aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/tools/arch/x86/lib
diff options
context:
space:
mode:
Diffstat (limited to '')
-rw-r--r--tools/arch/x86/lib/inat.c2
-rw-r--r--tools/arch/x86/lib/insn.c376
-rw-r--r--tools/arch/x86/lib/memcpy_64.S64
-rw-r--r--tools/arch/x86/lib/memset_64.S66
-rw-r--r--tools/arch/x86/lib/x86-opcode-map.txt433
5 files changed, 636 insertions, 305 deletions
diff --git a/tools/arch/x86/lib/inat.c b/tools/arch/x86/lib/inat.c
index 4f5ed49e1b4e..dfbcc6405941 100644
--- a/tools/arch/x86/lib/inat.c
+++ b/tools/arch/x86/lib/inat.c
@@ -4,7 +4,7 @@
*
* Written by Masami Hiramatsu <mhiramat@redhat.com>
*/
-#include "../include/asm/insn.h"
+#include "../include/asm/insn.h" /* __ignore_sync_check__ */
/* Attribute tables are generated from opcode map */
#include "inat-tables.c"
diff --git a/tools/arch/x86/lib/insn.c b/tools/arch/x86/lib/insn.c
index 0151dfc6da61..bce69c6bfa69 100644
--- a/tools/arch/x86/lib/insn.c
+++ b/tools/arch/x86/lib/insn.c
@@ -5,25 +5,43 @@
* Copyright (C) IBM Corporation, 2002, 2004, 2009
*/
+#include <linux/kernel.h>
#ifdef __KERNEL__
#include <linux/string.h>
#else
#include <string.h>
#endif
-#include "../include/asm/inat.h"
-#include "../include/asm/insn.h"
-
-#include "../include/asm/emulate_prefix.h"
+#include "../include/asm/inat.h" /* __ignore_sync_check__ */
+#include "../include/asm/insn.h" /* __ignore_sync_check__ */
+#include <linux/unaligned.h> /* __ignore_sync_check__ */
+
+#include <linux/errno.h>
+#include <linux/kconfig.h>
+
+#include "../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 = *(t*)insn->next_byte; insn->next_byte += sizeof(t); r; })
+ ({ 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 = *(t*)((insn)->next_byte + n); r; })
+ ({ 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); })
@@ -37,6 +55,7 @@
* 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)
@@ -52,7 +71,7 @@ void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64)
insn->kaddr = kaddr;
insn->end_kaddr = kaddr + buf_len;
insn->next_byte = kaddr;
- insn->x86_64 = x86_64 ? 1 : 0;
+ insn->x86_64 = x86_64;
insn->opnd_bytes = 4;
if (x86_64)
insn->addr_bytes = 8;
@@ -97,8 +116,12 @@ static void insn_get_emulate_prefix(struct insn *insn)
* 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
*/
-void insn_get_prefixes(struct insn *insn)
+int insn_get_prefixes(struct insn *insn)
{
struct insn_field *prefixes = &insn->prefixes;
insn_attr_t attr;
@@ -106,7 +129,7 @@ void insn_get_prefixes(struct insn *insn)
int i, nb;
if (prefixes->got)
- return;
+ return 0;
insn_get_emulate_prefix(insn);
@@ -147,9 +170,9 @@ found:
b = insn->prefixes.bytes[3];
for (i = 0; i < nb; i++)
if (prefixes->bytes[i] == lb)
- prefixes->bytes[i] = b;
+ insn_set_byte(prefixes, i, b);
}
- insn->prefixes.bytes[3] = lb;
+ insn_set_byte(&insn->prefixes, 3, lb);
}
/* Decode REX prefix */
@@ -157,12 +180,22 @@ found:
b = peek_next(insn_byte_t, insn);
attr = inat_get_opcode_attribute(b);
if (inat_is_rex_prefix(attr)) {
- insn->rex_prefix.value = b;
- insn->rex_prefix.nbytes = 1;
+ 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;
+ } else if (inat_is_rex2_prefix(attr)) {
+ insn_set_byte(&insn->rex_prefix, 0, b);
+ b = peek_nbyte_next(insn_byte_t, insn, 1);
+ insn_set_byte(&insn->rex_prefix, 1, b);
+ insn->rex_prefix.nbytes = 2;
+ insn->next_byte += 2;
+ if (X86_REX_W(b))
+ /* REX.W overrides opnd_size */
+ insn->opnd_bytes = 8;
+ insn->rex_prefix.got = 1;
+ goto vex_end;
}
}
insn->rex_prefix.got = 1;
@@ -181,13 +214,13 @@ found:
if (X86_MODRM_MOD(b2) != 3)
goto vex_end;
}
- insn->vex_prefix.bytes[0] = b;
- insn->vex_prefix.bytes[1] = b2;
+ 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->vex_prefix.bytes[2] = b2;
+ insn_set_byte(&insn->vex_prefix, 2, b2);
b2 = peek_nbyte_next(insn_byte_t, insn, 3);
- insn->vex_prefix.bytes[3] = b2;
+ 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))
@@ -195,7 +228,7 @@ found:
insn->opnd_bytes = 8;
} else if (inat_is_vex3_prefix(attr)) {
b2 = peek_nbyte_next(insn_byte_t, insn, 2);
- insn->vex_prefix.bytes[2] = b2;
+ 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))
@@ -207,7 +240,7 @@ found:
* Makes it easier to decode vex.W, vex.vvvv,
* vex.L and vex.pp. Masking with 0x7f sets vex.W == 0.
*/
- insn->vex_prefix.bytes[2] = b2 & 0x7f;
+ insn_set_byte(&insn->vex_prefix, 2, b2 & 0x7f);
insn->vex_prefix.nbytes = 2;
insn->next_byte += 2;
}
@@ -217,8 +250,10 @@ vex_end:
prefixes->got = 1;
+ return 0;
+
err_out:
- return;
+ return -ENODATA;
}
/**
@@ -230,20 +265,27 @@ err_out:
* 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
*/
-void insn_get_opcode(struct insn *insn)
+int insn_get_opcode(struct insn *insn)
{
struct insn_field *opcode = &insn->opcode;
+ int pfx_id, ret;
insn_byte_t op;
- int pfx_id;
+
if (opcode->got)
- return;
- if (!insn->prefixes.got)
- insn_get_prefixes(insn);
+ return 0;
+
+ ret = insn_get_prefixes(insn);
+ if (ret)
+ return ret;
/* Get first opcode */
op = get_next(insn_byte_t, insn);
- opcode->bytes[0] = op;
+ insn_set_byte(opcode, 0, op);
opcode->nbytes = 1;
/* Check if there is VEX prefix or not */
@@ -252,14 +294,41 @@ void insn_get_opcode(struct insn *insn)
m = insn_vex_m_bits(insn);
p = insn_vex_p_bits(insn);
insn->attr = inat_get_avx_attribute(op, m, p);
+ /* SCALABLE EVEX uses p bits to encode operand size */
+ if (inat_evex_scalable(insn->attr) && !insn_vex_w_bit(insn) &&
+ p == INAT_PFX_OPNDSZ)
+ insn->opnd_bytes = 2;
if ((inat_must_evex(insn->attr) && !insn_is_evex(insn)) ||
(!inat_accept_vex(insn->attr) &&
- !inat_is_group(insn->attr)))
- insn->attr = 0; /* This instruction is bad */
- goto end; /* VEX has only 1 byte for opcode */
+ !inat_is_group(insn->attr))) {
+ /* This instruction is bad */
+ insn->attr = 0;
+ return -EINVAL;
+ }
+ /* VEX has only 1 byte for opcode */
+ goto end;
+ }
+
+ /* Check if there is REX2 prefix or not */
+ if (insn_is_rex2(insn)) {
+ if (insn_rex2_m_bit(insn)) {
+ /* map 1 is escape 0x0f */
+ insn_attr_t esc_attr = inat_get_opcode_attribute(0x0f);
+
+ pfx_id = insn_last_prefix_id(insn);
+ insn->attr = inat_get_escape_attribute(op, pfx_id, esc_attr);
+ } else {
+ insn->attr = inat_get_opcode_attribute(op);
+ }
+ goto end;
}
insn->attr = inat_get_opcode_attribute(op);
+ if (insn->x86_64 && inat_is_invalid64(insn->attr)) {
+ /* This instruction is invalid, like UD2. Stop decoding. */
+ insn->attr &= INAT_INV64;
+ }
+
while (inat_is_escape(insn->attr)) {
/* Get escaped opcode */
op = get_next(insn_byte_t, insn);
@@ -267,13 +336,19 @@ void insn_get_opcode(struct insn *insn)
pfx_id = insn_last_prefix_id(insn);
insn->attr = inat_get_escape_attribute(op, pfx_id, insn->attr);
}
- if (inat_must_vex(insn->attr))
- insn->attr = 0; /* This instruction is bad */
+
+ if (inat_must_vex(insn->attr)) {
+ /* This instruction is bad */
+ insn->attr = 0;
+ return -EINVAL;
+ }
+
end:
opcode->got = 1;
+ return 0;
err_out:
- return;
+ return -ENODATA;
}
/**
@@ -283,35 +358,47 @@ err_out:
* 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
*/
-void insn_get_modrm(struct insn *insn)
+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;
- if (!insn->opcode.got)
- insn_get_opcode(insn);
+ return 0;
+
+ ret = insn_get_opcode(insn);
+ if (ret)
+ return ret;
if (inat_has_modrm(insn->attr)) {
mod = get_next(insn_byte_t, insn);
- modrm->value = mod;
- modrm->nbytes = 1;
+ 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))
- insn->attr = 0; /* This is bad */
+ 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;
+ return -ENODATA;
}
@@ -325,16 +412,19 @@ err_out:
int insn_rip_relative(struct insn *insn)
{
struct insn_field *modrm = &insn->modrm;
+ int ret;
if (!insn->x86_64)
return 0;
- if (!modrm->got)
- insn_get_modrm(insn);
+
+ 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->value & 0xc7) == 0x5);
+ return (modrm->nbytes && (modrm->bytes[0] & 0xc7) == 0x5);
}
/**
@@ -343,27 +433,37 @@ int insn_rip_relative(struct insn *insn)
*
* If necessary, first collects the instruction up to and including the
* ModRM byte.
+ *
+ * Returns:
+ * 0: if decoding succeeded
+ * < 0: otherwise.
*/
-void insn_get_sib(struct insn *insn)
+int insn_get_sib(struct insn *insn)
{
insn_byte_t modrm;
+ int ret;
if (insn->sib.got)
- return;
- if (!insn->modrm.got)
- insn_get_modrm(insn);
+ return 0;
+
+ ret = insn_get_modrm(insn);
+ if (ret)
+ return ret;
+
if (insn->modrm.nbytes) {
- modrm = (insn_byte_t)insn->modrm.value;
+ modrm = insn->modrm.bytes[0];
if (insn->addr_bytes != 2 &&
X86_MODRM_MOD(modrm) != 3 && X86_MODRM_RM(modrm) == 4) {
- insn->sib.value = get_next(insn_byte_t, insn);
- insn->sib.nbytes = 1;
+ insn_field_set(&insn->sib,
+ get_next(insn_byte_t, insn), 1);
}
}
insn->sib.got = 1;
+ return 0;
+
err_out:
- return;
+ return -ENODATA;
}
@@ -374,15 +474,23 @@ err_out:
* 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.
*/
-void insn_get_displacement(struct insn *insn)
+int insn_get_displacement(struct insn *insn)
{
insn_byte_t mod, rm, base;
+ int ret;
if (insn->displacement.got)
- return;
- if (!insn->sib.got)
- insn_get_sib(insn);
+ return 0;
+
+ ret = insn_get_sib(insn);
+ if (ret)
+ return ret;
+
if (insn->modrm.nbytes) {
/*
* Interpreting the modrm byte:
@@ -407,27 +515,27 @@ void insn_get_displacement(struct insn *insn)
if (mod == 3)
goto out;
if (mod == 1) {
- insn->displacement.value = get_next(signed char, insn);
- insn->displacement.nbytes = 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->displacement.value =
- get_next(short, insn);
- insn->displacement.nbytes = 2;
+ insn_field_set(&insn->displacement,
+ get_next(short, insn), 2);
}
} else {
if ((mod == 0 && rm == 5) || mod == 2 ||
(mod == 0 && base == 5)) {
- insn->displacement.value = get_next(int, insn);
- insn->displacement.nbytes = 4;
+ insn_field_set(&insn->displacement,
+ get_next(int, insn), 4);
}
}
}
out:
insn->displacement.got = 1;
+ return 0;
err_out:
- return;
+ return -ENODATA;
}
/* Decode moffset16/32/64. Return 0 if failed */
@@ -435,18 +543,14 @@ static int __get_moffset(struct insn *insn)
{
switch (insn->addr_bytes) {
case 2:
- insn->moffset1.value = get_next(short, insn);
- insn->moffset1.nbytes = 2;
+ insn_field_set(&insn->moffset1, get_next(short, insn), 2);
break;
case 4:
- insn->moffset1.value = get_next(int, insn);
- insn->moffset1.nbytes = 4;
+ insn_field_set(&insn->moffset1, get_next(int, insn), 4);
break;
case 8:
- insn->moffset1.value = get_next(int, insn);
- insn->moffset1.nbytes = 4;
- insn->moffset2.value = get_next(int, insn);
- insn->moffset2.nbytes = 4;
+ 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;
@@ -464,13 +568,11 @@ static int __get_immv32(struct insn *insn)
{
switch (insn->opnd_bytes) {
case 2:
- insn->immediate.value = get_next(short, insn);
- insn->immediate.nbytes = 2;
+ insn_field_set(&insn->immediate, get_next(short, insn), 2);
break;
case 4:
case 8:
- insn->immediate.value = get_next(int, insn);
- insn->immediate.nbytes = 4;
+ insn_field_set(&insn->immediate, get_next(int, insn), 4);
break;
default: /* opnd_bytes must be modified manually */
goto err_out;
@@ -487,18 +589,15 @@ static int __get_immv(struct insn *insn)
{
switch (insn->opnd_bytes) {
case 2:
- insn->immediate1.value = get_next(short, insn);
- insn->immediate1.nbytes = 2;
+ insn_field_set(&insn->immediate1, get_next(short, insn), 2);
break;
case 4:
- insn->immediate1.value = get_next(int, insn);
+ insn_field_set(&insn->immediate1, get_next(int, insn), 4);
insn->immediate1.nbytes = 4;
break;
case 8:
- insn->immediate1.value = get_next(int, insn);
- insn->immediate1.nbytes = 4;
- insn->immediate2.value = get_next(int, insn);
- insn->immediate2.nbytes = 4;
+ 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;
@@ -515,12 +614,10 @@ static int __get_immptr(struct insn *insn)
{
switch (insn->opnd_bytes) {
case 2:
- insn->immediate1.value = get_next(short, insn);
- insn->immediate1.nbytes = 2;
+ insn_field_set(&insn->immediate1, get_next(short, insn), 2);
break;
case 4:
- insn->immediate1.value = get_next(int, insn);
- insn->immediate1.nbytes = 4;
+ insn_field_set(&insn->immediate1, get_next(int, insn), 4);
break;
case 8:
/* ptr16:64 is not exist (no segment) */
@@ -528,8 +625,7 @@ static int __get_immptr(struct insn *insn)
default: /* opnd_bytes must be modified manually */
goto err_out;
}
- insn->immediate2.value = get_next(unsigned short, insn);
- insn->immediate2.nbytes = 2;
+ insn_field_set(&insn->immediate2, get_next(unsigned short, insn), 2);
insn->immediate1.got = insn->immediate2.got = 1;
return 1;
@@ -538,20 +634,28 @@ err_out:
}
/**
- * insn_get_immediate() - Get the immediates of instruction
+ * 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
- * get by bit masking with ((1 << (nbytes * 8)) - 1)
+ * computed by bit masking with ((1 << (nbytes * 8)) - 1)
+ *
+ * Returns:
+ * 0: on success
+ * < 0: on error
*/
-void insn_get_immediate(struct insn *insn)
+int insn_get_immediate(struct insn *insn)
{
+ int ret;
+
if (insn->immediate.got)
- return;
- if (!insn->displacement.got)
- insn_get_displacement(insn);
+ return 0;
+
+ ret = insn_get_displacement(insn);
+ if (ret)
+ return ret;
if (inat_has_moffset(insn->attr)) {
if (!__get_moffset(insn))
@@ -560,27 +664,21 @@ void insn_get_immediate(struct insn *insn)
}
if (!inat_has_immediate(insn->attr))
- /* no immediates */
goto done;
switch (inat_immediate_size(insn->attr)) {
case INAT_IMM_BYTE:
- insn->immediate.value = get_next(signed char, insn);
- insn->immediate.nbytes = 1;
+ insn_field_set(&insn->immediate, get_next(signed char, insn), 1);
break;
case INAT_IMM_WORD:
- insn->immediate.value = get_next(short, insn);
- insn->immediate.nbytes = 2;
+ insn_field_set(&insn->immediate, get_next(short, insn), 2);
break;
case INAT_IMM_DWORD:
- insn->immediate.value = get_next(int, insn);
- insn->immediate.nbytes = 4;
+ insn_field_set(&insn->immediate, get_next(int, insn), 4);
break;
case INAT_IMM_QWORD:
- insn->immediate1.value = get_next(int, insn);
- insn->immediate1.nbytes = 4;
- insn->immediate2.value = get_next(int, insn);
- insn->immediate2.nbytes = 4;
+ 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))
@@ -599,14 +697,14 @@ void insn_get_immediate(struct insn *insn)
goto err_out;
}
if (inat_has_second_immediate(insn->attr)) {
- insn->immediate2.value = get_next(signed char, insn);
- insn->immediate2.nbytes = 1;
+ insn_field_set(&insn->immediate2, get_next(signed char, insn), 1);
}
done:
insn->immediate.got = 1;
+ return 0;
err_out:
- return;
+ return -ENODATA;
}
/**
@@ -615,13 +713,63 @@ err_out:
*
* If necessary, first collects the instruction up to and including the
* immediates bytes.
- */
-void insn_get_length(struct insn *insn)
+ *
+ * Returns:
+ * - 0 on success
+ * - < 0 on error
+*/
+int insn_get_length(struct insn *insn)
{
+ int ret;
+
if (insn->length)
- return;
- if (!insn->immediate.got)
- insn_get_immediate(insn);
+ return 0;
+
+ 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 (enum insn_mode)-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/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index 0b5b8ae56bd9..ccc3d923fc1e 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -1,22 +1,13 @@
/* SPDX-License-Identifier: GPL-2.0-only */
/* Copyright 2002 Andi Kleen */
+#include <linux/export.h>
#include <linux/linkage.h>
#include <asm/errno.h>
#include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
-#include <asm/export.h>
+#include <asm/alternative.h>
-.pushsection .noinstr.text, "ax"
-
-/*
- * We build a jump to memcpy_orig by default which gets NOPped out on
- * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which
- * have the enhanced REP MOVSB/STOSB feature (ERMS), change those NOPs
- * to a jmp to memcpy_erms which does the REP; MOVSB mem copy.
- */
-
-.weak memcpy
+.section .noinstr.text, "ax"
/*
* memcpy - Copy a memory block.
@@ -28,37 +19,31 @@
*
* 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_FUNC_START_ALIAS(__memcpy)
-SYM_FUNC_START_LOCAL(memcpy)
- ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
- "jmp memcpy_erms", X86_FEATURE_ERMS
+SYM_TYPED_FUNC_START(__memcpy)
+ ALTERNATIVE "jmp memcpy_orig", "", X86_FEATURE_FSRM
movq %rdi, %rax
movq %rdx, %rcx
- shrq $3, %rcx
- andl $7, %edx
- rep movsq
- movl %edx, %ecx
rep movsb
- ret
-SYM_FUNC_END(memcpy)
-SYM_FUNC_END_ALIAS(__memcpy)
-EXPORT_SYMBOL(memcpy)
+ RET
+SYM_FUNC_END(__memcpy)
EXPORT_SYMBOL(__memcpy)
-/*
- * memcpy_erms() - enhanced fast string memcpy. This is faster and
- * simpler than memcpy. Use memcpy_erms when possible.
- */
-SYM_FUNC_START(memcpy_erms)
- movq %rdi, %rax
- movq %rdx, %rcx
- rep movsb
- ret
-SYM_FUNC_END(memcpy_erms)
+SYM_FUNC_ALIAS_MEMFUNC(memcpy, __memcpy)
+SYM_PIC_ALIAS(memcpy)
+EXPORT_SYMBOL(memcpy)
-SYM_FUNC_START(memcpy_orig)
+SYM_FUNC_START_LOCAL(memcpy_orig)
movq %rdi, %rax
cmpq $0x20, %rdx
@@ -139,7 +124,7 @@ SYM_FUNC_START(memcpy_orig)
movq %r9, 1*8(%rdi)
movq %r10, -2*8(%rdi, %rdx)
movq %r11, -1*8(%rdi, %rdx)
- retq
+ RET
.p2align 4
.Lless_16bytes:
cmpl $8, %edx
@@ -151,7 +136,7 @@ SYM_FUNC_START(memcpy_orig)
movq -1*8(%rsi, %rdx), %r9
movq %r8, 0*8(%rdi)
movq %r9, -1*8(%rdi, %rdx)
- retq
+ RET
.p2align 4
.Lless_8bytes:
cmpl $4, %edx
@@ -164,7 +149,7 @@ SYM_FUNC_START(memcpy_orig)
movl -4(%rsi, %rdx), %r8d
movl %ecx, (%rdi)
movl %r8d, -4(%rdi, %rdx)
- retq
+ RET
.p2align 4
.Lless_3bytes:
subl $1, %edx
@@ -182,7 +167,6 @@ SYM_FUNC_START(memcpy_orig)
movb %cl, (%rdi)
.Lend:
- retq
+ RET
SYM_FUNC_END(memcpy_orig)
-.popsection
diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S
index fd5d25a474b7..fb5a03cf5ab7 100644
--- a/tools/arch/x86/lib/memset_64.S
+++ b/tools/arch/x86/lib/memset_64.S
@@ -1,11 +1,13 @@
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright 2002 Andi Kleen, SuSE Labs */
+#include <linux/export.h>
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
#include <asm/cpufeatures.h>
-#include <asm/alternative-asm.h>
+#include <asm/alternative.h>
-.weak memset
+.section .noinstr.text, "ax"
/*
* ISO C memset - set a memory block to a byte value. This function uses fast
@@ -17,55 +19,33 @@
* rdx count (bytes)
*
* rax original destination
- */
-SYM_FUNC_START_ALIAS(memset)
-SYM_FUNC_START(__memset)
- /*
- * Some CPUs support enhanced REP MOVSB/STOSB feature. It is recommended
- * to use it when possible. If not available, use fast string instructions.
- *
- * Otherwise, use original memset function.
- */
- ALTERNATIVE_2 "jmp memset_orig", "", X86_FEATURE_REP_GOOD, \
- "jmp memset_erms", X86_FEATURE_ERMS
-
- movq %rdi,%r9
- movq %rdx,%rcx
- andl $7,%edx
- shrq $3,%rcx
- /* expand byte value */
- movzbl %sil,%esi
- movabs $0x0101010101010101,%rax
- imulq %rsi,%rax
- rep stosq
- movl %edx,%ecx
- rep stosb
- movq %r9,%rax
- ret
-SYM_FUNC_END(__memset)
-SYM_FUNC_END_ALIAS(memset)
-
-/*
- * ISO C memset - set a memory block to a byte value. This function uses
- * enhanced rep stosb to override the fast string function.
- * The code is simpler and shorter than the fast string function as well.
*
- * rdi destination
- * rsi value (char)
- * rdx count (bytes)
+ * 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.
*
- * rax original destination
+ * 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_erms)
+SYM_TYPED_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_erms)
+ RET
+SYM_FUNC_END(__memset)
+EXPORT_SYMBOL(__memset)
+
+SYM_FUNC_ALIAS_MEMFUNC(memset, __memset)
+SYM_PIC_ALIAS(memset)
+EXPORT_SYMBOL(memset)
-SYM_FUNC_START(memset_orig)
+SYM_FUNC_START_LOCAL(memset_orig)
movq %rdi,%r10
/* expand byte value */
@@ -124,7 +104,7 @@ SYM_FUNC_START(memset_orig)
.Lende:
movq %r10,%rax
- ret
+ RET
.Lbad_alignment:
cmpq $7,%rdx
diff --git a/tools/arch/x86/lib/x86-opcode-map.txt b/tools/arch/x86/lib/x86-opcode-map.txt
index ec31f5b60323..262f7ca1fb95 100644
--- a/tools/arch/x86/lib/x86-opcode-map.txt
+++ b/tools/arch/x86/lib/x86-opcode-map.txt
@@ -23,6 +23,7 @@
#
# AVX Superscripts
# (ev): this opcode requires EVEX prefix.
+# (es): this opcode requires EVEX prefix and is SCALABALE.
# (evo): this opcode is changed by EVEX prefix (EVEX opcode)
# (v): this opcode requires VEX prefix.
# (v1): this opcode only supports 128bit VEX.
@@ -33,6 +34,10 @@
# - (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.
+#
+# REX2 Prefix Superscripts
+# - (!REX2): REX2 is not allowed
+# - (REX2): REX2 variant e.g. JMPABS
Table: one byte opcode
Referrer:
@@ -142,13 +147,13 @@ AVXcode:
# 0x60 - 0x6f
60: PUSHA/PUSHAD (i64)
61: POPA/POPAD (i64)
-62: BOUND Gv,Ma (i64) | EVEX (Prefix)
+62: BOUND Gv,Ma (i64) | EVEX (Prefix),(o64)
63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64)
64: SEG=FS (Prefix)
65: SEG=GS (Prefix)
66: Operand-Size (Prefix)
67: Address-Size (Prefix)
-68: PUSH Iz (d64)
+68: PUSH Iz
69: IMUL Gv,Ev,Iz
6a: PUSH Ib (d64)
6b: IMUL Gv,Ev,Ib
@@ -157,22 +162,22 @@ AVXcode:
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
+70: JO Jb (!REX2)
+71: JNO Jb (!REX2)
+72: JB/JNAE/JC Jb (!REX2)
+73: JNB/JAE/JNC Jb (!REX2)
+74: JZ/JE Jb (!REX2)
+75: JNZ/JNE Jb (!REX2)
+76: JBE/JNA Jb (!REX2)
+77: JNBE/JA Jb (!REX2)
+78: JS Jb (!REX2)
+79: JNS Jb (!REX2)
+7a: JP/JPE Jb (!REX2)
+7b: JNP/JPO Jb (!REX2)
+7c: JL/JNGE Jb (!REX2)
+7d: JNL/JGE Jb (!REX2)
+7e: JLE/JNG Jb (!REX2)
+7f: JNLE/JG Jb (!REX2)
# 0x80 - 0x8f
80: Grp1 Eb,Ib (1A)
81: Grp1 Ev,Iz (1A)
@@ -208,24 +213,24 @@ AVXcode:
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
+a0: MOV AL,Ob (!REX2)
+a1: MOV rAX,Ov (!REX2) | JMPABS O (REX2),(o64)
+a2: MOV Ob,AL (!REX2)
+a3: MOV Ov,rAX (!REX2)
+a4: MOVS/B Yb,Xb (!REX2)
+a5: MOVS/W/D/Q Yv,Xv (!REX2)
+a6: CMPS/B Xb,Yb (!REX2)
+a7: CMPS/W/D Xv,Yv (!REX2)
+a8: TEST AL,Ib (!REX2)
+a9: TEST rAX,Iz (!REX2)
+aa: STOS/B Yb,AL (!REX2)
+ab: STOS/W/D/Q Yv,rAX (!REX2)
+ac: LODS/B AL,Xb (!REX2)
+ad: LODS/W/D/Q rAX,Xv (!REX2)
+ae: SCAS/B AL,Yb (!REX2)
# 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
+af: SCAS/W/D/Q rAX,Yv (!REX2)
# 0xb0 - 0xbf
b0: MOV AL/R8L,Ib
b1: MOV CL/R9L,Ib
@@ -248,8 +253,8 @@ c0: Grp2 Eb,Ib (1A)
c1: Grp2 Ev,Ib (1A)
c2: RETN Iw (f64)
c3: RETN
-c4: LES Gz,Mp (i64) | VEX+2byte (Prefix)
-c5: LDS Gz,Mp (i64) | VEX+1byte (Prefix)
+c4: LES Gz,Mp (i64) | VEX+2byte (Prefix),(o64)
+c5: LDS Gz,Mp (i64) | VEX+1byte (Prefix),(o64)
c6: Grp11A Eb,Ib (1A)
c7: Grp11B Ev,Iz (1A)
c8: ENTER Iw,Ib
@@ -266,7 +271,7 @@ d1: Grp2 Ev,1 (1A)
d2: Grp2 Eb,CL (1A)
d3: Grp2 Ev,CL (1A)
d4: AAM Ib (i64)
-d5: AAD Ib (i64)
+d5: AAD Ib (i64) | REX2 (Prefix),(o64)
d6:
d7: XLAT/XLATB
d8: ESC
@@ -281,26 +286,26 @@ df: ESC
# Note: "forced64" is Intel CPU behavior: they ignore 0x66 prefix
# in 64-bit mode. AMD CPUs accept 0x66 prefix, it causes RIP truncation
# to 16 bits. In 32-bit mode, 0x66 is accepted by both Intel and AMD.
-e0: LOOPNE/LOOPNZ Jb (f64)
-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
+e0: LOOPNE/LOOPNZ Jb (f64),(!REX2)
+e1: LOOPE/LOOPZ Jb (f64),(!REX2)
+e2: LOOP Jb (f64),(!REX2)
+e3: JrCXZ Jb (f64),(!REX2)
+e4: IN AL,Ib (!REX2)
+e5: IN eAX,Ib (!REX2)
+e6: OUT Ib,AL (!REX2)
+e7: OUT Ib,eAX (!REX2)
# 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
+e8: CALL Jz (f64),(!REX2)
+e9: JMP-near Jz (f64),(!REX2)
+ea: JMP-far Ap (i64),(!REX2)
+eb: JMP-short Jb (f64),(!REX2)
+ec: IN AL,DX (!REX2)
+ed: IN eAX,DX (!REX2)
+ee: OUT DX,AL (!REX2)
+ef: OUT DX,eAX (!REX2)
# 0xf0 - 0xff
f0: LOCK (Prefix)
f1:
@@ -386,14 +391,14 @@ AVXcode: 1
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
+30: WRMSR (!REX2)
+31: RDTSC (!REX2)
+32: RDMSR (!REX2)
+33: RDPMC (!REX2)
+34: SYSENTER (!REX2)
+35: SYSEXIT (!REX2)
36:
-37: GETSEC
+37: GETSEC (!REX2)
38: escape # 3-byte escape 1
39:
3a: escape # 3-byte escape 2
@@ -473,22 +478,22 @@ AVXcode: 1
7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev)
# 0x0f 0x80-0x8f
# Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
-80: JO Jz (f64)
-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)
+80: JO Jz (f64),(!REX2)
+81: JNO Jz (f64),(!REX2)
+82: JB/JC/JNAE Jz (f64),(!REX2)
+83: JAE/JNB/JNC Jz (f64),(!REX2)
+84: JE/JZ Jz (f64),(!REX2)
+85: JNE/JNZ Jz (f64),(!REX2)
+86: JBE/JNA Jz (f64),(!REX2)
+87: JA/JNBE Jz (f64),(!REX2)
+88: JS Jz (f64),(!REX2)
+89: JNS Jz (f64),(!REX2)
+8a: JP/JPE Jz (f64),(!REX2)
+8b: JNP/JPO Jz (f64),(!REX2)
+8c: JL/JNGE Jz (f64),(!REX2)
+8d: JNL/JGE Jz (f64),(!REX2)
+8e: JLE/JNG Jz (f64),(!REX2)
+8f: JNLE/JG Jz (f64),(!REX2)
# 0x0f 0x90-0x9f
90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66)
91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66)
@@ -690,32 +695,40 @@ AVXcode: 2
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 0x48-0x4b
+# 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)
+50: vpdpbusd Vx,Hx,Wx (66) | vpdpbssd Vx,Hx,Wx (F2),(v) | vpdpbsud Vx,Hx,Wx (F3),(v) | vpdpbuud Vx,Hx,Wx (v)
+51: vpdpbusds Vx,Hx,Wx (66) | vpdpbssds Vx,Hx,Wx (F2),(v) | vpdpbsuds Vx,Hx,Wx (F3),(v) | vpdpbuuds Vx,Hx,Wx (v)
+52: vdpbf16ps Vx,Hx,Wx (F3),(ev) | vpdpwssd Vx,Hx,Wx (66) | vp4dpwssd Vdqq,Hdqq,Wdq (F2),(ev)
+53: vpdpwssds Vx,Hx,Wx (66) | 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)
-# Skip 0x5c-0x61
+5c: TDPBF16PS Vt,Wt,Ht (F3),(v1) | TDPFP16PS Vt,Wt,Ht (F2),(v1),(o64)
+# 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
+# Skip 0x69-0x6b
+6c: TCMMIMFP16PS Vt,Wt,Ht (66),(v1),(o64) | TCMMRLFP16PS Vt,Wt,Ht (v1),(o64)
+# Skip 0x6d-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)
+72: vcvtne2ps2bf16 Vx,Hx,Wx (F2),(ev) | vcvtneps2bf16 Vx,Wx (F3) | 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)
@@ -771,8 +784,10 @@ 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)
+b0: vcvtneebf162ps Vx,Mx (F3),(!11B),(v) | vcvtneeph2ps Vx,Mx (66),(!11B),(v) | vcvtneobf162ps Vx,Mx (F2),(!11B),(v) | vcvtneoph2ps Vx,Mx (!11B),(v)
+b1: vbcstnebf162ps Vx,Mw (F3),(!11B),(v) | vbcstnesh2ps Vx,Mw (66),(!11B),(v)
+b4: vpmadd52luq Vx,Hx,Wx (66)
+b5: vpmadd52huq Vx,Hx,Wx (66)
b6: vfmaddsub231ps/d Vx,Hx,Wx (66),(v)
b7: vfmsubadd231ps/d Vx,Hx,Wx (66),(v)
b8: vfmadd231ps/d Vx,Hx,Wx (66),(v)
@@ -790,15 +805,35 @@ 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)
+cb: sha256rnds2 Vdq,Wdq | vrcp28ss/d Vx,Hx,Wx (66),(ev) | vsha512rnds2 Vqq,Hqq,Udq (F2),(11B),(v)
+cc: sha256msg1 Vdq,Wdq | vrsqrt28ps/d Vx,Wx (66),(ev) | vsha512msg1 Vqq,Udq (F2),(11B),(v)
+cd: sha256msg2 Vdq,Wdq | vrsqrt28ss/d Vx,Hx,Wx (66),(ev) | vsha512msg2 Vqq,Uqq (F2),(11B),(v)
cf: vgf2p8mulb Vx,Wx (66)
+d2: vpdpwsud Vx,Hx,Wx (F3),(v) | vpdpwusd Vx,Hx,Wx (66),(v) | vpdpwuud Vx,Hx,Wx (v)
+d3: vpdpwsuds Vx,Hx,Wx (F3),(v) | vpdpwusds Vx,Hx,Wx (66),(v) | vpdpwuuds Vx,Hx,Wx (v)
+d8: AESENCWIDE128KL Qpi (F3),(000),(00B) | AESENCWIDE256KL Qpi (F3),(000),(10B) | AESDECWIDE128KL Qpi (F3),(000),(01B) | AESDECWIDE256KL Qpi (F3),(000),(11B)
+da: vsm3msg1 Vdq,Hdq,Udq (v1) | vsm3msg2 Vdq,Hdq,Udq (66),(v1) | vsm4key4 Vx,Hx,Wx (F3),(v) | vsm4rnds4 Vx,Hx,Wx (F2),(v)
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)
+dc: vaesenc Vx,Hx,Wx (66) | LOADIWKEY Vx,Hx (F3) | AESENC128KL Vpd,Qpi (F3)
+dd: vaesenclast Vx,Hx,Wx (66) | AESDEC128KL Vpd,Qpi (F3)
+de: vaesdec Vx,Hx,Wx (66) | AESENC256KL Vpd,Qpi (F3)
+df: vaesdeclast Vx,Hx,Wx (66) | AESDEC256KL Vpd,Qpi (F3)
+e0: CMPOXADD My,Gy,By (66),(v1),(o64)
+e1: CMPNOXADD My,Gy,By (66),(v1),(o64)
+e2: CMPBXADD My,Gy,By (66),(v1),(o64)
+e3: CMPNBXADD My,Gy,By (66),(v1),(o64)
+e4: CMPZXADD My,Gy,By (66),(v1),(o64)
+e5: CMPNZXADD My,Gy,By (66),(v1),(o64)
+e6: CMPBEXADD My,Gy,By (66),(v1),(o64)
+e7: CMPNBEXADD My,Gy,By (66),(v1),(o64)
+e8: CMPSXADD My,Gy,By (66),(v1),(o64)
+e9: CMPNSXADD My,Gy,By (66),(v1),(o64)
+ea: CMPPXADD My,Gy,By (66),(v1),(o64)
+eb: CMPNPXADD My,Gy,By (66),(v1),(o64)
+ec: CMPLXADD My,Gy,By (66),(v1),(o64)
+ed: CMPNLXADD My,Gy,By (66),(v1),(o64)
+ee: CMPLEXADD My,Gy,By (66),(v1),(o64)
+ef: CMPNLEXADD My,Gy,By (66),(v1),(o64)
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)
@@ -806,8 +841,11 @@ 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)
+f8: MOVDIR64B Gv,Mdqq (66) | ENQCMD Gv,Mdqq (F2) | ENQCMDS Gv,Mdqq (F3) | URDMSR Rq,Gq (F2),(11B) | UWRMSR Gq,Rq (F3),(11B)
f9: MOVDIRI My,Gy
+fa: ENCODEKEY128 Ew,Ew (F3)
+fb: ENCODEKEY256 Ew,Ew (F3)
+fc: AADD My,Gy | AAND My,Gy (66) | AOR My,Gy (F2) | AXOR My,Gy (F3)
EndTable
Table: 3-byte opcode 2 (0x0f 0x3a)
@@ -822,9 +860,9 @@ AVXcode: 3
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)
+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)
+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)
@@ -846,8 +884,8 @@ AVXcode: 3
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)
-27: vgetmantss/d 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)
@@ -871,23 +909,201 @@ AVXcode: 3
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)
-57: vreducess/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)
-67: vfpclassss/d Vk,Wx,Ib (66),(ev)
+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)
+de: vsm3rnds2 Vdq,Hdq,Wdq,Ib (66),(v1)
df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
-f0: RORX Gy,Ey,Ib (F2),(v)
+f0: RORX Gy,Ey,Ib (F2),(v) | HRESET Gv,Ib (F3),(000),(11B)
+EndTable
+
+Table: EVEX map 4
+Referrer:
+AVXcode: 4
+00: ADD Eb,Gb (ev)
+01: ADD Ev,Gv (es) | ADD Ev,Gv (66),(es)
+02: ADD Gb,Eb (ev)
+03: ADD Gv,Ev (es) | ADD Gv,Ev (66),(es)
+08: OR Eb,Gb (ev)
+09: OR Ev,Gv (es) | OR Ev,Gv (66),(es)
+0a: OR Gb,Eb (ev)
+0b: OR Gv,Ev (es) | OR Gv,Ev (66),(es)
+10: ADC Eb,Gb (ev)
+11: ADC Ev,Gv (es) | ADC Ev,Gv (66),(es)
+12: ADC Gb,Eb (ev)
+13: ADC Gv,Ev (es) | ADC Gv,Ev (66),(es)
+18: SBB Eb,Gb (ev)
+19: SBB Ev,Gv (es) | SBB Ev,Gv (66),(es)
+1a: SBB Gb,Eb (ev)
+1b: SBB Gv,Ev (es) | SBB Gv,Ev (66),(es)
+20: AND Eb,Gb (ev)
+21: AND Ev,Gv (es) | AND Ev,Gv (66),(es)
+22: AND Gb,Eb (ev)
+23: AND Gv,Ev (es) | AND Gv,Ev (66),(es)
+24: SHLD Ev,Gv,Ib (es) | SHLD Ev,Gv,Ib (66),(es)
+28: SUB Eb,Gb (ev)
+29: SUB Ev,Gv (es) | SUB Ev,Gv (66),(es)
+2a: SUB Gb,Eb (ev)
+2b: SUB Gv,Ev (es) | SUB Gv,Ev (66),(es)
+2c: SHRD Ev,Gv,Ib (es) | SHRD Ev,Gv,Ib (66),(es)
+30: XOR Eb,Gb (ev)
+31: XOR Ev,Gv (es) | XOR Ev,Gv (66),(es)
+32: XOR Gb,Eb (ev)
+33: XOR Gv,Ev (es) | XOR Gv,Ev (66),(es)
+# CCMPSCC instructions are: CCOMB, CCOMBE, CCOMF, CCOML, CCOMLE, CCOMNB, CCOMNBE, CCOMNL, CCOMNLE,
+# CCOMNO, CCOMNS, CCOMNZ, CCOMO, CCOMS, CCOMT, CCOMZ
+38: CCMPSCC Eb,Gb (ev)
+39: CCMPSCC Ev,Gv (es) | CCMPSCC Ev,Gv (66),(es)
+3a: CCMPSCC Gv,Ev (ev)
+3b: CCMPSCC Gv,Ev (es) | CCMPSCC Gv,Ev (66),(es)
+40: CMOVO Gv,Ev (es) | CMOVO Gv,Ev (66),(es) | CFCMOVO Ev,Ev (es) | CFCMOVO Ev,Ev (66),(es) | SETO Eb (F2),(ev)
+41: CMOVNO Gv,Ev (es) | CMOVNO Gv,Ev (66),(es) | CFCMOVNO Ev,Ev (es) | CFCMOVNO Ev,Ev (66),(es) | SETNO Eb (F2),(ev)
+42: CMOVB Gv,Ev (es) | CMOVB Gv,Ev (66),(es) | CFCMOVB Ev,Ev (es) | CFCMOVB Ev,Ev (66),(es) | SETB Eb (F2),(ev)
+43: CMOVNB Gv,Ev (es) | CMOVNB Gv,Ev (66),(es) | CFCMOVNB Ev,Ev (es) | CFCMOVNB Ev,Ev (66),(es) | SETNB Eb (F2),(ev)
+44: CMOVZ Gv,Ev (es) | CMOVZ Gv,Ev (66),(es) | CFCMOVZ Ev,Ev (es) | CFCMOVZ Ev,Ev (66),(es) | SETZ Eb (F2),(ev)
+45: CMOVNZ Gv,Ev (es) | CMOVNZ Gv,Ev (66),(es) | CFCMOVNZ Ev,Ev (es) | CFCMOVNZ Ev,Ev (66),(es) | SETNZ Eb (F2),(ev)
+46: CMOVBE Gv,Ev (es) | CMOVBE Gv,Ev (66),(es) | CFCMOVBE Ev,Ev (es) | CFCMOVBE Ev,Ev (66),(es) | SETBE Eb (F2),(ev)
+47: CMOVNBE Gv,Ev (es) | CMOVNBE Gv,Ev (66),(es) | CFCMOVNBE Ev,Ev (es) | CFCMOVNBE Ev,Ev (66),(es) | SETNBE Eb (F2),(ev)
+48: CMOVS Gv,Ev (es) | CMOVS Gv,Ev (66),(es) | CFCMOVS Ev,Ev (es) | CFCMOVS Ev,Ev (66),(es) | SETS Eb (F2),(ev)
+49: CMOVNS Gv,Ev (es) | CMOVNS Gv,Ev (66),(es) | CFCMOVNS Ev,Ev (es) | CFCMOVNS Ev,Ev (66),(es) | SETNS Eb (F2),(ev)
+4a: CMOVP Gv,Ev (es) | CMOVP Gv,Ev (66),(es) | CFCMOVP Ev,Ev (es) | CFCMOVP Ev,Ev (66),(es) | SETP Eb (F2),(ev)
+4b: CMOVNP Gv,Ev (es) | CMOVNP Gv,Ev (66),(es) | CFCMOVNP Ev,Ev (es) | CFCMOVNP Ev,Ev (66),(es) | SETNP Eb (F2),(ev)
+4c: CMOVL Gv,Ev (es) | CMOVL Gv,Ev (66),(es) | CFCMOVL Ev,Ev (es) | CFCMOVL Ev,Ev (66),(es) | SETL Eb (F2),(ev)
+4d: CMOVNL Gv,Ev (es) | CMOVNL Gv,Ev (66),(es) | CFCMOVNL Ev,Ev (es) | CFCMOVNL Ev,Ev (66),(es) | SETNL Eb (F2),(ev)
+4e: CMOVLE Gv,Ev (es) | CMOVLE Gv,Ev (66),(es) | CFCMOVLE Ev,Ev (es) | CFCMOVLE Ev,Ev (66),(es) | SETLE Eb (F2),(ev)
+4f: CMOVNLE Gv,Ev (es) | CMOVNLE Gv,Ev (66),(es) | CFCMOVNLE Ev,Ev (es) | CFCMOVNLE Ev,Ev (66),(es) | SETNLE Eb (F2),(ev)
+60: MOVBE Gv,Ev (es) | MOVBE Gv,Ev (66),(es)
+61: MOVBE Ev,Gv (es) | MOVBE Ev,Gv (66),(es)
+65: WRUSSD Md,Gd (66),(ev) | WRUSSQ Mq,Gq (66),(ev)
+66: ADCX Gy,Ey (66),(ev) | ADOX Gy,Ey (F3),(ev) | WRSSD Md,Gd (ev) | WRSSQ Mq,Gq (66),(ev)
+69: IMUL Gv,Ev,Iz (es) | IMUL Gv,Ev,Iz (66),(es)
+6b: IMUL Gv,Ev,Ib (es) | IMUL Gv,Ev,Ib (66),(es)
+80: Grp1 Eb,Ib (1A),(ev)
+81: Grp1 Ev,Iz (1A),(es)
+83: Grp1 Ev,Ib (1A),(es)
+# CTESTSCC instructions are: CTESTB, CTESTBE, CTESTF, CTESTL, CTESTLE, CTESTNB, CTESTNBE, CTESTNL,
+# CTESTNLE, CTESTNO, CTESTNS, CTESTNZ, CTESTO, CTESTS, CTESTT, CTESTZ
+84: CTESTSCC Eb,Gb (ev)
+85: CTESTSCC Ev,Gv (es) | CTESTSCC Ev,Gv (66),(es)
+88: POPCNT Gv,Ev (es) | POPCNT Gv,Ev (66),(es)
+8f: POP2 Bq,Rq (000),(11B),(ev)
+a5: SHLD Ev,Gv,CL (es) | SHLD Ev,Gv,CL (66),(es)
+ad: SHRD Ev,Gv,CL (es) | SHRD Ev,Gv,CL (66),(es)
+af: IMUL Gv,Ev (es) | IMUL Gv,Ev (66),(es)
+c0: Grp2 Eb,Ib (1A),(ev)
+c1: Grp2 Ev,Ib (1A),(es)
+d0: Grp2 Eb,1 (1A),(ev)
+d1: Grp2 Ev,1 (1A),(es)
+d2: Grp2 Eb,CL (1A),(ev)
+d3: Grp2 Ev,CL (1A),(es)
+f0: CRC32 Gy,Eb (es) | INVEPT Gq,Mdq (F3),(ev)
+f1: CRC32 Gy,Ey (es) | CRC32 Gy,Ey (66),(es) | INVVPID Gy,Mdq (F3),(ev)
+f2: INVPCID Gy,Mdq (F3),(ev)
+f4: TZCNT Gv,Ev (es) | TZCNT Gv,Ev (66),(es)
+f5: LZCNT Gv,Ev (es) | LZCNT Gv,Ev (66),(es)
+f6: Grp3_1 Eb (1A),(ev)
+f7: Grp3_2 Ev (1A),(es)
+f8: MOVDIR64B Gv,Mdqq (66),(ev) | ENQCMD Gv,Mdqq (F2),(ev) | ENQCMDS Gv,Mdqq (F3),(ev) | URDMSR Rq,Gq (F2),(11B),(ev) | UWRMSR Gq,Rq (F3),(11B),(ev)
+f9: MOVDIRI My,Gy (ev)
+fe: Grp4 (1A),(ev)
+ff: Grp5 (1A),(es) | PUSH2 Bq,Rq (110),(11B),(ev)
+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
+
+Table: VEX map 7
+Referrer:
+AVXcode: 7
+f8: URDMSR Rq,Id (F2),(v1),(11B) | UWRMSR Id,Rq (F3),(v1),(11B)
EndTable
GrpTable: Grp1
@@ -962,15 +1178,16 @@ GrpTable: Grp6
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)
+0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) | WRMSRNS (110),(11B) | RDMSRLIST (F2),(110),(11B) | WRMSRLIST (F3),(110),(11B) | PBNDKB (111),(11B)
+1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B) | ERETU (F3),(010),(11B) | ERETS (F2),(010),(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)
+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
@@ -987,7 +1204,7 @@ GrpTable: Grp9
3: xrstors
4: xsavec
5: xsaves
-6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B)
+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
@@ -1051,6 +1268,8 @@ GrpTable: Grp16
1: prefetch T0
2: prefetch T1
3: prefetch T2
+6: prefetch IT1
+7: prefetch IT0
EndTable
GrpTable: Grp17
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.