Merge tag 'drm/tegra/for-6.3-rc1' of https://gitlab.freedesktop.org/d…

…rm/tegra into drm-next

drm/tegra: Changes for v6.3-rc1

This set of changes includes a rework of the custom syncpoint interrupt
code to take better advantage of existing DRM/KMS infrastructure.

There's also various bits of cleanup and fixes included.

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Thierry Reding <thierry.reding@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230127170119.495943-1-thierry.reding@gmail.com

MAINTAINERS

@@ -7040,7 +7040,7 @@ M:	Thierry Reding <thierry.reding@gmail.com>
 L:	dri-devel@lists.freedesktop.org
 L:	linux-tegra@vger.kernel.org
 S:	Supported
-T:	git git://anongit.freedesktop.org/tegra/linux.git
+T:	git https://gitlab.freedesktop.org/drm/tegra.git
 F:	Documentation/devicetree/bindings/display/tegra/nvidia,tegra20-host1x.yaml
 F:	Documentation/devicetree/bindings/gpu/host1x/
 F:	drivers/gpu/drm/tegra/

drivers/gpu/drm/tegra/dpaux.c

@@ -598,7 +598,6 @@ static int tegra_dpaux_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM
 static int tegra_dpaux_suspend(struct device *dev)
 {
 	struct tegra_dpaux *dpaux = dev_get_drvdata(dev);
@@ -657,10 +656,9 @@ static int tegra_dpaux_resume(struct device *dev)
 	clk_disable_unprepare(dpaux->clk);
 	return err;
 }
-#endif
 
 static const struct dev_pm_ops tegra_dpaux_pm_ops = {
-	SET_RUNTIME_PM_OPS(tegra_dpaux_suspend, tegra_dpaux_resume, NULL)
+	RUNTIME_PM_OPS(tegra_dpaux_suspend, tegra_dpaux_resume, NULL)
 };
 
 static const struct tegra_dpaux_soc tegra124_dpaux_soc = {
@@ -694,7 +692,7 @@ struct platform_driver tegra_dpaux_driver = {
 	.driver = {
 		.name = "tegra-dpaux",
 		.of_match_table = tegra_dpaux_of_match,
-		.pm = &tegra_dpaux_pm_ops,
+		.pm = pm_ptr(&tegra_dpaux_pm_ops),
 	},
 	.probe = tegra_dpaux_probe,
 	.remove = tegra_dpaux_remove,

drivers/gpu/drm/tegra/firewall.c

@@ -97,6 +97,9 @@ static int fw_check_regs_imm(struct tegra_drm_firewall *fw, u32 offset)
 {
 	bool is_addr;
 
+	if (!fw->client->ops->is_addr_reg)
+		return 0;
+
 	is_addr = fw->client->ops->is_addr_reg(fw->client->base.dev, fw->class,
 					       offset);
 	if (is_addr)

drivers/gpu/drm/tegra/nvdec.c

@@ -67,26 +67,18 @@ static inline void nvdec_writel(struct nvdec *nvdec, u32 value,
 
 static int nvdec_boot_falcon(struct nvdec *nvdec)
 {
-#ifdef CONFIG_IOMMU_API
-	struct iommu_fwspec *spec = dev_iommu_fwspec_get(nvdec->dev);
-#endif
+	u32 stream_id;
 	int err;
 
-#ifdef CONFIG_IOMMU_API
-	if (nvdec->config->supports_sid && spec) {
+	if (nvdec->config->supports_sid && tegra_dev_iommu_get_stream_id(nvdec->dev, &stream_id)) {
 		u32 value;
 
 		value = TRANSCFG_ATT(1, TRANSCFG_SID_FALCON) | TRANSCFG_ATT(0, TRANSCFG_SID_HW);
 		nvdec_writel(nvdec, value, NVDEC_TFBIF_TRANSCFG);
 
-		if (spec->num_ids > 0) {
-			value = spec->ids[0] & 0xffff;
-
-			nvdec_writel(nvdec, value, VIC_THI_STREAMID0);
-			nvdec_writel(nvdec, value, VIC_THI_STREAMID1);
-		}
+		nvdec_writel(nvdec, stream_id, VIC_THI_STREAMID0);
+		nvdec_writel(nvdec, stream_id, VIC_THI_STREAMID1);
 	}
-#endif
 
 	err = falcon_boot(&nvdec->falcon);
 	if (err < 0)

drivers/gpu/drm/tegra/submit.c

@@ -609,21 +609,13 @@ int tegra_drm_ioctl_channel_submit(struct drm_device *drm, void *data,
 			host1x_memory_context_get(job->memory_context);
 		}
 	} else if (context->client->ops->get_streamid_offset) {
-#ifdef CONFIG_IOMMU_API
-		struct iommu_fwspec *spec;
-
 		/*
 		 * Job submission will need to temporarily change stream ID,
 		 * so need to tell it what to change it back to.
 		 */
-		spec = dev_iommu_fwspec_get(context->client->base.dev);
-		if (spec && spec->num_ids > 0)
-			job->engine_fallback_streamid = spec->ids[0] & 0xffff;
-		else
-			job->engine_fallback_streamid = 0x7f;
-#else
-		job->engine_fallback_streamid = 0x7f;
-#endif
+		if (!tegra_dev_iommu_get_stream_id(context->client->base.dev,
+						   &job->engine_fallback_streamid))
+			job->engine_fallback_streamid = TEGRA_STREAM_ID_BYPASS;
 	}
 
 	/* Boot engine. */
@@ -654,7 +646,7 @@ int tegra_drm_ioctl_channel_submit(struct drm_device *drm, void *data,
 	args->syncpt.value = job->syncpt_end;
 
 	if (syncobj) {
-		struct dma_fence *fence = host1x_fence_create(job->syncpt, job->syncpt_end);
+		struct dma_fence *fence = host1x_fence_create(job->syncpt, job->syncpt_end, true);
 		if (IS_ERR(fence)) {
 			err = PTR_ERR(fence);
 			SUBMIT_ERR(context, "failed to create postfence: %d", err);
@@ -680,8 +672,7 @@ int tegra_drm_ioctl_channel_submit(struct drm_device *drm, void *data,
 		kfree(job_data->used_mappings);
 	}
 
-	if (job_data)
-		kfree(job_data);
+	kfree(job_data);
 put_bo:
 	gather_bo_put(&bo->base);
 unlock:

drivers/gpu/drm/tegra/vic.c

@@ -56,41 +56,30 @@ static void vic_writel(struct vic *vic, u32 value, unsigned int offset)
 
 static int vic_boot(struct vic *vic)
 {
-#ifdef CONFIG_IOMMU_API
-	struct iommu_fwspec *spec = dev_iommu_fwspec_get(vic->dev);
-#endif
-	u32 fce_ucode_size, fce_bin_data_offset;
+	u32 fce_ucode_size, fce_bin_data_offset, stream_id;
 	void *hdr;
 	int err = 0;
 
-#ifdef CONFIG_IOMMU_API
-	if (vic->config->supports_sid && spec) {
+	if (vic->config->supports_sid && tegra_dev_iommu_get_stream_id(vic->dev, &stream_id)) {
 		u32 value;
 
 		value = TRANSCFG_ATT(1, TRANSCFG_SID_FALCON) |
 			TRANSCFG_ATT(0, TRANSCFG_SID_HW);
 		vic_writel(vic, value, VIC_TFBIF_TRANSCFG);
 
-		if (spec->num_ids > 0) {
-			value = spec->ids[0] & 0xffff;
-
-			/*
-			 * STREAMID0 is used for input/output buffers.
-			 * Initialize it to SID_VIC in case context isolation
-			 * is not enabled, and SID_VIC is used for both firmware
-			 * and data buffers.
-			 *
-			 * If context isolation is enabled, it will be
-			 * overridden by the SETSTREAMID opcode as part of
-			 * each job.
-			 */
-			vic_writel(vic, value, VIC_THI_STREAMID0);
-
-			/* STREAMID1 is used for firmware loading. */
-			vic_writel(vic, value, VIC_THI_STREAMID1);
-		}
+		/*
+		 * STREAMID0 is used for input/output buffers. Initialize it to SID_VIC in case
+		 * context isolation is not enabled, and SID_VIC is used for both firmware and
+		 * data buffers.
+		 *
+		 * If context isolation is enabled, it will be overridden by the SETSTREAMID
+		 * opcode as part of each job.
+		 */
+		vic_writel(vic, stream_id, VIC_THI_STREAMID0);
+
+		/* STREAMID1 is used for firmware loading. */
+		vic_writel(vic, stream_id, VIC_THI_STREAMID1);
 	}
-#endif
 
 	/* setup clockgating registers */
 	vic_writel(vic, CG_IDLE_CG_DLY_CNT(4) |

drivers/gpu/host1x/cdma.c

@@ -490,6 +490,15 @@ void host1x_cdma_update_sync_queue(struct host1x_cdma *cdma,
 	host1x_hw_cdma_resume(host1x, cdma, restart_addr);
 }
 
+static void cdma_update_work(struct work_struct *work)
+{
+	struct host1x_cdma *cdma = container_of(work, struct host1x_cdma, update_work);
+
+	mutex_lock(&cdma->lock);
+	update_cdma_locked(cdma);
+	mutex_unlock(&cdma->lock);
+}
+
 /*
  * Create a cdma
  */
@@ -499,6 +508,7 @@ int host1x_cdma_init(struct host1x_cdma *cdma)
 
 	mutex_init(&cdma->lock);
 	init_completion(&cdma->complete);
+	INIT_WORK(&cdma->update_work, cdma_update_work);
 
 	INIT_LIST_HEAD(&cdma->sync_queue);
 
@@ -679,7 +689,5 @@ void host1x_cdma_end(struct host1x_cdma *cdma,
  */
 void host1x_cdma_update(struct host1x_cdma *cdma)
 {
-	mutex_lock(&cdma->lock);
-	update_cdma_locked(cdma);
-	mutex_unlock(&cdma->lock);
+	schedule_work(&cdma->update_work);
 }

drivers/gpu/host1x/cdma.h

@@ -11,6 +11,7 @@
 #include <linux/sched.h>
 #include <linux/completion.h>
 #include <linux/list.h>
+#include <linux/workqueue.h>
 
 struct host1x_syncpt;
 struct host1x_userctx_timeout;
@@ -69,6 +70,7 @@ struct host1x_cdma {
 	struct buffer_timeout timeout;	/* channel's timeout state/wq */
 	bool running;
 	bool torndown;
+	struct work_struct update_work;
 };
 
 #define cdma_to_channel(cdma) container_of(cdma, struct host1x_channel, cdma)

drivers/gpu/host1x/context.c

@@ -35,8 +35,6 @@ int host1x_memory_context_list_init(struct host1x *host1x)
 	cdl->len = err / 4;
 
 	for (i = 0; i < cdl->len; i++) {
-		struct iommu_fwspec *fwspec;
-
 		ctx = &cdl->devs[i];
 
 		ctx->host = host1x;
@@ -70,14 +68,12 @@ int host1x_memory_context_list_init(struct host1x *host1x)
 			goto del_devices;
 		}
 
-		fwspec = dev_iommu_fwspec_get(&ctx->dev);
-		if (!fwspec || !device_iommu_mapped(&ctx->dev)) {
+		if (!tegra_dev_iommu_get_stream_id(&ctx->dev, &ctx->stream_id) ||
+		    !device_iommu_mapped(&ctx->dev)) {
 			dev_err(host1x->dev, "Context device %d has no IOMMU!\n", i);
 			device_del(&ctx->dev);
 			goto del_devices;
 		}
-
-		ctx->stream_id = fwspec->ids[0] & 0xffff;
 	}
 
 	return 0;

drivers/gpu/host1x/debug.c

@@ -77,6 +77,7 @@ static int show_channel(struct host1x_channel *ch, void *data, bool show_fifo)
 
 static void show_syncpts(struct host1x *m, struct output *o, bool show_all)
 {
+	unsigned long irqflags;
 	struct list_head *pos;
 	unsigned int i;
 	int err;
@@ -92,10 +93,10 @@ static void show_syncpts(struct host1x *m, struct output *o, bool show_all)
 		u32 min = host1x_syncpt_load(m->syncpt + i);
 		unsigned int waiters = 0;
 
-		spin_lock(&m->syncpt[i].intr.lock);
-		list_for_each(pos, &m->syncpt[i].intr.wait_head)
+		spin_lock_irqsave(&m->syncpt[i].fences.lock, irqflags);
+		list_for_each(pos, &m->syncpt[i].fences.list)
 			waiters++;
-		spin_unlock(&m->syncpt[i].intr.lock);
+		spin_unlock_irqrestore(&m->syncpt[i].fences.lock, irqflags);
 
 		if (!kref_read(&m->syncpt[i].ref))
 			continue;

drivers/gpu/host1x/dev.c

@@ -516,7 +516,7 @@ static int host1x_probe(struct platform_device *pdev)
 			return PTR_ERR(host->regs);
 	}
 
-	syncpt_irq = platform_get_irq(pdev, 0);
+	host->syncpt_irq = platform_get_irq(pdev, 0);
 	if (syncpt_irq < 0)
 		return syncpt_irq;
 
@@ -578,7 +578,7 @@ static int host1x_probe(struct platform_device *pdev)
 		goto free_contexts;
 	}
 
-	err = host1x_intr_init(host, syncpt_irq);
+	err = host1x_intr_init(host);
 	if (err) {
 		dev_err(&pdev->dev, "failed to initialize interrupts\n");
 		goto deinit_syncpt;

drivers/gpu/host1x/dev.h

@@ -74,8 +74,7 @@ struct host1x_syncpt_ops {
 };
 
 struct host1x_intr_ops {
-	int (*init_host_sync)(struct host1x *host, u32 cpm,
-		void (*syncpt_thresh_work)(struct work_struct *work));
+	int (*init_host_sync)(struct host1x *host, u32 cpm);
 	void (*set_syncpt_threshold)(
 		struct host1x *host, unsigned int id, u32 thresh);
 	void (*enable_syncpt_intr)(struct host1x *host, unsigned int id);
@@ -125,6 +124,7 @@ struct host1x {
 	void __iomem *regs;
 	void __iomem *hv_regs; /* hypervisor region */
 	void __iomem *common_regs;
+	int syncpt_irq;
 	struct host1x_syncpt *syncpt;
 	struct host1x_syncpt_base *bases;
 	struct device *dev;
@@ -138,7 +138,6 @@ struct host1x {
 	dma_addr_t iova_end;
 
 	struct mutex intr_mutex;
-	int intr_syncpt_irq;
 
 	const struct host1x_syncpt_ops *syncpt_op;
 	const struct host1x_intr_ops *intr_op;
@@ -216,10 +215,9 @@ static inline void host1x_hw_syncpt_enable_protection(struct host1x *host)
 	return host->syncpt_op->enable_protection(host);
 }
 
-static inline int host1x_hw_intr_init_host_sync(struct host1x *host, u32 cpm,
-			void (*syncpt_thresh_work)(struct work_struct *))
+static inline int host1x_hw_intr_init_host_sync(struct host1x *host, u32 cpm)
 {
-	return host->intr_op->init_host_sync(host, cpm, syncpt_thresh_work);
+	return host->intr_op->init_host_sync(host, cpm);
 }
 
 static inline void host1x_hw_intr_set_syncpt_threshold(struct host1x *host,