summaryrefslogtreecommitdiffstats
path: root/arch/powerpc
diff options
context:
space:
mode:
authorPaul Mackerras <paulus@ozlabs.org>2018-08-23 10:08:58 +1000
committerMichael Ellerman <mpe@ellerman.id.au>2018-08-23 23:40:10 +1000
commit8cfbdbdc24815417a3ab35101ccf706b9a23ff17 (patch)
treeaf9ef442708bec1f9b481b8f87318809e5314ed3 /arch/powerpc
parentf08d08f3db55452d31ba4a37c702da6245876b96 (diff)
downloadlinux-8cfbdbdc24815417a3ab35101ccf706b9a23ff17.tar.bz2
KVM: PPC: Book3S: Fix guest DMA when guest partially backed by THP pages
Commit 76fa4975f3ed ("KVM: PPC: Check if IOMMU page is contained in the pinned physical page", 2018-07-17) added some checks to ensure that guest DMA mappings don't attempt to map more than the guest is entitled to access. However, errors in the logic mean that legitimate guest requests to map pages for DMA are being denied in some situations. Specifically, if the first page of the range passed to mm_iommu_get() is mapped with a normal page, and subsequent pages are mapped with transparent huge pages, we end up with mem->pageshift == 0. That means that the page size checks in mm_iommu_ua_to_hpa() and mm_iommu_up_to_hpa_rm() will always fail for every page in that region, and thus the guest can never map any memory in that region for DMA, typically leading to a flood of error messages like this: qemu-system-ppc64: VFIO_MAP_DMA: -22 qemu-system-ppc64: vfio_dma_map(0x10005f47780, 0x800000000000000, 0x10000, 0x7fff63ff0000) = -22 (Invalid argument) The logic errors in mm_iommu_get() are: (a) use of 'ua' not 'ua + (i << PAGE_SHIFT)' in the find_linux_pte() call (meaning that find_linux_pte() returns the pte for the first address in the range, not the address we are currently up to); (b) use of 'pageshift' as the variable to receive the hugepage shift returned by find_linux_pte() - for a normal page this gets set to 0, leading to us setting mem->pageshift to 0 when we conclude that the pte returned by find_linux_pte() didn't match the page we were looking at; (c) comparing 'compshift', which is a page order, i.e. log base 2 of the number of pages, with 'pageshift', which is a log base 2 of the number of bytes. To fix these problems, this patch introduces 'cur_ua' to hold the current user address and uses that in the find_linux_pte() call; introduces 'pteshift' to hold the hugepage shift found by find_linux_pte(); and compares 'pteshift' with 'compshift + PAGE_SHIFT' rather than 'compshift'. The patch also moves the local_irq_restore to the point after the PTE pointer returned by find_linux_pte() has been dereferenced because otherwise the PTE could change underneath us, and adds a check to avoid doing the find_linux_pte() call once mem->pageshift has been reduced to PAGE_SHIFT, as an optimization. Fixes: 76fa4975f3ed ("KVM: PPC: Check if IOMMU page is contained in the pinned physical page") Cc: stable@vger.kernel.org # v4.12+ Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Diffstat (limited to 'arch/powerpc')
-rw-r--r--arch/powerpc/mm/mmu_context_iommu.c17
1 files changed, 10 insertions, 7 deletions
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index a4ca57612558..c9ee9e23845f 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -129,6 +129,7 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
long i, j, ret = 0, locked_entries = 0;
unsigned int pageshift;
unsigned long flags;
+ unsigned long cur_ua;
struct page *page = NULL;
mutex_lock(&mem_list_mutex);
@@ -177,7 +178,8 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
}
for (i = 0; i < entries; ++i) {
- if (1 != get_user_pages_fast(ua + (i << PAGE_SHIFT),
+ cur_ua = ua + (i << PAGE_SHIFT);
+ if (1 != get_user_pages_fast(cur_ua,
1/* pages */, 1/* iswrite */, &page)) {
ret = -EFAULT;
for (j = 0; j < i; ++j)
@@ -196,7 +198,7 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
if (is_migrate_cma_page(page)) {
if (mm_iommu_move_page_from_cma(page))
goto populate;
- if (1 != get_user_pages_fast(ua + (i << PAGE_SHIFT),
+ if (1 != get_user_pages_fast(cur_ua,
1/* pages */, 1/* iswrite */,
&page)) {
ret = -EFAULT;
@@ -210,20 +212,21 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
}
populate:
pageshift = PAGE_SHIFT;
- if (PageCompound(page)) {
+ if (mem->pageshift > PAGE_SHIFT && PageCompound(page)) {
pte_t *pte;
struct page *head = compound_head(page);
unsigned int compshift = compound_order(head);
+ unsigned int pteshift;
local_irq_save(flags); /* disables as well */
- pte = find_linux_pte(mm->pgd, ua, NULL, &pageshift);
- local_irq_restore(flags);
+ pte = find_linux_pte(mm->pgd, cur_ua, NULL, &pteshift);
/* Double check it is still the same pinned page */
if (pte && pte_page(*pte) == head &&
- pageshift == compshift)
- pageshift = max_t(unsigned int, pageshift,
+ pteshift == compshift + PAGE_SHIFT)
+ pageshift = max_t(unsigned int, pteshift,
PAGE_SHIFT);
+ local_irq_restore(flags);
}
mem->pageshift = min(mem->pageshift, pageshift);
mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;