gpu: host1x: Update to Linux v5.19-rc1

Update the host1x driver to align with the latest upstream host1x
driver from Linux v5.19-rc1. Please note that the context bus support
is not included, because this needs to be built into the kernel.

Bug 3724727

Change-Id: Ic6fbe001462d160d1bb24f76038dd755c5550690
Signed-off-by: Jon Hunter <jonathanh@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvidia/+/2739538
Reviewed-by: svc_kernel_abi <svc_kernel_abi@nvidia.com>
Reviewed-by: Bibek Basu <bbasu@nvidia.com>

drivers/gpu/host1x/bus.c

@@ -5,6 +5,7 @@
  */
 
 #include <linux/debugfs.h>
+#include <linux/dma-mapping.h>
 #include <linux/host1x-next.h>
 #include <linux/of.h>
 #include <linux/seq_file.h>
@@ -762,7 +763,6 @@ EXPORT_SYMBOL(host1x_client_exit);
 /**
  * __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

drivers/gpu/host1x/channel.c

@@ -75,6 +75,14 @@ struct host1x_channel *host1x_channel_get_index(struct host1x *host,
 	return ch;
 }
 
+void host1x_channel_stop(struct host1x_channel *channel)
+{
+	struct host1x *host = dev_get_drvdata(channel->dev->parent);
+
+	host1x_hw_cdma_stop(host, &channel->cdma);
+}
+EXPORT_SYMBOL(host1x_channel_stop);
+
 static void release_channel(struct kref *kref)
 {
 	struct host1x_channel *channel =

drivers/gpu/host1x/debug.c

@@ -7,6 +7,7 @@
  */
 
 #include <linux/debugfs.h>
+#include <linux/pm_runtime.h>
 #include <linux/seq_file.h>
 #include <linux/uaccess.h>
 
@@ -52,6 +53,11 @@ static int show_channel(struct host1x_channel *ch, void *data, bool show_fifo)
 {
 	struct host1x *m = dev_get_drvdata(ch->dev->parent);
 	struct output *o = data;
+	int err;
+
+	err = pm_runtime_resume_and_get(m->dev);
+	if (err < 0)
+		return err;
 
 	mutex_lock(&ch->cdma.lock);
 	mutex_lock(&debug_lock);
@@ -64,16 +70,23 @@ static int show_channel(struct host1x_channel *ch, void *data, bool show_fifo)
 	mutex_unlock(&debug_lock);
 	mutex_unlock(&ch->cdma.lock);
 
+	pm_runtime_put(m->dev);
+
 	return 0;
 }
 
-static void show_syncpts(struct host1x *m, struct output *o)
+static void show_syncpts(struct host1x *m, struct output *o, bool show_all)
 {
 	struct list_head *pos;
 	unsigned int i;
+	int err;
 
 	host1x_debug_output(o, "---- syncpts ----\n");
 
+	err = pm_runtime_resume_and_get(m->dev);
+	if (err < 0)
+		return;
+
 	for (i = 0; i < host1x_syncpt_nb_pts(m); i++) {
 		u32 max = host1x_syncpt_read_max(m->syncpt + i);
 		u32 min = host1x_syncpt_load(m->syncpt + i);
@@ -84,7 +97,10 @@ static void show_syncpts(struct host1x *m, struct output *o)
 			waiters++;
 		spin_unlock(&m->syncpt[i].intr.lock);
 
-		if (!min && !max && !waiters)
+		if (!kref_read(&m->syncpt[i].ref))
+			continue;
+
+		if (!show_all && !min && !max && !waiters)
 			continue;
 
 		host1x_debug_output(o,
@@ -101,6 +117,8 @@ static void show_syncpts(struct host1x *m, struct output *o)
 					    base_val);
 	}
 
+	pm_runtime_put(m->dev);
+
 	host1x_debug_output(o, "\n");
 }
 
@@ -109,7 +127,7 @@ static void show_all(struct host1x *m, struct output *o, bool show_fifo)
 	unsigned int i;
 
 	host1x_hw_show_mlocks(m, o);
-	show_syncpts(m, o);
+	show_syncpts(m, o, true);
 	host1x_debug_output(o, "---- channels ----\n");
 
 	for (i = 0; i < m->info->nb_channels; ++i) {
@@ -226,5 +244,5 @@ void host1x_debug_dump_syncpts(struct host1x *host1x)
 		.fn = write_to_printk
 	};
 
-	show_syncpts(host1x, &o);
+	show_syncpts(host1x, &o, false);
 }

drivers/gpu/host1x/dev.c

@@ -6,18 +6,27 @@
  */
 
 #include <linux/clk.h>
+#include <linux/delay.h>
 #include <linux/dma-mapping.h>
 #include <linux/io.h>
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/of_device.h>
 #include <linux/of.h>
+#include <linux/pm_runtime.h>
 #include <linux/slab.h>
+#include <linux/version.h>
+
+#include <soc/tegra/common.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/host1x.h>
 #undef CREATE_TRACE_POINTS
 
+#if IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)
+#include <asm/dma-iommu.h>
+#endif
+
 #include "bus.h"
 #include "channel.h"
 #include "debug.h"
@@ -250,6 +259,9 @@ static void host1x_setup_sid_table(struct host1x *host)
 	const struct host1x_info *info = host->info;
 	unsigned int i;
 
+	if (!info->has_hypervisor)
+		return;
+
 	for (i = 0; i < info->num_sid_entries; i++) {
 		const struct host1x_sid_entry *entry = &info->sid_table[i];
 
@@ -298,6 +310,17 @@ static struct iommu_domain *host1x_iommu_attach(struct host1x *host)
 	struct iommu_domain *domain = iommu_get_domain_for_dev(host->dev);
 	int err;
 
+#if IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)
+	if (host->dev->archdata.mapping) {
+		struct dma_iommu_mapping *mapping =
+				to_dma_iommu_mapping(host->dev);
+		arm_iommu_detach_device(host->dev);
+		arm_iommu_release_mapping(mapping);
+
+		domain = iommu_get_domain_for_dev(host->dev);
+	}
+#endif
+
 	/*
 	 * We may not always want to enable IOMMU support (for example if the
 	 * host1x firewall is already enabled and we don't support addressing
@@ -407,6 +430,27 @@ static void host1x_iommu_exit(struct host1x *host)
 	}
 }
 
+static int host1x_get_resets(struct host1x *host)
+{
+	int err;
+
+	host->resets[0].id = "mc";
+	host->resets[1].id = "host1x";
+	host->nresets = ARRAY_SIZE(host->resets);
+
+	err = devm_reset_control_bulk_get_optional_exclusive_released(
+				host->dev, host->nresets, host->resets);
+	if (err) {
+		dev_err(host->dev, "failed to get reset: %d\n", err);
+		return err;
+	}
+
+	if (WARN_ON(!host->resets[1].rstc))
+		return -ENOENT;
+
+	return 0;
+}
+
 static int host1x_probe(struct platform_device *pdev)
 {
 	struct host1x *host;
@@ -446,7 +490,6 @@ static int host1x_probe(struct platform_device *pdev)
 	if (syncpt_irq < 0)
 		return syncpt_irq;
 
-	host1x_bo_cache_init(&host->cache);
 	mutex_init(&host->devices_lock);
 	INIT_LIST_HEAD(&host->devices);
 	INIT_LIST_HEAD(&host->list);
@@ -484,17 +527,16 @@ static int host1x_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	host->rst = devm_reset_control_get(&pdev->dev, "host1x");
+	err = host1x_get_resets(host);
-	if (IS_ERR(host->rst)) {
+	if (err)
-		err = PTR_ERR(host->rst);
-		dev_err(&pdev->dev, "failed to get reset: %d\n", err);
 		return err;
-	}
+
+	host1x_bo_cache_init(&host->cache);
 
 	err = host1x_iommu_init(host);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to setup IOMMU: %d\n", err);
-		return err;
+		goto destroy_cache;
 	}
 
 	err = host1x_channel_list_init(&host->channel_list,
@@ -504,22 +546,10 @@ static int host1x_probe(struct platform_device *pdev)
 		goto iommu_exit;
 	}
 
-	err = clk_prepare_enable(host->clk);
-	if (err < 0) {
-		dev_err(&pdev->dev, "failed to enable clock\n");
-		goto free_channels;
-	}
-
-	err = reset_control_deassert(host->rst);
-	if (err < 0) {
-		dev_err(&pdev->dev, "failed to deassert reset: %d\n", err);
-		goto unprepare_disable;
-	}
-
 	err = host1x_syncpt_init(host);
 	if (err) {
 		dev_err(&pdev->dev, "failed to initialize syncpts\n");
-		goto reset_assert;
+		goto free_channels;
 	}
 
 	err = host1x_intr_init(host, syncpt_irq);
@@ -528,10 +558,20 @@ static int host1x_probe(struct platform_device *pdev)
 		goto deinit_syncpt;
 	}
 
-	host1x_debug_init(host);
+	pm_runtime_enable(&pdev->dev);
 
-	if (host->info->has_hypervisor)
+#if LINUX_VERSION_CODE >= KERNEL_VERSION(5, 17, 0)
-		host1x_setup_sid_table(host);
+	err = devm_tegra_core_dev_init_opp_table_common(&pdev->dev);
+	if (err)
+		goto pm_disable;
+#endif
+
+	/* the driver's code isn't ready yet for the dynamic RPM */
+	err = pm_runtime_resume_and_get(&pdev->dev);
+	if (err)
+		goto pm_disable;
+
+	host1x_debug_init(host);
 
 	err = host1x_register(host);
 	if (err < 0)
@@ -547,17 +587,20 @@ unregister:
 	host1x_unregister(host);
 deinit_debugfs:
 	host1x_debug_deinit(host);
+
+	pm_runtime_put_sync_suspend(&pdev->dev);
+pm_disable:
+	pm_runtime_disable(&pdev->dev);
+
 	host1x_intr_deinit(host);
 deinit_syncpt:
 	host1x_syncpt_deinit(host);
-reset_assert:
-	reset_control_assert(host->rst);
-unprepare_disable:
-	clk_disable_unprepare(host->clk);
 free_channels:
 	host1x_channel_list_free(&host->channel_list);
 iommu_exit:
 	host1x_iommu_exit(host);
+destroy_cache:
+	host1x_bo_cache_destroy(&host->cache);
 
 	return err;
 }
@@ -568,20 +611,95 @@ static int host1x_remove(struct platform_device *pdev)
 
 	host1x_unregister(host);
 	host1x_debug_deinit(host);
+
+	pm_runtime_force_suspend(&pdev->dev);
+
 	host1x_intr_deinit(host);
 	host1x_syncpt_deinit(host);
-	reset_control_assert(host->rst);
+	host1x_channel_list_free(&host->channel_list);
-	clk_disable_unprepare(host->clk);
 	host1x_iommu_exit(host);
 	host1x_bo_cache_destroy(&host->cache);
 
 	return 0;
 }
 
+static int __maybe_unused host1x_runtime_suspend(struct device *dev)
+{
+	struct host1x *host = dev_get_drvdata(dev);
+	int err;
+
+	host1x_intr_stop(host);
+	host1x_syncpt_save(host);
+
+	err = reset_control_bulk_assert(host->nresets, host->resets);
+	if (err) {
+		dev_err(dev, "failed to assert reset: %d\n", err);
+		goto resume_host1x;
+	}
+
+	usleep_range(1000, 2000);
+
+	clk_disable_unprepare(host->clk);
+	reset_control_bulk_release(host->nresets, host->resets);
+
+	return 0;
+
+resume_host1x:
+	host1x_setup_sid_table(host);
+	host1x_syncpt_restore(host);
+	host1x_intr_start(host);
+
+	return err;
+}
+
+static int __maybe_unused host1x_runtime_resume(struct device *dev)
+{
+	struct host1x *host = dev_get_drvdata(dev);
+	int err;
+
+	err = reset_control_bulk_acquire(host->nresets, host->resets);
+	if (err) {
+		dev_err(dev, "failed to acquire reset: %d\n", err);
+		return err;
+	}
+
+	err = clk_prepare_enable(host->clk);
+	if (err) {
+		dev_err(dev, "failed to enable clock: %d\n", err);
+		goto release_reset;
+	}
+
+	err = reset_control_bulk_deassert(host->nresets, host->resets);
+	if (err < 0) {
+		dev_err(dev, "failed to deassert reset: %d\n", err);
+		goto disable_clk;
+	}
+
+	host1x_setup_sid_table(host);
+	host1x_syncpt_restore(host);
+	host1x_intr_start(host);
+
+	return 0;
+
+disable_clk:
+	clk_disable_unprepare(host->clk);
+release_reset:
+	reset_control_bulk_release(host->nresets, host->resets);
+
+	return err;
+}
+
+static const struct dev_pm_ops host1x_pm_ops = {
+	SET_RUNTIME_PM_OPS(host1x_runtime_suspend, host1x_runtime_resume,
+			   NULL)
+	/* TODO: add system suspend-resume once driver will be ready for that */
+};
+
 static struct platform_driver tegra_host1x_driver = {
 	.driver = {
 		.name = "tegra-host1x",
 		.of_match_table = host1x_of_match,
+		.pm = &host1x_pm_ops,
 	},
 	.probe = host1x_probe,
 	.remove = host1x_remove,

drivers/gpu/host1x/dev.h

@@ -118,7 +118,8 @@ struct host1x {
 	struct host1x_syncpt_base *bases;
 	struct device *dev;
 	struct clk *clk;
-	struct reset_control *rst;
+	struct reset_control_bulk_data resets[2];
+	unsigned int nresets;
 
 	struct iommu_group *group;
 	struct iommu_domain *domain;

drivers/gpu/host1x/fence.c

@@ -15,7 +15,7 @@
 #include "intr.h"
 #include "syncpt.h"
 
-DEFINE_SPINLOCK(lock);
+static DEFINE_SPINLOCK(lock);
 
 struct host1x_syncpt_fence {
 	struct dma_fence base;

drivers/gpu/host1x/hw/channel_hw.c

@@ -159,6 +159,27 @@ static void host1x_channel_set_streamid(struct host1x_channel *channel)
 #endif
 }
 
+static void host1x_enable_gather_filter(struct host1x_channel *ch)
+{
+#if HOST1X_HW >= 6
+	struct host1x *host = dev_get_drvdata(ch->dev->parent);
+	u32 val;
+
+	if (!host->hv_regs)
+		return;
+
+	val = host1x_hypervisor_readl(
+		host, HOST1X_HV_CH_KERNEL_FILTER_GBUFFER(ch->id / 32));
+	val |= BIT(ch->id % 32);
+	host1x_hypervisor_writel(
+		host, val, HOST1X_HV_CH_KERNEL_FILTER_GBUFFER(ch->id / 32));
+#elif HOST1X_HW >= 4
+	host1x_ch_writel(ch,
+			 HOST1X_CHANNEL_CHANNELCTRL_KERNEL_FILTER_GBUFFER(1),
+			 HOST1X_CHANNEL_CHANNELCTRL);
+#endif
+}
+
 static int channel_submit(struct host1x_job *job)
 {
 	struct host1x_channel *ch = job->channel;
@@ -190,6 +211,7 @@ static int channel_submit(struct host1x_job *job)
 	}
 
 	host1x_channel_set_streamid(ch);
+	host1x_enable_gather_filter(ch);
 
 	/* begin a CDMA submit */
 	err = host1x_cdma_begin(&ch->cdma, job);
@@ -251,27 +273,6 @@ error:
 	return err;
 }
 
-static void enable_gather_filter(struct host1x *host,
-				 struct host1x_channel *ch)
-{
-#if HOST1X_HW >= 6
-	u32 val;
-
-	if (!host->hv_regs)
-		return;
-
-	val = host1x_hypervisor_readl(
-		host, HOST1X_HV_CH_KERNEL_FILTER_GBUFFER(ch->id / 32));
-	val |= BIT(ch->id % 32);
-	host1x_hypervisor_writel(
-		host, val, HOST1X_HV_CH_KERNEL_FILTER_GBUFFER(ch->id / 32));
-#elif HOST1X_HW >= 4
-	host1x_ch_writel(ch,
-			 HOST1X_CHANNEL_CHANNELCTRL_KERNEL_FILTER_GBUFFER(1),
-			 HOST1X_CHANNEL_CHANNELCTRL);
-#endif
-}
-
 static int host1x_channel_init(struct host1x_channel *ch, struct host1x *dev,
 			       unsigned int index)
 {
@@ -280,7 +281,6 @@ static int host1x_channel_init(struct host1x_channel *ch, struct host1x *dev,
 #else
 	ch->regs = dev->regs + index * 0x100;
 #endif
-	enable_gather_filter(dev, ch);
 	return 0;
 }
 

drivers/gpu/host1x/include/linux/host1x-next.h

@@ -89,6 +89,7 @@ struct host1x_client_ops {
  * @parent: pointer to parent structure
  * @usecount: reference count for this structure
  * @lock: mutex for mutually exclusive concurrency
+ * @cache: host1x buffer object cache
  */
 struct host1x_client {
 	struct list_head list;
@@ -143,7 +144,7 @@ struct host1x_bo_ops {
 	struct host1x_bo *(*get)(struct host1x_bo *bo);
 	void (*put)(struct host1x_bo *bo);
 	struct host1x_bo_mapping *(*pin)(struct device *dev, struct host1x_bo *bo,
-					 enum dma_data_direction direction);
+					 enum dma_data_direction dir);
 	void (*unpin)(struct host1x_bo_mapping *map);
 	void *(*mmap)(struct host1x_bo *bo);
 	void (*munmap)(struct host1x_bo *bo, void *addr);
@@ -235,6 +236,7 @@ struct host1x_job;
 
 struct host1x_channel *host1x_channel_request(struct host1x_client *client);
 struct host1x_channel *host1x_channel_get(struct host1x_channel *channel);
+void host1x_channel_stop(struct host1x_channel *channel);
 void host1x_channel_put(struct host1x_channel *channel);
 int host1x_job_submit(struct host1x_job *job);
 

drivers/gpu/host1x/intr.c

@@ -297,14 +297,11 @@ int host1x_intr_init(struct host1x *host, unsigned int irq_sync)
 			 "host1x_sp_%02u", id);
 	}
 
-	host1x_intr_start(host);
-
 	return 0;
 }
 
 void host1x_intr_deinit(struct host1x *host)
 {
-	host1x_intr_stop(host);
 }
 
 void host1x_intr_start(struct host1x *host)

drivers/gpu/host1x/job.c

@@ -141,11 +141,9 @@ static unsigned int pin_job(struct host1x *host, struct host1x_job *job)
 	struct host1x_client *client = job->client;
 	struct device *dev = client->dev;
 	struct host1x_job_gather *g;
-	struct iommu_domain *domain;
 	unsigned int i;
 	int err;
 
-	domain = iommu_get_domain_for_dev(dev);
 	job->num_unpins = 0;
 
 	for (i = 0; i < job->num_relocs; i++) {

drivers/gpu/host1x/syncpt.c

@@ -137,12 +137,21 @@ void host1x_syncpt_restore(struct host1x *host)
 	struct host1x_syncpt *sp_base = host->syncpt;
 	unsigned int i;
 
-	for (i = 0; i < host1x_syncpt_nb_pts(host); i++)
+	for (i = 0; i < host1x_syncpt_nb_pts(host); i++) {
+		/*
+		 * Unassign syncpt from channels for purposes of Tegra186
+		 * syncpoint protection. This prevents any channel from
+		 * accessing it until it is reassigned.
+		 */
+		host1x_hw_syncpt_assign_to_channel(host, sp_base + i, NULL);
 		host1x_hw_syncpt_restore(host, sp_base + i);
+	}
 
 	for (i = 0; i < host1x_syncpt_nb_bases(host); i++)
 		host1x_hw_syncpt_restore_wait_base(host, sp_base + i);
 
+	host1x_hw_syncpt_enable_protection(host);
+
 	wmb();
 }
 
@@ -335,13 +344,6 @@ int host1x_syncpt_init(struct host1x *host)
 	for (i = 0; i < host->info->nb_pts; i++) {
 		syncpt[i].id = i;
 		syncpt[i].host = host;
-
-		/*
-		 * Unassign syncpt from channels for purposes of Tegra186
-		 * syncpoint protection. This prevents any channel from
-		 * accessing it until it is reassigned.
-		 */
-		host1x_hw_syncpt_assign_to_channel(host, &syncpt[i], NULL);
 	}
 
 	for (i = 0; i < host->info->nb_bases; i++)
@@ -351,9 +353,6 @@ int host1x_syncpt_init(struct host1x *host)
 	host->syncpt = syncpt;
 	host->bases = bases;
 
-	host1x_syncpt_restore(host);
-	host1x_hw_syncpt_enable_protection(host);
-
 	/* Allocate sync point to use for clearing waits for expired fences */
 	host->nop_sp = host1x_syncpt_alloc(host, 0, "reserved-nop");
 	if (!host->nop_sp)