i965: Stop passing num_samples to intel_miptree_alloc_hiz().

[mesa.git] / src / mesa / drivers / dri / intel / intel_tex_copy.c

diff --git a/src/mesa/drivers/dri/intel/intel_tex_copy.c b/src/mesa/drivers/dri/intel/intel_tex_copy.c
index f4366330f88278b23a6a5fc98988777724dc3c46..6043ed26adbf558cee2cae6ccd496e013e5fd959 100644 (file)
--- a/src/mesa/drivers/dri/intel/intel_tex_copy.c
+++ b/src/mesa/drivers/dri/intel/intel_tex_copy.c
@@ -41,6 +41,9 @@
 #include "intel_fbo.h"
 #include "intel_tex.h"
 #include "intel_blit.h"
+#ifndef I915
+#include "brw_context.h"
+#endif
 
 #define FILE_DEBUG_FLAG DEBUG_TEXTURE
 
@@ -70,6 +73,32 @@ intel_copy_texsubimage(struct intel_context *intel,
       assert(region);
    }
 
+   /* According to the Ivy Bridge PRM, Vol1 Part4, section 1.2.1.2 (Graphics
+    * Data Size Limitations):
+    *
+    *    The BLT engine is capable of transferring very large quantities of
+    *    graphics data. Any graphics data read from and written to the
+    *    destination is permitted to represent a number of pixels that
+    *    occupies up to 65,536 scan lines and up to 32,768 bytes per scan line
+    *    at the destination. The maximum number of pixels that may be
+    *    represented per scan line’s worth of graphics data depends on the
+    *    color depth.
+    *
+    * Furthermore, intelEmitCopyBlit (which is called below) uses a signed
+    * 16-bit integer to represent buffer pitch, so it can only handle buffer
+    * pitches < 32k.
+    *
+    * As a result of these two limitations, we can only use the blitter to do
+    * this copy when the region's pitch is less than 32k.
+    */
+   if (region->pitch >= 32768)
+      return false;
+
+   if (intelImage->base.Base.TexObject->Target == GL_TEXTURE_1D_ARRAY ||
+       intelImage->base.Base.TexObject->Target == GL_TEXTURE_2D_ARRAY) {
+      perf_debug("no support for array textures\n");
+   }
+
    copy_supported = intelImage->base.Base.TexFormat == intel_rb_format(irb);
 
    /* Converting ARGB8888 to XRGB8888 is trivial: ignore the alpha bits */
@@ -85,8 +114,7 @@ intel_copy_texsubimage(struct intel_context *intel,
    }
 
    if (!copy_supported && !copy_supported_with_alpha_override) {
-      if (unlikely(INTEL_DEBUG & DEBUG_PERF))
-        fprintf(stderr, "%s mismatched formats %s, %s\n",
+      perf_debug("%s mismatched formats %s, %s\n",
                 __FUNCTION__,
                 _mesa_get_format_name(intelImage->base.Base.TexFormat),
                 _mesa_get_format_name(intel_rb_format(irb)));
@@ -101,7 +129,6 @@ intel_copy_texsubimage(struct intel_context *intel,
       intel_miptree_get_image_offset(intelImage->mt,
                                     intelImage->base.Base.Level,
                                     intelImage->base.Base.Face,
-                                    0,
                                     &image_x, &image_y);
 
       /* The blitter can't handle Y-tiled buffers. */
@@ -152,15 +179,28 @@ intelCopyTexSubImage(struct gl_context *ctx, GLuint dims,
                      GLint x, GLint y,
                      GLsizei width, GLsizei height)
 {
-   if (dims == 3 || !intel_copy_texsubimage(intel_context(ctx),
-                               intel_texture_image(texImage),
-                               xoffset, yoffset,
-                               intel_renderbuffer(rb), x, y, width, height)) {
-      fallback_debug("%s - fallback to swrast\n", __FUNCTION__);
-      _mesa_meta_CopyTexSubImage(ctx, dims, texImage,
-                                 xoffset, yoffset, zoffset,
-                                 rb, x, y, width, height);
+   struct intel_context *intel = intel_context(ctx);
+   if (dims != 3) {
+#ifndef I915
+      /* Try BLORP first.  It can handle almost everything. */
+      if (brw_blorp_copytexsubimage(intel, rb, texImage, x, y,
+                                    xoffset, yoffset, width, height))
+         return;
+#endif
+
+      /* Next, try the BLT engine. */
+      if (intel_copy_texsubimage(intel,
+                                 intel_texture_image(texImage),
+                                 xoffset, yoffset,
+                                 intel_renderbuffer(rb), x, y, width, height))
+         return;
    }
+
+   /* Finally, fall back to meta.  This will likely be slow. */
+   perf_debug("%s - fallback to swrast\n", __FUNCTION__);
+   _mesa_meta_CopyTexSubImage(ctx, dims, texImage,
+                              xoffset, yoffset, zoffset,
+                              rb, x, y, width, height);
 }