summaryrefslogtreecommitdiffstats
path: root/arch/x86/lib
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-11 08:27:49 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-11 08:27:49 +0000
commitace9429bb58fd418f0c81d4c2835699bddf6bde6 (patch)
treeb2d64bc10158fdd5497876388cd68142ca374ed3 /arch/x86/lib
parentInitial commit. (diff)
downloadlinux-ace9429bb58fd418f0c81d4c2835699bddf6bde6.tar.xz
linux-ace9429bb58fd418f0c81d4c2835699bddf6bde6.zip
Adding upstream version 6.6.15.upstream/6.6.15
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'arch/x86/lib')
-rw-r--r--arch/x86/lib/.gitignore2
-rw-r--r--arch/x86/lib/Makefile77
-rw-r--r--arch/x86/lib/atomic64_32.c4
-rw-r--r--arch/x86/lib/atomic64_386_32.S195
-rw-r--r--arch/x86/lib/atomic64_cx8_32.S180
-rw-r--r--arch/x86/lib/cache-smp.c21
-rw-r--r--arch/x86/lib/checksum_32.S444
-rw-r--r--arch/x86/lib/clear_page_64.S141
-rw-r--r--arch/x86/lib/cmdline.c216
-rw-r--r--arch/x86/lib/cmpxchg16b_emu.S54
-rw-r--r--arch/x86/lib/cmpxchg8b_emu.S85
-rw-r--r--arch/x86/lib/copy_mc.c92
-rw-r--r--arch/x86/lib/copy_mc_64.S149
-rw-r--r--arch/x86/lib/copy_page_64.S89
-rw-r--r--arch/x86/lib/copy_user_64.S91
-rw-r--r--arch/x86/lib/copy_user_uncached_64.S242
-rw-r--r--arch/x86/lib/cpu.c38
-rw-r--r--arch/x86/lib/csum-copy_64.S256
-rw-r--r--arch/x86/lib/csum-partial_64.c123
-rw-r--r--arch/x86/lib/csum-wrappers_64.c97
-rw-r--r--arch/x86/lib/delay.c231
-rw-r--r--arch/x86/lib/error-inject.c25
-rw-r--r--arch/x86/lib/getuser.S185
-rw-r--r--arch/x86/lib/hweight.S83
-rw-r--r--arch/x86/lib/inat.c83
-rw-r--r--arch/x86/lib/insn-eval.c1670
-rw-r--r--arch/x86/lib/insn.c755
-rw-r--r--arch/x86/lib/iomap_copy_64.S15
-rw-r--r--arch/x86/lib/iomem.c123
-rw-r--r--arch/x86/lib/kaslr.c98
-rw-r--r--arch/x86/lib/memcpy_32.c19
-rw-r--r--arch/x86/lib/memcpy_64.S172
-rw-r--r--arch/x86/lib/memmove_32.S200
-rw-r--r--arch/x86/lib/memmove_64.S216
-rw-r--r--arch/x86/lib/memset_64.S117
-rw-r--r--arch/x86/lib/misc.c24
-rw-r--r--arch/x86/lib/msr-reg-export.c6
-rw-r--r--arch/x86/lib/msr-reg.S93
-rw-r--r--arch/x86/lib/msr-smp.c279
-rw-r--r--arch/x86/lib/msr.c144
-rw-r--r--arch/x86/lib/pc-conf-reg.c13
-rw-r--r--arch/x86/lib/putuser.S148
-rw-r--r--arch/x86/lib/retpoline.S361
-rw-r--r--arch/x86/lib/string_32.c237
-rw-r--r--arch/x86/lib/strstr_32.c33
-rw-r--r--arch/x86/lib/usercopy.c55
-rw-r--r--arch/x86/lib/usercopy_32.c340
-rw-r--r--arch/x86/lib/usercopy_64.c144
-rw-r--r--arch/x86/lib/x86-opcode-map.txt1189
49 files changed, 9654 insertions, 0 deletions
diff --git a/arch/x86/lib/.gitignore b/arch/x86/lib/.gitignore
new file mode 100644
index 0000000000..8ae0f93ecb
--- /dev/null
+++ b/arch/x86/lib/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+inat-tables.c
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
new file mode 100644
index 0000000000..ea3a28e7b6
--- /dev/null
+++ b/arch/x86/lib/Makefile
@@ -0,0 +1,77 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for x86 specific library files.
+#
+
+# Produces uninteresting flaky coverage.
+KCOV_INSTRUMENT_delay.o := n
+
+# KCSAN uses udelay for introducing watchpoint delay; avoid recursion.
+KCSAN_SANITIZE_delay.o := n
+ifdef CONFIG_KCSAN
+# In case KCSAN+lockdep+ftrace are enabled, disable ftrace for delay.o to avoid
+# lockdep -> [other libs] -> KCSAN -> udelay -> ftrace -> lockdep recursion.
+CFLAGS_REMOVE_delay.o = $(CC_FLAGS_FTRACE)
+endif
+
+# Early boot use of cmdline; don't instrument it
+ifdef CONFIG_AMD_MEM_ENCRYPT
+KCOV_INSTRUMENT_cmdline.o := n
+KASAN_SANITIZE_cmdline.o := n
+KCSAN_SANITIZE_cmdline.o := n
+
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_cmdline.o = -pg
+endif
+
+CFLAGS_cmdline.o := -fno-stack-protector -fno-jump-tables
+endif
+
+inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk
+inat_tables_maps = $(srctree)/arch/x86/lib/x86-opcode-map.txt
+quiet_cmd_inat_tables = GEN $@
+ cmd_inat_tables = $(AWK) -f $(inat_tables_script) $(inat_tables_maps) > $@
+
+$(obj)/inat-tables.c: $(inat_tables_script) $(inat_tables_maps)
+ $(call cmd,inat_tables)
+
+$(obj)/inat.o: $(obj)/inat-tables.c
+
+clean-files := inat-tables.c
+
+obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o
+
+lib-y := delay.o misc.o cmdline.o cpu.o
+lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o
+lib-y += memcpy_$(BITS).o
+lib-y += pc-conf-reg.o
+lib-$(CONFIG_ARCH_HAS_COPY_MC) += copy_mc.o copy_mc_64.o
+lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o
+lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
+lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
+lib-$(CONFIG_RETPOLINE) += retpoline.o
+
+obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o
+obj-y += iomem.o
+
+ifeq ($(CONFIG_X86_32),y)
+ obj-y += atomic64_32.o
+ lib-y += atomic64_cx8_32.o
+ lib-y += checksum_32.o
+ lib-y += strstr_32.o
+ lib-y += string_32.o
+ lib-y += memmove_32.o
+ lib-y += cmpxchg8b_emu.o
+ifneq ($(CONFIG_X86_CMPXCHG64),y)
+ lib-y += atomic64_386_32.o
+endif
+else
+ obj-y += iomap_copy_64.o
+ifneq ($(CONFIG_GENERIC_CSUM),y)
+ lib-y += csum-partial_64.o csum-copy_64.o csum-wrappers_64.o
+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
+endif
diff --git a/arch/x86/lib/atomic64_32.c b/arch/x86/lib/atomic64_32.c
new file mode 100644
index 0000000000..a0b4a350da
--- /dev/null
+++ b/arch/x86/lib/atomic64_32.c
@@ -0,0 +1,4 @@
+#define ATOMIC64_EXPORT EXPORT_SYMBOL
+
+#include <linux/export.h>
+#include <linux/atomic.h>
diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S
new file mode 100644
index 0000000000..e768815e58
--- /dev/null
+++ b/arch/x86/lib/atomic64_386_32.S
@@ -0,0 +1,195 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * atomic64_t for 386/486
+ *
+ * Copyright © 2010 Luca Barbieri
+ */
+
+#include <linux/linkage.h>
+#include <asm/alternative.h>
+
+/* if you want SMP support, implement these with real spinlocks */
+.macro IRQ_SAVE reg
+ pushfl
+ cli
+.endm
+
+.macro IRQ_RESTORE reg
+ popfl
+.endm
+
+#define BEGIN_IRQ_SAVE(op) \
+.macro endp; \
+SYM_FUNC_END(atomic64_##op##_386); \
+.purgem endp; \
+.endm; \
+SYM_FUNC_START(atomic64_##op##_386); \
+ IRQ_SAVE v;
+
+#define ENDP endp
+
+#define RET_IRQ_RESTORE \
+ IRQ_RESTORE v; \
+ RET
+
+#define v %ecx
+BEGIN_IRQ_SAVE(read)
+ movl (v), %eax
+ movl 4(v), %edx
+ RET_IRQ_RESTORE
+ENDP
+#undef v
+
+#define v %esi
+BEGIN_IRQ_SAVE(set)
+ movl %ebx, (v)
+ movl %ecx, 4(v)
+ RET_IRQ_RESTORE
+ENDP
+#undef v
+
+#define v %esi
+BEGIN_IRQ_SAVE(xchg)
+ movl (v), %eax
+ movl 4(v), %edx
+ movl %ebx, (v)
+ movl %ecx, 4(v)
+ RET_IRQ_RESTORE
+ENDP
+#undef v
+
+#define v %ecx
+BEGIN_IRQ_SAVE(add)
+ addl %eax, (v)
+ adcl %edx, 4(v)
+ RET_IRQ_RESTORE
+ENDP
+#undef v
+
+#define v %ecx
+BEGIN_IRQ_SAVE(add_return)
+ addl (v), %eax
+ adcl 4(v), %edx
+ movl %eax, (v)
+ movl %edx, 4(v)
+ RET_IRQ_RESTORE
+ENDP
+#undef v
+
+#define v %ecx
+BEGIN_IRQ_SAVE(sub)
+ subl %eax, (v)
+ sbbl %edx, 4(v)
+ RET_IRQ_RESTORE
+ENDP
+#undef v
+
+#define v %ecx
+BEGIN_IRQ_SAVE(sub_return)
+ negl %edx
+ negl %eax
+ sbbl $0, %edx
+ addl (v), %eax
+ adcl 4(v), %edx
+ movl %eax, (v)
+ movl %edx, 4(v)
+ RET_IRQ_RESTORE
+ENDP
+#undef v
+
+#define v %esi
+BEGIN_IRQ_SAVE(inc)
+ addl $1, (v)
+ adcl $0, 4(v)
+ RET_IRQ_RESTORE
+ENDP
+#undef v
+
+#define v %esi
+BEGIN_IRQ_SAVE(inc_return)
+ movl (v), %eax
+ movl 4(v), %edx
+ addl $1, %eax
+ adcl $0, %edx
+ movl %eax, (v)
+ movl %edx, 4(v)
+ RET_IRQ_RESTORE
+ENDP
+#undef v
+
+#define v %esi
+BEGIN_IRQ_SAVE(dec)
+ subl $1, (v)
+ sbbl $0, 4(v)
+ RET_IRQ_RESTORE
+ENDP
+#undef v
+
+#define v %esi
+BEGIN_IRQ_SAVE(dec_return)
+ movl (v), %eax
+ movl 4(v), %edx
+ subl $1, %eax
+ sbbl $0, %edx
+ movl %eax, (v)
+ movl %edx, 4(v)
+ RET_IRQ_RESTORE
+ENDP
+#undef v
+
+#define v %esi
+BEGIN_IRQ_SAVE(add_unless)
+ addl %eax, %ecx
+ adcl %edx, %edi
+ addl (v), %eax
+ adcl 4(v), %edx
+ cmpl %eax, %ecx
+ je 3f
+1:
+ movl %eax, (v)
+ movl %edx, 4(v)
+ movl $1, %eax
+2:
+ RET_IRQ_RESTORE
+3:
+ cmpl %edx, %edi
+ jne 1b
+ xorl %eax, %eax
+ jmp 2b
+ENDP
+#undef v
+
+#define v %esi
+BEGIN_IRQ_SAVE(inc_not_zero)
+ movl (v), %eax
+ movl 4(v), %edx
+ testl %eax, %eax
+ je 3f
+1:
+ addl $1, %eax
+ adcl $0, %edx
+ movl %eax, (v)
+ movl %edx, 4(v)
+ movl $1, %eax
+2:
+ RET_IRQ_RESTORE
+3:
+ testl %edx, %edx
+ jne 1b
+ jmp 2b
+ENDP
+#undef v
+
+#define v %esi
+BEGIN_IRQ_SAVE(dec_if_positive)
+ movl (v), %eax
+ movl 4(v), %edx
+ subl $1, %eax
+ sbbl $0, %edx
+ js 1f
+ movl %eax, (v)
+ movl %edx, 4(v)
+1:
+ RET_IRQ_RESTORE
+ENDP
+#undef v
diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S
new file mode 100644
index 0000000000..90afb488b3
--- /dev/null
+++ b/arch/x86/lib/atomic64_cx8_32.S
@@ -0,0 +1,180 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * atomic64_t for 586+
+ *
+ * Copyright © 2010 Luca Barbieri
+ */
+
+#include <linux/linkage.h>
+#include <asm/alternative.h>
+
+.macro read64 reg
+ movl %ebx, %eax
+ movl %ecx, %edx
+/* we need LOCK_PREFIX since otherwise cmpxchg8b always does the write */
+ LOCK_PREFIX
+ cmpxchg8b (\reg)
+.endm
+
+SYM_FUNC_START(atomic64_read_cx8)
+ read64 %ecx
+ RET
+SYM_FUNC_END(atomic64_read_cx8)
+
+SYM_FUNC_START(atomic64_set_cx8)
+1:
+/* we don't need LOCK_PREFIX since aligned 64-bit writes
+ * are atomic on 586 and newer */
+ cmpxchg8b (%esi)
+ jne 1b
+
+ RET
+SYM_FUNC_END(atomic64_set_cx8)
+
+SYM_FUNC_START(atomic64_xchg_cx8)
+1:
+ LOCK_PREFIX
+ cmpxchg8b (%esi)
+ jne 1b
+
+ RET
+SYM_FUNC_END(atomic64_xchg_cx8)
+
+.macro addsub_return func ins insc
+SYM_FUNC_START(atomic64_\func\()_return_cx8)
+ pushl %ebp
+ pushl %ebx
+ pushl %esi
+ pushl %edi
+
+ movl %eax, %esi
+ movl %edx, %edi
+ movl %ecx, %ebp
+
+ read64 %ecx
+1:
+ movl %eax, %ebx
+ movl %edx, %ecx
+ \ins\()l %esi, %ebx
+ \insc\()l %edi, %ecx
+ LOCK_PREFIX
+ cmpxchg8b (%ebp)
+ jne 1b
+
+10:
+ movl %ebx, %eax
+ movl %ecx, %edx
+ popl %edi
+ popl %esi
+ popl %ebx
+ popl %ebp
+ RET
+SYM_FUNC_END(atomic64_\func\()_return_cx8)
+.endm
+
+addsub_return add add adc
+addsub_return sub sub sbb
+
+.macro incdec_return func ins insc
+SYM_FUNC_START(atomic64_\func\()_return_cx8)
+ pushl %ebx
+
+ read64 %esi
+1:
+ movl %eax, %ebx
+ movl %edx, %ecx
+ \ins\()l $1, %ebx
+ \insc\()l $0, %ecx
+ LOCK_PREFIX
+ cmpxchg8b (%esi)
+ jne 1b
+
+10:
+ movl %ebx, %eax
+ movl %ecx, %edx
+ popl %ebx
+ RET
+SYM_FUNC_END(atomic64_\func\()_return_cx8)
+.endm
+
+incdec_return inc add adc
+incdec_return dec sub sbb
+
+SYM_FUNC_START(atomic64_dec_if_positive_cx8)
+ pushl %ebx
+
+ read64 %esi
+1:
+ movl %eax, %ebx
+ movl %edx, %ecx
+ subl $1, %ebx
+ sbb $0, %ecx
+ js 2f
+ LOCK_PREFIX
+ cmpxchg8b (%esi)
+ jne 1b
+
+2:
+ movl %ebx, %eax
+ movl %ecx, %edx
+ popl %ebx
+ RET
+SYM_FUNC_END(atomic64_dec_if_positive_cx8)
+
+SYM_FUNC_START(atomic64_add_unless_cx8)
+ pushl %ebp
+ pushl %ebx
+/* these just push these two parameters on the stack */
+ pushl %edi
+ pushl %ecx
+
+ movl %eax, %ebp
+ movl %edx, %edi
+
+ read64 %esi
+1:
+ cmpl %eax, 0(%esp)
+ je 4f
+2:
+ movl %eax, %ebx
+ movl %edx, %ecx
+ addl %ebp, %ebx
+ adcl %edi, %ecx
+ LOCK_PREFIX
+ cmpxchg8b (%esi)
+ jne 1b
+
+ movl $1, %eax
+3:
+ addl $8, %esp
+ popl %ebx
+ popl %ebp
+ RET
+4:
+ cmpl %edx, 4(%esp)
+ jne 2b
+ xorl %eax, %eax
+ jmp 3b
+SYM_FUNC_END(atomic64_add_unless_cx8)
+
+SYM_FUNC_START(atomic64_inc_not_zero_cx8)
+ pushl %ebx
+
+ read64 %esi
+1:
+ movl %eax, %ecx
+ orl %edx, %ecx
+ jz 3f
+ movl %eax, %ebx
+ xorl %ecx, %ecx
+ addl $1, %ebx
+ adcl %edx, %ecx
+ LOCK_PREFIX
+ cmpxchg8b (%esi)
+ jne 1b
+
+ movl $1, %eax
+3:
+ popl %ebx
+ RET
+SYM_FUNC_END(atomic64_inc_not_zero_cx8)
diff --git a/arch/x86/lib/cache-smp.c b/arch/x86/lib/cache-smp.c
new file mode 100644
index 0000000000..7c48ff4ae8
--- /dev/null
+++ b/arch/x86/lib/cache-smp.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/smp.h>
+#include <linux/export.h>
+
+static void __wbinvd(void *dummy)
+{
+ wbinvd();
+}
+
+void wbinvd_on_cpu(int cpu)
+{
+ smp_call_function_single(cpu, __wbinvd, NULL, 1);
+}
+EXPORT_SYMBOL(wbinvd_on_cpu);
+
+int wbinvd_on_all_cpus(void)
+{
+ on_each_cpu(__wbinvd, NULL, 1);
+ return 0;
+}
+EXPORT_SYMBOL(wbinvd_on_all_cpus);
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
new file mode 100644
index 0000000000..23318c338d
--- /dev/null
+++ b/arch/x86/lib/checksum_32.S
@@ -0,0 +1,444 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * INET An implementation of the TCP/IP protocol suite for the LINUX
+ * operating system. INET is implemented using the BSD Socket
+ * interface as the means of communication with the user level.
+ *
+ * IP/TCP/UDP checksumming routines
+ *
+ * Authors: Jorge Cwik, <jorge@laser.satlink.net>
+ * Arnt Gulbrandsen, <agulbra@nvg.unit.no>
+ * Tom May, <ftom@netcom.com>
+ * Pentium Pro/II routines:
+ * Alexander Kjeldaas <astor@guardian.no>
+ * Finn Arne Gangstad <finnag@guardian.no>
+ * Lots of code moved from tcp.c and ip.c; see those files
+ * for more names.
+ *
+ * Changes: Ingo Molnar, converted csum_partial_copy() to 2.1 exception
+ * handling.
+ * Andi Kleen, add zeroing on error
+ * converted to pure assembler
+ */
+
+#include <linux/linkage.h>
+#include <asm/errno.h>
+#include <asm/asm.h>
+#include <asm/export.h>
+#include <asm/nospec-branch.h>
+
+/*
+ * computes a partial checksum, e.g. for TCP/UDP fragments
+ */
+
+/*
+unsigned int csum_partial(const unsigned char * buff, int len, unsigned int sum)
+ */
+
+.text
+
+#ifndef CONFIG_X86_USE_PPRO_CHECKSUM
+
+ /*
+ * Experiments with Ethernet and SLIP connections show that buff
+ * is aligned on either a 2-byte or 4-byte boundary. We get at
+ * least a twofold speedup on 486 and Pentium if it is 4-byte aligned.
+ * Fortunately, it is easy to convert 2-byte alignment to 4-byte
+ * alignment for the unrolled loop.
+ */
+SYM_FUNC_START(csum_partial)
+ pushl %esi
+ pushl %ebx
+ movl 20(%esp),%eax # Function arg: unsigned int sum
+ movl 16(%esp),%ecx # Function arg: int len
+ movl 12(%esp),%esi # Function arg: unsigned char *buff
+ testl $3, %esi # Check alignment.
+ jz 2f # Jump if alignment is ok.
+ testl $1, %esi # Check alignment.
+ jz 10f # Jump if alignment is boundary of 2 bytes.
+
+ # buf is odd
+ dec %ecx
+ jl 8f
+ movzbl (%esi), %ebx
+ adcl %ebx, %eax
+ roll $8, %eax
+ inc %esi
+ testl $2, %esi
+ jz 2f
+10:
+ subl $2, %ecx # Alignment uses up two bytes.
+ jae 1f # Jump if we had at least two bytes.
+ addl $2, %ecx # ecx was < 2. Deal with it.
+ jmp 4f
+1: movw (%esi), %bx
+ addl $2, %esi
+ addw %bx, %ax
+ adcl $0, %eax
+2:
+ movl %ecx, %edx
+ shrl $5, %ecx
+ jz 2f
+ testl %esi, %esi
+1: movl (%esi), %ebx
+ adcl %ebx, %eax
+ movl 4(%esi), %ebx
+ adcl %ebx, %eax
+ movl 8(%esi), %ebx
+ adcl %ebx, %eax
+ movl 12(%esi), %ebx
+ adcl %ebx, %eax
+ movl 16(%esi), %ebx
+ adcl %ebx, %eax
+ movl 20(%esi), %ebx
+ adcl %ebx, %eax
+ movl 24(%esi), %ebx
+ adcl %ebx, %eax
+ movl 28(%esi), %ebx
+ adcl %ebx, %eax
+ lea 32(%esi), %esi
+ dec %ecx
+ jne 1b
+ adcl $0, %eax
+2: movl %edx, %ecx
+ andl $0x1c, %edx
+ je 4f
+ shrl $2, %edx # This clears CF
+3: adcl (%esi), %eax
+ lea 4(%esi), %esi
+ dec %edx
+ jne 3b
+ adcl $0, %eax
+4: andl $3, %ecx
+ jz 7f
+ cmpl $2, %ecx
+ jb 5f
+ movw (%esi),%cx
+ leal 2(%esi),%esi
+ je 6f
+ shll $16,%ecx
+5: movb (%esi),%cl
+6: addl %ecx,%eax
+ adcl $0, %eax
+7:
+ testb $1, 12(%esp)
+ jz 8f
+ roll $8, %eax
+8:
+ popl %ebx
+ popl %esi
+ RET
+SYM_FUNC_END(csum_partial)
+
+#else
+
+/* Version for PentiumII/PPro */
+
+SYM_FUNC_START(csum_partial)
+ pushl %esi
+ pushl %ebx
+ movl 20(%esp),%eax # Function arg: unsigned int sum
+ movl 16(%esp),%ecx # Function arg: int len
+ movl 12(%esp),%esi # Function arg: const unsigned char *buf
+
+ testl $3, %esi
+ jnz 25f
+10:
+ movl %ecx, %edx
+ movl %ecx, %ebx
+ andl $0x7c, %ebx
+ shrl $7, %ecx
+ addl %ebx,%esi
+ shrl $2, %ebx
+ negl %ebx
+ lea 45f(%ebx,%ebx,2), %ebx
+ testl %esi, %esi
+ JMP_NOSPEC ebx
+
+ # Handle 2-byte-aligned regions
+20: addw (%esi), %ax
+ lea 2(%esi), %esi
+ adcl $0, %eax
+ jmp 10b
+25:
+ testl $1, %esi
+ jz 30f
+ # buf is odd
+ dec %ecx
+ jl 90f
+ movzbl (%esi), %ebx
+ addl %ebx, %eax
+ adcl $0, %eax
+ roll $8, %eax
+ inc %esi
+ testl $2, %esi
+ jz 10b
+
+30: subl $2, %ecx
+ ja 20b
+ je 32f
+ addl $2, %ecx
+ jz 80f
+ movzbl (%esi),%ebx # csumming 1 byte, 2-aligned
+ addl %ebx, %eax
+ adcl $0, %eax
+ jmp 80f
+32:
+ addw (%esi), %ax # csumming 2 bytes, 2-aligned
+ adcl $0, %eax
+ jmp 80f
+
+40:
+ addl -128(%esi), %eax
+ adcl -124(%esi), %eax
+ adcl -120(%esi), %eax
+ adcl -116(%esi), %eax
+ adcl -112(%esi), %eax
+ adcl -108(%esi), %eax
+ adcl -104(%esi), %eax
+ adcl -100(%esi), %eax
+ adcl -96(%esi), %eax
+ adcl -92(%esi), %eax
+ adcl -88(%esi), %eax
+ adcl -84(%esi), %eax
+ adcl -80(%esi), %eax
+ adcl -76(%esi), %eax
+ adcl -72(%esi), %eax
+ adcl -68(%esi), %eax
+ adcl -64(%esi), %eax
+ adcl -60(%esi), %eax
+ adcl -56(%esi), %eax
+ adcl -52(%esi), %eax
+ adcl -48(%esi), %eax
+ adcl -44(%esi), %eax
+ adcl -40(%esi), %eax
+ adcl -36(%esi), %eax
+ adcl -32(%esi), %eax
+ adcl -28(%esi), %eax
+ adcl -24(%esi), %eax
+ adcl -20(%esi), %eax
+ adcl -16(%esi), %eax
+ adcl -12(%esi), %eax
+ adcl -8(%esi), %eax
+ adcl -4(%esi), %eax
+45:
+ lea 128(%esi), %esi
+ adcl $0, %eax
+ dec %ecx
+ jge 40b
+ movl %edx, %ecx
+50: andl $3, %ecx
+ jz 80f
+
+ # Handle the last 1-3 bytes without jumping
+ notl %ecx # 1->2, 2->1, 3->0, higher bits are masked
+ movl $0xffffff,%ebx # by the shll and shrl instructions
+ shll $3,%ecx
+ shrl %cl,%ebx
+ andl -128(%esi),%ebx # esi is 4-aligned so should be ok
+ addl %ebx,%eax
+ adcl $0,%eax
+80:
+ testb $1, 12(%esp)
+ jz 90f
+ roll $8, %eax
+90:
+ popl %ebx
+ popl %esi
+ RET
+SYM_FUNC_END(csum_partial)
+
+#endif
+EXPORT_SYMBOL(csum_partial)
+
+/*
+unsigned int csum_partial_copy_generic (const char *src, char *dst,
+ int len)
+ */
+
+/*
+ * Copy from ds while checksumming, otherwise like csum_partial
+ */
+
+#define EXC(y...) \
+ 9999: y; \
+ _ASM_EXTABLE_TYPE(9999b, 7f, EX_TYPE_UACCESS | EX_FLAG_CLEAR_AX)
+
+#ifndef CONFIG_X86_USE_PPRO_CHECKSUM
+
+#define ARGBASE 16
+#define FP 12
+
+SYM_FUNC_START(csum_partial_copy_generic)
+ subl $4,%esp
+ pushl %edi
+ pushl %esi
+ pushl %ebx
+ movl ARGBASE+12(%esp),%ecx # len
+ movl ARGBASE+4(%esp),%esi # src
+ movl ARGBASE+8(%esp),%edi # dst
+
+ movl $-1, %eax # sum
+ testl $2, %edi # Check alignment.
+ jz 2f # Jump if alignment is ok.
+ subl $2, %ecx # Alignment uses up two bytes.
+ jae 1f # Jump if we had at least two bytes.
+ addl $2, %ecx # ecx was < 2. Deal with it.
+ jmp 4f
+EXC(1: movw (%esi), %bx )
+ addl $2, %esi
+EXC( movw %bx, (%edi) )
+ addl $2, %edi
+ addw %bx, %ax
+ adcl $0, %eax
+2:
+ movl %ecx, FP(%esp)
+ shrl $5, %ecx
+ jz 2f
+ testl %esi, %esi # what's wrong with clc?
+EXC(1: movl (%esi), %ebx )
+EXC( movl 4(%esi), %edx )
+ adcl %ebx, %eax
+EXC( movl %ebx, (%edi) )
+ adcl %edx, %eax
+EXC( movl %edx, 4(%edi) )
+
+EXC( movl 8(%esi), %ebx )
+EXC( movl 12(%esi), %edx )
+ adcl %ebx, %eax
+EXC( movl %ebx, 8(%edi) )
+ adcl %edx, %eax
+EXC( movl %edx, 12(%edi) )
+
+EXC( movl 16(%esi), %ebx )
+EXC( movl 20(%esi), %edx )
+ adcl %ebx, %eax
+EXC( movl %ebx, 16(%edi) )
+ adcl %edx, %eax
+EXC( movl %edx, 20(%edi) )
+
+EXC( movl 24(%esi), %ebx )
+EXC( movl 28(%esi), %edx )
+ adcl %ebx, %eax
+EXC( movl %ebx, 24(%edi) )
+ adcl %edx, %eax
+EXC( movl %edx, 28(%edi) )
+
+ lea 32(%esi), %esi
+ lea 32(%edi), %edi
+ dec %ecx
+ jne 1b
+ adcl $0, %eax
+2: movl FP(%esp), %edx
+ movl %edx, %ecx
+ andl $0x1c, %edx
+ je 4f
+ shrl $2, %edx # This clears CF
+EXC(3: movl (%esi), %ebx )
+ adcl %ebx, %eax
+EXC( movl %ebx, (%edi) )
+ lea 4(%esi), %esi
+ lea 4(%edi), %edi
+ dec %edx
+ jne 3b
+ adcl $0, %eax
+4: andl $3, %ecx
+ jz 7f
+ cmpl $2, %ecx
+ jb 5f
+EXC( movw (%esi), %cx )
+ leal 2(%esi), %esi
+EXC( movw %cx, (%edi) )
+ leal 2(%edi), %edi
+ je 6f
+ shll $16,%ecx
+EXC(5: movb (%esi), %cl )
+EXC( movb %cl, (%edi) )
+6: addl %ecx, %eax
+ adcl $0, %eax
+7:
+
+ popl %ebx
+ popl %esi
+ popl %edi
+ popl %ecx # equivalent to addl $4,%esp
+ RET
+SYM_FUNC_END(csum_partial_copy_generic)
+
+#else
+
+/* Version for PentiumII/PPro */
+
+#define ROUND1(x) \
+ EXC(movl x(%esi), %ebx ) ; \
+ addl %ebx, %eax ; \
+ EXC(movl %ebx, x(%edi) ) ;
+
+#define ROUND(x) \
+ EXC(movl x(%esi), %ebx ) ; \
+ adcl %ebx, %eax ; \
+ EXC(movl %ebx, x(%edi) ) ;
+
+#define ARGBASE 12
+
+SYM_FUNC_START(csum_partial_copy_generic)
+ pushl %ebx
+ pushl %edi
+ pushl %esi
+ movl ARGBASE+4(%esp),%esi #src
+ movl ARGBASE+8(%esp),%edi #dst
+ movl ARGBASE+12(%esp),%ecx #len
+ movl $-1, %eax #sum
+# movl %ecx, %edx
+ movl %ecx, %ebx
+ movl %esi, %edx
+ shrl $6, %ecx
+ andl $0x3c, %ebx
+ negl %ebx
+ subl %ebx, %esi
+ subl %ebx, %edi
+ lea -1(%esi),%edx
+ andl $-32,%edx
+ lea 3f(%ebx,%ebx), %ebx
+ testl %esi, %esi
+ JMP_NOSPEC ebx
+1: addl $64,%esi
+ addl $64,%edi
+ EXC(movb -32(%edx),%bl) ; EXC(movb (%edx),%bl)
+ ROUND1(-64) ROUND(-60) ROUND(-56) ROUND(-52)
+ ROUND (-48) ROUND(-44) ROUND(-40) ROUND(-36)
+ ROUND (-32) ROUND(-28) ROUND(-24) ROUND(-20)
+ ROUND (-16) ROUND(-12) ROUND(-8) ROUND(-4)
+3: adcl $0,%eax
+ addl $64, %edx
+ dec %ecx
+ jge 1b
+4: movl ARGBASE+12(%esp),%edx #len
+ andl $3, %edx
+ jz 7f
+ cmpl $2, %edx
+ jb 5f
+EXC( movw (%esi), %dx )
+ leal 2(%esi), %esi
+EXC( movw %dx, (%edi) )
+ leal 2(%edi), %edi
+ je 6f
+ shll $16,%edx
+5:
+EXC( movb (%esi), %dl )
+EXC( movb %dl, (%edi) )
+6: addl %edx, %eax
+ adcl $0, %eax
+7:
+
+ popl %esi
+ popl %edi
+ popl %ebx
+ RET
+SYM_FUNC_END(csum_partial_copy_generic)
+
+#undef ROUND
+#undef ROUND1
+
+#endif
+EXPORT_SYMBOL(csum_partial_copy_generic)
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
new file mode 100644
index 0000000000..f74a3e704a
--- /dev/null
+++ b/arch/x86/lib/clear_page_64.S
@@ -0,0 +1,141 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#include <linux/linkage.h>
+#include <asm/asm.h>
+#include <asm/export.h>
+
+/*
+ * Most CPUs support enhanced REP MOVSB/STOSB instructions. It is
+ * recommended to use this when possible and we do use them by default.
+ * If enhanced REP MOVSB/STOSB is not available, try to use fast string.
+ * Otherwise, use original.
+ */
+
+/*
+ * Zero a page.
+ * %rdi - page
+ */
+SYM_FUNC_START(clear_page_rep)
+ movl $4096/8,%ecx
+ xorl %eax,%eax
+ rep stosq
+ RET
+SYM_FUNC_END(clear_page_rep)
+EXPORT_SYMBOL_GPL(clear_page_rep)
+
+SYM_FUNC_START(clear_page_orig)
+ xorl %eax,%eax
+ movl $4096/64,%ecx
+ .p2align 4
+.Lloop:
+ decl %ecx
+#define PUT(x) movq %rax,x*8(%rdi)
+ movq %rax,(%rdi)
+ PUT(1)
+ PUT(2)
+ PUT(3)
+ PUT(4)
+ PUT(5)
+ PUT(6)
+ PUT(7)
+ leaq 64(%rdi),%rdi
+ jnz .Lloop
+ nop
+ RET
+SYM_FUNC_END(clear_page_orig)
+EXPORT_SYMBOL_GPL(clear_page_orig)
+
+SYM_FUNC_START(clear_page_erms)
+ movl $4096,%ecx
+ xorl %eax,%eax
+ rep stosb
+ RET
+SYM_FUNC_END(clear_page_erms)
+EXPORT_SYMBOL_GPL(clear_page_erms)
+
+/*
+ * Default clear user-space.
+ * Input:
+ * rdi destination
+ * rcx count
+ * rax is zero
+ *
+ * Output:
+ * rcx: uncleared bytes or 0 if successful.
+ */
+SYM_FUNC_START(rep_stos_alternative)
+ cmpq $64,%rcx
+ jae .Lunrolled
+
+ cmp $8,%ecx
+ jae .Lword
+
+ testl %ecx,%ecx
+ je .Lexit
+
+.Lclear_user_tail:
+0: movb %al,(%rdi)
+ inc %rdi
+ dec %rcx
+ jnz .Lclear_user_tail
+.Lexit:
+ RET
+
+ _ASM_EXTABLE_UA( 0b, .Lexit)
+
+.Lword:
+1: movq %rax,(%rdi)
+ addq $8,%rdi
+ sub $8,%ecx
+ je .Lexit
+ cmp $8,%ecx
+ jae .Lword
+ jmp .Lclear_user_tail
+
+ .p2align 4
+.Lunrolled:
+10: movq %rax,(%rdi)
+11: movq %rax,8(%rdi)
+12: movq %rax,16(%rdi)
+13: movq %rax,24(%rdi)
+14: movq %rax,32(%rdi)
+15: movq %rax,40(%rdi)
+16: movq %rax,48(%rdi)
+17: movq %rax,56(%rdi)
+ addq $64,%rdi
+ subq $64,%rcx
+ cmpq $64,%rcx
+ jae .Lunrolled
+ cmpl $8,%ecx
+ jae .Lword
+ testl %ecx,%ecx
+ jne .Lclear_user_tail
+ RET
+
+ /*
+ * If we take an exception on any of the
+ * word stores, we know that %rcx isn't zero,
+ * so we can just go to the tail clearing to
+ * get the exact count.
+ *
+ * The unrolled case might end up clearing
+ * some bytes twice. Don't care.
+ *
+ * We could use the value in %rdi to avoid
+ * a second fault on the exact count case,
+ * but do we really care? No.
+ *
+ * Finally, we could try to align %rdi at the
+ * top of the unrolling. But unaligned stores
+ * just aren't that common or expensive.
+ */
+ _ASM_EXTABLE_UA( 1b, .Lclear_user_tail)
+ _ASM_EXTABLE_UA(10b, .Lclear_user_tail)
+ _ASM_EXTABLE_UA(11b, .Lclear_user_tail)
+ _ASM_EXTABLE_UA(12b, .Lclear_user_tail)
+ _ASM_EXTABLE_UA(13b, .Lclear_user_tail)
+ _ASM_EXTABLE_UA(14b, .Lclear_user_tail)
+ _ASM_EXTABLE_UA(15b, .Lclear_user_tail)
+ _ASM_EXTABLE_UA(16b, .Lclear_user_tail)
+ _ASM_EXTABLE_UA(17b, .Lclear_user_tail)
+SYM_FUNC_END(rep_stos_alternative)
+EXPORT_SYMBOL(rep_stos_alternative)
diff --git a/arch/x86/lib/cmdline.c b/arch/x86/lib/cmdline.c
new file mode 100644
index 0000000000..80570eb3c8
--- /dev/null
+++ b/arch/x86/lib/cmdline.c
@@ -0,0 +1,216 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *
+ * Misc librarized functions for cmdline poking.
+ */
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <asm/setup.h>
+#include <asm/cmdline.h>
+
+static inline int myisspace(u8 c)
+{
+ return c <= ' '; /* Close enough approximation */
+}
+
+/*
+ * Find a boolean option (like quiet,noapic,nosmp....)
+ *
+ * @cmdline: the cmdline string
+ * @max_cmdline_size: the maximum size of cmdline
+ * @option: option string to look for
+ *
+ * Returns the position of that @option (starts counting with 1)
+ * or 0 on not found. @option will only be found if it is found
+ * as an entire word in @cmdline. For instance, if @option="car"
+ * then a cmdline which contains "cart" will not match.
+ */
+static int
+__cmdline_find_option_bool(const char *cmdline, int max_cmdline_size,
+ const char *option)
+{
+ char c;
+ int pos = 0, wstart = 0;
+ const char *opptr = NULL;
+ enum {
+ st_wordstart = 0, /* Start of word/after whitespace */
+ st_wordcmp, /* Comparing this word */
+ st_wordskip, /* Miscompare, skip */
+ } state = st_wordstart;
+
+ if (!cmdline)
+ return -1; /* No command line */
+
+ /*
+ * This 'pos' check ensures we do not overrun
+ * a non-NULL-terminated 'cmdline'
+ */
+ while (pos < max_cmdline_size) {
+ c = *(char *)cmdline++;
+ pos++;
+
+ switch (state) {
+ case st_wordstart:
+ if (!c)
+ return 0;
+ else if (myisspace(c))
+ break;
+
+ state = st_wordcmp;
+ opptr = option;
+ wstart = pos;
+ fallthrough;
+
+ case st_wordcmp:
+ if (!*opptr) {
+ /*
+ * We matched all the way to the end of the
+ * option we were looking for. If the
+ * command-line has a space _or_ ends, then
+ * we matched!
+ */
+ if (!c || myisspace(c))
+ return wstart;
+ /*
+ * We hit the end of the option, but _not_
+ * the end of a word on the cmdline. Not
+ * a match.
+ */
+ } else if (!c) {
+ /*
+ * Hit the NULL terminator on the end of
+ * cmdline.
+ */
+ return 0;
+ } else if (c == *opptr++) {
+ /*
+ * We are currently matching, so continue
+ * to the next character on the cmdline.
+ */
+ break;
+ }
+ state = st_wordskip;
+ fallthrough;
+
+ case st_wordskip:
+ if (!c)
+ return 0;
+ else if (myisspace(c))
+ state = st_wordstart;
+ break;
+ }
+ }
+
+ return 0; /* Buffer overrun */
+}
+
+/*
+ * Find a non-boolean option (i.e. option=argument). In accordance with
+ * standard Linux practice, if this option is repeated, this returns the
+ * last instance on the command line.
+ *
+ * @cmdline: the cmdline string
+ * @max_cmdline_size: the maximum size of cmdline
+ * @option: option string to look for
+ * @buffer: memory buffer to return the option argument
+ * @bufsize: size of the supplied memory buffer
+ *
+ * Returns the length of the argument (regardless of if it was
+ * truncated to fit in the buffer), or -1 on not found.
+ */
+static int
+__cmdline_find_option(const char *cmdline, int max_cmdline_size,
+ const char *option, char *buffer, int bufsize)
+{
+ char c;
+ int pos = 0, len = -1;
+ const char *opptr = NULL;
+ char *bufptr = buffer;
+ enum {
+ st_wordstart = 0, /* Start of word/after whitespace */
+ st_wordcmp, /* Comparing this word */
+ st_wordskip, /* Miscompare, skip */
+ st_bufcpy, /* Copying this to buffer */
+ } state = st_wordstart;
+
+ if (!cmdline)
+ return -1; /* No command line */
+
+ /*
+ * This 'pos' check ensures we do not overrun
+ * a non-NULL-terminated 'cmdline'
+ */
+ while (pos++ < max_cmdline_size) {
+ c = *(char *)cmdline++;
+ if (!c)
+ break;
+
+ switch (state) {
+ case st_wordstart:
+ if (myisspace(c))
+ break;
+
+ state = st_wordcmp;
+ opptr = option;
+ fallthrough;
+
+ case st_wordcmp:
+ if ((c == '=') && !*opptr) {
+ /*
+ * We matched all the way to the end of the
+ * option we were looking for, prepare to
+ * copy the argument.
+ */
+ len = 0;
+ bufptr = buffer;
+ state = st_bufcpy;
+ break;
+ } else if (c == *opptr++) {
+ /*
+ * We are currently matching, so continue
+ * to the next character on the cmdline.
+ */
+ break;
+ }
+ state = st_wordskip;
+ fallthrough;
+
+ case st_wordskip:
+ if (myisspace(c))
+ state = st_wordstart;
+ break;
+
+ case st_bufcpy:
+ if (myisspace(c)) {
+ state = st_wordstart;
+ } else {
+ /*
+ * Increment len, but don't overrun the
+ * supplied buffer and leave room for the
+ * NULL terminator.
+ */
+ if (++len < bufsize)
+ *bufptr++ = c;
+ }
+ break;
+ }
+ }
+
+ if (bufsize)
+ *bufptr = '\0';
+
+ return len;
+}
+
+int cmdline_find_option_bool(const char *cmdline, const char *option)
+{
+ return __cmdline_find_option_bool(cmdline, COMMAND_LINE_SIZE, option);
+}
+
+int cmdline_find_option(const char *cmdline, const char *option, char *buffer,
+ int bufsize)
+{
+ return __cmdline_find_option(cmdline, COMMAND_LINE_SIZE, option,
+ buffer, bufsize);
+}
diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S
new file mode 100644
index 0000000000..6962df3157
--- /dev/null
+++ b/arch/x86/lib/cmpxchg16b_emu.S
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#include <linux/linkage.h>
+#include <asm/percpu.h>
+#include <asm/processor-flags.h>
+
+.text
+
+/*
+ * Emulate 'cmpxchg16b %gs:(%rsi)'
+ *
+ * Inputs:
+ * %rsi : memory location to compare
+ * %rax : low 64 bits of old value
+ * %rdx : high 64 bits of old value
+ * %rbx : low 64 bits of new value
+ * %rcx : high 64 bits of new value
+ *
+ * Notably this is not LOCK prefixed and is not safe against NMIs
+ */
+SYM_FUNC_START(this_cpu_cmpxchg16b_emu)
+
+ pushfq
+ cli
+
+ /* if (*ptr == old) */
+ cmpq PER_CPU_VAR(0(%rsi)), %rax
+ jne .Lnot_same
+ cmpq PER_CPU_VAR(8(%rsi)), %rdx
+ jne .Lnot_same
+
+ /* *ptr = new */
+ movq %rbx, PER_CPU_VAR(0(%rsi))
+ movq %rcx, PER_CPU_VAR(8(%rsi))
+
+ /* set ZF in EFLAGS to indicate success */
+ orl $X86_EFLAGS_ZF, (%rsp)
+
+ popfq
+ RET
+
+.Lnot_same:
+ /* *ptr != old */
+
+ /* old = *ptr */
+ movq PER_CPU_VAR(0(%rsi)), %rax
+ movq PER_CPU_VAR(8(%rsi)), %rdx
+
+ /* clear ZF in EFLAGS to indicate failure */
+ andl $(~X86_EFLAGS_ZF), (%rsp)
+
+ popfq
+ RET
+
+SYM_FUNC_END(this_cpu_cmpxchg16b_emu)
diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S
new file mode 100644
index 0000000000..49805257b1
--- /dev/null
+++ b/arch/x86/lib/cmpxchg8b_emu.S
@@ -0,0 +1,85 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include <linux/linkage.h>
+#include <asm/export.h>
+#include <asm/percpu.h>
+#include <asm/processor-flags.h>
+
+.text
+
+#ifndef CONFIG_X86_CMPXCHG64
+
+/*
+ * Emulate 'cmpxchg8b (%esi)' on UP
+ *
+ * Inputs:
+ * %esi : memory location to compare
+ * %eax : low 32 bits of old value
+ * %edx : high 32 bits of old value
+ * %ebx : low 32 bits of new value
+ * %ecx : high 32 bits of new value
+ */
+SYM_FUNC_START(cmpxchg8b_emu)
+
+ pushfl
+ cli
+
+ cmpl 0(%esi), %eax
+ jne .Lnot_same
+ cmpl 4(%esi), %edx
+ jne .Lnot_same
+
+ movl %ebx, 0(%esi)
+ movl %ecx, 4(%esi)
+
+ orl $X86_EFLAGS_ZF, (%esp)
+
+ popfl
+ RET
+
+.Lnot_same:
+ movl 0(%esi), %eax
+ movl 4(%esi), %edx
+
+ andl $(~X86_EFLAGS_ZF), (%esp)
+
+ popfl
+ RET
+
+SYM_FUNC_END(cmpxchg8b_emu)
+EXPORT_SYMBOL(cmpxchg8b_emu)
+
+#endif
+
+#ifndef CONFIG_UML
+
+SYM_FUNC_START(this_cpu_cmpxchg8b_emu)
+
+ pushfl
+ cli
+
+ cmpl PER_CPU_VAR(0(%esi)), %eax
+ jne .Lnot_same2
+ cmpl PER_CPU_VAR(4(%esi)), %edx
+ jne .Lnot_same2
+
+ movl %ebx, PER_CPU_VAR(0(%esi))
+ movl %ecx, PER_CPU_VAR(4(%esi))
+
+ orl $X86_EFLAGS_ZF, (%esp)
+
+ popfl
+ RET
+
+.Lnot_same2:
+ movl PER_CPU_VAR(0(%esi)), %eax
+ movl PER_CPU_VAR(4(%esi)), %edx
+
+ andl $(~X86_EFLAGS_ZF), (%esp)
+
+ popfl
+ RET
+
+SYM_FUNC_END(this_cpu_cmpxchg8b_emu)
+
+#endif
diff --git a/arch/x86/lib/copy_mc.c b/arch/x86/lib/copy_mc.c
new file mode 100644
index 0000000000..6e8b7e600d
--- /dev/null
+++ b/arch/x86/lib/copy_mc.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2016-2020 Intel Corporation. All rights reserved. */
+
+#include <linux/jump_label.h>
+#include <linux/uaccess.h>
+#include <linux/export.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+#include <asm/mce.h>
+
+#ifdef CONFIG_X86_MCE
+static DEFINE_STATIC_KEY_FALSE(copy_mc_fragile_key);
+
+void enable_copy_mc_fragile(void)
+{
+ static_branch_inc(&copy_mc_fragile_key);
+}
+#define copy_mc_fragile_enabled (static_branch_unlikely(&copy_mc_fragile_key))
+
+/*
+ * Similar to copy_user_handle_tail, probe for the write fault point, or
+ * source exception point.
+ */
+__visible notrace unsigned long
+copy_mc_fragile_handle_tail(char *to, char *from, unsigned len)
+{
+ for (; len; --len, to++, from++)
+ if (copy_mc_fragile(to, from, 1))
+ break;
+ return len;
+}
+#else
+/*
+ * No point in doing careful copying, or consulting a static key when
+ * there is no #MC handler in the CONFIG_X86_MCE=n case.
+ */
+void enable_copy_mc_fragile(void)
+{
+}
+#define copy_mc_fragile_enabled (0)
+#endif
+
+unsigned long copy_mc_enhanced_fast_string(void *dst, const void *src, unsigned len);
+
+/**
+ * copy_mc_to_kernel - memory copy that handles source exceptions
+ *
+ * @dst: destination address
+ * @src: source address
+ * @len: number of bytes to copy
+ *
+ * Call into the 'fragile' version on systems that benefit from avoiding
+ * corner case poison consumption scenarios, For example, accessing
+ * poison across 2 cachelines with a single instruction. Almost all
+ * other uses case can use copy_mc_enhanced_fast_string() for a fast
+ * recoverable copy, or fallback to plain memcpy.
+ *
+ * Return 0 for success, or number of bytes not copied if there was an
+ * exception.
+ */
+unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, unsigned len)
+{
+ if (copy_mc_fragile_enabled)
+ return copy_mc_fragile(dst, src, len);
+ if (static_cpu_has(X86_FEATURE_ERMS))
+ return copy_mc_enhanced_fast_string(dst, src, len);
+ memcpy(dst, src, len);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(copy_mc_to_kernel);
+
+unsigned long __must_check copy_mc_to_user(void __user *dst, const void *src, unsigned len)
+{
+ unsigned long ret;
+
+ if (copy_mc_fragile_enabled) {
+ __uaccess_begin();
+ ret = copy_mc_fragile((__force void *)dst, src, len);
+ __uaccess_end();
+ return ret;
+ }
+
+ if (static_cpu_has(X86_FEATURE_ERMS)) {
+ __uaccess_begin();
+ ret = copy_mc_enhanced_fast_string((__force void *)dst, src, len);
+ __uaccess_end();
+ return ret;
+ }
+
+ return copy_user_generic((__force void *)dst, src, len);
+}
diff --git a/arch/x86/lib/copy_mc_64.S b/arch/x86/lib/copy_mc_64.S
new file mode 100644
index 0000000000..c859a8a098
--- /dev/null
+++ b/arch/x86/lib/copy_mc_64.S
@@ -0,0 +1,149 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright(c) 2016-2020 Intel Corporation. All rights reserved. */
+
+#include <linux/linkage.h>
+#include <asm/asm.h>
+
+#ifndef CONFIG_UML
+
+#ifdef CONFIG_X86_MCE
+
+/*
+ * copy_mc_fragile - copy memory with indication if an exception / fault happened
+ *
+ * The 'fragile' version is opted into by platform quirks and takes
+ * pains to avoid unrecoverable corner cases like 'fast-string'
+ * instruction sequences, and consuming poison across a cacheline
+ * boundary. The non-fragile version is equivalent to memcpy()
+ * regardless of CPU machine-check-recovery capability.
+ */
+SYM_FUNC_START(copy_mc_fragile)
+ cmpl $8, %edx
+ /* Less than 8 bytes? Go to byte copy loop */
+ jb .L_no_whole_words
+
+ /* Check for bad alignment of source */
+ testl $7, %esi
+ /* Already aligned */
+ jz .L_8byte_aligned
+
+ /* Copy one byte at a time until source is 8-byte aligned */
+ movl %esi, %ecx
+ andl $7, %ecx
+ subl $8, %ecx
+ negl %ecx
+ subl %ecx, %edx
+.L_read_leading_bytes:
+ movb (%rsi), %al
+.L_write_leading_bytes:
+ movb %al, (%rdi)
+ incq %rsi
+ incq %rdi
+ decl %ecx
+ jnz .L_read_leading_bytes
+
+.L_8byte_aligned:
+ movl %edx, %ecx
+ andl $7, %edx
+ shrl $3, %ecx
+ jz .L_no_whole_words
+
+.L_read_words:
+ movq (%rsi), %r8
+.L_write_words:
+ movq %r8, (%rdi)
+ addq $8, %rsi
+ addq $8, %rdi
+ decl %ecx
+ jnz .L_read_words
+
+ /* Any trailing bytes? */
+.L_no_whole_words:
+ andl %edx, %edx
+ jz .L_done_memcpy_trap
+
+ /* Copy trailing bytes */
+ movl %edx, %ecx
+.L_read_trailing_bytes:
+ movb (%rsi), %al
+.L_write_trailing_bytes:
+ movb %al, (%rdi)
+ incq %rsi
+ incq %rdi
+ decl %ecx
+ jnz .L_read_trailing_bytes
+
+ /* Copy successful. Return zero */
+.L_done_memcpy_trap:
+ xorl %eax, %eax
+.L_done:
+ RET
+
+ /*
+ * Return number of bytes not copied for any failure. Note that
+ * there is no "tail" handling since the source buffer is 8-byte
+ * aligned and poison is cacheline aligned.
+ */
+.E_read_words:
+ shll $3, %ecx
+.E_leading_bytes:
+ addl %edx, %ecx
+.E_trailing_bytes:
+ mov %ecx, %eax
+ jmp .L_done
+
+ /*
+ * For write fault handling, given the destination is unaligned,
+ * we handle faults on multi-byte writes with a byte-by-byte
+ * copy up to the write-protected page.
+ */
+.E_write_words:
+ shll $3, %ecx
+ addl %edx, %ecx
+ movl %ecx, %edx
+ jmp copy_mc_fragile_handle_tail
+
+ _ASM_EXTABLE_TYPE(.L_read_leading_bytes, .E_leading_bytes, EX_TYPE_DEFAULT_MCE_SAFE)
+ _ASM_EXTABLE_TYPE(.L_read_words, .E_read_words, EX_TYPE_DEFAULT_MCE_SAFE)
+ _ASM_EXTABLE_TYPE(.L_read_trailing_bytes, .E_trailing_bytes, EX_TYPE_DEFAULT_MCE_SAFE)
+ _ASM_EXTABLE(.L_write_leading_bytes, .E_leading_bytes)
+ _ASM_EXTABLE(.L_write_words, .E_write_words)
+ _ASM_EXTABLE(.L_write_trailing_bytes, .E_trailing_bytes)
+
+SYM_FUNC_END(copy_mc_fragile)
+#endif /* CONFIG_X86_MCE */
+
+/*
+ * copy_mc_enhanced_fast_string - memory copy with exception handling
+ *
+ * Fast string copy + fault / exception handling. If the CPU does
+ * support machine check exception recovery, but does not support
+ * recovering from fast-string exceptions then this CPU needs to be
+ * added to the copy_mc_fragile_key set of quirks. Otherwise, absent any
+ * machine check recovery support this version should be no slower than
+ * standard memcpy.
+ */
+SYM_FUNC_START(copy_mc_enhanced_fast_string)
+ movq %rdi, %rax
+ movq %rdx, %rcx
+.L_copy:
+ rep movsb
+ /* Copy successful. Return zero */
+ xorl %eax, %eax
+ RET
+
+.E_copy:
+ /*
+ * On fault %rcx is updated such that the copy instruction could
+ * optionally be restarted at the fault position, i.e. it
+ * contains 'bytes remaining'. A non-zero return indicates error
+ * to copy_mc_generic() users, or indicate short transfers to
+ * user-copy routines.
+ */
+ movq %rcx, %rax
+ RET
+
+ _ASM_EXTABLE_TYPE(.L_copy, .E_copy, EX_TYPE_DEFAULT_MCE_SAFE)
+
+SYM_FUNC_END(copy_mc_enhanced_fast_string)
+#endif /* !CONFIG_UML */
diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S
new file mode 100644
index 0000000000..30ea644bf4
--- /dev/null
+++ b/arch/x86/lib/copy_page_64.S
@@ -0,0 +1,89 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Written 2003 by Andi Kleen, based on a kernel by Evandro Menezes */
+
+#include <linux/linkage.h>
+#include <asm/cpufeatures.h>
+#include <asm/alternative.h>
+#include <asm/export.h>
+
+/*
+ * Some CPUs run faster using the string copy instructions (sane microcode).
+ * It is also a lot simpler. Use this when possible. But, don't use streaming
+ * copy unless the CPU indicates X86_FEATURE_REP_GOOD. Could vary the
+ * prefetch distance based on SMP/UP.
+ */
+ ALIGN
+SYM_FUNC_START(copy_page)
+ ALTERNATIVE "jmp copy_page_regs", "", X86_FEATURE_REP_GOOD
+ movl $4096/8, %ecx
+ rep movsq
+ RET
+SYM_FUNC_END(copy_page)
+EXPORT_SYMBOL(copy_page)
+
+SYM_FUNC_START_LOCAL(copy_page_regs)
+ subq $2*8, %rsp
+ movq %rbx, (%rsp)
+ movq %r12, 1*8(%rsp)
+
+ movl $(4096/64)-5, %ecx
+ .p2align 4
+.Loop64:
+ dec %rcx
+ movq 0x8*0(%rsi), %rax
+ movq 0x8*1(%rsi), %rbx
+ movq 0x8*2(%rsi), %rdx
+ movq 0x8*3(%rsi), %r8
+ movq 0x8*4(%rsi), %r9
+ movq 0x8*5(%rsi), %r10
+ movq 0x8*6(%rsi), %r11
+ movq 0x8*7(%rsi), %r12
+
+ prefetcht0 5*64(%rsi)
+
+ movq %rax, 0x8*0(%rdi)
+ movq %rbx, 0x8*1(%rdi)
+ movq %rdx, 0x8*2(%rdi)
+ movq %r8, 0x8*3(%rdi)
+ movq %r9, 0x8*4(%rdi)
+ movq %r10, 0x8*5(%rdi)
+ movq %r11, 0x8*6(%rdi)
+ movq %r12, 0x8*7(%rdi)
+
+ leaq 64 (%rsi), %rsi
+ leaq 64 (%rdi), %rdi
+
+ jnz .Loop64
+
+ movl $5, %ecx
+ .p2align 4
+.Loop2:
+ decl %ecx
+
+ movq 0x8*0(%rsi), %rax
+ movq 0x8*1(%rsi), %rbx
+ movq 0x8*2(%rsi), %rdx
+ movq 0x8*3(%rsi), %r8
+ movq 0x8*4(%rsi), %r9
+ movq 0x8*5(%rsi), %r10
+ movq 0x8*6(%rsi), %r11
+ movq 0x8*7(%rsi), %r12
+
+ movq %rax, 0x8*0(%rdi)
+ movq %rbx, 0x8*1(%rdi)
+ movq %rdx, 0x8*2(%rdi)
+ movq %r8, 0x8*3(%rdi)
+ movq %r9, 0x8*4(%rdi)
+ movq %r10, 0x8*5(%rdi)
+ movq %r11, 0x8*6(%rdi)
+ movq %r12, 0x8*7(%rdi)
+
+ leaq 64(%rdi), %rdi
+ leaq 64(%rsi), %rsi
+ jnz .Loop2
+
+ movq (%rsp), %rbx
+ movq 1*8(%rsp), %r12
+ addq $2*8, %rsp
+ RET
+SYM_FUNC_END(copy_page_regs)
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
new file mode 100644
index 0000000000..0a81aafed7
--- /dev/null
+++ b/arch/x86/lib/copy_user_64.S
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright 2008 Vitaly Mayatskikh <vmayatsk@redhat.com>
+ * Copyright 2002 Andi Kleen, SuSE Labs.
+ *
+ * Functions to copy from and to user space.
+ */
+
+#include <linux/linkage.h>
+#include <asm/cpufeatures.h>
+#include <asm/alternative.h>
+#include <asm/asm.h>
+#include <asm/export.h>
+
+/*
+ * rep_movs_alternative - memory copy with exception handling.
+ * This version is for CPUs that don't have FSRM (Fast Short Rep Movs)
+ *
+ * Input:
+ * rdi destination
+ * rsi source
+ * rcx count
+ *
+ * Output:
+ * rcx uncopied bytes or 0 if successful.
+ *
+ * NOTE! The calling convention is very intentionally the same as
+ * for 'rep movs', so that we can rewrite the function call with
+ * just a plain 'rep movs' on machines that have FSRM. But to make
+ * it simpler for us, we can clobber rsi/rdi and rax freely.
+ */
+SYM_FUNC_START(rep_movs_alternative)
+ cmpq $64,%rcx
+ jae .Llarge
+
+ cmp $8,%ecx
+ jae .Lword
+
+ testl %ecx,%ecx
+ je .Lexit
+
+.Lcopy_user_tail:
+0: movb (%rsi),%al
+1: movb %al,(%rdi)
+ inc %rdi
+ inc %rsi
+ dec %rcx
+ jne .Lcopy_user_tail
+.Lexit:
+ RET
+
+ _ASM_EXTABLE_UA( 0b, .Lexit)
+ _ASM_EXTABLE_UA( 1b, .Lexit)
+
+ .p2align 4
+.Lword:
+2: movq (%rsi),%rax
+3: movq %rax,(%rdi)
+ addq $8,%rsi
+ addq $8,%rdi
+ sub $8,%ecx
+ je .Lexit
+ cmp $8,%ecx
+ jae .Lword
+ jmp .Lcopy_user_tail
+
+ _ASM_EXTABLE_UA( 2b, .Lcopy_user_tail)
+ _ASM_EXTABLE_UA( 3b, .Lcopy_user_tail)
+
+.Llarge:
+0: ALTERNATIVE "jmp .Llarge_movsq", "rep movsb", X86_FEATURE_ERMS
+1: RET
+
+ _ASM_EXTABLE_UA( 0b, 1b)
+
+.Llarge_movsq:
+ movq %rcx,%rax
+ shrq $3,%rcx
+ andl $7,%eax
+0: rep movsq
+ movl %eax,%ecx
+ testl %ecx,%ecx
+ jne .Lcopy_user_tail
+ RET
+
+1: leaq (%rax,%rcx,8),%rcx
+ jmp .Lcopy_user_tail
+
+ _ASM_EXTABLE_UA( 0b, 1b)
+SYM_FUNC_END(rep_movs_alternative)
+EXPORT_SYMBOL(rep_movs_alternative)
diff --git a/arch/x86/lib/copy_user_uncached_64.S b/arch/x86/lib/copy_user_uncached_64.S
new file mode 100644
index 0000000000..5c5f38d326
--- /dev/null
+++ b/arch/x86/lib/copy_user_uncached_64.S
@@ -0,0 +1,242 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright 2023 Linus Torvalds <torvalds@linux-foundation.org>
+ */
+
+#include <linux/linkage.h>
+#include <asm/asm.h>
+#include <asm/export.h>
+
+/*
+ * copy_user_nocache - Uncached memory copy with exception handling
+ *
+ * This copies from user space into kernel space, but the kernel
+ * space accesses can take a machine check exception, so they too
+ * need exception handling.
+ *
+ * Note: only 32-bit and 64-bit stores have non-temporal versions,
+ * and we only use aligned versions. Any unaligned parts at the
+ * start or end of the copy will be done using normal cached stores.
+ *
+ * Input:
+ * rdi destination
+ * rsi source
+ * edx count
+ *
+ * Output:
+ * rax uncopied bytes or 0 if successful.
+ */
+SYM_FUNC_START(__copy_user_nocache)
+ /* If destination is not 7-byte aligned, we'll have to align it */
+ testb $7,%dil
+ jne .Lalign
+
+.Lis_aligned:
+ cmp $64,%edx
+ jb .Lquadwords
+
+ .p2align 4,0x90
+.Lunrolled:
+10: movq (%rsi),%r8
+11: movq 8(%rsi),%r9
+12: movq 16(%rsi),%r10
+13: movq 24(%rsi),%r11
+20: movnti %r8,(%rdi)
+21: movnti %r9,8(%rdi)
+22: movnti %r10,16(%rdi)
+23: movnti %r11,24(%rdi)
+30: movq 32(%rsi),%r8
+31: movq 40(%rsi),%r9
+32: movq 48(%rsi),%r10
+33: movq 56(%rsi),%r11
+40: movnti %r8,32(%rdi)
+41: movnti %r9,40(%rdi)
+42: movnti %r10,48(%rdi)
+43: movnti %r11,56(%rdi)
+
+ addq $64,%rsi
+ addq $64,%rdi
+ sub $64,%edx
+ cmp $64,%edx
+ jae .Lunrolled
+
+/*
+ * First set of user mode loads have been done
+ * without any stores, so if they fail, we can
+ * just try the non-unrolled loop.
+ */
+_ASM_EXTABLE_UA(10b, .Lquadwords)
+_ASM_EXTABLE_UA(11b, .Lquadwords)
+_ASM_EXTABLE_UA(12b, .Lquadwords)
+_ASM_EXTABLE_UA(13b, .Lquadwords)
+
+/*
+ * The second set of user mode loads have been
+ * done with 32 bytes stored to the destination,
+ * so we need to take that into account before
+ * falling back to the unrolled loop.
+ */
+_ASM_EXTABLE_UA(30b, .Lfixup32)
+_ASM_EXTABLE_UA(31b, .Lfixup32)
+_ASM_EXTABLE_UA(32b, .Lfixup32)
+_ASM_EXTABLE_UA(33b, .Lfixup32)
+
+/*
+ * An exception on a write means that we're
+ * done, but we need to update the count
+ * depending on where in the unrolled loop
+ * we were.
+ */
+_ASM_EXTABLE_UA(20b, .Ldone0)
+_ASM_EXTABLE_UA(21b, .Ldone8)
+_ASM_EXTABLE_UA(22b, .Ldone16)
+_ASM_EXTABLE_UA(23b, .Ldone24)
+_ASM_EXTABLE_UA(40b, .Ldone32)
+_ASM_EXTABLE_UA(41b, .Ldone40)
+_ASM_EXTABLE_UA(42b, .Ldone48)
+_ASM_EXTABLE_UA(43b, .Ldone56)
+
+.Lquadwords:
+ cmp $8,%edx
+ jb .Llong
+50: movq (%rsi),%rax
+51: movnti %rax,(%rdi)
+ addq $8,%rsi
+ addq $8,%rdi
+ sub $8,%edx
+ jmp .Lquadwords
+
+/*
+ * If we fail on the last full quadword, we will
+ * not try to do any byte-wise cached accesses.
+ * We will try to do one more 4-byte uncached
+ * one, though.
+ */
+_ASM_EXTABLE_UA(50b, .Llast4)
+_ASM_EXTABLE_UA(51b, .Ldone0)
+
+.Llong:
+ test $4,%dl
+ je .Lword
+60: movl (%rsi),%eax
+61: movnti %eax,(%rdi)
+ addq $4,%rsi
+ addq $4,%rdi
+ sub $4,%edx
+.Lword:
+ sfence
+ test $2,%dl
+ je .Lbyte
+70: movw (%rsi),%ax
+71: movw %ax,(%rdi)
+ addq $2,%rsi
+ addq $2,%rdi
+ sub $2,%edx
+.Lbyte:
+ test $1,%dl
+ je .Ldone
+80: movb (%rsi),%al
+81: movb %al,(%rdi)
+ dec %edx
+.Ldone:
+ mov %edx,%eax
+ RET
+
+/*
+ * If we fail on the last four bytes, we won't
+ * bother with any fixups. It's dead, Jim. Note
+ * that there's no need for 'sfence' for any
+ * of this, since the exception will have been
+ * serializing.
+ */
+_ASM_EXTABLE_UA(60b, .Ldone)
+_ASM_EXTABLE_UA(61b, .Ldone)
+_ASM_EXTABLE_UA(70b, .Ldone)
+_ASM_EXTABLE_UA(71b, .Ldone)
+_ASM_EXTABLE_UA(80b, .Ldone)
+_ASM_EXTABLE_UA(81b, .Ldone)
+
+/*
+ * This is the "head needs aliging" case when
+ * the destination isn't 8-byte aligned. The
+ * 4-byte case can be done uncached, but any
+ * smaller alignment is done with regular stores.
+ */
+.Lalign:
+ test $1,%dil
+ je .Lalign_word
+ test %edx,%edx
+ je .Ldone
+90: movb (%rsi),%al
+91: movb %al,(%rdi)
+ inc %rsi
+ inc %rdi
+ dec %edx
+.Lalign_word:
+ test $2,%dil
+ je .Lalign_long
+ cmp $2,%edx
+ jb .Lbyte
+92: movw (%rsi),%ax
+93: movw %ax,(%rdi)
+ addq $2,%rsi
+ addq $2,%rdi
+ sub $2,%edx
+.Lalign_long:
+ test $4,%dil
+ je .Lis_aligned
+ cmp $4,%edx
+ jb .Lword
+94: movl (%rsi),%eax
+95: movnti %eax,(%rdi)
+ addq $4,%rsi
+ addq $4,%rdi
+ sub $4,%edx
+ jmp .Lis_aligned
+
+/*
+ * If we fail on the initial alignment accesses,
+ * we're all done. Again, no point in trying to
+ * do byte-by-byte probing if the 4-byte load
+ * fails - we're not doing any uncached accesses
+ * any more.
+ */
+_ASM_EXTABLE_UA(90b, .Ldone)
+_ASM_EXTABLE_UA(91b, .Ldone)
+_ASM_EXTABLE_UA(92b, .Ldone)
+_ASM_EXTABLE_UA(93b, .Ldone)
+_ASM_EXTABLE_UA(94b, .Ldone)
+_ASM_EXTABLE_UA(95b, .Ldone)
+
+/*
+ * Exception table fixups for faults in the middle
+ */
+.Ldone56: sub $8,%edx
+.Ldone48: sub $8,%edx
+.Ldone40: sub $8,%edx
+.Ldone32: sub $8,%edx
+.Ldone24: sub $8,%edx
+.Ldone16: sub $8,%edx
+.Ldone8: sub $8,%edx
+.Ldone0:
+ mov %edx,%eax
+ RET
+
+.Lfixup32:
+ addq $32,%rsi
+ addq $32,%rdi
+ sub $32,%edx
+ jmp .Lquadwords
+
+.Llast4:
+52: movl (%rsi),%eax
+53: movnti %eax,(%rdi)
+ sfence
+ sub $4,%edx
+ mov %edx,%eax
+ RET
+_ASM_EXTABLE_UA(52b, .Ldone0)
+_ASM_EXTABLE_UA(53b, .Ldone0)
+
+SYM_FUNC_END(__copy_user_nocache)
+EXPORT_SYMBOL(__copy_user_nocache)
diff --git a/arch/x86/lib/cpu.c b/arch/x86/lib/cpu.c
new file mode 100644
index 0000000000..7ad68917a5
--- /dev/null
+++ b/arch/x86/lib/cpu.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/types.h>
+#include <linux/export.h>
+#include <asm/cpu.h>
+
+unsigned int x86_family(unsigned int sig)
+{
+ unsigned int x86;
+
+ x86 = (sig >> 8) & 0xf;
+
+ if (x86 == 0xf)
+ x86 += (sig >> 20) & 0xff;
+
+ return x86;
+}
+EXPORT_SYMBOL_GPL(x86_family);
+
+unsigned int x86_model(unsigned int sig)
+{
+ unsigned int fam, model;
+
+ fam = x86_family(sig);
+
+ model = (sig >> 4) & 0xf;
+
+ if (fam >= 0x6)
+ model += ((sig >> 16) & 0xf) << 4;
+
+ return model;
+}
+EXPORT_SYMBOL_GPL(x86_model);
+
+unsigned int x86_stepping(unsigned int sig)
+{
+ return sig & 0xf;
+}
+EXPORT_SYMBOL_GPL(x86_stepping);
diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S
new file mode 100644
index 0000000000..d9e16a2cf2
--- /dev/null
+++ b/arch/x86/lib/csum-copy_64.S
@@ -0,0 +1,256 @@
+/*
+ * Copyright 2002, 2003 Andi Kleen, SuSE Labs.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file COPYING in the main directory of this archive
+ * for more details. No warranty for anything given at all.
+ */
+#include <linux/linkage.h>
+#include <asm/errno.h>
+#include <asm/asm.h>
+
+/*
+ * Checksum copy with exception handling.
+ * On exceptions src_err_ptr or dst_err_ptr is set to -EFAULT and the
+ * destination is zeroed.
+ *
+ * Input
+ * rdi source
+ * rsi destination
+ * edx len (32bit)
+ *
+ * Output
+ * eax 64bit sum. undefined in case of exception.
+ *
+ * Wrappers need to take care of valid exception sum and zeroing.
+ * They also should align source or destination to 8 bytes.
+ */
+
+ .macro source
+10:
+ _ASM_EXTABLE_UA(10b, .Lfault)
+ .endm
+
+ .macro dest
+20:
+ _ASM_EXTABLE_UA(20b, .Lfault)
+ .endm
+
+SYM_FUNC_START(csum_partial_copy_generic)
+ subq $5*8, %rsp
+ movq %rbx, 0*8(%rsp)
+ movq %r12, 1*8(%rsp)
+ movq %r14, 2*8(%rsp)
+ movq %r13, 3*8(%rsp)
+ movq %r15, 4*8(%rsp)
+
+ movl $-1, %eax
+ xorl %r9d, %r9d
+ movl %edx, %ecx
+ cmpl $8, %ecx
+ jb .Lshort
+
+ testb $7, %sil
+ jne .Lunaligned
+.Laligned:
+ movl %ecx, %r12d
+
+ shrq $6, %r12
+ jz .Lhandle_tail /* < 64 */
+
+ clc
+
+ /* main loop. clear in 64 byte blocks */
+ /* r9: zero, r8: temp2, rbx: temp1, rax: sum, rcx: saved length */
+ /* r11: temp3, rdx: temp4, r12 loopcnt */
+ /* r10: temp5, r15: temp6, r14 temp7, r13 temp8 */
+ .p2align 4
+.Lloop:
+ source
+ movq (%rdi), %rbx
+ source
+ movq 8(%rdi), %r8
+ source
+ movq 16(%rdi), %r11
+ source
+ movq 24(%rdi), %rdx
+
+ source
+ movq 32(%rdi), %r10
+ source
+ movq 40(%rdi), %r15
+ source
+ movq 48(%rdi), %r14
+ source
+ movq 56(%rdi), %r13
+
+30:
+ /*
+ * No _ASM_EXTABLE_UA; this is used for intentional prefetch on a
+ * potentially unmapped kernel address.
+ */
+ _ASM_EXTABLE(30b, 2f)
+ prefetcht0 5*64(%rdi)
+2:
+ adcq %rbx, %rax
+ adcq %r8, %rax
+ adcq %r11, %rax
+ adcq %rdx, %rax
+ adcq %r10, %rax
+ adcq %r15, %rax
+ adcq %r14, %rax
+ adcq %r13, %rax
+
+ decl %r12d
+
+ dest
+ movq %rbx, (%rsi)
+ dest
+ movq %r8, 8(%rsi)
+ dest
+ movq %r11, 16(%rsi)
+ dest
+ movq %rdx, 24(%rsi)
+
+ dest
+ movq %r10, 32(%rsi)
+ dest
+ movq %r15, 40(%rsi)
+ dest
+ movq %r14, 48(%rsi)
+ dest
+ movq %r13, 56(%rsi)
+
+ leaq 64(%rdi), %rdi
+ leaq 64(%rsi), %rsi
+
+ jnz .Lloop
+
+ adcq %r9, %rax
+
+ /* do last up to 56 bytes */
+.Lhandle_tail:
+ /* ecx: count, rcx.63: the end result needs to be rol8 */
+ movq %rcx, %r10
+ andl $63, %ecx
+ shrl $3, %ecx
+ jz .Lfold
+ clc
+ .p2align 4
+.Lloop_8:
+ source
+ movq (%rdi), %rbx
+ adcq %rbx, %rax
+ decl %ecx
+ dest
+ movq %rbx, (%rsi)
+ leaq 8(%rsi), %rsi /* preserve carry */
+ leaq 8(%rdi), %rdi
+ jnz .Lloop_8
+ adcq %r9, %rax /* add in carry */
+
+.Lfold:
+ /* reduce checksum to 32bits */
+ movl %eax, %ebx
+ shrq $32, %rax
+ addl %ebx, %eax
+ adcl %r9d, %eax
+
+ /* do last up to 6 bytes */
+.Lhandle_7:
+ movl %r10d, %ecx
+ andl $7, %ecx
+.L1: /* .Lshort rejoins the common path here */
+ shrl $1, %ecx
+ jz .Lhandle_1
+ movl $2, %edx
+ xorl %ebx, %ebx
+ clc
+ .p2align 4
+.Lloop_1:
+ source
+ movw (%rdi), %bx
+ adcl %ebx, %eax
+ decl %ecx
+ dest
+ movw %bx, (%rsi)
+ leaq 2(%rdi), %rdi
+ leaq 2(%rsi), %rsi
+ jnz .Lloop_1
+ adcl %r9d, %eax /* add in carry */
+
+ /* handle last odd byte */
+.Lhandle_1:
+ testb $1, %r10b
+ jz .Lende
+ xorl %ebx, %ebx
+ source
+ movb (%rdi), %bl
+ dest
+ movb %bl, (%rsi)
+ addl %ebx, %eax
+ adcl %r9d, %eax /* carry */
+
+.Lende:
+ testq %r10, %r10
+ js .Lwas_odd
+.Lout:
+ movq 0*8(%rsp), %rbx
+ movq 1*8(%rsp), %r12
+ movq 2*8(%rsp), %r14
+ movq 3*8(%rsp), %r13
+ movq 4*8(%rsp), %r15
+ addq $5*8, %rsp
+ RET
+.Lshort:
+ movl %ecx, %r10d
+ jmp .L1
+.Lunaligned:
+ xorl %ebx, %ebx
+ testb $1, %sil
+ jne .Lodd
+1: testb $2, %sil
+ je 2f
+ source
+ movw (%rdi), %bx
+ dest
+ movw %bx, (%rsi)
+ leaq 2(%rdi), %rdi
+ subq $2, %rcx
+ leaq 2(%rsi), %rsi
+ addq %rbx, %rax
+2: testb $4, %sil
+ je .Laligned
+ source
+ movl (%rdi), %ebx
+ dest
+ movl %ebx, (%rsi)
+ leaq 4(%rdi), %rdi
+ subq $4, %rcx
+ leaq 4(%rsi), %rsi
+ addq %rbx, %rax
+ jmp .Laligned
+
+.Lodd:
+ source
+ movb (%rdi), %bl
+ dest
+ movb %bl, (%rsi)
+ leaq 1(%rdi), %rdi
+ leaq 1(%rsi), %rsi
+ /* decrement, set MSB */
+ leaq -1(%rcx, %rcx), %rcx
+ rorq $1, %rcx
+ shll $8, %ebx
+ addq %rbx, %rax
+ jmp 1b
+
+.Lwas_odd:
+ roll $8, %eax
+ jmp .Lout
+
+ /* Exception: just return 0 */
+.Lfault:
+ xorl %eax, %eax
+ jmp .Lout
+SYM_FUNC_END(csum_partial_copy_generic)
diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c
new file mode 100644
index 0000000000..c9dae65ac0
--- /dev/null
+++ b/arch/x86/lib/csum-partial_64.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * arch/x86_64/lib/csum-partial.c
+ *
+ * This file contains network checksum routines that are better done
+ * in an architecture-specific manner due to speed.
+ */
+
+#include <linux/compiler.h>
+#include <linux/export.h>
+#include <asm/checksum.h>
+#include <asm/word-at-a-time.h>
+
+static inline __wsum csum_finalize_sum(u64 temp64)
+{
+ return (__force __wsum)((temp64 + ror64(temp64, 32)) >> 32);
+}
+
+static inline unsigned long update_csum_40b(unsigned long sum, const unsigned long m[5])
+{
+ asm("addq %1,%0\n\t"
+ "adcq %2,%0\n\t"
+ "adcq %3,%0\n\t"
+ "adcq %4,%0\n\t"
+ "adcq %5,%0\n\t"
+ "adcq $0,%0"
+ :"+r" (sum)
+ :"m" (m[0]), "m" (m[1]), "m" (m[2]),
+ "m" (m[3]), "m" (m[4]));
+ return sum;
+}
+
+/*
+ * Do a checksum on an arbitrary memory area.
+ * Returns a 32bit checksum.
+ *
+ * This isn't as time critical as it used to be because many NICs
+ * do hardware checksumming these days.
+ *
+ * Still, with CHECKSUM_COMPLETE this is called to compute
+ * checksums on IPv6 headers (40 bytes) and other small parts.
+ * it's best to have buff aligned on a 64-bit boundary
+ */
+__wsum csum_partial(const void *buff, int len, __wsum sum)
+{
+ u64 temp64 = (__force u64)sum;
+
+ /* Do two 40-byte chunks in parallel to get better ILP */
+ if (likely(len >= 80)) {
+ u64 temp64_2 = 0;
+ do {
+ temp64 = update_csum_40b(temp64, buff);
+ temp64_2 = update_csum_40b(temp64_2, buff + 40);
+ buff += 80;
+ len -= 80;
+ } while (len >= 80);
+
+ asm("addq %1,%0\n\t"
+ "adcq $0,%0"
+ :"+r" (temp64): "r" (temp64_2));
+ }
+
+ /*
+ * len == 40 is the hot case due to IPv6 headers, so return
+ * early for that exact case without checking the tail bytes.
+ */
+ if (len >= 40) {
+ temp64 = update_csum_40b(temp64, buff);
+ len -= 40;
+ if (!len)
+ return csum_finalize_sum(temp64);
+ buff += 40;
+ }
+
+ if (len & 32) {
+ asm("addq 0*8(%[src]),%[res]\n\t"
+ "adcq 1*8(%[src]),%[res]\n\t"
+ "adcq 2*8(%[src]),%[res]\n\t"
+ "adcq 3*8(%[src]),%[res]\n\t"
+ "adcq $0,%[res]"
+ : [res] "+r"(temp64)
+ : [src] "r"(buff), "m"(*(const char(*)[32])buff));
+ buff += 32;
+ }
+ if (len & 16) {
+ asm("addq 0*8(%[src]),%[res]\n\t"
+ "adcq 1*8(%[src]),%[res]\n\t"
+ "adcq $0,%[res]"
+ : [res] "+r"(temp64)
+ : [src] "r"(buff), "m"(*(const char(*)[16])buff));
+ buff += 16;
+ }
+ if (len & 8) {
+ asm("addq 0*8(%[src]),%[res]\n\t"
+ "adcq $0,%[res]"
+ : [res] "+r"(temp64)
+ : [src] "r"(buff), "m"(*(const char(*)[8])buff));
+ buff += 8;
+ }
+ if (len & 7) {
+ unsigned int shift = (-len << 3) & 63;
+ unsigned long trail;
+
+ trail = (load_unaligned_zeropad(buff) << shift) >> shift;
+
+ asm("addq %[trail],%[res]\n\t"
+ "adcq $0,%[res]"
+ : [res] "+r"(temp64)
+ : [trail] "r"(trail));
+ }
+ return csum_finalize_sum(temp64);
+}
+EXPORT_SYMBOL(csum_partial);
+
+/*
+ * this routine is used for miscellaneous IP-like checksums, mainly
+ * in icmp.c
+ */
+__sum16 ip_compute_csum(const void *buff, int len)
+{
+ return csum_fold(csum_partial(buff, len, 0));
+}
+EXPORT_SYMBOL(ip_compute_csum);
diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c
new file mode 100644
index 0000000000..145f9a0bde
--- /dev/null
+++ b/arch/x86/lib/csum-wrappers_64.c
@@ -0,0 +1,97 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2002, 2003 Andi Kleen, SuSE Labs.
+ *
+ * Wrappers of assembly checksum functions for x86-64.
+ */
+#include <asm/checksum.h>
+#include <linux/export.h>
+#include <linux/uaccess.h>
+#include <asm/smap.h>
+
+/**
+ * csum_and_copy_from_user - Copy and checksum from user space.
+ * @src: source address (user space)
+ * @dst: destination address
+ * @len: number of bytes to be copied.
+ * @isum: initial sum that is added into the result (32bit unfolded)
+ * @errp: set to -EFAULT for an bad source address.
+ *
+ * Returns an 32bit unfolded checksum of the buffer.
+ * src and dst are best aligned to 64bits.
+ */
+__wsum
+csum_and_copy_from_user(const void __user *src, void *dst, int len)
+{
+ __wsum sum;
+
+ might_sleep();
+ if (!user_access_begin(src, len))
+ return 0;
+ sum = csum_partial_copy_generic((__force const void *)src, dst, len);
+ user_access_end();
+ return sum;
+}
+
+/**
+ * csum_and_copy_to_user - Copy and checksum to user space.
+ * @src: source address
+ * @dst: destination address (user space)
+ * @len: number of bytes to be copied.
+ * @isum: initial sum that is added into the result (32bit unfolded)
+ * @errp: set to -EFAULT for an bad destination address.
+ *
+ * Returns an 32bit unfolded checksum of the buffer.
+ * src and dst are best aligned to 64bits.
+ */
+__wsum
+csum_and_copy_to_user(const void *src, void __user *dst, int len)
+{
+ __wsum sum;
+
+ might_sleep();
+ if (!user_access_begin(dst, len))
+ return 0;
+ sum = csum_partial_copy_generic(src, (void __force *)dst, len);
+ user_access_end();
+ return sum;
+}
+
+/**
+ * csum_partial_copy_nocheck - Copy and checksum.
+ * @src: source address
+ * @dst: destination address
+ * @len: number of bytes to be copied.
+ * @sum: initial sum that is added into the result (32bit unfolded)
+ *
+ * Returns an 32bit unfolded checksum of the buffer.
+ */
+__wsum
+csum_partial_copy_nocheck(const void *src, void *dst, int len)
+{
+ return csum_partial_copy_generic(src, dst, len);
+}
+EXPORT_SYMBOL(csum_partial_copy_nocheck);
+
+__sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+ const struct in6_addr *daddr,
+ __u32 len, __u8 proto, __wsum sum)
+{
+ __u64 rest, sum64;
+
+ rest = (__force __u64)htonl(len) + (__force __u64)htons(proto) +
+ (__force __u64)sum;
+
+ asm(" addq (%[saddr]),%[sum]\n"
+ " adcq 8(%[saddr]),%[sum]\n"
+ " adcq (%[daddr]),%[sum]\n"
+ " adcq 8(%[daddr]),%[sum]\n"
+ " adcq $0,%[sum]\n"
+
+ : [sum] "=r" (sum64)
+ : "[sum]" (rest), [saddr] "r" (saddr), [daddr] "r" (daddr));
+
+ return csum_fold(
+ (__force __wsum)add32_with_carry(sum64 & 0xffffffff, sum64>>32));
+}
+EXPORT_SYMBOL(csum_ipv6_magic);
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
new file mode 100644
index 0000000000..0e65d00e23
--- /dev/null
+++ b/arch/x86/lib/delay.c
@@ -0,0 +1,231 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Precise Delay Loops for i386
+ *
+ * Copyright (C) 1993 Linus Torvalds
+ * Copyright (C) 1997 Martin Mares <mj@atrey.karlin.mff.cuni.cz>
+ * Copyright (C) 2008 Jiri Hladky <hladky _dot_ jiri _at_ gmail _dot_ com>
+ *
+ * The __delay function must _NOT_ be inlined as its execution time
+ * depends wildly on alignment on many x86 processors. The additional
+ * jump magic is needed to get the timing stable on all the CPU's
+ * we have to worry about.
+ */
+
+#include <linux/export.h>
+#include <linux/sched.h>
+#include <linux/timex.h>
+#include <linux/preempt.h>
+#include <linux/delay.h>
+
+#include <asm/processor.h>
+#include <asm/delay.h>
+#include <asm/timer.h>
+#include <asm/mwait.h>
+
+#ifdef CONFIG_SMP
+# include <asm/smp.h>
+#endif
+
+static void delay_loop(u64 __loops);
+
+/*
+ * Calibration and selection of the delay mechanism happens only once
+ * during boot.
+ */
+static void (*delay_fn)(u64) __ro_after_init = delay_loop;
+static void (*delay_halt_fn)(u64 start, u64 cycles) __ro_after_init;
+
+/* simple loop based delay: */
+static void delay_loop(u64 __loops)
+{
+ unsigned long loops = (unsigned long)__loops;
+
+ asm volatile(
+ " test %0,%0 \n"
+ " jz 3f \n"
+ " jmp 1f \n"
+
+ ".align 16 \n"
+ "1: jmp 2f \n"
+
+ ".align 16 \n"
+ "2: dec %0 \n"
+ " jnz 2b \n"
+ "3: dec %0 \n"
+
+ : "+a" (loops)
+ :
+ );
+}
+
+/* TSC based delay: */
+static void delay_tsc(u64 cycles)
+{
+ u64 bclock, now;
+ int cpu;
+
+ preempt_disable();
+ cpu = smp_processor_id();
+ bclock = rdtsc_ordered();
+ for (;;) {
+ now = rdtsc_ordered();
+ if ((now - bclock) >= cycles)
+ break;
+
+ /* Allow RT tasks to run */
+ preempt_enable();
+ rep_nop();
+ preempt_disable();
+
+ /*
+ * It is possible that we moved to another CPU, and
+ * since TSC's are per-cpu we need to calculate
+ * that. The delay must guarantee that we wait "at
+ * least" the amount of time. Being moved to another
+ * CPU could make the wait longer but we just need to
+ * make sure we waited long enough. Rebalance the
+ * counter for this CPU.
+ */
+ if (unlikely(cpu != smp_processor_id())) {
+ cycles -= (now - bclock);
+ cpu = smp_processor_id();
+ bclock = rdtsc_ordered();
+ }
+ }
+ preempt_enable();
+}
+
+/*
+ * On Intel the TPAUSE instruction waits until any of:
+ * 1) the TSC counter exceeds the value provided in EDX:EAX
+ * 2) global timeout in IA32_UMWAIT_CONTROL is exceeded
+ * 3) an external interrupt occurs
+ */
+static void delay_halt_tpause(u64 start, u64 cycles)
+{
+ u64 until = start + cycles;
+ u32 eax, edx;
+
+ eax = lower_32_bits(until);
+ edx = upper_32_bits(until);
+
+ /*
+ * Hard code the deeper (C0.2) sleep state because exit latency is
+ * small compared to the "microseconds" that usleep() will delay.
+ */
+ __tpause(TPAUSE_C02_STATE, edx, eax);
+}
+
+/*
+ * On some AMD platforms, MWAITX has a configurable 32-bit timer, that
+ * counts with TSC frequency. The input value is the number of TSC cycles
+ * to wait. MWAITX will also exit when the timer expires.
+ */
+static void delay_halt_mwaitx(u64 unused, u64 cycles)
+{
+ u64 delay;
+
+ delay = min_t(u64, MWAITX_MAX_WAIT_CYCLES, cycles);
+ /*
+ * Use cpu_tss_rw as a cacheline-aligned, seldomly accessed per-cpu
+ * variable as the monitor target.
+ */
+ __monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0);
+
+ /*
+ * AMD, like Intel, supports the EAX hint and EAX=0xf means, do not
+ * enter any deep C-state and we use it here in delay() to minimize
+ * wakeup latency.
+ */
+ __mwaitx(MWAITX_DISABLE_CSTATES, delay, MWAITX_ECX_TIMER_ENABLE);
+}
+
+/*
+ * Call a vendor specific function to delay for a given amount of time. Because
+ * these functions may return earlier than requested, check for actual elapsed
+ * time and call again until done.
+ */
+static void delay_halt(u64 __cycles)
+{
+ u64 start, end, cycles = __cycles;
+
+ /*
+ * Timer value of 0 causes MWAITX to wait indefinitely, unless there
+ * is a store on the memory monitored by MONITORX.
+ */
+ if (!cycles)
+ return;
+
+ start = rdtsc_ordered();
+
+ for (;;) {
+ delay_halt_fn(start, cycles);
+ end = rdtsc_ordered();
+
+ if (cycles <= end - start)
+ break;
+
+ cycles -= end - start;
+ start = end;
+ }
+}
+
+void __init use_tsc_delay(void)
+{
+ if (delay_fn == delay_loop)
+ delay_fn = delay_tsc;
+}
+
+void __init use_tpause_delay(void)
+{
+ delay_halt_fn = delay_halt_tpause;
+ delay_fn = delay_halt;
+}
+
+void use_mwaitx_delay(void)
+{
+ delay_halt_fn = delay_halt_mwaitx;
+ delay_fn = delay_halt;
+}
+
+int read_current_timer(unsigned long *timer_val)
+{
+ if (delay_fn == delay_tsc) {
+ *timer_val = rdtsc();
+ return 0;
+ }
+ return -1;
+}
+
+void __delay(unsigned long loops)
+{
+ delay_fn(loops);
+}
+EXPORT_SYMBOL(__delay);
+
+noinline void __const_udelay(unsigned long xloops)
+{
+ unsigned long lpj = this_cpu_read(cpu_info.loops_per_jiffy) ? : loops_per_jiffy;
+ int d0;
+
+ xloops *= 4;
+ asm("mull %%edx"
+ :"=d" (xloops), "=&a" (d0)
+ :"1" (xloops), "0" (lpj * (HZ / 4)));
+
+ __delay(++xloops);
+}
+EXPORT_SYMBOL(__const_udelay);
+
+void __udelay(unsigned long usecs)
+{
+ __const_udelay(usecs * 0x000010c7); /* 2**32 / 1000000 (rounded up) */
+}
+EXPORT_SYMBOL(__udelay);
+
+void __ndelay(unsigned long nsecs)
+{
+ __const_udelay(nsecs * 0x00005); /* 2**32 / 1000000000 (rounded up) */
+}
+EXPORT_SYMBOL(__ndelay);
diff --git a/arch/x86/lib/error-inject.c b/arch/x86/lib/error-inject.c
new file mode 100644
index 0000000000..b5a6d83106
--- /dev/null
+++ b/arch/x86/lib/error-inject.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/linkage.h>
+#include <linux/error-injection.h>
+#include <linux/kprobes.h>
+#include <linux/objtool.h>
+
+asmlinkage void just_return_func(void);
+
+asm(
+ ".text\n"
+ ".type just_return_func, @function\n"
+ ".globl just_return_func\n"
+ ASM_FUNC_ALIGN
+ "just_return_func:\n"
+ ANNOTATE_NOENDBR
+ ASM_RET
+ ".size just_return_func, .-just_return_func\n"
+);
+
+void override_function_with_return(struct pt_regs *regs)
+{
+ regs->ip = (unsigned long)&just_return_func;
+}
+NOKPROBE_SYMBOL(override_function_with_return);
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
new file mode 100644
index 0000000000..9c63713477
--- /dev/null
+++ b/arch/x86/lib/getuser.S
@@ -0,0 +1,185 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * __get_user functions.
+ *
+ * (C) Copyright 1998 Linus Torvalds
+ * (C) Copyright 2005 Andi Kleen
+ * (C) Copyright 2008 Glauber Costa
+ *
+ * These functions have a non-standard call interface
+ * to make them more efficient, especially as they
+ * return an error value in addition to the "real"
+ * return value.
+ */
+
+/*
+ * __get_user_X
+ *
+ * Inputs: %[r|e]ax contains the address.
+ *
+ * Outputs: %[r|e]ax is error code (0 or -EFAULT)
+ * %[r|e]dx contains zero-extended value
+ * %ecx contains the high half for 32-bit __get_user_8
+ *
+ *
+ * These functions should not modify any other registers,
+ * as they get called from within inline assembly.
+ */
+
+#include <linux/linkage.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/export.h>
+
+#define ASM_BARRIER_NOSPEC ALTERNATIVE "", "lfence", X86_FEATURE_LFENCE_RDTSC
+
+.macro check_range size:req
+.if IS_ENABLED(CONFIG_X86_64)
+ mov %rax, %rdx
+ sar $63, %rdx
+ or %rdx, %rax
+.else
+ cmp $TASK_SIZE_MAX-\size+1, %eax
+ jae .Lbad_get_user
+ sbb %edx, %edx /* array_index_mask_nospec() */
+ and %edx, %eax
+.endif
+.endm
+
+ .text
+SYM_FUNC_START(__get_user_1)
+ check_range size=1
+ ASM_STAC
+1: movzbl (%_ASM_AX),%edx
+ xor %eax,%eax
+ ASM_CLAC
+ RET
+SYM_FUNC_END(__get_user_1)
+EXPORT_SYMBOL(__get_user_1)
+
+SYM_FUNC_START(__get_user_2)
+ check_range size=2
+ ASM_STAC
+2: movzwl (%_ASM_AX),%edx
+ xor %eax,%eax
+ ASM_CLAC
+ RET
+SYM_FUNC_END(__get_user_2)
+EXPORT_SYMBOL(__get_user_2)
+
+SYM_FUNC_START(__get_user_4)
+ check_range size=4
+ ASM_STAC
+3: movl (%_ASM_AX),%edx
+ xor %eax,%eax
+ ASM_CLAC
+ RET
+SYM_FUNC_END(__get_user_4)
+EXPORT_SYMBOL(__get_user_4)
+
+SYM_FUNC_START(__get_user_8)
+ check_range size=8
+ ASM_STAC
+#ifdef CONFIG_X86_64
+4: movq (%_ASM_AX),%rdx
+#else
+4: movl (%_ASM_AX),%edx
+5: movl 4(%_ASM_AX),%ecx
+#endif
+ xor %eax,%eax
+ ASM_CLAC
+ RET
+SYM_FUNC_END(__get_user_8)
+EXPORT_SYMBOL(__get_user_8)
+
+/* .. and the same for __get_user, just without the range checks */
+SYM_FUNC_START(__get_user_nocheck_1)
+ ASM_STAC
+ ASM_BARRIER_NOSPEC
+6: movzbl (%_ASM_AX),%edx
+ xor %eax,%eax
+ ASM_CLAC
+ RET
+SYM_FUNC_END(__get_user_nocheck_1)
+EXPORT_SYMBOL(__get_user_nocheck_1)
+
+SYM_FUNC_START(__get_user_nocheck_2)
+ ASM_STAC
+ ASM_BARRIER_NOSPEC
+7: movzwl (%_ASM_AX),%edx
+ xor %eax,%eax
+ ASM_CLAC
+ RET
+SYM_FUNC_END(__get_user_nocheck_2)
+EXPORT_SYMBOL(__get_user_nocheck_2)
+
+SYM_FUNC_START(__get_user_nocheck_4)
+ ASM_STAC
+ ASM_BARRIER_NOSPEC
+8: movl (%_ASM_AX),%edx
+ xor %eax,%eax
+ ASM_CLAC
+ RET
+SYM_FUNC_END(__get_user_nocheck_4)
+EXPORT_SYMBOL(__get_user_nocheck_4)
+
+SYM_FUNC_START(__get_user_nocheck_8)
+ ASM_STAC
+ ASM_BARRIER_NOSPEC
+#ifdef CONFIG_X86_64
+9: movq (%_ASM_AX),%rdx
+#else
+9: movl (%_ASM_AX),%edx
+10: movl 4(%_ASM_AX),%ecx
+#endif
+ xor %eax,%eax
+ ASM_CLAC
+ RET
+SYM_FUNC_END(__get_user_nocheck_8)
+EXPORT_SYMBOL(__get_user_nocheck_8)
+
+
+SYM_CODE_START_LOCAL(__get_user_handle_exception)
+ ASM_CLAC
+.Lbad_get_user:
+ xor %edx,%edx
+ mov $(-EFAULT),%_ASM_AX
+ RET
+SYM_CODE_END(__get_user_handle_exception)
+
+#ifdef CONFIG_X86_32
+SYM_CODE_START_LOCAL(__get_user_8_handle_exception)
+ ASM_CLAC
+bad_get_user_8:
+ xor %edx,%edx
+ xor %ecx,%ecx
+ mov $(-EFAULT),%_ASM_AX
+ RET
+SYM_CODE_END(__get_user_8_handle_exception)
+#endif
+
+/* get_user */
+ _ASM_EXTABLE(1b, __get_user_handle_exception)
+ _ASM_EXTABLE(2b, __get_user_handle_exception)
+ _ASM_EXTABLE(3b, __get_user_handle_exception)
+#ifdef CONFIG_X86_64
+ _ASM_EXTABLE(4b, __get_user_handle_exception)
+#else
+ _ASM_EXTABLE(4b, __get_user_8_handle_exception)
+ _ASM_EXTABLE(5b, __get_user_8_handle_exception)
+#endif
+
+/* __get_user */
+ _ASM_EXTABLE(6b, __get_user_handle_exception)
+ _ASM_EXTABLE(7b, __get_user_handle_exception)
+ _ASM_EXTABLE(8b, __get_user_handle_exception)
+#ifdef CONFIG_X86_64
+ _ASM_EXTABLE(9b, __get_user_handle_exception)
+#else
+ _ASM_EXTABLE(9b, __get_user_8_handle_exception)
+ _ASM_EXTABLE(10b, __get_user_8_handle_exception)
+#endif
diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S
new file mode 100644
index 0000000000..12c16c6aa4
--- /dev/null
+++ b/arch/x86/lib/hweight.S
@@ -0,0 +1,83 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/linkage.h>
+#include <asm/export.h>
+
+#include <asm/asm.h>
+
+/*
+ * unsigned int __sw_hweight32(unsigned int w)
+ * %rdi: w
+ */
+SYM_FUNC_START(__sw_hweight32)
+
+#ifdef CONFIG_X86_64
+ movl %edi, %eax # w
+#endif
+ __ASM_SIZE(push,) %__ASM_REG(dx)
+ movl %eax, %edx # w -> t
+ shrl %edx # t >>= 1
+ andl $0x55555555, %edx # t &= 0x55555555
+ subl %edx, %eax # w -= t
+
+ movl %eax, %edx # w -> t
+ shrl $2, %eax # w_tmp >>= 2
+ andl $0x33333333, %edx # t &= 0x33333333
+ andl $0x33333333, %eax # w_tmp &= 0x33333333
+ addl %edx, %eax # w = w_tmp + t
+
+ movl %eax, %edx # w -> t
+ shrl $4, %edx # t >>= 4
+ addl %edx, %eax # w_tmp += t
+ andl $0x0f0f0f0f, %eax # w_tmp &= 0x0f0f0f0f
+ imull $0x01010101, %eax, %eax # w_tmp *= 0x01010101
+ shrl $24, %eax # w = w_tmp >> 24
+ __ASM_SIZE(pop,) %__ASM_REG(dx)
+ RET
+SYM_FUNC_END(__sw_hweight32)
+EXPORT_SYMBOL(__sw_hweight32)
+
+SYM_FUNC_START(__sw_hweight64)
+#ifdef CONFIG_X86_64
+ pushq %rdi
+ pushq %rdx
+
+ movq %rdi, %rdx # w -> t
+ movabsq $0x5555555555555555, %rax
+ shrq %rdx # t >>= 1
+ andq %rdx, %rax # t &= 0x5555555555555555
+ movabsq $0x3333333333333333, %rdx
+ subq %rax, %rdi # w -= t
+
+ movq %rdi, %rax # w -> t
+ shrq $2, %rdi # w_tmp >>= 2
+ andq %rdx, %rax # t &= 0x3333333333333333
+ andq %rdi, %rdx # w_tmp &= 0x3333333333333333
+ addq %rdx, %rax # w = w_tmp + t
+
+ movq %rax, %rdx # w -> t
+ shrq $4, %rdx # t >>= 4
+ addq %rdx, %rax # w_tmp += t
+ movabsq $0x0f0f0f0f0f0f0f0f, %rdx
+ andq %rdx, %rax # w_tmp &= 0x0f0f0f0f0f0f0f0f
+ movabsq $0x0101010101010101, %rdx
+ imulq %rdx, %rax # w_tmp *= 0x0101010101010101
+ shrq $56, %rax # w = w_tmp >> 56
+
+ popq %rdx
+ popq %rdi
+ RET
+#else /* CONFIG_X86_32 */
+ /* We're getting an u64 arg in (%eax,%edx): unsigned long hweight64(__u64 w) */
+ pushl %ecx
+
+ call __sw_hweight32
+ movl %eax, %ecx # stash away result
+ movl %edx, %eax # second part of input
+ call __sw_hweight32
+ addl %ecx, %eax # result
+
+ popl %ecx
+ RET
+#endif
+SYM_FUNC_END(__sw_hweight64)
+EXPORT_SYMBOL(__sw_hweight64)
diff --git a/arch/x86/lib/inat.c b/arch/x86/lib/inat.c
new file mode 100644
index 0000000000..b0f3b2a62a
--- /dev/null
+++ b/arch/x86/lib/inat.c
@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * x86 instruction attribute tables
+ *
+ * Written by Masami Hiramatsu <mhiramat@redhat.com>
+ */
+#include <asm/insn.h> /* __ignore_sync_check__ */
+
+/* Attribute tables are generated from opcode map */
+#include "inat-tables.c"
+
+/* Attribute search APIs */
+insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode)
+{
+ return inat_primary_table[opcode];
+}
+
+int inat_get_last_prefix_id(insn_byte_t last_pfx)
+{
+ insn_attr_t lpfx_attr;
+
+ lpfx_attr = inat_get_opcode_attribute(last_pfx);
+ return inat_last_prefix_id(lpfx_attr);
+}
+
+insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, int lpfx_id,
+ insn_attr_t esc_attr)
+{
+ const insn_attr_t *table;
+ int n;
+
+ n = inat_escape_id(esc_attr);
+
+ table = inat_escape_tables[n][0];
+ if (!table)
+ return 0;
+ if (inat_has_variant(table[opcode]) && lpfx_id) {
+ table = inat_escape_tables[n][lpfx_id];
+ if (!table)
+ return 0;
+ }
+ return table[opcode];
+}
+
+insn_attr_t inat_get_group_attribute(insn_byte_t modrm, int lpfx_id,
+ insn_attr_t grp_attr)
+{
+ const insn_attr_t *table;
+ int n;
+
+ n = inat_group_id(grp_attr);
+
+ table = inat_group_tables[n][0];
+ if (!table)
+ return inat_group_common_attribute(grp_attr);
+ if (inat_has_variant(table[X86_MODRM_REG(modrm)]) && lpfx_id) {
+ table = inat_group_tables[n][lpfx_id];
+ if (!table)
+ return inat_group_common_attribute(grp_attr);
+ }
+ return table[X86_MODRM_REG(modrm)] |
+ inat_group_common_attribute(grp_attr);
+}
+
+insn_attr_t inat_get_avx_attribute(insn_byte_t opcode, insn_byte_t vex_m,
+ insn_byte_t vex_p)
+{
+ const insn_attr_t *table;
+ if (vex_m > X86_VEX_M_MAX || vex_p > INAT_LSTPFX_MAX)
+ return 0;
+ /* At first, this checks the master table */
+ table = inat_avx_tables[vex_m][0];
+ if (!table)
+ return 0;
+ if (!inat_is_group(table[opcode]) && vex_p) {
+ /* If this is not a group, get attribute directly */
+ table = inat_avx_tables[vex_m][vex_p];
+ if (!table)
+ return 0;
+ }
+ return table[opcode];
+}
+
diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c
new file mode 100644
index 0000000000..558a605929
--- /dev/null
+++ b/arch/x86/lib/insn-eval.c
@@ -0,0 +1,1670 @@
+/*
+ * Utility functions for x86 operand and address decoding
+ *
+ * Copyright (C) Intel Corporation 2017
+ */
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/ratelimit.h>
+#include <linux/mmu_context.h>
+#include <asm/desc_defs.h>
+#include <asm/desc.h>
+#include <asm/inat.h>
+#include <asm/insn.h>
+#include <asm/insn-eval.h>
+#include <asm/ldt.h>
+#include <asm/vm86.h>
+
+#undef pr_fmt
+#define pr_fmt(fmt) "insn: " fmt
+
+enum reg_type {
+ REG_TYPE_RM = 0,
+ REG_TYPE_REG,
+ REG_TYPE_INDEX,
+ REG_TYPE_BASE,
+};
+
+/**
+ * is_string_insn() - Determine if instruction is a string instruction
+ * @insn: Instruction containing the opcode to inspect
+ *
+ * Returns:
+ *
+ * true if the instruction, determined by the opcode, is any of the
+ * string instructions as defined in the Intel Software Development manual.
+ * False otherwise.
+ */
+static bool is_string_insn(struct insn *insn)
+{
+ /* All string instructions have a 1-byte opcode. */
+ if (insn->opcode.nbytes != 1)
+ return false;
+
+ switch (insn->opcode.bytes[0]) {
+ case 0x6c ... 0x6f: /* INS, OUTS */
+ case 0xa4 ... 0xa7: /* MOVS, CMPS */
+ case 0xaa ... 0xaf: /* STOS, LODS, SCAS */
+ return true;
+ default:
+ return false;
+ }
+}
+
+/**
+ * insn_has_rep_prefix() - Determine if instruction has a REP prefix
+ * @insn: Instruction containing the prefix to inspect
+ *
+ * Returns:
+ *
+ * true if the instruction has a REP prefix, false if not.
+ */
+bool insn_has_rep_prefix(struct insn *insn)
+{
+ insn_byte_t p;
+ int i;
+
+ insn_get_prefixes(insn);
+
+ for_each_insn_prefix(insn, i, p) {
+ if (p == 0xf2 || p == 0xf3)
+ return true;
+ }
+
+ return false;
+}
+
+/**
+ * get_seg_reg_override_idx() - obtain segment register override index
+ * @insn: Valid instruction with segment override prefixes
+ *
+ * Inspect the instruction prefixes in @insn and find segment overrides, if any.
+ *
+ * Returns:
+ *
+ * A constant identifying the segment register to use, among CS, SS, DS,
+ * ES, FS, or GS. INAT_SEG_REG_DEFAULT is returned if no segment override
+ * prefixes were found.
+ *
+ * -EINVAL in case of error.
+ */
+static int get_seg_reg_override_idx(struct insn *insn)
+{
+ int idx = INAT_SEG_REG_DEFAULT;
+ int num_overrides = 0, i;
+ insn_byte_t p;
+
+ insn_get_prefixes(insn);
+
+ /* Look for any segment override prefixes. */
+ for_each_insn_prefix(insn, i, p) {
+ insn_attr_t attr;
+
+ attr = inat_get_opcode_attribute(p);
+ switch (attr) {
+ case INAT_MAKE_PREFIX(INAT_PFX_CS):
+ idx = INAT_SEG_REG_CS;
+ num_overrides++;
+ break;
+ case INAT_MAKE_PREFIX(INAT_PFX_SS):
+ idx = INAT_SEG_REG_SS;
+ num_overrides++;
+ break;
+ case INAT_MAKE_PREFIX(INAT_PFX_DS):
+ idx = INAT_SEG_REG_DS;
+ num_overrides++;
+ break;
+ case INAT_MAKE_PREFIX(INAT_PFX_ES):
+ idx = INAT_SEG_REG_ES;
+ num_overrides++;
+ break;
+ case INAT_MAKE_PREFIX(INAT_PFX_FS):
+ idx = INAT_SEG_REG_FS;
+ num_overrides++;
+ break;
+ case INAT_MAKE_PREFIX(INAT_PFX_GS):
+ idx = INAT_SEG_REG_GS;
+ num_overrides++;
+ break;
+ /* No default action needed. */
+ }
+ }
+
+ /* More than one segment override prefix leads to undefined behavior. */
+ if (num_overrides > 1)
+ return -EINVAL;
+
+ return idx;
+}
+
+/**
+ * check_seg_overrides() - check if segment override prefixes are allowed
+ * @insn: Valid instruction with segment override prefixes
+ * @regoff: Operand offset, in pt_regs, for which the check is performed
+ *
+ * For a particular register used in register-indirect addressing, determine if
+ * segment override prefixes can be used. Specifically, no overrides are allowed
+ * for rDI if used with a string instruction.
+ *
+ * Returns:
+ *
+ * True if segment override prefixes can be used with the register indicated
+ * in @regoff. False if otherwise.
+ */
+static bool check_seg_overrides(struct insn *insn, int regoff)
+{
+ if (regoff == offsetof(struct pt_regs, di) && is_string_insn(insn))
+ return false;
+
+ return true;
+}
+
+/**
+ * resolve_default_seg() - resolve default segment register index for an operand
+ * @insn: Instruction with opcode and address size. Must be valid.
+ * @regs: Register values as seen when entering kernel mode
+ * @off: Operand offset, in pt_regs, for which resolution is needed
+ *
+ * Resolve the default segment register index associated with the instruction
+ * operand register indicated by @off. Such index is resolved based on defaults
+ * described in the Intel Software Development Manual.
+ *
+ * Returns:
+ *
+ * If in protected mode, a constant identifying the segment register to use,
+ * among CS, SS, ES or DS. If in long mode, INAT_SEG_REG_IGNORE.
+ *
+ * -EINVAL in case of error.
+ */
+static int resolve_default_seg(struct insn *insn, struct pt_regs *regs, int off)
+{
+ if (any_64bit_mode(regs))
+ return INAT_SEG_REG_IGNORE;
+ /*
+ * Resolve the default segment register as described in Section 3.7.4
+ * of the Intel Software Development Manual Vol. 1:
+ *
+ * + DS for all references involving r[ABCD]X, and rSI.
+ * + If used in a string instruction, ES for rDI. Otherwise, DS.
+ * + AX, CX and DX are not valid register operands in 16-bit address
+ * encodings but are valid for 32-bit and 64-bit encodings.
+ * + -EDOM is reserved to identify for cases in which no register
+ * is used (i.e., displacement-only addressing). Use DS.
+ * + SS for rSP or rBP.
+ * + CS for rIP.
+ */
+
+ switch (off) {
+ case offsetof(struct pt_regs, ax):
+ case offsetof(struct pt_regs, cx):
+ case offsetof(struct pt_regs, dx):
+ /* Need insn to verify address size. */
+ if (insn->addr_bytes == 2)
+ return -EINVAL;
+
+ fallthrough;
+
+ case -EDOM:
+ case offsetof(struct pt_regs, bx):
+ case offsetof(struct pt_regs, si):
+ return INAT_SEG_REG_DS;
+
+ case offsetof(struct pt_regs, di):
+ if (is_string_insn(insn))
+ return INAT_SEG_REG_ES;
+ return INAT_SEG_REG_DS;
+
+ case offsetof(struct pt_regs, bp):
+ case offsetof(struct pt_regs, sp):
+ return INAT_SEG_REG_SS;
+
+ case offsetof(struct pt_regs, ip):
+ return INAT_SEG_REG_CS;
+
+ default:
+ return -EINVAL;
+ }
+}
+
+/**
+ * resolve_seg_reg() - obtain segment register index
+ * @insn: Instruction with operands
+ * @regs: Register values as seen when entering kernel mode
+ * @regoff: Operand offset, in pt_regs, used to determine segment register
+ *
+ * Determine the segment register associated with the operands and, if
+ * applicable, prefixes and the instruction pointed by @insn.
+ *
+ * The segment register associated to an operand used in register-indirect
+ * addressing depends on:
+ *
+ * a) Whether running in long mode (in such a case segments are ignored, except
+ * if FS or GS are used).
+ *
+ * b) Whether segment override prefixes can be used. Certain instructions and
+ * registers do not allow override prefixes.
+ *
+ * c) Whether segment overrides prefixes are found in the instruction prefixes.
+ *
+ * d) If there are not segment override prefixes or they cannot be used, the
+ * default segment register associated with the operand register is used.
+ *
+ * The function checks first if segment override prefixes can be used with the
+ * operand indicated by @regoff. If allowed, obtain such overridden segment
+ * register index. Lastly, if not prefixes were found or cannot be used, resolve
+ * the segment register index to use based on the defaults described in the
+ * Intel documentation. In long mode, all segment register indexes will be
+ * ignored, except if overrides were found for FS or GS. All these operations
+ * are done using helper functions.
+ *
+ * The operand register, @regoff, is represented as the offset from the base of
+ * pt_regs.
+ *
+ * As stated, the main use of this function is to determine the segment register
+ * index based on the instruction, its operands and prefixes. Hence, @insn
+ * must be valid. However, if @regoff indicates rIP, we don't need to inspect
+ * @insn at all as in this case CS is used in all cases. This case is checked
+ * before proceeding further.
+ *
+ * Please note that this function does not return the value in the segment
+ * register (i.e., the segment selector) but our defined index. The segment
+ * selector needs to be obtained using get_segment_selector() and passing the
+ * segment register index resolved by this function.
+ *
+ * Returns:
+ *
+ * An index identifying the segment register to use, among CS, SS, DS,
+ * ES, FS, or GS. INAT_SEG_REG_IGNORE is returned if running in long mode.
+ *
+ * -EINVAL in case of error.
+ */
+static int resolve_seg_reg(struct insn *insn, struct pt_regs *regs, int regoff)
+{
+ int idx;
+
+ /*
+ * In the unlikely event of having to resolve the segment register
+ * index for rIP, do it first. Segment override prefixes should not
+ * be used. Hence, it is not necessary to inspect the instruction,
+ * which may be invalid at this point.
+ */
+ if (regoff == offsetof(struct pt_regs, ip)) {
+ if (any_64bit_mode(regs))
+ return INAT_SEG_REG_IGNORE;
+ else
+ return INAT_SEG_REG_CS;
+ }
+
+ if (!insn)
+ return -EINVAL;
+
+ if (!check_seg_overrides(insn, regoff))
+ return resolve_default_seg(insn, regs, regoff);
+
+ idx = get_seg_reg_override_idx(insn);
+ if (idx < 0)
+ return idx;
+
+ if (idx == INAT_SEG_REG_DEFAULT)
+ return resolve_default_seg(insn, regs, regoff);
+
+ /*
+ * In long mode, segment override prefixes are ignored, except for
+ * overrides for FS and GS.
+ */
+ if (any_64bit_mode(regs)) {
+ if (idx != INAT_SEG_REG_FS &&
+ idx != INAT_SEG_REG_GS)
+ idx = INAT_SEG_REG_IGNORE;
+ }
+
+ return idx;
+}
+
+/**
+ * get_segment_selector() - obtain segment selector
+ * @regs: Register values as seen when entering kernel mode
+ * @seg_reg_idx: Segment register index to use
+ *
+ * Obtain the segment selector from any of the CS, SS, DS, ES, FS, GS segment
+ * registers. In CONFIG_X86_32, the segment is obtained from either pt_regs or
+ * kernel_vm86_regs as applicable. In CONFIG_X86_64, CS and SS are obtained
+ * from pt_regs. DS, ES, FS and GS are obtained by reading the actual CPU
+ * registers. This done for only for completeness as in CONFIG_X86_64 segment
+ * registers are ignored.
+ *
+ * Returns:
+ *
+ * Value of the segment selector, including null when running in
+ * long mode.
+ *
+ * -EINVAL on error.
+ */
+static short get_segment_selector(struct pt_regs *regs, int seg_reg_idx)
+{
+ unsigned short sel;
+
+#ifdef CONFIG_X86_64
+ switch (seg_reg_idx) {
+ case INAT_SEG_REG_IGNORE:
+ return 0;
+ case INAT_SEG_REG_CS:
+ return (unsigned short)(regs->cs & 0xffff);
+ case INAT_SEG_REG_SS:
+ return (unsigned short)(regs->ss & 0xffff);
+ case INAT_SEG_REG_DS:
+ savesegment(ds, sel);
+ return sel;
+ case INAT_SEG_REG_ES:
+ savesegment(es, sel);
+ return sel;
+ case INAT_SEG_REG_FS:
+ savesegment(fs, sel);
+ return sel;
+ case INAT_SEG_REG_GS:
+ savesegment(gs, sel);
+ return sel;
+ default:
+ return -EINVAL;
+ }
+#else /* CONFIG_X86_32 */
+ struct kernel_vm86_regs *vm86regs = (struct kernel_vm86_regs *)regs;
+
+ if (v8086_mode(regs)) {
+ switch (seg_reg_idx) {
+ case INAT_SEG_REG_CS:
+ return (unsigned short)(regs->cs & 0xffff);
+ case INAT_SEG_REG_SS:
+ return (unsigned short)(regs->ss & 0xffff);
+ case INAT_SEG_REG_DS:
+ return vm86regs->ds;
+ case INAT_SEG_REG_ES:
+ return vm86regs->es;
+ case INAT_SEG_REG_FS:
+ return vm86regs->fs;
+ case INAT_SEG_REG_GS:
+ return vm86regs->gs;
+ case INAT_SEG_REG_IGNORE:
+ default:
+ return -EINVAL;
+ }
+ }
+
+ switch (seg_reg_idx) {
+ case INAT_SEG_REG_CS:
+ return (unsigned short)(regs->cs & 0xffff);
+ case INAT_SEG_REG_SS:
+ return (unsigned short)(regs->ss & 0xffff);
+ case INAT_SEG_REG_DS:
+ return (unsigned short)(regs->ds & 0xffff);
+ case INAT_SEG_REG_ES:
+ return (unsigned short)(regs->es & 0xffff);
+ case INAT_SEG_REG_FS:
+ return (unsigned short)(regs->fs & 0xffff);
+ case INAT_SEG_REG_GS:
+ savesegment(gs, sel);
+ return sel;
+ case INAT_SEG_REG_IGNORE:
+ default:
+ return -EINVAL;
+ }
+#endif /* CONFIG_X86_64 */
+}
+
+static const int pt_regoff[] = {
+ offsetof(struct pt_regs, ax),
+ offsetof(struct pt_regs, cx),
+ offsetof(struct pt_regs, dx),
+ offsetof(struct pt_regs, bx),
+ offsetof(struct pt_regs, sp),
+ offsetof(struct pt_regs, bp),
+ offsetof(struct pt_regs, si),
+ offsetof(struct pt_regs, di),
+#ifdef CONFIG_X86_64
+ offsetof(struct pt_regs, r8),
+ offsetof(struct pt_regs, r9),
+ offsetof(struct pt_regs, r10),
+ offsetof(struct pt_regs, r11),
+ offsetof(struct pt_regs, r12),
+ offsetof(struct pt_regs, r13),
+ offsetof(struct pt_regs, r14),
+ offsetof(struct pt_regs, r15),
+#else
+ offsetof(struct pt_regs, ds),
+ offsetof(struct pt_regs, es),
+ offsetof(struct pt_regs, fs),
+ offsetof(struct pt_regs, gs),
+#endif
+};
+
+int pt_regs_offset(struct pt_regs *regs, int regno)
+{
+ if ((unsigned)regno < ARRAY_SIZE(pt_regoff))
+ return pt_regoff[regno];
+ return -EDOM;
+}
+
+static int get_regno(struct insn *insn, enum reg_type type)
+{
+ int nr_registers = ARRAY_SIZE(pt_regoff);
+ int regno = 0;
+
+ /*
+ * Don't possibly decode a 32-bit instructions as
+ * reading a 64-bit-only register.
+ */
+ if (IS_ENABLED(CONFIG_X86_64) && !insn->x86_64)
+ nr_registers -= 8;
+
+ switch (type) {
+ case REG_TYPE_RM:
+ regno = X86_MODRM_RM(insn->modrm.value);
+
+ /*
+ * ModRM.mod == 0 and ModRM.rm == 5 means a 32-bit displacement
+ * follows the ModRM byte.
+ */
+ if (!X86_MODRM_MOD(insn->modrm.value) && regno == 5)
+ return -EDOM;
+
+ if (X86_REX_B(insn->rex_prefix.value))
+ regno += 8;
+ break;
+
+ case REG_TYPE_REG:
+ regno = X86_MODRM_REG(insn->modrm.value);
+
+ if (X86_REX_R(insn->rex_prefix.value))
+ regno += 8;
+ break;
+
+ case REG_TYPE_INDEX:
+ regno = X86_SIB_INDEX(insn->sib.value);
+ if (X86_REX_X(insn->rex_prefix.value))
+ regno += 8;
+
+ /*
+ * If ModRM.mod != 3 and SIB.index = 4 the scale*index
+ * portion of the address computation is null. This is
+ * true only if REX.X is 0. In such a case, the SIB index
+ * is used in the address computation.
+ */
+ if (X86_MODRM_MOD(insn->modrm.value) != 3 && regno == 4)
+ return -EDOM;
+ break;
+
+ case REG_TYPE_BASE:
+ regno = X86_SIB_BASE(insn->sib.value);
+ /*
+ * If ModRM.mod is 0 and SIB.base == 5, the base of the
+ * register-indirect addressing is 0. In this case, a
+ * 32-bit displacement follows the SIB byte.
+ */
+ if (!X86_MODRM_MOD(insn->modrm.value) && regno == 5)
+ return -EDOM;
+
+ if (X86_REX_B(insn->rex_prefix.value))
+ regno += 8;
+ break;
+
+ default:
+ pr_err_ratelimited("invalid register type: %d\n", type);
+ return -EINVAL;
+ }
+
+ if (regno >= nr_registers) {
+ WARN_ONCE(1, "decoded an instruction with an invalid register");
+ return -EINVAL;
+ }
+ return regno;
+}
+
+static int get_reg_offset(struct insn *insn, struct pt_regs *regs,
+ enum reg_type type)
+{
+ int regno = get_regno(insn, type);
+
+ if (regno < 0)
+ return regno;
+
+ return pt_regs_offset(regs, regno);
+}
+
+/**
+ * get_reg_offset_16() - Obtain offset of register indicated by instruction
+ * @insn: Instruction containing ModRM byte
+ * @regs: Register values as seen when entering kernel mode
+ * @offs1: Offset of the first operand register
+ * @offs2: Offset of the second operand register, if applicable
+ *
+ * Obtain the offset, in pt_regs, of the registers indicated by the ModRM byte
+ * in @insn. This function is to be used with 16-bit address encodings. The
+ * @offs1 and @offs2 will be written with the offset of the two registers
+ * indicated by the instruction. In cases where any of the registers is not
+ * referenced by the instruction, the value will be set to -EDOM.
+ *
+ * Returns:
+ *
+ * 0 on success, -EINVAL on error.
+ */
+static int get_reg_offset_16(struct insn *insn, struct pt_regs *regs,
+ int *offs1, int *offs2)
+{
+ /*
+ * 16-bit addressing can use one or two registers. Specifics of
+ * encodings are given in Table 2-1. "16-Bit Addressing Forms with the
+ * ModR/M Byte" of the Intel Software Development Manual.
+ */
+ static const int regoff1[] = {
+ offsetof(struct pt_regs, bx),
+ offsetof(struct pt_regs, bx),
+ offsetof(struct pt_regs, bp),
+ offsetof(struct pt_regs, bp),
+ offsetof(struct pt_regs, si),
+ offsetof(struct pt_regs, di),
+ offsetof(struct pt_regs, bp),
+ offsetof(struct pt_regs, bx),
+ };
+
+ static const int regoff2[] = {
+ offsetof(struct pt_regs, si),
+ offsetof(struct pt_regs, di),
+ offsetof(struct pt_regs, si),
+ offsetof(struct pt_regs, di),
+ -EDOM,
+ -EDOM,
+ -EDOM,
+ -EDOM,
+ };
+
+ if (!offs1 || !offs2)
+ return -EINVAL;
+
+ /* Operand is a register, use the generic function. */
+ if (X86_MODRM_MOD(insn->modrm.value) == 3) {
+ *offs1 = insn_get_modrm_rm_off(insn, regs);
+ *offs2 = -EDOM;
+ return 0;
+ }
+
+ *offs1 = regoff1[X86_MODRM_RM(insn->modrm.value)];
+ *offs2 = regoff2[X86_MODRM_RM(insn->modrm.value)];
+
+ /*
+ * If ModRM.mod is 0 and ModRM.rm is 110b, then we use displacement-
+ * only addressing. This means that no registers are involved in
+ * computing the effective address. Thus, ensure that the first
+ * register offset is invalid. The second register offset is already
+ * invalid under the aforementioned conditions.
+ */
+ if ((X86_MODRM_MOD(insn->modrm.value) == 0) &&
+ (X86_MODRM_RM(insn->modrm.value) == 6))
+ *offs1 = -EDOM;
+
+ return 0;
+}
+
+/**
+ * get_desc() - Obtain contents of a segment descriptor
+ * @out: Segment descriptor contents on success
+ * @sel: Segment selector
+ *
+ * Given a segment selector, obtain a pointer to the segment descriptor.
+ * Both global and local descriptor tables are supported.
+ *
+ * Returns:
+ *
+ * True on success, false on failure.
+ *
+ * NULL on error.
+ */
+static bool get_desc(struct desc_struct *out, unsigned short sel)
+{
+ struct desc_ptr gdt_desc = {0, 0};
+ unsigned long desc_base;
+
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+ if ((sel & SEGMENT_TI_MASK) == SEGMENT_LDT) {
+ bool success = false;
+ struct ldt_struct *ldt;
+
+ /* 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 (ldt && sel < ldt->nr_entries) {
+ *out = ldt->entries[sel];
+ success = true;
+ }
+
+ mutex_unlock(&current->active_mm->context.lock);
+
+ return success;
+ }
+#endif
+ native_store_gdt(&gdt_desc);
+
+ /*
+ * Segment descriptors have a size of 8 bytes. Thus, the index is
+ * multiplied by 8 to obtain the memory offset of the desired descriptor
+ * from the base of the GDT. As bits [15:3] of the segment selector
+ * contain the index, it can be regarded as multiplied by 8 already.
+ * All that remains is to clear bits [2:0].
+ */
+ desc_base = sel & ~(SEGMENT_RPL_MASK | SEGMENT_TI_MASK);
+
+ if (desc_base > gdt_desc.size)
+ return false;
+
+ *out = *(struct desc_struct *)(gdt_desc.address + desc_base);
+ return true;
+}
+
+/**
+ * insn_get_seg_base() - Obtain base address of segment descriptor.
+ * @regs: Register values as seen when entering kernel mode
+ * @seg_reg_idx: Index of the segment register pointing to seg descriptor
+ *
+ * Obtain the base address of the segment as indicated by the segment descriptor
+ * pointed by the segment selector. The segment selector is obtained from the
+ * input segment register index @seg_reg_idx.
+ *
+ * Returns:
+ *
+ * In protected mode, base address of the segment. Zero in long mode,
+ * except when FS or GS are used. In virtual-8086 mode, the segment
+ * selector shifted 4 bits to the right.
+ *
+ * -1L in case of error.
+ */
+unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx)
+{
+ struct desc_struct desc;
+ short sel;
+
+ sel = get_segment_selector(regs, seg_reg_idx);
+ if (sel < 0)
+ return -1L;
+
+ if (v8086_mode(regs))
+ /*
+ * Base is simply the segment selector shifted 4
+ * bits to the right.
+ */
+ return (unsigned long)(sel << 4);
+
+ if (any_64bit_mode(regs)) {
+ /*
+ * Only FS or GS will have a base address, the rest of
+ * the segments' bases are forced to 0.
+ */
+ unsigned long base;
+
+ if (seg_reg_idx == INAT_SEG_REG_FS) {
+ rdmsrl(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);
+ else
+ rdmsrl(MSR_GS_BASE, base);
+ } else {
+ base = 0;
+ }
+ return base;
+ }
+
+ /* In protected mode the segment selector cannot be null. */
+ if (!sel)
+ return -1L;
+
+ if (!get_desc(&desc, sel))
+ return -1L;
+
+ return get_desc_base(&desc);
+}
+
+/**
+ * get_seg_limit() - Obtain the limit of a segment descriptor
+ * @regs: Register values as seen when entering kernel mode
+ * @seg_reg_idx: Index of the segment register pointing to seg descriptor
+ *
+ * Obtain the limit of the segment as indicated by the segment descriptor
+ * pointed by the segment selector. The segment selector is obtained from the
+ * input segment register index @seg_reg_idx.
+ *
+ * Returns:
+ *
+ * In protected mode, the limit of the segment descriptor in bytes.
+ * In long mode and virtual-8086 mode, segment limits are not enforced. Thus,
+ * limit is returned as -1L to imply a limit-less segment.
+ *
+ * Zero is returned on error.
+ */
+static unsigned long get_seg_limit(struct pt_regs *regs, int seg_reg_idx)
+{
+ struct desc_struct desc;
+ unsigned long limit;
+ short sel;
+
+ sel = get_segment_selector(regs, seg_reg_idx);
+ if (sel < 0)
+ return 0;
+
+ if (any_64bit_mode(regs) || v8086_mode(regs))
+ return -1L;
+
+ if (!sel)
+ return 0;
+
+ if (!get_desc(&desc, sel))
+ return 0;
+
+ /*
+ * If the granularity bit is set, the limit is given in multiples
+ * of 4096. This also means that the 12 least significant bits are
+ * not tested when checking the segment limits. In practice,
+ * this means that the segment ends in (limit << 12) + 0xfff.
+ */
+ limit = get_desc_limit(&desc);
+ if (desc.g)
+ limit = (limit << 12) + 0xfff;
+
+ return limit;
+}
+
+/**
+ * insn_get_code_seg_params() - Obtain code segment parameters
+ * @regs: Structure with register values as seen when entering kernel mode
+ *
+ * Obtain address and operand sizes of the code segment. It is obtained from the
+ * selector contained in the CS register in regs. In protected mode, the default
+ * address is determined by inspecting the L and D bits of the segment
+ * descriptor. In virtual-8086 mode, the default is always two bytes for both
+ * address and operand sizes.
+ *
+ * Returns:
+ *
+ * An int containing ORed-in default parameters on success.
+ *
+ * -EINVAL on error.
+ */
+int insn_get_code_seg_params(struct pt_regs *regs)
+{
+ struct desc_struct desc;
+ short sel;
+
+ if (v8086_mode(regs))
+ /* Address and operand size are both 16-bit. */
+ return INSN_CODE_SEG_PARAMS(2, 2);
+
+ sel = get_segment_selector(regs, INAT_SEG_REG_CS);
+ if (sel < 0)
+ return sel;
+
+ if (!get_desc(&desc, sel))
+ return -EINVAL;
+
+ /*
+ * The most significant byte of the Type field of the segment descriptor
+ * determines whether a segment contains data or code. If this is a data
+ * segment, return error.
+ */
+ if (!(desc.type & BIT(3)))
+ return -EINVAL;
+
+ switch ((desc.l << 1) | desc.d) {
+ case 0: /*
+ * Legacy mode. CS.L=0, CS.D=0. Address and operand size are
+ * both 16-bit.
+ */
+ return INSN_CODE_SEG_PARAMS(2, 2);
+ case 1: /*
+ * Legacy mode. CS.L=0, CS.D=1. Address and operand size are
+ * both 32-bit.
+ */
+ return INSN_CODE_SEG_PARAMS(4, 4);
+ case 2: /*
+ * IA-32e 64-bit mode. CS.L=1, CS.D=0. Address size is 64-bit;
+ * operand size is 32-bit.
+ */
+ return INSN_CODE_SEG_PARAMS(4, 8);
+ case 3: /* Invalid setting. CS.L=1, CS.D=1 */
+ fallthrough;
+ default:
+ return -EINVAL;
+ }
+}
+
+/**
+ * insn_get_modrm_rm_off() - Obtain register in r/m part of the ModRM byte
+ * @insn: Instruction containing the ModRM byte
+ * @regs: Register values as seen when entering kernel mode
+ *
+ * Returns:
+ *
+ * The register indicated by the r/m part of the ModRM byte. The
+ * register is obtained as an offset from the base of pt_regs. In specific
+ * cases, the returned value can be -EDOM to indicate that the particular value
+ * of ModRM does not refer to a register and shall be ignored.
+ */
+int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs)
+{
+ return get_reg_offset(insn, regs, REG_TYPE_RM);
+}
+
+/**
+ * insn_get_modrm_reg_off() - Obtain register in reg part of the ModRM byte
+ * @insn: Instruction containing the ModRM byte
+ * @regs: Register values as seen when entering kernel mode
+ *
+ * Returns:
+ *
+ * The register indicated by the reg part of the ModRM byte. The
+ * register is obtained as an offset from the base of pt_regs.
+ */
+int insn_get_modrm_reg_off(struct insn *insn, struct pt_regs *regs)
+{
+ return get_reg_offset(insn, regs, REG_TYPE_REG);
+}
+
+/**
+ * insn_get_modrm_reg_ptr() - Obtain register pointer based on ModRM byte
+ * @insn: Instruction containing the ModRM byte
+ * @regs: Register values as seen when entering kernel mode
+ *
+ * Returns:
+ *
+ * The register indicated by the reg part of the ModRM byte.
+ * The register is obtained as a pointer within pt_regs.
+ */
+unsigned long *insn_get_modrm_reg_ptr(struct insn *insn, struct pt_regs *regs)
+{
+ int offset;
+
+ offset = insn_get_modrm_reg_off(insn, regs);
+ if (offset < 0)
+ return NULL;
+ return (void *)regs + offset;
+}
+
+/**
+ * get_seg_base_limit() - obtain base address and limit of a segment
+ * @insn: Instruction. Must be valid.
+ * @regs: Register values as seen when entering kernel mode
+ * @regoff: Operand offset, in pt_regs, used to resolve segment descriptor
+ * @base: Obtained segment base
+ * @limit: Obtained segment limit
+ *
+ * Obtain the base address and limit of the segment associated with the operand
+ * @regoff and, if any or allowed, override prefixes in @insn. This function is
+ * different from insn_get_seg_base() as the latter does not resolve the segment
+ * associated with the instruction operand. If a limit is not needed (e.g.,
+ * when running in long mode), @limit can be NULL.
+ *
+ * Returns:
+ *
+ * 0 on success. @base and @limit will contain the base address and of the
+ * resolved segment, respectively.
+ *
+ * -EINVAL on error.
+ */
+static int get_seg_base_limit(struct insn *insn, struct pt_regs *regs,
+ int regoff, unsigned long *base,
+ unsigned long *limit)
+{
+ int seg_reg_idx;
+
+ if (!base)
+ return -EINVAL;
+
+ seg_reg_idx = resolve_seg_reg(insn, regs, regoff);
+ if (seg_reg_idx < 0)
+ return seg_reg_idx;
+
+ *base = insn_get_seg_base(regs, seg_reg_idx);
+ if (*base == -1L)
+ return -EINVAL;
+
+ if (!limit)
+ return 0;
+
+ *limit = get_seg_limit(regs, seg_reg_idx);
+ if (!(*limit))
+ return -EINVAL;
+
+ return 0;
+}
+
+/**
+ * get_eff_addr_reg() - Obtain effective address from register operand
+ * @insn: Instruction. Must be valid.
+ * @regs: Register values as seen when entering kernel mode
+ * @regoff: Obtained operand offset, in pt_regs, with the effective address
+ * @eff_addr: Obtained effective address
+ *
+ * Obtain the effective address stored in the register operand as indicated by
+ * the ModRM byte. This function is to be used only with register addressing
+ * (i.e., ModRM.mod is 3). The effective address is saved in @eff_addr. The
+ * register operand, as an offset from the base of pt_regs, is saved in @regoff;
+ * such offset can then be used to resolve the segment associated with the
+ * operand. This function can be used with any of the supported address sizes
+ * in x86.
+ *
+ * Returns:
+ *
+ * 0 on success. @eff_addr will have the effective address stored in the
+ * operand indicated by ModRM. @regoff will have such operand as an offset from
+ * the base of pt_regs.
+ *
+ * -EINVAL on error.
+ */
+static int get_eff_addr_reg(struct insn *insn, struct pt_regs *regs,
+ int *regoff, long *eff_addr)
+{
+ int ret;
+
+ ret = insn_get_modrm(insn);
+ if (ret)
+ return ret;
+
+ if (X86_MODRM_MOD(insn->modrm.value) != 3)
+ return -EINVAL;
+
+ *regoff = get_reg_offset(insn, regs, REG_TYPE_RM);
+ if (*regoff < 0)
+ return -EINVAL;
+
+ /* Ignore bytes that are outside the address size. */
+ if (insn->addr_bytes == 2)
+ *eff_addr = regs_get_register(regs, *regoff) & 0xffff;
+ else if (insn->addr_bytes == 4)
+ *eff_addr = regs_get_register(regs, *regoff) & 0xffffffff;
+ else /* 64-bit address */
+ *eff_addr = regs_get_register(regs, *regoff);
+
+ return 0;
+}
+
+/**
+ * get_eff_addr_modrm() - Obtain referenced effective address via ModRM
+ * @insn: Instruction. Must be valid.
+ * @regs: Register values as seen when entering kernel mode
+ * @regoff: Obtained operand offset, in pt_regs, associated with segment
+ * @eff_addr: Obtained effective address
+ *
+ * Obtain the effective address referenced by the ModRM byte of @insn. After
+ * identifying the registers involved in the register-indirect memory reference,
+ * its value is obtained from the operands in @regs. The computed address is
+ * stored @eff_addr. Also, the register operand that indicates the associated
+ * segment is stored in @regoff, this parameter can later be used to determine
+ * such segment.
+ *
+ * Returns:
+ *
+ * 0 on success. @eff_addr will have the referenced effective address. @regoff
+ * will have a register, as an offset from the base of pt_regs, that can be used
+ * to resolve the associated segment.
+ *
+ * -EINVAL on error.
+ */
+static int get_eff_addr_modrm(struct insn *insn, struct pt_regs *regs,
+ int *regoff, long *eff_addr)
+{
+ long tmp;
+ int ret;
+
+ if (insn->addr_bytes != 8 && insn->addr_bytes != 4)
+ return -EINVAL;
+
+ ret = insn_get_modrm(insn);
+ if (ret)
+ return ret;
+
+ if (X86_MODRM_MOD(insn->modrm.value) > 2)
+ return -EINVAL;
+
+ *regoff = get_reg_offset(insn, regs, REG_TYPE_RM);
+
+ /*
+ * -EDOM means that we must ignore the address_offset. In such a case,
+ * in 64-bit mode the effective address relative to the rIP of the
+ * following instruction.
+ */
+ if (*regoff == -EDOM) {
+ if (any_64bit_mode(regs))
+ tmp = regs->ip + insn->length;
+ else
+ tmp = 0;
+ } else if (*regoff < 0) {
+ return -EINVAL;
+ } else {
+ tmp = regs_get_register(regs, *regoff);
+ }
+
+ if (insn->addr_bytes == 4) {
+ int addr32 = (int)(tmp & 0xffffffff) + insn->displacement.value;
+
+ *eff_addr = addr32 & 0xffffffff;
+ } else {
+ *eff_addr = tmp + insn->displacement.value;
+ }
+
+ return 0;
+}
+
+/**
+ * get_eff_addr_modrm_16() - Obtain referenced effective address via ModRM
+ * @insn: Instruction. Must be valid.
+ * @regs: Register values as seen when entering kernel mode
+ * @regoff: Obtained operand offset, in pt_regs, associated with segment
+ * @eff_addr: Obtained effective address
+ *
+ * Obtain the 16-bit effective address referenced by the ModRM byte of @insn.
+ * After identifying the registers involved in the register-indirect memory
+ * reference, its value is obtained from the operands in @regs. The computed
+ * address is stored @eff_addr. Also, the register operand that indicates
+ * the associated segment is stored in @regoff, this parameter can later be used
+ * to determine such segment.
+ *
+ * Returns:
+ *
+ * 0 on success. @eff_addr will have the referenced effective address. @regoff
+ * will have a register, as an offset from the base of pt_regs, that can be used
+ * to resolve the associated segment.
+ *
+ * -EINVAL on error.
+ */
+static int get_eff_addr_modrm_16(struct insn *insn, struct pt_regs *regs,
+ int *regoff, short *eff_addr)
+{
+ int addr_offset1, addr_offset2, ret;
+ short addr1 = 0, addr2 = 0, displacement;
+
+ if (insn->addr_bytes != 2)
+ return -EINVAL;
+
+ insn_get_modrm(insn);
+
+ if (!insn->modrm.nbytes)
+ return -EINVAL;
+
+ if (X86_MODRM_MOD(insn->modrm.value) > 2)
+ return -EINVAL;
+
+ ret = get_reg_offset_16(insn, regs, &addr_offset1, &addr_offset2);
+ if (ret < 0)
+ return -EINVAL;
+
+ /*
+ * Don't fail on invalid offset values. They might be invalid because
+ * they cannot be used for this particular value of ModRM. Instead, use
+ * them in the computation only if they contain a valid value.
+ */
+ if (addr_offset1 != -EDOM)
+ addr1 = regs_get_register(regs, addr_offset1) & 0xffff;
+
+ if (addr_offset2 != -EDOM)
+ addr2 = regs_get_register(regs, addr_offset2) & 0xffff;
+
+ displacement = insn->displacement.value & 0xffff;
+ *eff_addr = addr1 + addr2 + displacement;
+
+ /*
+ * The first operand register could indicate to use of either SS or DS
+ * registers to obtain the segment selector. The second operand
+ * register can only indicate the use of DS. Thus, the first operand
+ * will be used to obtain the segment selector.
+ */
+ *regoff = addr_offset1;
+
+ return 0;
+}
+
+/**
+ * get_eff_addr_sib() - Obtain referenced effective address via SIB
+ * @insn: Instruction. Must be valid.
+ * @regs: Register values as seen when entering kernel mode
+ * @regoff: Obtained operand offset, in pt_regs, associated with segment
+ * @eff_addr: Obtained effective address
+ *
+ * Obtain the effective address referenced by the SIB byte of @insn. After
+ * identifying the registers involved in the indexed, register-indirect memory
+ * reference, its value is obtained from the operands in @regs. The computed
+ * address is stored @eff_addr. Also, the register operand that indicates the
+ * associated segment is stored in @regoff, this parameter can later be used to
+ * determine such segment.
+ *
+ * Returns:
+ *
+ * 0 on success. @eff_addr will have the referenced effective address.
+ * @base_offset will have a register, as an offset from the base of pt_regs,
+ * that can be used to resolve the associated segment.
+ *
+ * Negative value on error.
+ */
+static int get_eff_addr_sib(struct insn *insn, struct pt_regs *regs,
+ int *base_offset, long *eff_addr)
+{
+ long base, indx;
+ int indx_offset;
+ int ret;
+
+ if (insn->addr_bytes != 8 && insn->addr_bytes != 4)
+ return -EINVAL;
+
+ ret = insn_get_modrm(insn);
+ if (ret)
+ return ret;
+
+ if (!insn->modrm.nbytes)
+ return -EINVAL;
+
+ if (X86_MODRM_MOD(insn->modrm.value) > 2)
+ return -EINVAL;
+
+ ret = insn_get_sib(insn);
+ if (ret)
+ return ret;
+
+ if (!insn->sib.nbytes)
+ return -EINVAL;
+
+ *base_offset = get_reg_offset(insn, regs, REG_TYPE_BASE);
+ indx_offset = get_reg_offset(insn, regs, REG_TYPE_INDEX);
+
+ /*
+ * Negative values in the base and index offset means an error when
+ * decoding the SIB byte. Except -EDOM, which means that the registers
+ * should not be used in the address computation.
+ */
+ if (*base_offset == -EDOM)
+ base = 0;
+ else if (*base_offset < 0)
+ return -EINVAL;
+ else
+ base = regs_get_register(regs, *base_offset);
+
+ if (indx_offset == -EDOM)
+ indx = 0;
+ else if (indx_offset < 0)
+ return -EINVAL;
+ else
+ indx = regs_get_register(regs, indx_offset);
+
+ if (insn->addr_bytes == 4) {
+ int addr32, base32, idx32;
+
+ base32 = base & 0xffffffff;
+ idx32 = indx & 0xffffffff;
+
+ addr32 = base32 + idx32 * (1 << X86_SIB_SCALE(insn->sib.value));
+ addr32 += insn->displacement.value;
+
+ *eff_addr = addr32 & 0xffffffff;
+ } else {
+ *eff_addr = base + indx * (1 << X86_SIB_SCALE(insn->sib.value));
+ *eff_addr += insn->displacement.value;
+ }
+
+ return 0;
+}
+
+/**
+ * get_addr_ref_16() - Obtain the 16-bit address referred by instruction
+ * @insn: Instruction containing ModRM byte and displacement
+ * @regs: Register values as seen when entering kernel mode
+ *
+ * This function is to be used with 16-bit address encodings. Obtain the memory
+ * address referred by the instruction's ModRM and displacement bytes. Also, the
+ * segment used as base is determined by either any segment override prefixes in
+ * @insn or the default segment of the registers involved in the address
+ * computation. In protected mode, segment limits are enforced.
+ *
+ * Returns:
+ *
+ * Linear address referenced by the instruction operands on success.
+ *
+ * -1L on error.
+ */
+static void __user *get_addr_ref_16(struct insn *insn, struct pt_regs *regs)
+{
+ unsigned long linear_addr = -1L, seg_base, seg_limit;
+ int ret, regoff;
+ short eff_addr;
+ long tmp;
+
+ if (insn_get_displacement(insn))
+ goto out;
+
+ if (insn->addr_bytes != 2)
+ goto out;
+
+ if (X86_MODRM_MOD(insn->modrm.value) == 3) {
+ ret = get_eff_addr_reg(insn, regs, &regoff, &tmp);
+ if (ret)
+ goto out;
+
+ eff_addr = tmp;
+ } else {
+ ret = get_eff_addr_modrm_16(insn, regs, &regoff, &eff_addr);
+ if (ret)
+ goto out;
+ }
+
+ ret = get_seg_base_limit(insn, regs, regoff, &seg_base, &seg_limit);
+ if (ret)
+ goto out;
+
+ /*
+ * Before computing the linear address, make sure the effective address
+ * is within the limits of the segment. In virtual-8086 mode, segment
+ * limits are not enforced. In such a case, the segment limit is -1L to
+ * reflect this fact.
+ */
+ if ((unsigned long)(eff_addr & 0xffff) > seg_limit)
+ goto out;
+
+ linear_addr = (unsigned long)(eff_addr & 0xffff) + seg_base;
+
+ /* Limit linear address to 20 bits */
+ if (v8086_mode(regs))
+ linear_addr &= 0xfffff;
+
+out:
+ return (void __user *)linear_addr;
+}
+
+/**
+ * get_addr_ref_32() - Obtain a 32-bit linear address
+ * @insn: Instruction with ModRM, SIB bytes and displacement
+ * @regs: Register values as seen when entering kernel mode
+ *
+ * This function is to be used with 32-bit address encodings to obtain the
+ * linear memory address referred by the instruction's ModRM, SIB,
+ * displacement bytes and segment base address, as applicable. If in protected
+ * mode, segment limits are enforced.
+ *
+ * Returns:
+ *
+ * Linear address referenced by instruction and registers on success.
+ *
+ * -1L on error.
+ */
+static void __user *get_addr_ref_32(struct insn *insn, struct pt_regs *regs)
+{
+ unsigned long linear_addr = -1L, seg_base, seg_limit;
+ int eff_addr, regoff;
+ long tmp;
+ int ret;
+
+ if (insn->addr_bytes != 4)
+ goto out;
+
+ if (X86_MODRM_MOD(insn->modrm.value) == 3) {
+ ret = get_eff_addr_reg(insn, regs, &regoff, &tmp);
+ if (ret)
+ goto out;
+
+ eff_addr = tmp;
+
+ } else {
+ if (insn->sib.nbytes) {
+ ret = get_eff_addr_sib(insn, regs, &regoff, &tmp);
+ if (ret)
+ goto out;
+
+ eff_addr = tmp;
+ } else {
+ ret = get_eff_addr_modrm(insn, regs, &regoff, &tmp);
+ if (ret)
+ goto out;
+
+ eff_addr = tmp;
+ }
+ }
+
+ ret = get_seg_base_limit(insn, regs, regoff, &seg_base, &seg_limit);
+ if (ret)
+ goto out;
+
+ /*
+ * In protected mode, before computing the linear address, make sure
+ * the effective address is within the limits of the segment.
+ * 32-bit addresses can be used in long and virtual-8086 modes if an
+ * address override prefix is used. In such cases, segment limits are
+ * not enforced. When in virtual-8086 mode, the segment limit is -1L
+ * to reflect this situation.
+ *
+ * After computed, the effective address is treated as an unsigned
+ * quantity.
+ */
+ if (!any_64bit_mode(regs) && ((unsigned int)eff_addr > seg_limit))
+ goto out;
+
+ /*
+ * Even though 32-bit address encodings are allowed in virtual-8086
+ * mode, the address range is still limited to [0x-0xffff].
+ */
+ if (v8086_mode(regs) && (eff_addr & ~0xffff))
+ goto out;
+
+ /*
+ * Data type long could be 64 bits in size. Ensure that our 32-bit
+ * effective address is not sign-extended when computing the linear
+ * address.
+ */
+ linear_addr = (unsigned long)(eff_addr & 0xffffffff) + seg_base;
+
+ /* Limit linear address to 20 bits */
+ if (v8086_mode(regs))
+ linear_addr &= 0xfffff;
+
+out:
+ return (void __user *)linear_addr;
+}
+
+/**
+ * get_addr_ref_64() - Obtain a 64-bit linear address
+ * @insn: Instruction struct with ModRM and SIB bytes and displacement
+ * @regs: Structure with register values as seen when entering kernel mode
+ *
+ * This function is to be used with 64-bit address encodings to obtain the
+ * linear memory address referred by the instruction's ModRM, SIB,
+ * displacement bytes and segment base address, as applicable.
+ *
+ * Returns:
+ *
+ * Linear address referenced by instruction and registers on success.
+ *
+ * -1L on error.
+ */
+#ifndef CONFIG_X86_64
+static void __user *get_addr_ref_64(struct insn *insn, struct pt_regs *regs)
+{
+ return (void __user *)-1L;
+}
+#else
+static void __user *get_addr_ref_64(struct insn *insn, struct pt_regs *regs)
+{
+ unsigned long linear_addr = -1L, seg_base;
+ int regoff, ret;
+ long eff_addr;
+
+ if (insn->addr_bytes != 8)
+ goto out;
+
+ if (X86_MODRM_MOD(insn->modrm.value) == 3) {
+ ret = get_eff_addr_reg(insn, regs, &regoff, &eff_addr);
+ if (ret)
+ goto out;
+
+ } else {
+ if (insn->sib.nbytes) {
+ ret = get_eff_addr_sib(insn, regs, &regoff, &eff_addr);
+ if (ret)
+ goto out;
+ } else {
+ ret = get_eff_addr_modrm(insn, regs, &regoff, &eff_addr);
+ if (ret)
+ goto out;
+ }
+
+ }
+
+ ret = get_seg_base_limit(insn, regs, regoff, &seg_base, NULL);
+ if (ret)
+ goto out;
+
+ linear_addr = (unsigned long)eff_addr + seg_base;
+
+out:
+ return (void __user *)linear_addr;
+}
+#endif /* CONFIG_X86_64 */
+
+/**
+ * insn_get_addr_ref() - Obtain the linear address referred by instruction
+ * @insn: Instruction structure containing ModRM byte and displacement
+ * @regs: Structure with register values as seen when entering kernel mode
+ *
+ * Obtain the linear address referred by the instruction's ModRM, SIB and
+ * displacement bytes, and segment base, as applicable. In protected mode,
+ * segment limits are enforced.
+ *
+ * Returns:
+ *
+ * Linear address referenced by instruction and registers on success.
+ *
+ * -1L on error.
+ */
+void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs)
+{
+ if (!insn || !regs)
+ return (void __user *)-1L;
+
+ if (insn_get_opcode(insn))
+ return (void __user *)-1L;
+
+ switch (insn->addr_bytes) {
+ case 2:
+ return get_addr_ref_16(insn, regs);
+ case 4:
+ return get_addr_ref_32(insn, regs);
+ case 8:
+ return get_addr_ref_64(insn, regs);
+ default:
+ return (void __user *)-1L;
+ }
+}
+
+int insn_get_effective_ip(struct pt_regs *regs, unsigned long *ip)
+{
+ unsigned long seg_base = 0;
+
+ /*
+ * If not in user-space long mode, a custom code segment could be in
+ * use. This is true in protected mode (if the process defined a local
+ * descriptor table), or virtual-8086 mode. In most of the cases
+ * seg_base will be zero as in USER_CS.
+ */
+ if (!user_64bit_mode(regs)) {
+ seg_base = insn_get_seg_base(regs, INAT_SEG_REG_CS);
+ if (seg_base == -1L)
+ return -EINVAL;
+ }
+
+ *ip = seg_base + regs->ip;
+
+ return 0;
+}
+
+/**
+ * insn_fetch_from_user() - Copy instruction bytes from user-space memory
+ * @regs: Structure with register values as seen when entering kernel mode
+ * @buf: Array to store the fetched instruction
+ *
+ * Gets the linear address of the instruction and copies the instruction bytes
+ * to the buf.
+ *
+ * Returns:
+ *
+ * - number of instruction bytes copied.
+ * - 0 if nothing was copied.
+ * - -EINVAL if the linear address of the instruction could not be calculated
+ */
+int insn_fetch_from_user(struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE])
+{
+ unsigned long ip;
+ int not_copied;
+
+ if (insn_get_effective_ip(regs, &ip))
+ return -EINVAL;
+
+ not_copied = copy_from_user(buf, (void __user *)ip, MAX_INSN_SIZE);
+
+ return MAX_INSN_SIZE - not_copied;
+}
+
+/**
+ * insn_fetch_from_user_inatomic() - Copy instruction bytes from user-space memory
+ * while in atomic code
+ * @regs: Structure with register values as seen when entering kernel mode
+ * @buf: Array to store the fetched instruction
+ *
+ * Gets the linear address of the instruction and copies the instruction bytes
+ * to the buf. This function must be used in atomic context.
+ *
+ * Returns:
+ *
+ * - number of instruction bytes copied.
+ * - 0 if nothing was copied.
+ * - -EINVAL if the linear address of the instruction could not be calculated.
+ */
+int insn_fetch_from_user_inatomic(struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE])
+{
+ unsigned long ip;
+ int not_copied;
+
+ if (insn_get_effective_ip(regs, &ip))
+ return -EINVAL;
+
+ not_copied = __copy_from_user_inatomic(buf, (void __user *)ip, MAX_INSN_SIZE);
+
+ return MAX_INSN_SIZE - not_copied;
+}
+
+/**
+ * insn_decode_from_regs() - Decode an instruction
+ * @insn: Structure to store decoded instruction
+ * @regs: Structure with register values as seen when entering kernel mode
+ * @buf: Buffer containing the instruction bytes
+ * @buf_size: Number of instruction bytes available in buf
+ *
+ * Decodes the instruction provided in buf and stores the decoding results in
+ * insn. Also determines the correct address and operand sizes.
+ *
+ * Returns:
+ *
+ * True if instruction was decoded, False otherwise.
+ */
+bool insn_decode_from_regs(struct insn *insn, struct pt_regs *regs,
+ unsigned char buf[MAX_INSN_SIZE], int buf_size)
+{
+ int seg_defs;
+
+ insn_init(insn, buf, buf_size, user_64bit_mode(regs));
+
+ /*
+ * Override the default operand and address sizes with what is specified
+ * in the code segment descriptor. The instruction decoder only sets
+ * the address size it to either 4 or 8 address bytes and does nothing
+ * for the operand bytes. This OK for most of the cases, but we could
+ * have special cases where, for instance, a 16-bit code segment
+ * descriptor is used.
+ * If there is an address override prefix, the instruction decoder
+ * correctly updates these values, even for 16-bit defaults.
+ */
+ seg_defs = insn_get_code_seg_params(regs);
+ if (seg_defs == -EINVAL)
+ return false;
+
+ insn->addr_bytes = INSN_CODE_SEG_ADDR_SZ(seg_defs);
+ insn->opnd_bytes = INSN_CODE_SEG_OPND_SZ(seg_defs);
+
+ if (insn_get_length(insn))
+ return false;
+
+ if (buf_size < insn->length)
+ return false;
+
+ return true;
+}
+
+/**
+ * insn_decode_mmio() - Decode a MMIO instruction
+ * @insn: Structure to store decoded instruction
+ * @bytes: Returns size of memory operand
+ *
+ * Decodes instruction that used for Memory-mapped I/O.
+ *
+ * Returns:
+ *
+ * Type of the instruction. Size of the memory operand is stored in
+ * @bytes. If decode failed, INSN_MMIO_DECODE_FAILED returned.
+ */
+enum insn_mmio_type insn_decode_mmio(struct insn *insn, int *bytes)
+{
+ enum insn_mmio_type type = INSN_MMIO_DECODE_FAILED;
+
+ *bytes = 0;
+
+ if (insn_get_opcode(insn))
+ return INSN_MMIO_DECODE_FAILED;
+
+ switch (insn->opcode.bytes[0]) {
+ case 0x88: /* MOV m8,r8 */
+ *bytes = 1;
+ fallthrough;
+ case 0x89: /* MOV m16/m32/m64, r16/m32/m64 */
+ if (!*bytes)
+ *bytes = insn->opnd_bytes;
+ type = INSN_MMIO_WRITE;
+ break;
+
+ case 0xc6: /* MOV m8, imm8 */
+ *bytes = 1;
+ fallthrough;
+ case 0xc7: /* MOV m16/m32/m64, imm16/imm32/imm64 */
+ if (!*bytes)
+ *bytes = insn->opnd_bytes;
+ type = INSN_MMIO_WRITE_IMM;
+ break;
+
+ case 0x8a: /* MOV r8, m8 */
+ *bytes = 1;
+ fallthrough;
+ case 0x8b: /* MOV r16/r32/r64, m16/m32/m64 */
+ if (!*bytes)
+ *bytes = insn->opnd_bytes;
+ type = INSN_MMIO_READ;
+ break;
+
+ case 0xa4: /* MOVS m8, m8 */
+ *bytes = 1;
+ fallthrough;
+ case 0xa5: /* MOVS m16/m32/m64, m16/m32/m64 */
+ if (!*bytes)
+ *bytes = insn->opnd_bytes;
+ type = INSN_MMIO_MOVS;
+ break;
+
+ case 0x0f: /* Two-byte instruction */
+ switch (insn->opcode.bytes[1]) {
+ case 0xb6: /* MOVZX r16/r32/r64, m8 */
+ *bytes = 1;
+ fallthrough;
+ case 0xb7: /* MOVZX r32/r64, m16 */
+ if (!*bytes)
+ *bytes = 2;
+ type = INSN_MMIO_READ_ZERO_EXTEND;
+ break;
+
+ case 0xbe: /* MOVSX r16/r32/r64, m8 */
+ *bytes = 1;
+ fallthrough;
+ case 0xbf: /* MOVSX r32/r64, m16 */
+ if (!*bytes)
+ *bytes = 2;
+ type = INSN_MMIO_READ_SIGN_EXTEND;
+ break;
+ }
+ break;
+ }
+
+ return type;
+}
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
new file mode 100644
index 0000000000..55e371cc69
--- /dev/null
+++ b/arch/x86/lib/insn.c
@@ -0,0 +1,755 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * x86 instruction analysis
+ *
+ * Copyright (C) IBM Corporation, 2002, 2004, 2009
+ */
+
+#include <linux/kernel.h>
+#ifdef __KERNEL__
+#include <linux/string.h>
+#else
+#include <string.h>
+#endif
+#include <asm/inat.h> /*__ignore_sync_check__ */
+#include <asm/insn.h> /* __ignore_sync_check__ */
+#include <asm/unaligned.h> /* __ignore_sync_check__ */
+
+#include <linux/errno.h>
+#include <linux/kconfig.h>
+
+#include <asm/emulate_prefix.h> /* __ignore_sync_check__ */
+
+#define leXX_to_cpu(t, r) \
+({ \
+ __typeof__(t) v; \
+ switch (sizeof(t)) { \
+ case 4: v = le32_to_cpu(r); break; \
+ case 2: v = le16_to_cpu(r); break; \
+ case 1: v = r; break; \
+ default: \
+ BUILD_BUG(); break; \
+ } \
+ v; \
+})
+
+/* Verify next sizeof(t) bytes can be on the same instruction */
+#define validate_next(t, insn, n) \
+ ((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr)
+
+#define __get_next(t, insn) \
+ ({ t r = get_unaligned((t *)(insn)->next_byte); (insn)->next_byte += sizeof(t); leXX_to_cpu(t, r); })
+
+#define __peek_nbyte_next(t, insn, n) \
+ ({ t r = get_unaligned((t *)(insn)->next_byte + n); leXX_to_cpu(t, r); })
+
+#define get_next(t, insn) \
+ ({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); })
+
+#define peek_nbyte_next(t, insn, n) \
+ ({ if (unlikely(!validate_next(t, insn, n))) goto err_out; __peek_nbyte_next(t, insn, n); })
+
+#define peek_next(t, insn) peek_nbyte_next(t, insn, 0)
+
+/**
+ * insn_init() - initialize struct insn
+ * @insn: &struct insn to be initialized
+ * @kaddr: address (in kernel memory) of instruction (or copy thereof)
+ * @buf_len: length of the insn buffer at @kaddr
+ * @x86_64: !0 for 64-bit kernel or 64-bit app
+ */
+void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64)
+{
+ /*
+ * Instructions longer than MAX_INSN_SIZE (15 bytes) are invalid
+ * even if the input buffer is long enough to hold them.
+ */
+ if (buf_len > MAX_INSN_SIZE)
+ buf_len = MAX_INSN_SIZE;
+
+ memset(insn, 0, sizeof(*insn));
+ insn->kaddr = kaddr;
+ insn->end_kaddr = kaddr + buf_len;
+ insn->next_byte = kaddr;
+ insn->x86_64 = x86_64 ? 1 : 0;
+ insn->opnd_bytes = 4;
+ if (x86_64)
+ insn->addr_bytes = 8;
+ else
+ insn->addr_bytes = 4;
+}
+
+static const insn_byte_t xen_prefix[] = { __XEN_EMULATE_PREFIX };
+static const insn_byte_t kvm_prefix[] = { __KVM_EMULATE_PREFIX };
+
+static int __insn_get_emulate_prefix(struct insn *insn,
+ const insn_byte_t *prefix, size_t len)
+{
+ size_t i;
+
+ for (i = 0; i < len; i++) {
+ if (peek_nbyte_next(insn_byte_t, insn, i) != prefix[i])
+ goto err_out;
+ }
+
+ insn->emulate_prefix_size = len;
+ insn->next_byte += len;
+
+ return 1;
+
+err_out:
+ return 0;
+}
+
+static void insn_get_emulate_prefix(struct insn *insn)
+{
+ if (__insn_get_emulate_prefix(insn, xen_prefix, sizeof(xen_prefix)))
+ return;
+
+ __insn_get_emulate_prefix(insn, kvm_prefix, sizeof(kvm_prefix));
+}
+
+/**
+ * insn_get_prefixes - scan x86 instruction prefix bytes
+ * @insn: &struct insn containing instruction
+ *
+ * Populates the @insn->prefixes bitmap, and updates @insn->next_byte
+ * to point to the (first) opcode. No effect if @insn->prefixes.got
+ * is already set.
+ *
+ * * Returns:
+ * 0: on success
+ * < 0: on error
+ */
+int insn_get_prefixes(struct insn *insn)
+{
+ struct insn_field *prefixes = &insn->prefixes;
+ insn_attr_t attr;
+ insn_byte_t b, lb;
+ int i, nb;
+
+ if (prefixes->got)
+ return 0;
+
+ insn_get_emulate_prefix(insn);
+
+ nb = 0;
+ lb = 0;
+ b = peek_next(insn_byte_t, insn);
+ attr = inat_get_opcode_attribute(b);
+ while (inat_is_legacy_prefix(attr)) {
+ /* Skip if same prefix */
+ for (i = 0; i < nb; i++)
+ if (prefixes->bytes[i] == b)
+ goto found;
+ if (nb == 4)
+ /* Invalid instruction */
+ break;
+ prefixes->bytes[nb++] = b;
+ if (inat_is_address_size_prefix(attr)) {
+ /* address size switches 2/4 or 4/8 */
+ if (insn->x86_64)
+ insn->addr_bytes ^= 12;
+ else
+ insn->addr_bytes ^= 6;
+ } else if (inat_is_operand_size_prefix(attr)) {
+ /* oprand size switches 2/4 */
+ insn->opnd_bytes ^= 6;
+ }
+found:
+ prefixes->nbytes++;
+ insn->next_byte++;
+ lb = b;
+ b = peek_next(insn_byte_t, insn);
+ attr = inat_get_opcode_attribute(b);
+ }
+ /* Set the last prefix */
+ if (lb && lb != insn->prefixes.bytes[3]) {
+ if (unlikely(insn->prefixes.bytes[3])) {
+ /* Swap the last prefix */
+ b = insn->prefixes.bytes[3];
+ for (i = 0; i < nb; i++)
+ if (prefixes->bytes[i] == lb)
+ insn_set_byte(prefixes, i, b);
+ }
+ insn_set_byte(&insn->prefixes, 3, lb);
+ }
+
+ /* Decode REX prefix */
+ if (insn->x86_64) {
+ b = peek_next(insn_byte_t, insn);
+ attr = inat_get_opcode_attribute(b);
+ if (inat_is_rex_prefix(attr)) {
+ insn_field_set(&insn->rex_prefix, b, 1);
+ insn->next_byte++;
+ if (X86_REX_W(b))
+ /* REX.W overrides opnd_size */
+ insn->opnd_bytes = 8;
+ }
+ }
+ insn->rex_prefix.got = 1;
+
+ /* Decode VEX prefix */
+ b = peek_next(insn_byte_t, insn);
+ attr = inat_get_opcode_attribute(b);
+ if (inat_is_vex_prefix(attr)) {
+ insn_byte_t b2 = peek_nbyte_next(insn_byte_t, insn, 1);
+ if (!insn->x86_64) {
+ /*
+ * In 32-bits mode, if the [7:6] bits (mod bits of
+ * ModRM) on the second byte are not 11b, it is
+ * LDS or LES or BOUND.
+ */
+ if (X86_MODRM_MOD(b2) != 3)
+ goto vex_end;
+ }
+ insn_set_byte(&insn->vex_prefix, 0, b);
+ insn_set_byte(&insn->vex_prefix, 1, b2);
+ if (inat_is_evex_prefix(attr)) {
+ b2 = peek_nbyte_next(insn_byte_t, insn, 2);
+ insn_set_byte(&insn->vex_prefix, 2, b2);
+ b2 = peek_nbyte_next(insn_byte_t, insn, 3);
+ insn_set_byte(&insn->vex_prefix, 3, b2);
+ insn->vex_prefix.nbytes = 4;
+ insn->next_byte += 4;
+ if (insn->x86_64 && X86_VEX_W(b2))
+ /* VEX.W overrides opnd_size */
+ insn->opnd_bytes = 8;
+ } else if (inat_is_vex3_prefix(attr)) {
+ b2 = peek_nbyte_next(insn_byte_t, insn, 2);
+ insn_set_byte(&insn->vex_prefix, 2, b2);
+ insn->vex_prefix.nbytes = 3;
+ insn->next_byte += 3;
+ if (insn->x86_64 && X86_VEX_W(b2))
+ /* VEX.W overrides opnd_size */
+ insn->opnd_bytes = 8;
+ } else {
+ /*
+ * For VEX2, fake VEX3-like byte#2.
+ * Makes it easier to decode vex.W, vex.vvvv,
+ * vex.L and vex.pp. Masking with 0x7f sets vex.W == 0.
+ */
+ insn_set_byte(&insn->vex_prefix, 2, b2 & 0x7f);
+ insn->vex_prefix.nbytes = 2;
+ insn->next_byte += 2;
+ }
+ }
+vex_end:
+ insn->vex_prefix.got = 1;
+
+ prefixes->got = 1;
+
+ return 0;
+
+err_out:
+ return -ENODATA;
+}
+
+/**
+ * insn_get_opcode - collect opcode(s)
+ * @insn: &struct insn containing instruction
+ *
+ * Populates @insn->opcode, updates @insn->next_byte to point past the
+ * opcode byte(s), and set @insn->attr (except for groups).
+ * If necessary, first collects any preceding (prefix) bytes.
+ * Sets @insn->opcode.value = opcode1. No effect if @insn->opcode.got
+ * is already 1.
+ *
+ * Returns:
+ * 0: on success
+ * < 0: on error
+ */
+int insn_get_opcode(struct insn *insn)
+{
+ struct insn_field *opcode = &insn->opcode;
+ int pfx_id, ret;
+ insn_byte_t op;
+
+ if (opcode->got)
+ return 0;
+
+ if (!insn->prefixes.got) {
+ ret = insn_get_prefixes(insn);
+ if (ret)
+ return ret;
+ }
+
+ /* Get first opcode */
+ op = get_next(insn_byte_t, insn);
+ insn_set_byte(opcode, 0, op);
+ opcode->nbytes = 1;
+
+ /* Check if there is VEX prefix or not */
+ if (insn_is_avx(insn)) {
+ insn_byte_t m, p;
+ m = insn_vex_m_bits(insn);
+ p = insn_vex_p_bits(insn);
+ insn->attr = inat_get_avx_attribute(op, m, p);
+ if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) ||
+ (!inat_accept_vex(insn->attr) &&
+ !inat_is_group(insn->attr))) {
+ /* This instruction is bad */
+ insn->attr = 0;
+ return -EINVAL;
+ }
+ /* VEX has only 1 byte for opcode */
+ goto end;
+ }
+
+ insn->attr = inat_get_opcode_attribute(op);
+ while (inat_is_escape(insn->attr)) {
+ /* Get escaped opcode */
+ op = get_next(insn_byte_t, insn);
+ opcode->bytes[opcode->nbytes++] = op;
+ pfx_id = insn_last_prefix_id(insn);
+ insn->attr = inat_get_escape_attribute(op, pfx_id, insn->attr);
+ }
+
+ if (inat_must_vex(insn->attr)) {
+ /* This instruction is bad */
+ insn->attr = 0;
+ return -EINVAL;
+ }
+end:
+ opcode->got = 1;
+ return 0;
+
+err_out:
+ return -ENODATA;
+}
+
+/**
+ * insn_get_modrm - collect ModRM byte, if any
+ * @insn: &struct insn containing instruction
+ *
+ * Populates @insn->modrm and updates @insn->next_byte to point past the
+ * ModRM byte, if any. If necessary, first collects the preceding bytes
+ * (prefixes and opcode(s)). No effect if @insn->modrm.got is already 1.
+ *
+ * Returns:
+ * 0: on success
+ * < 0: on error
+ */
+int insn_get_modrm(struct insn *insn)
+{
+ struct insn_field *modrm = &insn->modrm;
+ insn_byte_t pfx_id, mod;
+ int ret;
+
+ if (modrm->got)
+ return 0;
+
+ if (!insn->opcode.got) {
+ ret = insn_get_opcode(insn);
+ if (ret)
+ return ret;
+ }
+
+ if (inat_has_modrm(insn->attr)) {
+ mod = get_next(insn_byte_t, insn);
+ insn_field_set(modrm, mod, 1);
+ if (inat_is_group(insn->attr)) {
+ pfx_id = insn_last_prefix_id(insn);
+ insn->attr = inat_get_group_attribute(mod, pfx_id,
+ insn->attr);
+ if (insn_is_avx(insn) && !inat_accept_vex(insn->attr)) {
+ /* Bad insn */
+ insn->attr = 0;
+ return -EINVAL;
+ }
+ }
+ }
+
+ if (insn->x86_64 && inat_is_force64(insn->attr))
+ insn->opnd_bytes = 8;
+
+ modrm->got = 1;
+ return 0;
+
+err_out:
+ return -ENODATA;
+}
+
+
+/**
+ * insn_rip_relative() - Does instruction use RIP-relative addressing mode?
+ * @insn: &struct insn containing instruction
+ *
+ * If necessary, first collects the instruction up to and including the
+ * ModRM byte. No effect if @insn->x86_64 is 0.
+ */
+int insn_rip_relative(struct insn *insn)
+{
+ struct insn_field *modrm = &insn->modrm;
+ int ret;
+
+ if (!insn->x86_64)
+ return 0;
+
+ if (!modrm->got) {
+ ret = insn_get_modrm(insn);
+ if (ret)
+ return 0;
+ }
+ /*
+ * For rip-relative instructions, the mod field (top 2 bits)
+ * is zero and the r/m field (bottom 3 bits) is 0x5.
+ */
+ return (modrm->nbytes && (modrm->bytes[0] & 0xc7) == 0x5);
+}
+
+/**
+ * insn_get_sib() - Get the SIB byte of instruction
+ * @insn: &struct insn containing instruction
+ *
+ * If necessary, first collects the instruction up to and including the
+ * ModRM byte.
+ *
+ * Returns:
+ * 0: if decoding succeeded
+ * < 0: otherwise.
+ */
+int insn_get_sib(struct insn *insn)
+{
+ insn_byte_t modrm;
+ int ret;
+
+ if (insn->sib.got)
+ return 0;
+
+ if (!insn->modrm.got) {
+ ret = insn_get_modrm(insn);
+ if (ret)
+ return ret;
+ }
+
+ if (insn->modrm.nbytes) {
+ modrm = insn->modrm.bytes[0];
+ if (insn->addr_bytes != 2 &&
+ X86_MODRM_MOD(modrm) != 3 && X86_MODRM_RM(modrm) == 4) {
+ insn_field_set(&insn->sib,
+ get_next(insn_byte_t, insn), 1);
+ }
+ }
+ insn->sib.got = 1;
+
+ return 0;
+
+err_out:
+ return -ENODATA;
+}
+
+
+/**
+ * insn_get_displacement() - Get the displacement of instruction
+ * @insn: &struct insn containing instruction
+ *
+ * If necessary, first collects the instruction up to and including the
+ * SIB byte.
+ * Displacement value is sign-expanded.
+ *
+ * * Returns:
+ * 0: if decoding succeeded
+ * < 0: otherwise.
+ */
+int insn_get_displacement(struct insn *insn)
+{
+ insn_byte_t mod, rm, base;
+ int ret;
+
+ if (insn->displacement.got)
+ return 0;
+
+ if (!insn->sib.got) {
+ ret = insn_get_sib(insn);
+ if (ret)
+ return ret;
+ }
+
+ if (insn->modrm.nbytes) {
+ /*
+ * Interpreting the modrm byte:
+ * mod = 00 - no displacement fields (exceptions below)
+ * mod = 01 - 1-byte displacement field
+ * mod = 10 - displacement field is 4 bytes, or 2 bytes if
+ * address size = 2 (0x67 prefix in 32-bit mode)
+ * mod = 11 - no memory operand
+ *
+ * If address size = 2...
+ * mod = 00, r/m = 110 - displacement field is 2 bytes
+ *
+ * If address size != 2...
+ * mod != 11, r/m = 100 - SIB byte exists
+ * mod = 00, SIB base = 101 - displacement field is 4 bytes
+ * mod = 00, r/m = 101 - rip-relative addressing, displacement
+ * field is 4 bytes
+ */
+ mod = X86_MODRM_MOD(insn->modrm.value);
+ rm = X86_MODRM_RM(insn->modrm.value);
+ base = X86_SIB_BASE(insn->sib.value);
+ if (mod == 3)
+ goto out;
+ if (mod == 1) {
+ insn_field_set(&insn->displacement,
+ get_next(signed char, insn), 1);
+ } else if (insn->addr_bytes == 2) {
+ if ((mod == 0 && rm == 6) || mod == 2) {
+ insn_field_set(&insn->displacement,
+ get_next(short, insn), 2);
+ }
+ } else {
+ if ((mod == 0 && rm == 5) || mod == 2 ||
+ (mod == 0 && base == 5)) {
+ insn_field_set(&insn->displacement,
+ get_next(int, insn), 4);
+ }
+ }
+ }
+out:
+ insn->displacement.got = 1;
+ return 0;
+
+err_out:
+ return -ENODATA;
+}
+
+/* Decode moffset16/32/64. Return 0 if failed */
+static int __get_moffset(struct insn *insn)
+{
+ switch (insn->addr_bytes) {
+ case 2:
+ insn_field_set(&insn->moffset1, get_next(short, insn), 2);
+ break;
+ case 4:
+ insn_field_set(&insn->moffset1, get_next(int, insn), 4);
+ break;
+ case 8:
+ insn_field_set(&insn->moffset1, get_next(int, insn), 4);
+ insn_field_set(&insn->moffset2, get_next(int, insn), 4);
+ break;
+ default: /* opnd_bytes must be modified manually */
+ goto err_out;
+ }
+ insn->moffset1.got = insn->moffset2.got = 1;
+
+ return 1;
+
+err_out:
+ return 0;
+}
+
+/* Decode imm v32(Iz). Return 0 if failed */
+static int __get_immv32(struct insn *insn)
+{
+ switch (insn->opnd_bytes) {
+ case 2:
+ insn_field_set(&insn->immediate, get_next(short, insn), 2);
+ break;
+ case 4:
+ case 8:
+ insn_field_set(&insn->immediate, get_next(int, insn), 4);
+ break;
+ default: /* opnd_bytes must be modified manually */
+ goto err_out;
+ }
+
+ return 1;
+
+err_out:
+ return 0;
+}
+
+/* Decode imm v64(Iv/Ov), Return 0 if failed */
+static int __get_immv(struct insn *insn)
+{
+ switch (insn->opnd_bytes) {
+ case 2:
+ insn_field_set(&insn->immediate1, get_next(short, insn), 2);
+ break;
+ case 4:
+ insn_field_set(&insn->immediate1, get_next(int, insn), 4);
+ insn->immediate1.nbytes = 4;
+ break;
+ case 8:
+ insn_field_set(&insn->immediate1, get_next(int, insn), 4);
+ insn_field_set(&insn->immediate2, get_next(int, insn), 4);
+ break;
+ default: /* opnd_bytes must be modified manually */
+ goto err_out;
+ }
+ insn->immediate1.got = insn->immediate2.got = 1;
+
+ return 1;
+err_out:
+ return 0;
+}
+
+/* Decode ptr16:16/32(Ap) */
+static int __get_immptr(struct insn *insn)
+{
+ switch (insn->opnd_bytes) {
+ case 2:
+ insn_field_set(&insn->immediate1, get_next(short, insn), 2);
+ break;
+ case 4:
+ insn_field_set(&insn->immediate1, get_next(int, insn), 4);
+ break;
+ case 8:
+ /* ptr16:64 is not exist (no segment) */
+ return 0;
+ default: /* opnd_bytes must be modified manually */
+ goto err_out;
+ }
+ insn_field_set(&insn->immediate2, get_next(unsigned short, insn), 2);
+ insn->immediate1.got = insn->immediate2.got = 1;
+
+ return 1;
+err_out:
+ return 0;
+}
+
+/**
+ * insn_get_immediate() - Get the immediate in an instruction
+ * @insn: &struct insn containing instruction
+ *
+ * If necessary, first collects the instruction up to and including the
+ * displacement bytes.
+ * Basically, most of immediates are sign-expanded. Unsigned-value can be
+ * computed by bit masking with ((1 << (nbytes * 8)) - 1)
+ *
+ * Returns:
+ * 0: on success
+ * < 0: on error
+ */
+int insn_get_immediate(struct insn *insn)
+{
+ int ret;
+
+ if (insn->immediate.got)
+ return 0;
+
+ if (!insn->displacement.got) {
+ ret = insn_get_displacement(insn);
+ if (ret)
+ return ret;
+ }
+
+ if (inat_has_moffset(insn->attr)) {
+ if (!__get_moffset(insn))
+ goto err_out;
+ goto done;
+ }
+
+ if (!inat_has_immediate(insn->attr))
+ /* no immediates */
+ goto done;
+
+ switch (inat_immediate_size(insn->attr)) {
+ case INAT_IMM_BYTE:
+ insn_field_set(&insn->immediate, get_next(signed char, insn), 1);
+ break;
+ case INAT_IMM_WORD:
+ insn_field_set(&insn->immediate, get_next(short, insn), 2);
+ break;
+ case INAT_IMM_DWORD:
+ insn_field_set(&insn->immediate, get_next(int, insn), 4);
+ break;
+ case INAT_IMM_QWORD:
+ insn_field_set(&insn->immediate1, get_next(int, insn), 4);
+ insn_field_set(&insn->immediate2, get_next(int, insn), 4);
+ break;
+ case INAT_IMM_PTR:
+ if (!__get_immptr(insn))
+ goto err_out;
+ break;
+ case INAT_IMM_VWORD32:
+ if (!__get_immv32(insn))
+ goto err_out;
+ break;
+ case INAT_IMM_VWORD:
+ if (!__get_immv(insn))
+ goto err_out;
+ break;
+ default:
+ /* Here, insn must have an immediate, but failed */
+ goto err_out;
+ }
+ if (inat_has_second_immediate(insn->attr)) {
+ insn_field_set(&insn->immediate2, get_next(signed char, insn), 1);
+ }
+done:
+ insn->immediate.got = 1;
+ return 0;
+
+err_out:
+ return -ENODATA;
+}
+
+/**
+ * insn_get_length() - Get the length of instruction
+ * @insn: &struct insn containing instruction
+ *
+ * If necessary, first collects the instruction up to and including the
+ * immediates bytes.
+ *
+ * Returns:
+ * - 0 on success
+ * - < 0 on error
+*/
+int insn_get_length(struct insn *insn)
+{
+ int ret;
+
+ if (insn->length)
+ return 0;
+
+ if (!insn->immediate.got) {
+ ret = insn_get_immediate(insn);
+ if (ret)
+ return ret;
+ }
+
+ insn->length = (unsigned char)((unsigned long)insn->next_byte
+ - (unsigned long)insn->kaddr);
+
+ return 0;
+}
+
+/* Ensure this instruction is decoded completely */
+static inline int insn_complete(struct insn *insn)
+{
+ return insn->opcode.got && insn->modrm.got && insn->sib.got &&
+ insn->displacement.got && insn->immediate.got;
+}
+
+/**
+ * insn_decode() - Decode an x86 instruction
+ * @insn: &struct insn to be initialized
+ * @kaddr: address (in kernel memory) of instruction (or copy thereof)
+ * @buf_len: length of the insn buffer at @kaddr
+ * @m: insn mode, see enum insn_mode
+ *
+ * Returns:
+ * 0: if decoding succeeded
+ * < 0: otherwise.
+ */
+int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m)
+{
+ int ret;
+
+/* #define INSN_MODE_KERN -1 __ignore_sync_check__ mode is only valid in the kernel */
+
+ if (m == INSN_MODE_KERN)
+ insn_init(insn, kaddr, buf_len, IS_ENABLED(CONFIG_X86_64));
+ else
+ insn_init(insn, kaddr, buf_len, m == INSN_MODE_64);
+
+ ret = insn_get_length(insn);
+ if (ret)
+ return ret;
+
+ if (insn_complete(insn))
+ return 0;
+
+ return -EINVAL;
+}
diff --git a/arch/x86/lib/iomap_copy_64.S b/arch/x86/lib/iomap_copy_64.S
new file mode 100644
index 0000000000..6ff2f56cb0
--- /dev/null
+++ b/arch/x86/lib/iomap_copy_64.S
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright 2006 PathScale, Inc. All Rights Reserved.
+ */
+
+#include <linux/linkage.h>
+
+/*
+ * override generic version in lib/iomap_copy.c
+ */
+SYM_FUNC_START(__iowrite32_copy)
+ movl %edx,%ecx
+ rep movsl
+ RET
+SYM_FUNC_END(__iowrite32_copy)
diff --git a/arch/x86/lib/iomem.c b/arch/x86/lib/iomem.c
new file mode 100644
index 0000000000..e0411a3774
--- /dev/null
+++ b/arch/x86/lib/iomem.c
@@ -0,0 +1,123 @@
+#include <linux/string.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/kmsan-checks.h>
+
+#define movs(type,to,from) \
+ asm volatile("movs" type:"=&D" (to), "=&S" (from):"0" (to), "1" (from):"memory")
+
+/* Originally from i386/string.h */
+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"
+ "testb $2,%b4\n\t"
+ "je 1f\n\t"
+ "movsw\n"
+ "1:\ttestb $1,%b4\n\t"
+ "je 2f\n\t"
+ "movsb\n"
+ "2:"
+ : "=&c" (d0), "=&D" (d1), "=&S" (d2)
+ : "0" (n / 4), "q" (n), "1" ((long)to), "2" ((long)from)
+ : "memory");
+}
+
+static void string_memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
+{
+ if (unlikely(!n))
+ return;
+
+ /* Align any unaligned source IO */
+ if (unlikely(1 & (unsigned long)from)) {
+ movs("b", to, from);
+ n--;
+ }
+ if (n > 1 && unlikely(2 & (unsigned long)from)) {
+ movs("w", to, from);
+ n-=2;
+ }
+ rep_movs(to, (const void *)from, n);
+ /* KMSAN must treat values read from devices as initialized. */
+ kmsan_unpoison_memory(to, n);
+}
+
+static void string_memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
+{
+ if (unlikely(!n))
+ return;
+
+ /* Make sure uninitialized memory isn't copied to devices. */
+ kmsan_check_memory(from, n);
+ /* Align any unaligned destination IO */
+ if (unlikely(1 & (unsigned long)to)) {
+ movs("b", to, from);
+ n--;
+ }
+ if (n > 1 && unlikely(2 & (unsigned long)to)) {
+ movs("w", to, from);
+ n-=2;
+ }
+ rep_movs((void *)to, (const void *) from, n);
+}
+
+static void unrolled_memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
+{
+ const volatile char __iomem *in = from;
+ char *out = to;
+ int i;
+
+ for (i = 0; i < n; ++i)
+ out[i] = readb(&in[i]);
+}
+
+static void unrolled_memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
+{
+ volatile char __iomem *out = to;
+ const char *in = from;
+ int i;
+
+ for (i = 0; i < n; ++i)
+ writeb(in[i], &out[i]);
+}
+
+static void unrolled_memset_io(volatile void __iomem *a, int b, size_t c)
+{
+ volatile char __iomem *mem = a;
+ int i;
+
+ for (i = 0; i < c; ++i)
+ writeb(b, &mem[i]);
+}
+
+void memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
+{
+ if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO))
+ unrolled_memcpy_fromio(to, from, n);
+ else
+ string_memcpy_fromio(to, from, n);
+}
+EXPORT_SYMBOL(memcpy_fromio);
+
+void memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
+{
+ if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO))
+ unrolled_memcpy_toio(to, from, n);
+ else
+ string_memcpy_toio(to, from, n);
+}
+EXPORT_SYMBOL(memcpy_toio);
+
+void memset_io(volatile void __iomem *a, int b, size_t c)
+{
+ if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) {
+ unrolled_memset_io(a, b, c);
+ } else {
+ /*
+ * TODO: memset can mangle the IO patterns quite a bit.
+ * perhaps it would be better to use a dumb one:
+ */
+ memset((void *)a, b, c);
+ }
+}
+EXPORT_SYMBOL(memset_io);
diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c
new file mode 100644
index 0000000000..a58f451a7d
--- /dev/null
+++ b/arch/x86/lib/kaslr.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Entropy functions used on early boot for KASLR base and memory
+ * randomization. The base randomization is done in the compressed
+ * kernel and memory randomization is done early when the regular
+ * kernel starts. This file is included in the compressed kernel and
+ * normally linked in the regular.
+ */
+#include <asm/asm.h>
+#include <asm/kaslr.h>
+#include <asm/msr.h>
+#include <asm/archrandom.h>
+#include <asm/e820/api.h>
+#include <asm/shared/io.h>
+
+/*
+ * When built for the regular kernel, several functions need to be stubbed out
+ * or changed to their regular kernel equivalent.
+ */
+#ifndef KASLR_COMPRESSED_BOOT
+#include <asm/cpufeature.h>
+#include <asm/setup.h>
+
+#define debug_putstr(v) early_printk("%s", v)
+#define has_cpuflag(f) boot_cpu_has(f)
+#define get_boot_seed() kaslr_offset()
+#endif
+
+#define I8254_PORT_CONTROL 0x43
+#define I8254_PORT_COUNTER0 0x40
+#define I8254_CMD_READBACK 0xC0
+#define I8254_SELECT_COUNTER0 0x02
+#define I8254_STATUS_NOTREADY 0x40
+static inline u16 i8254(void)
+{
+ u16 status, timer;
+
+ do {
+ outb(I8254_CMD_READBACK | I8254_SELECT_COUNTER0,
+ I8254_PORT_CONTROL);
+ status = inb(I8254_PORT_COUNTER0);
+ timer = inb(I8254_PORT_COUNTER0);
+ timer |= inb(I8254_PORT_COUNTER0) << 8;
+ } while (status & I8254_STATUS_NOTREADY);
+
+ return timer;
+}
+
+unsigned long kaslr_get_random_long(const char *purpose)
+{
+#ifdef CONFIG_X86_64
+ const unsigned long mix_const = 0x5d6008cbf3848dd3UL;
+#else
+ const unsigned long mix_const = 0x3f39e593UL;
+#endif
+ unsigned long raw, random = get_boot_seed();
+ bool use_i8254 = true;
+
+ if (purpose) {
+ debug_putstr(purpose);
+ debug_putstr(" KASLR using");
+ }
+
+ if (has_cpuflag(X86_FEATURE_RDRAND)) {
+ if (purpose)
+ debug_putstr(" RDRAND");
+ if (rdrand_long(&raw)) {
+ random ^= raw;
+ use_i8254 = false;
+ }
+ }
+
+ if (has_cpuflag(X86_FEATURE_TSC)) {
+ if (purpose)
+ debug_putstr(" RDTSC");
+ raw = rdtsc();
+
+ random ^= raw;
+ use_i8254 = false;
+ }
+
+ if (use_i8254) {
+ if (purpose)
+ debug_putstr(" i8254");
+ random ^= i8254();
+ }
+
+ /* Circular multiply for better bit diffusion */
+ asm(_ASM_MUL "%3"
+ : "=a" (random), "=d" (raw)
+ : "a" (random), "rm" (mix_const));
+ random += raw;
+
+ if (purpose)
+ debug_putstr("...\n");
+
+ return random;
+}
diff --git a/arch/x86/lib/memcpy_32.c b/arch/x86/lib/memcpy_32.c
new file mode 100644
index 0000000000..a29b64befb
--- /dev/null
+++ b/arch/x86/lib/memcpy_32.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/string.h>
+#include <linux/export.h>
+
+#undef memcpy
+#undef memset
+#undef memmove
+
+__visible void *memcpy(void *to, const void *from, size_t n)
+{
+ return __memcpy(to, from, n);
+}
+EXPORT_SYMBOL(memcpy);
+
+__visible void *memset(void *s, int c, size_t count)
+{
+ return __memset(s, c, count);
+}
+EXPORT_SYMBOL(memset);
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
new file mode 100644
index 0000000000..76697df8df
--- /dev/null
+++ b/arch/x86/lib/memcpy_64.S
@@ -0,0 +1,172 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright 2002 Andi Kleen */
+
+#include <linux/linkage.h>
+#include <linux/cfi_types.h>
+#include <asm/errno.h>
+#include <asm/cpufeatures.h>
+#include <asm/alternative.h>
+#include <asm/export.h>
+
+.section .noinstr.text, "ax"
+
+/*
+ * memcpy - Copy a memory block.
+ *
+ * Input:
+ * rdi destination
+ * rsi source
+ * rdx count
+ *
+ * Output:
+ * rax original destination
+ *
+ * The FSRM alternative should be done inline (avoiding the call and
+ * the disgusting return handling), but that would require some help
+ * from the compiler for better calling conventions.
+ *
+ * The 'rep movsb' itself is small enough to replace the call, but the
+ * two register moves blow up the code. And one of them is "needed"
+ * only for the return value that is the same as the source input,
+ * which the compiler could/should do much better anyway.
+ */
+SYM_TYPED_FUNC_START(__memcpy)
+ ALTERNATIVE "jmp memcpy_orig", "", X86_FEATURE_FSRM
+
+ movq %rdi, %rax
+ movq %rdx, %rcx
+ rep movsb
+ RET
+SYM_FUNC_END(__memcpy)
+EXPORT_SYMBOL(__memcpy)
+
+SYM_FUNC_ALIAS_MEMFUNC(memcpy, __memcpy)
+EXPORT_SYMBOL(memcpy)
+
+SYM_FUNC_START_LOCAL(memcpy_orig)
+ movq %rdi, %rax
+
+ cmpq $0x20, %rdx
+ jb .Lhandle_tail
+
+ /*
+ * We check whether memory false dependence could occur,
+ * then jump to corresponding copy mode.
+ */
+ cmp %dil, %sil
+ jl .Lcopy_backward
+ subq $0x20, %rdx
+.Lcopy_forward_loop:
+ subq $0x20, %rdx
+
+ /*
+ * Move in blocks of 4x8 bytes:
+ */
+ movq 0*8(%rsi), %r8
+ movq 1*8(%rsi), %r9
+ movq 2*8(%rsi), %r10
+ movq 3*8(%rsi), %r11
+ leaq 4*8(%rsi), %rsi
+
+ movq %r8, 0*8(%rdi)
+ movq %r9, 1*8(%rdi)
+ movq %r10, 2*8(%rdi)
+ movq %r11, 3*8(%rdi)
+ leaq 4*8(%rdi), %rdi
+ jae .Lcopy_forward_loop
+ addl $0x20, %edx
+ jmp .Lhandle_tail
+
+.Lcopy_backward:
+ /*
+ * Calculate copy position to tail.
+ */
+ addq %rdx, %rsi
+ addq %rdx, %rdi
+ subq $0x20, %rdx
+ /*
+ * At most 3 ALU operations in one cycle,
+ * so append NOPS in the same 16 bytes trunk.
+ */
+ .p2align 4
+.Lcopy_backward_loop:
+ subq $0x20, %rdx
+ movq -1*8(%rsi), %r8
+ movq -2*8(%rsi), %r9
+ movq -3*8(%rsi), %r10
+ movq -4*8(%rsi), %r11
+ leaq -4*8(%rsi), %rsi
+ movq %r8, -1*8(%rdi)
+ movq %r9, -2*8(%rdi)
+ movq %r10, -3*8(%rdi)
+ movq %r11, -4*8(%rdi)
+ leaq -4*8(%rdi), %rdi
+ jae .Lcopy_backward_loop
+
+ /*
+ * Calculate copy position to head.
+ */
+ addl $0x20, %edx
+ subq %rdx, %rsi
+ subq %rdx, %rdi
+.Lhandle_tail:
+ cmpl $16, %edx
+ jb .Lless_16bytes
+
+ /*
+ * Move data from 16 bytes to 31 bytes.
+ */
+ movq 0*8(%rsi), %r8
+ movq 1*8(%rsi), %r9
+ movq -2*8(%rsi, %rdx), %r10
+ movq -1*8(%rsi, %rdx), %r11
+ movq %r8, 0*8(%rdi)
+ movq %r9, 1*8(%rdi)
+ movq %r10, -2*8(%rdi, %rdx)
+ movq %r11, -1*8(%rdi, %rdx)
+ RET
+ .p2align 4
+.Lless_16bytes:
+ cmpl $8, %edx
+ jb .Lless_8bytes
+ /*
+ * Move data from 8 bytes to 15 bytes.
+ */
+ movq 0*8(%rsi), %r8
+ movq -1*8(%rsi, %rdx), %r9
+ movq %r8, 0*8(%rdi)
+ movq %r9, -1*8(%rdi, %rdx)
+ RET
+ .p2align 4
+.Lless_8bytes:
+ cmpl $4, %edx
+ jb .Lless_3bytes
+
+ /*
+ * Move data from 4 bytes to 7 bytes.
+ */
+ movl (%rsi), %ecx
+ movl -4(%rsi, %rdx), %r8d
+ movl %ecx, (%rdi)
+ movl %r8d, -4(%rdi, %rdx)
+ RET
+ .p2align 4
+.Lless_3bytes:
+ subl $1, %edx
+ jb .Lend
+ /*
+ * Move data from 1 bytes to 3 bytes.
+ */
+ movzbl (%rsi), %ecx
+ jz .Lstore_1byte
+ movzbq 1(%rsi), %r8
+ movzbq (%rsi, %rdx), %r9
+ movb %r8b, 1(%rdi)
+ movb %r9b, (%rdi, %rdx)
+.Lstore_1byte:
+ movb %cl, (%rdi)
+
+.Lend:
+ RET
+SYM_FUNC_END(memcpy_orig)
+
diff --git a/arch/x86/lib/memmove_32.S b/arch/x86/lib/memmove_32.S
new file mode 100644
index 0000000000..0588b2c0fc
--- /dev/null
+++ b/arch/x86/lib/memmove_32.S
@@ -0,0 +1,200 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/linkage.h>
+#include <asm/export.h>
+
+SYM_FUNC_START(memmove)
+/*
+ * void *memmove(void *dest_in, const void *src_in, size_t n)
+ * -mregparm=3 passes these in registers:
+ * dest_in: %eax
+ * src_in: %edx
+ * n: %ecx
+ * See also: arch/x86/entry/calling.h for description of the calling convention.
+ *
+ * n can remain in %ecx, but for `rep movsl`, we'll need dest in %edi and src
+ * in %esi.
+ */
+.set dest_in, %eax
+.set dest, %edi
+.set src_in, %edx
+.set src, %esi
+.set n, %ecx
+.set tmp0, %edx
+.set tmp0w, %dx
+.set tmp1, %ebx
+.set tmp1w, %bx
+.set tmp2, %eax
+.set tmp3b, %cl
+
+/*
+ * Save all callee-saved registers, because this function is going to clobber
+ * all of them:
+ */
+ pushl %ebp
+ movl %esp, %ebp // set standard frame pointer
+
+ pushl %ebx
+ pushl %edi
+ pushl %esi
+ pushl %eax // save 'dest_in' parameter [eax] as the return value
+
+ movl src_in, src
+ movl dest_in, dest
+
+ /* Handle more 16 bytes in loop */
+ cmpl $0x10, n
+ jb .Lmove_16B
+
+ /* Decide forward/backward copy mode */
+ cmpl dest, src
+ jb .Lbackwards_header
+
+ /*
+ * movs instruction have many startup latency
+ * so we handle small size by general register.
+ */
+ cmpl $680, n
+ jb .Ltoo_small_forwards
+ /* movs instruction is only good for aligned case. */
+ movl src, tmp0
+ xorl dest, tmp0
+ andl $0xff, tmp0
+ jz .Lforward_movs
+.Ltoo_small_forwards:
+ subl $0x10, n
+
+ /* We gobble 16 bytes forward in each loop. */
+.Lmove_16B_forwards_loop:
+ subl $0x10, n
+ movl 0*4(src), tmp0
+ movl 1*4(src), tmp1
+ movl tmp0, 0*4(dest)
+ movl tmp1, 1*4(dest)
+ movl 2*4(src), tmp0
+ movl 3*4(src), tmp1
+ movl tmp0, 2*4(dest)
+ movl tmp1, 3*4(dest)
+ leal 0x10(src), src
+ leal 0x10(dest), dest
+ jae .Lmove_16B_forwards_loop
+ addl $0x10, n
+ jmp .Lmove_16B
+
+ /* Handle data forward by movs. */
+.p2align 4
+.Lforward_movs:
+ movl -4(src, n), tmp0
+ leal -4(dest, n), tmp1
+ shrl $2, n
+ rep movsl
+ movl tmp0, (tmp1)
+ jmp .Ldone
+
+ /* Handle data backward by movs. */
+.p2align 4
+.Lbackwards_movs:
+ movl (src), tmp0
+ movl dest, tmp1
+ leal -4(src, n), src
+ leal -4(dest, n), dest
+ shrl $2, n
+ std
+ rep movsl
+ movl tmp0,(tmp1)
+ cld
+ jmp .Ldone
+
+ /* Start to prepare for backward copy. */
+.p2align 4
+.Lbackwards_header:
+ cmpl $680, n
+ jb .Ltoo_small_backwards
+ movl src, tmp0
+ xorl dest, tmp0
+ andl $0xff, tmp0
+ jz .Lbackwards_movs
+
+ /* Calculate copy position to tail. */
+.Ltoo_small_backwards:
+ addl n, src
+ addl n, dest
+ subl $0x10, n
+
+ /* We gobble 16 bytes backward in each loop. */
+.Lmove_16B_backwards_loop:
+ subl $0x10, n
+
+ movl -1*4(src), tmp0
+ movl -2*4(src), tmp1
+ movl tmp0, -1*4(dest)
+ movl tmp1, -2*4(dest)
+ movl -3*4(src), tmp0
+ movl -4*4(src), tmp1
+ movl tmp0, -3*4(dest)
+ movl tmp1, -4*4(dest)
+ leal -0x10(src), src
+ leal -0x10(dest), dest
+ jae .Lmove_16B_backwards_loop
+ /* Calculate copy position to head. */
+ addl $0x10, n
+ subl n, src
+ subl n, dest
+
+ /* Move data from 8 bytes to 15 bytes. */
+.p2align 4
+.Lmove_16B:
+ cmpl $8, n
+ jb .Lmove_8B
+ movl 0*4(src), tmp0
+ movl 1*4(src), tmp1
+ movl -2*4(src, n), tmp2
+ movl -1*4(src, n), src
+
+ movl tmp0, 0*4(dest)
+ movl tmp1, 1*4(dest)
+ movl tmp2, -2*4(dest, n)
+ movl src, -1*4(dest, n)
+ jmp .Ldone
+
+ /* Move data from 4 bytes to 7 bytes. */
+.p2align 4
+.Lmove_8B:
+ cmpl $4, n
+ jb .Lmove_4B
+ movl 0*4(src), tmp0
+ movl -1*4(src, n), tmp1
+ movl tmp0, 0*4(dest)
+ movl tmp1, -1*4(dest, n)
+ jmp .Ldone
+
+ /* Move data from 2 bytes to 3 bytes. */
+.p2align 4
+.Lmove_4B:
+ cmpl $2, n
+ jb .Lmove_1B
+ movw 0*2(src), tmp0w
+ movw -1*2(src, n), tmp1w
+ movw tmp0w, 0*2(dest)
+ movw tmp1w, -1*2(dest, n)
+ jmp .Ldone
+
+ /* Move data for 1 byte. */
+.p2align 4
+.Lmove_1B:
+ cmpl $1, n
+ jb .Ldone
+ movb (src), tmp3b
+ movb tmp3b, (dest)
+.p2align 4
+.Ldone:
+ popl dest_in // restore 'dest_in' [eax] as the return value
+ /* Restore all callee-saved registers: */
+ popl %esi
+ popl %edi
+ popl %ebx
+ popl %ebp
+
+ RET
+SYM_FUNC_END(memmove)
+EXPORT_SYMBOL(memmove)
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
new file mode 100644
index 0000000000..ccdf3a5970
--- /dev/null
+++ b/arch/x86/lib/memmove_64.S
@@ -0,0 +1,216 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Normally compiler builtins are used, but sometimes the compiler calls out
+ * of line code. Based on asm-i386/string.h.
+ *
+ * This assembly file is re-written from memmove_64.c file.
+ * - Copyright 2011 Fenghua Yu <fenghua.yu@intel.com>
+ */
+#include <linux/linkage.h>
+#include <asm/cpufeatures.h>
+#include <asm/alternative.h>
+#include <asm/export.h>
+
+#undef memmove
+
+.section .noinstr.text, "ax"
+
+/*
+ * Implement memmove(). This can handle overlap between src and dst.
+ *
+ * Input:
+ * rdi: dest
+ * rsi: src
+ * rdx: count
+ *
+ * Output:
+ * rax: dest
+ */
+SYM_FUNC_START(__memmove)
+
+ mov %rdi, %rax
+
+ /* Decide forward/backward copy mode */
+ cmp %rdi, %rsi
+ jge .Lmemmove_begin_forward
+ mov %rsi, %r8
+ add %rdx, %r8
+ cmp %rdi, %r8
+ jg 2f
+
+#define CHECK_LEN cmp $0x20, %rdx; jb 1f
+#define MEMMOVE_BYTES movq %rdx, %rcx; rep movsb; RET
+.Lmemmove_begin_forward:
+ ALTERNATIVE_2 __stringify(CHECK_LEN), \
+ __stringify(CHECK_LEN; MEMMOVE_BYTES), X86_FEATURE_ERMS, \
+ __stringify(MEMMOVE_BYTES), X86_FEATURE_FSRM
+
+ /*
+ * movsq instruction have many startup latency
+ * so we handle small size by general register.
+ */
+ cmp $680, %rdx
+ jb 3f
+ /*
+ * movsq instruction is only good for aligned case.
+ */
+
+ cmpb %dil, %sil
+ je 4f
+3:
+ sub $0x20, %rdx
+ /*
+ * We gobble 32 bytes forward in each loop.
+ */
+5:
+ sub $0x20, %rdx
+ movq 0*8(%rsi), %r11
+ movq 1*8(%rsi), %r10
+ movq 2*8(%rsi), %r9
+ movq 3*8(%rsi), %r8
+ leaq 4*8(%rsi), %rsi
+
+ movq %r11, 0*8(%rdi)
+ movq %r10, 1*8(%rdi)
+ movq %r9, 2*8(%rdi)
+ movq %r8, 3*8(%rdi)
+ leaq 4*8(%rdi), %rdi
+ jae 5b
+ addq $0x20, %rdx
+ jmp 1f
+ /*
+ * Handle data forward by movsq.
+ */
+ .p2align 4
+4:
+ movq %rdx, %rcx
+ movq -8(%rsi, %rdx), %r11
+ lea -8(%rdi, %rdx), %r10
+ shrq $3, %rcx
+ rep movsq
+ movq %r11, (%r10)
+ jmp 13f
+.Lmemmove_end_forward:
+
+ /*
+ * Handle data backward by movsq.
+ */
+ .p2align 4
+7:
+ movq %rdx, %rcx
+ movq (%rsi), %r11
+ movq %rdi, %r10
+ leaq -8(%rsi, %rdx), %rsi
+ leaq -8(%rdi, %rdx), %rdi
+ shrq $3, %rcx
+ std
+ rep movsq
+ cld
+ movq %r11, (%r10)
+ jmp 13f
+
+ /*
+ * Start to prepare for backward copy.
+ */
+ .p2align 4
+2:
+ cmp $0x20, %rdx
+ jb 1f
+ cmp $680, %rdx
+ jb 6f
+ cmp %dil, %sil
+ je 7b
+6:
+ /*
+ * Calculate copy position to tail.
+ */
+ addq %rdx, %rsi
+ addq %rdx, %rdi
+ subq $0x20, %rdx
+ /*
+ * We gobble 32 bytes backward in each loop.
+ */
+8:
+ subq $0x20, %rdx
+ movq -1*8(%rsi), %r11
+ movq -2*8(%rsi), %r10
+ movq -3*8(%rsi), %r9
+ movq -4*8(%rsi), %r8
+ leaq -4*8(%rsi), %rsi
+
+ movq %r11, -1*8(%rdi)
+ movq %r10, -2*8(%rdi)
+ movq %r9, -3*8(%rdi)
+ movq %r8, -4*8(%rdi)
+ leaq -4*8(%rdi), %rdi
+ jae 8b
+ /*
+ * Calculate copy position to head.
+ */
+ addq $0x20, %rdx
+ subq %rdx, %rsi
+ subq %rdx, %rdi
+1:
+ cmpq $16, %rdx
+ jb 9f
+ /*
+ * Move data from 16 bytes to 31 bytes.
+ */
+ movq 0*8(%rsi), %r11
+ movq 1*8(%rsi), %r10
+ movq -2*8(%rsi, %rdx), %r9
+ movq -1*8(%rsi, %rdx), %r8
+ movq %r11, 0*8(%rdi)
+ movq %r10, 1*8(%rdi)
+ movq %r9, -2*8(%rdi, %rdx)
+ movq %r8, -1*8(%rdi, %rdx)
+ jmp 13f
+ .p2align 4
+9:
+ cmpq $8, %rdx
+ jb 10f
+ /*
+ * Move data from 8 bytes to 15 bytes.
+ */
+ movq 0*8(%rsi), %r11
+ movq -1*8(%rsi, %rdx), %r10
+ movq %r11, 0*8(%rdi)
+ movq %r10, -1*8(%rdi, %rdx)
+ jmp 13f
+10:
+ cmpq $4, %rdx
+ jb 11f
+ /*
+ * Move data from 4 bytes to 7 bytes.
+ */
+ movl (%rsi), %r11d
+ movl -4(%rsi, %rdx), %r10d
+ movl %r11d, (%rdi)
+ movl %r10d, -4(%rdi, %rdx)
+ jmp 13f
+11:
+ cmp $2, %rdx
+ jb 12f
+ /*
+ * Move data from 2 bytes to 3 bytes.
+ */
+ movw (%rsi), %r11w
+ movw -2(%rsi, %rdx), %r10w
+ movw %r11w, (%rdi)
+ movw %r10w, -2(%rdi, %rdx)
+ jmp 13f
+12:
+ cmp $1, %rdx
+ jb 13f
+ /*
+ * Move data for 1 byte.
+ */
+ movb (%rsi), %r11b
+ movb %r11b, (%rdi)
+13:
+ RET
+SYM_FUNC_END(__memmove)
+EXPORT_SYMBOL(__memmove)
+
+SYM_FUNC_ALIAS_MEMFUNC(memmove, __memmove)
+EXPORT_SYMBOL(memmove)
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
new file mode 100644
index 0000000000..3d818b849e
--- /dev/null
+++ b/arch/x86/lib/memset_64.S
@@ -0,0 +1,117 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright 2002 Andi Kleen, SuSE Labs */
+
+#include <linux/linkage.h>
+#include <asm/cpufeatures.h>
+#include <asm/alternative.h>
+#include <asm/export.h>
+
+.section .noinstr.text, "ax"
+
+/*
+ * ISO C memset - set a memory block to a byte value. This function uses fast
+ * string to get better performance than the original function. The code is
+ * simpler and shorter than the original function as well.
+ *
+ * rdi destination
+ * rsi value (char)
+ * rdx count (bytes)
+ *
+ * rax original destination
+ *
+ * The FSRS alternative should be done inline (avoiding the call and
+ * the disgusting return handling), but that would require some help
+ * from the compiler for better calling conventions.
+ *
+ * The 'rep stosb' itself is small enough to replace the call, but all
+ * the register moves blow up the code. And two of them are "needed"
+ * 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)
+ ALTERNATIVE "jmp memset_orig", "", X86_FEATURE_FSRS
+
+ movq %rdi,%r9
+ movb %sil,%al
+ movq %rdx,%rcx
+ rep stosb
+ movq %r9,%rax
+ RET
+SYM_FUNC_END(__memset)
+EXPORT_SYMBOL(__memset)
+
+SYM_FUNC_ALIAS_MEMFUNC(memset, __memset)
+EXPORT_SYMBOL(memset)
+
+SYM_FUNC_START_LOCAL(memset_orig)
+ movq %rdi,%r10
+
+ /* expand byte value */
+ movzbl %sil,%ecx
+ movabs $0x0101010101010101,%rax
+ imulq %rcx,%rax
+
+ /* align dst */
+ movl %edi,%r9d
+ andl $7,%r9d
+ jnz .Lbad_alignment
+.Lafter_bad_alignment:
+
+ movq %rdx,%rcx
+ shrq $6,%rcx
+ jz .Lhandle_tail
+
+ .p2align 4
+.Lloop_64:
+ decq %rcx
+ movq %rax,(%rdi)
+ movq %rax,8(%rdi)
+ movq %rax,16(%rdi)
+ movq %rax,24(%rdi)
+ movq %rax,32(%rdi)
+ movq %rax,40(%rdi)
+ movq %rax,48(%rdi)
+ movq %rax,56(%rdi)
+ leaq 64(%rdi),%rdi
+ jnz .Lloop_64
+
+ /* Handle tail in loops. The loops should be faster than hard
+ to predict jump tables. */
+ .p2align 4
+.Lhandle_tail:
+ movl %edx,%ecx
+ andl $63&(~7),%ecx
+ jz .Lhandle_7
+ shrl $3,%ecx
+ .p2align 4
+.Lloop_8:
+ decl %ecx
+ movq %rax,(%rdi)
+ leaq 8(%rdi),%rdi
+ jnz .Lloop_8
+
+.Lhandle_7:
+ andl $7,%edx
+ jz .Lende
+ .p2align 4
+.Lloop_1:
+ decl %edx
+ movb %al,(%rdi)
+ leaq 1(%rdi),%rdi
+ jnz .Lloop_1
+
+.Lende:
+ movq %r10,%rax
+ RET
+
+.Lbad_alignment:
+ cmpq $7,%rdx
+ jbe .Lhandle_7
+ movq %rax,(%rdi) /* unaligned store */
+ movq $8,%r8
+ subq %r9,%r8
+ addq %r8,%rdi
+ subq %r8,%rdx
+ jmp .Lafter_bad_alignment
+.Lfinal:
+SYM_FUNC_END(memset_orig)
diff --git a/arch/x86/lib/misc.c b/arch/x86/lib/misc.c
new file mode 100644
index 0000000000..40b81c338a
--- /dev/null
+++ b/arch/x86/lib/misc.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <asm/misc.h>
+
+/*
+ * Count the digits of @val including a possible sign.
+ *
+ * (Typed on and submitted from hpa's mobile phone.)
+ */
+int num_digits(int val)
+{
+ long long m = 10;
+ int d = 1;
+
+ if (val < 0) {
+ d++;
+ val = -val;
+ }
+
+ while (val >= m) {
+ m *= 10;
+ d++;
+ }
+ return d;
+}
diff --git a/arch/x86/lib/msr-reg-export.c b/arch/x86/lib/msr-reg-export.c
new file mode 100644
index 0000000000..876b4168ab
--- /dev/null
+++ b/arch/x86/lib/msr-reg-export.c
@@ -0,0 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/export.h>
+#include <asm/msr.h>
+
+EXPORT_SYMBOL(rdmsr_safe_regs);
+EXPORT_SYMBOL(wrmsr_safe_regs);
diff --git a/arch/x86/lib/msr-reg.S b/arch/x86/lib/msr-reg.S
new file mode 100644
index 0000000000..ebd259f314
--- /dev/null
+++ b/arch/x86/lib/msr-reg.S
@@ -0,0 +1,93 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/linkage.h>
+#include <linux/errno.h>
+#include <asm/asm.h>
+#include <asm/msr.h>
+
+#ifdef CONFIG_X86_64
+/*
+ * int {rdmsr,wrmsr}_safe_regs(u32 gprs[8]);
+ *
+ * reg layout: u32 gprs[eax, ecx, edx, ebx, esp, ebp, esi, edi]
+ *
+ */
+.macro op_safe_regs op
+SYM_FUNC_START(\op\()_safe_regs)
+ pushq %rbx
+ pushq %r12
+ movq %rdi, %r10 /* Save pointer */
+ xorl %r11d, %r11d /* Return value */
+ movl (%rdi), %eax
+ movl 4(%rdi), %ecx
+ movl 8(%rdi), %edx
+ movl 12(%rdi), %ebx
+ movl 20(%rdi), %r12d
+ movl 24(%rdi), %esi
+ movl 28(%rdi), %edi
+1: \op
+2: movl %eax, (%r10)
+ movl %r11d, %eax /* Return value */
+ movl %ecx, 4(%r10)
+ movl %edx, 8(%r10)
+ movl %ebx, 12(%r10)
+ movl %r12d, 20(%r10)
+ movl %esi, 24(%r10)
+ movl %edi, 28(%r10)
+ popq %r12
+ popq %rbx
+ RET
+3:
+ movl $-EIO, %r11d
+ jmp 2b
+
+ _ASM_EXTABLE(1b, 3b)
+SYM_FUNC_END(\op\()_safe_regs)
+.endm
+
+#else /* X86_32 */
+
+.macro op_safe_regs op
+SYM_FUNC_START(\op\()_safe_regs)
+ pushl %ebx
+ pushl %ebp
+ pushl %esi
+ pushl %edi
+ pushl $0 /* Return value */
+ pushl %eax
+ movl 4(%eax), %ecx
+ movl 8(%eax), %edx
+ movl 12(%eax), %ebx
+ movl 20(%eax), %ebp
+ movl 24(%eax), %esi
+ movl 28(%eax), %edi
+ movl (%eax), %eax
+1: \op
+2: pushl %eax
+ movl 4(%esp), %eax
+ popl (%eax)
+ addl $4, %esp
+ movl %ecx, 4(%eax)
+ movl %edx, 8(%eax)
+ movl %ebx, 12(%eax)
+ movl %ebp, 20(%eax)
+ movl %esi, 24(%eax)
+ movl %edi, 28(%eax)
+ popl %eax
+ popl %edi
+ popl %esi
+ popl %ebp
+ popl %ebx
+ RET
+3:
+ movl $-EIO, 4(%esp)
+ jmp 2b
+
+ _ASM_EXTABLE(1b, 3b)
+SYM_FUNC_END(\op\()_safe_regs)
+.endm
+
+#endif
+
+op_safe_regs rdmsr
+op_safe_regs wrmsr
+
diff --git a/arch/x86/lib/msr-smp.c b/arch/x86/lib/msr-smp.c
new file mode 100644
index 0000000000..40bbe56bde
--- /dev/null
+++ b/arch/x86/lib/msr-smp.c
@@ -0,0 +1,279 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/export.h>
+#include <linux/preempt.h>
+#include <linux/smp.h>
+#include <linux/completion.h>
+#include <asm/msr.h>
+
+static void __rdmsr_on_cpu(void *info)
+{
+ struct msr_info *rv = info;
+ struct msr *reg;
+ int this_cpu = raw_smp_processor_id();
+
+ if (rv->msrs)
+ reg = per_cpu_ptr(rv->msrs, this_cpu);
+ else
+ reg = &rv->reg;
+
+ rdmsr(rv->msr_no, reg->l, reg->h);
+}
+
+static void __wrmsr_on_cpu(void *info)
+{
+ struct msr_info *rv = info;
+ struct msr *reg;
+ int this_cpu = raw_smp_processor_id();
+
+ if (rv->msrs)
+ reg = per_cpu_ptr(rv->msrs, this_cpu);
+ else
+ reg = &rv->reg;
+
+ wrmsr(rv->msr_no, reg->l, reg->h);
+}
+
+int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
+{
+ int err;
+ struct msr_info rv;
+
+ memset(&rv, 0, sizeof(rv));
+
+ rv.msr_no = msr_no;
+ err = smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 1);
+ *l = rv.reg.l;
+ *h = rv.reg.h;
+
+ return err;
+}
+EXPORT_SYMBOL(rdmsr_on_cpu);
+
+int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
+{
+ int err;
+ struct msr_info rv;
+
+ memset(&rv, 0, sizeof(rv));
+
+ rv.msr_no = msr_no;
+ err = smp_call_function_single(cpu, __rdmsr_on_cpu, &rv, 1);
+ *q = rv.reg.q;
+
+ return err;
+}
+EXPORT_SYMBOL(rdmsrl_on_cpu);
+
+int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
+{
+ int err;
+ struct msr_info rv;
+
+ memset(&rv, 0, sizeof(rv));
+
+ rv.msr_no = msr_no;
+ rv.reg.l = l;
+ rv.reg.h = h;
+ err = smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 1);
+
+ return err;
+}
+EXPORT_SYMBOL(wrmsr_on_cpu);
+
+int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
+{
+ int err;
+ struct msr_info rv;
+
+ memset(&rv, 0, sizeof(rv));
+
+ rv.msr_no = msr_no;
+ rv.reg.q = q;
+
+ err = smp_call_function_single(cpu, __wrmsr_on_cpu, &rv, 1);
+
+ return err;
+}
+EXPORT_SYMBOL(wrmsrl_on_cpu);
+
+static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no,
+ struct msr *msrs,
+ void (*msr_func) (void *info))
+{
+ struct msr_info rv;
+ int this_cpu;
+
+ memset(&rv, 0, sizeof(rv));
+
+ rv.msrs = msrs;
+ rv.msr_no = msr_no;
+
+ this_cpu = get_cpu();
+
+ if (cpumask_test_cpu(this_cpu, mask))
+ msr_func(&rv);
+
+ smp_call_function_many(mask, msr_func, &rv, 1);
+ put_cpu();
+}
+
+/* rdmsr on a bunch of CPUs
+ *
+ * @mask: which CPUs
+ * @msr_no: which MSR
+ * @msrs: array of MSR values
+ *
+ */
+void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs)
+{
+ __rwmsr_on_cpus(mask, msr_no, msrs, __rdmsr_on_cpu);
+}
+EXPORT_SYMBOL(rdmsr_on_cpus);
+
+/*
+ * wrmsr on a bunch of CPUs
+ *
+ * @mask: which CPUs
+ * @msr_no: which MSR
+ * @msrs: array of MSR values
+ *
+ */
+void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs)
+{
+ __rwmsr_on_cpus(mask, msr_no, msrs, __wrmsr_on_cpu);
+}
+EXPORT_SYMBOL(wrmsr_on_cpus);
+
+struct msr_info_completion {
+ struct msr_info msr;
+ struct completion done;
+};
+
+/* These "safe" variants are slower and should be used when the target MSR
+ may not actually exist. */
+static void __rdmsr_safe_on_cpu(void *info)
+{
+ struct msr_info_completion *rv = info;
+
+ rv->msr.err = rdmsr_safe(rv->msr.msr_no, &rv->msr.reg.l, &rv->msr.reg.h);
+ complete(&rv->done);
+}
+
+static void __wrmsr_safe_on_cpu(void *info)
+{
+ struct msr_info *rv = info;
+
+ rv->err = wrmsr_safe(rv->msr_no, rv->reg.l, rv->reg.h);
+}
+
+int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
+{
+ struct msr_info_completion rv;
+ call_single_data_t csd;
+ int err;
+
+ INIT_CSD(&csd, __rdmsr_safe_on_cpu, &rv);
+
+ memset(&rv, 0, sizeof(rv));
+ init_completion(&rv.done);
+ rv.msr.msr_no = msr_no;
+
+ err = smp_call_function_single_async(cpu, &csd);
+ if (!err) {
+ wait_for_completion(&rv.done);
+ err = rv.msr.err;
+ }
+ *l = rv.msr.reg.l;
+ *h = rv.msr.reg.h;
+
+ return err;
+}
+EXPORT_SYMBOL(rdmsr_safe_on_cpu);
+
+int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
+{
+ int err;
+ struct msr_info rv;
+
+ memset(&rv, 0, sizeof(rv));
+
+ rv.msr_no = msr_no;
+ rv.reg.l = l;
+ rv.reg.h = h;
+ err = smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 1);
+
+ return err ? err : rv.err;
+}
+EXPORT_SYMBOL(wrmsr_safe_on_cpu);
+
+int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
+{
+ int err;
+ struct msr_info rv;
+
+ memset(&rv, 0, sizeof(rv));
+
+ rv.msr_no = msr_no;
+ rv.reg.q = q;
+
+ err = smp_call_function_single(cpu, __wrmsr_safe_on_cpu, &rv, 1);
+
+ return err ? err : rv.err;
+}
+EXPORT_SYMBOL(wrmsrl_safe_on_cpu);
+
+int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
+{
+ u32 low, high;
+ int err;
+
+ err = rdmsr_safe_on_cpu(cpu, msr_no, &low, &high);
+ *q = (u64)high << 32 | low;
+
+ return err;
+}
+EXPORT_SYMBOL(rdmsrl_safe_on_cpu);
+
+/*
+ * These variants are significantly slower, but allows control over
+ * the entire 32-bit GPR set.
+ */
+static void __rdmsr_safe_regs_on_cpu(void *info)
+{
+ struct msr_regs_info *rv = info;
+
+ rv->err = rdmsr_safe_regs(rv->regs);
+}
+
+static void __wrmsr_safe_regs_on_cpu(void *info)
+{
+ struct msr_regs_info *rv = info;
+
+ rv->err = wrmsr_safe_regs(rv->regs);
+}
+
+int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8])
+{
+ int err;
+ struct msr_regs_info rv;
+
+ rv.regs = regs;
+ rv.err = -EIO;
+ err = smp_call_function_single(cpu, __rdmsr_safe_regs_on_cpu, &rv, 1);
+
+ return err ? err : rv.err;
+}
+EXPORT_SYMBOL(rdmsr_safe_regs_on_cpu);
+
+int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8])
+{
+ int err;
+ struct msr_regs_info rv;
+
+ rv.regs = regs;
+ rv.err = -EIO;
+ err = smp_call_function_single(cpu, __wrmsr_safe_regs_on_cpu, &rv, 1);
+
+ return err ? err : rv.err;
+}
+EXPORT_SYMBOL(wrmsr_safe_regs_on_cpu);
diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c
new file mode 100644
index 0000000000..47fd9bd6b9
--- /dev/null
+++ b/arch/x86/lib/msr.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/export.h>
+#include <linux/percpu.h>
+#include <linux/preempt.h>
+#include <asm/msr.h>
+#define CREATE_TRACE_POINTS
+#include <asm/msr-trace.h>
+
+struct msr *msrs_alloc(void)
+{
+ struct msr *msrs = NULL;
+
+ msrs = alloc_percpu(struct msr);
+ if (!msrs) {
+ pr_warn("%s: error allocating msrs\n", __func__);
+ return NULL;
+ }
+
+ return msrs;
+}
+EXPORT_SYMBOL(msrs_alloc);
+
+void msrs_free(struct msr *msrs)
+{
+ free_percpu(msrs);
+}
+EXPORT_SYMBOL(msrs_free);
+
+/**
+ * msr_read - Read an MSR with error handling
+ * @msr: MSR to read
+ * @m: value to read into
+ *
+ * It returns read data only on success, otherwise it doesn't change the output
+ * argument @m.
+ *
+ * Return: %0 for success, otherwise an error code
+ */
+static int msr_read(u32 msr, struct msr *m)
+{
+ int err;
+ u64 val;
+
+ err = rdmsrl_safe(msr, &val);
+ if (!err)
+ m->q = val;
+
+ return err;
+}
+
+/**
+ * msr_write - Write an MSR with error handling
+ *
+ * @msr: MSR to write
+ * @m: value to write
+ *
+ * Return: %0 for success, otherwise an error code
+ */
+static int msr_write(u32 msr, struct msr *m)
+{
+ return wrmsrl_safe(msr, m->q);
+}
+
+static inline int __flip_bit(u32 msr, u8 bit, bool set)
+{
+ struct msr m, m1;
+ int err = -EINVAL;
+
+ if (bit > 63)
+ return err;
+
+ err = msr_read(msr, &m);
+ if (err)
+ return err;
+
+ m1 = m;
+ if (set)
+ m1.q |= BIT_64(bit);
+ else
+ m1.q &= ~BIT_64(bit);
+
+ if (m1.q == m.q)
+ return 0;
+
+ err = msr_write(msr, &m1);
+ if (err)
+ return err;
+
+ return 1;
+}
+
+/**
+ * msr_set_bit - Set @bit in a MSR @msr.
+ * @msr: MSR to write
+ * @bit: bit number to set
+ *
+ * Return:
+ * * < 0: An error was encountered.
+ * * = 0: Bit was already set.
+ * * > 0: Hardware accepted the MSR write.
+ */
+int msr_set_bit(u32 msr, u8 bit)
+{
+ return __flip_bit(msr, bit, true);
+}
+
+/**
+ * msr_clear_bit - Clear @bit in a MSR @msr.
+ * @msr: MSR to write
+ * @bit: bit number to clear
+ *
+ * Return:
+ * * < 0: An error was encountered.
+ * * = 0: Bit was already cleared.
+ * * > 0: Hardware accepted the MSR write.
+ */
+int msr_clear_bit(u32 msr, u8 bit)
+{
+ return __flip_bit(msr, bit, false);
+}
+
+#ifdef CONFIG_TRACEPOINTS
+void do_trace_write_msr(unsigned int 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)
+{
+ 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)
+{
+ trace_rdpmc(counter, val, failed);
+}
+EXPORT_SYMBOL(do_trace_rdpmc);
+EXPORT_TRACEPOINT_SYMBOL(rdpmc);
+
+#endif
diff --git a/arch/x86/lib/pc-conf-reg.c b/arch/x86/lib/pc-conf-reg.c
new file mode 100644
index 0000000000..febb52749e
--- /dev/null
+++ b/arch/x86/lib/pc-conf-reg.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Support for the configuration register space at port I/O locations
+ * 0x22 and 0x23 variously used by PC architectures, e.g. the MP Spec,
+ * Cyrix CPUs, numerous chipsets. As the space is indirectly addressed
+ * it may have to be protected with a spinlock, depending on the context.
+ */
+
+#include <linux/spinlock.h>
+
+#include <asm/pc-conf-reg.h>
+
+DEFINE_RAW_SPINLOCK(pc_conf_lock);
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
new file mode 100644
index 0000000000..235bbda6fc
--- /dev/null
+++ b/arch/x86/lib/putuser.S
@@ -0,0 +1,148 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * __put_user functions.
+ *
+ * (C) Copyright 2005 Linus Torvalds
+ * (C) Copyright 2005 Andi Kleen
+ * (C) Copyright 2008 Glauber Costa
+ *
+ * These functions have a non-standard call interface
+ * to make them more efficient, especially as they
+ * return an error value in addition to the "real"
+ * return value.
+ */
+#include <linux/linkage.h>
+#include <asm/thread_info.h>
+#include <asm/errno.h>
+#include <asm/asm.h>
+#include <asm/smap.h>
+#include <asm/export.h>
+
+
+/*
+ * __put_user_X
+ *
+ * Inputs: %eax[:%edx] contains the data
+ * %ecx contains the address
+ *
+ * Outputs: %ecx is error code (0 or -EFAULT)
+ *
+ * Clobbers: %ebx needed for task pointer
+ *
+ * These functions should not modify any other registers,
+ * as they get called from within inline assembly.
+ */
+
+.macro check_range size:req
+.if IS_ENABLED(CONFIG_X86_64)
+ mov %rcx, %rbx
+ sar $63, %rbx
+ or %rbx, %rcx
+.else
+ cmp $TASK_SIZE_MAX-\size+1, %ecx
+ jae .Lbad_put_user
+.endif
+.endm
+
+.text
+SYM_FUNC_START(__put_user_1)
+ check_range size=1
+ ASM_STAC
+1: movb %al,(%_ASM_CX)
+ xor %ecx,%ecx
+ ASM_CLAC
+ RET
+SYM_FUNC_END(__put_user_1)
+EXPORT_SYMBOL(__put_user_1)
+
+SYM_FUNC_START(__put_user_nocheck_1)
+ ASM_STAC
+2: movb %al,(%_ASM_CX)
+ xor %ecx,%ecx
+ ASM_CLAC
+ RET
+SYM_FUNC_END(__put_user_nocheck_1)
+EXPORT_SYMBOL(__put_user_nocheck_1)
+
+SYM_FUNC_START(__put_user_2)
+ check_range size=2
+ ASM_STAC
+3: movw %ax,(%_ASM_CX)
+ xor %ecx,%ecx
+ ASM_CLAC
+ RET
+SYM_FUNC_END(__put_user_2)
+EXPORT_SYMBOL(__put_user_2)
+
+SYM_FUNC_START(__put_user_nocheck_2)
+ ASM_STAC
+4: movw %ax,(%_ASM_CX)
+ xor %ecx,%ecx
+ ASM_CLAC
+ RET
+SYM_FUNC_END(__put_user_nocheck_2)
+EXPORT_SYMBOL(__put_user_nocheck_2)
+
+SYM_FUNC_START(__put_user_4)
+ check_range size=4
+ ASM_STAC
+5: movl %eax,(%_ASM_CX)
+ xor %ecx,%ecx
+ ASM_CLAC
+ RET
+SYM_FUNC_END(__put_user_4)
+EXPORT_SYMBOL(__put_user_4)
+
+SYM_FUNC_START(__put_user_nocheck_4)
+ ASM_STAC
+6: movl %eax,(%_ASM_CX)
+ xor %ecx,%ecx
+ ASM_CLAC
+ RET
+SYM_FUNC_END(__put_user_nocheck_4)
+EXPORT_SYMBOL(__put_user_nocheck_4)
+
+SYM_FUNC_START(__put_user_8)
+ check_range size=8
+ ASM_STAC
+7: mov %_ASM_AX,(%_ASM_CX)
+#ifdef CONFIG_X86_32
+8: movl %edx,4(%_ASM_CX)
+#endif
+ xor %ecx,%ecx
+ ASM_CLAC
+ RET
+SYM_FUNC_END(__put_user_8)
+EXPORT_SYMBOL(__put_user_8)
+
+SYM_FUNC_START(__put_user_nocheck_8)
+ ASM_STAC
+9: mov %_ASM_AX,(%_ASM_CX)
+#ifdef CONFIG_X86_32
+10: movl %edx,4(%_ASM_CX)
+#endif
+ xor %ecx,%ecx
+ ASM_CLAC
+ RET
+SYM_FUNC_END(__put_user_nocheck_8)
+EXPORT_SYMBOL(__put_user_nocheck_8)
+
+SYM_CODE_START_LOCAL(__put_user_handle_exception)
+ ASM_CLAC
+.Lbad_put_user:
+ movl $-EFAULT,%ecx
+ RET
+SYM_CODE_END(__put_user_handle_exception)
+
+ _ASM_EXTABLE(1b, __put_user_handle_exception)
+ _ASM_EXTABLE(2b, __put_user_handle_exception)
+ _ASM_EXTABLE(3b, __put_user_handle_exception)
+ _ASM_EXTABLE(4b, __put_user_handle_exception)
+ _ASM_EXTABLE(5b, __put_user_handle_exception)
+ _ASM_EXTABLE(6b, __put_user_handle_exception)
+ _ASM_EXTABLE(7b, __put_user_handle_exception)
+ _ASM_EXTABLE(9b, __put_user_handle_exception)
+#ifdef CONFIG_X86_32
+ _ASM_EXTABLE(8b, __put_user_handle_exception)
+ _ASM_EXTABLE(10b, __put_user_handle_exception)
+#endif
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
new file mode 100644
index 0000000000..cd86aeb5fd
--- /dev/null
+++ b/arch/x86/lib/retpoline.S
@@ -0,0 +1,361 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/stringify.h>
+#include <linux/linkage.h>
+#include <asm/dwarf2.h>
+#include <asm/cpufeatures.h>
+#include <asm/alternative.h>
+#include <asm/asm-offsets.h>
+#include <asm/export.h>
+#include <asm/nospec-branch.h>
+#include <asm/unwind_hints.h>
+#include <asm/percpu.h>
+#include <asm/frame.h>
+#include <asm/nops.h>
+
+ .section .text..__x86.indirect_thunk
+
+
+.macro POLINE reg
+ ANNOTATE_INTRA_FUNCTION_CALL
+ call .Ldo_rop_\@
+ int3
+.Ldo_rop_\@:
+ mov %\reg, (%_ASM_SP)
+ UNWIND_HINT_FUNC
+.endm
+
+.macro RETPOLINE reg
+ POLINE \reg
+ RET
+.endm
+
+.macro THUNK reg
+
+ .align RETPOLINE_THUNK_SIZE
+SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL)
+ UNWIND_HINT_UNDEFINED
+ ANNOTATE_NOENDBR
+
+ 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)
+
+.endm
+
+/*
+ * Despite being an assembler file we can't just use .irp here
+ * because __KSYM_DEPS__ only uses the C preprocessor and would
+ * only see one instance of "__x86_indirect_thunk_\reg" rather
+ * than one per register with the correct names. So we do it
+ * the simple and nasty way...
+ *
+ * Worse, you can only have a single EXPORT_SYMBOL per line,
+ * and CPP can't insert newlines, so we have to repeat everything
+ * at least twice.
+ */
+
+#define __EXPORT_THUNK(sym) _ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym)
+
+ .align RETPOLINE_THUNK_SIZE
+SYM_CODE_START(__x86_indirect_thunk_array)
+
+#define GEN(reg) THUNK reg
+#include <asm/GEN-for-each-reg.h>
+#undef GEN
+
+ .align RETPOLINE_THUNK_SIZE
+SYM_CODE_END(__x86_indirect_thunk_array)
+
+#define GEN(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg)
+#include <asm/GEN-for-each-reg.h>
+#undef GEN
+
+#ifdef CONFIG_CALL_DEPTH_TRACKING
+.macro CALL_THUNK reg
+ .align RETPOLINE_THUNK_SIZE
+
+SYM_INNER_LABEL(__x86_indirect_call_thunk_\reg, SYM_L_GLOBAL)
+ UNWIND_HINT_UNDEFINED
+ ANNOTATE_NOENDBR
+
+ CALL_DEPTH_ACCOUNT
+ POLINE \reg
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+.endm
+
+ .align RETPOLINE_THUNK_SIZE
+SYM_CODE_START(__x86_indirect_call_thunk_array)
+
+#define GEN(reg) CALL_THUNK reg
+#include <asm/GEN-for-each-reg.h>
+#undef GEN
+
+ .align RETPOLINE_THUNK_SIZE
+SYM_CODE_END(__x86_indirect_call_thunk_array)
+
+#define GEN(reg) __EXPORT_THUNK(__x86_indirect_call_thunk_ ## reg)
+#include <asm/GEN-for-each-reg.h>
+#undef GEN
+
+.macro JUMP_THUNK reg
+ .align RETPOLINE_THUNK_SIZE
+
+SYM_INNER_LABEL(__x86_indirect_jump_thunk_\reg, SYM_L_GLOBAL)
+ UNWIND_HINT_UNDEFINED
+ ANNOTATE_NOENDBR
+ POLINE \reg
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+.endm
+
+ .align RETPOLINE_THUNK_SIZE
+SYM_CODE_START(__x86_indirect_jump_thunk_array)
+
+#define GEN(reg) JUMP_THUNK reg
+#include <asm/GEN-for-each-reg.h>
+#undef GEN
+
+ .align RETPOLINE_THUNK_SIZE
+SYM_CODE_END(__x86_indirect_jump_thunk_array)
+
+#define GEN(reg) __EXPORT_THUNK(__x86_indirect_jump_thunk_ ## reg)
+#include <asm/GEN-for-each-reg.h>
+#undef GEN
+#endif
+/*
+ * This function name is magical and is used by -mfunction-return=thunk-extern
+ * for the compiler to generate JMPs to it.
+ */
+#ifdef CONFIG_RETHUNK
+
+/*
+ * srso_alias_untrain_ret() and srso_alias_safe_ret() are placed at
+ * special addresses:
+ *
+ * - srso_alias_untrain_ret() is 2M aligned
+ * - srso_alias_safe_ret() is also in the same 2M page but bits 2, 8, 14
+ * and 20 in its virtual address are set (while those bits in the
+ * srso_alias_untrain_ret() function are cleared).
+ *
+ * This guarantees that those two addresses will alias in the branch
+ * target buffer of Zen3/4 generations, leading to any potential
+ * poisoned entries at that BTB slot to get evicted.
+ *
+ * As a result, srso_alias_safe_ret() becomes a safe return.
+ */
+#ifdef CONFIG_CPU_SRSO
+ .section .text..__x86.rethunk_untrain
+
+SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
+ UNWIND_HINT_FUNC
+ ANNOTATE_NOENDBR
+ ASM_NOP2
+ lfence
+ jmp srso_alias_return_thunk
+SYM_FUNC_END(srso_alias_untrain_ret)
+__EXPORT_THUNK(srso_alias_untrain_ret)
+
+ .section .text..__x86.rethunk_safe
+#else
+/* dummy definition for alternatives */
+SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+SYM_FUNC_END(srso_alias_untrain_ret)
+#endif
+
+SYM_START(srso_alias_safe_ret, SYM_L_GLOBAL, SYM_A_NONE)
+ lea 8(%_ASM_SP), %_ASM_SP
+ UNWIND_HINT_FUNC
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+SYM_FUNC_END(srso_alias_safe_ret)
+
+ .section .text..__x86.return_thunk
+
+SYM_CODE_START(srso_alias_return_thunk)
+ UNWIND_HINT_FUNC
+ ANNOTATE_NOENDBR
+ call srso_alias_safe_ret
+ ud2
+SYM_CODE_END(srso_alias_return_thunk)
+
+/*
+ * Some generic notes on the untraining sequences:
+ *
+ * They are interchangeable when it comes to flushing potentially wrong
+ * RET predictions from the BTB.
+ *
+ * The SRSO Zen1/2 (MOVABS) untraining sequence is longer than the
+ * Retbleed sequence because the return sequence done there
+ * (srso_safe_ret()) is longer and the return sequence must fully nest
+ * (end before) the untraining sequence. Therefore, the untraining
+ * sequence must fully overlap the return sequence.
+ *
+ * Regarding alignment - the instructions which need to be untrained,
+ * must all start at a cacheline boundary for Zen1/2 generations. That
+ * is, instruction sequences starting at srso_safe_ret() and
+ * the respective instruction sequences at retbleed_return_thunk()
+ * must start at a cacheline boundary.
+ */
+
+/*
+ * Safety details here pertain to the AMD Zen{1,2} microarchitecture:
+ * 1) The RET at retbleed_return_thunk must be on a 64 byte boundary, for
+ * alignment within the BTB.
+ * 2) The instruction at retbleed_untrain_ret must contain, and not
+ * end with, the 0xc3 byte of the RET.
+ * 3) STIBP must be enabled, or SMT disabled, to prevent the sibling thread
+ * from re-poisioning the BTB prediction.
+ */
+ .align 64
+ .skip 64 - (retbleed_return_thunk - retbleed_untrain_ret), 0xcc
+SYM_START(retbleed_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
+ ANNOTATE_NOENDBR
+ /*
+ * As executed from retbleed_untrain_ret, this is:
+ *
+ * TEST $0xcc, %bl
+ * LFENCE
+ * JMP retbleed_return_thunk
+ *
+ * Executing the TEST instruction has a side effect of evicting any BTB
+ * prediction (potentially attacker controlled) attached to the RET, as
+ * retbleed_return_thunk + 1 isn't an instruction boundary at the moment.
+ */
+ .byte 0xf6
+
+ /*
+ * As executed from retbleed_return_thunk, this is a plain RET.
+ *
+ * As part of the TEST above, RET is the ModRM byte, and INT3 the imm8.
+ *
+ * We subsequently jump backwards and architecturally execute the RET.
+ * This creates a correct BTB prediction (type=ret), but in the
+ * meantime we suffer Straight Line Speculation (because the type was
+ * no branch) which is halted by the INT3.
+ *
+ * With SMT enabled and STIBP active, a sibling thread cannot poison
+ * RET's prediction to a type of its choice, but can evict the
+ * prediction due to competitive sharing. If the prediction is
+ * evicted, retbleed_return_thunk will suffer Straight Line Speculation
+ * which will be contained safely by the INT3.
+ */
+SYM_INNER_LABEL(retbleed_return_thunk, SYM_L_GLOBAL)
+ ret
+ int3
+SYM_CODE_END(retbleed_return_thunk)
+
+ /*
+ * Ensure the TEST decoding / BTB invalidation is complete.
+ */
+ lfence
+
+ /*
+ * Jump back and execute the RET in the middle of the TEST instruction.
+ * INT3 is for SLS protection.
+ */
+ jmp retbleed_return_thunk
+ int3
+SYM_FUNC_END(retbleed_untrain_ret)
+__EXPORT_THUNK(retbleed_untrain_ret)
+
+/*
+ * SRSO untraining sequence for Zen1/2, similar to retbleed_untrain_ret()
+ * above. On kernel entry, srso_untrain_ret() is executed which is a
+ *
+ * movabs $0xccccc30824648d48,%rax
+ *
+ * and when the return thunk executes the inner label srso_safe_ret()
+ * later, it is a stack manipulation and a RET which is mispredicted and
+ * thus a "safe" one to use.
+ */
+ .align 64
+ .skip 64 - (srso_safe_ret - srso_untrain_ret), 0xcc
+SYM_START(srso_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
+ ANNOTATE_NOENDBR
+ .byte 0x48, 0xb8
+
+/*
+ * This forces the function return instruction to speculate into a trap
+ * (UD2 in srso_return_thunk() below). This RET will then mispredict
+ * and execution will continue at the return site read from the top of
+ * the stack.
+ */
+SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL)
+ lea 8(%_ASM_SP), %_ASM_SP
+ ret
+ int3
+ int3
+ /* end of movabs */
+ lfence
+ call srso_safe_ret
+ ud2
+SYM_CODE_END(srso_safe_ret)
+SYM_FUNC_END(srso_untrain_ret)
+__EXPORT_THUNK(srso_untrain_ret)
+
+SYM_CODE_START(srso_return_thunk)
+ UNWIND_HINT_FUNC
+ ANNOTATE_NOENDBR
+ call srso_safe_ret
+ ud2
+SYM_CODE_END(srso_return_thunk)
+
+SYM_FUNC_START(entry_untrain_ret)
+ ALTERNATIVE_2 "jmp retbleed_untrain_ret", \
+ "jmp srso_untrain_ret", X86_FEATURE_SRSO, \
+ "jmp srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS
+SYM_FUNC_END(entry_untrain_ret)
+__EXPORT_THUNK(entry_untrain_ret)
+
+SYM_CODE_START(__x86_return_thunk)
+ UNWIND_HINT_FUNC
+ ANNOTATE_NOENDBR
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+SYM_CODE_END(__x86_return_thunk)
+EXPORT_SYMBOL(__x86_return_thunk)
+
+#endif /* CONFIG_RETHUNK */
+
+#ifdef CONFIG_CALL_DEPTH_TRACKING
+
+ .align 64
+SYM_FUNC_START(__x86_return_skl)
+ ANNOTATE_NOENDBR
+ /*
+ * Keep the hotpath in a 16byte I-fetch for the non-debug
+ * case.
+ */
+ CALL_THUNKS_DEBUG_INC_RETS
+ shlq $5, PER_CPU_VAR(pcpu_hot + X86_call_depth)
+ jz 1f
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+1:
+ CALL_THUNKS_DEBUG_INC_STUFFS
+ .rept 16
+ ANNOTATE_INTRA_FUNCTION_CALL
+ call 2f
+ int3
+2:
+ .endr
+ add $(8*16), %rsp
+
+ CREDIT_CALL_DEPTH
+
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+SYM_FUNC_END(__x86_return_skl)
+
+#endif /* CONFIG_CALL_DEPTH_TRACKING */
diff --git a/arch/x86/lib/string_32.c b/arch/x86/lib/string_32.c
new file mode 100644
index 0000000000..53b3f20226
--- /dev/null
+++ b/arch/x86/lib/string_32.c
@@ -0,0 +1,237 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Most of the string-functions are rather heavily hand-optimized,
+ * see especially strsep,strstr,str[c]spn. They should work, but are not
+ * very easy to understand. Everything is done entirely within the register
+ * set, making the functions fast and clean. String instructions have been
+ * used through-out, making for "slightly" unclear code :-)
+ *
+ * AK: On P4 and K7 using non string instruction implementations might be faster
+ * for large memory blocks. But most of them are unlikely to be used on large
+ * strings.
+ */
+
+#define __NO_FORTIFY
+#include <linux/string.h>
+#include <linux/export.h>
+
+#ifdef __HAVE_ARCH_STRCPY
+char *strcpy(char *dest, const char *src)
+{
+ int d0, d1, d2;
+ asm volatile("1:\tlodsb\n\t"
+ "stosb\n\t"
+ "testb %%al,%%al\n\t"
+ "jne 1b"
+ : "=&S" (d0), "=&D" (d1), "=&a" (d2)
+ : "0" (src), "1" (dest) : "memory");
+ return dest;
+}
+EXPORT_SYMBOL(strcpy);
+#endif
+
+#ifdef __HAVE_ARCH_STRNCPY
+char *strncpy(char *dest, const char *src, size_t count)
+{
+ int d0, d1, d2, d3;
+ asm volatile("1:\tdecl %2\n\t"
+ "js 2f\n\t"
+ "lodsb\n\t"
+ "stosb\n\t"
+ "testb %%al,%%al\n\t"
+ "jne 1b\n\t"
+ "rep\n\t"
+ "stosb\n"
+ "2:"
+ : "=&S" (d0), "=&D" (d1), "=&c" (d2), "=&a" (d3)
+ : "0" (src), "1" (dest), "2" (count) : "memory");
+ return dest;
+}
+EXPORT_SYMBOL(strncpy);
+#endif
+
+#ifdef __HAVE_ARCH_STRCAT
+char *strcat(char *dest, const char *src)
+{
+ int d0, d1, d2, d3;
+ asm volatile("repne\n\t"
+ "scasb\n\t"
+ "decl %1\n"
+ "1:\tlodsb\n\t"
+ "stosb\n\t"
+ "testb %%al,%%al\n\t"
+ "jne 1b"
+ : "=&S" (d0), "=&D" (d1), "=&a" (d2), "=&c" (d3)
+ : "0" (src), "1" (dest), "2" (0), "3" (0xffffffffu) : "memory");
+ return dest;
+}
+EXPORT_SYMBOL(strcat);
+#endif
+
+#ifdef __HAVE_ARCH_STRNCAT
+char *strncat(char *dest, const char *src, size_t count)
+{
+ int d0, d1, d2, d3;
+ asm volatile("repne\n\t"
+ "scasb\n\t"
+ "decl %1\n\t"
+ "movl %8,%3\n"
+ "1:\tdecl %3\n\t"
+ "js 2f\n\t"
+ "lodsb\n\t"
+ "stosb\n\t"
+ "testb %%al,%%al\n\t"
+ "jne 1b\n"
+ "2:\txorl %2,%2\n\t"
+ "stosb"
+ : "=&S" (d0), "=&D" (d1), "=&a" (d2), "=&c" (d3)
+ : "0" (src), "1" (dest), "2" (0), "3" (0xffffffffu), "g" (count)
+ : "memory");
+ return dest;
+}
+EXPORT_SYMBOL(strncat);
+#endif
+
+#ifdef __HAVE_ARCH_STRCMP
+int strcmp(const char *cs, const char *ct)
+{
+ int d0, d1;
+ int res;
+ asm volatile("1:\tlodsb\n\t"
+ "scasb\n\t"
+ "jne 2f\n\t"
+ "testb %%al,%%al\n\t"
+ "jne 1b\n\t"
+ "xorl %%eax,%%eax\n\t"
+ "jmp 3f\n"
+ "2:\tsbbl %%eax,%%eax\n\t"
+ "orb $1,%%al\n"
+ "3:"
+ : "=a" (res), "=&S" (d0), "=&D" (d1)
+ : "1" (cs), "2" (ct)
+ : "memory");
+ return res;
+}
+EXPORT_SYMBOL(strcmp);
+#endif
+
+#ifdef __HAVE_ARCH_STRNCMP
+int strncmp(const char *cs, const char *ct, size_t count)
+{
+ int res;
+ int d0, d1, d2;
+ asm volatile("1:\tdecl %3\n\t"
+ "js 2f\n\t"
+ "lodsb\n\t"
+ "scasb\n\t"
+ "jne 3f\n\t"
+ "testb %%al,%%al\n\t"
+ "jne 1b\n"
+ "2:\txorl %%eax,%%eax\n\t"
+ "jmp 4f\n"
+ "3:\tsbbl %%eax,%%eax\n\t"
+ "orb $1,%%al\n"
+ "4:"
+ : "=a" (res), "=&S" (d0), "=&D" (d1), "=&c" (d2)
+ : "1" (cs), "2" (ct), "3" (count)
+ : "memory");
+ return res;
+}
+EXPORT_SYMBOL(strncmp);
+#endif
+
+#ifdef __HAVE_ARCH_STRCHR
+char *strchr(const char *s, int c)
+{
+ int d0;
+ char *res;
+ asm volatile("movb %%al,%%ah\n"
+ "1:\tlodsb\n\t"
+ "cmpb %%ah,%%al\n\t"
+ "je 2f\n\t"
+ "testb %%al,%%al\n\t"
+ "jne 1b\n\t"
+ "movl $1,%1\n"
+ "2:\tmovl %1,%0\n\t"
+ "decl %0"
+ : "=a" (res), "=&S" (d0)
+ : "1" (s), "0" (c)
+ : "memory");
+ return res;
+}
+EXPORT_SYMBOL(strchr);
+#endif
+
+#ifdef __HAVE_ARCH_STRLEN
+size_t strlen(const char *s)
+{
+ int d0;
+ size_t res;
+ asm volatile("repne\n\t"
+ "scasb"
+ : "=c" (res), "=&D" (d0)
+ : "1" (s), "a" (0), "0" (0xffffffffu)
+ : "memory");
+ return ~res - 1;
+}
+EXPORT_SYMBOL(strlen);
+#endif
+
+#ifdef __HAVE_ARCH_MEMCHR
+void *memchr(const void *cs, int c, size_t count)
+{
+ int d0;
+ void *res;
+ if (!count)
+ return NULL;
+ asm volatile("repne\n\t"
+ "scasb\n\t"
+ "je 1f\n\t"
+ "movl $1,%0\n"
+ "1:\tdecl %0"
+ : "=D" (res), "=&c" (d0)
+ : "a" (c), "0" (cs), "1" (count)
+ : "memory");
+ return res;
+}
+EXPORT_SYMBOL(memchr);
+#endif
+
+#ifdef __HAVE_ARCH_MEMSCAN
+void *memscan(void *addr, int c, size_t size)
+{
+ if (!size)
+ return addr;
+ asm volatile("repnz; scasb\n\t"
+ "jnz 1f\n\t"
+ "dec %%edi\n"
+ "1:"
+ : "=D" (addr), "=c" (size)
+ : "0" (addr), "1" (size), "a" (c)
+ : "memory");
+ return addr;
+}
+EXPORT_SYMBOL(memscan);
+#endif
+
+#ifdef __HAVE_ARCH_STRNLEN
+size_t strnlen(const char *s, size_t count)
+{
+ int d0;
+ int res;
+ asm volatile("movl %2,%0\n\t"
+ "jmp 2f\n"
+ "1:\tcmpb $0,(%0)\n\t"
+ "je 3f\n\t"
+ "incl %0\n"
+ "2:\tdecl %1\n\t"
+ "cmpl $-1,%1\n\t"
+ "jne 1b\n"
+ "3:\tsubl %2,%0"
+ : "=a" (res), "=&d" (d0)
+ : "c" (s), "1" (count)
+ : "memory");
+ return res;
+}
+EXPORT_SYMBOL(strnlen);
+#endif
diff --git a/arch/x86/lib/strstr_32.c b/arch/x86/lib/strstr_32.c
new file mode 100644
index 0000000000..38f37df056
--- /dev/null
+++ b/arch/x86/lib/strstr_32.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/string.h>
+#include <linux/export.h>
+
+char *strstr(const char *cs, const char *ct)
+{
+int d0, d1;
+register char *__res;
+__asm__ __volatile__(
+ "movl %6,%%edi\n\t"
+ "repne\n\t"
+ "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"
+ "je 2f\n\t" /* also works for empty string, see above */
+ "xchgl %%eax,%%esi\n\t"
+ "incl %%esi\n\t"
+ "cmpb $0,-1(%%eax)\n\t"
+ "jne 1b\n\t"
+ "xorl %%eax,%%eax\n\t"
+ "2:"
+ : "=a" (__res), "=&c" (d0), "=&S" (d1)
+ : "0" (0), "1" (0xffffffff), "2" (cs), "g" (ct)
+ : "dx", "di");
+return __res;
+}
+EXPORT_SYMBOL(strstr);
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
new file mode 100644
index 0000000000..24b48af274
--- /dev/null
+++ b/arch/x86/lib/usercopy.c
@@ -0,0 +1,55 @@
+/*
+ * User address space access functions.
+ *
+ * For licencing details see kernel-base/COPYING
+ */
+
+#include <linux/uaccess.h>
+#include <linux/export.h>
+#include <linux/instrumented.h>
+
+#include <asm/tlbflush.h>
+
+/**
+ * copy_from_user_nmi - NMI safe copy from user
+ * @to: Pointer to the destination buffer
+ * @from: Pointer to a user space address of the current task
+ * @n: Number of bytes to copy
+ *
+ * Returns: The number of not copied bytes. 0 is success, i.e. all bytes copied
+ *
+ * Contrary to other copy_from_user() variants this function can be called
+ * from NMI context. Despite the name it is not restricted to be called
+ * from NMI context. It is safe to be called from any other context as
+ * well. It disables pagefaults across the copy which means a fault will
+ * abort the copy.
+ *
+ * For NMI context invocations this relies on the nested NMI work to allow
+ * atomic faults from the NMI path; the nested NMI paths are careful to
+ * preserve CR2.
+ */
+unsigned long
+copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
+{
+ unsigned long ret;
+
+ if (!__access_ok(from, n))
+ return n;
+
+ if (!nmi_uaccess_okay())
+ return n;
+
+ /*
+ * Even though this function is typically called from NMI/IRQ context
+ * disable pagefaults so that its behaviour is consistent even when
+ * called from other contexts.
+ */
+ pagefault_disable();
+ instrument_copy_from_user_before(to, from, n);
+ ret = raw_copy_from_user(to, from, n);
+ instrument_copy_from_user_after(to, from, n, ret);
+ pagefault_enable();
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(copy_from_user_nmi);
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
new file mode 100644
index 0000000000..422257c350
--- /dev/null
+++ b/arch/x86/lib/usercopy_32.c
@@ -0,0 +1,340 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * User address space access functions.
+ * The non inlined parts of asm-i386/uaccess.h are here.
+ *
+ * Copyright 1997 Andi Kleen <ak@muc.de>
+ * Copyright 1997 Linus Torvalds
+ */
+#include <linux/export.h>
+#include <linux/uaccess.h>
+#include <asm/asm.h>
+
+#ifdef CONFIG_X86_INTEL_USERCOPY
+/*
+ * Alignment at which movsl is preferred for bulk memory copies.
+ */
+struct movsl_mask movsl_mask __read_mostly;
+#endif
+
+static inline int __movsl_is_ok(unsigned long a1, unsigned long a2, unsigned long n)
+{
+#ifdef CONFIG_X86_INTEL_USERCOPY
+ if (n >= 64 && ((a1 ^ a2) & movsl_mask.mask))
+ return 0;
+#endif
+ return 1;
+}
+#define movsl_is_ok(a1, a2, n) \
+ __movsl_is_ok((unsigned long)(a1), (unsigned long)(a2), (n))
+
+/*
+ * Zero Userspace
+ */
+
+#define __do_clear_user(addr,size) \
+do { \
+ int __d0; \
+ might_fault(); \
+ __asm__ __volatile__( \
+ ASM_STAC "\n" \
+ "0: rep; stosl\n" \
+ " movl %2,%0\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) \
+ : "=&c"(size), "=&D" (__d0) \
+ : "r"(size & 3), "0"(size / 4), "1"(addr), "a"(0)); \
+} while (0)
+
+/**
+ * clear_user - Zero a block of memory in user space.
+ * @to: Destination address, in user space.
+ * @n: Number of bytes to zero.
+ *
+ * Zero a block of memory in user space.
+ *
+ * Return: number of bytes that could not be cleared.
+ * On success, this will be zero.
+ */
+unsigned long
+clear_user(void __user *to, unsigned long n)
+{
+ might_fault();
+ if (access_ok(to, n))
+ __do_clear_user(to, n);
+ return n;
+}
+EXPORT_SYMBOL(clear_user);
+
+/**
+ * __clear_user - Zero a block of memory in user space, with less checking.
+ * @to: Destination address, in user space.
+ * @n: Number of bytes to zero.
+ *
+ * Zero a block of memory in user space. Caller must check
+ * the specified block with access_ok() before calling this function.
+ *
+ * Return: number of bytes that could not be cleared.
+ * On success, this will be zero.
+ */
+unsigned long
+__clear_user(void __user *to, unsigned long n)
+{
+ __do_clear_user(to, n);
+ return n;
+}
+EXPORT_SYMBOL(__clear_user);
+
+#ifdef CONFIG_X86_INTEL_USERCOPY
+static unsigned long
+__copy_user_intel(void __user *to, const void *from, unsigned long size)
+{
+ int d0, d1;
+ __asm__ __volatile__(
+ " .align 2,0x90\n"
+ "1: movl 32(%4), %%eax\n"
+ " cmpl $67, %0\n"
+ " jbe 3f\n"
+ "2: movl 64(%4), %%eax\n"
+ " .align 2,0x90\n"
+ "3: movl 0(%4), %%eax\n"
+ "4: movl 4(%4), %%edx\n"
+ "5: movl %%eax, 0(%3)\n"
+ "6: movl %%edx, 4(%3)\n"
+ "7: movl 8(%4), %%eax\n"
+ "8: movl 12(%4),%%edx\n"
+ "9: movl %%eax, 8(%3)\n"
+ "10: movl %%edx, 12(%3)\n"
+ "11: movl 16(%4), %%eax\n"
+ "12: movl 20(%4), %%edx\n"
+ "13: movl %%eax, 16(%3)\n"
+ "14: movl %%edx, 20(%3)\n"
+ "15: movl 24(%4), %%eax\n"
+ "16: movl 28(%4), %%edx\n"
+ "17: movl %%eax, 24(%3)\n"
+ "18: movl %%edx, 28(%3)\n"
+ "19: movl 32(%4), %%eax\n"
+ "20: movl 36(%4), %%edx\n"
+ "21: movl %%eax, 32(%3)\n"
+ "22: movl %%edx, 36(%3)\n"
+ "23: movl 40(%4), %%eax\n"
+ "24: movl 44(%4), %%edx\n"
+ "25: movl %%eax, 40(%3)\n"
+ "26: movl %%edx, 44(%3)\n"
+ "27: movl 48(%4), %%eax\n"
+ "28: movl 52(%4), %%edx\n"
+ "29: movl %%eax, 48(%3)\n"
+ "30: movl %%edx, 52(%3)\n"
+ "31: movl 56(%4), %%eax\n"
+ "32: movl 60(%4), %%edx\n"
+ "33: movl %%eax, 56(%3)\n"
+ "34: movl %%edx, 60(%3)\n"
+ " addl $-64, %0\n"
+ " addl $64, %4\n"
+ " addl $64, %3\n"
+ " cmpl $63, %0\n"
+ " ja 1b\n"
+ "35: movl %0, %%eax\n"
+ " shrl $2, %0\n"
+ " andl $3, %%eax\n"
+ " cld\n"
+ "99: rep; movsl\n"
+ "36: movl %%eax, %0\n"
+ "37: rep; movsb\n"
+ "100:\n"
+ _ASM_EXTABLE_UA(1b, 100b)
+ _ASM_EXTABLE_UA(2b, 100b)
+ _ASM_EXTABLE_UA(3b, 100b)
+ _ASM_EXTABLE_UA(4b, 100b)
+ _ASM_EXTABLE_UA(5b, 100b)
+ _ASM_EXTABLE_UA(6b, 100b)
+ _ASM_EXTABLE_UA(7b, 100b)
+ _ASM_EXTABLE_UA(8b, 100b)
+ _ASM_EXTABLE_UA(9b, 100b)
+ _ASM_EXTABLE_UA(10b, 100b)
+ _ASM_EXTABLE_UA(11b, 100b)
+ _ASM_EXTABLE_UA(12b, 100b)
+ _ASM_EXTABLE_UA(13b, 100b)
+ _ASM_EXTABLE_UA(14b, 100b)
+ _ASM_EXTABLE_UA(15b, 100b)
+ _ASM_EXTABLE_UA(16b, 100b)
+ _ASM_EXTABLE_UA(17b, 100b)
+ _ASM_EXTABLE_UA(18b, 100b)
+ _ASM_EXTABLE_UA(19b, 100b)
+ _ASM_EXTABLE_UA(20b, 100b)
+ _ASM_EXTABLE_UA(21b, 100b)
+ _ASM_EXTABLE_UA(22b, 100b)
+ _ASM_EXTABLE_UA(23b, 100b)
+ _ASM_EXTABLE_UA(24b, 100b)
+ _ASM_EXTABLE_UA(25b, 100b)
+ _ASM_EXTABLE_UA(26b, 100b)
+ _ASM_EXTABLE_UA(27b, 100b)
+ _ASM_EXTABLE_UA(28b, 100b)
+ _ASM_EXTABLE_UA(29b, 100b)
+ _ASM_EXTABLE_UA(30b, 100b)
+ _ASM_EXTABLE_UA(31b, 100b)
+ _ASM_EXTABLE_UA(32b, 100b)
+ _ASM_EXTABLE_UA(33b, 100b)
+ _ASM_EXTABLE_UA(34b, 100b)
+ _ASM_EXTABLE_UA(35b, 100b)
+ _ASM_EXTABLE_UA(36b, 100b)
+ _ASM_EXTABLE_UA(37b, 100b)
+ _ASM_EXTABLE_TYPE_REG(99b, 100b, EX_TYPE_UCOPY_LEN4, %%eax)
+ : "=&c"(size), "=&D" (d0), "=&S" (d1)
+ : "1"(to), "2"(from), "0"(size)
+ : "eax", "edx", "memory");
+ return size;
+}
+
+static unsigned long __copy_user_intel_nocache(void *to,
+ const void __user *from, unsigned long size)
+{
+ int d0, d1;
+
+ __asm__ __volatile__(
+ " .align 2,0x90\n"
+ "0: movl 32(%4), %%eax\n"
+ " cmpl $67, %0\n"
+ " jbe 2f\n"
+ "1: movl 64(%4), %%eax\n"
+ " .align 2,0x90\n"
+ "2: movl 0(%4), %%eax\n"
+ "21: movl 4(%4), %%edx\n"
+ " movnti %%eax, 0(%3)\n"
+ " movnti %%edx, 4(%3)\n"
+ "3: movl 8(%4), %%eax\n"
+ "31: movl 12(%4),%%edx\n"
+ " movnti %%eax, 8(%3)\n"
+ " movnti %%edx, 12(%3)\n"
+ "4: movl 16(%4), %%eax\n"
+ "41: movl 20(%4), %%edx\n"
+ " movnti %%eax, 16(%3)\n"
+ " movnti %%edx, 20(%3)\n"
+ "10: movl 24(%4), %%eax\n"
+ "51: movl 28(%4), %%edx\n"
+ " movnti %%eax, 24(%3)\n"
+ " movnti %%edx, 28(%3)\n"
+ "11: movl 32(%4), %%eax\n"
+ "61: movl 36(%4), %%edx\n"
+ " movnti %%eax, 32(%3)\n"
+ " movnti %%edx, 36(%3)\n"
+ "12: movl 40(%4), %%eax\n"
+ "71: movl 44(%4), %%edx\n"
+ " movnti %%eax, 40(%3)\n"
+ " movnti %%edx, 44(%3)\n"
+ "13: movl 48(%4), %%eax\n"
+ "81: movl 52(%4), %%edx\n"
+ " movnti %%eax, 48(%3)\n"
+ " movnti %%edx, 52(%3)\n"
+ "14: movl 56(%4), %%eax\n"
+ "91: movl 60(%4), %%edx\n"
+ " movnti %%eax, 56(%3)\n"
+ " movnti %%edx, 60(%3)\n"
+ " addl $-64, %0\n"
+ " addl $64, %4\n"
+ " addl $64, %3\n"
+ " cmpl $63, %0\n"
+ " ja 0b\n"
+ " sfence \n"
+ "5: movl %0, %%eax\n"
+ " shrl $2, %0\n"
+ " andl $3, %%eax\n"
+ " cld\n"
+ "6: rep; movsl\n"
+ " movl %%eax,%0\n"
+ "7: rep; movsb\n"
+ "8:\n"
+ _ASM_EXTABLE_UA(0b, 8b)
+ _ASM_EXTABLE_UA(1b, 8b)
+ _ASM_EXTABLE_UA(2b, 8b)
+ _ASM_EXTABLE_UA(21b, 8b)
+ _ASM_EXTABLE_UA(3b, 8b)
+ _ASM_EXTABLE_UA(31b, 8b)
+ _ASM_EXTABLE_UA(4b, 8b)
+ _ASM_EXTABLE_UA(41b, 8b)
+ _ASM_EXTABLE_UA(10b, 8b)
+ _ASM_EXTABLE_UA(51b, 8b)
+ _ASM_EXTABLE_UA(11b, 8b)
+ _ASM_EXTABLE_UA(61b, 8b)
+ _ASM_EXTABLE_UA(12b, 8b)
+ _ASM_EXTABLE_UA(71b, 8b)
+ _ASM_EXTABLE_UA(13b, 8b)
+ _ASM_EXTABLE_UA(81b, 8b)
+ _ASM_EXTABLE_UA(14b, 8b)
+ _ASM_EXTABLE_UA(91b, 8b)
+ _ASM_EXTABLE_TYPE_REG(6b, 8b, EX_TYPE_UCOPY_LEN4, %%eax)
+ _ASM_EXTABLE_UA(7b, 8b)
+ : "=&c"(size), "=&D" (d0), "=&S" (d1)
+ : "1"(to), "2"(from), "0"(size)
+ : "eax", "edx", "memory");
+ return size;
+}
+
+#else
+
+/*
+ * Leave these declared but undefined. They should not be any references to
+ * them
+ */
+unsigned long __copy_user_intel(void __user *to, const void *from,
+ unsigned long size);
+#endif /* CONFIG_X86_INTEL_USERCOPY */
+
+/* Generic arbitrary sized copy. */
+#define __copy_user(to, from, size) \
+do { \
+ int __d0, __d1, __d2; \
+ __asm__ __volatile__( \
+ " cmp $7,%0\n" \
+ " jbe 1f\n" \
+ " movl %1,%0\n" \
+ " negl %0\n" \
+ " andl $7,%0\n" \
+ " subl %0,%3\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" \
+ " movl %3,%0\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) \
+ _ASM_EXTABLE_UA(1b, 2b) \
+ : "=&c"(size), "=&D" (__d0), "=&S" (__d1), "=r"(__d2) \
+ : "3"(size), "0"(size), "1"(to), "2"(from) \
+ : "memory"); \
+} while (0)
+
+unsigned long __copy_user_ll(void *to, const void *from, unsigned long n)
+{
+ __uaccess_begin_nospec();
+ if (movsl_is_ok(to, from, n))
+ __copy_user(to, from, n);
+ else
+ n = __copy_user_intel(to, from, n);
+ __uaccess_end();
+ return n;
+}
+EXPORT_SYMBOL(__copy_user_ll);
+
+unsigned long __copy_from_user_ll_nocache_nozero(void *to, const void __user *from,
+ unsigned long n)
+{
+ __uaccess_begin_nospec();
+#ifdef CONFIG_X86_INTEL_USERCOPY
+ if (n > 64 && static_cpu_has(X86_FEATURE_XMM2))
+ n = __copy_user_intel_nocache(to, from, n);
+ else
+ __copy_user(to, from, n);
+#else
+ __copy_user(to, from, n);
+#endif
+ __uaccess_end();
+ return n;
+}
+EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero);
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
new file mode 100644
index 0000000000..e9251b89a9
--- /dev/null
+++ b/arch/x86/lib/usercopy_64.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * User address space access functions.
+ *
+ * Copyright 1997 Andi Kleen <ak@muc.de>
+ * Copyright 1997 Linus Torvalds
+ * Copyright 2002 Andi Kleen <ak@suse.de>
+ */
+#include <linux/export.h>
+#include <linux/uaccess.h>
+#include <linux/highmem.h>
+#include <linux/libnvdimm.h>
+
+/*
+ * Zero Userspace
+ */
+
+#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
+/**
+ * clean_cache_range - write back a cache range with CLWB
+ * @vaddr: virtual start address
+ * @size: number of bytes to write back
+ *
+ * Write back a cache range using the CLWB (cache line write back)
+ * instruction. Note that @size is internally rounded up to be cache
+ * line size aligned.
+ */
+static void clean_cache_range(void *addr, size_t size)
+{
+ u16 x86_clflush_size = boot_cpu_data.x86_clflush_size;
+ unsigned long clflush_mask = x86_clflush_size - 1;
+ void *vend = addr + size;
+ void *p;
+
+ for (p = (void *)((unsigned long)addr & ~clflush_mask);
+ p < vend; p += x86_clflush_size)
+ clwb(p);
+}
+
+void arch_wb_cache_pmem(void *addr, size_t size)
+{
+ clean_cache_range(addr, size);
+}
+EXPORT_SYMBOL_GPL(arch_wb_cache_pmem);
+
+long __copy_user_flushcache(void *dst, const void __user *src, unsigned size)
+{
+ unsigned long flushed, dest = (unsigned long) dst;
+ long rc;
+
+ stac();
+ rc = __copy_user_nocache(dst, src, size);
+ clac();
+
+ /*
+ * __copy_user_nocache() uses non-temporal stores for the bulk
+ * of the transfer, but we need to manually flush if the
+ * transfer is unaligned. A cached memory copy is used when
+ * destination or size is not naturally aligned. That is:
+ * - Require 8-byte alignment when size is 8 bytes or larger.
+ * - Require 4-byte alignment when size is 4 bytes.
+ */
+ if (size < 8) {
+ if (!IS_ALIGNED(dest, 4) || size != 4)
+ clean_cache_range(dst, size);
+ } else {
+ if (!IS_ALIGNED(dest, 8)) {
+ dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);
+ clean_cache_range(dst, 1);
+ }
+
+ flushed = dest - (unsigned long) dst;
+ if (size > flushed && !IS_ALIGNED(size - flushed, 8))
+ clean_cache_range(dst + size - 1, 1);
+ }
+
+ return rc;
+}
+
+void __memcpy_flushcache(void *_dst, const void *_src, size_t size)
+{
+ unsigned long dest = (unsigned long) _dst;
+ unsigned long source = (unsigned long) _src;
+
+ /* cache copy and flush to align dest */
+ if (!IS_ALIGNED(dest, 8)) {
+ size_t len = min_t(size_t, size, ALIGN(dest, 8) - dest);
+
+ memcpy((void *) dest, (void *) source, len);
+ clean_cache_range((void *) dest, len);
+ dest += len;
+ source += len;
+ size -= len;
+ if (!size)
+ return;
+ }
+
+ /* 4x8 movnti loop */
+ while (size >= 32) {
+ asm("movq (%0), %%r8\n"
+ "movq 8(%0), %%r9\n"
+ "movq 16(%0), %%r10\n"
+ "movq 24(%0), %%r11\n"
+ "movnti %%r8, (%1)\n"
+ "movnti %%r9, 8(%1)\n"
+ "movnti %%r10, 16(%1)\n"
+ "movnti %%r11, 24(%1)\n"
+ :: "r" (source), "r" (dest)
+ : "memory", "r8", "r9", "r10", "r11");
+ dest += 32;
+ source += 32;
+ size -= 32;
+ }
+
+ /* 1x8 movnti loop */
+ while (size >= 8) {
+ asm("movq (%0), %%r8\n"
+ "movnti %%r8, (%1)\n"
+ :: "r" (source), "r" (dest)
+ : "memory", "r8");
+ dest += 8;
+ source += 8;
+ size -= 8;
+ }
+
+ /* 1x4 movnti loop */
+ while (size >= 4) {
+ asm("movl (%0), %%r8d\n"
+ "movnti %%r8d, (%1)\n"
+ :: "r" (source), "r" (dest)
+ : "memory", "r8");
+ dest += 4;
+ source += 4;
+ size -= 4;
+ }
+
+ /* cache copy for remaining bytes */
+ if (size) {
+ memcpy((void *) dest, (void *) source, size);
+ clean_cache_range((void *) dest, size);
+ }
+}
+EXPORT_SYMBOL_GPL(__memcpy_flushcache);
+#endif
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
new file mode 100644
index 0000000000..5168ee0360
--- /dev/null
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -0,0 +1,1189 @@
+# x86 Opcode Maps
+#
+# This is (mostly) based on following documentations.
+# - Intel(R) 64 and IA-32 Architectures Software Developer's Manual Vol.2C
+# (#326018-047US, June 2013)
+#
+#<Opcode maps>
+# Table: table-name
+# Referrer: escaped-name
+# AVXcode: avx-code
+# opcode: mnemonic|GrpXXX [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...]
+# (or)
+# opcode: escape # escaped-name
+# EndTable
+#
+# mnemonics that begin with lowercase 'v' accept a VEX or EVEX prefix
+# mnemonics that begin with lowercase 'k' accept a VEX prefix
+#
+#<group maps>
+# GrpTable: GrpXXX
+# reg: mnemonic [operand1[,operand2...]] [(extra1)[,(extra2)...] [| 2nd-mnemonic ...]
+# EndTable
+#
+# AVX Superscripts
+# (ev): this opcode requires EVEX prefix.
+# (evo): this opcode is changed by EVEX prefix (EVEX opcode)
+# (v): this opcode requires VEX prefix.
+# (v1): this opcode only supports 128bit VEX.
+#
+# Last Prefix Superscripts
+# - (66): the last prefix is 0x66
+# - (F3): the last prefix is 0xF3
+# - (F2): the last prefix is 0xF2
+# - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
+# - (66&F2): Both 0x66 and 0xF2 prefixes are specified.
+
+Table: one byte opcode
+Referrer:
+AVXcode:
+# 0x00 - 0x0f
+00: ADD Eb,Gb
+01: ADD Ev,Gv
+02: ADD Gb,Eb
+03: ADD Gv,Ev
+04: ADD AL,Ib
+05: ADD rAX,Iz
+06: PUSH ES (i64)
+07: POP ES (i64)
+08: OR Eb,Gb
+09: OR Ev,Gv
+0a: OR Gb,Eb
+0b: OR Gv,Ev
+0c: OR AL,Ib
+0d: OR rAX,Iz
+0e: PUSH CS (i64)
+0f: escape # 2-byte escape
+# 0x10 - 0x1f
+10: ADC Eb,Gb
+11: ADC Ev,Gv
+12: ADC Gb,Eb
+13: ADC Gv,Ev
+14: ADC AL,Ib
+15: ADC rAX,Iz
+16: PUSH SS (i64)
+17: POP SS (i64)
+18: SBB Eb,Gb
+19: SBB Ev,Gv
+1a: SBB Gb,Eb
+1b: SBB Gv,Ev
+1c: SBB AL,Ib
+1d: SBB rAX,Iz
+1e: PUSH DS (i64)
+1f: POP DS (i64)
+# 0x20 - 0x2f
+20: AND Eb,Gb
+21: AND Ev,Gv
+22: AND Gb,Eb
+23: AND Gv,Ev
+24: AND AL,Ib
+25: AND rAx,Iz
+26: SEG=ES (Prefix)
+27: DAA (i64)
+28: SUB Eb,Gb
+29: SUB Ev,Gv
+2a: SUB Gb,Eb
+2b: SUB Gv,Ev
+2c: SUB AL,Ib
+2d: SUB rAX,Iz
+2e: SEG=CS (Prefix)
+2f: DAS (i64)
+# 0x30 - 0x3f
+30: XOR Eb,Gb
+31: XOR Ev,Gv
+32: XOR Gb,Eb
+33: XOR Gv,Ev
+34: XOR AL,Ib
+35: XOR rAX,Iz
+36: SEG=SS (Prefix)
+37: AAA (i64)
+38: CMP Eb,Gb
+39: CMP Ev,Gv
+3a: CMP Gb,Eb
+3b: CMP Gv,Ev
+3c: CMP AL,Ib
+3d: CMP rAX,Iz
+3e: SEG=DS (Prefix)
+3f: AAS (i64)
+# 0x40 - 0x4f
+40: INC eAX (i64) | REX (o64)
+41: INC eCX (i64) | REX.B (o64)
+42: INC eDX (i64) | REX.X (o64)
+43: INC eBX (i64) | REX.XB (o64)
+44: INC eSP (i64) | REX.R (o64)
+45: INC eBP (i64) | REX.RB (o64)
+46: INC eSI (i64) | REX.RX (o64)
+47: INC eDI (i64) | REX.RXB (o64)
+48: DEC eAX (i64) | REX.W (o64)
+49: DEC eCX (i64) | REX.WB (o64)
+4a: DEC eDX (i64) | REX.WX (o64)
+4b: DEC eBX (i64) | REX.WXB (o64)
+4c: DEC eSP (i64) | REX.WR (o64)
+4d: DEC eBP (i64) | REX.WRB (o64)
+4e: DEC eSI (i64) | REX.WRX (o64)
+4f: DEC eDI (i64) | REX.WRXB (o64)
+# 0x50 - 0x5f
+50: PUSH rAX/r8 (d64)
+51: PUSH rCX/r9 (d64)
+52: PUSH rDX/r10 (d64)
+53: PUSH rBX/r11 (d64)
+54: PUSH rSP/r12 (d64)
+55: PUSH rBP/r13 (d64)
+56: PUSH rSI/r14 (d64)
+57: PUSH rDI/r15 (d64)
+58: POP rAX/r8 (d64)
+59: POP rCX/r9 (d64)
+5a: POP rDX/r10 (d64)
+5b: POP rBX/r11 (d64)
+5c: POP rSP/r12 (d64)
+5d: POP rBP/r13 (d64)
+5e: POP rSI/r14 (d64)
+5f: POP rDI/r15 (d64)
+# 0x60 - 0x6f
+60: PUSHA/PUSHAD (i64)
+61: POPA/POPAD (i64)
+62: BOUND Gv,Ma (i64) | EVEX (Prefix)
+63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64)
+64: SEG=FS (Prefix)
+65: SEG=GS (Prefix)
+66: Operand-Size (Prefix)
+67: Address-Size (Prefix)
+68: PUSH Iz (d64)
+69: IMUL Gv,Ev,Iz
+6a: PUSH Ib (d64)
+6b: IMUL Gv,Ev,Ib
+6c: INS/INSB Yb,DX
+6d: INS/INSW/INSD Yz,DX
+6e: OUTS/OUTSB DX,Xb
+6f: OUTS/OUTSW/OUTSD DX,Xz
+# 0x70 - 0x7f
+70: JO Jb
+71: JNO Jb
+72: JB/JNAE/JC Jb
+73: JNB/JAE/JNC Jb
+74: JZ/JE Jb
+75: JNZ/JNE Jb
+76: JBE/JNA Jb
+77: JNBE/JA Jb
+78: JS Jb
+79: JNS Jb
+7a: JP/JPE Jb
+7b: JNP/JPO Jb
+7c: JL/JNGE Jb
+7d: JNL/JGE Jb
+7e: JLE/JNG Jb
+7f: JNLE/JG Jb
+# 0x80 - 0x8f
+80: Grp1 Eb,Ib (1A)
+81: Grp1 Ev,Iz (1A)
+82: Grp1 Eb,Ib (1A),(i64)
+83: Grp1 Ev,Ib (1A)
+84: TEST Eb,Gb
+85: TEST Ev,Gv
+86: XCHG Eb,Gb
+87: XCHG Ev,Gv
+88: MOV Eb,Gb
+89: MOV Ev,Gv
+8a: MOV Gb,Eb
+8b: MOV Gv,Ev
+8c: MOV Ev,Sw
+8d: LEA Gv,M
+8e: MOV Sw,Ew
+8f: Grp1A (1A) | POP Ev (d64)
+# 0x90 - 0x9f
+90: NOP | PAUSE (F3) | XCHG r8,rAX
+91: XCHG rCX/r9,rAX
+92: XCHG rDX/r10,rAX
+93: XCHG rBX/r11,rAX
+94: XCHG rSP/r12,rAX
+95: XCHG rBP/r13,rAX
+96: XCHG rSI/r14,rAX
+97: XCHG rDI/r15,rAX
+98: CBW/CWDE/CDQE
+99: CWD/CDQ/CQO
+9a: CALLF Ap (i64)
+9b: FWAIT/WAIT
+9c: PUSHF/D/Q Fv (d64)
+9d: POPF/D/Q Fv (d64)
+9e: SAHF
+9f: LAHF
+# 0xa0 - 0xaf
+a0: MOV AL,Ob
+a1: MOV rAX,Ov
+a2: MOV Ob,AL
+a3: MOV Ov,rAX
+a4: MOVS/B Yb,Xb
+a5: MOVS/W/D/Q Yv,Xv
+a6: CMPS/B Xb,Yb
+a7: CMPS/W/D Xv,Yv
+a8: TEST AL,Ib
+a9: TEST rAX,Iz
+aa: STOS/B Yb,AL
+ab: STOS/W/D/Q Yv,rAX
+ac: LODS/B AL,Xb
+ad: LODS/W/D/Q rAX,Xv
+ae: SCAS/B AL,Yb
+# Note: The May 2011 Intel manual shows Xv for the second parameter of the
+# next instruction but Yv is correct
+af: SCAS/W/D/Q rAX,Yv
+# 0xb0 - 0xbf
+b0: MOV AL/R8L,Ib
+b1: MOV CL/R9L,Ib
+b2: MOV DL/R10L,Ib
+b3: MOV BL/R11L,Ib
+b4: MOV AH/R12L,Ib
+b5: MOV CH/R13L,Ib
+b6: MOV DH/R14L,Ib
+b7: MOV BH/R15L,Ib
+b8: MOV rAX/r8,Iv
+b9: MOV rCX/r9,Iv
+ba: MOV rDX/r10,Iv
+bb: MOV rBX/r11,Iv
+bc: MOV rSP/r12,Iv
+bd: MOV rBP/r13,Iv
+be: MOV rSI/r14,Iv
+bf: MOV rDI/r15,Iv
+# 0xc0 - 0xcf
+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)
+c6: Grp11A Eb,Ib (1A)
+c7: Grp11B Ev,Iz (1A)
+c8: ENTER Iw,Ib
+c9: LEAVE (d64)
+ca: RETF Iw
+cb: RETF
+cc: INT3
+cd: INT Ib
+ce: INTO (i64)
+cf: IRET/D/Q
+# 0xd0 - 0xdf
+d0: Grp2 Eb,1 (1A)
+d1: Grp2 Ev,1 (1A)
+d2: Grp2 Eb,CL (1A)
+d3: Grp2 Ev,CL (1A)
+d4: AAM Ib (i64)
+d5: AAD Ib (i64)
+d6:
+d7: XLAT/XLATB
+d8: ESC
+d9: ESC
+da: ESC
+db: ESC
+dc: ESC
+dd: ESC
+de: ESC
+df: ESC
+# 0xe0 - 0xef
+# 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)
+e1: LOOPE/LOOPZ Jb (f64)
+e2: LOOP Jb (f64)
+e3: JrCXZ Jb (f64)
+e4: IN AL,Ib
+e5: IN eAX,Ib
+e6: OUT Ib,AL
+e7: OUT Ib,eAX
+# With 0x66 prefix in 64-bit mode, for AMD CPUs immediate offset
+# 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)
+e9: JMP-near Jz (f64)
+ea: JMP-far Ap (i64)
+eb: JMP-short Jb (f64)
+ec: IN AL,DX
+ed: IN eAX,DX
+ee: OUT DX,AL
+ef: OUT DX,eAX
+# 0xf0 - 0xff
+f0: LOCK (Prefix)
+f1:
+f2: REPNE (Prefix) | XACQUIRE (Prefix)
+f3: REP/REPE (Prefix) | XRELEASE (Prefix)
+f4: HLT
+f5: CMC
+f6: Grp3_1 Eb (1A)
+f7: Grp3_2 Ev (1A)
+f8: CLC
+f9: STC
+fa: CLI
+fb: STI
+fc: CLD
+fd: STD
+fe: Grp4 (1A)
+ff: Grp5 (1A)
+EndTable
+
+Table: 2-byte opcode (0x0f)
+Referrer: 2-byte escape
+AVXcode: 1
+# 0x0f 0x00-0x0f
+00: Grp6 (1A)
+01: Grp7 (1A)
+02: LAR Gv,Ew
+03: LSL Gv,Ew
+04:
+05: SYSCALL (o64)
+06: CLTS
+07: SYSRET (o64)
+08: INVD
+09: WBINVD | WBNOINVD (F3)
+0a:
+0b: UD2 (1B)
+0c:
+# AMD's prefetch group. Intel supports prefetchw(/1) only.
+0d: GrpP
+0e: FEMMS
+# 3DNow! uses the last imm byte as opcode extension.
+0f: 3DNow! Pq,Qq,Ib
+# 0x0f 0x10-0x1f
+# NOTE: According to Intel SDM opcode map, vmovups and vmovupd has no operands
+# but it actually has operands. And also, vmovss and vmovsd only accept 128bit.
+# MOVSS/MOVSD has too many forms(3) on SDM. This map just shows a typical form.
+# Many AVX instructions lack v1 superscript, according to Intel AVX-Prgramming
+# Reference A.1
+10: vmovups Vps,Wps | vmovupd Vpd,Wpd (66) | vmovss Vx,Hx,Wss (F3),(v1) | vmovsd Vx,Hx,Wsd (F2),(v1)
+11: vmovups Wps,Vps | vmovupd Wpd,Vpd (66) | vmovss Wss,Hx,Vss (F3),(v1) | vmovsd Wsd,Hx,Vsd (F2),(v1)
+12: vmovlps Vq,Hq,Mq (v1) | vmovhlps Vq,Hq,Uq (v1) | vmovlpd Vq,Hq,Mq (66),(v1) | vmovsldup Vx,Wx (F3) | vmovddup Vx,Wx (F2)
+13: vmovlps Mq,Vq (v1) | vmovlpd Mq,Vq (66),(v1)
+14: vunpcklps Vx,Hx,Wx | vunpcklpd Vx,Hx,Wx (66)
+15: vunpckhps Vx,Hx,Wx | vunpckhpd Vx,Hx,Wx (66)
+16: vmovhps Vdq,Hq,Mq (v1) | vmovlhps Vdq,Hq,Uq (v1) | vmovhpd Vdq,Hq,Mq (66),(v1) | vmovshdup Vx,Wx (F3)
+17: vmovhps Mq,Vq (v1) | vmovhpd Mq,Vq (66),(v1)
+18: Grp16 (1A)
+19:
+# Intel SDM opcode map does not list MPX instructions. For now using Gv for
+# bnd registers and Ev for everything else is OK because the instruction
+# decoder does not use the information except as an indication that there is
+# a ModR/M byte.
+1a: BNDCL Gv,Ev (F3) | BNDCU Gv,Ev (F2) | BNDMOV Gv,Ev (66) | BNDLDX Gv,Ev
+1b: BNDCN Gv,Ev (F2) | BNDMOV Ev,Gv (66) | BNDMK Gv,Ev (F3) | BNDSTX Ev,Gv
+1c: Grp20 (1A),(1C)
+1d:
+1e: Grp21 (1A)
+1f: NOP Ev
+# 0x0f 0x20-0x2f
+20: MOV Rd,Cd
+21: MOV Rd,Dd
+22: MOV Cd,Rd
+23: MOV Dd,Rd
+24:
+25:
+26:
+27:
+28: vmovaps Vps,Wps | vmovapd Vpd,Wpd (66)
+29: vmovaps Wps,Vps | vmovapd Wpd,Vpd (66)
+2a: cvtpi2ps Vps,Qpi | cvtpi2pd Vpd,Qpi (66) | vcvtsi2ss Vss,Hss,Ey (F3),(v1) | vcvtsi2sd Vsd,Hsd,Ey (F2),(v1)
+2b: vmovntps Mps,Vps | vmovntpd Mpd,Vpd (66)
+2c: cvttps2pi Ppi,Wps | cvttpd2pi Ppi,Wpd (66) | vcvttss2si Gy,Wss (F3),(v1) | vcvttsd2si Gy,Wsd (F2),(v1)
+2d: cvtps2pi Ppi,Wps | cvtpd2pi Qpi,Wpd (66) | vcvtss2si Gy,Wss (F3),(v1) | vcvtsd2si Gy,Wsd (F2),(v1)
+2e: vucomiss Vss,Wss (v1) | vucomisd Vsd,Wsd (66),(v1)
+2f: vcomiss Vss,Wss (v1) | vcomisd Vsd,Wsd (66),(v1)
+# 0x0f 0x30-0x3f
+30: WRMSR
+31: RDTSC
+32: RDMSR
+33: RDPMC
+34: SYSENTER
+35: SYSEXIT
+36:
+37: GETSEC
+38: escape # 3-byte escape 1
+39:
+3a: escape # 3-byte escape 2
+3b:
+3c:
+3d:
+3e:
+3f:
+# 0x0f 0x40-0x4f
+40: CMOVO Gv,Ev
+41: CMOVNO Gv,Ev | kandw/q Vk,Hk,Uk | kandb/d Vk,Hk,Uk (66)
+42: CMOVB/C/NAE Gv,Ev | kandnw/q Vk,Hk,Uk | kandnb/d Vk,Hk,Uk (66)
+43: CMOVAE/NB/NC Gv,Ev
+44: CMOVE/Z Gv,Ev | knotw/q Vk,Uk | knotb/d Vk,Uk (66)
+45: CMOVNE/NZ Gv,Ev | korw/q Vk,Hk,Uk | korb/d Vk,Hk,Uk (66)
+46: CMOVBE/NA Gv,Ev | kxnorw/q Vk,Hk,Uk | kxnorb/d Vk,Hk,Uk (66)
+47: CMOVA/NBE Gv,Ev | kxorw/q Vk,Hk,Uk | kxorb/d Vk,Hk,Uk (66)
+48: CMOVS Gv,Ev
+49: CMOVNS Gv,Ev
+4a: CMOVP/PE Gv,Ev | kaddw/q Vk,Hk,Uk | kaddb/d Vk,Hk,Uk (66)
+4b: CMOVNP/PO Gv,Ev | kunpckbw Vk,Hk,Uk (66) | kunpckwd/dq Vk,Hk,Uk
+4c: CMOVL/NGE Gv,Ev
+4d: CMOVNL/GE Gv,Ev
+4e: CMOVLE/NG Gv,Ev
+4f: CMOVNLE/G Gv,Ev
+# 0x0f 0x50-0x5f
+50: vmovmskps Gy,Ups | vmovmskpd Gy,Upd (66)
+51: vsqrtps Vps,Wps | vsqrtpd Vpd,Wpd (66) | vsqrtss Vss,Hss,Wss (F3),(v1) | vsqrtsd Vsd,Hsd,Wsd (F2),(v1)
+52: vrsqrtps Vps,Wps | vrsqrtss Vss,Hss,Wss (F3),(v1)
+53: vrcpps Vps,Wps | vrcpss Vss,Hss,Wss (F3),(v1)
+54: vandps Vps,Hps,Wps | vandpd Vpd,Hpd,Wpd (66)
+55: vandnps Vps,Hps,Wps | vandnpd Vpd,Hpd,Wpd (66)
+56: vorps Vps,Hps,Wps | vorpd Vpd,Hpd,Wpd (66)
+57: vxorps Vps,Hps,Wps | vxorpd Vpd,Hpd,Wpd (66)
+58: vaddps Vps,Hps,Wps | vaddpd Vpd,Hpd,Wpd (66) | vaddss Vss,Hss,Wss (F3),(v1) | vaddsd Vsd,Hsd,Wsd (F2),(v1)
+59: vmulps Vps,Hps,Wps | vmulpd Vpd,Hpd,Wpd (66) | vmulss Vss,Hss,Wss (F3),(v1) | vmulsd Vsd,Hsd,Wsd (F2),(v1)
+5a: vcvtps2pd Vpd,Wps | vcvtpd2ps Vps,Wpd (66) | vcvtss2sd Vsd,Hx,Wss (F3),(v1) | vcvtsd2ss Vss,Hx,Wsd (F2),(v1)
+5b: vcvtdq2ps Vps,Wdq | vcvtqq2ps Vps,Wqq (evo) | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3)
+5c: vsubps Vps,Hps,Wps | vsubpd Vpd,Hpd,Wpd (66) | vsubss Vss,Hss,Wss (F3),(v1) | vsubsd Vsd,Hsd,Wsd (F2),(v1)
+5d: vminps Vps,Hps,Wps | vminpd Vpd,Hpd,Wpd (66) | vminss Vss,Hss,Wss (F3),(v1) | vminsd Vsd,Hsd,Wsd (F2),(v1)
+5e: vdivps Vps,Hps,Wps | vdivpd Vpd,Hpd,Wpd (66) | vdivss Vss,Hss,Wss (F3),(v1) | vdivsd Vsd,Hsd,Wsd (F2),(v1)
+5f: vmaxps Vps,Hps,Wps | vmaxpd Vpd,Hpd,Wpd (66) | vmaxss Vss,Hss,Wss (F3),(v1) | vmaxsd Vsd,Hsd,Wsd (F2),(v1)
+# 0x0f 0x60-0x6f
+60: punpcklbw Pq,Qd | vpunpcklbw Vx,Hx,Wx (66),(v1)
+61: punpcklwd Pq,Qd | vpunpcklwd Vx,Hx,Wx (66),(v1)
+62: punpckldq Pq,Qd | vpunpckldq Vx,Hx,Wx (66),(v1)
+63: packsswb Pq,Qq | vpacksswb Vx,Hx,Wx (66),(v1)
+64: pcmpgtb Pq,Qq | vpcmpgtb Vx,Hx,Wx (66),(v1)
+65: pcmpgtw Pq,Qq | vpcmpgtw Vx,Hx,Wx (66),(v1)
+66: pcmpgtd Pq,Qq | vpcmpgtd Vx,Hx,Wx (66),(v1)
+67: packuswb Pq,Qq | vpackuswb Vx,Hx,Wx (66),(v1)
+68: punpckhbw Pq,Qd | vpunpckhbw Vx,Hx,Wx (66),(v1)
+69: punpckhwd Pq,Qd | vpunpckhwd Vx,Hx,Wx (66),(v1)
+6a: punpckhdq Pq,Qd | vpunpckhdq Vx,Hx,Wx (66),(v1)
+6b: packssdw Pq,Qd | vpackssdw Vx,Hx,Wx (66),(v1)
+6c: vpunpcklqdq Vx,Hx,Wx (66),(v1)
+6d: vpunpckhqdq Vx,Hx,Wx (66),(v1)
+6e: movd/q Pd,Ey | vmovd/q Vy,Ey (66),(v1)
+6f: movq Pq,Qq | vmovdqa Vx,Wx (66) | vmovdqa32/64 Vx,Wx (66),(evo) | vmovdqu Vx,Wx (F3) | vmovdqu32/64 Vx,Wx (F3),(evo) | vmovdqu8/16 Vx,Wx (F2),(ev)
+# 0x0f 0x70-0x7f
+70: pshufw Pq,Qq,Ib | vpshufd Vx,Wx,Ib (66),(v1) | vpshufhw Vx,Wx,Ib (F3),(v1) | vpshuflw Vx,Wx,Ib (F2),(v1)
+71: Grp12 (1A)
+72: Grp13 (1A)
+73: Grp14 (1A)
+74: pcmpeqb Pq,Qq | vpcmpeqb Vx,Hx,Wx (66),(v1)
+75: pcmpeqw Pq,Qq | vpcmpeqw Vx,Hx,Wx (66),(v1)
+76: pcmpeqd Pq,Qq | vpcmpeqd Vx,Hx,Wx (66),(v1)
+# Note: Remove (v), because vzeroall and vzeroupper becomes emms without VEX.
+77: emms | vzeroupper | vzeroall
+78: VMREAD Ey,Gy | vcvttps2udq/pd2udq Vx,Wpd (evo) | vcvttsd2usi Gv,Wx (F2),(ev) | vcvttss2usi Gv,Wx (F3),(ev) | vcvttps2uqq/pd2uqq Vx,Wx (66),(ev)
+79: VMWRITE Gy,Ey | vcvtps2udq/pd2udq Vx,Wpd (evo) | vcvtsd2usi Gv,Wx (F2),(ev) | vcvtss2usi Gv,Wx (F3),(ev) | vcvtps2uqq/pd2uqq Vx,Wx (66),(ev)
+7a: vcvtudq2pd/uqq2pd Vpd,Wx (F3),(ev) | vcvtudq2ps/uqq2ps Vpd,Wx (F2),(ev) | vcvttps2qq/pd2qq Vx,Wx (66),(ev)
+7b: vcvtusi2sd Vpd,Hpd,Ev (F2),(ev) | vcvtusi2ss Vps,Hps,Ev (F3),(ev) | vcvtps2qq/pd2qq Vx,Wx (66),(ev)
+7c: vhaddpd Vpd,Hpd,Wpd (66) | vhaddps Vps,Hps,Wps (F2)
+7d: vhsubpd Vpd,Hpd,Wpd (66) | vhsubps Vps,Hps,Wps (F2)
+7e: movd/q Ey,Pd | vmovd/q Ey,Vy (66),(v1) | vmovq Vq,Wq (F3),(v1)
+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)
+81: JNO Jz (f64)
+82: JB/JC/JNAE Jz (f64)
+83: JAE/JNB/JNC Jz (f64)
+84: JE/JZ Jz (f64)
+85: JNE/JNZ Jz (f64)
+86: JBE/JNA Jz (f64)
+87: JA/JNBE Jz (f64)
+88: JS Jz (f64)
+89: JNS Jz (f64)
+8a: JP/JPE Jz (f64)
+8b: JNP/JPO Jz (f64)
+8c: JL/JNGE Jz (f64)
+8d: JNL/JGE Jz (f64)
+8e: JLE/JNG Jz (f64)
+8f: JNLE/JG Jz (f64)
+# 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)
+92: SETB/C/NAE Eb | kmovw Vk,Rv | kmovb Vk,Rv (66) | kmovq/d Vk,Rv (F2)
+93: SETAE/NB/NC Eb | kmovw Gv,Uk | kmovb Gv,Uk (66) | kmovq/d Gv,Uk (F2)
+94: SETE/Z Eb
+95: SETNE/NZ Eb
+96: SETBE/NA Eb
+97: SETA/NBE Eb
+98: SETS Eb | kortestw/q Vk,Uk | kortestb/d Vk,Uk (66)
+99: SETNS Eb | ktestw/q Vk,Uk | ktestb/d Vk,Uk (66)
+9a: SETP/PE Eb
+9b: SETNP/PO Eb
+9c: SETL/NGE Eb
+9d: SETNL/GE Eb
+9e: SETLE/NG Eb
+9f: SETNLE/G Eb
+# 0x0f 0xa0-0xaf
+a0: PUSH FS (d64)
+a1: POP FS (d64)
+a2: CPUID
+a3: BT Ev,Gv
+a4: SHLD Ev,Gv,Ib
+a5: SHLD Ev,Gv,CL
+a6: GrpPDLK
+a7: GrpRNG
+a8: PUSH GS (d64)
+a9: POP GS (d64)
+aa: RSM
+ab: BTS Ev,Gv
+ac: SHRD Ev,Gv,Ib
+ad: SHRD Ev,Gv,CL
+ae: Grp15 (1A),(1C)
+af: IMUL Gv,Ev
+# 0x0f 0xb0-0xbf
+b0: CMPXCHG Eb,Gb
+b1: CMPXCHG Ev,Gv
+b2: LSS Gv,Mp
+b3: BTR Ev,Gv
+b4: LFS Gv,Mp
+b5: LGS Gv,Mp
+b6: MOVZX Gv,Eb
+b7: MOVZX Gv,Ew
+b8: JMPE (!F3) | POPCNT Gv,Ev (F3)
+b9: Grp10 (1A)
+ba: Grp8 Ev,Ib (1A)
+bb: BTC Ev,Gv
+bc: BSF Gv,Ev (!F3) | TZCNT Gv,Ev (F3)
+bd: BSR Gv,Ev (!F3) | LZCNT Gv,Ev (F3)
+be: MOVSX Gv,Eb
+bf: MOVSX Gv,Ew
+# 0x0f 0xc0-0xcf
+c0: XADD Eb,Gb
+c1: XADD Ev,Gv
+c2: vcmpps Vps,Hps,Wps,Ib | vcmppd Vpd,Hpd,Wpd,Ib (66) | vcmpss Vss,Hss,Wss,Ib (F3),(v1) | vcmpsd Vsd,Hsd,Wsd,Ib (F2),(v1)
+c3: movnti My,Gy
+c4: pinsrw Pq,Ry/Mw,Ib | vpinsrw Vdq,Hdq,Ry/Mw,Ib (66),(v1)
+c5: pextrw Gd,Nq,Ib | vpextrw Gd,Udq,Ib (66),(v1)
+c6: vshufps Vps,Hps,Wps,Ib | vshufpd Vpd,Hpd,Wpd,Ib (66)
+c7: Grp9 (1A)
+c8: BSWAP RAX/EAX/R8/R8D
+c9: BSWAP RCX/ECX/R9/R9D
+ca: BSWAP RDX/EDX/R10/R10D
+cb: BSWAP RBX/EBX/R11/R11D
+cc: BSWAP RSP/ESP/R12/R12D
+cd: BSWAP RBP/EBP/R13/R13D
+ce: BSWAP RSI/ESI/R14/R14D
+cf: BSWAP RDI/EDI/R15/R15D
+# 0x0f 0xd0-0xdf
+d0: vaddsubpd Vpd,Hpd,Wpd (66) | vaddsubps Vps,Hps,Wps (F2)
+d1: psrlw Pq,Qq | vpsrlw Vx,Hx,Wx (66),(v1)
+d2: psrld Pq,Qq | vpsrld Vx,Hx,Wx (66),(v1)
+d3: psrlq Pq,Qq | vpsrlq Vx,Hx,Wx (66),(v1)
+d4: paddq Pq,Qq | vpaddq Vx,Hx,Wx (66),(v1)
+d5: pmullw Pq,Qq | vpmullw Vx,Hx,Wx (66),(v1)
+d6: vmovq Wq,Vq (66),(v1) | movq2dq Vdq,Nq (F3) | movdq2q Pq,Uq (F2)
+d7: pmovmskb Gd,Nq | vpmovmskb Gd,Ux (66),(v1)
+d8: psubusb Pq,Qq | vpsubusb Vx,Hx,Wx (66),(v1)
+d9: psubusw Pq,Qq | vpsubusw Vx,Hx,Wx (66),(v1)
+da: pminub Pq,Qq | vpminub Vx,Hx,Wx (66),(v1)
+db: pand Pq,Qq | vpand Vx,Hx,Wx (66),(v1) | vpandd/q Vx,Hx,Wx (66),(evo)
+dc: paddusb Pq,Qq | vpaddusb Vx,Hx,Wx (66),(v1)
+dd: paddusw Pq,Qq | vpaddusw Vx,Hx,Wx (66),(v1)
+de: pmaxub Pq,Qq | vpmaxub Vx,Hx,Wx (66),(v1)
+df: pandn Pq,Qq | vpandn Vx,Hx,Wx (66),(v1) | vpandnd/q Vx,Hx,Wx (66),(evo)
+# 0x0f 0xe0-0xef
+e0: pavgb Pq,Qq | vpavgb Vx,Hx,Wx (66),(v1)
+e1: psraw Pq,Qq | vpsraw Vx,Hx,Wx (66),(v1)
+e2: psrad Pq,Qq | vpsrad Vx,Hx,Wx (66),(v1)
+e3: pavgw Pq,Qq | vpavgw Vx,Hx,Wx (66),(v1)
+e4: pmulhuw Pq,Qq | vpmulhuw Vx,Hx,Wx (66),(v1)
+e5: pmulhw Pq,Qq | vpmulhw Vx,Hx,Wx (66),(v1)
+e6: vcvttpd2dq Vx,Wpd (66) | vcvtdq2pd Vx,Wdq (F3) | vcvtdq2pd/qq2pd Vx,Wdq (F3),(evo) | vcvtpd2dq Vx,Wpd (F2)
+e7: movntq Mq,Pq | vmovntdq Mx,Vx (66)
+e8: psubsb Pq,Qq | vpsubsb Vx,Hx,Wx (66),(v1)
+e9: psubsw Pq,Qq | vpsubsw Vx,Hx,Wx (66),(v1)
+ea: pminsw Pq,Qq | vpminsw Vx,Hx,Wx (66),(v1)
+eb: por Pq,Qq | vpor Vx,Hx,Wx (66),(v1) | vpord/q Vx,Hx,Wx (66),(evo)
+ec: paddsb Pq,Qq | vpaddsb Vx,Hx,Wx (66),(v1)
+ed: paddsw Pq,Qq | vpaddsw Vx,Hx,Wx (66),(v1)
+ee: pmaxsw Pq,Qq | vpmaxsw Vx,Hx,Wx (66),(v1)
+ef: pxor Pq,Qq | vpxor Vx,Hx,Wx (66),(v1) | vpxord/q Vx,Hx,Wx (66),(evo)
+# 0x0f 0xf0-0xff
+f0: vlddqu Vx,Mx (F2)
+f1: psllw Pq,Qq | vpsllw Vx,Hx,Wx (66),(v1)
+f2: pslld Pq,Qq | vpslld Vx,Hx,Wx (66),(v1)
+f3: psllq Pq,Qq | vpsllq Vx,Hx,Wx (66),(v1)
+f4: pmuludq Pq,Qq | vpmuludq Vx,Hx,Wx (66),(v1)
+f5: pmaddwd Pq,Qq | vpmaddwd Vx,Hx,Wx (66),(v1)
+f6: psadbw Pq,Qq | vpsadbw Vx,Hx,Wx (66),(v1)
+f7: maskmovq Pq,Nq | vmaskmovdqu Vx,Ux (66),(v1)
+f8: psubb Pq,Qq | vpsubb Vx,Hx,Wx (66),(v1)
+f9: psubw Pq,Qq | vpsubw Vx,Hx,Wx (66),(v1)
+fa: psubd Pq,Qq | vpsubd Vx,Hx,Wx (66),(v1)
+fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1)
+fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1)
+fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1)
+fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1)
+ff: UD0
+EndTable
+
+Table: 3-byte opcode 1 (0x0f 0x38)
+Referrer: 3-byte escape 1
+AVXcode: 2
+# 0x0f 0x38 0x00-0x0f
+00: pshufb Pq,Qq | vpshufb Vx,Hx,Wx (66),(v1)
+01: phaddw Pq,Qq | vphaddw Vx,Hx,Wx (66),(v1)
+02: phaddd Pq,Qq | vphaddd Vx,Hx,Wx (66),(v1)
+03: phaddsw Pq,Qq | vphaddsw Vx,Hx,Wx (66),(v1)
+04: pmaddubsw Pq,Qq | vpmaddubsw Vx,Hx,Wx (66),(v1)
+05: phsubw Pq,Qq | vphsubw Vx,Hx,Wx (66),(v1)
+06: phsubd Pq,Qq | vphsubd Vx,Hx,Wx (66),(v1)
+07: phsubsw Pq,Qq | vphsubsw Vx,Hx,Wx (66),(v1)
+08: psignb Pq,Qq | vpsignb Vx,Hx,Wx (66),(v1)
+09: psignw Pq,Qq | vpsignw Vx,Hx,Wx (66),(v1)
+0a: psignd Pq,Qq | vpsignd Vx,Hx,Wx (66),(v1)
+0b: pmulhrsw Pq,Qq | vpmulhrsw Vx,Hx,Wx (66),(v1)
+0c: vpermilps Vx,Hx,Wx (66),(v)
+0d: vpermilpd Vx,Hx,Wx (66),(v)
+0e: vtestps Vx,Wx (66),(v)
+0f: vtestpd Vx,Wx (66),(v)
+# 0x0f 0x38 0x10-0x1f
+10: pblendvb Vdq,Wdq (66) | vpsrlvw Vx,Hx,Wx (66),(evo) | vpmovuswb Wx,Vx (F3),(ev)
+11: vpmovusdb Wx,Vd (F3),(ev) | vpsravw Vx,Hx,Wx (66),(ev)
+12: vpmovusqb Wx,Vq (F3),(ev) | vpsllvw Vx,Hx,Wx (66),(ev)
+13: vcvtph2ps Vx,Wx (66),(v) | vpmovusdw Wx,Vd (F3),(ev)
+14: blendvps Vdq,Wdq (66) | vpmovusqw Wx,Vq (F3),(ev) | vprorvd/q Vx,Hx,Wx (66),(evo)
+15: blendvpd Vdq,Wdq (66) | vpmovusqd Wx,Vq (F3),(ev) | vprolvd/q Vx,Hx,Wx (66),(evo)
+16: vpermps Vqq,Hqq,Wqq (66),(v) | vpermps/d Vqq,Hqq,Wqq (66),(evo)
+17: vptest Vx,Wx (66)
+18: vbroadcastss Vx,Wd (66),(v)
+19: vbroadcastsd Vqq,Wq (66),(v) | vbroadcastf32x2 Vqq,Wq (66),(evo)
+1a: vbroadcastf128 Vqq,Mdq (66),(v) | vbroadcastf32x4/64x2 Vqq,Wq (66),(evo)
+1b: vbroadcastf32x8/64x4 Vqq,Mdq (66),(ev)
+1c: pabsb Pq,Qq | vpabsb Vx,Wx (66),(v1)
+1d: pabsw Pq,Qq | vpabsw Vx,Wx (66),(v1)
+1e: pabsd Pq,Qq | vpabsd Vx,Wx (66),(v1)
+1f: vpabsq Vx,Wx (66),(ev)
+# 0x0f 0x38 0x20-0x2f
+20: vpmovsxbw Vx,Ux/Mq (66),(v1) | vpmovswb Wx,Vx (F3),(ev)
+21: vpmovsxbd Vx,Ux/Md (66),(v1) | vpmovsdb Wx,Vd (F3),(ev)
+22: vpmovsxbq Vx,Ux/Mw (66),(v1) | vpmovsqb Wx,Vq (F3),(ev)
+23: vpmovsxwd Vx,Ux/Mq (66),(v1) | vpmovsdw Wx,Vd (F3),(ev)
+24: vpmovsxwq Vx,Ux/Md (66),(v1) | vpmovsqw Wx,Vq (F3),(ev)
+25: vpmovsxdq Vx,Ux/Mq (66),(v1) | vpmovsqd Wx,Vq (F3),(ev)
+26: vptestmb/w Vk,Hx,Wx (66),(ev) | vptestnmb/w Vk,Hx,Wx (F3),(ev)
+27: vptestmd/q Vk,Hx,Wx (66),(ev) | vptestnmd/q Vk,Hx,Wx (F3),(ev)
+28: vpmuldq Vx,Hx,Wx (66),(v1) | vpmovm2b/w Vx,Uk (F3),(ev)
+29: vpcmpeqq Vx,Hx,Wx (66),(v1) | vpmovb2m/w2m Vk,Ux (F3),(ev)
+2a: vmovntdqa Vx,Mx (66),(v1) | vpbroadcastmb2q Vx,Uk (F3),(ev)
+2b: vpackusdw Vx,Hx,Wx (66),(v1)
+2c: vmaskmovps Vx,Hx,Mx (66),(v) | vscalefps/d Vx,Hx,Wx (66),(evo)
+2d: vmaskmovpd Vx,Hx,Mx (66),(v) | vscalefss/d Vx,Hx,Wx (66),(evo)
+2e: vmaskmovps Mx,Hx,Vx (66),(v)
+2f: vmaskmovpd Mx,Hx,Vx (66),(v)
+# 0x0f 0x38 0x30-0x3f
+30: vpmovzxbw Vx,Ux/Mq (66),(v1) | vpmovwb Wx,Vx (F3),(ev)
+31: vpmovzxbd Vx,Ux/Md (66),(v1) | vpmovdb Wx,Vd (F3),(ev)
+32: vpmovzxbq Vx,Ux/Mw (66),(v1) | vpmovqb Wx,Vq (F3),(ev)
+33: vpmovzxwd Vx,Ux/Mq (66),(v1) | vpmovdw Wx,Vd (F3),(ev)
+34: vpmovzxwq Vx,Ux/Md (66),(v1) | vpmovqw Wx,Vq (F3),(ev)
+35: vpmovzxdq Vx,Ux/Mq (66),(v1) | vpmovqd Wx,Vq (F3),(ev)
+36: vpermd Vqq,Hqq,Wqq (66),(v) | vpermd/q Vqq,Hqq,Wqq (66),(evo)
+37: vpcmpgtq Vx,Hx,Wx (66),(v1)
+38: vpminsb Vx,Hx,Wx (66),(v1) | vpmovm2d/q Vx,Uk (F3),(ev)
+39: vpminsd Vx,Hx,Wx (66),(v1) | vpminsd/q Vx,Hx,Wx (66),(evo) | vpmovd2m/q2m Vk,Ux (F3),(ev)
+3a: vpminuw Vx,Hx,Wx (66),(v1) | vpbroadcastmw2d Vx,Uk (F3),(ev)
+3b: vpminud Vx,Hx,Wx (66),(v1) | vpminud/q Vx,Hx,Wx (66),(evo)
+3c: vpmaxsb Vx,Hx,Wx (66),(v1)
+3d: vpmaxsd Vx,Hx,Wx (66),(v1) | vpmaxsd/q Vx,Hx,Wx (66),(evo)
+3e: vpmaxuw Vx,Hx,Wx (66),(v1)
+3f: vpmaxud Vx,Hx,Wx (66),(v1) | vpmaxud/q Vx,Hx,Wx (66),(evo)
+# 0x0f 0x38 0x40-0x8f
+40: vpmulld Vx,Hx,Wx (66),(v1) | vpmulld/q Vx,Hx,Wx (66),(evo)
+41: vphminposuw Vdq,Wdq (66),(v1)
+42: vgetexpps/d Vx,Wx (66),(ev)
+43: vgetexpss/d Vx,Hx,Wx (66),(ev)
+44: vplzcntd/q Vx,Wx (66),(ev)
+45: vpsrlvd/q Vx,Hx,Wx (66),(v)
+46: vpsravd Vx,Hx,Wx (66),(v) | vpsravd/q Vx,Hx,Wx (66),(evo)
+47: vpsllvd/q Vx,Hx,Wx (66),(v)
+# Skip 0x48
+49: TILERELEASE (v1),(000),(11B) | LDTILECFG Mtc (v1)(000) | STTILECFG Mtc (66),(v1),(000) | TILEZERO Vt (F2),(v1),(11B)
+# Skip 0x4a
+4b: TILELOADD Vt,Wsm (F2),(v1) | TILELOADDT1 Vt,Wsm (66),(v1) | TILESTORED Wsm,Vt (F3),(v)
+4c: vrcp14ps/d Vpd,Wpd (66),(ev)
+4d: vrcp14ss/d Vsd,Hpd,Wsd (66),(ev)
+4e: vrsqrt14ps/d Vpd,Wpd (66),(ev)
+4f: vrsqrt14ss/d Vsd,Hsd,Wsd (66),(ev)
+50: vpdpbusd Vx,Hx,Wx (66),(ev)
+51: vpdpbusds Vx,Hx,Wx (66),(ev)
+52: vdpbf16ps Vx,Hx,Wx (F3),(ev) | vpdpwssd Vx,Hx,Wx (66),(ev) | vp4dpwssd Vdqq,Hdqq,Wdq (F2),(ev)
+53: vpdpwssds Vx,Hx,Wx (66),(ev) | vp4dpwssds Vdqq,Hdqq,Wdq (F2),(ev)
+54: vpopcntb/w Vx,Wx (66),(ev)
+55: vpopcntd/q Vx,Wx (66),(ev)
+58: vpbroadcastd Vx,Wx (66),(v)
+59: vpbroadcastq Vx,Wx (66),(v) | vbroadcasti32x2 Vx,Wx (66),(evo)
+5a: vbroadcasti128 Vqq,Mdq (66),(v) | vbroadcasti32x4/64x2 Vx,Wx (66),(evo)
+5b: vbroadcasti32x8/64x4 Vqq,Mdq (66),(ev)
+5c: TDPBF16PS Vt,Wt,Ht (F3),(v1)
+# Skip 0x5d
+5e: TDPBSSD Vt,Wt,Ht (F2),(v1) | TDPBSUD Vt,Wt,Ht (F3),(v1) | TDPBUSD Vt,Wt,Ht (66),(v1) | TDPBUUD Vt,Wt,Ht (v1)
+# Skip 0x5f-0x61
+62: vpexpandb/w Vx,Wx (66),(ev)
+63: vpcompressb/w Wx,Vx (66),(ev)
+64: vpblendmd/q Vx,Hx,Wx (66),(ev)
+65: vblendmps/d Vx,Hx,Wx (66),(ev)
+66: vpblendmb/w Vx,Hx,Wx (66),(ev)
+68: vp2intersectd/q Kx,Hx,Wx (F2),(ev)
+# Skip 0x69-0x6f
+70: vpshldvw Vx,Hx,Wx (66),(ev)
+71: vpshldvd/q Vx,Hx,Wx (66),(ev)
+72: vcvtne2ps2bf16 Vx,Hx,Wx (F2),(ev) | vcvtneps2bf16 Vx,Wx (F3),(ev) | vpshrdvw Vx,Hx,Wx (66),(ev)
+73: vpshrdvd/q Vx,Hx,Wx (66),(ev)
+75: vpermi2b/w Vx,Hx,Wx (66),(ev)
+76: vpermi2d/q Vx,Hx,Wx (66),(ev)
+77: vpermi2ps/d Vx,Hx,Wx (66),(ev)
+78: vpbroadcastb Vx,Wx (66),(v)
+79: vpbroadcastw Vx,Wx (66),(v)
+7a: vpbroadcastb Vx,Rv (66),(ev)
+7b: vpbroadcastw Vx,Rv (66),(ev)
+7c: vpbroadcastd/q Vx,Rv (66),(ev)
+7d: vpermt2b/w Vx,Hx,Wx (66),(ev)
+7e: vpermt2d/q Vx,Hx,Wx (66),(ev)
+7f: vpermt2ps/d Vx,Hx,Wx (66),(ev)
+80: INVEPT Gy,Mdq (66)
+81: INVVPID Gy,Mdq (66)
+82: INVPCID Gy,Mdq (66)
+83: vpmultishiftqb Vx,Hx,Wx (66),(ev)
+88: vexpandps/d Vpd,Wpd (66),(ev)
+89: vpexpandd/q Vx,Wx (66),(ev)
+8a: vcompressps/d Wx,Vx (66),(ev)
+8b: vpcompressd/q Wx,Vx (66),(ev)
+8c: vpmaskmovd/q Vx,Hx,Mx (66),(v)
+8d: vpermb/w Vx,Hx,Wx (66),(ev)
+8e: vpmaskmovd/q Mx,Vx,Hx (66),(v)
+8f: vpshufbitqmb Kx,Hx,Wx (66),(ev)
+# 0x0f 0x38 0x90-0xbf (FMA)
+90: vgatherdd/q Vx,Hx,Wx (66),(v) | vpgatherdd/q Vx,Wx (66),(evo)
+91: vgatherqd/q Vx,Hx,Wx (66),(v) | vpgatherqd/q Vx,Wx (66),(evo)
+92: vgatherdps/d Vx,Hx,Wx (66),(v)
+93: vgatherqps/d Vx,Hx,Wx (66),(v)
+94:
+95:
+96: vfmaddsub132ps/d Vx,Hx,Wx (66),(v)
+97: vfmsubadd132ps/d Vx,Hx,Wx (66),(v)
+98: vfmadd132ps/d Vx,Hx,Wx (66),(v)
+99: vfmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
+9a: vfmsub132ps/d Vx,Hx,Wx (66),(v) | v4fmaddps Vdqq,Hdqq,Wdq (F2),(ev)
+9b: vfmsub132ss/d Vx,Hx,Wx (66),(v),(v1) | v4fmaddss Vdq,Hdq,Wdq (F2),(ev)
+9c: vfnmadd132ps/d Vx,Hx,Wx (66),(v)
+9d: vfnmadd132ss/d Vx,Hx,Wx (66),(v),(v1)
+9e: vfnmsub132ps/d Vx,Hx,Wx (66),(v)
+9f: vfnmsub132ss/d Vx,Hx,Wx (66),(v),(v1)
+a0: vpscatterdd/q Wx,Vx (66),(ev)
+a1: vpscatterqd/q Wx,Vx (66),(ev)
+a2: vscatterdps/d Wx,Vx (66),(ev)
+a3: vscatterqps/d Wx,Vx (66),(ev)
+a6: vfmaddsub213ps/d Vx,Hx,Wx (66),(v)
+a7: vfmsubadd213ps/d Vx,Hx,Wx (66),(v)
+a8: vfmadd213ps/d Vx,Hx,Wx (66),(v)
+a9: vfmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
+aa: vfmsub213ps/d Vx,Hx,Wx (66),(v) | v4fnmaddps Vdqq,Hdqq,Wdq (F2),(ev)
+ab: vfmsub213ss/d Vx,Hx,Wx (66),(v),(v1) | v4fnmaddss Vdq,Hdq,Wdq (F2),(ev)
+ac: vfnmadd213ps/d Vx,Hx,Wx (66),(v)
+ad: vfnmadd213ss/d Vx,Hx,Wx (66),(v),(v1)
+ae: vfnmsub213ps/d Vx,Hx,Wx (66),(v)
+af: vfnmsub213ss/d Vx,Hx,Wx (66),(v),(v1)
+b4: vpmadd52luq Vx,Hx,Wx (66),(ev)
+b5: vpmadd52huq Vx,Hx,Wx (66),(ev)
+b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v)
+b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v)
+b8: vfmadd231ps/d Vx,Hx,Wx (66),(v)
+b9: vfmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
+ba: vfmsub231ps/d Vx,Hx,Wx (66),(v)
+bb: vfmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
+bc: vfnmadd231ps/d Vx,Hx,Wx (66),(v)
+bd: vfnmadd231ss/d Vx,Hx,Wx (66),(v),(v1)
+be: vfnmsub231ps/d Vx,Hx,Wx (66),(v)
+bf: vfnmsub231ss/d Vx,Hx,Wx (66),(v),(v1)
+# 0x0f 0x38 0xc0-0xff
+c4: vpconflictd/q Vx,Wx (66),(ev)
+c6: Grp18 (1A)
+c7: Grp19 (1A)
+c8: sha1nexte Vdq,Wdq | vexp2ps/d Vx,Wx (66),(ev)
+c9: sha1msg1 Vdq,Wdq
+ca: sha1msg2 Vdq,Wdq | vrcp28ps/d Vx,Wx (66),(ev)
+cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev)
+cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev)
+cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev)
+cf: vgf2p8mulb Vx,Wx (66)
+db: VAESIMC Vdq,Wdq (66),(v1)
+dc: vaesenc Vx,Hx,Wx (66)
+dd: vaesenclast Vx,Hx,Wx (66)
+de: vaesdec Vx,Hx,Wx (66)
+df: vaesdeclast Vx,Hx,Wx (66)
+f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) | CRC32 Gd,Eb (66&F2)
+f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) | CRC32 Gd,Ew (66&F2)
+f2: ANDN Gy,By,Ey (v)
+f3: Grp17 (1A)
+f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v) | WRUSSD/Q My,Gy (66)
+f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v) | WRSSD/Q My,Gy
+f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v)
+f8: MOVDIR64B Gv,Mdqq (66) | ENQCMD Gv,Mdqq (F2) | ENQCMDS Gv,Mdqq (F3)
+f9: MOVDIRI My,Gy
+EndTable
+
+Table: 3-byte opcode 2 (0x0f 0x3a)
+Referrer: 3-byte escape 2
+AVXcode: 3
+# 0x0f 0x3a 0x00-0xff
+00: vpermq Vqq,Wqq,Ib (66),(v)
+01: vpermpd Vqq,Wqq,Ib (66),(v)
+02: vpblendd Vx,Hx,Wx,Ib (66),(v)
+03: valignd/q Vx,Hx,Wx,Ib (66),(ev)
+04: vpermilps Vx,Wx,Ib (66),(v)
+05: vpermilpd Vx,Wx,Ib (66),(v)
+06: vperm2f128 Vqq,Hqq,Wqq,Ib (66),(v)
+07:
+08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(evo) | vrndscaleph Vx,Wx,Ib (evo)
+09: vroundpd Vx,Wx,Ib (66) | vrndscalepd Vx,Wx,Ib (66),(evo)
+0a: vroundss Vss,Wss,Ib (66),(v1) | vrndscaless Vx,Hx,Wx,Ib (66),(evo) | vrndscalesh Vx,Hx,Wx,Ib (evo)
+0b: vroundsd Vsd,Wsd,Ib (66),(v1) | vrndscalesd Vx,Hx,Wx,Ib (66),(evo)
+0c: vblendps Vx,Hx,Wx,Ib (66)
+0d: vblendpd Vx,Hx,Wx,Ib (66)
+0e: vpblendw Vx,Hx,Wx,Ib (66),(v1)
+0f: palignr Pq,Qq,Ib | vpalignr Vx,Hx,Wx,Ib (66),(v1)
+14: vpextrb Rd/Mb,Vdq,Ib (66),(v1)
+15: vpextrw Rd/Mw,Vdq,Ib (66),(v1)
+16: vpextrd/q Ey,Vdq,Ib (66),(v1)
+17: vextractps Ed,Vdq,Ib (66),(v1)
+18: vinsertf128 Vqq,Hqq,Wqq,Ib (66),(v) | vinsertf32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo)
+19: vextractf128 Wdq,Vqq,Ib (66),(v) | vextractf32x4/64x2 Wdq,Vqq,Ib (66),(evo)
+1a: vinsertf32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev)
+1b: vextractf32x8/64x4 Wdq,Vqq,Ib (66),(ev)
+1d: vcvtps2ph Wx,Vx,Ib (66),(v)
+1e: vpcmpud/q Vk,Hd,Wd,Ib (66),(ev)
+1f: vpcmpd/q Vk,Hd,Wd,Ib (66),(ev)
+20: vpinsrb Vdq,Hdq,Ry/Mb,Ib (66),(v1)
+21: vinsertps Vdq,Hdq,Udq/Md,Ib (66),(v1)
+22: vpinsrd/q Vdq,Hdq,Ey,Ib (66),(v1)
+23: vshuff32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
+25: vpternlogd/q Vx,Hx,Wx,Ib (66),(ev)
+26: vgetmantps/d Vx,Wx,Ib (66),(ev) | vgetmantph Vx,Wx,Ib (ev)
+27: vgetmantss/d Vx,Hx,Wx,Ib (66),(ev) | vgetmantsh Vx,Hx,Wx,Ib (ev)
+30: kshiftrb/w Vk,Uk,Ib (66),(v)
+31: kshiftrd/q Vk,Uk,Ib (66),(v)
+32: kshiftlb/w Vk,Uk,Ib (66),(v)
+33: kshiftld/q Vk,Uk,Ib (66),(v)
+38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v) | vinserti32x4/64x2 Vqq,Hqq,Wqq,Ib (66),(evo)
+39: vextracti128 Wdq,Vqq,Ib (66),(v) | vextracti32x4/64x2 Wdq,Vqq,Ib (66),(evo)
+3a: vinserti32x8/64x4 Vqq,Hqq,Wqq,Ib (66),(ev)
+3b: vextracti32x8/64x4 Wdq,Vqq,Ib (66),(ev)
+3e: vpcmpub/w Vk,Hk,Wx,Ib (66),(ev)
+3f: vpcmpb/w Vk,Hk,Wx,Ib (66),(ev)
+40: vdpps Vx,Hx,Wx,Ib (66)
+41: vdppd Vdq,Hdq,Wdq,Ib (66),(v1)
+42: vmpsadbw Vx,Hx,Wx,Ib (66),(v1) | vdbpsadbw Vx,Hx,Wx,Ib (66),(evo)
+43: vshufi32x4/64x2 Vx,Hx,Wx,Ib (66),(ev)
+44: vpclmulqdq Vx,Hx,Wx,Ib (66)
+46: vperm2i128 Vqq,Hqq,Wqq,Ib (66),(v)
+4a: vblendvps Vx,Hx,Wx,Lx (66),(v)
+4b: vblendvpd Vx,Hx,Wx,Lx (66),(v)
+4c: vpblendvb Vx,Hx,Wx,Lx (66),(v1)
+50: vrangeps/d Vx,Hx,Wx,Ib (66),(ev)
+51: vrangess/d Vx,Hx,Wx,Ib (66),(ev)
+54: vfixupimmps/d Vx,Hx,Wx,Ib (66),(ev)
+55: vfixupimmss/d Vx,Hx,Wx,Ib (66),(ev)
+56: vreduceps/d Vx,Wx,Ib (66),(ev) | vreduceph Vx,Wx,Ib (ev)
+57: vreducess/d Vx,Hx,Wx,Ib (66),(ev) | vreducesh Vx,Hx,Wx,Ib (ev)
+60: vpcmpestrm Vdq,Wdq,Ib (66),(v1)
+61: vpcmpestri Vdq,Wdq,Ib (66),(v1)
+62: vpcmpistrm Vdq,Wdq,Ib (66),(v1)
+63: vpcmpistri Vdq,Wdq,Ib (66),(v1)
+66: vfpclassps/d Vk,Wx,Ib (66),(ev) | vfpclassph Vx,Wx,Ib (ev)
+67: vfpclassss/d Vk,Wx,Ib (66),(ev) | vfpclasssh Vx,Wx,Ib (ev)
+70: vpshldw Vx,Hx,Wx,Ib (66),(ev)
+71: vpshldd/q Vx,Hx,Wx,Ib (66),(ev)
+72: vpshrdw Vx,Hx,Wx,Ib (66),(ev)
+73: vpshrdd/q Vx,Hx,Wx,Ib (66),(ev)
+c2: vcmpph Vx,Hx,Wx,Ib (ev) | vcmpsh Vx,Hx,Wx,Ib (F3),(ev)
+cc: sha1rnds4 Vdq,Wdq,Ib
+ce: vgf2p8affineqb Vx,Wx,Ib (66)
+cf: vgf2p8affineinvqb Vx,Wx,Ib (66)
+df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
+f0: RORX Gy,Ey,Ib (F2),(v) | HRESET Gv,Ib (F3),(000),(11B)
+EndTable
+
+Table: EVEX map 5
+Referrer:
+AVXcode: 5
+10: vmovsh Vx,Hx,Wx (F3),(ev) | vmovsh Vx,Wx (F3),(ev)
+11: vmovsh Wx,Hx,Vx (F3),(ev) | vmovsh Wx,Vx (F3),(ev)
+1d: vcvtps2phx Vx,Wx (66),(ev) | vcvtss2sh Vx,Hx,Wx (ev)
+2a: vcvtsi2sh Vx,Hx,Wx (F3),(ev)
+2c: vcvttsh2si Vx,Wx (F3),(ev)
+2d: vcvtsh2si Vx,Wx (F3),(ev)
+2e: vucomish Vx,Wx (ev)
+2f: vcomish Vx,Wx (ev)
+51: vsqrtph Vx,Wx (ev) | vsqrtsh Vx,Hx,Wx (F3),(ev)
+58: vaddph Vx,Hx,Wx (ev) | vaddsh Vx,Hx,Wx (F3),(ev)
+59: vmulph Vx,Hx,Wx (ev) | vmulsh Vx,Hx,Wx (F3),(ev)
+5a: vcvtpd2ph Vx,Wx (66),(ev) | vcvtph2pd Vx,Wx (ev) | vcvtsd2sh Vx,Hx,Wx (F2),(ev) | vcvtsh2sd Vx,Hx,Wx (F3),(ev)
+5b: vcvtdq2ph Vx,Wx (ev) | vcvtph2dq Vx,Wx (66),(ev) | vcvtqq2ph Vx,Wx (ev) | vcvttph2dq Vx,Wx (F3),(ev)
+5c: vsubph Vx,Hx,Wx (ev) | vsubsh Vx,Hx,Wx (F3),(ev)
+5d: vminph Vx,Hx,Wx (ev) | vminsh Vx,Hx,Wx (F3),(ev)
+5e: vdivph Vx,Hx,Wx (ev) | vdivsh Vx,Hx,Wx (F3),(ev)
+5f: vmaxph Vx,Hx,Wx (ev) | vmaxsh Vx,Hx,Wx (F3),(ev)
+6e: vmovw Vx,Wx (66),(ev)
+78: vcvttph2udq Vx,Wx (ev) | vcvttph2uqq Vx,Wx (66),(ev) | vcvttsh2usi Vx,Wx (F3),(ev)
+79: vcvtph2udq Vx,Wx (ev) | vcvtph2uqq Vx,Wx (66),(ev) | vcvtsh2usi Vx,Wx (F3),(ev)
+7a: vcvttph2qq Vx,Wx (66),(ev) | vcvtudq2ph Vx,Wx (F2),(ev) | vcvtuqq2ph Vx,Wx (F2),(ev)
+7b: vcvtph2qq Vx,Wx (66),(ev) | vcvtusi2sh Vx,Hx,Wx (F3),(ev)
+7c: vcvttph2uw Vx,Wx (ev) | vcvttph2w Vx,Wx (66),(ev)
+7d: vcvtph2uw Vx,Wx (ev) | vcvtph2w Vx,Wx (66),(ev) | vcvtuw2ph Vx,Wx (F2),(ev) | vcvtw2ph Vx,Wx (F3),(ev)
+7e: vmovw Wx,Vx (66),(ev)
+EndTable
+
+Table: EVEX map 6
+Referrer:
+AVXcode: 6
+13: vcvtph2psx Vx,Wx (66),(ev) | vcvtsh2ss Vx,Hx,Wx (ev)
+2c: vscalefph Vx,Hx,Wx (66),(ev)
+2d: vscalefsh Vx,Hx,Wx (66),(ev)
+42: vgetexpph Vx,Wx (66),(ev)
+43: vgetexpsh Vx,Hx,Wx (66),(ev)
+4c: vrcpph Vx,Wx (66),(ev)
+4d: vrcpsh Vx,Hx,Wx (66),(ev)
+4e: vrsqrtph Vx,Wx (66),(ev)
+4f: vrsqrtsh Vx,Hx,Wx (66),(ev)
+56: vfcmaddcph Vx,Hx,Wx (F2),(ev) | vfmaddcph Vx,Hx,Wx (F3),(ev)
+57: vfcmaddcsh Vx,Hx,Wx (F2),(ev) | vfmaddcsh Vx,Hx,Wx (F3),(ev)
+96: vfmaddsub132ph Vx,Hx,Wx (66),(ev)
+97: vfmsubadd132ph Vx,Hx,Wx (66),(ev)
+98: vfmadd132ph Vx,Hx,Wx (66),(ev)
+99: vfmadd132sh Vx,Hx,Wx (66),(ev)
+9a: vfmsub132ph Vx,Hx,Wx (66),(ev)
+9b: vfmsub132sh Vx,Hx,Wx (66),(ev)
+9c: vfnmadd132ph Vx,Hx,Wx (66),(ev)
+9d: vfnmadd132sh Vx,Hx,Wx (66),(ev)
+9e: vfnmsub132ph Vx,Hx,Wx (66),(ev)
+9f: vfnmsub132sh Vx,Hx,Wx (66),(ev)
+a6: vfmaddsub213ph Vx,Hx,Wx (66),(ev)
+a7: vfmsubadd213ph Vx,Hx,Wx (66),(ev)
+a8: vfmadd213ph Vx,Hx,Wx (66),(ev)
+a9: vfmadd213sh Vx,Hx,Wx (66),(ev)
+aa: vfmsub213ph Vx,Hx,Wx (66),(ev)
+ab: vfmsub213sh Vx,Hx,Wx (66),(ev)
+ac: vfnmadd213ph Vx,Hx,Wx (66),(ev)
+ad: vfnmadd213sh Vx,Hx,Wx (66),(ev)
+ae: vfnmsub213ph Vx,Hx,Wx (66),(ev)
+af: vfnmsub213sh Vx,Hx,Wx (66),(ev)
+b6: vfmaddsub231ph Vx,Hx,Wx (66),(ev)
+b7: vfmsubadd231ph Vx,Hx,Wx (66),(ev)
+b8: vfmadd231ph Vx,Hx,Wx (66),(ev)
+b9: vfmadd231sh Vx,Hx,Wx (66),(ev)
+ba: vfmsub231ph Vx,Hx,Wx (66),(ev)
+bb: vfmsub231sh Vx,Hx,Wx (66),(ev)
+bc: vfnmadd231ph Vx,Hx,Wx (66),(ev)
+bd: vfnmadd231sh Vx,Hx,Wx (66),(ev)
+be: vfnmsub231ph Vx,Hx,Wx (66),(ev)
+bf: vfnmsub231sh Vx,Hx,Wx (66),(ev)
+d6: vfcmulcph Vx,Hx,Wx (F2),(ev) | vfmulcph Vx,Hx,Wx (F3),(ev)
+d7: vfcmulcsh Vx,Hx,Wx (F2),(ev) | vfmulcsh Vx,Hx,Wx (F3),(ev)
+EndTable
+
+GrpTable: Grp1
+0: ADD
+1: OR
+2: ADC
+3: SBB
+4: AND
+5: SUB
+6: XOR
+7: CMP
+EndTable
+
+GrpTable: Grp1A
+0: POP
+EndTable
+
+GrpTable: Grp2
+0: ROL
+1: ROR
+2: RCL
+3: RCR
+4: SHL/SAL
+5: SHR
+6:
+7: SAR
+EndTable
+
+GrpTable: Grp3_1
+0: TEST Eb,Ib
+1: TEST Eb,Ib
+2: NOT Eb
+3: NEG Eb
+4: MUL AL,Eb
+5: IMUL AL,Eb
+6: DIV AL,Eb
+7: IDIV AL,Eb
+EndTable
+
+GrpTable: Grp3_2
+0: TEST Ev,Iz
+1: TEST Ev,Iz
+2: NOT Ev
+3: NEG Ev
+4: MUL rAX,Ev
+5: IMUL rAX,Ev
+6: DIV rAX,Ev
+7: IDIV rAX,Ev
+EndTable
+
+GrpTable: Grp4
+0: INC Eb
+1: DEC Eb
+EndTable
+
+GrpTable: Grp5
+0: INC Ev
+1: DEC Ev
+# Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
+2: CALLN Ev (f64)
+3: CALLF Ep
+4: JMPN Ev (f64)
+5: JMPF Mp
+6: PUSH Ev (d64)
+7:
+EndTable
+
+GrpTable: Grp6
+0: SLDT Rv/Mw
+1: STR Rv/Mw
+2: LLDT Ew
+3: LTR Ew
+4: VERR Ew
+5: VERW Ew
+6: LKGS Ew (F2)
+EndTable
+
+GrpTable: Grp7
+0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B)
+1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B)
+2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B)
+3: LIDT Ms
+4: SMSW Mw/Rv
+5: rdpkru (110),(11B) | wrpkru (111),(11B) | SAVEPREVSSP (F3),(010),(11B) | RSTORSSP Mq (F3) | SETSSBSY (F3),(000),(11B) | CLUI (F3),(110),(11B) | SERIALIZE (000),(11B) | STUI (F3),(111),(11B) | TESTUI (F3)(101)(11B) | UIRET (F3),(100),(11B) | XRESLDTRK (F2),(000),(11B) | XSUSLDTRK (F2),(001),(11B)
+6: LMSW Ew
+7: INVLPG Mb | SWAPGS (o64),(000),(11B) | RDTSCP (001),(11B)
+EndTable
+
+GrpTable: Grp8
+4: BT
+5: BTS
+6: BTR
+7: BTC
+EndTable
+
+GrpTable: Grp9
+1: CMPXCHG8B/16B Mq/Mdq
+3: xrstors
+4: xsavec
+5: xsaves
+6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B) | SENDUIPI Gq (F3)
+7: VMPTRST Mq | VMPTRST Mq (F3) | RDSEED Rv (11B)
+EndTable
+
+GrpTable: Grp10
+# all are UD1
+0: UD1
+1: UD1
+2: UD1
+3: UD1
+4: UD1
+5: UD1
+6: UD1
+7: UD1
+EndTable
+
+# Grp11A and Grp11B are expressed as Grp11 in Intel SDM
+GrpTable: Grp11A
+0: MOV Eb,Ib
+7: XABORT Ib (000),(11B)
+EndTable
+
+GrpTable: Grp11B
+0: MOV Eb,Iz
+7: XBEGIN Jz (000),(11B)
+EndTable
+
+GrpTable: Grp12
+2: psrlw Nq,Ib (11B) | vpsrlw Hx,Ux,Ib (66),(11B),(v1)
+4: psraw Nq,Ib (11B) | vpsraw Hx,Ux,Ib (66),(11B),(v1)
+6: psllw Nq,Ib (11B) | vpsllw Hx,Ux,Ib (66),(11B),(v1)
+EndTable
+
+GrpTable: Grp13
+0: vprord/q Hx,Wx,Ib (66),(ev)
+1: vprold/q Hx,Wx,Ib (66),(ev)
+2: psrld Nq,Ib (11B) | vpsrld Hx,Ux,Ib (66),(11B),(v1)
+4: psrad Nq,Ib (11B) | vpsrad Hx,Ux,Ib (66),(11B),(v1) | vpsrad/q Hx,Ux,Ib (66),(evo)
+6: pslld Nq,Ib (11B) | vpslld Hx,Ux,Ib (66),(11B),(v1)
+EndTable
+
+GrpTable: Grp14
+2: psrlq Nq,Ib (11B) | vpsrlq Hx,Ux,Ib (66),(11B),(v1)
+3: vpsrldq Hx,Ux,Ib (66),(11B),(v1)
+6: psllq Nq,Ib (11B) | vpsllq Hx,Ux,Ib (66),(11B),(v1)
+7: vpslldq Hx,Ux,Ib (66),(11B),(v1)
+EndTable
+
+GrpTable: Grp15
+0: fxsave | RDFSBASE Ry (F3),(11B)
+1: fxstor | RDGSBASE Ry (F3),(11B)
+2: vldmxcsr Md (v1) | WRFSBASE Ry (F3),(11B)
+3: vstmxcsr Md (v1) | WRGSBASE Ry (F3),(11B)
+4: XSAVE | ptwrite Ey (F3),(11B)
+5: XRSTOR | lfence (11B) | INCSSPD/Q Ry (F3),(11B)
+6: XSAVEOPT | clwb (66) | mfence (11B) | TPAUSE Rd (66),(11B) | UMONITOR Rv (F3),(11B) | UMWAIT Rd (F2),(11B) | CLRSSBSY Mq (F3)
+7: clflush | clflushopt (66) | sfence (11B)
+EndTable
+
+GrpTable: Grp16
+0: prefetch NTA
+1: prefetch T0
+2: prefetch T1
+3: prefetch T2
+EndTable
+
+GrpTable: Grp17
+1: BLSR By,Ey (v)
+2: BLSMSK By,Ey (v)
+3: BLSI By,Ey (v)
+EndTable
+
+GrpTable: Grp18
+1: vgatherpf0dps/d Wx (66),(ev)
+2: vgatherpf1dps/d Wx (66),(ev)
+5: vscatterpf0dps/d Wx (66),(ev)
+6: vscatterpf1dps/d Wx (66),(ev)
+EndTable
+
+GrpTable: Grp19
+1: vgatherpf0qps/d Wx (66),(ev)
+2: vgatherpf1qps/d Wx (66),(ev)
+5: vscatterpf0qps/d Wx (66),(ev)
+6: vscatterpf1qps/d Wx (66),(ev)
+EndTable
+
+GrpTable: Grp20
+0: cldemote Mb
+EndTable
+
+GrpTable: Grp21
+1: RDSSPD/Q Ry (F3),(11B)
+7: ENDBR64 (F3),(010),(11B) | ENDBR32 (F3),(011),(11B)
+EndTable
+
+# AMD's Prefetch Group
+GrpTable: GrpP
+0: PREFETCH
+1: PREFETCHW
+EndTable
+
+GrpTable: GrpPDLK
+0: MONTMUL
+1: XSHA1
+2: XSHA2
+EndTable
+
+GrpTable: GrpRNG
+0: xstore-rng
+1: xcrypt-ecb
+2: xcrypt-cbc
+4: xcrypt-cfb
+5: xcrypt-ofb
+EndTable