i965: Fix {src, dst}_pitch alignment check for XY_SRC_COPY_BLT

Current code checks the alignment restrictions only for Y tiling.
From Broadwell PRM vol 10:

 "pitch is of 512Byte granularity for Tile-X: This means the tiled-x
  surface pitch can be (512, 1024, 1536, 2048...)/4 (in Dwords)."

This patch adds the restriction for X tiling as well.

Signed-off-by: Anuj Phogat <anuj.phogat@gmail.com>
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>
Reviewed-by: Chad Versace <chad.versace@intel.com>

diff --git a/src/mesa/drivers/dri/i965/intel_blit.c b/src/mesa/drivers/dri/i965/intel_blit.c
index 8bb4120793006aa1efc5064e9f2c4aed1804e94c..0cd2a203cb39c42b9895a87fbf8e90d54225e264 100644 (file)
--- a/src/mesa/drivers/dri/i965/intel_blit.c
+++ b/src/mesa/drivers/dri/i965/intel_blit.c
@@ -522,6 +522,8 @@ intelEmitCopyBlit(struct brw_context *brw,
    bool dst_y_tiled = dst_tiling == I915_TILING_Y;
    bool src_y_tiled = src_tiling == I915_TILING_Y;
    bool use_fast_copy_blit = false;
+   uint32_t src_tile_w, src_tile_h;
+   uint32_t dst_tile_w, dst_tile_h;
 
    if ((dst_y_tiled || src_y_tiled) && brw->gen < 6)
       return false;
@@ -550,6 +552,9 @@ intelEmitCopyBlit(struct brw_context *brw,
        src_buffer, src_pitch, src_offset, src_x, src_y,
        dst_buffer, dst_pitch, dst_offset, dst_x, dst_y, w, h);
 
+   intel_get_tile_dims(src_tiling, src_tr_mode, cpp, &src_tile_w, &src_tile_h);
+   intel_get_tile_dims(dst_tiling, dst_tr_mode, cpp, &dst_tile_w, &dst_tile_h);
+
    use_fast_copy_blit = can_fast_copy_blit(brw,
                                            src_buffer,
                                            src_x, src_y,
@@ -588,8 +593,8 @@ intelEmitCopyBlit(struct brw_context *brw,
                         cpp, use_fast_copy_blit);
 
    } else {
-      assert(!dst_y_tiled || (dst_pitch % 128) == 0);
-      assert(!src_y_tiled || (src_pitch % 128) == 0);
+      assert(src_tiling == I915_TILING_NONE || (src_pitch % src_tile_w) == 0);
+      assert(dst_tiling == I915_TILING_NONE || (dst_pitch % dst_tile_w) == 0);
 
       /* For big formats (such as floating point), do the copy using 16 or
        * 32bpp and multiply the coordinates.