Merge branch 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull misc fixes from Thomas Gleixner:
"This update contains:
- a fix for stomp-machine so the nmi_watchdog wont trigger on the cpu
waiting for the others to execute the callback
- various fixes and updates to objtool including an resync of the
instruction decoder to match the kernel's decoder"
* 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
objtool: Un-capitalize "Warning" for out-of-sync instruction decoder
objtool: Resync x86 instruction decoder with the kernel's
objtool: Support new GCC 6 switch jump table pattern
stop_machine: Touch_nmi_watchdog() after MULTI_STOP_PREPARE
objtool: Add 'fixdep' to objtool/.gitignore
This commit is contained in:
Linus Torvalds
commit
228ffba23e
|
|
@ -21,6 +21,7 @@
|
|||
#include <linux/smpboot.h>
|
||||
#include <linux/atomic.h>
|
||||
#include <linux/lglock.h>
|
||||
#include <linux/nmi.h>
|
||||
|
||||
/*
|
||||
* Structure to determine completion condition and record errors. May
|
||||
|
|
@ -209,6 +210,13 @@ static int multi_cpu_stop(void *data)
|
|||
break;
|
||||
}
|
||||
ack_state(msdata);
|
||||
} else if (curstate > MULTI_STOP_PREPARE) {
|
||||
/*
|
||||
* At this stage all other CPUs we depend on must spin
|
||||
* in the same loop. Any reason for hard-lockup should
|
||||
* be detected and reported on their side.
|
||||
*/
|
||||
touch_nmi_watchdog();
|
||||
}
|
||||
} while (curstate != MULTI_STOP_EXIT);
|
||||
|
||||
|
|
|
|||
|
|
@ -1,2 +1,3 @@
|
|||
arch/x86/insn/inat-tables.c
|
||||
objtool
|
||||
fixdep
|
||||
|
|
|
|||
|
|
@ -51,7 +51,7 @@ $(OBJTOOL): $(LIBSUBCMD) $(OBJTOOL_IN)
|
|||
diff -I'^#include' arch/x86/insn/insn.h ../../arch/x86/include/asm/insn.h >/dev/null && \
|
||||
diff -I'^#include' arch/x86/insn/inat.h ../../arch/x86/include/asm/inat.h >/dev/null && \
|
||||
diff -I'^#include' arch/x86/insn/inat_types.h ../../arch/x86/include/asm/inat_types.h >/dev/null) \
|
||||
|| echo "Warning: objtool: x86 instruction decoder differs from kernel" >&2 )) || true
|
||||
|| echo "warning: objtool: x86 instruction decoder differs from kernel" >&2 )) || true
|
||||
$(QUIET_LINK)$(CC) $(OBJTOOL_IN) $(LDFLAGS) -o $@
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -72,12 +72,14 @@ BEGIN {
|
|||
lprefix_expr = "\\((66|F2|F3)\\)"
|
||||
max_lprefix = 4
|
||||
|
||||
# All opcodes starting with lower-case 'v' or with (v1) superscript
|
||||
# All opcodes starting with lower-case 'v', 'k' or with (v1) superscript
|
||||
# accepts VEX prefix
|
||||
vexok_opcode_expr = "^v.*"
|
||||
vexok_opcode_expr = "^[vk].*"
|
||||
vexok_expr = "\\(v1\\)"
|
||||
# All opcodes with (v) superscript supports *only* VEX prefix
|
||||
vexonly_expr = "\\(v\\)"
|
||||
# All opcodes with (ev) superscript supports *only* EVEX prefix
|
||||
evexonly_expr = "\\(ev\\)"
|
||||
|
||||
prefix_expr = "\\(Prefix\\)"
|
||||
prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
|
||||
|
|
@ -95,6 +97,7 @@ BEGIN {
|
|||
prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ"
|
||||
prefix_num["VEX+1byte"] = "INAT_PFX_VEX2"
|
||||
prefix_num["VEX+2byte"] = "INAT_PFX_VEX3"
|
||||
prefix_num["EVEX"] = "INAT_PFX_EVEX"
|
||||
|
||||
clear_vars()
|
||||
}
|
||||
|
|
@ -319,7 +322,9 @@ function convert_operands(count,opnd, i,j,imm,mod)
|
|||
flags = add_flags(flags, "INAT_MODRM")
|
||||
|
||||
# check VEX codes
|
||||
if (match(ext, vexonly_expr))
|
||||
if (match(ext, evexonly_expr))
|
||||
flags = add_flags(flags, "INAT_VEXOK | INAT_EVEXONLY")
|
||||
else if (match(ext, vexonly_expr))
|
||||
flags = add_flags(flags, "INAT_VEXOK | INAT_VEXONLY")
|
||||
else if (match(ext, vexok_expr) || match(opcode, vexok_opcode_expr))
|
||||
flags = add_flags(flags, "INAT_VEXOK")
|
||||
|
|
|
|||
|
|
@ -48,6 +48,7 @@
|
|||
/* AVX VEX prefixes */
|
||||
#define INAT_PFX_VEX2 13 /* 2-bytes VEX prefix */
|
||||
#define INAT_PFX_VEX3 14 /* 3-bytes VEX prefix */
|
||||
#define INAT_PFX_EVEX 15 /* EVEX prefix */
|
||||
|
||||
#define INAT_LSTPFX_MAX 3
|
||||
#define INAT_LGCPFX_MAX 11
|
||||
|
|
@ -89,6 +90,7 @@
|
|||
#define INAT_VARIANT (1 << (INAT_FLAG_OFFS + 4))
|
||||
#define INAT_VEXOK (1 << (INAT_FLAG_OFFS + 5))
|
||||
#define INAT_VEXONLY (1 << (INAT_FLAG_OFFS + 6))
|
||||
#define INAT_EVEXONLY (1 << (INAT_FLAG_OFFS + 7))
|
||||
/* Attribute making macros for attribute tables */
|
||||
#define INAT_MAKE_PREFIX(pfx) (pfx << INAT_PFX_OFFS)
|
||||
#define INAT_MAKE_ESCAPE(esc) (esc << INAT_ESC_OFFS)
|
||||
|
|
@ -141,7 +143,13 @@ static inline int inat_last_prefix_id(insn_attr_t attr)
|
|||
static inline int inat_is_vex_prefix(insn_attr_t attr)
|
||||
{
|
||||
attr &= INAT_PFX_MASK;
|
||||
return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3;
|
||||
return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3 ||
|
||||
attr == INAT_PFX_EVEX;
|
||||
}
|
||||
|
||||
static inline int inat_is_evex_prefix(insn_attr_t attr)
|
||||
{
|
||||
return (attr & INAT_PFX_MASK) == INAT_PFX_EVEX;
|
||||
}
|
||||
|
||||
static inline int inat_is_vex3_prefix(insn_attr_t attr)
|
||||
|
|
@ -216,6 +224,11 @@ static inline int inat_accept_vex(insn_attr_t attr)
|
|||
|
||||
static inline int inat_must_vex(insn_attr_t attr)
|
||||
{
|
||||
return attr & INAT_VEXONLY;
|
||||
return attr & (INAT_VEXONLY | INAT_EVEXONLY);
|
||||
}
|
||||
|
||||
static inline int inat_must_evex(insn_attr_t attr)
|
||||
{
|
||||
return attr & INAT_EVEXONLY;
|
||||
}
|
||||
#endif
|
||||
|
|
|
|||
|
|
@ -155,14 +155,24 @@ found:
|
|||
/*
|
||||
* 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.
|
||||
* LDS or LES or BOUND.
|
||||
*/
|
||||
if (X86_MODRM_MOD(b2) != 3)
|
||||
goto vex_end;
|
||||
}
|
||||
insn->vex_prefix.bytes[0] = b;
|
||||
insn->vex_prefix.bytes[1] = b2;
|
||||
if (inat_is_vex3_prefix(attr)) {
|
||||
if (inat_is_evex_prefix(attr)) {
|
||||
b2 = peek_nbyte_next(insn_byte_t, insn, 2);
|
||||
insn->vex_prefix.bytes[2] = b2;
|
||||
b2 = peek_nbyte_next(insn_byte_t, insn, 3);
|
||||
insn->vex_prefix.bytes[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->vex_prefix.bytes[2] = b2;
|
||||
insn->vex_prefix.nbytes = 3;
|
||||
|
|
@ -221,7 +231,9 @@ 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);
|
||||
if (!inat_accept_vex(insn->attr) && !inat_is_group(insn->attr))
|
||||
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 */
|
||||
}
|
||||
|
|
|
|||
|
|
@ -91,6 +91,7 @@ struct insn {
|
|||
#define X86_VEX_B(vex) ((vex) & 0x20) /* VEX3 Byte1 */
|
||||
#define X86_VEX_L(vex) ((vex) & 0x04) /* VEX3 Byte2, VEX2 Byte1 */
|
||||
/* VEX bit fields */
|
||||
#define X86_EVEX_M(vex) ((vex) & 0x03) /* EVEX Byte1 */
|
||||
#define X86_VEX3_M(vex) ((vex) & 0x1f) /* VEX3 Byte1 */
|
||||
#define X86_VEX2_M 1 /* VEX2.M always 1 */
|
||||
#define X86_VEX_V(vex) (((vex) & 0x78) >> 3) /* VEX3 Byte2, VEX2 Byte1 */
|
||||
|
|
@ -133,6 +134,13 @@ static inline int insn_is_avx(struct insn *insn)
|
|||
return (insn->vex_prefix.value != 0);
|
||||
}
|
||||
|
||||
static inline int insn_is_evex(struct insn *insn)
|
||||
{
|
||||
if (!insn->prefixes.got)
|
||||
insn_get_prefixes(insn);
|
||||
return (insn->vex_prefix.nbytes == 4);
|
||||
}
|
||||
|
||||
/* Ensure this instruction is decoded completely */
|
||||
static inline int insn_complete(struct insn *insn)
|
||||
{
|
||||
|
|
@ -144,8 +152,10 @@ static inline insn_byte_t insn_vex_m_bits(struct insn *insn)
|
|||
{
|
||||
if (insn->vex_prefix.nbytes == 2) /* 2 bytes VEX */
|
||||
return X86_VEX2_M;
|
||||
else
|
||||
else if (insn->vex_prefix.nbytes == 3) /* 3 bytes VEX */
|
||||
return X86_VEX3_M(insn->vex_prefix.bytes[1]);
|
||||
else /* EVEX */
|
||||
return X86_EVEX_M(insn->vex_prefix.bytes[1]);
|
||||
}
|
||||
|
||||
static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
|
||||
|
|
|
|||
|
|
@ -13,12 +13,17 @@
|
|||
# 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.
|
||||
#
|
||||
|
|
@ -137,7 +142,7 @@ AVXcode:
|
|||
# 0x60 - 0x6f
|
||||
60: PUSHA/PUSHAD (i64)
|
||||
61: POPA/POPAD (i64)
|
||||
62: BOUND Gv,Ma (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)
|
||||
|
|
@ -399,17 +404,17 @@ AVXcode: 1
|
|||
3f:
|
||||
# 0x0f 0x40-0x4f
|
||||
40: CMOVO Gv,Ev
|
||||
41: CMOVNO Gv,Ev
|
||||
42: CMOVB/C/NAE 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
|
||||
45: CMOVNE/NZ Gv,Ev
|
||||
46: CMOVBE/NA Gv,Ev
|
||||
47: CMOVA/NBE 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
|
||||
4b: CMOVNP/PO 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
|
||||
|
|
@ -426,7 +431,7 @@ AVXcode: 1
|
|||
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 | vcvtps2dq Vdq,Wps (66) | vcvttps2dq Vdq,Wps (F3)
|
||||
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)
|
||||
|
|
@ -447,7 +452,7 @@ AVXcode: 1
|
|||
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) | vmovdqu Vx,Wx (F3)
|
||||
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)
|
||||
|
|
@ -458,14 +463,14 @@ AVXcode: 1
|
|||
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
|
||||
79: VMWRITE Gy,Ey
|
||||
7a:
|
||||
7b:
|
||||
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) | vmovdqu Wx,Vx (F3)
|
||||
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)
|
||||
|
|
@ -485,16 +490,16 @@ AVXcode: 1
|
|||
8e: JLE/JNG Jz (f64)
|
||||
8f: JNLE/JG Jz (f64)
|
||||
# 0x0f 0x90-0x9f
|
||||
90: SETO Eb
|
||||
91: SETNO Eb
|
||||
92: SETB/C/NAE Eb
|
||||
93: SETAE/NB/NC Eb
|
||||
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
|
||||
99: SETNS 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
|
||||
|
|
@ -564,11 +569,11 @@ 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)
|
||||
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)
|
||||
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)
|
||||
|
|
@ -576,16 +581,16 @@ 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) | vcvtpd2dq Vx,Wpd (F2)
|
||||
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)
|
||||
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)
|
||||
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)
|
||||
|
|
@ -626,81 +631,105 @@ AVXcode: 2
|
|||
0e: vtestps Vx,Wx (66),(v)
|
||||
0f: vtestpd Vx,Wx (66),(v)
|
||||
# 0x0f 0x38 0x10-0x1f
|
||||
10: pblendvb Vdq,Wdq (66)
|
||||
11:
|
||||
12:
|
||||
13: vcvtph2ps Vx,Wx,Ib (66),(v)
|
||||
14: blendvps Vdq,Wdq (66)
|
||||
15: blendvpd Vdq,Wdq (66)
|
||||
16: vpermps Vqq,Hqq,Wqq (66),(v)
|
||||
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)
|
||||
1a: vbroadcastf128 Vqq,Mdq (66),(v)
|
||||
1b:
|
||||
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:
|
||||
1f: vpabsq Vx,Wx (66),(ev)
|
||||
# 0x0f 0x38 0x20-0x2f
|
||||
20: vpmovsxbw Vx,Ux/Mq (66),(v1)
|
||||
21: vpmovsxbd Vx,Ux/Md (66),(v1)
|
||||
22: vpmovsxbq Vx,Ux/Mw (66),(v1)
|
||||
23: vpmovsxwd Vx,Ux/Mq (66),(v1)
|
||||
24: vpmovsxwq Vx,Ux/Md (66),(v1)
|
||||
25: vpmovsxdq Vx,Ux/Mq (66),(v1)
|
||||
26:
|
||||
27:
|
||||
28: vpmuldq Vx,Hx,Wx (66),(v1)
|
||||
29: vpcmpeqq Vx,Hx,Wx (66),(v1)
|
||||
2a: vmovntdqa Vx,Mx (66),(v1)
|
||||
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)
|
||||
2d: vmaskmovpd Vx,Hx,Mx (66),(v)
|
||||
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)
|
||||
31: vpmovzxbd Vx,Ux/Md (66),(v1)
|
||||
32: vpmovzxbq Vx,Ux/Mw (66),(v1)
|
||||
33: vpmovzxwd Vx,Ux/Mq (66),(v1)
|
||||
34: vpmovzxwq Vx,Ux/Md (66),(v1)
|
||||
35: vpmovzxdq Vx,Ux/Mq (66),(v1)
|
||||
36: vpermd Vqq,Hqq,Wqq (66),(v)
|
||||
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)
|
||||
39: vpminsd Vx,Hx,Wx (66),(v1)
|
||||
3a: vpminuw Vx,Hx,Wx (66),(v1)
|
||||
3b: vpminud 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)
|
||||
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)
|
||||
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)
|
||||
40: vpmulld Vx,Hx,Wx (66),(v1) | vpmulld/q Vx,Hx,Wx (66),(evo)
|
||||
41: vphminposuw Vdq,Wdq (66),(v1)
|
||||
42:
|
||||
43:
|
||||
44:
|
||||
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)
|
||||
46: vpsravd Vx,Hx,Wx (66),(v) | vpsravd/q Vx,Hx,Wx (66),(evo)
|
||||
47: vpsllvd/q Vx,Hx,Wx (66),(v)
|
||||
# Skip 0x48-0x57
|
||||
# Skip 0x48-0x4b
|
||||
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)
|
||||
# Skip 0x50-0x57
|
||||
58: vpbroadcastd Vx,Wx (66),(v)
|
||||
59: vpbroadcastq Vx,Wx (66),(v)
|
||||
5a: vbroadcasti128 Vqq,Mdq (66),(v)
|
||||
# Skip 0x5b-0x77
|
||||
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-0x63
|
||||
64: vpblendmd/q Vx,Hx,Wx (66),(ev)
|
||||
65: vblendmps/d Vx,Hx,Wx (66),(ev)
|
||||
66: vpblendmb/w Vx,Hx,Wx (66),(ev)
|
||||
# Skip 0x67-0x74
|
||||
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)
|
||||
# Skip 0x7a-0x7f
|
||||
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: INVPID 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)
|
||||
# 0x0f 0x38 0x90-0xbf (FMA)
|
||||
90: vgatherdd/q Vx,Hx,Wx (66),(v)
|
||||
91: vgatherqd/q Vx,Hx,Wx (66),(v)
|
||||
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:
|
||||
|
|
@ -715,6 +744,10 @@ AVXcode: 2
|
|||
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)
|
||||
|
|
@ -725,6 +758,8 @@ 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)
|
||||
|
|
@ -736,12 +771,15 @@ 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
|
||||
c8: sha1nexte Vdq,Wdq
|
||||
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
|
||||
cb: sha256rnds2 Vdq,Wdq
|
||||
cc: sha256msg1 Vdq,Wdq
|
||||
cd: sha256msg2 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)
|
||||
db: VAESIMC Vdq,Wdq (66),(v1)
|
||||
dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
|
||||
dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
|
||||
|
|
@ -763,15 +801,15 @@ AVXcode: 3
|
|||
00: vpermq Vqq,Wqq,Ib (66),(v)
|
||||
01: vpermpd Vqq,Wqq,Ib (66),(v)
|
||||
02: vpblendd Vx,Hx,Wx,Ib (66),(v)
|
||||
03:
|
||||
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)
|
||||
09: vroundpd Vx,Wx,Ib (66)
|
||||
0a: vroundss Vss,Wss,Ib (66),(v1)
|
||||
0b: vroundsd Vsd,Wsd,Ib (66),(v1)
|
||||
08: vroundps Vx,Wx,Ib (66) | vrndscaleps Vx,Wx,Ib (66),(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)
|
||||
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)
|
||||
|
|
@ -780,26 +818,51 @@ AVXcode: 3
|
|||
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)
|
||||
19: vextractf128 Wdq,Vqq,Ib (66),(v)
|
||||
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)
|
||||
38: vinserti128 Vqq,Hqq,Wqq,Ib (66),(v)
|
||||
39: vextracti128 Wdq,Vqq,Ib (66),(v)
|
||||
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)
|
||||
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)
|
||||
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 Vdq,Hdq,Wdq,Ib (66),(v1)
|
||||
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)
|
||||
57: vreducess/d Vx,Hx,Wx,Ib (66),(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)
|
||||
cc: sha1rnds4 Vdq,Wdq,Ib
|
||||
df: VAESKEYGEN Vdq,Wdq,Ib (66),(v1)
|
||||
f0: RORX Gy,Ey,Ib (F2),(v)
|
||||
|
|
@ -927,8 +990,10 @@ GrpTable: Grp12
|
|||
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)
|
||||
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
|
||||
|
||||
|
|
@ -963,6 +1028,20 @@ GrpTable: Grp17
|
|||
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
|
||||
|
||||
# AMD's Prefetch Group
|
||||
GrpTable: GrpP
|
||||
0: PREFETCH
|
||||
|
|
|
|||
|
|
@ -107,6 +107,12 @@ static struct instruction *next_insn_same_sec(struct objtool_file *file,
|
|||
insn->offset < func->offset + func->len; \
|
||||
insn = list_next_entry(insn, list))
|
||||
|
||||
#define func_for_each_insn_continue_reverse(file, func, insn) \
|
||||
for (insn = list_prev_entry(insn, list); \
|
||||
&insn->list != &file->insn_list && \
|
||||
insn->sec == func->sec && insn->offset >= func->offset; \
|
||||
insn = list_prev_entry(insn, list))
|
||||
|
||||
#define sec_for_each_insn_from(file, insn) \
|
||||
for (; insn; insn = next_insn_same_sec(file, insn))
|
||||
|
||||
|
|
@ -664,65 +670,95 @@ static int add_switch_table(struct objtool_file *file, struct symbol *func,
|
|||
return 0;
|
||||
}
|
||||
|
||||
/*
|
||||
* find_switch_table() - Given a dynamic jump, find the switch jump table in
|
||||
* .rodata associated with it.
|
||||
*
|
||||
* There are 3 basic patterns:
|
||||
*
|
||||
* 1. jmpq *[rodata addr](,%reg,8)
|
||||
*
|
||||
* This is the most common case by far. It jumps to an address in a simple
|
||||
* jump table which is stored in .rodata.
|
||||
*
|
||||
* 2. jmpq *[rodata addr](%rip)
|
||||
*
|
||||
* This is caused by a rare GCC quirk, currently only seen in three driver
|
||||
* functions in the kernel, only with certain obscure non-distro configs.
|
||||
*
|
||||
* As part of an optimization, GCC makes a copy of an existing switch jump
|
||||
* table, modifies it, and then hard-codes the jump (albeit with an indirect
|
||||
* jump) to use a single entry in the table. The rest of the jump table and
|
||||
* some of its jump targets remain as dead code.
|
||||
*
|
||||
* In such a case we can just crudely ignore all unreachable instruction
|
||||
* warnings for the entire object file. Ideally we would just ignore them
|
||||
* for the function, but that would require redesigning the code quite a
|
||||
* bit. And honestly that's just not worth doing: unreachable instruction
|
||||
* warnings are of questionable value anyway, and this is such a rare issue.
|
||||
*
|
||||
* 3. mov [rodata addr],%reg1
|
||||
* ... some instructions ...
|
||||
* jmpq *(%reg1,%reg2,8)
|
||||
*
|
||||
* This is a fairly uncommon pattern which is new for GCC 6. As of this
|
||||
* writing, there are 11 occurrences of it in the allmodconfig kernel.
|
||||
*
|
||||
* TODO: Once we have DWARF CFI and smarter instruction decoding logic,
|
||||
* ensure the same register is used in the mov and jump instructions.
|
||||
*/
|
||||
static struct rela *find_switch_table(struct objtool_file *file,
|
||||
struct symbol *func,
|
||||
struct instruction *insn)
|
||||
{
|
||||
struct rela *text_rela, *rodata_rela;
|
||||
|
||||
text_rela = find_rela_by_dest_range(insn->sec, insn->offset, insn->len);
|
||||
if (text_rela && text_rela->sym == file->rodata->sym) {
|
||||
/* case 1 */
|
||||
rodata_rela = find_rela_by_dest(file->rodata,
|
||||
text_rela->addend);
|
||||
if (rodata_rela)
|
||||
return rodata_rela;
|
||||
|
||||
/* case 2 */
|
||||
rodata_rela = find_rela_by_dest(file->rodata,
|
||||
text_rela->addend + 4);
|
||||
if (!rodata_rela)
|
||||
return NULL;
|
||||
file->ignore_unreachables = true;
|
||||
return rodata_rela;
|
||||
}
|
||||
|
||||
/* case 3 */
|
||||
func_for_each_insn_continue_reverse(file, func, insn) {
|
||||
if (insn->type == INSN_JUMP_UNCONDITIONAL ||
|
||||
insn->type == INSN_JUMP_DYNAMIC)
|
||||
break;
|
||||
|
||||
text_rela = find_rela_by_dest_range(insn->sec, insn->offset,
|
||||
insn->len);
|
||||
if (text_rela && text_rela->sym == file->rodata->sym)
|
||||
return find_rela_by_dest(file->rodata,
|
||||
text_rela->addend);
|
||||
}
|
||||
|
||||
return NULL;
|
||||
}
|
||||
|
||||
static int add_func_switch_tables(struct objtool_file *file,
|
||||
struct symbol *func)
|
||||
{
|
||||
struct instruction *insn, *prev_jump;
|
||||
struct rela *text_rela, *rodata_rela, *prev_rela = NULL;
|
||||
struct instruction *insn, *prev_jump = NULL;
|
||||
struct rela *rela, *prev_rela = NULL;
|
||||
int ret;
|
||||
|
||||
prev_jump = NULL;
|
||||
|
||||
func_for_each_insn(file, func, insn) {
|
||||
if (insn->type != INSN_JUMP_DYNAMIC)
|
||||
continue;
|
||||
|
||||
text_rela = find_rela_by_dest_range(insn->sec, insn->offset,
|
||||
insn->len);
|
||||
if (!text_rela || text_rela->sym != file->rodata->sym)
|
||||
continue;
|
||||
|
||||
/* common case: jmpq *[addr](,%rax,8) */
|
||||
rodata_rela = find_rela_by_dest(file->rodata,
|
||||
text_rela->addend);
|
||||
|
||||
/*
|
||||
* rare case: jmpq *[addr](%rip)
|
||||
*
|
||||
* This check is for a rare gcc quirk, currently only seen in
|
||||
* three driver functions in the kernel, only with certain
|
||||
* obscure non-distro configs.
|
||||
*
|
||||
* As part of an optimization, gcc makes a copy of an existing
|
||||
* switch jump table, modifies it, and then hard-codes the jump
|
||||
* (albeit with an indirect jump) to use a single entry in the
|
||||
* table. The rest of the jump table and some of its jump
|
||||
* targets remain as dead code.
|
||||
*
|
||||
* In such a case we can just crudely ignore all unreachable
|
||||
* instruction warnings for the entire object file. Ideally we
|
||||
* would just ignore them for the function, but that would
|
||||
* require redesigning the code quite a bit. And honestly
|
||||
* that's just not worth doing: unreachable instruction
|
||||
* warnings are of questionable value anyway, and this is such
|
||||
* a rare issue.
|
||||
*
|
||||
* kbuild reports:
|
||||
* - https://lkml.kernel.org/r/201603231906.LWcVUpxm%25fengguang.wu@intel.com
|
||||
* - https://lkml.kernel.org/r/201603271114.K9i45biy%25fengguang.wu@intel.com
|
||||
* - https://lkml.kernel.org/r/201603291058.zuJ6ben1%25fengguang.wu@intel.com
|
||||
*
|
||||
* gcc bug:
|
||||
* - https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70604
|
||||
*/
|
||||
if (!rodata_rela) {
|
||||
rodata_rela = find_rela_by_dest(file->rodata,
|
||||
text_rela->addend + 4);
|
||||
if (rodata_rela)
|
||||
file->ignore_unreachables = true;
|
||||
}
|
||||
|
||||
if (!rodata_rela)
|
||||
rela = find_switch_table(file, func, insn);
|
||||
if (!rela)
|
||||
continue;
|
||||
|
||||
/*
|
||||
|
|
@ -732,13 +768,13 @@ static int add_func_switch_tables(struct objtool_file *file,
|
|||
*/
|
||||
if (prev_jump) {
|
||||
ret = add_switch_table(file, func, prev_jump, prev_rela,
|
||||
rodata_rela);
|
||||
rela);
|
||||
if (ret)
|
||||
return ret;
|
||||
}
|
||||
|
||||
prev_jump = insn;
|
||||
prev_rela = rodata_rela;
|
||||
prev_rela = rela;
|
||||
}
|
||||
|
||||
if (prev_jump) {
|
||||
|
|
|
|||
Loading…
Reference in New Issue