mirror of
https://github.com/izzy2lost/xemu.git
synced 2026-07-06 00:20:22 -07:00
Merge tag 'pull-tcg-20211207' of https://gitlab.com/rth7680/qemu into staging
Fix stack spills for arm neon. # gpg: Signature made Tue 07 Dec 2021 06:33:57 AM PST # gpg: using RSA key 7A481E78868B4DB6A85A05C064DF38E8AF7E215F # gpg: issuer "richard.henderson@linaro.org" # gpg: Good signature from "Richard Henderson <richard.henderson@linaro.org>" [ultimate] * tag 'pull-tcg-20211207' of https://gitlab.com/rth7680/qemu: tcg/arm: Reduce vector alignment requirement for NEON Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This commit is contained in:
@@ -2523,8 +2523,13 @@ 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();
|
||||
@@ -2543,8 +2548,8 @@ 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();
|
||||
|
||||
@@ -3061,7 +3061,13 @@ 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. */
|
||||
|
||||
Reference in New Issue
Block a user