mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-21 08:19:28 +00:00
![Shaohua Li](/assets/img/avatar_default.png)
swap_lock is heavily contended when I test swap to 3 fast SSD (even slightly slower than swap to 2 such SSD). The main contention comes from swap_info_get(). This patch tries to fix the gap with adding a new per-partition lock. Global data like nr_swapfiles, total_swap_pages, least_priority and swap_list are still protected by swap_lock. nr_swap_pages is an atomic now, it can be changed without swap_lock. In theory, it's possible get_swap_page() finds no swap pages but actually there are free swap pages. But sounds not a big problem. Accessing partition specific data (like scan_swap_map and so on) is only protected by swap_info_struct.lock. Changing swap_info_struct.flags need hold swap_lock and swap_info_struct.lock, because scan_scan_map() will check it. read the flags is ok with either the locks hold. If both swap_lock and swap_info_struct.lock must be hold, we always hold the former first to avoid deadlock. swap_entry_free() can change swap_list. To delete that code, we add a new highest_priority_index. Whenever get_swap_page() is called, we check it. If it's valid, we use it. It's a pity get_swap_page() still holds swap_lock(). But in practice, swap_lock() isn't heavily contended in my test with this patch (or I can say there are other much more heavier bottlenecks like TLB flush). And BTW, looks get_swap_page() doesn't really need the lock. We never free swap_info[] and we check SWAP_WRITEOK flag. The only risk without the lock is we could swapout to some low priority swap, but we can quickly recover after several rounds of swap, so sounds not a big deal to me. But I'd prefer to fix this if it's a real problem. "swap: make each swap partition have one address_space" improved the swapout speed from 1.7G/s to 2G/s. This patch further improves the speed to 2.3G/s, so around 15% improvement. It's a multi-process test, so TLB flush isn't the biggest bottleneck before the patches. [arnd@arndb.de: fix it for nommu] [hughd@google.com: add missing unlock] [minchan@kernel.org: get rid of lockdep whinge on sys_swapon] Signed-off-by: Shaohua Li <shli@fusionio.com> Cc: Hugh Dickins <hughd@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Seth Jennings <sjenning@linux.vnet.ibm.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Hugh Dickins <hughd@google.com> Signed-off-by: Minchan Kim <minchan@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
423 lines
11 KiB
C
423 lines
11 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,
|
|
.migratepage = migrate_page,
|
|
};
|
|
|
|
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),
|
|
.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;
|
|
}
|
|
|
|
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.
|
|
*/
|
|
static int __add_to_swap_cache(struct page *page, swp_entry_t entry)
|
|
{
|
|
int error;
|
|
struct address_space *address_space;
|
|
|
|
VM_BUG_ON(!PageLocked(page));
|
|
VM_BUG_ON(PageSwapCache(page));
|
|
VM_BUG_ON(!PageSwapBacked(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_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(!PageLocked(page));
|
|
VM_BUG_ON(!PageSwapCache(page));
|
|
VM_BUG_ON(PageWriteback(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)
|
|
{
|
|
swp_entry_t entry;
|
|
int err;
|
|
|
|
VM_BUG_ON(!PageLocked(page));
|
|
VM_BUG_ON(!PageUptodate(page));
|
|
|
|
entry = get_swap_page();
|
|
if (!entry.val)
|
|
return 0;
|
|
|
|
if (unlikely(PageTransHuge(page)))
|
|
if (unlikely(split_huge_page(page))) {
|
|
swapcache_free(entry, NULL);
|
|
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, NULL);
|
|
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);
|
|
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;
|
|
|
|
lru_add_drain();
|
|
while (nr) {
|
|
int todo = min(nr, PAGEVEC_SIZE);
|
|
int i;
|
|
|
|
for (i = 0; i < todo; i++)
|
|
free_swap_cache(pagep[i]);
|
|
release_pages(pagep, todo, 0);
|
|
pagep += todo;
|
|
nr -= todo;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* 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);
|
|
|
|
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_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) { /* seems racy */
|
|
radix_tree_preload_end();
|
|
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, NULL);
|
|
} while (err != -ENOMEM);
|
|
|
|
if (new_page)
|
|
page_cache_release(new_page);
|
|
return found_page;
|
|
}
|
|
|
|
/**
|
|
* 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 offset = swp_offset(entry);
|
|
unsigned long start_offset, end_offset;
|
|
unsigned long mask = (1UL << page_cluster) - 1;
|
|
struct blk_plug plug;
|
|
|
|
/* 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;
|
|
page_cache_release(page);
|
|
}
|
|
blk_finish_plug(&plug);
|
|
|
|
lru_add_drain(); /* Push any new pages onto the LRU now */
|
|
return read_swap_cache_async(entry, gfp_mask, vma, addr);
|
|
}
|