arm: intreadwrite: fix inline asm constraints for gcc 4.6 and later

With a dereferenced type-cast pointer as memory operand, gcc 4.6
and later will sometimes copy the data to a temporary location,
the address of which is used as the operand value, if it thinks
the target address might be misaligned.  Using a pointer to a
packed struct type instead does the right thing.

The 16-bit case is special since the ldrh instruction addressing
modes are limited compared to ldr.  The "Uq" constraint produces a
memory reference suitable for an ldrsb instruction, which supports
the same addressing modes as ldrh.  However, the restrictions appear
to apply only when the operand addresses a single byte.  The memory
reference must thus be split into two operands each targeting one
byte.  Finally, the "Uq" constraint is only available in ARM mode.
The Thumb-2 ldrh instruction supports most addressing modes so the
normal "m" constraint can be used there.

Signed-off-by: Mans Rullgard <mans@mansr.com>

1 files changed, 10 insertions, 3 deletions

diff --git a/libavutil/arm/intreadwrite.h b/libavutil/arm/intreadwrite.h
index 613abe511c..ec92d4d04b 100644
--- a/libavutil/arm/intreadwrite.h
+++ b/libavutil/arm/intreadwrite.h
@@ -27,8 +27,13 @@
 #define AV_RN16 AV_RN16
 static av_always_inline unsigned AV_RN16(const void *p)
 {
+    const uint8_t *q = p;
     unsigned v;
-    __asm__ ("ldrh %0, %1" : "=r"(v) : "m"(*(const uint16_t *)p));
+#ifdef __thumb__
+    __asm__ ("ldrh %0, %1" : "=r"(v) : "m"(q[0]), "m"(q[1]));
+#else
+    __asm__ ("ldrh %0, %1" : "=r"(v) : "Uq"(q[0]), "m"(q[1]));
+#endif
     return v;
 }
 
@@ -41,8 +46,9 @@ static av_always_inline void AV_WN16(void *p, uint16_t v)
 #define AV_RN32 AV_RN32
 static av_always_inline uint32_t AV_RN32(const void *p)
 {
+    const struct __attribute__((packed)) { uint32_t v; } *q = p;
     uint32_t v;
-    __asm__ ("ldr  %0, %1" : "=r"(v) : "m"(*(const uint32_t *)p));
+    __asm__ ("ldr  %0, %1" : "=r"(v) : "m"(*q));
     return v;
 }
 
@@ -55,11 +61,12 @@ static av_always_inline void AV_WN32(void *p, uint32_t v)
 #define AV_RN64 AV_RN64
 static av_always_inline uint64_t AV_RN64(const void *p)
 {
+    const struct __attribute__((packed)) { uint32_t v; } *q = p;
     uint64_t v;
     __asm__ ("ldr   %Q0, %1  \n\t"
              "ldr   %R0, %2  \n\t"
              : "=&r"(v)
-             : "m"(*(const uint32_t*)p), "m"(*((const uint32_t*)p+1)));
+             : "m"(q[0]), "m"(q[1]));
     return v;
 }