summaryrefslogtreecommitdiff
path: root/arch/x86/lib
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/lib')
-rw-r--r--arch/x86/lib/.gitignore4
-rw-r--r--arch/x86/lib/Makefile5
-rw-r--r--arch/x86/lib/bhi.S147
-rw-r--r--arch/x86/lib/cache-smp.c26
-rw-r--r--arch/x86/lib/clear_page_64.S9
-rw-r--r--arch/x86/lib/cmpxchg8b_emu.S2
-rw-r--r--arch/x86/lib/copy_page_64.S3
-rw-r--r--arch/x86/lib/copy_user_64.S21
-rw-r--r--arch/x86/lib/copy_user_uncached_64.S2
-rw-r--r--arch/x86/lib/delay.c4
-rw-r--r--arch/x86/lib/getuser.S21
-rw-r--r--arch/x86/lib/hweight.S3
-rw-r--r--arch/x86/lib/insn-eval.c20
-rw-r--r--arch/x86/lib/insn.c7
-rw-r--r--arch/x86/lib/iomem.c2
-rw-r--r--arch/x86/lib/kaslr.c2
-rw-r--r--arch/x86/lib/memcpy_64.S1
-rw-r--r--arch/x86/lib/memmove_64.S3
-rw-r--r--arch/x86/lib/memset_64.S4
-rw-r--r--arch/x86/lib/msr-reg.S3
-rw-r--r--arch/x86/lib/msr-smp.c16
-rw-r--r--arch/x86/lib/msr.c14
-rw-r--r--arch/x86/lib/putuser.S9
-rw-r--r--arch/x86/lib/retpoline.S53
-rw-r--r--arch/x86/lib/string_32.c17
-rw-r--r--arch/x86/lib/strstr_32.c6
-rw-r--r--arch/x86/lib/usercopy_32.c18
-rw-r--r--arch/x86/lib/usercopy_64.c2
-rw-r--r--arch/x86/lib/x86-opcode-map.txt60
29 files changed, 383 insertions, 101 deletions
diff --git a/arch/x86/lib/.gitignore b/arch/x86/lib/.gitignore
index 8ae0f93ecbfd..ec2131c9fd20 100644
--- a/arch/x86/lib/.gitignore
+++ b/arch/x86/lib/.gitignore
@@ -1,2 +1,6 @@
# SPDX-License-Identifier: GPL-2.0-only
+
+# This now-removed directory used to contain generated files.
+/crypto/
+
inat-tables.c
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 98583a9dbab3..2dba7f83ef97 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -49,7 +49,7 @@ ifeq ($(CONFIG_X86_32),y)
lib-y += string_32.o
lib-y += memmove_32.o
lib-y += cmpxchg8b_emu.o
-ifneq ($(CONFIG_X86_CMPXCHG64),y)
+ifneq ($(CONFIG_X86_CX8),y)
lib-y += atomic64_386_32.o
endif
else
@@ -59,5 +59,6 @@ endif
lib-y += clear_page_64.o copy_page_64.o
lib-y += memmove_64.o memset_64.o
lib-y += copy_user_64.o copy_user_uncached_64.o
- lib-y += cmpxchg16b_emu.o
+ lib-y += cmpxchg16b_emu.o
+ lib-y += bhi.o
endif
diff --git a/arch/x86/lib/bhi.S b/arch/x86/lib/bhi.S
new file mode 100644
index 000000000000..58891681261b
--- /dev/null
+++ b/arch/x86/lib/bhi.S
@@ -0,0 +1,147 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/linkage.h>
+#include <asm/unwind_hints.h>
+#include <asm/nospec-branch.h>
+
+/*
+ * Notably, the FineIBT preamble calling these will have ZF set and r10 zero.
+ *
+ * The very last element is in fact larger than 32 bytes, but since its the
+ * last element, this does not matter,
+ *
+ * There are 2 #UD sites, located between 0,1-2,3 and 4,5-6,7 such that they
+ * can be reached using Jcc.d8, these elements (1 and 5) have sufficiently
+ * big alignment holes for this to not stagger the array.
+ */
+
+.pushsection .noinstr.text, "ax"
+
+ .align 32
+SYM_CODE_START(__bhi_args)
+
+#ifdef CONFIG_FINEIBT_BHI
+
+ .align 32
+SYM_INNER_LABEL(__bhi_args_0, SYM_L_LOCAL)
+ ANNOTATE_NOENDBR
+ UNWIND_HINT_FUNC
+ jne .Lud_1
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+
+ .align 32
+SYM_INNER_LABEL(__bhi_args_1, SYM_L_LOCAL)
+ ANNOTATE_NOENDBR
+ UNWIND_HINT_FUNC
+ jne .Lud_1
+ cmovne %r10, %rdi
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+
+ .align 8
+ ANNOTATE_REACHABLE
+.Lud_1: ud2
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+
+ .align 32
+SYM_INNER_LABEL(__bhi_args_2, SYM_L_LOCAL)
+ ANNOTATE_NOENDBR
+ UNWIND_HINT_FUNC
+ jne .Lud_1
+ cmovne %r10, %rdi
+ cmovne %r10, %rsi
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+
+ .align 32
+SYM_INNER_LABEL(__bhi_args_3, SYM_L_LOCAL)
+ ANNOTATE_NOENDBR
+ UNWIND_HINT_FUNC
+ jne .Lud_1
+ cmovne %r10, %rdi
+ cmovne %r10, %rsi
+ cmovne %r10, %rdx
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+
+ .align 32
+SYM_INNER_LABEL(__bhi_args_4, SYM_L_LOCAL)
+ ANNOTATE_NOENDBR
+ UNWIND_HINT_FUNC
+ jne .Lud_2
+ cmovne %r10, %rdi
+ cmovne %r10, %rsi
+ cmovne %r10, %rdx
+ cmovne %r10, %rcx
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+
+ .align 32
+SYM_INNER_LABEL(__bhi_args_5, SYM_L_LOCAL)
+ ANNOTATE_NOENDBR
+ UNWIND_HINT_FUNC
+ jne .Lud_2
+ cmovne %r10, %rdi
+ cmovne %r10, %rsi
+ cmovne %r10, %rdx
+ cmovne %r10, %rcx
+ cmovne %r10, %r8
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+
+ .align 8
+ ANNOTATE_REACHABLE
+.Lud_2: ud2
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+
+ .align 32
+SYM_INNER_LABEL(__bhi_args_6, SYM_L_LOCAL)
+ ANNOTATE_NOENDBR
+ UNWIND_HINT_FUNC
+ jne .Lud_2
+ cmovne %r10, %rdi
+ cmovne %r10, %rsi
+ cmovne %r10, %rdx
+ cmovne %r10, %rcx
+ cmovne %r10, %r8
+ cmovne %r10, %r9
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+
+ .align 32
+SYM_INNER_LABEL(__bhi_args_7, SYM_L_LOCAL)
+ ANNOTATE_NOENDBR
+ UNWIND_HINT_FUNC
+ jne .Lud_2
+ cmovne %r10, %rdi
+ cmovne %r10, %rsi
+ cmovne %r10, %rdx
+ cmovne %r10, %rcx
+ cmovne %r10, %r8
+ cmovne %r10, %r9
+ cmovne %r10, %rsp
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+
+#endif /* CONFIG_FINEIBT_BHI */
+
+ .align 32
+SYM_INNER_LABEL(__bhi_args_end, SYM_L_GLOBAL)
+ ANNOTATE_NOENDBR
+ nop /* Work around toolchain+objtool quirk */
+SYM_CODE_END(__bhi_args)
+
+.popsection
diff --git a/arch/x86/lib/cache-smp.c b/arch/x86/lib/cache-smp.c
index 7af743bd3b13..c5c60d07308c 100644
--- a/arch/x86/lib/cache-smp.c
+++ b/arch/x86/lib/cache-smp.c
@@ -14,9 +14,31 @@ void wbinvd_on_cpu(int cpu)
}
EXPORT_SYMBOL(wbinvd_on_cpu);
-int wbinvd_on_all_cpus(void)
+void wbinvd_on_all_cpus(void)
{
on_each_cpu(__wbinvd, NULL, 1);
- return 0;
}
EXPORT_SYMBOL(wbinvd_on_all_cpus);
+
+void wbinvd_on_cpus_mask(struct cpumask *cpus)
+{
+ on_each_cpu_mask(cpus, __wbinvd, NULL, 1);
+}
+EXPORT_SYMBOL_GPL(wbinvd_on_cpus_mask);
+
+static void __wbnoinvd(void *dummy)
+{
+ wbnoinvd();
+}
+
+void wbnoinvd_on_all_cpus(void)
+{
+ on_each_cpu(__wbnoinvd, NULL, 1);
+}
+EXPORT_SYMBOL_GPL(wbnoinvd_on_all_cpus);
+
+void wbnoinvd_on_cpus_mask(struct cpumask *cpus)
+{
+ on_each_cpu_mask(cpus, __wbnoinvd, NULL, 1);
+}
+EXPORT_SYMBOL_GPL(wbnoinvd_on_cpus_mask);
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index 2760a15fbc00..a508e4a8c66a 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -1,6 +1,8 @@
/* SPDX-License-Identifier: GPL-2.0-only */
#include <linux/export.h>
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
+#include <linux/objtool.h>
#include <asm/asm.h>
/*
@@ -14,7 +16,7 @@
* Zero a page.
* %rdi - page
*/
-SYM_FUNC_START(clear_page_rep)
+SYM_TYPED_FUNC_START(clear_page_rep)
movl $4096/8,%ecx
xorl %eax,%eax
rep stosq
@@ -22,7 +24,7 @@ SYM_FUNC_START(clear_page_rep)
SYM_FUNC_END(clear_page_rep)
EXPORT_SYMBOL_GPL(clear_page_rep)
-SYM_FUNC_START(clear_page_orig)
+SYM_TYPED_FUNC_START(clear_page_orig)
xorl %eax,%eax
movl $4096/64,%ecx
.p2align 4
@@ -44,7 +46,7 @@ SYM_FUNC_START(clear_page_orig)
SYM_FUNC_END(clear_page_orig)
EXPORT_SYMBOL_GPL(clear_page_orig)
-SYM_FUNC_START(clear_page_erms)
+SYM_TYPED_FUNC_START(clear_page_erms)
movl $4096,%ecx
xorl %eax,%eax
rep stosb
@@ -63,6 +65,7 @@ EXPORT_SYMBOL_GPL(clear_page_erms)
* rcx: uncleared bytes or 0 if successful.
*/
SYM_FUNC_START(rep_stos_alternative)
+ ANNOTATE_NOENDBR
cmpq $64,%rcx
jae .Lunrolled
diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S
index 1c96be769adc..d4bb24347ff8 100644
--- a/arch/x86/lib/cmpxchg8b_emu.S
+++ b/arch/x86/lib/cmpxchg8b_emu.S
@@ -7,7 +7,7 @@
.text
-#ifndef CONFIG_X86_CMPXCHG64
+#ifndef CONFIG_X86_CX8
/*
* Emulate 'cmpxchg8b (%esi)' on UP
diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S
index d6ae793d08fa..d8e87fedc20d 100644
--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -3,6 +3,7 @@
#include <linux/export.h>
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
#include <asm/cpufeatures.h>
#include <asm/alternative.h>
@@ -13,7 +14,7 @@
* prefetch distance based on SMP/UP.
*/
ALIGN
-SYM_FUNC_START(copy_page)
+SYM_TYPED_FUNC_START(copy_page)
ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD
movl $4096/8, %ecx
rep movsq
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index fc9fb5d06174..06296eb69fd4 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -8,6 +8,8 @@
#include <linux/export.h>
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
+#include <linux/objtool.h>
#include <asm/cpufeatures.h>
#include <asm/alternative.h>
#include <asm/asm.h>
@@ -30,6 +32,7 @@
* it simpler for us, we can clobber rsi/rdi and rax freely.
*/
SYM_FUNC_START(rep_movs_alternative)
+ ANNOTATE_NOENDBR
cmpq $64,%rcx
jae .Llarge
@@ -74,6 +77,24 @@ SYM_FUNC_START(rep_movs_alternative)
_ASM_EXTABLE_UA( 0b, 1b)
.Llarge_movsq:
+ /* Do the first possibly unaligned word */
+0: movq (%rsi),%rax
+1: movq %rax,(%rdi)
+
+ _ASM_EXTABLE_UA( 0b, .Lcopy_user_tail)
+ _ASM_EXTABLE_UA( 1b, .Lcopy_user_tail)
+
+ /* What would be the offset to the aligned destination? */
+ leaq 8(%rdi),%rax
+ andq $-8,%rax
+ subq %rdi,%rax
+
+ /* .. and update pointers and count to match */
+ addq %rax,%rdi
+ addq %rax,%rsi
+ subq %rax,%rcx
+
+ /* make %rcx contain the number of words, %rax the remainder */
movq %rcx,%rax
shrq $3,%rcx
andl $7,%eax
diff --git a/arch/x86/lib/copy_user_uncached_64.S b/arch/x86/lib/copy_user_uncached_64.S
index 2918e36eece2..18350b343c2a 100644
--- a/arch/x86/lib/copy_user_uncached_64.S
+++ b/arch/x86/lib/copy_user_uncached_64.S
@@ -5,6 +5,7 @@
#include <linux/export.h>
#include <linux/linkage.h>
+#include <linux/objtool.h>
#include <asm/asm.h>
/*
@@ -27,6 +28,7 @@
* rax uncopied bytes or 0 if successful.
*/
SYM_FUNC_START(__copy_user_nocache)
+ ANNOTATE_NOENDBR
/* If destination is not 7-byte aligned, we'll have to align it */
testb $7,%dil
jne .Lalign
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index 23f81ca3f06b..eb2d2e1cbddd 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -75,7 +75,7 @@ static void delay_tsc(u64 cycles)
/* Allow RT tasks to run */
preempt_enable();
- rep_nop();
+ native_pause();
preempt_disable();
/*
@@ -131,7 +131,7 @@ static void delay_halt_mwaitx(u64 unused, u64 cycles)
* Use cpu_tss_rw as a cacheline-aligned, seldom accessed per-cpu
* variable as the monitor target.
*/
- __monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0);
+ __monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0);
/*
* AMD, like Intel, supports the EAX hint and EAX=0xf means, do not
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 4357ec2a0bfc..9d5654b8a72a 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -28,25 +28,22 @@
#include <linux/export.h>
#include <linux/linkage.h>
+#include <linux/objtool.h>
#include <asm/page_types.h>
#include <asm/errno.h>
#include <asm/asm-offsets.h>
#include <asm/thread_info.h>
#include <asm/asm.h>
#include <asm/smap.h>
+#include <asm/runtime-const.h>
#define ASM_BARRIER_NOSPEC ALTERNATIVE "", "lfence", X86_FEATURE_LFENCE_RDTSC
.macro check_range size:req
.if IS_ENABLED(CONFIG_X86_64)
- movq $0x0123456789abcdef,%rdx
- 1:
- .pushsection runtime_ptr_USER_PTR_MAX,"a"
- .long 1b - 8 - .
- .popsection
- cmp %rax, %rdx
- sbb %rdx, %rdx
- or %rdx, %rax
+ RUNTIME_CONST_PTR USER_PTR_MAX, rdx
+ cmp %rdx, %rax
+ cmova %rdx, %rax
.else
cmp $TASK_SIZE_MAX-\size+1, %eax
jae .Lbad_get_user
@@ -63,6 +60,7 @@
.text
SYM_FUNC_START(__get_user_1)
+ ANNOTATE_NOENDBR
check_range size=1
ASM_STAC
UACCESS movzbl (%_ASM_AX),%edx
@@ -73,6 +71,7 @@ SYM_FUNC_END(__get_user_1)
EXPORT_SYMBOL(__get_user_1)
SYM_FUNC_START(__get_user_2)
+ ANNOTATE_NOENDBR
check_range size=2
ASM_STAC
UACCESS movzwl (%_ASM_AX),%edx
@@ -83,6 +82,7 @@ SYM_FUNC_END(__get_user_2)
EXPORT_SYMBOL(__get_user_2)
SYM_FUNC_START(__get_user_4)
+ ANNOTATE_NOENDBR
check_range size=4
ASM_STAC
UACCESS movl (%_ASM_AX),%edx
@@ -93,6 +93,7 @@ SYM_FUNC_END(__get_user_4)
EXPORT_SYMBOL(__get_user_4)
SYM_FUNC_START(__get_user_8)
+ ANNOTATE_NOENDBR
#ifndef CONFIG_X86_64
xor %ecx,%ecx
#endif
@@ -112,6 +113,7 @@ EXPORT_SYMBOL(__get_user_8)
/* .. and the same for __get_user, just without the range checks */
SYM_FUNC_START(__get_user_nocheck_1)
+ ANNOTATE_NOENDBR
ASM_STAC
ASM_BARRIER_NOSPEC
UACCESS movzbl (%_ASM_AX),%edx
@@ -122,6 +124,7 @@ SYM_FUNC_END(__get_user_nocheck_1)
EXPORT_SYMBOL(__get_user_nocheck_1)
SYM_FUNC_START(__get_user_nocheck_2)
+ ANNOTATE_NOENDBR
ASM_STAC
ASM_BARRIER_NOSPEC
UACCESS movzwl (%_ASM_AX),%edx
@@ -132,6 +135,7 @@ SYM_FUNC_END(__get_user_nocheck_2)
EXPORT_SYMBOL(__get_user_nocheck_2)
SYM_FUNC_START(__get_user_nocheck_4)
+ ANNOTATE_NOENDBR
ASM_STAC
ASM_BARRIER_NOSPEC
UACCESS movl (%_ASM_AX),%edx
@@ -142,6 +146,7 @@ SYM_FUNC_END(__get_user_nocheck_4)
EXPORT_SYMBOL(__get_user_nocheck_4)
SYM_FUNC_START(__get_user_nocheck_8)
+ ANNOTATE_NOENDBR
ASM_STAC
ASM_BARRIER_NOSPEC
#ifdef CONFIG_X86_64
diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S
index 774bdf3e6f0a..edbeb3ecad38 100644
--- a/arch/x86/lib/hweight.S
+++ b/arch/x86/lib/hweight.S
@@ -1,6 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/export.h>
#include <linux/linkage.h>
+#include <linux/objtool.h>
#include <asm/asm.h>
@@ -9,6 +10,7 @@
* %rdi: w
*/
SYM_FUNC_START(__sw_hweight32)
+ ANNOTATE_NOENDBR
#ifdef CONFIG_X86_64
movl %edi, %eax # w
@@ -42,6 +44,7 @@ EXPORT_SYMBOL(__sw_hweight32)
*/
#ifdef CONFIG_X86_64
SYM_FUNC_START(__sw_hweight64)
+ ANNOTATE_NOENDBR
pushq %rdi
pushq %rdx
diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c
index 98631c0e7a11..4e385cbfd444 100644
--- a/arch/x86/lib/insn-eval.c
+++ b/arch/x86/lib/insn-eval.c
@@ -13,6 +13,7 @@
#include <asm/insn.h>
#include <asm/insn-eval.h>
#include <asm/ldt.h>
+#include <asm/msr.h>
#include <asm/vm86.h>
#undef pr_fmt
@@ -631,14 +632,21 @@ static bool get_desc(struct desc_struct *out, unsigned short sel)
/* Bits [15:3] contain the index of the desired entry. */
sel >>= 3;
- mutex_lock(&current->active_mm->context.lock);
- ldt = current->active_mm->context.ldt;
+ /*
+ * If we're not in a valid context with a real (not just lazy)
+ * user mm, then don't even try.
+ */
+ if (!nmi_uaccess_okay())
+ return false;
+
+ mutex_lock(&current->mm->context.lock);
+ ldt = current->mm->context.ldt;
if (ldt && sel < ldt->nr_entries) {
*out = ldt->entries[sel];
success = true;
}
- mutex_unlock(&current->active_mm->context.lock);
+ mutex_unlock(&current->mm->context.lock);
return success;
}
@@ -702,16 +710,16 @@ unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx)
unsigned long base;
if (seg_reg_idx == INAT_SEG_REG_FS) {
- rdmsrl(MSR_FS_BASE, base);
+ rdmsrq(MSR_FS_BASE, base);
} else if (seg_reg_idx == INAT_SEG_REG_GS) {
/*
* swapgs was called at the kernel entry point. Thus,
* MSR_KERNEL_GS_BASE will have the user-space GS base.
*/
if (user_mode(regs))
- rdmsrl(MSR_KERNEL_GS_BASE, base);
+ rdmsrq(MSR_KERNEL_GS_BASE, base);
else
- rdmsrl(MSR_GS_BASE, base);
+ rdmsrq(MSR_GS_BASE, base);
} else {
base = 0;
}
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 6ffb931b9fb1..149a57e334ab 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -324,6 +324,11 @@ int insn_get_opcode(struct insn *insn)
}
insn->attr = inat_get_opcode_attribute(op);
+ if (insn->x86_64 && inat_is_invalid64(insn->attr)) {
+ /* This instruction is invalid, like UD2. Stop decoding. */
+ insn->attr &= INAT_INV64;
+ }
+
while (inat_is_escape(insn->attr)) {
/* Get escaped opcode */
op = get_next(insn_byte_t, insn);
@@ -337,6 +342,7 @@ int insn_get_opcode(struct insn *insn)
insn->attr = 0;
return -EINVAL;
}
+
end:
opcode->got = 1;
return 0;
@@ -658,7 +664,6 @@ int insn_get_immediate(struct insn *insn)
}
if (!inat_has_immediate(insn->attr))
- /* no immediates */
goto done;
switch (inat_immediate_size(insn->attr)) {
diff --git a/arch/x86/lib/iomem.c b/arch/x86/lib/iomem.c
index 5eecb45d05d5..c20e04764edc 100644
--- a/arch/x86/lib/iomem.c
+++ b/arch/x86/lib/iomem.c
@@ -10,7 +10,7 @@
static __always_inline void rep_movs(void *to, const void *from, size_t n)
{
unsigned long d0, d1, d2;
- asm volatile("rep ; movsl\n\t"
+ asm volatile("rep movsl\n\t"
"testb $2,%b4\n\t"
"je 1f\n\t"
"movsw\n"
diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c
index a58f451a7dd3..b5893928d55c 100644
--- a/arch/x86/lib/kaslr.c
+++ b/arch/x86/lib/kaslr.c
@@ -8,7 +8,7 @@
*/
#include <asm/asm.h>
#include <asm/kaslr.h>
-#include <asm/msr.h>
+#include <asm/tsc.h>
#include <asm/archrandom.h>
#include <asm/e820/api.h>
#include <asm/shared/io.h>
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 0ae2e1712e2e..12a23fa7c44c 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -41,6 +41,7 @@ SYM_FUNC_END(__memcpy)
EXPORT_SYMBOL(__memcpy)
SYM_FUNC_ALIAS_MEMFUNC(memcpy, __memcpy)
+SYM_PIC_ALIAS(memcpy)
EXPORT_SYMBOL(memcpy)
SYM_FUNC_START_LOCAL(memcpy_orig)
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 1b60ae81ecd8..aa1f92ee6b2e 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -8,6 +8,7 @@
*/
#include <linux/export.h>
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
#include <asm/cpufeatures.h>
#include <asm/alternative.h>
@@ -26,7 +27,7 @@
* Output:
* rax: dest
*/
-SYM_FUNC_START(__memmove)
+SYM_TYPED_FUNC_START(__memmove)
mov %rdi, %rax
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 0199d56cb479..fb5a03cf5ab7 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -3,6 +3,7 @@
#include <linux/export.h>
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
#include <asm/cpufeatures.h>
#include <asm/alternative.h>
@@ -28,7 +29,7 @@
* only for the return value that is the same as the source input,
* which the compiler could/should do much better anyway.
*/
-SYM_FUNC_START(__memset)
+SYM_TYPED_FUNC_START(__memset)
ALTERNATIVE "jmp memset_orig", "", X86_FEATURE_FSRS
movq %rdi,%r9
@@ -41,6 +42,7 @@ SYM_FUNC_END(__memset)
EXPORT_SYMBOL(__memset)
SYM_FUNC_ALIAS_MEMFUNC(memset, __memset)
+SYM_PIC_ALIAS(memset)
EXPORT_SYMBOL(memset)
SYM_FUNC_START_LOCAL(memset_orig)
diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S
index ebd259f31496..5ef8494896e8 100644
--- a/arch/x86/lib/msr-reg.S
+++ b/arch/x86/lib/msr-reg.S
@@ -1,6 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/linkage.h>
#include <linux/errno.h>
+#include <linux/cfi_types.h>
#include <asm/asm.h>
#include <asm/msr.h>
@@ -12,7 +13,7 @@
*
*/
.macro op_safe_regs op
-SYM_FUNC_START(\op\()_safe_regs)
+SYM_TYPED_FUNC_START(\op\()_safe_regs)
pushq %rbx
pushq %r12
movq %rdi, %r10 /* Save pointer */
diff --git a/arch/x86/lib/msr-smp.c b/arch/x86/lib/msr-smp.c
index acd463d887e1..b8f63419e6ae 100644
--- a/arch/x86/lib/msr-smp.c
+++ b/arch/x86/lib/msr-smp.c
@@ -47,7 +47,7 @@ int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
}
EXPORT_SYMBOL(rdmsr_on_cpu);
-int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
+int rdmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
{
int err;
struct msr_info rv;
@@ -60,7 +60,7 @@ int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
return err;
}
-EXPORT_SYMBOL(rdmsrl_on_cpu);
+EXPORT_SYMBOL(rdmsrq_on_cpu);
int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
{
@@ -78,7 +78,7 @@ int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
}
EXPORT_SYMBOL(wrmsr_on_cpu);
-int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
+int wrmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
{
int err;
struct msr_info rv;
@@ -92,7 +92,7 @@ int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
return err;
}
-EXPORT_SYMBOL(wrmsrl_on_cpu);
+EXPORT_SYMBOL(wrmsrq_on_cpu);
static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no,
struct msr __percpu *msrs,
@@ -204,7 +204,7 @@ int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
}
EXPORT_SYMBOL(wrmsr_safe_on_cpu);
-int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
+int wrmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
{
int err;
struct msr_info rv;
@@ -218,9 +218,9 @@ int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
return err ? err : rv.err;
}
-EXPORT_SYMBOL(wrmsrl_safe_on_cpu);
+EXPORT_SYMBOL(wrmsrq_safe_on_cpu);
-int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
+int rdmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
{
u32 low, high;
int err;
@@ -230,7 +230,7 @@ int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
return err;
}
-EXPORT_SYMBOL(rdmsrl_safe_on_cpu);
+EXPORT_SYMBOL(rdmsrq_safe_on_cpu);
/*
* These variants are significantly slower, but allows control over
diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c
index 4bf4fad5b148..4ef7c6dcbea6 100644
--- a/arch/x86/lib/msr.c
+++ b/arch/x86/lib/msr.c
@@ -41,7 +41,7 @@ static int msr_read(u32 msr, struct msr *m)
int err;
u64 val;
- err = rdmsrl_safe(msr, &val);
+ err = rdmsrq_safe(msr, &val);
if (!err)
m->q = val;
@@ -58,7 +58,7 @@ static int msr_read(u32 msr, struct msr *m)
*/
static int msr_write(u32 msr, struct msr *m)
{
- return wrmsrl_safe(msr, m->q);
+ return wrmsrq_safe(msr, m->q);
}
static inline int __flip_bit(u32 msr, u8 bit, bool set)
@@ -103,6 +103,7 @@ int msr_set_bit(u32 msr, u8 bit)
{
return __flip_bit(msr, bit, true);
}
+EXPORT_SYMBOL_GPL(msr_set_bit);
/**
* msr_clear_bit - Clear @bit in a MSR @msr.
@@ -118,25 +119,26 @@ int msr_clear_bit(u32 msr, u8 bit)
{
return __flip_bit(msr, bit, false);
}
+EXPORT_SYMBOL_GPL(msr_clear_bit);
#ifdef CONFIG_TRACEPOINTS
-void do_trace_write_msr(unsigned int msr, u64 val, int failed)
+void do_trace_write_msr(u32 msr, u64 val, int failed)
{
trace_write_msr(msr, val, failed);
}
EXPORT_SYMBOL(do_trace_write_msr);
EXPORT_TRACEPOINT_SYMBOL(write_msr);
-void do_trace_read_msr(unsigned int msr, u64 val, int failed)
+void do_trace_read_msr(u32 msr, u64 val, int failed)
{
trace_read_msr(msr, val, failed);
}
EXPORT_SYMBOL(do_trace_read_msr);
EXPORT_TRACEPOINT_SYMBOL(read_msr);
-void do_trace_rdpmc(unsigned counter, u64 val, int failed)
+void do_trace_rdpmc(u32 msr, u64 val, int failed)
{
- trace_rdpmc(counter, val, failed);
+ trace_rdpmc(msr, val, failed);
}
EXPORT_SYMBOL(do_trace_rdpmc);
EXPORT_TRACEPOINT_SYMBOL(rdpmc);
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index 975c9c18263d..46d9e9b98a61 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -13,6 +13,7 @@
*/
#include <linux/export.h>
#include <linux/linkage.h>
+#include <linux/objtool.h>
#include <asm/thread_info.h>
#include <asm/errno.h>
#include <asm/asm.h>
@@ -45,6 +46,7 @@
.text
SYM_FUNC_START(__put_user_1)
+ ANNOTATE_NOENDBR
check_range size=1
ASM_STAC
1: movb %al,(%_ASM_CX)
@@ -55,6 +57,7 @@ SYM_FUNC_END(__put_user_1)
EXPORT_SYMBOL(__put_user_1)
SYM_FUNC_START(__put_user_nocheck_1)
+ ANNOTATE_NOENDBR
ASM_STAC
2: movb %al,(%_ASM_CX)
xor %ecx,%ecx
@@ -64,6 +67,7 @@ SYM_FUNC_END(__put_user_nocheck_1)
EXPORT_SYMBOL(__put_user_nocheck_1)
SYM_FUNC_START(__put_user_2)
+ ANNOTATE_NOENDBR
check_range size=2
ASM_STAC
3: movw %ax,(%_ASM_CX)
@@ -74,6 +78,7 @@ SYM_FUNC_END(__put_user_2)
EXPORT_SYMBOL(__put_user_2)
SYM_FUNC_START(__put_user_nocheck_2)
+ ANNOTATE_NOENDBR
ASM_STAC
4: movw %ax,(%_ASM_CX)
xor %ecx,%ecx
@@ -83,6 +88,7 @@ SYM_FUNC_END(__put_user_nocheck_2)
EXPORT_SYMBOL(__put_user_nocheck_2)
SYM_FUNC_START(__put_user_4)
+ ANNOTATE_NOENDBR
check_range size=4
ASM_STAC
5: movl %eax,(%_ASM_CX)
@@ -93,6 +99,7 @@ SYM_FUNC_END(__put_user_4)
EXPORT_SYMBOL(__put_user_4)
SYM_FUNC_START(__put_user_nocheck_4)
+ ANNOTATE_NOENDBR
ASM_STAC
6: movl %eax,(%_ASM_CX)
xor %ecx,%ecx
@@ -102,6 +109,7 @@ SYM_FUNC_END(__put_user_nocheck_4)
EXPORT_SYMBOL(__put_user_nocheck_4)
SYM_FUNC_START(__put_user_8)
+ ANNOTATE_NOENDBR
check_range size=8
ASM_STAC
7: mov %_ASM_AX,(%_ASM_CX)
@@ -115,6 +123,7 @@ SYM_FUNC_END(__put_user_8)
EXPORT_SYMBOL(__put_user_8)
SYM_FUNC_START(__put_user_nocheck_8)
+ ANNOTATE_NOENDBR
ASM_STAC
9: mov %_ASM_AX,(%_ASM_CX)
#ifdef CONFIG_X86_32
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 391059b2c6fb..d78d769a02bd 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -40,6 +40,7 @@ SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL)
ALTERNATIVE_2 __stringify(RETPOLINE \reg), \
__stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg; int3), X86_FEATURE_RETPOLINE_LFENCE, \
__stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), ALT_NOT(X86_FEATURE_RETPOLINE)
+SYM_PIC_ALIAS(__x86_indirect_thunk_\reg)
.endm
@@ -326,6 +327,7 @@ SYM_FUNC_END(retbleed_untrain_ret)
#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)
SYM_FUNC_START(entry_untrain_ret)
+ ANNOTATE_NOENDBR
ALTERNATIVE JMP_RETBLEED_UNTRAIN_RET, JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO
SYM_FUNC_END(entry_untrain_ret)
__EXPORT_THUNK(entry_untrain_ret)
@@ -342,7 +344,7 @@ SYM_FUNC_START(call_depth_return_thunk)
* case.
*/
CALL_THUNKS_DEBUG_INC_RETS
- shlq $5, PER_CPU_VAR(pcpu_hot + X86_call_depth)
+ shlq $5, PER_CPU_VAR(__x86_call_depth)
jz 1f
ANNOTATE_UNRET_SAFE
ret
@@ -366,6 +368,54 @@ SYM_FUNC_END(call_depth_return_thunk)
#endif /* CONFIG_MITIGATION_CALL_DEPTH_TRACKING */
+#ifdef CONFIG_MITIGATION_ITS
+
+.macro ITS_THUNK reg
+
+/*
+ * If CFI paranoid is used then the ITS thunk starts with opcodes (0xea; jne 1b)
+ * that complete the fineibt_paranoid caller sequence.
+ */
+1: .byte 0xea
+SYM_INNER_LABEL(__x86_indirect_paranoid_thunk_\reg, SYM_L_GLOBAL)
+ UNWIND_HINT_UNDEFINED
+ ANNOTATE_NOENDBR
+ jne 1b
+SYM_INNER_LABEL(__x86_indirect_its_thunk_\reg, SYM_L_GLOBAL)
+ UNWIND_HINT_UNDEFINED
+ ANNOTATE_NOENDBR
+ ANNOTATE_RETPOLINE_SAFE
+ jmp *%\reg
+ int3
+ .align 32, 0xcc /* fill to the end of the line */
+ .skip 32 - (__x86_indirect_its_thunk_\reg - 1b), 0xcc /* skip to the next upper half */
+.endm
+
+/* ITS mitigation requires thunks be aligned to upper half of cacheline */
+.align 64, 0xcc
+.skip 29, 0xcc
+
+#define GEN(reg) ITS_THUNK reg
+#include <asm/GEN-for-each-reg.h>
+#undef GEN
+
+ .align 64, 0xcc
+SYM_FUNC_ALIAS(__x86_indirect_its_thunk_array, __x86_indirect_its_thunk_rax)
+SYM_CODE_END(__x86_indirect_its_thunk_array)
+
+.align 64, 0xcc
+.skip 32, 0xcc
+SYM_CODE_START(its_return_thunk)
+ UNWIND_HINT_FUNC
+ ANNOTATE_NOENDBR
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+SYM_CODE_END(its_return_thunk)
+EXPORT_SYMBOL(its_return_thunk)
+
+#endif /* CONFIG_MITIGATION_ITS */
+
/*
* This function name is magical and is used by -mfunction-return=thunk-extern
* for the compiler to generate JMPs to it.
@@ -393,6 +443,7 @@ SYM_CODE_START(__x86_return_thunk)
#endif
int3
SYM_CODE_END(__x86_return_thunk)
+SYM_PIC_ALIAS(__x86_return_thunk)
EXPORT_SYMBOL(__x86_return_thunk)
#endif /* CONFIG_MITIGATION_RETHUNK */
diff --git a/arch/x86/lib/string_32.c b/arch/x86/lib/string_32.c
index 53b3f202267c..f87ec24fa579 100644
--- a/arch/x86/lib/string_32.c
+++ b/arch/x86/lib/string_32.c
@@ -40,8 +40,7 @@ char *strncpy(char *dest, const char *src, size_t count)
"stosb\n\t"
"testb %%al,%%al\n\t"
"jne 1b\n\t"
- "rep\n\t"
- "stosb\n"
+ "rep stosb\n"
"2:"
: "=&S" (d0), "=&D" (d1), "=&c" (d2), "=&a" (d3)
: "0" (src), "1" (dest), "2" (count) : "memory");
@@ -54,8 +53,7 @@ EXPORT_SYMBOL(strncpy);
char *strcat(char *dest, const char *src)
{
int d0, d1, d2, d3;
- asm volatile("repne\n\t"
- "scasb\n\t"
+ asm volatile("repne scasb\n\t"
"decl %1\n"
"1:\tlodsb\n\t"
"stosb\n\t"
@@ -72,8 +70,7 @@ EXPORT_SYMBOL(strcat);
char *strncat(char *dest, const char *src, size_t count)
{
int d0, d1, d2, d3;
- asm volatile("repne\n\t"
- "scasb\n\t"
+ asm volatile("repne scasb\n\t"
"decl %1\n\t"
"movl %8,%3\n"
"1:\tdecl %3\n\t"
@@ -167,8 +164,7 @@ size_t strlen(const char *s)
{
int d0;
size_t res;
- asm volatile("repne\n\t"
- "scasb"
+ asm volatile("repne scasb"
: "=c" (res), "=&D" (d0)
: "1" (s), "a" (0), "0" (0xffffffffu)
: "memory");
@@ -184,8 +180,7 @@ void *memchr(const void *cs, int c, size_t count)
void *res;
if (!count)
return NULL;
- asm volatile("repne\n\t"
- "scasb\n\t"
+ asm volatile("repne scasb\n\t"
"je 1f\n\t"
"movl $1,%0\n"
"1:\tdecl %0"
@@ -202,7 +197,7 @@ void *memscan(void *addr, int c, size_t size)
{
if (!size)
return addr;
- asm volatile("repnz; scasb\n\t"
+ asm volatile("repnz scasb\n\t"
"jnz 1f\n\t"
"dec %%edi\n"
"1:"
diff --git a/arch/x86/lib/strstr_32.c b/arch/x86/lib/strstr_32.c
index 38f37df056f7..28267985e85f 100644
--- a/arch/x86/lib/strstr_32.c
+++ b/arch/x86/lib/strstr_32.c
@@ -8,16 +8,14 @@ int d0, d1;
register char *__res;
__asm__ __volatile__(
"movl %6,%%edi\n\t"
- "repne\n\t"
- "scasb\n\t"
+ "repne scasb\n\t"
"notl %%ecx\n\t"
"decl %%ecx\n\t" /* NOTE! This also sets Z if searchstring='' */
"movl %%ecx,%%edx\n"
"1:\tmovl %6,%%edi\n\t"
"movl %%esi,%%eax\n\t"
"movl %%edx,%%ecx\n\t"
- "repe\n\t"
- "cmpsb\n\t"
+ "repe cmpsb\n\t"
"je 2f\n\t" /* also works for empty string, see above */
"xchgl %%eax,%%esi\n\t"
"incl %%esi\n\t"
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 422257c350c6..f6f436f1d573 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -38,9 +38,9 @@ do { \
might_fault(); \
__asm__ __volatile__( \
ASM_STAC "\n" \
- "0: rep; stosl\n" \
+ "0: rep stosl\n" \
" movl %2,%0\n" \
- "1: rep; stosb\n" \
+ "1: rep stosb\n" \
"2: " ASM_CLAC "\n" \
_ASM_EXTABLE_TYPE_REG(0b, 2b, EX_TYPE_UCOPY_LEN4, %2) \
_ASM_EXTABLE_UA(1b, 2b) \
@@ -140,9 +140,9 @@ __copy_user_intel(void __user *to, const void *from, unsigned long size)
" shrl $2, %0\n"
" andl $3, %%eax\n"
" cld\n"
- "99: rep; movsl\n"
+ "99: rep movsl\n"
"36: movl %%eax, %0\n"
- "37: rep; movsb\n"
+ "37: rep movsb\n"
"100:\n"
_ASM_EXTABLE_UA(1b, 100b)
_ASM_EXTABLE_UA(2b, 100b)
@@ -242,9 +242,9 @@ static unsigned long __copy_user_intel_nocache(void *to,
" shrl $2, %0\n"
" andl $3, %%eax\n"
" cld\n"
- "6: rep; movsl\n"
+ "6: rep movsl\n"
" movl %%eax,%0\n"
- "7: rep; movsb\n"
+ "7: rep movsb\n"
"8:\n"
_ASM_EXTABLE_UA(0b, 8b)
_ASM_EXTABLE_UA(1b, 8b)
@@ -293,14 +293,14 @@ do { \
" negl %0\n" \
" andl $7,%0\n" \
" subl %0,%3\n" \
- "4: rep; movsb\n" \
+ "4: rep movsb\n" \
" movl %3,%0\n" \
" shrl $2,%0\n" \
" andl $3,%3\n" \
" .align 2,0x90\n" \
- "0: rep; movsl\n" \
+ "0: rep movsl\n" \
" movl %3,%0\n" \
- "1: rep; movsb\n" \
+ "1: rep movsb\n" \
"2:\n" \
_ASM_EXTABLE_TYPE_REG(4b, 2b, EX_TYPE_UCOPY_LEN1, %3) \
_ASM_EXTABLE_TYPE_REG(0b, 2b, EX_TYPE_UCOPY_LEN4, %3) \
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index e9251b89a9e9..654280aaa3e9 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -18,7 +18,7 @@
#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
/**
* clean_cache_range - write back a cache range with CLWB
- * @vaddr: virtual start address
+ * @addr: virtual start address
* @size: number of bytes to write back
*
* Write back a cache range using the CLWB (cache line write back)
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index caedb3ef6688..262f7ca1fb95 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -35,7 +35,7 @@
# - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
# - (66&F2): Both 0x66 and 0xF2 prefixes are specified.
#
-# REX2 Prefix
+# REX2 Prefix Superscripts
# - (!REX2): REX2 is not allowed
# - (REX2): REX2 variant e.g. JMPABS
@@ -147,7 +147,7 @@ AVXcode:
# 0x60 - 0x6f
60: PUSHA/PUSHAD (i64)
61: POPA/POPAD (i64)
-62: BOUND Gv,Ma (i64) | EVEX (Prefix)
+62: BOUND Gv,Ma (i64) | EVEX (Prefix),(o64)
63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64)
64: SEG=FS (Prefix)
65: SEG=GS (Prefix)
@@ -253,8 +253,8 @@ c0: Grp2 Eb,Ib (1A)
c1: Grp2 Ev,Ib (1A)
c2: RETN Iw (f64)
c3: RETN
-c4: LES Gz,Mp (i64) | VEX+2byte (Prefix)
-c5: LDS Gz,Mp (i64) | VEX+1byte (Prefix)
+c4: LES Gz,Mp (i64) | VEX+2byte (Prefix),(o64)
+c5: LDS Gz,Mp (i64) | VEX+1byte (Prefix),(o64)
c6: Grp11A Eb,Ib (1A)
c7: Grp11B Ev,Iz (1A)
c8: ENTER Iw,Ib
@@ -286,10 +286,10 @@ df: ESC
# Note: "forced64" is Intel CPU behavior: they ignore 0x66 prefix
# in 64-bit mode. AMD CPUs accept 0x66 prefix, it causes RIP truncation
# to 16 bits. In 32-bit mode, 0x66 is accepted by both Intel and AMD.
-e0: LOOPNE/LOOPNZ Jb (f64) (!REX2)
-e1: LOOPE/LOOPZ Jb (f64) (!REX2)
-e2: LOOP Jb (f64) (!REX2)
-e3: JrCXZ Jb (f64) (!REX2)
+e0: LOOPNE/LOOPNZ Jb (f64),(!REX2)
+e1: LOOPE/LOOPZ Jb (f64),(!REX2)
+e2: LOOP Jb (f64),(!REX2)
+e3: JrCXZ Jb (f64),(!REX2)
e4: IN AL,Ib (!REX2)
e5: IN eAX,Ib (!REX2)
e6: OUT Ib,AL (!REX2)
@@ -298,10 +298,10 @@ e7: OUT Ib,eAX (!REX2)
# in "near" jumps and calls is 16-bit. For CALL,
# push of return address is 16-bit wide, RSP is decremented by 2
# but is not truncated to 16 bits, unlike RIP.
-e8: CALL Jz (f64) (!REX2)
-e9: JMP-near Jz (f64) (!REX2)
-ea: JMP-far Ap (i64) (!REX2)
-eb: JMP-short Jb (f64) (!REX2)
+e8: CALL Jz (f64),(!REX2)
+e9: JMP-near Jz (f64),(!REX2)
+ea: JMP-far Ap (i64),(!REX2)
+eb: JMP-short Jb (f64),(!REX2)
ec: IN AL,DX (!REX2)
ed: IN eAX,DX (!REX2)
ee: OUT DX,AL (!REX2)
@@ -478,22 +478,22 @@ AVXcode: 1
7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev)
# 0x0f 0x80-0x8f
# Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
-80: JO Jz (f64) (!REX2)
-81: JNO Jz (f64) (!REX2)
-82: JB/JC/JNAE Jz (f64) (!REX2)
-83: JAE/JNB/JNC Jz (f64) (!REX2)
-84: JE/JZ Jz (f64) (!REX2)
-85: JNE/JNZ Jz (f64) (!REX2)
-86: JBE/JNA Jz (f64) (!REX2)
-87: JA/JNBE Jz (f64) (!REX2)
-88: JS Jz (f64) (!REX2)
-89: JNS Jz (f64) (!REX2)
-8a: JP/JPE Jz (f64) (!REX2)
-8b: JNP/JPO Jz (f64) (!REX2)
-8c: JL/JNGE Jz (f64) (!REX2)
-8d: JNL/JGE Jz (f64) (!REX2)
-8e: JLE/JNG Jz (f64) (!REX2)
-8f: JNLE/JG Jz (f64) (!REX2)
+80: JO Jz (f64),(!REX2)
+81: JNO Jz (f64),(!REX2)
+82: JB/JC/JNAE Jz (f64),(!REX2)
+83: JAE/JNB/JNC Jz (f64),(!REX2)
+84: JE/JZ Jz (f64),(!REX2)
+85: JNE/JNZ Jz (f64),(!REX2)
+86: JBE/JNA Jz (f64),(!REX2)
+87: JA/JNBE Jz (f64),(!REX2)
+88: JS Jz (f64),(!REX2)
+89: JNS Jz (f64),(!REX2)
+8a: JP/JPE Jz (f64),(!REX2)
+8b: JNP/JPO Jz (f64),(!REX2)
+8c: JL/JNGE Jz (f64),(!REX2)
+8d: JNL/JGE Jz (f64),(!REX2)
+8e: JLE/JNG Jz (f64),(!REX2)
+8f: JNLE/JG Jz (f64),(!REX2)
# 0x0f 0x90-0x9f
90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66)
91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66)
@@ -996,8 +996,8 @@ AVXcode: 4
83: Grp1 Ev,Ib (1A),(es)
# CTESTSCC instructions are: CTESTB, CTESTBE, CTESTF, CTESTL, CTESTLE, CTESTNB, CTESTNBE, CTESTNL,
# CTESTNLE, CTESTNO, CTESTNS, CTESTNZ, CTESTO, CTESTS, CTESTT, CTESTZ
-84: CTESTSCC (ev)
-85: CTESTSCC (es) | CTESTSCC (66),(es)
+84: CTESTSCC Eb,Gb (ev)
+85: CTESTSCC Ev,Gv (es) | CTESTSCC Ev,Gv (66),(es)
88: POPCNT Gv,Ev (es) | POPCNT Gv,Ev (66),(es)
8f: POP2 Bq,Rq (000),(11B),(ev)
a5: SHLD Ev,Gv,CL (es) | SHLD Ev,Gv,CL (66),(es)