summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/Kconfig7
-rw-r--r--arch/arm/boot/dts/lan966x.dtsi2
-rw-r--r--arch/arm/include/asm/dma.h2
-rw-r--r--arch/arm/lib/findbit.S16
-rw-r--r--arch/arm/mach-pxa/corgi.c2
-rw-r--r--arch/arm/mach-pxa/hx4700.c2
-rw-r--r--arch/arm/mach-pxa/icontrol.c4
-rw-r--r--arch/arm/mach-pxa/littleton.c2
-rw-r--r--arch/arm/mach-pxa/magician.c2
-rw-r--r--arch/arm/mach-pxa/spitz.c2
-rw-r--r--arch/arm/mach-pxa/z2.c4
-rw-r--r--arch/csky/include/asm/tlb.h15
-rw-r--r--arch/loongarch/Kconfig2
-rw-r--r--arch/loongarch/include/asm/asmmacro.h12
-rw-r--r--arch/loongarch/include/asm/atomic.h37
-rw-r--r--arch/loongarch/include/asm/barrier.h4
-rw-r--r--arch/loongarch/include/asm/cmpxchg.h4
-rw-r--r--arch/loongarch/include/asm/compiler.h15
-rw-r--r--arch/loongarch/include/asm/elf.h2
-rw-r--r--arch/loongarch/include/asm/futex.h11
-rw-r--r--arch/loongarch/include/asm/irqflags.h1
-rw-r--r--arch/loongarch/include/asm/local.h1
-rw-r--r--arch/loongarch/include/asm/loongson.h16
-rw-r--r--arch/loongarch/include/asm/stacktrace.h12
-rw-r--r--arch/loongarch/include/asm/thread_info.h4
-rw-r--r--arch/loongarch/include/asm/tlb.h10
-rw-r--r--arch/loongarch/include/asm/uaccess.h2
-rw-r--r--arch/loongarch/kernel/cacheinfo.c11
-rw-r--r--arch/loongarch/kernel/entry.S4
-rw-r--r--arch/loongarch/kernel/env.c20
-rw-r--r--arch/loongarch/kernel/fpu.S174
-rw-r--r--arch/loongarch/kernel/genex.S12
-rw-r--r--arch/loongarch/kernel/head.S8
-rw-r--r--arch/loongarch/kernel/ptrace.c12
-rw-r--r--arch/loongarch/kernel/reset.c1
-rw-r--r--arch/loongarch/kernel/setup.c2
-rw-r--r--arch/loongarch/kernel/smp.c113
-rw-r--r--arch/loongarch/kernel/switch.S4
-rw-r--r--arch/loongarch/lib/clear_user.S2
-rw-r--r--arch/loongarch/lib/copy_user.S2
-rw-r--r--arch/loongarch/lib/delay.c1
-rw-r--r--arch/loongarch/mm/page.S118
-rw-r--r--arch/loongarch/mm/tlbex.S98
-rw-r--r--arch/powerpc/Kconfig5
-rw-r--r--arch/powerpc/include/asm/tlb.h2
-rw-r--r--arch/powerpc/kernel/Makefile1
-rw-r--r--arch/riscv/Makefile3
-rw-r--r--arch/riscv/boot/dts/canaan/canaan_kd233.dts2
-rw-r--r--arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts2
-rw-r--r--arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts2
-rw-r--r--arch/riscv/boot/dts/canaan/sipeed_maix_go.dts6
-rw-r--r--arch/riscv/boot/dts/canaan/sipeed_maixduino.dts2
-rw-r--r--arch/riscv/kernel/Makefile2
-rw-r--r--arch/riscv/kernel/elf_kexec.c2
-rw-r--r--arch/s390/Kconfig1
-rw-r--r--arch/s390/include/asm/archrandom.h9
-rw-r--r--arch/s390/include/asm/tlb.h3
-rw-r--r--arch/sparc/Kconfig2
-rw-r--r--arch/sparc/include/asm/tlb_64.h2
-rw-r--r--arch/x86/Kconfig9
-rw-r--r--arch/x86/Makefile1
-rw-r--r--arch/x86/events/intel/lbr.c19
-rw-r--r--arch/x86/include/asm/cpufeatures.h1
-rw-r--r--arch/x86/include/asm/nospec-branch.h2
-rw-r--r--arch/x86/include/asm/sev.h7
-rw-r--r--arch/x86/include/asm/tlb.h3
-rw-r--r--arch/x86/include/asm/tlbflush.h1
-rw-r--r--arch/x86/kernel/alternative.c4
-rw-r--r--arch/x86/kernel/cpu/bugs.c15
-rw-r--r--arch/x86/kernel/cpu/mce/inject.c47
-rw-r--r--arch/x86/kernel/cpu/mce/internal.h2
-rw-r--r--arch/x86/kernel/cpu/vmware.c4
-rw-r--r--arch/x86/kernel/sev-shared.c25
-rw-r--r--arch/x86/kernel/sev.c17
-rw-r--r--arch/x86/kvm/x86.c8
-rw-r--r--arch/x86/mm/init.c2
-rw-r--r--arch/x86/mm/pkeys.c15
-rw-r--r--arch/x86/mm/tlb.c31
78 files changed, 481 insertions, 553 deletions
diff --git a/arch/Kconfig b/arch/Kconfig
index fcf9a41a4ef5..71b9272acb28 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -438,6 +438,13 @@ config MMU_GATHER_PAGE_SIZE
config MMU_GATHER_NO_RANGE
bool
+ select MMU_GATHER_MERGE_VMAS
+
+config MMU_GATHER_NO_FLUSH_CACHE
+ bool
+
+config MMU_GATHER_MERGE_VMAS
+ bool
config MMU_GATHER_NO_GATHER
bool
diff --git a/arch/arm/boot/dts/lan966x.dtsi b/arch/arm/boot/dts/lan966x.dtsi
index 3cb02fffe716..38e90a31d2dd 100644
--- a/arch/arm/boot/dts/lan966x.dtsi
+++ b/arch/arm/boot/dts/lan966x.dtsi
@@ -38,7 +38,7 @@
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 a81dda65c576..45180a2cc47c 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 b5e8b9ae4c7d..7fd3600db8ef 100644
--- a/arch/arm/lib/findbit.S
+++ b/arch/arm/lib/findbit.S
@@ -40,8 +40,8 @@ ENDPROC(_find_first_zero_bit_le)
* 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 @@ ENDPROC(_find_first_bit_le)
* 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 @@ ENTRY(_find_first_zero_bit_be)
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 @@ ENTRY(_find_first_bit_be)
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 c546356d0f02..5738496717e2 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 2ae06edf413c..2fd665944103 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 753fe166ab68..624088257cfc 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 f98dc61e87af..98423a96f440 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 20456a55c4c5..0827ebca1d38 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 dd88953adc9d..9964729cd428 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 d03520555497..c4d4162a7e6e 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/csky/include/asm/tlb.h b/arch/csky/include/asm/tlb.h
index 3498e65f59f8..702861c68874 100644
--- a/arch/csky/include/asm/tlb.h
+++ b/arch/csky/include/asm/tlb.h
@@ -4,21 +4,6 @@
#define __ASM_CSKY_TLB_H
#include <asm/cacheflush.h>
-
-#define tlb_start_vma(tlb, vma) \
- do { \
- if (!(tlb)->fullmm) \
- flush_cache_range(vma, (vma)->vm_start, (vma)->vm_end); \
- } while (0)
-
-#define tlb_end_vma(tlb, vma) \
- do { \
- if (!(tlb)->fullmm) \
- flush_tlb_range(vma, (vma)->vm_start, (vma)->vm_end); \
- } while (0)
-
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
#include <asm-generic/tlb.h>
#endif /* __ASM_CSKY_TLB_H */
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 53a912befb62..62b5b07fa4e1 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -69,7 +69,6 @@ config LOONGARCH
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
@@ -108,6 +107,7 @@ config LOONGARCH
select TRACE_IRQFLAGS_SUPPORT
select USE_PERCPU_NUMA_NODE_ID
select ZONE_DMA32
+ select MMU_GATHER_MERGE_VMAS if MMU
config 32BIT
bool
diff --git a/arch/loongarch/include/asm/asmmacro.h b/arch/loongarch/include/asm/asmmacro.h
index a1a04083bd67..be037a40580d 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 979367ad4e2c..6b9aca9ab6e9 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 b6517eeeb141..cda977675854 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 75b3a4478652..0a9b0fac1eee 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 657cebe70ace..000000000000
--- 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 f3960b18a90e..5f3ff4781fda 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 9de8231694ec..feb6658c84ff 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 52121cd791fe..319a8c616f1f 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 2052a2267337..65fbbae9fc4d 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 6a8038725ba7..6e8f6972ceb6 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 26483e396ad1..6b5c2a7aa706 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 " $ra, %1, "STR_LONGSIZE"\n\t"
STORE_ONE_REG(2)
STORE_ONE_REG(3)
STORE_ONE_REG(4)
diff --git a/arch/loongarch/include/asm/thread_info.h b/arch/loongarch/include/asm/thread_info.h
index 99beb11c2fa8..b7dd9f19a5a9 100644
--- a/arch/loongarch/include/asm/thread_info.h
+++ b/arch/loongarch/include/asm/thread_info.h
@@ -44,14 +44,14 @@ struct thread_info {
}
/* How to get the thread information struct from C. */
-register struct thread_info *__current_thread_info __asm__("$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/tlb.h b/arch/loongarch/include/asm/tlb.h
index 4f629ae9d5a9..dd24f5898f65 100644
--- a/arch/loongarch/include/asm/tlb.h
+++ b/arch/loongarch/include/asm/tlb.h
@@ -137,16 +137,6 @@ static inline void invtlb_all(u32 op, u32 info, u64 addr)
);
}
-/*
- * LoongArch doesn't need any special per-pte or per-vma handling, except
- * we need to flush cache for area to be unmapped.
- */
-#define tlb_start_vma(tlb, vma) \
- do { \
- if (!(tlb)->fullmm) \
- flush_cache_range(vma, vma->vm_start, vma->vm_end); \
- } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
static void tlb_flush(struct mmu_gather *tlb);
diff --git a/arch/loongarch/include/asm/uaccess.h b/arch/loongarch/include/asm/uaccess.h
index 217c6a3727b1..2b44edc604a2 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 b38f5489d094..4662b06269f4 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 = &current_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 d5b3dbcf5425..d53b631c9022 100644
--- a/arch/loongarch/kernel/entry.S
+++ b/arch/loongarch/kernel/entry.S
@@ -27,7 +27,7 @@ SYM_FUNC_START(handle_syscall)
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 @@ SYM_FUNC_START(handle_syscall)
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 467946ecf451..82b478a5c665 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 a631a7137667..576b3370a296 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 @@ EXPORT_SYMBOL(_save_fp)
* 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 @@ SYM_FUNC_START(_init_fpu)
movgr2fr.d $f30, t1
movgr2fr.d $f31, t1
- jirl zero, ra, 0
+ jr ra
SYM_FUNC_END(_init_fpu)
/*
@@ -225,11 +225,11 @@ SYM_FUNC_END(_init_fpu)
* 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 @@ SYM_FUNC_END(_save_fp_context)
* 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 93496852b3cc..75e5be807a0d 100644
--- a/arch/loongarch/kernel/genex.S
+++ b/arch/loongarch/kernel/genex.S
@@ -28,23 +28,23 @@ SYM_FUNC_START(__arch_cpu_idle)
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 @@ SYM_FUNC_END(except_vec_cex)
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_END(except_vec_cex)
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 d01e62dd414f..7062cdf0e33e 100644
--- a/arch/loongarch/kernel/head.S
+++ b/arch/loongarch/kernel/head.S
@@ -32,7 +32,7 @@ SYM_CODE_START(kernel_entry) # kernel entry point
/* 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 @@ SYM_CODE_START(kernel_entry) # kernel entry point
/* 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 @@ SYM_CODE_START(smpboot_entry)
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 e6ab87948e1d..dc2b82ea894c 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 2b86469e4718..800c965a17ea 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 c74860b53375..8f5c2f9a1a83 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 73cec62504fb..09743103d9b3 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);
+
+ __smp_mb();
+ do {
+ __asm__ __volatile__("idle 0\n\t");
+ addr = iocsr_read64(LOONGARCH_IOCSR_MBUF0);
+ } while (addr == 0);
- __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);
+ 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 53e2fa8e580e..37e84ac8ffc2 100644
--- a/arch/loongarch/kernel/switch.S
+++ b/arch/loongarch/kernel/switch.S
@@ -24,8 +24,8 @@ SYM_FUNC_START(__switch_to)
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 25d9be5fbb19..16ba2b8dd68a 100644
--- a/arch/loongarch/lib/clear_user.S
+++ b/arch/loongarch/lib/clear_user.S
@@ -32,7 +32,7 @@ SYM_FUNC_START(__clear_user)
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 9ae507f851b5..97d20327a69e 100644
--- a/arch/loongarch/lib/copy_user.S
+++ b/arch/loongarch/lib/copy_user.S
@@ -35,7 +35,7 @@ SYM_FUNC_START(__copy_user)
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 5d856694fcfe..831d4761f385 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 ddc78ab33c7b..4c874a7af0ad 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 7eee40271577..de19fa2d7f0d 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 @@ SYM_FUNC_START(handle_tlb_protect)
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 @@ SYM_FUNC_START(handle_tlb_load)
* 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 @@ vmalloc_done_load:
* 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 @@ smp_pgtable_change_load:
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 @@ tlb_huge_update_load:
#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 @@ tlb_huge_update_load:
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 @@ SYM_FUNC_START(handle_tlb_store)
* 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 @@ vmalloc_done_store:
* 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 @@ smp_pgtable_change_store:
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 @@ tlb_huge_update_store:
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 @@ tlb_huge_update_store:
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 @@ SYM_FUNC_START(handle_tlb_modify)
* 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 @@ vmalloc_done_modify:
* 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 @@ smp_pgtable_change_modify:
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 @@ leave_modify:
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 @@ tlb_huge_update_modify:
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 @@ tlb_huge_update_modify:
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 7aa12e88c580..4d8f26c1399b 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -256,6 +256,7 @@ config PPC
select IRQ_FORCED_THREADING
select MMU_GATHER_PAGE_SIZE
select MMU_GATHER_RCU_TABLE_FREE
+ select MMU_GATHER_MERGE_VMAS
select MODULES_USE_ELF_RELA
select NEED_DMA_MAP_STATE if PPC64 || NOT_COHERENT_CACHE
select NEED_PER_CPU_EMBED_FIRST_CHUNK if PPC64
@@ -281,6 +282,10 @@ config PPC
# 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/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index 09a9ae5f3656..b3de6102a907 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -19,8 +19,6 @@
#include <linux/pagemap.h>
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
#define __tlb_remove_tlb_entry __tlb_remove_tlb_entry
#define tlb_flush tlb_flush
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index f91f0f29a566..c8cf924bf9c0 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -20,6 +20,7 @@ CFLAGS_prom.o += $(DISABLE_LATENT_ENTROPY_PLUGIN)
CFLAGS_prom_init.o += -fno-stack-protector
CFLAGS_prom_init.o += -DDISABLE_BRANCH_PROFILING
CFLAGS_prom_init.o += -ffreestanding
+CFLAGS_prom_init.o += $(call cc-option, -ftrivial-auto-var-init=uninitialized)
ifdef CONFIG_FUNCTION_TRACER
# Do not trace early boot code
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index 34cf8a598617..81029d40a672 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -73,6 +73,7 @@ ifeq ($(CONFIG_PERF_EVENTS),y)
endif
KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax)
+KBUILD_AFLAGS_MODULE += $(call as-option,-Wa$(comma)-mno-relax)
# GCC versions that support the "-mstrict-align" option default to allowing
# unaligned accesses. While unaligned accesses are explicitly allowed in the
@@ -110,7 +111,7 @@ PHONY += vdso_install
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/riscv/boot/dts/canaan/canaan_kd233.dts b/arch/riscv/boot/dts/canaan/canaan_kd233.dts
index 039b92abf046..f72540bd14a3 100644
--- a/arch/riscv/boot/dts/canaan/canaan_kd233.dts
+++ b/arch/riscv/boot/dts/canaan/canaan_kd233.dts
@@ -35,7 +35,7 @@
gpio-keys {
compatible = "gpio-keys";
- key0 {
+ key {
label = "KEY0";
linux,code = <BTN_0>;
gpios = <&gpio0 10 GPIO_ACTIVE_LOW>;
diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts
index b9e30df127fe..8abdbe26a1d0 100644
--- a/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts
+++ b/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts
@@ -47,7 +47,7 @@
gpio-keys {
compatible = "gpio-keys";
- boot {
+ key-boot {
label = "BOOT";
linux,code = <BTN_0>;
gpios = <&gpio0 0 GPIO_ACTIVE_LOW>;
diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts
index 8d23401b0bbb..3c6df1ecf76f 100644
--- a/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts
+++ b/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts
@@ -52,7 +52,7 @@
gpio-keys {
compatible = "gpio-keys";
- boot {
+ key-boot {
label = "BOOT";
linux,code = <BTN_0>;
gpios = <&gpio0 0 GPIO_ACTIVE_LOW>;
diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts
index 24fd83b43d9d..03c9843d503e 100644
--- a/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts
+++ b/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts
@@ -46,19 +46,19 @@
gpio-keys {
compatible = "gpio-keys";
- up {
+ key-up {
label = "UP";
linux,code = <BTN_1>;
gpios = <&gpio1_0 7 GPIO_ACTIVE_LOW>;
};
- press {
+ key-press {
label = "PRESS";
linux,code = <BTN_0>;
gpios = <&gpio0 0 GPIO_ACTIVE_LOW>;
};
- down {
+ key-down {
label = "DOWN";
linux,code = <BTN_2>;
gpios = <&gpio0 1 GPIO_ACTIVE_LOW>;
diff --git a/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts b/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts
index 25341f38292a..7164ad063178 100644
--- a/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts
+++ b/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts
@@ -23,7 +23,7 @@
gpio-keys {
compatible = "gpio-keys";
- boot {
+ key-boot {
label = "BOOT";
linux,code = <BTN_0>;
gpios = <&gpio0 0 GPIO_ACTIVE_LOW>;
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index c71d6591d539..33bb60a354cd 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -78,7 +78,7 @@ obj-$(CONFIG_SMP) += cpu_ops_sbi.o
endif
obj-$(CONFIG_HOTPLUG_CPU) += cpu-hotplug.o
obj-$(CONFIG_KGDB) += kgdb.o
-obj-$(CONFIG_KEXEC) += kexec_relocate.o crash_save_regs.o machine_kexec.o
+obj-$(CONFIG_KEXEC_CORE) += kexec_relocate.o crash_save_regs.o machine_kexec.o
obj-$(CONFIG_KEXEC_FILE) += elf_kexec.o machine_kexec_file.o
obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c
index 9cb85095fd45..0cb94992c15b 100644
--- a/arch/riscv/kernel/elf_kexec.c
+++ b/arch/riscv/kernel/elf_kexec.c
@@ -349,7 +349,7 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
{
const char *strtab, *name, *shstrtab;
const Elf_Shdr *sechdrs;
- Elf_Rela *relas;
+ Elf64_Rela *relas;
int i, r_type;
/* String & section header string table */
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 8cd9e56c629b..5a1a8dfda6f8 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -204,6 +204,7 @@ config S390
select IOMMU_SUPPORT if PCI
select MMU_GATHER_NO_GATHER
select MMU_GATHER_RCU_TABLE_FREE
+ select MMU_GATHER_MERGE_VMAS
select MODULES_USE_ELF_RELA
select NEED_DMA_MAP_STATE if PCI
select NEED_SG_DMA_LENGTH if PCI
diff --git a/arch/s390/include/asm/archrandom.h b/arch/s390/include/asm/archrandom.h
index 2c6e1c6ecbe7..4120c428dc37 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/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index fe6407f0eb1b..3a5c8fb590e5 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -27,9 +27,6 @@ static inline void tlb_flush(struct mmu_gather *tlb);
static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
struct page *page, int page_size);
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-
#define tlb_flush tlb_flush
#define pte_free_tlb pte_free_tlb
#define pmd_free_tlb pmd_free_tlb
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index ba449c47effd..4f7d1dfbc608 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -67,6 +67,8 @@ config SPARC64
select HAVE_KRETPROBES
select HAVE_KPROBES
select MMU_GATHER_RCU_TABLE_FREE if SMP
+ select MMU_GATHER_MERGE_VMAS
+ select MMU_GATHER_NO_FLUSH_CACHE
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
select HAVE_DYNAMIC_FTRACE
select HAVE_FTRACE_MCOUNT_RECORD
diff --git a/arch/sparc/include/asm/tlb_64.h b/arch/sparc/include/asm/tlb_64.h
index 779a5a0f0608..3037187482db 100644
--- a/arch/sparc/include/asm/tlb_64.h
+++ b/arch/sparc/include/asm/tlb_64.h
@@ -22,8 +22,6 @@ void smp_flush_tlb_mm(struct mm_struct *mm);
void __flush_tlb_pending(unsigned long, unsigned long, unsigned long *);
void flush_tlb_pending(void);
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
#define tlb_flush(tlb) flush_tlb_pending()
/*
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e58798f636d4..52a7f91527fe 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -245,6 +245,7 @@ config X86
select HAVE_PERF_REGS
select HAVE_PERF_USER_STACK_DUMP
select MMU_GATHER_RCU_TABLE_FREE if PARAVIRT
+ select MMU_GATHER_MERGE_VMAS
select HAVE_POSIX_CPU_TIMERS_TASK_WORK
select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_RELIABLE_STACKTRACE if UNWINDER_ORC || STACK_VALIDATION
@@ -2473,7 +2474,7 @@ config RETHUNK
bool "Enable return-thunks"
depends on RETPOLINE && CC_HAS_RETURN_THUNK
select OBJTOOL if HAVE_OBJTOOL
- default y
+ default y if X86_64
help
Compile the kernel with the return-thunks compiler option to guard
against kernel-to-user data leaks by avoiding return speculation.
@@ -2482,21 +2483,21 @@ config RETHUNK
config CPU_UNRET_ENTRY
bool "Enable UNRET on kernel entry"
- depends on CPU_SUP_AMD && RETHUNK
+ depends on CPU_SUP_AMD && RETHUNK && X86_64
default y
help
Compile the kernel with support for the retbleed=unret mitigation.
config CPU_IBPB_ENTRY
bool "Enable IBPB on kernel entry"
- depends on CPU_SUP_AMD
+ depends on CPU_SUP_AMD && X86_64
default y
help
Compile the kernel with support for the retbleed=ibpb mitigation.
config CPU_IBRS_ENTRY
bool "Enable IBRS on kernel entry"
- depends on CPU_SUP_INTEL
+ depends on CPU_SUP_INTEL && X86_64
default y
help
Compile the kernel with support for the spectre_v2=ibrs mitigation.
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 1f40dad30d50..7854685c5f25 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -27,6 +27,7 @@ RETHUNK_CFLAGS := -mfunction-return=thunk-extern
RETPOLINE_CFLAGS += $(RETHUNK_CFLAGS)
endif
+export RETHUNK_CFLAGS
export RETPOLINE_CFLAGS
export RETPOLINE_VDSO_CFLAGS
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 13179f31fe10..4f70fb6c2c1e 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -278,9 +278,9 @@ enum {
};
/*
- * For formats with LBR_TSX flags (e.g. LBR_FORMAT_EIP_FLAGS2), bits 61:62 in
- * MSR_LAST_BRANCH_FROM_x are the TSX flags when TSX is supported, but when
- * TSX is not supported they have no consistent behavior:
+ * For format LBR_FORMAT_EIP_FLAGS2, bits 61:62 in MSR_LAST_BRANCH_FROM_x
+ * are the TSX flags when TSX is supported, but when TSX is not supported
+ * they have no consistent behavior:
*
* - For wrmsr(), bits 61:62 are considered part of the sign extension.
* - For HW updates (branch captures) bits 61:62 are always OFF and are not
@@ -288,7 +288,7 @@ enum {
*
* Therefore, if:
*
- * 1) LBR has TSX format
+ * 1) LBR format LBR_FORMAT_EIP_FLAGS2
* 2) CPU has no TSX support enabled
*
* ... then any value passed to wrmsr() must be sign extended to 63 bits and any
@@ -300,7 +300,7 @@ static inline bool lbr_from_signext_quirk_needed(void)
bool tsx_support = boot_cpu_has(X86_FEATURE_HLE) ||
boot_cpu_has(X86_FEATURE_RTM);
- return !tsx_support && x86_pmu.lbr_has_tsx;
+ return !tsx_support;
}
static DEFINE_STATIC_KEY_FALSE(lbr_from_quirk_key);
@@ -1609,9 +1609,6 @@ void intel_pmu_lbr_init_hsw(void)
x86_pmu.lbr_sel_map = hsw_lbr_sel_map;
x86_get_pmu(smp_processor_id())->task_ctx_cache = create_lbr_kmem_cache(size, 0);
-
- if (lbr_from_signext_quirk_needed())
- static_branch_enable(&lbr_from_quirk_key);
}
/* skylake */
@@ -1702,7 +1699,11 @@ void intel_pmu_lbr_init(void)
switch (x86_pmu.intel_cap.lbr_format) {
case LBR_FORMAT_EIP_FLAGS2:
x86_pmu.lbr_has_tsx = 1;
- fallthrough;
+ x86_pmu.lbr_from_flags = 1;
+ if (lbr_from_signext_quirk_needed())
+ static_branch_enable(&lbr_from_quirk_key);
+ break;
+
case LBR_FORMAT_EIP_FLAGS:
x86_pmu.lbr_from_flags = 1;
break;
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 00f5227c8459..a77b915d36a8 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/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/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 10a3bfc1eb23..38a3e86e665e 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -297,6 +297,8 @@ do { \
alternative_msr_write(MSR_IA32_SPEC_CTRL, \
spec_ctrl_current() | SPEC_CTRL_IBRS, \
X86_FEATURE_USE_IBRS_FW); \
+ alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, \
+ X86_FEATURE_USE_IBPB_FW); \
} while (0)
#define firmware_restrict_branch_speculation_end() \
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 19514524f0f8..4a23e52fe0ee 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -72,7 +72,6 @@ static inline u64 lower_bits(u64 val, unsigned int bits)
struct real_mode_header;
enum stack_type;
-struct ghcb;
/* Early IDT entry points for #VC handler */
extern void vc_no_ghcb(void);
@@ -156,11 +155,7 @@ static __always_inline void sev_es_nmi_complete(void)
__sev_es_nmi_complete();
}
extern int __init sev_es_efi_map_ghcbs(pgd_t *pgd);
-extern enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
- bool set_ghcb_msr,
- struct es_em_ctxt *ctxt,
- u64 exit_code, u64 exit_info_1,
- u64 exit_info_2);
+
static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs)
{
int rc;
diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index 1bfe979bb9bc..580636cdc257 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -2,9 +2,6 @@
#ifndef _ASM_X86_TLB_H
#define _ASM_X86_TLB_H
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-
#define tlb_flush tlb_flush
static inline void tlb_flush(struct mmu_gather *tlb);
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 4af5579c7ef7..cda3118f3b27 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -16,6 +16,7 @@
void __flush_tlb_all(void);
#define TLB_FLUSH_ALL -1UL
+#define TLB_GENERATION_INVALID 0
void cr4_update_irqsoff(unsigned long set, unsigned long clear);
unsigned long cr4_read_shadow(void);
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index d6858533e6e5..62f6b8b7c4a5 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -555,7 +555,9 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end)
dest = addr + insn.length + insn.immediate.value;
if (__static_call_fixup(addr, op, dest) ||
- WARN_ON_ONCE(dest != &__x86_return_thunk))
+ WARN_ONCE(dest != &__x86_return_thunk,
+ "missing return thunk: %pS-%pS: %*ph",
+ addr, dest, 5, addr))
continue;
DPRINTK("return thunk at: %pS (%px) len: %d to: %pS",
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index aa34f908c39f..6761668100b9 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -975,6 +975,7 @@ static inline const char *spectre_v2_module_string(void) { return ""; }
#define SPECTRE_V2_LFENCE_MSG "WARNING: LFENCE mitigation is not recommended for this CPU, data leaks possible!\n"
#define SPECTRE_V2_EIBRS_EBPF_MSG "WARNING: Unprivileged eBPF is enabled with eIBRS on, data leaks possible via Spectre v2 BHB attacks!\n"
#define SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG "WARNING: Unprivileged eBPF is enabled with eIBRS+LFENCE mitigation and SMT, data leaks possible via Spectre v2 BHB attacks!\n"
+#define SPECTRE_V2_IBRS_PERF_MSG "WARNING: IBRS mitigation selected on Enhanced IBRS CPU, this may cause unnecessary performance loss\n"
#ifdef CONFIG_BPF_SYSCALL
void unpriv_ebpf_notify(int new_state)
@@ -1415,6 +1416,8 @@ static void __init spectre_v2_select_mitigation(void)
case SPECTRE_V2_IBRS:
setup_force_cpu_cap(X86_FEATURE_KERNEL_IBRS);
+ if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED))
+ pr_warn(SPECTRE_V2_IBRS_PERF_MSG);
break;
case SPECTRE_V2_LFENCE:
@@ -1516,7 +1519,17 @@ static void __init spectre_v2_select_mitigation(void)
* the CPU supports Enhanced IBRS, kernel might un-intentionally not
* enable IBRS around firmware calls.
*/
- if (boot_cpu_has(X86_FEATURE_IBRS) && !spectre_v2_in_ibrs_mode(mode)) {
+ if (boot_cpu_has_bug(X86_BUG_RETBLEED) &&
+ boot_cpu_has(X86_FEATURE_IBPB) &&
+ (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) {
+
+ if (retbleed_cmd != RETBLEED_CMD_IBPB) {
+ setup_force_cpu_cap(X86_FEATURE_USE_IBPB_FW);
+ pr_info("Enabling Speculation Barrier for firmware calls\n");
+ }
+
+ } else if (boot_cpu_has(X86_FEATURE_IBRS) && !spectre_v2_in_ibrs_mode(mode)) {
setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW);
pr_info("Enabling Restricted Speculation for firmware calls\n");
}
diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 5fbd7ffb3233..12cf2e7ca33c 100644
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -33,6 +33,8 @@
#include "internal.h"
+static bool hw_injection_possible = true;
+
/*
* Collect all the MCi_XXX settings
*/
@@ -339,6 +341,8 @@ static int __set_inj(const char *buf)
for (i = 0; i < N_INJ_TYPES; i++) {
if (!strncmp(flags_options[i], buf, strlen(flags_options[i]))) {
+ if (i > SW_INJ && !hw_injection_possible)
+ continue;
inj_type = i;
return 0;
}
@@ -717,11 +721,54 @@ static void __init debugfs_init(void)
&i_mce, dfs_fls[i].fops);
}
+static void check_hw_inj_possible(void)
+{
+ int cpu;
+ u8 bank;
+
+ /*
+ * This behavior exists only on SMCA systems though its not directly
+ * related to SMCA.
+ */
+ if (!cpu_feature_enabled(X86_FEATURE_SMCA))
+ return;
+
+ cpu = get_cpu();
+
+ for (bank = 0; bank < MAX_NR_BANKS; ++bank) {
+ u64 status = MCI_STATUS_VAL, ipid;
+
+ /* Check whether bank is populated */
+ rdmsrl(MSR_AMD64_SMCA_MCx_IPID(bank), ipid);
+ if (!ipid)
+ continue;
+
+ toggle_hw_mce_inject(cpu, true);
+
+ wrmsrl_safe(mca_msr_reg(bank, MCA_STATUS), status);
+ rdmsrl_safe(mca_msr_reg(bank, MCA_STATUS), &status);
+
+ if (!status) {
+ hw_injection_possible = false;
+ pr_warn("Platform does not allow *hardware* error injection."
+ "Try using APEI EINJ instead.\n");
+ }
+
+ toggle_hw_mce_inject(cpu, false);
+
+ break;
+ }
+
+ put_cpu();
+}
+
static int __init inject_init(void)
{
if (!alloc_cpumask_var(&mce_inject_cpumask, GFP_KERNEL))
return -ENOMEM;
+ check_hw_inj_possible();
+
debugfs_init();
register_nmi_handler(NMI_LOCAL, mce_raise_notify, 0, "mce_notify");
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 4ae0e603f7fa..7e03f5b7f6bd 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -211,7 +211,7 @@ noinstr u64 mce_rdmsrl(u32 msr);
static __always_inline u32 mca_msr_reg(int bank, enum mca_msr reg)
{
- if (mce_flags.smca) {
+ if (cpu_feature_enabled(X86_FEATURE_SMCA)) {
switch (reg) {
case MCA_CTL: return MSR_AMD64_SMCA_MCx_CTL(bank);
case MCA_ADDR: return MSR_AMD64_SMCA_MCx_ADDR(bank);
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index c04b933f48d3..02039ec3597d 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -476,8 +476,8 @@ static bool __init vmware_legacy_x2apic_available(void)
{
uint32_t eax, ebx, ecx, edx;
VMWARE_CMD(GETVCPU_INFO, eax, ebx, ecx, edx);
- return (eax & (1 << VMWARE_CMD_VCPU_RESERVED)) == 0 &&
- (eax & (1 << VMWARE_CMD_LEGACY_X2APIC)) != 0;
+ return !(eax & BIT(VMWARE_CMD_VCPU_RESERVED)) &&
+ (eax & BIT(VMWARE_CMD_LEGACY_X2APIC));
}
#ifdef CONFIG_AMD_MEM_ENCRYPT
diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c
index b478edf43bec..3a5b0c9c4fcc 100644
--- a/arch/x86/kernel/sev-shared.c
+++ b/arch/x86/kernel/sev-shared.c
@@ -219,9 +219,10 @@ static enum es_result verify_exception_info(struct ghcb *ghcb, struct es_em_ctxt
return ES_VMM_ERROR;
}
-enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, bool set_ghcb_msr,
- struct es_em_ctxt *ctxt, u64 exit_code,
- u64 exit_info_1, u64 exit_info_2)
+static enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
+ struct es_em_ctxt *ctxt,
+ u64 exit_code, u64 exit_info_1,
+ u64 exit_info_2)
{
/* Fill in protocol and format specifiers */
ghcb->protocol_version = ghcb_version;
@@ -231,14 +232,7 @@ enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, bool set_ghcb_msr,
ghcb_set_sw_exit_info_1(ghcb, exit_info_1);
ghcb_set_sw_exit_info_2(ghcb, exit_info_2);
- /*
- * Hyper-V unenlightened guests use a paravisor for communicating and
- * GHCB pages are being allocated and set up by that paravisor. Linux
- * should not change the GHCB page's physical address.
- */
- if (set_ghcb_msr)
- sev_es_wr_ghcb_msr(__pa(ghcb));
-
+ sev_es_wr_ghcb_msr(__pa(ghcb));
VMGEXIT();
return verify_exception_info(ghcb, ctxt);
@@ -795,7 +789,7 @@ static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
*/
sw_scratch = __pa(ghcb) + offsetof(struct ghcb, shared_buffer);
ghcb_set_sw_scratch(ghcb, sw_scratch);
- ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_IOIO,
+ ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO,
exit_info_1, exit_info_2);
if (ret != ES_OK)
return ret;
@@ -837,8 +831,7 @@ static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
ghcb_set_rax(ghcb, rax);
- ret = sev_es_ghcb_hv_call(ghcb, true, ctxt,
- SVM_EXIT_IOIO, exit_info_1, 0);
+ ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO, exit_info_1, 0);
if (ret != ES_OK)
return ret;
@@ -894,7 +887,7 @@ static enum es_result vc_handle_cpuid(struct ghcb *ghcb,
/* xgetbv will cause #GP - use reset value for xcr0 */
ghcb_set_xcr0(ghcb, 1);
- ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_CPUID, 0, 0);
+ ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_CPUID, 0, 0);
if (ret != ES_OK)
return ret;
@@ -919,7 +912,7 @@ static enum es_result vc_handle_rdtsc(struct ghcb *ghcb,
bool rdtscp = (exit_code == SVM_EXIT_RDTSCP);
enum es_result ret;
- ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, exit_code, 0, 0);
+ ret = sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, 0, 0);
if (ret != ES_OK)
return ret;
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index c05f0124c410..63dc626627a0 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -786,7 +786,7 @@ static int vmgexit_psc(struct snp_psc_desc *desc)
ghcb_set_sw_scratch(ghcb, (u64)__pa(data));
/* This will advance the shared buffer data points to. */
- ret = sev_es_ghcb_hv_call(ghcb, true, &ctxt, SVM_VMGEXIT_PSC, 0, 0);
+ ret = sev_es_ghcb_hv_call(ghcb, &ctxt, SVM_VMGEXIT_PSC, 0, 0);
/*
* Page State Change VMGEXIT can pass error code through
@@ -1212,8 +1212,7 @@ static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
ghcb_set_rdx(ghcb, regs->dx);
}
- ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_MSR,
- exit_info_1, 0);
+ ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_MSR, exit_info_1, 0);
if ((ret == ES_OK) && (!exit_info_1)) {
regs->ax = ghcb->save.rax;
@@ -1452,7 +1451,7 @@ static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
ghcb_set_sw_scratch(ghcb, ghcb_pa + offsetof(struct ghcb, shared_buffer));
- return sev_es_ghcb_hv_call(ghcb, true, ctxt, exit_code, exit_info_1, exit_info_2);
+ return sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, exit_info_1, exit_info_2);
}
/*
@@ -1628,7 +1627,7 @@ static enum es_result vc_handle_dr7_write(struct ghcb *ghcb,
/* Using a value of 0 for ExitInfo1 means RAX holds the value */
ghcb_set_rax(ghcb, val);
- ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_WRITE_DR7, 0, 0);
+ ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WRITE_DR7, 0, 0);
if (ret != ES_OK)
return ret;
@@ -1658,7 +1657,7 @@ static enum es_result vc_handle_dr7_read(struct ghcb *ghcb,
static enum es_result vc_handle_wbinvd(struct ghcb *ghcb,
struct es_em_ctxt *ctxt)
{
- return sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_WBINVD, 0, 0);
+ return sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WBINVD, 0, 0);
}
static enum es_result vc_handle_rdpmc(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
@@ -1667,7 +1666,7 @@ static enum es_result vc_handle_rdpmc(struct ghcb *ghcb, struct es_em_ctxt *ctxt
ghcb_set_rcx(ghcb, ctxt->regs->cx);
- ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_RDPMC, 0, 0);
+ ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_RDPMC, 0, 0);
if (ret != ES_OK)
return ret;
@@ -1708,7 +1707,7 @@ static enum es_result vc_handle_vmmcall(struct ghcb *ghcb,
if (x86_platform.hyper.sev_es_hcall_prepare)
x86_platform.hyper.sev_es_hcall_prepare(ghcb, ctxt->regs);
- ret = sev_es_ghcb_hv_call(ghcb, true, ctxt, SVM_EXIT_VMMCALL, 0, 0);
+ ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_VMMCALL, 0, 0);
if (ret != ES_OK)
return ret;
@@ -2197,7 +2196,7 @@ int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, unsigned
ghcb_set_rbx(ghcb, input->data_npages);
}
- ret = sev_es_ghcb_hv_call(ghcb, true, &ctxt, exit_code, input->req_gpa, input->resp_gpa);
+ ret = sev_es_ghcb_hv_call(ghcb, &ctxt, exit_code, input->req_gpa, input->resp_gpa);
if (ret)
goto e_put;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 143e37298d8a..e5fa335a4ea7 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6029,6 +6029,11 @@ split_irqchip_unlock:
r = 0;
break;
case KVM_CAP_X86_USER_SPACE_MSR:
+ r = -EINVAL;
+ if (cap->args[0] & ~(KVM_MSR_EXIT_REASON_INVAL |
+ KVM_MSR_EXIT_REASON_UNKNOWN |
+ KVM_MSR_EXIT_REASON_FILTER))
+ break;
kvm->arch.user_space_msr_mask = cap->args[0];
r = 0;
break;
@@ -6183,6 +6188,9 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp)
if (copy_from_user(&filter, user_msr_filter, sizeof(filter)))
return -EFAULT;
+ if (filter.flags & ~KVM_MSR_FILTER_DEFAULT_DENY)
+ return -EINVAL;
+
for (i = 0; i < ARRAY_SIZE(filter.ranges); i++)
empty &= !filter.ranges[i].nmsrs;
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 57ba5502aecf..82a042c03824 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -856,7 +856,7 @@ int devmem_is_allowed(unsigned long pagenr)
/*
* This must follow RAM test, since System RAM is considered a
- * restricted resource under CONFIG_STRICT_IOMEM.
+ * restricted resource under CONFIG_STRICT_DEVMEM.
*/
if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) {
/* Low 1MB bypasses iomem restrictions. */
diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c
index e44e938885b7..7418c367e328 100644
--- a/arch/x86/mm/pkeys.c
+++ b/arch/x86/mm/pkeys.c
@@ -110,7 +110,7 @@ int __arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey
return vma_pkey(vma);
}
-#define PKRU_AD_KEY(pkey) (PKRU_AD_BIT << ((pkey) * PKRU_BITS_PER_PKEY))
+#define PKRU_AD_MASK(pkey) (PKRU_AD_BIT << ((pkey) * PKRU_BITS_PER_PKEY))
/*
* Make the default PKRU value (at execve() time) as restrictive
@@ -118,11 +118,14 @@ int __arch_override_mprotect_pkey(struct vm_area_struct *vma, int prot, int pkey
* in the process's lifetime will not accidentally get access
* to data which is pkey-protected later on.
*/
-u32 init_pkru_value = PKRU_AD_KEY( 1) | PKRU_AD_KEY( 2) | PKRU_AD_KEY( 3) |
- PKRU_AD_KEY( 4) | PKRU_AD_KEY( 5) | PKRU_AD_KEY( 6) |
- PKRU_AD_KEY( 7) | PKRU_AD_KEY( 8) | PKRU_AD_KEY( 9) |
- PKRU_AD_KEY(10) | PKRU_AD_KEY(11) | PKRU_AD_KEY(12) |
- PKRU_AD_KEY(13) | PKRU_AD_KEY(14) | PKRU_AD_KEY(15);
+u32 init_pkru_value = PKRU_AD_MASK( 1) | PKRU_AD_MASK( 2) |
+ PKRU_AD_MASK( 3) | PKRU_AD_MASK( 4) |
+ PKRU_AD_MASK( 5) | PKRU_AD_MASK( 6) |
+ PKRU_AD_MASK( 7) | PKRU_AD_MASK( 8) |
+ PKRU_AD_MASK( 9) | PKRU_AD_MASK(10) |
+ PKRU_AD_MASK(11) | PKRU_AD_MASK(12) |
+ PKRU_AD_MASK(13) | PKRU_AD_MASK(14) |
+ PKRU_AD_MASK(15);
static ssize_t init_pkru_read_file(struct file *file, char __user *user_buf,
size_t count, loff_t *ppos)
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index d400b6d9d246..c1e31e9a85d7 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -734,10 +734,10 @@ static void flush_tlb_func(void *info)
const struct flush_tlb_info *f = info;
struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
- u64 mm_tlb_gen = atomic64_read(&loaded_mm->context.tlb_gen);
u64 local_tlb_gen = this_cpu_read(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen);
bool local = smp_processor_id() == f->initiating_cpu;
unsigned long nr_invalidate = 0;
+ u64 mm_tlb_gen;
/* This code cannot presently handle being reentered. */
VM_WARN_ON(!irqs_disabled());
@@ -771,6 +771,23 @@ static void flush_tlb_func(void *info)
return;
}
+ if (unlikely(f->new_tlb_gen != TLB_GENERATION_INVALID &&
+ f->new_tlb_gen <= local_tlb_gen)) {
+ /*
+ * The TLB is already up to date in respect to f->new_tlb_gen.
+ * While the core might be still behind mm_tlb_gen, checking
+ * mm_tlb_gen unnecessarily would have negative caching effects
+ * so avoid it.
+ */
+ return;
+ }
+
+ /*
+ * Defer mm_tlb_gen reading as long as possible to avoid cache
+ * contention.
+ */
+ mm_tlb_gen = atomic64_read(&loaded_mm->context.tlb_gen);
+
if (unlikely(local_tlb_gen == mm_tlb_gen)) {
/*
* There's nothing to do: we're already up to date. This can
@@ -827,6 +844,12 @@ static void flush_tlb_func(void *info)
/* Partial flush */
unsigned long addr = f->start;
+ /* Partial flush cannot have invalid generations */
+ VM_WARN_ON(f->new_tlb_gen == TLB_GENERATION_INVALID);
+
+ /* Partial flush must have valid mm */
+ VM_WARN_ON(f->mm == NULL);
+
nr_invalidate = (f->end - f->start) >> f->stride_shift;
while (addr < f->end) {
@@ -1029,7 +1052,8 @@ void flush_tlb_kernel_range(unsigned long start, unsigned long end)
struct flush_tlb_info *info;
preempt_disable();
- info = get_flush_tlb_info(NULL, start, end, 0, false, 0);
+ info = get_flush_tlb_info(NULL, start, end, 0, false,
+ TLB_GENERATION_INVALID);
on_each_cpu(do_kernel_range_flush, info, 1);
@@ -1198,7 +1222,8 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
int cpu = get_cpu();
- info = get_flush_tlb_info(NULL, 0, TLB_FLUSH_ALL, 0, false, 0);
+ info = get_flush_tlb_info(NULL, 0, TLB_FLUSH_ALL, 0, false,
+ TLB_GENERATION_INVALID);
/*
* flush_tlb_multi() is not optimized for the common case in which only
* a local TLB flush is needed. Optimize this use-case by calling