[PATCH v9 6/7] mm: zswap: Support large folios in zswap_store().

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



zswap_store() will store large folios by compressing them page by page.

This patch provides a sequential implementation of storing a large folio
in zswap_store() by iterating through each page in the folio to compress
and store it in the zswap zpool.

zswap_store() calls the newly added zswap_store_page() function for each
page in the folio. zswap_store_page() handles compressing and storing each
page.

We check the global and per-cgroup limits once at the beginning of
zswap_store(), and only check that the limit is not reached yet. This is
racy and inaccurate, but it should be sufficient for now. We also obtain
initial references to the relevant objcg and pool to guarantee that
subsequent references can be acquired by zswap_store_page(). A new function
zswap_pool_get() is added to facilitate this.

If these one-time checks pass, we compress the pages of the folio, while
maintaining a running count of compressed bytes for all the folio's pages.
If all pages are successfully compressed and stored, we do the cgroup
zswap charging with the total compressed bytes, and batch update the
zswap_stored_pages atomic/zswpout event stats with folio_nr_pages() once,
before returning from zswap_store().

If an error is encountered during the store of any page in the folio,
all pages in that folio currently stored in zswap will be invalidated.
Thus, a folio is either entirely stored in zswap, or entirely not stored
in zswap.

The most important value provided by this patch is it enables swapping out
large folios to zswap without splitting them. Furthermore, it batches some
operations while doing so (cgroup charging, stats updates).

This patch also forms the basis for building compress batching of pages in
a large folio in zswap_store() by compressing up to say, 8 pages of the
folio in parallel in hardware using the Intel In-Memory Analytics
Accelerator (Intel IAA).

This change reuses and adapts the functionality in Ryan Roberts' RFC
patch [1]:

  "[RFC,v1] mm: zswap: Store large folios without splitting"

  [1] https://lore.kernel.org/linux-mm/20231019110543.3284654-1-ryan.roberts@xxxxxxx/T/#u

Also, addressed some of the RFC comments from the discussion in [1].

Co-developed-by: Ryan Roberts
Signed-off-by:
Signed-off-by: Kanchana P Sridhar <kanchana.p.sridhar@xxxxxxxxx>
---
 mm/zswap.c | 220 +++++++++++++++++++++++++++++++++++++----------------
 1 file changed, 153 insertions(+), 67 deletions(-)

diff --git a/mm/zswap.c b/mm/zswap.c
index 2b8da50f6322..b74c8de99646 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -411,6 +411,12 @@ static int __must_check zswap_pool_tryget(struct zswap_pool *pool)
 	return percpu_ref_tryget(&pool->ref);
 }
 
+/* The caller must already have a reference. */
+static void zswap_pool_get(struct zswap_pool *pool)
+{
+	percpu_ref_get(&pool->ref);
+}
+
 static void zswap_pool_put(struct zswap_pool *pool)
 {
 	percpu_ref_put(&pool->ref);
@@ -1402,68 +1408,52 @@ static void shrink_worker(struct work_struct *w)
 /*********************************
 * main API
 **********************************/
-bool zswap_store(struct folio *folio)
+
+/*
+ * Stores the page at specified "index" in a folio.
+ *
+ * @page:  The page to store in zswap.
+ * @objcg: The folio's objcg. Caller has a reference.
+ * @pool:  The zswap_pool to store the compressed data for the page.
+ *         The caller should have obtained a reference to a valid
+ *         zswap_pool by calling zswap_pool_tryget(), to pass as this
+ *         argument.
+ * @tree:  The xarray for the @page's folio's swap.
+ * @compressed_bytes: The compressed entry->length value is added
+ *                    to this, so that the caller can get the total
+ *                    compressed lengths of all sub-pages in a folio.
+ */
+static bool zswap_store_page(struct page *page,
+			     struct obj_cgroup *objcg,
+			     struct zswap_pool *pool,
+			     struct xarray *tree,
+			     size_t *compressed_bytes)
 {
-	swp_entry_t swp = folio->swap;
-	pgoff_t offset = swp_offset(swp);
-	struct xarray *tree = swap_zswap_tree(swp);
 	struct zswap_entry *entry, *old;
-	struct obj_cgroup *objcg = NULL;
-	struct mem_cgroup *memcg = NULL;
-
-	VM_WARN_ON_ONCE(!folio_test_locked(folio));
-	VM_WARN_ON_ONCE(!folio_test_swapcache(folio));
-
-	/* Large folios aren't supported */
-	if (folio_test_large(folio))
-		return false;
-
-	if (!zswap_enabled)
-		goto check_old;
-
-	/* Check cgroup limits */
-	objcg = get_obj_cgroup_from_folio(folio);
-	if (objcg && !obj_cgroup_may_zswap(objcg)) {
-		memcg = get_mem_cgroup_from_objcg(objcg);
-		if (shrink_memcg(memcg)) {
-			mem_cgroup_put(memcg);
-			goto reject;
-		}
-		mem_cgroup_put(memcg);
-	}
-
-	if (zswap_check_limits())
-		goto reject;
 
 	/* allocate entry */
-	entry = zswap_entry_cache_alloc(GFP_KERNEL, folio_nid(folio));
+	entry = zswap_entry_cache_alloc(GFP_KERNEL, folio_nid(page_folio(page)));
 	if (!entry) {
 		zswap_reject_kmemcache_fail++;
 		goto reject;
 	}
 
-	/* if entry is successfully added, it keeps the reference */
-	entry->pool = zswap_pool_current_get();
-	if (!entry->pool)
-		goto freepage;
+	/* zswap_store() already holds a ref on 'objcg' and 'pool' */
+	if (objcg)
+		obj_cgroup_get(objcg);
+	zswap_pool_get(pool);
 
-	if (objcg) {
-		memcg = get_mem_cgroup_from_objcg(objcg);
-		if (memcg_list_lru_alloc(memcg, &zswap_list_lru, GFP_KERNEL)) {
-			mem_cgroup_put(memcg);
-			goto put_pool;
-		}
-		mem_cgroup_put(memcg);
-	}
+	/* if entry is successfully added, it keeps the reference */
+	entry->pool = pool;
 
-	if (!zswap_compress(&folio->page, entry))
-		goto put_pool;
+	if (!zswap_compress(page, entry))
+		goto put_pool_objcg;
 
-	entry->swpentry = swp;
+	entry->swpentry = page_swap_entry(page);
 	entry->objcg = objcg;
 	entry->referenced = true;
 
-	old = xa_store(tree, offset, entry, GFP_KERNEL);
+	old = xa_store(tree, swp_offset(entry->swpentry), entry, GFP_KERNEL);
 	if (xa_is_err(old)) {
 		int err = xa_err(old);
 
@@ -1480,11 +1470,6 @@ bool zswap_store(struct folio *folio)
 	if (old)
 		zswap_entry_free(old);
 
-	if (objcg) {
-		obj_cgroup_charge_zswap(objcg, entry->length);
-		count_objcg_events(objcg, ZSWPOUT, 1);
-	}
-
 	/*
 	 * We finish initializing the entry while it's already in xarray.
 	 * This is safe because:
@@ -1496,36 +1481,137 @@ bool zswap_store(struct folio *folio)
 	 *    an incoherent entry.
 	 */
 	if (entry->length) {
+		*compressed_bytes += entry->length;
 		INIT_LIST_HEAD(&entry->lru);
 		zswap_lru_add(&zswap_list_lru, entry);
 	}
 
-	/* update stats */
-	atomic_long_inc(&zswap_stored_pages);
-	count_vm_event(ZSWPOUT);
-
+	/*
+	 * We shouldn't have any possibility of failure after the entry is
+	 * added in the xarray. The pool/objcg refs obtained here will only
+	 * be dropped if/when zswap_entry_free() gets called.
+	 */
 	return true;
 
 store_failed:
 	zpool_free(entry->pool->zpool, entry->handle);
-put_pool:
-	zswap_pool_put(entry->pool);
-freepage:
+put_pool_objcg:
+	zswap_pool_put(pool);
+	obj_cgroup_put(objcg);
 	zswap_entry_cache_free(entry);
 reject:
+	return false;
+}
+
+bool zswap_store(struct folio *folio)
+{
+	long nr_pages = folio_nr_pages(folio);
+	swp_entry_t swp = folio->swap;
+	struct xarray *tree = swap_zswap_tree(swp);
+	struct obj_cgroup *objcg = NULL;
+	struct mem_cgroup *memcg = NULL;
+	struct zswap_pool *pool;
+	size_t compressed_bytes = 0;
+	bool ret = false;
+	long index;
+
+	VM_WARN_ON_ONCE(!folio_test_locked(folio));
+	VM_WARN_ON_ONCE(!folio_test_swapcache(folio));
+
+	if (!zswap_enabled)
+		goto check_old;
+
+	/*
+	 * Check cgroup zswap limits:
+	 *
+	 * The cgroup zswap limit check is done once at the beginning of
+	 * zswap_store(). The cgroup charging is done once, at the end
+	 * of a successful folio store. What this means is, if the cgroup
+	 * was within the zswap_max limit at the beginning of a large folio
+	 * store, it could go over the limit by at most (HPAGE_PMD_NR - 1)
+	 * pages due to this store.
+	 */
+	objcg = get_obj_cgroup_from_folio(folio);
+	if (objcg && !obj_cgroup_may_zswap(objcg)) {
+		memcg = get_mem_cgroup_from_objcg(objcg);
+		if (shrink_memcg(memcg)) {
+			mem_cgroup_put(memcg);
+			goto put_objcg;
+		}
+		mem_cgroup_put(memcg);
+	}
+
+	/*
+	 * Check zpool utilization against zswap limits:
+	 *
+	 * The zswap zpool utilization is also checked against the limits
+	 * just once, at the start of zswap_store(). If the check passes,
+	 * any breaches of the limits set by zswap_max_pages() or
+	 * zswap_accept_thr_pages() that may happen while storing this
+	 * folio, will only be detected during the next call to
+	 * zswap_store() by any process.
+	 */
+	if (zswap_check_limits())
+		goto put_objcg;
+
+	pool = zswap_pool_current_get();
+	if (!pool)
+		goto put_objcg;
+
+	if (objcg) {
+		memcg = get_mem_cgroup_from_objcg(objcg);
+		if (memcg_list_lru_alloc(memcg, &zswap_list_lru, GFP_KERNEL)) {
+			mem_cgroup_put(memcg);
+			goto put_pool;
+		}
+		mem_cgroup_put(memcg);
+	}
+
+	/*
+	 * Store each page of the folio as a separate entry. If we fail to
+	 * store a page, unwind by deleting all the pages for this folio
+	 * currently in zswap.
+	 */
+	for (index = 0; index < nr_pages; ++index) {
+		if (!zswap_store_page(folio_page(folio, index), objcg, pool, tree, &compressed_bytes))
+			goto put_pool;
+	}
+
+	if (objcg) {
+		obj_cgroup_charge_zswap(objcg, compressed_bytes);
+		count_objcg_events(objcg, ZSWPOUT, nr_pages);
+	}
+
+	atomic_long_add(nr_pages, &zswap_stored_pages);
+	count_vm_events(ZSWPOUT, nr_pages);
+
+	ret = true;
+
+put_pool:
+	zswap_pool_put(pool);
+put_objcg:
 	obj_cgroup_put(objcg);
-	if (zswap_pool_reached_full)
+	if (!ret && zswap_pool_reached_full)
 		queue_work(shrink_wq, &zswap_shrink_work);
 check_old:
 	/*
-	 * If the zswap store fails or zswap is disabled, we must invalidate the
-	 * possibly stale entry which was previously stored at this offset.
-	 * Otherwise, writeback could overwrite the new data in the swapfile.
+	 * If the zswap store fails or zswap is disabled, we must invalidate
+	 * the possibly stale entries which were previously stored at the
+	 * offsets corresponding to each page of the folio. Otherwise,
+	 * writeback could overwrite the new data in the swapfile.
 	 */
-	entry = xa_erase(tree, offset);
-	if (entry)
-		zswap_entry_free(entry);
-	return false;
+	if (!ret) {
+		pgoff_t offset = swp_offset(swp);
+		struct zswap_entry *entry;
+
+		for (index = 0; index < nr_pages; ++index) {
+			entry = xa_erase(tree, offset + index);
+			if (entry)
+				zswap_entry_free(entry);
+		}
+	}
+
+	return ret;
 }
 
 bool zswap_load(struct folio *folio)
-- 
2.27.0





[Index of Archives]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [IETF Annouce]     [Bugtraq]     [Linux OMAP]     [Linux MIPS]     [eCos]     [Asterisk Internet PBX]     [Linux API]

  Powered by Linux