@@ -2253,7 +2253,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
struct folio *folio = NULL;
bool skip_swapcache = false;
swp_entry_t swap;
- int error, nr_pages;
+ int error, nr_pages, order, split_order;
VM_BUG_ON(!*foliop || !xa_is_value(*foliop));
swap = radix_to_swp_entry(*foliop);
@@ -2272,10 +2272,9 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
/* Look it up and read it in.. */
folio = swap_cache_get_folio(swap, NULL, 0);
+ order = xa_get_order(&mapping->i_pages, index);
if (!folio) {
- int order = xa_get_order(&mapping->i_pages, index);
bool fallback_order0 = false;
- int split_order;
/* Or update major stats only when swapin succeeds?? */
if (fault_type) {
@@ -2339,6 +2338,29 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
error = -ENOMEM;
goto failed;
}
+ } else if (order != folio_order(folio)) {
+ /*
+ * Swap readahead may swap in order 0 folios into swapcache
+ * asynchronously, while the shmem mapping can still stores
+ * large swap entries. In such cases, we should split the
+ * large swap entry to prevent possible data corruption.
+ */
+ split_order = shmem_split_large_entry(inode, index, swap, gfp);
+ if (split_order < 0) {
+ error = split_order;
+ goto failed;
+ }
+
+ /*
+ * If the large swap entry has already been split, it is
+ * necessary to recalculate the new swap entry based on
+ * the old order alignment.
+ */
+ if (split_order > 0) {
+ pgoff_t offset = index - round_down(index, 1 << split_order);
+
+ swap = swp_entry(swp_type(swap), swp_offset(swap) + offset);
+ }
}
alloced:
@@ -2346,7 +2368,8 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
folio_lock(folio);
if ((!skip_swapcache && !folio_test_swapcache(folio)) ||
folio->swap.val != swap.val ||
- !shmem_confirm_swap(mapping, index, swap)) {
+ !shmem_confirm_swap(mapping, index, swap) ||
+ xa_get_order(&mapping->i_pages, index) != folio_order(folio)) {
error = -EEXIST;
goto unlock;
}
Alex and Kairui reported some issues (system hang or data corruption) when swapping out or swapping in large shmem folios. This is especially easy to reproduce when the tmpfs is mount with the 'huge=within_size' parameter. Thanks to Kairui's reproducer, the issue can be easily replicated. The root cause of the problem is that swap readahead may asynchronously swap in order 0 folios into the swap cache, while the shmem mapping can still store large swap entries. Then an order 0 folio is inserted into the shmem mapping without splitting the large swap entry, which overwrites the original large swap entry, leading to data corruption. When getting a folio from the swap cache, we should split the large swap entry stored in the shmem mapping if the orders do not match, to fix this issue. Fixes: 809bc86517cc ("mm: shmem: support large folio swap out") Reported-by: Alex Xu (Hello71) <alex_y_xu@yahoo.ca> Reported-by: Kairui Song <ryncsn@gmail.com> Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com> --- mm/shmem.c | 31 +++++++++++++++++++++++++++---- 1 file changed, 27 insertions(+), 4 deletions(-)