summaryrefslogtreecommitdiff
path: root/tools/arch/x86/lib
diff options
context:
space:
mode:
Diffstat (limited to 'tools/arch/x86/lib')
-rw-r--r--tools/arch/x86/lib/inat.c13
-rw-r--r--tools/arch/x86/lib/insn.c42
-rw-r--r--tools/arch/x86/lib/memcpy_64.S1
-rw-r--r--tools/arch/x86/lib/memset_64.S4
-rw-r--r--tools/arch/x86/lib/x86-opcode-map.txt171
5 files changed, 189 insertions, 42 deletions
diff --git a/tools/arch/x86/lib/inat.c b/tools/arch/x86/lib/inat.c
index dfbcc6405941..ffcb0e27453b 100644
--- a/tools/arch/x86/lib/inat.c
+++ b/tools/arch/x86/lib/inat.c
@@ -81,3 +81,16 @@ insn_attr_t inat_get_avx_attribute(insn_byte_t opcode, insn_byte_t vex_m,
return table[opcode];
}
+insn_attr_t inat_get_xop_attribute(insn_byte_t opcode, insn_byte_t map_select)
+{
+ const insn_attr_t *table;
+
+ if (map_select < X86_XOP_M_MIN || map_select > X86_XOP_M_MAX)
+ return 0;
+ map_select -= X86_XOP_M_MIN;
+ /* At first, this checks the master table */
+ table = inat_xop_tables[map_select];
+ if (!table)
+ return 0;
+ return table[opcode];
+}
diff --git a/tools/arch/x86/lib/insn.c b/tools/arch/x86/lib/insn.c
index e91d4c4e1c16..1d1c57c74d1f 100644
--- a/tools/arch/x86/lib/insn.c
+++ b/tools/arch/x86/lib/insn.c
@@ -200,12 +200,15 @@ found:
}
insn->rex_prefix.got = 1;
- /* Decode VEX prefix */
+ /* Decode VEX/XOP prefix */
b = peek_next(insn_byte_t, insn);
- attr = inat_get_opcode_attribute(b);
- if (inat_is_vex_prefix(attr)) {
+ if (inat_is_vex_prefix(attr) || inat_is_xop_prefix(attr)) {
insn_byte_t b2 = peek_nbyte_next(insn_byte_t, insn, 1);
- if (!insn->x86_64) {
+
+ if (inat_is_xop_prefix(attr) && X86_MODRM_REG(b2) == 0) {
+ /* Grp1A.0 is always POP Ev */
+ goto vex_end;
+ } else 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
@@ -226,13 +229,13 @@ found:
if (insn->x86_64 && X86_VEX_W(b2))
/* VEX.W overrides opnd_size */
insn->opnd_bytes = 8;
- } else if (inat_is_vex3_prefix(attr)) {
+ } else if (inat_is_vex3_prefix(attr) || inat_is_xop_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 */
+ /* VEX.W/XOP.W overrides opnd_size */
insn->opnd_bytes = 8;
} else {
/*
@@ -288,9 +291,22 @@ int insn_get_opcode(struct insn *insn)
insn_set_byte(opcode, 0, op);
opcode->nbytes = 1;
- /* Check if there is VEX prefix or not */
- if (insn_is_avx(insn)) {
+ /* Check if there is VEX/XOP prefix or not */
+ if (insn_is_avx_or_xop(insn)) {
insn_byte_t m, p;
+
+ /* XOP prefix has different encoding */
+ if (unlikely(avx_insn_is_xop(insn))) {
+ m = insn_xop_map_bits(insn);
+ insn->attr = inat_get_xop_attribute(op, m);
+ if (!inat_accept_xop(insn->attr)) {
+ insn->attr = 0;
+ return -EINVAL;
+ }
+ /* XOP has only 1 byte for opcode */
+ goto end;
+ }
+
m = insn_vex_m_bits(insn);
p = insn_vex_p_bits(insn);
insn->attr = inat_get_avx_attribute(op, m, p);
@@ -324,6 +340,11 @@ int insn_get_opcode(struct insn *insn)
}
insn->attr = inat_get_opcode_attribute(op);
+ if (insn->x86_64 && inat_is_invalid64(insn->attr)) {
+ /* This instruction is invalid, like UD2. Stop decoding. */
+ insn->attr &= INAT_INV64;
+ }
+
while (inat_is_escape(insn->attr)) {
/* Get escaped opcode */
op = get_next(insn_byte_t, insn);
@@ -337,6 +358,7 @@ int insn_get_opcode(struct insn *insn)
insn->attr = 0;
return -EINVAL;
}
+
end:
opcode->got = 1;
return 0;
@@ -377,7 +399,8 @@ int insn_get_modrm(struct insn *insn)
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)) {
+ if (insn_is_avx_or_xop(insn) && !inat_accept_vex(insn->attr) &&
+ !inat_accept_xop(insn->attr)) {
/* Bad insn */
insn->attr = 0;
return -EINVAL;
@@ -658,7 +681,6 @@ int insn_get_immediate(struct insn *insn)
}
if (!inat_has_immediate(insn->attr))
- /* no immediates */
goto done;
switch (inat_immediate_size(insn->attr)) {
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index 59cf6f9065aa..ccc3d923fc1e 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -40,6 +40,7 @@ SYM_FUNC_END(__memcpy)
EXPORT_SYMBOL(__memcpy)
SYM_FUNC_ALIAS_MEMFUNC(memcpy, __memcpy)
+SYM_PIC_ALIAS(memcpy)
EXPORT_SYMBOL(memcpy)
SYM_FUNC_START_LOCAL(memcpy_orig)
diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S
index 0199d56cb479..fb5a03cf5ab7 100644
--- a/tools/arch/x86/lib/memset_64.S
+++ b/tools/arch/x86/lib/memset_64.S
@@ -3,6 +3,7 @@
#include <linux/export.h>
#include <linux/linkage.h>
+#include <linux/cfi_types.h>
#include <asm/cpufeatures.h>
#include <asm/alternative.h>
@@ -28,7 +29,7 @@
* only for the return value that is the same as the source input,
* which the compiler could/should do much better anyway.
*/
-SYM_FUNC_START(__memset)
+SYM_TYPED_FUNC_START(__memset)
ALTERNATIVE "jmp memset_orig", "", X86_FEATURE_FSRS
movq %rdi,%r9
@@ -41,6 +42,7 @@ SYM_FUNC_END(__memset)
EXPORT_SYMBOL(__memset)
SYM_FUNC_ALIAS_MEMFUNC(memset, __memset)
+SYM_PIC_ALIAS(memset)
EXPORT_SYMBOL(memset)
SYM_FUNC_START_LOCAL(memset_orig)
diff --git a/tools/arch/x86/lib/x86-opcode-map.txt b/tools/arch/x86/lib/x86-opcode-map.txt
index caedb3ef6688..2a4e69ecc2de 100644
--- a/tools/arch/x86/lib/x86-opcode-map.txt
+++ b/tools/arch/x86/lib/x86-opcode-map.txt
@@ -27,6 +27,11 @@
# (evo): this opcode is changed by EVEX prefix (EVEX opcode)
# (v): this opcode requires VEX prefix.
# (v1): this opcode only supports 128bit VEX.
+# (xop): this opcode accepts XOP prefix.
+#
+# XOP Superscripts
+# (W=0): this opcode requires XOP.W == 0
+# (W=1): this opcode requires XOP.W == 1
#
# Last Prefix Superscripts
# - (66): the last prefix is 0x66
@@ -35,7 +40,7 @@
# - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
# - (66&F2): Both 0x66 and 0xF2 prefixes are specified.
#
-# REX2 Prefix
+# REX2 Prefix Superscripts
# - (!REX2): REX2 is not allowed
# - (REX2): REX2 variant e.g. JMPABS
@@ -147,7 +152,7 @@ AVXcode:
# 0x60 - 0x6f
60: PUSHA/PUSHAD (i64)
61: POPA/POPAD (i64)
-62: BOUND Gv,Ma (i64) | EVEX (Prefix)
+62: BOUND Gv,Ma (i64) | EVEX (Prefix),(o64)
63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64)
64: SEG=FS (Prefix)
65: SEG=GS (Prefix)
@@ -194,7 +199,7 @@ AVXcode:
8c: MOV Ev,Sw
8d: LEA Gv,M
8e: MOV Sw,Ew
-8f: Grp1A (1A) | POP Ev (d64)
+8f: Grp1A (1A) | POP Ev (d64) | XOP (Prefix)
# 0x90 - 0x9f
90: NOP | PAUSE (F3) | XCHG r8,rAX
91: XCHG rCX/r9,rAX
@@ -253,8 +258,8 @@ c0: Grp2 Eb,Ib (1A)
c1: Grp2 Ev,Ib (1A)
c2: RETN Iw (f64)
c3: RETN
-c4: LES Gz,Mp (i64) | VEX+2byte (Prefix)
-c5: LDS Gz,Mp (i64) | VEX+1byte (Prefix)
+c4: LES Gz,Mp (i64) | VEX+2byte (Prefix),(o64)
+c5: LDS Gz,Mp (i64) | VEX+1byte (Prefix),(o64)
c6: Grp11A Eb,Ib (1A)
c7: Grp11B Ev,Iz (1A)
c8: ENTER Iw,Ib
@@ -286,10 +291,10 @@ df: ESC
# Note: "forced64" is Intel CPU behavior: they ignore 0x66 prefix
# in 64-bit mode. AMD CPUs accept 0x66 prefix, it causes RIP truncation
# to 16 bits. In 32-bit mode, 0x66 is accepted by both Intel and AMD.
-e0: LOOPNE/LOOPNZ Jb (f64) (!REX2)
-e1: LOOPE/LOOPZ Jb (f64) (!REX2)
-e2: LOOP Jb (f64) (!REX2)
-e3: JrCXZ Jb (f64) (!REX2)
+e0: LOOPNE/LOOPNZ Jb (f64),(!REX2)
+e1: LOOPE/LOOPZ Jb (f64),(!REX2)
+e2: LOOP Jb (f64),(!REX2)
+e3: JrCXZ Jb (f64),(!REX2)
e4: IN AL,Ib (!REX2)
e5: IN eAX,Ib (!REX2)
e6: OUT Ib,AL (!REX2)
@@ -298,10 +303,10 @@ e7: OUT Ib,eAX (!REX2)
# in "near" jumps and calls is 16-bit. For CALL,
# push of return address is 16-bit wide, RSP is decremented by 2
# but is not truncated to 16 bits, unlike RIP.
-e8: CALL Jz (f64) (!REX2)
-e9: JMP-near Jz (f64) (!REX2)
-ea: JMP-far Ap (i64) (!REX2)
-eb: JMP-short Jb (f64) (!REX2)
+e8: CALL Jz (f64),(!REX2)
+e9: JMP-near Jz (f64),(!REX2)
+ea: JMP-far Ap (i64),(!REX2)
+eb: JMP-short Jb (f64),(!REX2)
ec: IN AL,DX (!REX2)
ed: IN eAX,DX (!REX2)
ee: OUT DX,AL (!REX2)
@@ -478,22 +483,22 @@ AVXcode: 1
7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev)
# 0x0f 0x80-0x8f
# Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
-80: JO Jz (f64) (!REX2)
-81: JNO Jz (f64) (!REX2)
-82: JB/JC/JNAE Jz (f64) (!REX2)
-83: JAE/JNB/JNC Jz (f64) (!REX2)
-84: JE/JZ Jz (f64) (!REX2)
-85: JNE/JNZ Jz (f64) (!REX2)
-86: JBE/JNA Jz (f64) (!REX2)
-87: JA/JNBE Jz (f64) (!REX2)
-88: JS Jz (f64) (!REX2)
-89: JNS Jz (f64) (!REX2)
-8a: JP/JPE Jz (f64) (!REX2)
-8b: JNP/JPO Jz (f64) (!REX2)
-8c: JL/JNGE Jz (f64) (!REX2)
-8d: JNL/JGE Jz (f64) (!REX2)
-8e: JLE/JNG Jz (f64) (!REX2)
-8f: JNLE/JG Jz (f64) (!REX2)
+80: JO Jz (f64),(!REX2)
+81: JNO Jz (f64),(!REX2)
+82: JB/JC/JNAE Jz (f64),(!REX2)
+83: JAE/JNB/JNC Jz (f64),(!REX2)
+84: JE/JZ Jz (f64),(!REX2)
+85: JNE/JNZ Jz (f64),(!REX2)
+86: JBE/JNA Jz (f64),(!REX2)
+87: JA/JNBE Jz (f64),(!REX2)
+88: JS Jz (f64),(!REX2)
+89: JNS Jz (f64),(!REX2)
+8a: JP/JPE Jz (f64),(!REX2)
+8b: JNP/JPO Jz (f64),(!REX2)
+8c: JL/JNGE Jz (f64),(!REX2)
+8d: JNL/JGE Jz (f64),(!REX2)
+8e: JLE/JNG Jz (f64),(!REX2)
+8f: JNLE/JG Jz (f64),(!REX2)
# 0x0f 0x90-0x9f
90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66)
91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66)
@@ -996,8 +1001,8 @@ AVXcode: 4
83: Grp1 Ev,Ib (1A),(es)
# CTESTSCC instructions are: CTESTB, CTESTBE, CTESTF, CTESTL, CTESTLE, CTESTNB, CTESTNBE, CTESTNL,
# CTESTNLE, CTESTNO, CTESTNS, CTESTNZ, CTESTO, CTESTS, CTESTT, CTESTZ
-84: CTESTSCC (ev)
-85: CTESTSCC (es) | CTESTSCC (66),(es)
+84: CTESTSCC Eb,Gb (ev)
+85: CTESTSCC Ev,Gv (es) | CTESTSCC Ev,Gv (66),(es)
88: POPCNT Gv,Ev (es) | POPCNT Gv,Ev (66),(es)
8f: POP2 Bq,Rq (000),(11B),(ev)
a5: SHLD Ev,Gv,CL (es) | SHLD Ev,Gv,CL (66),(es)
@@ -1106,6 +1111,84 @@ AVXcode: 7
f8: URDMSR Rq,Id (F2),(v1),(11B) | UWRMSR Id,Rq (F3),(v1),(11B)
EndTable
+# From AMD64 Architecture Programmer's Manual Vol3, Appendix A.1.5
+Table: XOP map 8h
+Referrer:
+XOPcode: 0
+85: VPMACSSWW Vo,Ho,Wo,Lo
+86: VPMACSSWD Vo,Ho,Wo,Lo
+87: VPMACSSDQL Vo,Ho,Wo,Lo
+8e: VPMACSSDD Vo,Ho,Wo,Lo
+8f: VPMACSSDQH Vo,Ho,Wo,Lo
+95: VPMACSWW Vo,Ho,Wo,Lo
+96: VPMACSWD Vo,Ho,Wo,Lo
+97: VPMACSDQL Vo,Ho,Wo,Lo
+9e: VPMACSDD Vo,Ho,Wo,Lo
+9f: VPMACSDQH Vo,Ho,Wo,Lo
+a2: VPCMOV Vx,Hx,Wx,Lx (W=0) | VPCMOV Vx,Hx,Lx,Wx (W=1)
+a3: VPPERM Vo,Ho,Wo,Lo (W=0) | VPPERM Vo,Ho,Lo,Wo (W=1)
+a6: VPMADCSSWD Vo,Ho,Wo,Lo
+b6: VPMADCSWD Vo,Ho,Wo,Lo
+c0: VPROTB Vo,Wo,Ib
+c1: VPROTW Vo,Wo,Ib
+c2: VPROTD Vo,Wo,Ib
+c3: VPROTQ Vo,Wo,Ib
+cc: VPCOMccB Vo,Ho,Wo,Ib
+cd: VPCOMccW Vo,Ho,Wo,Ib
+ce: VPCOMccD Vo,Ho,Wo,Ib
+cf: VPCOMccQ Vo,Ho,Wo,Ib
+ec: VPCOMccUB Vo,Ho,Wo,Ib
+ed: VPCOMccUW Vo,Ho,Wo,Ib
+ee: VPCOMccUD Vo,Ho,Wo,Ib
+ef: VPCOMccUQ Vo,Ho,Wo,Ib
+EndTable
+
+Table: XOP map 9h
+Referrer:
+XOPcode: 1
+01: GrpXOP1
+02: GrpXOP2
+12: GrpXOP3
+80: VFRCZPS Vx,Wx
+81: VFRCZPD Vx,Wx
+82: VFRCZSS Vq,Wss
+83: VFRCZSD Vq,Wsd
+90: VPROTB Vo,Wo,Ho (W=0) | VPROTB Vo,Ho,Wo (W=1)
+91: VPROTW Vo,Wo,Ho (W=0) | VPROTB Vo,Ho,Wo (W=1)
+92: VPROTD Vo,Wo,Ho (W=0) | VPROTB Vo,Ho,Wo (W=1)
+93: VPROTQ Vo,Wo,Ho (W=0) | VPROTB Vo,Ho,Wo (W=1)
+94: VPSHLB Vo,Wo,Ho (W=0) | VPSHLB Vo,Ho,Wo (W=1)
+95: VPSHLW Vo,Wo,Ho (W=0) | VPSHLW Vo,Ho,Wo (W=1)
+96: VPSHLD Vo,Wo,Ho (W=0) | VPSHLD Vo,Ho,Wo (W=1)
+97: VPSHLQ Vo,Wo,Ho (W=0) | VPSHLQ Vo,Ho,Wo (W=1)
+98: VPSHAB Vo,Wo,Ho (W=0) | VPSHAB Vo,Ho,Wo (W=1)
+99: VPSHAW Vo,Wo,Ho (W=0) | VPSHAW Vo,Ho,Wo (W=1)
+9a: VPSHAD Vo,Wo,Ho (W=0) | VPSHAD Vo,Ho,Wo (W=1)
+9b: VPSHAQ Vo,Wo,Ho (W=0) | VPSHAQ Vo,Ho,Wo (W=1)
+c1: VPHADDBW Vo,Wo
+c2: VPHADDBD Vo,Wo
+c3: VPHADDBQ Vo,Wo
+c6: VPHADDWD Vo,Wo
+c7: VPHADDWQ Vo,Wo
+cb: VPHADDDQ Vo,Wo
+d1: VPHADDUBWD Vo,Wo
+d2: VPHADDUBD Vo,Wo
+d3: VPHADDUBQ Vo,Wo
+d6: VPHADDUWD Vo,Wo
+d7: VPHADDUWQ Vo,Wo
+db: VPHADDUDQ Vo,Wo
+e1: VPHSUBBW Vo,Wo
+e2: VPHSUBWD Vo,Wo
+e3: VPHSUBDQ Vo,Wo
+EndTable
+
+Table: XOP map Ah
+Referrer:
+XOPcode: 2
+10: BEXTR Gy,Ey,Id
+12: GrpXOP4
+EndTable
+
GrpTable: Grp1
0: ADD
1: OR
@@ -1320,3 +1403,29 @@ GrpTable: GrpRNG
4: xcrypt-cfb
5: xcrypt-ofb
EndTable
+
+# GrpXOP1-4 is shown in AMD APM Vol.3 Appendix A as XOP group #1-4
+GrpTable: GrpXOP1
+1: BLCFILL By,Ey (xop)
+2: BLSFILL By,Ey (xop)
+3: BLCS By,Ey (xop)
+4: TZMSK By,Ey (xop)
+5: BLCIC By,Ey (xop)
+6: BLSIC By,Ey (xop)
+7: T1MSKC By,Ey (xop)
+EndTable
+
+GrpTable: GrpXOP2
+1: BLCMSK By,Ey (xop)
+6: BLCI By,Ey (xop)
+EndTable
+
+GrpTable: GrpXOP3
+0: LLWPCB Ry (xop)
+1: SLWPCB Ry (xop)
+EndTable
+
+GrpTable: GrpXOP4
+0: LWPINS By,Ed,Id (xop)
+1: LWPVAL By,Ed,Id (xop)
+EndTable