i965: Use __attribute__((flatten)) on fast tiled teximage code.

The fast tiled texture upload code does not compile with GCC 4.8's -Og
optimization flag.

memcpy() has the always_inline attribute set.  This poses a problem,
since {x,y}tile_copy_faster calls it indirectly via {x,y}tile_copy,
and {x,y}tile_copy normally aren't inlined at -Og.

Using __attribute__((flatten)) tells GCC to inline every function call
inside the function, which I believe was the author's intent.

Fix suggested by Alexander Monakov.

Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Chad Versace <chad.versace@linux.intel.com>
Cc: mesa-stable@lists.freedesktop.org

src/mesa/drivers/dri/i965/intel_tex_subimage.c

@@ -331,6 +331,12 @@ ytile_copy(
    }
 }
 
+#ifdef __GNUC__
+#define FLATTEN __attribute__((flatten))
+#else
+#define FLATTEN
+#endif
+
 /**
  * Copy texture data from linear to X tile layout, faster.
  *
@@ -340,7 +346,7 @@ ytile_copy(
  *
  * \copydoc tile_copy_fn
  */
-static void
+static FLATTEN void
 xtile_copy_faster(uint32_t x0, uint32_t x1, uint32_t x2, uint32_t x3,
                   uint32_t y0, uint32_t y1,
                   char *dst, const char *src,
@@ -376,7 +382,7 @@ xtile_copy_faster(uint32_t x0, uint32_t x1, uint32_t x2, uint32_t x3,
  *
  * \copydoc tile_copy_fn
  */
-static void
+static FLATTEN void
 ytile_copy_faster(uint32_t x0, uint32_t x1, uint32_t x2, uint32_t x3,
                   uint32_t y0, uint32_t y1,
                   char *dst, const char *src,