radeonsi: More assorted depth/stencil changes ported from r600g.

[ Squashed port of the following r600g commits: - Michel Dänzer ]

commit 428e37c2da420f7dc14a2ea265f2387270f9bee1
Author: Marek Olšák <[email protected]>
Date:   Tue Oct 2 22:02:54 2012 +0200

    r600g: add in-place DB decompression and texturing with DB tiling

    The decompression is done in-place and only the compressed tiles are
    decompressed. Note: R6xx-R7xx can do that only with Z16 and Z32F.

    The texture unit is programmed to use non-displayable tiling and depth
    ordering of samples, so that it can fetch the texture in the native DB format.

    The latest version of the libdrm surface allocator is required for stencil
    texturing to work. The old one didn't create the mipmap tree correctly.
    We need a separate mipmap tree for stencil, because the stencil mipmap
    offsets are not really depth offsets/4.

    There are still some known bugs, but this should save some memory and it also
    improves performance a little bit in Lightsmark (especially with low
    resolutions; tested with Radeon HD 5000).

    The DB->CB copy is still used for transfers.

commit e2f623f1d6da9bc987582ff68d0471061ae44030
Author: Marek Olšák <[email protected]>
Date:   Sat Jul 28 13:55:59 2012 +0200

    r600g: don't decompress depth or stencil if there isn't any

commit 43e226b6efb77db2247741cc2057d9625a2cfa05
Author: Marek Olšák <[email protected]>
Date:   Wed Jul 18 00:32:50 2012 +0200

    r600g: optimize uploading depth textures

    Make it only copy the portion of a depth texture being uploaded and
    not the whole 2D layer.

    There is also a little code cleanup.

commit b242adbe5cfa165b252064a1ea36f802d8251ef1
Author: Marek Olšák <[email protected]>
Date:   Wed Jul 18 00:17:46 2012 +0200

    r600g: remove needless wrapper r600_texture_depth_flush

commit 611dd529425281d73f1f0ad2000362d4a5525a25
Author: Marek Olšák <[email protected]>
Date:   Wed Jul 18 00:05:14 2012 +0200

    r600g: init_flushed_depth_texture should be able to report errors

commit 80755ff56317446a8c89e611edc1fdf320d6779b
Author: Marek Olšák <[email protected]>
Date:   Sat Jul 14 17:06:27 2012 +0200

    r600g: properly track which textures are depth

    This fixes the issue with have_depth_texture never being set to false.

commit fe1fd675565231b49d3ac53d0b4bec39d8bc6781
Author: Marek Olšák <[email protected]>
Date:   Sun Jul 8 03:10:37 2012 +0200

    r600g: don't flush depth textures set as colorbuffers

    The only case a depth buffer can be set as a color buffer is when flushing.

    That wasn't always the case, but now this code isn't required anymore.

commit 5a17d8318ec2c20bf86275044dc8f715105a88e7
Author: Marek Olšák <[email protected]>
Date:   Sun Jul 8 02:14:18 2012 +0200

    r600g: flush depth textures bound to vertex shaders

    This was missing/broken. There are also minor code cleanups.

commit dee58f94af833906863b0ff2955b20f3ab407e63
Author: Marek Olšák <[email protected]>
Date:   Sun Jul 8 01:54:24 2012 +0200

    r600g: do fine-grained depth texture flushing

    - maintain a mask of which mipmap levels are dirty (instead of one big flag)
    - only flush what was requested at a given point and not the whole resource
      (most often only one level and one layer has to be flushed)

Signed-off-by: Michel Dänzer <[email protected]>

1 files changed, 63 insertions, 43 deletions

diff --git a/src/gallium/drivers/radeonsi/r600_texture.c b/src/gallium/drivers/radeonsi/r600_texture.c
index b790d8d3719..2bbf2ebb212 100644
--- a/src/gallium/drivers/radeonsi/r600_texture.c
+++ b/src/gallium/drivers/radeonsi/r600_texture.c
@@ -331,13 +331,15 @@ static void *si_texture_transfer_map(struct pipe_context *ctx,
 		*/
 		struct r600_resource_texture *staging_depth;
 
-		r600_texture_depth_flush(ctx, texture, &staging_depth);
-		if (!staging_depth) {
+		if (!r600_init_flushed_depth_texture(ctx, texture, &staging_depth)) {
 			R600_ERR("failed to create temporary texture to hold untiled copy\n");
 			pipe_resource_reference(&trans->transfer.resource, NULL);
 			FREE(trans);
 			return NULL;
 		}
+		si_blit_uncompress_depth(ctx, rtex, staging_depth,
+					 level, level,
+					 box->z, box->z + box->depth - 1);
 		trans->transfer.stride = staging_depth->surface.level[level].pitch_bytes;
 		trans->offset = r600_texture_get_offset(staging_depth, level, box->z);
 
@@ -424,22 +426,13 @@ static void si_texture_transfer_unmap(struct pipe_context *ctx,
 	}
 	rctx->ws->buffer_unmap(buf);
 
-	if (rtex->is_depth) {
-		if ((transfer->usage & PIPE_TRANSFER_WRITE) && rtransfer->staging) {
-			struct pipe_box sbox;
-
-			sbox.x = sbox.y = sbox.z = 0;
-			sbox.width = texture->width0;
-			sbox.height = texture->height0;
-			/* XXX that might be wrong */
-			sbox.depth = 1;
-
-			ctx->resource_copy_region(ctx, texture, 0, 0, 0, 0,
-						  &si_resource(rtransfer->staging)->b.b, 0,
-						  &sbox);
-		}
-	} else if (rtransfer->staging) {
-		if (transfer->usage & PIPE_TRANSFER_WRITE) {
+	if ((transfer->usage & PIPE_TRANSFER_WRITE) && rtransfer->staging) {
+		if (rtex->is_depth) {
+			ctx->resource_copy_region(ctx, texture, transfer->level,
+						  transfer->box.x, transfer->box.y, transfer->box.z,
+						  &si_resource(rtransfer->staging)->b.b, transfer->level,
+						  &transfer->box);
+		} else {
 			r600_copy_from_staging_texture(ctx, rtransfer);
 		}
 	}
@@ -461,6 +454,8 @@ static const struct u_resource_vtbl r600_texture_vtbl =
 	NULL	/* transfer_inline_write */
 };
 
+DEBUG_GET_ONCE_BOOL_OPTION(print_texdepth, "RADEON_PRINT_TEXDEPTH", FALSE);
+
 static struct r600_resource_texture *
 r600_texture_create_object(struct pipe_screen *screen,
 			   const struct pipe_resource *base,
@@ -515,6 +510,51 @@ r600_texture_create_object(struct pipe_screen *screen,
 		resource->domains = RADEON_DOMAIN_GTT | RADEON_DOMAIN_VRAM;
 	}
 
+	if (debug_get_option_print_texdepth() && rtex->is_depth) {
+		printf("Texture: npix_x=%u, npix_y=%u, npix_z=%u, blk_w=%u, "
+		       "blk_h=%u, blk_d=%u, array_size=%u, last_level=%u, "
+		       "bpe=%u, nsamples=%u, flags=%u\n",
+		       rtex->surface.npix_x, rtex->surface.npix_y,
+		       rtex->surface.npix_z, rtex->surface.blk_w,
+		       rtex->surface.blk_h, rtex->surface.blk_d,
+		       rtex->surface.array_size, rtex->surface.last_level,
+		       rtex->surface.bpe, rtex->surface.nsamples,
+		       rtex->surface.flags);
+		if (rtex->surface.flags & RADEON_SURF_ZBUFFER) {
+			for (int i = 0; i <= rtex->surface.last_level; i++) {
+				printf("  Z %i: offset=%llu, slice_size=%llu, npix_x=%u, "
+				       "npix_y=%u, npix_z=%u, nblk_x=%u, nblk_y=%u, "
+				       "nblk_z=%u, pitch_bytes=%u, mode=%u\n",
+				       i, rtex->surface.level[i].offset,
+				       rtex->surface.level[i].slice_size,
+				       rtex->surface.level[i].npix_x,
+				       rtex->surface.level[i].npix_y,
+				       rtex->surface.level[i].npix_z,
+				       rtex->surface.level[i].nblk_x,
+				       rtex->surface.level[i].nblk_y,
+				       rtex->surface.level[i].nblk_z,
+				       rtex->surface.level[i].pitch_bytes,
+				       rtex->surface.level[i].mode);
+			}
+		}
+		if (rtex->surface.flags & RADEON_SURF_SBUFFER) {
+			for (int i = 0; i <= rtex->surface.last_level; i++) {
+				printf("  S %i: offset=%llu, slice_size=%llu, npix_x=%u, "
+				       "npix_y=%u, npix_z=%u, nblk_x=%u, nblk_y=%u, "
+				       "nblk_z=%u, pitch_bytes=%u, mode=%u\n",
+				       i, rtex->surface.stencil_level[i].offset,
+				       rtex->surface.stencil_level[i].slice_size,
+				       rtex->surface.stencil_level[i].npix_x,
+				       rtex->surface.stencil_level[i].npix_y,
+				       rtex->surface.stencil_level[i].npix_z,
+				       rtex->surface.stencil_level[i].nblk_x,
+				       rtex->surface.stencil_level[i].nblk_y,
+				       rtex->surface.stencil_level[i].nblk_z,
+				       rtex->surface.stencil_level[i].pitch_bytes,
+				       rtex->surface.stencil_level[i].mode);
+			}
+		}
+	}
 	return rtex;
 }
 
@@ -622,7 +662,7 @@ struct pipe_resource *si_texture_from_handle(struct pipe_screen *screen,
 								  stride, 0, buf, FALSE, &surface);
 }
 
-void r600_init_flushed_depth_texture(struct pipe_context *ctx,
+bool r600_init_flushed_depth_texture(struct pipe_context *ctx,
 				     struct pipe_resource *texture,
 				     struct r600_resource_texture **staging)
 {
@@ -632,7 +672,7 @@ void r600_init_flushed_depth_texture(struct pipe_context *ctx,
 			staging : &rtex->flushed_depth_texture;
 
 	if (!staging && rtex->flushed_depth_texture)
-		return; /* it's ready */
+		return true; /* it's ready */
 
 	resource.target = texture->target;
 	resource.format = texture->format;
@@ -649,36 +689,16 @@ void r600_init_flushed_depth_texture(struct pipe_context *ctx,
 	if (staging)
 		resource.flags |= R600_RESOURCE_FLAG_TRANSFER;
 	else
-		rtex->dirty_db = TRUE;
+		rtex->dirty_db_mask = (1 << (resource.last_level+1)) - 1;
 
 	*flushed_depth_texture = (struct r600_resource_texture *)ctx->screen->resource_create(ctx->screen, &resource);
 	if (*flushed_depth_texture == NULL) {
 		R600_ERR("failed to create temporary texture to hold flushed depth\n");
-		return;
+		return false;
 	}
 
 	(*flushed_depth_texture)->is_flushing_texture = TRUE;
-}
-
-void r600_texture_depth_flush(struct pipe_context *ctx,
-			      struct pipe_resource *texture,
-			      struct r600_resource_texture **staging)
-{
-	struct r600_resource_texture *rtex = (struct r600_resource_texture*)texture;
-
-	r600_init_flushed_depth_texture(ctx, texture, staging);
-
-	if (staging) {
-		if (!*staging)
-			return; /* error */
-
-		si_blit_uncompress_depth(ctx, rtex, *staging);
-	} else {
-		if (!rtex->flushed_depth_texture)
-			return; /* error */
-
-		si_blit_uncompress_depth(ctx, rtex, NULL);
-	}
+	return true;
 }
 
 void si_init_surface_functions(struct r600_context *r600)