Merge tag 'amd-drm-next-6.5-2023-06-09' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.5-2023-06-02:

amdgpu:
- SR-IOV fixes
- Warning fixes
- Misc code cleanups and spelling fixes
- DCN 3.2 updates
- Improved DC FAMS support for better power management
- Improved DC SubVP support for better power management
- DCN 3.1.x fixes
- Max IB size query
- DC GPU reset fixes
- RAS updates
- DCN 3.0.x fixes
- S/G display fixes
- CP shadow buffer support
- Implement connector force callback
- Z8 power improvements
- PSP 13.0.10 vbflash support
- Mode2 reset fixes
- Store MQDs in VRAM to improve queue switch latency
- VCN 3.x fixes
- JPEG 3.x fixes
- Enable DC_FP on LoongArch
- GFXOFF fixes
- GC 9.4.3 partition support
- SDMA 4.4.2 partition support
- VCN/JPEG 4.0.3 partition support
- VCN 4.0.3 updates
- NBIO 7.9 updates
- GC 9.4.3 updates
- Take NUMA into account when allocating memory
- Handle NUMA for partitions
- SMU 13.0.6 updates
- GC 9.4.3 RAS updates
- Stop including unused swiotlb.h
- SMU 13.0.7 fixes
- Fix clock output ordering on some APUs
- Clean up DC FPGA code
- GFX9 preemption fixes
- Misc irq fixes
- S0ix fixes
- Add new DRM_AMDGPU_WERROR config parameter to help with CI
- PCIe fix for RDNA2
- kdoc fixes
- Documentation updates

amdkfd:
- Query TTM mem limit rather than hardcoding it
- GC 9.4.3 partition support
- Handle NUMA for partitions

radeon:
- Fix possible double free
- Stop including unused swiotlb.h
- Fix possible division by zero

ttm:
- Add query for TTM mem limit
- Add NUMA awareness to pools
- Export ttm_pool_fini()

UAPI:
- Add new ctx query flag to better handle GPU resets
  Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22290
- Add new interface to query and set shadow buffer for RDNA3
  Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21986
- Add new INFO query for max IB size
  Proposed userspace: https://gitlab.freedesktop.org/bnieuwenhuizen/mesa/-/commits/ib-rejection-v3

amd-drm-next-6.5-2023-06-09:

amdgpu:
- S0ix fixes
- Initial SMU13 Overdrive support
- kdoc fixes
- Misc clode cleanups
- Flexible array fixes
- Display OTG fixes
- SMU 13.0.6 updates
- Revert some broken clock counter updates
- Misc display fixes
- GFX9 preemption fixes
- Add support for newer EEPROM bad page table format
- Add missing radeon secondary id
- Add support for new colorspace KMS API
- CSA fix
- Stable pstate fixes for APUs
- make vbl interface admin only
- Handle PCI accelerator class

amdkfd:
- Add debugger support for gdb

radeon:
- Fix possible UAF

drm:
- Add Colorspace functionality

UAPI:
- Add debugger interface for enabling gdb
  Proposed userspace: https://github.com/ROCm-Developer-Tools/ROCdbgapi/tree/wip-dbgapi
- Add KMS colorspace API
  Discussion: https://lists.freedesktop.org/archives/dri-devel/2023-June/408128.html

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230609174817.7764-1-alexander.deucher@amd.com

1 files changed, 65 insertions, 14 deletions

diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
index 1f5ee5cde6e1..00f32ffe0079 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c
@@ -274,8 +274,7 @@ bool dcn32_apply_idle_power_optimizations(struct dc *dc, bool enable)
 				cmd.cab.header.sub_type = DMUB_CMD__CAB_NO_DCN_REQ;
 				cmd.cab.header.payload_bytes = sizeof(cmd.cab) - sizeof(cmd.cab.header);
 
-				dc_dmub_srv_cmd_queue(dc->ctx->dmub_srv, &cmd);
-				dc_dmub_srv_cmd_execute(dc->ctx->dmub_srv);
+				dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_NO_WAIT);
 
 				return true;
 			}
@@ -309,8 +308,7 @@ bool dcn32_apply_idle_power_optimizations(struct dc *dc, bool enable)
 				cmd.cab.header.payload_bytes = sizeof(cmd.cab) - sizeof(cmd.cab.header);
 				cmd.cab.cab_alloc_ways = ways;
 
-				dc_dmub_srv_cmd_queue(dc->ctx->dmub_srv, &cmd);
-				dc_dmub_srv_cmd_execute(dc->ctx->dmub_srv);
+				dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_NO_WAIT);
 
 				return true;
 			}
@@ -326,9 +324,7 @@ bool dcn32_apply_idle_power_optimizations(struct dc *dc, bool enable)
 	cmd.cab.header.payload_bytes =
 			sizeof(cmd.cab) - sizeof(cmd.cab.header);
 
-	dc_dmub_srv_cmd_queue(dc->ctx->dmub_srv, &cmd);
-	dc_dmub_srv_cmd_execute(dc->ctx->dmub_srv);
-	dc_dmub_srv_wait_idle(dc->ctx->dmub_srv);
+	dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT);
 
 	return true;
 }
@@ -413,6 +409,30 @@ void dcn32_subvp_pipe_control_lock(struct dc *dc,
 	}
 }
 
+void dcn32_subvp_pipe_control_lock_fast(union block_sequence_params *params)
+{
+	struct dc *dc = params->subvp_pipe_control_lock_fast_params.dc;
+	bool lock = params->subvp_pipe_control_lock_fast_params.lock;
+	struct pipe_ctx *pipe_ctx = params->subvp_pipe_control_lock_fast_params.pipe_ctx;
+	bool subvp_immediate_flip = false;
+
+	if (pipe_ctx && pipe_ctx->stream && pipe_ctx->plane_state) {
+		if (pipe_ctx->stream->mall_stream_config.type == SUBVP_MAIN &&
+				pipe_ctx->plane_state->flip_immediate)
+			subvp_immediate_flip = true;
+	}
+
+	// Don't need to lock for DRR VSYNC flips -- FW will wait for DRR pending update cleared.
+	if (subvp_immediate_flip) {
+		union dmub_inbox0_cmd_lock_hw hw_lock_cmd = { 0 };
+
+		hw_lock_cmd.bits.command_code = DMUB_INBOX0_CMD__HW_LOCK;
+		hw_lock_cmd.bits.hw_lock_client = HW_LOCK_CLIENT_DRIVER;
+		hw_lock_cmd.bits.lock = lock;
+		hw_lock_cmd.bits.should_release = !lock;
+		dmub_hw_lock_mgr_inbox0_cmd(dc->ctx->dmub_srv, hw_lock_cmd);
+	}
+}
 
 bool dcn32_set_mpc_shaper_3dlut(
 	struct pipe_ctx *pipe_ctx, const struct dc_stream_state *stream)
@@ -587,8 +607,8 @@ void dcn32_update_force_pstate(struct dc *dc, struct dc_state *context)
 		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
 		struct hubp *hubp = pipe->plane_res.hubp;
 
-		if (!pipe->stream || (pipe->stream && !(pipe->stream->mall_stream_config.type == SUBVP_MAIN ||
-						pipe->stream->fpo_in_use))) {
+		if (!pipe->stream || !(pipe->stream->mall_stream_config.type == SUBVP_MAIN ||
+		    pipe->stream->fpo_in_use)) {
 			if (hubp && hubp->funcs->hubp_update_force_pstate_disallow)
 				hubp->funcs->hubp_update_force_pstate_disallow(hubp, false);
 		}
@@ -596,7 +616,7 @@ void dcn32_update_force_pstate(struct dc *dc, struct dc_state *context)
 		/* Today only FPO uses cursor P-State force. Only clear cursor P-State force
 		 * if it's not FPO.
 		 */
-		if (!pipe->stream || (pipe->stream && !pipe->stream->fpo_in_use)) {
+		if (!pipe->stream || !pipe->stream->fpo_in_use) {
 			if (hubp && hubp->funcs->hubp_update_force_cursor_pstate_disallow)
 				hubp->funcs->hubp_update_force_cursor_pstate_disallow(hubp, false);
 		}
@@ -721,6 +741,9 @@ static void dcn32_initialize_min_clocks(struct dc *dc)
 	clocks->socclk_khz = dc->clk_mgr->bw_params->clk_table.entries[0].socclk_mhz * 1000;
 	clocks->dramclk_khz = dc->clk_mgr->bw_params->clk_table.entries[0].memclk_mhz * 1000;
 	clocks->dppclk_khz = dc->clk_mgr->bw_params->clk_table.entries[0].dppclk_mhz * 1000;
+	clocks->ref_dtbclk_khz = dc->clk_mgr->bw_params->clk_table.entries[0].dtbclk_mhz * 1000;
+	clocks->fclk_p_state_change_support = true;
+	clocks->p_state_change_support = true;
 	if (dc->debug.disable_boot_optimizations) {
 		clocks->dispclk_khz = dc->clk_mgr->bw_params->clk_table.entries[0].dispclk_mhz * 1000;
 	} else {
@@ -730,9 +753,6 @@ static void dcn32_initialize_min_clocks(struct dc *dc)
 		 * freq to ensure that the timing is valid and unchanged.
 		 */
 		clocks->dispclk_khz = dc->clk_mgr->funcs->get_dispclk_from_dentist(dc->clk_mgr);
-		clocks->ref_dtbclk_khz = dc->clk_mgr->bw_params->clk_table.entries[0].dtbclk_mhz * 1000;
-		clocks->fclk_p_state_change_support = true;
-		clocks->p_state_change_support = true;
 	}
 
 	dc->clk_mgr->funcs->update_clocks(
@@ -946,8 +966,10 @@ void dcn32_init_hw(struct dc *dc)
 
 	// Get DMCUB capabilities
 	if (dc->ctx->dmub_srv) {
-		dc_dmub_srv_query_caps_cmd(dc->ctx->dmub_srv->dmub);
+		dc_dmub_srv_query_caps_cmd(dc->ctx->dmub_srv);
 		dc->caps.dmub_caps.psr = dc->ctx->dmub_srv->dmub->feature_caps.psr;
+		dc->caps.dmub_caps.subvp_psr = dc->ctx->dmub_srv->dmub->feature_caps.subvp_psr_support;
+		dc->caps.dmub_caps.gecc_enable = dc->ctx->dmub_srv->dmub->feature_caps.gecc_enable;
 		dc->caps.dmub_caps.mclk_sw = dc->ctx->dmub_srv->dmub->feature_caps.fw_assisted_mclk_switch;
 	}
 }
@@ -1177,6 +1199,35 @@ void dcn32_set_pixels_per_cycle(struct pipe_ctx *pipe_ctx)
 				pix_per_cycle);
 }
 
+void dcn32_resync_fifo_dccg_dio(struct dce_hwseq *hws, struct dc *dc, struct dc_state *context)
+{
+	unsigned int i;
+	struct pipe_ctx *pipe = NULL;
+	bool otg_disabled[MAX_PIPES] = {false};
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		pipe = &dc->current_state->res_ctx.pipe_ctx[i];
+
+		if (pipe->top_pipe || pipe->prev_odm_pipe)
+			continue;
+
+		if (pipe->stream && (pipe->stream->dpms_off || dc_is_virtual_signal(pipe->stream->signal))) {
+			pipe->stream_res.tg->funcs->disable_crtc(pipe->stream_res.tg);
+			reset_sync_context_for_pipe(dc, context, i);
+			otg_disabled[i] = true;
+		}
+	}
+
+	hws->ctx->dc->res_pool->dccg->funcs->trigger_dio_fifo_resync(hws->ctx->dc->res_pool->dccg);
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		pipe = &dc->current_state->res_ctx.pipe_ctx[i];
+
+		if (otg_disabled[i])
+			pipe->stream_res.tg->funcs->enable_crtc(pipe->stream_res.tg);
+	}
+}
+
 void dcn32_unblank_stream(struct pipe_ctx *pipe_ctx,
 		struct dc_link_settings *link_settings)
 {