cregit-Linux how code gets into the kernel

Release 4.11 mm/swapfile.c

Directory: mm
/*
 *  linux/mm/swapfile.c
 *
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *  Swap reorganised 29.12.95, Stephen Tweedie
 */

#include <linux/mm.h>
#include <linux/sched/mm.h>
#include <linux/sched/task.h>
#include <linux/hugetlb.h>
#include <linux/mman.h>
#include <linux/slab.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/vmalloc.h>
#include <linux/pagemap.h>
#include <linux/namei.h>
#include <linux/shmem_fs.h>
#include <linux/blkdev.h>
#include <linux/random.h>
#include <linux/writeback.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/init.h>
#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/security.h>
#include <linux/backing-dev.h>
#include <linux/mutex.h>
#include <linux/capability.h>
#include <linux/syscalls.h>
#include <linux/memcontrol.h>
#include <linux/poll.h>
#include <linux/oom.h>
#include <linux/frontswap.h>
#include <linux/swapfile.h>
#include <linux/export.h>
#include <linux/swap_slots.h>

#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <linux/swapops.h>
#include <linux/swap_cgroup.h>

static bool swap_count_continued(struct swap_info_struct *, pgoff_t,
				 unsigned char);
static void free_swap_count_continuations(struct swap_info_struct *);
static sector_t map_swap_entry(swp_entry_t, struct block_device**);


DEFINE_SPINLOCK(swap_lock);

static unsigned int nr_swapfiles;

atomic_long_t nr_swap_pages;
/*
 * Some modules use swappable objects and may try to swap them out under
 * memory pressure (via the shrinker). Before doing so, they may wish to
 * check to see if any swap space is available.
 */

EXPORT_SYMBOL_GPL(nr_swap_pages);
/* protected with swap_lock. reading in vm_swap_full() doesn't need lock */

long total_swap_pages;

static int least_priority;


static const char Bad_file[] = "Bad swap file entry ";

static const char Unused_file[] = "Unused swap file entry ";

static const char Bad_offset[] = "Bad swap offset entry ";

static const char Unused_offset[] = "Unused swap offset entry ";

/*
 * all active swap_info_structs
 * protected with swap_lock, and ordered by priority.
 */

PLIST_HEAD(swap_active_head);

/*
 * all available (active, not full) swap_info_structs
 * protected with swap_avail_lock, ordered by priority.
 * This is used by get_swap_page() instead of swap_active_head
 * because swap_active_head includes all swap_info_structs,
 * but get_swap_page() doesn't need to look at full ones.
 * This uses its own lock instead of swap_lock because when a
 * swap_info_struct changes between not-full/full, it needs to
 * add/remove itself to/from this list, but the swap_info_struct->lock
 * is held and the locking order requires swap_lock to be taken
 * before any swap_info_struct->lock.
 */
static PLIST_HEAD(swap_avail_head);
static DEFINE_SPINLOCK(swap_avail_lock);


struct swap_info_struct *swap_info[MAX_SWAPFILES];

static DEFINE_MUTEX(swapon_mutex);

static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait);
/* Activity counter to indicate that a swapon or swapoff has occurred */

static atomic_t proc_poll_event = ATOMIC_INIT(0);


static inline unsigned char swap_count(unsigned char ent) { return ent & ~SWAP_HAS_CACHE; /* may include SWAP_HAS_CONT flag */ }

Contributors

PersonTokensPropCommitsCommitProp
Kamezawa Hiroyuki1473.68%125.00%
Hugh Dickins526.32%375.00%
Total19100.00%4100.00%

/* returns 1 if swap entry is freed */
static int __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset) { swp_entry_t entry = swp_entry(si->type, offset); struct page *page; int ret = 0; page = find_get_page(swap_address_space(entry), swp_offset(entry)); if (!page) return 0; /* * This function is called from scan_swap_map() and it's called * by vmscan.c at reclaiming pages. So, we hold a lock on a page, here. * We have to use trylock for avoiding deadlock. This is a special * case and you should use try_to_free_swap() with explicit lock_page() * in usual operations. */ if (trylock_page(page)) { ret = try_to_free_swap(page); unlock_page(page); } put_page(page); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
Kamezawa Hiroyuki8088.89%120.00%
Shaohua Li44.44%120.00%
Huang Ying33.33%120.00%
Hugh Dickins22.22%120.00%
Kirill A. Shutemov11.11%120.00%
Total90100.00%5100.00%

/* * swapon tell device that all the old swap contents can be discarded, * to allow the swap device to optimize its wear-levelling. */
static int discard_swap(struct swap_info_struct *si) { struct swap_extent *se; sector_t start_block; sector_t nr_blocks; int err = 0; /* Do not discard the swap header page! */ se = &si->first_swap_extent; start_block = (se->start_block + 1) << (PAGE_SHIFT - 9); nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9); if (nr_blocks) { err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL, 0); if (err) return err; cond_resched(); } list_for_each_entry(se, &si->first_swap_extent.list, list) { start_block = se->start_block << (PAGE_SHIFT - 9); nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL, 0); if (err) break; cond_resched(); } return err; /* That will often be -EOPNOTSUPP */ }

Contributors

PersonTokensPropCommitsCommitProp
Hugh Dickins16698.22%360.00%
Christoph Hellwig31.78%240.00%
Total169100.00%5100.00%

/* * swap allocation tell device that a cluster of swap can now be discarded, * to allow the swap device to optimize its wear-levelling. */
static void discard_swap_cluster(struct swap_info_struct *si, pgoff_t start_page, pgoff_t nr_pages) { struct swap_extent *se = si->curr_swap_extent; int found_extent = 0; while (nr_pages) { if (se->start_page <= start_page && start_page < se->start_page + se->nr_pages) { pgoff_t offset = start_page - se->start_page; sector_t start_block = se->start_block + offset; sector_t nr_blocks = se->nr_pages - offset; if (nr_blocks > nr_pages) nr_blocks = nr_pages; start_page += nr_blocks; nr_pages -= nr_blocks; if (!found_extent++) si->curr_swap_extent = se; start_block <<= PAGE_SHIFT - 9; nr_blocks <<= PAGE_SHIFT - 9; if (blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_NOIO, 0)) break; } se = list_next_entry(se, list); } }

Contributors

PersonTokensPropCommitsCommitProp
Hugh Dickins14997.39%240.00%
Christoph Hellwig21.31%240.00%
Geliang Tang21.31%120.00%
Total153100.00%5100.00%

#define SWAPFILE_CLUSTER 256 #define LATENCY_LIMIT 256
static inline void cluster_set_flag(struct swap_cluster_info *info, unsigned int flag) { info->flags = flag; }

Contributors

PersonTokensPropCommitsCommitProp
Shaohua Li22100.00%1100.00%
Total22100.00%1100.00%


static inline unsigned int cluster_count(struct swap_cluster_info *info) { return info->data; }

Contributors

PersonTokensPropCommitsCommitProp
Shaohua Li18100.00%1100.00%
Total18100.00%1100.00%


static inline void cluster_set_count(struct swap_cluster_info *info, unsigned int c) { info->data = c; }

Contributors

PersonTokensPropCommitsCommitProp
Shaohua Li22100.00%1100.00%
Total22100.00%1100.00%


static inline void cluster_set_count_flag(struct swap_cluster_info *info, unsigned int c, unsigned int f) { info->flags = f; info->data = c; }

Contributors

PersonTokensPropCommitsCommitProp
Shaohua Li32100.00%1100.00%
Total32100.00%1100.00%


static inline unsigned int cluster_next(struct swap_cluster_info *info) { return info->data; }

Contributors

PersonTokensPropCommitsCommitProp
Shaohua Li18100.00%1100.00%
Total18100.00%1100.00%


static inline void cluster_set_next(struct swap_cluster_info *info, unsigned int n) { info->data = n; }

Contributors

PersonTokensPropCommitsCommitProp
Shaohua Li22100.00%1100.00%
Total22100.00%1100.00%


static inline void cluster_set_next_flag(struct swap_cluster_info *info, unsigned int n, unsigned int f) { info->flags = f; info->data = n; }

Contributors

PersonTokensPropCommitsCommitProp
Shaohua Li32100.00%1100.00%
Total32100.00%1100.00%


static inline bool cluster_is_free(struct swap_cluster_info *info) { return info->flags & CLUSTER_FLAG_FREE; }

Contributors

PersonTokensPropCommitsCommitProp
Shaohua Li19100.00%1100.00%
Total19100.00%1100.00%


static inline bool cluster_is_null(struct swap_cluster_info *info) { return info->flags & CLUSTER_FLAG_NEXT_NULL; }

Contributors

PersonTokensPropCommitsCommitProp
Shaohua Li19100.00%1100.00%
Total19100.00%1100.00%


static inline void cluster_set_null(struct swap_cluster_info *info) { info->flags = CLUSTER_FLAG_NEXT_NULL; info->data = 0; }

Contributors

PersonTokensPropCommitsCommitProp
Shaohua Li24100.00%1100.00%
Total24100.00%1100.00%


static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si, unsigned long offset) { struct swap_cluster_info *ci; ci = si->cluster_info; if (ci) { ci += offset / SWAPFILE_CLUSTER; spin_lock(&ci->lock); } return ci; }

Contributors

PersonTokensPropCommitsCommitProp
Huang Ying52100.00%1100.00%
Total52100.00%1100.00%


static inline void unlock_cluster(struct swap_cluster_info *ci) { if (ci) spin_unlock(&ci->lock); }

Contributors

PersonTokensPropCommitsCommitProp
Huang Ying24100.00%1100.00%
Total24100.00%1100.00%


static inline struct swap_cluster_info *lock_cluster_or_swap_info( struct swap_info_struct *si, unsigned long offset) { struct swap_cluster_info *ci; ci = lock_cluster(si, offset); if (!ci) spin_lock(&si->lock); return ci; }

Contributors

PersonTokensPropCommitsCommitProp
Huang Ying48100.00%1100.00%
Total48100.00%1100.00%


static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si, struct swap_cluster_info *ci) { if (ci) unlock_cluster(ci); else spin_unlock(&si->lock); }

Contributors

PersonTokensPropCommitsCommitProp
Huang Ying35100.00%1100.00%
Total35100.00%1100.00%


static inline bool cluster_list_empty(struct swap_cluster_list *list) { return cluster_is_null(&list->head); }

Contributors

PersonTokensPropCommitsCommitProp
Huang Ying1780.95%150.00%
Shaohua Li419.05%150.00%
Total21100.00%2100.00%


static inline unsigned int cluster_list_first(struct swap_cluster_list *list) { return cluster_next(&list->head); }

Contributors

PersonTokensPropCommitsCommitProp
Huang Ying1672.73%150.00%
Shaohua Li627.27%150.00%
Total22100.00%2100.00%


static void cluster_list_init(struct swap_cluster_list *list) { cluster_set_null(&list->head); cluster_set_null(&list->tail); }

Contributors

PersonTokensPropCommitsCommitProp
Huang Ying2281.48%150.00%
Shaohua Li518.52%150.00%
Total27100.00%2100.00%


static void cluster_list_add_tail(struct swap_cluster_list *list, struct swap_cluster_info *ci, unsigned int idx) { if (cluster_list_empty(list)) { cluster_set_next_flag(&list->head, idx, 0); cluster_set_next_flag(&list->tail, idx, 0); } else { struct swap_cluster_info *ci_tail; unsigned int tail = cluster_next(&list->tail); /* * Nested cluster lock, but both cluster locks are * only acquired when we held swap_info_struct->lock */ ci_tail = ci + tail; spin_lock_nested(&ci_tail->lock, SINGLE_DEPTH_NESTING); cluster_set_next(ci_tail, idx); unlock_cluster(ci_tail); cluster_set_next_flag(&list->tail, idx, 0); } }

Contributors

PersonTokensPropCommitsCommitProp
Huang Ying6153.51%266.67%
Shaohua Li5346.49%133.33%
Total114100.00%3100.00%


static unsigned int cluster_list_del_first(struct swap_cluster_list *list, struct swap_cluster_info *ci) { unsigned int idx; idx = cluster_next(&list->head); if (cluster_next(&list->tail) == idx) { cluster_set_null(&list->head); cluster_set_null(&list->tail); } else cluster_set_next_flag(&list->head, cluster_next(&ci[idx]), 0); return idx; }

Contributors

PersonTokensPropCommitsCommitProp
Shaohua Li4250.00%150.00%
Huang Ying4250.00%150.00%
Total84100.00%2100.00%

/* Add a cluster to discard list and schedule it to do discard */
static void swap_cluster_schedule_discard(struct swap_info_struct *si, unsigned int idx) { /* * If scan_swap_map() can't find a free cluster, it will check * si->swap_map directly. To make sure the discarding cluster isn't * taken by scan_swap_map(), mark the swap entries bad (occupied). It * will be cleared after discard */ memset(si->swap_map + idx * SWAPFILE_CLUSTER, SWAP_MAP_BAD, SWAPFILE_CLUSTER); cluster_list_add_tail(&si->discard_clusters, si->cluster_info, idx); schedule_work(&si->discard_work); }

Contributors

PersonTokensPropCommitsCommitProp
Huang Ying2954.72%150.00%
Shaohua Li2445.28%150.00%
Total53100.00%2100.00%

/* * Doing discard actually. After a cluster discard is finished, the cluster * will be added to free cluster list. caller should hold si->lock. */
static void swap_do_scheduled_discard(struct swap_info_struct *si) { struct swap_cluster_info *info, *ci; unsigned int idx; info = si->cluster_info; while (!cluster_list_empty(&si->discard_clusters)) { idx = cluster_list_del_first(&si->discard_clusters, info); spin_unlock(&si->lock); discard_swap_cluster(si, idx * SWAPFILE_CLUSTER, SWAPFILE_CLUSTER); spin_lock(&si->lock); ci = lock_cluster(si, idx * SWAPFILE_CLUSTER); cluster_set_flag(ci, CLUSTER_FLAG_FREE); unlock_cluster(ci); cluster_list_add_tail(&si->free_clusters, info, idx); ci = lock_cluster(si, idx * SWAPFILE_CLUSTER); memset(si->swap_map + idx * SWAPFILE_CLUSTER, 0, SWAPFILE_CLUSTER); unlock_cluster(ci); } }

Contributors

PersonTokensPropCommitsCommitProp
Huang Ying8557.82%266.67%
Shaohua Li6242.18%133.33%
Total147100.00%3100.00%


static void swap_discard_work(struct work_struct *work) { struct swap_info_struct *si; si = container_of(work, struct swap_info_struct, discard_work); spin_lock(&si->lock); swap_do_scheduled_discard(si); spin_unlock(&si->lock); }

Contributors

PersonTokensPropCommitsCommitProp
Shaohua Li49100.00%1100.00%
Total49100.00%1100.00%

/* * The cluster corresponding to page_nr will be used. The cluster will be * removed from free cluster list and its usage counter will be increased. */
static void inc_cluster_info_page(struct swap_info_struct *p, struct swap_cluster_info *cluster_info, unsigned long page_nr) { unsigned long idx = page_nr / SWAPFILE_CLUSTER; if (!cluster_info) return; if (cluster_is_free(&cluster_info[idx])) { VM_BUG_ON(cluster_list_first(&p->free_clusters) != idx); cluster_list_del_first(&p->free_clusters, cluster_info); cluster_set_count_flag(&cluster_info[idx], 0, 0); } VM_BUG_ON(cluster_count(&cluster_info[idx]) >= SWAPFILE_CLUSTER); cluster_set_count(&cluster_info[idx], cluster_count(&cluster_info[idx]) + 1); }

Contributors

PersonTokensPropCommitsCommitProp
Shaohua Li11396.58%150.00%
Huang Ying43.42%150.00%
Total117100.00%2100.00%

/* * The cluster corresponding to page_nr decreases one usage. If the usage * counter becomes 0, which means no page in the cluster is in using, we can * optionally discard the cluster and add it to free cluster list. */
static void dec_cluster_info_page(struct swap_info_struct *p, struct swap_cluster_info *cluster_info, unsigned long page_nr) { unsigned long idx = page_nr / SWAPFILE_CLUSTER; if (!cluster_info) return; VM_BUG_ON(cluster_count(&cluster_info[idx]) == 0); cluster_set_count(&cluster_info[idx], cluster_count(&cluster_info[idx]) - 1); if (cluster_count(&cluster_info[idx]) == 0) { /* * If the swap is discardable, prepare discard the cluster * instead of free it immediately. The cluster will be freed * after discard. */ if ((p->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) == (SWP_WRITEOK | SWP_PAGE_DISCARD)) { swap_cluster_schedule_discard(p, idx); return; } cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE); cluster_list_add_tail(&p->free_clusters, cluster_info, idx); } }

Contributors

PersonTokensPropCommitsCommitProp
Shaohua Li13598.54%375.00%
Huang Ying21.46%125.00%
Total137100.00%4100.00%

/* * It's possible scan_swap_map() uses a free cluster in the middle of free * cluster list. Avoiding such abuse to avoid list corruption. */
static bool scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si, unsigned long offset) { struct percpu_cluster *percpu_cluster; bool conflict; offset /= SWAPFILE_CLUSTER; conflict = !cluster_list_empty(&si->free_clusters) && offset != cluster_list_first(&si->free_clusters) && cluster_is_free(&si->cluster_info[offset]); if (!conflict) return false; percpu_cluster = this_cpu_ptr(si->percpu_cluster); cluster_set_null(&percpu_cluster->index); return true; }

Contributors

PersonTokensPropCommitsCommitProp
Shaohua Li8395.40%266.67%
Huang Ying44.60%133.33%
Total87100.00%3100.00%

/* * Try to get a swap entry from current cpu's swap entry pool (a cluster). This * might involve allocating a new cluster for current CPU too. */
static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, unsigned long *offset, unsigned long *scan_base) { struct percpu_cluster *cluster; struct swap_cluster_info *ci; bool found_free; unsigned long tmp, max; new_cluster: cluster = this_cpu_ptr(si->percpu_cluster); if (cluster_is_null(&cluster->index)) { if (!cluster_list_empty(&si->free_clusters)) { cluster->index = si->free_clusters.head; cluster->next = cluster_next(&cluster->index) * SWAPFILE_CLUSTER; } else if (!cluster_list_empty(&si->discard_clusters)) { /* * we don't have free cluster but have some clusters in * discarding, do discard now and reclaim them */ swap_do_scheduled_discard(si); *scan_base = *offset = si->cluster_next; goto new_cluster; } else return false; } found_free = false; /* * Other CPUs can use our cluster if they can't find a free cluster, * check if there is still free entry in the cluster */ tmp = cluster->next; max = min_t(unsigned long, si->max, (cluster_next(&cluster->index) + 1) * SWAPFILE_CLUSTER); if (tmp >= max) { cluster_set_null(&cluster->index); goto new_cluster; } ci = lock_cluster(si, tmp); while (tmp < max) { if (!si->swap_map[tmp]) { found_free = true; break; } tmp++; } unlock_cluster(ci); if (!found_free) { cluster_set_null(&cluster->index); goto new_cluster; } cluster->next = tmp + 1; *offset = tmp; *scan_base = tmp; return found_free; }

Contributors

PersonTokensPropCommitsCommitProp
Shaohua Li16161.69%320.00%
Huang Ying5621.46%213.33%
Linus Torvalds (pre-git)186.90%320.00%
Hugh Dickins186.90%533.33%
Tim Chen72.68%16.67%
Kamezawa Hiroyuki10.38%16.67%
Total261100.00%15100.00%


static int scan_swap_map_slots(struct swap_info_struct *si, unsigned char usage, int nr, swp_entry_t slots[]) { struct swap_cluster_info *ci; unsigned long offset; unsigned long scan_base; unsigned long last_in_cluster = 0; int latency_ration = LATENCY_LIMIT; int n_ret = 0; if (nr > SWAP_BATCH) nr = SWAP_BATCH; /* * We try to cluster swap pages by allocating them sequentially * in swap. Once we've allocated SWAPFILE_CLUSTER pages this * way, however, we resort to first-free allocation, starting * a new cluster. This prevents us from scattering swap pages * all over the entire swap partition, so that we reduce * overall disk seek times between swap pages. -- sct * But we do now try to find an empty cluster. -Andrea * And we let swap pages go all over an SSD partition. Hugh */ si->flags += SWP_SCANNING; scan_base = offset = si->cluster_next; /* SSD algorithm */ if (si->cluster_info) { if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) goto checks; else goto scan; } if (unlikely(!si->cluster_nr--)) { if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) { si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; } spin_unlock(&si->lock); /* * If seek is expensive, start searching for new cluster from * start of partition, to minimize the span of allocated swap. * If seek is cheap, that is the SWP_SOLIDSTATE si->cluster_info * case, just handled by scan_swap_map_try_ssd_cluster() above. */ scan_base = offset = si->lowest_bit; last_in_cluster = offset + SWAPFILE_CLUSTER - 1; /* Locate the first empty (unaligned) cluster */ for (; last_in_cluster <= si->highest_bit; offset++) { if (si->swap_map[offset]) last_in_cluster = offset + SWAPFILE_CLUSTER; else if (offset == last_in_cluster) { spin_lock(&si->lock); offset -= SWAPFILE_CLUSTER - 1; si->cluster_next = offset; si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; } } offset = scan_base; spin_lock(&si->lock); si->cluster_nr = SWAPFILE_CLUSTER - 1; } checks: if (si->cluster_info) { while (scan_swap_map_ssd_cluster_conflict(si, offset)) { /* take a break if we already got some slots */ if (n_ret) goto done; if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) goto scan; } } if (!(si->flags & SWP_WRITEOK)) goto no_page; if (!si->highest_bit) goto no_page; if (offset > si->highest_bit) scan_base = offset = si->lowest_bit; ci = lock_cluster(si, offset); /* reuse swap entry of cache-only swap if not busy. */ if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { int swap_was_freed; unlock_cluster(ci); spin_unlock(&si->lock); swap_was_freed = __try_to_reclaim_swap(si, offset); spin_lock(&si->lock); /* entry was freed successfully, try to use this again */ if (swap_was_freed) goto checks; goto scan; /* check next one */ } if (si->swap_map[offset]) { unlock_cluster(ci); if (!n_ret) goto scan; else goto done; } if (offset == si->lowest_bit) si->lowest_bit++; if (offset == si->highest_bit) si->highest_bit--; si->inuse_pages++; if (si->inuse_pages == si->pages) { si->lowest_bit = si->max; si->highest_bit = 0; spin_lock(&swap_avail_lock); plist_del(&si->avail_list, &swap_avail_head); spin_unlock(&swap_avail_lock); } si->swap_map[offset] = usage; inc_cluster_info_page(si, si->cluster_info, offset); unlock_cluster(ci); si->cluster_next = offset + 1; slots[n_ret++] = swp_entry(si->type, offset); /* got enough slots or reach max slots? */ if ((n_ret == nr) || (offset >= si->highest_bit)) goto done; /* search for next available slot */ /* time to take a break? */ if (unlikely(--latency_ration < 0)) { if (n_ret) goto done; spin_unlock(&si->lock); cond_resched(); spin_lock(&si->lock); latency_ration = LATENCY_LIMIT; } /* try to get more slots in cluster */ if (si->cluster_info) { if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) goto checks; else goto done; } /* non-ssd case */ ++offset; /* non-ssd case, still more slots in cluster? */ if (si->cluster_nr && !si->swap_map[offset]) { --si->cluster_nr; goto checks; } done: si->flags -= SWP_SCANNING; return n_ret; scan: spin_unlock(&si->lock); while (++offset <= si->highest_bit) { if (!si->swap_map[offset]) { spin_lock(&si->lock); goto checks; } if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { spin_lock(&si->lock); goto checks; } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; } } offset = si->lowest_bit; while (offset < scan_base) { if (!si->swap_map[offset]) { spin_lock(&si->lock); goto checks; } if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { spin_lock(&si->lock); goto checks; } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; } offset++; } spin_lock(&si->lock); no_page: si->flags -= SWP_SCANNING; return n_ret; }

Contributors

PersonTokensPropCommitsCommitProp
Hugh Dickins27129.52%834.78%
Tim Chen19821.57%14.35%
Shaohua Li17619.17%417.39%
Kamezawa Hiroyuki9810.68%14.35%
Linus Torvalds (pre-git)889.59%313.04%
Huang Ying313.38%14.35%
Linus Torvalds272.94%14.35%
Dan Streetman232.51%14.35%
Jamie Liu30.33%14.35%
Andrew Morton20.22%14.35%
Chen Yucong10.11%14.35%
Total918100.00%23100.00%


static unsigned long scan_swap_map(struct swap_info_struct *si, unsigned char usage) { swp_entry_t entry; int n_ret; n_ret = scan_swap_map_slots(si, usage, 1, &entry); if (n_ret) return swp_offset(entry); else return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Tim Chen4998.00%150.00%
Linus Torvalds (pre-git)12.00%150.00%
Total50100.00%2100.00%


int get_swap_pages(int n_goal, swp_entry_t swp_entries[]) { struct swap_info_struct *si, *next; long avail_pgs; int n_ret = 0; avail_pgs = atomic_long_read(&nr_swap_pages); if (avail_pgs <= 0) goto noswap; if (n_goal > SWAP_BATCH) n_goal = SWAP_BATCH; if (n_goal > avail_pgs) n_goal = avail_pgs; atomic_long_sub(n_goal, &nr_swap_pages); spin_lock(&swap_avail_lock); start_over: plist_for_each_entry_safe(si, next, &swap_avail_head, avail_list) { /* requeue si to after same-priority siblings */ plist_requeue(&si->avail_list, &swap_avail_head); spin_unlock(&swap_avail_lock); spin_lock(&si->lock); if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) { spin_lock(&swap_avail_lock); if (plist_node_empty(&si->avail_list)) { spin_unlock(&si->lock); goto nextsi; } WARN(!si->highest_bit, "swap_info %d in list but !highest_bit\n", si->type); WARN(!(si->flags & SWP_WRITEOK), "swap_info %d in list but !SWP_WRITEOK\n", si->type); plist_del(&si->avail_list, &swap_avail_head); spin_unlock(&si->lock); goto nextsi; } n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, n_goal, swp_entries); spin_unlock(&si->lock); if (n_ret) goto check_out; pr_debug("scan_swap_map of si %d failed to find offset\n", si->type); spin_lock(&swap_avail_lock); nextsi: /* * if we got here, it's likely that si was almost full before, * and since scan_swap_map() can drop the si->lock, multiple * callers probably all tried to get a page from the same si * and it filled up before we could get one; or, the si filled * up between us dropping swap_avail_lock and taking si->lock. * Since we dropped the swap_avail_lock, the swap_avail_head * list may have been modified; so if next is still in the * swap_avail_head list then try it, otherwise start over * if we have not gotten any slots. */ if (plist_node_empty(&next->avail_list)) goto start_over; } spin_unlock(&swap_avail_lock); check_out: if (n_ret < n_goal) atomic_long_add((long) (n_goal-n_ret), &nr_swap_pages); noswap: return n_ret; }

Contributors

PersonTokensPropCommitsCommitProp
Dan Streetman13442.81%214.29%
Tim Chen7624.28%17.14%
Shaohua Li5216.61%17.14%
Hugh Dickins247.67%321.43%
Linus Torvalds (pre-git)227.03%428.57%
Rafael J. Wysocki30.96%17.14%
Linus Torvalds10.32%17.14%
Kamezawa Hiroyuki10.32%17.14%
Total313100.00%14100.00%

/* The only caller of this function is now suspend routine */
swp_entry_t get_swap_page_of_type(int type) { struct swap_info_struct *si; pgoff_t offset; si = swap_info[type]; spin_lock(&si->lock); if (si && (si->flags & SWP_WRITEOK)) { atomic_long_dec(&nr_swap_pages); /* This is called for allocating swap entry, not cache */ offset = scan_swap_map(si, 1); if (offset) { spin_unlock(&si->lock); return swp_entry(type, offset); } atomic_long_inc(&nr_swap_pages); } spin_unlock(&si->lock); return (swp_entry_t) {0}; }

Contributors

PersonTokensPropCommitsCommitProp
Hugh Dickins8379.05%150.00%
Shaohua Li2220.95%150.00%
Total105100.00%2100.00%


static struct swap_info_struct *__swap_info_get(swp_entry_t entry) { struct swap_info_struct *p; unsigned long offset, type; if (!entry.val) goto out; type = swp_type(entry); if (type >= nr_swapfiles) goto bad_nofile; p = swap_info[type]; if (!(p->flags & SWP_USED)) goto bad_device; offset = swp_offset(entry); if (offset >= p->max) goto bad_offset; return p; bad_offset: pr_err("swap_info_get: %s%08lx\n", Bad_offset, entry.val); goto out; bad_device: pr_err("swap_info_get: %s%08lx\n", Unused_file, entry.val); goto out; bad_nofile: pr_err("swap_info_get: %s%08lx\n", Bad_file, entry.val); out: return NULL; }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)7956.43%337.50%
Linus Torvalds4028.57%112.50%
Tim Chen139.29%112.50%
Andrew Morton53.57%225.00%
Huang Ying32.14%112.50%
Total140100.00%8100.00%


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; }

Contributors

PersonTokensPropCommitsCommitProp
Tim Chen5171.83%125.00%
Linus Torvalds1825.35%125.00%
Huang Ying11.41%125.00%
Andrew Morton11.41%125.00%
Total71100.00%4100.00%


static struct swap_info_struct *swap_info_get(swp_entry_t entry) { struct swap_info_struct *p; p = _swap_info_get(entry); if (p) spin_lock(&p->lock); return p; }

Contributors

PersonTokensPropCommitsCommitProp
Huang Ying38100.00%1100.00%
Total38100.00%1100.00%


static struct swap_info_struct *swap_info_get_cont(swp_entry_t entry, struct swap_info_struct *q) { struct swap_info_struct *p; p = _swap_info_get(entry); if (p != q) { if (q != NULL) spin_unlock(&q->lock); if (p != NULL) spin_lock(&p->lock); } return p; }

Contributors

PersonTokensPropCommitsCommitProp
Tim Chen67100.00%1100.00%
Total67100.00%1100.00%


static unsigned char __swap_entry_free(struct swap_info_struct *p, swp_entry_t entry, unsigned char usage) { struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); unsigned char count; unsigned char has_cache; ci = lock_cluster_or_swap_info(p, offset); count = p->swap_map[offset]; has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (usage == SWAP_HAS_CACHE) { VM_BUG_ON(!has_cache); has_cache = 0; } else if (count == SWAP_MAP_SHMEM) { /* * Or we could insist on shmem.c using a special * swap_shmem_free() and free_shmem_swap_and_cache()... */ count = 0; } else if ((count & ~COUNT_CONTINUED) <= SWAP_MAP_MAX) { if (count == COUNT_CONTINUED) { if (swap_count_continued(p, offset, count)) count = SWAP_MAP_MAX | COUNT_CONTINUED; else count = SWAP_MAP_MAX; } else count--; } usage = count | has_cache; p->swap_map[offset] = usage ? : SWAP_HAS_CACHE; unlock_cluster_or_swap_info(p, ci); return usage; }

Contributors

PersonTokensPropCommitsCommitProp
Hugh Dickins8950.00%428.57%
Kamezawa Hiroyuki2614.61%214.29%
Dan Streetman1910.67%17.14%
Huang Ying179.55%17.14%
Tim Chen116.18%17.14%
Linus Torvalds95.06%214.29%
Shaohua Li52.81%17.14%
Linus Torvalds (pre-git)21.12%214.29%
Total178100.00%14100.00%


static void swap_entry_free(struct swap_info_struct *p, swp_entry_t entry) { struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); unsigned char count; ci = lock_cluster(p, offset); count = p->swap_map[offset]; VM_BUG_ON(count != SWAP_HAS_CACHE); p->swap_map[offset] = 0; dec_cluster_info_page(p, p->cluster_info, offset); unlock_cluster(ci); mem_cgroup_uncharge_swap(entry); if (offset < p->lowest_bit) p->lowest_bit = offset; if (offset > p->highest_bit) { bool was_full = !p->highest_bit; p->highest_bit = offset; if (was_full && (p->flags & SWP_WRITEOK)) { spin_lock(&swap_avail_lock); WARN_ON(!plist_node_empty(&p->avail_list)); if (plist_node_empty(&p->avail_list)) plist_add(&p->avail_list, &swap_avail_head); spin_unlock(&swap_avail_lock); } } atomic_long_inc(&nr_swap_pages); p->inuse_pages--; frontswap_invalidate_page(p->type, offset); if (p->flags & SWP_BLKDEV) { struct gendisk *disk = p->bdev->bd_disk; if (disk->fops->swap_slot_free_notify) disk->fops->swap_slot_free_notify(p->bdev, offset); } }

Contributors

PersonTokensPropCommitsCommitProp
Dan Streetman6928.05%17.14%
Tim Chen5723.17%17.14%
Linus Torvalds (pre-git)3112.60%321.43%
Nitin Gupta2610.57%17.14%
Mel Gorman166.50%17.14%
Shaohua Li156.10%214.29%
Huang Ying145.69%17.14%
Dan Magenheimer93.66%17.14%
Andrew Morton52.03%17.14%
Vladimir Davydov31.22%17.14%
Kamezawa Hiroyuki10.41%17.14%
Total246100.00%14100.00%

/* * Caller has made sure that the swap device corresponding to entry * is still around or has not been recycled. */
void swap_free(swp_entry_t entry) { struct swap_info_struct *p; p = _swap_info_get(entry); if (p) { if (!__swap_entry_free(p, entry, 1)) free_swap_slot(entry); } }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds2353.49%222.22%
Tim Chen1125.58%222.22%
Linus Torvalds (pre-git)613.95%222.22%
Huang Ying12.33%111.11%
Kamezawa Hiroyuki12.33%111.11%
Hugh Dickins12.33%111.11%
Total43100.00%9100.00%

/* * Called after dropping swapcache to decrease refcnt to swap entries. */
void swapcache_free(swp_entry_t entry) { struct swap_info_struct *p; p = _swap_info_get(entry); if (p) { if (!__swap_entry_free(p, entry, SWAP_HAS_CACHE)) free_swap_slot(entry); } }

Contributors

PersonTokensPropCommitsCommitProp
Kamezawa Hiroyuki2762.79%233.33%
Tim Chen1432.56%233.33%
Huang Ying12.33%116.67%
Hugh Dickins12.33%116.67%
Total43100.00%6100.00%


void swapcache_free_entries(swp_entry_t *entries, int n) { struct swap_info_struct *p, *prev; int i; if (n <= 0) return; prev = NULL; p = NULL; for (i = 0; i < n; ++i) { p = swap_info_get_cont(entries[i], prev); if (p) swap_entry_free(p, entries[i]); else break; prev = p; } if (p) spin_unlock(&p->lock); }

Contributors

PersonTokensPropCommitsCommitProp
Tim Chen9496.91%133.33%
Kamezawa Hiroyuki33.09%266.67%
Total97100.00%3100.00%

/* * How many references to page 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 page_swapcount(struct page *page) { int count = 0; struct swap_info_struct *p; struct swap_cluster_info *ci; swp_entry_t entry; unsigned long offset; entry.val = page_private(page); p = _swap_info_get(entry); if (p) { offset = swp_offset(entry); ci = lock_cluster_or_swap_info(p, offset); count = swap_count(p->swap_map[offset]); unlock_cluster_or_swap_info(p, ci); } return count; }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds5054.35%116.67%
Huang Ying3032.61%116.67%
Hugh Dickins88.70%233.33%
Kamezawa Hiroyuki33.26%116.67%
Shaohua Li11.09%116.67%
Total92100.00%6100.00%

/* * 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; }

Contributors

PersonTokensPropCommitsCommitProp
Tim Chen77100.00%1100.00%
Total77100.00%1100.00%

/* * How many references to @entry are currently swapped out? * This considers COUNT_CONTINUED so it returns exact answer. */
int swp_swapcount(swp_entry_t entry) { int count, tmp_count, n; struct swap_info_struct *p; struct swap_cluster_info *ci; struct page *page; pgoff_t offset; unsigned char *map; p = _swap_info_get(entry); if (!p) return 0; offset = swp_offset(entry); ci = lock_cluster_or_swap_info(p, offset); count = swap_count(p->swap_map[offset]); if (!(count & COUNT_CONTINUED)) goto out; count &= ~COUNT_CONTINUED; n = SWAP_MAP_MAX + 1; page = vmalloc_to_page(p->swap_map + offset); offset &= ~PAGE_MASK; VM_BUG_ON(page_private(page) != SWP_CONTINUED); do { page = list_next_entry(page, lru); map = kmap_atomic(page); tmp_count = map[offset]; kunmap_atomic(map); count += (tmp_count & ~COUNT_CONTINUED) * n; n *= (SWAP_CONT_MAX + 1); } while (tmp_count & COUNT_CONTINUED); out: unlock_cluster_or_swap_info(p, ci); return count; }

Contributors

PersonTokensPropCommitsCommitProp
MinChan Kim17286.43%133.33%
Huang Ying2613.07%133.33%
Geliang Tang10.50%133.33%
Total199100.00%3100.00%

/* * We can write to an anon page without COW if there are no other references * to it. And as a side-effect, free up its swap: because the old content * on disk will never be read, and seeking back there to write new content * later would only waste time away from clustering. * * NOTE: total_mapcount should not be relied upon by the caller if * reuse_swap_page() returns false, but it may be always overwritten * (see the other implementation for CONFIG_SWAP=n). */
bool reuse_swap_page(struct page *page, int *total_mapcount) { int count; VM_BUG_ON_PAGE(!PageLocked(page), page); if (unlikely(PageKsm(page))) return false; count = page_trans_huge_mapcount(page, total_mapcount); if (count <= 1 && PageSwapCache(page)) { count += page_swapcount(page); if (count != 1) goto out; if (!PageWriteback(page)) { delete_from_swap_cache(page); SetPageDirty(page); } else { swp_entry_t entry; struct swap_info_struct *p; entry.val = page_private(page); p = swap_info_get(entry); if (p->flags & SWP_STABLE_WRITES) { spin_unlock(&p->lock); return false; } spin_unlock(&p->lock); } } out: return count <= 1; }

Contributors

PersonTokensPropCommitsCommitProp
MinChan Kim6540.12%110.00%
Hugh Dickins5232.10%330.00%
Linus Torvalds3018.52%220.00%
Andrea Arcangeli95.56%110.00%
Sasha Levin31.85%110.00%
Andrew Morton21.23%110.00%
Kirill A. Shutemov10.62%110.00%
Total162100.00%10100.00%

/* * If swap is getting full, or if there are no more mappings of this page, * then try_to_free_swap is called to free its swap space. */
int try_to_free_swap(struct page *page) { VM_BUG_ON_PAGE(!PageLocked(page), page); if (!PageSwapCache(page)) return 0; if (PageWriteback(page)) return 0; if (page_swapcount(page)) return 0; /* * Once hibernation has begun to create its image of memory, * there's a danger that one of the calls to try_to_free_swap() * - most probably a call from __try_to_reclaim_swap() while * hibernation is allocating its own swap pages for the image, * but conceivably even a call from memory reclaim - will free * the swap from a page which has already been recorded in the * image as a clean swapcache page, and then reuse its swap for * another page of the image. On waking from hibernation, the * original page might be freed under memory pressure, then * later read back in from swap, now with the wrong data. * * Hibernation suspends storage while it is writing the image * to disk so check that here. */ if (pm_suspended_storage()) return 0; delete_from_swap_cache(page); SetPageDirty(page); return 1; }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds4155.41%218.18%
Andrew Morton1216.22%218.18%
Hugh Dickins1216.22%327.27%
Rik Van Riel34.05%19.09%
Sasha Levin34.05%19.09%
Mel Gorman22.70%19.09%
Seth Jennings11.35%19.09%
Total74100.00%11100.00%

/* * Free the swap entry like above, but also try to * free the page cache entry if it is the last user. */
int free_swap_and_cache(swp_entry_t entry) { struct swap_info_struct *p; struct page *page = NULL; unsigned char count; if (non_swap_entry(entry)) return 1; p = _swap_info_get(entry); if (p) { count = __swap_entry_free(p, entry, 1); if (count == SWAP_HAS_CACHE) { page = find_get_page(swap_address_space(entry), swp_offset(entry)); if (page && !trylock_page(page)) { put_page(page); page = NULL; } } else if (!count) free_swap_slot(entry); } if (page) { /* * Not mapped elsewhere, or swap space full? Free it! * Also recheck PageSwapCache now page is locked (above). */ if (PageSwapCache(page) && !PageWriteback(page) && (!page_mapped(page) || mem_cgroup_swap_full(page))) { delete_from_swap_cache(page); SetPageDirty(page); } unlock_page(page); put_page(page); } return p != NULL; }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds6738.73%313.64%
Nicholas Piggin2816.18%29.09%
Tim Chen2011.56%29.09%
Hugh Dickins169.25%313.64%
Andrew Morton116.36%29.09%
Linus Torvalds (pre-git)95.20%313.64%
Christoph Lameter63.47%14.55%
Shaohua Li42.31%14.55%
Vladimir Davydov42.31%14.55%
Huang Ying31.73%14.55%
Kirill A. Shutemov21.16%14.55%
Kamezawa Hiroyuki21.16%14.55%
Andi Kleen10.58%14.55%
Total173100.00%22100.00%

#ifdef CONFIG_HIBERNATION /* * Find the swap type that corresponds to given device (if any). * * @offset - number of the PAGE_SIZE-sized block of the device, starting * from 0, in which the swap header is expected to be located. * * This is needed for the suspend to disk (aka swsusp). */
int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p) { struct block_device *bdev = NULL; int type; if (device) bdev = bdget(device); spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; if (!bdev) { if (bdev_p) *bdev_p = bdgrab(sis->bdev); spin_unlock(&swap_lock); return type; } if (bdev == sis->bdev) { struct swap_extent *se = &sis->first_swap_extent; if (se->start_block == offset) { if (bdev_p) *bdev_p = bdgrab(sis->bdev); spin_unlock(&swap_lock); bdput(bdev); return type; } } } spin_unlock(&swap_lock); if (bdev) bdput(bdev); return -ENODEV; }

Contributors

PersonTokensPropCommitsCommitProp
Rafael J. Wysocki16989.89%450.00%
Hugh Dickins136.91%225.00%
Alan Jenkins63.19%225.00%
Total188100.00%8100.00%

/* * Get the (PAGE_SIZE) block corresponding to given offset on the swapdev * corresponding to given index in swap_info (swap type). */
sector_t swapdev_block(int type, pgoff_t offset) { struct block_device *bdev; if ((unsigned int)type >= nr_swapfiles) return 0; if (!(swap_info[type]->flags & SWP_WRITEOK)) return 0; return map_swap_entry(swp_entry(type, offset), &bdev); }

Contributors

PersonTokensPropCommitsCommitProp
Hugh Dickins5998.33%150.00%
Lee Schermerhorn11.67%150.00%
Total60100.00%2100.00%

/* * Return either the total number of swap pages of given type, or the number * of free pages of that type (depending on @free) * * This is needed for software suspend */
unsigned int count_swap_pages(int type, int free) { unsigned int n = 0; spin_lock(&swap_lock); if ((unsigned int)type < nr_swapfiles) { struct swap_info_struct *sis = swap_info[type]; spin_lock(&sis->lock); if (sis->flags & SWP_WRITEOK) { n = sis->pages; if (free) n -= sis->inuse_pages; } spin_unlock(&sis->lock); } spin_unlock(&swap_lock); return n; }

Contributors

PersonTokensPropCommitsCommitProp
Rafael J. Wysocki5758.76%133.33%
Hugh Dickins2424.74%133.33%
Shaohua Li1616.49%133.33%
Total97100.00%3100.00%

#endif /* CONFIG_HIBERNATION */
static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte) { return pte_same(pte_swp_clear_soft_dirty(pte), swp_pte); }

Contributors

PersonTokensPropCommitsCommitProp
Cyrill V. Gorcunov2291.67%150.00%
Hugh Dickins28.33%150.00%
Total24100.00%2100.00%

/* * No need to decide whether this PTE shares the swap entry with others, * just let do_wp_page work it out if a write is requested later - to * force COW, vm_page_prot omits write permission from any private vma. */
static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, swp_entry_t entry, struct page *page) { struct page *swapcache; struct mem_cgroup *memcg; spinlock_t *ptl; pte_t *pte; int ret = 1; swapcache = page; page = ksm_might_need_to_copy(page, vma, addr); if (unlikely(!page)) return -ENOMEM; if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg, false)) { ret = -ENOMEM; goto out_nolock; } pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) { mem_cgroup_cancel_charge(page, memcg, false); ret = 0; goto out; } dec_mm_counter(vma->vm_mm, MM_SWAPENTS); inc_mm_counter(vma->vm_mm, MM_ANONPAGES); get_page(page); set_pte_at(vma->vm_mm, addr, pte, pte_mkold(mk_pte(page, vma->vm_page_prot))); if (page == swapcache) { page_add_anon_rmap(page, vma, addr, false); mem_cgroup_commit_charge(page, memcg, true, false); } else { /* ksm created a completely new copy */ page_add_new_anon_rmap(page, vma, addr, false); mem_cgroup_commit_charge(page, memcg, false, false); lru_cache_add_active_or_unevictable(page, vma); } swap_free(entry); /* * Move the page to the active list so it is not * immediately swapped out again after swapon. */ activate_page(page); out: pte_unmap_unlock(pte, ptl); out_nolock: if (page != swapcache) { unlock_page(page); put_page(page); } return ret; }

Contributors

PersonTokensPropCommitsCommitProp
Hugh Dickins15349.68%414.81%
Linus Torvalds (pre-git)4213.64%518.52%
Johannes Weiner3310.71%27.41%
Kamezawa Hiroyuki299.42%518.52%
Balbir Singh144.55%27.41%
Kirill A. Shutemov123.90%27.41%
Andrew Morton123.90%414.81%
David S. Miller61.95%13.70%
Christoph Lameter41.30%13.70%
Linus Torvalds30.97%13.70%
Total308100.00%27100.00%


static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, swp_entry_t entry, struct page *page) { pte_t swp_pte = swp_entry_to_pte(entry); pte_t *pte; int ret = 0; /* * We don't actually need pte lock while scanning for swp_pte: since * we hold page lock and mmap_sem, swp_pte cannot be inserted into the * page table while we're scanning; though it could get zapped, and on * some architectures (e.g. x86_32 with PAE) we might catch a glimpse * of unmatched parts which look like swp_pte, so unuse_pte must * recheck under pte lock. Scanning without pte lock lets it be * preemptable whenever CONFIG_PREEMPT but not CONFIG_HIGHPTE. */ pte = pte_offset_map(pmd, addr); do { /* * swapoff spends a _lot_ of time in this loop! * Test inline before going to call unuse_pte. */ if (unlikely(pte_same_as_swp(*pte, swp_pte))) { pte_unmap(pte); ret = unuse_pte(vma, pmd, addr, entry, page); if (ret) goto out; pte = pte_offset_map(pmd, addr); } } while (pte++, addr += PAGE_SIZE, addr != end); pte_unmap(pte - 1); out: return ret; }

Contributors

PersonTokensPropCommitsCommitProp
Hugh Dickins5338.13%535.71%
Linus Torvalds (pre-git)4935.25%428.57%
Andrew Morton2618.71%214.29%
Ingo Molnar64.32%17.14%
Balbir Singh42.88%17.14%
Seth Jennings10.72%17.14%
Total139100.00%14100.00%


static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, swp_entry_t entry, struct page *page) { pmd_t *pmd; unsigned long next; int ret; pmd = pmd_offset(pud, addr); do { cond_resched(); next = pmd_addr_end(addr, end); if (pmd_none_or_trans_huge_or_clear_bad(pmd)) continue; ret = unuse_pte_range(vma, pmd, addr, next, entry, page); if (ret) return ret; } while (pmd++, addr = next, addr != end); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)5950.86%430.77%
Hugh Dickins3631.03%538.46%
Balbir Singh108.62%17.69%
Andrew Morton65.17%17.69%
Andi Kleen43.45%17.69%
Andrea Arcangeli10.86%17.69%
Total116100.00%13100.00%


static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, swp_entry_t entry, struct page *page) { pud_t *pud; unsigned long next; int ret; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; ret = unuse_pmd_range(vma, pud, addr, next, entry, page); if (ret) return ret; } while (pud++, addr = next, addr != end); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Andi Kleen6658.41%114.29%
Hugh Dickins3430.09%457.14%
Balbir Singh108.85%114.29%
Kirill A. Shutemov32.65%114.29%
Total113100.00%7100.00%


static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, swp_entry_t entry, struct page *page) { p4d_t *p4d; unsigned long next; int ret; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; ret = unuse_pud_range(vma, p4d, addr, next, entry, page); if (ret) return ret; } while (p4d++, addr = next, addr != end); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Kirill A. Shutemov113100.00%1100.00%
Total113100.00%1100.00%


static int unuse_vma(struct vm_area_struct *vma, swp_entry_t entry, struct page *page) { pgd_t *pgd; unsigned long addr, end, next; int ret; if (page_anon_vma(page)) { addr = page_address_in_vma(page, vma); if (addr == -EFAULT) return 0; else end = addr + PAGE_SIZE; } else { addr = vma->vm_start; end = vma->vm_end; } pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; ret = unuse_p4d_range(vma, pgd, addr, next, entry, page); if (ret) return ret; } while (pgd++, addr = next, addr != end); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Hugh Dickins9359.62%535.71%
Linus Torvalds (pre-git)3623.08%428.57%
Balbir Singh106.41%17.14%
Andi Kleen95.77%17.14%
Andrew Morton74.49%214.29%
Kirill A. Shutemov10.64%17.14%
Total156100.00%14100.00%


static int unuse_mm(struct mm_struct *mm, swp_entry_t entry, struct page *page) { struct vm_area_struct *vma; int ret = 0; if (!down_read_trylock(&mm->mmap_sem)) { /* * Activate page so shrink_inactive_list is unlikely to unmap * its ptes while lock is dropped, so swapoff can make progress. */ activate_page(page); unlock_page(page); down_read(&mm->mmap_sem); lock_page(page); } for (vma = mm->mmap; vma; vma = vma->vm_next) { if (vma->anon_vma && (ret = unuse_vma(vma, entry, page))) break; cond_resched(); } up_read(&mm->mmap_sem); return (ret < 0)? ret: 0; }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)4838.10%533.33%
Hugh Dickins3527.78%533.33%
Andrew Morton2519.84%320.00%
Balbir Singh1713.49%16.67%
Fernando Luis Vázquez Cao10.79%16.67%
Total126100.00%15100.00%

/* * Scan swap_map (or frontswap_map if frontswap parameter is true) * from current position to next entry still in use. * Recycle to start on reaching the end, returning 0 when empty. */
static unsigned int find_next_to_unuse(struct swap_info_struct *si, unsigned int prev, bool frontswap) { unsigned int max = si->max; unsigned int i = prev; unsigned char count; /* * No need for swap_lock here: we're just looking * for whether an entry is in use, not modifying it; false * hits are okay, and sys_swapoff() has already prevented new * allocations from this area (while holding swap_lock). */ for (;;) { if (++i >= max) { if (!prev) { i = 0; break; } /* * No entries in use at top of swap_map, * loop back to start and recheck there. */ max = prev + 1; prev = 0; i = 1; } count = READ_ONCE(si->swap_map[i]); if (count && swap_count(count) != SWAP_MAP_BAD) if (!frontswap || frontswap_test(si, i)) break; if ((i % LATENCY_LIMIT) == 0) cond_resched(); } return i; }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds8966.92%216.67%
Hugh Dickins3224.06%433.33%
Kamezawa Hiroyuki32.26%18.33%
Linus Torvalds (pre-git)32.26%216.67%
Dan Magenheimer32.26%18.33%
Shaohua Li21.50%18.33%
Jason Low10.75%18.33%
Total133100.00%12100.00%

/* * We completely avoid races by reading each swap page in advance, * and then search for the process using it. All the necessary * page table adjustments can then be made atomically. * * if the boolean frontswap is true, only unuse pages_to_unuse pages; * pages_to_unuse==0 means all pages; ignored if frontswap is false */
int try_to_unuse(unsigned int type, bool frontswap, unsigned long pages_to_unuse) { struct swap_info_struct *si = swap_info[type]; struct mm_struct *start_mm; volatile unsigned char *swap_map; /* swap_map is accessed without * locking. Mark it as volatile * to prevent compiler doing * something odd. */ unsigned char swcount; struct page *page; swp_entry_t entry; unsigned int i = 0; int retval = 0; /* * When searching mms for an entry, a good strategy is to * start at the first mm we freed the previous entry from * (though actually we don't notice whether we or coincidence * freed the entry). Initialize this start_mm with a hold. * * A simpler strategy would be to start at the last mm we * freed the previous entry from; but that would take less * advantage of mmlist ordering, which clusters forked mms * together, child after parent. If we race with dup_mmap(), we * prefer to resolve parent before child, lest we miss entries * duplicated after we scanned child: using last mm would invert * that. */ start_mm = &init_mm; mmget(&init_mm); /* * Keep on scanning until all entries have gone. Usually, * one pass through swap_map is enough, but not necessarily: * there are races when an instance of an entry might be missed. */ while ((i = find_next_to_unuse(si, i, frontswap)) != 0) { if (signal_pending(current)) { retval = -EINTR; break; } /* * Get a page for the entry, using the existing swap * cache page if there is one. Otherwise, get a clean * page and read the swap into it. */ swap_map = &si->swap_map[i]; entry = swp_entry(type, i); page = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE, NULL, 0); if (!page) { /* * Either swap_duplicate() failed because entry * has been freed independently, and will not be * reused since sys_swapoff() already disabled * allocation from here, or alloc_page() failed. */ swcount = *swap_map; /* * We don't hold lock here, so the swap entry could be * SWAP_MAP_BAD (when the cluster is discarding). * Instead of fail out, We can just skip the swap * entry because swapoff will wait for discarding * finish anyway. */ if (!swcount || swcount == SWAP_MAP_BAD) continue; retval = -ENOMEM; break; } /* * Don't hold on to start_mm if it looks like exiting. */ if (atomic_read(&start_mm->mm_users) == 1) { mmput(start_mm); start_mm = &init_mm; mmget(&init_mm); } /* * Wait for and lock page. When do_swap_page races with * try_to_unuse, do_swap_page can handle the fault much * faster than try_to_unuse can locate the entry. This * apparently redundant "wait_on_page_locked" lets try_to_unuse * defer to do_swap_page in such a case - in some tests, * do_swap_page and try_to_unuse repeatedly compete. */ wait_on_page_locked(page); wait_on_page_writeback(page); lock_page(page); wait_on_page_writeback(page); /* * Remove all references to entry. */ swcount = *swap_map; if (swap_count(swcount) == SWAP_MAP_SHMEM) { retval = shmem_unuse(entry, page); /* page has already been unlocked and released */ if (retval < 0) break; continue; } if (swap_count(swcount) && start_mm != &init_mm) retval = unuse_mm(start_mm, entry, page); if (swap_count(*swap_map)) { int set_start_mm = (*swap_map >= swcount); struct list_head *p = &start_mm->mmlist; struct mm_struct *new_start_mm = start_mm; struct mm_struct *prev_mm = start_mm; struct mm_struct *mm; mmget(new_start_mm); mmget(prev_mm); spin_lock(&mmlist_lock); while (swap_count(*swap_map) && !retval && (p = p->next) != &start_mm->mmlist) { mm = list_entry(p, struct mm_struct, mmlist); if (!mmget_not_zero(mm)) continue; spin_unlock(&mmlist_lock); mmput(prev_mm); prev_mm = mm; cond_resched(); swcount = *swap_map; if (!swap_count(swcount)) /* any usage ? */ ; else if (mm == &init_mm) set_start_mm = 1; else retval = unuse_mm(mm, entry, page); if (set_start_mm && *swap_map < swcount) { mmput(new_start_mm); mmget(mm); new_start_mm = mm; set_start_mm = 0; } spin_lock(&mmlist_lock); } spin_unlock(&mmlist_lock); mmput(prev_mm); mmput(start_mm); start_mm = new_start_mm; } if (retval) { unlock_page(page); put_page(page); break; } /* * If a reference remains (rare), we would like to leave * the page in the swap cache; but try_to_unmap could * then re-duplicate the entry once we drop page lock, * so we might loop indefinitely; also, that page could * not be swapped out to other storage meanwhile. So: * delete from cache even if there's another reference, * after ensuring that the data has been saved to disk - * since if the reference remains (rarer), it will be * read from disk into another page. Splitting into two * pages would be incorrect if swap supported "shared * private" pages, but they are handled by tmpfs files. * * Given how unuse_vma() targets one particular offset * in an anon_vma, once the anon_vma has been determined, * this splitting happens to be just what is needed to * handle where KSM pages have been swapped out: re-reading * is unnecessarily slow, but we can fix that later on. */ if (swap_count(*swap_map) && PageDirty(page) && PageSwapCache(page)) { struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, }; swap_writepage(page, &wbc); lock_page(page); wait_on_page_writeback(page); } /* * It is conceivable that a racing task removed this page from * swap cache just before we acquired the page lock at the top, * or while we dropped it in unuse_mm(). The page might even * be back in swap cache on another swap area: that we must not * delete, since it may not have been written out to swap yet. */ if (PageSwapCache(page) && likely(page_private(page) == entry.val)) delete_from_swap_cache(page); /* * So we could skip searching mms once swap count went * to 1, we did not mark any present ptes as dirty: must * mark page dirty so shrink_page_list will preserve it. */ SetPageDirty(page); unlock_page(page); put_page(page); /* * Make sure that we aren't completely killing * interactive performance. */ cond_resched(); if (frontswap && pages_to_unuse > 0) { if (!--pages_to_unuse) break; } } mmput(start_mm); return retval; }

Contributors

PersonTokensPropCommitsCommitProp
Linus Torvalds32951.25%510.64%
Andrew Morton13320.72%1021.28%
Hugh Dickins649.97%1327.66%
Linus Torvalds (pre-git)507.79%1123.40%
Dan Magenheimer264.05%12.13%
Kamezawa Hiroyuki172.65%12.13%
Shaohua Li132.02%12.13%
Vegard Nossum60.93%24.26%
Kirill A. Shutemov20.31%12.13%
Anderson Briglia10.16%12.13%
Ingo Molnar10.16%12.13%
Total642100.00%47100.00%

/* * After a successful try_to_unuse, if no swap is now in use, we know * we can empty the mmlist. swap_lock must be held on entry and exit. * Note that mmlist_lock nests inside swap_lock, and an mm must be * added to the mmlist just after page_duplicate - before would be racy. */
static void drain_mmlist(void) { struct list_head *p, *next; unsigned int type; for (type = 0; type < nr_swapfiles; type++) if (swap_info[type]->inuse_pages) return; spin_lock(&mmlist_lock); list_for_each_safe(p, next, &init_mm.mmlist) list_del_init(p); spin_unlock(&mmlist_lock); }

Contributors

PersonTokensPropCommitsCommitProp
Hugh Dickins68100.00%2100.00%
Total68100.00%2100.00%

/* * Use this swapdev's extent info to locate the (PAGE_SIZE) block which * corresponds to page offset for the specified swap entry. * Note that the type of this function is sector_t, but it returns page offset * into the bdev, not sector offset. */
static sector_t map_swap_entry(swp_entry_t entry, struct block_device **bdev) { struct swap_info_struct *sis; struct swap_extent *start_se; struct swap_extent *se; pgoff_t offset; sis = swap_info[swp_type(entry)]; *bdev = sis->bdev; offset = swp_offset(entry); start_se = sis->curr_swap_extent; se = start_se; for ( ; ; ) { if (se->start_page <= offset && offset < (se->start_page + se->nr_pages)) { return se->start_block + (offset - se->start_page); } se = list_next_entry(se, list); sis->curr_swap_extent = se; BUG_ON(se == start_se); /* It *must* be present */ } }

Contributors

PersonTokensPropCommitsCommitProp
Andrew Morton5138.64%111.11%
Hugh Dickins4836.36%222.22%
Linus Torvalds (pre-git)2619.70%222.22%
Linus Torvalds32.27%222.22%
Lee Schermerhorn21.52%111.11%
Geliang Tang21.52%111.11%
Total132100.00%9100.00%

/* * Returns the page offset into bdev for the specified page's swap entry. */
sector_t map_swap_page(struct page *page, struct block_device **bdev) { swp_entry_t entry; entry.val = page_private(page); return map_swap_entry(entry, bdev); }

Contributors

PersonTokensPropCommitsCommitProp
Lee Schermerhorn36100.00%1100.00%
Total36100.00%1100.00%

/* * Free all of a swapdev's extent information */
static void destroy_swap_extents(struct swap_info_struct *sis) { while (!list_empty(&sis->first_swap_extent.list)) { struct swap_extent *se; se = list_first_entry(&sis->first_swap_extent.list, struct swap_extent, list); list_del(&se->list); kfree(se); } if (sis->flags & SWP_FILE) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; sis->flags &= ~SWP_FILE; mapping->a_ops->swap_deactivate(swap_file); } }

Contributors

PersonTokensPropCommitsCommitProp
Andrew Morton5350.48%125.00%
Mel Gorman4441.90%125.00%
Hugh Dickins65.71%125.00%
Geliang Tang21.90%125.00%
Total105100.00%4100.00%

/* * Add a block range (and the corresponding page range) into this swapdev's * extent list. The extent list is kept sorted in page order. * * This function rather assumes that it is called in ascending page order. */
int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { struct swap_extent *se; struct swap_extent *new_se; struct list_head *lh; if (start_page == 0) { se = &sis->first_swap_extent; sis->curr_swap_extent = se; se->start_page = 0; se->nr_pages = nr_pages; se->start_block = start_block; return 1; } else { lh = sis->first_swap_extent.list.prev; /* Highest extent */ se = list_entry(lh, struct swap_extent, list); BUG_ON(se->start_page + se->nr_pages != start_page); if (se->start_block + se->nr_pages == start_block) { /* Merge it */ se->nr_pages += nr_pages; return 0; } } /* * No merge. Insert a new extent, preserving ordering. */ new_se = kmalloc(sizeof(*se), GFP_KERNEL); if (new_se == NULL) return -ENOMEM; new_se->start_page = start_page; new_se->nr_pages = nr_pages; new_se->start_block = start_block; list_add_tail(&new_se->list, &sis->first_swap_extent.list); return 1; }

Contributors

PersonTokensPropCommitsCommitProp
Andrew Morton13567.16%240.00%
Hugh Dickins6632.84%360.00%
Total201100.00%5100.00%

/* * A `swap extent' is a simple thing which maps a contiguous range of pages * onto a contiguous range of disk blocks. An ordered list of swap extents * is built at swapon time and is then used at swap_writepage/swap_readpage * time for locating where on disk a page belongs. * * If the swapfile is an S_ISBLK block device, a single extent is installed. * This is done so that the main operating code can treat S_ISBLK and S_ISREG * swap files identically. * * Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap * extent list operates in PAGE_SIZE disk blocks. Both S_ISREG and S_ISBLK * swapfiles are handled *identically* after swapon time. * * For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks * and will parse them into an ordered extent list, in PAGE_SIZE chunks. If * some stray blocks are found which do not fall within the PAGE_SIZE alignment * requirements, they are simply tossed out - we will never use those blocks * for swapping. * * For S_ISREG swapfiles we set S_SWAPFILE across the life of the swapon. This * prevents root from shooting her foot off by ftruncating an in-use swapfile, * which will scribble on the fs. * * The amount of disk space which a single swap extent represents varies. * Typically it is in the 1-4 megabyte range. So we can have hundreds of * extents in the list. To avoid much list walking, we cache the previous * search location in `curr_swap_extent', and start new searches from there. * This is extremely effective. The average number of iterations in * map_swap_page() has been measured at about 0.3 per page. - akpm. */
static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; struct inode *inode = mapping->host; int ret; if (S_ISBLK(inode->i_mode)) { ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; return ret; } if (mapping->a_ops->swap_activate) { ret = mapping->a_ops->swap_activate(sis, swap_file, span); if (!ret) { sis->flags |= SWP_FILE; ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; } return ret; } return generic_swapfile_activate(sis, swap_file, span); }

Contributors

PersonTokensPropCommitsCommitProp
Mel Gorman9058.44%250.00%
Andrew Morton5233.77%125.00%
Hugh Dickins127.79%125.00%
Total154100.00%4100.00%


static void _enable_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info) { if (prio >= 0) p->prio = prio; else p->prio = --least_priority; /* * the plist prio is negated because plist ordering is * low-to-high, while swap ordering is high-to-low */ p->list.prio = -p->prio; p->avail_list.prio = -p->prio; p->swap_map = swap_map; p->cluster_info = cluster_info; p->flags |= SWP_WRITEOK; atomic_long_add(p->pages, &nr_swap_pages); total_swap_pages += p->pages; assert_spin_locked(&swap_lock); /* * both lists are plists, and thus priority ordered. * swap_active_head needs to be priority ordered for swapoff(), * which on removal of any swap_info_struct with an auto-assigned * (i.e. negative) priority increments the auto-assigned priority * of any lower-priority swap_info_structs. * swap_avail_head needs to be priority ordered for get_swap_page(), * which allocates swap pages from the highest available priority * swap_info_struct. */ plist_add(&p->list, &swap_active_head); spin_lock(&swap_avail_lock); plist_add(&p->avail_list, &swap_avail_head); spin_unlock(&swap_avail_lock); }

Contributors

PersonTokensPropCommitsCommitProp
Cesar Eduardo Barros6747.18%233.33%
Dan Streetman5840.85%233.33%
Shaohua Li1711.97%233.33%
Total142100.00%6100.00%


static void enable_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long *frontswap_map) { frontswap_init(p->type, frontswap_map); spin_lock(&swap_lock); spin_lock(&p->lock); _enable_swap_info(p, prio, swap_map, cluster_info); spin_unlock(&p->lock); spin_unlock(&swap_lock); }

Contributors

PersonTokensPropCommitsCommitProp
Cesar Eduardo Barros4558.44%240.00%
Shaohua Li2329.87%240.00%
MinChan Kim911.69%120.00%
Total77100.00%5100.00%


static void reinsert_swap_info(struct swap_info_struct *p) { spin_lock(&swap_lock); spin_lock(&p->lock); _enable_swap_info(p, p->prio, p->swap_map, p->cluster_info); spin_unlock(&p->lock); spin_unlock(&swap_lock); }

Contributors

PersonTokensPropCommitsCommitProp
Cesar Eduardo Barros3664.29%250.00%
Shaohua Li2035.71%250.00%
Total56100.00%4100.00%


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; }

Contributors

PersonTokensPropCommitsCommitProp
Tim Chen39100.00%1100.00%
Total39100.00%1100.00%

SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; unsigned char *swap_map; struct swap_cluster_info *cluster_info; unsigned long *frontswap_map; struct file *swap_file, *victim; struct address_space *mapping; struct inode *inode; struct filename *pathname; int err, found = 0; unsigned int old_block_size; if (!capable(CAP_SYS_ADMIN)) return -EPERM; BUG_ON(!current->mm); pathname = getname(specialfile); if (IS_ERR(pathname)) return PTR_ERR(pathname); victim = file_open_name(pathname, O_RDWR|O_LARGEFILE, 0); err = PTR_ERR(victim); if (IS_ERR(victim)) goto out; mapping = victim->f_mapping; spin_lock(&swap_lock); plist_for_each_entry(p, &swap_active_head, list) { if (p->flags & SWP_WRITEOK) { if (p->swap_file->f_mapping == mapping) { found = 1; break; } } } if (!found) { err = -EINVAL; spin_unlock(&swap_lock); goto out_dput; } if (!security_vm_enough_memory_mm(current->mm, p->pages)) vm_unacct_memory(p->pages); else { err = -ENOMEM; spin_unlock(&swap_lock); goto out_dput; } spin_lock(&swap_avail_lock); plist_del(&p->avail_list, &swap_avail_head); spin_unlock(&swap_avail_lock); spin_lock(&p->lock); if (p->prio < 0) { struct swap_info_struct *si = p; plist_for_each_entry_continue(si, &swap_active_head, list) { si->prio++; si->list.prio--; si->avail_list.prio--; } least_priority++; } plist_del(&p->list, &swap_active_head); atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; p->flags &= ~SWP_WRITEOK; spin_unlock(&p->lock); spin_unlock(&swap_lock); disable_swap_slots_cache_lock(); set_current_oom_origin(); err = try_to_unuse(p->type, false, 0); /* force unuse all pages */ clear_current_oom_origin(); if (err) { /* re-insert swap space back into swap_list */ reinsert_swap_info(p); reenable_swap_slots_cache_unlock(); goto out_dput; } reenable_swap_slots_cache_unlock(); flush_work(&p->discard_work); destroy_swap_extents(p); if (p->flags & SWP_CONTINUED) free_swap_count_continuations(p); mutex_lock(&swapon_mutex); spin_lock(&swap_lock); spin_lock(&p->lock); drain_mmlist(); /* wait for anyone still in scan_swap_map */ p->highest_bit = 0; /* cuts scans short */ while (p->flags >= SWP_SCANNING) { spin_unlock(&p->lock); spin_unlock(&swap_lock); schedule_timeout_uninterruptible(1); spin_lock(&swap_lock); spin_lock(&p->lock); } swap_file = p->swap_file; old_block_size = p->old_block_size; p->swap_file = NULL; p->max = 0; swap_map = p->swap_map; p->swap_map = NULL; cluster_info = p->cluster_info; p->cluster_info = NULL; frontswap_map = frontswap_map_get(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); frontswap_invalidate_area(p->type); frontswap_map_set(p, NULL); mutex_unlock(&swapon_mutex); free_percpu(p->percpu_cluster); p->percpu_cluster = NULL; vfree(swap_map); vfree(cluster_info); vfree(frontswap_map); /* Destroy swap account information */ swap_cgroup_swapoff(p->type); exit_swap_address_space(p->type); inode = mapping->host; if (S_ISBLK(inode->i_mode)) { struct block_device *bdev = I_BDEV(inode); set_blocksize(bdev, old_block_size); blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); } else { inode_lock(inode); inode->i_flags &= ~S_SWAPFILE; inode_unlock(inode); } filp_close(swap_file, NULL); /* * Clear the SWP_USED flag after all resources are freed so that swapon * can reuse this swap_info in alloc_swap_info() safely. It is ok to * not hold p->lock after we cleared its SWP_WRITEOK. */ spin_lock(&swap_lock); p->flags = 0; spin_unlock(&swap_lock); err = 0; atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); out_dput: filp_close(victim, NULL); out: putname(pathname); return err; } #ifdef CONFIG_PROC_FS
static unsigned swaps_poll(struct file *file, poll_table *wait) { struct seq_file *seq = file->private_data; poll_wait(file, &proc_poll_wait, wait); if (seq->poll_event != atomic_read(&proc_poll_event)) { seq->poll_event = atomic_read(&proc_poll_event); return POLLIN | POLLRDNORM | POLLERR | POLLPRI; } return POLLIN | POLLRDNORM; }

Contributors

PersonTokensPropCommitsCommitProp
Kay Sievers72100.00%2100.00%
Total72100.00%2100.00%

/* iterator */
static void *swap_start(struct seq_file *swap, loff_t *pos) { struct swap_info_struct *si; int type; loff_t l = *pos; mutex_lock(&swapon_mutex); if (!l) return SEQ_START_TOKEN; for (type = 0; type < nr_swapfiles; type++) { smp_rmb(); /* read nr_swapfiles before swap_info[type] */ si = swap_info[type]; if (!(si->flags & SWP_USED) || !si->swap_map) continue; if (!--l) return si; } return NULL; }

Contributors

PersonTokensPropCommitsCommitProp
Randy Dunlap5151.52%114.29%
Hugh Dickins1919.19%114.29%
Linus Torvalds (pre-git)1515.15%228.57%
Suleiman Souhlal99.09%114.29%
Al Viro33.03%114.29%
Ingo Molnar22.02%114.29%
Total99100.00%7100.00%


static void *swap_next(struct seq_file *swap, void *v, loff_t *pos) { struct swap_info_struct *si = v; int type; if (v == SEQ_START_TOKEN) type = 0; else type = si->type + 1; for (; type < nr_swapfiles; type++) { smp_rmb(); /* read nr_swapfiles before swap_info[type] */ si = swap_info[type]; if (!(si->flags & SWP_USED) || !si->swap_map) continue; ++*pos; return si; } return NULL; }

Contributors

PersonTokensPropCommitsCommitProp
Randy Dunlap4040.40%116.67%
Hugh Dickins3030.30%116.67%
Suleiman Souhlal1111.11%116.67%
Al Viro77.07%116.67%
Linus Torvalds (pre-git)77.07%116.67%
Linus Torvalds44.04%116.67%
Total99100.00%6100.00%


static void swap_stop(struct seq_file *swap, void *v) { mutex_unlock(&swapon_mutex); }

Contributors

PersonTokensPropCommitsCommitProp
Randy Dunlap1676.19%133.33%
Al Viro314.29%133.33%
Ingo Molnar29.52%133.33%
Total21100.00%3100.00%


static int swap_show(struct seq_file *swap, void *v) { struct swap_info_struct *si = v; struct file *file; int len; if (si == SEQ_START_TOKEN) { seq_puts(swap,"Filename\t\t\t\tType\t\tSize\tUsed\tPriority\n"); return 0; } file = si->swap_file; len = seq_file_path(swap, file, " \t\n\\"); seq_printf(swap, "%*s%s\t%u\t%u\t%d\n", len < 40 ? 40 - len : 1, " ", S_ISBLK(file_inode(file)->i_mode) ? "partition" : "file\t", si->pages << (PAGE_SHIFT - 10), si->inuse_pages << (PAGE_SHIFT - 10), si->prio); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Randy Dunlap4032.00%17.14%
Al Viro3225.60%321.43%
Linus Torvalds (pre-git)3124.80%214.29%
Hugh Dickins75.60%214.29%
Suleiman Souhlal64.80%17.14%
Linus Torvalds64.80%321.43%
Andrew Morton21.60%17.14%
Miklos Szeredi10.80%17.14%
Total125100.00%14100.00%

static const struct seq_operations swaps_op = { .start = swap_start, .next = swap_next, .stop = swap_stop, .show = swap_show };
static int swaps_open(struct inode *inode, struct file *file) { struct seq_file *seq; int ret; ret = seq_open(file, &swaps_op); if (ret) return ret; seq = file->private_data; seq->poll_event = atomic_read(&proc_poll_event); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Kay Sievers3660.00%266.67%
Christoph Hellwig2440.00%133.33%
Total60100.00%3100.00%

static const struct file_operations proc_swaps_operations = { .open = swaps_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, .poll = swaps_poll, };
static int __init procswaps_init(void) { proc_create("swaps", 0, NULL, &proc_swaps_operations); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Christoph Hellwig2187.50%150.00%
Denis V. Lunev312.50%150.00%
Total24100.00%2100.00%

__initcall(procswaps_init); #endif /* CONFIG_PROC_FS */ #ifdef MAX_SWAPFILES_CHECK
static int __init max_swapfiles_check(void) { MAX_SWAPFILES_CHECK(); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Jan Beulich15100.00%1100.00%
Total15100.00%1100.00%

late_initcall(max_swapfiles_check); #endif
static struct swap_info_struct *alloc_swap_info(void) { struct swap_info_struct *p; unsigned int type; p = kzalloc(sizeof(*p), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { if (!(swap_info[type]->flags & SWP_USED)) break; } if (type >= MAX_SWAPFILES) { spin_unlock(&swap_lock); kfree(p); return ERR_PTR(-EPERM); } if (type >= nr_swapfiles) { p->type = type; swap_info[type] = p; /* * Write swap_info[type] before nr_swapfiles, in case a * racing procfs swap_start() or swap_next() is reading them. * (We never shrink nr_swapfiles, we never free this entry.) */ smp_wmb(); nr_swapfiles++; } else { kfree(p); p = swap_info[type]; /* * Do not memset this entry: a racing procfs swap_next() * would be relying on p->type to remain valid. */ } INIT_LIST_HEAD(&p->first_swap_extent.list); plist_node_init(&p->list, 0); plist_node_init(&p->avail_list, 0); p->flags = SWP_USED; spin_unlock(&swap_lock); spin_lock_init(&p->lock); return p; }

Contributors

PersonTokensPropCommitsCommitProp
Hugh Dickins9144.83%428.57%
Linus Torvalds (pre-git)5426.60%214.29%
Cesar Eduardo Barros2210.84%214.29%
Dan Streetman199.36%214.29%
Shaohua Li83.94%17.14%
Linus Torvalds52.46%17.14%
Christoph Lameter20.99%17.14%
Andrew Morton20.99%17.14%
Total203100.00%14100.00%


static int claim_swapfile(struct swap_info_struct *p, struct inode *inode) { int error; if (S_ISBLK(inode->i_mode)) { p->bdev = bdgrab(I_BDEV(inode)); error = blkdev_get(p->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL, p); if (error < 0) { p->bdev = NULL; return error; } p->old_block_size = block_size(p->bdev); error = set_blocksize(p->bdev, PAGE_SIZE); if (error < 0) return error; p->flags |= SWP_BLKDEV; } else if (S_ISREG(inode->i_mode)) { p->bdev = inode->i_sb->s_bdev; inode_lock(inode); if (IS_SWAPFILE(inode)) return -EBUSY; } else return -EINVAL; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Cesar Eduardo Barros15698.11%250.00%
Hugh Dickins21.26%125.00%
Al Viro10.63%125.00%
Total159100.00%4100.00%


static unsigned long read_swap_header(struct swap_info_struct *p, union swap_header *swap_header, struct inode *inode) { int i; unsigned long maxpages; unsigned long swapfilepages; unsigned long last_page; if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) { pr_err("Unable to find swap-space signature\n"); return 0; } /* swap partition endianess hack... */ if (swab32(swap_header->info.version) == 1) { swab32s(&swap_header->info.version); swab32s(&swap_header->info.last_page); swab32s(&swap_header->info.nr_badpages); if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; for (i = 0; i < swap_header->info.nr_badpages; i++) swab32s(&swap_header->info.badpages[i]); } /* Check the swap header's sub-version */ if (swap_header->info.version != 1) { pr_warn("Unable to handle swap header version %d\n", swap_header->info.version); return 0; } p->lowest_bit = 1; p->cluster_next = 1; p->cluster_nr = 0; /* * Find out how many pages are allowed for a single swap * device. There are two limiting factors: 1) the number * of bits for the swap offset in the swp_entry_t type, and * 2) the number of bits in the swap pte as defined by the * different architectures. In order to find the * largest possible bit mask, a swap entry with swap type 0 * and swap offset ~0UL is created, encoded to a swap pte, * decoded to a swp_entry_t again, and finally the swap * offset is extracted. This will mask all the bits from * the initial ~0UL mask that can't be encoded in either * the swp_entry_t or the architecture definition of a * swap pte. */ maxpages = swp_offset(pte_to_swp_entry( swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; last_page = swap_header->info.last_page; if (last_page > maxpages) { pr_warn("Truncating oversized swap area, only using %luk out of %luk\n", maxpages << (PAGE_SHIFT - 10), last_page << (PAGE_SHIFT - 10)); } if (maxpages > last_page) { maxpages = last_page + 1; /* p->max is an unsigned int: don't overflow it */ if ((unsigned int)maxpages == 0) maxpages = UINT_MAX; } p->highest_bit = maxpages - 1; if (!maxpages) return 0; swapfilepages = i_size_read(inode) >> PAGE_SHIFT; if (swapfilepages && maxpages > swapfilepages) { pr_warn("Swap area shorter than signature indicates\n"); return 0; } if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode)) return 0; if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; return maxpages; }

Contributors

PersonTokensPropCommitsCommitProp
Cesar Eduardo Barros30383.93%233.33%
Raymond Jennings4011.08%116.67%
Jann Horn133.60%116.67%
Andrew Morton41.11%116.67%
Hugh Dickins10.28%116.67%
Total361100.00%6100.00%

#define SWAP_CLUSTER_INFO_COLS \ DIV_ROUND_UP(L1_CACHE_BYTES, sizeof(struct swap_cluster_info)) #define SWAP_CLUSTER_SPACE_COLS \ DIV_ROUND_UP(SWAP_ADDRESS_SPACE_PAGES, SWAPFILE_CLUSTER) #define SWAP_CLUSTER_COLS \ max_t(unsigned int, SWAP_CLUSTER_INFO_COLS, SWAP_CLUSTER_SPACE_COLS)
static int setup_swap_map_and_extents(struct swap_info_struct *p, union swap_header *swap_header, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long maxpages, sector_t *span) { unsigned int j, k; unsigned int nr_good_pages; int nr_extents; unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); unsigned long col = p->cluster_next / SWAPFILE_CLUSTER % SWAP_CLUSTER_COLS; unsigned long i, idx; nr_good_pages = maxpages - 1; /* omit header page */ cluster_list_init(&p->free_clusters); cluster_list_init(&p->discard_clusters); for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; if (page_nr == 0 || page_nr > swap_header->info.last_page) return -EINVAL; if (page_nr < maxpages) { swap_map[page_nr] = SWAP_MAP_BAD; nr_good_pages--; /* * Haven't marked the cluster free yet, no list * operation involved */ inc_cluster_info_page(p, cluster_info, page_nr); } } /* Haven't marked the cluster free yet, no list operation involved */ for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++) inc_cluster_info_page(p, cluster_info, i); if (nr_good_pages) { swap_map[0] = SWAP_MAP_BAD; /* * Not mark the cluster free yet, no list * operation involved */ inc_cluster_info_page(p, cluster_info, 0); p->max = maxpages; p->pages = nr_good_pages; nr_extents = setup_swap_extents(p, span); if (nr_extents < 0) return nr_extents; nr_good_pages = p->pages; } if (!nr_good_pages) { pr_warn("Empty swap-file\n"); return -EINVAL; } if (!cluster_info) return nr_extents; /* * Reduce false cache line sharing between cluster_info and * sharing same address space. */ for (k = 0; k < SWAP_CLUSTER_COLS; k++) { j = (k + col) % SWAP_CLUSTER_COLS; for (i = 0; i < DIV_ROUND_UP(nr_clusters, SWAP_CLUSTER_COLS); i++) { idx = i * SWAP_CLUSTER_COLS + j; if (idx >= nr_clusters) continue; if (cluster_count(&cluster_info[idx])) continue; cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE); cluster_list_add_tail(&p->free_clusters, cluster_info, idx); } } return nr_extents; }

Contributors

PersonTokensPropCommitsCommitProp
Cesar Eduardo Barros17845.99%225.00%
Shaohua Li14336.95%225.00%
Huang Ying6516.80%337.50%
Andrew Morton10.26%112.50%
Total387100.00%8100.00%

/* * Helper to sys_swapon determining if a given swap * backing device queue supports DISCARD operations. */
static bool swap_discardable(struct swap_info_struct *si) { struct request_queue *q = bdev_get_queue(si->bdev); if (!q || !blk_queue_discard(q)) return false; return true; }

Contributors

PersonTokensPropCommitsCommitProp
Rafael Aquini40100.00%1100.00%
Total40100.00%1100.00%

SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { struct swap_info_struct *p; struct filename *name; struct file *swap_file = NULL; struct address_space *mapping; int prio; int error; union swap_header *swap_header; int nr_extents; sector_t span; unsigned long maxpages; unsigned char *swap_map = NULL; struct swap_cluster_info *cluster_info = NULL; unsigned long *frontswap_map = NULL; struct page *page = NULL; struct inode *inode = NULL; if (swap_flags & ~SWAP_FLAGS_VALID) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; p = alloc_swap_info(); if (IS_ERR(p)) return PTR_ERR(p); INIT_WORK(&p->discard_work, swap_discard_work); name = getname(specialfile); if (IS_ERR(name)) { error = PTR_ERR(name); name = NULL; goto bad_swap; } swap_file = file_open_name(name, O_RDWR|O_LARGEFILE, 0); if (IS_ERR(swap_file)) { error = PTR_ERR(swap_file); swap_file = NULL; goto bad_swap; } p->swap_file = swap_file; mapping = swap_file->f_mapping; inode = mapping->host; /* If S_ISREG(inode->i_mode) will do inode_lock(inode); */ error = claim_swapfile(p, inode); if (unlikely(error)) goto bad_swap; /* * Read the swap header. */ if (!mapping->a_ops->readpage) { error = -EINVAL; goto bad_swap; } page = read_mapping_page(mapping, 0, swap_file); if (IS_ERR(page)) { error = PTR_ERR(page); goto bad_swap; } swap_header = kmap(page); maxpages = read_swap_header(p, swap_header, inode); if (unlikely(!maxpages)) { error = -EINVAL; goto bad_swap; } /* OK, set up the swap map and apply the bad block list */ swap_map = vzalloc(maxpages); if (!swap_map) { error = -ENOMEM; goto bad_swap; } if (bdi_cap_stable_pages_required(inode_to_bdi(inode))) p->flags |= SWP_STABLE_WRITES; if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) { int cpu; unsigned long ci, nr_cluster; p->flags |= SWP_SOLIDSTATE; /* * select a random position to start with to help wear leveling * SSD */ p->cluster_next = 1 + (prandom_u32() % p->highest_bit); nr_cluster = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); cluster_info = vzalloc(nr_cluster * sizeof(*cluster_info)); if (!cluster_info) { error = -ENOMEM; goto bad_swap; } for (ci = 0; ci < nr_cluster; ci++) spin_lock_init(&((cluster_info + ci)->lock)); p->percpu_cluster = alloc_percpu(struct percpu_cluster); if (!p->percpu_cluster) { error = -ENOMEM; goto bad_swap; } for_each_possible_cpu(cpu) { struct percpu_cluster *cluster; cluster = per_cpu_ptr(p->percpu_cluster, cpu); cluster_set_null(&cluster->index); } } error = swap_cgroup_swapon(p->type, maxpages); if (error) goto bad_swap; nr_extents = setup_swap_map_and_extents(p, swap_header, swap_map, cluster_info, maxpages, &span); if (unlikely(nr_extents < 0)) { error = nr_extents; goto bad_swap; } /* frontswap enabled? set up bit-per-page map for frontswap */ if (IS_ENABLED(CONFIG_FRONTSWAP)) frontswap_map = vzalloc(BITS_TO_LONGS(maxpages) * sizeof(long)); if (p->bdev &&(swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) { /* * When discard is enabled for swap with no particular * policy flagged, we set all swap discard flags here in * order to sustain backward compatibility with older * swapon(8) releases. */ p->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD | SWP_PAGE_DISCARD); /* * By flagging sys_swapon, a sysadmin can tell us to * either do single-time area discards only, or to just * perform discards for released swap page-clusters. * Now it's time to adjust the p->flags accordingly. */ if (swap_flags & SWAP_FLAG_DISCARD_ONCE) p->flags &= ~SWP_PAGE_DISCARD; else if (swap_flags & SWAP_FLAG_DISCARD_PAGES) p->flags &= ~SWP_AREA_DISCARD; /* issue a swapon-time discard if it's still required */ if (p->flags & SWP_AREA_DISCARD) { int err = discard_swap(p); if (unlikely(err)) pr_err("swapon: discard_swap(%p): %d\n", p, err); } } error = init_swap_address_space(p->type, maxpages); if (error) goto bad_swap; mutex_lock(&swapon_mutex); prio = -1; if (swap_flags & SWAP_FLAG_PREFER) prio = (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT; enable_swap_info(p, prio, swap_map, cluster_info, frontswap_map); pr_info("Adding %uk swap on %s. Priority:%d extents:%d across:%lluk %s%s%s%s%s\n", p->pages<<(PAGE_SHIFT-10), name->name, p->prio, nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10), (p->flags & SWP_SOLIDSTATE) ? "SS" : "", (p->flags & SWP_DISCARDABLE) ? "D" : "", (p->flags & SWP_AREA_DISCARD) ? "s" : "", (p->flags & SWP_PAGE_DISCARD) ? "c" : "", (frontswap_map) ? "FS" : ""); mutex_unlock(&swapon_mutex); atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); if (S_ISREG(inode->i_mode)) inode->i_flags |= S_SWAPFILE; error = 0; goto out; bad_swap: free_percpu(p->percpu_cluster); p->percpu_cluster = NULL; if (inode && S_ISBLK(inode->i_mode) && p->bdev) { set_blocksize(p->bdev, p->old_block_size); blkdev_put(p->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); } destroy_swap_extents(p); swap_cgroup_swapoff(p->type); spin_lock(&swap_lock); p->swap_file = NULL; p->flags = 0; spin_unlock(&swap_lock); vfree(swap_map); vfree(cluster_info); if (swap_file) { if (inode && S_ISREG(inode->i_mode)) { inode_unlock(inode); inode = NULL; } filp_close(swap_file, NULL); } out: if (page && !IS_ERR(page)) { kunmap(page); put_page(page); } if (name) putname(name); if (inode && S_ISREG(inode->i_mode)) inode_unlock(inode); if (!error) enable_swap_slots_cache(); return error; }
void si_swapinfo(struct sysinfo *val) { unsigned int type; unsigned long nr_to_be_unused = 0; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *si = swap_info[type]; if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK)) nr_to_be_unused += si->inuse_pages; } val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused; val->totalswap = total_swap_pages + nr_to_be_unused; spin_unlock(&swap_lock); }

Contributors

PersonTokensPropCommitsCommitProp
Andrew Morton4443.14%233.33%
Hugh Dickins3231.37%233.33%
Linus Torvalds (pre-git)2221.57%116.67%
Shaohua Li43.92%116.67%
Total102100.00%6100.00%

/* * Verify that a swap entry is valid and increment its swap map count. * * Returns error code in following case. * - success -> 0 * - swp_entry is invalid -> EINVAL * - swp_entry is migration entry -> EINVAL * - swap-cache reference is requested but there is already one. -> EEXIST * - swap-cache reference is requested but the entry is not used. -> ENOENT * - swap-mapped reference requested but needs continued swap count. -> ENOMEM */
static int __swap_duplicate(swp_entry_t entry, unsigned char usage) { struct swap_info_struct *p; struct swap_cluster_info *ci; unsigned long offset, type; unsigned char count; unsigned char has_cache; int err = -EINVAL; if (non_swap_entry(entry)) goto out; type = swp_type(entry); if (type >= nr_swapfiles) goto bad_file; p = swap_info[type]; offset = swp_offset(entry); if (unlikely(offset >= p->max)) goto out; ci = lock_cluster_or_swap_info(p, offset); count = p->swap_map[offset]; /* * swapin_readahead() doesn't check if a swap entry is valid, so the * swap entry could be SWAP_MAP_BAD. Check here with lock held. */ if (unlikely(swap_count(count) == SWAP_MAP_BAD)) { err = -ENOENT; goto unlock_out; } has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; err = 0; if (usage == SWAP_HAS_CACHE) { /* set SWAP_HAS_CACHE if there is no cache and entry is used */ if (!has_cache && count) has_cache = SWAP_HAS_CACHE; else if (has_cache) /* someone else added cache */ err = -EEXIST; else /* no users remaining */ err = -ENOENT; } else if (count || has_cache) { if ((count & ~COUNT_CONTINUED) < SWAP_MAP_MAX) count += usage; else if ((count & ~COUNT_CONTINUED) > SWAP_MAP_MAX) err = -EINVAL; else if (swap_count_continued(p, offset, count)) count = COUNT_CONTINUED; else err = -ENOMEM; } else err = -ENOENT; /* unused swap entry */ p->swap_map[offset] = count | has_cache; unlock_out: unlock_cluster_or_swap_info(p, ci); out: return err; bad_file: pr_err("swap_dup: %s%08lx\n", Bad_file, entry.val); goto out; }

Contributors

PersonTokensPropCommitsCommitProp
Hugh Dickins8427.81%426.67%
Kamezawa Hiroyuki7123.51%16.67%
Linus Torvalds (pre-git)4916.23%16.67%
Andrew Morton4414.57%320.00%
Shaohua Li247.95%213.33%
Huang Ying185.96%16.67%
Christoph Lameter61.99%16.67%
Linus Torvalds51.66%16.67%
Andi Kleen10.33%16.67%
Total302100.00%15100.00%

/* * Help swapoff by noting that swap entry belongs to shmem/tmpfs * (in which case its reference count is never incremented). */
void swap_shmem_alloc(swp_entry_t entry) { __swap_duplicate(entry, SWAP_MAP_SHMEM); }

Contributors

PersonTokensPropCommitsCommitProp
Hugh Dickins15100.00%1100.00%
Total15100.00%1100.00%

/* * Increase reference count of swap entry by 1. * Returns 0 for success, or -ENOMEM if a swap_count_continuation is required * but could not be atomically allocated. Returns 0, just as if it succeeded, * if __swap_duplicate() fails for another reason (-EINVAL or -ENOENT), which * might occur if a page table entry has got corrupted. */
int swap_duplicate(swp_entry_t entry) { int err = 0; while (!err && __swap_duplicate(entry, 1) == -ENOMEM) err = add_swap_count_continuation(entry, GFP_ATOMIC); return err; }

Contributors

PersonTokensPropCommitsCommitProp
Hugh Dickins2767.50%266.67%
Kamezawa Hiroyuki1332.50%133.33%
Total40100.00%3100.00%

/* * @entry: swap entry for which we allocate swap cache. * * Called when allocating swap cache for existing swap entry, * This can return error codes. Returns 0 at success. * -EBUSY means there is a swap cache. * Note: return code is different from swap_duplicate(). */
int swapcache_prepare(swp_entry_t entry) { return __swap_duplicate(entry, SWAP_HAS_CACHE); }

Contributors

PersonTokensPropCommitsCommitProp
Kamezawa Hiroyuki1593.75%266.67%
Hugh Dickins16.25%133.33%
Total16100.00%3100.00%


struct swap_info_struct *page_swap_info(struct page *page) { swp_entry_t swap = { .val = page_private(page) }; return swap_info[swp_type(swap)]; }

Contributors

PersonTokensPropCommitsCommitProp
Mel Gorman34100.00%1100.00%
Total34100.00%1100.00%

/* * out-of-line __page_file_ methods to avoid include hell. */
struct address_space *__page_file_mapping(struct page *page) { VM_BUG_ON_PAGE(!PageSwapCache(page), page); return page_swap_info(page)->swap_file->f_mapping; }

Contributors

PersonTokensPropCommitsCommitProp
Mel Gorman3090.91%150.00%
Sasha Levin39.09%150.00%
Total33100.00%2100.00%

EXPORT_SYMBOL_GPL(__page_file_mapping);
pgoff_t __page_file_index(struct page *page) { swp_entry_t swap = { .val = page_private(page) }; VM_BUG_ON_PAGE(!PageSwapCache(page), page); return swp_offset(swap); }

Contributors

PersonTokensPropCommitsCommitProp
Mel Gorman3792.50%150.00%
Sasha Levin37.50%150.00%
Total40100.00%2100.00%

EXPORT_SYMBOL_GPL(__page_file_index); /* * add_swap_count_continuation - called when a swap count is duplicated * beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's * page of the original vmalloc'ed swap_map, to hold the continuation count * (for that entry and for its neighbouring PAGE_SIZE swap entries). Called * again when count is duplicated beyond SWAP_MAP_MAX * SWAP_CONT_MAX, etc. * * These continuation pages are seldom referenced: the common paths all work * on the original swap_map, only referring to a continuation page when the * low "digit" of a count is incremented or decremented through SWAP_MAP_MAX. * * add_swap_count_continuation(, GFP_ATOMIC) can be called while holding * page table locks; if it fails, add_swap_count_continuation(, GFP_KERNEL) * can be called after dropping locks. */
int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) { struct swap_info_struct *si; struct swap_cluster_info *ci; struct page *head; struct page *page; struct page *list_page; pgoff_t offset; unsigned char count; /* * When debugging, it's easier to use __GFP_ZERO here; but it's better * for latency not to zero a page while GFP_ATOMIC and holding locks. */ page = alloc_page(gfp_mask | __GFP_HIGHMEM); si = swap_info_get(entry); if (!si) { /* * An acceptable race has occurred since the failing * __swap_duplicate(): the swap entry has been freed, * perhaps even the whole swap_map cleared for swapoff. */ goto outer; } offset = swp_offset(entry); ci = lock_cluster(si, offset); count = si->swap_map[offset] & ~SWAP_HAS_CACHE; if ((count & ~COUNT_CONTINUED) != SWAP_MAP_MAX) { /* * The higher the swap count, the more likely it is that tasks * will race to add swap count continuation: we need to avoid * over-provisioning. */ goto out; } if (!page) { unlock_cluster(ci); spin_unlock(&si->lock); return -ENOMEM; } /* * We are fortunate that although vmalloc_to_page uses pte_offset_map, * no architecture is using highmem pages for kernel page tables: so it * will not corrupt the GFP_ATOMIC caller's atomic page table kmaps. */ head = vmalloc_to_page(si->swap_map + offset); offset &= ~PAGE_MASK; /* * Page allocation does not initialize the page's lru field, * but it does always reset its private field. */ if (!page_private(head)) { BUG_ON(count & COUNT_CONTINUED); INIT_LIST_HEAD(&head->lru); set_page_private(head, SWP_CONTINUED); si->flags |= SWP_CONTINUED; } list_for_each_entry(list_page, &head->lru, lru) { unsigned char *map; /* * If the previous map said no continuation, but we've found * a continuation page, free our allocation and use this one. */ if (!(count & COUNT_CONTINUED)) goto out; map = kmap_atomic(list_page) + offset; count = *map; kunmap_atomic(map); /* * If this continuation count now has some space in it, * free our allocation and use this one. */ if ((count & ~COUNT_CONTINUED) != SWAP_CONT_MAX) goto out; } list_add_tail(&page->lru, &head->lru); page = NULL; /* now it's attached, don't free it */ out: unlock_cluster(ci); spin_unlock(&si->lock); outer: if (page) __free_page(page); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
Hugh Dickins27489.84%125.00%
Huang Ying247.87%125.00%
Shaohua Li61.97%125.00%
Seth Jennings10.33%125.00%
Total305100.00%4100.00%

/* * swap_count_continued - when the original swap_map count is incremented * from SWAP_MAP_MAX, check if there is already a continuation page to carry * into, carry if so, or else fail until a new continuation page is allocated; * when the original swap_map count is decremented from 0 with continuation, * borrow from the continuation and report whether it still holds more. * Called while __swap_duplicate() or swap_entry_free() holds swap or cluster * lock. */
static bool swap_count_continued(struct swap_info_struct *si, pgoff_t offset, unsigned char count) { struct page *head; struct page *page; unsigned char *map; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head) != SWP_CONTINUED) { BUG_ON(count & COUNT_CONTINUED); return false; /* need to add count continuation */ } offset &= ~PAGE_MASK; page = list_entry(head->lru.next, struct page, lru); map = kmap_atomic(page) + offset; if (count == SWAP_MAP_MAX) /* initial increment from swap_map */ goto init_map; /* jump over SWAP_CONT_MAX checks */ if (count == (SWAP_MAP_MAX | COUNT_CONTINUED)) { /* incrementing */ /* * Think of how you add 1 to 999 */ while (*map == (SWAP_CONT_MAX | COUNT_CONTINUED)) { kunmap_atomic(map); page = list_entry(page->lru.next, struct page, lru); BUG_ON(page == head); map = kmap_atomic(page) + offset; } if (*map == SWAP_CONT_MAX) { kunmap_atomic(map); page = list_entry(page->lru.next, struct page, lru); if (page == head) return false; /* add count continuation */ map = kmap_atomic(page) + offset; init_map: *map = 0; /* we didn't zero the page */ } *map += 1; kunmap_atomic(map); page = list_entry(page->lru.prev, struct page, lru); while (page != head) { map = kmap_atomic(page) + offset; *map = COUNT_CONTINUED; kunmap_atomic(map); page = list_entry(page->lru.prev, struct page, lru); } return true; /* incremented */ } else { /* decrementing */ /* * Think of how you subtract 1 from 1000 */ BUG_ON(count != COUNT_CONTINUED); while (*map == COUNT_CONTINUED) { kunmap_atomic(map); page = list_entry(page->lru.next, struct page, lru); BUG_ON(page == head); map = kmap_atomic(page) + offset; } BUG_ON(*map == 0); *map -= 1; if (*map == 0) count = 0; kunmap_atomic(map); page = list_entry(page->lru.prev, struct page, lru); while (page != head) { map = kmap_atomic(page) + offset; *map = SWAP_CONT_MAX | count; count = COUNT_CONTINUED; kunmap_atomic(map); page = list_entry(page->lru.prev, struct page, lru); } return count == COUNT_CONTINUED; } }

Contributors

PersonTokensPropCommitsCommitProp
Hugh Dickins458100.00%1100.00%
Total458100.00%1100.00%

/* * free_swap_count_continuations - swapoff free all the continuation pages * appended to the swap_map, after swap_map is quiesced, before vfree'ing it. */
static void free_swap_count_continuations(struct swap_info_struct *si) { pgoff_t offset; for (offset = 0; offset < si->max; offset += PAGE_SIZE) { struct page *head; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head)) { struct page *page, *next; list_for_each_entry_safe(page, next, &head->lru, lru) { list_del(&page->lru); __free_page(page); } } } }

Contributors

PersonTokensPropCommitsCommitProp
Hugh Dickins8190.00%150.00%
Geliang Tang910.00%150.00%
Total90100.00%2100.00%


Overall Contributors

PersonTokensPropCommitsCommitProp
Hugh Dickins310522.77%6220.39%
Shaohua Li179613.17%72.30%
Cesar Eduardo Barros11528.45%247.89%
Linus Torvalds (pre-git)9116.68%289.21%
Andrew Morton8766.42%3110.20%
Linus Torvalds8556.27%196.25%
Huang Ying8556.27%51.64%
Tim Chen8055.90%51.64%
Dan Streetman4343.18%20.66%
Kamezawa Hiroyuki4183.06%113.62%
MinChan Kim2802.05%30.99%
Mel Gorman2762.02%61.97%
Rafael J. Wysocki2361.73%61.97%
Randy Dunlap1861.36%20.66%
Kay Sievers1561.14%20.66%
Al Viro1421.04%92.96%
Kirill A. Shutemov1361.00%51.64%
Rafael Aquini1350.99%10.33%
Christoph Hellwig890.65%41.32%
Dan Magenheimer870.64%10.33%
Andi Kleen810.59%20.66%
Balbir Singh680.50%20.66%
Lee Schermerhorn530.39%10.33%
Raymond Jennings400.29%10.33%
Johannes Weiner340.25%30.99%
Ingo Molnar300.22%51.64%
Nicholas Piggin280.21%20.66%
Suleiman Souhlal260.19%10.33%
Nitin Gupta260.19%10.33%
David S. Miller250.18%20.66%
Jan Beulich250.18%10.33%
Cyrill V. Gorcunov220.16%10.33%
Weijie Yang190.14%10.33%
Christoph Lameter180.13%20.66%
Krzysztof Kozlowski170.12%20.66%
Geliang Tang160.12%20.66%
Tejun Heo140.10%10.33%
Jann Horn130.10%10.33%
Sasha Levin120.09%10.33%
Xiaotian Feng110.08%10.33%
Andrea Arcangeli110.08%20.66%
Eric Sandeen90.07%10.33%
Jeff Layton80.06%20.66%
Heiko Carstens80.06%10.33%
David Rientjes80.06%20.66%
Vladimir Davydov70.05%20.66%
Seth Jennings60.04%10.33%
Vegard Nossum60.04%20.66%
Alan Jenkins60.04%20.66%
Chris Wilson60.04%10.33%
Jens Axboe60.04%10.33%
William Lee Irwin III40.03%10.33%
Thomas Gleixner40.03%10.33%
Vlastimil Babka40.03%10.33%
Akinobu Mita40.03%10.33%
Jeff Garzik30.02%10.33%
Rik Van Riel30.02%10.33%
Jamie Liu30.02%10.33%
Denis V. Lunev30.02%10.33%
Russell King30.02%10.33%
Arnd Bergmann30.02%10.33%
Suresh Jayaraman30.02%10.33%
Chris Dearman20.01%10.33%
Helge Deller20.01%10.33%
Jason Low10.01%10.33%
Chen Yucong10.01%10.33%
Joe Perches10.01%10.33%
Fernando Luis Vázquez Cao10.01%10.33%
Anderson Briglia10.01%10.33%
Nishanth Aravamudan10.01%10.33%
Miklos Szeredi10.01%10.33%
Adrian Bunk10.01%10.33%
Total13638100.00%304100.00%
Directory: mm
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
Created with cregit.