[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <tip-130b78b2bf16d5d89091db38374faef896360cf9@git.kernel.org>
Date: Mon, 5 Dec 2011 09:42:01 -0800
From: tip-bot for Masami Hiramatsu <masami.hiramatsu.pt@...achi.com>
To: linux-tip-commits@...r.kernel.org
Cc: linux-kernel@...r.kernel.org, hpa@...or.com, mingo@...hat.com,
masami.hiramatsu.pt@...achi.com, tglx@...utronix.de, mingo@...e.hu
Subject: [tip:perf/core] x86: Fix instruction decoder to handle grouped AVX instructions
Commit-ID: 130b78b2bf16d5d89091db38374faef896360cf9
Gitweb: http://git.kernel.org/tip/130b78b2bf16d5d89091db38374faef896360cf9
Author: Masami Hiramatsu <masami.hiramatsu.pt@...achi.com>
AuthorDate: Mon, 5 Dec 2011 21:05:39 +0900
Committer: Ingo Molnar <mingo@...e.hu>
CommitDate: Mon, 5 Dec 2011 14:53:15 +0100
x86: Fix instruction decoder to handle grouped AVX instructions
For reducing memory usage of attribute table, x86 instruction
decoder puts "Group" attribute only on "no-last-prefix"
attribute table (same as vex_p == 0 case).
Thus, the decoder should look no-last-prefix table first, and
then only if it is not a group, move on to "with-last-prefix"
table (vex_p != 0).
However, current implementation, inat_get_avx_attribute()
looks with-last-prefix directly. So, when decoding
a grouped AVX instruction, the decoder fails to find correct
group because there is no "Group" attribute on the table.
This ends up with the mis-decoding of instructions, as Ingo
reported in http://thread.gmane.org/gmane.linux.kernel/1214103
This patch fixes it to check no-last-prefix table first
even if that is an AVX instruction, and get an attribute from
"with last-prefix" table only if that is not a group.
Reported-by: Ingo Molnar <mingo@...e.hu>
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@...achi.com>
Cc: "H. Peter Anvin" <hpa@...or.com>
Cc: yrl.pp-manager.tt@...achi.com
Link: http://lkml.kernel.org/r/20111205120539.15475.91428.stgit@cloud
Signed-off-by: Ingo Molnar <mingo@...e.hu>
---
arch/x86/lib/inat.c | 9 ++++++++-
arch/x86/lib/insn.c | 4 +++-
2 files changed, 11 insertions(+), 2 deletions(-)
diff --git a/arch/x86/lib/inat.c b/arch/x86/lib/inat.c
index 46fc4ee..88ad5fb 100644
--- a/arch/x86/lib/inat.c
+++ b/arch/x86/lib/inat.c
@@ -82,9 +82,16 @@ insn_attr_t inat_get_avx_attribute(insn_byte_t opcode, insn_byte_t vex_m,
const insn_attr_t *table;
if (vex_m > X86_VEX_M_MAX || vex_p > INAT_LSTPFX_MAX)
return 0;
- table = inat_avx_tables[vex_m][vex_p];
+ /* At first, this checks the master table */
+ table = inat_avx_tables[vex_m][0];
if (!table)
return 0;
+ if (!inat_is_group(table[opcode]) && vex_p) {
+ /* If this is not a group, get attribute directly */
+ table = inat_avx_tables[vex_m][vex_p];
+ if (!table)
+ return 0;
+ }
return table[opcode];
}
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 374562e..5a1f9f3 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -202,7 +202,7 @@ 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))
+ if (!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 */
}
@@ -249,6 +249,8 @@ void insn_get_modrm(struct insn *insn)
pfx = insn_last_prefix(insn);
insn->attr = inat_get_group_attribute(mod, pfx,
insn->attr);
+ if (insn_is_avx(insn) && !inat_accept_vex(insn->attr))
+ insn->attr = 0; /* This is bad */
}
}
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists