Merge tag 'drm-msm-fixes-2021-10-11' of https://gitlab.freedesktop.org/drm/msm into drm-fixes

* Fix a new crash on dev file close if the dev file was opened when
  GPU is not loaded (such as missing fw in initrd)
* Switch to single drm_sched_entity per priority level per drm_file
  to unbreak multi-context userspace
* Serialize GMU access to fix GMU OOB errors
* Various error path fixes
* A couple integer overflow fixes
* Fix mdp5 cursor plane WARNs
Signed-off-by: Dave Airlie <airlied@redhat.com>
From:   Rob Clark <robdclark@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/CAF6AEGtD4u7yyiy+BQLmibUCbn=AdDRu7FrmdViHVx0QrcGf8g@mail.gmail.com

drivers/gpu/drm/msm/adreno/a3xx_gpu.c

@@ -571,13 +571,14 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev)
 	}
 
 	icc_path = devm_of_icc_get(&pdev->dev, "gfx-mem");
-	ret = IS_ERR(icc_path);
-	if (ret)
+	if (IS_ERR(icc_path)) {
+		ret = PTR_ERR(icc_path);
 		goto fail;
+	}
 
 	ocmem_icc_path = devm_of_icc_get(&pdev->dev, "ocmem");
-	ret = IS_ERR(ocmem_icc_path);
-	if (ret) {
+	if (IS_ERR(ocmem_icc_path)) {
+		ret = PTR_ERR(ocmem_icc_path);
 		/* allow -ENODATA, ocmem icc is optional */
 		if (ret != -ENODATA)
 			goto fail;

drivers/gpu/drm/msm/adreno/a4xx_gpu.c

@@ -699,13 +699,14 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev)
 	}
 
 	icc_path = devm_of_icc_get(&pdev->dev, "gfx-mem");
-	ret = IS_ERR(icc_path);
-	if (ret)
+	if (IS_ERR(icc_path)) {
+		ret = PTR_ERR(icc_path);
 		goto fail;
+	}
 
 	ocmem_icc_path = devm_of_icc_get(&pdev->dev, "ocmem");
-	ret = IS_ERR(ocmem_icc_path);
-	if (ret) {
+	if (IS_ERR(ocmem_icc_path)) {
+		ret = PTR_ERR(ocmem_icc_path);
 		/* allow -ENODATA, ocmem icc is optional */
 		if (ret != -ENODATA)
 			goto fail;

drivers/gpu/drm/msm/adreno/a6xx_gmu.c

@@ -296,6 +296,8 @@ int a6xx_gmu_set_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state)
 	u32 val;
 	int request, ack;
 
+	WARN_ON_ONCE(!mutex_is_locked(&gmu->lock));
+
 	if (state >= ARRAY_SIZE(a6xx_gmu_oob_bits))
 		return -EINVAL;
 
@@ -337,6 +339,8 @@ void a6xx_gmu_clear_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state)
 {
 	int bit;
 
+	WARN_ON_ONCE(!mutex_is_locked(&gmu->lock));
+
 	if (state >= ARRAY_SIZE(a6xx_gmu_oob_bits))
 		return;
 
@@ -1482,6 +1486,8 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node)
 	if (!pdev)
 		return -ENODEV;
 
+	mutex_init(&gmu->lock);
+
 	gmu->dev = &pdev->dev;
 
 	of_dma_configure(gmu->dev, node, true);

drivers/gpu/drm/msm/adreno/a6xx_gmu.h

@@ -44,6 +44,9 @@ struct a6xx_gmu_bo {
 struct a6xx_gmu {
 	struct device *dev;
 
+	/* For serializing communication with the GMU: */
+	struct mutex lock;
+
 	struct msm_gem_address_space *aspace;
 
 	void * __iomem mmio;

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

@@ -106,7 +106,7 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
 	u32 asid;
 	u64 memptr = rbmemptr(ring, ttbr0);
 
-	if (ctx == a6xx_gpu->cur_ctx)
+	if (ctx->seqno == a6xx_gpu->cur_ctx_seqno)
 		return;
 
 	if (msm_iommu_pagetable_params(ctx->aspace->mmu, &ttbr, &asid))
@@ -139,7 +139,7 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
 	OUT_PKT7(ring, CP_EVENT_WRITE, 1);
 	OUT_RING(ring, 0x31);
 
-	a6xx_gpu->cur_ctx = ctx;
+	a6xx_gpu->cur_ctx_seqno = ctx->seqno;
 }
 
 static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
@@ -881,7 +881,7 @@ static int a6xx_zap_shader_init(struct msm_gpu *gpu)
 	  A6XX_RBBM_INT_0_MASK_UCHE_OOB_ACCESS | \
 	  A6XX_RBBM_INT_0_MASK_UCHE_TRAP_INTR)
 
-static int a6xx_hw_init(struct msm_gpu *gpu)
+static int hw_init(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
@@ -1081,7 +1081,7 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	/* Always come up on rb 0 */
 	a6xx_gpu->cur_ring = gpu->rb[0];
 
-	a6xx_gpu->cur_ctx = NULL;
+	a6xx_gpu->cur_ctx_seqno = 0;
 
 	/* Enable the SQE_to start the CP engine */
 	gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 1);
@@ -1135,6 +1135,19 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 	return ret;
 }
 
+static int a6xx_hw_init(struct msm_gpu *gpu)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
+	int ret;
+
+	mutex_lock(&a6xx_gpu->gmu.lock);
+	ret = hw_init(gpu);
+	mutex_unlock(&a6xx_gpu->gmu.lock);
+
+	return ret;
+}
+
 static void a6xx_dump(struct msm_gpu *gpu)
 {
 	DRM_DEV_INFO(&gpu->pdev->dev, "status:   %08x\n",
@@ -1509,7 +1522,9 @@ static int a6xx_pm_resume(struct msm_gpu *gpu)
 
 	trace_msm_gpu_resume(0);
 
+	mutex_lock(&a6xx_gpu->gmu.lock);
 	ret = a6xx_gmu_resume(a6xx_gpu);
+	mutex_unlock(&a6xx_gpu->gmu.lock);
 	if (ret)
 		return ret;
 
@@ -1532,7 +1547,9 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu)
 
 	msm_devfreq_suspend(gpu);
 
+	mutex_lock(&a6xx_gpu->gmu.lock);
 	ret = a6xx_gmu_stop(a6xx_gpu);
+	mutex_unlock(&a6xx_gpu->gmu.lock);
 	if (ret)
 		return ret;
 
@@ -1547,18 +1564,19 @@ static int a6xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
-	static DEFINE_MUTEX(perfcounter_oob);
 
-	mutex_lock(&perfcounter_oob);
+	mutex_lock(&a6xx_gpu->gmu.lock);
 
 	/* Force the GPU power on so we can read this register */
 	a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET);
 
 	*value = gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO,
-		REG_A6XX_CP_ALWAYS_ON_COUNTER_HI);
+			    REG_A6XX_CP_ALWAYS_ON_COUNTER_HI);
 
 	a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET);
-	mutex_unlock(&perfcounter_oob);
+
+	mutex_unlock(&a6xx_gpu->gmu.lock);
+
 	return 0;
 }
 
@@ -1622,6 +1640,16 @@ static unsigned long a6xx_gpu_busy(struct msm_gpu *gpu)
 	return (unsigned long)busy_time;
 }
 
+void a6xx_gpu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
+
+	mutex_lock(&a6xx_gpu->gmu.lock);
+	a6xx_gmu_set_freq(gpu, opp);
+	mutex_unlock(&a6xx_gpu->gmu.lock);
+}
+
 static struct msm_gem_address_space *
 a6xx_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev)
 {
@@ -1766,7 +1794,7 @@ static const struct adreno_gpu_funcs funcs = {
 #endif
 		.gpu_busy = a6xx_gpu_busy,
 		.gpu_get_freq = a6xx_gmu_get_freq,
-		.gpu_set_freq = a6xx_gmu_set_freq,
+		.gpu_set_freq = a6xx_gpu_set_freq,
 #if defined(CONFIG_DRM_MSM_GPU_STATE)
 		.gpu_state_get = a6xx_gpu_state_get,
 		.gpu_state_put = a6xx_gpu_state_put,

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

@@ -19,7 +19,16 @@ struct a6xx_gpu {
 	uint64_t sqe_iova;
 
 	struct msm_ringbuffer *cur_ring;
-	struct msm_file_private *cur_ctx;
+
+	/**
+	 * cur_ctx_seqno:
+	 *
+	 * The ctx->seqno value of the context with current pgtables
+	 * installed.  Tracked by seqno rather than pointer value to
+	 * avoid dangling pointers, and cases where a ctx can be freed
+	 * and a new one created with the same address.
+	 */
+	int cur_ctx_seqno;
 
 	struct a6xx_gmu gmu;
 

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

@@ -794,7 +794,7 @@ static const struct dpu_pingpong_cfg sm8150_pp[] = {
 			DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30),
 			-1),
 	PP_BLK("pingpong_5", PINGPONG_5, 0x72800, MERGE_3D_2, sdm845_pp_sblk,
-			DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30),
+			DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31),
 			-1),
 };
 

drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c

@@ -1125,6 +1125,20 @@ static void mdp5_crtc_reset(struct drm_crtc *crtc)
 	__drm_atomic_helper_crtc_reset(crtc, &mdp5_cstate->base);
 }
 
+static const struct drm_crtc_funcs mdp5_crtc_no_lm_cursor_funcs = {
+	.set_config = drm_atomic_helper_set_config,
+	.destroy = mdp5_crtc_destroy,
+	.page_flip = drm_atomic_helper_page_flip,
+	.reset = mdp5_crtc_reset,
+	.atomic_duplicate_state = mdp5_crtc_duplicate_state,
+	.atomic_destroy_state = mdp5_crtc_destroy_state,
+	.atomic_print_state = mdp5_crtc_atomic_print_state,
+	.get_vblank_counter = mdp5_crtc_get_vblank_counter,
+	.enable_vblank  = msm_crtc_enable_vblank,
+	.disable_vblank = msm_crtc_disable_vblank,
+	.get_vblank_timestamp = drm_crtc_vblank_helper_get_vblank_timestamp,
+};
+
 static const struct drm_crtc_funcs mdp5_crtc_funcs = {
 	.set_config = drm_atomic_helper_set_config,
 	.destroy = mdp5_crtc_destroy,
@@ -1313,6 +1327,8 @@ struct drm_crtc *mdp5_crtc_init(struct drm_device *dev,
 	mdp5_crtc->lm_cursor_enabled = cursor_plane ? false : true;
 
 	drm_crtc_init_with_planes(dev, crtc, plane, cursor_plane,
+				  cursor_plane ?
+				  &mdp5_crtc_no_lm_cursor_funcs :
 				  &mdp5_crtc_funcs, NULL);
 
 	drm_flip_work_init(&mdp5_crtc->unref_cursor_work,

drivers/gpu/drm/msm/dp/dp_display.c

@@ -1309,14 +1309,14 @@ static int dp_pm_resume(struct device *dev)
 	 * can not declared display is connected unless
 	 * HDMI cable is plugged in and sink_count of
 	 * dongle become 1
+	 * also only signal audio when disconnected
 	 */
-	if (dp->link->sink_count)
+	if (dp->link->sink_count) {
 		dp->dp_display.is_connected = true;
-	else
+	} else {
 		dp->dp_display.is_connected = false;
-
-	dp_display_handle_plugged_change(g_dp_display,
-				dp->dp_display.is_connected);
+		dp_display_handle_plugged_change(g_dp_display, false);
+	}
 
 	DRM_DEBUG_DP("After, sink_count=%d is_connected=%d core_inited=%d power_on=%d\n",
 			dp->link->sink_count, dp->dp_display.is_connected,

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

@@ -215,8 +215,10 @@ int msm_dsi_modeset_init(struct msm_dsi *msm_dsi, struct drm_device *dev,
 		goto fail;
 	}
 
-	if (!msm_dsi_manager_validate_current_config(msm_dsi->id))
+	if (!msm_dsi_manager_validate_current_config(msm_dsi->id)) {
+		ret = -EINVAL;
 		goto fail;
+	}
 
 	msm_dsi->encoder = encoder;
 

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

@@ -451,7 +451,7 @@ static int dsi_bus_clk_enable(struct msm_dsi_host *msm_host)
 
 	return 0;
 err:
-	for (; i > 0; i--)
+	while (--i >= 0)
 		clk_disable_unprepare(msm_host->bus_clks[i]);
 
 	return ret;

drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c

@@ -110,14 +110,13 @@ static struct dsi_pll_14nm *pll_14nm_list[DSI_MAX];
 static bool pll_14nm_poll_for_ready(struct dsi_pll_14nm *pll_14nm,
 				    u32 nb_tries, u32 timeout_us)
 {
-	bool pll_locked = false;
+	bool pll_locked = false, pll_ready = false;
 	void __iomem *base = pll_14nm->phy->pll_base;
 	u32 tries, val;
 
 	tries = nb_tries;
 	while (tries--) {
-		val = dsi_phy_read(base +
-			       REG_DSI_14nm_PHY_PLL_RESET_SM_READY_STATUS);
+		val = dsi_phy_read(base + REG_DSI_14nm_PHY_PLL_RESET_SM_READY_STATUS);
 		pll_locked = !!(val & BIT(5));
 
 		if (pll_locked)
@@ -126,23 +125,24 @@ static bool pll_14nm_poll_for_ready(struct dsi_pll_14nm *pll_14nm,
 		udelay(timeout_us);
 	}
 
-	if (!pll_locked) {
-		tries = nb_tries;
-		while (tries--) {
-			val = dsi_phy_read(base +
-				REG_DSI_14nm_PHY_PLL_RESET_SM_READY_STATUS);
-			pll_locked = !!(val & BIT(0));
+	if (!pll_locked)
+		goto out;
 
-			if (pll_locked)
-				break;
+	tries = nb_tries;
+	while (tries--) {
+		val = dsi_phy_read(base + REG_DSI_14nm_PHY_PLL_RESET_SM_READY_STATUS);
+		pll_ready = !!(val & BIT(0));
 
-			udelay(timeout_us);
-		}
+		if (pll_ready)
+			break;
+
+		udelay(timeout_us);
 	}
 
-	DBG("DSI PLL is %slocked", pll_locked ? "" : "*not* ");
+out:
+	DBG("DSI PLL is %slocked, %sready", pll_locked ? "" : "*not* ", pll_ready ? "" : "*not* ");
 
-	return pll_locked;
+	return pll_locked && pll_ready;
 }
 
 static void dsi_pll_14nm_config_init(struct dsi_pll_config *pconf)

drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c

@@ -428,7 +428,7 @@ static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm, struct clk_hw **prov
 	bytediv->reg = pll_28nm->phy->pll_base + REG_DSI_28nm_8960_PHY_PLL_CTRL_9;
 
 	snprintf(parent_name, 32, "dsi%dvco_clk", pll_28nm->phy->id);
-	snprintf(clk_name, 32, "dsi%dpllbyte", pll_28nm->phy->id);
+	snprintf(clk_name, 32, "dsi%dpllbyte", pll_28nm->phy->id + 1);
 
 	bytediv_init.name = clk_name;
 	bytediv_init.ops = &clk_bytediv_ops;
@@ -442,7 +442,7 @@ static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm, struct clk_hw **prov
 		return ret;
 	provided_clocks[DSI_BYTE_PLL_CLK] = &bytediv->hw;
 
-	snprintf(clk_name, 32, "dsi%dpll", pll_28nm->phy->id);
+	snprintf(clk_name, 32, "dsi%dpll", pll_28nm->phy->id + 1);
 	/* DIV3 */
 	hw = devm_clk_hw_register_divider(dev, clk_name,
 				parent_name, 0, pll_28nm->phy->pll_base +

drivers/gpu/drm/msm/edp/edp_ctrl.c

@@ -1116,7 +1116,7 @@ void msm_edp_ctrl_power(struct edp_ctrl *ctrl, bool on)
 int msm_edp_ctrl_init(struct msm_edp *edp)
 {
 	struct edp_ctrl *ctrl = NULL;
-	struct device *dev = &edp->pdev->dev;
+	struct device *dev;
 	int ret;
 
 	if (!edp) {
@@ -1124,6 +1124,7 @@ int msm_edp_ctrl_init(struct msm_edp *edp)
 		return -EINVAL;
 	}
 
+	dev = &edp->pdev->dev;
 	ctrl = devm_kzalloc(dev, sizeof(*ctrl), GFP_KERNEL);
 	if (!ctrl)
 		return -ENOMEM;

drivers/gpu/drm/msm/msm_drv.c

@@ -630,10 +630,11 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv)
 	if (ret)
 		goto err_msm_uninit;
 
-	ret = msm_disp_snapshot_init(ddev);
-	if (ret)
-		DRM_DEV_ERROR(dev, "msm_disp_snapshot_init failed ret = %d\n", ret);
-
+	if (kms) {
+		ret = msm_disp_snapshot_init(ddev);
+		if (ret)
+			DRM_DEV_ERROR(dev, "msm_disp_snapshot_init failed ret = %d\n", ret);
+	}
 	drm_mode_config_reset(ddev);
 
 #ifdef CONFIG_DRM_FBDEV_EMULATION
@@ -682,6 +683,7 @@ static void load_gpu(struct drm_device *dev)
 
 static int context_init(struct drm_device *dev, struct drm_file *file)
 {
+	static atomic_t ident = ATOMIC_INIT(0);
 	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_file_private *ctx;
 
@@ -689,12 +691,17 @@ static int context_init(struct drm_device *dev, struct drm_file *file)
 	if (!ctx)
 		return -ENOMEM;
 
+	INIT_LIST_HEAD(&ctx->submitqueues);
+	rwlock_init(&ctx->queuelock);
+
 	kref_init(&ctx->ref);
 	msm_submitqueue_init(dev, ctx);
 
 	ctx->aspace = msm_gpu_create_private_address_space(priv->gpu, current);
 	file->driver_priv = ctx;
 
+	ctx->seqno = atomic_inc_return(&ident);
+
 	return 0;
 }
 

drivers/gpu/drm/msm/msm_drv.h

@@ -53,14 +53,6 @@ struct msm_disp_state;
 
 #define FRAC_16_16(mult, div)    (((mult) << 16) / (div))
 
-struct msm_file_private {
-	rwlock_t queuelock;
-	struct list_head submitqueues;
-	int queueid;
-	struct msm_gem_address_space *aspace;
-	struct kref ref;
-};
-
 enum msm_mdp_plane_property {
 	PLANE_PROP_ZPOS,
 	PLANE_PROP_ALPHA,
@@ -488,41 +480,6 @@ void msm_writel(u32 data, void __iomem *addr);
 u32 msm_readl(const void __iomem *addr);
 void msm_rmw(void __iomem *addr, u32 mask, u32 or);
 
-struct msm_gpu_submitqueue;
-int msm_submitqueue_init(struct drm_device *drm, struct msm_file_private *ctx);
-struct msm_gpu_submitqueue *msm_submitqueue_get(struct msm_file_private *ctx,
-		u32 id);
-int msm_submitqueue_create(struct drm_device *drm,
-		struct msm_file_private *ctx,
-		u32 prio, u32 flags, u32 *id);
-int msm_submitqueue_query(struct drm_device *drm, struct msm_file_private *ctx,
-		struct drm_msm_submitqueue_query *args);
-int msm_submitqueue_remove(struct msm_file_private *ctx, u32 id);
-void msm_submitqueue_close(struct msm_file_private *ctx);
-
-void msm_submitqueue_destroy(struct kref *kref);
-
-static inline void __msm_file_private_destroy(struct kref *kref)
-{
-	struct msm_file_private *ctx = container_of(kref,
-		struct msm_file_private, ref);
-
-	msm_gem_address_space_put(ctx->aspace);
-	kfree(ctx);
-}
-
-static inline void msm_file_private_put(struct msm_file_private *ctx)
-{
-	kref_put(&ctx->ref, __msm_file_private_destroy);
-}
-
-static inline struct msm_file_private *msm_file_private_get(
-	struct msm_file_private *ctx)
-{
-	kref_get(&ctx->ref);
-	return ctx;
-}
-
 #define DBG(fmt, ...) DRM_DEBUG_DRIVER(fmt"\n", ##__VA_ARGS__)
 #define VERB(fmt, ...) if (0) DRM_DEBUG_DRIVER(fmt"\n", ##__VA_ARGS__)
 
@@ -547,7 +504,7 @@ static inline int align_pitch(int width, int bpp)
 static inline unsigned long timeout_to_jiffies(const ktime_t *timeout)
 {
 	ktime_t now = ktime_get();
-	unsigned long remaining_jiffies;
+	s64 remaining_jiffies;
 
 	if (ktime_compare(*timeout, now) < 0) {
 		remaining_jiffies = 0;
@@ -556,7 +513,7 @@ static inline unsigned long timeout_to_jiffies(const ktime_t *timeout)
 		remaining_jiffies = ktime_divns(rem, NSEC_PER_SEC / HZ);
 	}
 
-	return remaining_jiffies;
+	return clamp(remaining_jiffies, 0LL, (s64)INT_MAX);
 }
 
 #endif /* __MSM_DRV_H__ */

drivers/gpu/drm/msm/msm_gem_submit.c

@@ -46,7 +46,7 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev,
 	if (!submit)
 		return ERR_PTR(-ENOMEM);
 
-	ret = drm_sched_job_init(&submit->base, &queue->entity, queue);
+	ret = drm_sched_job_init(&submit->base, queue->entity, queue);
 	if (ret) {
 		kfree(submit);
 		return ERR_PTR(ret);
@@ -171,7 +171,8 @@ static int submit_lookup_objects(struct msm_gem_submit *submit,
 static int submit_lookup_cmds(struct msm_gem_submit *submit,
 		struct drm_msm_gem_submit *args, struct drm_file *file)
 {
-	unsigned i, sz;
+	unsigned i;
+	size_t sz;
 	int ret = 0;
 
 	for (i = 0; i < args->nr_cmds; i++) {
@@ -907,7 +908,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	/* The scheduler owns a ref now: */
 	msm_gem_submit_get(submit);
 
-	drm_sched_entity_push_job(&submit->base, &queue->entity);
+	drm_sched_entity_push_job(&submit->base, queue->entity);
 
 	args->fence = submit->fence_id;
 

drivers/gpu/drm/msm/msm_gpu.h

@@ -257,6 +257,39 @@ struct msm_gpu_perfcntr {
  */
 #define NR_SCHED_PRIORITIES (1 + DRM_SCHED_PRIORITY_HIGH - DRM_SCHED_PRIORITY_MIN)
 
+/**
+ * struct msm_file_private - per-drm_file context
+ *
+ * @queuelock:    synchronizes access to submitqueues list
+ * @submitqueues: list of &msm_gpu_submitqueue created by userspace
+ * @queueid:      counter incremented each time a submitqueue is created,
+ *                used to assign &msm_gpu_submitqueue.id
+ * @aspace:       the per-process GPU address-space
+ * @ref:          reference count
+ * @seqno:        unique per process seqno
+ */
+struct msm_file_private {
+	rwlock_t queuelock;
+	struct list_head submitqueues;
+	int queueid;
+	struct msm_gem_address_space *aspace;
+	struct kref ref;
+	int seqno;
+
+	/**
+	 * entities:
+	 *
+	 * Table of per-priority-level sched entities used by submitqueues
+	 * associated with this &drm_file.  Because some userspace apps
+	 * make assumptions about rendering from multiple gl contexts
+	 * (of the same priority) within the process happening in FIFO
+	 * order without requiring any fencing beyond MakeCurrent(), we
+	 * create at most one &drm_sched_entity per-process per-priority-
+	 * level.
+	 */
+	struct drm_sched_entity *entities[NR_SCHED_PRIORITIES * MSM_GPU_MAX_RINGS];
+};
+
 /**
  * msm_gpu_convert_priority - Map userspace priority to ring # and sched priority
  *
@@ -304,6 +337,8 @@ static inline int msm_gpu_convert_priority(struct msm_gpu *gpu, int prio,
 }
 
 /**
+ * struct msm_gpu_submitqueues - Userspace created context.
+ *
  * A submitqueue is associated with a gl context or vk queue (or equiv)
  * in userspace.
  *
@@ -321,7 +356,7 @@ static inline int msm_gpu_convert_priority(struct msm_gpu *gpu, int prio,
  *             seqno, protected by submitqueue lock
  * @lock:      submitqueue lock
  * @ref:       reference count
- * @entity: the submit job-queue
+ * @entity:    the submit job-queue
  */
 struct msm_gpu_submitqueue {
 	int id;
@@ -333,7 +368,7 @@ struct msm_gpu_submitqueue {
 	struct idr fence_idr;
 	struct mutex lock;
 	struct kref ref;
-	struct drm_sched_entity entity;
+	struct drm_sched_entity *entity;
 };
 
 struct msm_gpu_state_bo {
@@ -421,6 +456,33 @@ static inline void gpu_write64(struct msm_gpu *gpu, u32 lo, u32 hi, u64 val)
 int msm_gpu_pm_suspend(struct msm_gpu *gpu);
 int msm_gpu_pm_resume(struct msm_gpu *gpu);
 
+int msm_submitqueue_init(struct drm_device *drm, struct msm_file_private *ctx);
+struct msm_gpu_submitqueue *msm_submitqueue_get(struct msm_file_private *ctx,
+		u32 id);
+int msm_submitqueue_create(struct drm_device *drm,
+		struct msm_file_private *ctx,
+		u32 prio, u32 flags, u32 *id);
+int msm_submitqueue_query(struct drm_device *drm, struct msm_file_private *ctx,
+		struct drm_msm_submitqueue_query *args);
+int msm_submitqueue_remove(struct msm_file_private *ctx, u32 id);
+void msm_submitqueue_close(struct msm_file_private *ctx);
+
+void msm_submitqueue_destroy(struct kref *kref);
+
+void __msm_file_private_destroy(struct kref *kref);
+
+static inline void msm_file_private_put(struct msm_file_private *ctx)
+{
+	kref_put(&ctx->ref, __msm_file_private_destroy);
+}
+
+static inline struct msm_file_private *msm_file_private_get(
+	struct msm_file_private *ctx)
+{
+	kref_get(&ctx->ref);
+	return ctx;
+}
+
 void msm_devfreq_init(struct msm_gpu *gpu);
 void msm_devfreq_cleanup(struct msm_gpu *gpu);
 void msm_devfreq_resume(struct msm_gpu *gpu);

drivers/gpu/drm/msm/msm_gpu_devfreq.c

@@ -151,6 +151,9 @@ void msm_devfreq_active(struct msm_gpu *gpu)
 	unsigned int idle_time;
 	unsigned long target_freq = df->idle_freq;
 
+	if (!df->devfreq)
+		return;
+
 	/*
 	 * Hold devfreq lock to synchronize with get_dev_status()/
 	 * target() callbacks
@@ -186,6 +189,9 @@ void msm_devfreq_idle(struct msm_gpu *gpu)
 	struct msm_gpu_devfreq *df = &gpu->devfreq;
 	unsigned long idle_freq, target_freq = 0;
 
+	if (!df->devfreq)
+		return;
+
 	/*
 	 * Hold devfreq lock to synchronize with get_dev_status()/
 	 * target() callbacks

drivers/gpu/drm/msm/msm_submitqueue.c

@@ -7,6 +7,24 @@
 
 #include "msm_gpu.h"
 
+void __msm_file_private_destroy(struct kref *kref)
+{
+	struct msm_file_private *ctx = container_of(kref,
+		struct msm_file_private, ref);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(ctx->entities); i++) {
+		if (!ctx->entities[i])
+			continue;
+
+		drm_sched_entity_destroy(ctx->entities[i]);
+		kfree(ctx->entities[i]);
+	}
+
+	msm_gem_address_space_put(ctx->aspace);
+	kfree(ctx);
+}
+
 void msm_submitqueue_destroy(struct kref *kref)
 {
 	struct msm_gpu_submitqueue *queue = container_of(kref,
@@ -14,8 +32,6 @@ void msm_submitqueue_destroy(struct kref *kref)
 
 	idr_destroy(&queue->fence_idr);
 
-	drm_sched_entity_destroy(&queue->entity);
-
 	msm_file_private_put(queue->ctx);
 
 	kfree(queue);
@@ -61,13 +77,47 @@ void msm_submitqueue_close(struct msm_file_private *ctx)
 	}
 }
 
+static struct drm_sched_entity *
+get_sched_entity(struct msm_file_private *ctx, struct msm_ringbuffer *ring,
+		 unsigned ring_nr, enum drm_sched_priority sched_prio)
+{
+	static DEFINE_MUTEX(entity_lock);
+	unsigned idx = (ring_nr * NR_SCHED_PRIORITIES) + sched_prio;
+
+	/* We should have already validated that the requested priority is
+	 * valid by the time we get here.
+	 */
+	if (WARN_ON(idx >= ARRAY_SIZE(ctx->entities)))
+		return ERR_PTR(-EINVAL);
+
+	mutex_lock(&entity_lock);
+
+	if (!ctx->entities[idx]) {
+		struct drm_sched_entity *entity;
+		struct drm_gpu_scheduler *sched = &ring->sched;
+		int ret;
+
+		entity = kzalloc(sizeof(*ctx->entities[idx]), GFP_KERNEL);
+
+		ret = drm_sched_entity_init(entity, sched_prio, &sched, 1, NULL);
+		if (ret) {
+			kfree(entity);
+			return ERR_PTR(ret);
+		}
+
+		ctx->entities[idx] = entity;
+	}
+
+	mutex_unlock(&entity_lock);
+
+	return ctx->entities[idx];
+}
+
 int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
 		u32 prio, u32 flags, u32 *id)
 {
 	struct msm_drm_private *priv = drm->dev_private;
 	struct msm_gpu_submitqueue *queue;
-	struct msm_ringbuffer *ring;
-	struct drm_gpu_scheduler *sched;
 	enum drm_sched_priority sched_prio;
 	unsigned ring_nr;
 	int ret;
@@ -91,12 +141,10 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx,
 	queue->flags = flags;
 	queue->ring_nr = ring_nr;
 
-	ring = priv->gpu->rb[ring_nr];
-	sched = &ring->sched;
-
-	ret = drm_sched_entity_init(&queue->entity,
-			sched_prio, &sched, 1, NULL);
-	if (ret) {
+	queue->entity = get_sched_entity(ctx, priv->gpu->rb[ring_nr],
+					 ring_nr, sched_prio);
+	if (IS_ERR(queue->entity)) {
+		ret = PTR_ERR(queue->entity);
 		kfree(queue);
 		return ret;
 	}
@@ -140,10 +188,6 @@ int msm_submitqueue_init(struct drm_device *drm, struct msm_file_private *ctx)
 	 */
 	default_prio = DIV_ROUND_UP(max_priority, 2);
 
-	INIT_LIST_HEAD(&ctx->submitqueues);
-
-	rwlock_init(&ctx->queuelock);
-
 	return msm_submitqueue_create(drm, ctx, default_prio, 0, NULL);
 }