OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

tu: Lazily init VSC to fix dynamic rendering in secondary cmdbufs

Browse Source 
Dynamic renderpasses need vsc_prim_strm_pitch, vsc_draw_strm_pitch
values, and a correct BO. The easiest way to solve this is to
lazily init VSC when it is needed, and not at every cmdbuf
initialization.

Fixes CTS tests (when running with TU_DEBUG=gmem,forcebin):
 dEQP-VK.draw.dynamic_rendering.complete_secondary_cmd_buff.*

Signed-off-by: Danylo Piliaiev <dpiliaiev@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18996>
This commit is contained in:
Danylo Piliaiev
2022-10-07 11:46:55 +02:00
committed by Marge Bot
parent e70a2148e5
commit 4eba6d71a8
3 changed files with 53 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

91
src/freedreno/vulkan/tu_cmd_buffer.c
View File

@@ -83,6 +83,53 @@ tu6_lazy_emit_tessfactor_addr(struct tu_cmd_buffer *cmd)
cmd->state.tessfactor_addr_set = true;
}
static void
tu6_lazy_emit_vsc(struct tu_cmd_buffer *cmd, struct tu_cs *cs)
{
struct tu_device *dev = cmd->device;
/* VSC buffers:
* use vsc pitches from the largest values used so far with this device
* if there hasn't been overflow, there will already be a scratch bo
* allocated for these sizes
*
* if overflow is detected, the stream size is increased by 2x
*/
mtx_lock(&dev->mutex);
struct tu6_global *global = dev->global_bo->map;
uint32_t vsc_draw_overflow = global->vsc_draw_overflow;
uint32_t vsc_prim_overflow = global->vsc_prim_overflow;
if (vsc_draw_overflow >= dev->vsc_draw_strm_pitch)
dev->vsc_draw_strm_pitch = (dev->vsc_draw_strm_pitch - VSC_PAD) * 2 + VSC_PAD;
if (vsc_prim_overflow >= dev->vsc_prim_strm_pitch)
dev->vsc_prim_strm_pitch = (dev->vsc_prim_strm_pitch - VSC_PAD) * 2 + VSC_PAD;
cmd->vsc_prim_strm_pitch = dev->vsc_prim_strm_pitch;
cmd->vsc_draw_strm_pitch = dev->vsc_draw_strm_pitch;
mtx_unlock(&dev->mutex);
struct tu_bo *vsc_bo;
uint32_t size0 = cmd->vsc_prim_strm_pitch * MAX_VSC_PIPES +
cmd->vsc_draw_strm_pitch * MAX_VSC_PIPES;
tu_get_scratch_bo(dev, size0 + MAX_VSC_PIPES * 4, &vsc_bo);
tu_cs_emit_regs(cs,
A6XX_VSC_DRAW_STRM_SIZE_ADDRESS(.bo = vsc_bo, .bo_offset = size0));
tu_cs_emit_regs(cs,
A6XX_VSC_PRIM_STRM_ADDRESS(.bo = vsc_bo));
tu_cs_emit_regs(cs,
A6XX_VSC_DRAW_STRM_ADDRESS(.bo = vsc_bo,
.bo_offset = cmd->vsc_prim_strm_pitch * MAX_VSC_PIPES));
cmd->vsc_initialized = true;
}
static void
tu6_emit_flushes(struct tu_cmd_buffer *cmd_buffer,
struct tu_cs *cs,
@@ -951,45 +998,6 @@ tu6_init_hw(struct tu_cmd_buffer *cmd, struct tu_cs *cs)
A6XX_SP_PS_TP_BORDER_COLOR_BASE_ADDR(.bo = dev->global_bo,
.bo_offset = gb_offset(bcolor_builtin)));
/* VSC buffers:
* use vsc pitches from the largest values used so far with this device
* if there hasn't been overflow, there will already be a scratch bo
* allocated for these sizes
*
* if overflow is detected, the stream size is increased by 2x
*/
mtx_lock(&dev->mutex);
struct tu6_global *global = dev->global_bo->map;
uint32_t vsc_draw_overflow = global->vsc_draw_overflow;
uint32_t vsc_prim_overflow = global->vsc_prim_overflow;
if (vsc_draw_overflow >= dev->vsc_draw_strm_pitch)
dev->vsc_draw_strm_pitch = (dev->vsc_draw_strm_pitch - VSC_PAD) * 2 + VSC_PAD;
if (vsc_prim_overflow >= dev->vsc_prim_strm_pitch)
dev->vsc_prim_strm_pitch = (dev->vsc_prim_strm_pitch - VSC_PAD) * 2 + VSC_PAD;
cmd->vsc_prim_strm_pitch = dev->vsc_prim_strm_pitch;
cmd->vsc_draw_strm_pitch = dev->vsc_draw_strm_pitch;
mtx_unlock(&dev->mutex);
struct tu_bo *vsc_bo;
uint32_t size0 = cmd->vsc_prim_strm_pitch * MAX_VSC_PIPES +
cmd->vsc_draw_strm_pitch * MAX_VSC_PIPES;
tu_get_scratch_bo(dev, size0 + MAX_VSC_PIPES * 4, &vsc_bo);
tu_cs_emit_regs(cs,
A6XX_VSC_DRAW_STRM_SIZE_ADDRESS(.bo = vsc_bo, .bo_offset = size0));
tu_cs_emit_regs(cs,
A6XX_VSC_PRIM_STRM_ADDRESS(.bo = vsc_bo));
tu_cs_emit_regs(cs,
A6XX_VSC_DRAW_STRM_ADDRESS(.bo = vsc_bo,
.bo_offset = cmd->vsc_prim_strm_pitch * MAX_VSC_PIPES));
tu_cs_sanity_check(cs);
}
@@ -1378,6 +1386,10 @@ tu6_tile_render_begin(struct tu_cmd_buffer *cmd, struct tu_cs *cs,
tu_emit_cache_flush_ccu(cmd, cs, TU_CMD_CCU_GMEM);
if (use_hw_binning(cmd)) {
if (!cmd->vsc_initialized) {
tu6_lazy_emit_vsc(cmd, cs);
}
tu6_emit_bin_size(cs, tiling->tile0.width, tiling->tile0.height,
A6XX_RB_BIN_CONTROL_RENDER_MODE(BINNING_PASS) |
A6XX_RB_BIN_CONTROL_LRZ_FEEDBACK_ZMODE_MASK(0x6));
@@ -1712,6 +1724,7 @@ tu_reset_cmd_buffer(struct vk_command_buffer *vk_cmd_buffer,
u_trace_init(&cmd_buffer->trace, &cmd_buffer->device->trace_context);
cmd_buffer->state.max_vbs_bound = 0;
cmd_buffer->vsc_initialized = false;
cmd_buffer->status = TU_CMD_BUFFER_STATUS_INITIAL;
}

1
src/freedreno/vulkan/tu_cmd_buffer.h
View File

@@ -588,6 +588,7 @@ struct tu_cmd_buffer
uint32_t vsc_draw_strm_pitch;
uint32_t vsc_prim_strm_pitch;
bool vsc_initialized;
};
VK_DEFINE_HANDLE_CASTS(tu_cmd_buffer, vk.base, VkCommandBuffer,
VK_OBJECT_TYPE_COMMAND_BUFFER)

2
src/freedreno/vulkan/tu_dynamic_rendering.c
View File

@@ -201,8 +201,6 @@ tu_insert_dynamic_cmdbufs(struct tu_device *dev,
* because we skip tu6_emit_hw().
*/
cmd_buffer->state.ccu_state = old_cmds[i]->state.ccu_state;
cmd_buffer->vsc_draw_strm_pitch = old_cmds[i]->vsc_draw_strm_pitch;
cmd_buffer->vsc_prim_strm_pitch = old_cmds[i]->vsc_prim_strm_pitch;
break;
}
}