Merge tag 'pull-tcg-20230116' of https://gitlab.com/rth7680/qemu into staging

- Reorg cpu_tb_exec around setjmp.
- Use __attribute__((target)) for buffer_is_zero.
- Add perfmap and jitdump for perf support.

# -----BEGIN PGP SIGNATURE-----
#
# iQFRBAABCgA7FiEEekgeeIaLTbaoWgXAZN846K9+IV8FAmPFtXgdHHJpY2hhcmQu
# aGVuZGVyc29uQGxpbmFyby5vcmcACgkQZN846K9+IV+62Af/YLdd77+IO8wcPN1n
# 2esKNlrrYQ2/x40Hede6L4pp+Qz6M810YgNbhMchBS3u8YGIFzmVLaiz5N4nBGTq
# ricOit6Jj2KonlxWaxgma1BW36ydBIwphC20WjrLTVgdNGvxmy4JKbfklTd4oIZ+
# +Kf1VTN1bbt7vfDntd454ck2rhtVZBEvYTynikA3LJ1W7EVN5etDUnrN3VwbaTTK
# 0aY8MbDfGUASyrDzmaRcF5F90K+V2STuEUs1whgOuTBusZ6n3+FSDhW8CuDhsy/l
# rXtPkQba3rtUWfJ1+o7bx3Gg4nbfn/9lxIfGwhQ79ywD9InjqLqu9etwVyhijx+n
# k+tvPw==
# =xFfF
# -----END PGP SIGNATURE-----
# gpg: Signature made Mon 16 Jan 2023 20:37:12 GMT
# gpg:                using RSA key 7A481E78868B4DB6A85A05C064DF38E8AF7E215F
# gpg:                issuer "richard.henderson@linaro.org"
# gpg: Good signature from "Richard Henderson <richard.henderson@linaro.org>" [full]
# Primary key fingerprint: 7A48 1E78 868B 4DB6 A85A  05C0 64DF 38E8 AF7E 215F

* tag 'pull-tcg-20230116' of https://gitlab.com/rth7680/qemu:
  accel/tcg: Split out cpu_exec_{setjmp,loop}
  util/bufferiszero: Use __attribute__((target)) for avx2/avx512
  tcg: add perfmap and jitdump
  accel/tcg: Add debuginfo support
  linux-user: Clean up when exiting due to a signal

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 6 insertions, 35 deletions

diff --git a/util/bufferiszero.c b/util/bufferiszero.c
index ec3cd4ca15..1790ded7d4 100644
--- a/util/bufferiszero.c
+++ b/util/bufferiszero.c
@@ -64,18 +64,11 @@ buffer_zero_int(const void *buf, size_t len)
 }
 
 #if defined(CONFIG_AVX512F_OPT) || defined(CONFIG_AVX2_OPT) || defined(__SSE2__)
-/* Do not use push_options pragmas unnecessarily, because clang
- * does not support them.
- */
-#if defined(CONFIG_AVX512F_OPT) || defined(CONFIG_AVX2_OPT)
-#pragma GCC push_options
-#pragma GCC target("sse2")
-#endif
-#include <emmintrin.h>
+#include <immintrin.h>
 
 /* Note that each of these vectorized functions require len >= 64.  */
 
-static bool
+static bool __attribute__((target("sse2")))
 buffer_zero_sse2(const void *buf, size_t len)
 {
     __m128i t = _mm_loadu_si128(buf);
@@ -104,20 +97,9 @@ buffer_zero_sse2(const void *buf, size_t len)
 
     return _mm_movemask_epi8(_mm_cmpeq_epi8(t, zero)) == 0xFFFF;
 }
-#if defined(CONFIG_AVX512F_OPT) || defined(CONFIG_AVX2_OPT)
-#pragma GCC pop_options
-#endif
 
 #ifdef CONFIG_AVX2_OPT
-/* Note that due to restrictions/bugs wrt __builtin functions in gcc <= 4.8,
- * the includes have to be within the corresponding push_options region, and
- * therefore the regions themselves have to be ordered with increasing ISA.
- */
-#pragma GCC push_options
-#pragma GCC target("sse4")
-#include <smmintrin.h>
-
-static bool
+static bool __attribute__((target("sse4")))
 buffer_zero_sse4(const void *buf, size_t len)
 {
     __m128i t = _mm_loadu_si128(buf);
@@ -145,12 +127,7 @@ buffer_zero_sse4(const void *buf, size_t len)
     return _mm_testz_si128(t, t);
 }
 
-#pragma GCC pop_options
-#pragma GCC push_options
-#pragma GCC target("avx2")
-#include <immintrin.h>
-
-static bool
+static bool __attribute__((target("avx2")))
 buffer_zero_avx2(const void *buf, size_t len)
 {
     /* Begin with an unaligned head of 32 bytes.  */
@@ -176,15 +153,10 @@ buffer_zero_avx2(const void *buf, size_t len)
 
     return _mm256_testz_si256(t, t);
 }
-#pragma GCC pop_options
 #endif /* CONFIG_AVX2_OPT */
 
 #ifdef CONFIG_AVX512F_OPT
-#pragma GCC push_options
-#pragma GCC target("avx512f")
-#include <immintrin.h>
-
-static bool
+static bool __attribute__((target("avx512f")))
 buffer_zero_avx512(const void *buf, size_t len)
 {
     /* Begin with an unaligned head of 64 bytes.  */
@@ -210,8 +182,7 @@ buffer_zero_avx512(const void *buf, size_t len)
     return !_mm512_test_epi64_mask(t, t);
 
 }
-#pragma GCC pop_options
-#endif
+#endif /* CONFIG_AVX512F_OPT */
 
 
 /* Note that for test_buffer_is_zero_next_accel, the most preferred