tcg/arm: Reduce vector alignment requirement for NEON

With arm32, the ABI gives us 8-byte alignment for the stack.
While it's possible to realign the stack to provide 16-byte alignment,
it's far easier to simply not encode 16-byte alignment in the
VLD1 and VST1 instructions that we emit.

Remove the assertion in temp_allocate_frame, limit natural alignment
to the provided stack alignment, and add a comment.

Resolves: https://bugzilla.redhat.com/show_bug.cgi?id=1999878
Reported-by: Richard W.M. Jones <rjones@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20210912174925.200132-1-richard.henderson@linaro.org>
Message-Id: <20211206191335.230683-2-richard.henderson@linaro.org>
(cherry picked from commit b9537d5904f6e3df896264a6144883ab07db9608)
Signed-off-by: Michael Roth <michael.roth@amd.com>

diff --git a/tcg/arm/tcg-target.c.inc b/tcg/arm/tcg-target.c.inc
index 007ceee68e23102ad96dd47e2d0204845718d9f9..34acfb522c22c78c580cf93e6caa794d11e639a6 100644 (file)
--- a/tcg/arm/tcg-target.c.inc
+++ b/tcg/arm/tcg-target.c.inc
@@ -2477,8 +2477,13 @@ static void tcg_out_ld(TCGContext *s, TCGType type, TCGReg arg,
         tcg_out_vldst(s, INSN_VLD1 | 0x7d0, arg, arg1, arg2);
         return;
     case TCG_TYPE_V128:
-        /* regs 2; size 8; align 16 */
-        tcg_out_vldst(s, INSN_VLD1 | 0xae0, arg, arg1, arg2);
+        /*
+         * We have only 8-byte alignment for the stack per the ABI.
+         * Rather than dynamically re-align the stack, it's easier
+         * to simply not request alignment beyond that.  So:
+         * regs 2; size 8; align 8
+         */
+        tcg_out_vldst(s, INSN_VLD1 | 0xad0, arg, arg1, arg2);
         return;
     default:
         g_assert_not_reached();
@@ -2497,8 +2502,8 @@ static void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg,
         tcg_out_vldst(s, INSN_VST1 | 0x7d0, arg, arg1, arg2);
         return;
     case TCG_TYPE_V128:
-        /* regs 2; size 8; align 16 */
-        tcg_out_vldst(s, INSN_VST1 | 0xae0, arg, arg1, arg2);
+        /* See tcg_out_ld re alignment: regs 2; size 8; align 8 */
+        tcg_out_vldst(s, INSN_VST1 | 0xad0, arg, arg1, arg2);
         return;
     default:
         g_assert_not_reached();

diff --git a/tcg/tcg.c b/tcg/tcg.c
index 4142d42d7752223828e1e73bd7a62a8713a995e1..ca5bcc46358225bac0ed81a92b4c2aa6a4309620 100644 (file)
--- a/tcg/tcg.c
+++ b/tcg/tcg.c
@@ -3060,7 +3060,13 @@ static void temp_allocate_frame(TCGContext *s, TCGTemp *ts)
         g_assert_not_reached();
     }
 
-    assert(align <= TCG_TARGET_STACK_ALIGN);
+    /*
+     * Assume the stack is sufficiently aligned.
+     * This affects e.g. ARM NEON, where we have 8 byte stack alignment
+     * and do not require 16 byte vector alignment.  This seems slightly
+     * easier than fully parameterizing the above switch statement.
+     */
+    align = MIN(TCG_TARGET_STACK_ALIGN, align);
     off = ROUND_UP(s->current_frame_offset, align);
 
     /* If we've exhausted the stack frame, restart with a smaller TB. */