[FFmpeg-devel] [PATCH] x86: Remove inline MMX assembly that clobbers the FPU state

[Martin Storsjö]

These inline implementations of AV_COPY64, AV_SWAP64 and AV_ZERO64
are known to clobber the FPU state - which has to be restored
with the 'emms' instruction afterwards.

This was known and signaled with the FF_COPY_SWAP_ZERO_USES_MMX
define, which calling code seems to have been supposed to check,
in order to call emms_c() after using them. See
0b1972d4096df5879038f0af776f87f41e90ebd4,
29c4c0886d143790fcbeddbe40a23dfc6f56345c and
df215e575850e41b19aeb1fd99e53372a6b3d537 for history on earlier
fixes in the same area.

However, new code can use these AV_*64() macros without knowing
about the need to call emms_c().

Just get rid of these dangerous inline assembly snippets; this
doesn't make any difference for 64 bit architectures anyway.

Signed-off-by: Martin Storsjö <martin at martin.st>
---
 libavcodec/dca_core.c        | 16 ----------------
 libavutil/x86/intreadwrite.h | 36 ------------------------------------
 2 files changed, 52 deletions(-)

diff --git a/libavcodec/dca_core.c b/libavcodec/dca_core.c
index 60508fabb9..5dd727fc72 100644
--- a/libavcodec/dca_core.c
+++ b/libavcodec/dca_core.c
@@ -770,10 +770,6 @@ static void erase_adpcm_history(DCACoreDecoder *s)
     for (ch = 0; ch < DCA_CHANNELS; ch++)
         for (band = 0; band < DCA_SUBBANDS; band++)
             AV_ZERO128(s->subband_samples[ch][band] - DCA_ADPCM_COEFFS);
-
-#ifdef FF_COPY_SWAP_ZERO_USES_MMX
-    emms_c();
-#endif
 }
 
 static int alloc_sample_buffer(DCACoreDecoder *s)
@@ -837,10 +833,6 @@ static int parse_frame_data(DCACoreDecoder *s, enum HeaderType header, int xch_b
         }
     }
 
-#ifdef FF_COPY_SWAP_ZERO_USES_MMX
-    emms_c();
-#endif
-
     return 0;
 }
 
@@ -1283,10 +1275,6 @@ static void erase_x96_adpcm_history(DCACoreDecoder *s)
     for (ch = 0; ch < DCA_CHANNELS; ch++)
         for (band = 0; band < DCA_SUBBANDS_X96; band++)
             AV_ZERO128(s->x96_subband_samples[ch][band] - DCA_ADPCM_COEFFS);
-
-#ifdef FF_COPY_SWAP_ZERO_USES_MMX
-    emms_c();
-#endif
 }
 
 static int alloc_x96_sample_buffer(DCACoreDecoder *s)
@@ -1516,10 +1504,6 @@ static int parse_x96_frame_data(DCACoreDecoder *s, int exss, int xch_base)
         }
     }
 
-#ifdef FF_COPY_SWAP_ZERO_USES_MMX
-    emms_c();
-#endif
-
     return 0;
 }
 
diff --git a/libavutil/x86/intreadwrite.h b/libavutil/x86/intreadwrite.h
index 40f375b013..5e57d6a8cd 100644
--- a/libavutil/x86/intreadwrite.h
+++ b/libavutil/x86/intreadwrite.h
@@ -27,42 +27,6 @@
 
 #if HAVE_MMX
 
-#if !HAVE_FAST_64BIT && defined(__MMX__)
-
-#define FF_COPY_SWAP_ZERO_USES_MMX
-
-#define AV_COPY64 AV_COPY64
-static av_always_inline void AV_COPY64(void *d, const void *s)
-{
-    __asm__("movq   %1, %%mm0  \n\t"
-            "movq   %%mm0, %0  \n\t"
-            : "=m"(*(uint64_t*)d)
-            : "m" (*(const uint64_t*)s)
-            : "mm0");
-}
-
-#define AV_SWAP64 AV_SWAP64
-static av_always_inline void AV_SWAP64(void *a, void *b)
-{
-    __asm__("movq   %1, %%mm0  \n\t"
-            "movq   %0, %%mm1  \n\t"
-            "movq   %%mm0, %0  \n\t"
-            "movq   %%mm1, %1  \n\t"
-            : "+m"(*(uint64_t*)a), "+m"(*(uint64_t*)b)
-            ::"mm0", "mm1");
-}
-
-#define AV_ZERO64 AV_ZERO64
-static av_always_inline void AV_ZERO64(void *d)
-{
-    __asm__("pxor %%mm0, %%mm0  \n\t"
-            "movq %%mm0, %0     \n\t"
-            : "=m"(*(uint64_t*)d)
-            :: "mm0");
-}
-
-#endif /* !HAVE_FAST_64BIT && defined(__MMX__) */
-
 #ifdef __SSE__
 
 #define AV_COPY128 AV_COPY128
-- 
2.34.1