mm/swap: free swap slots in batch

Add new functions that free unused swap slots in batches without the
need to reacquire swap info lock.  This improves scalability and reduce
lock contention.

Link: http://lkml.kernel.org/r/c25e0fcdfd237ec4ca7db91631d3b9f6ed23824e.1484082593.git.tim.c.chen@linux.intel.com
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Cc: Aaron Lu <aaron.lu@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net> escreveu:
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Tim Chen 2017-02-22 15:45:36 -08:00 committed by Linus Torvalds
parent 36005bae20
commit 7c00bafee8
2 changed files with 98 additions and 64 deletions

View File

@ -394,6 +394,7 @@ extern int swap_duplicate(swp_entry_t);
extern int swapcache_prepare(swp_entry_t); extern int swapcache_prepare(swp_entry_t);
extern void swap_free(swp_entry_t); extern void swap_free(swp_entry_t);
extern void swapcache_free(swp_entry_t); extern void swapcache_free(swp_entry_t);
extern void swapcache_free_entries(swp_entry_t *entries, int n);
extern int free_swap_and_cache(swp_entry_t); extern int free_swap_and_cache(swp_entry_t);
extern int swap_type_of(dev_t, sector_t, struct block_device **); extern int swap_type_of(dev_t, sector_t, struct block_device **);
extern unsigned int count_swap_pages(int, int); extern unsigned int count_swap_pages(int, int);

View File

@ -942,35 +942,34 @@ static struct swap_info_struct *swap_info_get(swp_entry_t entry)
return p; return p;
} }
static unsigned char swap_entry_free(struct swap_info_struct *p, static struct swap_info_struct *swap_info_get_cont(swp_entry_t entry,
swp_entry_t entry, unsigned char usage, struct swap_info_struct *q)
bool swap_info_locked) {
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;
}
static unsigned char __swap_entry_free(struct swap_info_struct *p,
swp_entry_t entry, unsigned char usage)
{ {
struct swap_cluster_info *ci; struct swap_cluster_info *ci;
unsigned long offset = swp_offset(entry); unsigned long offset = swp_offset(entry);
unsigned char count; unsigned char count;
unsigned char has_cache; unsigned char has_cache;
bool lock_swap_info = false;
if (!swap_info_locked) { ci = lock_cluster_or_swap_info(p, offset);
count = p->swap_map[offset];
if (!p->cluster_info || count == usage || count == SWAP_MAP_SHMEM) {
lock_swap_info:
swap_info_locked = true;
lock_swap_info = true;
spin_lock(&p->lock);
}
}
ci = lock_cluster(p, offset);
count = p->swap_map[offset]; count = p->swap_map[offset];
if (!swap_info_locked && (count == usage || count == SWAP_MAP_SHMEM)) {
unlock_cluster(ci);
goto lock_swap_info;
}
has_cache = count & SWAP_HAS_CACHE; has_cache = count & SWAP_HAS_CACHE;
count &= ~SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE;
@ -994,48 +993,54 @@ lock_swap_info:
} }
usage = count | has_cache; usage = count | has_cache;
p->swap_map[offset] = usage; p->swap_map[offset] = usage ? : SWAP_HAS_CACHE;
unlock_cluster(ci); unlock_cluster_or_swap_info(p, ci);
/* free if no reference */
if (!usage) {
VM_BUG_ON(!swap_info_locked);
mem_cgroup_uncharge_swap(entry);
ci = lock_cluster(p, offset);
dec_cluster_info_page(p, p->cluster_info, offset);
unlock_cluster(ci);
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);
}
}
if (lock_swap_info)
spin_unlock(&p->lock);
return usage; return usage;
} }
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);
}
}
/* /*
* Caller has made sure that the swap device corresponding to entry * Caller has made sure that the swap device corresponding to entry
* is still around or has not been recycled. * is still around or has not been recycled.
@ -1045,8 +1050,10 @@ void swap_free(swp_entry_t entry)
struct swap_info_struct *p; struct swap_info_struct *p;
p = _swap_info_get(entry); p = _swap_info_get(entry);
if (p) if (p) {
swap_entry_free(p, entry, 1, false); if (!__swap_entry_free(p, entry, 1))
swapcache_free_entries(&entry, 1);
}
} }
/* /*
@ -1057,8 +1064,32 @@ void swapcache_free(swp_entry_t entry)
struct swap_info_struct *p; struct swap_info_struct *p;
p = _swap_info_get(entry); p = _swap_info_get(entry);
if (p) {
if (!__swap_entry_free(p, entry, SWAP_HAS_CACHE))
swapcache_free_entries(&entry, 1);
}
}
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) if (p)
swap_entry_free(p, entry, SWAP_HAS_CACHE, false); spin_unlock(&p->lock);
} }
/* /*
@ -1241,21 +1272,23 @@ int free_swap_and_cache(swp_entry_t entry)
{ {
struct swap_info_struct *p; struct swap_info_struct *p;
struct page *page = NULL; struct page *page = NULL;
unsigned char count;
if (non_swap_entry(entry)) if (non_swap_entry(entry))
return 1; return 1;
p = swap_info_get(entry); p = _swap_info_get(entry);
if (p) { if (p) {
if (swap_entry_free(p, entry, 1, true) == SWAP_HAS_CACHE) { count = __swap_entry_free(p, entry, 1);
if (count == SWAP_HAS_CACHE) {
page = find_get_page(swap_address_space(entry), page = find_get_page(swap_address_space(entry),
swp_offset(entry)); swp_offset(entry));
if (page && !trylock_page(page)) { if (page && !trylock_page(page)) {
put_page(page); put_page(page);
page = NULL; page = NULL;
} }
} } else if (!count)
spin_unlock(&p->lock); swapcache_free_entries(&entry, 1);
} }
if (page) { if (page) {
/* /*