[tip: objtool/core] x86/insn: Fix vector instruction decoding on big endian cross-compiles

From: tip-bot2 for Vasily Gorbik
Date: Mon Jan 18 2021 - 15:59:54 EST


The following commit has been merged into the objtool/core branch of tip:

Commit-ID: 5ed934e57e712b676ca62e1904ad672a9fa1505a
Gitweb: https://git.kernel.org/tip/5ed934e57e712b676ca62e1904ad672a9fa1505a
Author: Vasily Gorbik <gor@xxxxxxxxxxxxx>
AuthorDate: Fri, 13 Nov 2020 17:09:54 +01:00
Committer: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
CommitterDate: Wed, 13 Jan 2021 18:13:17 -06:00

x86/insn: Fix vector instruction decoding on big endian cross-compiles

Running instruction decoder posttest on an s390 host with an x86 target
with allyesconfig shows errors. Instructions used in a couple of kernel
objects could not be correctly decoded on big endian system.

insn_decoder_test: warning: objdump says 6 bytes, but insn_get_length() says 5
insn_decoder_test: warning: Found an x86 instruction decoder bug, please report this.
insn_decoder_test: warning: ffffffff831eb4e1: 62 d1 fd 48 7f 04 24 vmovdqa64 %zmm0,(%r12)
insn_decoder_test: warning: objdump says 7 bytes, but insn_get_length() says 6
insn_decoder_test: warning: Found an x86 instruction decoder bug, please report this.
insn_decoder_test: warning: ffffffff831eb4e8: 62 51 fd 48 7f 44 24 01 vmovdqa64 %zmm8,0x40(%r12)
insn_decoder_test: warning: objdump says 8 bytes, but insn_get_length() says 6

This is because in a few places instruction field bytes are set directly
with further usage of "value". To address that introduce and use a
insn_set_byte() helper, which correctly updates "value" on big endian
systems.

Signed-off-by: Vasily Gorbik <gor@xxxxxxxxxxxxx>
Acked-by: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Signed-off-by: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
---
arch/x86/include/asm/insn.h | 12 ++++++++++++
arch/x86/lib/insn.c | 18 +++++++++---------
tools/arch/x86/include/asm/insn.h | 12 ++++++++++++
tools/arch/x86/lib/insn.c | 18 +++++++++---------
4 files changed, 42 insertions(+), 18 deletions(-)

diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 090863c..95a448f 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -30,6 +30,12 @@ static inline void insn_field_set(struct insn_field *p, insn_value_t v,
p->nbytes = n;
}

+static inline void insn_set_byte(struct insn_field *p, unsigned char n,
+ insn_byte_t v)
+{
+ p->bytes[n] = v;
+}
+
#else

struct insn_field {
@@ -51,6 +57,12 @@ static inline void insn_field_set(struct insn_field *p, insn_value_t v,
p->nbytes = n;
}

+static inline void insn_set_byte(struct insn_field *p, unsigned char n,
+ insn_byte_t v)
+{
+ p->bytes[n] = v;
+ p->value = __le32_to_cpu(p->little);
+}
#endif

struct insn {
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 520b31f..435630a 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -161,9 +161,9 @@ 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 */
@@ -194,13 +194,13 @@ 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))
@@ -208,7 +208,7 @@ 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))
@@ -220,7 +220,7 @@ 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;
}
@@ -256,7 +256,7 @@ void insn_get_opcode(struct insn *insn)

/* 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 */
diff --git a/tools/arch/x86/include/asm/insn.h b/tools/arch/x86/include/asm/insn.h
index c1fab7a..cc777c1 100644
--- a/tools/arch/x86/include/asm/insn.h
+++ b/tools/arch/x86/include/asm/insn.h
@@ -30,6 +30,12 @@ static inline void insn_field_set(struct insn_field *p, insn_value_t v,
p->nbytes = n;
}

+static inline void insn_set_byte(struct insn_field *p, unsigned char n,
+ insn_byte_t v)
+{
+ p->bytes[n] = v;
+}
+
#else

struct insn_field {
@@ -51,6 +57,12 @@ static inline void insn_field_set(struct insn_field *p, insn_value_t v,
p->nbytes = n;
}

+static inline void insn_set_byte(struct insn_field *p, unsigned char n,
+ insn_byte_t v)
+{
+ p->bytes[n] = v;
+ p->value = __le32_to_cpu(p->little);
+}
#endif

struct insn {
diff --git a/tools/arch/x86/lib/insn.c b/tools/arch/x86/lib/insn.c
index 77e92aa..3d9355e 100644
--- a/tools/arch/x86/lib/insn.c
+++ b/tools/arch/x86/lib/insn.c
@@ -161,9 +161,9 @@ 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 */
@@ -194,13 +194,13 @@ 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))
@@ -208,7 +208,7 @@ 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))
@@ -220,7 +220,7 @@ 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;
}
@@ -256,7 +256,7 @@ void insn_get_opcode(struct insn *insn)

/* 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 */