Skip to contentSkip to conversation

powerpc/iommu: use iommu_num_pages() to calculate the number of iommu page

PATCH In review Wei Yang 2 participants 5 messages Sep 19, 2015 – Nov 12, 2015 PowerPC

lore
Share & tools
lore

Wei Yang

author
#0 lore raw

PATCH 1/1 powerpc/iommu: use iommu_num_pages() to calculate the number of iommu page

On PowerPC, currently we support different value of PAGE_SIZE and different value of IOMMU Page Size.

In case the PAGE_SIZE is 4K and the IOMMU Page Size is 16M, and driver asked for some DMA less than 16M, the current calculation would return 0 and the following allocation in iommu_alloc() would fail.

This patch uses iommu_num_pages() to calculate it.

---
 arch/powerpc/kernel/iommu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/powerpc/kernel/iommu.c +1 -1
index a8e3490..9885397 100644
@@ -842,7 +842,7 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
 	memset(ret, 0, size);
 
 	/* Set up tces to cover the allocated range */
-	nio_pages = size >> tbl->it_page_shift;
+	nio_pages = iommu_num_pages(0, size, IOMMU_PAGE_SIZE(tbl));
 	io_order = get_iommu_order(size, tbl);
 	mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL,
 			      mask >> tbl->it_page_shift, io_order, NULL);
Signature · 1 line
2.5.0
author
#1 lore raw

Hmm... some comments on this one? like it or not?

Quoted 29 lines · Wei Yang

On PowerPC, currently we support different value of PAGE_SIZE and different value of IOMMU Page Size.

In case the PAGE_SIZE is 4K and the IOMMU Page Size is 16M, and driver asked for some DMA less than 16M, the current calculation would return 0 and the following allocation in iommu_alloc() would fail.

This patch uses iommu_num_pages() to calculate it.

---
arch/powerpc/kernel/iommu.c | 2 +-

1 file changed, 1 insertion(+), 1 deletion(-)
arch/powerpc/kernel/iommu.c +1 -1
index a8e3490..9885397 100644
@@ -842,7 +842,7 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
 	memset(ret, 0, size);
 
 	/* Set up tces to cover the allocated range */
-	nio_pages = size >> tbl->it_page_shift;
+	nio_pages = iommu_num_pages(0, size, IOMMU_PAGE_SIZE(tbl));
 	io_order = get_iommu_order(size, tbl);
 	mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL,
 			      mask >> tbl->it_page_shift, io_order, NULL);
Signature · 1 line
2.5.0
Signature · 2 lines
Richard Yang
Help you, Help me
#2 lore raw
Quoted 1 line · Wei Yang

Hmm... some comments on this one? like it or not?

It sounds like it's fixing a bug, but you don't really say. Have you seen this fail in the wild?

Which commit introduced the breakage?

cheers

author
#3 lore raw
Quoted 5 lines · Michael Ellerman
Quoted 1 line · Wei Yang

Hmm... some comments on this one? like it or not?

It sounds like it's fixing a bug, but you don't really say. Have you seen this fail in the wild?

Hmm... as described in the commit log, this would be a bug when PAGE_SIZE is much smaller than IOMMU Page Size. This configuration doesn't happen on current platform. So I didn't see this failure yet.

Quoted 2 lines

Which commit introduced the breakage?

Hmm... maybe we could say it is 'commit d084775738b7 <powerpc/iommu: Update the generic code to use dynamic iommu page sizes>'.

Quoted 1 line

From this commit, powerpc iommu supports dynamic iommu page size.

Before this commit, the size is aligned with PAGE_SIZE, so the value after shift would be non-zero. After this commit, when PAGE_SIZE is smaller than the IOMMU Page Size, shift right will make the size 0.

Quoted 3 lines

cheers

Signature · 2 lines
Richard Yang
Help you, Help me
author
#4 lore raw

Someone willing to take a look?

Quoted 29 lines · Wei Yang
Quoted 5 lines · Michael Ellerman
Quoted 1 line · Wei Yang

Hmm... some comments on this one? like it or not?

It sounds like it's fixing a bug, but you don't really say. Have you seen this fail in the wild?

Hmm... as described in the commit log, this would be a bug when PAGE_SIZE is much smaller than IOMMU Page Size. This configuration doesn't happen on current platform. So I didn't see this failure yet.

Quoted 2 lines

Which commit introduced the breakage?

Hmm... maybe we could say it is 'commit d084775738b7 <powerpc/iommu: Update the generic code to use dynamic iommu page sizes>'.

Quoted 1 line

From this commit, powerpc iommu supports dynamic iommu page size.

Before this commit, the size is aligned with PAGE_SIZE, so the value after shift would be non-zero. After this commit, when PAGE_SIZE is smaller than the IOMMU Page Size, shift right will make the size 0.

Quoted 3 lines

cheers

Signature · 2 lines
Richard Yang
Help you, Help me
Signature · 2 lines
Richard Yang
Help you, Help me