drm/amd/display: Use cursor locking to prevent flip delays

[Why]
Current locking scheme for cursor can result in a flip missing
its vsync, deferring it for one or more vsyncs.  Result is a
potential for stuttering when cursor is moved.

[How]
Use cursor update lock so that flips are not blocked while cursor
is being programmed.

Signed-off-by: Aric Cyr <aric.cyr@amd.com>
Reviewed-by: Nicholas Kazlauskas <Nicholas.Kazlauskas@amd.com>
Acked-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

6 files changed, 53 insertions, 8 deletions

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index bfc8578eda15..2eb5d0e3e425 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -1669,6 +1669,16 @@ void dcn10_pipe_control_lock(
 		hws->funcs.verify_allow_pstate_change_high(dc);
 }
 
+void dcn10_cursor_lock(struct dc *dc, struct pipe_ctx *pipe, bool lock)
+{
+	/* cursor lock is per MPCC tree, so only need to lock one pipe per stream */
+	if (!pipe || pipe->top_pipe)
+		return;
+
+	dc->res_pool->mpc->funcs->cursor_lock(dc->res_pool->mpc,
+			pipe->stream_res.opp->inst, lock);
+}
+
 static bool wait_for_reset_trigger_to_occur(
 	struct dc_context *dc_ctx,
 	struct timing_generator *tg)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
index 16a50e05ffbf..af51424315d5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
@@ -49,6 +49,7 @@ void dcn10_pipe_control_lock(
 	struct dc *dc,
 	struct pipe_ctx *pipe,
 	bool lock);
+void dcn10_cursor_lock(struct dc *dc, struct pipe_ctx *pipe, bool lock);
 void dcn10_blank_pixel_data(
 		struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c
index 6f3dbcdb06f5..6ff7e2bd1d4a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_init.c
@@ -50,6 +50,7 @@ static const struct hw_sequencer_funcs dcn10_funcs = {
 	.disable_audio_stream = dce110_disable_audio_stream,
 	.disable_plane = dcn10_disable_plane,
 	.pipe_control_lock = dcn10_pipe_control_lock,
+	.cursor_lock = dcn10_cursor_lock,
 	.interdependent_update_lock = dcn10_lock_all_pipes,
 	.prepare_bandwidth = dcn10_prepare_bandwidth,
 	.optimize_bandwidth = dcn10_optimize_bandwidth,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
index 04f863499cfb..3fcd408e9103 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
@@ -223,6 +223,9 @@ struct mpcc *mpc1_insert_plane(
 	REG_SET(MPCC_TOP_SEL[mpcc_id], 0, MPCC_TOP_SEL, dpp_id);
 	REG_SET(MPCC_OPP_ID[mpcc_id], 0, MPCC_OPP_ID, tree->opp_id);
 
+	/* Configure VUPDATE lock set for this MPCC to map to the OPP */
+	REG_SET(MPCC_UPDATE_LOCK_SEL[mpcc_id], 0, MPCC_UPDATE_LOCK_SEL, tree->opp_id);
+
 	/* update mpc tree mux setting */
 	if (tree->opp_list == insert_above_mpcc) {
 		/* insert the toppest mpcc */
@@ -318,6 +321,7 @@ void mpc1_remove_mpcc(
 		REG_SET(MPCC_TOP_SEL[mpcc_id], 0, MPCC_TOP_SEL, 0xf);
 		REG_SET(MPCC_BOT_SEL[mpcc_id], 0, MPCC_BOT_SEL, 0xf);
 		REG_SET(MPCC_OPP_ID[mpcc_id],  0, MPCC_OPP_ID,  0xf);
+		REG_SET(MPCC_UPDATE_LOCK_SEL[mpcc_id], 0, MPCC_UPDATE_LOCK_SEL, 0xf);
 
 		/* mark this mpcc as not in use */
 		mpc10->mpcc_in_use_mask &= ~(1 << mpcc_id);
@@ -328,6 +332,7 @@ void mpc1_remove_mpcc(
 		REG_SET(MPCC_TOP_SEL[mpcc_id], 0, MPCC_TOP_SEL, 0xf);
 		REG_SET(MPCC_BOT_SEL[mpcc_id], 0, MPCC_BOT_SEL, 0xf);
 		REG_SET(MPCC_OPP_ID[mpcc_id],  0, MPCC_OPP_ID,  0xf);
+		REG_SET(MPCC_UPDATE_LOCK_SEL[mpcc_id], 0, MPCC_UPDATE_LOCK_SEL, 0xf);
 	}
 }
 
@@ -361,6 +366,7 @@ void mpc1_mpc_init(struct mpc *mpc)
 		REG_SET(MPCC_TOP_SEL[mpcc_id], 0, MPCC_TOP_SEL, 0xf);
 		REG_SET(MPCC_BOT_SEL[mpcc_id], 0, MPCC_BOT_SEL, 0xf);
 		REG_SET(MPCC_OPP_ID[mpcc_id],  0, MPCC_OPP_ID,  0xf);
+		REG_SET(MPCC_UPDATE_LOCK_SEL[mpcc_id], 0, MPCC_UPDATE_LOCK_SEL, 0xf);
 
 		mpc1_init_mpcc(&(mpc->mpcc_array[mpcc_id]), mpcc_id);
 	}
@@ -381,6 +387,7 @@ void mpc1_mpc_init_single_inst(struct mpc *mpc, unsigned int mpcc_id)
 	REG_SET(MPCC_TOP_SEL[mpcc_id], 0, MPCC_TOP_SEL, 0xf);
 	REG_SET(MPCC_BOT_SEL[mpcc_id], 0, MPCC_BOT_SEL, 0xf);
 	REG_SET(MPCC_OPP_ID[mpcc_id],  0, MPCC_OPP_ID,  0xf);
+	REG_SET(MPCC_UPDATE_LOCK_SEL[mpcc_id], 0, MPCC_UPDATE_LOCK_SEL, 0xf);
 
 	mpc1_init_mpcc(&(mpc->mpcc_array[mpcc_id]), mpcc_id);
 
@@ -453,6 +460,13 @@ void mpc1_read_mpcc_state(
 			MPCC_BUSY, &s->busy);
 }
 
+void mpc1_cursor_lock(struct mpc *mpc, int opp_id, bool lock)
+{
+	struct dcn10_mpc *mpc10 = TO_DCN10_MPC(mpc);
+
+	REG_SET(CUR[opp_id], 0, CUR_VUPDATE_LOCK_SET, lock ? 1 : 0);
+}
+
 static const struct mpc_funcs dcn10_mpc_funcs = {
 	.read_mpcc_state = mpc1_read_mpcc_state,
 	.insert_plane = mpc1_insert_plane,
@@ -464,6 +478,7 @@ static const struct mpc_funcs dcn10_mpc_funcs = {
 	.assert_mpcc_idle_before_connect = mpc1_assert_mpcc_idle_before_connect,
 	.init_mpcc_list_from_hw = mpc1_init_mpcc_list_from_hw,
 	.update_blending = mpc1_update_blending,
+	.cursor_lock = mpc1_cursor_lock,
 	.set_denorm = NULL,
 	.set_denorm_clamp = NULL,
 	.set_output_csc = NULL,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.h
index 962a68e322ee..66a4719c22a0 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.h
@@ -39,11 +39,12 @@
 	SRII(MPCC_BG_G_Y, MPCC, inst),\
 	SRII(MPCC_BG_R_CR, MPCC, inst),\
 	SRII(MPCC_BG_B_CB, MPCC, inst),\
-	SRII(MPCC_BG_B_CB, MPCC, inst),\
-	SRII(MPCC_SM_CONTROL, MPCC, inst)
+	SRII(MPCC_SM_CONTROL, MPCC, inst),\
+	SRII(MPCC_UPDATE_LOCK_SEL, MPCC, inst)
 
 #define MPC_OUT_MUX_COMMON_REG_LIST_DCN1_0(inst) \
-	SRII(MUX, MPC_OUT, inst)
+	SRII(MUX, MPC_OUT, inst),\
+	VUPDATE_SRII(CUR, VUPDATE_LOCK_SET, inst)
 
 #define MPC_COMMON_REG_VARIABLE_LIST \
 	uint32_t MPCC_TOP_SEL[MAX_MPCC]; \
@@ -55,7 +56,9 @@
 	uint32_t MPCC_BG_R_CR[MAX_MPCC]; \
 	uint32_t MPCC_BG_B_CB[MAX_MPCC]; \
 	uint32_t MPCC_SM_CONTROL[MAX_MPCC]; \
-	uint32_t MUX[MAX_OPP];
+	uint32_t MUX[MAX_OPP]; \
+	uint32_t MPCC_UPDATE_LOCK_SEL[MAX_MPCC]; \
+	uint32_t CUR[MAX_OPP];
 
 #define MPC_COMMON_MASK_SH_LIST_DCN1_0(mask_sh)\
 	SF(MPCC0_MPCC_TOP_SEL, MPCC_TOP_SEL, mask_sh),\
@@ -78,7 +81,8 @@
 	SF(MPCC0_MPCC_SM_CONTROL, MPCC_SM_FIELD_ALT, mask_sh),\
 	SF(MPCC0_MPCC_SM_CONTROL, MPCC_SM_FORCE_NEXT_FRAME_POL, mask_sh),\
 	SF(MPCC0_MPCC_SM_CONTROL, MPCC_SM_FORCE_NEXT_TOP_POL, mask_sh),\
-	SF(MPC_OUT0_MUX, MPC_OUT_MUX, mask_sh)
+	SF(MPC_OUT0_MUX, MPC_OUT_MUX, mask_sh),\
+	SF(MPCC0_MPCC_UPDATE_LOCK_SEL, MPCC_UPDATE_LOCK_SEL, mask_sh)
 
 #define MPC_REG_FIELD_LIST(type) \
 	type MPCC_TOP_SEL;\
@@ -101,7 +105,9 @@
 	type MPCC_SM_FIELD_ALT;\
 	type MPCC_SM_FORCE_NEXT_FRAME_POL;\
 	type MPCC_SM_FORCE_NEXT_TOP_POL;\
-	type MPC_OUT_MUX;
+	type MPC_OUT_MUX;\
+	type MPCC_UPDATE_LOCK_SEL;\
+	type CUR_VUPDATE_LOCK_SET;
 
 struct dcn_mpc_registers {
 	MPC_COMMON_REG_VARIABLE_LIST
@@ -192,4 +198,6 @@ void mpc1_read_mpcc_state(
 		int mpcc_inst,
 		struct mpcc_state *s);
 
+void mpc1_cursor_lock(struct mpc *mpc, int opp_id, bool lock);
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 6d506c37fc71..bacf865f55c0 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -182,6 +182,14 @@ enum dcn10_clk_src_array_id {
 	.reg_name[id] = BASE(mm ## block ## id ## _ ## reg_name ## _BASE_IDX) + \
 					mm ## block ## id ## _ ## reg_name
 
+#define VUPDATE_SRII(reg_name, block, id)\
+	.reg_name[id] = BASE(mm ## reg_name ## 0 ## _ ## block ## id ## _BASE_IDX) + \
+					mm ## reg_name ## 0 ## _ ## block ## id
+
+/* set field/register/bitfield name */
+#define SFRB(field_name, reg_name, bitfield, post_fix)\
+	.field_name = reg_name ## __ ## bitfield ## post_fix
+
 /* NBIO */
 #define NBIO_BASE_INNER(seg) \
 	NBIF_BASE__INST0_SEG ## seg
@@ -432,11 +440,13 @@ static const struct dcn_mpc_registers mpc_regs = {
 };
 
 static const struct dcn_mpc_shift mpc_shift = {
-	MPC_COMMON_MASK_SH_LIST_DCN1_0(__SHIFT)
+	MPC_COMMON_MASK_SH_LIST_DCN1_0(__SHIFT),\
+	SFRB(CUR_VUPDATE_LOCK_SET, CUR0_VUPDATE_LOCK_SET0, CUR0_VUPDATE_LOCK_SET, __SHIFT)
 };
 
 static const struct dcn_mpc_mask mpc_mask = {
-	MPC_COMMON_MASK_SH_LIST_DCN1_0(_MASK),
+	MPC_COMMON_MASK_SH_LIST_DCN1_0(_MASK),\
+	SFRB(CUR_VUPDATE_LOCK_SET, CUR0_VUPDATE_LOCK_SET0, CUR0_VUPDATE_LOCK_SET, _MASK)
 };
 
 #define tg_regs(id)\