mm: shmem: split large entry if the swapin folio is not large

Now the swap device can only swap-in order 0 folio, even though a large
folio is swapped out.  This requires us to split the large entry
previously saved in the shmem pagecache to support the swap in of small
folios.

[hughd@google.com: fix warnings from kmalloc_fix_flags()]
  Link: https://lkml.kernel.org/r/e2a2ba5d-864c-50aa-7579-97cba1c7dd0c@google.com
[baolin.wang@linux.alibaba.com: drop the 'new_order' parameter]
  Link: https://lkml.kernel.org/r/39c71ccf-669b-4d9f-923c-f6b9c4ceb8df@linux.alibaba.com
Link: https://lkml.kernel.org/r/4a0f12f27c54a62eb4d9ca1265fed3a62531a63e.1723434324.git.baolin.wang@linux.alibaba.com
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Chris Li <chrisl@kernel.org>
Cc: Daniel Gomez <da.gomez@samsung.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Lance Yang <ioworker0@gmail.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Pankaj Raghav <p.raghav@samsung.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 103 insertions, 0 deletions

diff --git a/mm/shmem.c b/mm/shmem.c
index 598d003b7a89..4af6f3ea9c4f 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1999,6 +1999,84 @@ static void shmem_set_folio_swapin_error(struct inode *inode, pgoff_t index,
 	swap_free_nr(swap, nr_pages);
 }
 
+static int shmem_split_large_entry(struct inode *inode, pgoff_t index,
+				   swp_entry_t swap, gfp_t gfp)
+{
+	struct address_space *mapping = inode->i_mapping;
+	XA_STATE_ORDER(xas, &mapping->i_pages, index, 0);
+	void *alloced_shadow = NULL;
+	int alloced_order = 0, i;
+
+	/* Convert user data gfp flags to xarray node gfp flags */
+	gfp &= GFP_RECLAIM_MASK;
+
+	for (;;) {
+		int order = -1, split_order = 0;
+		void *old = NULL;
+
+		xas_lock_irq(&xas);
+		old = xas_load(&xas);
+		if (!xa_is_value(old) || swp_to_radix_entry(swap) != old) {
+			xas_set_err(&xas, -EEXIST);
+			goto unlock;
+		}
+
+		order = xas_get_order(&xas);
+
+		/* Swap entry may have changed before we re-acquire the lock */
+		if (alloced_order &&
+		    (old != alloced_shadow || order != alloced_order)) {
+			xas_destroy(&xas);
+			alloced_order = 0;
+		}
+
+		/* Try to split large swap entry in pagecache */
+		if (order > 0) {
+			if (!alloced_order) {
+				split_order = order;
+				goto unlock;
+			}
+			xas_split(&xas, old, order);
+
+			/*
+			 * Re-set the swap entry after splitting, and the swap
+			 * offset of the original large entry must be continuous.
+			 */
+			for (i = 0; i < 1 << order; i++) {
+				pgoff_t aligned_index = round_down(index, 1 << order);
+				swp_entry_t tmp;
+
+				tmp = swp_entry(swp_type(swap), swp_offset(swap) + i);
+				__xa_store(&mapping->i_pages, aligned_index + i,
+					   swp_to_radix_entry(tmp), 0);
+			}
+		}
+
+unlock:
+		xas_unlock_irq(&xas);
+
+		/* split needed, alloc here and retry. */
+		if (split_order) {
+			xas_split_alloc(&xas, old, split_order, gfp);
+			if (xas_error(&xas))
+				goto error;
+			alloced_shadow = old;
+			alloced_order = split_order;
+			xas_reset(&xas);
+			continue;
+		}
+
+		if (!xas_nomem(&xas, gfp))
+			break;
+	}
+
+error:
+	if (xas_error(&xas))
+		return xas_error(&xas);
+
+	return alloced_order;
+}
+
 /*
  * Swap in the folio pointed to by *foliop.
  * Caller has to make sure that *foliop contains a valid swapped folio.
@@ -2036,12 +2114,37 @@ 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);
 	if (!folio) {
+		int split_order;
+
 		/* Or update major stats only when swapin succeeds?? */
 		if (fault_type) {
 			*fault_type |= VM_FAULT_MAJOR;
 			count_vm_event(PGMAJFAULT);
 			count_memcg_event_mm(fault_mm, PGMAJFAULT);
 		}
+
+		/*
+		 * Now swap device can only swap in order 0 folio, then we
+		 * should split the large swap entry stored in the pagecache
+		 * if necessary.
+		 */
+		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);
+		}
+
 		/* Here we actually start the io */
 		folio = shmem_swapin_cluster(swap, gfp, info, index);
 		if (!folio) {