2007-10-25 23:08:40

by FUJITA Tomonori

Subject: [PATCH] x86: fix pci-gart failure handling

blk_rq_map_sg doesn't initialize sg->dma_address/length to zero
anymore. Some low level drivers reuse sg lists without initializing so
IOMMUs might get non-zero dma_address/length. If map_sg fails, we need
pass the number of the mapped entries to gart_unmap_sg.

Signed-off-by: FUJITA Tomonori <[email protected]>
---
arch/x86/kernel/pci-gart_64.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index c56e9ee..6e7f826 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -436,7 +436,7 @@ static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents,

error:
flush_gart();
- gart_unmap_sg(dev, sg, nents, dir);
+ gart_unmap_sg(dev, sg, out, dir);
/* When it was forced or merged try again in a dumb way */
if (force_iommu || iommu_merge) {
out = dma_map_sg_nonforce(dev, sg, nents, dir);
--
1.5.2.4

2007-10-26 11:58:17

by Jens Axboe

Subject: Re: [PATCH] x86: fix pci-gart failure handling

On Fri, Oct 26 2007, FUJITA Tomonori wrote:
> blk_rq_map_sg doesn't initialize sg->dma_address/length to zero
> anymore. Some low level drivers reuse sg lists without initializing so
> IOMMUs might get non-zero dma_address/length. If map_sg fails, we need
> pass the number of the mapped entries to gart_unmap_sg.
>
> Signed-off-by: FUJITA Tomonori <[email protected]>

Thanks Tomo, applied!

--
Jens Axboe