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

24 files changed, 277 insertions, 661 deletions

diff --git a/drivers/gpu/drm/tegra/dpaux.c b/drivers/gpu/drm/tegra/dpaux.c
index 7dc681e2ee90..3c84e73d5051 100644
--- a/drivers/gpu/drm/tegra/dpaux.c
+++ b/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 @@ disable_clk:
 	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,
diff --git a/drivers/gpu/drm/tegra/firewall.c b/drivers/gpu/drm/tegra/firewall.c
index 1824d2db0e2c..d53f890fa689 100644
--- a/drivers/gpu/drm/tegra/firewall.c
+++ b/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)
diff --git a/drivers/gpu/drm/tegra/nvdec.c b/drivers/gpu/drm/tegra/nvdec.c
index 10fd21517281..86c5818ac27b 100644
--- a/drivers/gpu/drm/tegra/nvdec.c
+++ b/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)
diff --git a/drivers/gpu/drm/tegra/submit.c b/drivers/gpu/drm/tegra/submit.c
index 066f88564169..2430fcc97448 100644
--- a/drivers/gpu/drm/tegra/submit.c
+++ b/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 @@ free_job_data:
 		kfree(job_data->used_mappings);
 	}
 
-	if (job_data)
-		kfree(job_data);
+	kfree(job_data);
 put_bo:
 	gather_bo_put(&bo->base);
 unlock:
diff --git a/drivers/gpu/drm/tegra/vic.c b/drivers/gpu/drm/tegra/vic.c
index 7382ee132eb7..531a71c72061 100644
--- a/drivers/gpu/drm/tegra/vic.c
+++ b/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) |
diff --git a/drivers/gpu/host1x/cdma.c b/drivers/gpu/host1x/cdma.c
index 103fda055394..bc821b0ed908 100644
--- a/drivers/gpu/host1x/cdma.c
+++ b/drivers/gpu/host1x/cdma.c
@@ -490,6 +490,15 @@ resume:
 	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);
 }
diff --git a/drivers/gpu/host1x/cdma.h b/drivers/gpu/host1x/cdma.h
index 12c4327c4df0..7fd8168af4f9 100644
--- a/drivers/gpu/host1x/cdma.h
+++ b/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)
diff --git a/drivers/gpu/host1x/context.c b/drivers/gpu/host1x/context.c
index c8e7994c2c9c..8beedcf080ab 100644
--- a/drivers/gpu/host1x/context.c
+++ b/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;
diff --git a/drivers/gpu/host1x/debug.c b/drivers/gpu/host1x/debug.c
index 6649b04b7131..a18cc8d8caf5 100644
--- a/drivers/gpu/host1x/debug.c
+++ b/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;
diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c
index f31039aca03c..4872d183d860 100644
--- a/drivers/gpu/host1x/dev.c
+++ b/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;
diff --git a/drivers/gpu/host1x/dev.h b/drivers/gpu/host1x/dev.h
index 920e5548cfbc..75de50fe03d0 100644
--- a/drivers/gpu/host1x/dev.h
+++ b/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,
diff --git a/drivers/gpu/host1x/fence.c b/drivers/gpu/host1x/fence.c
index df428bcbae69..139ad1afd935 100644
--- a/drivers/gpu/host1x/fence.c
+++ b/drivers/gpu/host1x/fence.c
@@ -15,22 +15,6 @@
 #include "intr.h"
 #include "syncpt.h"
 
-static DEFINE_SPINLOCK(lock);
-
-struct host1x_syncpt_fence {
-	struct dma_fence base;
-
-	atomic_t signaling;
-
-	struct host1x_syncpt *sp;
-	u32 threshold;
-
-	struct host1x_waitlist *waiter;
-	void *waiter_ref;
-
-	struct delayed_work timeout_work;
-};
-
 static const char *host1x_syncpt_fence_get_driver_name(struct dma_fence *f)
 {
 	return "host1x";
@@ -49,11 +33,11 @@ static struct host1x_syncpt_fence *to_host1x_fence(struct dma_fence *f)
 static bool host1x_syncpt_fence_enable_signaling(struct dma_fence *f)
 {
 	struct host1x_syncpt_fence *sf = to_host1x_fence(f);
-	int err;
 
 	if (host1x_syncpt_is_expired(sf->sp, sf->threshold))
 		return false;
 
+	/* Reference for interrupt path. */
 	dma_fence_get(f);
 
 	/*
@@ -61,24 +45,17 @@ static bool host1x_syncpt_fence_enable_signaling(struct dma_fence *f)
 	 * reference to any fences for which 'enable_signaling' has been
 	 * called (and that have not been signalled).
 	 *
-	 * We provide a userspace API to create arbitrary syncpoint fences,
-	 * so we cannot normally guarantee that all fences get signalled.
-	 * As such, setup a timeout, so that long-lasting fences will get
-	 * reaped eventually.
+	 * We cannot currently always guarantee that all fences get signalled
+	 * or cancelled. As such, for such situations, set up a timeout, so
+	 * that long-lasting fences will get reaped eventually.
 	 */
-	schedule_delayed_work(&sf->timeout_work, msecs_to_jiffies(30000));
-
-	err = host1x_intr_add_action(sf->sp->host, sf->sp, sf->threshold,
-				     HOST1X_INTR_ACTION_SIGNAL_FENCE, f,
-				     sf->waiter, &sf->waiter_ref);
-	if (err) {
-		cancel_delayed_work_sync(&sf->timeout_work);
-		dma_fence_put(f);
-		return false;
+	if (sf->timeout) {
+		/* Reference for timeout path. */
+		dma_fence_get(f);
+		schedule_delayed_work(&sf->timeout_work, msecs_to_jiffies(30000));
 	}
 
-	/* intr framework takes ownership of waiter */
-	sf->waiter = NULL;
+	host1x_intr_add_fence_locked(sf->sp->host, sf);
 
 	/*
 	 * The fence may get signalled at any time after the above call,
@@ -89,37 +66,32 @@ static bool host1x_syncpt_fence_enable_signaling(struct dma_fence *f)
 	return true;
 }
 
-static void host1x_syncpt_fence_release(struct dma_fence *f)
-{
-	struct host1x_syncpt_fence *sf = to_host1x_fence(f);
-
-	if (sf->waiter)
-		kfree(sf->waiter);
-
-	dma_fence_free(f);
-}
-
 static const struct dma_fence_ops host1x_syncpt_fence_ops = {
 	.get_driver_name = host1x_syncpt_fence_get_driver_name,
 	.get_timeline_name = host1x_syncpt_fence_get_timeline_name,
 	.enable_signaling = host1x_syncpt_fence_enable_signaling,
-	.release = host1x_syncpt_fence_release,
 };
 
 void host1x_fence_signal(struct host1x_syncpt_fence *f)
 {
-	if (atomic_xchg(&f->signaling, 1))
+	if (atomic_xchg(&f->signaling, 1)) {
+		/*
+		 * Already on timeout path, but we removed the fence before
+		 * timeout path could, so drop interrupt path reference.
+		 */
+		dma_fence_put(&f->base);
 		return;
+	}
 
-	/*
-	 * Cancel pending timeout work - if it races, it will
-	 * not get 'f->signaling' and return.
-	 */
-	cancel_delayed_work_sync(&f->timeout_work);
-
-	host1x_intr_put_ref(f->sp->host, f->sp->id, f->waiter_ref, false);
+	if (f->timeout && cancel_delayed_work(&f->timeout_work)) {
+		/*
+		 * We know that the timeout path will not be entered.
+		 * Safe to drop the timeout path's reference now.
+		 */
+		dma_fence_put(&f->base);
+	}
 
-	dma_fence_signal(&f->base);
+	dma_fence_signal_locked(&f->base);
 	dma_fence_put(&f->base);
 }
 
@@ -129,21 +101,29 @@ static void do_fence_timeout(struct work_struct *work)
 	struct host1x_syncpt_fence *f =
 		container_of(dwork, struct host1x_syncpt_fence, timeout_work);
 
-	if (atomic_xchg(&f->signaling, 1))
+	if (atomic_xchg(&f->signaling, 1)) {
+		/* Already on interrupt path, drop timeout path reference if any. */
+		if (f->timeout)
+			dma_fence_put(&f->base);
 		return;
+	}
 
-	/*
-	 * Cancel pending timeout work - if it races, it will
-	 * not get 'f->signaling' and return.
-	 */
-	host1x_intr_put_ref(f->sp->host, f->sp->id, f->waiter_ref, true);
+	if (host1x_intr_remove_fence(f->sp->host, f)) {
+		/*
+		 * Managed to remove fence from queue, so it's safe to drop
+		 * the interrupt path's reference.
+		 */
+		dma_fence_put(&f->base);
+	}
 
 	dma_fence_set_error(&f->base, -ETIMEDOUT);
 	dma_fence_signal(&f->base);
-	dma_fence_put(&f->base);
+	if (f->timeout)
+		dma_fence_put(&f->base);
 }
 
-struct dma_fence *host1x_fence_create(struct host1x_syncpt *sp, u32 threshold)
+struct dma_fence *host1x_fence_create(struct host1x_syncpt *sp, u32 threshold,
+				      bool timeout)
 {
 	struct host1x_syncpt_fence *fence;
 
@@ -151,16 +131,11 @@ struct dma_fence *host1x_fence_create(struct host1x_syncpt *sp, u32 threshold)
 	if (!fence)
 		return ERR_PTR(-ENOMEM);
 
-	fence->waiter = kzalloc(sizeof(*fence->waiter), GFP_KERNEL);
-	if (!fence->waiter) {
-		kfree(fence);
-		return ERR_PTR(-ENOMEM);
-	}
-
 	fence->sp = sp;
 	fence->threshold = threshold;
+	fence->timeout = timeout;
 
-	dma_fence_init(&fence->base, &host1x_syncpt_fence_ops, &lock,
+	dma_fence_init(&fence->base, &host1x_syncpt_fence_ops, &sp->fences.lock,
 		       dma_fence_context_alloc(1), 0);
 
 	INIT_DELAYED_WORK(&fence->timeout_work, do_fence_timeout);
@@ -168,3 +143,12 @@ struct dma_fence *host1x_fence_create(struct host1x_syncpt *sp, u32 threshold)
 	return &fence->base;
 }
 EXPORT_SYMBOL(host1x_fence_create);
+
+void host1x_fence_cancel(struct dma_fence *f)
+{
+	struct host1x_syncpt_fence *sf = to_host1x_fence(f);
+
+	schedule_delayed_work(&sf->timeout_work, 0);
+	flush_delayed_work(&sf->timeout_work);
+}
+EXPORT_SYMBOL(host1x_fence_cancel);
diff --git a/drivers/gpu/host1x/fence.h b/drivers/gpu/host1x/fence.h
index 70c91de82f14..f3c644c73cad 100644
--- a/drivers/gpu/host1x/fence.h
+++ b/drivers/gpu/host1x/fence.h
@@ -6,7 +6,24 @@
 #ifndef HOST1X_FENCE_H
 #define HOST1X_FENCE_H
 
-struct host1x_syncpt_fence;
+struct host1x_syncpt_fence {
+	struct dma_fence base;
+
+	atomic_t signaling;
+
+	struct host1x_syncpt *sp;
+	u32 threshold;
+	bool timeout;
+
+	struct delayed_work timeout_work;
+
+	struct list_head list;
+};
+
+struct host1x_fence_list {
+	spinlock_t lock;
+	struct list_head list;
+};
 
 void host1x_fence_signal(struct host1x_syncpt_fence *fence);
 
diff --git a/drivers/gpu/host1x/hw/channel_hw.c b/drivers/gpu/host1x/hw/channel_hw.c
index 732abe0750ff..d44b8de890be 100644
--- a/drivers/gpu/host1x/hw/channel_hw.c
+++ b/drivers/gpu/host1x/hw/channel_hw.c
@@ -179,14 +179,12 @@ static inline void synchronize_syncpt_base(struct host1x_job *job)
 static void host1x_channel_set_streamid(struct host1x_channel *channel)
 {
 #if HOST1X_HW >= 6
-	u32 sid = 0x7f;
-#ifdef CONFIG_IOMMU_API
-	struct iommu_fwspec *spec = dev_iommu_fwspec_get(channel->dev->parent);
-	if (spec)
-		sid = spec->ids[0] & 0xffff;
-#endif
+	u32 stream_id;
+
+	if (!tegra_dev_iommu_get_stream_id(channel->dev->parent, &stream_id))
+		stream_id = TEGRA_STREAM_ID_BYPASS;
 
-	host1x_ch_writel(channel, sid, HOST1X_CHANNEL_SMMU_STREAMID);
+	host1x_ch_writel(channel, stream_id, HOST1X_CHANNEL_SMMU_STREAMID);
 #endif
 }
 
@@ -278,6 +276,14 @@ static void channel_program_cdma(struct host1x_job *job)
 #endif
 }
 
+static void job_complete_callback(struct dma_fence *fence, struct dma_fence_cb *cb)
+{
+	struct host1x_job *job = container_of(cb, struct host1x_job, fence_cb);
+
+	/* Schedules CDMA update. */
+	host1x_cdma_update(&job->channel->cdma);
+}
+
 static int channel_submit(struct host1x_job *job)
 {
 	struct host1x_channel *ch = job->channel;
@@ -285,7 +291,6 @@ static int channel_submit(struct host1x_job *job)
 	u32 prev_max = 0;
 	u32 syncval;
 	int err;
-	struct host1x_waitlist *completed_waiter = NULL;
 	struct host1x *host = dev_get_drvdata(ch->dev->parent);
 
 	trace_host1x_channel_submit(dev_name(ch->dev),
@@ -298,14 +303,7 @@ static int channel_submit(struct host1x_job *job)
 	/* get submit lock */
 	err = mutex_lock_interruptible(&ch->submitlock);
 	if (err)
-		goto error;
-
-	completed_waiter = kzalloc(sizeof(*completed_waiter), GFP_KERNEL);
-	if (!completed_waiter) {
-		mutex_unlock(&ch->submitlock);
-		err = -ENOMEM;
-		goto error;
-	}
+		return err;
 
 	host1x_channel_set_streamid(ch);
 	host1x_enable_gather_filter(ch);
@@ -315,31 +313,37 @@ static int channel_submit(struct host1x_job *job)
 	err = host1x_cdma_begin(&ch->cdma, job);
 	if (err) {
 		mutex_unlock(&ch->submitlock);
-		goto error;
+		return err;
 	}
 
 	channel_program_cdma(job);
 	syncval = host1x_syncpt_read_max(sp);
 
+	/*
+	 * Create fence before submitting job to HW to avoid job completing
+	 * before the fence is set up.
+	 */
+	job->fence = host1x_fence_create(sp, syncval, true);
+	if (WARN(IS_ERR(job->fence), "Failed to create submit complete fence")) {
+		job->fence = NULL;
+	} else {
+		err = dma_fence_add_callback(job->fence, &job->fence_cb,
+					     job_complete_callback);
+	}
+
 	/* end CDMA submit & stash pinned hMems into sync queue */
 	host1x_cdma_end(&ch->cdma, job);
 
 	trace_host1x_channel_submitted(dev_name(ch->dev), prev_max, syncval);
 
-	/* schedule a submit complete interrupt */
-	err = host1x_intr_add_action(host, sp, syncval,
-				     HOST1X_INTR_ACTION_SUBMIT_COMPLETE, ch,
-				     completed_waiter, &job->waiter);
-	completed_waiter = NULL;
-	WARN(err, "Failed to set submit complete interrupt");
-
 	mutex_unlock(&ch->submitlock);
 
-	return 0;
+	if (err == -ENOENT)
+		host1x_cdma_update(&ch->cdma);
+	else
+		WARN(err, "Failed to set submit complete interrupt");
 
-error:
-	kfree(completed_waiter);
-	return err;
+	return 0;
 }
 
 static int host1x_channel_init(struct host1x_channel *ch, struct host1x *dev,
diff --git a/drivers/gpu/host1x/hw/hw_host1x06_uclass.h b/drivers/gpu/host1x/hw/hw_host1x06_uclass.h
index 5f831438d19b..50c32de452fb 100644
--- a/drivers/gpu/host1x/hw/hw_host1x06_uclass.h
+++ b/drivers/gpu/host1x/hw/hw_host1x06_uclass.h
@@ -53,7 +53,7 @@ static inline u32 host1x_uclass_incr_syncpt_cond_f(u32 v)
 	host1x_uclass_incr_syncpt_cond_f(v)
 static inline u32 host1x_uclass_incr_syncpt_indx_f(u32 v)
 {
-	return (v & 0xff) << 0;
+	return (v & 0x3ff) << 0;
 }
 #define HOST1X_UCLASS_INCR_SYNCPT_INDX_F(v) \
 	host1x_uclass_incr_syncpt_indx_f(v)
diff --git a/drivers/gpu/host1x/hw/hw_host1x07_uclass.h b/drivers/gpu/host1x/hw/hw_host1x07_uclass.h
index 8cd2ef087d5d..887b878f92f7 100644
--- a/drivers/gpu/host1x/hw/hw_host1x07_uclass.h
+++ b/drivers/gpu/host1x/hw/hw_host1x07_uclass.h
@@ -53,7 +53,7 @@ static inline u32 host1x_uclass_incr_syncpt_cond_f(u32 v)
 	host1x_uclass_incr_syncpt_cond_f(v)
 static inline u32 host1x_uclass_incr_syncpt_indx_f(u32 v)
 {
-	return (v & 0xff) << 0;
+	return (v & 0x3ff) << 0;
 }
 #define HOST1X_UCLASS_INCR_SYNCPT_INDX_F(v) \
 	host1x_uclass_incr_syncpt_indx_f(v)
diff --git a/drivers/gpu/host1x/hw/hw_host1x08_uclass.h b/drivers/gpu/host1x/hw/hw_host1x08_uclass.h
index 724cccd71aa1..4fb1d090edae 100644
--- a/drivers/gpu/host1x/hw/hw_host1x08_uclass.h
+++ b/drivers/gpu/host1x/hw/hw_host1x08_uclass.h
@@ -53,7 +53,7 @@ static inline u32 host1x_uclass_incr_syncpt_cond_f(u32 v)
 	host1x_uclass_incr_syncpt_cond_f(v)
 static inline u32 host1x_uclass_incr_syncpt_indx_f(u32 v)
 {
-	return (v & 0xff) << 0;
+	return (v & 0x3ff) << 0;
 }
 #define HOST1X_UCLASS_INCR_SYNCPT_INDX_F(v) \
 	host1x_uclass_incr_syncpt_indx_f(v)
diff --git a/drivers/gpu/host1x/hw/intr_hw.c b/drivers/gpu/host1x/hw/intr_hw.c
index 9acccdb139e6..b915ef7d0348 100644
--- a/drivers/gpu/host1x/hw/intr_hw.c
+++ b/drivers/gpu/host1x/hw/intr_hw.c
@@ -13,23 +13,6 @@
 #include "../intr.h"
 #include "../dev.h"
 
-/*
- * Sync point threshold interrupt service function
- * Handles sync point threshold triggers, in interrupt context
- */
-static void host1x_intr_syncpt_handle(struct host1x_syncpt *syncpt)
-{
-	unsigned int id = syncpt->id;
-	struct host1x *host = syncpt->host;
-
-	host1x_sync_writel(host, BIT(id % 32),
-		HOST1X_SYNC_SYNCPT_THRESH_INT_DISABLE(id / 32));
-	host1x_sync_writel(host, BIT(id % 32),
-		HOST1X_SYNC_SYNCPT_THRESH_CPU0_INT_STATUS(id / 32));
-
-	schedule_work(&syncpt->intr.work);
-}
-
 static irqreturn_t syncpt_thresh_isr(int irq, void *dev_id)
 {
 	struct host1x *host = dev_id;
@@ -39,17 +22,20 @@ static irqreturn_t syncpt_thresh_isr(int irq, void *dev_id)
 	for (i = 0; i < DIV_ROUND_UP(host->info->nb_pts, 32); i++) {
 		reg = host1x_sync_readl(host,
 			HOST1X_SYNC_SYNCPT_THRESH_CPU0_INT_STATUS(i));
-		for_each_set_bit(id, &reg, 32) {
-			struct host1x_syncpt *syncpt =
-				host->syncpt + (i * 32 + id);
-			host1x_intr_syncpt_handle(syncpt);
-		}
+
+		host1x_sync_writel(host, reg,
+			HOST1X_SYNC_SYNCPT_THRESH_INT_DISABLE(i));
+		host1x_sync_writel(host, reg,
+			HOST1X_SYNC_SYNCPT_THRESH_CPU0_INT_STATUS(i));
+
+		for_each_set_bit(id, &reg, 32)
+			host1x_intr_handle_interrupt(host, i * 32 + id);
 	}
 
 	return IRQ_HANDLED;
 }
 
-static void _host1x_intr_disable_all_syncpt_intrs(struct host1x *host)
+static void host1x_intr_disable_all_syncpt_intrs(struct host1x *host)
 {
 	unsigned int i;
 
@@ -90,45 +76,38 @@ static void intr_hw_init(struct host1x *host, u32 cpm)
 }
 
 static int
-_host1x_intr_init_host_sync(struct host1x *host, u32 cpm,
-			    void (*syncpt_thresh_work)(struct work_struct *))
+host1x_intr_init_host_sync(struct host1x *host, u32 cpm)
 {
-	unsigned int i;
 	int err;
 
 	host1x_hw_intr_disable_all_syncpt_intrs(host);
 
-	for (i = 0; i < host->info->nb_pts; i++)
-		INIT_WORK(&host->syncpt[i].intr.work, syncpt_thresh_work);
-
-	err = devm_request_irq(host->dev, host->intr_syncpt_irq,
+	err = devm_request_irq(host->dev, host->syncpt_irq,
 			       syncpt_thresh_isr, IRQF_SHARED,
 			       "host1x_syncpt", host);
-	if (err < 0) {
-		WARN_ON(1);
+	if (err < 0)
 		return err;
-	}
 
 	intr_hw_init(host, cpm);
 
 	return 0;
 }
 
-static void _host1x_intr_set_syncpt_threshold(struct host1x *host,
+static void host1x_intr_set_syncpt_threshold(struct host1x *host,
 					      unsigned int id,
 					      u32 thresh)
 {
 	host1x_sync_writel(host, thresh, HOST1X_SYNC_SYNCPT_INT_THRESH(id));
 }
 
-static void _host1x_intr_enable_syncpt_intr(struct host1x *host,
+static void host1x_intr_enable_syncpt_intr(struct host1x *host,
 					    unsigned int id)
 {
 	host1x_sync_writel(host, BIT(id % 32),
 		HOST1X_SYNC_SYNCPT_THRESH_INT_ENABLE_CPU0(id / 32));
 }
 
-static void _host1x_intr_disable_syncpt_intr(struct host1x *host,
+static void host1x_intr_disable_syncpt_intr(struct host1x *host,
 					     unsigned int id)
 {
 	host1x_sync_writel(host, BIT(id % 32),
@@ -137,23 +116,10 @@ static void _host1x_intr_disable_syncpt_intr(struct host1x *host,
 		HOST1X_SYNC_SYNCPT_THRESH_CPU0_INT_STATUS(id / 32));
 }
 
-static int _host1x_free_syncpt_irq(struct host1x *host)
-{
-	unsigned int i;
-
-	devm_free_irq(host->dev, host->intr_syncpt_irq, host);
-
-	for (i = 0; i < host->info->nb_pts; i++)
-		cancel_work_sync(&host->syncpt[i].intr.work);
-
-	return 0;
-}
-
 static const struct host1x_intr_ops host1x_intr_ops = {
-	.init_host_sync = _host1x_intr_init_host_sync,
-	.set_syncpt_threshold = _host1x_intr_set_syncpt_threshold,
-	.enable_syncpt_intr = _host1x_intr_enable_syncpt_intr,
-	.disable_syncpt_intr = _host1x_intr_disable_syncpt_intr,
-	.disable_all_syncpt_intrs = _host1x_intr_disable_all_syncpt_intrs,
-	.free_syncpt_irq = _host1x_free_syncpt_irq,
+	.init_host_sync = host1x_intr_init_host_sync,
+	.set_syncpt_threshold = host1x_intr_set_syncpt_threshold,
+	.enable_syncpt_intr = host1x_intr_enable_syncpt_intr,
+	.disable_syncpt_intr = host1x_intr_disable_syncpt_intr,
+	.disable_all_syncpt_intrs = host1x_intr_disable_all_syncpt_intrs,
 };
diff --git a/drivers/gpu/host1x/hw/syncpt_hw.c b/drivers/gpu/host1x/hw/syncpt_hw.c
index dd39d67ccec3..8cf35b2eff3d 100644
--- a/drivers/gpu/host1x/hw/syncpt_hw.c
+++ b/drivers/gpu/host1x/hw/syncpt_hw.c
@@ -106,9 +106,6 @@ static void syncpt_assign_to_channel(struct host1x_syncpt *sp,
 #if HOST1X_HW >= 6
 	struct host1x *host = sp->host;
 
-	if (!host->hv_regs)
-		return;
-
 	host1x_sync_writel(host,
 			   HOST1X_SYNC_SYNCPT_CH_APP_CH(ch ? ch->id : 0xff),
 			   HOST1X_SYNC_SYNCPT_CH_APP(sp->id));
diff --git a/drivers/gpu/host1x/intr.c b/drivers/gpu/host1x/intr.c
index 965ba21818b1..995bfa980837 100644
--- a/drivers/gpu/host1x/intr.c
+++ b/drivers/gpu/host1x/intr.c
@@ -2,299 +2,113 @@
 /*
  * Tegra host1x Interrupt Management
  *
- * Copyright (c) 2010-2013, NVIDIA Corporation.
+ * Copyright (c) 2010-2021, NVIDIA Corporation.
  */
 
 #include <linux/clk.h>
-#include <linux/interrupt.h>
-#include <linux/slab.h>
-#include <linux/irq.h>
 
-#include <trace/events/host1x.h>
-#include "channel.h"
 #include "dev.h"
 #include "fence.h"
 #include "intr.h"
 
-/* Wait list management */
-
-enum waitlist_state {
-	WLS_PENDING,
-	WLS_REMOVED,
-	WLS_CANCELLED,
-	WLS_HANDLED
-};
-
-static void waiter_release(struct kref *kref)
-{
-	kfree(container_of(kref, struct host1x_waitlist, refcount));
-}
-
-/*
- * add a waiter to a waiter queue, sorted by threshold
- * returns true if it was added at the head of the queue
- */
-static bool add_waiter_to_queue(struct host1x_waitlist *waiter,
-				struct list_head *queue)
-{
-	struct host1x_waitlist *pos;
-	u32 thresh = waiter->thresh;
-
-	list_for_each_entry_reverse(pos, queue, list)
-		if ((s32)(pos->thresh - thresh) <= 0) {
-			list_add(&waiter->list, &pos->list);
-			return false;
-		}
-
-	list_add(&waiter->list, queue);
-	return true;
-}
-
-/*
- * run through a waiter queue for a single sync point ID
- * and gather all completed waiters into lists by actions
- */
-static void remove_completed_waiters(struct list_head *head, u32 sync,
-			struct list_head completed[HOST1X_INTR_ACTION_COUNT])
+static void host1x_intr_add_fence_to_list(struct host1x_fence_list *list,
+					  struct host1x_syncpt_fence *fence)
 {
-	struct list_head *dest;
-	struct host1x_waitlist *waiter, *next, *prev;
-
-	list_for_each_entry_safe(waiter, next, head, list) {
-		if ((s32)(waiter->thresh - sync) > 0)
-			break;
+	struct host1x_syncpt_fence *fence_in_list;
 
-		dest = completed + waiter->action;
-
-		/* consolidate submit cleanups */
-		if (waiter->action == HOST1X_INTR_ACTION_SUBMIT_COMPLETE &&
-		    !list_empty(dest)) {
-			prev = list_entry(dest->prev,
-					  struct host1x_waitlist, list);
-			if (prev->data == waiter->data) {
-				prev->count++;
-				dest = NULL;
-			}
+	list_for_each_entry_reverse(fence_in_list, &list->list, list) {
+		if ((s32)(fence_in_list->threshold - fence->threshold) <= 0) {
+			/* Fence in list is before us, we can insert here */
+			list_add(&fence->list, &fence_in_list->list);
+			return;
 		}
-
-		/* PENDING->REMOVED or CANCELLED->HANDLED */
-		if (atomic_inc_return(&waiter->state) == WLS_HANDLED || !dest) {
-			list_del(&waiter->list);
-			kref_put(&waiter->refcount, waiter_release);
-		} else
-			list_move_tail(&waiter->list, dest);
 	}
-}
-
-static void reset_threshold_interrupt(struct host1x *host,
-				      struct list_head *head,
-				      unsigned int id)
-{
-	u32 thresh =
-		list_first_entry(head, struct host1x_waitlist, list)->thresh;
-
-	host1x_hw_intr_set_syncpt_threshold(host, id, thresh);
-	host1x_hw_intr_enable_syncpt_intr(host, id);
-}
-
-static void action_submit_complete(struct host1x_waitlist *waiter)
-{
-	struct host1x_channel *channel = waiter->data;
-
-	host1x_cdma_update(&channel->cdma);
-
-	/*  Add nr_completed to trace */
-	trace_host1x_channel_submit_complete(dev_name(channel->dev),
-					     waiter->count, waiter->thresh);
-}
 
-static void action_wakeup(struct host1x_waitlist *waiter)
-{
-	wait_queue_head_t *wq = waiter->data;
-
-	wake_up(wq);
-}
-
-static void action_wakeup_interruptible(struct host1x_waitlist *waiter)
-{
-	wait_queue_head_t *wq = waiter->data;
-
-	wake_up_interruptible(wq);
+	/* Add as first in list */
+	list_add(&fence->list, &list->list);
 }
 
-static void action_signal_fence(struct host1x_waitlist *waiter)
+static void host1x_intr_update_hw_state(struct host1x *host, struct host1x_syncpt *sp)
 {
-	struct host1x_syncpt_fence *f = waiter->data;
-
-	host1x_fence_signal(f);
-}
+	struct host1x_syncpt_fence *fence;
 
-typedef void (*action_handler)(struct host1x_waitlist *waiter);
+	if (!list_empty(&sp->fences.list)) {
+		fence = list_first_entry(&sp->fences.list, struct host1x_syncpt_fence, list);
 
-static const action_handler action_handlers[HOST1X_INTR_ACTION_COUNT] = {
-	action_submit_complete,
-	action_wakeup,
-	action_wakeup_interruptible,
-	action_signal_fence,
-};
-
-static void run_handlers(struct list_head completed[HOST1X_INTR_ACTION_COUNT])
-{
-	struct list_head *head = completed;
-	unsigned int i;
-
-	for (i = 0; i < HOST1X_INTR_ACTION_COUNT; ++i, ++head) {
-		action_handler handler = action_handlers[i];
-		struct host1x_waitlist *waiter, *next;
-
-		list_for_each_entry_safe(waiter, next, head, list) {
-			list_del(&waiter->list);
-			handler(waiter);
-			WARN_ON(atomic_xchg(&waiter->state, WLS_HANDLED) !=
-				WLS_REMOVED);
-			kref_put(&waiter->refcount, waiter_release);
-		}
+		host1x_hw_intr_set_syncpt_threshold(host, sp->id, fence->threshold);
+		host1x_hw_intr_enable_syncpt_intr(host, sp->id);
+	} else {
+		host1x_hw_intr_disable_syncpt_intr(host, sp->id);
 	}
 }
 
-/*
- * Remove & handle all waiters that have completed for the given syncpt
- */
-static int process_wait_list(struct host1x *host,
-			     struct host1x_syncpt *syncpt,
-			     u32 threshold)
+void host1x_intr_add_fence_locked(struct host1x *host, struct host1x_syncpt_fence *fence)
 {
-	struct list_head completed[HOST1X_INTR_ACTION_COUNT];
-	unsigned int i;
-	int empty;
-
-	for (i = 0; i < HOST1X_INTR_ACTION_COUNT; ++i)
-		INIT_LIST_HEAD(completed + i);
-
-	spin_lock(&syncpt->intr.lock);
-
-	remove_completed_waiters(&syncpt->intr.wait_head, threshold,
-				 completed);
-
-	empty = list_empty(&syncpt->intr.wait_head);
-	if (empty)
-		host1x_hw_intr_disable_syncpt_intr(host, syncpt->id);
-	else
-		reset_threshold_interrupt(host, &syncpt->intr.wait_head,
-					  syncpt->id);
-
-	spin_unlock(&syncpt->intr.lock);
-
-	run_handlers(completed);
-
-	return empty;
-}
+	struct host1x_fence_list *fence_list = &fence->sp->fences;
 
-/*
- * Sync point threshold interrupt service thread function
- * Handles sync point threshold triggers, in thread context
- */
+	INIT_LIST_HEAD(&fence->list);
 
-static void syncpt_thresh_work(struct work_struct *work)
-{
-	struct host1x_syncpt_intr *syncpt_intr =
-		container_of(work, struct host1x_syncpt_intr, work);
-	struct host1x_syncpt *syncpt =
-		container_of(syncpt_intr, struct host1x_syncpt, intr);
-	unsigned int id = syncpt->id;
-	struct host1x *host = syncpt->host;
-
-	(void)process_wait_list(host, syncpt,
-				host1x_syncpt_load(host->syncpt + id));
+	host1x_intr_add_fence_to_list(fence_list, fence);
+	host1x_intr_update_hw_state(host, fence->sp);
 }
 
-int host1x_intr_add_action(struct host1x *host, struct host1x_syncpt *syncpt,
-			   u32 thresh, enum host1x_intr_action action,
-			   void *data, struct host1x_waitlist *waiter,
-			   void **ref)
+bool host1x_intr_remove_fence(struct host1x *host, struct host1x_syncpt_fence *fence)
 {
-	int queue_was_empty;
-
-	if (waiter == NULL) {
-		pr_warn("%s: NULL waiter\n", __func__);
-		return -EINVAL;
-	}
-
-	/* initialize a new waiter */
-	INIT_LIST_HEAD(&waiter->list);
-	kref_init(&waiter->refcount);
-	if (ref)
-		kref_get(&waiter->refcount);
-	waiter->thresh = thresh;
-	waiter->action = action;
-	atomic_set(&waiter->state, WLS_PENDING);
-	waiter->data = data;
-	waiter->count = 1;
-
-	spin_lock(&syncpt->intr.lock);
+	struct host1x_fence_list *fence_list = &fence->sp->fences;
+	unsigned long irqflags;
 
-	queue_was_empty = list_empty(&syncpt->intr.wait_head);
+	spin_lock_irqsave(&fence_list->lock, irqflags);
 
-	if (add_waiter_to_queue(waiter, &syncpt->intr.wait_head)) {
-		/* added at head of list - new threshold value */
-		host1x_hw_intr_set_syncpt_threshold(host, syncpt->id, thresh);
-
-		/* added as first waiter - enable interrupt */
-		if (queue_was_empty)
-			host1x_hw_intr_enable_syncpt_intr(host, syncpt->id);
+	if (list_empty(&fence->list)) {
+		spin_unlock_irqrestore(&fence_list->lock, irqflags);
+		return false;
 	}
 
-	if (ref)
-		*ref = waiter;
+	list_del_init(&fence->list);
+	host1x_intr_update_hw_state(host, fence->sp);
 
-	spin_unlock(&syncpt->intr.lock);
+	spin_unlock_irqrestore(&fence_list->lock, irqflags);
 
-	return 0;
+	return true;
 }
 
-void host1x_intr_put_ref(struct host1x *host, unsigned int id, void *ref,
-			 bool flush)
+void host1x_intr_handle_interrupt(struct host1x *host, unsigned int id)
 {
-	struct host1x_waitlist *waiter = ref;
-	struct host1x_syncpt *syncpt;
+	struct host1x_syncpt *sp = &host->syncpt[id];
+	struct host1x_syncpt_fence *fence, *tmp;
+	unsigned int value;
 
-	atomic_cmpxchg(&waiter->state, WLS_PENDING, WLS_CANCELLED);
+	value = host1x_syncpt_load(sp);
 
-	syncpt = host->syncpt + id;
+	spin_lock(&sp->fences.lock);
 
-	spin_lock(&syncpt->intr.lock);
-	if (atomic_cmpxchg(&waiter->state, WLS_CANCELLED, WLS_HANDLED) ==
-	    WLS_CANCELLED) {
-		list_del(&waiter->list);
-		kref_put(&waiter->refcount, waiter_release);
-	}
-	spin_unlock(&syncpt->intr.lock);
+	list_for_each_entry_safe(fence, tmp, &sp->fences.list, list) {
+		if (((value - fence->threshold) & 0x80000000U) != 0U) {
+			/* Fence is not yet expired, we are done */
+			break;
+		}
 
-	if (flush) {
-		/* Wait until any concurrently executing handler has finished. */
-		while (atomic_read(&waiter->state) != WLS_HANDLED)
-			schedule();
+		list_del_init(&fence->list);
+		host1x_fence_signal(fence);
 	}
 
-	kref_put(&waiter->refcount, waiter_release);
+	/* Re-enable interrupt if necessary */
+	host1x_intr_update_hw_state(host, sp);
+
+	spin_unlock(&sp->fences.lock);
 }
 
-int host1x_intr_init(struct host1x *host, unsigned int irq_sync)
+int host1x_intr_init(struct host1x *host)
 {
 	unsigned int id;
-	u32 nb_pts = host1x_syncpt_nb_pts(host);
 
 	mutex_init(&host->intr_mutex);
-	host->intr_syncpt_irq = irq_sync;
 
-	for (id = 0; id < nb_pts; ++id) {
-		struct host1x_syncpt *syncpt = host->syncpt + id;
+	for (id = 0; id < host1x_syncpt_nb_pts(host); ++id) {
+		struct host1x_syncpt *syncpt = &host->syncpt[id];
 
-		spin_lock_init(&syncpt->intr.lock);
-		INIT_LIST_HEAD(&syncpt->intr.wait_head);
-		snprintf(syncpt->intr.thresh_irq_name,
-			 sizeof(syncpt->intr.thresh_irq_name),
-			 "host1x_sp_%02u", id);
+		spin_lock_init(&syncpt->fences.lock);
+		INIT_LIST_HEAD(&syncpt->fences.list);
 	}
 
 	return 0;
@@ -310,8 +124,7 @@ void host1x_intr_start(struct host1x *host)
 	int err;
 
 	mutex_lock(&host->intr_mutex);
-	err = host1x_hw_intr_init_host_sync(host, DIV_ROUND_UP(hz, 1000000),
-					    syncpt_thresh_work);
+	err = host1x_hw_intr_init_host_sync(host, DIV_ROUND_UP(hz, 1000000));
 	if (err) {
 		mutex_unlock(&host->intr_mutex);
 		return;
@@ -321,36 +134,5 @@ void host1x_intr_start(struct host1x *host)
 
 void host1x_intr_stop(struct host1x *host)
 {
-	unsigned int id;
-	struct host1x_syncpt *syncpt = host->syncpt;
-	u32 nb_pts = host1x_syncpt_nb_pts(host);
-
-	mutex_lock(&host->intr_mutex);
-
 	host1x_hw_intr_disable_all_syncpt_intrs(host);
-
-	for (id = 0; id < nb_pts; ++id) {
-		struct host1x_waitlist *waiter, *next;
-
-		list_for_each_entry_safe(waiter, next,
-			&syncpt[id].intr.wait_head, list) {
-			if (atomic_cmpxchg(&waiter->state,
-			    WLS_CANCELLED, WLS_HANDLED) == WLS_CANCELLED) {
-				list_del(&waiter->list);
-				kref_put(&waiter->refcount, waiter_release);
-			}
-		}
-
-		if (!list_empty(&syncpt[id].intr.wait_head)) {
-			/* output diagnostics */
-			mutex_unlock(&host->intr_mutex);
-			pr_warn("%s cannot stop syncpt intr id=%u\n",
-				__func__, id);
-			return;
-		}
-	}
-
-	host1x_hw_intr_free_syncpt_irq(host);
-
-	mutex_unlock(&host->intr_mutex);
 }
diff --git a/drivers/gpu/host1x/intr.h b/drivers/gpu/host1x/intr.h
index e4c346099273..3b5610b525e5 100644
--- a/drivers/gpu/host1x/intr.h
+++ b/drivers/gpu/host1x/intr.h
@@ -2,87 +2,17 @@
 /*
  * Tegra host1x Interrupt Management
  *
- * Copyright (c) 2010-2013, NVIDIA Corporation.
+ * Copyright (c) 2010-2021, NVIDIA Corporation.
  */
 
 #ifndef __HOST1X_INTR_H
 #define __HOST1X_INTR_H
 
-#include <linux/interrupt.h>
-#include <linux/workqueue.h>
-
-struct host1x_syncpt;
 struct host1x;
-
-enum host1x_intr_action {
-	/*
-	 * Perform cleanup after a submit has completed.
-	 * 'data' points to a channel
-	 */
-	HOST1X_INTR_ACTION_SUBMIT_COMPLETE = 0,
-
-	/*
-	 * Wake up a  task.
-	 * 'data' points to a wait_queue_head_t
-	 */
-	HOST1X_INTR_ACTION_WAKEUP,
-
-	/*
-	 * Wake up a interruptible task.
-	 * 'data' points to a wait_queue_head_t
-	 */
-	HOST1X_INTR_ACTION_WAKEUP_INTERRUPTIBLE,
-
-	HOST1X_INTR_ACTION_SIGNAL_FENCE,
-
-	HOST1X_INTR_ACTION_COUNT
-};
-
-struct host1x_syncpt_intr {
-	spinlock_t lock;
-	struct list_head wait_head;
-	char thresh_irq_name[12];
-	struct work_struct work;
-};
-
-struct host1x_waitlist {
-	struct list_head list;
-	struct kref refcount;
-	u32 thresh;
-	enum host1x_intr_action action;
-	atomic_t state;
-	void *data;
-	int count;
-};
-
-/*
- * Schedule an action to be taken when a sync point reaches the given threshold.
- *
- * @id the sync point
- * @thresh the threshold
- * @action the action to take
- * @data a pointer to extra data depending on action, see above
- * @waiter waiter structure - assumes ownership
- * @ref must be passed if cancellation is possible, else NULL
- *
- * This is a non-blocking api.
- */
-int host1x_intr_add_action(struct host1x *host, struct host1x_syncpt *syncpt,
-			   u32 thresh, enum host1x_intr_action action,
-			   void *data, struct host1x_waitlist *waiter,
-			   void **ref);
-
-/*
- * Unreference an action submitted to host1x_intr_add_action().
- * You must call this if you passed non-NULL as ref.
- * @ref the ref returned from host1x_intr_add_action()
- * @flush wait until any pending handlers have completed before returning.
- */
-void host1x_intr_put_ref(struct host1x *host, unsigned int id, void *ref,
-			 bool flush);
+struct host1x_syncpt_fence;
 
 /* Initialize host1x sync point interrupt */
-int host1x_intr_init(struct host1x *host, unsigned int irq_sync);
+int host1x_intr_init(struct host1x *host);
 
 /* Deinitialize host1x sync point interrupt */
 void host1x_intr_deinit(struct host1x *host);
@@ -93,5 +23,10 @@ void host1x_intr_start(struct host1x *host);
 /* Disable host1x sync point interrupt */
 void host1x_intr_stop(struct host1x *host);
 
-irqreturn_t host1x_syncpt_thresh_fn(void *dev_id);
+void host1x_intr_handle_interrupt(struct host1x *host, unsigned int id);
+
+void host1x_intr_add_fence_locked(struct host1x *host, struct host1x_syncpt_fence *fence);
+
+bool host1x_intr_remove_fence(struct host1x *host, struct host1x_syncpt_fence *fence);
+
 #endif
diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c
index b2761aa03b95..3ed49e1fd933 100644
--- a/drivers/gpu/host1x/job.c
+++ b/drivers/gpu/host1x/job.c
@@ -88,9 +88,15 @@ static void job_free(struct kref *ref)
 	if (job->release)
 		job->release(job);
 
-	if (job->waiter)
-		host1x_intr_put_ref(job->syncpt->host, job->syncpt->id,
-				    job->waiter, false);
+	if (job->fence) {
+		/*
+		 * remove_callback is atomic w.r.t. fence signaling, so
+		 * after the call returns, we know that the callback is not
+		 * in execution, and the fence can be safely freed.
+		 */
+		dma_fence_remove_callback(job->fence, &job->fence_cb);
+		dma_fence_put(job->fence);
+	}
 
 	if (job->syncpt)
 		host1x_syncpt_put(job->syncpt);
diff --git a/drivers/gpu/host1x/syncpt.c b/drivers/gpu/host1x/syncpt.c
index f87a8705f518..2d2007760eac 100644
--- a/drivers/gpu/host1x/syncpt.c
+++ b/drivers/gpu/host1x/syncpt.c
@@ -7,6 +7,7 @@
 
 #include <linux/module.h>
 #include <linux/device.h>
+#include <linux/dma-fence.h>
 #include <linux/slab.h>
 
 #include <trace/events/host1x.h>
@@ -209,17 +210,6 @@ int host1x_syncpt_incr(struct host1x_syncpt *sp)
 }
 EXPORT_SYMBOL(host1x_syncpt_incr);
 
-/*
- * Updated sync point form hardware, and returns true if syncpoint is expired,
- * false if we may need to wait
- */
-static bool syncpt_load_min_is_expired(struct host1x_syncpt *sp, u32 thresh)
-{
-	host1x_hw_syncpt_load(sp->host, sp);
-
-	return host1x_syncpt_is_expired(sp, thresh);
-}
-
 /**
  * host1x_syncpt_wait() - wait for a syncpoint to reach a given value
  * @sp: host1x syncpoint
@@ -230,10 +220,10 @@ static bool syncpt_load_min_is_expired(struct host1x_syncpt *sp, u32 thresh)
 int host1x_syncpt_wait(struct host1x_syncpt *sp, u32 thresh, long timeout,
 		       u32 *value)
 {
-	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
-	void *ref;
-	struct host1x_waitlist *waiter;
-	int err = 0, check_count = 0;
+	struct dma_fence *fence;
+	long wait_err;
+
+	host1x_hw_syncpt_load(sp->host, sp);
 
 	if (value)
 		*value = host1x_syncpt_load(sp);
@@ -241,73 +231,29 @@ int host1x_syncpt_wait(struct host1x_syncpt *sp, u32 thresh, long timeout,
 	if (host1x_syncpt_is_expired(sp, thresh))
 		return 0;
 
-	if (!timeout) {
-		err = -EAGAIN;
-		goto done;
-	}
-
-	/* allocate a waiter */
-	waiter = kzalloc(sizeof(*waiter), GFP_KERNEL);
-	if (!waiter) {
-		err = -ENOMEM;
-		goto done;
-	}
-
-	/* schedule a wakeup when the syncpoint value is reached */
-	err = host1x_intr_add_action(sp->host, sp, thresh,
-				     HOST1X_INTR_ACTION_WAKEUP_INTERRUPTIBLE,
-				     &wq, waiter, &ref);
-	if (err)
-		goto done;
-
-	err = -EAGAIN;
-	/* Caller-specified timeout may be impractically low */
 	if (timeout < 0)
 		timeout = LONG_MAX;
+	else if (timeout == 0)
+		return -EAGAIN;
 
-	/* wait for the syncpoint, or timeout, or signal */
-	while (timeout) {
-		long check = min_t(long, SYNCPT_CHECK_PERIOD, timeout);
-		int remain;
-
-		remain = wait_event_interruptible_timeout(wq,
-				syncpt_load_min_is_expired(sp, thresh),
-				check);
-		if (remain > 0 || host1x_syncpt_is_expired(sp, thresh)) {
-			if (value)
-				*value = host1x_syncpt_load(sp);
+	fence = host1x_fence_create(sp, thresh, false);
+	if (IS_ERR(fence))
+		return PTR_ERR(fence);
 
-			err = 0;
+	wait_err = dma_fence_wait_timeout(fence, true, timeout);
+	if (wait_err == 0)
+		host1x_fence_cancel(fence);
+	dma_fence_put(fence);
 
-			break;
-		}
-
-		if (remain < 0) {
-			err = remain;
-			break;
-		}
-
-		timeout -= check;
-
-		if (timeout && check_count <= MAX_STUCK_CHECK_COUNT) {
-			dev_warn(sp->host->dev,
-				"%s: syncpoint id %u (%s) stuck waiting %d, timeout=%ld\n",
-				 current->comm, sp->id, sp->name,
-				 thresh, timeout);
-
-			host1x_debug_dump_syncpts(sp->host);
-
-			if (check_count == MAX_STUCK_CHECK_COUNT)
-				host1x_debug_dump(sp->host);
-
-			check_count++;
-		}
-	}
-
-	host1x_intr_put_ref(sp->host, sp->id, ref, true);
+	if (value)
+		*value = host1x_syncpt_load(sp);
 
-done:
-	return err;
+	if (wait_err == 0)
+		return -EAGAIN;
+	else if (wait_err < 0)
+		return wait_err;
+	else
+		return 0;
 }
 EXPORT_SYMBOL(host1x_syncpt_wait);
 
diff --git a/drivers/gpu/host1x/syncpt.h b/drivers/gpu/host1x/syncpt.h
index 95cd29b79d6d..4c3f3b2f0e9c 100644
--- a/drivers/gpu/host1x/syncpt.h
+++ b/drivers/gpu/host1x/syncpt.h
@@ -14,6 +14,7 @@
 #include <linux/kref.h>
 #include <linux/sched.h>
 
+#include "fence.h"
 #include "intr.h"
 
 struct host1x;
@@ -39,7 +40,7 @@ struct host1x_syncpt {
 	struct host1x_syncpt_base *base;
 
 	/* interrupt data */
-	struct host1x_syncpt_intr intr;
+	struct host1x_fence_list fences;
 
 	/*
 	 * If a submission incrementing this syncpoint fails, lock it so that