[PATCH] x86: extend insn decoder to understand xop and evex prefixes
From: Denys Vlasenko
Date: Mon May 19 2014 - 11:27:12 EST
Since xop and evex prefixes are extensions of vex mechanism,
they have similar bit layouts, and they can never be combined
(an instruction can have only one of them),
(ab)use insn->vex_prefix to store data of xop and evex too.
Users will need to conditionalize on insn->vex_prefix.bytes[0]
instead of insn->vex_prefix.nbytes if they want to determine
which of vex(-like) prefixes are there.
v2: on Masami's request, retained use of inattr bits
for determining prefixes.
Signed-off-by: Denys Vlasenko <dvlasenk@xxxxxxxxxx>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@xxxxxxxxxxx>
Cc: Frank Ch. Eigler <fche@xxxxxxxxxx>
Cc: Srikar Dronamraju <srikar@xxxxxxxxxxxxxxxxxx>
Cc: Ananth N Mavinakayanahalli <ananth@xxxxxxxxxx>
Cc: Jim Keniston <jkenisto@xxxxxxxxxxxxxxxxxx>
Cc: Oleg Nesterov <oleg@xxxxxxxxxx>
Cc: Andi Kleen <andi@xxxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
---
arch/x86/include/asm/inat.h | 26 +++++++++++++----
arch/x86/lib/insn.c | 54 ++++++++++++++++++++++++------------
arch/x86/lib/x86-opcode-map.txt | 4 +--
arch/x86/tools/gen-insn-attr-x86.awk | 2 ++
4 files changed, 62 insertions(+), 24 deletions(-)
diff --git a/arch/x86/include/asm/inat.h b/arch/x86/include/asm/inat.h
index 74a2e31..2c7b4cc 100644
--- a/arch/x86/include/asm/inat.h
+++ b/arch/x86/include/asm/inat.h
@@ -48,6 +48,8 @@
/* AVX VEX prefixes */
#define INAT_PFX_VEX2 13 /* 2-bytes VEX prefix */
#define INAT_PFX_VEX3 14 /* 3-bytes VEX prefix */
+#define INAT_PFX_XOP 15 /* 3-bytes XOP prefix */
+#define INAT_PFX_EVEX 16 /* 4-bytes EVEX prefix */
#define INAT_LSTPFX_MAX 3
#define INAT_LGCPFX_MAX 11
@@ -63,7 +65,7 @@
/* Legacy prefix */
#define INAT_PFX_OFFS 0
-#define INAT_PFX_BITS 4
+#define INAT_PFX_BITS 5
#define INAT_PFX_MAX ((1 << INAT_PFX_BITS) - 1)
#define INAT_PFX_MASK (INAT_PFX_MAX << INAT_PFX_OFFS)
/* Escape opcodes */
@@ -138,15 +140,29 @@ static inline int inat_last_prefix_id(insn_attr_t attr)
return attr & INAT_PFX_MASK;
}
+static inline int inat_is_vex3_prefix(insn_attr_t attr)
+{
+ return attr & INAT_PFX_VEX3;
+}
+
+static inline int inat_is_vex2_prefix(insn_attr_t attr)
+{
+ return attr & INAT_PFX_VEX2;
+}
+
+static inline int inat_is_xop_prefix(insn_attr_t attr)
+{
+ return attr & INAT_PFX_XOP;
+}
+
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 | INAT_PFX_VEX3);
}
-static inline int inat_is_vex3_prefix(insn_attr_t attr)
+static inline int inat_is_vex_like_prefix(insn_attr_t attr)
{
- return (attr & INAT_PFX_MASK) == INAT_PFX_VEX3;
+ return attr & (INAT_PFX_VEX2 | INAT_PFX_VEX3 | INAT_PFX_XOP | INAT_PFX_EVEX);
}
static inline int inat_is_escape(insn_attr_t attr)
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 829ca4c..def44c8 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -138,40 +138,60 @@ found:
}
insn->rex_prefix.got = 1;
- /* Decode VEX prefix */
+ /* Decode VEX prefixes et al. Layouts are:
+ * vex2: c5 rvvvvLpp
+ * vex3/xop: c4/8f rxbmmmmm wvvvvLpp
+ * evex: 62 rxbR00mm wvvvv1pp zllBVaaa
+ */
b = peek_next(insn_byte_t, insn);
attr = inat_get_opcode_attribute(b);
- if (inat_is_vex_prefix(attr)) {
- insn_byte_t b2 = peek_nbyte_next(insn_byte_t, insn, 1);
- if (!insn->x86_64) {
+ if (inat_is_vex_like_prefix(attr)) {
+ insn_byte_t b2;
+
+ b2 = peek_nbyte_next(insn_byte_t, insn, 1);
+ if (inat_is_xop_prefix(attr)) {
/*
- * 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.
+ * XOP: If modrm.reg bits are 000, it's POP reg/mem.
+ */
+ if (X86_MODRM_REG(b2) == 0)
+ goto vex_end;
+ }
+ else if (!insn->x86_64) {
+ /*
+ * [E]VEX: In 32-bits mode, if modrm.mod bits
+ * are not 11b, it is LDS, 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)) {
- b2 = peek_nbyte_next(insn_byte_t, insn, 2);
- insn->vex_prefix.bytes[2] = b2;
- insn->vex_prefix.nbytes = 3;
- insn->next_byte += 3;
- if (insn->x86_64 && X86_VEX_W(b2))
- /* VEX.W overrides opnd_size */
- insn->opnd_bytes = 8;
- } else {
+ if (inat_is_vex2_prefix(attr)) {
/*
* For VEX2, fake VEX3-like byte#2.
* Makes it easier to decode vex.W, vex.vvvv,
- * vex.L and vex.pp. Masking with 0x7f sets vex.W == 0.
+ * vex.L and vex.pp. Masking with 0x7f sets vex.W = 0.
*/
insn->vex_prefix.bytes[2] = b2 & 0x7f;
insn->vex_prefix.nbytes = 2;
insn->next_byte += 2;
+ goto vex_end;
+ }
+ b2 = peek_nbyte_next(insn_byte_t, insn, 2);
+ insn->vex_prefix.bytes[2] = b2;
+ if (insn->x86_64 && X86_VEX_W(b2)) {
+ /* VEX.W overrides opnd_size */
+ insn->opnd_bytes = 8;
+ }
+ if (inat_is_vex3_prefix(attr) || inat_is_xop_prefix(attr)) {
+ insn->vex_prefix.nbytes = 3;
+ insn->next_byte += 3;
+ goto vex_end;
}
+ b2 = peek_nbyte_next(insn_byte_t, insn, 3);
+ insn->vex_prefix.bytes[3] = b2;
+ insn->vex_prefix.nbytes = 4;
+ insn->next_byte += 4;
}
vex_end:
insn->vex_prefix.got = 1;
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index 1a2be7c..9d8a964 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -137,7 +137,7 @@ AVXcode:
# 0x60 - 0x6f
60: PUSHA/PUSHAD (i64)
61: POPA/POPAD (i64)
-62: BOUND Gv,Ma (i64)
+62: BOUND Gv,Ma (i64) | EVEX+3byte (Prefix)
63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64)
64: SEG=FS (Prefix)
65: SEG=GS (Prefix)
@@ -184,7 +184,7 @@ 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+2byte (Prefix)
# 0x90 - 0x9f
90: NOP | PAUSE (F3) | XCHG r8,rAX
91: XCHG rCX/r9,rAX
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
index 093a892..d288754 100644
--- a/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -95,6 +95,8 @@ BEGIN {
prefix_num["Address-Size"] = "INAT_PFX_ADDRSZ"
prefix_num["VEX+1byte"] = "INAT_PFX_VEX2"
prefix_num["VEX+2byte"] = "INAT_PFX_VEX3"
+ prefix_num["XOP+2byte"] = "INAT_PFX_XOP"
+ prefix_num["EVEX+3byte"] = "INAT_PFX_EVEX"
clear_vars()
}
--
1.8.1.4
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/