diff mbox series

drm/panfrost: Add support for 2MB page entries

Message ID 20190411215313.1937-1-robh@kernel.org
State Accepted
Commit 4dff47c7607a7ceb9916fec179dc88e7b90f3b7c
Headers show
Series drm/panfrost: Add support for 2MB page entries | expand

Commit Message

Rob Herring April 11, 2019, 9:53 p.m. UTC 
Add support for 2MB sized pages. This will improve our map and unmap
times and save a bit of memory by avoiding 3rd level page tables for
contiguous allocations.

As we use shmem for buffers and huge page allocations for shmem are off
by default, there isn't an improvement out of the box and userspace must
enable THP for shmem.

It's not clear if the h/w can support 1GB page sizes which standard
ARM long format descriptors support. In any case, it is unlikely we'll
see any contiguous 1GB allocations on current h/w.

Cc: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Daniel Vetter <daniel@ffwll.ch>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 drivers/gpu/drm/panfrost/panfrost_mmu.c | 32 ++++++++++++++++++-------
 1 file changed, 24 insertions(+), 8 deletions(-)

Comments

Alyssa Rosenzweig April 11, 2019, 9:54 p.m. UTC | #1 
Acked-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Steven Price April 12, 2019, 10:40 a.m. UTC | #2 
On 11/04/2019 22:53, Rob Herring wrote:
> Add support for 2MB sized pages. This will improve our map and unmap
> times and save a bit of memory by avoiding 3rd level page tables for
> contiguous allocations.
> 
> As we use shmem for buffers and huge page allocations for shmem are off
> by default, there isn't an improvement out of the box and userspace must
> enable THP for shmem.
> 
> It's not clear if the h/w can support 1GB page sizes which standard
> ARM long format descriptors support. In any case, it is unlikely we'll
> see any contiguous 1GB allocations on current h/w.
> 
> Cc: Tomeu Vizoso <tomeu.vizoso@collabora.com>
> Cc: David Airlie <airlied@linux.ie>
> Cc: Daniel Vetter <daniel@ffwll.ch>
> Signed-off-by: Rob Herring <robh@kernel.org>

LGTM, and I see a nice speed up too!

Reviewed-by: Steven Price <steven.price@arm.com>
Tomeu Vizoso April 12, 2019, 2:52 p.m. UTC | #3 
Acked-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>

Thanks!

Tomeu

On Fri, 12 Apr 2019 at 09:27, Alyssa Rosenzweig <alyssa@rosenzweig.io> wrote:
>
> Acked-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
> _______________________________________________
> dri-devel mailing list
> dri-devel@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/dri-devel
diff mbox series

Patch

diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index 502af37d4b62..762b1bd2a8c2 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -137,6 +137,14 @@  static void mmu_disable(struct panfrost_device *pfdev, u32 as_nr)
 	write_cmd(pfdev, as_nr, AS_COMMAND_UPDATE);
 }
 
+static size_t get_pgsize(u64 addr, size_t size)
+{
+	if (addr & (SZ_2M - 1) || size < SZ_2M)
+		return SZ_4K;
+
+	return SZ_2M;
+}
+
 int panfrost_mmu_map(struct panfrost_gem_object *bo)
 {
 	struct drm_gem_object *obj = &bo->base.base;
@@ -165,10 +173,12 @@  int panfrost_mmu_map(struct panfrost_gem_object *bo)
 		dev_dbg(pfdev->dev, "map: iova=%llx, paddr=%lx, len=%zx", iova, paddr, len);
 
 		while (len) {
-			ops->map(ops, iova, paddr, SZ_4K, IOMMU_WRITE | IOMMU_READ);
-			iova += SZ_4K;
-			paddr += SZ_4K;
-			len -= SZ_4K;
+			size_t pgsize = get_pgsize(iova | paddr, len);
+
+			ops->map(ops, iova, paddr, pgsize, IOMMU_WRITE | IOMMU_READ);
+			iova += pgsize;
+			paddr += pgsize;
+			len -= pgsize;
 		}
 	}
 
@@ -202,9 +212,15 @@  void panfrost_mmu_unmap(struct panfrost_gem_object *bo)
 	mutex_lock(&pfdev->mmu->lock);
 
 	while (unmapped_len < len) {
-		ops->unmap(ops, iova, SZ_4K);
-		iova += SZ_4K;
-		unmapped_len += SZ_4K;
+		size_t unmapped_page;
+		size_t pgsize = get_pgsize(iova, len - unmapped_len);
+
+		unmapped_page = ops->unmap(ops, iova, pgsize);
+		if (!unmapped_page)
+			break;
+
+		iova += unmapped_page;
+		unmapped_len += unmapped_page;
 	}
 
 	mmu_hw_do_operation(pfdev, 0, bo->node.start << PAGE_SHIFT,
@@ -342,7 +358,7 @@  int panfrost_mmu_init(struct panfrost_device *pfdev)
 	mmu_write(pfdev, MMU_INT_MASK, ~0);
 
 	pfdev->mmu->pgtbl_cfg = (struct io_pgtable_cfg) {
-		.pgsize_bitmap	= SZ_4K, // | SZ_2M | SZ_1G),
+		.pgsize_bitmap	= SZ_4K | SZ_2M,
 		.ias		= FIELD_GET(0xff, pfdev->features.mmu_features),
 		.oas		= FIELD_GET(0xff00, pfdev->features.mmu_features),
 		.tlb		= &mmu_tlb_ops,