aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJan Kara <jack@suse.cz>2018-10-04 07:55:19 +1000
committerStephen Rothwell <sfr@canb.auug.org.au>2018-10-05 15:57:19 +1000
commitcdfac305a2cd0a59f359aff452ba25a0ff8113f7 (patch)
tree591866061fc2f587fe52b09f5e43d58fecb156fd
parent10007f50b95c2e50c53a6a46208f2bcac9244268 (diff)
download96b-common-cdfac305a2cd0a59f359aff452ba25a0ff8113f7.tar.gz
mm: Fix warning in insert_pfn()
In DAX mode a write pagefault can race with write(2) in the following way: CPU0 CPU1 write fault for mapped zero page (hole) dax_iomap_rw() iomap_apply() xfs_file_iomap_begin() - allocates blocks dax_iomap_actor() invalidate_inode_pages2_range() - invalidates radix tree entries in given range dax_iomap_pte_fault() grab_mapping_entry() - no entry found, creates empty ... xfs_file_iomap_begin() - finds already allocated block ... vmf_insert_mixed_mkwrite() - WARNs and does nothing because there is still zero page mapped in PTE unmap_mapping_pages() This race results in WARN_ON from insert_pfn() and is occasionally triggered by fstest generic/344. Note that the race is otherwise harmless as before write(2) on CPU0 is finished, we will invalidate page tables properly and thus user of mmap will see modified data from write(2) from that point on. So just restrict the warning only to the case when the PFN in PTE is not zero page. Link: http://lkml.kernel.org/r/20180824154542.26872-1-jack@suse.cz Signed-off-by: Jan Kara <jack@suse.cz> Reviewed-by: Andrew Morton <akpm@linux-foundation.org> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Jiang <dave.jiang@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
-rw-r--r--mm/memory.c9
1 files changed, 7 insertions, 2 deletions
diff --git a/mm/memory.c b/mm/memory.c
index c9e4c7d68f24..fa8894c70575 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1537,10 +1537,15 @@ static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr,
* in may not match the PFN we have mapped if the
* mapped PFN is a writeable COW page. In the mkwrite
* case we are creating a writable PTE for a shared
- * mapping and we expect the PFNs to match.
+ * mapping and we expect the PFNs to match. If they
+ * don't match, we are likely racing with block
+ * allocation and mapping invalidation so just skip the
+ * update.
*/
- if (WARN_ON_ONCE(pte_pfn(*pte) != pfn_t_to_pfn(pfn)))
+ if (pte_pfn(*pte) != pfn_t_to_pfn(pfn)) {
+ WARN_ON_ONCE(!is_zero_pfn(pte_pfn(*pte)));
goto out_unlock;
+ }
entry = *pte;
goto out_mkwrite;
} else