Merge tag 'drm-misc-next-fixes-2019-09-06' of git://anongit.freedesktop.org/drm/drm-misc into drm-next

 - A significant number of panfrost fixes for runtime_pm, MMU and GEM support
 - A fix for DCS transfers on mcde

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

From: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190906070500.dfxacpgxoxalcha3@flea

9 files changed, 149 insertions, 114 deletions

diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
index df8f2c8adb2b..f5918707672f 100644
--- a/drivers/gpu/drm/drm_gem_shmem_helper.c
+++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
@@ -390,6 +390,12 @@ void drm_gem_shmem_purge_locked(struct drm_gem_object *obj)
 
 	WARN_ON(!drm_gem_shmem_is_purgeable(shmem));
 
+	dma_unmap_sg(obj->dev->dev, shmem->sgt->sgl,
+		     shmem->sgt->nents, DMA_BIDIRECTIONAL);
+	sg_free_table(shmem->sgt);
+	kfree(shmem->sgt);
+	shmem->sgt = NULL;
+
 	drm_gem_shmem_put_pages_locked(shmem);
 
 	shmem->madv = -1;
@@ -409,13 +415,16 @@ void drm_gem_shmem_purge_locked(struct drm_gem_object *obj)
 }
 EXPORT_SYMBOL(drm_gem_shmem_purge_locked);
 
-void drm_gem_shmem_purge(struct drm_gem_object *obj)
+bool drm_gem_shmem_purge(struct drm_gem_object *obj)
 {
 	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
 
-	mutex_lock(&shmem->pages_lock);
+	if (!mutex_trylock(&shmem->pages_lock))
+		return false;
 	drm_gem_shmem_purge_locked(obj);
 	mutex_unlock(&shmem->pages_lock);
+
+	return true;
 }
 EXPORT_SYMBOL(drm_gem_shmem_purge);
 
diff --git a/drivers/gpu/drm/mcde/mcde_dsi.c b/drivers/gpu/drm/mcde/mcde_dsi.c
index 07f7090d08b3..f9c9e32b299c 100644
--- a/drivers/gpu/drm/mcde/mcde_dsi.c
+++ b/drivers/gpu/drm/mcde/mcde_dsi.c
@@ -178,22 +178,26 @@ static ssize_t mcde_dsi_host_transfer(struct mipi_dsi_host *host,
 	const u32 loop_delay_us = 10; /* us */
 	const u8 *tx = msg->tx_buf;
 	u32 loop_counter;
-	size_t txlen;
+	size_t txlen = msg->tx_len;
+	size_t rxlen = msg->rx_len;
 	u32 val;
 	int ret;
 	int i;
 
-	txlen = msg->tx_len;
-	if (txlen > 12) {
+	if (txlen > 16) {
 		dev_err(d->dev,
-			"dunno how to write more than 12 bytes yet\n");
+			"dunno how to write more than 16 bytes yet\n");
+		return -EIO;
+	}
+	if (rxlen > 4) {
+		dev_err(d->dev,
+			"dunno how to read more than 4 bytes yet\n");
 		return -EIO;
 	}
 
 	dev_dbg(d->dev,
-		"message to channel %d, %zd bytes",
-		msg->channel,
-		txlen);
+		"message to channel %d, write %zd bytes read %zd bytes\n",
+		msg->channel, txlen, rxlen);
 
 	/* Command "nature" */
 	if (MCDE_DSI_HOST_IS_READ(msg->type))
@@ -210,9 +214,7 @@ static ssize_t mcde_dsi_host_transfer(struct mipi_dsi_host *host,
 	if (mipi_dsi_packet_format_is_long(msg->type))
 		val |= DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_LONGNOTSHORT;
 	val |= 0 << DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_ID_SHIFT;
-	/* Add one to the length for the MIPI DCS command */
-	val |= txlen
-		<< DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_SIZE_SHIFT;
+	val |= txlen << DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_SIZE_SHIFT;
 	val |= DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_LP_EN;
 	val |= msg->type << DSI_DIRECT_CMD_MAIN_SETTINGS_CMD_HEAD_SHIFT;
 	writel(val, d->regs + DSI_DIRECT_CMD_MAIN_SETTINGS);
@@ -249,17 +251,36 @@ static ssize_t mcde_dsi_host_transfer(struct mipi_dsi_host *host,
 	writel(1, d->regs + DSI_DIRECT_CMD_SEND);
 
 	loop_counter = 1000 * 1000 / loop_delay_us;
-	while (!(readl(d->regs + DSI_DIRECT_CMD_STS) &
-		 DSI_DIRECT_CMD_STS_WRITE_COMPLETED)
-	       && --loop_counter)
-		usleep_range(loop_delay_us, (loop_delay_us * 3) / 2);
-
-	if (!loop_counter) {
-		dev_err(d->dev, "DSI write timeout!\n");
-		return -ETIME;
+	if (MCDE_DSI_HOST_IS_READ(msg->type)) {
+		/* Read command */
+		while (!(readl(d->regs + DSI_DIRECT_CMD_STS) &
+			 (DSI_DIRECT_CMD_STS_READ_COMPLETED |
+			  DSI_DIRECT_CMD_STS_READ_COMPLETED_WITH_ERR))
+		       && --loop_counter)
+			usleep_range(loop_delay_us, (loop_delay_us * 3) / 2);
+		if (!loop_counter) {
+			dev_err(d->dev, "DSI read timeout!\n");
+			return -ETIME;
+		}
+	} else {
+		/* Writing only */
+		while (!(readl(d->regs + DSI_DIRECT_CMD_STS) &
+			 DSI_DIRECT_CMD_STS_WRITE_COMPLETED)
+		       && --loop_counter)
+			usleep_range(loop_delay_us, (loop_delay_us * 3) / 2);
+
+		if (!loop_counter) {
+			dev_err(d->dev, "DSI write timeout!\n");
+			return -ETIME;
+		}
 	}
 
 	val = readl(d->regs + DSI_DIRECT_CMD_STS);
+	if (val & DSI_DIRECT_CMD_STS_READ_COMPLETED_WITH_ERR) {
+		dev_err(d->dev, "read completed with error\n");
+		writel(1, d->regs + DSI_DIRECT_CMD_RD_INIT);
+		return -EIO;
+	}
 	if (val & DSI_DIRECT_CMD_STS_ACKNOWLEDGE_WITH_ERR_RECEIVED) {
 		val >>= DSI_DIRECT_CMD_STS_ACK_VAL_SHIFT;
 		dev_err(d->dev, "error during transmission: %04x\n",
@@ -269,10 +290,7 @@ static ssize_t mcde_dsi_host_transfer(struct mipi_dsi_host *host,
 
 	if (!MCDE_DSI_HOST_IS_READ(msg->type)) {
 		/* Return number of bytes written */
-		if (mipi_dsi_packet_format_is_long(msg->type))
-			ret = 4 + txlen;
-		else
-			ret = 4;
+		ret = txlen;
 	} else {
 		/* OK this is a read command, get the response */
 		u32 rdsz;
@@ -282,7 +300,13 @@ static ssize_t mcde_dsi_host_transfer(struct mipi_dsi_host *host,
 		rdsz = readl(d->regs + DSI_DIRECT_CMD_RD_PROPERTY);
 		rdsz &= DSI_DIRECT_CMD_RD_PROPERTY_RD_SIZE_MASK;
 		rddat = readl(d->regs + DSI_DIRECT_CMD_RDDAT);
-		for (i = 0; i < 4 && i < rdsz; i++)
+		if (rdsz < rxlen) {
+			dev_err(d->dev, "read error, requested %zd got %d\n",
+				rxlen, rdsz);
+			return -EIO;
+		}
+		/* FIXME: read more than 4 bytes */
+		for (i = 0; i < 4 && i < rxlen; i++)
 			rx[i] = (rddat >> (i * 8)) & 0xff;
 		ret = rdsz;
 	}
diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.c b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
index 710d903f8e0d..a1f5fa6a742a 100644
--- a/drivers/gpu/drm/panfrost/panfrost_devfreq.c
+++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
@@ -53,8 +53,10 @@ static int panfrost_devfreq_target(struct device *dev, unsigned long *freq,
 	if (err) {
 		dev_err(dev, "Cannot set frequency %lu (%d)\n", target_rate,
 			err);
-		regulator_set_voltage(pfdev->regulator, pfdev->devfreq.cur_volt,
-				      pfdev->devfreq.cur_volt);
+		if (pfdev->regulator)
+			regulator_set_voltage(pfdev->regulator,
+					      pfdev->devfreq.cur_volt,
+					      pfdev->devfreq.cur_volt);
 		return err;
 	}
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_device.c b/drivers/gpu/drm/panfrost/panfrost_device.c
index 4da71bb56c20..46b0b02e4289 100644
--- a/drivers/gpu/drm/panfrost/panfrost_device.c
+++ b/drivers/gpu/drm/panfrost/panfrost_device.c
@@ -5,7 +5,6 @@
 #include <linux/clk.h>
 #include <linux/reset.h>
 #include <linux/platform_device.h>
-#include <linux/pm_runtime.h>
 #include <linux/regulator/consumer.h>
 
 #include "panfrost_device.h"
@@ -125,7 +124,6 @@ int panfrost_device_init(struct panfrost_device *pfdev)
 	INIT_LIST_HEAD(&pfdev->scheduled_jobs);
 	INIT_LIST_HEAD(&pfdev->as_lru_list);
 
-	spin_lock_init(&pfdev->hwaccess_lock);
 	spin_lock_init(&pfdev->as_lock);
 
 	err = panfrost_clk_init(pfdev);
@@ -166,14 +164,6 @@ int panfrost_device_init(struct panfrost_device *pfdev)
 	if (err)
 		goto err_out4;
 
-	/* runtime PM will wake us up later */
-	panfrost_gpu_power_off(pfdev);
-
-	pm_runtime_set_active(pfdev->dev);
-	pm_runtime_get_sync(pfdev->dev);
-	pm_runtime_mark_last_busy(pfdev->dev);
-	pm_runtime_put_autosuspend(pfdev->dev);
-
 	err = panfrost_perfcnt_init(pfdev);
 	if (err)
 		goto err_out5;
diff --git a/drivers/gpu/drm/panfrost/panfrost_device.h b/drivers/gpu/drm/panfrost/panfrost_device.h
index f503c566e99f..9c39b9794811 100644
--- a/drivers/gpu/drm/panfrost/panfrost_device.h
+++ b/drivers/gpu/drm/panfrost/panfrost_device.h
@@ -63,8 +63,6 @@ struct panfrost_device {
 	struct drm_device *ddev;
 	struct platform_device *pdev;
 
-	spinlock_t hwaccess_lock;
-
 	void __iomem *iomem;
 	struct clk *clock;
 	struct clk *bus_clock;
@@ -104,7 +102,6 @@ struct panfrost_device {
 struct panfrost_mmu {
 	struct io_pgtable_cfg pgtbl_cfg;
 	struct io_pgtable_ops *pgtbl_ops;
-	struct mutex lock;
 	int as;
 	atomic_t as_count;
 	struct list_head list;
diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c
index 44a558c6e17e..bc2ddeb55f5d 100644
--- a/drivers/gpu/drm/panfrost/panfrost_drv.c
+++ b/drivers/gpu/drm/panfrost/panfrost_drv.c
@@ -523,10 +523,6 @@ static int panfrost_probe(struct platform_device *pdev)
 	mutex_init(&pfdev->shrinker_lock);
 	INIT_LIST_HEAD(&pfdev->shrinker_list);
 
-	pm_runtime_use_autosuspend(pfdev->dev);
-	pm_runtime_set_autosuspend_delay(pfdev->dev, 50); /* ~3 frames */
-	pm_runtime_enable(pfdev->dev);
-
 	err = panfrost_device_init(pfdev);
 	if (err) {
 		if (err != -EPROBE_DEFER)
@@ -541,6 +537,12 @@ static int panfrost_probe(struct platform_device *pdev)
 		goto err_out1;
 	}
 
+	pm_runtime_set_active(pfdev->dev);
+	pm_runtime_mark_last_busy(pfdev->dev);
+	pm_runtime_enable(pfdev->dev);
+	pm_runtime_set_autosuspend_delay(pfdev->dev, 50); /* ~3 frames */
+	pm_runtime_use_autosuspend(pfdev->dev);
+
 	/*
 	 * Register the DRM device with the core and the connectors with
 	 * sysfs
@@ -570,11 +572,13 @@ static int panfrost_remove(struct platform_device *pdev)
 
 	drm_dev_unregister(ddev);
 	panfrost_gem_shrinker_cleanup(ddev);
+
 	pm_runtime_get_sync(pfdev->dev);
-	pm_runtime_put_sync_autosuspend(pfdev->dev);
-	pm_runtime_disable(pfdev->dev);
 	panfrost_devfreq_fini(pfdev);
 	panfrost_device_fini(pfdev);
+	pm_runtime_put_sync_suspend(pfdev->dev);
+	pm_runtime_disable(pfdev->dev);
+
 	drm_dev_put(ddev);
 	return 0;
 }
diff --git a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
index d191632b6197..458f0fa68111 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c
@@ -36,15 +36,18 @@ panfrost_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc
 	return count;
 }
 
-static void panfrost_gem_purge(struct drm_gem_object *obj)
+static bool panfrost_gem_purge(struct drm_gem_object *obj)
 {
 	struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj);
-	mutex_lock(&shmem->pages_lock);
+
+	if (!mutex_trylock(&shmem->pages_lock))
+		return false;
 
 	panfrost_mmu_unmap(to_panfrost_bo(obj));
 	drm_gem_shmem_purge_locked(obj);
 
 	mutex_unlock(&shmem->pages_lock);
+	return true;
 }
 
 static unsigned long
@@ -61,8 +64,8 @@ panfrost_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
 	list_for_each_entry_safe(shmem, tmp, &pfdev->shrinker_list, madv_list) {
 		if (freed >= sc->nr_to_scan)
 			break;
-		if (drm_gem_shmem_is_purgeable(shmem)) {
-			panfrost_gem_purge(&shmem->base);
+		if (drm_gem_shmem_is_purgeable(shmem) &&
+		    panfrost_gem_purge(&shmem->base)) {
 			freed += shmem->base.size >> PAGE_SHIFT;
 			list_del_init(&shmem->madv_list);
 		}
diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
index 05c85f45a0de..a58551668d9a 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.c
+++ b/drivers/gpu/drm/panfrost/panfrost_job.c
@@ -141,7 +141,6 @@ static void panfrost_job_write_affinity(struct panfrost_device *pfdev,
 static void panfrost_job_hw_submit(struct panfrost_job *job, int js)
 {
 	struct panfrost_device *pfdev = job->pfdev;
-	unsigned long flags;
 	u32 cfg;
 	u64 jc_head = job->jc;
 	int ret;
@@ -150,13 +149,14 @@ static void panfrost_job_hw_submit(struct panfrost_job *job, int js)
 	if (ret < 0)
 		return;
 
-	if (WARN_ON(job_read(pfdev, JS_COMMAND_NEXT(js))))
-		goto end;
+	if (WARN_ON(job_read(pfdev, JS_COMMAND_NEXT(js)))) {
+		pm_runtime_put_sync_autosuspend(pfdev->dev);
+		return;
+	}
 
 	cfg = panfrost_mmu_as_get(pfdev, &job->file_priv->mmu);
 
 	panfrost_devfreq_record_transition(pfdev, js);
-	spin_lock_irqsave(&pfdev->hwaccess_lock, flags);
 
 	job_write(pfdev, JS_HEAD_NEXT_LO(js), jc_head & 0xFFFFFFFF);
 	job_write(pfdev, JS_HEAD_NEXT_HI(js), jc_head >> 32);
@@ -185,12 +185,6 @@ static void panfrost_job_hw_submit(struct panfrost_job *job, int js)
 				job, js, jc_head);
 
 	job_write(pfdev, JS_COMMAND_NEXT(js), JS_COMMAND_START);
-
-	spin_unlock_irqrestore(&pfdev->hwaccess_lock, flags);
-
-end:
-	pm_runtime_mark_last_busy(pfdev->dev);
-	pm_runtime_put_autosuspend(pfdev->dev);
 }
 
 static void panfrost_acquire_object_fences(struct drm_gem_object **bos,
@@ -369,6 +363,7 @@ static void panfrost_job_timedout(struct drm_sched_job *sched_job)
 	struct panfrost_job *job = to_panfrost_job(sched_job);
 	struct panfrost_device *pfdev = job->pfdev;
 	int js = panfrost_job_get_slot(job);
+	unsigned long flags;
 	int i;
 
 	/*
@@ -394,6 +389,15 @@ static void panfrost_job_timedout(struct drm_sched_job *sched_job)
 	if (sched_job)
 		drm_sched_increase_karma(sched_job);
 
+	spin_lock_irqsave(&pfdev->js->job_lock, flags);
+	for (i = 0; i < NUM_JOB_SLOTS; i++) {
+		if (pfdev->jobs[i]) {
+			pm_runtime_put_noidle(pfdev->dev);
+			pfdev->jobs[i] = NULL;
+		}
+	}
+	spin_unlock_irqrestore(&pfdev->js->job_lock, flags);
+
 	/* panfrost_core_dump(pfdev); */
 
 	panfrost_devfreq_record_transition(pfdev, js);
@@ -450,12 +454,21 @@ static irqreturn_t panfrost_job_irq_handler(int irq, void *data)
 		}
 
 		if (status & JOB_INT_MASK_DONE(j)) {
-			struct panfrost_job *job = pfdev->jobs[j];
+			struct panfrost_job *job;
+
+			spin_lock(&pfdev->js->job_lock);
+			job = pfdev->jobs[j];
+			/* Only NULL if job timeout occurred */
+			if (job) {
+				pfdev->jobs[j] = NULL;
+
+				panfrost_mmu_as_put(pfdev, &job->file_priv->mmu);
+				panfrost_devfreq_record_transition(pfdev, j);
 
-			pfdev->jobs[j] = NULL;
-			panfrost_mmu_as_put(pfdev, &job->file_priv->mmu);
-			panfrost_devfreq_record_transition(pfdev, j);
-			dma_fence_signal(job->done_fence);
+				dma_fence_signal_locked(job->done_fence);
+				pm_runtime_put_autosuspend(pfdev->dev);
+			}
+			spin_unlock(&pfdev->js->job_lock);
 		}
 
 		status &= ~mask;
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index 842bdd7cf6be..387d830cb7cf 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -80,19 +80,11 @@ static void lock_region(struct panfrost_device *pfdev, u32 as_nr,
 }
 
 
-static int mmu_hw_do_operation(struct panfrost_device *pfdev,
-			       struct panfrost_mmu *mmu,
-			       u64 iova, size_t size, u32 op)
+static int mmu_hw_do_operation_locked(struct panfrost_device *pfdev, int as_nr,
+				      u64 iova, size_t size, u32 op)
 {
-	int ret, as_nr;
-
-	spin_lock(&pfdev->as_lock);
-	as_nr = mmu->as;
-
-	if (as_nr < 0) {
-		spin_unlock(&pfdev->as_lock);
+	if (as_nr < 0)
 		return 0;
-	}
 
 	if (op != AS_COMMAND_UNLOCK)
 		lock_region(pfdev, as_nr, iova, size);
@@ -101,10 +93,18 @@ static int mmu_hw_do_operation(struct panfrost_device *pfdev,
 	write_cmd(pfdev, as_nr, op);
 
 	/* Wait for the flush to complete */
-	ret = wait_ready(pfdev, as_nr);
+	return wait_ready(pfdev, as_nr);
+}
 
-	spin_unlock(&pfdev->as_lock);
+static int mmu_hw_do_operation(struct panfrost_device *pfdev,
+			       struct panfrost_mmu *mmu,
+			       u64 iova, size_t size, u32 op)
+{
+	int ret;
 
+	spin_lock(&pfdev->as_lock);
+	ret = mmu_hw_do_operation_locked(pfdev, mmu->as, iova, size, op);
+	spin_unlock(&pfdev->as_lock);
 	return ret;
 }
 
@@ -115,6 +115,8 @@ static void panfrost_mmu_enable(struct panfrost_device *pfdev, struct panfrost_m
 	u64 transtab = cfg->arm_mali_lpae_cfg.transtab;
 	u64 memattr = cfg->arm_mali_lpae_cfg.memattr;
 
+	mmu_hw_do_operation_locked(pfdev, as_nr, 0, ~0UL, AS_COMMAND_FLUSH_MEM);
+
 	mmu_write(pfdev, AS_TRANSTAB_LO(as_nr), transtab & 0xffffffffUL);
 	mmu_write(pfdev, AS_TRANSTAB_HI(as_nr), transtab >> 32);
 
@@ -127,8 +129,10 @@ static void panfrost_mmu_enable(struct panfrost_device *pfdev, struct panfrost_m
 	write_cmd(pfdev, as_nr, AS_COMMAND_UPDATE);
 }
 
-static void mmu_disable(struct panfrost_device *pfdev, u32 as_nr)
+static void panfrost_mmu_disable(struct panfrost_device *pfdev, u32 as_nr)
 {
+	mmu_hw_do_operation_locked(pfdev, as_nr, 0, ~0UL, AS_COMMAND_FLUSH_MEM);
+
 	mmu_write(pfdev, AS_TRANSTAB_LO(as_nr), 0);
 	mmu_write(pfdev, AS_TRANSTAB_HI(as_nr), 0);
 
@@ -220,6 +224,22 @@ static size_t get_pgsize(u64 addr, size_t size)
 	return SZ_2M;
 }
 
+void panfrost_mmu_flush_range(struct panfrost_device *pfdev,
+			      struct panfrost_mmu *mmu,
+			      u64 iova, size_t size)
+{
+	if (mmu->as < 0)
+		return;
+
+	pm_runtime_get_noresume(pfdev->dev);
+
+	/* Flush the PTs only if we're already awake */
+	if (pm_runtime_active(pfdev->dev))
+		mmu_hw_do_operation(pfdev, mmu, iova, size, AS_COMMAND_FLUSH_PT);
+
+	pm_runtime_put_sync_autosuspend(pfdev->dev);
+}
+
 static int mmu_map_sg(struct panfrost_device *pfdev, struct panfrost_mmu *mmu,
 		      u64 iova, int prot, struct sg_table *sgt)
 {
@@ -228,8 +248,6 @@ static int mmu_map_sg(struct panfrost_device *pfdev, struct panfrost_mmu *mmu,
 	struct io_pgtable_ops *ops = mmu->pgtbl_ops;
 	u64 start_iova = iova;
 
-	mutex_lock(&mmu->lock);
-
 	for_each_sg(sgt->sgl, sgl, sgt->nents, count) {
 		unsigned long paddr = sg_dma_address(sgl);
 		size_t len = sg_dma_len(sgl);
@@ -246,10 +264,7 @@ static int mmu_map_sg(struct panfrost_device *pfdev, struct panfrost_mmu *mmu,
 		}
 	}
 
-	mmu_hw_do_operation(pfdev, mmu, start_iova, iova - start_iova,
-			    AS_COMMAND_FLUSH_PT);
-
-	mutex_unlock(&mmu->lock);
+	panfrost_mmu_flush_range(pfdev, mmu, start_iova, iova - start_iova);
 
 	return 0;
 }
@@ -259,7 +274,6 @@ int panfrost_mmu_map(struct panfrost_gem_object *bo)
 	struct drm_gem_object *obj = &bo->base.base;
 	struct panfrost_device *pfdev = to_panfrost_device(obj->dev);
 	struct sg_table *sgt;
-	int ret;
 	int prot = IOMMU_READ | IOMMU_WRITE;
 
 	if (WARN_ON(bo->is_mapped))
@@ -272,14 +286,7 @@ int panfrost_mmu_map(struct panfrost_gem_object *bo)
 	if (WARN_ON(IS_ERR(sgt)))
 		return PTR_ERR(sgt);
 
-	ret = pm_runtime_get_sync(pfdev->dev);
-	if (ret < 0)
-		return ret;
-
 	mmu_map_sg(pfdev, bo->mmu, bo->node.start << PAGE_SHIFT, prot, sgt);
-
-	pm_runtime_mark_last_busy(pfdev->dev);
-	pm_runtime_put_autosuspend(pfdev->dev);
 	bo->is_mapped = true;
 
 	return 0;
@@ -293,19 +300,12 @@ void panfrost_mmu_unmap(struct panfrost_gem_object *bo)
 	u64 iova = bo->node.start << PAGE_SHIFT;
 	size_t len = bo->node.size << PAGE_SHIFT;
 	size_t unmapped_len = 0;
-	int ret;
 
 	if (WARN_ON(!bo->is_mapped))
 		return;
 
 	dev_dbg(pfdev->dev, "unmap: as=%d, iova=%llx, len=%zx", bo->mmu->as, iova, len);
 
-	ret = pm_runtime_get_sync(pfdev->dev);
-	if (ret < 0)
-		return;
-
-	mutex_lock(&bo->mmu->lock);
-
 	while (unmapped_len < len) {
 		size_t unmapped_page;
 		size_t pgsize = get_pgsize(iova, len - unmapped_len);
@@ -318,22 +318,12 @@ void panfrost_mmu_unmap(struct panfrost_gem_object *bo)
 		unmapped_len += pgsize;
 	}
 
-	mmu_hw_do_operation(pfdev, bo->mmu, bo->node.start << PAGE_SHIFT,
-			    bo->node.size << PAGE_SHIFT, AS_COMMAND_FLUSH_PT);
-
-	mutex_unlock(&bo->mmu->lock);
-
-	pm_runtime_mark_last_busy(pfdev->dev);
-	pm_runtime_put_autosuspend(pfdev->dev);
+	panfrost_mmu_flush_range(pfdev, bo->mmu, bo->node.start << PAGE_SHIFT, len);
 	bo->is_mapped = false;
 }
 
 static void mmu_tlb_inv_context_s1(void *cookie)
-{
-	struct panfrost_file_priv *priv = cookie;
-
-	mmu_hw_do_operation(priv->pfdev, &priv->mmu, 0, ~0UL, AS_COMMAND_FLUSH_MEM);
-}
+{}
 
 static void mmu_tlb_inv_range_nosync(unsigned long iova, size_t size,
 				     size_t granule, bool leaf, void *cookie)
@@ -356,7 +346,6 @@ int panfrost_mmu_pgtable_alloc(struct panfrost_file_priv *priv)
 	struct panfrost_mmu *mmu = &priv->mmu;
 	struct panfrost_device *pfdev = priv->pfdev;
 
-	mutex_init(&mmu->lock);
 	INIT_LIST_HEAD(&mmu->list);
 	mmu->as = -1;
 
@@ -383,6 +372,11 @@ void panfrost_mmu_pgtable_free(struct panfrost_file_priv *priv)
 
 	spin_lock(&pfdev->as_lock);
 	if (mmu->as >= 0) {
+		pm_runtime_get_noresume(pfdev->dev);
+		if (pm_runtime_active(pfdev->dev))
+			panfrost_mmu_disable(pfdev, mmu->as);
+		pm_runtime_put_autosuspend(pfdev->dev);
+
 		clear_bit(mmu->as, &pfdev->as_alloc_mask);
 		clear_bit(mmu->as, &pfdev->as_in_use_mask);
 		list_del(&mmu->list);
@@ -627,5 +621,4 @@ int panfrost_mmu_init(struct panfrost_device *pfdev)
 void panfrost_mmu_fini(struct panfrost_device *pfdev)
 {
 	mmu_write(pfdev, MMU_INT_MASK, 0);
-	mmu_disable(pfdev, 0);
 }