The patch titled
x86_64: Fix a race in the free_iommu path
has been added to the -mm tree. Its filename is
x86_64-fix-a-race-in-the-free_iommu-path.patch
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
From: Mike Waychison <mikew@xxxxxxxxxx>
We do this by removing a micro-optimization that tries to avoid grabbing
the iommu_bitmap_lock spinlock and using a bus-locked operation.
This still races with other simultaneous alloc_iommu or free_iommu(size >
1) which both use bus-unlocked operations.
The end result of this race is eventually ending up with an
iommu_gart_bitmap that has bits errornously set all over, making large
contiguous iommu space allocations fail with 'PCI-DMA: Out of IOMMU space'.
Signed-off-by: Mike Waychison <mikew@xxxxxxxxxx>
Signed-off-by: Andi Kleen <ak@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxx>
---
arch/x86_64/kernel/pci-gart.c | 4 ----
1 files changed, 4 deletions(-)
diff -puN arch/x86_64/kernel/pci-gart.c~x86_64-fix-a-race-in-the-free_iommu-path arch/x86_64/kernel/pci-gart.c
--- 25/arch/x86_64/kernel/pci-gart.c~x86_64-fix-a-race-in-the-free_iommu-path Fri Apr 21 13:57:03 2006
+++ 25-akpm/arch/x86_64/kernel/pci-gart.c Fri Apr 21 13:57:03 2006
@@ -112,10 +112,6 @@ static unsigned long alloc_iommu(int siz
static void free_iommu(unsigned long offset, int size)
{
unsigned long flags;
- if (size == 1) {
- clear_bit(offset, iommu_gart_bitmap);
- return;
- }
spin_lock_irqsave(&iommu_bitmap_lock, flags);
__clear_bit_string(iommu_gart_bitmap, offset, size);
spin_unlock_irqrestore(&iommu_bitmap_lock, flags);
_
Patches currently in -mm which might be from mikew@xxxxxxxxxx are
x86_64-fix-a-race-in-the-free_iommu-path.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
