radv: set cb base tile swizzles for MRT speedups (v4)

This patch uses addrlib to workout the tile swizzles according
to the surface index. It seems to produce the same values as
amdgpu-pro for the deferred test.

v2: don't apply swizzle to CMASK. the eg docs don't mention
it, and we clearly don't align cmask for that.
v3: disable surf index for dedicated images, as these will
most likely be shared, and I don't think the metadata has
space for this info in it yet.
v4: update for shareable images, rename combined_swizzle
to tile_swizzle

This gets the deferred demo from 730->950fps on my rx480.
(dcc cmask elim predication patches get it further)

Reviewed-by: Bas Nieuwenhuizen <[email protected]>
Signed-off-by: Dave Airlie <[email protected]>

5 files changed, 34 insertions, 2 deletions

diff --git a/src/amd/common/ac_surface.c b/src/amd/common/ac_surface.c
index a4df595653b..1677d1b3155 100644
--- a/src/amd/common/ac_surface.c
+++ b/src/amd/common/ac_surface.c
@@ -692,6 +692,20 @@ static int gfx6_compute_surface(ADDR_HANDLE addrlib,
 		surf->htile_size *= 2;
 
 	surf->is_linear = surf->u.legacy.level[0].mode == RADEON_SURF_MODE_LINEAR_ALIGNED;
+
+	/* workout base swizzle */
+	if (!(surf->flags & RADEON_SURF_Z_OR_SBUFFER)) {
+		ADDR_COMPUTE_BASE_SWIZZLE_INPUT AddrBaseSwizzleIn = {0};
+		ADDR_COMPUTE_BASE_SWIZZLE_OUTPUT AddrBaseSwizzleOut = {0};
+
+		AddrBaseSwizzleIn.surfIndex = config->info.surf_index;
+		AddrBaseSwizzleIn.tileIndex = AddrSurfInfoIn.tileIndex;
+		AddrBaseSwizzleIn.macroModeIndex = AddrSurfInfoOut.macroModeIndex;
+		AddrBaseSwizzleIn.pTileInfo = AddrSurfInfoOut.pTileInfo;
+		AddrBaseSwizzleIn.tileMode = AddrSurfInfoOut.tileMode;
+		AddrComputeBaseSwizzle(addrlib, &AddrBaseSwizzleIn, &AddrBaseSwizzleOut);
+		surf->u.legacy.tile_swizzle = AddrBaseSwizzleOut.tileSwizzle;
+	}
 	return 0;
 }
 
diff --git a/src/amd/common/ac_surface.h b/src/amd/common/ac_surface.h
index 4d893ff5009..3eaef639aad 100644
--- a/src/amd/common/ac_surface.h
+++ b/src/amd/common/ac_surface.h
@@ -97,6 +97,7 @@ struct legacy_surf_layout {
     unsigned                    depth_adjusted:1;
     unsigned                    stencil_adjusted:1;
 
+    uint8_t                     tile_swizzle;
     struct legacy_surf_level    level[RADEON_SURF_MAX_LEVELS];
     struct legacy_surf_level    stencil_level[RADEON_SURF_MAX_LEVELS];
     uint8_t                     tiling_index[RADEON_SURF_MAX_LEVELS];
@@ -194,6 +195,7 @@ struct ac_surf_info {
 	uint32_t width;
 	uint32_t height;
 	uint32_t depth;
+	uint32_t surf_index;
 	uint8_t samples;
 	uint8_t levels;
 	uint16_t array_size;
diff --git a/src/amd/vulkan/radv_device.c b/src/amd/vulkan/radv_device.c
index 2670d47fdb8..3b405838f39 100644
--- a/src/amd/vulkan/radv_device.c
+++ b/src/amd/vulkan/radv_device.c
@@ -2814,7 +2814,8 @@ radv_initialise_color_surface(struct radv_device *device,
 	}
 
 	cb->cb_color_base = va >> 8;
-
+	if (device->physical_device->rad_info.chip_class < GFX9)
+		cb->cb_color_base |= iview->image->surface.u.legacy.tile_swizzle;
 	/* CMASK variables */
 	va = device->ws->buffer_get_va(iview->bo) + iview->image->offset;
 	va += iview->image->cmask.offset;
@@ -2823,6 +2824,8 @@ radv_initialise_color_surface(struct radv_device *device,
 	va = device->ws->buffer_get_va(iview->bo) + iview->image->offset;
 	va += iview->image->dcc_offset;
 	cb->cb_dcc_base = va >> 8;
+	if (device->physical_device->rad_info.chip_class < GFX9)
+		cb->cb_dcc_base |= iview->image->surface.u.legacy.tile_swizzle;
 
 	uint32_t max_slice = radv_surface_layer_count(iview);
 	cb->cb_color_view = S_028C6C_SLICE_START(iview->base_layer) |
@@ -2838,6 +2841,8 @@ radv_initialise_color_surface(struct radv_device *device,
 	if (iview->image->fmask.size) {
 		va = device->ws->buffer_get_va(iview->bo) + iview->image->offset + iview->image->fmask.offset;
 		cb->cb_color_fmask = va >> 8;
+		if (device->physical_device->rad_info.chip_class < GFX9)
+			cb->cb_color_fmask |= iview->image->surface.u.legacy.tile_swizzle;
 	} else {
 		cb->cb_color_fmask = cb->cb_color_base;
 	}
diff --git a/src/amd/vulkan/radv_image.c b/src/amd/vulkan/radv_image.c
index 17ee74b5f5b..a8af4fd6d68 100644
--- a/src/amd/vulkan/radv_image.c
+++ b/src/amd/vulkan/radv_image.c
@@ -32,6 +32,7 @@
 #include "sid.h"
 #include "gfx9d.h"
 #include "util/debug.h"
+#include "util/u_atomic.h"
 static unsigned
 radv_choose_tiling(struct radv_device *Device,
 		   const struct radv_image_create_info *create_info)
@@ -210,6 +211,8 @@ si_set_mutable_tex_desc_fields(struct radv_device *device,
 		va += base_level_info->offset;
 
 	state[0] = va >> 8;
+	if (chip_class < GFX9)
+		state[0] |= image->surface.u.legacy.tile_swizzle;
 	state[1] &= C_008F14_BASE_ADDRESS_HI;
 	state[1] |= S_008F14_BASE_ADDRESS_HI(va >> 40);
 	state[3] |= S_008F1C_TILING_INDEX(si_tile_mode_index(image, base_level,
@@ -225,7 +228,8 @@ si_set_mutable_tex_desc_fields(struct radv_device *device,
 				meta_va += base_level_info->dcc_offset;
 			state[6] |= S_008F28_COMPRESSION_EN(1);
 			state[7] = meta_va >> 8;
-
+			if (chip_class < GFX9)
+				state[7] |= image->surface.u.legacy.tile_swizzle;
 		}
 	}
 
@@ -473,6 +477,8 @@ si_make_texture_descriptor(struct radv_device *device,
 		}
 
 		fmask_state[0] = va >> 8;
+		if (device->physical_device->rad_info.chip_class < GFX9)
+			fmask_state[0] |= image->surface.u.legacy.tile_swizzle;
 		fmask_state[1] = S_008F14_BASE_ADDRESS_HI(va >> 40) |
 			S_008F14_DATA_FORMAT_GFX6(fmask_format) |
 			S_008F14_NUM_FORMAT_GFX6(num_format);
@@ -792,6 +798,9 @@ radv_image_create(VkDevice _device,
 
 	image->shareable = vk_find_struct_const(pCreateInfo->pNext,
 	                                        EXTERNAL_MEMORY_IMAGE_CREATE_INFO_KHR) != NULL;
+	if (!vk_format_is_depth(pCreateInfo->format) && !create_info->scanout && !image->shareable) {
+		image->info.surf_index = p_atomic_inc_return(&device->image_mrt_offset_counter) - 1;
+	}
 
 	radv_init_surface(device, &image->surface, create_info);
 
diff --git a/src/amd/vulkan/radv_private.h b/src/amd/vulkan/radv_private.h
index 2f633b4dbd9..e1fb5565494 100644
--- a/src/amd/vulkan/radv_private.h
+++ b/src/amd/vulkan/radv_private.h
@@ -547,6 +547,8 @@ struct radv_device {
 
 	/* Backup in-memory cache to be used if the app doesn't provide one */
 	struct radv_pipeline_cache *                mem_cache;
+
+	uint32_t image_mrt_offset_counter;
 };
 
 struct radv_device_memory {