[Qemu-devel] [PULL 16/16] tcg/i386: Use MOVDQA for TCG_TYPE_V128 load/store

[Richard Henderson <richard.henderson@linaro.org>]

This instruction raises #GP, aka SIGSEGV, if the effective address
is not aligned to 16-bytes.

We have assertions in tcg-op-gvec.c that the offset from ENV is
aligned, for vector types <= V128.  But the offset itself does not
validate that the final pointer is aligned -- one must also remember
to use the QEMU_ALIGNED() attribute on the vector member within ENV.

PowerPC Altivec has vector load/store instructions that silently
discard the low 4 bits of the address, making alignment mistakes
difficult to discover.  Aid that by making the most popular host
visibly signal the error.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/i386/tcg-target.inc.c | 24 ++++++++++++++++++++++--
 1 file changed, 22 insertions(+), 2 deletions(-)

diff --git a/tcg/i386/tcg-target.inc.c b/tcg/i386/tcg-target.inc.c
index 6ec5e60448..c0443da4af 100644
--- a/tcg/i386/tcg-target.inc.c
+++ b/tcg/i386/tcg-target.inc.c
@@ -1082,14 +1082,24 @@ static void tcg_out_ld(TCGContext *s, TCGType type, TCGReg ret,
         }
         /* FALLTHRU */
     case TCG_TYPE_V64:
+        /* There is no instruction that can validate 8-byte alignment.  */
         tcg_debug_assert(ret >= 16);
         tcg_out_vex_modrm_offset(s, OPC_MOVQ_VqWq, ret, 0, arg1, arg2);
         break;
     case TCG_TYPE_V128:
+        /*
+         * The gvec infrastructure is asserts that v128 vector loads
+         * and stores use a 16-byte aligned offset.  Validate that the
+         * final pointer is aligned by using an insn that will SIGSEGV.
+         */
         tcg_debug_assert(ret >= 16);
-        tcg_out_vex_modrm_offset(s, OPC_MOVDQU_VxWx, ret, 0, arg1, arg2);
+        tcg_out_vex_modrm_offset(s, OPC_MOVDQA_VxWx, ret, 0, arg1, arg2);
         break;
     case TCG_TYPE_V256:
+        /*
+         * The gvec infrastructure only requires 16-byte alignment,
+         * so here we must use an unaligned load.
+         */
         tcg_debug_assert(ret >= 16);
         tcg_out_vex_modrm_offset(s, OPC_MOVDQU_VxWx | P_VEXL,
                                  ret, 0, arg1, arg2);
@@ -1117,14 +1127,24 @@ static void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg,
         }
         /* FALLTHRU */
     case TCG_TYPE_V64:
+        /* There is no instruction that can validate 8-byte alignment.  */
         tcg_debug_assert(arg >= 16);
         tcg_out_vex_modrm_offset(s, OPC_MOVQ_WqVq, arg, 0, arg1, arg2);
         break;
     case TCG_TYPE_V128:
+        /*
+         * The gvec infrastructure is asserts that v128 vector loads
+         * and stores use a 16-byte aligned offset.  Validate that the
+         * final pointer is aligned by using an insn that will SIGSEGV.
+         */
         tcg_debug_assert(arg >= 16);
-        tcg_out_vex_modrm_offset(s, OPC_MOVDQU_WxVx, arg, 0, arg1, arg2);
+        tcg_out_vex_modrm_offset(s, OPC_MOVDQA_WxVx, arg, 0, arg1, arg2);
         break;
     case TCG_TYPE_V256:
+        /*
+         * The gvec infrastructure only requires 16-byte alignment,
+         * so here we must use an unaligned store.
+         */
         tcg_debug_assert(arg >= 16);
         tcg_out_vex_modrm_offset(s, OPC_MOVDQU_WxVx | P_VEXL,
                                  arg, 0, arg1, arg2);
-- 
2.17.1