linux-stable/mm/swap_state.c
Michal Hocko aabfb57296 mm: memcontrol: do not kill uncharge batching in free_pages_and_swap_cache
free_pages_and_swap_cache limits release_pages to PAGEVEC_SIZE chunks.
This is not a big deal for the normal release path but it completely kills
memcg uncharge batching which reduces res_counter spin_lock contention.
Dave has noticed this with his page fault scalability test case on a large
machine when the lock was basically dominating on all CPUs:

    80.18%    80.18%  [kernel]               [k] _raw_spin_lock
                  |
                  --- _raw_spin_lock
                     |
                     |--66.59%-- res_counter_uncharge_until
                     |          res_counter_uncharge
                     |          uncharge_batch
                     |          uncharge_list
                     |          mem_cgroup_uncharge_list
                     |          release_pages
                     |          free_pages_and_swap_cache
                     |          tlb_flush_mmu_free
                     |          |
                     |          |--90.12%-- unmap_single_vma
                     |          |          unmap_vmas
                     |          |          unmap_region
                     |          |          do_munmap
                     |          |          vm_munmap
                     |          |          sys_munmap
                     |          |          system_call_fastpath
                     |          |          __GI___munmap
                     |          |
                     |           --9.88%-- tlb_flush_mmu
                     |                     tlb_finish_mmu
                     |                     unmap_region
                     |                     do_munmap
                     |                     vm_munmap
                     |                     sys_munmap
                     |                     system_call_fastpath
                     |                     __GI___munmap

In his case the load was running in the root memcg and that part has been
handled by reverting 05b8430123 ("mm: memcontrol: use root_mem_cgroup
res_counter") because this is a clear regression, but the problem remains
inside dedicated memcgs.

There is no reason to limit release_pages to PAGEVEC_SIZE batches other
than lru_lock held times.  This logic, however, can be moved inside the
function.  mem_cgroup_uncharge_list and free_hot_cold_page_list do not
hold any lock for the whole pages_to_free list so it is safe to call them
in a single run.

The release_pages() code was previously breaking the lru_lock each
PAGEVEC_SIZE pages (ie, 14 pages).  However this code has no usage of
pagevecs so switch to breaking the lock at least every SWAP_CLUSTER_MAX
(32) pages.  This means that the lock acquisition frequency is
approximately halved and the max hold times are approximately doubled.

The now unneeded batching is removed from free_pages_and_swap_cache().

Also update the grossly out-of-date release_pages documentation.

Signed-off-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: Dave Hansen <dave@sr71.net>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: Greg Thelen <gthelen@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-10-09 22:25:59 -04:00

493 lines
13 KiB
C

/*
* linux/mm/swap_state.c
*
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
* Swap reorganised 29.12.95, Stephen Tweedie
*
* Rewritten to use page cache, (C) 1998 Stephen Tweedie
*/
#include <linux/mm.h>
#include <linux/gfp.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/backing-dev.h>
#include <linux/blkdev.h>
#include <linux/pagevec.h>
#include <linux/migrate.h>
#include <linux/page_cgroup.h>
#include <asm/pgtable.h>
/*
* swapper_space is a fiction, retained to simplify the path through
* vmscan's shrink_page_list.
*/
static const struct address_space_operations swap_aops = {
.writepage = swap_writepage,
.set_page_dirty = swap_set_page_dirty,
#ifdef CONFIG_MIGRATION
.migratepage = migrate_page,
#endif
};
static struct backing_dev_info swap_backing_dev_info = {
.name = "swap",
.capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
};
struct address_space swapper_spaces[MAX_SWAPFILES] = {
[0 ... MAX_SWAPFILES - 1] = {
.page_tree = RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN),
.i_mmap_writable = ATOMIC_INIT(0),
.a_ops = &swap_aops,
.backing_dev_info = &swap_backing_dev_info,
}
};
#define INC_CACHE_INFO(x) do { swap_cache_info.x++; } while (0)
static struct {
unsigned long add_total;
unsigned long del_total;
unsigned long find_success;
unsigned long find_total;
} swap_cache_info;
unsigned long total_swapcache_pages(void)
{
int i;
unsigned long ret = 0;
for (i = 0; i < MAX_SWAPFILES; i++)
ret += swapper_spaces[i].nrpages;
return ret;
}
static atomic_t swapin_readahead_hits = ATOMIC_INIT(4);
void show_swap_cache_info(void)
{
printk("%lu pages in swap cache\n", total_swapcache_pages());
printk("Swap cache stats: add %lu, delete %lu, find %lu/%lu\n",
swap_cache_info.add_total, swap_cache_info.del_total,
swap_cache_info.find_success, swap_cache_info.find_total);
printk("Free swap = %ldkB\n",
get_nr_swap_pages() << (PAGE_SHIFT - 10));
printk("Total swap = %lukB\n", total_swap_pages << (PAGE_SHIFT - 10));
}
/*
* __add_to_swap_cache resembles add_to_page_cache_locked on swapper_space,
* but sets SwapCache flag and private instead of mapping and index.
*/
int __add_to_swap_cache(struct page *page, swp_entry_t entry)
{
int error;
struct address_space *address_space;
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(PageSwapCache(page), page);
VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
page_cache_get(page);
SetPageSwapCache(page);
set_page_private(page, entry.val);
address_space = swap_address_space(entry);
spin_lock_irq(&address_space->tree_lock);
error = radix_tree_insert(&address_space->page_tree,
entry.val, page);
if (likely(!error)) {
address_space->nrpages++;
__inc_zone_page_state(page, NR_FILE_PAGES);
INC_CACHE_INFO(add_total);
}
spin_unlock_irq(&address_space->tree_lock);
if (unlikely(error)) {
/*
* Only the context which have set SWAP_HAS_CACHE flag
* would call add_to_swap_cache().
* So add_to_swap_cache() doesn't returns -EEXIST.
*/
VM_BUG_ON(error == -EEXIST);
set_page_private(page, 0UL);
ClearPageSwapCache(page);
page_cache_release(page);
}
return error;
}
int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask)
{
int error;
error = radix_tree_maybe_preload(gfp_mask);
if (!error) {
error = __add_to_swap_cache(page, entry);
radix_tree_preload_end();
}
return error;
}
/*
* This must be called only on pages that have
* been verified to be in the swap cache.
*/
void __delete_from_swap_cache(struct page *page)
{
swp_entry_t entry;
struct address_space *address_space;
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(!PageSwapCache(page), page);
VM_BUG_ON_PAGE(PageWriteback(page), page);
entry.val = page_private(page);
address_space = swap_address_space(entry);
radix_tree_delete(&address_space->page_tree, page_private(page));
set_page_private(page, 0);
ClearPageSwapCache(page);
address_space->nrpages--;
__dec_zone_page_state(page, NR_FILE_PAGES);
INC_CACHE_INFO(del_total);
}
/**
* add_to_swap - allocate swap space for a page
* @page: page we want to move to swap
*
* Allocate swap space for the page and add the page to the
* swap cache. Caller needs to hold the page lock.
*/
int add_to_swap(struct page *page, struct list_head *list)
{
swp_entry_t entry;
int err;
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(!PageUptodate(page), page);
entry = get_swap_page();
if (!entry.val)
return 0;
if (unlikely(PageTransHuge(page)))
if (unlikely(split_huge_page_to_list(page, list))) {
swapcache_free(entry);
return 0;
}
/*
* Radix-tree node allocations from PF_MEMALLOC contexts could
* completely exhaust the page allocator. __GFP_NOMEMALLOC
* stops emergency reserves from being allocated.
*
* TODO: this could cause a theoretical memory reclaim
* deadlock in the swap out path.
*/
/*
* Add it to the swap cache and mark it dirty
*/
err = add_to_swap_cache(page, entry,
__GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN);
if (!err) { /* Success */
SetPageDirty(page);
return 1;
} else { /* -ENOMEM radix-tree allocation failure */
/*
* add_to_swap_cache() doesn't return -EEXIST, so we can safely
* clear SWAP_HAS_CACHE flag.
*/
swapcache_free(entry);
return 0;
}
}
/*
* This must be called only on pages that have
* been verified to be in the swap cache and locked.
* It will never put the page into the free list,
* the caller has a reference on the page.
*/
void delete_from_swap_cache(struct page *page)
{
swp_entry_t entry;
struct address_space *address_space;
entry.val = page_private(page);
address_space = swap_address_space(entry);
spin_lock_irq(&address_space->tree_lock);
__delete_from_swap_cache(page);
spin_unlock_irq(&address_space->tree_lock);
swapcache_free(entry);
page_cache_release(page);
}
/*
* If we are the only user, then try to free up the swap cache.
*
* Its ok to check for PageSwapCache without the page lock
* here because we are going to recheck again inside
* try_to_free_swap() _with_ the lock.
* - Marcelo
*/
static inline void free_swap_cache(struct page *page)
{
if (PageSwapCache(page) && !page_mapped(page) && trylock_page(page)) {
try_to_free_swap(page);
unlock_page(page);
}
}
/*
* Perform a free_page(), also freeing any swap cache associated with
* this page if it is the last user of the page.
*/
void free_page_and_swap_cache(struct page *page)
{
free_swap_cache(page);
page_cache_release(page);
}
/*
* Passed an array of pages, drop them all from swapcache and then release
* them. They are removed from the LRU and freed if this is their last use.
*/
void free_pages_and_swap_cache(struct page **pages, int nr)
{
struct page **pagep = pages;
int i;
lru_add_drain();
for (i = 0; i < nr; i++)
free_swap_cache(pagep[i]);
release_pages(pagep, nr, false);
}
/*
* Lookup a swap entry in the swap cache. A found page will be returned
* unlocked and with its refcount incremented - we rely on the kernel
* lock getting page table operations atomic even if we drop the page
* lock before returning.
*/
struct page * lookup_swap_cache(swp_entry_t entry)
{
struct page *page;
page = find_get_page(swap_address_space(entry), entry.val);
if (page) {
INC_CACHE_INFO(find_success);
if (TestClearPageReadahead(page))
atomic_inc(&swapin_readahead_hits);
}
INC_CACHE_INFO(find_total);
return page;
}
/*
* Locate a page of swap in physical memory, reserving swap cache space
* and reading the disk if it is not already cached.
* A failure return means that either the page allocation failed or that
* the swap entry is no longer in use.
*/
struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
struct vm_area_struct *vma, unsigned long addr)
{
struct page *found_page, *new_page = NULL;
int err;
do {
/*
* First check the swap cache. Since this is normally
* called after lookup_swap_cache() failed, re-calling
* that would confuse statistics.
*/
found_page = find_get_page(swap_address_space(entry),
entry.val);
if (found_page)
break;
/*
* Get a new page to read into from swap.
*/
if (!new_page) {
new_page = alloc_page_vma(gfp_mask, vma, addr);
if (!new_page)
break; /* Out of memory */
}
/*
* call radix_tree_preload() while we can wait.
*/
err = radix_tree_maybe_preload(gfp_mask & GFP_KERNEL);
if (err)
break;
/*
* Swap entry may have been freed since our caller observed it.
*/
err = swapcache_prepare(entry);
if (err == -EEXIST) {
radix_tree_preload_end();
/*
* We might race against get_swap_page() and stumble
* across a SWAP_HAS_CACHE swap_map entry whose page
* has not been brought into the swapcache yet, while
* the other end is scheduled away waiting on discard
* I/O completion at scan_swap_map().
*
* In order to avoid turning this transitory state
* into a permanent loop around this -EEXIST case
* if !CONFIG_PREEMPT and the I/O completion happens
* to be waiting on the CPU waitqueue where we are now
* busy looping, we just conditionally invoke the
* scheduler here, if there are some more important
* tasks to run.
*/
cond_resched();
continue;
}
if (err) { /* swp entry is obsolete ? */
radix_tree_preload_end();
break;
}
/* May fail (-ENOMEM) if radix-tree node allocation failed. */
__set_page_locked(new_page);
SetPageSwapBacked(new_page);
err = __add_to_swap_cache(new_page, entry);
if (likely(!err)) {
radix_tree_preload_end();
/*
* Initiate read into locked page and return.
*/
lru_cache_add_anon(new_page);
swap_readpage(new_page);
return new_page;
}
radix_tree_preload_end();
ClearPageSwapBacked(new_page);
__clear_page_locked(new_page);
/*
* add_to_swap_cache() doesn't return -EEXIST, so we can safely
* clear SWAP_HAS_CACHE flag.
*/
swapcache_free(entry);
} while (err != -ENOMEM);
if (new_page)
page_cache_release(new_page);
return found_page;
}
static unsigned long swapin_nr_pages(unsigned long offset)
{
static unsigned long prev_offset;
unsigned int pages, max_pages, last_ra;
static atomic_t last_readahead_pages;
max_pages = 1 << ACCESS_ONCE(page_cluster);
if (max_pages <= 1)
return 1;
/*
* This heuristic has been found to work well on both sequential and
* random loads, swapping to hard disk or to SSD: please don't ask
* what the "+ 2" means, it just happens to work well, that's all.
*/
pages = atomic_xchg(&swapin_readahead_hits, 0) + 2;
if (pages == 2) {
/*
* We can have no readahead hits to judge by: but must not get
* stuck here forever, so check for an adjacent offset instead
* (and don't even bother to check whether swap type is same).
*/
if (offset != prev_offset + 1 && offset != prev_offset - 1)
pages = 1;
prev_offset = offset;
} else {
unsigned int roundup = 4;
while (roundup < pages)
roundup <<= 1;
pages = roundup;
}
if (pages > max_pages)
pages = max_pages;
/* Don't shrink readahead too fast */
last_ra = atomic_read(&last_readahead_pages) / 2;
if (pages < last_ra)
pages = last_ra;
atomic_set(&last_readahead_pages, pages);
return pages;
}
/**
* swapin_readahead - swap in pages in hope we need them soon
* @entry: swap entry of this memory
* @gfp_mask: memory allocation flags
* @vma: user vma this address belongs to
* @addr: target address for mempolicy
*
* Returns the struct page for entry and addr, after queueing swapin.
*
* Primitive swap readahead code. We simply read an aligned block of
* (1 << page_cluster) entries in the swap area. This method is chosen
* because it doesn't cost us any seek time. We also make sure to queue
* the 'original' request together with the readahead ones...
*
* This has been extended to use the NUMA policies from the mm triggering
* the readahead.
*
* Caller must hold down_read on the vma->vm_mm if vma is not NULL.
*/
struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask,
struct vm_area_struct *vma, unsigned long addr)
{
struct page *page;
unsigned long entry_offset = swp_offset(entry);
unsigned long offset = entry_offset;
unsigned long start_offset, end_offset;
unsigned long mask;
struct blk_plug plug;
mask = swapin_nr_pages(offset) - 1;
if (!mask)
goto skip;
/* Read a page_cluster sized and aligned cluster around offset. */
start_offset = offset & ~mask;
end_offset = offset | mask;
if (!start_offset) /* First page is swap header. */
start_offset++;
blk_start_plug(&plug);
for (offset = start_offset; offset <= end_offset ; offset++) {
/* Ok, do the async read-ahead now */
page = read_swap_cache_async(swp_entry(swp_type(entry), offset),
gfp_mask, vma, addr);
if (!page)
continue;
if (offset != entry_offset)
SetPageReadahead(page);
page_cache_release(page);
}
blk_finish_plug(&plug);
lru_add_drain(); /* Push any new pages onto the LRU now */
skip:
return read_swap_cache_async(entry, gfp_mask, vma, addr);
}