From 4b3ef9daa4fc0bba742a79faecb17fdaaead083b Mon Sep 17 00:00:00 2001 From: "Huang, Ying" Date: Wed, 22 Feb 2017 15:45:26 -0800 Subject: mm/swap: split swap cache into 64MB trunks The patch is to improve the scalability of the swap out/in via using fine grained locks for the swap cache. In current kernel, one address space will be used for each swap device. And in the common configuration, the number of the swap device is very small (one is typical). This causes the heavy lock contention on the radix tree of the address space if multiple tasks swap out/in concurrently. But in fact, there is no dependency between pages in the swap cache. So that, we can split the one shared address space for each swap device into several address spaces to reduce the lock contention. In the patch, the shared address space is split into 64MB trunks. 64MB is chosen to balance the memory space usage and effect of lock contention reduction. The size of struct address_space on x86_64 architecture is 408B, so with the patch, 6528B more memory will be used for every 1GB swap space on x86_64 architecture. One address space is still shared for the swap entries in the same 64M trunks. To avoid lock contention for the first round of swap space allocation, the order of the swap clusters in the initial free clusters list is changed. The swap space distance between the consecutive swap clusters in the free cluster list is at least 64M. After the first round of allocation, the swap clusters are expected to be freed randomly, so the lock contention should be reduced effectively. Link: http://lkml.kernel.org/r/735bab895e64c930581ffb0a05b661e01da82bc5.1484082593.git.tim.c.chen@linux.intel.com Signed-off-by: "Huang, Ying" Signed-off-by: Tim Chen Cc: Aaron Lu Cc: Andi Kleen Cc: Andrea Arcangeli Cc: Christian Borntraeger Cc: Dave Hansen Cc: Hillf Danton Cc: Huang Ying Cc: Hugh Dickins Cc: Johannes Weiner Cc: Jonathan Corbet escreveu: Cc: Kirill A. Shutemov Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Cc: Shaohua Li Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swap_state.c | 68 +++++++++++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 56 insertions(+), 12 deletions(-) (limited to 'mm/swap_state.c') diff --git a/mm/swap_state.c b/mm/swap_state.c index 35d7e0ee1c77..3863acd6189c 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -17,6 +17,7 @@ #include #include #include +#include #include @@ -32,15 +33,8 @@ static const struct address_space_operations swap_aops = { #endif }; -struct address_space swapper_spaces[MAX_SWAPFILES] = { - [0 ... MAX_SWAPFILES - 1] = { - .page_tree = RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN), - .i_mmap_writable = ATOMIC_INIT(0), - .a_ops = &swap_aops, - /* swap cache doesn't use writeback related tags */ - .flags = 1 << AS_NO_WRITEBACK_TAGS, - } -}; +struct address_space *swapper_spaces[MAX_SWAPFILES]; +static unsigned int nr_swapper_spaces[MAX_SWAPFILES]; #define INC_CACHE_INFO(x) do { swap_cache_info.x++; } while (0) @@ -53,11 +47,26 @@ static struct { unsigned long total_swapcache_pages(void) { - int i; + unsigned int i, j, nr; unsigned long ret = 0; + struct address_space *spaces; - for (i = 0; i < MAX_SWAPFILES; i++) - ret += swapper_spaces[i].nrpages; + rcu_read_lock(); + for (i = 0; i < MAX_SWAPFILES; i++) { + /* + * The corresponding entries in nr_swapper_spaces and + * swapper_spaces will be reused only after at least + * one grace period. So it is impossible for them + * belongs to different usage. + */ + nr = nr_swapper_spaces[i]; + spaces = rcu_dereference(swapper_spaces[i]); + if (!nr || !spaces) + continue; + for (j = 0; j < nr; j++) + ret += spaces[j].nrpages; + } + rcu_read_unlock(); return ret; } @@ -505,3 +514,38 @@ struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, skip: return read_swap_cache_async(entry, gfp_mask, vma, addr); } + +int init_swap_address_space(unsigned int type, unsigned long nr_pages) +{ + struct address_space *spaces, *space; + unsigned int i, nr; + + nr = DIV_ROUND_UP(nr_pages, SWAP_ADDRESS_SPACE_PAGES); + spaces = vzalloc(sizeof(struct address_space) * nr); + if (!spaces) + return -ENOMEM; + for (i = 0; i < nr; i++) { + space = spaces + i; + INIT_RADIX_TREE(&space->page_tree, GFP_ATOMIC|__GFP_NOWARN); + atomic_set(&space->i_mmap_writable, 0); + space->a_ops = &swap_aops; + /* swap cache doesn't use writeback related tags */ + mapping_set_no_writeback_tags(space); + spin_lock_init(&space->tree_lock); + } + nr_swapper_spaces[type] = nr; + rcu_assign_pointer(swapper_spaces[type], spaces); + + return 0; +} + +void exit_swap_address_space(unsigned int type) +{ + struct address_space *spaces; + + spaces = swapper_spaces[type]; + nr_swapper_spaces[type] = 0; + rcu_assign_pointer(swapper_spaces[type], NULL); + synchronize_rcu(); + kvfree(spaces); +} -- cgit From e8c26ab60598558ec3a626e7925b06e7417d7710 Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Wed, 22 Feb 2017 15:45:29 -0800 Subject: mm/swap: skip readahead for unreferenced swap slots We can avoid needlessly allocating page for swap slots that are not used by anyone. No pages have to be read in for these slots. Link: http://lkml.kernel.org/r/0784b3f20b9bd3aa5552219624cb78dc4ae710c9.1484082593.git.tim.c.chen@linux.intel.com Signed-off-by: Tim Chen Signed-off-by: "Huang, Ying" Cc: Aaron Lu Cc: Andi Kleen Cc: Andrea Arcangeli Cc: Christian Borntraeger Cc: Dave Hansen Cc: Hillf Danton Cc: Huang Ying Cc: Hugh Dickins Cc: Johannes Weiner Cc: Jonathan Corbet escreveu: Cc: Kirill A. Shutemov Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Cc: Shaohua Li Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 6 ++++++ mm/swap_state.c | 4 ++++ mm/swapfile.c | 47 +++++++++++++++++++++++++++++++++++++++++------ 3 files changed, 51 insertions(+), 6 deletions(-) (limited to 'mm/swap_state.c') diff --git a/include/linux/swap.h b/include/linux/swap.h index 648a32b58e3e..3116382067cd 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -398,6 +398,7 @@ extern unsigned int count_swap_pages(int, int); extern sector_t map_swap_page(struct page *, struct block_device **); extern sector_t swapdev_block(int, pgoff_t); extern int page_swapcount(struct page *); +extern int __swp_swapcount(swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); extern struct swap_info_struct *page_swap_info(struct page *); extern bool reuse_swap_page(struct page *, int *); @@ -492,6 +493,11 @@ static inline int page_swapcount(struct page *page) return 0; } +static inline int __swp_swapcount(swp_entry_t entry) +{ + return 0; +} + static inline int swp_swapcount(swp_entry_t entry) { return 0; diff --git a/mm/swap_state.c b/mm/swap_state.c index 3863acd6189c..3d76d80c07d6 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -323,6 +323,10 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, if (found_page) break; + /* Just skip read ahead for unused swap slot */ + if (!__swp_swapcount(entry)) + return NULL; + /* * Get a new page to read into from swap. */ diff --git a/mm/swapfile.c b/mm/swapfile.c index 66e95eb73040..7e888de35c41 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -798,7 +798,7 @@ swp_entry_t get_swap_page_of_type(int type) return (swp_entry_t) {0}; } -static struct swap_info_struct *_swap_info_get(swp_entry_t entry) +static struct swap_info_struct *__swap_info_get(swp_entry_t entry) { struct swap_info_struct *p; unsigned long offset, type; @@ -814,13 +814,8 @@ static struct swap_info_struct *_swap_info_get(swp_entry_t entry) offset = swp_offset(entry); if (offset >= p->max) goto bad_offset; - if (!p->swap_map[offset]) - goto bad_free; return p; -bad_free: - pr_err("swap_info_get: %s%08lx\n", Unused_offset, entry.val); - goto out; bad_offset: pr_err("swap_info_get: %s%08lx\n", Bad_offset, entry.val); goto out; @@ -833,6 +828,24 @@ out: return NULL; } +static struct swap_info_struct *_swap_info_get(swp_entry_t entry) +{ + struct swap_info_struct *p; + + p = __swap_info_get(entry); + if (!p) + goto out; + if (!p->swap_map[swp_offset(entry)]) + goto bad_free; + return p; + +bad_free: + pr_err("swap_info_get: %s%08lx\n", Unused_offset, entry.val); + goto out; +out: + return NULL; +} + static struct swap_info_struct *swap_info_get(swp_entry_t entry) { struct swap_info_struct *p; @@ -986,6 +999,28 @@ int page_swapcount(struct page *page) return count; } +/* + * How many references to @entry are currently swapped out? + * This does not give an exact answer when swap count is continued, + * but does include the high COUNT_CONTINUED flag to allow for that. + */ +int __swp_swapcount(swp_entry_t entry) +{ + int count = 0; + pgoff_t offset; + struct swap_info_struct *si; + struct swap_cluster_info *ci; + + si = __swap_info_get(entry); + if (si) { + offset = swp_offset(entry); + ci = lock_cluster_or_swap_info(si, offset); + count = swap_count(si->swap_map[offset]); + unlock_cluster_or_swap_info(si, ci); + } + return count; +} + /* * How many references to @entry are currently swapped out? * This considers COUNT_CONTINUED so it returns exact answer. -- cgit From 67afa38e012e9581b9b42f2a41dfc56b1280794d Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Wed, 22 Feb 2017 15:45:39 -0800 Subject: mm/swap: add cache for swap slots allocation We add per cpu caches for swap slots that can be allocated and freed quickly without the need to touch the swap info lock. Two separate caches are maintained for swap slots allocated and swap slots returned. This is to allow the swap slots to be returned to the global pool in a batch so they will have a chance to be coaelesced with other slots in a cluster. We do not reuse the slots that are returned right away, as it may increase fragmentation of the slots. The swap allocation cache is protected by a mutex as we may sleep when searching for empty slots in cache. The swap free cache is protected by a spin lock as we cannot sleep in the free path. We refill the swap slots cache when we run out of slots, and we disable the swap slots cache and drain the slots if the global number of slots fall below a low watermark threshold. We re-enable the cache agian when the slots available are above a high watermark. [ying.huang@intel.com: use raw_cpu_ptr over this_cpu_ptr for swap slots access] [tim.c.chen@linux.intel.com: add comments on locks in swap_slots.h] Link: http://lkml.kernel.org/r/20170118180327.GA24225@linux.intel.com Link: http://lkml.kernel.org/r/35de301a4eaa8daa2977de6e987f2c154385eb66.1484082593.git.tim.c.chen@linux.intel.com Signed-off-by: Tim Chen Signed-off-by: "Huang, Ying" Reviewed-by: Michal Hocko Cc: Aaron Lu Cc: Andi Kleen Cc: Andrea Arcangeli Cc: Christian Borntraeger Cc: Dave Hansen Cc: Hillf Danton Cc: Huang Ying Cc: Hugh Dickins Cc: Johannes Weiner Cc: Jonathan Corbet escreveu: Cc: Kirill A. Shutemov Cc: Minchan Kim Cc: Rik van Riel Cc: Shaohua Li Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 4 + include/linux/swap_slots.h | 28 ++++ mm/Makefile | 2 +- mm/swap_slots.c | 342 +++++++++++++++++++++++++++++++++++++++++++++ mm/swap_state.c | 1 + mm/swapfile.c | 26 ++-- 6 files changed, 391 insertions(+), 12 deletions(-) create mode 100644 include/linux/swap_slots.h create mode 100644 mm/swap_slots.c (limited to 'mm/swap_state.c') diff --git a/include/linux/swap.h b/include/linux/swap.h index bcc0b18f96d2..45e91dd6716d 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -372,6 +372,7 @@ extern struct page *swapin_readahead(swp_entry_t, gfp_t, /* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages; extern long total_swap_pages; +extern bool has_usable_swap(void); /* Swap 50% full? Release swapcache more aggressively.. */ static inline bool vm_swap_full(void) @@ -410,6 +411,9 @@ struct backing_dev_info; extern int init_swap_address_space(unsigned int type, unsigned long nr_pages); extern void exit_swap_address_space(unsigned int type); +extern int get_swap_slots(int n, swp_entry_t *slots); +extern void swapcache_free_batch(swp_entry_t *entries, int n); + #else /* CONFIG_SWAP */ #define swap_address_space(entry) (NULL) diff --git a/include/linux/swap_slots.h b/include/linux/swap_slots.h new file mode 100644 index 000000000000..ba5623b27c60 --- /dev/null +++ b/include/linux/swap_slots.h @@ -0,0 +1,28 @@ +#ifndef _LINUX_SWAP_SLOTS_H +#define _LINUX_SWAP_SLOTS_H + +#include +#include +#include + +#define SWAP_SLOTS_CACHE_SIZE SWAP_BATCH +#define THRESHOLD_ACTIVATE_SWAP_SLOTS_CACHE (5*SWAP_SLOTS_CACHE_SIZE) +#define THRESHOLD_DEACTIVATE_SWAP_SLOTS_CACHE (2*SWAP_SLOTS_CACHE_SIZE) + +struct swap_slots_cache { + bool lock_initialized; + struct mutex alloc_lock; /* protects slots, nr, cur */ + swp_entry_t *slots; + int nr; + int cur; + spinlock_t free_lock; /* protects slots_ret, n_ret */ + swp_entry_t *slots_ret; + int n_ret; +}; + +void disable_swap_slots_cache_lock(void); +void reenable_swap_slots_cache_unlock(void); +int enable_swap_slots_cache(void); +int free_swap_slot(swp_entry_t entry); + +#endif /* _LINUX_SWAP_SLOTS_H */ diff --git a/mm/Makefile b/mm/Makefile index 295bd7a9f76b..433eaf9a876e 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -35,7 +35,7 @@ obj-y := filemap.o mempool.o oom_kill.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ util.o mmzone.o vmstat.o backing-dev.o \ mm_init.o mmu_context.o percpu.o slab_common.o \ - compaction.o vmacache.o \ + compaction.o vmacache.o swap_slots.o \ interval_tree.o list_lru.o workingset.o \ debug.o $(mmu-y) diff --git a/mm/swap_slots.c b/mm/swap_slots.c new file mode 100644 index 000000000000..ebf4f1cbac04 --- /dev/null +++ b/mm/swap_slots.c @@ -0,0 +1,342 @@ +/* + * Manage cache of swap slots to be used for and returned from + * swap. + * + * Copyright(c) 2016 Intel Corporation. + * + * Author: Tim Chen + * + * We allocate the swap slots from the global pool and put + * it into local per cpu caches. This has the advantage + * of no needing to acquire the swap_info lock every time + * we need a new slot. + * + * There is also opportunity to simply return the slot + * to local caches without needing to acquire swap_info + * lock. We do not reuse the returned slots directly but + * move them back to the global pool in a batch. This + * allows the slots to coaellesce and reduce fragmentation. + * + * The swap entry allocated is marked with SWAP_HAS_CACHE + * flag in map_count that prevents it from being allocated + * again from the global pool. + * + * The swap slots cache is protected by a mutex instead of + * a spin lock as when we search for slots with scan_swap_map, + * we can possibly sleep. + */ + +#include +#include +#include +#include +#include + +#ifdef CONFIG_SWAP + +static DEFINE_PER_CPU(struct swap_slots_cache, swp_slots); +static bool swap_slot_cache_active; +static bool swap_slot_cache_enabled; +static bool swap_slot_cache_initialized; +DEFINE_MUTEX(swap_slots_cache_mutex); +/* Serialize swap slots cache enable/disable operations */ +DEFINE_MUTEX(swap_slots_cache_enable_mutex); + +static void __drain_swap_slots_cache(unsigned int type); +static void deactivate_swap_slots_cache(void); +static void reactivate_swap_slots_cache(void); + +#define use_swap_slot_cache (swap_slot_cache_active && \ + swap_slot_cache_enabled && swap_slot_cache_initialized) +#define SLOTS_CACHE 0x1 +#define SLOTS_CACHE_RET 0x2 + +static void deactivate_swap_slots_cache(void) +{ + mutex_lock(&swap_slots_cache_mutex); + swap_slot_cache_active = false; + __drain_swap_slots_cache(SLOTS_CACHE|SLOTS_CACHE_RET); + mutex_unlock(&swap_slots_cache_mutex); +} + +static void reactivate_swap_slots_cache(void) +{ + mutex_lock(&swap_slots_cache_mutex); + swap_slot_cache_active = true; + mutex_unlock(&swap_slots_cache_mutex); +} + +/* Must not be called with cpu hot plug lock */ +void disable_swap_slots_cache_lock(void) +{ + mutex_lock(&swap_slots_cache_enable_mutex); + swap_slot_cache_enabled = false; + if (swap_slot_cache_initialized) { + /* serialize with cpu hotplug operations */ + get_online_cpus(); + __drain_swap_slots_cache(SLOTS_CACHE|SLOTS_CACHE_RET); + put_online_cpus(); + } +} + +static void __reenable_swap_slots_cache(void) +{ + swap_slot_cache_enabled = has_usable_swap(); +} + +void reenable_swap_slots_cache_unlock(void) +{ + __reenable_swap_slots_cache(); + mutex_unlock(&swap_slots_cache_enable_mutex); +} + +static bool check_cache_active(void) +{ + long pages; + + if (!swap_slot_cache_enabled || !swap_slot_cache_initialized) + return false; + + pages = get_nr_swap_pages(); + if (!swap_slot_cache_active) { + if (pages > num_online_cpus() * + THRESHOLD_ACTIVATE_SWAP_SLOTS_CACHE) + reactivate_swap_slots_cache(); + goto out; + } + + /* if global pool of slot caches too low, deactivate cache */ + if (pages < num_online_cpus() * THRESHOLD_DEACTIVATE_SWAP_SLOTS_CACHE) + deactivate_swap_slots_cache(); +out: + return swap_slot_cache_active; +} + +static int alloc_swap_slot_cache(unsigned int cpu) +{ + struct swap_slots_cache *cache; + swp_entry_t *slots, *slots_ret; + + /* + * Do allocation outside swap_slots_cache_mutex + * as vzalloc could trigger reclaim and get_swap_page, + * which can lock swap_slots_cache_mutex. + */ + slots = vzalloc(sizeof(swp_entry_t) * SWAP_SLOTS_CACHE_SIZE); + if (!slots) + return -ENOMEM; + + slots_ret = vzalloc(sizeof(swp_entry_t) * SWAP_SLOTS_CACHE_SIZE); + if (!slots_ret) { + vfree(slots); + return -ENOMEM; + } + + mutex_lock(&swap_slots_cache_mutex); + cache = &per_cpu(swp_slots, cpu); + if (cache->slots || cache->slots_ret) + /* cache already allocated */ + goto out; + if (!cache->lock_initialized) { + mutex_init(&cache->alloc_lock); + spin_lock_init(&cache->free_lock); + cache->lock_initialized = true; + } + cache->nr = 0; + cache->cur = 0; + cache->n_ret = 0; + cache->slots = slots; + slots = NULL; + cache->slots_ret = slots_ret; + slots_ret = NULL; +out: + mutex_unlock(&swap_slots_cache_mutex); + if (slots) + vfree(slots); + if (slots_ret) + vfree(slots_ret); + return 0; +} + +static void drain_slots_cache_cpu(unsigned int cpu, unsigned int type, + bool free_slots) +{ + struct swap_slots_cache *cache; + swp_entry_t *slots = NULL; + + cache = &per_cpu(swp_slots, cpu); + if ((type & SLOTS_CACHE) && cache->slots) { + mutex_lock(&cache->alloc_lock); + swapcache_free_entries(cache->slots + cache->cur, cache->nr); + cache->cur = 0; + cache->nr = 0; + if (free_slots && cache->slots) { + vfree(cache->slots); + cache->slots = NULL; + } + mutex_unlock(&cache->alloc_lock); + } + if ((type & SLOTS_CACHE_RET) && cache->slots_ret) { + spin_lock_irq(&cache->free_lock); + swapcache_free_entries(cache->slots_ret, cache->n_ret); + cache->n_ret = 0; + if (free_slots && cache->slots_ret) { + slots = cache->slots_ret; + cache->slots_ret = NULL; + } + spin_unlock_irq(&cache->free_lock); + if (slots) + vfree(slots); + } +} + +static void __drain_swap_slots_cache(unsigned int type) +{ + unsigned int cpu; + + /* + * This function is called during + * 1) swapoff, when we have to make sure no + * left over slots are in cache when we remove + * a swap device; + * 2) disabling of swap slot cache, when we run low + * on swap slots when allocating memory and need + * to return swap slots to global pool. + * + * We cannot acquire cpu hot plug lock here as + * this function can be invoked in the cpu + * hot plug path: + * cpu_up -> lock cpu_hotplug -> cpu hotplug state callback + * -> memory allocation -> direct reclaim -> get_swap_page + * -> drain_swap_slots_cache + * + * Hence the loop over current online cpu below could miss cpu that + * is being brought online but not yet marked as online. + * That is okay as we do not schedule and run anything on a + * cpu before it has been marked online. Hence, we will not + * fill any swap slots in slots cache of such cpu. + * There are no slots on such cpu that need to be drained. + */ + for_each_online_cpu(cpu) + drain_slots_cache_cpu(cpu, type, false); +} + +static int free_slot_cache(unsigned int cpu) +{ + mutex_lock(&swap_slots_cache_mutex); + drain_slots_cache_cpu(cpu, SLOTS_CACHE | SLOTS_CACHE_RET, true); + mutex_unlock(&swap_slots_cache_mutex); + return 0; +} + +int enable_swap_slots_cache(void) +{ + int ret = 0; + + mutex_lock(&swap_slots_cache_enable_mutex); + if (swap_slot_cache_initialized) { + __reenable_swap_slots_cache(); + goto out_unlock; + } + + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "swap_slots_cache", + alloc_swap_slot_cache, free_slot_cache); + if (ret < 0) + goto out_unlock; + swap_slot_cache_initialized = true; + __reenable_swap_slots_cache(); +out_unlock: + mutex_unlock(&swap_slots_cache_enable_mutex); + return 0; +} + +/* called with swap slot cache's alloc lock held */ +static int refill_swap_slots_cache(struct swap_slots_cache *cache) +{ + if (!use_swap_slot_cache || cache->nr) + return 0; + + cache->cur = 0; + if (swap_slot_cache_active) + cache->nr = get_swap_pages(SWAP_SLOTS_CACHE_SIZE, cache->slots); + + return cache->nr; +} + +int free_swap_slot(swp_entry_t entry) +{ + struct swap_slots_cache *cache; + + BUG_ON(!swap_slot_cache_initialized); + + cache = &get_cpu_var(swp_slots); + if (use_swap_slot_cache && cache->slots_ret) { + spin_lock_irq(&cache->free_lock); + /* Swap slots cache may be deactivated before acquiring lock */ + if (!use_swap_slot_cache) { + spin_unlock_irq(&cache->free_lock); + goto direct_free; + } + if (cache->n_ret >= SWAP_SLOTS_CACHE_SIZE) { + /* + * Return slots to global pool. + * The current swap_map value is SWAP_HAS_CACHE. + * Set it to 0 to indicate it is available for + * allocation in global pool + */ + swapcache_free_entries(cache->slots_ret, cache->n_ret); + cache->n_ret = 0; + } + cache->slots_ret[cache->n_ret++] = entry; + spin_unlock_irq(&cache->free_lock); + } else { +direct_free: + swapcache_free_entries(&entry, 1); + } + put_cpu_var(swp_slots); + + return 0; +} + +swp_entry_t get_swap_page(void) +{ + swp_entry_t entry, *pentry; + struct swap_slots_cache *cache; + + /* + * Preemption is allowed here, because we may sleep + * in refill_swap_slots_cache(). But it is safe, because + * accesses to the per-CPU data structure are protected by the + * mutex cache->alloc_lock. + * + * The alloc path here does not touch cache->slots_ret + * so cache->free_lock is not taken. + */ + cache = raw_cpu_ptr(&swp_slots); + + entry.val = 0; + if (check_cache_active()) { + mutex_lock(&cache->alloc_lock); + if (cache->slots) { +repeat: + if (cache->nr) { + pentry = &cache->slots[cache->cur++]; + entry = *pentry; + pentry->val = 0; + cache->nr--; + } else { + if (refill_swap_slots_cache(cache)) + goto repeat; + } + } + mutex_unlock(&cache->alloc_lock); + if (entry.val) + return entry; + } + + get_swap_pages(1, &entry); + + return entry; +} + +#endif /* CONFIG_SWAP */ diff --git a/mm/swap_state.c b/mm/swap_state.c index 3d76d80c07d6..e1f07cafecaa 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -18,6 +18,7 @@ #include #include #include +#include #include diff --git a/mm/swapfile.c b/mm/swapfile.c index 8b5bd34b1a00..30a90fd140b7 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -34,6 +34,7 @@ #include #include #include +#include #include #include @@ -854,14 +855,6 @@ noswap: return n_ret; } -swp_entry_t get_swap_page(void) -{ - swp_entry_t entry; - - get_swap_pages(1, &entry); - return entry; -} - /* The only caller of this function is now suspend routine */ swp_entry_t get_swap_page_of_type(int type) { @@ -1052,7 +1045,7 @@ void swap_free(swp_entry_t entry) p = _swap_info_get(entry); if (p) { if (!__swap_entry_free(p, entry, 1)) - swapcache_free_entries(&entry, 1); + free_swap_slot(entry); } } @@ -1066,7 +1059,7 @@ void swapcache_free(swp_entry_t entry) p = _swap_info_get(entry); if (p) { if (!__swap_entry_free(p, entry, SWAP_HAS_CACHE)) - swapcache_free_entries(&entry, 1); + free_swap_slot(entry); } } @@ -1288,7 +1281,7 @@ int free_swap_and_cache(swp_entry_t entry) page = NULL; } } else if (!count) - swapcache_free_entries(&entry, 1); + free_swap_slot(entry); } if (page) { /* @@ -2116,6 +2109,17 @@ static void reinsert_swap_info(struct swap_info_struct *p) spin_unlock(&swap_lock); } +bool has_usable_swap(void) +{ + bool ret = true; + + spin_lock(&swap_lock); + if (plist_head_empty(&swap_active_head)) + ret = false; + spin_unlock(&swap_lock); + return ret; +} + SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; -- cgit From ba81f83842549871cbd7226fc11530dc464500bb Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 22 Feb 2017 15:45:46 -0800 Subject: mm/swap: skip readahead only when swap slot cache is enabled Because during swap off, a swap entry may have swap_map[] == SWAP_HAS_CACHE (for example, just allocated). If we return NULL in __read_swap_cache_async(), the swap off will abort. So when swap slot cache is disabled, (for swap off), we will wait for page to be put into swap cache in such race condition. This should not be a problem for swap slot cache, because swap slot cache should be drained after clearing swap_slot_cache_enabled. [ying.huang@intel.com: fix memory leak in __read_swap_cache_async()] Link: http://lkml.kernel.org/r/874lzt6znd.fsf@yhuang-dev.intel.com Link: http://lkml.kernel.org/r/5e2c5f6abe8e6eb0797408897b1bba80938e9b9d.1484082593.git.tim.c.chen@linux.intel.com Signed-off-by: "Huang, Ying" Signed-off-by: Tim Chen Cc: Aaron Lu Cc: Andi Kleen Cc: Andrea Arcangeli Cc: Christian Borntraeger Cc: Dave Hansen Cc: Hillf Danton Cc: Huang Ying Cc: Hugh Dickins Cc: Johannes Weiner Cc: Jonathan Corbet escreveu: Cc: Kirill A. Shutemov Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Cc: Shaohua Li Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap_slots.h | 2 ++ mm/swap_slots.c | 2 +- mm/swap_state.c | 13 ++++++++++--- 3 files changed, 13 insertions(+), 4 deletions(-) (limited to 'mm/swap_state.c') diff --git a/include/linux/swap_slots.h b/include/linux/swap_slots.h index ba5623b27c60..6ef92d17633d 100644 --- a/include/linux/swap_slots.h +++ b/include/linux/swap_slots.h @@ -25,4 +25,6 @@ void reenable_swap_slots_cache_unlock(void); int enable_swap_slots_cache(void); int free_swap_slot(swp_entry_t entry); +extern bool swap_slot_cache_enabled; + #endif /* _LINUX_SWAP_SLOTS_H */ diff --git a/mm/swap_slots.c b/mm/swap_slots.c index ebf4f1cbac04..9b5bc86f96ad 100644 --- a/mm/swap_slots.c +++ b/mm/swap_slots.c @@ -36,7 +36,7 @@ static DEFINE_PER_CPU(struct swap_slots_cache, swp_slots); static bool swap_slot_cache_active; -static bool swap_slot_cache_enabled; +bool swap_slot_cache_enabled; static bool swap_slot_cache_initialized; DEFINE_MUTEX(swap_slots_cache_mutex); /* Serialize swap slots cache enable/disable operations */ diff --git a/mm/swap_state.c b/mm/swap_state.c index e1f07cafecaa..473b71e052a8 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -324,9 +324,16 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, if (found_page) break; - /* Just skip read ahead for unused swap slot */ - if (!__swp_swapcount(entry)) - return NULL; + /* + * Just skip read ahead for unused swap slot. + * During swap_off when swap_slot_cache is disabled, + * we have to handle the race between putting + * swap entry in swap cache and marking swap slot + * as SWAP_HAS_CACHE. That's done in later part of code or + * else swap_off will be aborted if we return NULL. + */ + if (!__swp_swapcount(entry) && swap_slot_cache_enabled) + break; /* * Get a new page to read into from swap. -- cgit