Merge tag 'drm-msm-fixes-2025-12-26' of https://gitlab.freedesktop.org/drm/msm into drm-fixes

Fixes for v6.19:

GPU:
- Fix crash on a7xx GPUs not supporting IFPC
- Fix perfcntr use with IFPC
- Concurrent binning fix

DPU:
- Fixed DSC and SSPP fetching issues
- Switched to scnprint instead of snprintf
- Added missing NULL checks in pingpong code

Also documentation fixes.

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Rob Clark <rob.clark@oss.qualcomm.com>
Link: https://patch.msgid.link/CACSVV01jcLLChsFtmqc4VDNoQ2ic2q+d86n3wdoSUdmW6xaSdQ@mail.gmail.com

Author: airlied

drivers/gpu/drm/msm/adreno/a6xx_catalog.c

@@ -1376,7 +1376,6 @@ static const uint32_t a7xx_pwrup_reglist_regs[] = {
 	REG_A6XX_UCHE_MODE_CNTL,
 	REG_A6XX_RB_NC_MODE_CNTL,
 	REG_A6XX_RB_CMP_DBG_ECO_CNTL,
-	REG_A7XX_GRAS_NC_MODE_CNTL,
 	REG_A6XX_RB_CONTEXT_SWITCH_GMEM_SAVE_RESTORE_ENABLE,
 	REG_A6XX_UCHE_GBIF_GX_CONFIG,
 	REG_A6XX_UCHE_CLIENT_PF,
@@ -1392,6 +1391,7 @@ static const u32 a750_ifpc_reglist_regs[] = {
 	REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(2),
 	REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(3),
 	REG_A6XX_TPL1_BICUBIC_WEIGHTS_TABLE(4),
+	REG_A6XX_RBBM_PERFCTR_CNTL,
 	REG_A6XX_TPL1_NC_MODE_CNTL,
 	REG_A6XX_SP_NC_MODE_CNTL,
 	REG_A6XX_CP_DBG_ECO_CNTL,
@@ -1448,6 +1448,12 @@ static const u32 a750_ifpc_reglist_regs[] = {
 
 DECLARE_ADRENO_REGLIST_LIST(a750_ifpc_reglist);
 
+static const struct adreno_reglist_pipe a7xx_dyn_pwrup_reglist_regs[] = {
+	{ REG_A7XX_GRAS_NC_MODE_CNTL, 0, BIT(PIPE_BV) | BIT(PIPE_BR) },
+};
+
+DECLARE_ADRENO_REGLIST_PIPE_LIST(a7xx_dyn_pwrup_reglist);
+
 static const struct adreno_info a7xx_gpus[] = {
 	{
 		.chip_ids = ADRENO_CHIP_IDS(0x07000200),
@@ -1491,6 +1497,7 @@ static const struct adreno_info a7xx_gpus[] = {
 			.hwcg = a730_hwcg,
 			.protect = &a730_protect,
 			.pwrup_reglist = &a7xx_pwrup_reglist,
+			.dyn_pwrup_reglist = &a7xx_dyn_pwrup_reglist,
 			.gbif_cx = a640_gbif,
 			.gmu_cgc_mode = 0x00020000,
 		},
@@ -1513,6 +1520,7 @@ static const struct adreno_info a7xx_gpus[] = {
 			.hwcg = a740_hwcg,
 			.protect = &a730_protect,
 			.pwrup_reglist = &a7xx_pwrup_reglist,
+			.dyn_pwrup_reglist = &a7xx_dyn_pwrup_reglist,
 			.gbif_cx = a640_gbif,
 			.gmu_chipid = 0x7020100,
 			.gmu_cgc_mode = 0x00020202,
@@ -1547,6 +1555,7 @@ static const struct adreno_info a7xx_gpus[] = {
 			.hwcg = a740_hwcg,
 			.protect = &a730_protect,
 			.pwrup_reglist = &a7xx_pwrup_reglist,
+			.dyn_pwrup_reglist = &a7xx_dyn_pwrup_reglist,
 			.ifpc_reglist = &a750_ifpc_reglist,
 			.gbif_cx = a640_gbif,
 			.gmu_chipid = 0x7050001,
@@ -1589,6 +1598,7 @@ static const struct adreno_info a7xx_gpus[] = {
 		.a6xx = &(const struct a6xx_info) {
 			.protect = &a730_protect,
 			.pwrup_reglist = &a7xx_pwrup_reglist,
+			.dyn_pwrup_reglist = &a7xx_dyn_pwrup_reglist,
 			.ifpc_reglist = &a750_ifpc_reglist,
 			.gbif_cx = a640_gbif,
 			.gmu_chipid = 0x7090100,
@@ -1623,6 +1633,7 @@ static const struct adreno_info a7xx_gpus[] = {
 			.hwcg = a740_hwcg,
 			.protect = &a730_protect,
 			.pwrup_reglist = &a7xx_pwrup_reglist,
+			.dyn_pwrup_reglist = &a7xx_dyn_pwrup_reglist,
 			.gbif_cx = a640_gbif,
 			.gmu_chipid = 0x70f0000,
 			.gmu_cgc_mode = 0x00020222,

drivers/gpu/drm/msm/adreno/a6xx_gpu.c

@@ -849,9 +849,16 @@ static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
 		  min_acc_len_64b << 3 |
 		  hbb_lo << 1 | ubwc_mode);
 
-	if (adreno_is_a7xx(adreno_gpu))
-		gpu_write(gpu, REG_A7XX_GRAS_NC_MODE_CNTL,
-			  FIELD_PREP(GENMASK(8, 5), hbb_lo));
+	if (adreno_is_a7xx(adreno_gpu)) {
+		for (u32 pipe_id = PIPE_BR; pipe_id <= PIPE_BV; pipe_id++) {
+			gpu_write(gpu, REG_A7XX_CP_APERTURE_CNTL_HOST,
+				  A7XX_CP_APERTURE_CNTL_HOST_PIPE(pipe_id));
+			gpu_write(gpu, REG_A7XX_GRAS_NC_MODE_CNTL,
+				  FIELD_PREP(GENMASK(8, 5), hbb_lo));
+		}
+		gpu_write(gpu, REG_A7XX_CP_APERTURE_CNTL_HOST,
+			  A7XX_CP_APERTURE_CNTL_HOST_PIPE(PIPE_NONE));
+	}
 
 	gpu_write(gpu, REG_A6XX_UCHE_MODE_CNTL,
 		  min_acc_len_64b << 23 | hbb_lo << 21);
@@ -865,23 +872,27 @@ static void a7xx_patch_pwrup_reglist(struct msm_gpu *gpu)
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
 	const struct adreno_reglist_list *reglist;
+	const struct adreno_reglist_pipe_list *dyn_pwrup_reglist;
 	void *ptr = a6xx_gpu->pwrup_reglist_ptr;
 	struct cpu_gpu_lock *lock = ptr;
 	u32 *dest = (u32 *)&lock->regs[0];
+	u32 dyn_pwrup_reglist_count = 0;
 	int i;
 
 	lock->gpu_req = lock->cpu_req = lock->turn = 0;
 
 	reglist = adreno_gpu->info->a6xx->ifpc_reglist;
-	lock->ifpc_list_len = reglist->count;
+	if (reglist) {
+		lock->ifpc_list_len = reglist->count;
 
-	/*
-	 * For each entry in each of the lists, write the offset and the current
-	 * register value into the GPU buffer
-	 */
-	for (i = 0; i < reglist->count; i++) {
-		*dest++ = reglist->regs[i];
-		*dest++ = gpu_read(gpu, reglist->regs[i]);
+		/*
+		 * For each entry in each of the lists, write the offset and the current
+		 * register value into the GPU buffer
+		 */
+		for (i = 0; i < reglist->count; i++) {
+			*dest++ = reglist->regs[i];
+			*dest++ = gpu_read(gpu, reglist->regs[i]);
+		}
 	}
 
 	reglist = adreno_gpu->info->a6xx->pwrup_reglist;
@@ -907,7 +918,24 @@ static void a7xx_patch_pwrup_reglist(struct msm_gpu *gpu)
 	 * (<aperture, shifted 12 bits> <address> <data>), and the length is
 	 * stored as number for triplets in dynamic_list_len.
 	 */
-	lock->dynamic_list_len = 0;
+	dyn_pwrup_reglist = adreno_gpu->info->a6xx->dyn_pwrup_reglist;
+	if (dyn_pwrup_reglist) {
+		for (u32 pipe_id = PIPE_BR; pipe_id <= PIPE_BV; pipe_id++) {
+			gpu_write(gpu, REG_A7XX_CP_APERTURE_CNTL_HOST,
+				  A7XX_CP_APERTURE_CNTL_HOST_PIPE(pipe_id));
+			for (i = 0; i < dyn_pwrup_reglist->count; i++) {
+				if ((dyn_pwrup_reglist->regs[i].pipe & BIT(pipe_id)) == 0)
+					continue;
+				*dest++ = A7XX_CP_APERTURE_CNTL_HOST_PIPE(pipe_id);
+				*dest++ = dyn_pwrup_reglist->regs[i].offset;
+				*dest++ = gpu_read(gpu, dyn_pwrup_reglist->regs[i].offset);
+				dyn_pwrup_reglist_count++;
+			}
+		}
+		gpu_write(gpu, REG_A7XX_CP_APERTURE_CNTL_HOST,
+			  A7XX_CP_APERTURE_CNTL_HOST_PIPE(PIPE_NONE));
+	}
+	lock->dynamic_list_len = dyn_pwrup_reglist_count;
 }
 
 static int a7xx_preempt_start(struct msm_gpu *gpu)

drivers/gpu/drm/msm/adreno/a6xx_gpu.h

@@ -45,6 +45,7 @@ struct a6xx_info {
 	const struct adreno_reglist *hwcg;
 	const struct adreno_protect *protect;
 	const struct adreno_reglist_list *pwrup_reglist;
+	const struct adreno_reglist_pipe_list *dyn_pwrup_reglist;
 	const struct adreno_reglist_list *ifpc_reglist;
 	const struct adreno_reglist *gbif_cx;
 	const struct adreno_reglist_pipe *nonctxt_reglist;

drivers/gpu/drm/msm/adreno/a6xx_preempt.c

@@ -454,11 +454,11 @@ void a6xx_preempt_init(struct msm_gpu *gpu)
 			gpu->vm, &a6xx_gpu->preempt_postamble_bo,
 			&a6xx_gpu->preempt_postamble_iova);
 
-	preempt_prepare_postamble(a6xx_gpu);
-
 	if (IS_ERR(a6xx_gpu->preempt_postamble_ptr))
 		goto fail;
 
+	preempt_prepare_postamble(a6xx_gpu);
+
 	timer_setup(&a6xx_gpu->preempt_timer, a6xx_preempt_timer, 0);
 
 	return;

drivers/gpu/drm/msm/adreno/adreno_gpu.h

@@ -188,6 +188,19 @@ static const struct adreno_reglist_list name = {		\
 	.count = ARRAY_SIZE(name ## _regs),		\
 };
 
+struct adreno_reglist_pipe_list {
+	/** @reg: List of register **/
+	const struct adreno_reglist_pipe *regs;
+	/** @count: Number of registers in the list **/
+	u32 count;
+};
+
+#define DECLARE_ADRENO_REGLIST_PIPE_LIST(name)	\
+static const struct adreno_reglist_pipe_list name = {		\
+	.regs = name ## _regs,				\
+	.count = ARRAY_SIZE(name ## _regs),		\
+};
+
 struct adreno_gpu {
 	struct msm_gpu base;
 	const struct adreno_info *info;

drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c

@@ -200,7 +200,7 @@ static int dpu_crtc_get_lm_crc(struct drm_crtc *crtc,
 		struct dpu_crtc_state *crtc_state)
 {
 	struct dpu_crtc_mixer *m;
-	u32 crcs[CRTC_QUAD_MIXERS];
+	u32 crcs[CRTC_DUAL_MIXERS];
 
 	int rc = 0;
 	int i;
@@ -1328,7 +1328,6 @@ static struct msm_display_topology dpu_crtc_get_topology(
 	struct drm_display_mode *mode = &crtc_state->adjusted_mode;
 	struct msm_display_topology topology = {0};
 	struct drm_encoder *drm_enc;
-	u32 num_rt_intf;
 
 	drm_for_each_encoder_mask(drm_enc, crtc->dev, crtc_state->encoder_mask)
 		dpu_encoder_update_topology(drm_enc, &topology, crtc_state->state,
@@ -1342,14 +1341,11 @@ static struct msm_display_topology dpu_crtc_get_topology(
 	 * Dual display
 	 * 2 LM, 2 INTF ( Split display using 2 interfaces)
 	 *
-	 * If DSC is enabled, try to use 4:4:2 topology if there is enough
-	 * resource. Otherwise, use 2:2:2 topology.
-	 *
 	 * Single display
 	 * 1 LM, 1 INTF
 	 * 2 LM, 1 INTF (stream merge to support high resolution interfaces)
 	 *
-	 * If DSC is enabled, use 2:2:1 topology
+	 * If DSC is enabled, use 2 LMs for 2:2:1 topology
 	 *
 	 * Add dspps to the reservation requirements if ctm is requested
 	 *
@@ -1361,23 +1357,14 @@ static struct msm_display_topology dpu_crtc_get_topology(
 	 * (mode->hdisplay > MAX_HDISPLAY_SPLIT) check.
 	 */
 
-	num_rt_intf = topology.num_intf;
-	if (topology.cwb_enabled)
-		num_rt_intf--;
-
-	if (topology.num_dsc) {
-		if (dpu_kms->catalog->dsc_count >= num_rt_intf * 2)
-			topology.num_dsc = num_rt_intf * 2;
-		else
-			topology.num_dsc = num_rt_intf;
-		topology.num_lm = topology.num_dsc;
-	} else if (num_rt_intf == 2) {
+	if (topology.num_intf == 2 && !topology.cwb_enabled)
+		topology.num_lm = 2;
+	else if (topology.num_dsc == 2)
 		topology.num_lm = 2;
-	} else if (dpu_kms->catalog->caps->has_3d_merge) {
+	else if (dpu_kms->catalog->caps->has_3d_merge)
 		topology.num_lm = (mode->hdisplay > MAX_HDISPLAY_SPLIT) ? 2 : 1;
-	} else {
+	else
 		topology.num_lm = 1;
-	}
 
 	if (crtc_state->ctm)
 		topology.num_dspp = topology.num_lm;
@@ -1620,17 +1607,6 @@ int dpu_crtc_vblank(struct drm_crtc *crtc, bool en)
 	return 0;
 }
 
-/**
- * dpu_crtc_get_num_lm - Get mixer number in this CRTC pipeline
- * @state: Pointer to drm crtc state object
- */
-unsigned int dpu_crtc_get_num_lm(const struct drm_crtc_state *state)
-{
-	struct dpu_crtc_state *cstate = to_dpu_crtc_state(state);
-
-	return cstate->num_mixers;
-}
-
 #ifdef CONFIG_DEBUG_FS
 static int _dpu_debugfs_status_show(struct seq_file *s, void *data)
 {

drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h

@@ -210,18 +210,18 @@ struct dpu_crtc_state {
 
 	bool bw_control;
 	bool bw_split_vote;
-	struct drm_rect lm_bounds[CRTC_QUAD_MIXERS];
+	struct drm_rect lm_bounds[CRTC_DUAL_MIXERS];
 
 	uint64_t input_fence_timeout_ns;
 
 	struct dpu_core_perf_params new_perf;
 
 	/* HW Resources reserved for the crtc */
 	u32 num_mixers;
-	struct dpu_crtc_mixer mixers[CRTC_QUAD_MIXERS];
+	struct dpu_crtc_mixer mixers[CRTC_DUAL_MIXERS];
 
 	u32 num_ctls;
-	struct dpu_hw_ctl *hw_ctls[CRTC_QUAD_MIXERS];
+	struct dpu_hw_ctl *hw_ctls[CRTC_DUAL_MIXERS];
 
 	enum dpu_crtc_crc_source crc_source;
 	int crc_frame_skip_count;
@@ -267,6 +267,4 @@ static inline enum dpu_crtc_client_type dpu_crtc_get_client_type(
 
 void dpu_crtc_frame_event_cb(struct drm_crtc *crtc, u32 event);
 
-unsigned int dpu_crtc_get_num_lm(const struct drm_crtc_state *state);
-
 #endif /* _DPU_CRTC_H_ */

drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c

@@ -55,7 +55,7 @@
 #define MAX_PHYS_ENCODERS_PER_VIRTUAL \
 	(MAX_H_TILES_PER_DISPLAY * NUM_PHYS_ENCODER_TYPES)
 
-#define MAX_CHANNELS_PER_ENC 4
+#define MAX_CHANNELS_PER_ENC 2
 #define MAX_CWB_PER_ENC 2
 
 #define IDLE_SHORT_TIMEOUT	1
@@ -661,6 +661,7 @@ void dpu_encoder_update_topology(struct drm_encoder *drm_enc,
 	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
 	struct msm_drm_private *priv = dpu_enc->base.dev->dev_private;
 	struct msm_display_info *disp_info = &dpu_enc->disp_info;
+	struct dpu_kms *dpu_kms = to_dpu_kms(priv->kms);
 	struct drm_connector *connector;
 	struct drm_connector_state *conn_state;
 	struct drm_framebuffer *fb;
@@ -674,12 +675,22 @@ void dpu_encoder_update_topology(struct drm_encoder *drm_enc,
 
 	dsc = dpu_encoder_get_dsc_config(drm_enc);
 
-	/*
-	 * Set DSC number as 1 to mark the enabled status, will be adjusted
-	 * in dpu_crtc_get_topology()
-	 */
-	if (dsc)
-		topology->num_dsc = 1;
+	/* We only support 2 DSC mode (with 2 LM and 1 INTF) */
+	if (dsc) {
+		/*
+		 * Use 2 DSC encoders, 2 layer mixers and 1 or 2 interfaces
+		 * when Display Stream Compression (DSC) is enabled,
+		 * and when enough DSC blocks are available.
+		 * This is power-optimal and can drive up to (including) 4k
+		 * screens.
+		 */
+		WARN(topology->num_intf > 2,
+		     "DSC topology cannot support more than 2 interfaces\n");
+		if (topology->num_intf >= 2 || dpu_kms->catalog->dsc_count >= 2)
+			topology->num_dsc = 2;
+		else
+			topology->num_dsc = 1;
+	}
 
 	connector = drm_atomic_get_new_connector_for_encoder(state, drm_enc);
 	if (!connector)
@@ -2169,8 +2180,8 @@ static void dpu_encoder_helper_reset_mixers(struct dpu_encoder_phys *phys_enc)
 {
 	int i, num_lm;
 	struct dpu_global_state *global_state;
-	struct dpu_hw_blk *hw_lm[MAX_CHANNELS_PER_ENC];
-	struct dpu_hw_mixer *hw_mixer[MAX_CHANNELS_PER_ENC];
+	struct dpu_hw_blk *hw_lm[2];
+	struct dpu_hw_mixer *hw_mixer[2];
 	struct dpu_hw_ctl *ctl = phys_enc->hw_ctl;
 
 	/* reset all mixers for this encoder */

drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h

@@ -302,7 +302,7 @@ static inline enum dpu_3d_blend_mode dpu_encoder_helper_get_3d_blend_mode(
 
 	/* Use merge_3d unless DSC MERGE topology is used */
 	if (phys_enc->split_role == ENC_ROLE_SOLO &&
-	    (dpu_cstate->num_mixers != 1) &&
+	    dpu_cstate->num_mixers == CRTC_DUAL_MIXERS &&
 	    !dpu_encoder_use_dsc_merge(phys_enc->parent))
 		return BLEND_3D_H_ROW_INT;
 

drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c

@@ -247,14 +247,12 @@ static void dpu_encoder_phys_wb_setup_ctl(struct dpu_encoder_phys *phys_enc)
 		if (hw_cdm)
 			intf_cfg.cdm = hw_cdm->idx;
 
-		if (phys_enc->hw_pp->merge_3d && phys_enc->hw_pp->merge_3d->ops.setup_3d_mode)
-			phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d,
-					mode_3d);
+		if (hw_pp && hw_pp->merge_3d && hw_pp->merge_3d->ops.setup_3d_mode)
+			hw_pp->merge_3d->ops.setup_3d_mode(hw_pp->merge_3d, mode_3d);
 
 		/* setup which pp blk will connect to this wb */
-		if (hw_pp && phys_enc->hw_wb->ops.bind_pingpong_blk)
-			phys_enc->hw_wb->ops.bind_pingpong_blk(phys_enc->hw_wb,
-					phys_enc->hw_pp->idx);
+		if (hw_pp && hw_wb->ops.bind_pingpong_blk)
+			hw_wb->ops.bind_pingpong_blk(hw_wb, hw_pp->idx);
 
 		phys_enc->hw_ctl->ops.setup_intf_cfg(phys_enc->hw_ctl, &intf_cfg);
 	} else if (phys_enc->hw_ctl && phys_enc->hw_ctl->ops.setup_intf_cfg) {