[PATCH v2 hmm 7/9] mm/hmm: do not unconditionally set pfns when returning EBUSY

Jason Gunthorpe jgg at ziepe.ca
Fri Mar 27 20:00:19 UTC 2020


From: Jason Gunthorpe <jgg at mellanox.com>

In hmm_vma_handle_pte() and hmm_vma_walk_hugetlb_entry() if fault happens
then -EBUSY will be returned and the pfns input flags will have been
destroyed.

For hmm_vma_handle_pte() set HMM_PFN_NONE only on the success returns that
don't otherwise store to pfns.

For hmm_vma_walk_hugetlb_entry() all exit paths already set pfns, so
remove the redundant store.

Fixes: 2aee09d8c116 ("mm/hmm: change hmm_vma_fault() to allow write fault on page basis")
Reviewed-by: Christoph Hellwig <hch at lst.de>
Signed-off-by: Jason Gunthorpe <jgg at mellanox.com>
---
 mm/hmm.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/mm/hmm.c b/mm/hmm.c
index 3303686bf16d24..dc826898979bc5 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -244,11 +244,11 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 	pte_t pte = *ptep;
 	uint64_t orig_pfn = *pfn;
 
-	*pfn = range->values[HMM_PFN_NONE];
 	if (pte_none(pte)) {
 		required_fault = hmm_pte_need_fault(hmm_vma_walk, orig_pfn, 0);
 		if (required_fault)
 			goto fault;
+		*pfn = range->values[HMM_PFN_NONE];
 		return 0;
 	}
 
@@ -269,8 +269,10 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 		}
 
 		required_fault = hmm_pte_need_fault(hmm_vma_walk, orig_pfn, 0);
-		if (!required_fault)
+		if (!required_fault) {
+			*pfn = range->values[HMM_PFN_NONE];
 			return 0;
+		}
 
 		if (!non_swap_entry(entry))
 			goto fault;
@@ -488,7 +490,6 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
 
 	i = (start - range->start) >> PAGE_SHIFT;
 	orig_pfn = range->pfns[i];
-	range->pfns[i] = range->values[HMM_PFN_NONE];
 	cpu_flags = pte_to_hmm_pfn_flags(range, entry);
 	required_fault = hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags);
 	if (required_fault) {
-- 
2.25.2



More information about the amd-gfx mailing list