Piteball/android_kernel_google_msm
1
0
Fork 0
mirror of https://github.com/followmsi/android_kernel_google_msm.git synced 2024-11-06 23:17:41 +00:00
Code Issues Projects Releases Wiki Activity

iommu/amd: Only unmap large pages from the first pte

Browse source 
commit 60d0ca3cfd upstream.

If we use a large mapping, the expectation is that only unmaps from
the first pte in the superpage are supported.  Unmaps from offsets
into the superpage should fail (ie. return zero sized unmap).  In the
current code, unmapping from an offset clears the size of the full
mapping starting from an offset.  For instance, if we map a 16k
physically contiguous range at IOVA 0x0 with a large page, then
attempt to unmap 4k at offset 12k, 4 ptes are cleared (12k - 28k) and
the unmap returns 16k unmapped.  This potentially incorrectly clears
valid mappings and confuses drivers like VFIO that use the unmap size
to release pinned pages.

Fix by refusing to unmap from offsets into the page.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Joerg Roedel <joro@8bytes.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
Alex Williamson 2013-06-21 14:33:19 -06:00 committed by Greg Kroah-Hartman
parent d018274f85
commit ca9c5a9c9b
1 changed files with 5 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
drivers/iommu/amd_iommu.c
View file

@ -1309,6 +1309,10 @@ static unsigned long iommu_unmap_page(struct protection_domain *dom,
/* Large PTE found which maps this address */
unmap_size = PTE_PAGE_SIZE(*pte);
/* Only unmap from the first pte in the page */
if ((unmap_size - 1) & bus_addr)
break;
count = PAGE_SIZE_PTE_COUNT(unmap_size);
for (i = 0; i < count; i++)
pte[i] = 0ULL;
@ -1318,7 +1322,7 @@ static unsigned long iommu_unmap_page(struct protection_domain *dom,
unmapped += unmap_size;
}
BUG_ON(!is_power_of_2(unmapped));
BUG_ON(unmapped && !is_power_of_2(unmapped));
return unmapped;
}