From af7628d6ec196999175ecb3fdb38336489b0f88a Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Fri, 17 Nov 2023 16:14:47 +0000 Subject: fs: convert error_remove_page to error_remove_folio There were already assertions that we were not passing a tail page to error_remove_page(), so make the compiler enforce that by converting everything to pass and use a folio. Link: https://lkml.kernel.org/r/20231117161447.2461643-7-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Cc: Naoya Horiguchi Signed-off-by: Andrew Morton --- mm/shmem.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'mm/shmem.c') diff --git a/mm/shmem.c b/mm/shmem.c index 91e2620148b2..97bc622da774 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -4445,8 +4445,8 @@ static void __init shmem_destroy_inodecache(void) } /* Keep the page in page cache instead of truncating it */ -static int shmem_error_remove_page(struct address_space *mapping, - struct page *page) +static int shmem_error_remove_folio(struct address_space *mapping, + struct folio *folio) { return 0; } @@ -4461,7 +4461,7 @@ const struct address_space_operations shmem_aops = { #ifdef CONFIG_MIGRATION .migrate_folio = migrate_folio, #endif - .error_remove_page = shmem_error_remove_page, + .error_remove_folio = shmem_error_remove_folio, }; EXPORT_SYMBOL(shmem_aops); -- cgit v1.2.3 From a4575c4138db887bd27dc7f87cf7cfb0224c6f5e Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Wed, 13 Dec 2023 21:58:42 +0000 Subject: mm: convert swap_cluster_readahead and swap_vma_readahead to return a folio shmem_swapin_cluster() immediately converts the page back to a folio, and swapin_readahead() may as well call folio_file_page() once instead of having each function call it. [willy@infradead.org: avoid NULL pointer deref] Link: https://lkml.kernel.org/r/ZYI7OcVlM1voKfBl@casper.infradead.org Link: https://lkml.kernel.org/r/20231213215842.671461-14-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Andrew Morton --- mm/shmem.c | 8 +++----- mm/swap.h | 6 +++--- mm/swap_state.c | 24 +++++++++++++----------- 3 files changed, 19 insertions(+), 19 deletions(-) (limited to 'mm/shmem.c') diff --git a/mm/shmem.c b/mm/shmem.c index c62f904ba1ca..a4d388973021 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1570,15 +1570,13 @@ static struct folio *shmem_swapin_cluster(swp_entry_t swap, gfp_t gfp, { struct mempolicy *mpol; pgoff_t ilx; - struct page *page; + struct folio *folio; mpol = shmem_get_pgoff_policy(info, index, 0, &ilx); - page = swap_cluster_readahead(swap, gfp, mpol, ilx); + folio = swap_cluster_readahead(swap, gfp, mpol, ilx); mpol_cond_put(mpol); - if (!page) - return NULL; - return page_folio(page); + return folio; } /* diff --git a/mm/swap.h b/mm/swap.h index 82c68ccb5ab1..758c46ca671e 100644 --- a/mm/swap.h +++ b/mm/swap.h @@ -52,8 +52,8 @@ struct folio *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, struct folio *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_flags, struct mempolicy *mpol, pgoff_t ilx, bool *new_page_allocated, bool skip_if_exists); -struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t flag, - struct mempolicy *mpol, pgoff_t ilx); +struct folio *swap_cluster_readahead(swp_entry_t entry, gfp_t flag, + struct mempolicy *mpol, pgoff_t ilx); struct page *swapin_readahead(swp_entry_t entry, gfp_t flag, struct vm_fault *vmf); @@ -80,7 +80,7 @@ static inline void show_swap_cache_info(void) { } -static inline struct page *swap_cluster_readahead(swp_entry_t entry, +static inline struct folio *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, struct mempolicy *mpol, pgoff_t ilx) { return NULL; diff --git a/mm/swap_state.c b/mm/swap_state.c index 97c8a950dd18..e671266ad772 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -620,7 +620,7 @@ static unsigned long swapin_nr_pages(unsigned long offset) * @mpol: NUMA memory allocation policy to be applied * @ilx: NUMA interleave index, for use only when MPOL_INTERLEAVE * - * Returns the struct page for entry and addr, after queueing swapin. + * Returns the struct folio for entry and addr, after queueing swapin. * * Primitive swap readahead code. We simply read an aligned block of * (1 << page_cluster) entries in the swap area. This method is chosen @@ -631,7 +631,7 @@ static unsigned long swapin_nr_pages(unsigned long offset) * are used for every page of the readahead: neighbouring pages on swap * are fairly likely to have been swapped out from the same node. */ -struct page *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, +struct folio *swap_cluster_readahead(swp_entry_t entry, gfp_t gfp_mask, struct mempolicy *mpol, pgoff_t ilx) { struct folio *folio; @@ -683,7 +683,7 @@ skip: if (unlikely(page_allocated)) swap_read_folio(folio, false, NULL); zswap_folio_swapin(folio); - return folio_file_page(folio, swp_offset(entry)); + return folio; } int init_swap_address_space(unsigned int type, unsigned long nr_pages) @@ -787,7 +787,7 @@ static void swap_ra_info(struct vm_fault *vmf, * @targ_ilx: NUMA interleave index, for use only when MPOL_INTERLEAVE * @vmf: fault information * - * Returns the struct page for entry and addr, after queueing swapin. + * Returns the struct folio for entry and addr, after queueing swapin. * * Primitive swap readahead code. We simply read in a few pages whose * virtual addresses are around the fault address in the same vma. @@ -795,9 +795,8 @@ static void swap_ra_info(struct vm_fault *vmf, * Caller must hold read mmap_lock if vmf->vma is not NULL. * */ -static struct page *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask, - struct mempolicy *mpol, pgoff_t targ_ilx, - struct vm_fault *vmf) +static struct folio *swap_vma_readahead(swp_entry_t targ_entry, gfp_t gfp_mask, + struct mempolicy *mpol, pgoff_t targ_ilx, struct vm_fault *vmf) { struct blk_plug plug; struct swap_iocb *splug = NULL; @@ -859,7 +858,7 @@ skip: if (unlikely(page_allocated)) swap_read_folio(folio, false, NULL); zswap_folio_swapin(folio); - return folio_file_page(folio, swp_offset(entry)); + return folio; } /** @@ -879,14 +878,17 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, { struct mempolicy *mpol; pgoff_t ilx; - struct page *page; + struct folio *folio; mpol = get_vma_policy(vmf->vma, vmf->address, 0, &ilx); - page = swap_use_vma_readahead() ? + folio = swap_use_vma_readahead() ? swap_vma_readahead(entry, gfp_mask, mpol, ilx, vmf) : swap_cluster_readahead(entry, gfp_mask, mpol, ilx); mpol_cond_put(mpol); - return page; + + if (!folio) + return NULL; + return folio_file_page(folio, swp_offset(entry)); } #ifdef CONFIG_SYSFS -- cgit v1.2.3 From 501a06fe8e4c185bbda371b8cedbdf1b23a633d8 Mon Sep 17 00:00:00 2001 From: Nhat Pham Date: Thu, 7 Dec 2023 11:24:06 -0800 Subject: zswap: memcontrol: implement zswap writeback disabling During our experiment with zswap, we sometimes observe swap IOs due to occasional zswap store failures and writebacks-to-swap. These swapping IOs prevent many users who cannot tolerate swapping from adopting zswap to save memory and improve performance where possible. This patch adds the option to disable this behavior entirely: do not writeback to backing swapping device when a zswap store attempt fail, and do not write pages in the zswap pool back to the backing swap device (both when the pool is full, and when the new zswap shrinker is called). This new behavior can be opted-in/out on a per-cgroup basis via a new cgroup file. By default, writebacks to swap device is enabled, which is the previous behavior. Initially, writeback is enabled for the root cgroup, and a newly created cgroup will inherit the current setting of its parent. Note that this is subtly different from setting memory.swap.max to 0, as it still allows for pages to be stored in the zswap pool (which itself consumes swap space in its current form). This patch should be applied on top of the zswap shrinker series: https://lore.kernel.org/linux-mm/20231130194023.4102148-1-nphamcs@gmail.com/ as it also disables the zswap shrinker, a major source of zswap writebacks. For the most part, this feature is motivated by internal parties who have already established their opinions regarding swapping - the workloads that are highly sensitive to IO, and especially those who are using servers with really slow disk performance (for instance, massive but slow HDDs). For these folks, it's impossible to convince them to even entertain zswap if swapping also comes as a packaged deal. Writeback disabling is quite a useful feature in these situations - on a mixed workloads deployment, they can disable writeback for the more IO-sensitive workloads, and enable writeback for other background workloads. For instance, on a server with HDD, I allocate memories and populate them with random values (so that zswap store will always fail), and specify memory.high low enough to trigger reclaim. The time it takes to allocate the memories and just read through it a couple of times (doing silly things like computing the values' average etc.): zswap.writeback disabled: real 0m30.537s user 0m23.687s sys 0m6.637s 0 pages swapped in 0 pages swapped out zswap.writeback enabled: real 0m45.061s user 0m24.310s sys 0m8.892s 712686 pages swapped in 461093 pages swapped out (the last two lines are from vmstat -s). [nphamcs@gmail.com: add a comment about recurring zswap store failures leading to reclaim inefficiency] Link: https://lkml.kernel.org/r/20231221005725.3446672-1-nphamcs@gmail.com Link: https://lkml.kernel.org/r/20231207192406.3809579-1-nphamcs@gmail.com Signed-off-by: Nhat Pham Suggested-by: Johannes Weiner Reviewed-by: Yosry Ahmed Acked-by: Chris Li Cc: Dan Streetman Cc: David Heidelberg Cc: Domenico Cerasuolo Cc: Hugh Dickins Cc: Jonathan Corbet Cc: Konrad Rzeszutek Wilk Cc: Michal Hocko Cc: Mike Rapoport (IBM) Cc: Muchun Song Cc: Roman Gushchin Cc: Sergey Senozhatsky Cc: Seth Jennings Cc: Shakeel Butt Cc: Tejun Heo Cc: Vitaly Wool Cc: Zefan Li Signed-off-by: Andrew Morton --- Documentation/admin-guide/cgroup-v2.rst | 15 +++++++++++++ Documentation/admin-guide/mm/zswap.rst | 10 +++++++++ include/linux/memcontrol.h | 12 +++++++++++ include/linux/zswap.h | 7 ++++++ mm/memcontrol.c | 38 +++++++++++++++++++++++++++++++++ mm/page_io.c | 5 +++++ mm/shmem.c | 3 +-- mm/zswap.c | 13 +++++++++-- 8 files changed, 99 insertions(+), 4 deletions(-) (limited to 'mm/shmem.c') diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 3f85254f3cef..5ec7dd753cd1 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1679,6 +1679,21 @@ PAGE_SIZE multiple when read back. limit, it will refuse to take any more stores before existing entries fault back in or are written out to disk. + memory.zswap.writeback + A read-write single value file. The default value is "1". The + initial value of the root cgroup is 1, and when a new cgroup is + created, it inherits the current value of its parent. + + When this is set to 0, all swapping attempts to swapping devices + are disabled. This included both zswap writebacks, and swapping due + to zswap store failures. If the zswap store failures are recurring + (for e.g if the pages are incompressible), users can observe + reclaim inefficiency after disabling writeback (because the same + pages might be rejected again and again). + + Note that this is subtly different from setting memory.swap.max to + 0, as it still allows for pages to be written to the zswap pool. + memory.pressure A read-only nested-keyed file. diff --git a/Documentation/admin-guide/mm/zswap.rst b/Documentation/admin-guide/mm/zswap.rst index 62fc244ec702..b42132969e31 100644 --- a/Documentation/admin-guide/mm/zswap.rst +++ b/Documentation/admin-guide/mm/zswap.rst @@ -153,6 +153,16 @@ attribute, e. g.:: Setting this parameter to 100 will disable the hysteresis. +Some users cannot tolerate the swapping that comes with zswap store failures +and zswap writebacks. Swapping can be disabled entirely (without disabling +zswap itself) on a cgroup-basis as follows: + + echo 0 > /sys/fs/cgroup//memory.zswap.writeback + +Note that if the store failures are recurring (for e.g if the pages are +incompressible), users can observe reclaim inefficiency after disabling +writeback (because the same pages might be rejected again and again). + When there is a sizable amount of cold memory residing in the zswap pool, it can be advantageous to proactively write these cold pages to swap and reclaim the memory for other use cases. By default, the zswap shrinker is disabled. diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 43b77363ab8e..5de775e6cdd9 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -219,6 +219,12 @@ struct mem_cgroup { #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) unsigned long zswap_max; + + /* + * Prevent pages from this memcg from being written back from zswap to + * swap, and from being swapped out on zswap store failures. + */ + bool zswap_writeback; #endif unsigned long soft_limit; @@ -1941,6 +1947,7 @@ static inline void count_objcg_event(struct obj_cgroup *objcg, bool obj_cgroup_may_zswap(struct obj_cgroup *objcg); void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size); void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size); +bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg); #else static inline bool obj_cgroup_may_zswap(struct obj_cgroup *objcg) { @@ -1954,6 +1961,11 @@ static inline void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size) { } +static inline bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg) +{ + /* if zswap is disabled, do not block pages going to the swapping device */ + return true; +} #endif #endif /* _LINUX_MEMCONTROL_H */ diff --git a/include/linux/zswap.h b/include/linux/zswap.h index e88572d4c720..0b709f5bc65f 100644 --- a/include/linux/zswap.h +++ b/include/linux/zswap.h @@ -35,6 +35,7 @@ void zswap_swapoff(int type); void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg); void zswap_lruvec_state_init(struct lruvec *lruvec); void zswap_folio_swapin(struct folio *folio); +bool is_zswap_enabled(void); #else struct zswap_lruvec_state {}; @@ -55,6 +56,12 @@ static inline void zswap_swapoff(int type) {} static inline void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg) {} static inline void zswap_lruvec_state_init(struct lruvec *lruvec) {} static inline void zswap_folio_swapin(struct folio *folio) {} + +static inline bool is_zswap_enabled(void) +{ + return false; +} + #endif #endif /* _LINUX_ZSWAP_H */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b08b9cd4a3a8..3ca691fb5b49 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5538,6 +5538,8 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) WRITE_ONCE(memcg->soft_limit, PAGE_COUNTER_MAX); #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP) memcg->zswap_max = PAGE_COUNTER_MAX; + WRITE_ONCE(memcg->zswap_writeback, + !parent || READ_ONCE(parent->zswap_writeback)); #endif page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX); if (parent) { @@ -8166,6 +8168,12 @@ void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size) rcu_read_unlock(); } +bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg) +{ + /* if zswap is disabled, do not block pages going to the swapping device */ + return !is_zswap_enabled() || !memcg || READ_ONCE(memcg->zswap_writeback); +} + static u64 zswap_current_read(struct cgroup_subsys_state *css, struct cftype *cft) { @@ -8198,6 +8206,31 @@ static ssize_t zswap_max_write(struct kernfs_open_file *of, return nbytes; } +static int zswap_writeback_show(struct seq_file *m, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_seq(m); + + seq_printf(m, "%d\n", READ_ONCE(memcg->zswap_writeback)); + return 0; +} + +static ssize_t zswap_writeback_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + int zswap_writeback; + ssize_t parse_ret = kstrtoint(strstrip(buf), 0, &zswap_writeback); + + if (parse_ret) + return parse_ret; + + if (zswap_writeback != 0 && zswap_writeback != 1) + return -EINVAL; + + WRITE_ONCE(memcg->zswap_writeback, zswap_writeback); + return nbytes; +} + static struct cftype zswap_files[] = { { .name = "zswap.current", @@ -8210,6 +8243,11 @@ static struct cftype zswap_files[] = { .seq_show = zswap_max_show, .write = zswap_max_write, }, + { + .name = "zswap.writeback", + .seq_show = zswap_writeback_show, + .write = zswap_writeback_write, + }, { } /* terminate */ }; #endif /* CONFIG_MEMCG_KMEM && CONFIG_ZSWAP */ diff --git a/mm/page_io.c b/mm/page_io.c index 09c6a4f316f3..ae2b49055e43 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -201,6 +201,11 @@ int swap_writepage(struct page *page, struct writeback_control *wbc) folio_end_writeback(folio); return 0; } + if (!mem_cgroup_zswap_writeback_enabled(folio_memcg(folio))) { + folio_mark_dirty(folio); + return AOP_WRITEPAGE_ACTIVATE; + } + __swap_writepage(folio, wbc); return 0; } diff --git a/mm/shmem.c b/mm/shmem.c index a4d388973021..928aa2304932 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1514,8 +1514,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) mutex_unlock(&shmem_swaplist_mutex); BUG_ON(folio_mapped(folio)); - swap_writepage(&folio->page, wbc); - return 0; + return swap_writepage(&folio->page, wbc); } mutex_unlock(&shmem_swaplist_mutex); diff --git a/mm/zswap.c b/mm/zswap.c index f760801a3ea8..ca25b676048e 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -153,6 +153,11 @@ static bool zswap_shrinker_enabled = IS_ENABLED( CONFIG_ZSWAP_SHRINKER_DEFAULT_ON); module_param_named(shrinker_enabled, zswap_shrinker_enabled, bool, 0644); +bool is_zswap_enabled(void) +{ + return zswap_enabled; +} + /********************************* * data structures **********************************/ @@ -596,7 +601,8 @@ static unsigned long zswap_shrinker_scan(struct shrinker *shrinker, struct zswap_pool *pool = shrinker->private_data; bool encountered_page_in_swapcache = false; - if (!zswap_shrinker_enabled) { + if (!zswap_shrinker_enabled || + !mem_cgroup_zswap_writeback_enabled(sc->memcg)) { sc->nr_scanned = 0; return SHRINK_STOP; } @@ -637,7 +643,7 @@ static unsigned long zswap_shrinker_count(struct shrinker *shrinker, struct lruvec *lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(sc->nid)); unsigned long nr_backing, nr_stored, nr_freeable, nr_protected; - if (!zswap_shrinker_enabled) + if (!zswap_shrinker_enabled || !mem_cgroup_zswap_writeback_enabled(memcg)) return 0; #ifdef CONFIG_MEMCG_KMEM @@ -923,6 +929,9 @@ static int shrink_memcg(struct mem_cgroup *memcg) struct zswap_pool *pool; int nid, shrunk = 0; + if (!mem_cgroup_zswap_writeback_enabled(memcg)) + return -EINVAL; + /* * Skip zombies because their LRUs are reparented and we would be * reclaiming from the parent instead of the dead memcg. -- cgit v1.2.3