Fix stack spills for arm neon.

-----BEGIN PGP SIGNATURE-----
 
 iQFRBAABCgA7FiEEekgeeIaLTbaoWgXAZN846K9+IV8FAmGvcNUdHHJpY2hhcmQu
 aGVuZGVyc29uQGxpbmFyby5vcmcACgkQZN846K9+IV/Frgf8CCasn2VfHSZxUHVe
 8Uc9vLeIVCht9kP3uP5GrRsyKljsyubQSf0ADSBuslLwZN5Nw9fElXiWoqW0jbOv
 hKJLEyhaUB02u0tGCIOvuAL4/cYBt0d9MWafqLrn5G43E9PjBAZiwQl0SxJkr5ju
 b2oKkvBFohy2x3W89pfw/Dbw3BoDWJe6d0Ky5R9UuVyXKLT8em/Ftr/J3+AGZh47
 h3S6LVrryvrd8olhnT4oZGRAq/Nm7eWMHyNfX+8cgxze0ov8mO4wqdipBIpVidgP
 2RYjZVesecOOJuoyiy7O1ef62n18Df8pGHooRfvCRGG895dRbp6vyOdpGOF78m6J
 j7GiSg==
 =LmtK
 -----END PGP SIGNATURE-----

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:
Richard Henderson 2021-12-07 06:40:14 -08:00
commit 92ac58e34c
2 changed files with 16 additions and 5 deletions

View File

@ -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();

View File

@ -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. */