[PATCH v3 06/15] mm/shmem: hold off eviction in shmem_writeout()

[David Hildenbrand (Arm)]

From: Josef Bacik <josef@xxxxxxxxxxxxxx>

Once shmem_writeout() has moved the folio from the page cache to the
swap cache, the folio lock no longer keeps the inode alive: truncation
and eviction find a swap entry, free it and do not wait for anybody.
That did not matter as long as swap_writeout() was the last thing the
function did.  But since it puts the folio back when swap_writeout()
returns AOP_WRITEPAGE_ACTIVATE, it uses the mapping and the inode
afterwards:

  reclaim                               last close of an unlinked file
  shmem_writeout()
    shmem_delete_from_page_cache()
    swap_writeout()
      zswap_store() fails               shmem_evict_inode()
      writeback is disabled               shmem_truncate_range()
      return AOP_WRITEPAGE_ACTIVATE         shmem_free_swap()
                                        destroy_inode()
                                        ... RCU grace period, freed
    shmem_add_to_page_cache(mapping)
      xas_lock_irq()            <- use after free

swap_writeout() behaves that way if zswap is enabled, cannot take the
folio and the memcg or one of its ancestors has memory.zswap.writeback
set to 0.

shmem_unuse() already added infrastructure to deal with that.
Reuse info->stop_eviction to protect the inode during writeout. Increment
it before removing the folio from the page cache, and decrement it after
swap_writeout() and any attempted reinsertion and inode accounting.
In shmem_evict_inode(), wait for the counter to reach zero even if
swapoff has already removed the inode from the swap list. Add some helpers
to make the code easier to digest.

Fix generated by an LLM and sent by Josef Bacik in private.

Fixes: 6344a6d9ce13 ("mm/shmem: writeout free swap if swap_writeout() reactivates")
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Josef Bacik <josef@xxxxxxxxxxxxxx>
Acked-by: Pedro Falcato <pfalcato@xxxxxxx>
Acked-by: Kiryl Shutsemau (Meta) <kas@xxxxxxxxxx>
Reviewed-by: Nhat Pham <nphamcs@xxxxxxxxx>
Reviewed-by: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
Tested-by: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
[ david: code cleanups; improve description ]
Tested-by: Gregory Price (Meta) <gourry@xxxxxxxxxx>
Signed-off-by: David Hildenbrand (Arm) <david@xxxxxxxxxx>
---
 mm/shmem.c | 36 ++++++++++++++++++++++++++++++------
 1 file changed, 30 insertions(+), 6 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index e3e4bbbe1d80..eddd5870be07 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1616,6 +1616,17 @@ static int shmem_setattr(const struct mnt_idmap *idmap,
 	return error;
 }
 
+static void shmem_disallow_eviction(struct shmem_inode_info *info)
+{
+	atomic_inc(&info->stop_eviction);
+}
+
+static void shmem_allow_eviction(struct shmem_inode_info *info)
+{
+	if (atomic_dec_and_test(&info->stop_eviction))
+		wake_up_var(&info->stop_eviction);
+}
+
 static void shmem_evict_inode(struct inode *inode)
 {
 	struct shmem_inode_info *info = SHMEM_I(inode);
@@ -1628,16 +1639,21 @@ static void shmem_evict_inode(struct inode *inode)
 		mapping_set_exiting(inode->i_mapping);
 		shmem_truncate_range(inode, 0, (loff_t)-1);
 		shmem_unused_huge_del(inode);
-		while (!list_empty(&info->swaplist)) {
-			/* Wait while shmem_unuse() is scanning this inode... */
+		/*
+		 * Writeout may still use the inode after swapoff has removed it
+		 * from the swaplist, so always wait at least once.
+		 */
+		do {
 			wait_var_event(&info->stop_eviction,
 				       !atomic_read(&info->stop_eviction));
+			if (list_empty(&info->swaplist))
+				break;
 			spin_lock(&shmem_swaplist_lock);
 			/* ...but beware of the race if we peeked too early */
 			if (!atomic_read(&info->stop_eviction))
 				list_del_init(&info->swaplist);
 			spin_unlock(&shmem_swaplist_lock);
-		}
+		} while (!list_empty(&info->swaplist));
 	}
 
 	simple_xattrs_free(&sbinfo->xa_cache, &info->xattrs, sbinfo->max_inodes ? &freed : NULL);
@@ -1776,15 +1792,14 @@ int shmem_unuse(unsigned int type)
 		 * remove placeholder inode from swaplist, nor let it be freed
 		 * (igrab() would protect from unlink, but not from unmount).
 		 */
-		atomic_inc(&info->stop_eviction);
+		shmem_disallow_eviction(info);
 		spin_unlock(&shmem_swaplist_lock);
 
 		error = shmem_unuse_inode(&info->vfs_inode, type);
 		cond_resched();
 
 		spin_lock(&shmem_swaplist_lock);
-		if (atomic_dec_and_test(&info->stop_eviction))
-			wake_up_var(&info->stop_eviction);
+		shmem_allow_eviction(info);
 		if (error)
 			break;
 		if (list_empty(&info->swaplist))
@@ -1915,6 +1930,13 @@ int shmem_writeout(struct swap_io_ctx *ctx, struct folio *folio,
 			spin_unlock(&shmem_swaplist_lock);
 		}
 
+		/*
+		 * Once the folio has left the page cache, its lock no longer
+		 * keeps the inode from being evicted and freed: hold eviction
+		 * off, in case the folio has to be put back below.
+		 */
+		shmem_disallow_eviction(info);
+
 		folio_dup_swap(folio, NULL);
 		shmem_delete_from_page_cache(folio, swp_to_radix_entry(folio->swap));
 
@@ -1922,6 +1944,7 @@ int shmem_writeout(struct swap_io_ctx *ctx, struct folio *folio,
 		error = swap_writeout(ctx, folio);
 		if (error != AOP_WRITEPAGE_ACTIVATE) {
 			/* folio has been unlocked */
+			shmem_allow_eviction(info);
 			return error;
 		}
 
@@ -1938,6 +1961,7 @@ int shmem_writeout(struct swap_io_ctx *ctx, struct folio *folio,
 			shmem_recalc_inode(inode, 0, -nr_pages);
 			folio_put_swap(folio, NULL);
 		}
+		shmem_allow_eviction(info);
 
 		/*
 		 * The swap_cache_del_folio() below could be left for

-- 
2.43.0