dri-devel Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Rob Herring <robh@kernel.org>
To: dri-devel@lists.freedesktop.org
Cc: Maxime Ripard <maxime.ripard@bootlin.com>,
	Tomeu Vizoso <tomeu.vizoso@collabora.com>,
	David Airlie <airlied@linux.ie>, Sean Paul <sean@poorly.run>,
	Steven Price <steven.price@arm.com>,
	Boris Brezillon <boris.brezillon@collabora.com>,
	Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>,
	Robin Murphy <robin.murphy@arm.com>
Subject: [PATCH v2 7/8] drm/panfrost: Rework page table flushing and runtime PM interaction
Date: Thu, 22 Aug 2019 21:12:15 -0500	[thread overview]
Message-ID: <20190823021216.5862-8-robh@kernel.org> (raw)
In-Reply-To: <20190823021216.5862-1-robh@kernel.org>

There is no point in resuming the h/w just to do flush operations and
doing so takes several locks which cause lockdep issues with the shrinker.
Rework the flush operations to only happen when the h/w is already awake.
This avoids taking any locks associated with resuming.

Cc: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Cc: Steven Price <steven.price@arm.com>
Cc: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Daniel Vetter <daniel@ffwll.ch>
Signed-off-by: Rob Herring <robh@kernel.org>
---
v2: new patch

 drivers/gpu/drm/panfrost/panfrost_mmu.c | 41 ++++++++++++-------------
 1 file changed, 20 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index 842bdd7cf6be..ccf671a9c3fb 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -220,6 +220,23 @@ 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;
+
+	/* Flush the PTs only if we're already awake */
+	if (!pm_runtime_get_if_in_use(pfdev->dev))
+		return;
+
+	mmu_hw_do_operation(pfdev, mmu, iova, size, AS_COMMAND_FLUSH_PT);
+
+	pm_runtime_mark_last_busy(pfdev->dev);
+	pm_runtime_put_autosuspend(pfdev->dev);
+}
+
 static int mmu_map_sg(struct panfrost_device *pfdev, struct panfrost_mmu *mmu,
 		      u64 iova, int prot, struct sg_table *sgt)
 {
@@ -246,11 +263,10 @@ 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 +275,6 @@ 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 +287,7 @@ 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;
@@ -293,17 +301,12 @@ 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) {
@@ -318,13 +321,9 @@ 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;
 }
 
-- 
2.20.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

  parent reply	other threads:[~2019-08-23  2:12 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-23  2:12 (unknown) Rob Herring
2019-08-23  2:12 ` [PATCH v2 1/8] drm/panfrost: Fix possible suspend in panfrost_remove Rob Herring
2019-08-23 14:50   ` Steven Price
2019-08-23  2:12 ` [PATCH v2 2/8] drm/panfrost: Rework runtime PM initialization Rob Herring
2019-08-23 10:54   ` Robin Murphy
2019-08-23 12:16     ` Rob Herring
2019-08-23  2:12 ` [PATCH v2 3/8] drm/panfrost: Hold runtime PM reference until jobs complete Rob Herring
2019-08-23 14:50   ` Steven Price
2019-08-23 15:13     ` Rob Herring
2019-08-23  2:12 ` [PATCH v2 4/8] drm/shmem: Do dma_unmap_sg before purging pages Rob Herring
2019-08-23  2:12 ` [PATCH v2 5/8] drm/shmem: Use mutex_trylock in drm_gem_shmem_purge Rob Herring
2019-08-23 14:53   ` Steven Price
2019-08-23  2:12 ` [PATCH v2 6/8] drm/panfrost: Use mutex_trylock in panfrost_gem_purge Rob Herring
2019-08-23 14:55   ` Steven Price
2019-08-23  2:12 ` Rob Herring [this message]
2019-08-23 11:11   ` [PATCH v2 7/8] drm/panfrost: Rework page table flushing and runtime PM interaction Robin Murphy
2019-08-23 15:05     ` Steven Price
2019-08-23 15:44       ` Robin Murphy
2019-08-23 15:57         ` Rob Herring
2019-08-23 16:16           ` Robin Murphy
2019-08-23 16:45             ` Rob Herring
2019-08-23 15:09   ` Steven Price
2019-08-23 15:49     ` Rob Herring
2019-08-23  2:12 ` [PATCH v2 8/8] drm/panfrost: Remove unnecessary flushing from tlb_inv_context Rob Herring
2019-08-23 12:56   ` Robin Murphy
2019-08-23 13:18     ` Rob Herring
2019-08-23 14:05       ` Robin Murphy
2019-08-23 14:26         ` Rob Herring
2019-08-23 14:56           ` Robin Murphy
2019-08-23 15:12   ` Steven Price

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190823021216.5862-8-robh@kernel.org \
    --to=robh@kernel.org \
    --cc=airlied@linux.ie \
    --cc=alyssa.rosenzweig@collabora.com \
    --cc=boris.brezillon@collabora.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=maxime.ripard@bootlin.com \
    --cc=robin.murphy@arm.com \
    --cc=sean@poorly.run \
    --cc=steven.price@arm.com \
    --cc=tomeu.vizoso@collabora.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox