summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--mm/memory.c20
-rw-r--r--mm/shmem.c6
-rw-r--r--mm/swap.h23
3 files changed, 28 insertions, 21 deletions
diff --git a/mm/memory.c b/mm/memory.c
index 8eba595056fe..b0cda5aab398 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4315,26 +4315,6 @@ static struct folio *__alloc_swap_folio(struct vm_fault *vmf)
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline int non_swapcache_batch(swp_entry_t entry, int max_nr)
-{
- struct swap_info_struct *si = swp_swap_info(entry);
- pgoff_t offset = swp_offset(entry);
- int i;
-
- /*
- * While allocating a large folio and doing swap_read_folio, which is
- * the case the being faulted pte doesn't have swapcache. We need to
- * ensure all PTEs have no cache as well, otherwise, we might go to
- * swap devices while the content is in swapcache.
- */
- for (i = 0; i < max_nr; i++) {
- if ((si->swap_map[offset + i] & SWAP_HAS_CACHE))
- return i;
- }
-
- return i;
-}
-
/*
* Check if the PTEs within a range are contiguous swap entries
* and have consistent swapcache, zeromap.
diff --git a/mm/shmem.c b/mm/shmem.c
index 0c5fb4ffa03a..3a5a65b1f41a 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2259,6 +2259,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
folio = swap_cache_get_folio(swap, NULL, 0);
order = xa_get_order(&mapping->i_pages, index);
if (!folio) {
+ int nr_pages = 1 << order;
bool fallback_order0 = false;
/* Or update major stats only when swapin succeeds?? */
@@ -2272,9 +2273,12 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
* If uffd is active for the vma, we need per-page fault
* fidelity to maintain the uffd semantics, then fallback
* to swapin order-0 folio, as well as for zswap case.
+ * Any existing sub folio in the swap cache also blocks
+ * mTHP swapin.
*/
if (order > 0 && ((vma && unlikely(userfaultfd_armed(vma))) ||
- !zswap_never_enabled()))
+ !zswap_never_enabled() ||
+ non_swapcache_batch(swap, nr_pages) != nr_pages))
fallback_order0 = true;
/* Skip swapcache for synchronous device. */
diff --git a/mm/swap.h b/mm/swap.h
index 2269eb9df0af..9096082a915e 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -106,6 +106,25 @@ static inline int swap_zeromap_batch(swp_entry_t entry, int max_nr,
return find_next_bit(sis->zeromap, end, start) - start;
}
+static inline int non_swapcache_batch(swp_entry_t entry, int max_nr)
+{
+ struct swap_info_struct *si = swp_swap_info(entry);
+ pgoff_t offset = swp_offset(entry);
+ int i;
+
+ /*
+ * While allocating a large folio and doing mTHP swapin, we need to
+ * ensure all entries are not cached, otherwise, the mTHP folio will
+ * be in conflict with the folio in swap cache.
+ */
+ for (i = 0; i < max_nr; i++) {
+ if ((si->swap_map[offset + i] & SWAP_HAS_CACHE))
+ return i;
+ }
+
+ return i;
+}
+
#else /* CONFIG_SWAP */
struct swap_iocb;
static inline void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
@@ -199,6 +218,10 @@ static inline int swap_zeromap_batch(swp_entry_t entry, int max_nr,
return 0;
}
+static inline int non_swapcache_batch(swp_entry_t entry, int max_nr)
+{
+ return 0;
+}
#endif /* CONFIG_SWAP */
/**