x86: fix broken flushing in GART nofullflush path
PATCH 1/1 x86: fix broken flushing in GART nofullflush path
In the non-default nofullflush case the GART is only flushed when next_bit wraps around. But it can happen that an unmap operation unmaps memory which is behind the current next_bit location. If these addresses are reused it may result in stale GART IO/TLB entries. Fix this by setting the GART next_bit always behind an unmapped location.
--- arch/x86/kernel/pci-gart_64.c | 2 ++ 1 files changed, 2 insertions(+), 0 deletions(-)
arch/x86/kernel/pci-gart_64.c +2 -0
@@ -123,6 +123,8 @@ static void free_iommu(unsigned long offset, int size)spin_lock_irqsave (&iommu_bitmap_lock, flags);iommu_area_free (iommu_gart_bitmap, offset, size); +if (offset >= next_bit) + next_bit = offset + size;spin_unlock_irqrestore (&iommu_bitmap_lock, flags); }
Signature · 1 line
1.5.6.4
Ingo Molnar
AppliedQuoted 10 lines · Joerg Roedel
In the non-default nofullflush case the GART is only flushed when
next_bitwraps around. But it can happen that an unmap operation unmaps memory which is behind the currentnext_bitlocation. If these addresses are reused it may result in stale GART IO/TLB entries. Fix this by setting the GARTnext_bitalways behind an unmapped location.Signed-off-by Joerg Roedel <[email protected]>--- arch/x86/kernel/pci-gart_64.c | 2 ++ 1 files changed, 2 insertions(+), 0 deletions(-)
applied to tip/x86/iommu, thanks Joerg!
a stale iotlb should not cause any problems in this particular GART case, right? It might be a security leak in a security-domain enforcing iotlb case, but the GART is a DMA bouncing helper in essence. Can you see any failure mode of this bug?
Ingo
Quoted 14 lines · Ingo Molnar
Quoted 10 lines · Joerg Roedel
In the non-default nofullflush case the GART is only flushed when
next_bitwraps around. But it can happen that an unmap operation unmaps memory which is behind the currentnext_bitlocation. If these addresses are reused it may result in stale GART IO/TLB entries. Fix this by setting the GARTnext_bitalways behind an unmapped location.Signed-off-by Joerg Roedel <[email protected]>--- arch/x86/kernel/pci-gart_64.c | 2 ++ 1 files changed, 2 insertions(+), 0 deletions(-)
Quoted 6 lines
applied to tip/x86/iommu, thanks Joerg!
a stale iotlb should not cause any problems in this particular GART case, right? It might be a security leak in a security-domain enforcing iotlb case, but the GART is a DMA bouncing helper in essence. Can you see any failure mode of this bug?
It can cause data corruption because the GART redirects the IO to a wrong address because of a stale entry in its TLB. I found this bug after I fixed the same issue in the AMD IOMMU code (commit 80be308d).
The reason this was not found earlier is that lazy flushing is not the default in GART. But I didn't try to trigger the bug.
Joerg
u
Quoted 22 lines · Joerg Roedel
Quoted 14 lines · Ingo Molnar
Quoted 10 lines · Joerg Roedel
In the non-default nofullflush case the GART is only flushed when
next_bitwraps around. But it can happen that an unmap operation unmaps memory which is behind the currentnext_bitlocation. If these addresses are reused it may result in stale GART IO/TLB entries. Fix this by setting the GARTnext_bitalways behind an unmapped location.Signed-off-by Joerg Roedel <[email protected]>--- arch/x86/kernel/pci-gart_64.c | 2 ++ 1 files changed, 2 insertions(+), 0 deletions(-)Quoted 6 lines
applied to tip/x86/iommu, thanks Joerg!
a stale iotlb should not cause any problems in this particular GART case, right? It might be a security leak in a security-domain enforcing iotlb case, but the GART is a DMA bouncing helper in essence. Can you see any failure mode of this bug?
Quoted 6 lines
It can cause data corruption because the GART redirects the IO to a wrong address because of a stale entry in its TLB. I found this bug after I fixed the same issue in the AMD IOMMU code (commit
80be308d).The reason this was not found earlier is that lazy flushing is not the default in GART. But I didn't try to trigger the bug.
ah, indeed. The stale entries themselves are not an issue - the problem is reuse: if a stale entry is reused but then we do not flush, we can get data corruption. I've cherry-picked it over into x86/urgent as well.
Ingo