linux-hardened/mm/swap_state.c
Huang Ying 9c1cc2e4f2 mm, swap: fix comment in __read_swap_cache_async
Commit cbab0e4eec ("swap: avoid read_swap_cache_async() race to
deadlock while waiting on discard I/O completion") fixed a deadlock in
read_swap_cache_async().  Because at that time, in swap allocation path,
a swap entry may be set as SWAP_HAS_CACHE, then wait for discarding to
complete before the page for the swap entry is added to the swap cache.

But in commit 815c2c543d ("swap: make swap discard async"), the
discarding for swap become asynchronous, waiting for discarding to
complete will be done before the swap entry is set as SWAP_HAS_CACHE.
So the comments in code is incorrect now.  This patch fixes the
comments.

The cond_resched() added in the commit cbab0e4eec is not necessary now
too.  But if we added some sleep in swap allocation path in the future,
there may be some hard to debug/reproduce deadlock bug.  So it is kept.

Link: http://lkml.kernel.org/r/20170317064635.12792-1-ying.huang@intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Acked-by: Rafael Aquini <aquini@redhat.com>
Cc: Shaohua Li <shli@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-05-03 15:52:10 -07:00

553 lines
14 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/vmalloc.h>
#include <linux/swap_slots.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
};
struct address_space *swapper_spaces[MAX_SWAPFILES];
static unsigned int nr_swapper_spaces[MAX_SWAPFILES];
#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)
{
unsigned int i, j, nr;
unsigned long ret = 0;
struct address_space *spaces;
rcu_read_lock();
for (i = 0; i < MAX_SWAPFILES; i++) {
/*
* The corresponding entries in nr_swapper_spaces and
* swapper_spaces will be reused only after at least
* one grace period. So it is impossible for them
* belongs to different usage.
*/
nr = nr_swapper_spaces[i];
spaces = rcu_dereference(swapper_spaces[i]);
if (!nr || !spaces)
continue;
for (j = 0; j < nr; j++)
ret += spaces[j].nrpages;
}
rcu_read_unlock();
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);
get_page(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,
swp_offset(entry), page);
if (likely(!error)) {
address_space->nrpages++;
__inc_node_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);
put_page(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, swp_offset(entry));
set_page_private(page, 0);
ClearPageSwapCache(page);
address_space->nrpages--;
__dec_node_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 (mem_cgroup_try_charge_swap(page, entry)) {
swapcache_free(entry);
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.
*/
err = add_to_swap_cache(page, entry,
__GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN);
if (!err) {
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);
put_page(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);
if (!is_huge_zero_page(page))
put_page(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), swp_offset(entry));
if (page) {
INC_CACHE_INFO(find_success);
if (TestClearPageReadahead(page))
atomic_inc(&swapin_readahead_hits);
}
INC_CACHE_INFO(find_total);
return page;
}
struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
struct vm_area_struct *vma, unsigned long addr,
bool *new_page_allocated)
{
struct page *found_page, *new_page = NULL;
struct address_space *swapper_space = swap_address_space(entry);
int err;
*new_page_allocated = false;
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, swp_offset(entry));
if (found_page)
break;
/*
* Just skip read ahead for unused swap slot.
* During swap_off when swap_slot_cache is disabled,
* we have to handle the race between putting
* swap entry in swap cache and marking swap slot
* as SWAP_HAS_CACHE. That's done in later part of code or
* else swap_off will be aborted if we return NULL.
*/
if (!__swp_swapcount(entry) && swap_slot_cache_enabled)
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.
*/
cond_resched();
continue;
}
if (err) { /* swp entry is obsolete ? */
radix_tree_preload_end();
break;
}
/* May fail (-ENOMEM) if radix-tree node allocation failed. */
__SetPageLocked(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);
*new_page_allocated = true;
return new_page;
}
radix_tree_preload_end();
__ClearPageLocked(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)
put_page(new_page);
return found_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)
{
bool page_was_allocated;
struct page *retpage = __read_swap_cache_async(entry, gfp_mask,
vma, addr, &page_was_allocated);
if (page_was_allocated)
swap_readpage(retpage);
return retpage;
}
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 << READ_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);
put_page(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);
}
int init_swap_address_space(unsigned int type, unsigned long nr_pages)
{
struct address_space *spaces, *space;
unsigned int i, nr;
nr = DIV_ROUND_UP(nr_pages, SWAP_ADDRESS_SPACE_PAGES);
spaces = vzalloc(sizeof(struct address_space) * nr);
if (!spaces)
return -ENOMEM;
for (i = 0; i < nr; i++) {
space = spaces + i;
INIT_RADIX_TREE(&space->page_tree, GFP_ATOMIC|__GFP_NOWARN);
atomic_set(&space->i_mmap_writable, 0);
space->a_ops = &swap_aops;
/* swap cache doesn't use writeback related tags */
mapping_set_no_writeback_tags(space);
spin_lock_init(&space->tree_lock);
}
nr_swapper_spaces[type] = nr;
rcu_assign_pointer(swapper_spaces[type], spaces);
return 0;
}
void exit_swap_address_space(unsigned int type)
{
struct address_space *spaces;
spaces = swapper_spaces[type];
nr_swapper_spaces[type] = 0;
rcu_assign_pointer(swapper_spaces[type], NULL);
synchronize_rcu();
kvfree(spaces);
}