aboutsummaryrefslogtreecommitdiff
path: root/tcg
diff options
context:
space:
mode:
authorPeter Maydell <peter.maydell@linaro.org>2018-05-04 16:34:31 +0100
committerRichard Henderson <richard.henderson@linaro.org>2018-05-09 08:30:57 -0700
commit7eb30ef0ba2eb59e7430d4848ae8d4bf4e50f768 (patch)
treeea80a4f751ad4c129bc062c9f3b21a7e6fc9a27e /tcg
parente5cd695266c5709308aa95b1baae499e4b5d4544 (diff)
downloadqemu-7eb30ef0ba2eb59e7430d4848ae8d4bf4e50f768.zip
qemu-7eb30ef0ba2eb59e7430d4848ae8d4bf4e50f768.tar.gz
qemu-7eb30ef0ba2eb59e7430d4848ae8d4bf4e50f768.tar.bz2
tcg/i386: Fix dup_vec in non-AVX2 codepath
The VPUNPCKLD* instructions are all "non-destructive source", indicated by "NDS" in the encoding string in the x86 ISA manual. This means that they take two source operands, one of which is encoded in the VEX.vvvv field. We were incorrectly treating them as if they were destructive-source and passing 0 as the 'v' argument of tcg_out_vex_modrm(). This meant we were always using %xmm0 as one of the source operands, causing incorrect results if the register allocator happened to want to use something else. For instance the input AArch64 insn: DUP v26.16b, w21 which becomes TCG IR ops: dup_vec v128,e8,tmp2,x21 st_vec v128,e8,tmp2,env,$0xa40 was assembled to: 0x607c568c: c4 c1 7a 7e 86 e8 00 00 vmovq 0xe8(%r14), %xmm0 0x607c5694: 00 0x607c5695: c5 f9 60 c8 vpunpcklbw %xmm0, %xmm0, %xmm1 0x607c5699: c5 f9 61 c9 vpunpcklwd %xmm1, %xmm0, %xmm1 0x607c569d: c5 f9 70 c9 00 vpshufd $0, %xmm1, %xmm1 0x607c56a2: c4 c1 7a 7f 8e 40 0a 00 vmovdqu %xmm1, 0xa40(%r14) 0x607c56aa: 00 when the vpunpcklwd insn should be "%xmm1, %xmm1, %xmm1". This resulted in our incorrectly setting the output vector to q26=0000320000003200:0000320000003200 when given an input of x21 == 0000000002803200 rather than the expected all-zeroes. Pass the correct source register number to tcg_out_vex_modrm() for these insns. Fixes: 770c2fc7bb70804a Cc: qemu-stable@nongnu.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-Id: <20180504153431.5169-1-peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Diffstat (limited to 'tcg')
-rw-r--r--tcg/i386/tcg-target.inc.c6
1 files changed, 3 insertions, 3 deletions
diff --git a/tcg/i386/tcg-target.inc.c b/tcg/i386/tcg-target.inc.c
index d7e59e7..5357909 100644
--- a/tcg/i386/tcg-target.inc.c
+++ b/tcg/i386/tcg-target.inc.c
@@ -854,11 +854,11 @@ static void tcg_out_dup_vec(TCGContext *s, TCGType type, unsigned vece,
switch (vece) {
case MO_8:
/* ??? With zero in a register, use PSHUFB. */
- tcg_out_vex_modrm(s, OPC_PUNPCKLBW, r, 0, a);
+ tcg_out_vex_modrm(s, OPC_PUNPCKLBW, r, a, a);
a = r;
/* FALLTHRU */
case MO_16:
- tcg_out_vex_modrm(s, OPC_PUNPCKLWD, r, 0, a);
+ tcg_out_vex_modrm(s, OPC_PUNPCKLWD, r, a, a);
a = r;
/* FALLTHRU */
case MO_32:
@@ -867,7 +867,7 @@ static void tcg_out_dup_vec(TCGContext *s, TCGType type, unsigned vece,
tcg_out8(s, 0);
break;
case MO_64:
- tcg_out_vex_modrm(s, OPC_PUNPCKLQDQ, r, 0, a);
+ tcg_out_vex_modrm(s, OPC_PUNPCKLQDQ, r, a, a);
break;
default:
g_assert_not_reached();