Merge tag 'drm-fixes-2021-04-02' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Things have settled down in time for Easter, a random smattering of
  small fixes across a few drivers.

  I'm guessing though there might be some i915 and misc fixes out there
  I haven't gotten yet, but since today is a public holiday here, I'm
  sending this early so I can have the day off, I'll see if more
  requests come in and decide what to do with them later.

  amdgpu:
   - Polaris idle power fix
   - VM fix
   - Vangogh S3 fix
   - Fixes for non-4K page sizes

  amdkfd:
   - dqm fence memory corruption fix

  tegra:
   - lockdep warning fix
   - runtine PM reference fix
   - display controller fix
   - PLL Fix

  imx:
   - memory leak in error path fix
   - LDB driver channel registration fix
   - oob array warning in LDB driver

  exynos
   - unused header file removal"

* tag 'drm-fixes-2021-04-02' of git://anongit.freedesktop.org/drm/drm:
  drm/amdgpu: check alignment on CPU page for bo map
  drm/amdgpu: Set a suitable dev_info.gart_page_size
  drm/amdgpu/vangogh: don't check for dpm in is_dpm_running when in suspend
  drm/amdkfd: dqm fence memory corruption
  drm/tegra: sor: Grab runtime PM reference across reset
  drm/tegra: dc: Restore coupling of display controllers
  gpu: host1x: Use different lock classes for each client
  drm/tegra: dc: Don't set PLL clock to 0Hz
  drm/amdgpu: fix offset calculation in amdgpu_vm_bo_clear_mappings()
  drm/amd/pm: no need to force MCLK to highest when no display connected
  drm/exynos/decon5433: Remove the unused include statements
  drm/imx: imx-ldb: fix out of bounds array access warning
  drm/imx: imx-ldb: Register LDB channel1 when it is the only channel to be used
  drm/imx: fix memory leak when fails to init

drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c

@@ -778,9 +778,9 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 			dev_info->high_va_offset = AMDGPU_GMC_HOLE_END;
 			dev_info->high_va_max = AMDGPU_GMC_HOLE_END | vm_size;
 		}
-		dev_info->virtual_address_alignment = max((int)PAGE_SIZE, AMDGPU_GPU_PAGE_SIZE);
+		dev_info->virtual_address_alignment = max_t(u32, PAGE_SIZE, AMDGPU_GPU_PAGE_SIZE);
 		dev_info->pte_fragment_size = (1 << adev->vm_manager.fragment_size) * AMDGPU_GPU_PAGE_SIZE;
-		dev_info->gart_page_size = AMDGPU_GPU_PAGE_SIZE;
+		dev_info->gart_page_size = max_t(u32, PAGE_SIZE, AMDGPU_GPU_PAGE_SIZE);
 		dev_info->cu_active_number = adev->gfx.cu_info.number;
 		dev_info->cu_ao_mask = adev->gfx.cu_info.ao_cu_mask;
 		dev_info->ce_ram_size = adev->gfx.ce_ram_size;

drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c

@@ -2197,8 +2197,8 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
 	uint64_t eaddr;
 
 	/* validate the parameters */
-	if (saddr & AMDGPU_GPU_PAGE_MASK || offset & AMDGPU_GPU_PAGE_MASK ||
-	    size == 0 || size & AMDGPU_GPU_PAGE_MASK)
+	if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK ||
+	    size == 0 || size & ~PAGE_MASK)
 		return -EINVAL;
 
 	/* make sure object fit at this offset */
@@ -2263,8 +2263,8 @@ int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev,
 	int r;
 
 	/* validate the parameters */
-	if (saddr & AMDGPU_GPU_PAGE_MASK || offset & AMDGPU_GPU_PAGE_MASK ||
-	    size == 0 || size & AMDGPU_GPU_PAGE_MASK)
+	if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK ||
+	    size == 0 || size & ~PAGE_MASK)
 		return -EINVAL;
 
 	/* make sure object fit at this offset */
@@ -2409,7 +2409,7 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev,
 			after->start = eaddr + 1;
 			after->last = tmp->last;
 			after->offset = tmp->offset;
-			after->offset += after->start - tmp->start;
+			after->offset += (after->start - tmp->start) << PAGE_SHIFT;
 			after->flags = tmp->flags;
 			after->bo_va = tmp->bo_va;
 			list_add(&after->list, &tmp->bo_va->invalids);

drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c

@@ -155,7 +155,7 @@ static int dbgdev_diq_submit_ib(struct kfd_dbgdev *dbgdev,
 
 	/* Wait till CP writes sync code: */
 	status = amdkfd_fence_wait_timeout(
-			(unsigned int *) rm_state,
+			rm_state,
 			QUEUESTATE__ACTIVE, 1500);
 
 	kfd_gtt_sa_free(dbgdev->dev, mem_obj);

drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c

@@ -1167,7 +1167,7 @@ static int start_cpsch(struct device_queue_manager *dqm)
 	if (retval)
 		goto fail_allocate_vidmem;
 
-	dqm->fence_addr = dqm->fence_mem->cpu_ptr;
+	dqm->fence_addr = (uint64_t *)dqm->fence_mem->cpu_ptr;
 	dqm->fence_gpu_addr = dqm->fence_mem->gpu_addr;
 
 	init_interrupts(dqm);
@@ -1340,8 +1340,8 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 	return retval;
 }
 
-int amdkfd_fence_wait_timeout(unsigned int *fence_addr,
-				unsigned int fence_value,
+int amdkfd_fence_wait_timeout(uint64_t *fence_addr,
+				uint64_t fence_value,
 				unsigned int timeout_ms)
 {
 	unsigned long end_jiffies = msecs_to_jiffies(timeout_ms) + jiffies;

drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h

@@ -192,7 +192,7 @@ struct device_queue_manager {
 	uint16_t		vmid_pasid[VMID_NUM];
 	uint64_t		pipelines_addr;
 	uint64_t		fence_gpu_addr;
-	unsigned int		*fence_addr;
+	uint64_t		*fence_addr;
 	struct kfd_mem_obj	*fence_mem;
 	bool			active_runlist;
 	int			sched_policy;

drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c

@@ -347,7 +347,7 @@ int pm_send_runlist(struct packet_manager *pm, struct list_head *dqm_queues)
 }
 
 int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address,
-			uint32_t fence_value)
+			uint64_t fence_value)
 {
 	uint32_t *buffer, size;
 	int retval = 0;

drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c

@@ -283,7 +283,7 @@ static int pm_unmap_queues_v9(struct packet_manager *pm, uint32_t *buffer,
 }
 
 static int pm_query_status_v9(struct packet_manager *pm, uint32_t *buffer,
-			uint64_t fence_address,	uint32_t fence_value)
+			uint64_t fence_address,	uint64_t fence_value)
 {
 	struct pm4_mes_query_status *packet;
 

drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_vi.c

@@ -263,7 +263,7 @@ static int pm_unmap_queues_vi(struct packet_manager *pm, uint32_t *buffer,
 }
 
 static int pm_query_status_vi(struct packet_manager *pm, uint32_t *buffer,
-			uint64_t fence_address,	uint32_t fence_value)
+			uint64_t fence_address,	uint64_t fence_value)
 {
 	struct pm4_mes_query_status *packet;
 

drivers/gpu/drm/amd/amdkfd/kfd_priv.h

@@ -1003,8 +1003,8 @@ int pqm_get_wave_state(struct process_queue_manager *pqm,
 		       u32 *ctl_stack_used_size,
 		       u32 *save_area_used_size);
 
-int amdkfd_fence_wait_timeout(unsigned int *fence_addr,
-			      unsigned int fence_value,
+int amdkfd_fence_wait_timeout(uint64_t *fence_addr,
+			      uint64_t fence_value,
 			      unsigned int timeout_ms);
 
 /* Packet Manager */
@@ -1040,7 +1040,7 @@ struct packet_manager_funcs {
 			uint32_t filter_param, bool reset,
 			unsigned int sdma_engine);
 	int (*query_status)(struct packet_manager *pm, uint32_t *buffer,
-			uint64_t fence_address,	uint32_t fence_value);
+			uint64_t fence_address,	uint64_t fence_value);
 	int (*release_mem)(uint64_t gpu_addr, uint32_t *buffer);
 
 	/* Packet sizes */
@@ -1062,7 +1062,7 @@ int pm_send_set_resources(struct packet_manager *pm,
 				struct scheduling_resources *res);
 int pm_send_runlist(struct packet_manager *pm, struct list_head *dqm_queues);
 int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address,
-				uint32_t fence_value);
+				uint64_t fence_value);
 
 int pm_send_unmap_queue(struct packet_manager *pm, enum kfd_queue_type type,
 			enum kfd_unmap_queues_filter mode,

drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c

@@ -3330,7 +3330,8 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 
 	disable_mclk_switching_for_display = ((1 < hwmgr->display_config->num_display) &&
 						!hwmgr->display_config->multi_monitor_in_sync) ||
-						smu7_vblank_too_short(hwmgr, hwmgr->display_config->min_vblank_time);
+						(hwmgr->display_config->num_display &&
+						smu7_vblank_too_short(hwmgr, hwmgr->display_config->min_vblank_time));
 
 	disable_mclk_switching = disable_mclk_switching_for_frame_lock ||
 					 disable_mclk_switching_for_display;

drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c

@@ -384,10 +384,15 @@ static int vangogh_dpm_set_jpeg_enable(struct smu_context *smu, bool enable)
 
 static bool vangogh_is_dpm_running(struct smu_context *smu)
 {
+	struct amdgpu_device *adev = smu->adev;
 	int ret = 0;
 	uint32_t feature_mask[2];
 	uint64_t feature_enabled;
 
+	/* we need to re-init after suspend so return false */
+	if (adev->in_suspend)
+		return false;
+
 	ret = smu_cmn_get_enabled_32_bits_mask(smu, feature_mask, 2);
 
 	if (ret)

drivers/gpu/drm/exynos/exynos5433_drm_decon.c

@@ -13,7 +13,6 @@
 #include <linux/irq.h>
 #include <linux/mfd/syscon.h>
 #include <linux/of_device.h>
-#include <linux/of_gpio.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/regmap.h>

drivers/gpu/drm/imx/imx-drm-core.c

@@ -215,7 +215,7 @@ static int imx_drm_bind(struct device *dev)
 
 	ret = drmm_mode_config_init(drm);
 	if (ret)
-		return ret;
+		goto err_kms;
 
 	ret = drm_vblank_init(drm, MAX_CRTC);
 	if (ret)

drivers/gpu/drm/imx/imx-ldb.c

@@ -197,6 +197,11 @@ static void imx_ldb_encoder_enable(struct drm_encoder *encoder)
 	int dual = ldb->ldb_ctrl & LDB_SPLIT_MODE_EN;
 	int mux = drm_of_encoder_active_port_id(imx_ldb_ch->child, encoder);
 
+	if (mux < 0 || mux >= ARRAY_SIZE(ldb->clk_sel)) {
+		dev_warn(ldb->dev, "%s: invalid mux %d\n", __func__, mux);
+		return;
+	}
+
 	drm_panel_prepare(imx_ldb_ch->panel);
 
 	if (dual) {
@@ -255,6 +260,11 @@ imx_ldb_encoder_atomic_mode_set(struct drm_encoder *encoder,
 	int mux = drm_of_encoder_active_port_id(imx_ldb_ch->child, encoder);
 	u32 bus_format = imx_ldb_ch->bus_format;
 
+	if (mux < 0 || mux >= ARRAY_SIZE(ldb->clk_sel)) {
+		dev_warn(ldb->dev, "%s: invalid mux %d\n", __func__, mux);
+		return;
+	}
+
 	if (mode->clock > 170000) {
 		dev_warn(ldb->dev,
 			 "%s: mode exceeds 170 MHz pixel clock\n", __func__);
@@ -583,7 +593,7 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data)
 		struct imx_ldb_channel *channel = &imx_ldb->channel[i];
 
 		if (!channel->ldb)
-			break;
+			continue;
 
 		ret = imx_ldb_register(drm, channel);
 		if (ret)

drivers/gpu/drm/tegra/dc.c

@@ -1688,6 +1688,11 @@ static void tegra_dc_commit_state(struct tegra_dc *dc,
 			dev_err(dc->dev,
 				"failed to set clock rate to %lu Hz\n",
 				state->pclk);
+
+		err = clk_set_rate(dc->clk, state->pclk);
+		if (err < 0)
+			dev_err(dc->dev, "failed to set clock %pC to %lu Hz: %d\n",
+				dc->clk, state->pclk, err);
 	}
 
 	DRM_DEBUG_KMS("rate: %lu, div: %u\n", clk_get_rate(dc->clk),
@@ -1698,11 +1703,6 @@ static void tegra_dc_commit_state(struct tegra_dc *dc,
 		value = SHIFT_CLK_DIVIDER(state->div) | PIXEL_CLK_DIVIDER_PCD1;
 		tegra_dc_writel(dc, value, DC_DISP_DISP_CLOCK_CONTROL);
 	}
-
-	err = clk_set_rate(dc->clk, state->pclk);
-	if (err < 0)
-		dev_err(dc->dev, "failed to set clock %pC to %lu Hz: %d\n",
-			dc->clk, state->pclk, err);
 }
 
 static void tegra_dc_stop(struct tegra_dc *dc)
@@ -2501,22 +2501,18 @@ static int tegra_dc_couple(struct tegra_dc *dc)
 	 * POWER_CONTROL registers during CRTC enabling.
 	 */
 	if (dc->soc->coupled_pm && dc->pipe == 1) {
-		u32 flags = DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE_CONSUMER;
-		struct device_link *link;
-		struct device *partner;
+		struct device *companion;
+		struct tegra_dc *parent;
 
-		partner = driver_find_device(dc->dev->driver, NULL, NULL,
-					     tegra_dc_match_by_pipe);
-		if (!partner)
+		companion = driver_find_device(dc->dev->driver, NULL, (const void *)0,
+					       tegra_dc_match_by_pipe);
+		if (!companion)
 			return -EPROBE_DEFER;
 
-		link = device_link_add(dc->dev, partner, flags);
-		if (!link) {
-			dev_err(dc->dev, "failed to link controllers\n");
-			return -EINVAL;
-		}
+		parent = dev_get_drvdata(companion);
+		dc->client.parent = &parent->client;
 
-		dev_dbg(dc->dev, "coupled to %s\n", dev_name(partner));
+		dev_dbg(dc->dev, "coupled to %s\n", dev_name(companion));
 	}
 
 	return 0;

drivers/gpu/drm/tegra/sor.c

@@ -3115,6 +3115,12 @@ static int tegra_sor_init(struct host1x_client *client)
 	 * kernel is possible.
 	 */
 	if (sor->rst) {
+		err = pm_runtime_resume_and_get(sor->dev);
+		if (err < 0) {
+			dev_err(sor->dev, "failed to get runtime PM: %d\n", err);
+			return err;
+		}
+
 		err = reset_control_acquire(sor->rst);
 		if (err < 0) {
 			dev_err(sor->dev, "failed to acquire SOR reset: %d\n",
@@ -3148,6 +3154,7 @@ static int tegra_sor_init(struct host1x_client *client)
 		}
 
 		reset_control_release(sor->rst);
+		pm_runtime_put(sor->dev);
 	}
 
 	err = clk_prepare_enable(sor->clk_safe);

drivers/gpu/host1x/bus.c

@@ -705,8 +705,9 @@ void host1x_driver_unregister(struct host1x_driver *driver)
 EXPORT_SYMBOL(host1x_driver_unregister);
 
 /**
- * host1x_client_register() - register a host1x client
+ * __host1x_client_register() - register a host1x client
  * @client: host1x client
+ * @key: lock class key for the client-specific mutex
  *
  * Registers a host1x client with each host1x controller instance. Note that
  * each client will only match their parent host1x controller and will only be
@@ -715,13 +716,14 @@ EXPORT_SYMBOL(host1x_driver_unregister);
  * device and call host1x_device_init(), which will in turn call each client's
  * &host1x_client_ops.init implementation.
  */
-int host1x_client_register(struct host1x_client *client)
+int __host1x_client_register(struct host1x_client *client,
+			     struct lock_class_key *key)
 {
 	struct host1x *host1x;
 	int err;
 
 	INIT_LIST_HEAD(&client->list);
-	mutex_init(&client->lock);
+	__mutex_init(&client->lock, "host1x client lock", key);
 	client->usecount = 0;
 
 	mutex_lock(&devices_lock);
@@ -742,7 +744,7 @@ int host1x_client_register(struct host1x_client *client)
 
 	return 0;
 }
-EXPORT_SYMBOL(host1x_client_register);
+EXPORT_SYMBOL(__host1x_client_register);
 
 /**
  * host1x_client_unregister() - unregister a host1x client

include/linux/host1x.h

@@ -320,7 +320,14 @@ static inline struct host1x_device *to_host1x_device(struct device *dev)
 int host1x_device_init(struct host1x_device *device);
 int host1x_device_exit(struct host1x_device *device);
 
-int host1x_client_register(struct host1x_client *client);
+int __host1x_client_register(struct host1x_client *client,
+			     struct lock_class_key *key);
+#define host1x_client_register(class) \
+	({ \
+		static struct lock_class_key __key; \
+		__host1x_client_register(class, &__key); \
+	})
+
 int host1x_client_unregister(struct host1x_client *client);
 
 int host1x_client_suspend(struct host1x_client *client);