linux/mm/swap_state.c
Nick Piggin 0ed361dec3 mm: fix PageUptodate data race
After running SetPageUptodate, preceeding stores to the page contents to
actually bring it uptodate may not be ordered with the store to set the
page uptodate.

Therefore, another CPU which checks PageUptodate is true, then reads the
page contents can get stale data.

Fix this by having an smp_wmb before SetPageUptodate, and smp_rmb after
PageUptodate.

Many places that test PageUptodate, do so with the page locked, and this
would be enough to ensure memory ordering in those places if
SetPageUptodate were only called while the page is locked.  Unfortunately
that is not always the case for some filesystems, but it could be an idea
for the future.

Also bring the handling of anonymous page uptodateness in line with that of
file backed page management, by marking anon pages as uptodate when they
_are_ uptodate, rather than when our implementation requires that they be
marked as such.  Doing allows us to get rid of the smp_wmb's in the page
copying functions, which were especially added for anonymous pages for an
analogous memory ordering problem.  Both file and anonymous pages are
handled with the same barriers.

FAQ:
Q. Why not do this in flush_dcache_page?
A. Firstly, flush_dcache_page handles only one side (the smb side) of the
ordering protocol; we'd still need smp_rmb somewhere. Secondly, hiding away
memory barriers in a completely unrelated function is nasty; at least in the
PageUptodate macros, they are located together with (half) the operations
involved in the ordering. Thirdly, the smp_wmb is only required when first
bringing the page uptodate, wheras flush_dcache_page should be called each time
it is written to through the kernel mapping. It is logically the wrong place to
put it.

Q. Why does this increase my text size / reduce my performance / etc.
A. Because it is adding the necessary instructions to eliminate the data-race.

Q. Can it be improved?
A. Yes, eg. if you were to create a rule that all SetPageUptodate operations
run under the page lock, we could avoid the smp_rmb places where PageUptodate
is queried under the page lock. Requires audit of all filesystems and at least
some would need reworking. That's great you're interested, I'm eagerly awaiting
your patches.

Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 09:44:19 -08:00

359 lines
9.7 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/module.h>
#include <linux/mm.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/buffer_head.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
#include <linux/migrate.h>
#include <asm/pgtable.h>
/*
* swapper_space is a fiction, retained to simplify the path through
* vmscan's shrink_page_list, to make sync_page look nicer, and to allow
* future use of radix_tree tags in the swap cache.
*/
static const struct address_space_operations swap_aops = {
.writepage = swap_writepage,
.sync_page = block_sync_page,
.set_page_dirty = __set_page_dirty_nobuffers,
.migratepage = migrate_page,
};
static struct backing_dev_info swap_backing_dev_info = {
.capabilities = BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
.unplug_io_fn = swap_unplug_io_fn,
};
struct address_space swapper_space = {
.page_tree = RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN),
.tree_lock = __RW_LOCK_UNLOCKED(swapper_space.tree_lock),
.a_ops = &swap_aops,
.i_mmap_nonlinear = LIST_HEAD_INIT(swapper_space.i_mmap_nonlinear),
.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;
void show_swap_cache_info(void)
{
printk("Swap cache: 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 = %lukB\n", 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 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, gfp_t gfp_mask)
{
int error;
BUG_ON(!PageLocked(page));
BUG_ON(PageSwapCache(page));
BUG_ON(PagePrivate(page));
error = radix_tree_preload(gfp_mask);
if (!error) {
write_lock_irq(&swapper_space.tree_lock);
error = radix_tree_insert(&swapper_space.page_tree,
entry.val, page);
if (!error) {
page_cache_get(page);
SetPageSwapCache(page);
set_page_private(page, entry.val);
total_swapcache_pages++;
__inc_zone_page_state(page, NR_FILE_PAGES);
INC_CACHE_INFO(add_total);
}
write_unlock_irq(&swapper_space.tree_lock);
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)
{
BUG_ON(!PageLocked(page));
BUG_ON(!PageSwapCache(page));
BUG_ON(PageWriteback(page));
BUG_ON(PagePrivate(page));
radix_tree_delete(&swapper_space.page_tree, page_private(page));
set_page_private(page, 0);
ClearPageSwapCache(page);
total_swapcache_pages--;
__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, gfp_t gfp_mask)
{
swp_entry_t entry;
int err;
BUG_ON(!PageLocked(page));
BUG_ON(!PageUptodate(page));
for (;;) {
entry = get_swap_page();
if (!entry.val)
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_mask|__GFP_NOMEMALLOC|__GFP_NOWARN);
switch (err) {
case 0: /* Success */
SetPageDirty(page);
return 1;
case -EEXIST:
/* Raced with "speculative" read_swap_cache_async */
swap_free(entry);
continue;
default:
/* -ENOMEM radix-tree allocation failure */
swap_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;
entry.val = page_private(page);
write_lock_irq(&swapper_space.tree_lock);
__delete_from_swap_cache(page);
write_unlock_irq(&swapper_space.tree_lock);
swap_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
* exclusive_swap_page() _with_ the lock.
* - Marcelo
*/
static inline void free_swap_cache(struct page *page)
{
if (PageSwapCache(page) && !TestSetPageLocked(page)) {
remove_exclusive_swap_page(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(&swapper_space, 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(&swapper_space, 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 */
}
/*
* Swap entry may have been freed since our caller observed it.
*/
if (!swap_duplicate(entry))
break;
/*
* Associate the page with swap entry in the swap cache.
* May fail (-EEXIST) if there is already a page associated
* with this entry in the swap cache: added by a racing
* read_swap_cache_async, or add_to_swap or shmem_writepage
* re-using the just freed swap entry for an existing page.
* May fail (-ENOMEM) if radix-tree node allocation failed.
*/
SetPageLocked(new_page);
err = add_to_swap_cache(new_page, entry, gfp_mask & GFP_KERNEL);
if (!err) {
/*
* Initiate read into locked page and return.
*/
lru_cache_add_active(new_page);
swap_readpage(NULL, new_page);
return new_page;
}
ClearPageLocked(new_page);
swap_free(entry);
} 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
* @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)
{
int nr_pages;
struct page *page;
unsigned long offset;
unsigned long end_offset;
/*
* Get starting offset for readaround, and number of pages to read.
* Adjust starting address by readbehind (for NUMA interleave case)?
* No, it's very unlikely that swap layout would follow vma layout,
* more likely that neighbouring swap pages came from the same node:
* so use the same "addr" to choose the same node for each swap read.
*/
nr_pages = valid_swaphandles(entry, &offset);
for (end_offset = offset + nr_pages; 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)
break;
page_cache_release(page);
}
lru_add_drain(); /* Push any new pages onto the LRU now */
return read_swap_cache_async(entry, gfp_mask, vma, addr);
}