Merge tag 'drm-msm-fixes-2024-10-16' of https://gitlab.freedesktop.org/drm/msm into drm-fixes

Fixes for v6.12

Display:
- move CRTC resource assignment to atomic_check otherwise to make
  consecutive calls to atomic_check() consistent
- fix rounding / sign-extension issues with pclk calculation in
  case of DSC
- cleanups to drop incorrect null checks in dpu snapshots
- fix to use kvzalloc in dpu snapshot to avoid allocation issues
  in heavily loaded system cases
- Fix to not program merge_3d block if dual LM is not being used
- Fix to not flush merge_3d block if its not enabled otherwise
  this leads to false timeouts

GPU:
- a7xx: add a fence wait before SMMU table update
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Rob Clark <robdclark@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/CAF6AEGsp3Zbd_H3FhHdRz9yCYA4wxX4SenpYRSk=Mx2d8GMSuQ@mail.gmail.com

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

@@ -101,9 +101,10 @@ static void get_stats_counter(struct msm_ringbuffer *ring, u32 counter,
 }
 
 static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
-		struct msm_ringbuffer *ring, struct msm_file_private *ctx)
+		struct msm_ringbuffer *ring, struct msm_gem_submit *submit)
 {
 	bool sysprof = refcount_read(&a6xx_gpu->base.base.sysprof_active) > 1;
+	struct msm_file_private *ctx = submit->queue->ctx;
 	struct adreno_gpu *adreno_gpu = &a6xx_gpu->base;
 	phys_addr_t ttbr;
 	u32 asid;
@@ -115,6 +116,15 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
 	if (msm_iommu_pagetable_params(ctx->aspace->mmu, &ttbr, &asid))
 		return;
 
+	if (adreno_gpu->info->family >= ADRENO_7XX_GEN1) {
+		/* Wait for previous submit to complete before continuing: */
+		OUT_PKT7(ring, CP_WAIT_TIMESTAMP, 4);
+		OUT_RING(ring, 0);
+		OUT_RING(ring, lower_32_bits(rbmemptr(ring, fence)));
+		OUT_RING(ring, upper_32_bits(rbmemptr(ring, fence)));
+		OUT_RING(ring, submit->seqno - 1);
+	}
+
 	if (!sysprof) {
 		if (!adreno_is_a7xx(adreno_gpu)) {
 			/* Turn off protected mode to write to special registers */
@@ -193,7 +203,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	struct msm_ringbuffer *ring = submit->ring;
 	unsigned int i, ibs = 0;
 
-	a6xx_set_pagetable(a6xx_gpu, ring, submit->queue->ctx);
+	a6xx_set_pagetable(a6xx_gpu, ring, submit);
 
 	get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP(0),
 		rbmemptr_stats(ring, index, cpcycles_start));
@@ -283,7 +293,7 @@ static void a7xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	OUT_PKT7(ring, CP_THREAD_CONTROL, 1);
 	OUT_RING(ring, CP_THREAD_CONTROL_0_SYNC_THREADS | CP_SET_THREAD_BR);
 
-	a6xx_set_pagetable(a6xx_gpu, ring, submit->queue->ctx);
+	a6xx_set_pagetable(a6xx_gpu, ring, submit);
 
 	get_stats_counter(ring, REG_A7XX_RBBM_PERFCTR_CP(0),
 		rbmemptr_stats(ring, index, cpcycles_start));

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

@@ -711,12 +711,13 @@ void dpu_crtc_complete_commit(struct drm_crtc *crtc)
 	_dpu_crtc_complete_flip(crtc);
 }
 
-static void _dpu_crtc_setup_lm_bounds(struct drm_crtc *crtc,
+static int _dpu_crtc_check_and_setup_lm_bounds(struct drm_crtc *crtc,
 		struct drm_crtc_state *state)
 {
 	struct dpu_crtc_state *cstate = to_dpu_crtc_state(state);
 	struct drm_display_mode *adj_mode = &state->adjusted_mode;
 	u32 crtc_split_width = adj_mode->hdisplay / cstate->num_mixers;
+	struct dpu_kms *dpu_kms = _dpu_crtc_get_kms(crtc);
 	int i;
 
 	for (i = 0; i < cstate->num_mixers; i++) {
@@ -727,7 +728,12 @@ static void _dpu_crtc_setup_lm_bounds(struct drm_crtc *crtc,
 		r->y2 = adj_mode->vdisplay;
 
 		trace_dpu_crtc_setup_lm_bounds(DRMID(crtc), i, r);
+
+		if (drm_rect_width(r) > dpu_kms->catalog->caps->max_mixer_width)
+			return -E2BIG;
 	}
+
+	return 0;
 }
 
 static void _dpu_crtc_get_pcc_coeff(struct drm_crtc_state *state,
@@ -803,7 +809,7 @@ static void dpu_crtc_atomic_begin(struct drm_crtc *crtc,
 
 	DRM_DEBUG_ATOMIC("crtc%d\n", crtc->base.id);
 
-	_dpu_crtc_setup_lm_bounds(crtc, crtc->state);
+	_dpu_crtc_check_and_setup_lm_bounds(crtc, crtc->state);
 
 	/* encoder will trigger pending mask now */
 	drm_for_each_encoder_mask(encoder, crtc->dev, crtc->state->encoder_mask)
@@ -1091,9 +1097,6 @@ static void dpu_crtc_disable(struct drm_crtc *crtc,
 
 	dpu_core_perf_crtc_update(crtc, 0);
 
-	memset(cstate->mixers, 0, sizeof(cstate->mixers));
-	cstate->num_mixers = 0;
-
 	/* disable clk & bw control until clk & bw properties are set */
 	cstate->bw_control = false;
 	cstate->bw_split_vote = false;
@@ -1192,8 +1195,11 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc,
 	if (crtc_state->active_changed)
 		crtc_state->mode_changed = true;
 
-	if (cstate->num_mixers)
-		_dpu_crtc_setup_lm_bounds(crtc, crtc_state);
+	if (cstate->num_mixers) {
+		rc = _dpu_crtc_check_and_setup_lm_bounds(crtc, crtc_state);
+		if (rc)
+			return rc;
+	}
 
 	/* FIXME: move this to dpu_plane_atomic_check? */
 	drm_atomic_crtc_state_for_each_plane_state(plane, pstate, crtc_state) {

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

@@ -624,6 +624,40 @@ static struct msm_display_topology dpu_encoder_get_topology(
 	return topology;
 }
 
+static void dpu_encoder_assign_crtc_resources(struct dpu_kms *dpu_kms,
+					      struct drm_encoder *drm_enc,
+					      struct dpu_global_state *global_state,
+					      struct drm_crtc_state *crtc_state)
+{
+	struct dpu_crtc_state *cstate;
+	struct dpu_hw_blk *hw_ctl[MAX_CHANNELS_PER_ENC];
+	struct dpu_hw_blk *hw_lm[MAX_CHANNELS_PER_ENC];
+	struct dpu_hw_blk *hw_dspp[MAX_CHANNELS_PER_ENC];
+	int num_lm, num_ctl, num_dspp, i;
+
+	cstate = to_dpu_crtc_state(crtc_state);
+
+	memset(cstate->mixers, 0, sizeof(cstate->mixers));
+
+	num_ctl = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
+		drm_enc->base.id, DPU_HW_BLK_CTL, hw_ctl, ARRAY_SIZE(hw_ctl));
+	num_lm = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
+		drm_enc->base.id, DPU_HW_BLK_LM, hw_lm, ARRAY_SIZE(hw_lm));
+	num_dspp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
+		drm_enc->base.id, DPU_HW_BLK_DSPP, hw_dspp,
+		ARRAY_SIZE(hw_dspp));
+
+	for (i = 0; i < num_lm; i++) {
+		int ctl_idx = (i < num_ctl) ? i : (num_ctl-1);
+
+		cstate->mixers[i].hw_lm = to_dpu_hw_mixer(hw_lm[i]);
+		cstate->mixers[i].lm_ctl = to_dpu_hw_ctl(hw_ctl[ctl_idx]);
+		cstate->mixers[i].hw_dspp = i < num_dspp ? to_dpu_hw_dspp(hw_dspp[i]) : NULL;
+	}
+
+	cstate->num_mixers = num_lm;
+}
+
 static int dpu_encoder_virt_atomic_check(
 		struct drm_encoder *drm_enc,
 		struct drm_crtc_state *crtc_state,
@@ -692,6 +726,9 @@ static int dpu_encoder_virt_atomic_check(
 		if (!crtc_state->active_changed || crtc_state->enable)
 			ret = dpu_rm_reserve(&dpu_kms->rm, global_state,
 					drm_enc, crtc_state, topology);
+		if (!ret)
+			dpu_encoder_assign_crtc_resources(dpu_kms, drm_enc,
+							  global_state, crtc_state);
 	}
 
 	trace_dpu_enc_atomic_check_flags(DRMID(drm_enc), adj_mode->flags);
@@ -1093,14 +1130,11 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc,
 	struct dpu_encoder_virt *dpu_enc;
 	struct msm_drm_private *priv;
 	struct dpu_kms *dpu_kms;
-	struct dpu_crtc_state *cstate;
 	struct dpu_global_state *global_state;
 	struct dpu_hw_blk *hw_pp[MAX_CHANNELS_PER_ENC];
 	struct dpu_hw_blk *hw_ctl[MAX_CHANNELS_PER_ENC];
-	struct dpu_hw_blk *hw_lm[MAX_CHANNELS_PER_ENC];
-	struct dpu_hw_blk *hw_dspp[MAX_CHANNELS_PER_ENC] = { NULL };
 	struct dpu_hw_blk *hw_dsc[MAX_CHANNELS_PER_ENC];
-	int num_lm, num_ctl, num_pp, num_dsc;
+	int num_ctl, num_pp, num_dsc;
 	unsigned int dsc_mask = 0;
 	int i;
 
@@ -1129,11 +1163,6 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc,
 		ARRAY_SIZE(hw_pp));
 	num_ctl = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
 		drm_enc->base.id, DPU_HW_BLK_CTL, hw_ctl, ARRAY_SIZE(hw_ctl));
-	num_lm = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
-		drm_enc->base.id, DPU_HW_BLK_LM, hw_lm, ARRAY_SIZE(hw_lm));
-	dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state,
-		drm_enc->base.id, DPU_HW_BLK_DSPP, hw_dspp,
-		ARRAY_SIZE(hw_dspp));
 
 	for (i = 0; i < MAX_CHANNELS_PER_ENC; i++)
 		dpu_enc->hw_pp[i] = i < num_pp ? to_dpu_hw_pingpong(hw_pp[i])
@@ -1159,36 +1188,23 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc,
 		dpu_enc->cur_master->hw_cdm = hw_cdm ? to_dpu_hw_cdm(hw_cdm) : NULL;
 	}
 
-	cstate = to_dpu_crtc_state(crtc_state);
-
-	for (i = 0; i < num_lm; i++) {
-		int ctl_idx = (i < num_ctl) ? i : (num_ctl-1);
-
-		cstate->mixers[i].hw_lm = to_dpu_hw_mixer(hw_lm[i]);
-		cstate->mixers[i].lm_ctl = to_dpu_hw_ctl(hw_ctl[ctl_idx]);
-		cstate->mixers[i].hw_dspp = to_dpu_hw_dspp(hw_dspp[i]);
-	}
-
-	cstate->num_mixers = num_lm;
-
 	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
 		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
 
-		if (!dpu_enc->hw_pp[i]) {
+		phys->hw_pp = dpu_enc->hw_pp[i];
+		if (!phys->hw_pp) {
 			DPU_ERROR_ENC(dpu_enc,
 				"no pp block assigned at idx: %d\n", i);
 			return;
 		}
 
-		if (!hw_ctl[i]) {
+		phys->hw_ctl = i < num_ctl ? to_dpu_hw_ctl(hw_ctl[i]) : NULL;
+		if (!phys->hw_ctl) {
 			DPU_ERROR_ENC(dpu_enc,
 				"no ctl block assigned at idx: %d\n", i);
 			return;
 		}
 
-		phys->hw_pp = dpu_enc->hw_pp[i];
-		phys->hw_ctl = to_dpu_hw_ctl(hw_ctl[i]);
-
 		phys->cached_mode = crtc_state->adjusted_mode;
 		if (phys->ops.atomic_mode_set)
 			phys->ops.atomic_mode_set(phys, crtc_state, conn_state);

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

@@ -302,7 +302,7 @@ static void dpu_encoder_phys_vid_setup_timing_engine(
 	intf_cfg.stream_sel = 0; /* Don't care value for video mode */
 	intf_cfg.mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc);
 	intf_cfg.dsc = dpu_encoder_helper_get_dsc(phys_enc);
-	if (phys_enc->hw_pp->merge_3d)
+	if (intf_cfg.mode_3d && phys_enc->hw_pp->merge_3d)
 		intf_cfg.merge_3d = phys_enc->hw_pp->merge_3d->idx;
 
 	spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
@@ -440,10 +440,12 @@ static void dpu_encoder_phys_vid_enable(struct dpu_encoder_phys *phys_enc)
 	struct dpu_hw_ctl *ctl;
 	const struct msm_format *fmt;
 	u32 fmt_fourcc;
+	u32 mode_3d;
 
 	ctl = phys_enc->hw_ctl;
 	fmt_fourcc = dpu_encoder_get_drm_fmt(phys_enc);
 	fmt = mdp_get_format(&phys_enc->dpu_kms->base, fmt_fourcc, 0);
+	mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc);
 
 	DPU_DEBUG_VIDENC(phys_enc, "\n");
 
@@ -466,7 +468,8 @@ static void dpu_encoder_phys_vid_enable(struct dpu_encoder_phys *phys_enc)
 		goto skip_flush;
 
 	ctl->ops.update_pending_flush_intf(ctl, phys_enc->hw_intf->idx);
-	if (ctl->ops.update_pending_flush_merge_3d && phys_enc->hw_pp->merge_3d)
+	if (mode_3d && ctl->ops.update_pending_flush_merge_3d &&
+	    phys_enc->hw_pp->merge_3d)
 		ctl->ops.update_pending_flush_merge_3d(ctl, phys_enc->hw_pp->merge_3d->idx);
 
 	if (ctl->ops.update_pending_flush_cdm && phys_enc->hw_cdm)

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

@@ -275,6 +275,7 @@ static void _dpu_encoder_phys_wb_update_flush(struct dpu_encoder_phys *phys_enc)
 	struct dpu_hw_pingpong *hw_pp;
 	struct dpu_hw_cdm *hw_cdm;
 	u32 pending_flush = 0;
+	u32 mode_3d;
 
 	if (!phys_enc)
 		return;
@@ -283,6 +284,7 @@ static void _dpu_encoder_phys_wb_update_flush(struct dpu_encoder_phys *phys_enc)
 	hw_pp = phys_enc->hw_pp;
 	hw_ctl = phys_enc->hw_ctl;
 	hw_cdm = phys_enc->hw_cdm;
+	mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc);
 
 	DPU_DEBUG("[wb:%d]\n", hw_wb->idx - WB_0);
 
@@ -294,7 +296,8 @@ static void _dpu_encoder_phys_wb_update_flush(struct dpu_encoder_phys *phys_enc)
 	if (hw_ctl->ops.update_pending_flush_wb)
 		hw_ctl->ops.update_pending_flush_wb(hw_ctl, hw_wb->idx);
 
-	if (hw_ctl->ops.update_pending_flush_merge_3d && hw_pp && hw_pp->merge_3d)
+	if (mode_3d && hw_ctl->ops.update_pending_flush_merge_3d &&
+	    hw_pp && hw_pp->merge_3d)
 		hw_ctl->ops.update_pending_flush_merge_3d(hw_ctl,
 				hw_pp->merge_3d->idx);
 

drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c

@@ -26,7 +26,7 @@ static void msm_disp_state_dump_regs(u32 **reg, u32 aligned_len, void __iomem *b
 	end_addr = base_addr + aligned_len;
 
 	if (!(*reg))
-		*reg = kzalloc(len_padded, GFP_KERNEL);
+		*reg = kvzalloc(len_padded, GFP_KERNEL);
 
 	if (*reg)
 		dump_addr = *reg;
@@ -48,20 +48,21 @@ static void msm_disp_state_dump_regs(u32 **reg, u32 aligned_len, void __iomem *b
 	}
 }
 
-static void msm_disp_state_print_regs(u32 **reg, u32 len, void __iomem *base_addr,
-		struct drm_printer *p)
+static void msm_disp_state_print_regs(const u32 *dump_addr, u32 len,
+		void __iomem *base_addr, struct drm_printer *p)
 {
 	int i;
-	u32 *dump_addr = NULL;
 	void __iomem *addr;
 	u32 num_rows;
 
+	if (!dump_addr) {
+		drm_printf(p, "Registers not stored\n");
+		return;
+	}
+
 	addr = base_addr;
 	num_rows = len / REG_DUMP_ALIGN;
 
-	if (*reg)
-		dump_addr = *reg;
-
 	for (i = 0; i < num_rows; i++) {
 		drm_printf(p, "0x%lx : %08x %08x %08x %08x\n",
 				(unsigned long)(addr - base_addr),
@@ -89,7 +90,7 @@ void msm_disp_state_print(struct msm_disp_state *state, struct drm_printer *p)
 
 	list_for_each_entry_safe(block, tmp, &state->blocks, node) {
 		drm_printf(p, "====================%s================\n", block->name);
-		msm_disp_state_print_regs(&block->state, block->size, block->base_addr, p);
+		msm_disp_state_print_regs(block->state, block->size, block->base_addr, p);
 	}
 
 	drm_printf(p, "===================dpu drm state================\n");
@@ -161,7 +162,7 @@ void msm_disp_state_free(void *data)
 
 	list_for_each_entry_safe(block, tmp, &disp_state->blocks, node) {
 		list_del(&block->node);
-		kfree(block->state);
+		kvfree(block->state);
 		kfree(block);
 	}
 

drivers/gpu/drm/msm/dsi/dsi_host.c

@@ -542,7 +542,7 @@ static unsigned long dsi_adjust_pclk_for_compression(const struct drm_display_mo
 
 	int new_htotal = mode->htotal - mode->hdisplay + new_hdisplay;
 
-	return new_htotal * mode->vtotal * drm_mode_vrefresh(mode);
+	return mult_frac(mode->clock * 1000u, new_htotal, mode->htotal);
 }
 
 static unsigned long dsi_get_pclk_rate(const struct drm_display_mode *mode,
@@ -550,7 +550,7 @@ static unsigned long dsi_get_pclk_rate(const struct drm_display_mode *mode,
 {
 	unsigned long pclk_rate;
 
-	pclk_rate = mode->clock * 1000;
+	pclk_rate = mode->clock * 1000u;
 
 	if (dsc)
 		pclk_rate = dsi_adjust_pclk_for_compression(mode, dsc);

drivers/gpu/drm/msm/hdmi/hdmi_phy_8998.c

@@ -153,15 +153,6 @@ static inline u32 pll_get_pll_cmp(u64 fdata, unsigned long ref_clk)
 	return dividend - 1;
 }
 
-static inline u64 pll_cmp_to_fdata(u32 pll_cmp, unsigned long ref_clk)
-{
-	u64 fdata = ((u64)pll_cmp) * ref_clk * 10;
-
-	do_div(fdata, HDMI_PLL_CMP_CNT);
-
-	return fdata;
-}
-
 #define HDMI_REF_CLOCK_HZ ((u64)19200000)
 #define HDMI_MHZ_TO_HZ ((u64)1000000)
 static int pll_get_post_div(struct hdmi_8998_post_divider *pd, u64 bclk)