Reported-by: David Sadler <dsadler@xxxxxxxxxx>
This patch fixes a race condition that shows in conjunction with
xip_file_fault
when two threads of the same user process fault on the same memory page.
In this
case, the race winner will install the page table entry, and the unlucky
loser
will cause an oops:
xip_file_fault calls vm_insert_pfn (via vm_insert_mixed) which drops out at
this check:
retval = -EBUSY;
if (!pte_none(*pte))
goto out_unlock;
The resulting -EBUSY return value will trigger a BUG_ON() in xip_file_fault.
This fix simply considers the fault as fixed in this case, because the
race winner has successfully installed the pte.
Signed-off-by: Carsten Otte <cotte@xxxxxxxxxx>
---
mm/filemap_xip.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -263,7 +263,10 @@ found:
xip_pfn);
if (err == -ENOMEM)
return VM_FAULT_OOM;
- BUG_ON(err);
+ /* err == -EBUSY is fine, we've raced against another thread
+ that faulted-in the same page */
+ if (err != -EBUSY)
+ BUG_ON(err);
return VM_FAULT_NOPAGE;
} else {
int err, ret = VM_FAULT_OOM;
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxxx For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>