diff options
Diffstat (limited to 'media-video/ffmpeg/files/ffmpeg-6.0.1-alignment.patch')
| -rw-r--r-- | media-video/ffmpeg/files/ffmpeg-6.0.1-alignment.patch | 114 |
1 files changed, 114 insertions, 0 deletions
diff --git a/media-video/ffmpeg/files/ffmpeg-6.0.1-alignment.patch b/media-video/ffmpeg/files/ffmpeg-6.0.1-alignment.patch new file mode 100644 index 000000000000..256feab8aea2 --- /dev/null +++ b/media-video/ffmpeg/files/ffmpeg-6.0.1-alignment.patch @@ -0,0 +1,114 @@ +https://trac.ffmpeg.org/ticket/10549 +https://bugs.gentoo.org/915384 +https://git.videolan.org/?p=ffmpeg.git;a=patch;h=7945d30e91b96d2f4f5b612048169087d214d41e + +From 7945d30e91b96d2f4f5b612048169087d214d41e Mon Sep 17 00:00:00 2001 +From: Timo Rothenpieler <timo@rothenpieler.org> +Date: Sun, 3 Dec 2023 21:01:50 +0100 +Subject: [PATCH] avutil/mem: limit alignment to maximum simd align + +FFmpeg has instances of DECLARE_ALIGNED(32, ...) in a lot of structs, +which then end up heap-allocated. +By declaring any variable in a struct, or tree of structs, to be 32 byte +aligned, it allows the compiler to safely assume the entire struct +itself is also 32 byte aligned. + +This might make the compiler emit code which straight up crashes or +misbehaves in other ways, and at least in one instances is now +documented to actually do (see ticket 10549 on trac). +The issue there is that an unrelated variable in SingleChannelElement is +declared to have an alignment of 32 bytes. So if the compiler does a copy +in decode_cpe() with avx instructions, but ffmpeg is built with +--disable-avx, this results in a crash, since the memory is only 16 byte +aligned. + +Mind you, even if the compiler does not emit avx instructions, the code +is still invalid and could misbehave. It just happens not to. Declaring +any variable in a struct with a 32 byte alignment promises 32 byte +alignment of the whole struct to the compiler. + +This patch limits the maximum alignment to the maximum possible simd +alignment according to configure. +While not perfect, it at the very least gets rid of a lot of UB, by +matching up the maximum DECLARE_ALIGNED value with the alignment of heap +allocations done by lavu. +--- + libavutil/mem.c | 2 +- + libavutil/mem_internal.h | 33 ++++++++++++++++++++++++++++----- + 2 files changed, 29 insertions(+), 6 deletions(-) + +diff --git a/libavutil/mem.c b/libavutil/mem.c +index 36b8940a0c..62163b4cb3 100644 +--- a/libavutil/mem.c ++++ b/libavutil/mem.c +@@ -62,7 +62,7 @@ void free(void *ptr); + + #endif /* MALLOC_PREFIX */ + +-#define ALIGN (HAVE_AVX512 ? 64 : (HAVE_AVX ? 32 : 16)) ++#define ALIGN (HAVE_SIMD_ALIGN_64 ? 64 : (HAVE_SIMD_ALIGN_32 ? 32 : 16)) + + /* NOTE: if you want to override these functions with your own + * implementations (not recommended) you have to link libav* as +diff --git a/libavutil/mem_internal.h b/libavutil/mem_internal.h +index 2448c606f1..b1d89a0605 100644 +--- a/libavutil/mem_internal.h ++++ b/libavutil/mem_internal.h +@@ -76,27 +76,50 @@ + */ + + #if defined(__INTEL_COMPILER) && __INTEL_COMPILER < 1110 || defined(__SUNPRO_C) +- #define DECLARE_ALIGNED(n,t,v) t __attribute__ ((aligned (n))) v ++ #define DECLARE_ALIGNED_T(n,t,v) t __attribute__ ((aligned (n))) v + #define DECLARE_ASM_ALIGNED(n,t,v) t __attribute__ ((aligned (n))) v + #define DECLARE_ASM_CONST(n,t,v) const t __attribute__ ((aligned (n))) v + #elif defined(__DJGPP__) +- #define DECLARE_ALIGNED(n,t,v) t __attribute__ ((aligned (FFMIN(n, 16)))) v ++ #define DECLARE_ALIGNED_T(n,t,v) t __attribute__ ((aligned (FFMIN(n, 16)))) v + #define DECLARE_ASM_ALIGNED(n,t,v) t av_used __attribute__ ((aligned (FFMIN(n, 16)))) v + #define DECLARE_ASM_CONST(n,t,v) static const t av_used __attribute__ ((aligned (FFMIN(n, 16)))) v + #elif defined(__GNUC__) || defined(__clang__) +- #define DECLARE_ALIGNED(n,t,v) t __attribute__ ((aligned (n))) v ++ #define DECLARE_ALIGNED_T(n,t,v) t __attribute__ ((aligned (n))) v + #define DECLARE_ASM_ALIGNED(n,t,v) t av_used __attribute__ ((aligned (n))) v + #define DECLARE_ASM_CONST(n,t,v) static const t av_used __attribute__ ((aligned (n))) v + #elif defined(_MSC_VER) +- #define DECLARE_ALIGNED(n,t,v) __declspec(align(n)) t v ++ #define DECLARE_ALIGNED_T(n,t,v) __declspec(align(n)) t v + #define DECLARE_ASM_ALIGNED(n,t,v) __declspec(align(n)) t v + #define DECLARE_ASM_CONST(n,t,v) __declspec(align(n)) static const t v + #else +- #define DECLARE_ALIGNED(n,t,v) t v ++ #define DECLARE_ALIGNED_T(n,t,v) t v + #define DECLARE_ASM_ALIGNED(n,t,v) t v + #define DECLARE_ASM_CONST(n,t,v) static const t v + #endif + ++#if HAVE_SIMD_ALIGN_64 ++ #define ALIGN_64 64 ++ #define ALIGN_32 32 ++#elif HAVE_SIMD_ALIGN_32 ++ #define ALIGN_64 32 ++ #define ALIGN_32 32 ++#else ++ #define ALIGN_64 16 ++ #define ALIGN_32 16 ++#endif ++ ++#define DECLARE_ALIGNED(n,t,v) DECLARE_ALIGNED_V(n,t,v) ++ ++// Macro needs to be double-wrapped in order to expand ++// possible other macros being passed for n. ++#define DECLARE_ALIGNED_V(n,t,v) DECLARE_ALIGNED_##n(t,v) ++ ++#define DECLARE_ALIGNED_4(t,v) DECLARE_ALIGNED_T( 4, t, v) ++#define DECLARE_ALIGNED_8(t,v) DECLARE_ALIGNED_T( 8, t, v) ++#define DECLARE_ALIGNED_16(t,v) DECLARE_ALIGNED_T( 16, t, v) ++#define DECLARE_ALIGNED_32(t,v) DECLARE_ALIGNED_T(ALIGN_32, t, v) ++#define DECLARE_ALIGNED_64(t,v) DECLARE_ALIGNED_T(ALIGN_64, t, v) ++ + // Some broken preprocessors need a second expansion + // to be forced to tokenize __VA_ARGS__ + #define E1(x) x +-- +2.30.2 |