[PATCH v3 06/11] mm, swap: write back vswap zswap entries to physical swap

[Nhat Pham <nphamcs@gmail.com>]

Add support for writing back zswap-backed vswap entries to physical
swap. The mechanism mirrors the existing zswap writeback path, except
the backing physical slot is allocated on demand at writeback time
rather than already being pinned by the PTE.

Now that vswap entries can be written back, relax the zswap shrinker
gate: replace the blanket "skip while vswap is enabled" check with
can_zswap_writeback(), which only skips when no physical slot is free to
allocate on demand. This keeps the shrinker off futile writeback when no
physical swap is available while letting it drain vswap entries
otherwise.

Signed-off-by: Nhat Pham <nphamcs@gmail.com>
---
 mm/zswap.c | 76 +++++++++++++++++++++++++++++++++++++++---------------
 1 file changed, 55 insertions(+), 21 deletions(-)

diff --git a/mm/zswap.c b/mm/zswap.c
index 5dc338188a29..128309d5063b 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1007,12 +1007,12 @@ static bool zswap_decompress(struct zswap_entry *entry, struct folio *folio)
 static int zswap_writeback_entry(struct zswap_entry *entry,
 				 swp_entry_t swpentry)
 {
-	struct xarray *tree;
 	pgoff_t offset = swp_offset(swpentry);
 	struct folio *folio;
 	struct mempolicy *mpol;
 	struct swap_info_struct *si;
 	struct swap_io_ctx ctx = {};
+	swp_entry_t phys = {};
 	int ret = 0;
 
 	/* try to allocate swap cache folio */
@@ -1020,12 +1020,6 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
 	if (!si)
 		return -EEXIST;
 
-	/* Vswap entries have no physical backing to write to. */
-	if (swap_is_vswap(si)) {
-		put_swap_device(si);
-		return -EINVAL;
-	}
-
 	mpol = get_task_policy(current);
 	folio = swap_cache_alloc_folio(swpentry, GFP_KERNEL, BIT(0), NULL, mpol,
 				       NO_INTERLEAVE_INDEX);
@@ -1044,41 +1038,71 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
 	/*
 	 * folio is locked, and the swapcache is now secured against
 	 * concurrent swapping to and from the slot, and concurrent
-	 * swapoff so we can safely dereference the zswap tree here.
-	 * Verify that the swap entry hasn't been invalidated and recycled
-	 * behind our backs, to avoid overwriting a new swap folio with
-	 * old compressed data. Only when this is successful can the entry
-	 * be dereferenced.
+	 * swapoff so we can safely dereference the zswap tree (or vswap
+	 * vtable) here. Verify that the swap entry hasn't been
+	 * invalidated and recycled behind our backs, to avoid overwriting
+	 * a new swap folio with old compressed data. Only when this is
+	 * successful can the entry be dereferenced.
 	 */
-	tree = swap_zswap_tree(swpentry);
-	if (entry != xa_load(tree, offset)) {
+	if (entry != zswap_entry_load(swpentry)) {
 		ret = -ENOMEM;
 		goto out;
 	}
 
+	if (swap_is_vswap(si)) {
+		/*
+		 * Allocate physical backing before decompress so a failure
+		 * wastes no work. folio_realloc_swap retags the vtable to
+		 * PHYS, leaving the entry pointer held only by the caller.
+		 */
+		phys = folio_realloc_swap(folio);
+		if (!phys.val) {
+			ret = -ENOMEM;
+			goto out;
+		}
+	}
+
 	if (!zswap_decompress(entry, folio)) {
 		ret = -EIO;
+		/*
+		 * For vswap: folio_realloc_swap already moved the entry
+		 * out of the vtable. Restore it via vswap_zswap_store so
+		 * the entry stays tracked (and the just-allocated PHYS
+		 * slot is freed). For non-vswap: entry is still in the
+		 * zswap tree.
+		 */
+		if (swap_is_vswap(si) && phys.val)
+			vswap_zswap_store(swpentry, entry);
 		goto out;
 	}
 
-	xa_erase(tree, offset);
+	if (!swap_is_vswap(si))
+		xa_erase(swap_zswap_tree(swpentry), offset);
 
 	count_vm_event(ZSWPWB);
 	if (entry->objcg)
 		count_objcg_events(entry->objcg, ZSWPWB, 1);
 
-	zswap_entry_free(entry);
-
 	/* folio is up to date */
 	folio_mark_uptodate(folio);
 
 	/* move it to the tail of the inactive list after end_writeback */
 	folio_set_reclaim(folio);
 
-	/* start writeback */
-	__swap_writepage(&ctx, folio, folio->swap);
+	/*
+	 * Start writeback. The entry has been moved out of its prior location
+	 * (vtable PHYS for vswap, removed from the tree otherwise), so we own
+	 * the free. vswap writes to the on-demand physical slot; others write
+	 * to the folio's own entry.
+	 */
+	if (swap_is_vswap(si))
+		__swap_writepage(&ctx, folio, phys);
+	else
+		__swap_writepage(&ctx, folio, folio->swap);
 	swap_write_submit(&ctx);
 
+	zswap_entry_free(entry);
+
 out:
 	if (ret) {
 		swap_cache_del_folio(folio);
@@ -1091,6 +1115,16 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
 /*********************************
 * shrinker functions
 **********************************/
+/*
+ * vswap zswap entries need a physical slot allocated on demand (via
+ * folio_realloc_swap) for writeback; if none is free, writeback fails, so
+ * skip the shrinker to avoid spinning on entries we cannot drain.
+ */
+static bool can_zswap_writeback(void)
+{
+	return !vswap_is_enabled() || get_nr_swap_pages();
+}
+
 /*
  * The dynamic shrinker is modulated by the following factors:
  *
@@ -1228,7 +1262,7 @@ static unsigned long zswap_shrinker_count(struct shrinker *shrinker,
 	if (!zswap_shrinker_enabled || !mem_cgroup_zswap_writeback_enabled(memcg))
 		return 0;
 
-	if (vswap_is_enabled())
+	if (!can_zswap_writeback())
 		return 0;
 
 	/*
@@ -1313,7 +1347,7 @@ static int shrink_memcg(struct mem_cgroup *memcg)
 	if (!mem_cgroup_zswap_writeback_enabled(memcg))
 		return -ENOENT;
 
-	if (vswap_is_enabled())
+	if (!can_zswap_writeback())
 		return -ENOENT;
 
 	/*
-- 
2.53.0-Meta