Merge tag 'locking_urgent_for_v5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull locking fix from Borislav Petkov:
- Avoid rwsem lockups in certain situations when handling the handoff
bit
* tag 'locking_urgent_for_v5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
locking/rwsem: Allow slowpath writer to ignore handoff bit if not set by first waiter
diff --git a/.mailmap b/.mailmap
index 13e4f50..71577c3 100644
--- a/.mailmap
+++ b/.mailmap
@@ -60,6 +60,10 @@
Atish Patra <atishp@atishpatra.org> <atish.patra@wdc.com>
Axel Dyks <xl@xlsigned.net>
Axel Lin <axel.lin@gmail.com>
+Baolin Wang <baolin.wang@linux.alibaba.com> <baolin.wang@linaro.org>
+Baolin Wang <baolin.wang@linux.alibaba.com> <baolin.wang@spreadtrum.com>
+Baolin Wang <baolin.wang@linux.alibaba.com> <baolin.wang@unisoc.com>
+Baolin Wang <baolin.wang@linux.alibaba.com> <baolin.wang7@gmail.com>
Bart Van Assche <bvanassche@acm.org> <bart.vanassche@sandisk.com>
Bart Van Assche <bvanassche@acm.org> <bart.vanassche@wdc.com>
Ben Gardner <bgardner@wabtec.com>
@@ -135,6 +139,8 @@
Frank Zago <fzago@systemfabricworks.com>
Gao Xiang <xiang@kernel.org> <gaoxiang25@huawei.com>
Gao Xiang <xiang@kernel.org> <hsiangkao@aol.com>
+Gao Xiang <xiang@kernel.org> <hsiangkao@linux.alibaba.com>
+Gao Xiang <xiang@kernel.org> <hsiangkao@redhat.com>
Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@de.ibm.com>
Gerald Schaefer <gerald.schaefer@linux.ibm.com> <gerald.schaefer@de.ibm.com>
Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@linux.vnet.ibm.com>
@@ -371,6 +377,7 @@
Sebastian Reichel <sre@kernel.org> <sebastian.reichel@collabora.co.uk>
Sebastian Reichel <sre@kernel.org> <sre@debian.org>
Sedat Dilek <sedat.dilek@gmail.com> <sedat.dilek@credativ.de>
+Seth Forshee <sforshee@kernel.org> <seth.forshee@canonical.com>
Shiraz Hashim <shiraz.linux.kernel@gmail.com> <shiraz.hashim@st.com>
Shuah Khan <shuah@kernel.org> <shuahkhan@gmail.com>
Shuah Khan <shuah@kernel.org> <shuah.khan@hp.com>
diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
index 4f15463..170cd20 100644
--- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml
+++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml
@@ -167,70 +167,65 @@
- in-band-status
fixed-link:
- allOf:
- - if:
- type: array
- then:
- deprecated: true
- items:
- - minimum: 0
- maximum: 31
- description:
- Emulated PHY ID, choose any but unique to the all
- specified fixed-links
+ oneOf:
+ - $ref: /schemas/types.yaml#/definitions/uint32-array
+ deprecated: true
+ items:
+ - minimum: 0
+ maximum: 31
+ description:
+ Emulated PHY ID, choose any but unique to the all
+ specified fixed-links
- - enum: [0, 1]
- description:
- Duplex configuration. 0 for half duplex or 1 for
- full duplex
+ - enum: [0, 1]
+ description:
+ Duplex configuration. 0 for half duplex or 1 for
+ full duplex
- - enum: [10, 100, 1000, 2500, 10000]
- description:
- Link speed in Mbits/sec.
+ - enum: [10, 100, 1000, 2500, 10000]
+ description:
+ Link speed in Mbits/sec.
- - enum: [0, 1]
- description:
- Pause configuration. 0 for no pause, 1 for pause
+ - enum: [0, 1]
+ description:
+ Pause configuration. 0 for no pause, 1 for pause
- - enum: [0, 1]
- description:
- Asymmetric pause configuration. 0 for no asymmetric
- pause, 1 for asymmetric pause
+ - enum: [0, 1]
+ description:
+ Asymmetric pause configuration. 0 for no asymmetric
+ pause, 1 for asymmetric pause
+ - type: object
+ additionalProperties: false
+ properties:
+ speed:
+ description:
+ Link speed.
+ $ref: /schemas/types.yaml#/definitions/uint32
+ enum: [10, 100, 1000, 2500, 10000]
+ full-duplex:
+ $ref: /schemas/types.yaml#/definitions/flag
+ description:
+ Indicates that full-duplex is used. When absent, half
+ duplex is assumed.
- - if:
- type: object
- then:
- properties:
- speed:
- description:
- Link speed.
- $ref: /schemas/types.yaml#/definitions/uint32
- enum: [10, 100, 1000, 2500, 10000]
+ pause:
+ $ref: /schemas/types.yaml#definitions/flag
+ description:
+ Indicates that pause should be enabled.
- full-duplex:
- $ref: /schemas/types.yaml#/definitions/flag
- description:
- Indicates that full-duplex is used. When absent, half
- duplex is assumed.
+ asym-pause:
+ $ref: /schemas/types.yaml#/definitions/flag
+ description:
+ Indicates that asym_pause should be enabled.
- pause:
- $ref: /schemas/types.yaml#definitions/flag
- description:
- Indicates that pause should be enabled.
+ link-gpios:
+ maxItems: 1
+ description:
+ GPIO to determine if the link is up
- asym-pause:
- $ref: /schemas/types.yaml#/definitions/flag
- description:
- Indicates that asym_pause should be enabled.
-
- link-gpios:
- maxItems: 1
- description:
- GPIO to determine if the link is up
-
- required:
- - speed
+ required:
+ - speed
additionalProperties: true
diff --git a/Documentation/devicetree/bindings/net/fsl,fec.yaml b/Documentation/devicetree/bindings/net/fsl,fec.yaml
index daa2f79..1b18530 100644
--- a/Documentation/devicetree/bindings/net/fsl,fec.yaml
+++ b/Documentation/devicetree/bindings/net/fsl,fec.yaml
@@ -183,6 +183,7 @@
Should specify the gpio for phy reset.
phy-reset-duration:
+ $ref: /schemas/types.yaml#/definitions/uint32
deprecated: true
description:
Reset duration in milliseconds. Should present only if property
@@ -191,12 +192,14 @@
and 1 millisecond will be used instead.
phy-reset-active-high:
+ type: boolean
deprecated: true
description:
If present then the reset sequence using the GPIO specified in the
"phy-reset-gpios" property is reversed (H=reset state, L=operation state).
phy-reset-post-delay:
+ $ref: /schemas/types.yaml#/definitions/uint32
deprecated: true
description:
Post reset delay in milliseconds. If present then a delay of phy-reset-post-delay
diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index 66c7223..d7a1bf1 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -2866,7 +2866,14 @@
Default: 4K
sctp_wmem - vector of 3 INTEGERs: min, default, max
- Currently this tunable has no effect.
+ Only the first value ("min") is used, "default" and "max" are
+ ignored.
+
+ min: Minimum size of send buffer that can be used by SCTP sockets.
+ It is guaranteed to each SCTP socket (but not association) even
+ under moderate memory pressure.
+
+ Default: 4K
addr_scope_policy - INTEGER
Control IPv4 address scoping - draft-stewart-tsvwg-sctp-ipv4-00
diff --git a/arch/arm/boot/dts/lan966x.dtsi b/arch/arm/boot/dts/lan966x.dtsi
index 3cb02ff..38e90a3 100644
--- a/arch/arm/boot/dts/lan966x.dtsi
+++ b/arch/arm/boot/dts/lan966x.dtsi
@@ -38,7 +38,7 @@ clocks {
sys_clk: sys_clk {
compatible = "fixed-clock";
#clock-cells = <0>;
- clock-frequency = <162500000>;
+ clock-frequency = <165625000>;
};
cpu_clk: cpu_clk {
diff --git a/arch/arm/include/asm/dma.h b/arch/arm/include/asm/dma.h
index a81dda6..45180a2c 100644
--- a/arch/arm/include/asm/dma.h
+++ b/arch/arm/include/asm/dma.h
@@ -10,7 +10,7 @@
#else
#define MAX_DMA_ADDRESS ({ \
extern phys_addr_t arm_dma_zone_size; \
- arm_dma_zone_size && arm_dma_zone_size < (0x10000000 - PAGE_OFFSET) ? \
+ arm_dma_zone_size && arm_dma_zone_size < (0x100000000ULL - PAGE_OFFSET) ? \
(PAGE_OFFSET + arm_dma_zone_size) : 0xffffffffUL; })
#endif
diff --git a/arch/arm/lib/findbit.S b/arch/arm/lib/findbit.S
index b5e8b9a..7fd3600 100644
--- a/arch/arm/lib/findbit.S
+++ b/arch/arm/lib/findbit.S
@@ -40,8 +40,8 @@
* Prototype: int find_next_zero_bit(void *addr, unsigned int maxbit, int offset)
*/
ENTRY(_find_next_zero_bit_le)
- teq r1, #0
- beq 3b
+ cmp r2, r1
+ bhs 3b
ands ip, r2, #7
beq 1b @ If new byte, goto old routine
ARM( ldrb r3, [r0, r2, lsr #3] )
@@ -81,8 +81,8 @@
* Prototype: int find_next_zero_bit(void *addr, unsigned int maxbit, int offset)
*/
ENTRY(_find_next_bit_le)
- teq r1, #0
- beq 3b
+ cmp r2, r1
+ bhs 3b
ands ip, r2, #7
beq 1b @ If new byte, goto old routine
ARM( ldrb r3, [r0, r2, lsr #3] )
@@ -115,8 +115,8 @@
ENDPROC(_find_first_zero_bit_be)
ENTRY(_find_next_zero_bit_be)
- teq r1, #0
- beq 3b
+ cmp r2, r1
+ bhs 3b
ands ip, r2, #7
beq 1b @ If new byte, goto old routine
eor r3, r2, #0x18 @ big endian byte ordering
@@ -149,8 +149,8 @@
ENDPROC(_find_first_bit_be)
ENTRY(_find_next_bit_be)
- teq r1, #0
- beq 3b
+ cmp r2, r1
+ bhs 3b
ands ip, r2, #7
beq 1b @ If new byte, goto old routine
eor r3, r2, #0x18 @ big endian byte ordering
diff --git a/arch/arm/mach-pxa/corgi.c b/arch/arm/mach-pxa/corgi.c
index c546356..5738496 100644
--- a/arch/arm/mach-pxa/corgi.c
+++ b/arch/arm/mach-pxa/corgi.c
@@ -549,7 +549,7 @@ static struct pxa2xx_spi_controller corgi_spi_info = {
};
static struct gpiod_lookup_table corgi_spi_gpio_table = {
- .dev_id = "pxa2xx-spi.1",
+ .dev_id = "spi1",
.table = {
GPIO_LOOKUP_IDX("gpio-pxa", CORGI_GPIO_ADS7846_CS, "cs", 0, GPIO_ACTIVE_LOW),
GPIO_LOOKUP_IDX("gpio-pxa", CORGI_GPIO_LCDCON_CS, "cs", 1, GPIO_ACTIVE_LOW),
diff --git a/arch/arm/mach-pxa/hx4700.c b/arch/arm/mach-pxa/hx4700.c
index 2ae06ed..2fd6659 100644
--- a/arch/arm/mach-pxa/hx4700.c
+++ b/arch/arm/mach-pxa/hx4700.c
@@ -635,7 +635,7 @@ static struct pxa2xx_spi_controller pxa_ssp2_master_info = {
};
static struct gpiod_lookup_table pxa_ssp2_gpio_table = {
- .dev_id = "pxa2xx-spi.2",
+ .dev_id = "spi2",
.table = {
GPIO_LOOKUP_IDX("gpio-pxa", GPIO88_HX4700_TSC2046_CS, "cs", 0, GPIO_ACTIVE_LOW),
{ },
diff --git a/arch/arm/mach-pxa/icontrol.c b/arch/arm/mach-pxa/icontrol.c
index 753fe16..62408825 100644
--- a/arch/arm/mach-pxa/icontrol.c
+++ b/arch/arm/mach-pxa/icontrol.c
@@ -140,7 +140,7 @@ struct platform_device pxa_spi_ssp4 = {
};
static struct gpiod_lookup_table pxa_ssp3_gpio_table = {
- .dev_id = "pxa2xx-spi.3",
+ .dev_id = "spi3",
.table = {
GPIO_LOOKUP_IDX("gpio-pxa", ICONTROL_MCP251x_nCS1, "cs", 0, GPIO_ACTIVE_LOW),
GPIO_LOOKUP_IDX("gpio-pxa", ICONTROL_MCP251x_nCS2, "cs", 1, GPIO_ACTIVE_LOW),
@@ -149,7 +149,7 @@ static struct gpiod_lookup_table pxa_ssp3_gpio_table = {
};
static struct gpiod_lookup_table pxa_ssp4_gpio_table = {
- .dev_id = "pxa2xx-spi.4",
+ .dev_id = "spi4",
.table = {
GPIO_LOOKUP_IDX("gpio-pxa", ICONTROL_MCP251x_nCS3, "cs", 0, GPIO_ACTIVE_LOW),
GPIO_LOOKUP_IDX("gpio-pxa", ICONTROL_MCP251x_nCS4, "cs", 1, GPIO_ACTIVE_LOW),
diff --git a/arch/arm/mach-pxa/littleton.c b/arch/arm/mach-pxa/littleton.c
index f98dc61..98423a9 100644
--- a/arch/arm/mach-pxa/littleton.c
+++ b/arch/arm/mach-pxa/littleton.c
@@ -207,7 +207,7 @@ static struct spi_board_info littleton_spi_devices[] __initdata = {
};
static struct gpiod_lookup_table littleton_spi_gpio_table = {
- .dev_id = "pxa2xx-spi.2",
+ .dev_id = "spi2",
.table = {
GPIO_LOOKUP_IDX("gpio-pxa", LITTLETON_GPIO_LCD_CS, "cs", 0, GPIO_ACTIVE_LOW),
{ },
diff --git a/arch/arm/mach-pxa/magician.c b/arch/arm/mach-pxa/magician.c
index 20456a5..0827ebc 100644
--- a/arch/arm/mach-pxa/magician.c
+++ b/arch/arm/mach-pxa/magician.c
@@ -994,7 +994,7 @@ static struct pxa2xx_spi_controller magician_spi_info = {
};
static struct gpiod_lookup_table magician_spi_gpio_table = {
- .dev_id = "pxa2xx-spi.2",
+ .dev_id = "spi2",
.table = {
/* NOTICE must be GPIO, incompatibility with hw PXA SPI framing */
GPIO_LOOKUP_IDX("gpio-pxa", GPIO14_MAGICIAN_TSC2046_CS, "cs", 0, GPIO_ACTIVE_LOW),
diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c
index dd88953..9964729 100644
--- a/arch/arm/mach-pxa/spitz.c
+++ b/arch/arm/mach-pxa/spitz.c
@@ -578,7 +578,7 @@ static struct pxa2xx_spi_controller spitz_spi_info = {
};
static struct gpiod_lookup_table spitz_spi_gpio_table = {
- .dev_id = "pxa2xx-spi.2",
+ .dev_id = "spi2",
.table = {
GPIO_LOOKUP_IDX("gpio-pxa", SPITZ_GPIO_ADS7846_CS, "cs", 0, GPIO_ACTIVE_LOW),
GPIO_LOOKUP_IDX("gpio-pxa", SPITZ_GPIO_LCDCON_CS, "cs", 1, GPIO_ACTIVE_LOW),
diff --git a/arch/arm/mach-pxa/z2.c b/arch/arm/mach-pxa/z2.c
index d035205..c4d4162 100644
--- a/arch/arm/mach-pxa/z2.c
+++ b/arch/arm/mach-pxa/z2.c
@@ -623,7 +623,7 @@ static struct pxa2xx_spi_controller pxa_ssp2_master_info = {
};
static struct gpiod_lookup_table pxa_ssp1_gpio_table = {
- .dev_id = "pxa2xx-spi.1",
+ .dev_id = "spi1",
.table = {
GPIO_LOOKUP_IDX("gpio-pxa", GPIO24_ZIPITZ2_WIFI_CS, "cs", 0, GPIO_ACTIVE_LOW),
{ },
@@ -631,7 +631,7 @@ static struct gpiod_lookup_table pxa_ssp1_gpio_table = {
};
static struct gpiod_lookup_table pxa_ssp2_gpio_table = {
- .dev_id = "pxa2xx-spi.2",
+ .dev_id = "spi2",
.table = {
GPIO_LOOKUP_IDX("gpio-pxa", GPIO88_ZIPITZ2_LCD_CS, "cs", 0, GPIO_ACTIVE_LOW),
{ },
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index b57daee..62b5b07 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -69,7 +69,6 @@
select GENERIC_TIME_VSYSCALL
select GPIOLIB
select HAVE_ARCH_AUDITSYSCALL
- select HAVE_ARCH_COMPILER_H
select HAVE_ARCH_MMAP_RND_BITS if MMU
select HAVE_ARCH_SECCOMP_FILTER
select HAVE_ARCH_TRACEHOOK
diff --git a/arch/loongarch/include/asm/asmmacro.h b/arch/loongarch/include/asm/asmmacro.h
index a1a0408..be037a4 100644
--- a/arch/loongarch/include/asm/asmmacro.h
+++ b/arch/loongarch/include/asm/asmmacro.h
@@ -274,16 +274,4 @@
nor \dst, \src, zero
.endm
-.macro bgt r0 r1 label
- blt \r1, \r0, \label
-.endm
-
-.macro bltz r0 label
- blt \r0, zero, \label
-.endm
-
-.macro bgez r0 label
- bge \r0, zero, \label
-.endm
-
#endif /* _ASM_ASMMACRO_H */
diff --git a/arch/loongarch/include/asm/atomic.h b/arch/loongarch/include/asm/atomic.h
index 979367a..6b9aca9 100644
--- a/arch/loongarch/include/asm/atomic.h
+++ b/arch/loongarch/include/asm/atomic.h
@@ -10,7 +10,6 @@
#include <linux/types.h>
#include <asm/barrier.h>
#include <asm/cmpxchg.h>
-#include <asm/compiler.h>
#if __SIZEOF_LONG__ == 4
#define __LL "ll.w "
@@ -157,27 +156,25 @@ static inline int arch_atomic_sub_if_positive(int i, atomic_t *v)
__asm__ __volatile__(
"1: ll.w %1, %2 # atomic_sub_if_positive\n"
" addi.w %0, %1, %3 \n"
- " or %1, %0, $zero \n"
- " blt %0, $zero, 2f \n"
+ " move %1, %0 \n"
+ " bltz %0, 2f \n"
" sc.w %1, %2 \n"
- " beq $zero, %1, 1b \n"
+ " beqz %1, 1b \n"
"2: \n"
__WEAK_LLSC_MB
- : "=&r" (result), "=&r" (temp),
- "+" GCC_OFF_SMALL_ASM() (v->counter)
+ : "=&r" (result), "=&r" (temp), "+ZC" (v->counter)
: "I" (-i));
} else {
__asm__ __volatile__(
"1: ll.w %1, %2 # atomic_sub_if_positive\n"
" sub.w %0, %1, %3 \n"
- " or %1, %0, $zero \n"
- " blt %0, $zero, 2f \n"
+ " move %1, %0 \n"
+ " bltz %0, 2f \n"
" sc.w %1, %2 \n"
- " beq $zero, %1, 1b \n"
+ " beqz %1, 1b \n"
"2: \n"
__WEAK_LLSC_MB
- : "=&r" (result), "=&r" (temp),
- "+" GCC_OFF_SMALL_ASM() (v->counter)
+ : "=&r" (result), "=&r" (temp), "+ZC" (v->counter)
: "r" (i));
}
@@ -320,27 +317,25 @@ static inline long arch_atomic64_sub_if_positive(long i, atomic64_t *v)
__asm__ __volatile__(
"1: ll.d %1, %2 # atomic64_sub_if_positive \n"
" addi.d %0, %1, %3 \n"
- " or %1, %0, $zero \n"
- " blt %0, $zero, 2f \n"
+ " move %1, %0 \n"
+ " bltz %0, 2f \n"
" sc.d %1, %2 \n"
- " beq %1, $zero, 1b \n"
+ " beqz %1, 1b \n"
"2: \n"
__WEAK_LLSC_MB
- : "=&r" (result), "=&r" (temp),
- "+" GCC_OFF_SMALL_ASM() (v->counter)
+ : "=&r" (result), "=&r" (temp), "+ZC" (v->counter)
: "I" (-i));
} else {
__asm__ __volatile__(
"1: ll.d %1, %2 # atomic64_sub_if_positive \n"
" sub.d %0, %1, %3 \n"
- " or %1, %0, $zero \n"
- " blt %0, $zero, 2f \n"
+ " move %1, %0 \n"
+ " bltz %0, 2f \n"
" sc.d %1, %2 \n"
- " beq %1, $zero, 1b \n"
+ " beqz %1, 1b \n"
"2: \n"
__WEAK_LLSC_MB
- : "=&r" (result), "=&r" (temp),
- "+" GCC_OFF_SMALL_ASM() (v->counter)
+ : "=&r" (result), "=&r" (temp), "+ZC" (v->counter)
: "r" (i));
}
diff --git a/arch/loongarch/include/asm/barrier.h b/arch/loongarch/include/asm/barrier.h
index b6517ee..cda9776 100644
--- a/arch/loongarch/include/asm/barrier.h
+++ b/arch/loongarch/include/asm/barrier.h
@@ -48,9 +48,9 @@ static inline unsigned long array_index_mask_nospec(unsigned long index,
__asm__ __volatile__(
"sltu %0, %1, %2\n\t"
#if (__SIZEOF_LONG__ == 4)
- "sub.w %0, $r0, %0\n\t"
+ "sub.w %0, $zero, %0\n\t"
#elif (__SIZEOF_LONG__ == 8)
- "sub.d %0, $r0, %0\n\t"
+ "sub.d %0, $zero, %0\n\t"
#endif
: "=r" (mask)
: "r" (index), "r" (size)
diff --git a/arch/loongarch/include/asm/cmpxchg.h b/arch/loongarch/include/asm/cmpxchg.h
index 75b3a44..0a9b0fa 100644
--- a/arch/loongarch/include/asm/cmpxchg.h
+++ b/arch/loongarch/include/asm/cmpxchg.h
@@ -55,9 +55,9 @@ static inline unsigned long __xchg(volatile void *ptr, unsigned long x,
__asm__ __volatile__( \
"1: " ld " %0, %2 # __cmpxchg_asm \n" \
" bne %0, %z3, 2f \n" \
- " or $t0, %z4, $zero \n" \
+ " move $t0, %z4 \n" \
" " st " $t0, %1 \n" \
- " beq $zero, $t0, 1b \n" \
+ " beqz $t0, 1b \n" \
"2: \n" \
__WEAK_LLSC_MB \
: "=&r" (__ret), "=ZB"(*m) \
diff --git a/arch/loongarch/include/asm/compiler.h b/arch/loongarch/include/asm/compiler.h
deleted file mode 100644
index 657cebe..0000000
--- a/arch/loongarch/include/asm/compiler.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
- */
-#ifndef _ASM_COMPILER_H
-#define _ASM_COMPILER_H
-
-#define GCC_OFF_SMALL_ASM() "ZC"
-
-#define LOONGARCH_ISA_LEVEL "loongarch"
-#define LOONGARCH_ISA_ARCH_LEVEL "arch=loongarch"
-#define LOONGARCH_ISA_LEVEL_RAW loongarch
-#define LOONGARCH_ISA_ARCH_LEVEL_RAW LOONGARCH_ISA_LEVEL_RAW
-
-#endif /* _ASM_COMPILER_H */
diff --git a/arch/loongarch/include/asm/elf.h b/arch/loongarch/include/asm/elf.h
index f3960b1..5f3ff47 100644
--- a/arch/loongarch/include/asm/elf.h
+++ b/arch/loongarch/include/asm/elf.h
@@ -288,8 +288,6 @@ struct arch_elf_state {
.interp_fp_abi = LOONGARCH_ABI_FP_ANY, \
}
-#define elf_read_implies_exec(ex, exec_stk) (exec_stk == EXSTACK_DEFAULT)
-
extern int arch_elf_pt_proc(void *ehdr, void *phdr, struct file *elf,
bool is_interp, struct arch_elf_state *state);
diff --git a/arch/loongarch/include/asm/futex.h b/arch/loongarch/include/asm/futex.h
index 9de8231..feb6658 100644
--- a/arch/loongarch/include/asm/futex.h
+++ b/arch/loongarch/include/asm/futex.h
@@ -8,7 +8,6 @@
#include <linux/futex.h>
#include <linux/uaccess.h>
#include <asm/barrier.h>
-#include <asm/compiler.h>
#include <asm/errno.h>
#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \
@@ -17,7 +16,7 @@
"1: ll.w %1, %4 # __futex_atomic_op\n" \
" " insn " \n" \
"2: sc.w $t0, %2 \n" \
- " beq $t0, $zero, 1b \n" \
+ " beqz $t0, 1b \n" \
"3: \n" \
" .section .fixup,\"ax\" \n" \
"4: li.w %0, %6 \n" \
@@ -82,9 +81,9 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newv
"# futex_atomic_cmpxchg_inatomic \n"
"1: ll.w %1, %3 \n"
" bne %1, %z4, 3f \n"
- " or $t0, %z5, $zero \n"
+ " move $t0, %z5 \n"
"2: sc.w $t0, %2 \n"
- " beq $zero, $t0, 1b \n"
+ " beqz $t0, 1b \n"
"3: \n"
__WEAK_LLSC_MB
" .section .fixup,\"ax\" \n"
@@ -95,8 +94,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newv
" "__UA_ADDR "\t1b, 4b \n"
" "__UA_ADDR "\t2b, 4b \n"
" .previous \n"
- : "+r" (ret), "=&r" (val), "=" GCC_OFF_SMALL_ASM() (*uaddr)
- : GCC_OFF_SMALL_ASM() (*uaddr), "Jr" (oldval), "Jr" (newval),
+ : "+r" (ret), "=&r" (val), "=ZC" (*uaddr)
+ : "ZC" (*uaddr), "Jr" (oldval), "Jr" (newval),
"i" (-EFAULT)
: "memory", "t0");
diff --git a/arch/loongarch/include/asm/irqflags.h b/arch/loongarch/include/asm/irqflags.h
index 52121cd..319a8c6 100644
--- a/arch/loongarch/include/asm/irqflags.h
+++ b/arch/loongarch/include/asm/irqflags.h
@@ -9,7 +9,6 @@
#include <linux/compiler.h>
#include <linux/stringify.h>
-#include <asm/compiler.h>
#include <asm/loongarch.h>
static inline void arch_local_irq_enable(void)
diff --git a/arch/loongarch/include/asm/local.h b/arch/loongarch/include/asm/local.h
index 2052a22..65fbbae 100644
--- a/arch/loongarch/include/asm/local.h
+++ b/arch/loongarch/include/asm/local.h
@@ -9,7 +9,6 @@
#include <linux/bitops.h>
#include <linux/atomic.h>
#include <asm/cmpxchg.h>
-#include <asm/compiler.h>
typedef struct {
atomic_long_t a;
diff --git a/arch/loongarch/include/asm/loongson.h b/arch/loongarch/include/asm/loongson.h
index 6a80387..6e8f697 100644
--- a/arch/loongarch/include/asm/loongson.h
+++ b/arch/loongarch/include/asm/loongson.h
@@ -39,18 +39,6 @@ extern const struct plat_smp_ops loongson3_smp_ops;
#define MAX_PACKAGES 16
-/* Chip Config register of each physical cpu package */
-extern u64 loongson_chipcfg[MAX_PACKAGES];
-#define LOONGSON_CHIPCFG(id) (*(volatile u32 *)(loongson_chipcfg[id]))
-
-/* Chip Temperature register of each physical cpu package */
-extern u64 loongson_chiptemp[MAX_PACKAGES];
-#define LOONGSON_CHIPTEMP(id) (*(volatile u32 *)(loongson_chiptemp[id]))
-
-/* Freq Control register of each physical cpu package */
-extern u64 loongson_freqctrl[MAX_PACKAGES];
-#define LOONGSON_FREQCTRL(id) (*(volatile u32 *)(loongson_freqctrl[id]))
-
#define xconf_readl(addr) readl(addr)
#define xconf_readq(addr) readq(addr)
@@ -58,7 +46,7 @@ static inline void xconf_writel(u32 val, volatile void __iomem *addr)
{
asm volatile (
" st.w %[v], %[hw], 0 \n"
- " ld.b $r0, %[hw], 0 \n"
+ " ld.b $zero, %[hw], 0 \n"
:
: [hw] "r" (addr), [v] "r" (val)
);
@@ -68,7 +56,7 @@ static inline void xconf_writeq(u64 val64, volatile void __iomem *addr)
{
asm volatile (
" st.d %[v], %[hw], 0 \n"
- " ld.b $r0, %[hw], 0 \n"
+ " ld.b $zero, %[hw], 0 \n"
:
: [hw] "r" (addr), [v] "r" (val64)
);
diff --git a/arch/loongarch/include/asm/stacktrace.h b/arch/loongarch/include/asm/stacktrace.h
index 26483e3..6b5c2a7 100644
--- a/arch/loongarch/include/asm/stacktrace.h
+++ b/arch/loongarch/include/asm/stacktrace.h
@@ -23,13 +23,13 @@
static __always_inline void prepare_frametrace(struct pt_regs *regs)
{
__asm__ __volatile__(
- /* Save $r1 */
+ /* Save $ra */
STORE_ONE_REG(1)
- /* Use $r1 to save PC */
- "pcaddi $r1, 0\n\t"
- STR_LONG_S " $r1, %0\n\t"
- /* Restore $r1 */
- STR_LONG_L " $r1, %1, "STR_LONGSIZE"\n\t"
+ /* Use $ra to save PC */
+ "pcaddi $ra, 0\n\t"
+ STR_LONG_S " $ra, %0\n\t"
+ /* Restore $ra */
+ STR_LONG_L " $ra, %1, "STR_LONGSIZE"\n\t"
STORE_ONE_REG(2)
STORE_ONE_REG(3)
STORE_ONE_REG(4)
diff --git a/arch/loongarch/include/asm/thread_info.h b/arch/loongarch/include/asm/thread_info.h
index 99beb11..b7dd9f1 100644
--- a/arch/loongarch/include/asm/thread_info.h
+++ b/arch/loongarch/include/asm/thread_info.h
@@ -44,14 +44,14 @@ struct thread_info {
}
/* How to get the thread information struct from C. */
-register struct thread_info *__current_thread_info __asm__("$r2");
+register struct thread_info *__current_thread_info __asm__("$tp");
static inline struct thread_info *current_thread_info(void)
{
return __current_thread_info;
}
-register unsigned long current_stack_pointer __asm__("$r3");
+register unsigned long current_stack_pointer __asm__("$sp");
#endif /* !__ASSEMBLY__ */
diff --git a/arch/loongarch/include/asm/uaccess.h b/arch/loongarch/include/asm/uaccess.h
index 217c6a3..2b44edc 100644
--- a/arch/loongarch/include/asm/uaccess.h
+++ b/arch/loongarch/include/asm/uaccess.h
@@ -162,7 +162,7 @@ do { \
"2: \n" \
" .section .fixup,\"ax\" \n" \
"3: li.w %0, %3 \n" \
- " or %1, $r0, $r0 \n" \
+ " move %1, $zero \n" \
" b 2b \n" \
" .previous \n" \
" .section __ex_table,\"a\" \n" \
diff --git a/arch/loongarch/kernel/cacheinfo.c b/arch/loongarch/kernel/cacheinfo.c
index b38f548..4662b06 100644
--- a/arch/loongarch/kernel/cacheinfo.c
+++ b/arch/loongarch/kernel/cacheinfo.c
@@ -4,8 +4,9 @@
*
* Copyright (C) 2020-2022 Loongson Technology Corporation Limited
*/
-#include <asm/cpu-info.h>
#include <linux/cacheinfo.h>
+#include <asm/bootinfo.h>
+#include <asm/cpu-info.h>
/* Populates leaf and increments to next leaf */
#define populate_cache(cache, leaf, c_level, c_type) \
@@ -17,6 +18,8 @@ do { \
leaf->ways_of_associativity = c->cache.ways; \
leaf->size = c->cache.linesz * c->cache.sets * \
c->cache.ways; \
+ if (leaf->level > 2) \
+ leaf->size *= nodes_per_package; \
leaf++; \
} while (0)
@@ -95,11 +98,15 @@ static void cache_cpumap_setup(unsigned int cpu)
int populate_cache_leaves(unsigned int cpu)
{
- int level = 1;
+ int level = 1, nodes_per_package = 1;
struct cpuinfo_loongarch *c = ¤t_cpu_data;
struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
struct cacheinfo *this_leaf = this_cpu_ci->info_list;
+ if (loongson_sysconf.nr_nodes > 1)
+ nodes_per_package = loongson_sysconf.cores_per_package
+ / loongson_sysconf.cores_per_node;
+
if (c->icache.waysize) {
populate_cache(dcache, this_leaf, level, CACHE_TYPE_DATA);
populate_cache(icache, this_leaf, level++, CACHE_TYPE_INST);
diff --git a/arch/loongarch/kernel/entry.S b/arch/loongarch/kernel/entry.S
index d5b3dbc..d53b631 100644
--- a/arch/loongarch/kernel/entry.S
+++ b/arch/loongarch/kernel/entry.S
@@ -27,7 +27,7 @@
addi.d sp, sp, -PT_SIZE
cfi_st t2, PT_R3
- cfi_rel_offset sp, PT_R3
+ cfi_rel_offset sp, PT_R3
st.d zero, sp, PT_R0
csrrd t2, LOONGARCH_CSR_PRMD
st.d t2, sp, PT_PRMD
@@ -50,7 +50,7 @@
cfi_st a7, PT_R11
csrrd ra, LOONGARCH_CSR_ERA
st.d ra, sp, PT_ERA
- cfi_rel_offset ra, PT_ERA
+ cfi_rel_offset ra, PT_ERA
cfi_st tp, PT_R2
cfi_st u0, PT_R21
diff --git a/arch/loongarch/kernel/env.c b/arch/loongarch/kernel/env.c
index 467946e..82b478a 100644
--- a/arch/loongarch/kernel/env.c
+++ b/arch/loongarch/kernel/env.c
@@ -17,21 +17,6 @@ u64 efi_system_table;
struct loongson_system_configuration loongson_sysconf;
EXPORT_SYMBOL(loongson_sysconf);
-u64 loongson_chipcfg[MAX_PACKAGES];
-u64 loongson_chiptemp[MAX_PACKAGES];
-u64 loongson_freqctrl[MAX_PACKAGES];
-unsigned long long smp_group[MAX_PACKAGES];
-
-static void __init register_addrs_set(u64 *registers, const u64 addr, int num)
-{
- u64 i;
-
- for (i = 0; i < num; i++) {
- *registers = (i << 44) | addr;
- registers++;
- }
-}
-
void __init init_environ(void)
{
int efi_boot = fw_arg0;
@@ -50,11 +35,6 @@ void __init init_environ(void)
efi_memmap_init_early(&data);
memblock_reserve(data.phys_map & PAGE_MASK,
PAGE_ALIGN(data.size + (data.phys_map & ~PAGE_MASK)));
-
- register_addrs_set(smp_group, TO_UNCACHE(0x1fe01000), 16);
- register_addrs_set(loongson_chipcfg, TO_UNCACHE(0x1fe00180), 16);
- register_addrs_set(loongson_chiptemp, TO_UNCACHE(0x1fe0019c), 16);
- register_addrs_set(loongson_freqctrl, TO_UNCACHE(0x1fe001d0), 16);
}
static int __init init_cpu_fullname(void)
diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S
index a631a71..576b337 100644
--- a/arch/loongarch/kernel/fpu.S
+++ b/arch/loongarch/kernel/fpu.S
@@ -27,78 +27,78 @@
.endm
.macro sc_save_fp base
- EX fst.d $f0, \base, (0 * FPU_REG_WIDTH)
- EX fst.d $f1, \base, (1 * FPU_REG_WIDTH)
- EX fst.d $f2, \base, (2 * FPU_REG_WIDTH)
- EX fst.d $f3, \base, (3 * FPU_REG_WIDTH)
- EX fst.d $f4, \base, (4 * FPU_REG_WIDTH)
- EX fst.d $f5, \base, (5 * FPU_REG_WIDTH)
- EX fst.d $f6, \base, (6 * FPU_REG_WIDTH)
- EX fst.d $f7, \base, (7 * FPU_REG_WIDTH)
- EX fst.d $f8, \base, (8 * FPU_REG_WIDTH)
- EX fst.d $f9, \base, (9 * FPU_REG_WIDTH)
- EX fst.d $f10, \base, (10 * FPU_REG_WIDTH)
- EX fst.d $f11, \base, (11 * FPU_REG_WIDTH)
- EX fst.d $f12, \base, (12 * FPU_REG_WIDTH)
- EX fst.d $f13, \base, (13 * FPU_REG_WIDTH)
- EX fst.d $f14, \base, (14 * FPU_REG_WIDTH)
- EX fst.d $f15, \base, (15 * FPU_REG_WIDTH)
- EX fst.d $f16, \base, (16 * FPU_REG_WIDTH)
- EX fst.d $f17, \base, (17 * FPU_REG_WIDTH)
- EX fst.d $f18, \base, (18 * FPU_REG_WIDTH)
- EX fst.d $f19, \base, (19 * FPU_REG_WIDTH)
- EX fst.d $f20, \base, (20 * FPU_REG_WIDTH)
- EX fst.d $f21, \base, (21 * FPU_REG_WIDTH)
- EX fst.d $f22, \base, (22 * FPU_REG_WIDTH)
- EX fst.d $f23, \base, (23 * FPU_REG_WIDTH)
- EX fst.d $f24, \base, (24 * FPU_REG_WIDTH)
- EX fst.d $f25, \base, (25 * FPU_REG_WIDTH)
- EX fst.d $f26, \base, (26 * FPU_REG_WIDTH)
- EX fst.d $f27, \base, (27 * FPU_REG_WIDTH)
- EX fst.d $f28, \base, (28 * FPU_REG_WIDTH)
- EX fst.d $f29, \base, (29 * FPU_REG_WIDTH)
- EX fst.d $f30, \base, (30 * FPU_REG_WIDTH)
- EX fst.d $f31, \base, (31 * FPU_REG_WIDTH)
+ EX fst.d $f0, \base, (0 * FPU_REG_WIDTH)
+ EX fst.d $f1, \base, (1 * FPU_REG_WIDTH)
+ EX fst.d $f2, \base, (2 * FPU_REG_WIDTH)
+ EX fst.d $f3, \base, (3 * FPU_REG_WIDTH)
+ EX fst.d $f4, \base, (4 * FPU_REG_WIDTH)
+ EX fst.d $f5, \base, (5 * FPU_REG_WIDTH)
+ EX fst.d $f6, \base, (6 * FPU_REG_WIDTH)
+ EX fst.d $f7, \base, (7 * FPU_REG_WIDTH)
+ EX fst.d $f8, \base, (8 * FPU_REG_WIDTH)
+ EX fst.d $f9, \base, (9 * FPU_REG_WIDTH)
+ EX fst.d $f10, \base, (10 * FPU_REG_WIDTH)
+ EX fst.d $f11, \base, (11 * FPU_REG_WIDTH)
+ EX fst.d $f12, \base, (12 * FPU_REG_WIDTH)
+ EX fst.d $f13, \base, (13 * FPU_REG_WIDTH)
+ EX fst.d $f14, \base, (14 * FPU_REG_WIDTH)
+ EX fst.d $f15, \base, (15 * FPU_REG_WIDTH)
+ EX fst.d $f16, \base, (16 * FPU_REG_WIDTH)
+ EX fst.d $f17, \base, (17 * FPU_REG_WIDTH)
+ EX fst.d $f18, \base, (18 * FPU_REG_WIDTH)
+ EX fst.d $f19, \base, (19 * FPU_REG_WIDTH)
+ EX fst.d $f20, \base, (20 * FPU_REG_WIDTH)
+ EX fst.d $f21, \base, (21 * FPU_REG_WIDTH)
+ EX fst.d $f22, \base, (22 * FPU_REG_WIDTH)
+ EX fst.d $f23, \base, (23 * FPU_REG_WIDTH)
+ EX fst.d $f24, \base, (24 * FPU_REG_WIDTH)
+ EX fst.d $f25, \base, (25 * FPU_REG_WIDTH)
+ EX fst.d $f26, \base, (26 * FPU_REG_WIDTH)
+ EX fst.d $f27, \base, (27 * FPU_REG_WIDTH)
+ EX fst.d $f28, \base, (28 * FPU_REG_WIDTH)
+ EX fst.d $f29, \base, (29 * FPU_REG_WIDTH)
+ EX fst.d $f30, \base, (30 * FPU_REG_WIDTH)
+ EX fst.d $f31, \base, (31 * FPU_REG_WIDTH)
.endm
.macro sc_restore_fp base
- EX fld.d $f0, \base, (0 * FPU_REG_WIDTH)
- EX fld.d $f1, \base, (1 * FPU_REG_WIDTH)
- EX fld.d $f2, \base, (2 * FPU_REG_WIDTH)
- EX fld.d $f3, \base, (3 * FPU_REG_WIDTH)
- EX fld.d $f4, \base, (4 * FPU_REG_WIDTH)
- EX fld.d $f5, \base, (5 * FPU_REG_WIDTH)
- EX fld.d $f6, \base, (6 * FPU_REG_WIDTH)
- EX fld.d $f7, \base, (7 * FPU_REG_WIDTH)
- EX fld.d $f8, \base, (8 * FPU_REG_WIDTH)
- EX fld.d $f9, \base, (9 * FPU_REG_WIDTH)
- EX fld.d $f10, \base, (10 * FPU_REG_WIDTH)
- EX fld.d $f11, \base, (11 * FPU_REG_WIDTH)
- EX fld.d $f12, \base, (12 * FPU_REG_WIDTH)
- EX fld.d $f13, \base, (13 * FPU_REG_WIDTH)
- EX fld.d $f14, \base, (14 * FPU_REG_WIDTH)
- EX fld.d $f15, \base, (15 * FPU_REG_WIDTH)
- EX fld.d $f16, \base, (16 * FPU_REG_WIDTH)
- EX fld.d $f17, \base, (17 * FPU_REG_WIDTH)
- EX fld.d $f18, \base, (18 * FPU_REG_WIDTH)
- EX fld.d $f19, \base, (19 * FPU_REG_WIDTH)
- EX fld.d $f20, \base, (20 * FPU_REG_WIDTH)
- EX fld.d $f21, \base, (21 * FPU_REG_WIDTH)
- EX fld.d $f22, \base, (22 * FPU_REG_WIDTH)
- EX fld.d $f23, \base, (23 * FPU_REG_WIDTH)
- EX fld.d $f24, \base, (24 * FPU_REG_WIDTH)
- EX fld.d $f25, \base, (25 * FPU_REG_WIDTH)
- EX fld.d $f26, \base, (26 * FPU_REG_WIDTH)
- EX fld.d $f27, \base, (27 * FPU_REG_WIDTH)
- EX fld.d $f28, \base, (28 * FPU_REG_WIDTH)
- EX fld.d $f29, \base, (29 * FPU_REG_WIDTH)
- EX fld.d $f30, \base, (30 * FPU_REG_WIDTH)
- EX fld.d $f31, \base, (31 * FPU_REG_WIDTH)
+ EX fld.d $f0, \base, (0 * FPU_REG_WIDTH)
+ EX fld.d $f1, \base, (1 * FPU_REG_WIDTH)
+ EX fld.d $f2, \base, (2 * FPU_REG_WIDTH)
+ EX fld.d $f3, \base, (3 * FPU_REG_WIDTH)
+ EX fld.d $f4, \base, (4 * FPU_REG_WIDTH)
+ EX fld.d $f5, \base, (5 * FPU_REG_WIDTH)
+ EX fld.d $f6, \base, (6 * FPU_REG_WIDTH)
+ EX fld.d $f7, \base, (7 * FPU_REG_WIDTH)
+ EX fld.d $f8, \base, (8 * FPU_REG_WIDTH)
+ EX fld.d $f9, \base, (9 * FPU_REG_WIDTH)
+ EX fld.d $f10, \base, (10 * FPU_REG_WIDTH)
+ EX fld.d $f11, \base, (11 * FPU_REG_WIDTH)
+ EX fld.d $f12, \base, (12 * FPU_REG_WIDTH)
+ EX fld.d $f13, \base, (13 * FPU_REG_WIDTH)
+ EX fld.d $f14, \base, (14 * FPU_REG_WIDTH)
+ EX fld.d $f15, \base, (15 * FPU_REG_WIDTH)
+ EX fld.d $f16, \base, (16 * FPU_REG_WIDTH)
+ EX fld.d $f17, \base, (17 * FPU_REG_WIDTH)
+ EX fld.d $f18, \base, (18 * FPU_REG_WIDTH)
+ EX fld.d $f19, \base, (19 * FPU_REG_WIDTH)
+ EX fld.d $f20, \base, (20 * FPU_REG_WIDTH)
+ EX fld.d $f21, \base, (21 * FPU_REG_WIDTH)
+ EX fld.d $f22, \base, (22 * FPU_REG_WIDTH)
+ EX fld.d $f23, \base, (23 * FPU_REG_WIDTH)
+ EX fld.d $f24, \base, (24 * FPU_REG_WIDTH)
+ EX fld.d $f25, \base, (25 * FPU_REG_WIDTH)
+ EX fld.d $f26, \base, (26 * FPU_REG_WIDTH)
+ EX fld.d $f27, \base, (27 * FPU_REG_WIDTH)
+ EX fld.d $f28, \base, (28 * FPU_REG_WIDTH)
+ EX fld.d $f29, \base, (29 * FPU_REG_WIDTH)
+ EX fld.d $f30, \base, (30 * FPU_REG_WIDTH)
+ EX fld.d $f31, \base, (31 * FPU_REG_WIDTH)
.endm
.macro sc_save_fcc base, tmp0, tmp1
movcf2gr \tmp0, $fcc0
- move \tmp1, \tmp0
+ move \tmp1, \tmp0
movcf2gr \tmp0, $fcc1
bstrins.d \tmp1, \tmp0, 15, 8
movcf2gr \tmp0, $fcc2
@@ -113,11 +113,11 @@
bstrins.d \tmp1, \tmp0, 55, 48
movcf2gr \tmp0, $fcc7
bstrins.d \tmp1, \tmp0, 63, 56
- EX st.d \tmp1, \base, 0
+ EX st.d \tmp1, \base, 0
.endm
.macro sc_restore_fcc base, tmp0, tmp1
- EX ld.d \tmp0, \base, 0
+ EX ld.d \tmp0, \base, 0
bstrpick.d \tmp1, \tmp0, 7, 0
movgr2cf $fcc0, \tmp1
bstrpick.d \tmp1, \tmp0, 15, 8
@@ -138,11 +138,11 @@
.macro sc_save_fcsr base, tmp0
movfcsr2gr \tmp0, fcsr0
- EX st.w \tmp0, \base, 0
+ EX st.w \tmp0, \base, 0
.endm
.macro sc_restore_fcsr base, tmp0
- EX ld.w \tmp0, \base, 0
+ EX ld.w \tmp0, \base, 0
movgr2fcsr fcsr0, \tmp0
.endm
@@ -151,9 +151,9 @@
*/
SYM_FUNC_START(_save_fp)
fpu_save_csr a0 t1
- fpu_save_double a0 t1 # clobbers t1
+ fpu_save_double a0 t1 # clobbers t1
fpu_save_cc a0 t1 t2 # clobbers t1, t2
- jirl zero, ra, 0
+ jr ra
SYM_FUNC_END(_save_fp)
EXPORT_SYMBOL(_save_fp)
@@ -161,10 +161,10 @@
* Restore a thread's fp context.
*/
SYM_FUNC_START(_restore_fp)
- fpu_restore_double a0 t1 # clobbers t1
- fpu_restore_csr a0 t1
- fpu_restore_cc a0 t1 t2 # clobbers t1, t2
- jirl zero, ra, 0
+ fpu_restore_double a0 t1 # clobbers t1
+ fpu_restore_csr a0 t1
+ fpu_restore_cc a0 t1 t2 # clobbers t1, t2
+ jr ra
SYM_FUNC_END(_restore_fp)
/*
@@ -216,7 +216,7 @@
movgr2fr.d $f30, t1
movgr2fr.d $f31, t1
- jirl zero, ra, 0
+ jr ra
SYM_FUNC_END(_init_fpu)
/*
@@ -225,11 +225,11 @@
* a2: fcsr
*/
SYM_FUNC_START(_save_fp_context)
- sc_save_fcc a1 t1 t2
- sc_save_fcsr a2 t1
- sc_save_fp a0
- li.w a0, 0 # success
- jirl zero, ra, 0
+ sc_save_fcc a1 t1 t2
+ sc_save_fcsr a2 t1
+ sc_save_fp a0
+ li.w a0, 0 # success
+ jr ra
SYM_FUNC_END(_save_fp_context)
/*
@@ -238,14 +238,14 @@
* a2: fcsr
*/
SYM_FUNC_START(_restore_fp_context)
- sc_restore_fp a0
- sc_restore_fcc a1 t1 t2
- sc_restore_fcsr a2 t1
- li.w a0, 0 # success
- jirl zero, ra, 0
+ sc_restore_fp a0
+ sc_restore_fcc a1 t1 t2
+ sc_restore_fcsr a2 t1
+ li.w a0, 0 # success
+ jr ra
SYM_FUNC_END(_restore_fp_context)
SYM_FUNC_START(fault)
li.w a0, -EFAULT # failure
- jirl zero, ra, 0
+ jr ra
SYM_FUNC_END(fault)
diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S
index 9349685..75e5be8 100644
--- a/arch/loongarch/kernel/genex.S
+++ b/arch/loongarch/kernel/genex.S
@@ -28,23 +28,23 @@
nop
idle 0
/* end of rollback region */
-1: jirl zero, ra, 0
+1: jr ra
SYM_FUNC_END(__arch_cpu_idle)
SYM_FUNC_START(handle_vint)
BACKUP_T0T1
SAVE_ALL
la.abs t1, __arch_cpu_idle
- LONG_L t0, sp, PT_ERA
+ LONG_L t0, sp, PT_ERA
/* 32 byte rollback region */
ori t0, t0, 0x1f
xori t0, t0, 0x1f
bne t0, t1, 1f
- LONG_S t0, sp, PT_ERA
+ LONG_S t0, sp, PT_ERA
1: move a0, sp
move a1, sp
la.abs t0, do_vint
- jirl ra, t0, 0
+ jirl ra, t0, 0
RESTORE_ALL_AND_RET
SYM_FUNC_END(handle_vint)
@@ -72,7 +72,7 @@
build_prep_\prep
move a0, sp
la.abs t0, do_\handler
- jirl ra, t0, 0
+ jirl ra, t0, 0
RESTORE_ALL_AND_RET
SYM_FUNC_END(handle_\exception)
.endm
@@ -91,5 +91,5 @@
SYM_FUNC_START(handle_sys)
la.abs t0, handle_syscall
- jirl zero, t0, 0
+ jr t0
SYM_FUNC_END(handle_sys)
diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S
index d01e62dd..7062cdf 100644
--- a/arch/loongarch/kernel/head.S
+++ b/arch/loongarch/kernel/head.S
@@ -32,7 +32,7 @@
/* We might not get launched at the address the kernel is linked to,
so we jump there. */
la.abs t0, 0f
- jirl zero, t0, 0
+ jr t0
0:
la t0, __bss_start # clear .bss
st.d zero, t0, 0
@@ -50,7 +50,7 @@
/* KSave3 used for percpu base, initialized as 0 */
csrwr zero, PERCPU_BASE_KS
/* GPR21 used for percpu base (runtime), initialized as 0 */
- or u0, zero, zero
+ move u0, zero
la tp, init_thread_union
/* Set the SP after an empty pt_regs. */
@@ -85,8 +85,8 @@
ld.d sp, t0, CPU_BOOT_STACK
ld.d tp, t0, CPU_BOOT_TINFO
- la.abs t0, 0f
- jirl zero, t0, 0
+ la.abs t0, 0f
+ jr t0
0:
bl start_secondary
SYM_CODE_END(smpboot_entry)
diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c
index e6ab879..dc2b82e 100644
--- a/arch/loongarch/kernel/ptrace.c
+++ b/arch/loongarch/kernel/ptrace.c
@@ -193,7 +193,7 @@ static int fpr_set(struct task_struct *target,
const void *kbuf, const void __user *ubuf)
{
const int fcc_start = NUM_FPU_REGS * sizeof(elf_fpreg_t);
- const int fcc_end = fcc_start + sizeof(u64);
+ const int fcsr_start = fcc_start + sizeof(u64);
int err;
BUG_ON(count % sizeof(elf_fpreg_t));
@@ -209,10 +209,12 @@ static int fpr_set(struct task_struct *target,
if (err)
return err;
- if (count > 0)
- err |= user_regset_copyin(&pos, &count, &kbuf, &ubuf,
- &target->thread.fpu.fcc,
- fcc_start, fcc_end);
+ err |= user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.fpu.fcc, fcc_start,
+ fcc_start + sizeof(u64));
+ err |= user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+ &target->thread.fpu.fcsr, fcsr_start,
+ fcsr_start + sizeof(u32));
return err;
}
diff --git a/arch/loongarch/kernel/reset.c b/arch/loongarch/kernel/reset.c
index 2b86469..800c965 100644
--- a/arch/loongarch/kernel/reset.c
+++ b/arch/loongarch/kernel/reset.c
@@ -13,7 +13,6 @@
#include <linux/console.h>
#include <acpi/reboot.h>
-#include <asm/compiler.h>
#include <asm/idle.h>
#include <asm/loongarch.h>
#include <asm/reboot.h>
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index c74860b..8f5c2f9 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -126,7 +126,7 @@ static void __init parse_bios_table(const struct dmi_header *dm)
char *dmi_data = (char *)dm;
bios_extern = *(dmi_data + SMBIOS_BIOSEXTERN_OFFSET);
- b_info.bios_size = *(dmi_data + SMBIOS_BIOSSIZE_OFFSET);
+ b_info.bios_size = (*(dmi_data + SMBIOS_BIOSSIZE_OFFSET) + 1) << 6;
if (bios_extern & LOONGSON_EFI_ENABLE)
set_bit(EFI_BOOT, &efi.flags);
diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
index 73cec625..0974310 100644
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@@ -278,116 +278,29 @@ void loongson3_cpu_die(unsigned int cpu)
mb();
}
-/*
- * The target CPU should go to XKPRANGE (uncached area) and flush
- * ICache/DCache/VCache before the control CPU can safely disable its clock.
- */
-static void loongson3_play_dead(int *state_addr)
+void play_dead(void)
{
- register int val;
- register void *addr;
+ register uint64_t addr;
register void (*init_fn)(void);
- __asm__ __volatile__(
- " li.d %[addr], 0x8000000000000000\n"
- "1: cacop 0x8, %[addr], 0 \n" /* flush ICache */
- " cacop 0x8, %[addr], 1 \n"
- " cacop 0x8, %[addr], 2 \n"
- " cacop 0x8, %[addr], 3 \n"
- " cacop 0x9, %[addr], 0 \n" /* flush DCache */
- " cacop 0x9, %[addr], 1 \n"
- " cacop 0x9, %[addr], 2 \n"
- " cacop 0x9, %[addr], 3 \n"
- " addi.w %[sets], %[sets], -1 \n"
- " addi.d %[addr], %[addr], 0x40 \n"
- " bnez %[sets], 1b \n"
- " li.d %[addr], 0x8000000000000000\n"
- "2: cacop 0xa, %[addr], 0 \n" /* flush VCache */
- " cacop 0xa, %[addr], 1 \n"
- " cacop 0xa, %[addr], 2 \n"
- " cacop 0xa, %[addr], 3 \n"
- " cacop 0xa, %[addr], 4 \n"
- " cacop 0xa, %[addr], 5 \n"
- " cacop 0xa, %[addr], 6 \n"
- " cacop 0xa, %[addr], 7 \n"
- " cacop 0xa, %[addr], 8 \n"
- " cacop 0xa, %[addr], 9 \n"
- " cacop 0xa, %[addr], 10 \n"
- " cacop 0xa, %[addr], 11 \n"
- " cacop 0xa, %[addr], 12 \n"
- " cacop 0xa, %[addr], 13 \n"
- " cacop 0xa, %[addr], 14 \n"
- " cacop 0xa, %[addr], 15 \n"
- " addi.w %[vsets], %[vsets], -1 \n"
- " addi.d %[addr], %[addr], 0x40 \n"
- " bnez %[vsets], 2b \n"
- " li.w %[val], 0x7 \n" /* *state_addr = CPU_DEAD; */
- " st.w %[val], %[state_addr], 0 \n"
- " dbar 0 \n"
- " cacop 0x11, %[state_addr], 0 \n" /* flush entry of *state_addr */
- : [addr] "=&r" (addr), [val] "=&r" (val)
- : [state_addr] "r" (state_addr),
- [sets] "r" (cpu_data[smp_processor_id()].dcache.sets),
- [vsets] "r" (cpu_data[smp_processor_id()].vcache.sets));
-
+ idle_task_exit();
local_irq_enable();
- change_csr_ecfg(ECFG0_IM, ECFGF_IPI);
+ set_csr_ecfg(ECFGF_IPI);
+ __this_cpu_write(cpu_state, CPU_DEAD);
- __asm__ __volatile__(
- " idle 0 \n"
- " li.w $t0, 0x1020 \n"
- " iocsrrd.d %[init_fn], $t0 \n" /* Get init PC */
- : [init_fn] "=&r" (addr)
- : /* No Input */
- : "a0");
- init_fn = __va(addr);
+ __smp_mb();
+ do {
+ __asm__ __volatile__("idle 0\n\t");
+ addr = iocsr_read64(LOONGARCH_IOCSR_MBUF0);
+ } while (addr == 0);
+
+ init_fn = (void *)TO_CACHE(addr);
+ iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_CLEAR);
init_fn();
unreachable();
}
-void play_dead(void)
-{
- int *state_addr;
- unsigned int cpu = smp_processor_id();
- void (*play_dead_uncached)(int *s);
-
- idle_task_exit();
- play_dead_uncached = (void *)TO_UNCACHE(__pa((unsigned long)loongson3_play_dead));
- state_addr = &per_cpu(cpu_state, cpu);
- mb();
- play_dead_uncached(state_addr);
-}
-
-static int loongson3_enable_clock(unsigned int cpu)
-{
- uint64_t core_id = cpu_data[cpu].core;
- uint64_t package_id = cpu_data[cpu].package;
-
- LOONGSON_FREQCTRL(package_id) |= 1 << (core_id * 4 + 3);
-
- return 0;
-}
-
-static int loongson3_disable_clock(unsigned int cpu)
-{
- uint64_t core_id = cpu_data[cpu].core;
- uint64_t package_id = cpu_data[cpu].package;
-
- LOONGSON_FREQCTRL(package_id) &= ~(1 << (core_id * 4 + 3));
-
- return 0;
-}
-
-static int register_loongson3_notifier(void)
-{
- return cpuhp_setup_state_nocalls(CPUHP_LOONGARCH_SOC_PREPARE,
- "loongarch/loongson:prepare",
- loongson3_enable_clock,
- loongson3_disable_clock);
-}
-early_initcall(register_loongson3_notifier);
-
#endif
/*
diff --git a/arch/loongarch/kernel/switch.S b/arch/loongarch/kernel/switch.S
index 53e2fa8..37e84ac 100644
--- a/arch/loongarch/kernel/switch.S
+++ b/arch/loongarch/kernel/switch.S
@@ -24,8 +24,8 @@
move tp, a2
cpu_restore_nonscratch a1
- li.w t0, _THREAD_SIZE - 32
- PTR_ADD t0, t0, tp
+ li.w t0, _THREAD_SIZE - 32
+ PTR_ADD t0, t0, tp
set_saved_sp t0, t1, t2
ldptr.d t1, a1, THREAD_CSRPRMD
diff --git a/arch/loongarch/lib/clear_user.S b/arch/loongarch/lib/clear_user.S
index 25d9be5..16ba2b8 100644
--- a/arch/loongarch/lib/clear_user.S
+++ b/arch/loongarch/lib/clear_user.S
@@ -32,7 +32,7 @@
1: st.b zero, a0, 0
addi.d a0, a0, 1
addi.d a1, a1, -1
- bgt a1, zero, 1b
+ bgtz a1, 1b
2: move a0, a1
jr ra
diff --git a/arch/loongarch/lib/copy_user.S b/arch/loongarch/lib/copy_user.S
index 9ae507f..97d2032 100644
--- a/arch/loongarch/lib/copy_user.S
+++ b/arch/loongarch/lib/copy_user.S
@@ -35,7 +35,7 @@
addi.d a0, a0, 1
addi.d a1, a1, 1
addi.d a2, a2, -1
- bgt a2, zero, 1b
+ bgtz a2, 1b
3: move a0, a2
jr ra
diff --git a/arch/loongarch/lib/delay.c b/arch/loongarch/lib/delay.c
index 5d85669..831d476 100644
--- a/arch/loongarch/lib/delay.c
+++ b/arch/loongarch/lib/delay.c
@@ -7,7 +7,6 @@
#include <linux/smp.h>
#include <linux/timex.h>
-#include <asm/compiler.h>
#include <asm/processor.h>
void __delay(unsigned long cycles)
diff --git a/arch/loongarch/mm/page.S b/arch/loongarch/mm/page.S
index ddc78ab..4c874a7a 100644
--- a/arch/loongarch/mm/page.S
+++ b/arch/loongarch/mm/page.S
@@ -10,75 +10,75 @@
.align 5
SYM_FUNC_START(clear_page)
- lu12i.w t0, 1 << (PAGE_SHIFT - 12)
- add.d t0, t0, a0
+ lu12i.w t0, 1 << (PAGE_SHIFT - 12)
+ add.d t0, t0, a0
1:
- st.d zero, a0, 0
- st.d zero, a0, 8
- st.d zero, a0, 16
- st.d zero, a0, 24
- st.d zero, a0, 32
- st.d zero, a0, 40
- st.d zero, a0, 48
- st.d zero, a0, 56
- addi.d a0, a0, 128
- st.d zero, a0, -64
- st.d zero, a0, -56
- st.d zero, a0, -48
- st.d zero, a0, -40
- st.d zero, a0, -32
- st.d zero, a0, -24
- st.d zero, a0, -16
- st.d zero, a0, -8
- bne t0, a0, 1b
+ st.d zero, a0, 0
+ st.d zero, a0, 8
+ st.d zero, a0, 16
+ st.d zero, a0, 24
+ st.d zero, a0, 32
+ st.d zero, a0, 40
+ st.d zero, a0, 48
+ st.d zero, a0, 56
+ addi.d a0, a0, 128
+ st.d zero, a0, -64
+ st.d zero, a0, -56
+ st.d zero, a0, -48
+ st.d zero, a0, -40
+ st.d zero, a0, -32
+ st.d zero, a0, -24
+ st.d zero, a0, -16
+ st.d zero, a0, -8
+ bne t0, a0, 1b
- jirl $r0, ra, 0
+ jr ra
SYM_FUNC_END(clear_page)
EXPORT_SYMBOL(clear_page)
.align 5
SYM_FUNC_START(copy_page)
- lu12i.w t8, 1 << (PAGE_SHIFT - 12)
- add.d t8, t8, a0
+ lu12i.w t8, 1 << (PAGE_SHIFT - 12)
+ add.d t8, t8, a0
1:
- ld.d t0, a1, 0
- ld.d t1, a1, 8
- ld.d t2, a1, 16
- ld.d t3, a1, 24
- ld.d t4, a1, 32
- ld.d t5, a1, 40
- ld.d t6, a1, 48
- ld.d t7, a1, 56
+ ld.d t0, a1, 0
+ ld.d t1, a1, 8
+ ld.d t2, a1, 16
+ ld.d t3, a1, 24
+ ld.d t4, a1, 32
+ ld.d t5, a1, 40
+ ld.d t6, a1, 48
+ ld.d t7, a1, 56
- st.d t0, a0, 0
- st.d t1, a0, 8
- ld.d t0, a1, 64
- ld.d t1, a1, 72
- st.d t2, a0, 16
- st.d t3, a0, 24
- ld.d t2, a1, 80
- ld.d t3, a1, 88
- st.d t4, a0, 32
- st.d t5, a0, 40
- ld.d t4, a1, 96
- ld.d t5, a1, 104
- st.d t6, a0, 48
- st.d t7, a0, 56
- ld.d t6, a1, 112
- ld.d t7, a1, 120
- addi.d a0, a0, 128
- addi.d a1, a1, 128
+ st.d t0, a0, 0
+ st.d t1, a0, 8
+ ld.d t0, a1, 64
+ ld.d t1, a1, 72
+ st.d t2, a0, 16
+ st.d t3, a0, 24
+ ld.d t2, a1, 80
+ ld.d t3, a1, 88
+ st.d t4, a0, 32
+ st.d t5, a0, 40
+ ld.d t4, a1, 96
+ ld.d t5, a1, 104
+ st.d t6, a0, 48
+ st.d t7, a0, 56
+ ld.d t6, a1, 112
+ ld.d t7, a1, 120
+ addi.d a0, a0, 128
+ addi.d a1, a1, 128
- st.d t0, a0, -64
- st.d t1, a0, -56
- st.d t2, a0, -48
- st.d t3, a0, -40
- st.d t4, a0, -32
- st.d t5, a0, -24
- st.d t6, a0, -16
- st.d t7, a0, -8
+ st.d t0, a0, -64
+ st.d t1, a0, -56
+ st.d t2, a0, -48
+ st.d t3, a0, -40
+ st.d t4, a0, -32
+ st.d t5, a0, -24
+ st.d t6, a0, -16
+ st.d t7, a0, -8
- bne t8, a0, 1b
- jirl $r0, ra, 0
+ bne t8, a0, 1b
+ jr ra
SYM_FUNC_END(copy_page)
EXPORT_SYMBOL(copy_page)
diff --git a/arch/loongarch/mm/tlbex.S b/arch/loongarch/mm/tlbex.S
index 7eee402..de19fa2 100644
--- a/arch/loongarch/mm/tlbex.S
+++ b/arch/loongarch/mm/tlbex.S
@@ -18,7 +18,7 @@
REG_S a2, sp, PT_BVADDR
li.w a1, \write
la.abs t0, do_page_fault
- jirl ra, t0, 0
+ jirl ra, t0, 0
RESTORE_ALL_AND_RET
SYM_FUNC_END(tlb_do_page_fault_\write)
.endm
@@ -34,7 +34,7 @@
csrrd a2, LOONGARCH_CSR_BADV
REG_S a2, sp, PT_BVADDR
la.abs t0, do_page_fault
- jirl ra, t0, 0
+ jirl ra, t0, 0
RESTORE_ALL_AND_RET
SYM_FUNC_END(handle_tlb_protect)
@@ -47,7 +47,7 @@
* The vmalloc handling is not in the hotpath.
*/
csrrd t0, LOONGARCH_CSR_BADV
- blt t0, $r0, vmalloc_load
+ bltz t0, vmalloc_load
csrrd t1, LOONGARCH_CSR_PGDL
vmalloc_done_load:
@@ -80,7 +80,7 @@
* see if we need to jump to huge tlb processing.
*/
andi t0, ra, _PAGE_HUGE
- bne t0, $r0, tlb_huge_update_load
+ bnez t0, tlb_huge_update_load
csrrd t0, LOONGARCH_CSR_BADV
srli.d t0, t0, (PAGE_SHIFT + PTE_ORDER)
@@ -100,12 +100,12 @@
srli.d ra, t0, _PAGE_PRESENT_SHIFT
andi ra, ra, 1
- beq ra, $r0, nopage_tlb_load
+ beqz ra, nopage_tlb_load
ori t0, t0, _PAGE_VALID
#ifdef CONFIG_SMP
sc.d t0, t1, 0
- beq t0, $r0, smp_pgtable_change_load
+ beqz t0, smp_pgtable_change_load
#else
st.d t0, t1, 0
#endif
@@ -139,23 +139,23 @@
#endif
srli.d ra, t0, _PAGE_PRESENT_SHIFT
andi ra, ra, 1
- beq ra, $r0, nopage_tlb_load
+ beqz ra, nopage_tlb_load
tlbsrch
ori t0, t0, _PAGE_VALID
#ifdef CONFIG_SMP
sc.d t0, t1, 0
- beq t0, $r0, tlb_huge_update_load
+ beqz t0, tlb_huge_update_load
ld.d t0, t1, 0
#else
st.d t0, t1, 0
#endif
- addu16i.d t1, $r0, -(CSR_TLBIDX_EHINV >> 16)
- addi.d ra, t1, 0
- csrxchg ra, t1, LOONGARCH_CSR_TLBIDX
+ addu16i.d t1, zero, -(CSR_TLBIDX_EHINV >> 16)
+ addi.d ra, t1, 0
+ csrxchg ra, t1, LOONGARCH_CSR_TLBIDX
tlbwr
- csrxchg $r0, t1, LOONGARCH_CSR_TLBIDX
+ csrxchg zero, t1, LOONGARCH_CSR_TLBIDX
/*
* A huge PTE describes an area the size of the
@@ -178,27 +178,27 @@
addi.d t0, ra, 0
/* Convert to entrylo1 */
- addi.d t1, $r0, 1
+ addi.d t1, zero, 1
slli.d t1, t1, (HPAGE_SHIFT - 1)
add.d t0, t0, t1
csrwr t0, LOONGARCH_CSR_TLBELO1
/* Set huge page tlb entry size */
- addu16i.d t0, $r0, (CSR_TLBIDX_PS >> 16)
- addu16i.d t1, $r0, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
+ addu16i.d t0, zero, (CSR_TLBIDX_PS >> 16)
+ addu16i.d t1, zero, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
csrxchg t1, t0, LOONGARCH_CSR_TLBIDX
tlbfill
- addu16i.d t0, $r0, (CSR_TLBIDX_PS >> 16)
- addu16i.d t1, $r0, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
+ addu16i.d t0, zero, (CSR_TLBIDX_PS >> 16)
+ addu16i.d t1, zero, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
csrxchg t1, t0, LOONGARCH_CSR_TLBIDX
nopage_tlb_load:
dbar 0
csrrd ra, EXCEPTION_KS2
la.abs t0, tlb_do_page_fault_0
- jirl $r0, t0, 0
+ jr t0
SYM_FUNC_END(handle_tlb_load)
SYM_FUNC_START(handle_tlb_store)
@@ -210,7 +210,7 @@
* The vmalloc handling is not in the hotpath.
*/
csrrd t0, LOONGARCH_CSR_BADV
- blt t0, $r0, vmalloc_store
+ bltz t0, vmalloc_store
csrrd t1, LOONGARCH_CSR_PGDL
vmalloc_done_store:
@@ -244,7 +244,7 @@
* see if we need to jump to huge tlb processing.
*/
andi t0, ra, _PAGE_HUGE
- bne t0, $r0, tlb_huge_update_store
+ bnez t0, tlb_huge_update_store
csrrd t0, LOONGARCH_CSR_BADV
srli.d t0, t0, (PAGE_SHIFT + PTE_ORDER)
@@ -265,12 +265,12 @@
srli.d ra, t0, _PAGE_PRESENT_SHIFT
andi ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT)
xori ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT)
- bne ra, $r0, nopage_tlb_store
+ bnez ra, nopage_tlb_store
ori t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
#ifdef CONFIG_SMP
sc.d t0, t1, 0
- beq t0, $r0, smp_pgtable_change_store
+ beqz t0, smp_pgtable_change_store
#else
st.d t0, t1, 0
#endif
@@ -306,24 +306,24 @@
srli.d ra, t0, _PAGE_PRESENT_SHIFT
andi ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT)
xori ra, ra, ((_PAGE_PRESENT | _PAGE_WRITE) >> _PAGE_PRESENT_SHIFT)
- bne ra, $r0, nopage_tlb_store
+ bnez ra, nopage_tlb_store
tlbsrch
ori t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
#ifdef CONFIG_SMP
sc.d t0, t1, 0
- beq t0, $r0, tlb_huge_update_store
+ beqz t0, tlb_huge_update_store
ld.d t0, t1, 0
#else
st.d t0, t1, 0
#endif
- addu16i.d t1, $r0, -(CSR_TLBIDX_EHINV >> 16)
- addi.d ra, t1, 0
- csrxchg ra, t1, LOONGARCH_CSR_TLBIDX
+ addu16i.d t1, zero, -(CSR_TLBIDX_EHINV >> 16)
+ addi.d ra, t1, 0
+ csrxchg ra, t1, LOONGARCH_CSR_TLBIDX
tlbwr
- csrxchg $r0, t1, LOONGARCH_CSR_TLBIDX
+ csrxchg zero, t1, LOONGARCH_CSR_TLBIDX
/*
* A huge PTE describes an area the size of the
* configured huge page size. This is twice the
@@ -345,28 +345,28 @@
addi.d t0, ra, 0
/* Convert to entrylo1 */
- addi.d t1, $r0, 1
+ addi.d t1, zero, 1
slli.d t1, t1, (HPAGE_SHIFT - 1)
add.d t0, t0, t1
csrwr t0, LOONGARCH_CSR_TLBELO1
/* Set huge page tlb entry size */
- addu16i.d t0, $r0, (CSR_TLBIDX_PS >> 16)
- addu16i.d t1, $r0, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
+ addu16i.d t0, zero, (CSR_TLBIDX_PS >> 16)
+ addu16i.d t1, zero, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
csrxchg t1, t0, LOONGARCH_CSR_TLBIDX
tlbfill
/* Reset default page size */
- addu16i.d t0, $r0, (CSR_TLBIDX_PS >> 16)
- addu16i.d t1, $r0, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
+ addu16i.d t0, zero, (CSR_TLBIDX_PS >> 16)
+ addu16i.d t1, zero, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
csrxchg t1, t0, LOONGARCH_CSR_TLBIDX
nopage_tlb_store:
dbar 0
csrrd ra, EXCEPTION_KS2
la.abs t0, tlb_do_page_fault_1
- jirl $r0, t0, 0
+ jr t0
SYM_FUNC_END(handle_tlb_store)
SYM_FUNC_START(handle_tlb_modify)
@@ -378,7 +378,7 @@
* The vmalloc handling is not in the hotpath.
*/
csrrd t0, LOONGARCH_CSR_BADV
- blt t0, $r0, vmalloc_modify
+ bltz t0, vmalloc_modify
csrrd t1, LOONGARCH_CSR_PGDL
vmalloc_done_modify:
@@ -411,7 +411,7 @@
* see if we need to jump to huge tlb processing.
*/
andi t0, ra, _PAGE_HUGE
- bne t0, $r0, tlb_huge_update_modify
+ bnez t0, tlb_huge_update_modify
csrrd t0, LOONGARCH_CSR_BADV
srli.d t0, t0, (PAGE_SHIFT + PTE_ORDER)
@@ -431,12 +431,12 @@
srli.d ra, t0, _PAGE_WRITE_SHIFT
andi ra, ra, 1
- beq ra, $r0, nopage_tlb_modify
+ beqz ra, nopage_tlb_modify
ori t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
#ifdef CONFIG_SMP
sc.d t0, t1, 0
- beq t0, $r0, smp_pgtable_change_modify
+ beqz t0, smp_pgtable_change_modify
#else
st.d t0, t1, 0
#endif
@@ -454,7 +454,7 @@
ertn
#ifdef CONFIG_64BIT
vmalloc_modify:
- la.abs t1, swapper_pg_dir
+ la.abs t1, swapper_pg_dir
b vmalloc_done_modify
#endif
@@ -471,14 +471,14 @@
srli.d ra, t0, _PAGE_WRITE_SHIFT
andi ra, ra, 1
- beq ra, $r0, nopage_tlb_modify
+ beqz ra, nopage_tlb_modify
tlbsrch
ori t0, t0, (_PAGE_VALID | _PAGE_DIRTY | _PAGE_MODIFIED)
#ifdef CONFIG_SMP
sc.d t0, t1, 0
- beq t0, $r0, tlb_huge_update_modify
+ beqz t0, tlb_huge_update_modify
ld.d t0, t1, 0
#else
st.d t0, t1, 0
@@ -504,28 +504,28 @@
addi.d t0, ra, 0
/* Convert to entrylo1 */
- addi.d t1, $r0, 1
+ addi.d t1, zero, 1
slli.d t1, t1, (HPAGE_SHIFT - 1)
add.d t0, t0, t1
csrwr t0, LOONGARCH_CSR_TLBELO1
/* Set huge page tlb entry size */
- addu16i.d t0, $r0, (CSR_TLBIDX_PS >> 16)
- addu16i.d t1, $r0, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
- csrxchg t1, t0, LOONGARCH_CSR_TLBIDX
+ addu16i.d t0, zero, (CSR_TLBIDX_PS >> 16)
+ addu16i.d t1, zero, (PS_HUGE_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
+ csrxchg t1, t0, LOONGARCH_CSR_TLBIDX
tlbwr
/* Reset default page size */
- addu16i.d t0, $r0, (CSR_TLBIDX_PS >> 16)
- addu16i.d t1, $r0, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
- csrxchg t1, t0, LOONGARCH_CSR_TLBIDX
+ addu16i.d t0, zero, (CSR_TLBIDX_PS >> 16)
+ addu16i.d t1, zero, (PS_DEFAULT_SIZE << (CSR_TLBIDX_PS_SHIFT - 16))
+ csrxchg t1, t0, LOONGARCH_CSR_TLBIDX
nopage_tlb_modify:
dbar 0
csrrd ra, EXCEPTION_KS2
la.abs t0, tlb_do_page_fault_1
- jirl $r0, t0, 0
+ jr t0
SYM_FUNC_END(handle_tlb_modify)
SYM_FUNC_START(handle_tlb_refill)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index c235648..4d8f26c 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -282,6 +282,10 @@
# Please keep this list sorted alphabetically.
#
+config PPC_LONG_DOUBLE_128
+ depends on PPC64
+ def_bool $(success,test "$(shell,echo __LONG_DOUBLE_128__ | $(CC) -E -P -)" = 1)
+
config PPC_BARRIER_NOSPEC
bool
default y
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index f91f0f29..c8cf924 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -20,6 +20,7 @@
CFLAGS_prom_init.o += -fno-stack-protector
CFLAGS_prom_init.o += -DDISABLE_BRANCH_PROFILING
CFLAGS_prom_init.o += -ffreestanding
+CFLAGS_prom_init.o += $(call cc-option, -ftrivial-auto-var-init=uninitialized)
ifdef CONFIG_FUNCTION_TRACER
# Do not trace early boot code
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index a4c46a0..81029d4 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -111,7 +111,7 @@
vdso_install:
$(Q)$(MAKE) $(build)=arch/riscv/kernel/vdso $@
$(if $(CONFIG_COMPAT),$(Q)$(MAKE) \
- $(build)=arch/riscv/kernel/compat_vdso $@)
+ $(build)=arch/riscv/kernel/compat_vdso compat_$@)
ifeq ($(KBUILD_EXTMOD),)
ifeq ($(CONFIG_MMU),y)
diff --git a/arch/s390/include/asm/archrandom.h b/arch/s390/include/asm/archrandom.h
index 2c6e1c6..4120c42 100644
--- a/arch/s390/include/asm/archrandom.h
+++ b/arch/s390/include/asm/archrandom.h
@@ -2,7 +2,7 @@
/*
* Kernel interface for the s390 arch_random_* functions
*
- * Copyright IBM Corp. 2017, 2020
+ * Copyright IBM Corp. 2017, 2022
*
* Author: Harald Freudenberger <freude@de.ibm.com>
*
@@ -14,6 +14,7 @@
#ifdef CONFIG_ARCH_RANDOM
#include <linux/static_key.h>
+#include <linux/preempt.h>
#include <linux/atomic.h>
#include <asm/cpacf.h>
@@ -32,7 +33,8 @@ static inline bool __must_check arch_get_random_int(unsigned int *v)
static inline bool __must_check arch_get_random_seed_long(unsigned long *v)
{
- if (static_branch_likely(&s390_arch_random_available)) {
+ if (static_branch_likely(&s390_arch_random_available) &&
+ in_task()) {
cpacf_trng(NULL, 0, (u8 *)v, sizeof(*v));
atomic64_add(sizeof(*v), &s390_arch_random_counter);
return true;
@@ -42,7 +44,8 @@ static inline bool __must_check arch_get_random_seed_long(unsigned long *v)
static inline bool __must_check arch_get_random_seed_int(unsigned int *v)
{
- if (static_branch_likely(&s390_arch_random_available)) {
+ if (static_branch_likely(&s390_arch_random_available) &&
+ in_task()) {
cpacf_trng(NULL, 0, (u8 *)v, sizeof(*v));
atomic64_add(sizeof(*v), &s390_arch_random_counter);
return true;
diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index 59b0bed..c8fa7dc 100644
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -103,9 +103,14 @@ static void dimm_setup_label(struct dimm_info *dimm, u16 handle)
dmi_memdev_name(handle, &bank, &device);
- /* both strings must be non-zero */
- if (bank && *bank && device && *device)
- snprintf(dimm->label, sizeof(dimm->label), "%s %s", bank, device);
+ /*
+ * Set to a NULL string when both bank and device are zero. In this case,
+ * the label assigned by default will be preserved.
+ */
+ snprintf(dimm->label, sizeof(dimm->label), "%s%s%s",
+ (bank && *bank) ? bank : "",
+ (bank && *bank && device && *device) ? " " : "",
+ (device && *device) ? device : "");
}
static void assign_dmi_dimm_info(struct dimm_info *dimm, struct memdev_dmi_entry *entry)
diff --git a/drivers/edac/synopsys_edac.c b/drivers/edac/synopsys_edac.c
index 1cee64b..f7d37c2 100644
--- a/drivers/edac/synopsys_edac.c
+++ b/drivers/edac/synopsys_edac.c
@@ -514,6 +514,28 @@ static void handle_error(struct mem_ctl_info *mci, struct synps_ecc_status *p)
memset(p, 0, sizeof(*p));
}
+static void enable_intr(struct synps_edac_priv *priv)
+{
+ /* Enable UE/CE Interrupts */
+ if (priv->p_data->quirks & DDR_ECC_INTR_SELF_CLEAR)
+ writel(DDR_UE_MASK | DDR_CE_MASK,
+ priv->baseaddr + ECC_CLR_OFST);
+ else
+ writel(DDR_QOSUE_MASK | DDR_QOSCE_MASK,
+ priv->baseaddr + DDR_QOS_IRQ_EN_OFST);
+
+}
+
+static void disable_intr(struct synps_edac_priv *priv)
+{
+ /* Disable UE/CE Interrupts */
+ if (priv->p_data->quirks & DDR_ECC_INTR_SELF_CLEAR)
+ writel(0x0, priv->baseaddr + ECC_CLR_OFST);
+ else
+ writel(DDR_QOSUE_MASK | DDR_QOSCE_MASK,
+ priv->baseaddr + DDR_QOS_IRQ_DB_OFST);
+}
+
/**
* intr_handler - Interrupt Handler for ECC interrupts.
* @irq: IRQ number.
@@ -555,6 +577,9 @@ static irqreturn_t intr_handler(int irq, void *dev_id)
/* v3.0 of the controller does not have this register */
if (!(priv->p_data->quirks & DDR_ECC_INTR_SELF_CLEAR))
writel(regval, priv->baseaddr + DDR_QOS_IRQ_STAT_OFST);
+ else
+ enable_intr(priv);
+
return IRQ_HANDLED;
}
@@ -837,25 +862,6 @@ static void mc_init(struct mem_ctl_info *mci, struct platform_device *pdev)
init_csrows(mci);
}
-static void enable_intr(struct synps_edac_priv *priv)
-{
- /* Enable UE/CE Interrupts */
- if (priv->p_data->quirks & DDR_ECC_INTR_SELF_CLEAR)
- writel(DDR_UE_MASK | DDR_CE_MASK,
- priv->baseaddr + ECC_CLR_OFST);
- else
- writel(DDR_QOSUE_MASK | DDR_QOSCE_MASK,
- priv->baseaddr + DDR_QOS_IRQ_EN_OFST);
-
-}
-
-static void disable_intr(struct synps_edac_priv *priv)
-{
- /* Disable UE/CE Interrupts */
- writel(DDR_QOSUE_MASK | DDR_QOSCE_MASK,
- priv->baseaddr + DDR_QOS_IRQ_DB_OFST);
-}
-
static int setup_irq(struct mem_ctl_info *mci,
struct platform_device *pdev)
{
diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig
index 0ba0598..ec6771e 100644
--- a/drivers/gpu/drm/amd/display/Kconfig
+++ b/drivers/gpu/drm/amd/display/Kconfig
@@ -6,7 +6,7 @@
bool "AMD DC - Enable new display engine"
default y
select SND_HDA_COMPONENT if SND_HDA_CORE
- select DRM_AMD_DC_DCN if X86 && !(KCOV_INSTRUMENT_ALL && KCOV_ENABLE_COMPARISONS)
+ select DRM_AMD_DC_DCN if (X86 || PPC_LONG_DOUBLE_128) && !(KCOV_INSTRUMENT_ALL && KCOV_ENABLE_COMPARISONS)
help
Choose this option if you want to use the new display engine
support for AMDGPU. This adds required support for Vega and
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index 1431f1e..04e435b 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -201,6 +201,8 @@ int intel_ring_submission_setup(struct intel_engine_cs *engine);
int intel_engine_stop_cs(struct intel_engine_cs *engine);
void intel_engine_cancel_stop_cs(struct intel_engine_cs *engine);
+void intel_engine_wait_for_pending_mi_fw(struct intel_engine_cs *engine);
+
void intel_engine_set_hwsp_writemask(struct intel_engine_cs *engine, u32 mask);
u64 intel_engine_get_active_head(const struct intel_engine_cs *engine);
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 14c6ddb..5b6ce10 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1282,10 +1282,10 @@ static int __intel_engine_stop_cs(struct intel_engine_cs *engine,
intel_uncore_write_fw(uncore, mode, _MASKED_BIT_ENABLE(STOP_RING));
/*
- * Wa_22011802037 : gen12, Prior to doing a reset, ensure CS is
+ * Wa_22011802037 : gen11, gen12, Prior to doing a reset, ensure CS is
* stopped, set ring stop bit and prefetch disable bit to halt CS
*/
- if (GRAPHICS_VER(engine->i915) == 12)
+ if (IS_GRAPHICS_VER(engine->i915, 11, 12))
intel_uncore_write_fw(uncore, RING_MODE_GEN7(engine->mmio_base),
_MASKED_BIT_ENABLE(GEN12_GFX_PREFETCH_DISABLE));
@@ -1308,6 +1308,18 @@ int intel_engine_stop_cs(struct intel_engine_cs *engine)
return -ENODEV;
ENGINE_TRACE(engine, "\n");
+ /*
+ * TODO: Find out why occasionally stopping the CS times out. Seen
+ * especially with gem_eio tests.
+ *
+ * Occasionally trying to stop the cs times out, but does not adversely
+ * affect functionality. The timeout is set as a config parameter that
+ * defaults to 100ms. In most cases the follow up operation is to wait
+ * for pending MI_FORCE_WAKES. The assumption is that this timeout is
+ * sufficient for any pending MI_FORCEWAKEs to complete. Once root
+ * caused, the caller must check and handle the return from this
+ * function.
+ */
if (__intel_engine_stop_cs(engine, 1000, stop_timeout(engine))) {
ENGINE_TRACE(engine,
"timed out on STOP_RING -> IDLE; HEAD:%04x, TAIL:%04x\n",
@@ -1334,6 +1346,78 @@ void intel_engine_cancel_stop_cs(struct intel_engine_cs *engine)
ENGINE_WRITE_FW(engine, RING_MI_MODE, _MASKED_BIT_DISABLE(STOP_RING));
}
+static u32 __cs_pending_mi_force_wakes(struct intel_engine_cs *engine)
+{
+ static const i915_reg_t _reg[I915_NUM_ENGINES] = {
+ [RCS0] = MSG_IDLE_CS,
+ [BCS0] = MSG_IDLE_BCS,
+ [VCS0] = MSG_IDLE_VCS0,
+ [VCS1] = MSG_IDLE_VCS1,
+ [VCS2] = MSG_IDLE_VCS2,
+ [VCS3] = MSG_IDLE_VCS3,
+ [VCS4] = MSG_IDLE_VCS4,
+ [VCS5] = MSG_IDLE_VCS5,
+ [VCS6] = MSG_IDLE_VCS6,
+ [VCS7] = MSG_IDLE_VCS7,
+ [VECS0] = MSG_IDLE_VECS0,
+ [VECS1] = MSG_IDLE_VECS1,
+ [VECS2] = MSG_IDLE_VECS2,
+ [VECS3] = MSG_IDLE_VECS3,
+ [CCS0] = MSG_IDLE_CS,
+ [CCS1] = MSG_IDLE_CS,
+ [CCS2] = MSG_IDLE_CS,
+ [CCS3] = MSG_IDLE_CS,
+ };
+ u32 val;
+
+ if (!_reg[engine->id].reg) {
+ drm_err(&engine->i915->drm,
+ "MSG IDLE undefined for engine id %u\n", engine->id);
+ return 0;
+ }
+
+ val = intel_uncore_read(engine->uncore, _reg[engine->id]);
+
+ /* bits[29:25] & bits[13:9] >> shift */
+ return (val & (val >> 16) & MSG_IDLE_FW_MASK) >> MSG_IDLE_FW_SHIFT;
+}
+
+static void __gpm_wait_for_fw_complete(struct intel_gt *gt, u32 fw_mask)
+{
+ int ret;
+
+ /* Ensure GPM receives fw up/down after CS is stopped */
+ udelay(1);
+
+ /* Wait for forcewake request to complete in GPM */
+ ret = __intel_wait_for_register_fw(gt->uncore,
+ GEN9_PWRGT_DOMAIN_STATUS,
+ fw_mask, fw_mask, 5000, 0, NULL);
+
+ /* Ensure CS receives fw ack from GPM */
+ udelay(1);
+
+ if (ret)
+ GT_TRACE(gt, "Failed to complete pending forcewake %d\n", ret);
+}
+
+/*
+ * Wa_22011802037:gen12: In addition to stopping the cs, we need to wait for any
+ * pending MI_FORCE_WAKEUP requests that the CS has initiated to complete. The
+ * pending status is indicated by bits[13:9] (masked by bits[29:25]) in the
+ * MSG_IDLE register. There's one MSG_IDLE register per reset domain. Since we
+ * are concerned only with the gt reset here, we use a logical OR of pending
+ * forcewakeups from all reset domains and then wait for them to complete by
+ * querying PWRGT_DOMAIN_STATUS.
+ */
+void intel_engine_wait_for_pending_mi_fw(struct intel_engine_cs *engine)
+{
+ u32 fw_pending = __cs_pending_mi_force_wakes(engine);
+
+ if (fw_pending)
+ __gpm_wait_for_fw_complete(engine->gt, fw_pending);
+}
+
static u32
read_subslice_reg(const struct intel_engine_cs *engine,
int slice, int subslice, i915_reg_t reg)
diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
index 2b0266c..0627fa10 100644
--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
@@ -2968,6 +2968,13 @@ static void execlists_reset_prepare(struct intel_engine_cs *engine)
ring_set_paused(engine, 1);
intel_engine_stop_cs(engine);
+ /*
+ * Wa_22011802037:gen11/gen12: In addition to stopping the cs, we need
+ * to wait for any pending mi force wakeups
+ */
+ if (IS_GRAPHICS_VER(engine->i915, 11, 12))
+ intel_engine_wait_for_pending_mi_fw(engine);
+
engine->execlists.reset_ccid = active_ccid(engine);
}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
index 2c4ad4a..8c6885f 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
@@ -310,8 +310,8 @@ static u32 guc_ctl_wa_flags(struct intel_guc *guc)
if (IS_DG2(gt->i915))
flags |= GUC_WA_DUAL_QUEUE;
- /* Wa_22011802037: graphics version 12 */
- if (GRAPHICS_VER(gt->i915) == 12)
+ /* Wa_22011802037: graphics version 11/12 */
+ if (IS_GRAPHICS_VER(gt->i915, 11, 12))
flags |= GUC_WA_PRE_PARSER;
/* Wa_16011777198:dg2 */
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 9ffb343..2d9f5f1 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -1578,87 +1578,18 @@ static void guc_reset_state(struct intel_context *ce, u32 head, bool scrub)
lrc_update_regs(ce, engine, head);
}
-static u32 __cs_pending_mi_force_wakes(struct intel_engine_cs *engine)
-{
- static const i915_reg_t _reg[I915_NUM_ENGINES] = {
- [RCS0] = MSG_IDLE_CS,
- [BCS0] = MSG_IDLE_BCS,
- [VCS0] = MSG_IDLE_VCS0,
- [VCS1] = MSG_IDLE_VCS1,
- [VCS2] = MSG_IDLE_VCS2,
- [VCS3] = MSG_IDLE_VCS3,
- [VCS4] = MSG_IDLE_VCS4,
- [VCS5] = MSG_IDLE_VCS5,
- [VCS6] = MSG_IDLE_VCS6,
- [VCS7] = MSG_IDLE_VCS7,
- [VECS0] = MSG_IDLE_VECS0,
- [VECS1] = MSG_IDLE_VECS1,
- [VECS2] = MSG_IDLE_VECS2,
- [VECS3] = MSG_IDLE_VECS3,
- [CCS0] = MSG_IDLE_CS,
- [CCS1] = MSG_IDLE_CS,
- [CCS2] = MSG_IDLE_CS,
- [CCS3] = MSG_IDLE_CS,
- };
- u32 val;
-
- if (!_reg[engine->id].reg)
- return 0;
-
- val = intel_uncore_read(engine->uncore, _reg[engine->id]);
-
- /* bits[29:25] & bits[13:9] >> shift */
- return (val & (val >> 16) & MSG_IDLE_FW_MASK) >> MSG_IDLE_FW_SHIFT;
-}
-
-static void __gpm_wait_for_fw_complete(struct intel_gt *gt, u32 fw_mask)
-{
- int ret;
-
- /* Ensure GPM receives fw up/down after CS is stopped */
- udelay(1);
-
- /* Wait for forcewake request to complete in GPM */
- ret = __intel_wait_for_register_fw(gt->uncore,
- GEN9_PWRGT_DOMAIN_STATUS,
- fw_mask, fw_mask, 5000, 0, NULL);
-
- /* Ensure CS receives fw ack from GPM */
- udelay(1);
-
- if (ret)
- GT_TRACE(gt, "Failed to complete pending forcewake %d\n", ret);
-}
-
-/*
- * Wa_22011802037:gen12: In addition to stopping the cs, we need to wait for any
- * pending MI_FORCE_WAKEUP requests that the CS has initiated to complete. The
- * pending status is indicated by bits[13:9] (masked by bits[ 29:25]) in the
- * MSG_IDLE register. There's one MSG_IDLE register per reset domain. Since we
- * are concerned only with the gt reset here, we use a logical OR of pending
- * forcewakeups from all reset domains and then wait for them to complete by
- * querying PWRGT_DOMAIN_STATUS.
- */
static void guc_engine_reset_prepare(struct intel_engine_cs *engine)
{
- u32 fw_pending;
-
- if (GRAPHICS_VER(engine->i915) != 12)
+ if (!IS_GRAPHICS_VER(engine->i915, 11, 12))
return;
- /*
- * Wa_22011802037
- * TODO: Occasionally trying to stop the cs times out, but does not
- * adversely affect functionality. The timeout is set as a config
- * parameter that defaults to 100ms. Assuming that this timeout is
- * sufficient for any pending MI_FORCEWAKEs to complete, ignore the
- * timeout returned here until it is root caused.
- */
intel_engine_stop_cs(engine);
- fw_pending = __cs_pending_mi_force_wakes(engine);
- if (fw_pending)
- __gpm_wait_for_fw_complete(engine->gt, fw_pending);
+ /*
+ * Wa_22011802037:gen11/gen12: In addition to stopping the cs, we need
+ * to wait for any pending mi force wakeups
+ */
+ intel_engine_wait_for_pending_mi_fw(engine);
}
static void guc_reset_nop(struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
index 7ba66ad..1635661 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
@@ -680,7 +680,11 @@ nouveau_dmem_migrate_vma(struct nouveau_drm *drm,
goto out_free_dma;
for (i = 0; i < npages; i += max) {
- args.end = start + (max << PAGE_SHIFT);
+ if (args.start + (max << PAGE_SHIFT) > end)
+ args.end = end;
+ else
+ args.end = args.start + (max << PAGE_SHIFT);
+
ret = migrate_vma_setup(&args);
if (ret)
goto out_free_pfns;
diff --git a/drivers/gpu/drm/tiny/simpledrm.c b/drivers/gpu/drm/tiny/simpledrm.c
index 768242a..5422363 100644
--- a/drivers/gpu/drm/tiny/simpledrm.c
+++ b/drivers/gpu/drm/tiny/simpledrm.c
@@ -627,7 +627,7 @@ static const struct drm_connector_funcs simpledrm_connector_funcs = {
.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
};
-static int
+static enum drm_mode_status
simpledrm_simple_display_pipe_mode_valid(struct drm_simple_display_pipe *pipe,
const struct drm_display_mode *mode)
{
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index f5c6802..907700d 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -162,7 +162,13 @@ static __cpuidle int intel_idle_irq(struct cpuidle_device *dev,
raw_local_irq_enable();
ret = __intel_idle(dev, drv, index);
- raw_local_irq_disable();
+
+ /*
+ * The lockdep hardirqs state may be changed to 'on' with timer
+ * tick interrupt followed by __do_softirq(). Use local_irq_disable()
+ * to keep the hardirqs state correct.
+ */
+ local_irq_disable();
return ret;
}
diff --git a/drivers/net/ethernet/fungible/funeth/funeth_rx.c b/drivers/net/ethernet/fungible/funeth/funeth_rx.c
index 0f6a549..29a6c2e 100644
--- a/drivers/net/ethernet/fungible/funeth/funeth_rx.c
+++ b/drivers/net/ethernet/fungible/funeth/funeth_rx.c
@@ -142,6 +142,7 @@ static void *fun_run_xdp(struct funeth_rxq *q, skb_frag_t *frags, void *buf_va,
int ref_ok, struct funeth_txq *xdp_q)
{
struct bpf_prog *xdp_prog;
+ struct xdp_frame *xdpf;
struct xdp_buff xdp;
u32 act;
@@ -163,7 +164,9 @@ static void *fun_run_xdp(struct funeth_rxq *q, skb_frag_t *frags, void *buf_va,
case XDP_TX:
if (unlikely(!ref_ok))
goto pass;
- if (!fun_xdp_tx(xdp_q, xdp.data, xdp.data_end - xdp.data))
+
+ xdpf = xdp_convert_buff_to_frame(&xdp);
+ if (!xdpf || !fun_xdp_tx(xdp_q, xdpf))
goto xdp_error;
FUN_QSTAT_INC(q, xdp_tx);
q->xdp_flush |= FUN_XDP_FLUSH_TX;
diff --git a/drivers/net/ethernet/fungible/funeth/funeth_tx.c b/drivers/net/ethernet/fungible/funeth/funeth_tx.c
index ff6e292..2f6698b 100644
--- a/drivers/net/ethernet/fungible/funeth/funeth_tx.c
+++ b/drivers/net/ethernet/fungible/funeth/funeth_tx.c
@@ -466,7 +466,7 @@ static unsigned int fun_xdpq_clean(struct funeth_txq *q, unsigned int budget)
do {
fun_xdp_unmap(q, reclaim_idx);
- page_frag_free(q->info[reclaim_idx].vaddr);
+ xdp_return_frame(q->info[reclaim_idx].xdpf);
trace_funeth_tx_free(q, reclaim_idx, 1, head);
@@ -479,11 +479,11 @@ static unsigned int fun_xdpq_clean(struct funeth_txq *q, unsigned int budget)
return npkts;
}
-bool fun_xdp_tx(struct funeth_txq *q, void *data, unsigned int len)
+bool fun_xdp_tx(struct funeth_txq *q, struct xdp_frame *xdpf)
{
struct fun_eth_tx_req *req;
struct fun_dataop_gl *gle;
- unsigned int idx;
+ unsigned int idx, len;
dma_addr_t dma;
if (fun_txq_avail(q) < FUN_XDP_CLEAN_THRES)
@@ -494,7 +494,8 @@ bool fun_xdp_tx(struct funeth_txq *q, void *data, unsigned int len)
return false;
}
- dma = dma_map_single(q->dma_dev, data, len, DMA_TO_DEVICE);
+ len = xdpf->len;
+ dma = dma_map_single(q->dma_dev, xdpf->data, len, DMA_TO_DEVICE);
if (unlikely(dma_mapping_error(q->dma_dev, dma))) {
FUN_QSTAT_INC(q, tx_map_err);
return false;
@@ -514,7 +515,7 @@ bool fun_xdp_tx(struct funeth_txq *q, void *data, unsigned int len)
gle = (struct fun_dataop_gl *)req->dataop.imm;
fun_dataop_gl_init(gle, 0, 0, len, dma);
- q->info[idx].vaddr = data;
+ q->info[idx].xdpf = xdpf;
u64_stats_update_begin(&q->syncp);
q->stats.tx_bytes += len;
@@ -545,12 +546,9 @@ int fun_xdp_xmit_frames(struct net_device *dev, int n,
if (unlikely(q_idx >= fp->num_xdpqs))
return -ENXIO;
- for (q = xdpqs[q_idx], i = 0; i < n; i++) {
- const struct xdp_frame *xdpf = frames[i];
-
- if (!fun_xdp_tx(q, xdpf->data, xdpf->len))
+ for (q = xdpqs[q_idx], i = 0; i < n; i++)
+ if (!fun_xdp_tx(q, frames[i]))
break;
- }
if (unlikely(flags & XDP_XMIT_FLUSH))
fun_txq_wr_db(q);
@@ -577,7 +575,7 @@ static void fun_xdpq_purge(struct funeth_txq *q)
unsigned int idx = q->cons_cnt & q->mask;
fun_xdp_unmap(q, idx);
- page_frag_free(q->info[idx].vaddr);
+ xdp_return_frame(q->info[idx].xdpf);
q->cons_cnt++;
}
}
diff --git a/drivers/net/ethernet/fungible/funeth/funeth_txrx.h b/drivers/net/ethernet/fungible/funeth/funeth_txrx.h
index 04c9f91..8708e28 100644
--- a/drivers/net/ethernet/fungible/funeth/funeth_txrx.h
+++ b/drivers/net/ethernet/fungible/funeth/funeth_txrx.h
@@ -95,8 +95,8 @@ struct funeth_txq_stats { /* per Tx queue SW counters */
struct funeth_tx_info { /* per Tx descriptor state */
union {
- struct sk_buff *skb; /* associated packet */
- void *vaddr; /* start address for XDP */
+ struct sk_buff *skb; /* associated packet (sk_buff path) */
+ struct xdp_frame *xdpf; /* associated XDP frame (XDP path) */
};
};
@@ -245,7 +245,7 @@ static inline int fun_irq_node(const struct fun_irq *p)
int fun_rxq_napi_poll(struct napi_struct *napi, int budget);
int fun_txq_napi_poll(struct napi_struct *napi, int budget);
netdev_tx_t fun_start_xmit(struct sk_buff *skb, struct net_device *netdev);
-bool fun_xdp_tx(struct funeth_txq *q, void *data, unsigned int len);
+bool fun_xdp_tx(struct funeth_txq *q, struct xdp_frame *xdpf);
int fun_xdp_xmit_frames(struct net_device *dev, int n,
struct xdp_frame **frames, u32 flags);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 7f1a0d9..685556e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -1925,11 +1925,15 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
* non-zero req_queue_pairs says that user requested a new
* queue count via ethtool's set_channels, so use this
* value for queues distribution across traffic classes
+ * We need at least one queue pair for the interface
+ * to be usable as we see in else statement.
*/
if (vsi->req_queue_pairs > 0)
vsi->num_queue_pairs = vsi->req_queue_pairs;
else if (pf->flags & I40E_FLAG_MSIX_ENABLED)
vsi->num_queue_pairs = pf->num_lan_msix;
+ else
+ vsi->num_queue_pairs = 1;
}
/* Number of queues per enabled TC */
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 70335f6e..4efa5e5 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -658,7 +658,8 @@ static int ice_lbtest_receive_frames(struct ice_rx_ring *rx_ring)
rx_desc = ICE_RX_DESC(rx_ring, i);
if (!(rx_desc->wb.status_error0 &
- cpu_to_le16(ICE_TX_DESC_CMD_EOP | ICE_TX_DESC_CMD_RS)))
+ (cpu_to_le16(BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S)) |
+ cpu_to_le16(BIT(ICE_RX_FLEX_DESC_STATUS0_EOF_S)))))
continue;
rx_buf = &rx_ring->rx_buf[i];
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index ff2eac2f..9f02b60 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4656,6 +4656,8 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
ice_set_safe_mode_caps(hw);
}
+ hw->ucast_shared = true;
+
err = ice_init_pf(pf);
if (err) {
dev_err(dev, "ice_init_pf failed: %d\n", err);
@@ -6011,10 +6013,12 @@ int ice_vsi_cfg(struct ice_vsi *vsi)
if (vsi->netdev) {
ice_set_rx_mode(vsi->netdev);
- err = ice_vsi_vlan_setup(vsi);
+ if (vsi->type != ICE_VSI_LB) {
+ err = ice_vsi_vlan_setup(vsi);
- if (err)
- return err;
+ if (err)
+ return err;
+ }
}
ice_vsi_cfg_dcb_rings(vsi);
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c
index bb1721f1..f4907a3 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.c
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.c
@@ -1310,39 +1310,6 @@ ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi)
}
/**
- * ice_unicast_mac_exists - check if the unicast MAC exists on the PF's switch
- * @pf: PF used to reference the switch's rules
- * @umac: unicast MAC to compare against existing switch rules
- *
- * Return true on the first/any match, else return false
- */
-static bool ice_unicast_mac_exists(struct ice_pf *pf, u8 *umac)
-{
- struct ice_sw_recipe *mac_recipe_list =
- &pf->hw.switch_info->recp_list[ICE_SW_LKUP_MAC];
- struct ice_fltr_mgmt_list_entry *list_itr;
- struct list_head *rule_head;
- struct mutex *rule_lock; /* protect MAC filter list access */
-
- rule_head = &mac_recipe_list->filt_rules;
- rule_lock = &mac_recipe_list->filt_rule_lock;
-
- mutex_lock(rule_lock);
- list_for_each_entry(list_itr, rule_head, list_entry) {
- u8 *existing_mac = &list_itr->fltr_info.l_data.mac.mac_addr[0];
-
- if (ether_addr_equal(existing_mac, umac)) {
- mutex_unlock(rule_lock);
- return true;
- }
- }
-
- mutex_unlock(rule_lock);
-
- return false;
-}
-
-/**
* ice_set_vf_mac
* @netdev: network interface device structure
* @vf_id: VF identifier
@@ -1376,13 +1343,6 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
if (ret)
goto out_put_vf;
- if (ice_unicast_mac_exists(pf, mac)) {
- netdev_err(netdev, "Unicast MAC %pM already exists on this PF. Preventing setting VF %u unicast MAC address to %pM\n",
- mac, vf_id, mac);
- ret = -EINVAL;
- goto out_put_vf;
- }
-
mutex_lock(&vf->cfg_lock);
/* VF is notified of its new MAC via the PF's response to the
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 3f8b727..836dce8 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1751,11 +1751,13 @@ int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
protocol = vlan_get_protocol(skb);
- if (eth_p_mpls(protocol))
+ if (eth_p_mpls(protocol)) {
ip.hdr = skb_inner_network_header(skb);
- else
+ l4.hdr = skb_checksum_start(skb);
+ } else {
ip.hdr = skb_network_header(skb);
- l4.hdr = skb_checksum_start(skb);
+ l4.hdr = skb_transport_header(skb);
+ }
/* compute outer L2 header size */
l2_len = ip.hdr - skb->data;
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index 4547bc1..24188ec 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -2948,7 +2948,8 @@ ice_vc_validate_add_vlan_filter_list(struct ice_vsi *vsi,
struct virtchnl_vlan_filtering_caps *vfc,
struct virtchnl_vlan_filter_list_v2 *vfl)
{
- u16 num_requested_filters = vsi->num_vlan + vfl->num_elements;
+ u16 num_requested_filters = ice_vsi_num_non_zero_vlans(vsi) +
+ vfl->num_elements;
if (num_requested_filters > vfc->max_filters)
return false;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
index 28b1994..e64318c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
@@ -28,6 +28,9 @@
#define MAX_RATE_EXPONENT 0x0FULL
#define MAX_RATE_MANTISSA 0xFFULL
+#define CN10K_MAX_BURST_MANTISSA 0x7FFFULL
+#define CN10K_MAX_BURST_SIZE 8453888ULL
+
/* Bitfields in NIX_TLX_PIR register */
#define TLX_RATE_MANTISSA GENMASK_ULL(8, 1)
#define TLX_RATE_EXPONENT GENMASK_ULL(12, 9)
@@ -35,6 +38,9 @@
#define TLX_BURST_MANTISSA GENMASK_ULL(36, 29)
#define TLX_BURST_EXPONENT GENMASK_ULL(40, 37)
+#define CN10K_TLX_BURST_MANTISSA GENMASK_ULL(43, 29)
+#define CN10K_TLX_BURST_EXPONENT GENMASK_ULL(47, 44)
+
struct otx2_tc_flow_stats {
u64 bytes;
u64 pkts;
@@ -77,33 +83,42 @@ int otx2_tc_alloc_ent_bitmap(struct otx2_nic *nic)
}
EXPORT_SYMBOL(otx2_tc_alloc_ent_bitmap);
-static void otx2_get_egress_burst_cfg(u32 burst, u32 *burst_exp,
- u32 *burst_mantissa)
+static void otx2_get_egress_burst_cfg(struct otx2_nic *nic, u32 burst,
+ u32 *burst_exp, u32 *burst_mantissa)
{
+ int max_burst, max_mantissa;
unsigned int tmp;
+ if (is_dev_otx2(nic->pdev)) {
+ max_burst = MAX_BURST_SIZE;
+ max_mantissa = MAX_BURST_MANTISSA;
+ } else {
+ max_burst = CN10K_MAX_BURST_SIZE;
+ max_mantissa = CN10K_MAX_BURST_MANTISSA;
+ }
+
/* Burst is calculated as
* ((256 + BURST_MANTISSA) << (1 + BURST_EXPONENT)) / 256
* Max supported burst size is 130,816 bytes.
*/
- burst = min_t(u32, burst, MAX_BURST_SIZE);
+ burst = min_t(u32, burst, max_burst);
if (burst) {
*burst_exp = ilog2(burst) ? ilog2(burst) - 1 : 0;
tmp = burst - rounddown_pow_of_two(burst);
- if (burst < MAX_BURST_MANTISSA)
+ if (burst < max_mantissa)
*burst_mantissa = tmp * 2;
else
*burst_mantissa = tmp / (1ULL << (*burst_exp - 7));
} else {
*burst_exp = MAX_BURST_EXPONENT;
- *burst_mantissa = MAX_BURST_MANTISSA;
+ *burst_mantissa = max_mantissa;
}
}
-static void otx2_get_egress_rate_cfg(u32 maxrate, u32 *exp,
+static void otx2_get_egress_rate_cfg(u64 maxrate, u32 *exp,
u32 *mantissa, u32 *div_exp)
{
- unsigned int tmp;
+ u64 tmp;
/* Rate calculation by hardware
*
@@ -132,21 +147,44 @@ static void otx2_get_egress_rate_cfg(u32 maxrate, u32 *exp,
}
}
-static int otx2_set_matchall_egress_rate(struct otx2_nic *nic, u32 burst, u32 maxrate)
+static u64 otx2_get_txschq_rate_regval(struct otx2_nic *nic,
+ u64 maxrate, u32 burst)
+{
+ u32 burst_exp, burst_mantissa;
+ u32 exp, mantissa, div_exp;
+ u64 regval = 0;
+
+ /* Get exponent and mantissa values from the desired rate */
+ otx2_get_egress_burst_cfg(nic, burst, &burst_exp, &burst_mantissa);
+ otx2_get_egress_rate_cfg(maxrate, &exp, &mantissa, &div_exp);
+
+ if (is_dev_otx2(nic->pdev)) {
+ regval = FIELD_PREP(TLX_BURST_EXPONENT, (u64)burst_exp) |
+ FIELD_PREP(TLX_BURST_MANTISSA, (u64)burst_mantissa) |
+ FIELD_PREP(TLX_RATE_DIVIDER_EXPONENT, div_exp) |
+ FIELD_PREP(TLX_RATE_EXPONENT, exp) |
+ FIELD_PREP(TLX_RATE_MANTISSA, mantissa) | BIT_ULL(0);
+ } else {
+ regval = FIELD_PREP(CN10K_TLX_BURST_EXPONENT, (u64)burst_exp) |
+ FIELD_PREP(CN10K_TLX_BURST_MANTISSA, (u64)burst_mantissa) |
+ FIELD_PREP(TLX_RATE_DIVIDER_EXPONENT, div_exp) |
+ FIELD_PREP(TLX_RATE_EXPONENT, exp) |
+ FIELD_PREP(TLX_RATE_MANTISSA, mantissa) | BIT_ULL(0);
+ }
+
+ return regval;
+}
+
+static int otx2_set_matchall_egress_rate(struct otx2_nic *nic,
+ u32 burst, u64 maxrate)
{
struct otx2_hw *hw = &nic->hw;
struct nix_txschq_config *req;
- u32 burst_exp, burst_mantissa;
- u32 exp, mantissa, div_exp;
int txschq, err;
/* All SQs share the same TL4, so pick the first scheduler */
txschq = hw->txschq_list[NIX_TXSCH_LVL_TL4][0];
- /* Get exponent and mantissa values from the desired rate */
- otx2_get_egress_burst_cfg(burst, &burst_exp, &burst_mantissa);
- otx2_get_egress_rate_cfg(maxrate, &exp, &mantissa, &div_exp);
-
mutex_lock(&nic->mbox.lock);
req = otx2_mbox_alloc_msg_nix_txschq_cfg(&nic->mbox);
if (!req) {
@@ -157,11 +195,7 @@ static int otx2_set_matchall_egress_rate(struct otx2_nic *nic, u32 burst, u32 ma
req->lvl = NIX_TXSCH_LVL_TL4;
req->num_regs = 1;
req->reg[0] = NIX_AF_TL4X_PIR(txschq);
- req->regval[0] = FIELD_PREP(TLX_BURST_EXPONENT, burst_exp) |
- FIELD_PREP(TLX_BURST_MANTISSA, burst_mantissa) |
- FIELD_PREP(TLX_RATE_DIVIDER_EXPONENT, div_exp) |
- FIELD_PREP(TLX_RATE_EXPONENT, exp) |
- FIELD_PREP(TLX_RATE_MANTISSA, mantissa) | BIT_ULL(0);
+ req->regval[0] = otx2_get_txschq_rate_regval(nic, maxrate, burst);
err = otx2_sync_mbox_msg(&nic->mbox);
mutex_unlock(&nic->mbox.lock);
@@ -230,7 +264,7 @@ static int otx2_tc_egress_matchall_install(struct otx2_nic *nic,
struct netlink_ext_ack *extack = cls->common.extack;
struct flow_action *actions = &cls->rule->action;
struct flow_action_entry *entry;
- u32 rate;
+ u64 rate;
int err;
err = otx2_tc_validate_flow(nic, actions, extack);
@@ -256,7 +290,7 @@ static int otx2_tc_egress_matchall_install(struct otx2_nic *nic,
}
/* Convert bytes per second to Mbps */
rate = entry->police.rate_bytes_ps * 8;
- rate = max_t(u32, rate / 1000000, 1);
+ rate = max_t(u64, rate / 1000000, 1);
err = otx2_set_matchall_egress_rate(nic, entry->police.burst, rate);
if (err)
return err;
@@ -614,21 +648,27 @@ static int otx2_tc_prepare_flow(struct otx2_nic *nic, struct otx2_tc_flow *node,
flow_spec->dport = match.key->dst;
flow_mask->dport = match.mask->dst;
- if (ip_proto == IPPROTO_UDP)
- req->features |= BIT_ULL(NPC_DPORT_UDP);
- else if (ip_proto == IPPROTO_TCP)
- req->features |= BIT_ULL(NPC_DPORT_TCP);
- else if (ip_proto == IPPROTO_SCTP)
- req->features |= BIT_ULL(NPC_DPORT_SCTP);
+
+ if (flow_mask->dport) {
+ if (ip_proto == IPPROTO_UDP)
+ req->features |= BIT_ULL(NPC_DPORT_UDP);
+ else if (ip_proto == IPPROTO_TCP)
+ req->features |= BIT_ULL(NPC_DPORT_TCP);
+ else if (ip_proto == IPPROTO_SCTP)
+ req->features |= BIT_ULL(NPC_DPORT_SCTP);
+ }
flow_spec->sport = match.key->src;
flow_mask->sport = match.mask->src;
- if (ip_proto == IPPROTO_UDP)
- req->features |= BIT_ULL(NPC_SPORT_UDP);
- else if (ip_proto == IPPROTO_TCP)
- req->features |= BIT_ULL(NPC_SPORT_TCP);
- else if (ip_proto == IPPROTO_SCTP)
- req->features |= BIT_ULL(NPC_SPORT_SCTP);
+
+ if (flow_mask->sport) {
+ if (ip_proto == IPPROTO_UDP)
+ req->features |= BIT_ULL(NPC_SPORT_UDP);
+ else if (ip_proto == IPPROTO_TCP)
+ req->features |= BIT_ULL(NPC_SPORT_TCP);
+ else if (ip_proto == IPPROTO_SCTP)
+ req->features |= BIT_ULL(NPC_SPORT_SCTP);
+ }
}
return otx2_tc_parse_actions(nic, &rule->action, req, f, node);
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index e31f8fb..df2ab5c 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -4233,7 +4233,7 @@ static void nfp_bpf_opt_ldst_gather(struct nfp_prog *nfp_prog)
}
/* If the chain is ended by an load/store pair then this
- * could serve as the new head of the the next chain.
+ * could serve as the new head of the next chain.
*/
if (curr_pair_is_memcpy(meta1, meta2)) {
head_ld_meta = meta1;
diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
index 4625f85..10ad0b9 100644
--- a/drivers/net/ethernet/sfc/ptp.c
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -1100,7 +1100,29 @@ static void efx_ptp_xmit_skb_queue(struct efx_nic *efx, struct sk_buff *skb)
tx_queue = efx_channel_get_tx_queue(ptp_data->channel, type);
if (tx_queue && tx_queue->timestamping) {
+ /* This code invokes normal driver TX code which is always
+ * protected from softirqs when called from generic TX code,
+ * which in turn disables preemption. Look at __dev_queue_xmit
+ * which uses rcu_read_lock_bh disabling preemption for RCU
+ * plus disabling softirqs. We do not need RCU reader
+ * protection here.
+ *
+ * Although it is theoretically safe for current PTP TX/RX code
+ * running without disabling softirqs, there are three good
+ * reasond for doing so:
+ *
+ * 1) The code invoked is mainly implemented for non-PTP
+ * packets and it is always executed with softirqs
+ * disabled.
+ * 2) This being a single PTP packet, better to not
+ * interrupt its processing by softirqs which can lead
+ * to high latencies.
+ * 3) netdev_xmit_more checks preemption is disabled and
+ * triggers a BUG_ON if not.
+ */
+ local_bh_disable();
efx_enqueue_skb(tx_queue, skb);
+ local_bh_enable();
} else {
WARN_ONCE(1, "PTP channel has no timestamped tx queue\n");
dev_kfree_skb_any(skb);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
index ca8ab29..d42e1af 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
@@ -688,18 +688,19 @@ static int mediatek_dwmac_probe(struct platform_device *pdev)
ret = mediatek_dwmac_clks_config(priv_plat, true);
if (ret)
- return ret;
+ goto err_remove_config_dt;
ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
- if (ret) {
- stmmac_remove_config_dt(pdev, plat_dat);
+ if (ret)
goto err_drv_probe;
- }
return 0;
err_drv_probe:
mediatek_dwmac_clks_config(priv_plat, false);
+err_remove_config_dt:
+ stmmac_remove_config_dt(pdev, plat_dat);
+
return ret;
}
diff --git a/drivers/net/ipa/ipa_qmi_msg.h b/drivers/net/ipa/ipa_qmi_msg.h
index 3233d14..495e85a 100644
--- a/drivers/net/ipa/ipa_qmi_msg.h
+++ b/drivers/net/ipa/ipa_qmi_msg.h
@@ -214,7 +214,7 @@ struct ipa_init_modem_driver_req {
/* The response to a IPA_QMI_INIT_DRIVER request begins with a standard
* QMI response, but contains other information as well. Currently we
- * simply wait for the the INIT_DRIVER transaction to complete and
+ * simply wait for the INIT_DRIVER transaction to complete and
* ignore any other data that might be returned.
*/
struct ipa_init_modem_driver_rsp {
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 817577e..f354fad 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -243,6 +243,7 @@ static struct macsec_cb *macsec_skb_cb(struct sk_buff *skb)
#define DEFAULT_SEND_SCI true
#define DEFAULT_ENCRYPT false
#define DEFAULT_ENCODING_SA 0
+#define MACSEC_XPN_MAX_REPLAY_WINDOW (((1 << 30) - 1))
static bool send_sci(const struct macsec_secy *secy)
{
@@ -1697,7 +1698,7 @@ static bool validate_add_rxsa(struct nlattr **attrs)
return false;
if (attrs[MACSEC_SA_ATTR_PN] &&
- *(u64 *)nla_data(attrs[MACSEC_SA_ATTR_PN]) == 0)
+ nla_get_u64(attrs[MACSEC_SA_ATTR_PN]) == 0)
return false;
if (attrs[MACSEC_SA_ATTR_ACTIVE]) {
@@ -1753,7 +1754,8 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info)
}
pn_len = secy->xpn ? MACSEC_XPN_PN_LEN : MACSEC_DEFAULT_PN_LEN;
- if (nla_len(tb_sa[MACSEC_SA_ATTR_PN]) != pn_len) {
+ if (tb_sa[MACSEC_SA_ATTR_PN] &&
+ nla_len(tb_sa[MACSEC_SA_ATTR_PN]) != pn_len) {
pr_notice("macsec: nl: add_rxsa: bad pn length: %d != %d\n",
nla_len(tb_sa[MACSEC_SA_ATTR_PN]), pn_len);
rtnl_unlock();
@@ -1769,7 +1771,7 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info)
if (nla_len(tb_sa[MACSEC_SA_ATTR_SALT]) != MACSEC_SALT_LEN) {
pr_notice("macsec: nl: add_rxsa: bad salt length: %d != %d\n",
nla_len(tb_sa[MACSEC_SA_ATTR_SALT]),
- MACSEC_SA_ATTR_SALT);
+ MACSEC_SALT_LEN);
rtnl_unlock();
return -EINVAL;
}
@@ -1842,7 +1844,7 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info)
return 0;
cleanup:
- kfree(rx_sa);
+ macsec_rxsa_put(rx_sa);
rtnl_unlock();
return err;
}
@@ -1939,7 +1941,7 @@ static bool validate_add_txsa(struct nlattr **attrs)
if (nla_get_u8(attrs[MACSEC_SA_ATTR_AN]) >= MACSEC_NUM_AN)
return false;
- if (nla_get_u32(attrs[MACSEC_SA_ATTR_PN]) == 0)
+ if (nla_get_u64(attrs[MACSEC_SA_ATTR_PN]) == 0)
return false;
if (attrs[MACSEC_SA_ATTR_ACTIVE]) {
@@ -2011,7 +2013,7 @@ static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info)
if (nla_len(tb_sa[MACSEC_SA_ATTR_SALT]) != MACSEC_SALT_LEN) {
pr_notice("macsec: nl: add_txsa: bad salt length: %d != %d\n",
nla_len(tb_sa[MACSEC_SA_ATTR_SALT]),
- MACSEC_SA_ATTR_SALT);
+ MACSEC_SALT_LEN);
rtnl_unlock();
return -EINVAL;
}
@@ -2085,7 +2087,7 @@ static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info)
cleanup:
secy->operational = was_operational;
- kfree(tx_sa);
+ macsec_txsa_put(tx_sa);
rtnl_unlock();
return err;
}
@@ -2293,7 +2295,7 @@ static bool validate_upd_sa(struct nlattr **attrs)
if (nla_get_u8(attrs[MACSEC_SA_ATTR_AN]) >= MACSEC_NUM_AN)
return false;
- if (attrs[MACSEC_SA_ATTR_PN] && nla_get_u32(attrs[MACSEC_SA_ATTR_PN]) == 0)
+ if (attrs[MACSEC_SA_ATTR_PN] && nla_get_u64(attrs[MACSEC_SA_ATTR_PN]) == 0)
return false;
if (attrs[MACSEC_SA_ATTR_ACTIVE]) {
@@ -3745,9 +3747,6 @@ static int macsec_changelink_common(struct net_device *dev,
secy->operational = tx_sa && tx_sa->active;
}
- if (data[IFLA_MACSEC_WINDOW])
- secy->replay_window = nla_get_u32(data[IFLA_MACSEC_WINDOW]);
-
if (data[IFLA_MACSEC_ENCRYPT])
tx_sc->encrypt = !!nla_get_u8(data[IFLA_MACSEC_ENCRYPT]);
@@ -3793,6 +3792,16 @@ static int macsec_changelink_common(struct net_device *dev,
}
}
+ if (data[IFLA_MACSEC_WINDOW]) {
+ secy->replay_window = nla_get_u32(data[IFLA_MACSEC_WINDOW]);
+
+ /* IEEE 802.1AEbw-2013 10.7.8 - maximum replay window
+ * for XPN cipher suites */
+ if (secy->xpn &&
+ secy->replay_window > MACSEC_XPN_MAX_REPLAY_WINDOW)
+ return -EINVAL;
+ }
+
return 0;
}
@@ -3822,7 +3831,7 @@ static int macsec_changelink(struct net_device *dev, struct nlattr *tb[],
ret = macsec_changelink_common(dev, data);
if (ret)
- return ret;
+ goto cleanup;
/* If h/w offloading is available, propagate to the device */
if (macsec_is_offloaded(macsec)) {
diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c
index 4cfd05c..d25fbb9 100644
--- a/drivers/net/pcs/pcs-xpcs.c
+++ b/drivers/net/pcs/pcs-xpcs.c
@@ -896,7 +896,7 @@ static int xpcs_get_state_c37_sgmii(struct dw_xpcs *xpcs,
*/
ret = xpcs_read(xpcs, MDIO_MMD_VEND2, DW_VR_MII_AN_INTR_STS);
if (ret < 0)
- return false;
+ return ret;
if (ret & DW_VR_MII_C37_ANSGM_SP_LNKSTS) {
int speed_value;
diff --git a/drivers/net/sungem_phy.c b/drivers/net/sungem_phy.c
index ff22b6b..36803d9 100644
--- a/drivers/net/sungem_phy.c
+++ b/drivers/net/sungem_phy.c
@@ -450,6 +450,7 @@ static int bcm5421_init(struct mii_phy* phy)
int can_low_power = 1;
if (np == NULL || of_get_property(np, "no-autolowpower", NULL))
can_low_power = 0;
+ of_node_put(np);
if (can_low_power) {
/* Enable automatic low-power */
sungem_phy_write(phy, 0x1c, 0x9002);
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 356cf8d..ec8e1b3 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -242,9 +242,15 @@ struct virtnet_info {
/* Packet virtio header size */
u8 hdr_len;
- /* Work struct for refilling if we run low on memory. */
+ /* Work struct for delayed refilling if we run low on memory. */
struct delayed_work refill;
+ /* Is delayed refill enabled? */
+ bool refill_enabled;
+
+ /* The lock to synchronize the access to refill_enabled */
+ spinlock_t refill_lock;
+
/* Work struct for config space updates */
struct work_struct config_work;
@@ -348,6 +354,20 @@ static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask)
return p;
}
+static void enable_delayed_refill(struct virtnet_info *vi)
+{
+ spin_lock_bh(&vi->refill_lock);
+ vi->refill_enabled = true;
+ spin_unlock_bh(&vi->refill_lock);
+}
+
+static void disable_delayed_refill(struct virtnet_info *vi)
+{
+ spin_lock_bh(&vi->refill_lock);
+ vi->refill_enabled = false;
+ spin_unlock_bh(&vi->refill_lock);
+}
+
static void virtqueue_napi_schedule(struct napi_struct *napi,
struct virtqueue *vq)
{
@@ -1527,8 +1547,12 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
}
if (rq->vq->num_free > min((unsigned int)budget, virtqueue_get_vring_size(rq->vq)) / 2) {
- if (!try_fill_recv(vi, rq, GFP_ATOMIC))
- schedule_delayed_work(&vi->refill, 0);
+ if (!try_fill_recv(vi, rq, GFP_ATOMIC)) {
+ spin_lock(&vi->refill_lock);
+ if (vi->refill_enabled)
+ schedule_delayed_work(&vi->refill, 0);
+ spin_unlock(&vi->refill_lock);
+ }
}
u64_stats_update_begin(&rq->stats.syncp);
@@ -1651,6 +1675,8 @@ static int virtnet_open(struct net_device *dev)
struct virtnet_info *vi = netdev_priv(dev);
int i, err;
+ enable_delayed_refill(vi);
+
for (i = 0; i < vi->max_queue_pairs; i++) {
if (i < vi->curr_queue_pairs)
/* Make sure we have some buffers: if oom use wq. */
@@ -2033,6 +2059,8 @@ static int virtnet_close(struct net_device *dev)
struct virtnet_info *vi = netdev_priv(dev);
int i;
+ /* Make sure NAPI doesn't schedule refill work */
+ disable_delayed_refill(vi);
/* Make sure refill_work doesn't re-enable napi! */
cancel_delayed_work_sync(&vi->refill);
@@ -2792,6 +2820,8 @@ static int virtnet_restore_up(struct virtio_device *vdev)
virtio_device_ready(vdev);
+ enable_delayed_refill(vi);
+
if (netif_running(vi->dev)) {
err = virtnet_open(vi->dev);
if (err)
@@ -3535,6 +3565,7 @@ static int virtnet_probe(struct virtio_device *vdev)
vdev->priv = vi;
INIT_WORK(&vi->config_work, virtnet_config_changed_work);
+ spin_lock_init(&vi->refill_lock);
/* If we can receive ANY GSO packets, we must allocate large ones. */
if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 58c72d5..73d9fcb 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -3515,6 +3515,8 @@ static const struct pci_device_id nvme_id_table[] = {
.driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(0x1e49, 0x0041), /* ZHITAI TiPro7000 NVMe SSD */
.driver_data = NVME_QUIRK_NO_DEEPEST_PS, },
+ { PCI_DEVICE(0xc0a9, 0x540a), /* Crucial P2 */
+ .driver_data = NVME_QUIRK_BOGUS_NID, },
{ PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0061),
.driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, },
{ PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0x0065),
diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig
index 458218f..fe4971b 100644
--- a/drivers/ptp/Kconfig
+++ b/drivers/ptp/Kconfig
@@ -176,6 +176,7 @@
depends on !S390
depends on COMMON_CLK
select NET_DEVLINK
+ select CRC16
help
This driver adds support for an OpenCompute time card.
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 9e54fe7..35d4b39 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -3565,7 +3565,7 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index,
if (!atomic_read(&queue->set_pci_flags_count)) {
/*
* there's no outstanding PCI any more, so we
- * have to request a PCI to be sure the the PCI
+ * have to request a PCI to be sure the PCI
* will wake at some time in the future then we
* can flush packed buffers that might still be
* hanging around, which can happen if no
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index b519f4b..5e8887f 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -11386,6 +11386,7 @@ scsih_shutdown(struct pci_dev *pdev)
_scsih_ir_shutdown(ioc);
_scsih_nvme_shutdown(ioc);
mpt3sas_base_mask_interrupts(ioc);
+ mpt3sas_base_stop_watchdog(ioc);
ioc->shost_recovery = 1;
mpt3sas_base_make_ioc_ready(ioc, SOFT_RESET);
ioc->shost_recovery = 0;
diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c
index a480c4d..729e309 100644
--- a/drivers/scsi/scsi_ioctl.c
+++ b/drivers/scsi/scsi_ioctl.c
@@ -450,7 +450,7 @@ static int sg_io(struct scsi_device *sdev, struct sg_io_hdr *hdr, fmode_t mode)
goto out_put_request;
ret = 0;
- if (hdr->iovec_count) {
+ if (hdr->iovec_count && hdr->dxfer_len) {
struct iov_iter i;
struct iovec *iov = NULL;
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index c7b3374..3d367be 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -2953,37 +2953,59 @@ ufshcd_dev_cmd_completion(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
static int ufshcd_wait_for_dev_cmd(struct ufs_hba *hba,
struct ufshcd_lrb *lrbp, int max_timeout)
{
- int err = 0;
- unsigned long time_left;
+ unsigned long time_left = msecs_to_jiffies(max_timeout);
unsigned long flags;
+ bool pending;
+ int err;
+retry:
time_left = wait_for_completion_timeout(hba->dev_cmd.complete,
- msecs_to_jiffies(max_timeout));
+ time_left);
- spin_lock_irqsave(hba->host->host_lock, flags);
- hba->dev_cmd.complete = NULL;
if (likely(time_left)) {
+ /*
+ * The completion handler called complete() and the caller of
+ * this function still owns the @lrbp tag so the code below does
+ * not trigger any race conditions.
+ */
+ hba->dev_cmd.complete = NULL;
err = ufshcd_get_tr_ocs(lrbp);
if (!err)
err = ufshcd_dev_cmd_completion(hba, lrbp);
- }
- spin_unlock_irqrestore(hba->host->host_lock, flags);
-
- if (!time_left) {
+ } else {
err = -ETIMEDOUT;
dev_dbg(hba->dev, "%s: dev_cmd request timedout, tag %d\n",
__func__, lrbp->task_tag);
- if (!ufshcd_clear_cmds(hba, 1U << lrbp->task_tag))
+ if (ufshcd_clear_cmds(hba, 1U << lrbp->task_tag) == 0) {
/* successfully cleared the command, retry if needed */
err = -EAGAIN;
- /*
- * in case of an error, after clearing the doorbell,
- * we also need to clear the outstanding_request
- * field in hba
- */
- spin_lock_irqsave(&hba->outstanding_lock, flags);
- __clear_bit(lrbp->task_tag, &hba->outstanding_reqs);
- spin_unlock_irqrestore(&hba->outstanding_lock, flags);
+ /*
+ * Since clearing the command succeeded we also need to
+ * clear the task tag bit from the outstanding_reqs
+ * variable.
+ */
+ spin_lock_irqsave(&hba->outstanding_lock, flags);
+ pending = test_bit(lrbp->task_tag,
+ &hba->outstanding_reqs);
+ if (pending) {
+ hba->dev_cmd.complete = NULL;
+ __clear_bit(lrbp->task_tag,
+ &hba->outstanding_reqs);
+ }
+ spin_unlock_irqrestore(&hba->outstanding_lock, flags);
+
+ if (!pending) {
+ /*
+ * The completion handler ran while we tried to
+ * clear the command.
+ */
+ time_left = 1;
+ goto retry;
+ }
+ } else {
+ dev_err(hba->dev, "%s: failed to clear tag %d\n",
+ __func__, lrbp->task_tag);
+ }
}
return err;
diff --git a/drivers/ufs/host/ufshcd-pltfrm.c b/drivers/ufs/host/ufshcd-pltfrm.c
index e7332cc..173aea8 100644
--- a/drivers/ufs/host/ufshcd-pltfrm.c
+++ b/drivers/ufs/host/ufshcd-pltfrm.c
@@ -108,9 +108,20 @@ static int ufshcd_parse_clock_info(struct ufs_hba *hba)
return ret;
}
+static bool phandle_exists(const struct device_node *np,
+ const char *phandle_name, int index)
+{
+ struct device_node *parse_np = of_parse_phandle(np, phandle_name, index);
+
+ if (parse_np)
+ of_node_put(parse_np);
+
+ return parse_np != NULL;
+}
+
#define MAX_PROP_SIZE 32
static int ufshcd_populate_vreg(struct device *dev, const char *name,
- struct ufs_vreg **out_vreg)
+ struct ufs_vreg **out_vreg)
{
char prop_name[MAX_PROP_SIZE];
struct ufs_vreg *vreg = NULL;
@@ -122,7 +133,7 @@ static int ufshcd_populate_vreg(struct device *dev, const char *name,
}
snprintf(prop_name, MAX_PROP_SIZE, "%s-supply", name);
- if (!of_parse_phandle(np, prop_name, 0)) {
+ if (!phandle_exists(np, prop_name, 0)) {
dev_info(dev, "%s: Unable to find %s regulator, assuming enabled\n",
__func__, prop_name);
goto out;
diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c
index 4de597a..52615e6 100644
--- a/fs/ntfs/attrib.c
+++ b/fs/ntfs/attrib.c
@@ -592,8 +592,12 @@ static int ntfs_attr_find(const ATTR_TYPE type, const ntfschar *name,
a = (ATTR_RECORD*)((u8*)ctx->attr +
le32_to_cpu(ctx->attr->length));
for (;; a = (ATTR_RECORD*)((u8*)a + le32_to_cpu(a->length))) {
- if ((u8*)a < (u8*)ctx->mrec || (u8*)a > (u8*)ctx->mrec +
- le32_to_cpu(ctx->mrec->bytes_allocated))
+ u8 *mrec_end = (u8 *)ctx->mrec +
+ le32_to_cpu(ctx->mrec->bytes_allocated);
+ u8 *name_end = (u8 *)a + le16_to_cpu(a->name_offset) +
+ a->name_length * sizeof(ntfschar);
+ if ((u8*)a < (u8*)ctx->mrec || (u8*)a > mrec_end ||
+ name_end > mrec_end)
break;
ctx->attr = a;
if (unlikely(le32_to_cpu(a->type) > le32_to_cpu(type) ||
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 3375275..740b642 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -277,7 +277,6 @@ enum ocfs2_mount_options
OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT = 1 << 15, /* Journal Async Commit */
OCFS2_MOUNT_ERRORS_CONT = 1 << 16, /* Return EIO to the calling process on error */
OCFS2_MOUNT_ERRORS_ROFS = 1 << 17, /* Change filesystem to read-only on error */
- OCFS2_MOUNT_NOCLUSTER = 1 << 18, /* No cluster aware filesystem mount */
};
#define OCFS2_OSB_SOFT_RO 0x0001
@@ -673,8 +672,7 @@ static inline int ocfs2_cluster_o2cb_global_heartbeat(struct ocfs2_super *osb)
static inline int ocfs2_mount_local(struct ocfs2_super *osb)
{
- return ((osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT)
- || (osb->s_mount_opt & OCFS2_MOUNT_NOCLUSTER));
+ return (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT);
}
static inline int ocfs2_uses_extended_slot_map(struct ocfs2_super *osb)
diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c
index 0b0ae3e..da7718c 100644
--- a/fs/ocfs2/slot_map.c
+++ b/fs/ocfs2/slot_map.c
@@ -252,16 +252,14 @@ static int __ocfs2_find_empty_slot(struct ocfs2_slot_info *si,
int i, ret = -ENOSPC;
if ((preferred >= 0) && (preferred < si->si_num_slots)) {
- if (!si->si_slots[preferred].sl_valid ||
- !si->si_slots[preferred].sl_node_num) {
+ if (!si->si_slots[preferred].sl_valid) {
ret = preferred;
goto out;
}
}
for(i = 0; i < si->si_num_slots; i++) {
- if (!si->si_slots[i].sl_valid ||
- !si->si_slots[i].sl_node_num) {
+ if (!si->si_slots[i].sl_valid) {
ret = i;
break;
}
@@ -456,30 +454,24 @@ int ocfs2_find_slot(struct ocfs2_super *osb)
spin_lock(&osb->osb_lock);
ocfs2_update_slot_info(si);
- if (ocfs2_mount_local(osb))
- /* use slot 0 directly in local mode */
- slot = 0;
- else {
- /* search for ourselves first and take the slot if it already
- * exists. Perhaps we need to mark this in a variable for our
- * own journal recovery? Possibly not, though we certainly
- * need to warn to the user */
- slot = __ocfs2_node_num_to_slot(si, osb->node_num);
+ /* search for ourselves first and take the slot if it already
+ * exists. Perhaps we need to mark this in a variable for our
+ * own journal recovery? Possibly not, though we certainly
+ * need to warn to the user */
+ slot = __ocfs2_node_num_to_slot(si, osb->node_num);
+ if (slot < 0) {
+ /* if no slot yet, then just take 1st available
+ * one. */
+ slot = __ocfs2_find_empty_slot(si, osb->preferred_slot);
if (slot < 0) {
- /* if no slot yet, then just take 1st available
- * one. */
- slot = __ocfs2_find_empty_slot(si, osb->preferred_slot);
- if (slot < 0) {
- spin_unlock(&osb->osb_lock);
- mlog(ML_ERROR, "no free slots available!\n");
- status = -EINVAL;
- goto bail;
- }
- } else
- printk(KERN_INFO "ocfs2: Slot %d on device (%s) was "
- "already allocated to this node!\n",
- slot, osb->dev_str);
- }
+ spin_unlock(&osb->osb_lock);
+ mlog(ML_ERROR, "no free slots available!\n");
+ status = -EINVAL;
+ goto bail;
+ }
+ } else
+ printk(KERN_INFO "ocfs2: Slot %d on device (%s) was already "
+ "allocated to this node!\n", slot, osb->dev_str);
ocfs2_set_slot(si, slot, osb->node_num);
osb->slot_num = slot;
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index f729881..438be02 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -172,7 +172,6 @@ enum {
Opt_dir_resv_level,
Opt_journal_async_commit,
Opt_err_cont,
- Opt_nocluster,
Opt_err,
};
@@ -206,7 +205,6 @@ static const match_table_t tokens = {
{Opt_dir_resv_level, "dir_resv_level=%u"},
{Opt_journal_async_commit, "journal_async_commit"},
{Opt_err_cont, "errors=continue"},
- {Opt_nocluster, "nocluster"},
{Opt_err, NULL}
};
@@ -618,13 +616,6 @@ static int ocfs2_remount(struct super_block *sb, int *flags, char *data)
goto out;
}
- tmp = OCFS2_MOUNT_NOCLUSTER;
- if ((osb->s_mount_opt & tmp) != (parsed_options.mount_opt & tmp)) {
- ret = -EINVAL;
- mlog(ML_ERROR, "Cannot change nocluster option on remount\n");
- goto out;
- }
-
tmp = OCFS2_MOUNT_HB_LOCAL | OCFS2_MOUNT_HB_GLOBAL |
OCFS2_MOUNT_HB_NONE;
if ((osb->s_mount_opt & tmp) != (parsed_options.mount_opt & tmp)) {
@@ -865,7 +856,6 @@ static int ocfs2_verify_userspace_stack(struct ocfs2_super *osb,
}
if (ocfs2_userspace_stack(osb) &&
- !(osb->s_mount_opt & OCFS2_MOUNT_NOCLUSTER) &&
strncmp(osb->osb_cluster_stack, mopt->cluster_stack,
OCFS2_STACK_LABEL_LEN)) {
mlog(ML_ERROR,
@@ -1137,11 +1127,6 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
osb->s_mount_opt & OCFS2_MOUNT_DATA_WRITEBACK ? "writeback" :
"ordered");
- if ((osb->s_mount_opt & OCFS2_MOUNT_NOCLUSTER) &&
- !(osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_LOCAL_MOUNT))
- printk(KERN_NOTICE "ocfs2: The shared device (%s) is mounted "
- "without cluster aware mode.\n", osb->dev_str);
-
atomic_set(&osb->vol_state, VOLUME_MOUNTED);
wake_up(&osb->osb_mount_event);
@@ -1452,9 +1437,6 @@ static int ocfs2_parse_options(struct super_block *sb,
case Opt_journal_async_commit:
mopt->mount_opt |= OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT;
break;
- case Opt_nocluster:
- mopt->mount_opt |= OCFS2_MOUNT_NOCLUSTER;
- break;
default:
mlog(ML_ERROR,
"Unrecognized mount option \"%s\" "
@@ -1566,9 +1548,6 @@ static int ocfs2_show_options(struct seq_file *s, struct dentry *root)
if (opts & OCFS2_MOUNT_JOURNAL_ASYNC_COMMIT)
seq_printf(s, ",journal_async_commit");
- if (opts & OCFS2_MOUNT_NOCLUSTER)
- seq_printf(s, ",nocluster");
-
return 0;
}
diff --git a/fs/read_write.c b/fs/read_write.c
index e0777ee..397da02 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1263,6 +1263,9 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
count, fl);
file_end_write(out.file);
} else {
+ if (out.file->f_flags & O_NONBLOCK)
+ fl |= SPLICE_F_NONBLOCK;
+
retval = splice_file_to_pipe(in.file, opipe, &pos, count, fl);
}
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index e943370..de86f5b 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -192,17 +192,19 @@ static inline void msg_init(struct uffd_msg *msg)
}
static inline struct uffd_msg userfault_msg(unsigned long address,
+ unsigned long real_address,
unsigned int flags,
unsigned long reason,
unsigned int features)
{
struct uffd_msg msg;
+
msg_init(&msg);
msg.event = UFFD_EVENT_PAGEFAULT;
- if (!(features & UFFD_FEATURE_EXACT_ADDRESS))
- address &= PAGE_MASK;
- msg.arg.pagefault.address = address;
+ msg.arg.pagefault.address = (features & UFFD_FEATURE_EXACT_ADDRESS) ?
+ real_address : address;
+
/*
* These flags indicate why the userfault occurred:
* - UFFD_PAGEFAULT_FLAG_WP indicates a write protect fault.
@@ -488,8 +490,8 @@ vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function);
uwq.wq.private = current;
- uwq.msg = userfault_msg(vmf->real_address, vmf->flags, reason,
- ctx->features);
+ uwq.msg = userfault_msg(vmf->address, vmf->real_address, vmf->flags,
+ reason, ctx->features);
uwq.ctx = ctx;
uwq.waken = false;
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index 7ce93aa..98954dd 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -1125,9 +1125,7 @@ static inline void memcpy_toio(volatile void __iomem *addr, const void *buffer,
}
#endif
-#ifndef CONFIG_GENERIC_DEVMEM_IS_ALLOWED
extern int devmem_is_allowed(unsigned long pfn);
-#endif
#endif /* __KERNEL__ */
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 19f0dbf..b66c5f3 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -130,7 +130,6 @@ enum cpuhp_state {
CPUHP_ZCOMP_PREPARE,
CPUHP_TIMERS_PREPARE,
CPUHP_MIPS_SOC_PREPARE,
- CPUHP_LOONGARCH_SOC_PREPARE,
CPUHP_BP_PREPARE_DYN,
CPUHP_BP_PREPARE_DYN_END = CPUHP_BP_PREPARE_DYN + 20,
CPUHP_BRINGUP_CPU,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index cf3d0d6..7898e29 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1130,23 +1130,27 @@ static inline bool is_zone_movable_page(const struct page *page)
#if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_FS_DAX)
DECLARE_STATIC_KEY_FALSE(devmap_managed_key);
-bool __put_devmap_managed_page(struct page *page);
-static inline bool put_devmap_managed_page(struct page *page)
+bool __put_devmap_managed_page_refs(struct page *page, int refs);
+static inline bool put_devmap_managed_page_refs(struct page *page, int refs)
{
if (!static_branch_unlikely(&devmap_managed_key))
return false;
if (!is_zone_device_page(page))
return false;
- return __put_devmap_managed_page(page);
+ return __put_devmap_managed_page_refs(page, refs);
}
-
#else /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */
-static inline bool put_devmap_managed_page(struct page *page)
+static inline bool put_devmap_managed_page_refs(struct page *page, int refs)
{
return false;
}
#endif /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */
+static inline bool put_devmap_managed_page(struct page *page)
+{
+ return put_devmap_managed_page_refs(page, 1);
+}
+
/* 127: arbitrary random number, small enough to assemble well */
#define folio_ref_zero_or_close_to_overflow(folio) \
((unsigned int) folio_ref_count(folio) + 127u <= 127u)
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index f7506f0..c04f359 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -405,6 +405,9 @@ static inline bool ip6_ignore_linkdown(const struct net_device *dev)
{
const struct inet6_dev *idev = __in6_dev_get(dev);
+ if (unlikely(!idev))
+ return true;
+
return !!idev->cnf.ignore_routes_with_linkdown;
}
diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 3c4f550..2f766e3 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -847,6 +847,7 @@ enum {
};
void l2cap_chan_hold(struct l2cap_chan *c);
+struct l2cap_chan *l2cap_chan_hold_unless_zero(struct l2cap_chan *c);
void l2cap_chan_put(struct l2cap_chan *c);
static inline void l2cap_chan_lock(struct l2cap_chan *chan)
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 85cd695..ee88f0f 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -321,7 +321,7 @@ void inet_csk_update_fastreuse(struct inet_bind_bucket *tb,
struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu);
-#define TCP_PINGPONG_THRESH 3
+#define TCP_PINGPONG_THRESH 1
static inline void inet_csk_enter_pingpong_mode(struct sock *sk)
{
@@ -338,14 +338,6 @@ static inline bool inet_csk_in_pingpong_mode(struct sock *sk)
return inet_csk(sk)->icsk_ack.pingpong >= TCP_PINGPONG_THRESH;
}
-static inline void inet_csk_inc_pingpong_cnt(struct sock *sk)
-{
- struct inet_connection_sock *icsk = inet_csk(sk);
-
- if (icsk->icsk_ack.pingpong < U8_MAX)
- icsk->icsk_ack.pingpong++;
-}
-
static inline bool inet_csk_has_ulp(struct sock *sk)
{
return inet_sk(sk)->is_icsk && !!inet_csk(sk)->icsk_ulp_ops;
diff --git a/include/net/sock.h b/include/net/sock.h
index 9fa5476..7a48991 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2843,18 +2843,18 @@ static inline int sk_get_wmem0(const struct sock *sk, const struct proto *proto)
{
/* Does this proto have per netns sysctl_wmem ? */
if (proto->sysctl_wmem_offset)
- return *(int *)((void *)sock_net(sk) + proto->sysctl_wmem_offset);
+ return READ_ONCE(*(int *)((void *)sock_net(sk) + proto->sysctl_wmem_offset));
- return *proto->sysctl_wmem;
+ return READ_ONCE(*proto->sysctl_wmem);
}
static inline int sk_get_rmem0(const struct sock *sk, const struct proto *proto)
{
/* Does this proto have per netns sysctl_rmem ? */
if (proto->sysctl_rmem_offset)
- return *(int *)((void *)sock_net(sk) + proto->sysctl_rmem_offset);
+ return READ_ONCE(*(int *)((void *)sock_net(sk) + proto->sysctl_rmem_offset));
- return *proto->sysctl_rmem;
+ return READ_ONCE(*proto->sysctl_rmem);
}
/* Default TCP Small queue budget is ~1 ms of data (1sec >> 10)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 071735e..78a64e1 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1419,7 +1419,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space,
static inline int tcp_win_from_space(const struct sock *sk, int space)
{
- int tcp_adv_win_scale = sock_net(sk)->ipv4.sysctl_tcp_adv_win_scale;
+ int tcp_adv_win_scale = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_adv_win_scale);
return tcp_adv_win_scale <= 0 ?
(space>>(-tcp_adv_win_scale)) :
diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h
index f13d37b..1ecdb91 100644
--- a/include/uapi/asm-generic/fcntl.h
+++ b/include/uapi/asm-generic/fcntl.h
@@ -192,6 +192,7 @@ struct f_owner_ex {
#define F_LINUX_SPECIFIC_BASE 1024
+#ifndef HAVE_ARCH_STRUCT_FLOCK
struct flock {
short l_type;
short l_whence;
@@ -216,5 +217,6 @@ struct flock64 {
__ARCH_FLOCK64_PAD
#endif
};
+#endif /* HAVE_ARCH_STRUCT_FLOCK */
#endif /* _ASM_GENERIC_FCNTL_H */
diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c
index bb9962b..59ddb00 100644
--- a/kernel/watch_queue.c
+++ b/kernel/watch_queue.c
@@ -454,6 +454,33 @@ void init_watch(struct watch *watch, struct watch_queue *wqueue)
rcu_assign_pointer(watch->queue, wqueue);
}
+static int add_one_watch(struct watch *watch, struct watch_list *wlist, struct watch_queue *wqueue)
+{
+ const struct cred *cred;
+ struct watch *w;
+
+ hlist_for_each_entry(w, &wlist->watchers, list_node) {
+ struct watch_queue *wq = rcu_access_pointer(w->queue);
+ if (wqueue == wq && watch->id == w->id)
+ return -EBUSY;
+ }
+
+ cred = current_cred();
+ if (atomic_inc_return(&cred->user->nr_watches) > task_rlimit(current, RLIMIT_NOFILE)) {
+ atomic_dec(&cred->user->nr_watches);
+ return -EAGAIN;
+ }
+
+ watch->cred = get_cred(cred);
+ rcu_assign_pointer(watch->watch_list, wlist);
+
+ kref_get(&wqueue->usage);
+ kref_get(&watch->usage);
+ hlist_add_head(&watch->queue_node, &wqueue->watches);
+ hlist_add_head_rcu(&watch->list_node, &wlist->watchers);
+ return 0;
+}
+
/**
* add_watch_to_object - Add a watch on an object to a watch list
* @watch: The watch to add
@@ -468,34 +495,21 @@ void init_watch(struct watch *watch, struct watch_queue *wqueue)
*/
int add_watch_to_object(struct watch *watch, struct watch_list *wlist)
{
- struct watch_queue *wqueue = rcu_access_pointer(watch->queue);
- struct watch *w;
+ struct watch_queue *wqueue;
+ int ret = -ENOENT;
- hlist_for_each_entry(w, &wlist->watchers, list_node) {
- struct watch_queue *wq = rcu_access_pointer(w->queue);
- if (wqueue == wq && watch->id == w->id)
- return -EBUSY;
- }
+ rcu_read_lock();
- watch->cred = get_current_cred();
- rcu_assign_pointer(watch->watch_list, wlist);
-
- if (atomic_inc_return(&watch->cred->user->nr_watches) >
- task_rlimit(current, RLIMIT_NOFILE)) {
- atomic_dec(&watch->cred->user->nr_watches);
- put_cred(watch->cred);
- return -EAGAIN;
- }
-
+ wqueue = rcu_access_pointer(watch->queue);
if (lock_wqueue(wqueue)) {
- kref_get(&wqueue->usage);
- kref_get(&watch->usage);
- hlist_add_head(&watch->queue_node, &wqueue->watches);
+ spin_lock(&wlist->lock);
+ ret = add_one_watch(watch, wlist, wqueue);
+ spin_unlock(&wlist->lock);
unlock_wqueue(wqueue);
}
- hlist_add_head(&watch->list_node, &wlist->watchers);
- return 0;
+ rcu_read_unlock();
+ return ret;
}
EXPORT_SYMBOL(add_watch_to_object);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 1ea50f6..aa8a82b 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -5001,7 +5001,10 @@ static void unbind_workers(int cpu)
for_each_pool_worker(worker, pool) {
kthread_set_per_cpu(worker->task, -1);
- WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, wq_unbound_cpumask) < 0);
+ if (cpumask_intersects(wq_unbound_cpumask, cpu_active_mask))
+ WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, wq_unbound_cpumask) < 0);
+ else
+ WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_possible_mask) < 0);
}
mutex_unlock(&wq_pool_attach_mutex);
diff --git a/mm/gup.c b/mm/gup.c
index 5512644..e2a39e3 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -87,7 +87,8 @@ static inline struct folio *try_get_folio(struct page *page, int refs)
* belongs to this folio.
*/
if (unlikely(page_folio(page) != folio)) {
- folio_put_refs(folio, refs);
+ if (!put_devmap_managed_page_refs(&folio->page, refs))
+ folio_put_refs(folio, refs);
goto retry;
}
@@ -176,7 +177,8 @@ static void gup_put_folio(struct folio *folio, int refs, unsigned int flags)
refs *= GUP_PIN_COUNTING_BIAS;
}
- folio_put_refs(folio, refs);
+ if (!put_devmap_managed_page_refs(&folio->page, refs))
+ folio_put_refs(folio, refs);
}
/**
diff --git a/mm/hmm.c b/mm/hmm.c
index 3fd3242..f2aa63b 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -212,14 +212,6 @@ int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
unsigned long end, unsigned long hmm_pfns[], pmd_t pmd);
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-static inline bool hmm_is_device_private_entry(struct hmm_range *range,
- swp_entry_t entry)
-{
- return is_device_private_entry(entry) &&
- pfn_swap_entry_to_page(entry)->pgmap->owner ==
- range->dev_private_owner;
-}
-
static inline unsigned long pte_to_hmm_pfn_flags(struct hmm_range *range,
pte_t pte)
{
@@ -252,10 +244,12 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
swp_entry_t entry = pte_to_swp_entry(pte);
/*
- * Never fault in device private pages, but just report
- * the PFN even if not present.
+ * Don't fault in device private pages owned by the caller,
+ * just report the PFN.
*/
- if (hmm_is_device_private_entry(range, entry)) {
+ if (is_device_private_entry(entry) &&
+ pfn_swap_entry_to_page(entry)->pgmap->owner ==
+ range->dev_private_owner) {
cpu_flags = HMM_PFN_VALID;
if (is_writable_device_private_entry(entry))
cpu_flags |= HMM_PFN_WRITE;
@@ -273,6 +267,9 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
if (!non_swap_entry(entry))
goto fault;
+ if (is_device_private_entry(entry))
+ goto fault;
+
if (is_device_exclusive_entry(entry))
goto fault;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a57e1be..a18c071 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4788,8 +4788,13 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
* sharing with another vma.
*/
;
- } else if (unlikely(is_hugetlb_entry_migration(entry) ||
- is_hugetlb_entry_hwpoisoned(entry))) {
+ } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) {
+ bool uffd_wp = huge_pte_uffd_wp(entry);
+
+ if (!userfaultfd_wp(dst_vma) && uffd_wp)
+ entry = huge_pte_clear_uffd_wp(entry);
+ set_huge_pte_at(dst, addr, dst_pte, entry);
+ } else if (unlikely(is_hugetlb_entry_migration(entry))) {
swp_entry_t swp_entry = pte_to_swp_entry(entry);
bool uffd_wp = huge_pte_uffd_wp(entry);
@@ -5947,6 +5952,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
page = alloc_huge_page(dst_vma, dst_addr, 0);
if (IS_ERR(page)) {
+ put_page(*pagep);
ret = -ENOMEM;
*pagep = NULL;
goto out;
diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index 4b5e5a3..6aff49f 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -603,14 +603,6 @@ static unsigned long kfence_init_pool(void)
addr += 2 * PAGE_SIZE;
}
- /*
- * The pool is live and will never be deallocated from this point on.
- * Remove the pool object from the kmemleak object tree, as it would
- * otherwise overlap with allocations returned by kfence_alloc(), which
- * are registered with kmemleak through the slab post-alloc hook.
- */
- kmemleak_free(__kfence_pool);
-
return 0;
}
@@ -623,8 +615,16 @@ static bool __init kfence_init_pool_early(void)
addr = kfence_init_pool();
- if (!addr)
+ if (!addr) {
+ /*
+ * The pool is live and will never be deallocated from this point on.
+ * Ignore the pool object from the kmemleak phys object tree, as it would
+ * otherwise overlap with allocations returned by kfence_alloc(), which
+ * are registered with kmemleak through the slab post-alloc hook.
+ */
+ kmemleak_ignore_phys(__pa(__kfence_pool));
return true;
+ }
/*
* Only release unprotected pages, and do not try to go back and change
diff --git a/mm/memory.c b/mm/memory.c
index 4cf7d4b..1c6027a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3043,7 +3043,7 @@ static inline void wp_page_reuse(struct vm_fault *vmf)
pte_t entry;
VM_BUG_ON(!(vmf->flags & FAULT_FLAG_WRITE));
- VM_BUG_ON(PageAnon(page) && !PageAnonExclusive(page));
+ VM_BUG_ON(page && PageAnon(page) && !PageAnonExclusive(page));
/*
* Clear the pages cpupid information as the existing
@@ -4369,9 +4369,12 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
return VM_FAULT_OOM;
}
- /* See comment in handle_pte_fault() */
+ /*
+ * See comment in handle_pte_fault() for how this scenario happens, we
+ * need to return NOPAGE so that we drop this page.
+ */
if (pmd_devmap_trans_unstable(vmf->pmd))
- return 0;
+ return VM_FAULT_NOPAGE;
vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
vmf->address, &vmf->ptl);
diff --git a/mm/memremap.c b/mm/memremap.c
index b870a65..745eea0 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -499,7 +499,7 @@ void free_zone_device_page(struct page *page)
}
#ifdef CONFIG_FS_DAX
-bool __put_devmap_managed_page(struct page *page)
+bool __put_devmap_managed_page_refs(struct page *page, int refs)
{
if (page->pgmap->type != MEMORY_DEVICE_FS_DAX)
return false;
@@ -509,9 +509,9 @@ bool __put_devmap_managed_page(struct page *page)
* refcount is 1, then the page is free and the refcount is
* stable because nobody holds a reference on the page.
*/
- if (page_ref_dec_return(page) == 1)
+ if (page_ref_sub_return(page, refs) == 1)
wake_up_var(&page->_refcount);
return true;
}
-EXPORT_SYMBOL(__put_devmap_managed_page);
+EXPORT_SYMBOL(__put_devmap_managed_page_refs);
#endif /* CONFIG_FS_DAX */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e008a3d..b5b14b7 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3968,11 +3968,15 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
* need to be calculated.
*/
if (!order) {
- long fast_free;
+ long usable_free;
+ long reserved;
- fast_free = free_pages;
- fast_free -= __zone_watermark_unusable_free(z, 0, alloc_flags);
- if (fast_free > mark + z->lowmem_reserve[highest_zoneidx])
+ usable_free = free_pages;
+ reserved = __zone_watermark_unusable_free(z, 0, alloc_flags);
+
+ /* reserved may over estimate high-atomic reserves. */
+ usable_free -= min(usable_free, reserved);
+ if (usable_free > mark + z->lowmem_reserve[highest_zoneidx])
return true;
}
diff --git a/mm/secretmem.c b/mm/secretmem.c
index 206ed6b..f06279d 100644
--- a/mm/secretmem.c
+++ b/mm/secretmem.c
@@ -55,22 +55,28 @@ static vm_fault_t secretmem_fault(struct vm_fault *vmf)
gfp_t gfp = vmf->gfp_mask;
unsigned long addr;
struct page *page;
+ vm_fault_t ret;
int err;
if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode))
return vmf_error(-EINVAL);
+ filemap_invalidate_lock_shared(mapping);
+
retry:
page = find_lock_page(mapping, offset);
if (!page) {
page = alloc_page(gfp | __GFP_ZERO);
- if (!page)
- return VM_FAULT_OOM;
+ if (!page) {
+ ret = VM_FAULT_OOM;
+ goto out;
+ }
err = set_direct_map_invalid_noflush(page);
if (err) {
put_page(page);
- return vmf_error(err);
+ ret = vmf_error(err);
+ goto out;
}
__SetPageUptodate(page);
@@ -86,7 +92,8 @@ static vm_fault_t secretmem_fault(struct vm_fault *vmf)
if (err == -EEXIST)
goto retry;
- return vmf_error(err);
+ ret = vmf_error(err);
+ goto out;
}
addr = (unsigned long)page_address(page);
@@ -94,7 +101,11 @@ static vm_fault_t secretmem_fault(struct vm_fault *vmf)
}
vmf->page = page;
- return VM_FAULT_LOCKED;
+ ret = VM_FAULT_LOCKED;
+
+out:
+ filemap_invalidate_unlock_shared(mapping);
+ return ret;
}
static const struct vm_operations_struct secretmem_vm_ops = {
@@ -162,12 +173,20 @@ static int secretmem_setattr(struct user_namespace *mnt_userns,
struct dentry *dentry, struct iattr *iattr)
{
struct inode *inode = d_inode(dentry);
+ struct address_space *mapping = inode->i_mapping;
unsigned int ia_valid = iattr->ia_valid;
+ int ret;
+
+ filemap_invalidate_lock(mapping);
if ((ia_valid & ATTR_SIZE) && inode->i_size)
- return -EINVAL;
+ ret = -EINVAL;
+ else
+ ret = simple_setattr(mnt_userns, dentry, iattr);
- return simple_setattr(mnt_userns, dentry, iattr);
+ filemap_invalidate_unlock(mapping);
+
+ return ret;
}
static const struct inode_operations secretmem_iops = {
diff --git a/mm/shmem.c b/mm/shmem.c
index a6f5653..b7f2d4a 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3392,7 +3392,7 @@ static int shmem_parse_one(struct fs_context *fc, struct fs_parameter *param)
break;
case Opt_nr_blocks:
ctx->blocks = memparse(param->string, &rest);
- if (*rest)
+ if (*rest || ctx->blocks > S64_MAX)
goto bad_value;
ctx->seen |= SHMEM_SEEN_BLOCKS;
break;
@@ -3514,10 +3514,7 @@ static int shmem_reconfigure(struct fs_context *fc)
raw_spin_lock(&sbinfo->stat_lock);
inodes = sbinfo->max_inodes - sbinfo->free_inodes;
- if (ctx->blocks > S64_MAX) {
- err = "Number of blocks too large";
- goto out;
- }
+
if ((ctx->seen & SHMEM_SEEN_BLOCKS) && ctx->blocks) {
if (!sbinfo->max_blocks) {
err = "Cannot retroactively limit size";
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 1739e8c..c170216 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -4973,6 +4973,9 @@ int hci_suspend_sync(struct hci_dev *hdev)
return err;
}
+ /* Update event mask so only the allowed event can wakeup the host */
+ hci_set_event_mask_sync(hdev);
+
/* Only configure accept list if disconnect succeeded and wake
* isn't being prevented.
*/
@@ -4984,9 +4987,6 @@ int hci_suspend_sync(struct hci_dev *hdev)
/* Unpause to take care of updating scanning params */
hdev->scanning_paused = false;
- /* Update event mask so only the allowed event can wakeup the host */
- hci_set_event_mask_sync(hdev);
-
/* Enable event filter for paired devices */
hci_update_event_filter_sync(hdev);
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index ae78490..5266866 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -111,7 +111,8 @@ static struct l2cap_chan *__l2cap_get_chan_by_scid(struct l2cap_conn *conn,
}
/* Find channel with given SCID.
- * Returns locked channel. */
+ * Returns a reference locked channel.
+ */
static struct l2cap_chan *l2cap_get_chan_by_scid(struct l2cap_conn *conn,
u16 cid)
{
@@ -119,15 +120,19 @@ static struct l2cap_chan *l2cap_get_chan_by_scid(struct l2cap_conn *conn,
mutex_lock(&conn->chan_lock);
c = __l2cap_get_chan_by_scid(conn, cid);
- if (c)
- l2cap_chan_lock(c);
+ if (c) {
+ /* Only lock if chan reference is not 0 */
+ c = l2cap_chan_hold_unless_zero(c);
+ if (c)
+ l2cap_chan_lock(c);
+ }
mutex_unlock(&conn->chan_lock);
return c;
}
/* Find channel with given DCID.
- * Returns locked channel.
+ * Returns a reference locked channel.
*/
static struct l2cap_chan *l2cap_get_chan_by_dcid(struct l2cap_conn *conn,
u16 cid)
@@ -136,8 +141,12 @@ static struct l2cap_chan *l2cap_get_chan_by_dcid(struct l2cap_conn *conn,
mutex_lock(&conn->chan_lock);
c = __l2cap_get_chan_by_dcid(conn, cid);
- if (c)
- l2cap_chan_lock(c);
+ if (c) {
+ /* Only lock if chan reference is not 0 */
+ c = l2cap_chan_hold_unless_zero(c);
+ if (c)
+ l2cap_chan_lock(c);
+ }
mutex_unlock(&conn->chan_lock);
return c;
@@ -162,8 +171,12 @@ static struct l2cap_chan *l2cap_get_chan_by_ident(struct l2cap_conn *conn,
mutex_lock(&conn->chan_lock);
c = __l2cap_get_chan_by_ident(conn, ident);
- if (c)
- l2cap_chan_lock(c);
+ if (c) {
+ /* Only lock if chan reference is not 0 */
+ c = l2cap_chan_hold_unless_zero(c);
+ if (c)
+ l2cap_chan_lock(c);
+ }
mutex_unlock(&conn->chan_lock);
return c;
@@ -497,6 +510,16 @@ void l2cap_chan_hold(struct l2cap_chan *c)
kref_get(&c->kref);
}
+struct l2cap_chan *l2cap_chan_hold_unless_zero(struct l2cap_chan *c)
+{
+ BT_DBG("chan %p orig refcnt %u", c, kref_read(&c->kref));
+
+ if (!kref_get_unless_zero(&c->kref))
+ return NULL;
+
+ return c;
+}
+
void l2cap_chan_put(struct l2cap_chan *c)
{
BT_DBG("chan %p orig refcnt %u", c, kref_read(&c->kref));
@@ -1968,7 +1991,10 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm,
src_match = !bacmp(&c->src, src);
dst_match = !bacmp(&c->dst, dst);
if (src_match && dst_match) {
- l2cap_chan_hold(c);
+ c = l2cap_chan_hold_unless_zero(c);
+ if (!c)
+ continue;
+
read_unlock(&chan_list_lock);
return c;
}
@@ -1983,7 +2009,7 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm,
}
if (c1)
- l2cap_chan_hold(c1);
+ c1 = l2cap_chan_hold_unless_zero(c1);
read_unlock(&chan_list_lock);
@@ -4463,6 +4489,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn,
unlock:
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
return err;
}
@@ -4577,6 +4604,7 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn,
done:
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
return err;
}
@@ -5304,6 +5332,7 @@ static inline int l2cap_move_channel_req(struct l2cap_conn *conn,
l2cap_send_move_chan_rsp(chan, result);
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
return 0;
}
@@ -5396,6 +5425,7 @@ static void l2cap_move_continue(struct l2cap_conn *conn, u16 icid, u16 result)
}
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
}
static void l2cap_move_fail(struct l2cap_conn *conn, u8 ident, u16 icid,
@@ -5425,6 +5455,7 @@ static void l2cap_move_fail(struct l2cap_conn *conn, u8 ident, u16 icid,
l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED);
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
}
static int l2cap_move_channel_rsp(struct l2cap_conn *conn,
@@ -5488,6 +5519,7 @@ static int l2cap_move_channel_confirm(struct l2cap_conn *conn,
l2cap_send_move_chan_cfm_rsp(conn, cmd->ident, icid);
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
return 0;
}
@@ -5523,6 +5555,7 @@ static inline int l2cap_move_channel_confirm_rsp(struct l2cap_conn *conn,
}
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
return 0;
}
@@ -5895,12 +5928,11 @@ static inline int l2cap_le_credits(struct l2cap_conn *conn,
if (credits > max_credits) {
BT_ERR("LE credits overflow");
l2cap_send_disconn_req(chan, ECONNRESET);
- l2cap_chan_unlock(chan);
/* Return 0 so that we don't trigger an unnecessary
* command reject packet.
*/
- return 0;
+ goto unlock;
}
chan->tx_credits += credits;
@@ -5911,7 +5943,9 @@ static inline int l2cap_le_credits(struct l2cap_conn *conn,
if (chan->tx_credits)
chan->ops->resume(chan);
+unlock:
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
return 0;
}
@@ -7597,6 +7631,7 @@ static void l2cap_data_channel(struct l2cap_conn *conn, u16 cid,
done:
l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
}
static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm,
@@ -8085,7 +8120,7 @@ static struct l2cap_chan *l2cap_global_fixed_chan(struct l2cap_chan *c,
if (src_type != c->src_type)
continue;
- l2cap_chan_hold(c);
+ c = l2cap_chan_hold_unless_zero(c);
read_unlock(&chan_list_lock);
return c;
}
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index ae758ab..2f91a8c 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4723,7 +4723,6 @@ static int __add_adv_patterns_monitor(struct sock *sk, struct hci_dev *hdev,
else
status = MGMT_STATUS_FAILED;
- mgmt_pending_remove(cmd);
goto unlock;
}
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index bb01776..c96509c 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -589,9 +589,13 @@ static int br_fill_ifinfo(struct sk_buff *skb,
}
done:
+ if (af) {
+ if (nlmsg_get_pos(skb) - (void *)af > nla_attr_size(0))
+ nla_nest_end(skb, af);
+ else
+ nla_nest_cancel(skb, af);
+ }
- if (af)
- nla_nest_end(skb, af);
nlmsg_end(skb, nlh);
return 0;
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 251e666..748be72 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -47,7 +47,7 @@ enum caif_states {
struct caifsock {
struct sock sk; /* must be first member */
struct cflayer layer;
- u32 flow_state;
+ unsigned long flow_state;
struct caif_connect_request conn_req;
struct mutex readlock;
struct dentry *debugfs_socket_dir;
@@ -56,38 +56,32 @@ struct caifsock {
static int rx_flow_is_on(struct caifsock *cf_sk)
{
- return test_bit(RX_FLOW_ON_BIT,
- (void *) &cf_sk->flow_state);
+ return test_bit(RX_FLOW_ON_BIT, &cf_sk->flow_state);
}
static int tx_flow_is_on(struct caifsock *cf_sk)
{
- return test_bit(TX_FLOW_ON_BIT,
- (void *) &cf_sk->flow_state);
+ return test_bit(TX_FLOW_ON_BIT, &cf_sk->flow_state);
}
static void set_rx_flow_off(struct caifsock *cf_sk)
{
- clear_bit(RX_FLOW_ON_BIT,
- (void *) &cf_sk->flow_state);
+ clear_bit(RX_FLOW_ON_BIT, &cf_sk->flow_state);
}
static void set_rx_flow_on(struct caifsock *cf_sk)
{
- set_bit(RX_FLOW_ON_BIT,
- (void *) &cf_sk->flow_state);
+ set_bit(RX_FLOW_ON_BIT, &cf_sk->flow_state);
}
static void set_tx_flow_off(struct caifsock *cf_sk)
{
- clear_bit(TX_FLOW_ON_BIT,
- (void *) &cf_sk->flow_state);
+ clear_bit(TX_FLOW_ON_BIT, &cf_sk->flow_state);
}
static void set_tx_flow_on(struct caifsock *cf_sk)
{
- set_bit(TX_FLOW_ON_BIT,
- (void *) &cf_sk->flow_state);
+ set_bit(TX_FLOW_ON_BIT, &cf_sk->flow_state);
}
static void caif_read_lock(struct sock *sk)
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index dc92a67..7d542eb 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -480,8 +480,8 @@ static struct sock *dn_alloc_sock(struct net *net, struct socket *sock, gfp_t gf
sk->sk_family = PF_DECnet;
sk->sk_protocol = 0;
sk->sk_allocation = gfp;
- sk->sk_sndbuf = sysctl_decnet_wmem[1];
- sk->sk_rcvbuf = sysctl_decnet_rmem[1];
+ sk->sk_sndbuf = READ_ONCE(sysctl_decnet_wmem[1]);
+ sk->sk_rcvbuf = READ_ONCE(sysctl_decnet_rmem[1]);
/* Initialization of DECnet Session Control Port */
scp = DN_SK(sk);
diff --git a/net/dsa/switch.c b/net/dsa/switch.c
index 2b56218..4dfd68c 100644
--- a/net/dsa/switch.c
+++ b/net/dsa/switch.c
@@ -344,6 +344,7 @@ static int dsa_switch_do_lag_fdb_add(struct dsa_switch *ds, struct dsa_lag *lag,
ether_addr_copy(a->addr, addr);
a->vid = vid;
+ a->db = db;
refcount_set(&a->refcount, 1);
list_add_tail(&a->list, &lag->fdbs);
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 46e8a51..452ff17 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1042,6 +1042,7 @@ fib_find_matching_alias(struct net *net, const struct fib_rt_info *fri)
void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri)
{
+ u8 fib_notify_on_flag_change;
struct fib_alias *fa_match;
struct sk_buff *skb;
int err;
@@ -1063,14 +1064,16 @@ void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri)
WRITE_ONCE(fa_match->offload, fri->offload);
WRITE_ONCE(fa_match->trap, fri->trap);
+ fib_notify_on_flag_change = READ_ONCE(net->ipv4.sysctl_fib_notify_on_flag_change);
+
/* 2 means send notifications only if offload_failed was changed. */
- if (net->ipv4.sysctl_fib_notify_on_flag_change == 2 &&
+ if (fib_notify_on_flag_change == 2 &&
READ_ONCE(fa_match->offload_failed) == fri->offload_failed)
goto out;
WRITE_ONCE(fa_match->offload_failed, fri->offload_failed);
- if (!net->ipv4.sysctl_fib_notify_on_flag_change)
+ if (!fib_notify_on_flag_change)
goto out;
skb = nlmsg_new(fib_nlmsg_size(fa_match->fa_info), GFP_ATOMIC);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 2faaaaf..7668817 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -452,8 +452,8 @@ void tcp_init_sock(struct sock *sk)
icsk->icsk_sync_mss = tcp_sync_mss;
- WRITE_ONCE(sk->sk_sndbuf, sock_net(sk)->ipv4.sysctl_tcp_wmem[1]);
- WRITE_ONCE(sk->sk_rcvbuf, sock_net(sk)->ipv4.sysctl_tcp_rmem[1]);
+ WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]));
+ WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]));
sk_sockets_allocated_inc(sk);
}
@@ -686,7 +686,7 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb,
int size_goal)
{
return skb->len < size_goal &&
- sock_net(sk)->ipv4.sysctl_tcp_autocorking &&
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_autocorking) &&
!tcp_rtx_queue_empty(sk) &&
refcount_read(&sk->sk_wmem_alloc) > skb->truesize &&
tcp_skb_can_collapse_to(skb);
@@ -1724,7 +1724,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val)
if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
cap = sk->sk_rcvbuf >> 1;
else
- cap = sock_net(sk)->ipv4.sysctl_tcp_rmem[2] >> 1;
+ cap = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;
val = min(val, cap);
WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
@@ -4459,9 +4459,18 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
return SKB_DROP_REASON_TCP_MD5UNEXPECTED;
}
- /* check the signature */
- genhash = tp->af_specific->calc_md5_hash(newhash, hash_expected,
- NULL, skb);
+ /* Check the signature.
+ * To support dual stack listeners, we need to handle
+ * IPv4-mapped case.
+ */
+ if (family == AF_INET)
+ genhash = tcp_v4_md5_hash_skb(newhash,
+ hash_expected,
+ NULL, skb);
+ else
+ genhash = tp->af_specific->calc_md5_hash(newhash,
+ hash_expected,
+ NULL, skb);
if (genhash || memcmp(hash_location, newhash, 16) != 0) {
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 07dbcba..b163799 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -426,7 +426,7 @@ static void tcp_sndbuf_expand(struct sock *sk)
if (sk->sk_sndbuf < sndmem)
WRITE_ONCE(sk->sk_sndbuf,
- min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]));
+ min(sndmem, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[2])));
}
/* 2. Tuning advertised window (window_clamp, rcv_ssthresh)
@@ -461,7 +461,7 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb,
struct tcp_sock *tp = tcp_sk(sk);
/* Optimize this! */
int truesize = tcp_win_from_space(sk, skbtruesize) >> 1;
- int window = tcp_win_from_space(sk, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;
+ int window = tcp_win_from_space(sk, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])) >> 1;
while (tp->rcv_ssthresh <= window) {
if (truesize <= skb->len)
@@ -534,7 +534,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb,
*/
static void tcp_init_buffer_space(struct sock *sk)
{
- int tcp_app_win = sock_net(sk)->ipv4.sysctl_tcp_app_win;
+ int tcp_app_win = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_app_win);
struct tcp_sock *tp = tcp_sk(sk);
int maxwin;
@@ -574,16 +574,17 @@ static void tcp_clamp_window(struct sock *sk)
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
struct net *net = sock_net(sk);
+ int rmem2;
icsk->icsk_ack.quick = 0;
+ rmem2 = READ_ONCE(net->ipv4.sysctl_tcp_rmem[2]);
- if (sk->sk_rcvbuf < net->ipv4.sysctl_tcp_rmem[2] &&
+ if (sk->sk_rcvbuf < rmem2 &&
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
!tcp_under_memory_pressure(sk) &&
sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) {
WRITE_ONCE(sk->sk_rcvbuf,
- min(atomic_read(&sk->sk_rmem_alloc),
- net->ipv4.sysctl_tcp_rmem[2]));
+ min(atomic_read(&sk->sk_rmem_alloc), rmem2));
}
if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss);
@@ -724,7 +725,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
* <prev RTT . ><current RTT .. ><next RTT .... >
*/
- if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf &&
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
int rcvmem, rcvbuf;
u64 rcvwin, grow;
@@ -745,7 +746,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
do_div(rcvwin, tp->advmss);
rcvbuf = min_t(u64, rcvwin * rcvmem,
- sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
if (rcvbuf > sk->sk_rcvbuf) {
WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
@@ -910,9 +911,9 @@ static void tcp_update_pacing_rate(struct sock *sk)
* end of slow start and should slow down.
*/
if (tcp_snd_cwnd(tp) < tp->snd_ssthresh / 2)
- rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ss_ratio;
+ rate *= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pacing_ss_ratio);
else
- rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ca_ratio;
+ rate *= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pacing_ca_ratio);
rate *= max(tcp_snd_cwnd(tp), tp->packets_out);
@@ -2175,7 +2176,7 @@ void tcp_enter_loss(struct sock *sk)
* loss recovery is underway except recurring timeout(s) on
* the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing
*/
- tp->frto = net->ipv4.sysctl_tcp_frto &&
+ tp->frto = READ_ONCE(net->ipv4.sysctl_tcp_frto) &&
(new_recovery || icsk->icsk_retransmits) &&
!inet_csk(sk)->icsk_mtup.probe_size;
}
@@ -3058,7 +3059,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us, const int flag)
{
- u32 wlen = sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen * HZ;
+ u32 wlen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen) * HZ;
struct tcp_sock *tp = tcp_sk(sk);
if ((flag & FLAG_ACK_MAYBE_DELAYED) && rtt_us > tcp_min_rtt(tp)) {
@@ -3581,7 +3582,8 @@ static bool __tcp_oow_rate_limited(struct net *net, int mib_idx,
if (*last_oow_ack_time) {
s32 elapsed = (s32)(tcp_jiffies32 - *last_oow_ack_time);
- if (0 <= elapsed && elapsed < net->ipv4.sysctl_tcp_invalid_ratelimit) {
+ if (0 <= elapsed &&
+ elapsed < READ_ONCE(net->ipv4.sysctl_tcp_invalid_ratelimit)) {
NET_INC_STATS(net, mib_idx);
return true; /* rate-limited: don't send yet! */
}
@@ -3629,7 +3631,7 @@ static void tcp_send_challenge_ack(struct sock *sk)
/* Then check host-wide RFC 5961 rate limit. */
now = jiffies / HZ;
if (now != challenge_timestamp) {
- u32 ack_limit = net->ipv4.sysctl_tcp_challenge_ack_limit;
+ u32 ack_limit = READ_ONCE(net->ipv4.sysctl_tcp_challenge_ack_limit);
u32 half = (ack_limit + 1) >> 1;
challenge_timestamp = now;
@@ -4426,7 +4428,7 @@ static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq)
{
struct tcp_sock *tp = tcp_sk(sk);
- if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
+ if (tcp_is_sack(tp) && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_dsack)) {
int mib_idx;
if (before(seq, tp->rcv_nxt))
@@ -4473,7 +4475,7 @@ static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb)
NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);
- if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
+ if (tcp_is_sack(tp) && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_dsack)) {
u32 end_seq = TCP_SKB_CB(skb)->end_seq;
tcp_rcv_spurious_retrans(sk, skb);
@@ -5519,7 +5521,7 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible)
}
if (!tcp_is_sack(tp) ||
- tp->compressed_ack >= sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr)
+ tp->compressed_ack >= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr))
goto send_now;
if (tp->compressed_ack_rcv_nxt != tp->rcv_nxt) {
@@ -5540,11 +5542,12 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible)
if (tp->srtt_us && tp->srtt_us < rtt)
rtt = tp->srtt_us;
- delay = min_t(unsigned long, sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns,
+ delay = min_t(unsigned long,
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns),
rtt * (NSEC_PER_USEC >> 3)/20);
sock_hold(sk);
hrtimer_start_range_ns(&tp->compressed_ack_timer, ns_to_ktime(delay),
- sock_net(sk)->ipv4.sysctl_tcp_comp_sack_slack_ns,
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_slack_ns),
HRTIMER_MODE_REL_PINNED_SOFT);
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d16e6e4..586c102 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1006,7 +1006,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
if (skb) {
__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
- tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
+ tos = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ?
(tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
(inet_sk(sk)->tos & INET_ECN_MASK) :
inet_sk(sk)->tos;
@@ -1526,7 +1526,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
/* Set ToS of the new socket based upon the value of incoming SYN.
* ECT bits are set later in tcp_init_transfer().
*/
- if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos))
newinet->tos = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;
if (!dst) {
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index a501150..d58e672 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -329,7 +329,7 @@ void tcp_update_metrics(struct sock *sk)
int m;
sk_dst_confirm(sk);
- if (net->ipv4.sysctl_tcp_nometrics_save || !dst)
+ if (READ_ONCE(net->ipv4.sysctl_tcp_nometrics_save) || !dst)
return;
rcu_read_lock();
@@ -385,7 +385,7 @@ void tcp_update_metrics(struct sock *sk)
if (tcp_in_initial_slowstart(tp)) {
/* Slow start still did not finish. */
- if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save &&
+ if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) &&
!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) {
val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
if (val && (tcp_snd_cwnd(tp) >> 1) > val)
@@ -401,7 +401,7 @@ void tcp_update_metrics(struct sock *sk)
} else if (!tcp_in_slow_start(tp) &&
icsk->icsk_ca_state == TCP_CA_Open) {
/* Cong. avoidance phase, cwnd is reliable. */
- if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save &&
+ if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) &&
!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH))
tcp_metric_set(tm, TCP_METRIC_SSTHRESH,
max(tcp_snd_cwnd(tp) >> 1, tp->snd_ssthresh));
@@ -418,7 +418,7 @@ void tcp_update_metrics(struct sock *sk)
tcp_metric_set(tm, TCP_METRIC_CWND,
(val + tp->snd_ssthresh) >> 1);
}
- if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save &&
+ if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) &&
!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) {
val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
if (val && tp->snd_ssthresh > val)
@@ -463,7 +463,7 @@ void tcp_init_metrics(struct sock *sk)
if (tcp_metric_locked(tm, TCP_METRIC_CWND))
tp->snd_cwnd_clamp = tcp_metric_get(tm, TCP_METRIC_CWND);
- val = net->ipv4.sysctl_tcp_no_ssthresh_metrics_save ?
+ val = READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) ?
0 : tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
if (val) {
tp->snd_ssthresh = val;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index c38e07b..4c376b6 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -167,16 +167,13 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
if (tcp_packets_in_flight(tp) == 0)
tcp_ca_event(sk, CA_EVENT_TX_START);
- /* If this is the first data packet sent in response to the
- * previous received data,
- * and it is a reply for ato after last received packet,
- * increase pingpong count.
- */
- if (before(tp->lsndtime, icsk->icsk_ack.lrcvtime) &&
- (u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
- inet_csk_inc_pingpong_cnt(sk);
-
tp->lsndtime = now;
+
+ /* If it is a reply for ato after last received
+ * packet, enter pingpong mode.
+ */
+ if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
+ inet_csk_enter_pingpong_mode(sk);
}
/* Account for an ACK we sent. */
@@ -230,7 +227,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
* which we interpret as a sign the remote TCP is not
* misinterpreting the window field as a signed quantity.
*/
- if (sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows))
(*rcv_wnd) = min(space, MAX_TCP_WINDOW);
else
(*rcv_wnd) = min_t(u32, space, U16_MAX);
@@ -241,7 +238,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
*rcv_wscale = 0;
if (wscale_ok) {
/* Set window scaling on max possible window */
- space = max_t(u32, space, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+ space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
space = max_t(u32, space, sysctl_rmem_max);
space = min_t(u32, space, *window_clamp);
*rcv_wscale = clamp_t(int, ilog2(space) - 15,
@@ -285,7 +282,7 @@ static u16 tcp_select_window(struct sock *sk)
* scaled window.
*/
if (!tp->rx_opt.rcv_wscale &&
- sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows))
new_win = min(new_win, MAX_TCP_WINDOW);
else
new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale));
@@ -1976,7 +1973,7 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,
bytes = sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift);
- r = tcp_min_rtt(tcp_sk(sk)) >> sock_net(sk)->ipv4.sysctl_tcp_tso_rtt_log;
+ r = tcp_min_rtt(tcp_sk(sk)) >> READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tso_rtt_log);
if (r < BITS_PER_TYPE(sk->sk_gso_max_size))
bytes += sk->sk_gso_max_size >> r;
@@ -1995,7 +1992,7 @@ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now)
min_tso = ca_ops->min_tso_segs ?
ca_ops->min_tso_segs(sk) :
- sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs;
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
tso_segs = tcp_tso_autosize(sk, mss_now, min_tso);
return min_t(u32, tso_segs, sk->sk_gso_max_segs);
@@ -2507,7 +2504,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift));
if (sk->sk_pacing_status == SK_PACING_NONE)
limit = min_t(unsigned long, limit,
- sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes);
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes));
limit <<= factor;
if (static_branch_unlikely(&tcp_tx_delay_enabled) &&
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 7f695c3..87c699d 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1522,7 +1522,6 @@ static void mld_query_work(struct work_struct *work)
if (++cnt >= MLD_MAX_QUEUE) {
rework = true;
- schedule_delayed_work(&idev->mc_query_work, 0);
break;
}
}
@@ -1533,8 +1532,10 @@ static void mld_query_work(struct work_struct *work)
__mld_query_work(skb);
mutex_unlock(&idev->mc_lock);
- if (!rework)
- in6_dev_put(idev);
+ if (rework && queue_delayed_work(mld_wq, &idev->mc_query_work, 0))
+ return;
+
+ in6_dev_put(idev);
}
/* called with rcu_read_lock() */
@@ -1624,7 +1625,6 @@ static void mld_report_work(struct work_struct *work)
if (++cnt >= MLD_MAX_QUEUE) {
rework = true;
- schedule_delayed_work(&idev->mc_report_work, 0);
break;
}
}
@@ -1635,8 +1635,10 @@ static void mld_report_work(struct work_struct *work)
__mld_report_work(skb);
mutex_unlock(&idev->mc_lock);
- if (!rework)
- in6_dev_put(idev);
+ if (rework && queue_delayed_work(mld_wq, &idev->mc_report_work, 0))
+ return;
+
+ in6_dev_put(idev);
}
static bool is_in(struct ifmcaddr6 *pmc, struct ip6_sf_list *psf, int type,
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index ecf3a55..8c6c2d8 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -22,6 +22,11 @@
#include <linux/proc_fs.h>
#include <net/ping.h>
+static void ping_v6_destroy(struct sock *sk)
+{
+ inet6_destroy_sock(sk);
+}
+
/* Compatibility glue so we can support IPv6 when it's compiled as a module */
static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len,
int *addr_len)
@@ -181,6 +186,7 @@ struct proto pingv6_prot = {
.owner = THIS_MODULE,
.init = ping_init_sock,
.close = ping_close,
+ .destroy = ping_v6_destroy,
.connect = ip6_datagram_connect_v6_only,
.disconnect = __udp_disconnect,
.setsockopt = ipv6_setsockopt,
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 9d3ede2..be09941 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -546,7 +546,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
if (np->repflow && ireq->pktopts)
fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
- tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
+ tclass = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ?
(tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
(np->tclass & INET_ECN_MASK) :
np->tclass;
@@ -1314,7 +1314,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
/* Set ToS of the new socket based upon the value of incoming SYN.
* ECT bits are set later in tcp_init_transfer().
*/
- if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos))
newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;
/* Clone native IPv6 options from listening socket (if any)
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 15a73b7..1a9ada4 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -377,9 +377,8 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
bool cancel_scan;
struct cfg80211_nan_func *func;
- spin_lock_bh(&local->fq.lock);
clear_bit(SDATA_STATE_RUNNING, &sdata->state);
- spin_unlock_bh(&local->fq.lock);
+ synchronize_rcu(); /* flush _ieee80211_wake_txqs() */
cancel_scan = rcu_access_pointer(local->scan_sdata) == sdata;
if (cancel_scan)
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index bd8f0f4..30d2890 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -1271,7 +1271,7 @@ static void mptcp_set_rwin(struct tcp_sock *tp, struct tcphdr *th)
if (unlikely(th->syn))
new_win = min(new_win, 65535U) << tp->rx_opt.rcv_wscale;
if (!tp->rx_opt.rcv_wscale &&
- sock_net(ssk)->ipv4.sysctl_tcp_workaround_signed_windows)
+ READ_ONCE(sock_net(ssk)->ipv4.sysctl_tcp_workaround_signed_windows))
new_win = min(new_win, MAX_TCP_WINDOW);
else
new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale));
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 21a3ed6..7e1518b 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1908,7 +1908,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
if (msk->rcvq_space.copied <= msk->rcvq_space.space)
goto new_measure;
- if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf &&
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
int rcvmem, rcvbuf;
u64 rcvwin, grow;
@@ -1926,7 +1926,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
do_div(rcvwin, advmss);
rcvbuf = min_t(u64, rcvwin * rcvmem,
- sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
if (rcvbuf > sk->sk_rcvbuf) {
u32 window_clamp;
@@ -2669,8 +2669,8 @@ static int mptcp_init_sock(struct sock *sk)
mptcp_ca_reset(sk);
sk_sockets_allocated_inc(sk);
- sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1];
- sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1];
+ sk->sk_rcvbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]);
+ sk->sk_sndbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]);
return 0;
}
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 63e8892..af28f3b 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1533,7 +1533,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
mptcp_sock_graft(ssk, sk->sk_socket);
iput(SOCK_INODE(sf));
WRITE_ONCE(msk->allow_infinite_fallback, false);
- return err;
+ return 0;
failed_unlink:
list_del(&subflow->node);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 646d5fd..9f976b1 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3340,6 +3340,8 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain)
if (err < 0)
return err;
}
+
+ cond_resched();
}
return 0;
@@ -9367,9 +9369,13 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx,
break;
}
}
+
+ cond_resched();
}
list_for_each_entry(set, &ctx->table->sets, list) {
+ cond_resched();
+
if (!nft_is_active_next(ctx->net, set))
continue;
if (!(set->flags & NFT_SET_MAP) ||
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index a364f8e..87a9009 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -843,11 +843,16 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum)
}
static int
-nfqnl_mangle(void *data, int data_len, struct nf_queue_entry *e, int diff)
+nfqnl_mangle(void *data, unsigned int data_len, struct nf_queue_entry *e, int diff)
{
struct sk_buff *nskb;
if (diff < 0) {
+ unsigned int min_len = skb_transport_offset(e->skb);
+
+ if (data_len < min_len)
+ return -EINVAL;
+
if (pskb_trim(e->skb, data_len))
return -ENOMEM;
} else if (diff > 0) {
diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c
index 15e4b76..da29e92 100644
--- a/net/netfilter/nft_queue.c
+++ b/net/netfilter/nft_queue.c
@@ -68,6 +68,31 @@ static void nft_queue_sreg_eval(const struct nft_expr *expr,
regs->verdict.code = ret;
}
+static int nft_queue_validate(const struct nft_ctx *ctx,
+ const struct nft_expr *expr,
+ const struct nft_data **data)
+{
+ static const unsigned int supported_hooks = ((1 << NF_INET_PRE_ROUTING) |
+ (1 << NF_INET_LOCAL_IN) |
+ (1 << NF_INET_FORWARD) |
+ (1 << NF_INET_LOCAL_OUT) |
+ (1 << NF_INET_POST_ROUTING));
+
+ switch (ctx->family) {
+ case NFPROTO_IPV4:
+ case NFPROTO_IPV6:
+ case NFPROTO_INET:
+ case NFPROTO_BRIDGE:
+ break;
+ case NFPROTO_NETDEV: /* lacks okfn */
+ fallthrough;
+ default:
+ return -EOPNOTSUPP;
+ }
+
+ return nft_chain_validate_hooks(ctx->chain, supported_hooks);
+}
+
static const struct nla_policy nft_queue_policy[NFTA_QUEUE_MAX + 1] = {
[NFTA_QUEUE_NUM] = { .type = NLA_U16 },
[NFTA_QUEUE_TOTAL] = { .type = NLA_U16 },
@@ -164,6 +189,7 @@ static const struct nft_expr_ops nft_queue_ops = {
.eval = nft_queue_eval,
.init = nft_queue_init,
.dump = nft_queue_dump,
+ .validate = nft_queue_validate,
.reduce = NFT_REDUCE_READONLY,
};
@@ -173,6 +199,7 @@ static const struct nft_expr_ops nft_queue_sreg_ops = {
.eval = nft_queue_sreg_eval,
.init = nft_queue_sreg_init,
.dump = nft_queue_sreg_dump,
+ .validate = nft_queue_validate,
.reduce = NFT_REDUCE_READONLY,
};
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index be29da0..3460abc 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -229,9 +229,8 @@ static struct sctp_association *sctp_association_init(
if (!sctp_ulpq_init(&asoc->ulpq, asoc))
goto fail_init;
- if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams,
- 0, gfp))
- goto fail_init;
+ if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams, 0, gfp))
+ goto stream_free;
/* Initialize default path MTU. */
asoc->pathmtu = sp->pathmtu;
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 6dc95dc..ef9fcea 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -137,7 +137,7 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
ret = sctp_stream_alloc_out(stream, outcnt, gfp);
if (ret)
- goto out_err;
+ return ret;
for (i = 0; i < stream->outcnt; i++)
SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN;
@@ -145,22 +145,9 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
handle_in:
sctp_stream_interleave_init(stream);
if (!incnt)
- goto out;
+ return 0;
- ret = sctp_stream_alloc_in(stream, incnt, gfp);
- if (ret)
- goto in_err;
-
- goto out;
-
-in_err:
- sched->free(stream);
- genradix_free(&stream->in);
-out_err:
- genradix_free(&stream->out);
- stream->outcnt = 0;
-out:
- return ret;
+ return sctp_stream_alloc_in(stream, incnt, gfp);
}
int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid)
diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c
index 518b1b9..1ad565e 100644
--- a/net/sctp/stream_sched.c
+++ b/net/sctp/stream_sched.c
@@ -160,7 +160,7 @@ int sctp_sched_set_sched(struct sctp_association *asoc,
if (!SCTP_SO(&asoc->stream, i)->ext)
continue;
- ret = n->init_sid(&asoc->stream, i, GFP_KERNEL);
+ ret = n->init_sid(&asoc->stream, i, GFP_ATOMIC);
if (ret)
goto err;
}
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 43509c7..f1c3b8e 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -517,7 +517,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
timer_setup(&sk->sk_timer, tipc_sk_timeout, 0);
sk->sk_shutdown = 0;
sk->sk_backlog_rcv = tipc_sk_backlog_rcv;
- sk->sk_rcvbuf = sysctl_tipc_rmem[1];
+ sk->sk_rcvbuf = READ_ONCE(sysctl_tipc_rmem[1]);
sk->sk_data_ready = tipc_data_ready;
sk->sk_write_space = tipc_write_space;
sk->sk_destruct = tipc_sock_destruct;
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 879b902..9975df3 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -1376,8 +1376,13 @@ static int tls_device_down(struct net_device *netdev)
* by tls_device_free_ctx. rx_conf and tx_conf stay in TLS_HW.
* Now release the ref taken above.
*/
- if (refcount_dec_and_test(&ctx->refcount))
+ if (refcount_dec_and_test(&ctx->refcount)) {
+ /* sk_destruct ran after tls_device_down took a ref, and
+ * it returned early. Complete the destruction here.
+ */
+ list_del(&ctx->list);
tls_device_free_ctx(ctx);
+ }
}
up_write(&device_offload_lock);
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 00f5227..a77b915 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -302,6 +302,7 @@
#define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* "" Use LFENCE for Spectre variant 2 */
#define X86_FEATURE_RETHUNK (11*32+14) /* "" Use REturn THUNK */
#define X86_FEATURE_UNRET (11*32+15) /* "" AMD BTB untrain return */
+#define X86_FEATURE_USE_IBPB_FW (11*32+16) /* "" Use IBPB during runtime firmware calls */
/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */
diff --git a/tools/include/uapi/asm-generic/fcntl.h b/tools/include/uapi/asm-generic/fcntl.h
index 0197042..1ecdb91 100644
--- a/tools/include/uapi/asm-generic/fcntl.h
+++ b/tools/include/uapi/asm-generic/fcntl.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
#ifndef _ASM_GENERIC_FCNTL_H
#define _ASM_GENERIC_FCNTL_H
@@ -90,7 +91,7 @@
/* a horrid kludge trying to make sure that this will fail on old kernels */
#define O_TMPFILE (__O_TMPFILE | O_DIRECTORY)
-#define O_TMPFILE_MASK (__O_TMPFILE | O_DIRECTORY | O_CREAT)
+#define O_TMPFILE_MASK (__O_TMPFILE | O_DIRECTORY | O_CREAT)
#ifndef O_NDELAY
#define O_NDELAY O_NONBLOCK
@@ -115,11 +116,13 @@
#define F_GETSIG 11 /* for sockets. */
#endif
+#if __BITS_PER_LONG == 32 || defined(__KERNEL__)
#ifndef F_GETLK64
#define F_GETLK64 12 /* using 'struct flock64' */
#define F_SETLK64 13
#define F_SETLKW64 14
#endif
+#endif /* __BITS_PER_LONG == 32 || defined(__KERNEL__) */
#ifndef F_SETOWN_EX
#define F_SETOWN_EX 15
@@ -178,6 +181,10 @@ struct f_owner_ex {
blocking */
#define LOCK_UN 8 /* remove lock */
+/*
+ * LOCK_MAND support has been removed from the kernel. We leave the symbols
+ * here to not break legacy builds, but these should not be used in new code.
+ */
#define LOCK_MAND 32 /* This is a mandatory flock ... */
#define LOCK_READ 64 /* which allows concurrent read operations */
#define LOCK_WRITE 128 /* which allows concurrent write operations */
@@ -185,6 +192,7 @@ struct f_owner_ex {
#define F_LINUX_SPECIFIC_BASE 1024
+#ifndef HAVE_ARCH_STRUCT_FLOCK
struct flock {
short l_type;
short l_whence;
@@ -209,5 +217,6 @@ struct flock64 {
__ARCH_FLOCK64_PAD
#endif
};
+#endif /* HAVE_ARCH_STRUCT_FLOCK */
#endif /* _ASM_GENERIC_FCNTL_H */
diff --git a/tools/perf/scripts/python/arm-cs-trace-disasm.py b/tools/perf/scripts/python/arm-cs-trace-disasm.py
index 5f57d98..4339692 100755
--- a/tools/perf/scripts/python/arm-cs-trace-disasm.py
+++ b/tools/perf/scripts/python/arm-cs-trace-disasm.py
@@ -61,7 +61,7 @@
def get_offset(perf_dict, field):
if field in perf_dict:
- return f"+0x{perf_dict[field]:x}"
+ return "+%#x" % perf_dict[field]
return ""
def get_dso_file_path(dso_name, dso_build_id):
@@ -76,7 +76,7 @@
else:
append = "/elf"
- dso_path = f"{os.environ['PERF_BUILDID_DIR']}/{dso_name}/{dso_build_id}{append}"
+ dso_path = os.environ['PERF_BUILDID_DIR'] + "/" + dso_name + "/" + dso_build_id + append;
# Replace duplicate slash chars to single slash char
dso_path = dso_path.replace('//', '/', 1)
return dso_path
@@ -94,8 +94,8 @@
start_addr = start_addr - dso_start;
stop_addr = stop_addr - dso_start;
disasm = [ options.objdump_name, "-d", "-z",
- f"--start-address=0x{start_addr:x}",
- f"--stop-address=0x{stop_addr:x}" ]
+ "--start-address="+format(start_addr,"#x"),
+ "--stop-address="+format(stop_addr,"#x") ]
disasm += [ dso_fname ]
disasm_output = check_output(disasm).decode('utf-8').split('\n')
disasm_cache[addr_range] = disasm_output
@@ -109,12 +109,14 @@
m = disasm_re.search(line)
if m is None:
continue
- print(f"\t{line}")
+ print("\t" + line)
def print_sample(sample):
- print(f"Sample = {{ cpu: {sample['cpu']:04} addr: 0x{sample['addr']:016x} " \
- f"phys_addr: 0x{sample['phys_addr']:016x} ip: 0x{sample['ip']:016x} " \
- f"pid: {sample['pid']} tid: {sample['tid']} period: {sample['period']} time: {sample['time']} }}")
+ print("Sample = { cpu: %04d addr: 0x%016x phys_addr: 0x%016x ip: 0x%016x " \
+ "pid: %d tid: %d period: %d time: %d }" % \
+ (sample['cpu'], sample['addr'], sample['phys_addr'], \
+ sample['ip'], sample['pid'], sample['tid'], \
+ sample['period'], sample['time']))
def trace_begin():
print('ARM CoreSight Trace Data Assembler Dump')
@@ -131,7 +133,7 @@
cpu = sample["cpu"]
pid = sample["pid"]
tid = sample["tid"]
- return f"{comm:>16} {pid:>5}/{tid:<5} [{cpu:04}] {sec:9}.{ns:09} "
+ return "%16s %5u/%-5u [%04u] %9u.%09u " % (comm, pid, tid, cpu, sec, ns)
# This code is copied from intel-pt-events.py for printing source code
# line and symbols.
@@ -171,7 +173,7 @@
glb_line_number = line_number
glb_source_file_name = source_file_name
- print(f"{start_str}{src_str}")
+ print(start_str, src_str)
def process_event(param_dict):
global cache_size
@@ -188,7 +190,7 @@
symbol = get_optional(param_dict, "symbol")
if (options.verbose == True):
- print(f"Event type: {name}")
+ print("Event type: %s" % name)
print_sample(sample)
# If cannot find dso so cannot dump assembler, bail out
@@ -197,7 +199,7 @@
# Validate dso start and end addresses
if ((dso_start == '[unknown]') or (dso_end == '[unknown]')):
- print(f"Failed to find valid dso map for dso {dso}")
+ print("Failed to find valid dso map for dso %s" % dso)
return
if (name[0:12] == "instructions"):
@@ -244,15 +246,15 @@
# Handle CS_ETM_TRACE_ON packet if start_addr=0 and stop_addr=4
if (start_addr == 0 and stop_addr == 4):
- print(f"CPU{cpu}: CS_ETM_TRACE_ON packet is inserted")
+ print("CPU%d: CS_ETM_TRACE_ON packet is inserted" % cpu)
return
if (start_addr < int(dso_start) or start_addr > int(dso_end)):
- print(f"Start address 0x{start_addr:x} is out of range [ 0x{dso_start:x} .. 0x{dso_end:x} ] for dso {dso}")
+ print("Start address 0x%x is out of range [ 0x%x .. 0x%x ] for dso %s" % (start_addr, int(dso_start), int(dso_end), dso))
return
if (stop_addr < int(dso_start) or stop_addr > int(dso_end)):
- print(f"Stop address 0x{stop_addr:x} is out of range [ 0x{dso_start:x} .. 0x{dso_end:x} ] for dso {dso}")
+ print("Stop address 0x%x is out of range [ 0x%x .. 0x%x ] for dso %s" % (stop_addr, int(dso_start), int(dso_end), dso))
return
if (options.objdump_name != None):
@@ -267,6 +269,6 @@
if path.exists(dso_fname):
print_disam(dso_fname, dso_vm_start, start_addr, stop_addr)
else:
- print(f"Failed to find dso {dso} for address range [ 0x{start_addr:x} .. 0x{stop_addr:x} ]")
+ print("Failed to find dso %s for address range [ 0x%x .. 0x%x ]" % (dso, start_addr, stop_addr))
print_srccode(comm, param_dict, sample, symbol, dso)
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index f8ad581..cdd6463 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -63,20 +63,16 @@ static struct hashmap *bpf_map_hash;
static struct bpf_perf_object *
bpf_perf_object__next(struct bpf_perf_object *prev)
{
- struct bpf_perf_object *next;
+ if (!prev) {
+ if (list_empty(&bpf_objects_list))
+ return NULL;
- if (!prev)
- next = list_first_entry(&bpf_objects_list,
- struct bpf_perf_object,
- list);
- else
- next = list_next_entry(prev, list);
-
- /* Empty list is noticed here so don't need checking on entry. */
- if (&next->list == &bpf_objects_list)
+ return list_first_entry(&bpf_objects_list, struct bpf_perf_object, list);
+ }
+ if (list_is_last(&prev->list, &bpf_objects_list))
return NULL;
- return next;
+ return list_next_entry(prev, list);
}
#define bpf_perf_object__for_each(perf_obj, tmp) \
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index ecd3779..b3be5b1 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -233,6 +233,33 @@ Elf_Scn *elf_section_by_name(Elf *elf, GElf_Ehdr *ep,
return NULL;
}
+static int elf_read_program_header(Elf *elf, u64 vaddr, GElf_Phdr *phdr)
+{
+ size_t i, phdrnum;
+ u64 sz;
+
+ if (elf_getphdrnum(elf, &phdrnum))
+ return -1;
+
+ for (i = 0; i < phdrnum; i++) {
+ if (gelf_getphdr(elf, i, phdr) == NULL)
+ return -1;
+
+ if (phdr->p_type != PT_LOAD)
+ continue;
+
+ sz = max(phdr->p_memsz, phdr->p_filesz);
+ if (!sz)
+ continue;
+
+ if (vaddr >= phdr->p_vaddr && (vaddr < phdr->p_vaddr + sz))
+ return 0;
+ }
+
+ /* Not found any valid program header */
+ return -1;
+}
+
static bool want_demangle(bool is_kernel_sym)
{
return is_kernel_sym ? symbol_conf.demangle_kernel : symbol_conf.demangle;
@@ -1209,6 +1236,7 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
sym.st_value);
used_opd = true;
}
+
/*
* When loading symbols in a data mapping, ABS symbols (which
* has a value of SHN_ABS in its st_shndx) failed at
@@ -1227,6 +1255,17 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
gelf_getshdr(sec, &shdr);
+ /*
+ * If the attribute bit SHF_ALLOC is not set, the section
+ * doesn't occupy memory during process execution.
+ * E.g. ".gnu.warning.*" section is used by linker to generate
+ * warnings when calling deprecated functions, the symbols in
+ * the section aren't loaded to memory during process execution,
+ * so skip them.
+ */
+ if (!(shdr.sh_flags & SHF_ALLOC))
+ continue;
+
secstrs = secstrs_sym;
/*
@@ -1262,11 +1301,20 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
goto out_elf_end;
} else if ((used_opd && runtime_ss->adjust_symbols) ||
(!used_opd && syms_ss->adjust_symbols)) {
+ GElf_Phdr phdr;
+
+ if (elf_read_program_header(syms_ss->elf,
+ (u64)sym.st_value, &phdr)) {
+ pr_warning("%s: failed to find program header for "
+ "symbol: %s st_value: %#" PRIx64 "\n",
+ __func__, elf_name, (u64)sym.st_value);
+ continue;
+ }
pr_debug4("%s: adjusting symbol: st_value: %#" PRIx64 " "
- "sh_addr: %#" PRIx64 " sh_offset: %#" PRIx64 "\n", __func__,
- (u64)sym.st_value, (u64)shdr.sh_addr,
- (u64)shdr.sh_offset);
- sym.st_value -= shdr.sh_addr - shdr.sh_offset;
+ "p_vaddr: %#" PRIx64 " p_offset: %#" PRIx64 "\n",
+ __func__, (u64)sym.st_value, (u64)phdr.p_vaddr,
+ (u64)phdr.p_offset);
+ sym.st_value -= phdr.p_vaddr - phdr.p_offset;
}
demangled = demangle_sym(dso, kmodule, elf_name);
