summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/arm64/crypto/ghash-ce-glue.c29
-rw-r--r--arch/arm64/crypto/sm4-ce-glue.c2
-rw-r--r--arch/m68k/mac/misc.c10
-rw-r--r--arch/nios2/Kconfig.debug9
-rw-r--r--arch/powerpc/Kconfig1
-rw-r--r--arch/riscv/include/asm/tlb.h4
-rw-r--r--arch/riscv/kernel/sys_riscv.c15
-rw-r--r--arch/x86/crypto/aesni-intel_asm.S66
-rw-r--r--arch/x86/include/asm/pgtable-3level.h7
-rw-r--r--arch/x86/xen/mmu_pv.c9
10 files changed, 72 insertions, 80 deletions
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index 6e9f33d14930..067d8937d5af 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -417,7 +417,7 @@ static int gcm_encrypt(struct aead_request *req)
__aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv, nrounds);
put_unaligned_be32(2, iv + GCM_IV_SIZE);
- while (walk.nbytes >= AES_BLOCK_SIZE) {
+ while (walk.nbytes >= (2 * AES_BLOCK_SIZE)) {
int blocks = walk.nbytes / AES_BLOCK_SIZE;
u8 *dst = walk.dst.virt.addr;
u8 *src = walk.src.virt.addr;
@@ -437,11 +437,18 @@ static int gcm_encrypt(struct aead_request *req)
NULL);
err = skcipher_walk_done(&walk,
- walk.nbytes % AES_BLOCK_SIZE);
+ walk.nbytes % (2 * AES_BLOCK_SIZE));
}
- if (walk.nbytes)
+ if (walk.nbytes) {
__aes_arm64_encrypt(ctx->aes_key.key_enc, ks, iv,
nrounds);
+ if (walk.nbytes > AES_BLOCK_SIZE) {
+ crypto_inc(iv, AES_BLOCK_SIZE);
+ __aes_arm64_encrypt(ctx->aes_key.key_enc,
+ ks + AES_BLOCK_SIZE, iv,
+ nrounds);
+ }
+ }
}
/* handle the tail */
@@ -545,7 +552,7 @@ static int gcm_decrypt(struct aead_request *req)
__aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv, nrounds);
put_unaligned_be32(2, iv + GCM_IV_SIZE);
- while (walk.nbytes >= AES_BLOCK_SIZE) {
+ while (walk.nbytes >= (2 * AES_BLOCK_SIZE)) {
int blocks = walk.nbytes / AES_BLOCK_SIZE;
u8 *dst = walk.dst.virt.addr;
u8 *src = walk.src.virt.addr;
@@ -564,11 +571,21 @@ static int gcm_decrypt(struct aead_request *req)
} while (--blocks > 0);
err = skcipher_walk_done(&walk,
- walk.nbytes % AES_BLOCK_SIZE);
+ walk.nbytes % (2 * AES_BLOCK_SIZE));
}
- if (walk.nbytes)
+ if (walk.nbytes) {
+ if (walk.nbytes > AES_BLOCK_SIZE) {
+ u8 *iv2 = iv + AES_BLOCK_SIZE;
+
+ memcpy(iv2, iv, AES_BLOCK_SIZE);
+ crypto_inc(iv2, AES_BLOCK_SIZE);
+
+ __aes_arm64_encrypt(ctx->aes_key.key_enc, iv2,
+ iv2, nrounds);
+ }
__aes_arm64_encrypt(ctx->aes_key.key_enc, iv, iv,
nrounds);
+ }
}
/* handle the tail */
diff --git a/arch/arm64/crypto/sm4-ce-glue.c b/arch/arm64/crypto/sm4-ce-glue.c
index b7fb5274b250..0c4fc223f225 100644
--- a/arch/arm64/crypto/sm4-ce-glue.c
+++ b/arch/arm64/crypto/sm4-ce-glue.c
@@ -69,5 +69,5 @@ static void __exit sm4_ce_mod_fini(void)
crypto_unregister_alg(&sm4_ce_alg);
}
-module_cpu_feature_match(SM3, sm4_ce_mod_init);
+module_cpu_feature_match(SM4, sm4_ce_mod_init);
module_exit(sm4_ce_mod_fini);
diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c
index 3534aa6a4dc2..1b083c500b9a 100644
--- a/arch/m68k/mac/misc.c
+++ b/arch/m68k/mac/misc.c
@@ -98,11 +98,10 @@ static time64_t pmu_read_time(void)
if (pmu_request(&req, NULL, 1, PMU_READ_RTC) < 0)
return 0;
- while (!req.complete)
- pmu_poll();
+ pmu_wait_complete(&req);
- time = (u32)((req.reply[1] << 24) | (req.reply[2] << 16) |
- (req.reply[3] << 8) | req.reply[4]);
+ time = (u32)((req.reply[0] << 24) | (req.reply[1] << 16) |
+ (req.reply[2] << 8) | req.reply[3]);
return time - RTC_OFFSET;
}
@@ -116,8 +115,7 @@ static void pmu_write_time(time64_t time)
(data >> 24) & 0xFF, (data >> 16) & 0xFF,
(data >> 8) & 0xFF, data & 0xFF) < 0)
return;
- while (!req.complete)
- pmu_poll();
+ pmu_wait_complete(&req);
}
static __u8 pmu_read_pram(int offset)
diff --git a/arch/nios2/Kconfig.debug b/arch/nios2/Kconfig.debug
index 7a49f0d28d14..f1da8a7b17ff 100644
--- a/arch/nios2/Kconfig.debug
+++ b/arch/nios2/Kconfig.debug
@@ -3,15 +3,6 @@
config TRACE_IRQFLAGS_SUPPORT
def_bool y
-config DEBUG_STACK_USAGE
- bool "Enable stack utilization instrumentation"
- depends on DEBUG_KERNEL
- help
- Enables the display of the minimum amount of free stack which each
- task has ever had available in the sysrq-T and sysrq-P debug output.
-
- This option will slow down process creation somewhat.
-
config EARLY_PRINTK
bool "Activate early kernel debugging"
default y
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index db0b6eebbfa5..a80669209155 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -177,7 +177,6 @@ config PPC
select HAVE_ARCH_KGDB
select HAVE_ARCH_MMAP_RND_BITS
select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
- select HAVE_ARCH_PREL32_RELOCATIONS
select HAVE_ARCH_SECCOMP_FILTER
select HAVE_ARCH_TRACEHOOK
select HAVE_CBPF_JIT if !PPC64
diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
index c229509288ea..439dc7072e05 100644
--- a/arch/riscv/include/asm/tlb.h
+++ b/arch/riscv/include/asm/tlb.h
@@ -14,6 +14,10 @@
#ifndef _ASM_RISCV_TLB_H
#define _ASM_RISCV_TLB_H
+struct mmu_gather;
+
+static void tlb_flush(struct mmu_gather *tlb);
+
#include <asm-generic/tlb.h>
static inline void tlb_flush(struct mmu_gather *tlb)
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index 568026ccf6e8..fb03a4482ad6 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -65,24 +65,11 @@ SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len,
SYSCALL_DEFINE3(riscv_flush_icache, uintptr_t, start, uintptr_t, end,
uintptr_t, flags)
{
-#ifdef CONFIG_SMP
- struct mm_struct *mm = current->mm;
- bool local = (flags & SYS_RISCV_FLUSH_ICACHE_LOCAL) != 0;
-#endif
-
/* Check the reserved flags. */
if (unlikely(flags & ~SYS_RISCV_FLUSH_ICACHE_ALL))
return -EINVAL;
- /*
- * Without CONFIG_SMP flush_icache_mm is a just a flush_icache_all(),
- * which generates unused variable warnings all over this function.
- */
-#ifdef CONFIG_SMP
- flush_icache_mm(mm, local);
-#else
- flush_icache_all();
-#endif
+ flush_icache_mm(current->mm, flags & SYS_RISCV_FLUSH_ICACHE_LOCAL);
return 0;
}
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 9bd139569b41..cb2deb61c5d9 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -223,34 +223,34 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff
pcmpeqd TWOONE(%rip), \TMP2
pand POLY(%rip), \TMP2
pxor \TMP2, \TMP3
- movdqa \TMP3, HashKey(%arg2)
+ movdqu \TMP3, HashKey(%arg2)
movdqa \TMP3, \TMP5
pshufd $78, \TMP3, \TMP1
pxor \TMP3, \TMP1
- movdqa \TMP1, HashKey_k(%arg2)
+ movdqu \TMP1, HashKey_k(%arg2)
GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
# TMP5 = HashKey^2<<1 (mod poly)
- movdqa \TMP5, HashKey_2(%arg2)
+ movdqu \TMP5, HashKey_2(%arg2)
# HashKey_2 = HashKey^2<<1 (mod poly)
pshufd $78, \TMP5, \TMP1
pxor \TMP5, \TMP1
- movdqa \TMP1, HashKey_2_k(%arg2)
+ movdqu \TMP1, HashKey_2_k(%arg2)
GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
# TMP5 = HashKey^3<<1 (mod poly)
- movdqa \TMP5, HashKey_3(%arg2)
+ movdqu \TMP5, HashKey_3(%arg2)
pshufd $78, \TMP5, \TMP1
pxor \TMP5, \TMP1
- movdqa \TMP1, HashKey_3_k(%arg2)
+ movdqu \TMP1, HashKey_3_k(%arg2)
GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
# TMP5 = HashKey^3<<1 (mod poly)
- movdqa \TMP5, HashKey_4(%arg2)
+ movdqu \TMP5, HashKey_4(%arg2)
pshufd $78, \TMP5, \TMP1
pxor \TMP5, \TMP1
- movdqa \TMP1, HashKey_4_k(%arg2)
+ movdqu \TMP1, HashKey_4_k(%arg2)
.endm
# GCM_INIT initializes a gcm_context struct to prepare for encoding/decoding.
@@ -271,7 +271,7 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff
movdqu %xmm0, CurCount(%arg2) # ctx_data.current_counter = iv
PRECOMPUTE \SUBKEY, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7,
- movdqa HashKey(%arg2), %xmm13
+ movdqu HashKey(%arg2), %xmm13
CALC_AAD_HASH %xmm13, \AAD, \AADLEN, %xmm0, %xmm1, %xmm2, %xmm3, \
%xmm4, %xmm5, %xmm6
@@ -997,7 +997,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
pshufd $78, \XMM5, \TMP6
pxor \XMM5, \TMP6
paddd ONE(%rip), \XMM0 # INCR CNT
- movdqa HashKey_4(%arg2), \TMP5
+ movdqu HashKey_4(%arg2), \TMP5
PCLMULQDQ 0x11, \TMP5, \TMP4 # TMP4 = a1*b1
movdqa \XMM0, \XMM1
paddd ONE(%rip), \XMM0 # INCR CNT
@@ -1016,7 +1016,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
pxor (%arg1), \XMM2
pxor (%arg1), \XMM3
pxor (%arg1), \XMM4
- movdqa HashKey_4_k(%arg2), \TMP5
+ movdqu HashKey_4_k(%arg2), \TMP5
PCLMULQDQ 0x00, \TMP5, \TMP6 # TMP6 = (a1+a0)*(b1+b0)
movaps 0x10(%arg1), \TMP1
AESENC \TMP1, \XMM1 # Round 1
@@ -1031,7 +1031,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
movdqa \XMM6, \TMP1
pshufd $78, \XMM6, \TMP2
pxor \XMM6, \TMP2
- movdqa HashKey_3(%arg2), \TMP5
+ movdqu HashKey_3(%arg2), \TMP5
PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1 * b1
movaps 0x30(%arg1), \TMP3
AESENC \TMP3, \XMM1 # Round 3
@@ -1044,7 +1044,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
AESENC \TMP3, \XMM2
AESENC \TMP3, \XMM3
AESENC \TMP3, \XMM4
- movdqa HashKey_3_k(%arg2), \TMP5
+ movdqu HashKey_3_k(%arg2), \TMP5
PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
movaps 0x50(%arg1), \TMP3
AESENC \TMP3, \XMM1 # Round 5
@@ -1058,7 +1058,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
movdqa \XMM7, \TMP1
pshufd $78, \XMM7, \TMP2
pxor \XMM7, \TMP2
- movdqa HashKey_2(%arg2), \TMP5
+ movdqu HashKey_2(%arg2), \TMP5
# Multiply TMP5 * HashKey using karatsuba
@@ -1074,7 +1074,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
AESENC \TMP3, \XMM2
AESENC \TMP3, \XMM3
AESENC \TMP3, \XMM4
- movdqa HashKey_2_k(%arg2), \TMP5
+ movdqu HashKey_2_k(%arg2), \TMP5
PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
movaps 0x80(%arg1), \TMP3
AESENC \TMP3, \XMM1 # Round 8
@@ -1092,7 +1092,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
movdqa \XMM8, \TMP1
pshufd $78, \XMM8, \TMP2
pxor \XMM8, \TMP2
- movdqa HashKey(%arg2), \TMP5
+ movdqu HashKey(%arg2), \TMP5
PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1*b1
movaps 0x90(%arg1), \TMP3
AESENC \TMP3, \XMM1 # Round 9
@@ -1121,7 +1121,7 @@ aes_loop_par_enc_done\@:
AESENCLAST \TMP3, \XMM2
AESENCLAST \TMP3, \XMM3
AESENCLAST \TMP3, \XMM4
- movdqa HashKey_k(%arg2), \TMP5
+ movdqu HashKey_k(%arg2), \TMP5
PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
movdqu (%arg4,%r11,1), \TMP3
pxor \TMP3, \XMM1 # Ciphertext/Plaintext XOR EK
@@ -1205,7 +1205,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
pshufd $78, \XMM5, \TMP6
pxor \XMM5, \TMP6
paddd ONE(%rip), \XMM0 # INCR CNT
- movdqa HashKey_4(%arg2), \TMP5
+ movdqu HashKey_4(%arg2), \TMP5
PCLMULQDQ 0x11, \TMP5, \TMP4 # TMP4 = a1*b1
movdqa \XMM0, \XMM1
paddd ONE(%rip), \XMM0 # INCR CNT
@@ -1224,7 +1224,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
pxor (%arg1), \XMM2
pxor (%arg1), \XMM3
pxor (%arg1), \XMM4
- movdqa HashKey_4_k(%arg2), \TMP5
+ movdqu HashKey_4_k(%arg2), \TMP5
PCLMULQDQ 0x00, \TMP5, \TMP6 # TMP6 = (a1+a0)*(b1+b0)
movaps 0x10(%arg1), \TMP1
AESENC \TMP1, \XMM1 # Round 1
@@ -1239,7 +1239,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
movdqa \XMM6, \TMP1
pshufd $78, \XMM6, \TMP2
pxor \XMM6, \TMP2
- movdqa HashKey_3(%arg2), \TMP5
+ movdqu HashKey_3(%arg2), \TMP5
PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1 * b1
movaps 0x30(%arg1), \TMP3
AESENC \TMP3, \XMM1 # Round 3
@@ -1252,7 +1252,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
AESENC \TMP3, \XMM2
AESENC \TMP3, \XMM3
AESENC \TMP3, \XMM4
- movdqa HashKey_3_k(%arg2), \TMP5
+ movdqu HashKey_3_k(%arg2), \TMP5
PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
movaps 0x50(%arg1), \TMP3
AESENC \TMP3, \XMM1 # Round 5
@@ -1266,7 +1266,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
movdqa \XMM7, \TMP1
pshufd $78, \XMM7, \TMP2
pxor \XMM7, \TMP2
- movdqa HashKey_2(%arg2), \TMP5
+ movdqu HashKey_2(%arg2), \TMP5
# Multiply TMP5 * HashKey using karatsuba
@@ -1282,7 +1282,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
AESENC \TMP3, \XMM2
AESENC \TMP3, \XMM3
AESENC \TMP3, \XMM4
- movdqa HashKey_2_k(%arg2), \TMP5
+ movdqu HashKey_2_k(%arg2), \TMP5
PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
movaps 0x80(%arg1), \TMP3
AESENC \TMP3, \XMM1 # Round 8
@@ -1300,7 +1300,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation
movdqa \XMM8, \TMP1
pshufd $78, \XMM8, \TMP2
pxor \XMM8, \TMP2
- movdqa HashKey(%arg2), \TMP5
+ movdqu HashKey(%arg2), \TMP5
PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1*b1
movaps 0x90(%arg1), \TMP3
AESENC \TMP3, \XMM1 # Round 9
@@ -1329,7 +1329,7 @@ aes_loop_par_dec_done\@:
AESENCLAST \TMP3, \XMM2
AESENCLAST \TMP3, \XMM3
AESENCLAST \TMP3, \XMM4
- movdqa HashKey_k(%arg2), \TMP5
+ movdqu HashKey_k(%arg2), \TMP5
PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
movdqu (%arg4,%r11,1), \TMP3
pxor \TMP3, \XMM1 # Ciphertext/Plaintext XOR EK
@@ -1405,10 +1405,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst
movdqa \XMM1, \TMP6
pshufd $78, \XMM1, \TMP2
pxor \XMM1, \TMP2
- movdqa HashKey_4(%arg2), \TMP5
+ movdqu HashKey_4(%arg2), \TMP5
PCLMULQDQ 0x11, \TMP5, \TMP6 # TMP6 = a1*b1
PCLMULQDQ 0x00, \TMP5, \XMM1 # XMM1 = a0*b0
- movdqa HashKey_4_k(%arg2), \TMP4
+ movdqu HashKey_4_k(%arg2), \TMP4
PCLMULQDQ 0x00, \TMP4, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
movdqa \XMM1, \XMMDst
movdqa \TMP2, \XMM1 # result in TMP6, XMMDst, XMM1
@@ -1418,10 +1418,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst
movdqa \XMM2, \TMP1
pshufd $78, \XMM2, \TMP2
pxor \XMM2, \TMP2
- movdqa HashKey_3(%arg2), \TMP5
+ movdqu HashKey_3(%arg2), \TMP5
PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1*b1
PCLMULQDQ 0x00, \TMP5, \XMM2 # XMM2 = a0*b0
- movdqa HashKey_3_k(%arg2), \TMP4
+ movdqu HashKey_3_k(%arg2), \TMP4
PCLMULQDQ 0x00, \TMP4, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
pxor \TMP1, \TMP6
pxor \XMM2, \XMMDst
@@ -1433,10 +1433,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst
movdqa \XMM3, \TMP1
pshufd $78, \XMM3, \TMP2
pxor \XMM3, \TMP2
- movdqa HashKey_2(%arg2), \TMP5
+ movdqu HashKey_2(%arg2), \TMP5
PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1*b1
PCLMULQDQ 0x00, \TMP5, \XMM3 # XMM3 = a0*b0
- movdqa HashKey_2_k(%arg2), \TMP4
+ movdqu HashKey_2_k(%arg2), \TMP4
PCLMULQDQ 0x00, \TMP4, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
pxor \TMP1, \TMP6
pxor \XMM3, \XMMDst
@@ -1446,10 +1446,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst
movdqa \XMM4, \TMP1
pshufd $78, \XMM4, \TMP2
pxor \XMM4, \TMP2
- movdqa HashKey(%arg2), \TMP5
+ movdqu HashKey(%arg2), \TMP5
PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1*b1
PCLMULQDQ 0x00, \TMP5, \XMM4 # XMM4 = a0*b0
- movdqa HashKey_k(%arg2), \TMP4
+ movdqu HashKey_k(%arg2), \TMP4
PCLMULQDQ 0x00, \TMP4, \TMP2 # TMP2 = (a1+a0)*(b1+b0)
pxor \TMP1, \TMP6
pxor \XMM4, \XMMDst
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index a564084c6141..f8b1ad2c3828 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -2,6 +2,8 @@
#ifndef _ASM_X86_PGTABLE_3LEVEL_H
#define _ASM_X86_PGTABLE_3LEVEL_H
+#include <asm/atomic64_32.h>
+
/*
* Intel Physical Address Extension (PAE) Mode - three-level page
* tables on PPro+ CPUs.
@@ -150,10 +152,7 @@ static inline pte_t native_ptep_get_and_clear(pte_t *ptep)
{
pte_t res;
- /* xchg acts as a barrier before the setting of the high bits */
- res.pte_low = xchg(&ptep->pte_low, 0);
- res.pte_high = ptep->pte_high;
- ptep->pte_high = 0;
+ res.pte = (pteval_t)arch_atomic64_xchg((atomic64_t *)ptep, 0);
return res;
}
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 45b700ac5fe7..2fe5c9b1816b 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -435,14 +435,13 @@ static void xen_set_pud(pud_t *ptr, pud_t val)
static void xen_set_pte_atomic(pte_t *ptep, pte_t pte)
{
trace_xen_mmu_set_pte_atomic(ptep, pte);
- set_64bit((u64 *)ptep, native_pte_val(pte));
+ __xen_set_pte(ptep, pte);
}
static void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
{
trace_xen_mmu_pte_clear(mm, addr, ptep);
- if (!xen_batched_set_pte(ptep, native_make_pte(0)))
- native_pte_clear(mm, addr, ptep);
+ __xen_set_pte(ptep, native_make_pte(0));
}
static void xen_pmd_clear(pmd_t *pmdp)
@@ -1570,7 +1569,7 @@ static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) &
pte_val_ma(pte));
#endif
- native_set_pte(ptep, pte);
+ __xen_set_pte(ptep, pte);
}
/* Early in boot, while setting up the initial pagetable, assume
@@ -2061,7 +2060,6 @@ void __init xen_relocate_p2m(void)
pud_t *pud;
pgd_t *pgd;
unsigned long *new_p2m;
- int save_pud;
size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long));
n_pte = roundup(size, PAGE_SIZE) >> PAGE_SHIFT;
@@ -2091,7 +2089,6 @@ void __init xen_relocate_p2m(void)
pgd = __va(read_cr3_pa());
new_p2m = (unsigned long *)(2 * PGDIR_SIZE);
- save_pud = n_pud;
for (idx_pud = 0; idx_pud < n_pud; idx_pud++) {
pud = early_memremap(pud_phys, PAGE_SIZE);
clear_page(pud);
generated by cgit (git 2.34.1) at 2024-05-19 08:37:22 +0000