r600g: add htile support v16

htile is used for HiZ and HiS support and fast Z/S clears.
This commit just adds the htile setup and Fast Z clear.
We don't take full advantage of HiS with that patch.

v2 really use fast clear, still random issue with some tiles
   need to try more flush combination, fix depth/stencil
   texture decompression
v3 fix random issue on r6xx/r7xx
v4 rebase on top of lastest mesa, disable CB export when clearing
   htile surface to avoid wasting bandwidth
v5 resummarize htile surface when uploading z value. Fix z/stencil
   decompression, the custom blitter with custom dsa is no longer
   needed.
v6 Reorganize render control/override update mecanism, fixing more
   issues in the process.
v7 Add nop after depth surface base update to work around some htile
   flushing issue. For htile to 8x8 on r6xx/r7xx as other combination
   have issue. Do not enable hyperz when flushing/uncompressing
   depth buffer.
v8 Fix htile surface, preload and prefetch setup. Only set preload
   and prefetch on htile surface clear like fglrx. Record depth
   clear value per level. Support several level for the htile
   surface. First depth clear can't be a fast clear.
v9 Fix comments, properly account new register in emit function,
   disable fast zclear if clearing different layer of texture
   array to different value
v10 Disable hyperz for texture array making test simpler. Force
    db_misc_state update when no depth buffer is bound. Remove
    unused variable, rename depth_clearstencil to depth_clear.
    Don't allocate htile surface for flushed depth. Something
    broken the cliprect change, this need to be investigated.
v11 Rebase on top of newer mesa
v12 Rebase on top of newer mesa
v13 Rebase on top of newer mesa, htile surface need to be initialized
    to zero, somehow special casing first clear to not use fast clear
    and thus initialize the htile surface with proper value does not
    work in all case.
v14 Use resource not texture for htile buffer make the htile buffer
    size computation easier and simpler. Disable preload on evergreen
    as its still troublesome in some case
v15 Cleanup some comment and remove some left over
v16 Define name for bit 20 of CP_COHER_CNTL

Signed-off-by: Pierre-Eric Pelloux-Prayer <pelloux@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jerome Glisse <jglisse@redhat.com>

1 files changed, 17 insertions, 9 deletions

diff --git a/src/gallium/drivers/r600/r600_pipe.h b/src/gallium/drivers/r600/r600_pipe.h
index 8df50e9bc83..515174a2e6e 100644
--- a/src/gallium/drivers/r600/r600_pipe.h
+++ b/src/gallium/drivers/r600/r600_pipe.h
@@ -35,7 +35,7 @@
 #include "r600_resource.h"
 #include "evergreen_compute.h"
 
-#define R600_NUM_ATOMS 36
+#define R600_NUM_ATOMS 37
 
 #define R600_MAX_USER_CONST_BUFFERS 1
 #define R600_MAX_DRIVER_CONST_BUFFERS 2
@@ -77,15 +77,21 @@ struct r600_command_buffer {
 	unsigned pkt_flags;
 };
 
+struct r600_db_state {
+	struct r600_atom		atom;
+	struct r600_surface		*rsurf;
+};
+
 struct r600_db_misc_state {
-	struct r600_atom atom;
-	bool occlusion_query_enabled;
-	bool flush_depthstencil_through_cb;
-	bool flush_depthstencil_in_place;
-	bool copy_depth, copy_stencil;
-	unsigned copy_sample;
-	unsigned log_samples;
-	unsigned db_shader_control;
+	struct r600_atom		atom;
+	bool				occlusion_query_enabled;
+	bool				flush_depthstencil_through_cb;
+	bool				flush_depthstencil_in_place;
+	bool				copy_depth, copy_stencil;
+	unsigned			copy_sample;
+	unsigned			log_samples;
+	unsigned			db_shader_control;
+	bool				htile_clear;
 };
 
 struct r600_cb_misc_state {
@@ -220,6 +226,7 @@ struct r600_screen {
 	bool				has_streamout;
 	bool				has_msaa;
 	enum r600_msaa_texture_mode	msaa_texture_support;
+	bool				use_hyperz;
 	struct r600_tiling_info		tiling_info;
 	struct r600_pipe_fences		fences;
 
@@ -439,6 +446,7 @@ struct r600_context {
 	struct r600_clip_misc_state	clip_misc_state;
 	struct r600_clip_state		clip_state;
 	struct r600_db_misc_state	db_misc_state;
+	struct r600_db_state		db_state;
 	struct r600_cso_state		dsa_state;
 	struct r600_framebuffer		framebuffer;
 	struct r600_poly_offset_state	poly_offset_state;