Merge tag 'drm-fixes-2023-07-28' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Regular scheduled fixes, msm and amdgpu leading the way, with some
  i915 and a single misc fbdev, all seems fine.

  fbdev:
   - remove unused function

  amdgpu:
   - gfxhub partition fix
   - Fix error handling in psp_sw_init()
   - SMU13 fix
   - DCN 3.1 fix
   - DCN 3.2 fix
   - Fix for display PHY programming sequence
   - DP MST error handling fix
   - GFX 9.4.3 fix

  amdkfd:
   - GFX11 trap handling fix

  i915:
   - Use shmem for dpt objects
   - Fix an error handling path in igt_write_huge()

  msm:
   - display:
      - Fix to correct the UBWC programming for decoder version 4.3 seen
        on SM8550
      - Add the missing flush and fetch bits for DMA4 and DMA5 SSPPs.
      - Fix to drop the unused dpu_core_perf_data_bus_id enum from the
        code
      - Drop the unused dsi_phy_14nm_17mA_regulators from QCM 2290 DSI
        cfg.
   - gpu:
      - Fix warn splat for newer devices without revn
      - Remove name/revn for a690.. we shouldn't be populating these for
        newer devices, for consistency, but it slipped through review
      - Fix a6xx gpu snapshot BINDLESS_DATA size (was listed in bytes
        instead of dwords, causing AHB faults on a6xx gen4/a660-family)
      - Disallow submit with fence id 0"

* tag 'drm-fixes-2023-07-28' of git://anongit.freedesktop.org/drm/drm: (22 commits)
  drm/msm: Disallow submit with fence id 0
  drm/amdgpu: Restore HQD persistent state register
  drm/amd/display: Unlock on error path in dm_handle_mst_sideband_msg_ready_event()
  drm/amd/display: Exit idle optimizations before attempt to access PHY
  drm/amd/display: Don't apply FIFO resync W/A if rdivider = 0
  drm/amd/display: Guard DCN31 PHYD32CLK logic against chip family
  drm/amd/smu: use AverageGfxclkFrequency* to replace previous GFX Curr Clock
  drm/amd: Fix an error handling mistake in psp_sw_init()
  drm/amdgpu: Fix infinite loop in gfxhub_v1_2_xcc_gart_enable (v2)
  drm/amdkfd: fix trap handling work around for debugging
  drm/fb-helper: Remove unused inline function drm_fb_helper_defio_init()
  drm/i915: Fix an error handling path in igt_write_huge()
  drm/i915/dpt: Use shmem for dpt objects
  drm/msm: Fix hw_fence error path cleanup
  drm/msm: Fix IS_ERR_OR_NULL() vs NULL check in a5xx_submit_in_rb()
  drm/msm/adreno: Fix snapshot BINDLESS_DATA size
  drm/msm/a690: Remove revn and name
  drm/msm/adreno: Fix warn splat for devices without revn
  drm/msm/dsi: Drop unused regulators from QCM2290 14nm DSI PHY config
  drm/msm/dpu: drop enum dpu_core_perf_data_bus_id
  ...

23 files changed, 88 insertions, 50 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 6d676bdd1505..78d1ee71f3f4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -498,11 +498,11 @@ static int psp_sw_init(void *handle)
 	return 0;
 
 failed2:
-	amdgpu_bo_free_kernel(&psp->fw_pri_bo,
-			      &psp->fw_pri_mc_addr, &psp->fw_pri_buf);
-failed1:
 	amdgpu_bo_free_kernel(&psp->fence_buf_bo,
 			      &psp->fence_buf_mc_addr, &psp->fence_buf);
+failed1:
+	amdgpu_bo_free_kernel(&psp->fw_pri_bo,
+			      &psp->fw_pri_mc_addr, &psp->fw_pri_buf);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
index 9e3b835bdbb2..4f883b94f98e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c
@@ -46,6 +46,7 @@ MODULE_FIRMWARE("amdgpu/gc_9_4_3_rlc.bin");
 #define RLCG_UCODE_LOADING_START_ADDRESS 0x00002000L
 
 #define GOLDEN_GB_ADDR_CONFIG 0x2a114042
+#define CP_HQD_PERSISTENT_STATE_DEFAULT 0xbe05301
 
 struct amdgpu_gfx_ras gfx_v9_4_3_ras;
 
@@ -1736,7 +1737,7 @@ static int gfx_v9_4_3_xcc_q_fini_register(struct amdgpu_ring *ring,
 
 	WREG32_SOC15_RLC(GC, GET_INST(GC, xcc_id), regCP_HQD_IQ_TIMER, 0);
 	WREG32_SOC15_RLC(GC, GET_INST(GC, xcc_id), regCP_HQD_IB_CONTROL, 0);
-	WREG32_SOC15_RLC(GC, GET_INST(GC, xcc_id), regCP_HQD_PERSISTENT_STATE, 0);
+	WREG32_SOC15_RLC(GC, GET_INST(GC, xcc_id), regCP_HQD_PERSISTENT_STATE, CP_HQD_PERSISTENT_STATE_DEFAULT);
 	WREG32_SOC15_RLC(GC, GET_INST(GC, xcc_id), regCP_HQD_PQ_DOORBELL_CONTROL, 0x40000000);
 	WREG32_SOC15_RLC(GC, GET_INST(GC, xcc_id), regCP_HQD_PQ_DOORBELL_CONTROL, 0);
 	WREG32_SOC15_RLC(GC, GET_INST(GC, xcc_id), regCP_HQD_PQ_RPTR, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c
index 4dabf910334b..d9f14dc55998 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c
@@ -402,18 +402,15 @@ static void gfxhub_v1_2_xcc_program_invalidation(struct amdgpu_device *adev,
 static int gfxhub_v1_2_xcc_gart_enable(struct amdgpu_device *adev,
 				       uint32_t xcc_mask)
 {
-	uint32_t tmp_mask;
 	int i;
 
-	tmp_mask = xcc_mask;
 	/*
 	 * MC_VM_FB_LOCATION_BASE/TOP is NULL for VF, because they are
 	 * VF copy registers so vbios post doesn't program them, for
 	 * SRIOV driver need to program them
 	 */
 	if (amdgpu_sriov_vf(adev)) {
-		for_each_inst(i, tmp_mask) {
-			i = ffs(tmp_mask) - 1;
+		for_each_inst(i, xcc_mask) {
 			WREG32_SOC15_RLC(GC, GET_INST(GC, i), regMC_VM_FB_LOCATION_BASE,
 				     adev->gmc.vram_start >> 24);
 			WREG32_SOC15_RLC(GC, GET_INST(GC, i), regMC_VM_FB_LOCATION_TOP,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
index fff3ccc04fa9..9766076e9ec4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
@@ -302,8 +302,7 @@ static int kfd_dbg_set_queue_workaround(struct queue *q, bool enable)
 	if (!q)
 		return 0;
 
-	if (KFD_GC_VERSION(q->device) < IP_VERSION(11, 0, 0) ||
-	    KFD_GC_VERSION(q->device) >= IP_VERSION(12, 0, 0))
+	if (!kfd_dbg_has_cwsr_workaround(q->device))
 		return 0;
 
 	if (enable && q->properties.is_user_cu_masked)
@@ -349,7 +348,7 @@ int kfd_dbg_set_mes_debug_mode(struct kfd_process_device *pdd)
 {
 	uint32_t spi_dbg_cntl = pdd->spi_dbg_override | pdd->spi_dbg_launch_mode;
 	uint32_t flags = pdd->process->dbg_flags;
-	bool sq_trap_en = !!spi_dbg_cntl;
+	bool sq_trap_en = !!spi_dbg_cntl || !kfd_dbg_has_cwsr_workaround(pdd->dev);
 
 	if (!kfd_dbg_is_per_vmid_supported(pdd->dev))
 		return 0;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debug.h b/drivers/gpu/drm/amd/amdkfd/kfd_debug.h
index a289e59ceb79..662a13a0d582 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_debug.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_debug.h
@@ -100,6 +100,12 @@ static inline bool kfd_dbg_is_rlc_restore_supported(struct kfd_node *dev)
 		 KFD_GC_VERSION(dev) == IP_VERSION(10, 1, 1));
 }
 
+static inline bool kfd_dbg_has_cwsr_workaround(struct kfd_node *dev)
+{
+	return KFD_GC_VERSION(dev) >= IP_VERSION(11, 0, 0) &&
+	       KFD_GC_VERSION(dev) <= IP_VERSION(11, 0, 3);
+}
+
 static inline bool kfd_dbg_has_gws_support(struct kfd_node *dev)
 {
 	if ((KFD_GC_VERSION(dev) == IP_VERSION(9, 0, 1)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index f515cb8f30ca..2df153828ff4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -226,8 +226,7 @@ static int add_queue_mes(struct device_queue_manager *dqm, struct queue *q,
 	queue_input.paging = false;
 	queue_input.tba_addr = qpd->tba_addr;
 	queue_input.tma_addr = qpd->tma_addr;
-	queue_input.trap_en = KFD_GC_VERSION(q->device) < IP_VERSION(11, 0, 0) ||
-			      KFD_GC_VERSION(q->device) > IP_VERSION(11, 0, 3);
+	queue_input.trap_en = !kfd_dbg_has_cwsr_workaround(q->device);
 	queue_input.skip_process_ctx_clear = qpd->pqm->process->debug_trap_enabled;
 
 	queue_type = convert_to_mes_queue_type(q->properties.type);
@@ -1806,8 +1805,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 	 */
 	q->properties.is_evicted = !!qpd->evicted;
 	q->properties.is_dbg_wa = qpd->pqm->process->debug_trap_enabled &&
-			KFD_GC_VERSION(q->device) >= IP_VERSION(11, 0, 0) &&
-			KFD_GC_VERSION(q->device) <= IP_VERSION(11, 0, 3);
+				  kfd_dbg_has_cwsr_workaround(q->device);
 
 	if (qd)
 		mqd_mgr->restore_mqd(mqd_mgr, &q->mqd, q->mqd_mem_obj, &q->gart_mqd_addr,
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 888e80f498e9..9bc86deac9e8 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -706,7 +706,7 @@ void dm_handle_mst_sideband_msg_ready_event(
 
 			if (retry == 3) {
 				DRM_ERROR("Failed to ack MST event.\n");
-				return;
+				break;
 			}
 
 			drm_dp_mst_hpd_irq_send_new_request(&aconnector->mst_mgr);
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index 6c9ca43d1040..20d4d08a6a2f 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -1792,10 +1792,13 @@ void dce110_enable_accelerated_mode(struct dc *dc, struct dc_state *context)
 			hws->funcs.edp_backlight_control(edp_link_with_sink, false);
 		}
 		/*resume from S3, no vbios posting, no need to power down again*/
+		clk_mgr_exit_optimized_pwr_state(dc, dc->clk_mgr);
+
 		power_down_all_hw_blocks(dc);
 		disable_vga_and_power_gate_all_controllers(dc);
 		if (edp_link_with_sink && !keep_edp_vdd_on)
 			dc->hwss.edp_power_control(edp_link_with_sink, false);
+		clk_mgr_optimize_pwr_state(dc, dc->clk_mgr);
 	}
 	bios_set_scratch_acc_mode_change(dc->ctx->dc_bios, 1);
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c
index 65c1d754e2d6..01cc679ae418 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c
@@ -84,7 +84,8 @@ static enum phyd32clk_clock_source get_phy_mux_symclk(
 		struct dcn_dccg *dccg_dcn,
 		enum phyd32clk_clock_source src)
 {
-	if (dccg_dcn->base.ctx->asic_id.hw_internal_rev == YELLOW_CARP_B0) {
+	if (dccg_dcn->base.ctx->asic_id.chip_family == FAMILY_YELLOW_CARP &&
+			dccg_dcn->base.ctx->asic_id.hw_internal_rev == YELLOW_CARP_B0) {
 		if (src == PHYD32CLKC)
 			src = PHYD32CLKF;
 		if (src == PHYD32CLKD)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c
index 11e28e056cf7..61ceff6bc0b1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_dccg.c
@@ -49,7 +49,10 @@ static void dccg32_trigger_dio_fifo_resync(
 	uint32_t dispclk_rdivider_value = 0;
 
 	REG_GET(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_RDIVIDER, &dispclk_rdivider_value);
-	REG_UPDATE(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_WDIVIDER, dispclk_rdivider_value);
+
+	/* Not valid for the WDIVIDER to be set to 0 */
+	if (dispclk_rdivider_value != 0)
+		REG_UPDATE(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_WDIVIDER, dispclk_rdivider_value);
 }
 
 static void dccg32_get_pixel_rate_div(
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
index b9bde5fa8f8f..3d188616ba24 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
@@ -1734,7 +1734,7 @@ static ssize_t smu_v13_0_0_get_gpu_metrics(struct smu_context *smu,
 	gpu_metrics->average_vclk1_frequency = metrics->AverageVclk1Frequency;
 	gpu_metrics->average_dclk1_frequency = metrics->AverageDclk1Frequency;
 
-	gpu_metrics->current_gfxclk = metrics->CurrClock[PPCLK_GFXCLK];
+	gpu_metrics->current_gfxclk = gpu_metrics->average_gfxclk_frequency;
 	gpu_metrics->current_socclk = metrics->CurrClock[PPCLK_SOCCLK];
 	gpu_metrics->current_uclk = metrics->CurrClock[PPCLK_UCLK];
 	gpu_metrics->current_vclk0 = metrics->CurrClock[PPCLK_VCLK_0];
diff --git a/drivers/gpu/drm/i915/display/intel_dpt.c b/drivers/gpu/drm/i915/display/intel_dpt.c
index 7c5fddb203ba..fbfd8f959f17 100644
--- a/drivers/gpu/drm/i915/display/intel_dpt.c
+++ b/drivers/gpu/drm/i915/display/intel_dpt.c
@@ -166,6 +166,8 @@ struct i915_vma *intel_dpt_pin(struct i915_address_space *vm)
 		i915_vma_get(vma);
 	}
 
+	dpt->obj->mm.dirty = true;
+
 	atomic_dec(&i915->gpu_error.pending_fb_pin);
 	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
 
@@ -261,7 +263,7 @@ intel_dpt_create(struct intel_framebuffer *fb)
 		dpt_obj = i915_gem_object_create_stolen(i915, size);
 	if (IS_ERR(dpt_obj) && !HAS_LMEM(i915)) {
 		drm_dbg_kms(&i915->drm, "Allocating dpt from smem\n");
-		dpt_obj = i915_gem_object_create_internal(i915, size);
+		dpt_obj = i915_gem_object_create_shmem(i915, size);
 	}
 	if (IS_ERR(dpt_obj))
 		return ERR_CAST(dpt_obj);
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index df6c9a84252c..6b9f6cf50bf6 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -1246,8 +1246,10 @@ static int igt_write_huge(struct drm_i915_private *i915,
 	 * times in succession a possibility by enlarging the permutation array.
 	 */
 	order = i915_random_order(count * count, &prng);
-	if (!order)
-		return -ENOMEM;
+	if (!order) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	max_page_size = rounddown_pow_of_two(obj->mm.page_sizes.sg);
 	max = div_u64(max - size, max_page_size);
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index a99310b68793..bbb1bf33f98e 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -89,7 +89,7 @@ static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit
 			 * since we've already mapped it once in
 			 * submit_reloc()
 			 */
-			if (WARN_ON(!ptr))
+			if (WARN_ON(IS_ERR_OR_NULL(ptr)))
 				return;
 
 			for (i = 0; i < dwords; i++) {
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
index 790f55e24533..e788ed72eb0d 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h
@@ -206,7 +206,7 @@ static const struct a6xx_shader_block {
 	SHADER(A6XX_SP_LB_3_DATA, 0x800),
 	SHADER(A6XX_SP_LB_4_DATA, 0x800),
 	SHADER(A6XX_SP_LB_5_DATA, 0x200),
-	SHADER(A6XX_SP_CB_BINDLESS_DATA, 0x2000),
+	SHADER(A6XX_SP_CB_BINDLESS_DATA, 0x800),
 	SHADER(A6XX_SP_CB_LEGACY_DATA, 0x280),
 	SHADER(A6XX_SP_UAV_DATA, 0x80),
 	SHADER(A6XX_SP_INST_TAG, 0x80),
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index cb94cfd137a8..ce8d0b2475bf 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -369,8 +369,6 @@ static const struct adreno_info gpulist[] = {
 		.hwcg = a640_hwcg,
 	}, {
 		.rev = ADRENO_REV(6, 9, 0, ANY_ID),
-		.revn = 690,
-		.name = "A690",
 		.fw = {
 			[ADRENO_FW_SQE] = "a660_sqe.fw",
 			[ADRENO_FW_GMU] = "a690_gmu.bin",
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index d8c9e8cc3753..845019891ad1 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -149,7 +149,8 @@ bool adreno_cmp_rev(struct adreno_rev rev1, struct adreno_rev rev2);
 
 static inline bool adreno_is_revn(const struct adreno_gpu *gpu, uint32_t revn)
 {
-	WARN_ON_ONCE(!gpu->revn);
+	/* revn can be zero, but if not is set at same time as info */
+	WARN_ON_ONCE(!gpu->info);
 
 	return gpu->revn == revn;
 }
@@ -161,14 +162,16 @@ static inline bool adreno_has_gmu_wrapper(const struct adreno_gpu *gpu)
 
 static inline bool adreno_is_a2xx(const struct adreno_gpu *gpu)
 {
-	WARN_ON_ONCE(!gpu->revn);
+	/* revn can be zero, but if not is set at same time as info */
+	WARN_ON_ONCE(!gpu->info);
 
 	return (gpu->revn < 300);
 }
 
 static inline bool adreno_is_a20x(const struct adreno_gpu *gpu)
 {
-	WARN_ON_ONCE(!gpu->revn);
+	/* revn can be zero, but if not is set at same time as info */
+	WARN_ON_ONCE(!gpu->info);
 
 	return (gpu->revn < 210);
 }
@@ -307,7 +310,8 @@ static inline int adreno_is_a680(const struct adreno_gpu *gpu)
 
 static inline int adreno_is_a690(const struct adreno_gpu *gpu)
 {
-	return adreno_is_revn(gpu, 690);
+	/* The order of args is important here to handle ANY_ID correctly */
+	return adreno_cmp_rev(ADRENO_REV(6, 9, 0, ANY_ID), gpu->rev);
 };
 
 /* check for a615, a616, a618, a619 or any derivatives */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
index e3795995e145..29bb8ee2bc26 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
@@ -15,19 +15,6 @@
 #define	DPU_PERF_DEFAULT_MAX_CORE_CLK_RATE	412500000
 
 /**
- * enum dpu_core_perf_data_bus_id - data bus identifier
- * @DPU_CORE_PERF_DATA_BUS_ID_MNOC: DPU/MNOC data bus
- * @DPU_CORE_PERF_DATA_BUS_ID_LLCC: MNOC/LLCC data bus
- * @DPU_CORE_PERF_DATA_BUS_ID_EBI: LLCC/EBI data bus
- */
-enum dpu_core_perf_data_bus_id {
-	DPU_CORE_PERF_DATA_BUS_ID_MNOC,
-	DPU_CORE_PERF_DATA_BUS_ID_LLCC,
-	DPU_CORE_PERF_DATA_BUS_ID_EBI,
-	DPU_CORE_PERF_DATA_BUS_ID_MAX,
-};
-
-/**
  * struct dpu_core_perf_params - definition of performance parameters
  * @max_per_pipe_ib: maximum instantaneous bandwidth request
  * @bw_ctl: arbitrated bandwidth request
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
index c278fb9d2b5b..86182c734606 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
@@ -51,7 +51,7 @@
 
 static const u32 fetch_tbl[SSPP_MAX] = {CTL_INVALID_BIT, 16, 17, 18, 19,
 	CTL_INVALID_BIT, CTL_INVALID_BIT, CTL_INVALID_BIT, CTL_INVALID_BIT, 0,
-	1, 2, 3, CTL_INVALID_BIT, CTL_INVALID_BIT};
+	1, 2, 3, 4, 5};
 
 static int _mixer_stages(const struct dpu_lm_cfg *mixer, int count,
 		enum dpu_lm lm)
@@ -198,6 +198,12 @@ static void dpu_hw_ctl_update_pending_flush_sspp(struct dpu_hw_ctl *ctx,
 	case SSPP_DMA3:
 		ctx->pending_flush_mask |= BIT(25);
 		break;
+	case SSPP_DMA4:
+		ctx->pending_flush_mask |= BIT(13);
+		break;
+	case SSPP_DMA5:
+		ctx->pending_flush_mask |= BIT(14);
+		break;
 	case SSPP_CURSOR0:
 		ctx->pending_flush_mask |= BIT(22);
 		break;
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c
index 3ce45b023e63..31deda1c664a 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c
@@ -1087,8 +1087,6 @@ const struct msm_dsi_phy_cfg dsi_phy_14nm_8953_cfgs = {
 
 const struct msm_dsi_phy_cfg dsi_phy_14nm_2290_cfgs = {
 	.has_phy_lane = true,
-	.regulator_data = dsi_phy_14nm_17mA_regulators,
-	.num_regulators = ARRAY_SIZE(dsi_phy_14nm_17mA_regulators),
 	.ops = {
 		.enable = dsi_14nm_phy_enable,
 		.disable = dsi_14nm_phy_disable,
diff --git a/drivers/gpu/drm/msm/msm_fence.c b/drivers/gpu/drm/msm/msm_fence.c
index 96599ec3eb78..1a5d4f1c8b42 100644
--- a/drivers/gpu/drm/msm/msm_fence.c
+++ b/drivers/gpu/drm/msm/msm_fence.c
@@ -191,6 +191,12 @@ msm_fence_init(struct dma_fence *fence, struct msm_fence_context *fctx)
 
 	f->fctx = fctx;
 
+	/*
+	 * Until this point, the fence was just some pre-allocated memory,
+	 * no-one should have taken a reference to it yet.
+	 */
+	WARN_ON(kref_read(&fence->refcount));
+
 	dma_fence_init(&f->base, &msm_fence_ops, &fctx->spinlock,
 		       fctx->context, ++fctx->last_fence);
 }
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 3f1aa4de3b87..63c96416e183 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -86,7 +86,19 @@ void __msm_gem_submit_destroy(struct kref *kref)
 	}
 
 	dma_fence_put(submit->user_fence);
-	dma_fence_put(submit->hw_fence);
+
+	/*
+	 * If the submit is freed before msm_job_run(), then hw_fence is
+	 * just some pre-allocated memory, not a reference counted fence.
+	 * Once the job runs and the hw_fence is initialized, it will
+	 * have a refcount of at least one, since the submit holds a ref
+	 * to the hw_fence.
+	 */
+	if (kref_read(&submit->hw_fence->refcount) == 0) {
+		kfree(submit->hw_fence);
+	} else {
+		dma_fence_put(submit->hw_fence);
+	}
 
 	put_pid(submit->pid);
 	msm_submitqueue_put(submit->queue);
@@ -889,7 +901,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	 * after the job is armed
 	 */
 	if ((args->flags & MSM_SUBMIT_FENCE_SN_IN) &&
-			idr_find(&queue->fence_idr, args->fence)) {
+			(!args->fence || idr_find(&queue->fence_idr, args->fence))) {
 		spin_unlock(&queue->idr_lock);
 		idr_preload_end();
 		ret = -EINVAL;
diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c
index 05648c910c68..798bd4f3b662 100644
--- a/drivers/gpu/drm/msm/msm_mdss.c
+++ b/drivers/gpu/drm/msm/msm_mdss.c
@@ -189,6 +189,7 @@ static int _msm_mdss_irq_domain_add(struct msm_mdss *msm_mdss)
 #define UBWC_2_0 0x20000000
 #define UBWC_3_0 0x30000000
 #define UBWC_4_0 0x40000000
+#define UBWC_4_3 0x40030000
 
 static void msm_mdss_setup_ubwc_dec_20(struct msm_mdss *msm_mdss)
 {
@@ -227,7 +228,10 @@ static void msm_mdss_setup_ubwc_dec_40(struct msm_mdss *msm_mdss)
 		writel_relaxed(1, msm_mdss->mmio + UBWC_CTRL_2);
 		writel_relaxed(0, msm_mdss->mmio + UBWC_PREDICTION_MODE);
 	} else {
-		writel_relaxed(2, msm_mdss->mmio + UBWC_CTRL_2);
+		if (data->ubwc_dec_version == UBWC_4_3)
+			writel_relaxed(3, msm_mdss->mmio + UBWC_CTRL_2);
+		else
+			writel_relaxed(2, msm_mdss->mmio + UBWC_CTRL_2);
 		writel_relaxed(1, msm_mdss->mmio + UBWC_PREDICTION_MODE);
 	}
 }
@@ -271,6 +275,7 @@ static int msm_mdss_enable(struct msm_mdss *msm_mdss)
 		msm_mdss_setup_ubwc_dec_30(msm_mdss);
 		break;
 	case UBWC_4_0:
+	case UBWC_4_3:
 		msm_mdss_setup_ubwc_dec_40(msm_mdss);
 		break;
 	default:
@@ -569,6 +574,16 @@ static const struct msm_mdss_data sm8250_data = {
 	.macrotile_mode = 1,
 };
 
+static const struct msm_mdss_data sm8550_data = {
+	.ubwc_version = UBWC_4_0,
+	.ubwc_dec_version = UBWC_4_3,
+	.ubwc_swizzle = 6,
+	.ubwc_static = 1,
+	/* TODO: highest_bank_bit = 2 for LP_DDR4 */
+	.highest_bank_bit = 3,
+	.macrotile_mode = 1,
+};
+
 static const struct of_device_id mdss_dt_match[] = {
 	{ .compatible = "qcom,mdss" },
 	{ .compatible = "qcom,msm8998-mdss" },
@@ -585,7 +600,7 @@ static const struct of_device_id mdss_dt_match[] = {
 	{ .compatible = "qcom,sm8250-mdss", .data = &sm8250_data },
 	{ .compatible = "qcom,sm8350-mdss", .data = &sm8250_data },
 	{ .compatible = "qcom,sm8450-mdss", .data = &sm8250_data },
-	{ .compatible = "qcom,sm8550-mdss", .data = &sm8250_data },
+	{ .compatible = "qcom,sm8550-mdss", .data = &sm8550_data },
 	{}
 };
 MODULE_DEVICE_TABLE(of, mdss_dt_match);