[PATCH] x86_64: Fix a race in the free_iommu path

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@google.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/arch/x86_64/kernel/pci-gart.c b/arch/x86_64/kernel/pci-gart.c
index a6c01e1..9d3d76c 100644 (file)
--- a/arch/x86_64/kernel/pci-gart.c
+++ b/arch/x86_64/kernel/pci-gart.c
@@ -112,10 +112,6 @@ static unsigned long alloc_iommu(int size)
 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);