diff mbox series

[Stable-7.2.7,24/62] target/i386: Fix exception classes for MOVNTPS/MOVNTPD.

Message ID 20231109135933.1462615-24-mjt@tls.msk.ru (mailing list archive)
State New, archived
Headers show
Series Patch Round-up for stable 7.2.7, freeze on 2023-11-19 | expand

Commit Message

Michael Tokarev Nov. 9, 2023, 1:58 p.m. UTC 
From: Ricky Zhou <ricky@rzhou.org>

Before this change, MOVNTPS and MOVNTPD were labeled as Exception Class
4 (only requiring alignment for legacy SSE instructions). This changes
them to Exception Class 1 (always requiring memory alignment), as
documented in the Intel manual.
Message-Id: <20230501111428.95998-3-ricky@rzhou.org>

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 8bf171c2d126aea6b60b818f1cee7e0e9eef0390)
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
diff mbox series

Patch

diff --git a/target/i386/tcg/decode-new.c.inc b/target/i386/tcg/decode-new.c.inc
index 8c477c1bab..8a8d353b32 100644
--- a/target/i386/tcg/decode-new.c.inc
+++ b/target/i386/tcg/decode-new.c.inc
@@ -750,8 +750,9 @@  static void decode_0F2A(DisasContext *s, CPUX86State *env, X86OpEntry *entry, ui
 static void decode_0F2B(DisasContext *s, CPUX86State *env, X86OpEntry *entry, uint8_t *b)
 {
     static const X86OpEntry opcodes_0F2B[4] = {
-        X86_OP_ENTRY3(MOVDQ,      M,x,  None,None, V,x, vex4), /* MOVNTPS */
-        X86_OP_ENTRY3(MOVDQ,      M,x,  None,None, V,x, vex4), /* MOVNTPD */
+        X86_OP_ENTRY3(MOVDQ,      M,x,  None,None, V,x, vex1), /* MOVNTPS */
+        X86_OP_ENTRY3(MOVDQ,      M,x,  None,None, V,x, vex1), /* MOVNTPD */
+        /* AMD extensions */
         X86_OP_ENTRY3(VMOVSS_st,  M,ss, None,None, V,x, vex4 cpuid(SSE4A)), /* MOVNTSS */
         X86_OP_ENTRY3(VMOVLPx_st, M,sd, None,None, V,x, vex4 cpuid(SSE4A)), /* MOVNTSD */
     };