Merge tag 'drm-next-2023-09-08' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Regular rounds of rc1 fixes, a large bunch for amdgpu since it's three
  weeks in one go, one i915, one nouveau and one ivpu.

  I think there might be a few more fixes in misc that I haven't pulled
  in yet, but we should get them all for rc2.

  amdgpu:
   - Display replay fixes
   - Fixes for headless boards
   - Fix documentation breakage
   - RAS fixes
   - Handle newer IP discovery tables
   - SMU 13.0.6 fixes
   - SR-IOV fixes
   - Display vstartup fixes
   - NBIO 7.9 fixes
   - Display scaling mode fixes
   - Debugfs power reporting fix
   - GC 9.4.3 fixes
   - Dirty framebuffer fixes for fbcon
   - eDP fixes
   - DCN 3.1.5 fix
   - Display ODM fixes
   - GPU core dump fix
   - Re-enable zops property now that IGT test is fixed
   - Fix possible UAF in CS code
   - Cursor degamma fix

  amdkfd:
   - HMM fixes
   - Interrupt masking fix
   - GFX11 MQD fixes

  i915:
   - Mark requests for GuC virtual engines to avoid use-after-free

  nouveau:
   - Fix fence state in nouveau_fence_emit()

  ivpu:
   - replace strncpy"

* tag 'drm-next-2023-09-08' of git://anongit.freedesktop.org/drm/drm: (51 commits)
  drm/amdgpu: Restrict bootloader wait to SMUv13.0.6
  drm/amd/display: prevent potential division by zero errors
  drm/amd/display: enable cursor degamma for DCN3+ DRM legacy gamma
  drm/amd/display: limit the v_startup workaround to ASICs older than DCN3.1
  Revert "drm/amd/display: Remove v_startup workaround for dcn3+"
  drm/amdgpu: fix amdgpu_cs_p1_user_fence
  Revert "Revert "drm/amd/display: Implement zpos property""
  drm/amdkfd: Add missing gfx11 MQD manager callbacks
  drm/amdgpu: Free ras cmd input buffer properly
  drm/amdgpu: Hide xcp partition sysfs under SRIOV
  drm/amdgpu: use read-modify-write mode for gfx v9_4_3 SQ setting
  drm/amdkfd: use mask to get v9 interrupt sq data bits correctly
  drm/amdgpu: Allocate coredump memory in a nonblocking way
  drm/amdgpu: Support query ecc cap for aqua_vanjaram
  drm/amdgpu: Add umc_info v4_0 structure
  drm/amd/display: always switch off ODM before committing more streams
  drm/amd/display: Remove wait while locked
  drm/amd/display: update blank state on ODM changes
  drm/amd/display: Add smu write msg id fail retry process
  drm/amdgpu: Add SMU v13.0.6 default reset methods
  ...

14 files changed, 235 insertions, 93 deletions

diff --git a/drivers/gpu/drm/amd/display/dc/Makefile b/drivers/gpu/drm/amd/display/dc/Makefile
index 69ffd4424dc7..1b8c2aef4633 100644
--- a/drivers/gpu/drm/amd/display/dc/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/Makefile
@@ -78,3 +78,4 @@ DC_EDID += dc_edid_parser.o
 AMD_DISPLAY_DMUB = $(addprefix $(AMDDALPATH)/dc/,$(DC_DMUB))
 AMD_DISPLAY_EDID = $(addprefix $(AMDDALPATH)/dc/,$(DC_EDID))
 AMD_DISPLAY_FILES += $(AMD_DISPLAY_DMUB) $(AMD_DISPLAY_EDID)
+
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c
index 3e0da873cf4c..1042cf1a3ab0 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_smu.c
@@ -32,6 +32,7 @@
 
 #define MAX_INSTANCE                                        6
 #define MAX_SEGMENT                                         6
+#define SMU_REGISTER_WRITE_RETRY_COUNT                      5
 
 struct IP_BASE_INSTANCE {
     unsigned int segment[MAX_SEGMENT];
@@ -132,6 +133,8 @@ static int dcn315_smu_send_msg_with_param(
 		unsigned int msg_id, unsigned int param)
 {
 	uint32_t result;
+	uint32_t i = 0;
+	uint32_t read_back_data;
 
 	result = dcn315_smu_wait_for_response(clk_mgr, 10, 200000);
 
@@ -148,10 +151,19 @@ static int dcn315_smu_send_msg_with_param(
 	/* Set the parameter register for the SMU message, unit is Mhz */
 	REG_WRITE(MP1_SMN_C2PMSG_37, param);
 
-	/* Trigger the message transaction by writing the message ID */
-	generic_write_indirect_reg(CTX,
-		REG_NBIO(RSMU_INDEX), REG_NBIO(RSMU_DATA),
-		mmMP1_C2PMSG_3, msg_id);
+	for (i = 0; i < SMU_REGISTER_WRITE_RETRY_COUNT; i++) {
+		/* Trigger the message transaction by writing the message ID */
+		generic_write_indirect_reg(CTX,
+			REG_NBIO(RSMU_INDEX), REG_NBIO(RSMU_DATA),
+			mmMP1_C2PMSG_3, msg_id);
+		read_back_data = generic_read_indirect_reg(CTX,
+			REG_NBIO(RSMU_INDEX), REG_NBIO(RSMU_DATA),
+			mmMP1_C2PMSG_3);
+		if (read_back_data == msg_id)
+			break;
+		udelay(2);
+		smu_print("SMU msg id write fail %x times. \n", i + 1);
+	}
 
 	result = dcn315_smu_wait_for_response(clk_mgr, 10, 200000);
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 566d7045b2de..3a9077b60029 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -2073,12 +2073,12 @@ enum dc_status dc_commit_streams(struct dc *dc,
 		}
 	}
 
-	/* Check for case where we are going from odm 2:1 to max
-	 *  pipe scenario.  For these cases, we will call
-	 *  commit_minimal_transition_state() to exit out of odm 2:1
-	 *  first before processing new streams
+	/* ODM Combine 2:1 power optimization is only applied for single stream
+	 * scenario, it uses extra pipes than needed to reduce power consumption
+	 * We need to switch off this feature to make room for new streams.
 	 */
-	if (stream_count == dc->res_pool->pipe_count) {
+	if (stream_count > dc->current_state->stream_count &&
+			dc->current_state->stream_count == 1) {
 		for (i = 0; i < dc->res_pool->pipe_count; i++) {
 			pipe = &dc->current_state->res_ctx.pipe_ctx[i];
 			if (pipe->next_odm_pipe)
@@ -3501,6 +3501,45 @@ static void commit_planes_for_stream_fast(struct dc *dc,
 		top_pipe_to_program->stream->update_flags.raw = 0;
 }
 
+static void wait_for_outstanding_hw_updates(struct dc *dc, const struct dc_state *dc_context)
+{
+/*
+ * This function calls HWSS to wait for any potentially double buffered
+ * operations to complete. It should be invoked as a pre-amble prior
+ * to full update programming before asserting any HW locks.
+ */
+	int pipe_idx;
+	int opp_inst;
+	int opp_count = dc->res_pool->pipe_count;
+	struct hubp *hubp;
+	int mpcc_inst;
+	const struct pipe_ctx *pipe_ctx;
+
+	for (pipe_idx = 0; pipe_idx < dc->res_pool->pipe_count; pipe_idx++) {
+		pipe_ctx = &dc_context->res_ctx.pipe_ctx[pipe_idx];
+
+		if (!pipe_ctx->stream)
+			continue;
+
+		if (pipe_ctx->stream_res.tg->funcs->wait_drr_doublebuffer_pending_clear)
+			pipe_ctx->stream_res.tg->funcs->wait_drr_doublebuffer_pending_clear(pipe_ctx->stream_res.tg);
+
+		hubp = pipe_ctx->plane_res.hubp;
+		if (!hubp)
+			continue;
+
+		mpcc_inst = hubp->inst;
+		// MPCC inst is equal to pipe index in practice
+		for (opp_inst = 0; opp_inst < opp_count; opp_inst++) {
+			if (dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst]) {
+				dc->res_pool->mpc->funcs->wait_for_idle(dc->res_pool->mpc, mpcc_inst);
+				dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst] = false;
+				break;
+			}
+		}
+	}
+}
+
 static void commit_planes_for_stream(struct dc *dc,
 		struct dc_surface_update *srf_updates,
 		int surface_count,
@@ -3519,24 +3558,9 @@ static void commit_planes_for_stream(struct dc *dc,
 	// dc->current_state anymore, so we have to cache it before we apply
 	// the new SubVP context
 	subvp_prev_use = false;
-
-
 	dc_z10_restore(dc);
-
-	if (update_type == UPDATE_TYPE_FULL) {
-		/* wait for all double-buffer activity to clear on all pipes */
-		int pipe_idx;
-
-		for (pipe_idx = 0; pipe_idx < dc->res_pool->pipe_count; pipe_idx++) {
-			struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[pipe_idx];
-
-			if (!pipe_ctx->stream)
-				continue;
-
-			if (pipe_ctx->stream_res.tg->funcs->wait_drr_doublebuffer_pending_clear)
-				pipe_ctx->stream_res.tg->funcs->wait_drr_doublebuffer_pending_clear(pipe_ctx->stream_res.tg);
-		}
-	}
+	if (update_type == UPDATE_TYPE_FULL)
+		wait_for_outstanding_hw_updates(dc, context);
 
 	if (update_type == UPDATE_TYPE_FULL) {
 		dc_allow_idle_optimizations(dc, false);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index 65fa9e21ad9c..e72f15ac0048 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -1106,29 +1106,6 @@ void dcn20_blank_pixel_data(
 			v_active,
 			offset);
 
-	if (!blank && dc->debug.enable_single_display_2to1_odm_policy) {
-		/* when exiting dynamic ODM need to reinit DPG state for unused pipes */
-		struct pipe_ctx *old_odm_pipe = dc->current_state->res_ctx.pipe_ctx[pipe_ctx->pipe_idx].next_odm_pipe;
-
-		odm_pipe = pipe_ctx->next_odm_pipe;
-
-		while (old_odm_pipe) {
-			if (!odm_pipe || old_odm_pipe->pipe_idx != odm_pipe->pipe_idx)
-				dc->hwss.set_disp_pattern_generator(dc,
-						old_odm_pipe,
-						CONTROLLER_DP_TEST_PATTERN_VIDEOMODE,
-						CONTROLLER_DP_COLOR_SPACE_UDEFINED,
-						COLOR_DEPTH_888,
-						NULL,
-						0,
-						0,
-						0);
-			old_odm_pipe = old_odm_pipe->next_odm_pipe;
-			if (odm_pipe)
-				odm_pipe = odm_pipe->next_odm_pipe;
-		}
-	}
-
 	if (!blank)
 		if (stream_res->abm) {
 			dc->hwss.set_pipe(pipe_ctx);
@@ -1584,17 +1561,6 @@ static void dcn20_update_dchubp_dpp(
 			|| plane_state->update_flags.bits.global_alpha_change
 			|| plane_state->update_flags.bits.per_pixel_alpha_change) {
 		// MPCC inst is equal to pipe index in practice
-		int mpcc_inst = hubp->inst;
-		int opp_inst;
-		int opp_count = dc->res_pool->pipe_count;
-
-		for (opp_inst = 0; opp_inst < opp_count; opp_inst++) {
-			if (dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst]) {
-				dc->res_pool->mpc->funcs->wait_for_idle(dc->res_pool->mpc, mpcc_inst);
-				dc->res_pool->opps[opp_inst]->mpcc_disconnect_pending[mpcc_inst] = false;
-				break;
-			}
-		}
 		hws->funcs.update_mpcc(dc, pipe_ctx);
 	}
 
@@ -1722,11 +1688,16 @@ static void dcn20_program_pipe(
 		struct dc_state *context)
 {
 	struct dce_hwseq *hws = dc->hwseq;
-	/* Only need to unblank on top pipe */
 
-	if ((pipe_ctx->update_flags.bits.enable || pipe_ctx->stream->update_flags.bits.abm_level)
-			&& !pipe_ctx->top_pipe && !pipe_ctx->prev_odm_pipe)
-		hws->funcs.blank_pixel_data(dc, pipe_ctx, !pipe_ctx->plane_state->visible);
+	/* Only need to unblank on top pipe */
+	if (resource_is_pipe_type(pipe_ctx, OTG_MASTER)) {
+		if (pipe_ctx->update_flags.bits.enable ||
+				pipe_ctx->update_flags.bits.odm ||
+				pipe_ctx->stream->update_flags.bits.abm_level)
+			hws->funcs.blank_pixel_data(dc, pipe_ctx,
+					!pipe_ctx->plane_state ||
+					!pipe_ctx->plane_state->visible);
+	}
 
 	/* Only update TG on top pipe */
 	if (pipe_ctx->update_flags.bits.global_sync && !pipe_ctx->top_pipe
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
index 6cef62d7a2e5..255713ec29bb 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c
@@ -987,3 +987,20 @@ void dcn30_prepare_bandwidth(struct dc *dc,
 	}
 }
 
+void dcn30_set_static_screen_control(struct pipe_ctx **pipe_ctx,
+		int num_pipes, const struct dc_static_screen_params *params)
+{
+	unsigned int i;
+	unsigned int triggers = 0;
+
+	if (params->triggers.surface_update)
+		triggers |= 0x100;
+	if (params->triggers.cursor_update)
+		triggers |= 0x8;
+	if (params->triggers.force_trigger)
+		triggers |= 0x1;
+
+	for (i = 0; i < num_pipes; i++)
+		pipe_ctx[i]->stream_res.tg->funcs->set_static_screen_control(pipe_ctx[i]->stream_res.tg,
+					triggers, params->num_frames);
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.h
index a24a8e33a3d2..ce19c54097f8 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.h
@@ -87,5 +87,7 @@ void dcn30_set_hubp_blank(const struct dc *dc,
 void dcn30_prepare_bandwidth(struct dc *dc,
 	struct dc_state *context);
 
+void dcn30_set_static_screen_control(struct pipe_ctx **pipe_ctx,
+		int num_pipes, const struct dc_static_screen_params *params);
 
 #endif /* __DC_HWSS_DCN30_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c
index 3d19acaa12f3..0de8b2783cf6 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_init.c
@@ -64,7 +64,7 @@ static const struct hw_sequencer_funcs dcn30_funcs = {
 	.update_bandwidth = dcn20_update_bandwidth,
 	.set_drr = dcn10_set_drr,
 	.get_position = dcn10_get_position,
-	.set_static_screen_control = dcn10_set_static_screen_control,
+	.set_static_screen_control = dcn30_set_static_screen_control,
 	.setup_stereo = dcn10_setup_stereo,
 	.set_avmute = dcn30_set_avmute,
 	.log_hw_state = dcn10_log_hw_state,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c
index 257df8660b4c..61205cdbe2d5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_init.c
@@ -75,6 +75,7 @@ static const struct hw_sequencer_funcs dcn301_funcs = {
 	.get_hw_state = dcn10_get_hw_state,
 	.clear_status_bits = dcn10_clear_status_bits,
 	.wait_for_mpcc_disconnect = dcn10_wait_for_mpcc_disconnect,
+	.edp_backlight_control = dce110_edp_backlight_control,
 	.edp_power_control = dce110_edp_power_control,
 	.edp_wait_for_hpd_ready = dce110_edp_wait_for_hpd_ready,
 	.set_cursor_position = dcn10_set_cursor_position,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c
index fc25cc300a17..1d7bc1e39afe 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c
@@ -67,7 +67,7 @@ static const struct hw_sequencer_funcs dcn31_funcs = {
 	.update_bandwidth = dcn20_update_bandwidth,
 	.set_drr = dcn10_set_drr,
 	.get_position = dcn10_get_position,
-	.set_static_screen_control = dcn10_set_static_screen_control,
+	.set_static_screen_control = dcn30_set_static_screen_control,
 	.setup_stereo = dcn10_setup_stereo,
 	.set_avmute = dcn30_set_avmute,
 	.log_hw_state = dcn10_log_hw_state,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c
index ca8fe55c33b8..4ef85c3a0688 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c
@@ -69,7 +69,7 @@ static const struct hw_sequencer_funcs dcn314_funcs = {
 	.update_bandwidth = dcn20_update_bandwidth,
 	.set_drr = dcn10_set_drr,
 	.get_position = dcn10_get_position,
-	.set_static_screen_control = dcn10_set_static_screen_control,
+	.set_static_screen_control = dcn30_set_static_screen_control,
 	.setup_stereo = dcn10_setup_stereo,
 	.set_avmute = dcn30_set_avmute,
 	.log_hw_state = dcn10_log_hw_state,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c
index 777b2fac20c4..c7417147dff1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c
@@ -65,7 +65,7 @@ static const struct hw_sequencer_funcs dcn32_funcs = {
 	.update_bandwidth = dcn20_update_bandwidth,
 	.set_drr = dcn10_set_drr,
 	.get_position = dcn10_get_position,
-	.set_static_screen_control = dcn10_set_static_screen_control,
+	.set_static_screen_control = dcn30_set_static_screen_control,
 	.setup_stereo = dcn10_setup_stereo,
 	.set_avmute = dcn30_set_avmute,
 	.log_hw_state = dcn10_log_hw_state,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
index 935cd23e6a01..f9d601c8c721 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c
@@ -2564,18 +2564,128 @@ static int find_optimal_free_pipe_as_secondary_dpp_pipe(
 	return free_pipe_idx;
 }
 
+static struct pipe_ctx *find_idle_secondary_pipe_check_mpo(
+		struct resource_context *res_ctx,
+		const struct resource_pool *pool,
+		const struct pipe_ctx *primary_pipe)
+{
+	int i;
+	struct pipe_ctx *secondary_pipe = NULL;
+	struct pipe_ctx *next_odm_mpo_pipe = NULL;
+	int primary_index, preferred_pipe_idx;
+	struct pipe_ctx *old_primary_pipe = NULL;
+
+	/*
+	 * Modified from find_idle_secondary_pipe
+	 * With windowed MPO and ODM, we want to avoid the case where we want a
+	 *  free pipe for the left side but the free pipe is being used on the
+	 *  right side.
+	 * Add check on current_state if the primary_pipe is the left side,
+	 *  to check the right side ( primary_pipe->next_odm_pipe ) to see if
+	 *  it is using a pipe for MPO ( primary_pipe->next_odm_pipe->bottom_pipe )
+	 * - If so, then don't use this pipe
+	 * EXCEPTION - 3 plane ( 2 MPO plane ) case
+	 * - in this case, the primary pipe has already gotten a free pipe for the
+	 *  MPO window in the left
+	 * - when it tries to get a free pipe for the MPO window on the right,
+	 *  it will see that it is already assigned to the right side
+	 *  ( primary_pipe->next_odm_pipe ).  But in this case, we want this
+	 *  free pipe, since it will be for the right side.  So add an
+	 *  additional condition, that skipping the free pipe on the right only
+	 *  applies if the primary pipe has no bottom pipe currently assigned
+	 */
+	if (primary_pipe) {
+		primary_index = primary_pipe->pipe_idx;
+		old_primary_pipe = &primary_pipe->stream->ctx->dc->current_state->res_ctx.pipe_ctx[primary_index];
+		if ((old_primary_pipe->next_odm_pipe) && (old_primary_pipe->next_odm_pipe->bottom_pipe)
+			&& (!primary_pipe->bottom_pipe))
+			next_odm_mpo_pipe = old_primary_pipe->next_odm_pipe->bottom_pipe;
+
+		preferred_pipe_idx = (pool->pipe_count - 1) - primary_pipe->pipe_idx;
+		if ((res_ctx->pipe_ctx[preferred_pipe_idx].stream == NULL) &&
+			!(next_odm_mpo_pipe && next_odm_mpo_pipe->pipe_idx == preferred_pipe_idx)) {
+			secondary_pipe = &res_ctx->pipe_ctx[preferred_pipe_idx];
+			secondary_pipe->pipe_idx = preferred_pipe_idx;
+		}
+	}
+
+	/*
+	 * search backwards for the second pipe to keep pipe
+	 * assignment more consistent
+	 */
+	if (!secondary_pipe)
+		for (i = pool->pipe_count - 1; i >= 0; i--) {
+			if ((res_ctx->pipe_ctx[i].stream == NULL) &&
+				!(next_odm_mpo_pipe && next_odm_mpo_pipe->pipe_idx == i)) {
+				secondary_pipe = &res_ctx->pipe_ctx[i];
+				secondary_pipe->pipe_idx = i;
+				break;
+			}
+		}
+
+	return secondary_pipe;
+}
+
+static struct pipe_ctx *dcn32_acquire_idle_pipe_for_head_pipe_in_layer(
+		struct dc_state *state,
+		const struct resource_pool *pool,
+		struct dc_stream_state *stream,
+		const struct pipe_ctx *head_pipe)
+{
+	struct resource_context *res_ctx = &state->res_ctx;
+	struct pipe_ctx *idle_pipe, *pipe;
+	struct resource_context *old_ctx = &stream->ctx->dc->current_state->res_ctx;
+	int head_index;
+
+	if (!head_pipe)
+		ASSERT(0);
+
+	/*
+	 * Modified from dcn20_acquire_idle_pipe_for_layer
+	 * Check if head_pipe in old_context already has bottom_pipe allocated.
+	 * - If so, check if that pipe is available in the current context.
+	 * --  If so, reuse pipe from old_context
+	 */
+	head_index = head_pipe->pipe_idx;
+	pipe = &old_ctx->pipe_ctx[head_index];
+	if (pipe->bottom_pipe && res_ctx->pipe_ctx[pipe->bottom_pipe->pipe_idx].stream == NULL) {
+		idle_pipe = &res_ctx->pipe_ctx[pipe->bottom_pipe->pipe_idx];
+		idle_pipe->pipe_idx = pipe->bottom_pipe->pipe_idx;
+	} else {
+		idle_pipe = find_idle_secondary_pipe_check_mpo(res_ctx, pool, head_pipe);
+		if (!idle_pipe)
+			return NULL;
+	}
+
+	idle_pipe->stream = head_pipe->stream;
+	idle_pipe->stream_res.tg = head_pipe->stream_res.tg;
+	idle_pipe->stream_res.opp = head_pipe->stream_res.opp;
+
+	idle_pipe->plane_res.hubp = pool->hubps[idle_pipe->pipe_idx];
+	idle_pipe->plane_res.ipp = pool->ipps[idle_pipe->pipe_idx];
+	idle_pipe->plane_res.dpp = pool->dpps[idle_pipe->pipe_idx];
+	idle_pipe->plane_res.mpcc_inst = pool->dpps[idle_pipe->pipe_idx]->inst;
+
+	return idle_pipe;
+}
+
 struct pipe_ctx *dcn32_acquire_free_pipe_as_secondary_dpp_pipe(
 		const struct dc_state *cur_ctx,
 		struct dc_state *new_ctx,
 		const struct resource_pool *pool,
 		const struct pipe_ctx *opp_head_pipe)
 {
-	int free_pipe_idx =
-			find_optimal_free_pipe_as_secondary_dpp_pipe(
-					&cur_ctx->res_ctx, &new_ctx->res_ctx,
-					pool, opp_head_pipe);
+
+	int free_pipe_idx;
 	struct pipe_ctx *free_pipe;
 
+	if (!opp_head_pipe->stream->ctx->dc->config.enable_windowed_mpo_odm)
+		return dcn32_acquire_idle_pipe_for_head_pipe_in_layer(
+				new_ctx, pool, opp_head_pipe->stream, opp_head_pipe);
+
+	free_pipe_idx = find_optimal_free_pipe_as_secondary_dpp_pipe(
+					&cur_ctx->res_ctx, &new_ctx->res_ctx,
+					pool, opp_head_pipe);
 	if (free_pipe_idx >= 0) {
 		free_pipe = &new_ctx->res_ctx.pipe_ctx[free_pipe_idx];
 		free_pipe->pipe_idx = free_pipe_idx;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
index 8afda5ecc0cd..5805fb02af14 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
@@ -1099,6 +1099,11 @@ void dcn20_calculate_dlg_params(struct dc *dc,
 		context->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz =
 						pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000;
 		context->res_ctx.pipe_ctx[i].pipe_dlg_param = pipes[pipe_idx].pipe.dest;
+		if (dc->ctx->dce_version < DCN_VERSION_3_1 &&
+		    context->res_ctx.pipe_ctx[i].stream->adaptive_sync_infopacket.valid)
+			dcn20_adjust_freesync_v_startup(
+				&context->res_ctx.pipe_ctx[i].stream->timing,
+				&context->res_ctx.pipe_ctx[i].pipe_dlg_param.vstartup_start);
 
 		pipe_idx++;
 	}
@@ -1927,7 +1932,6 @@ static bool dcn20_validate_bandwidth_internal(struct dc *dc, struct dc_state *co
 	int vlevel = 0;
 	int pipe_split_from[MAX_PIPES];
 	int pipe_cnt = 0;
-	int i = 0;
 	display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_ATOMIC);
 	DC_LOGGER_INIT(dc->ctx->logger);
 
@@ -1951,15 +1955,6 @@ static bool dcn20_validate_bandwidth_internal(struct dc *dc, struct dc_state *co
 	dcn20_calculate_wm(dc, context, pipes, &pipe_cnt, pipe_split_from, vlevel, fast_validate);
 	dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel);
 
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		if (!context->res_ctx.pipe_ctx[i].stream)
-			continue;
-		if (context->res_ctx.pipe_ctx[i].stream->adaptive_sync_infopacket.valid)
-			dcn20_adjust_freesync_v_startup(
-				&context->res_ctx.pipe_ctx[i].stream->timing,
-				&context->res_ctx.pipe_ctx[i].pipe_dlg_param.vstartup_start);
-	}
-
 	BW_VAL_TRACE_END_WATERMARKS();
 
 	goto validate_out;
@@ -2232,7 +2227,6 @@ bool dcn21_validate_bandwidth_fp(struct dc *dc,
 	int vlevel = 0;
 	int pipe_split_from[MAX_PIPES];
 	int pipe_cnt = 0;
-	int i = 0;
 	display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_ATOMIC);
 	DC_LOGGER_INIT(dc->ctx->logger);
 
@@ -2261,15 +2255,6 @@ bool dcn21_validate_bandwidth_fp(struct dc *dc,
 	dcn21_calculate_wm(dc, context, pipes, &pipe_cnt, pipe_split_from, vlevel, fast_validate);
 	dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel);
 
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		if (!context->res_ctx.pipe_ctx[i].stream)
-			continue;
-		if (context->res_ctx.pipe_ctx[i].stream->adaptive_sync_infopacket.valid)
-			dcn20_adjust_freesync_v_startup(
-				&context->res_ctx.pipe_ctx[i].stream->timing,
-				&context->res_ctx.pipe_ctx[i].pipe_dlg_param.vstartup_start);
-	}
-
 	BW_VAL_TRACE_END_WATERMARKS();
 
 	goto validate_out;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
index 07adb614366e..fb21572750e8 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c
@@ -293,6 +293,17 @@ static unsigned int micro_sec_to_vert_lines(unsigned int num_us, struct dc_crtc_
 	return num_lines;
 }
 
+static unsigned int get_vertical_back_porch(struct dc_crtc_timing *timing)
+{
+	unsigned int v_active = 0, v_blank = 0, v_back_porch = 0;
+
+	v_active = timing->v_border_top + timing->v_addressable + timing->v_border_bottom;
+	v_blank = timing->v_total - v_active;
+	v_back_porch = v_blank - timing->v_front_porch - timing->v_sync_width;
+
+	return v_back_porch;
+}
+
 int dcn314_populate_dml_pipes_from_context_fpu(struct dc *dc, struct dc_state *context,
 					       display_e2e_pipe_params_st *pipes,
 					       bool fast_validate)
@@ -310,6 +321,7 @@ int dcn314_populate_dml_pipes_from_context_fpu(struct dc *dc, struct dc_state *c
 	for (i = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) {
 		struct dc_crtc_timing *timing;
 		unsigned int num_lines = 0;
+		unsigned int v_back_porch = 0;
 
 		if (!res_ctx->pipe_ctx[i].stream)
 			continue;
@@ -323,9 +335,16 @@ int dcn314_populate_dml_pipes_from_context_fpu(struct dc *dc, struct dc_state *c
 		else
 			pipes[pipe_cnt].pipe.dest.vtotal = timing->v_total;
 
+		v_back_porch  = get_vertical_back_porch(timing);
+
 		pipes[pipe_cnt].pipe.dest.vblank_nom = timing->v_total - pipes[pipe_cnt].pipe.dest.vactive;
 		pipes[pipe_cnt].pipe.dest.vblank_nom = min(pipes[pipe_cnt].pipe.dest.vblank_nom, num_lines);
-		pipes[pipe_cnt].pipe.dest.vblank_nom = max(pipes[pipe_cnt].pipe.dest.vblank_nom, timing->v_sync_width);
+		// vblank_nom should not smaller than (VSync (timing->v_sync_width + v_back_porch) + 2)
+		// + 2 is because
+		// 1 -> VStartup_start should be 1 line before VSync
+		// 1 -> always reserve 1 line between start of vblank to vstartup signal
+		pipes[pipe_cnt].pipe.dest.vblank_nom =
+			max(pipes[pipe_cnt].pipe.dest.vblank_nom, timing->v_sync_width + v_back_porch + 2);
 		pipes[pipe_cnt].pipe.dest.vblank_nom = min(pipes[pipe_cnt].pipe.dest.vblank_nom, max_allowed_vblank_nom);
 
 		if (pipe->plane_state &&