_MAX 128
+
struct test_data {
struct perf_tool tool;
struct machine *machine;
@@ -45,6 +47,8 @@ struct test_data {
u64 bar;
u64 ip;
u64 addr;
+ char name[DLFILTER_TEST_NAME_MAX];
+ char desc[DLFILTER_TEST_NAME_MAX];
char perf[PATH_MAX];
char perf_data_file_name[PATH_MAX];
char c_file_name[PATH_MAX];
@@ -215,7 +219,7 @@ static int write_prog(char *file_name)
return err ? -1 : 0;
}

-static int get_dlfilters_path(char *buf, size_t sz)
+static int get_dlfilters_path(const char *name, char *buf, size_t sz)
{
char perf[PATH_MAX];
char path[PATH_MAX];
@@ -224,12 +228,12 @@ static int get_dlfilters_path(char *buf, size_t sz)

perf_exe(perf, sizeof(perf));
perf_path = dirname(perf);
- snprintf(path, sizeof(path), "%s/dlfilters/dlfilter-test-api-v0.so", perf_path);
+ snprintf(path, sizeof(path), "%s/dlfilters/%s", perf_path, name);
if (access(path, R_OK)) {
exec_path = get_argv_exec_path();
if (!exec_path)
return -1;
- snprintf(path, sizeof(path), "%s/dlfilters/dlfilter-test-api-v0.so", exec_path);
+ snprintf(path, sizeof(path), "%s/dlfilters/%s", exec_path, name);
free(exec_path);
if (access(path, R_OK))
return -1;
@@ -244,9 +248,9 @@ static int check_filter_desc(struct test_data *td)
char *desc = NULL;
int ret;

- if (get_filter_desc(td->dlfilters, "dlfilter-test-api-v0.so", &desc, &long_desc) &&
+ if (get_filter_desc(td->dlfilters, td->name, &desc, &long_desc) &&
long_desc && !strcmp(long_desc, "Filter used by the 'dlfilter C API' perf test") &&
- desc && !strcmp(desc, "dlfilter to test v0 C API"))
+ desc && !strcmp(desc, td->desc))
ret = 0;
else
ret = -1;
@@ -284,7 +288,7 @@ static int get_ip_addr(struct test_data *td)
static int do_run_perf_script(struct test_data *td, int do_early)
{
return system_cmd("%s script -i %s "
- "--dlfilter %s/dlfilter-test-api-v0.so "
+ "--dlfilter %s/%s "
"--dlarg first "
"--dlarg %d "
"--dlarg %" PRIu64 " "
@@ -292,7 +296,7 @@ static int do_run_perf_script(struct test_data *td, int do_early)
"--dlarg %d "
"--dlarg last",
td->perf, td->perf_data_file_name, td->dlfilters,
- verbose, td->ip, td->addr, do_early);
+ td->name, verbose, td->ip, td->addr, do_early);
}

static int run_perf_script(struct test_data *td)
@@ -321,7 +325,7 @@ static int test__dlfilter_test(struct test_data *td)
u64 id = 99;
int err;

- if (get_dlfilters_path(td->dlfilters, PATH_MAX))
+ if (get_dlfilters_path(td->name, td->dlfilters, PATH_MAX))
return test_result("dlfilters not found", TEST_SKIP);

if (check_filter_desc(td))
@@ -399,14 +403,18 @@ static void test_data__free(struct test_data *td)
}
}

-static int test__dlfilter(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
+static int test__dlfilter_ver(int ver)
{
struct test_data td = {.fd = -1};
int pid = getpid();
int err;

+ pr_debug("\n-- Testing version %d API --\n", ver);
+
perf_exe(td.perf, sizeof(td.perf));

+ snprintf(td.name, sizeof(td.name), "dlfilter-test-api-v%d.so", ver);
+ snprintf(td.desc, sizeof(td.desc), "dlfilter to test v%d C API", ver);
snprintf(td.perf_data_file_name, PATH_MAX, "/tmp/dlfilter-test-%u-perf-data", pid);
snprintf(td.c_file_name, PATH_MAX, "/tmp/dlfilter-test-%u-prog.c", pid);
snprintf(td.prog_file_name, PATH_MAX, "/tmp/dlfilter-test-%u-prog", pid);
@@ -416,4 +424,14 @@ static int test__dlfilter(struct test_suite *test __maybe_unused, int subtest __
return err;
}

+static int test__dlfilter(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
+{
+ int err = test__dlfilter_ver(0);
+
+ if (err)
+ return err;
+ /* No test for version 1 */
+ return test__dlfilter_ver(2);
+}
+
DEFINE_SUITE("dlfilter C API", dlfilter);
diff --git a/tools/perf/tests/shell/stat_bpf_counters.sh b/tools/perf/tests/shell/stat_bpf_counters.sh
index 13473aeba489..6bf24b85294c 100755
--- a/tools/perf/tests/shell/stat_bpf_counters.sh
+++ b/tools/perf/tests/shell/stat_bpf_counters.sh
@@ -22,10 +22,10 @@ compare_number()
}

# skip if --bpf-counters is not supported
-if ! perf stat --bpf-counters true > /dev/null 2>&1; then
+if ! perf stat -e cycles --bpf-counters true > /dev/null 2>&1; then
if [ "$1" = "-v" ]; then
echo "Skipping: --bpf-counters not supported"
- perf --no-pager stat --bpf-counters true || true
+ perf --no-pager stat -e cycles --bpf-counters true || true
fi
exit 2
fi
diff --git a/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh
index d724855d097c..e75d0780dc78 100755
--- a/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh
+++ b/tools/perf/tests/shell/stat_bpf_counters_cgrp.sh
@@ -25,22 +25,22 @@ check_bpf_counter()
find_cgroups()
{
# try usual systemd slices first
- if [ -d /sys/fs/cgroup/system.slice -a -d /sys/fs/cgroup/user.slice ]; then
+ if [ -d /sys/fs/cgroup/system.slice ] && [ -d /sys/fs/cgroup/user.slice ]; then
test_cgroups="system.slice,user.slice"
return
fi

# try root and self cgroups
- local self_cgrp=$(grep perf_event /proc/self/cgroup | cut -d: -f3)
- if [ -z ${self_cgrp} ]; then
+ find_cgroups_self_cgrp=$(grep perf_event /proc/self/cgroup | cut -d: -f3)
+ if [ -z ${find_cgroups_self_cgrp} ]; then
# cgroup v2 doesn't specify perf_event
- self_cgrp=$(grep ^0: /proc/self/cgroup | cut -d: -f3)
+ find_cgroups_self_cgrp=$(grep ^0: /proc/self/cgroup | cut -d: -f3)
fi

- if [ -z ${self_cgrp} ]; then
+ if [ -z ${find_cgroups_self_cgrp} ]; then
test_cgroups="/"
else
- test_cgroups="/,${self_cgrp}"
+ test_cgroups="/,${find_cgroups_self_cgrp}"
fi
}

@@ -48,13 +48,11 @@ find_cgroups()
# Just check if it runs without failure and has non-zero results.
check_system_wide_counted()
{
- local output
-
- output=$(perf stat -a --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, sleep 1 2>&1)
- if echo ${output} | grep -q -F "<not "; then
+ check_system_wide_counted_output=$(perf stat -a --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, sleep 1 2>&1)
+ if echo ${check_system_wide_counted_output} | grep -q -F "<not "; then
echo "Some system-wide events are not counted"
if [ "${verbose}" = "1" ]; then
- echo ${output}
+ echo ${check_system_wide_counted_output}
fi
exit 1
fi
@@ -62,13 +60,11 @@ check_system_wide_counted()

check_cpu_list_counted()
{
- local output
-
- output=$(perf stat -C 1 --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, taskset -c 1 sleep 1 2>&1)
- if echo ${output} | grep -q -F "<not "; then
+ check_cpu_list_counted_output=$(perf stat -C 0,1 --bpf-counters --for-each-cgroup ${test_cgroups} -e cpu-clock -x, taskset -c 1 sleep 1 2>&1)
+ if echo ${check_cpu_list_counted_output} | grep -q -F "<not "; then
echo "Some CPU events are not counted"
if [ "${verbose}" = "1" ]; then
- echo ${output}
+ echo ${check_cpu_list_counted_output}
fi
exit 1
fi
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index c7ad9e003080..70db5a717905 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -407,11 +407,6 @@ static bool hist_browser__selection_has_children(struct hist_browser *browser)
return container_of(ms, struct callchain_list, ms)->has_children;
}

-static bool hist_browser__he_selection_unfolded(struct hist_browser *browser)
-{
- return browser->he_selection ? browser->he_selection->unfolded : false;
-}
-
static bool hist_browser__selection_unfolded(struct hist_browser *browser)
{
struct hist_entry *he = browser->he_selection;
@@ -584,8 +579,8 @@ static int hierarchy_set_folding(struct hist_browser *hb, struct hist_entry *he,
return n;
}

-static void __hist_entry__set_folding(struct hist_entry *he,
- struct hist_browser *hb, bool unfold)
+static void hist_entry__set_folding(struct hist_entry *he,
+ struct hist_browser *hb, bool unfold)
{
hist_entry__init_have_children(he);
he->unfolded = unfold ? he->has_children : false;
@@ -603,34 +598,12 @@ static void __hist_entry__set_folding(struct hist_entry *he,
he->nr_rows = 0;
}

-static void hist_entry__set_folding(struct hist_entry *he,
- struct hist_browser *browser, bool unfold)
-{
- double percent;
-
- percent = hist_entry__get_percent_limit(he);
- if (he->filtered || percent < browser->min_pcnt)
- return;
-
- __hist_entry__set_folding(he, browser, unfold);
-
- if (!he->depth || unfold)
- browser->nr_hierarchy_entries++;
- if (he->leaf)
- browser->nr_callchain_rows += he->nr_rows;
- else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) {
- browser->nr_hierarchy_entries++;
- he->has_no_entry = true;
- he->nr_rows = 1;
- } else
- he->has_no_entry = false;
-}
-
static void
__hist_browser__set_folding(struct hist_browser *browser, bool unfold)
{
struct rb_node *nd;
struct hist_entry *he;
+ double percent;

nd = rb_first_cached(&browser->hists->entries);
while (nd) {
@@ -640,6 +613,21 @@ __hist_browser__set_folding(struct hist_browser *browser, bool unfold)
nd = __rb_hierarchy_next(nd, HMD_FORCE_CHILD);

hist_entry__set_folding(he, browser, unfold);
+
+ percent = hist_entry__get_percent_limit(he);
+ if (he->filtered || percent < browser->min_pcnt)
+ continue;
+
+ if (!he->depth || unfold)
+ browser->nr_hierarchy_entries++;
+ if (he->leaf)
+ browser->nr_callchain_rows += he->nr_rows;
+ else if (unfold && !hist_entry__has_hierarchy_children(he, browser->min_pcnt)) {
+ browser->nr_hierarchy_entries++;
+ he->has_no_entry = true;
+ he->nr_rows = 1;
+ } else
+ he->has_no_entry = false;
}
}

@@ -659,8 +647,10 @@ static void hist_browser__set_folding_selected(struct hist_browser *browser, boo
if (!browser->he_selection)
return;

- hist_entry__set_folding(browser->he_selection, browser, unfold);
- browser->b.nr_entries = hist_browser__nr_entries(browser);
+ if (unfold == browser->he_selection->unfolded)
+ return;
+
+ hist_browser__toggle_fold(browser);
}

static void ui_browser__warn_lost_events(struct ui_browser *browser)
@@ -732,8 +722,8 @@ static int hist_browser__handle_hotkey(struct hist_browser *browser, bool warn_l
hist_browser__set_folding(browser, true);
break;
case 'e':
- /* Expand the selected entry. */
- hist_browser__set_folding_selected(browser, !hist_browser__he_selection_unfolded(browser));
+ /* Toggle expand/collapse the selected entry. */
+ hist_browser__toggle_fold(browser);
break;
case 'H':
browser->show_headers = !browser->show_headers;
@@ -1779,7 +1769,7 @@ static void hists_browser__hierarchy_headers(struct hist_browser *browser)
hists_browser__scnprintf_hierarchy_headers(browser, headers,
sizeof(headers));

- ui_browser__gotorc(&browser->b, 0, 0);
+ ui_browser__gotorc_title(&browser->b, 0, 0);
ui_browser__set_color(&browser->b, HE_COLORSET_ROOT);
ui_browser__write_nstring(&browser->b, headers, browser->b.width + 1);
}
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index ba988a13dacb..82956adf9963 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1846,8 +1846,11 @@ static int symbol__disassemble_bpf(struct symbol *sym,
perf_exe(tpath, sizeof(tpath));

bfdf = bfd_openr(tpath, NULL);
- assert(bfdf);
- assert(bfd_check_format(bfdf, bfd_object));
+ if (bfdf == NULL)
+ abort();
+
+ if (!bfd_check_format(bfdf, bfd_object))
+ abort();

s = open_memstream(&buf, &buf_size);
if (!s) {
@@ -1895,7 +1898,8 @@ static int symbol__disassemble_bpf(struct symbol *sym,
#else
disassemble = disassembler(bfdf);
#endif
- assert(disassemble);
+ if (disassemble == NULL)
+ abort();

fflush(s);
do {
diff --git a/tools/perf/util/bpf-filter.c b/tools/perf/util/bpf-filter.c
index 0b30688d78a7..b51544996046 100644
--- a/tools/perf/util/bpf-filter.c
+++ b/tools/perf/util/bpf-filter.c
@@ -9,8 +9,8 @@
#include "util/evsel.h"

#include "util/bpf-filter.h"
-#include "util/bpf-filter-flex.h"
-#include "util/bpf-filter-bison.h"
+#include <util/bpf-filter-flex.h>
+#include <util/bpf-filter-bison.h>

#include "bpf_skel/sample-filter.h"
#include "bpf_skel/sample_filter.skel.h"
@@ -62,6 +62,16 @@ static int check_sample_flags(struct evsel *evsel, struct perf_bpf_filter_expr *
if (evsel->core.attr.sample_type & expr->sample_flags)
return 0;

+ if (expr->op == PBF_OP_GROUP_BEGIN) {
+ struct perf_bpf_filter_expr *group;
+
+ list_for_each_entry(group, &expr->groups, list) {
+ if (check_sample_flags(evsel, group) < 0)
+ return -1;
+ }
+ return 0;
+ }
+
info = get_sample_info(expr->sample_flags);
if (info == NULL) {
pr_err("Error: %s event does not have sample flags %lx\n",
diff --git a/tools/perf/util/dlfilter.c b/tools/perf/util/dlfilter.c
index 46f74b2344db..e0f822ebb9b9 100644
--- a/tools/perf/util/dlfilter.c
+++ b/tools/perf/util/dlfilter.c
@@ -10,6 +10,8 @@
#include <subcmd/exec-cmd.h>
#include <linux/zalloc.h>
#include <linux/build_bug.h>
+#include <linux/kernel.h>
+#include <linux/string.h>

#include "debug.h"
#include "event.h"
@@ -63,6 +65,7 @@ static void al_to_d_al(struct addr_location *al, struct perf_dlfilter_al *d_al)
d_al->addr = al->addr;
d_al->comm = NULL;
d_al->filtered = 0;
+ d_al->priv = NULL;
}

static struct addr_location *get_al(struct dlfilter *d)
@@ -151,6 +154,11 @@ static char **dlfilter__args(void *ctx, int *dlargc)
return d->dlargv;
}

+static bool has_priv(struct perf_dlfilter_al *d_al_p)
+{
+ return d_al_p->size >= offsetof(struct perf_dlfilter_al, priv) + sizeof(d_al_p->priv);
+}
+
static __s32 dlfilter__resolve_address(void *ctx, __u64 address, struct perf_dlfilter_al *d_al_p)
{
struct dlfilter *d = (struct dlfilter *)ctx;
@@ -166,6 +174,7 @@ static __s32 dlfilter__resolve_address(void *ctx, __u64 address, struct perf_dlf
if (!thread)
return -1;

+ addr_location__init(&al);
thread__find_symbol_fb(thread, d->sample->cpumode, address, &al);

al_to_d_al(&al, &d_al);
@@ -176,9 +185,29 @@ static __s32 dlfilter__resolve_address(void *ctx, __u64 address, struct perf_dlf
memcpy(d_al_p, &d_al, min((size_t)sz, sizeof(d_al)));
d_al_p->size = sz;

+ if (has_priv(d_al_p))
+ d_al_p->priv = memdup(&al, sizeof(al));
+
return 0;
}

+static void dlfilter__al_cleanup(void *ctx __maybe_unused, struct perf_dlfilter_al *d_al_p)
+{
+ struct addr_location *al;
+
+ /* Ensure backward compatibility */
+ if (!has_priv(d_al_p) || !d_al_p->priv)
+ return;
+
+ al = d_al_p->priv;
+
+ d_al_p->priv = NULL;
+
+ addr_location__exit(al);
+
+ free(al);
+}
+
static const __u8 *dlfilter__insn(void *ctx, __u32 *len)
{
struct dlfilter *d = (struct dlfilter *)ctx;
@@ -296,6 +325,7 @@ static const struct perf_dlfilter_fns perf_dlfilter_fns = {
.resolve_addr = dlfilter__resolve_addr,
.args = dlfilter__args,
.resolve_address = dlfilter__resolve_address,
+ .al_cleanup = dlfilter__al_cleanup,
.insn = dlfilter__insn,
.srcline = dlfilter__srcline,
.attr = dlfilter__attr,
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index 4814262e3805..7410a165f68b 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -10,8 +10,8 @@
#include "debug.h"
#include "evlist.h"
#include "expr.h"
-#include "expr-bison.h"
-#include "expr-flex.h"
+#include <util/expr-bison.h>
+#include <util/expr-flex.h>
#include "util/hashmap.h"
#include "smt.h"
#include "tsc.h"
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 52fbf526fe74..7af85a479786 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1605,8 +1605,15 @@ static int write_pmu_caps(struct feat_fd *ff,
int ret;

while ((pmu = perf_pmus__scan(pmu))) {
- if (!pmu->name || !strcmp(pmu->name, "cpu") ||
- perf_pmu__caps_parse(pmu) <= 0)
+ if (!strcmp(pmu->name, "cpu")) {
+ /*
+ * The "cpu" PMU is special and covered by
+ * HEADER_CPU_PMU_CAPS. Note, core PMUs are
+ * counted/written here for ARM, s390 and Intel hybrid.
+ */
+ continue;
+ }
+ if (perf_pmu__caps_parse(pmu) <= 0)
continue;
nr_pmu++;
}
@@ -1619,23 +1626,17 @@ static int write_pmu_caps(struct feat_fd *ff,
return 0;

/*
- * Write hybrid pmu caps first to maintain compatibility with
- * older perf tool.
+ * Note older perf tools assume core PMUs come first, this is a property
+ * of perf_pmus__scan.
*/
- if (perf_pmus__num_core_pmus() > 1) {
- pmu = NULL;
- while ((pmu = perf_pmus__scan_core(pmu))) {
- ret = __write_pmu_caps(ff, pmu, true);
- if (ret < 0)
- return ret;
- }
- }
-
pmu = NULL;
while ((pmu = perf_pmus__scan(pmu))) {
- if (pmu->is_core || !pmu->nr_caps)
+ if (!strcmp(pmu->name, "cpu")) {
+ /* Skip as above. */
+ continue;
+ }
+ if (perf_pmu__caps_parse(pmu) <= 0)
continue;
-
ret = __write_pmu_caps(ff, pmu, true);
if (ret < 0)
return ret;
@@ -4381,7 +4382,8 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
union perf_event *event,
struct evlist **pevlist)
{
- u32 i, ids, n_ids;
+ u32 i, n_ids;
+ u64 *ids;
struct evsel *evsel;
struct evlist *evlist = *pevlist;

@@ -4397,9 +4399,8 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused,

evlist__add(evlist, evsel);

- ids = event->header.size;
- ids -= (void *)&event->attr.id - (void *)event;
- n_ids = ids / sizeof(u64);
+ n_ids = event->header.size - sizeof(event->header) - event->attr.attr.size;
+ n_ids = n_ids / sizeof(u64);
/*
* We don't have the cpu and thread maps on the header, so
* for allocating the perf_sample_id table we fake 1 cpu and
@@ -4408,8 +4409,9 @@ int perf_event__process_attr(struct perf_tool *tool __maybe_unused,
if (perf_evsel__alloc_id(&evsel->core, 1, n_ids))
return -ENOMEM;

+ ids = (void *)&event->attr.attr + event->attr.attr.size;
for (i = 0; i < n_ids; i++) {
- perf_evlist__id_add(&evlist->core, &evsel->core, 0, i, event->attr.id[i]);
+ perf_evlist__id_add(&evlist->core, &evsel->core, 0, i, ids[i]);
}

return 0;
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index c9ec0cafb69d..30311844eea7 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -18,8 +18,8 @@
#include "debug.h"
#include <api/fs/tracing_path.h>
#include <perf/cpumap.h>
-#include "parse-events-bison.h"
-#include "parse-events-flex.h"
+#include <util/parse-events-bison.h>
+#include <util/parse-events-flex.h>
#include "pmu.h"
#include "pmus.h"
#include "asm/bug.h"
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 9f28d4b5502f..c590cf7f02a4 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -28,6 +28,13 @@ do { \
YYABORT; \
} while (0)

+#define PE_ABORT(val) \
+do { \
+ if (val == -ENOMEM) \
+ YYNOMEM; \
+ YYABORT; \
+} while (0)
+
static struct list_head* alloc_list(void)
{
struct list_head *list;
@@ -285,37 +292,38 @@ event_pmu:
PE_NAME opt_pmu_config
{
struct parse_events_state *parse_state = _parse_state;
- struct parse_events_error *error = parse_state->error;
struct list_head *list = NULL, *orig_terms = NULL, *terms= NULL;
char *pattern = NULL;

-#define CLEANUP_YYABORT \
+#define CLEANUP \
do { \
parse_events_terms__delete($2); \
parse_events_terms__delete(orig_terms); \
free(list); \
free($1); \
free(pattern); \
- YYABORT; \
} while(0)

- if (parse_events_copy_term_list($2, &orig_terms))
- CLEANUP_YYABORT;
-
- if (error)
- error->idx = @1.first_column;
+ if (parse_events_copy_term_list($2, &orig_terms)) {
+ CLEANUP;
+ YYNOMEM;
+ }

list = alloc_list();
- if (!list)
- CLEANUP_YYABORT;
+ if (!list) {
+ CLEANUP;
+ YYNOMEM;
+ }
/* Attempt to add to list assuming $1 is a PMU name. */
if (parse_events_add_pmu(parse_state, list, $1, $2, /*auto_merge_stats=*/false)) {
struct perf_pmu *pmu = NULL;
int ok = 0;

/* Failure to add, try wildcard expansion of $1 as a PMU name. */
- if (asprintf(&pattern, "%s*", $1) < 0)
- CLEANUP_YYABORT;
+ if (asprintf(&pattern, "%s*", $1) < 0) {
+ CLEANUP;
+ YYNOMEM;
+ }

while ((pmu = perf_pmus__scan(pmu)) != NULL) {
char *name = pmu->name;
@@ -330,8 +338,10 @@ PE_NAME opt_pmu_config
!perf_pmu__match(pattern, pmu->alias_name, $1)) {
bool auto_merge_stats = perf_pmu__auto_merge_stats(pmu);

- if (parse_events_copy_term_list(orig_terms, &terms))
- CLEANUP_YYABORT;
+ if (parse_events_copy_term_list(orig_terms, &terms)) {
+ CLEANUP;
+ YYNOMEM;
+ }
if (!parse_events_add_pmu(parse_state, list, pmu->name, terms,
auto_merge_stats)) {
ok++;
@@ -347,15 +357,23 @@ PE_NAME opt_pmu_config
ok = !parse_events_multi_pmu_add(parse_state, $1, $2, &list);
$2 = NULL;
}
- if (!ok)
- CLEANUP_YYABORT;
+ if (!ok) {
+ struct parse_events_error *error = parse_state->error;
+ char *help;
+
+ if (asprintf(&help, "Unabled to find PMU or event on a PMU of '%s'", $1) < 0)
+ help = NULL;
+ parse_events_error__handle(error, @1.first_column,
+ strdup("Bad event or PMU"),
+ help);
+ CLEANUP;
+ YYABORT;
+ }
}
- parse_events_terms__delete($2);
- parse_events_terms__delete(orig_terms);
- free(pattern);
- free($1);
$$ = list;
-#undef CLEANUP_YYABORT
+ list = NULL;
+ CLEANUP;
+#undef CLEANUP
}
|
PE_KERNEL_PMU_EVENT sep_dc
@@ -376,9 +394,18 @@ PE_NAME sep_dc
int err;

err = parse_events_multi_pmu_add(_parse_state, $1, NULL, &list);
+ if (err < 0) {
+ struct parse_events_state *parse_state = _parse_state;
+ struct parse_events_error *error = parse_state->error;
+ char *help;
+
+ if (asprintf(&help, "Unabled to find PMU or event on a PMU of '%s'", $1) < 0)
+ help = NULL;
+ parse_events_error__handle(error, @1.first_column, strdup("Bad event name"), help);
+ free($1);
+ PE_ABORT(err);
+ }
free($1);
- if (err < 0)
- YYABORT;
$$ = list;
}
|
@@ -448,12 +475,13 @@ value_sym '/' event_config '/'
bool wildcard = (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE);

list = alloc_list();
- ABORT_ON(!list);
+ if (!list)
+ YYNOMEM;
err = parse_events_add_numeric(_parse_state, list, type, config, $3, wildcard);
parse_events_terms__delete($3);
if (err) {
free_list_evsel(list);
- YYABORT;
+ PE_ABORT(err);
}
$$ = list;
}
@@ -464,21 +492,28 @@ value_sym sep_slash_slash_dc
int type = $1 >> 16;
int config = $1 & 255;
bool wildcard = (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE);
+ int err;

list = alloc_list();
- ABORT_ON(!list);
- ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config,
- /*head_config=*/NULL, wildcard));
+ if (!list)
+ YYNOMEM;
+ err = parse_events_add_numeric(_parse_state, list, type, config, /*head_config=*/NULL, wildcard);
+ if (err)
+ PE_ABORT(err);
$$ = list;
}
|
PE_VALUE_SYM_TOOL sep_slash_slash_dc
{
struct list_head *list;
+ int err;

list = alloc_list();
- ABORT_ON(!list);
- ABORT_ON(parse_events_add_tool(_parse_state, list, $1));
+ if (!list)
+ YYNOMEM;
+ err = parse_events_add_tool(_parse_state, list, $1);
+ if (err)
+ YYNOMEM;
$$ = list;
}

@@ -490,14 +525,16 @@ PE_LEGACY_CACHE opt_event_config
int err;

list = alloc_list();
- ABORT_ON(!list);
+ if (!list)
+ YYNOMEM;
+
err = parse_events_add_cache(list, &parse_state->idx, $1, parse_state, $2);

parse_events_terms__delete($2);
free($1);
if (err) {
free_list_evsel(list);
- YYABORT;
+ PE_ABORT(err);
}
$$ = list;
}
@@ -509,14 +546,16 @@ PE_PREFIX_MEM PE_VALUE PE_BP_SLASH PE_VALUE PE_BP_COLON PE_MODIFIER_BP opt_event
int err;

list = alloc_list();
- ABORT_ON(!list);
+ if (!list)
+ YYNOMEM;
+
err = parse_events_add_breakpoint(_parse_state, list,
$2, $6, $4, $7);
parse_events_terms__delete($7);
free($6);
if (err) {
free(list);
- YYABORT;
+ PE_ABORT(err);
}
$$ = list;
}
@@ -527,13 +566,15 @@ PE_PREFIX_MEM PE_VALUE PE_BP_SLASH PE_VALUE opt_event_config
int err;

list = alloc_list();
- ABORT_ON(!list);
+ if (!list)
+ YYNOMEM;
+
err = parse_events_add_breakpoint(_parse_state, list,
$2, NULL, $4, $5);
parse_events_terms__delete($5);
if (err) {
free(list);
- YYABORT;
+ PE_ABORT(err);
}
$$ = list;
}
@@ -544,14 +585,16 @@ PE_PREFIX_MEM PE_VALUE PE_BP_COLON PE_MODIFIER_BP opt_event_config
int err;

list = alloc_list();
- ABORT_ON(!list);
+ if (!list)
+ YYNOMEM;
+
err = parse_events_add_breakpoint(_parse_state, list,
$2, $4, 0, $5);
parse_events_terms__delete($5);
free($4);
if (err) {
free(list);
- YYABORT;
+ PE_ABORT(err);
}
$$ = list;
}
@@ -562,13 +605,14 @@ PE_PREFIX_MEM PE_VALUE opt_event_config
int err;

list = alloc_list();
- ABORT_ON(!list);
+ if (!list)
+ YYNOMEM;
err = parse_events_add_breakpoint(_parse_state, list,
$2, NULL, 0, $3);
parse_events_terms__delete($3);
if (err) {
free(list);
- YYABORT;
+ PE_ABORT(err);
}
$$ = list;
}
@@ -582,7 +626,8 @@ tracepoint_name opt_event_config
int err;

list = alloc_list();
- ABORT_ON(!list);
+ if (!list)
+ YYNOMEM;
if (error)
error->idx = @1.first_column;

@@ -594,7 +639,7 @@ tracepoint_name opt_event_config
free($1.event);
if (err) {
free(list);
- YYABORT;
+ PE_ABORT(err);
}
$$ = list;
}
@@ -614,13 +659,14 @@ PE_VALUE ':' PE_VALUE opt_event_config
int err;

list = alloc_list();
- ABORT_ON(!list);
+ if (!list)
+ YYNOMEM;
err = parse_events_add_numeric(_parse_state, list, (u32)$1, $3, $4,
/*wildcard=*/false);
parse_events_terms__delete($4);
if (err) {
free(list);
- YYABORT;
+ PE_ABORT(err);
}
$$ = list;
}
@@ -633,7 +679,8 @@ PE_RAW opt_event_config
u64 num;

list = alloc_list();
- ABORT_ON(!list);
+ if (!list)
+ YYNOMEM;
errno = 0;
num = strtoull($1 + 1, NULL, 16);
ABORT_ON(errno);
@@ -643,7 +690,7 @@ PE_RAW opt_event_config
parse_events_terms__delete($2);
if (err) {
free(list);
- YYABORT;
+ PE_ABORT(err);
}
$$ = list;
}
@@ -656,13 +703,14 @@ PE_BPF_OBJECT opt_event_config
int err;

list = alloc_list();
- ABORT_ON(!list);
+ if (!list)
+ YYNOMEM;
err = parse_events_load_bpf(parse_state, list, $1, false, $2);
parse_events_terms__delete($2);
free($1);
if (err) {
free(list);
- YYABORT;
+ PE_ABORT(err);
}
$$ = list;
}
@@ -673,12 +721,13 @@ PE_BPF_SOURCE opt_event_config
int err;

list = alloc_list();
- ABORT_ON(!list);
+ if (!list)
+ YYNOMEM;
err = parse_events_load_bpf(_parse_state, list, $1, true, $2);
parse_events_terms__delete($2);
if (err) {
free(list);
- YYABORT;
+ PE_ABORT(err);
}
$$ = list;
}
@@ -738,7 +787,8 @@ event_term
struct list_head *head = malloc(sizeof(*head));
struct parse_events_term *term = $1;

- ABORT_ON(!head);
+ if (!head)
+ YYNOMEM;
INIT_LIST_HEAD(head);
list_add_tail(&term->list, head);
$$ = head;
@@ -752,11 +802,12 @@ event_term:
PE_RAW
{
struct parse_events_term *term;
+ int err = parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_RAW,
+ strdup("raw"), $1, &@1, &@1);

- if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_RAW,
- strdup("raw"), $1, &@1, &@1)) {
+ if (err) {
free($1);
- YYABORT;
+ PE_ABORT(err);
}
$$ = term;
}
@@ -764,12 +815,12 @@ PE_RAW
name_or_raw '=' name_or_legacy
{
struct parse_events_term *term;
+ int err = parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, $1, $3, &@1, &@3);

- if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
- $1, $3, &@1, &@3)) {
+ if (err) {
free($1);
free($3);
- YYABORT;
+ PE_ABORT(err);
}
$$ = term;
}
@@ -777,11 +828,12 @@ name_or_raw '=' name_or_legacy
name_or_raw '=' PE_VALUE
{
struct parse_events_term *term;
+ int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+ $1, $3, false, &@1, &@3);

- if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
- $1, $3, false, &@1, &@3)) {
+ if (err) {
free($1);
- YYABORT;
+ PE_ABORT(err);
}
$$ = term;
}
@@ -789,12 +841,13 @@ name_or_raw '=' PE_VALUE
name_or_raw '=' PE_TERM_HW
{
struct parse_events_term *term;
+ int err = parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
+ $1, $3.str, &@1, &@3);

- if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
- $1, $3.str, &@1, &@3)) {
+ if (err) {
free($1);
free($3.str);
- YYABORT;
+ PE_ABORT(err);
}
$$ = term;
}
@@ -802,11 +855,12 @@ name_or_raw '=' PE_TERM_HW
PE_LEGACY_CACHE
{
struct parse_events_term *term;
+ int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE,
+ $1, 1, true, &@1, NULL);

- if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE,
- $1, 1, true, &@1, NULL)) {
+ if (err) {
free($1);
- YYABORT;
+ PE_ABORT(err);
}
$$ = term;
}
@@ -814,11 +868,12 @@ PE_LEGACY_CACHE
PE_NAME
{
struct parse_events_term *term;
+ int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
+ $1, 1, true, &@1, NULL);

- if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
- $1, 1, true, &@1, NULL)) {
+ if (err) {
free($1);
- YYABORT;
+ PE_ABORT(err);
}
$$ = term;
}
@@ -826,11 +881,12 @@ PE_NAME
PE_TERM_HW
{
struct parse_events_term *term;
+ int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_HARDWARE,
+ $1.str, $1.num & 255, false, &@1, NULL);

- if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_HARDWARE,
- $1.str, $1.num & 255, false, &@1, NULL)) {
+ if (err) {
free($1.str);
- YYABORT;
+ PE_ABORT(err);
}
$$ = term;
}
@@ -838,10 +894,11 @@ PE_TERM_HW
PE_TERM '=' name_or_legacy
{
struct parse_events_term *term;
+ int err = parse_events_term__str(&term, (int)$1, NULL, $3, &@1, &@3);

- if (parse_events_term__str(&term, (int)$1, NULL, $3, &@1, &@3)) {
+ if (err) {
free($3);
- YYABORT;
+ PE_ABORT(err);
}
$$ = term;
}
@@ -849,10 +906,11 @@ PE_TERM '=' name_or_legacy
PE_TERM '=' PE_TERM_HW
{
struct parse_events_term *term;
+ int err = parse_events_term__str(&term, (int)$1, NULL, $3.str, &@1, &@3);

- if (parse_events_term__str(&term, (int)$1, NULL, $3.str, &@1, &@3)) {
+ if (err) {
free($3.str);
- YYABORT;
+ PE_ABORT(err);
}
$$ = term;
}
@@ -860,37 +918,46 @@ PE_TERM '=' PE_TERM_HW
PE_TERM '=' PE_TERM
{
struct parse_events_term *term;
+ int err = parse_events_term__term(&term, (int)$1, (int)$3, &@1, &@3);
+
+ if (err)
+ PE_ABORT(err);

- ABORT_ON(parse_events_term__term(&term, (int)$1, (int)$3, &@1, &@3));
$$ = term;
}
|
PE_TERM '=' PE_VALUE
{
struct parse_events_term *term;
+ int err = parse_events_term__num(&term, (int)$1, NULL, $3, false, &@1, &@3);
+
+ if (err)
+ PE_ABORT(err);

- ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, $3, false, &@1, &@3));
$$ = term;
}
|
PE_TERM
{
struct parse_events_term *term;
+ int err = parse_events_term__num(&term, (int)$1, NULL, 1, true, &@1, NULL);
+
+ if (err)
+ PE_ABORT(err);

- ABORT_ON(parse_events_term__num(&term, (int)$1, NULL, 1, true, &@1, NULL));
$$ = term;
}
|
name_or_raw array '=' name_or_legacy
{
struct parse_events_term *term;
+ int err = parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, $1, $4, &@1, &@4);

- if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
- $1, $4, &@1, &@4)) {
+ if (err) {
free($1);
free($4);
free($2.ranges);
- YYABORT;
+ PE_ABORT(err);
}
term->array = $2;
$$ = term;
@@ -899,12 +966,12 @@ name_or_raw array '=' name_or_legacy
name_or_raw array '=' PE_VALUE
{
struct parse_events_term *term;
+ int err = parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER, $1, $4, false, &@1, &@4);

- if (parse_events_term__num(&term, PARSE_EVENTS__TERM_TYPE_USER,
- $1, $4, false, &@1, &@4)) {
+ if (err) {
free($1);
free($2.ranges);
- YYABORT;
+ PE_ABORT(err);
}
term->array = $2;
$$ = term;
@@ -914,13 +981,15 @@ PE_DRV_CFG_TERM
{
struct parse_events_term *term;
char *config = strdup($1);
+ int err;

- ABORT_ON(!config);
- if (parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_DRV_CFG,
- config, $1, &@1, NULL)) {
+ if (!config)
+ YYNOMEM;
+ err = parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_DRV_CFG, config, $1, &@1, NULL);
+ if (err) {
free($1);
free(config);
- YYABORT;
+ PE_ABORT(err);
}
$$ = term;
}
@@ -946,7 +1015,8 @@ array_terms ',' array_term
new_array.ranges = realloc($1.ranges,
sizeof(new_array.ranges[0]) *
new_array.nr_ranges);
- ABORT_ON(!new_array.ranges);
+ if (!new_array.ranges)
+ YYNOMEM;
memcpy(&new_array.ranges[$1.nr_ranges], $3.ranges,
$3.nr_ranges * sizeof(new_array.ranges[0]));
free($3.ranges);
@@ -962,7 +1032,8 @@ PE_VALUE

array.nr_ranges = 1;
array.ranges = malloc(sizeof(array.ranges[0]));
- ABORT_ON(!array.ranges);
+ if (!array.ranges)
+ YYNOMEM;
array.ranges[0].start = $1;
array.ranges[0].length = 1;
$$ = array;
@@ -975,7 +1046,8 @@ PE_VALUE PE_ARRAY_RANGE PE_VALUE
ABORT_ON($3 < $1);
array.nr_ranges = 1;
array.ranges = malloc(sizeof(array.ranges[0]));
- ABORT_ON(!array.ranges);
+ if (!array.ranges)
+ YYNOMEM;
array.ranges[0].start = $1;
array.ranges[0].length = $3 - $1 + 1;
$$ = array;
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 28380e7aa8d0..d5406effc169 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -19,8 +19,8 @@
#include "evsel.h"
#include "pmu.h"
#include "pmus.h"
-#include "pmu-bison.h"
-#include "pmu-flex.h"
+#include <util/pmu-bison.h>
+#include <util/pmu-flex.h>
#include "parse-events.h"
#include "print-events.h"
#include "header.h"
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c
index 31f1e815f671..ee0458a5ce78 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_pinning.c
@@ -8,6 +8,7 @@
#include <linux/unistd.h>
#include <linux/mount.h>
#include <sys/syscall.h>
+#include "bpf/libbpf_internal.h"

static inline int sys_fsopen(const char *fsname, unsigned flags)
{
@@ -155,7 +156,7 @@ static void validate_pin(int map_fd, const char *map_name, int src_value,
ASSERT_OK(err, "obj_pin");

/* cleanup */
- if (pin_opts.path_fd >= 0)
+ if (path_kind == PATH_FD_REL && pin_opts.path_fd >= 0)
close(pin_opts.path_fd);
if (old_cwd[0])
ASSERT_OK(chdir(old_cwd), "restore_cwd");
@@ -220,7 +221,7 @@ static void validate_get(int map_fd, const char *map_name, int src_value,
goto cleanup;

/* cleanup */
- if (get_opts.path_fd >= 0)
+ if (path_kind == PATH_FD_REL && get_opts.path_fd >= 0)
close(get_opts.path_fd);
if (old_cwd[0])
ASSERT_OK(chdir(old_cwd), "restore_cwd");
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
index d12665490a90..36d829a65aa4 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_helpers.h
@@ -179,6 +179,32 @@
__ret; \
})

+static inline int poll_connect(int fd, unsigned int timeout_sec)
+{
+ struct timeval timeout = { .tv_sec = timeout_sec };
+ fd_set wfds;
+ int r, eval;
+ socklen_t esize = sizeof(eval);
+
+ FD_ZERO(&wfds);
+ FD_SET(fd, &wfds);
+
+ r = select(fd + 1, NULL, &wfds, NULL, &timeout);
+ if (r == 0)
+ errno = ETIME;
+ if (r != 1)
+ return -1;
+
+ if (getsockopt(fd, SOL_SOCKET, SO_ERROR, &eval, &esize) < 0)
+ return -1;
+ if (eval != 0) {
+ errno = eval;
+ return -1;
+ }
+
+ return 0;
+}
+
static inline int poll_read(int fd, unsigned int timeout_sec)
{
struct timeval timeout = { .tv_sec = timeout_sec };
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index 5674a9d0cacf..8df8cbb447f1 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -1452,11 +1452,18 @@ static int vsock_socketpair_connectible(int sotype, int *v0, int *v1)
if (p < 0)
goto close_cli;

+ if (poll_connect(c, IO_TIMEOUT_SEC) < 0) {
+ FAIL_ERRNO("poll_connect");
+ goto close_acc;
+ }
+
*v0 = p;
*v1 = c;

return 0;

+close_acc:
+ close(p);
close_cli:
close(c);
close_srv:
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-dynstring.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-dynstring.tc
index 213d890ed188..174376ddbc6c 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-dynstring.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-dynstring.tc
@@ -1,7 +1,7 @@
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
# description: event trigger - test inter-event histogram trigger trace action with dynamic string param
-# requires: set_event synthetic_events events/sched/sched_process_exec/hist "char name[]' >> synthetic_events":README ping:program
+# requires: set_event synthetic_events events/sched/sched_process_exec/hist "' >> synthetic_events":README ping:program

fail() { #msg
echo $1
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic_event_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic_event_syntax_errors.tc
index 955e3ceea44b..b927ee54c02d 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic_event_syntax_errors.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic_event_syntax_errors.tc
@@ -1,7 +1,7 @@
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
# description: event trigger - test synthetic_events syntax parser errors
-# requires: synthetic_events error_log "char name[]' >> synthetic_events":README
+# requires: synthetic_events error_log "' >> synthetic_events":README

check_error() { # command-with-error-pos-by-^
ftrace_errlog_check 'synthetic_events' "$1" 'synthetic_events'
diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh
index 1c952d1401d4..70e0a465e30d 100644
--- a/tools/testing/selftests/kselftest/runner.sh
+++ b/tools/testing/selftests/kselftest/runner.sh
@@ -36,7 +36,8 @@ tap_timeout()
{
# Make sure tests will time out if utility is available.
if [ -x /usr/bin/timeout ] ; then
- /usr/bin/timeout --foreground "$kselftest_timeout" $1
+ /usr/bin/timeout --foreground "$kselftest_timeout" \
+ /usr/bin/timeout "$kselftest_timeout" $1
else
$1
fi
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index d17854285f2b..118e0964bda9 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -106,7 +106,7 @@ endef
run_tests: all
ifdef building_out_of_srctree
@if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \
- rsync -aLq $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT); \
+ rsync -aq --copy-unsafe-links $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT); \
fi
@if [ "X$(TEST_PROGS)" != "X" ]; then \
$(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) \
@@ -120,7 +120,7 @@ endif

define INSTALL_SINGLE_RULE
$(if $(INSTALL_LIST),@mkdir -p $(INSTALL_PATH))
- $(if $(INSTALL_LIST),rsync -aL $(INSTALL_LIST) $(INSTALL_PATH)/)
+ $(if $(INSTALL_LIST),rsync -a --copy-unsafe-links $(INSTALL_LIST) $(INSTALL_PATH)/)
endef

define INSTALL_RULE
diff --git a/tools/testing/selftests/net/bind_wildcard.c b/tools/testing/selftests/net/bind_wildcard.c
index 58edfc15d28b..e7ebe72e879d 100644
--- a/tools/testing/selftests/net/bind_wildcard.c
+++ b/tools/testing/selftests/net/bind_wildcard.c
@@ -100,7 +100,7 @@ void bind_sockets(struct __test_metadata *_metadata,
TEST_F(bind_wildcard, v4_v6)
{
bind_sockets(_metadata, self,
- (struct sockaddr *)&self->addr4, sizeof(self->addr6),
+ (struct sockaddr *)&self->addr4, sizeof(self->addr4),
(struct sockaddr *)&self->addr6, sizeof(self->addr6));
}