1 files changed, 55 insertions, 15 deletions

diff --git a/mm/zswap.c b/mm/zswap.c
index 9dec853647c8..6f8850c44b61 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1080,7 +1080,17 @@ static void zswap_decompress(struct zswap_entry *entry, struct page *page)
 	mutex_lock(&acomp_ctx->mutex);
 
 	src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
-	if (acomp_ctx->is_sleepable && !zpool_can_sleep_mapped(zpool)) {
+	/*
+	 * If zpool_map_handle is atomic, we cannot reliably utilize its mapped buffer
+	 * to do crypto_acomp_decompress() which might sleep. In such cases, we must
+	 * resort to copying the buffer to a temporary one.
+	 * Meanwhile, zpool_map_handle() might return a non-linearly mapped buffer,
+	 * such as a kmap address of high memory or even ever a vmap address.
+	 * However, sg_init_one is only equipped to handle linearly mapped low memory.
+	 * In such cases, we also must copy the buffer to a temporary and lowmem one.
+	 */
+	if ((acomp_ctx->is_sleepable && !zpool_can_sleep_mapped(zpool)) ||
+	    !virt_addr_valid(src)) {
 		memcpy(acomp_ctx->buffer, src, entry->length);
 		src = acomp_ctx->buffer;
 		zpool_unmap_handle(zpool, entry->handle);
@@ -1094,7 +1104,7 @@ static void zswap_decompress(struct zswap_entry *entry, struct page *page)
 	BUG_ON(acomp_ctx->req->dlen != PAGE_SIZE);
 	mutex_unlock(&acomp_ctx->mutex);
 
-	if (!acomp_ctx->is_sleepable || zpool_can_sleep_mapped(zpool))
+	if (src != acomp_ctx->buffer)
 		zpool_unmap_handle(zpool, entry->handle);
 }
 
@@ -1313,15 +1323,30 @@ static unsigned long zswap_shrinker_count(struct shrinker *shrinker,
 	if (!zswap_shrinker_enabled || !mem_cgroup_zswap_writeback_enabled(memcg))
 		return 0;
 
-#ifdef CONFIG_MEMCG_KMEM
-	mem_cgroup_flush_stats(memcg);
-	nr_backing = memcg_page_state(memcg, MEMCG_ZSWAP_B) >> PAGE_SHIFT;
-	nr_stored = memcg_page_state(memcg, MEMCG_ZSWAPPED);
-#else
-	/* use pool stats instead of memcg stats */
-	nr_backing = zswap_pool_total_size >> PAGE_SHIFT;
-	nr_stored = atomic_read(&zswap_nr_stored);
-#endif
+	/*
+	 * The shrinker resumes swap writeback, which will enter block
+	 * and may enter fs. XXX: Harmonize with vmscan.c __GFP_FS
+	 * rules (may_enter_fs()), which apply on a per-folio basis.
+	 */
+	if (!gfp_has_io_fs(sc->gfp_mask))
+		return 0;
+
+	/*
+	 * For memcg, use the cgroup-wide ZSWAP stats since we don't
+	 * have them per-node and thus per-lruvec. Careful if memcg is
+	 * runtime-disabled: we can get sc->memcg == NULL, which is ok
+	 * for the lruvec, but not for memcg_page_state().
+	 *
+	 * Without memcg, use the zswap pool-wide metrics.
+	 */
+	if (!mem_cgroup_disabled()) {
+		mem_cgroup_flush_stats(memcg);
+		nr_backing = memcg_page_state(memcg, MEMCG_ZSWAP_B) >> PAGE_SHIFT;
+		nr_stored = memcg_page_state(memcg, MEMCG_ZSWAPPED);
+	} else {
+		nr_backing = zswap_pool_total_size >> PAGE_SHIFT;
+		nr_stored = atomic_read(&zswap_nr_stored);
+	}
 
 	if (!nr_stored)
 		return 0;
@@ -1618,6 +1643,7 @@ bool zswap_load(struct folio *folio)
 	swp_entry_t swp = folio->swap;
 	pgoff_t offset = swp_offset(swp);
 	struct page *page = &folio->page;
+	bool swapcache = folio_test_swapcache(folio);
 	struct zswap_tree *tree = swap_zswap_tree(swp);
 	struct zswap_entry *entry;
 	u8 *dst;
@@ -1630,7 +1656,20 @@ bool zswap_load(struct folio *folio)
 		spin_unlock(&tree->lock);
 		return false;
 	}
-	zswap_rb_erase(&tree->rbroot, entry);
+	/*
+	 * When reading into the swapcache, invalidate our entry. The
+	 * swapcache can be the authoritative owner of the page and
+	 * its mappings, and the pressure that results from having two
+	 * in-memory copies outweighs any benefits of caching the
+	 * compression work.
+	 *
+	 * (Most swapins go through the swapcache. The notable
+	 * exception is the singleton fault on SWP_SYNCHRONOUS_IO
+	 * files, which reads into a private page and may free it if
+	 * the fault fails. We remain the primary owner of the entry.)
+	 */
+	if (swapcache)
+		zswap_rb_erase(&tree->rbroot, entry);
 	spin_unlock(&tree->lock);
 
 	if (entry->length)
@@ -1645,9 +1684,10 @@ bool zswap_load(struct folio *folio)
 	if (entry->objcg)
 		count_objcg_event(entry->objcg, ZSWPIN);
 
-	zswap_entry_free(entry);
-
-	folio_mark_dirty(folio);
+	if (swapcache) {
+		zswap_entry_free(entry);
+		folio_mark_dirty(folio);
+	}
 
 	return true;
 }