[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <SJ0PR11MB56783A35B58B15851C4AD32FC98D2@SJ0PR11MB5678.namprd11.prod.outlook.com>
Date: Tue, 20 Aug 2024 20:03:06 +0000
From: "Sridhar, Kanchana P" <kanchana.p.sridhar@...el.com>
To: "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"linux-mm@...ck.org" <linux-mm@...ck.org>, "hannes@...xchg.org"
<hannes@...xchg.org>, "yosryahmed@...gle.com" <yosryahmed@...gle.com>,
"nphamcs@...il.com" <nphamcs@...il.com>, "ryan.roberts@....com"
<ryan.roberts@....com>, "Huang, Ying" <ying.huang@...el.com>,
"21cnbao@...il.com" <21cnbao@...il.com>, "akpm@...ux-foundation.org"
<akpm@...ux-foundation.org>
CC: "Zou, Nanhai" <nanhai.zou@...el.com>, "Feghali, Wajdi K"
<wajdi.k.feghali@...el.com>, "Gopal, Vinodh" <vinodh.gopal@...el.com>,
"Sridhar, Kanchana P" <kanchana.p.sridhar@...el.com>
Subject: RE: [PATCH v4 2/4] mm: zswap: zswap_store() extended to handle mTHP
folios.
The build error is fixed in the following patch implemented against the latest mm-unstable:
https://patchwork.kernel.org/project/linux-mm/patch/20240820195005.5941-1-kanchana.p.sridhar@intel.com/
Reported-by: kernel test robot <lkp@...el.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202408202320.trSaY2o4-lkp@intel.com/
> -----Original Message-----
> From: Sridhar, Kanchana P <kanchana.p.sridhar@...el.com>
> Sent: Sunday, August 18, 2024 7:16 PM
> To: linux-kernel@...r.kernel.org; linux-mm@...ck.org;
> hannes@...xchg.org; yosryahmed@...gle.com; nphamcs@...il.com;
> ryan.roberts@....com; Huang, Ying <ying.huang@...el.com>;
> 21cnbao@...il.com; akpm@...ux-foundation.org
> Cc: Zou, Nanhai <nanhai.zou@...el.com>; Feghali, Wajdi K
> <wajdi.k.feghali@...el.com>; Gopal, Vinodh <vinodh.gopal@...el.com>;
> Sridhar, Kanchana P <kanchana.p.sridhar@...el.com>
> Subject: [PATCH v4 2/4] mm: zswap: zswap_store() extended to handle mTHP
> folios.
>
> zswap_store() will now process and store mTHP and PMD-size THP folios.
>
> 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@....com/T/#u
>
> This patch provides a sequential implementation of storing an mTHP in
> zswap_store() by iterating through each page in the folio to compress
> and store it in the zswap zpool.
>
> Towards this goal, zswap_compress() is modified to take a page instead
> of a folio as input.
>
> Each page's swap offset is stored as a separate zswap entry.
>
> If an error is encountered during the store of any page in the mTHP,
> all previous pages/entries stored will be invalidated. Thus, an mTHP
> is either entirely stored in ZSWAP, or entirely not stored in ZSWAP.
>
> This forms the basis for building batching of pages during zswap store
> of large folios, by compressing batches of up to say, 8 pages in an
> mTHP in parallel in hardware, with the Intel In-Memory Analytics
> Accelerator (Intel IAA).
>
> 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@...el.com>
> ---
> mm/zswap.c | 234 +++++++++++++++++++++++++++++++++++++++----------
> ----
> 1 file changed, 172 insertions(+), 62 deletions(-)
>
> diff --git a/mm/zswap.c b/mm/zswap.c
> index 6434e76a4ea3..9862a4cf0651 100644
> --- a/mm/zswap.c
> +++ b/mm/zswap.c
> @@ -886,7 +886,7 @@ static int zswap_cpu_comp_dead(unsigned int cpu,
> struct hlist_node *node)
> return 0;
> }
>
> -static bool zswap_compress(struct folio *folio, struct zswap_entry *entry)
> +static bool zswap_compress(struct page *page, struct zswap_entry *entry)
> {
> struct crypto_acomp_ctx *acomp_ctx;
> struct scatterlist input, output;
> @@ -904,7 +904,7 @@ static bool zswap_compress(struct folio *folio, struct
> zswap_entry *entry)
>
> dst = acomp_ctx->buffer;
> sg_init_table(&input, 1);
> - sg_set_folio(&input, folio, PAGE_SIZE, 0);
> + sg_set_page(&input, page, PAGE_SIZE, 0);
>
> /*
> * We need PAGE_SIZE * 2 here since there maybe over-compression
> case,
> @@ -1455,36 +1455,83 @@ static void zswap_fill_folio(struct folio *folio,
> unsigned long value)
> /*********************************
> * main API
> **********************************/
> -bool zswap_store(struct folio *folio)
> +
> +/*
> + * Returns true if the entry was successfully
> + * stored in the xarray, and false otherwise.
> + */
> +static bool zswap_store_entry(struct xarray *tree,
> + struct zswap_entry *entry)
> {
> - 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;
> - unsigned long value;
> + struct zswap_entry *old;
> + pgoff_t offset = swp_offset(entry->swpentry);
>
> - VM_WARN_ON_ONCE(!folio_test_locked(folio));
> - VM_WARN_ON_ONCE(!folio_test_swapcache(folio));
> + old = xa_store(tree, offset, entry, GFP_KERNEL);
>
> - /* Large folios aren't supported */
> - if (folio_test_large(folio))
> + if (xa_is_err(old)) {
> + int err = xa_err(old);
> +
> + WARN_ONCE(err != -ENOMEM, "unexpected xarray error:
> %d\n", err);
> + zswap_reject_alloc_fail++;
> return false;
> + }
>
> - if (!zswap_enabled)
> - goto check_old;
> + /*
> + * We may have had an existing entry that became stale when
> + * the folio was redirtied and now the new version is being
> + * swapped out. Get rid of the old.
> + */
> + if (old)
> + zswap_entry_free(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);
> + return true;
> +}
> +
> +/*
> + * 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.
> + *
> + * This is called after the store of the i-th offset in a large folio has
> + * failed. All zswap entries in the folio must be deleted. This helps make
> + * sure that a swapped-out mTHP is either entirely stored in zswap, or
> + * entirely not stored in zswap.
> + *
> + * This is also called if zswap_store() is invoked, but zswap is not enabled.
> + * All offsets for the folio are deleted from zswap in this case.
> + */
> +static void zswap_delete_stored_offsets(struct xarray *tree,
> + pgoff_t offset,
> + long nr_pages)
> +{
> + struct zswap_entry *entry;
> + long i;
> +
> + for (i = 0; i < nr_pages; ++i) {
> + entry = xa_erase(tree, offset + i);
> + if (entry)
> + zswap_entry_free(entry);
> }
> +}
> +
> +/*
> + * Stores the page at specified "index" in a folio.
> + */
> +static bool zswap_store_page(struct folio *folio, long index,
> + struct obj_cgroup *objcg,
> + struct zswap_pool *pool)
> +{
> + swp_entry_t swp = folio->swap;
> + int type = swp_type(swp);
> + pgoff_t offset = swp_offset(swp) + index;
> + struct page *page = folio_page(folio, index);
> + struct xarray *tree = swap_zswap_tree(swp);
> + struct zswap_entry *entry;
> + unsigned long value;
> +
> + if (objcg)
> + obj_cgroup_get(objcg);
>
> if (zswap_check_limits())
> goto reject;
> @@ -1496,7 +1543,7 @@ bool zswap_store(struct folio *folio)
> goto reject;
> }
>
> - if (zswap_is_folio_same_filled(folio, 0, &value)) {
> + if (zswap_is_folio_same_filled(folio, index, &value)) {
> entry->length = 0;
> entry->value = value;
> atomic_inc(&zswap_same_filled_pages);
> @@ -1504,43 +1551,21 @@ bool zswap_store(struct folio *folio)
> }
>
> /* if entry is successfully added, it keeps the reference */
> - entry->pool = zswap_pool_current_get();
> - if (!entry->pool)
> + if (!zswap_pool_get(pool))
> goto freepage;
>
> - 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);
> - }
> + entry->pool = pool;
>
> - if (!zswap_compress(folio, entry))
> + if (!zswap_compress(page, entry))
> goto put_pool;
>
> store_entry:
> - entry->swpentry = swp;
> + entry->swpentry = swp_entry(type, offset);
> entry->objcg = objcg;
> entry->referenced = true;
>
> - old = xa_store(tree, offset, entry, GFP_KERNEL);
> - if (xa_is_err(old)) {
> - int err = xa_err(old);
> -
> - WARN_ONCE(err != -ENOMEM, "unexpected xarray error:
> %d\n", err);
> - zswap_reject_alloc_fail++;
> + if (!zswap_store_entry(tree, entry))
> goto store_failed;
> - }
> -
> - /*
> - * We may have had an existing entry that became stale when
> - * the folio was redirtied and now the new version is being
> - * swapped out. Get rid of the old.
> - */
> - if (old)
> - zswap_entry_free(old);
>
> if (objcg) {
> obj_cgroup_charge_zswap(objcg, entry->length);
> @@ -1574,7 +1599,7 @@ bool zswap_store(struct folio *folio)
> else {
> zpool_free(entry->pool->zpool, entry->handle);
> put_pool:
> - zswap_pool_put(entry->pool);
> + zswap_pool_put(pool);
> }
> freepage:
> zswap_entry_cache_free(entry);
> @@ -1582,16 +1607,101 @@ bool zswap_store(struct folio *folio)
> obj_cgroup_put(objcg);
> if (zswap_pool_reached_full)
> queue_work(shrink_wq, &zswap_shrink_work);
> -check_old:
> +
> + return false;
> +}
> +
> +/*
> + * Modified to store mTHP folios. Each page in the mTHP will be compressed
> + * and stored sequentially.
> + */
> +bool zswap_store(struct folio *folio)
> +{
> + long nr_pages = folio_nr_pages(folio);
> + swp_entry_t swp = folio->swap;
> + pgoff_t offset = swp_offset(swp);
> + struct xarray *tree = swap_zswap_tree(swp);
> + struct obj_cgroup *objcg = NULL;
> + struct mem_cgroup *memcg = NULL;
> + struct zswap_pool *pool;
> + 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 reject;
> +
> /*
> - * 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.
> + * Check cgroup limits:
> + *
> + * The cgroup zswap limit check is done once at the beginning of an
> + * mTHP store, and not within zswap_store_page() for each page
> + * in the mTHP. We do however check the zswap pool limits at the
> + * start of zswap_store_page(). What this means is, the cgroup
> + * could go over the limits by at most (HPAGE_PMD_NR - 1) pages.
> + * However, the per-store-page zswap pool limits check should
> + * hopefully trigger the cgroup aware and zswap LRU aware global
> + * reclaim implemented in the shrinker. If this assumption holds,
> + * the cgroup exceeding the zswap limits could potentially be
> + * resolved before the next zswap_store, and if it is not, the next
> + * zswap_store would fail the cgroup zswap limit check at the start.
> */
> - entry = xa_erase(tree, offset);
> - if (entry)
> - zswap_entry_free(entry);
> - return false;
> + 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);
> + }
> +
> + 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 removing all the previous pages we stored.
> + */
> + for (index = 0; index < nr_pages; ++index) {
> + if (!zswap_store_page(folio, index, objcg, pool))
> + goto put_pool;
> + }
> +
> + ret = true;
> +
> +put_pool:
> + zswap_pool_put(pool);
> +put_objcg:
> + obj_cgroup_put(objcg);
> + if (zswap_pool_reached_full)
> + queue_work(shrink_wq, &zswap_shrink_work);
> +reject:
> + /*
> + * 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.
> + */
> + if (!ret)
> + zswap_delete_stored_offsets(tree, offset, nr_pages);
> +
> + return ret;
> }
>
> bool zswap_load(struct folio *folio)
> --
> 2.27.0
Powered by blists - more mailing lists