android_kernel_motorola_sm6225/mm/swapfile.c

2217 lines
55 KiB
C
Raw Normal View History

/*
* linux/mm/swapfile.c
*
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
* Swap reorganised 29.12.95, Stephen Tweedie
*/
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/mman.h>
#include <linux/slab.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/vmalloc.h>
#include <linux/pagemap.h>
#include <linux/namei.h>
#include <linux/shm.h>
#include <linux/blkdev.h>
#include <linux/random.h>
#include <linux/writeback.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/rmap.h>
#include <linux/security.h>
#include <linux/backing-dev.h>
#include <linux/mutex.h>
#include <linux/capability.h>
#include <linux/syscalls.h>
Memory controller: memory accounting Add the accounting hooks. The accounting is carried out for RSS and Page Cache (unmapped) pages. There is now a common limit and accounting for both. The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap() time. Page cache is accounted at add_to_page_cache(), __delete_from_page_cache(). Swap cache is also accounted for. Each page's page_cgroup is protected with the last bit of the page_cgroup pointer, this makes handling of race conditions involving simultaneous mappings of a page easier. A reference count is kept in the page_cgroup to deal with cases where a page might be unmapped from the RSS of all tasks, but still lives in the page cache. Credits go to Vaidyanathan Srinivasan for helping with reference counting work of the page cgroup. Almost all of the page cache accounting code has help from Vaidyanathan Srinivasan. [hugh@veritas.com: fix swapoff breakage] [akpm@linux-foundation.org: fix locking] Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: <Valdis.Kletnieks@vt.edu> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 09:13:53 +01:00
#include <linux/memcontrol.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <linux/swapops.h>
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 03:07:58 +01:00
#include <linux/page_cgroup.h>
static DEFINE_SPINLOCK(swap_lock);
static unsigned int nr_swapfiles;
long nr_swap_pages;
long total_swap_pages;
static int swap_overflow;
static int least_priority;
static const char Bad_file[] = "Bad swap file entry ";
static const char Unused_file[] = "Unused swap file entry ";
static const char Bad_offset[] = "Bad swap offset entry ";
static const char Unused_offset[] = "Unused swap offset entry ";
static struct swap_list_t swap_list = {-1, -1};
static struct swap_info_struct swap_info[MAX_SWAPFILES];
static DEFINE_MUTEX(swapon_mutex);
/* For reference count accounting in swap_map */
/* enum for swap_map[] handling. internal use only */
enum {
SWAP_MAP = 0, /* ops for reference from swap users */
SWAP_CACHE, /* ops for reference from swap cache */
};
static inline int swap_count(unsigned short ent)
{
return ent & SWAP_COUNT_MASK;
}
static inline bool swap_has_cache(unsigned short ent)
{
return !!(ent & SWAP_HAS_CACHE);
}
static inline unsigned short encode_swapmap(int count, bool has_cache)
{
unsigned short ret = count;
if (has_cache)
return SWAP_HAS_CACHE | ret;
return ret;
}
/* returnes 1 if swap entry is freed */
static int
__try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset)
{
int type = si - swap_info;
swp_entry_t entry = swp_entry(type, offset);
struct page *page;
int ret = 0;
page = find_get_page(&swapper_space, entry.val);
if (!page)
return 0;
/*
* This function is called from scan_swap_map() and it's called
* by vmscan.c at reclaiming pages. So, we hold a lock on a page, here.
* We have to use trylock for avoiding deadlock. This is a special
* case and you should use try_to_free_swap() with explicit lock_page()
* in usual operations.
*/
if (trylock_page(page)) {
ret = try_to_free_swap(page);
unlock_page(page);
}
page_cache_release(page);
return ret;
}
/*
* We need this because the bdev->unplug_fn can sleep and we cannot
* hold swap_lock while calling the unplug_fn. And swap_lock
* cannot be turned into a mutex.
*/
static DECLARE_RWSEM(swap_unplug_sem);
void swap_unplug_io_fn(struct backing_dev_info *unused_bdi, struct page *page)
{
swp_entry_t entry;
down_read(&swap_unplug_sem);
[PATCH] mm: split page table lock Christoph Lameter demonstrated very poor scalability on the SGI 512-way, with a many-threaded application which concurrently initializes different parts of a large anonymous area. This patch corrects that, by using a separate spinlock per page table page, to guard the page table entries in that page, instead of using the mm's single page_table_lock. (But even then, page_table_lock is still used to guard page table allocation, and anon_vma allocation.) In this implementation, the spinlock is tucked inside the struct page of the page table page: with a BUILD_BUG_ON in case it overflows - which it would in the case of 32-bit PA-RISC with spinlock debugging enabled. Splitting the lock is not quite for free: another cacheline access. Ideally, I suppose we would use split ptlock only for multi-threaded processes on multi-cpu machines; but deciding that dynamically would have its own costs. So for now enable it by config, at some number of cpus - since the Kconfig language doesn't support inequalities, let preprocessor compare that with NR_CPUS. But I don't think it's worth being user-configurable: for good testing of both split and unsplit configs, split now at 4 cpus, and perhaps change that to 8 later. There is a benefit even for singly threaded processes: kswapd can be attacking one part of the mm while another part is busy faulting. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 02:16:40 +01:00
entry.val = page_private(page);
if (PageSwapCache(page)) {
struct block_device *bdev = swap_info[swp_type(entry)].bdev;
struct backing_dev_info *bdi;
/*
* If the page is removed from swapcache from under us (with a
* racy try_to_unuse/swapoff) we need an additional reference
[PATCH] mm: split page table lock Christoph Lameter demonstrated very poor scalability on the SGI 512-way, with a many-threaded application which concurrently initializes different parts of a large anonymous area. This patch corrects that, by using a separate spinlock per page table page, to guard the page table entries in that page, instead of using the mm's single page_table_lock. (But even then, page_table_lock is still used to guard page table allocation, and anon_vma allocation.) In this implementation, the spinlock is tucked inside the struct page of the page table page: with a BUILD_BUG_ON in case it overflows - which it would in the case of 32-bit PA-RISC with spinlock debugging enabled. Splitting the lock is not quite for free: another cacheline access. Ideally, I suppose we would use split ptlock only for multi-threaded processes on multi-cpu machines; but deciding that dynamically would have its own costs. So for now enable it by config, at some number of cpus - since the Kconfig language doesn't support inequalities, let preprocessor compare that with NR_CPUS. But I don't think it's worth being user-configurable: for good testing of both split and unsplit configs, split now at 4 cpus, and perhaps change that to 8 later. There is a benefit even for singly threaded processes: kswapd can be attacking one part of the mm while another part is busy faulting. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 02:16:40 +01:00
* count to avoid reading garbage from page_private(page) above.
* If the WARN_ON triggers during a swapoff it maybe the race
* condition and it's harmless. However if it triggers without
* swapoff it signals a problem.
*/
WARN_ON(page_count(page) <= 1);
bdi = bdev->bd_inode->i_mapping->backing_dev_info;
blk_run_backing_dev(bdi, page);
}
up_read(&swap_unplug_sem);
}
/*
* swapon tell device that all the old swap contents can be discarded,
* to allow the swap device to optimize its wear-levelling.
*/
static int discard_swap(struct swap_info_struct *si)
{
struct swap_extent *se;
int err = 0;
list_for_each_entry(se, &si->extent_list, list) {
sector_t start_block = se->start_block << (PAGE_SHIFT - 9);
sector_t nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9);
if (se->start_page == 0) {
/* Do not discard the swap header page! */
start_block += 1 << (PAGE_SHIFT - 9);
nr_blocks -= 1 << (PAGE_SHIFT - 9);
if (!nr_blocks)
continue;
}
err = blkdev_issue_discard(si->bdev, start_block,
nr_blocks, GFP_KERNEL);
if (err)
break;
cond_resched();
}
return err; /* That will often be -EOPNOTSUPP */
}
/*
* swap allocation tell device that a cluster of swap can now be discarded,
* to allow the swap device to optimize its wear-levelling.
*/
static void discard_swap_cluster(struct swap_info_struct *si,
pgoff_t start_page, pgoff_t nr_pages)
{
struct swap_extent *se = si->curr_swap_extent;
int found_extent = 0;
while (nr_pages) {
struct list_head *lh;
if (se->start_page <= start_page &&
start_page < se->start_page + se->nr_pages) {
pgoff_t offset = start_page - se->start_page;
sector_t start_block = se->start_block + offset;
sector_t nr_blocks = se->nr_pages - offset;
if (nr_blocks > nr_pages)
nr_blocks = nr_pages;
start_page += nr_blocks;
nr_pages -= nr_blocks;
if (!found_extent++)
si->curr_swap_extent = se;
start_block <<= PAGE_SHIFT - 9;
nr_blocks <<= PAGE_SHIFT - 9;
if (blkdev_issue_discard(si->bdev, start_block,
nr_blocks, GFP_NOIO))
break;
}
lh = se->list.next;
if (lh == &si->extent_list)
lh = lh->next;
se = list_entry(lh, struct swap_extent, list);
}
}
static int wait_for_discard(void *word)
{
schedule();
return 0;
}
#define SWAPFILE_CLUSTER 256
#define LATENCY_LIMIT 256
static inline unsigned long scan_swap_map(struct swap_info_struct *si,
int cache)
{
unsigned long offset;
unsigned long scan_base;
unsigned long last_in_cluster = 0;
int latency_ration = LATENCY_LIMIT;
int found_free_cluster = 0;
/*
* We try to cluster swap pages by allocating them sequentially
* in swap. Once we've allocated SWAPFILE_CLUSTER pages this
* way, however, we resort to first-free allocation, starting
* a new cluster. This prevents us from scattering swap pages
* all over the entire swap partition, so that we reduce
* overall disk seek times between swap pages. -- sct
* But we do now try to find an empty cluster. -Andrea
* And we let swap pages go all over an SSD partition. Hugh
*/
si->flags += SWP_SCANNING;
scan_base = offset = si->cluster_next;
if (unlikely(!si->cluster_nr--)) {
if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) {
si->cluster_nr = SWAPFILE_CLUSTER - 1;
goto checks;
}
if (si->flags & SWP_DISCARDABLE) {
/*
* Start range check on racing allocations, in case
* they overlap the cluster we eventually decide on
* (we scan without swap_lock to allow preemption).
* It's hardly conceivable that cluster_nr could be
* wrapped during our scan, but don't depend on it.
*/
if (si->lowest_alloc)
goto checks;
si->lowest_alloc = si->max;
si->highest_alloc = 0;
}
spin_unlock(&swap_lock);
/*
* If seek is expensive, start searching for new cluster from
* start of partition, to minimize the span of allocated swap.
* But if seek is cheap, search from our current position, so
* that swap is allocated from all over the partition: if the
* Flash Translation Layer only remaps within limited zones,
* we don't want to wear out the first zone too quickly.
*/
if (!(si->flags & SWP_SOLIDSTATE))
scan_base = offset = si->lowest_bit;
last_in_cluster = offset + SWAPFILE_CLUSTER - 1;
/* Locate the first empty (unaligned) cluster */
for (; last_in_cluster <= si->highest_bit; offset++) {
if (si->swap_map[offset])
last_in_cluster = offset + SWAPFILE_CLUSTER;
else if (offset == last_in_cluster) {
spin_lock(&swap_lock);
offset -= SWAPFILE_CLUSTER - 1;
si->cluster_next = offset;
si->cluster_nr = SWAPFILE_CLUSTER - 1;
found_free_cluster = 1;
goto checks;
}
if (unlikely(--latency_ration < 0)) {
cond_resched();
latency_ration = LATENCY_LIMIT;
}
}
offset = si->lowest_bit;
last_in_cluster = offset + SWAPFILE_CLUSTER - 1;
/* Locate the first empty (unaligned) cluster */
for (; last_in_cluster < scan_base; offset++) {
if (si->swap_map[offset])
last_in_cluster = offset + SWAPFILE_CLUSTER;
else if (offset == last_in_cluster) {
spin_lock(&swap_lock);
offset -= SWAPFILE_CLUSTER - 1;
si->cluster_next = offset;
si->cluster_nr = SWAPFILE_CLUSTER - 1;
found_free_cluster = 1;
goto checks;
}
if (unlikely(--latency_ration < 0)) {
cond_resched();
latency_ration = LATENCY_LIMIT;
}
}
offset = scan_base;
spin_lock(&swap_lock);
si->cluster_nr = SWAPFILE_CLUSTER - 1;
si->lowest_alloc = 0;
}
checks:
if (!(si->flags & SWP_WRITEOK))
goto no_page;
if (!si->highest_bit)
goto no_page;
if (offset > si->highest_bit)
scan_base = offset = si->lowest_bit;
/* reuse swap entry of cache-only swap if not busy. */
if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) {
int swap_was_freed;
spin_unlock(&swap_lock);
swap_was_freed = __try_to_reclaim_swap(si, offset);
spin_lock(&swap_lock);
/* entry was freed successfully, try to use this again */
if (swap_was_freed)
goto checks;
goto scan; /* check next one */
}
if (si->swap_map[offset])
goto scan;
if (offset == si->lowest_bit)
si->lowest_bit++;
if (offset == si->highest_bit)
si->highest_bit--;
si->inuse_pages++;
if (si->inuse_pages == si->pages) {
si->lowest_bit = si->max;
si->highest_bit = 0;
}
if (cache == SWAP_CACHE) /* at usual swap-out via vmscan.c */
si->swap_map[offset] = encode_swapmap(0, true);
else /* at suspend */
si->swap_map[offset] = encode_swapmap(1, false);
si->cluster_next = offset + 1;
si->flags -= SWP_SCANNING;
if (si->lowest_alloc) {
/*
* Only set when SWP_DISCARDABLE, and there's a scan
* for a free cluster in progress or just completed.
*/
if (found_free_cluster) {
/*
* To optimize wear-levelling, discard the
* old data of the cluster, taking care not to
* discard any of its pages that have already
* been allocated by racing tasks (offset has
* already stepped over any at the beginning).
*/
if (offset < si->highest_alloc &&
si->lowest_alloc <= last_in_cluster)
last_in_cluster = si->lowest_alloc - 1;
si->flags |= SWP_DISCARDING;
spin_unlock(&swap_lock);
if (offset < last_in_cluster)
discard_swap_cluster(si, offset,
last_in_cluster - offset + 1);
spin_lock(&swap_lock);
si->lowest_alloc = 0;
si->flags &= ~SWP_DISCARDING;
smp_mb(); /* wake_up_bit advises this */
wake_up_bit(&si->flags, ilog2(SWP_DISCARDING));
} else if (si->flags & SWP_DISCARDING) {
/*
* Delay using pages allocated by racing tasks
* until the whole discard has been issued. We
* could defer that delay until swap_writepage,
* but it's easier to keep this self-contained.
*/
spin_unlock(&swap_lock);
wait_on_bit(&si->flags, ilog2(SWP_DISCARDING),
wait_for_discard, TASK_UNINTERRUPTIBLE);
spin_lock(&swap_lock);
} else {
/*
* Note pages allocated by racing tasks while
* scan for a free cluster is in progress, so
* that its final discard can exclude them.
*/
if (offset < si->lowest_alloc)
si->lowest_alloc = offset;
if (offset > si->highest_alloc)
si->highest_alloc = offset;
}
}
return offset;
scan:
spin_unlock(&swap_lock);
while (++offset <= si->highest_bit) {
if (!si->swap_map[offset]) {
spin_lock(&swap_lock);
goto checks;
}
if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) {
spin_lock(&swap_lock);
goto checks;
}
if (unlikely(--latency_ration < 0)) {
cond_resched();
latency_ration = LATENCY_LIMIT;
}
}
offset = si->lowest_bit;
while (++offset < scan_base) {
if (!si->swap_map[offset]) {
spin_lock(&swap_lock);
goto checks;
}
if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) {
spin_lock(&swap_lock);
goto checks;
}
if (unlikely(--latency_ration < 0)) {
cond_resched();
latency_ration = LATENCY_LIMIT;
}
}
spin_lock(&swap_lock);
no_page:
si->flags -= SWP_SCANNING;
return 0;
}
swp_entry_t get_swap_page(void)
{
struct swap_info_struct *si;
pgoff_t offset;
int type, next;
int wrapped = 0;
spin_lock(&swap_lock);
if (nr_swap_pages <= 0)
goto noswap;
nr_swap_pages--;
for (type = swap_list.next; type >= 0 && wrapped < 2; type = next) {
si = swap_info + type;
next = si->next;
if (next < 0 ||
(!wrapped && si->prio != swap_info[next].prio)) {
next = swap_list.head;
wrapped++;
}
if (!si->highest_bit)
continue;
if (!(si->flags & SWP_WRITEOK))
continue;
swap_list.next = next;
/* This is called for allocating swap entry for cache */
offset = scan_swap_map(si, SWAP_CACHE);
if (offset) {
spin_unlock(&swap_lock);
return swp_entry(type, offset);
}
next = swap_list.next;
}
nr_swap_pages++;
noswap:
spin_unlock(&swap_lock);
return (swp_entry_t) {0};
}
/* The only caller of this function is now susupend routine */
swp_entry_t get_swap_page_of_type(int type)
{
struct swap_info_struct *si;
pgoff_t offset;
spin_lock(&swap_lock);
si = swap_info + type;
if (si->flags & SWP_WRITEOK) {
nr_swap_pages--;
/* This is called for allocating swap entry, not cache */
offset = scan_swap_map(si, SWAP_MAP);
if (offset) {
spin_unlock(&swap_lock);
return swp_entry(type, offset);
}
nr_swap_pages++;
}
spin_unlock(&swap_lock);
return (swp_entry_t) {0};
}
static struct swap_info_struct * swap_info_get(swp_entry_t entry)
{
struct swap_info_struct * p;
unsigned long offset, type;
if (!entry.val)
goto out;
type = swp_type(entry);
if (type >= nr_swapfiles)
goto bad_nofile;
p = & swap_info[type];
if (!(p->flags & SWP_USED))
goto bad_device;
offset = swp_offset(entry);
if (offset >= p->max)
goto bad_offset;
if (!p->swap_map[offset])
goto bad_free;
spin_lock(&swap_lock);
return p;
bad_free:
printk(KERN_ERR "swap_free: %s%08lx\n", Unused_offset, entry.val);
goto out;
bad_offset:
printk(KERN_ERR "swap_free: %s%08lx\n", Bad_offset, entry.val);
goto out;
bad_device:
printk(KERN_ERR "swap_free: %s%08lx\n", Unused_file, entry.val);
goto out;
bad_nofile:
printk(KERN_ERR "swap_free: %s%08lx\n", Bad_file, entry.val);
out:
return NULL;
}
static int swap_entry_free(struct swap_info_struct *p,
swp_entry_t ent, int cache)
{
memcg: mem+swap controller core This patch implements per cgroup limit for usage of memory+swap. However there are SwapCache, double counting of swap-cache and swap-entry is avoided. Mem+Swap controller works as following. - memory usage is limited by memory.limit_in_bytes. - memory + swap usage is limited by memory.memsw_limit_in_bytes. This has following benefits. - A user can limit total resource usage of mem+swap. Without this, because memory resource controller doesn't take care of usage of swap, a process can exhaust all the swap (by memory leak.) We can avoid this case. And Swap is shared resource but it cannot be reclaimed (goes back to memory) until it's used. This characteristic can be trouble when the memory is divided into some parts by cpuset or memcg. Assume group A and group B. After some application executes, the system can be.. Group A -- very large free memory space but occupy 99% of swap. Group B -- under memory shortage but cannot use swap...it's nearly full. Ability to set appropriate swap limit for each group is required. Maybe someone wonder "why not swap but mem+swap ?" - The global LRU(kswapd) can swap out arbitrary pages. Swap-out means to move account from memory to swap...there is no change in usage of mem+swap. In other words, when we want to limit the usage of swap without affecting global LRU, mem+swap limit is better than just limiting swap. Accounting target information is stored in swap_cgroup which is per swap entry record. Charge is done as following. map - charge page and memsw. unmap - uncharge page/memsw if not SwapCache. swap-out (__delete_from_swap_cache) - uncharge page - record mem_cgroup information to swap_cgroup. swap-in (do_swap_page) - charged as page and memsw. record in swap_cgroup is cleared. memsw accounting is decremented. swap-free (swap_free()) - if swap entry is freed, memsw is uncharged by PAGE_SIZE. There are people work under never-swap environments and consider swap as something bad. For such people, this mem+swap controller extension is just an overhead. This overhead is avoided by config or boot option. (see Kconfig. detail is not in this patch.) TODO: - maybe more optimization can be don in swap-in path. (but not very safe.) But we just do simple accounting at this stage. [nishimura@mxp.nes.nec.co.jp: make resize limit hold mutex] [hugh@veritas.com: memswap controller core swapcache fixes] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 03:08:00 +01:00
unsigned long offset = swp_offset(ent);
int count = swap_count(p->swap_map[offset]);
bool has_cache;
has_cache = swap_has_cache(p->swap_map[offset]);
if (cache == SWAP_MAP) { /* dropping usage count of swap */
if (count < SWAP_MAP_MAX) {
count--;
p->swap_map[offset] = encode_swapmap(count, has_cache);
}
} else { /* dropping swap cache flag */
VM_BUG_ON(!has_cache);
p->swap_map[offset] = encode_swapmap(count, false);
}
/* return code. */
count = p->swap_map[offset];
/* free if no reference */
if (!count) {
if (offset < p->lowest_bit)
p->lowest_bit = offset;
if (offset > p->highest_bit)
p->highest_bit = offset;
if (p->prio > swap_info[swap_list.next].prio)
swap_list.next = p - swap_info;
nr_swap_pages++;
p->inuse_pages--;
}
if (!swap_count(count))
mem_cgroup_uncharge_swap(ent);
return count;
}
/*
* Caller has made sure that the swapdevice corresponding to entry
* is still around or has not been recycled.
*/
void swap_free(swp_entry_t entry)
{
struct swap_info_struct * p;
p = swap_info_get(entry);
if (p) {
swap_entry_free(p, entry, SWAP_MAP);
spin_unlock(&swap_lock);
}
}
/*
* Called after dropping swapcache to decrease refcnt to swap entries.
*/
void swapcache_free(swp_entry_t entry, struct page *page)
{
struct swap_info_struct *p;
int ret;
p = swap_info_get(entry);
if (p) {
ret = swap_entry_free(p, entry, SWAP_CACHE);
if (page) {
bool swapout;
if (ret)
swapout = true; /* the end of swap out */
else
swapout = false; /* no more swap users! */
mem_cgroup_uncharge_swapcache(page, entry, swapout);
}
spin_unlock(&swap_lock);
}
return;
}
/*
* How many references to page are currently swapped out?
*/
static inline int page_swapcount(struct page *page)
{
int count = 0;
struct swap_info_struct *p;
swp_entry_t entry;
[PATCH] mm: split page table lock Christoph Lameter demonstrated very poor scalability on the SGI 512-way, with a many-threaded application which concurrently initializes different parts of a large anonymous area. This patch corrects that, by using a separate spinlock per page table page, to guard the page table entries in that page, instead of using the mm's single page_table_lock. (But even then, page_table_lock is still used to guard page table allocation, and anon_vma allocation.) In this implementation, the spinlock is tucked inside the struct page of the page table page: with a BUILD_BUG_ON in case it overflows - which it would in the case of 32-bit PA-RISC with spinlock debugging enabled. Splitting the lock is not quite for free: another cacheline access. Ideally, I suppose we would use split ptlock only for multi-threaded processes on multi-cpu machines; but deciding that dynamically would have its own costs. So for now enable it by config, at some number of cpus - since the Kconfig language doesn't support inequalities, let preprocessor compare that with NR_CPUS. But I don't think it's worth being user-configurable: for good testing of both split and unsplit configs, split now at 4 cpus, and perhaps change that to 8 later. There is a benefit even for singly threaded processes: kswapd can be attacking one part of the mm while another part is busy faulting. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-10-30 02:16:40 +01:00
entry.val = page_private(page);
p = swap_info_get(entry);
if (p) {
count = swap_count(p->swap_map[swp_offset(entry)]);
spin_unlock(&swap_lock);
}
return count;
}
/*
* We can write to an anon page without COW if there are no other references
* to it. And as a side-effect, free up its swap: because the old content
* on disk will never be read, and seeking back there to write new content
* later would only waste time away from clustering.
*/
int reuse_swap_page(struct page *page)
{
int count;
VM_BUG_ON(!PageLocked(page));
count = page_mapcount(page);
if (count <= 1 && PageSwapCache(page)) {
count += page_swapcount(page);
if (count == 1 && !PageWriteback(page)) {
delete_from_swap_cache(page);
SetPageDirty(page);
}
}
return count == 1;
}
/*
mm: try_to_free_swap replaces remove_exclusive_swap_page remove_exclusive_swap_page(): its problem is in living up to its name. It doesn't matter if someone else has a reference to the page (raised page_count); it doesn't matter if the page is mapped into userspace (raised page_mapcount - though that hints it may be worth keeping the swap): all that matters is that there be no more references to the swap (and no writeback in progress). swapoff (try_to_unuse) has been removing pages from swapcache for years, with no concern for page count or page mapcount, and we used to have a comment in lookup_swap_cache() recognizing that: if you go for a page of swapcache, you'll get the right page, but it could have been removed from swapcache by the time you get page lock. So, give up asking for exclusivity: get rid of remove_exclusive_swap_page(), and remove_exclusive_swap_page_ref() and remove_exclusive_swap_page_count() which were spawned for the recent LRU work: replace them by the simpler try_to_free_swap() which just checks page_swapcount(). Similarly, remove the page_count limitation from free_swap_and_count(), but assume that it's worth holding on to the swap if page is mapped and swap nowhere near full. Add a vm_swap_full() test in free_swap_cache()? It would be consistent, but I think we probably have enough for now. Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Rik van Riel <riel@redhat.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Robin Holt <holt@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-06 23:39:36 +01:00
* If swap is getting full, or if there are no more mappings of this page,
* then try_to_free_swap is called to free its swap space.
*/
mm: try_to_free_swap replaces remove_exclusive_swap_page remove_exclusive_swap_page(): its problem is in living up to its name. It doesn't matter if someone else has a reference to the page (raised page_count); it doesn't matter if the page is mapped into userspace (raised page_mapcount - though that hints it may be worth keeping the swap): all that matters is that there be no more references to the swap (and no writeback in progress). swapoff (try_to_unuse) has been removing pages from swapcache for years, with no concern for page count or page mapcount, and we used to have a comment in lookup_swap_cache() recognizing that: if you go for a page of swapcache, you'll get the right page, but it could have been removed from swapcache by the time you get page lock. So, give up asking for exclusivity: get rid of remove_exclusive_swap_page(), and remove_exclusive_swap_page_ref() and remove_exclusive_swap_page_count() which were spawned for the recent LRU work: replace them by the simpler try_to_free_swap() which just checks page_swapcount(). Similarly, remove the page_count limitation from free_swap_and_count(), but assume that it's worth holding on to the swap if page is mapped and swap nowhere near full. Add a vm_swap_full() test in free_swap_cache()? It would be consistent, but I think we probably have enough for now. Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Rik van Riel <riel@redhat.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Robin Holt <holt@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-06 23:39:36 +01:00
int try_to_free_swap(struct page *page)
{
VM_BUG_ON(!PageLocked(page));
if (!PageSwapCache(page))
return 0;
if (PageWriteback(page))
return 0;
mm: try_to_free_swap replaces remove_exclusive_swap_page remove_exclusive_swap_page(): its problem is in living up to its name. It doesn't matter if someone else has a reference to the page (raised page_count); it doesn't matter if the page is mapped into userspace (raised page_mapcount - though that hints it may be worth keeping the swap): all that matters is that there be no more references to the swap (and no writeback in progress). swapoff (try_to_unuse) has been removing pages from swapcache for years, with no concern for page count or page mapcount, and we used to have a comment in lookup_swap_cache() recognizing that: if you go for a page of swapcache, you'll get the right page, but it could have been removed from swapcache by the time you get page lock. So, give up asking for exclusivity: get rid of remove_exclusive_swap_page(), and remove_exclusive_swap_page_ref() and remove_exclusive_swap_page_count() which were spawned for the recent LRU work: replace them by the simpler try_to_free_swap() which just checks page_swapcount(). Similarly, remove the page_count limitation from free_swap_and_count(), but assume that it's worth holding on to the swap if page is mapped and swap nowhere near full. Add a vm_swap_full() test in free_swap_cache()? It would be consistent, but I think we probably have enough for now. Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Rik van Riel <riel@redhat.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Robin Holt <holt@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-06 23:39:36 +01:00
if (page_swapcount(page))
return 0;
mm: try_to_free_swap replaces remove_exclusive_swap_page remove_exclusive_swap_page(): its problem is in living up to its name. It doesn't matter if someone else has a reference to the page (raised page_count); it doesn't matter if the page is mapped into userspace (raised page_mapcount - though that hints it may be worth keeping the swap): all that matters is that there be no more references to the swap (and no writeback in progress). swapoff (try_to_unuse) has been removing pages from swapcache for years, with no concern for page count or page mapcount, and we used to have a comment in lookup_swap_cache() recognizing that: if you go for a page of swapcache, you'll get the right page, but it could have been removed from swapcache by the time you get page lock. So, give up asking for exclusivity: get rid of remove_exclusive_swap_page(), and remove_exclusive_swap_page_ref() and remove_exclusive_swap_page_count() which were spawned for the recent LRU work: replace them by the simpler try_to_free_swap() which just checks page_swapcount(). Similarly, remove the page_count limitation from free_swap_and_count(), but assume that it's worth holding on to the swap if page is mapped and swap nowhere near full. Add a vm_swap_full() test in free_swap_cache()? It would be consistent, but I think we probably have enough for now. Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Rik van Riel <riel@redhat.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Robin Holt <holt@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-06 23:39:36 +01:00
delete_from_swap_cache(page);
SetPageDirty(page);
return 1;
}
/*
* Free the swap entry like above, but also try to
* free the page cache entry if it is the last user.
*/
int free_swap_and_cache(swp_entry_t entry)
{
struct swap_info_struct *p;
struct page *page = NULL;
[PATCH] Swapless page migration: add R/W migration entries Implement read/write migration ptes We take the upper two swapfiles for the two types of migration ptes and define a series of macros in swapops.h. The VM is modified to handle the migration entries. migration entries can only be encountered when the page they are pointing to is locked. This limits the number of places one has to fix. We also check in copy_pte_range and in mprotect_pte_range() for migration ptes. We check for migration ptes in do_swap_cache and call a function that will then wait on the page lock. This allows us to effectively stop all accesses to apge. Migration entries are created by try_to_unmap if called for migration and removed by local functions in migrate.c From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration (I've no NUMA, just hacking it up to migrate recklessly while running load), I've hit the BUG_ON(!PageLocked(p)) in migration_entry_to_page. This comes from an orphaned migration entry, unrelated to the current correctly locked migration, but hit by remove_anon_migration_ptes as it checks an address in each vma of the anon_vma list. Such an orphan may be left behind if an earlier migration raced with fork: copy_one_pte can duplicate a migration entry from parent to child, after remove_anon_migration_ptes has checked the child vma, but before it has removed it from the parent vma. (If the process were later to fault on this orphaned entry, it would hit the same BUG from migration_entry_wait.) This could be fixed by locking anon_vma in copy_one_pte, but we'd rather not. There's no such problem with file pages, because vma_prio_tree_add adds child vma after parent vma, and the page table locking at each end is enough to serialize. Follow that example with anon_vma: add new vmas to the tail instead of the head. (There's no corresponding problem when inserting migration entries, because a missed pte will leave the page count and mapcount high, which is allowed for. And there's no corresponding problem when migrating via swap, because a leftover swap entry will be correctly faulted. But the swapless method has no refcounting of its entries.) From: Ingo Molnar <mingo@elte.hu> pte_unmap_unlock() takes the pte pointer as an argument. From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration, gcc has tried to exec a pointer instead of a string: smells like COW mappings are not being properly write-protected on fork. The protection in copy_one_pte looks very convincing, until at last you realize that the second arg to make_migration_entry is a boolean "write", and SWP_MIGRATION_READ is 30. Anyway, it's better done like in change_pte_range, using is_write_migration_entry and make_migration_entry_read. From: Hugh Dickins <hugh@veritas.com> Remove unnecessary obfuscation from sys_swapon's range check on swap type, which blew up causing memory corruption once swapless migration made MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT. Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Christoph Lameter <clameter@engr.sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> From: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 11:03:35 +02:00
if (is_migration_entry(entry))
return 1;
[PATCH] Swapless page migration: add R/W migration entries Implement read/write migration ptes We take the upper two swapfiles for the two types of migration ptes and define a series of macros in swapops.h. The VM is modified to handle the migration entries. migration entries can only be encountered when the page they are pointing to is locked. This limits the number of places one has to fix. We also check in copy_pte_range and in mprotect_pte_range() for migration ptes. We check for migration ptes in do_swap_cache and call a function that will then wait on the page lock. This allows us to effectively stop all accesses to apge. Migration entries are created by try_to_unmap if called for migration and removed by local functions in migrate.c From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration (I've no NUMA, just hacking it up to migrate recklessly while running load), I've hit the BUG_ON(!PageLocked(p)) in migration_entry_to_page. This comes from an orphaned migration entry, unrelated to the current correctly locked migration, but hit by remove_anon_migration_ptes as it checks an address in each vma of the anon_vma list. Such an orphan may be left behind if an earlier migration raced with fork: copy_one_pte can duplicate a migration entry from parent to child, after remove_anon_migration_ptes has checked the child vma, but before it has removed it from the parent vma. (If the process were later to fault on this orphaned entry, it would hit the same BUG from migration_entry_wait.) This could be fixed by locking anon_vma in copy_one_pte, but we'd rather not. There's no such problem with file pages, because vma_prio_tree_add adds child vma after parent vma, and the page table locking at each end is enough to serialize. Follow that example with anon_vma: add new vmas to the tail instead of the head. (There's no corresponding problem when inserting migration entries, because a missed pte will leave the page count and mapcount high, which is allowed for. And there's no corresponding problem when migrating via swap, because a leftover swap entry will be correctly faulted. But the swapless method has no refcounting of its entries.) From: Ingo Molnar <mingo@elte.hu> pte_unmap_unlock() takes the pte pointer as an argument. From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration, gcc has tried to exec a pointer instead of a string: smells like COW mappings are not being properly write-protected on fork. The protection in copy_one_pte looks very convincing, until at last you realize that the second arg to make_migration_entry is a boolean "write", and SWP_MIGRATION_READ is 30. Anyway, it's better done like in change_pte_range, using is_write_migration_entry and make_migration_entry_read. From: Hugh Dickins <hugh@veritas.com> Remove unnecessary obfuscation from sys_swapon's range check on swap type, which blew up causing memory corruption once swapless migration made MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT. Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Christoph Lameter <clameter@engr.sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> From: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 11:03:35 +02:00
p = swap_info_get(entry);
if (p) {
if (swap_entry_free(p, entry, SWAP_MAP) == SWAP_HAS_CACHE) {
page = find_get_page(&swapper_space, entry.val);
if (page && !trylock_page(page)) {
page_cache_release(page);
page = NULL;
}
}
spin_unlock(&swap_lock);
}
if (page) {
mm: try_to_free_swap replaces remove_exclusive_swap_page remove_exclusive_swap_page(): its problem is in living up to its name. It doesn't matter if someone else has a reference to the page (raised page_count); it doesn't matter if the page is mapped into userspace (raised page_mapcount - though that hints it may be worth keeping the swap): all that matters is that there be no more references to the swap (and no writeback in progress). swapoff (try_to_unuse) has been removing pages from swapcache for years, with no concern for page count or page mapcount, and we used to have a comment in lookup_swap_cache() recognizing that: if you go for a page of swapcache, you'll get the right page, but it could have been removed from swapcache by the time you get page lock. So, give up asking for exclusivity: get rid of remove_exclusive_swap_page(), and remove_exclusive_swap_page_ref() and remove_exclusive_swap_page_count() which were spawned for the recent LRU work: replace them by the simpler try_to_free_swap() which just checks page_swapcount(). Similarly, remove the page_count limitation from free_swap_and_count(), but assume that it's worth holding on to the swap if page is mapped and swap nowhere near full. Add a vm_swap_full() test in free_swap_cache()? It would be consistent, but I think we probably have enough for now. Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Rik van Riel <riel@redhat.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Robin Holt <holt@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-06 23:39:36 +01:00
/*
* Not mapped elsewhere, or swap space full? Free it!
* Also recheck PageSwapCache now page is locked (above).
*/
if (PageSwapCache(page) && !PageWriteback(page) &&
mm: try_to_free_swap replaces remove_exclusive_swap_page remove_exclusive_swap_page(): its problem is in living up to its name. It doesn't matter if someone else has a reference to the page (raised page_count); it doesn't matter if the page is mapped into userspace (raised page_mapcount - though that hints it may be worth keeping the swap): all that matters is that there be no more references to the swap (and no writeback in progress). swapoff (try_to_unuse) has been removing pages from swapcache for years, with no concern for page count or page mapcount, and we used to have a comment in lookup_swap_cache() recognizing that: if you go for a page of swapcache, you'll get the right page, but it could have been removed from swapcache by the time you get page lock. So, give up asking for exclusivity: get rid of remove_exclusive_swap_page(), and remove_exclusive_swap_page_ref() and remove_exclusive_swap_page_count() which were spawned for the recent LRU work: replace them by the simpler try_to_free_swap() which just checks page_swapcount(). Similarly, remove the page_count limitation from free_swap_and_count(), but assume that it's worth holding on to the swap if page is mapped and swap nowhere near full. Add a vm_swap_full() test in free_swap_cache()? It would be consistent, but I think we probably have enough for now. Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Rik van Riel <riel@redhat.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Robin Holt <holt@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-06 23:39:36 +01:00
(!page_mapped(page) || vm_swap_full())) {
delete_from_swap_cache(page);
SetPageDirty(page);
}
unlock_page(page);
page_cache_release(page);
}
return p != NULL;
}
#ifdef CONFIG_HIBERNATION
/*
2006-12-07 05:34:07 +01:00
* Find the swap type that corresponds to given device (if any).
*
2006-12-07 05:34:07 +01:00
* @offset - number of the PAGE_SIZE-sized block of the device, starting
* from 0, in which the swap header is expected to be located.
*
* This is needed for the suspend to disk (aka swsusp).
*/
int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p)
{
2006-12-07 05:34:07 +01:00
struct block_device *bdev = NULL;
int i;
2006-12-07 05:34:07 +01:00
if (device)
bdev = bdget(device);
spin_lock(&swap_lock);
for (i = 0; i < nr_swapfiles; i++) {
2006-12-07 05:34:07 +01:00
struct swap_info_struct *sis = swap_info + i;
2006-12-07 05:34:07 +01:00
if (!(sis->flags & SWP_WRITEOK))
continue;
2006-12-07 05:34:07 +01:00
if (!bdev) {
if (bdev_p)
*bdev_p = bdget(sis->bdev->bd_dev);
spin_unlock(&swap_lock);
return i;
}
2006-12-07 05:34:07 +01:00
if (bdev == sis->bdev) {
struct swap_extent *se;
se = list_entry(sis->extent_list.next,
struct swap_extent, list);
if (se->start_block == offset) {
if (bdev_p)
*bdev_p = bdget(sis->bdev->bd_dev);
2006-12-07 05:34:07 +01:00
spin_unlock(&swap_lock);
bdput(bdev);
return i;
}
}
}
spin_unlock(&swap_lock);
2006-12-07 05:34:07 +01:00
if (bdev)
bdput(bdev);
return -ENODEV;
}
/*
* Return either the total number of swap pages of given type, or the number
* of free pages of that type (depending on @free)
*
* This is needed for software suspend
*/
unsigned int count_swap_pages(int type, int free)
{
unsigned int n = 0;
if (type < nr_swapfiles) {
spin_lock(&swap_lock);
if (swap_info[type].flags & SWP_WRITEOK) {
n = swap_info[type].pages;
if (free)
n -= swap_info[type].inuse_pages;
}
spin_unlock(&swap_lock);
}
return n;
}
#endif
/*
* No need to decide whether this PTE shares the swap entry with others,
* just let do_wp_page work it out if a write is requested later - to
* force COW, vm_page_prot omits write permission from any private vma.
*/
static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, swp_entry_t entry, struct page *page)
{
memcg: introduce charge-commit-cancel style of functions There is a small race in do_swap_page(). When the page swapped-in is charged, the mapcount can be greater than 0. But, at the same time some process (shares it ) call unmap and make mapcount 1->0 and the page is uncharged. CPUA CPUB mapcount == 1. (1) charge if mapcount==0 zap_pte_range() (2) mapcount 1 => 0. (3) uncharge(). (success) (4) set page's rmap() mapcount 0=>1 Then, this swap page's account is leaked. For fixing this, I added a new interface. - charge account to res_counter by PAGE_SIZE and try to free pages if necessary. - commit register page_cgroup and add to LRU if necessary. - cancel uncharge PAGE_SIZE because of do_swap_page failure. CPUA (1) charge (always) (2) set page's rmap (mapcount > 0) (3) commit charge was necessary or not after set_pte(). This protocol uses PCG_USED bit on page_cgroup for avoiding over accounting. Usual mem_cgroup_charge_common() does charge -> commit at a time. And this patch also adds following function to clarify all charges. - mem_cgroup_newpage_charge() ....replacement for mem_cgroup_charge() called against newly allocated anon pages. - mem_cgroup_charge_migrate_fixup() called only from remove_migration_ptes(). we'll have to rewrite this later.(this patch just keeps old behavior) This function will be removed by additional patch to make migration clearer. Good for clarifying "what we do" Then, we have 4 following charge points. - newpage - swap-in - add-to-cache. - migration. [akpm@linux-foundation.org: add missing inline directives to stubs] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Cc: Balbir Singh <balbir@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 03:07:48 +01:00
struct mem_cgroup *ptr = NULL;
spinlock_t *ptl;
pte_t *pte;
int ret = 1;
if (mem_cgroup_try_charge_swapin(vma->vm_mm, page, GFP_KERNEL, &ptr)) {
ret = -ENOMEM;
goto out_nolock;
}
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
if (unlikely(!pte_same(*pte, swp_entry_to_pte(entry)))) {
if (ret > 0)
memcg: introduce charge-commit-cancel style of functions There is a small race in do_swap_page(). When the page swapped-in is charged, the mapcount can be greater than 0. But, at the same time some process (shares it ) call unmap and make mapcount 1->0 and the page is uncharged. CPUA CPUB mapcount == 1. (1) charge if mapcount==0 zap_pte_range() (2) mapcount 1 => 0. (3) uncharge(). (success) (4) set page's rmap() mapcount 0=>1 Then, this swap page's account is leaked. For fixing this, I added a new interface. - charge account to res_counter by PAGE_SIZE and try to free pages if necessary. - commit register page_cgroup and add to LRU if necessary. - cancel uncharge PAGE_SIZE because of do_swap_page failure. CPUA (1) charge (always) (2) set page's rmap (mapcount > 0) (3) commit charge was necessary or not after set_pte(). This protocol uses PCG_USED bit on page_cgroup for avoiding over accounting. Usual mem_cgroup_charge_common() does charge -> commit at a time. And this patch also adds following function to clarify all charges. - mem_cgroup_newpage_charge() ....replacement for mem_cgroup_charge() called against newly allocated anon pages. - mem_cgroup_charge_migrate_fixup() called only from remove_migration_ptes(). we'll have to rewrite this later.(this patch just keeps old behavior) This function will be removed by additional patch to make migration clearer. Good for clarifying "what we do" Then, we have 4 following charge points. - newpage - swap-in - add-to-cache. - migration. [akpm@linux-foundation.org: add missing inline directives to stubs] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Cc: Balbir Singh <balbir@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 03:07:48 +01:00
mem_cgroup_cancel_charge_swapin(ptr);
ret = 0;
goto out;
}
Memory controller: memory accounting Add the accounting hooks. The accounting is carried out for RSS and Page Cache (unmapped) pages. There is now a common limit and accounting for both. The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap() time. Page cache is accounted at add_to_page_cache(), __delete_from_page_cache(). Swap cache is also accounted for. Each page's page_cgroup is protected with the last bit of the page_cgroup pointer, this makes handling of race conditions involving simultaneous mappings of a page easier. A reference count is kept in the page_cgroup to deal with cases where a page might be unmapped from the RSS of all tasks, but still lives in the page cache. Credits go to Vaidyanathan Srinivasan for helping with reference counting work of the page cgroup. Almost all of the page cache accounting code has help from Vaidyanathan Srinivasan. [hugh@veritas.com: fix swapoff breakage] [akpm@linux-foundation.org: fix locking] Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: <Valdis.Kletnieks@vt.edu> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 09:13:53 +01:00
inc_mm_counter(vma->vm_mm, anon_rss);
get_page(page);
set_pte_at(vma->vm_mm, addr, pte,
pte_mkold(mk_pte(page, vma->vm_page_prot)));
page_add_anon_rmap(page, vma, addr);
memcg: introduce charge-commit-cancel style of functions There is a small race in do_swap_page(). When the page swapped-in is charged, the mapcount can be greater than 0. But, at the same time some process (shares it ) call unmap and make mapcount 1->0 and the page is uncharged. CPUA CPUB mapcount == 1. (1) charge if mapcount==0 zap_pte_range() (2) mapcount 1 => 0. (3) uncharge(). (success) (4) set page's rmap() mapcount 0=>1 Then, this swap page's account is leaked. For fixing this, I added a new interface. - charge account to res_counter by PAGE_SIZE and try to free pages if necessary. - commit register page_cgroup and add to LRU if necessary. - cancel uncharge PAGE_SIZE because of do_swap_page failure. CPUA (1) charge (always) (2) set page's rmap (mapcount > 0) (3) commit charge was necessary or not after set_pte(). This protocol uses PCG_USED bit on page_cgroup for avoiding over accounting. Usual mem_cgroup_charge_common() does charge -> commit at a time. And this patch also adds following function to clarify all charges. - mem_cgroup_newpage_charge() ....replacement for mem_cgroup_charge() called against newly allocated anon pages. - mem_cgroup_charge_migrate_fixup() called only from remove_migration_ptes(). we'll have to rewrite this later.(this patch just keeps old behavior) This function will be removed by additional patch to make migration clearer. Good for clarifying "what we do" Then, we have 4 following charge points. - newpage - swap-in - add-to-cache. - migration. [akpm@linux-foundation.org: add missing inline directives to stubs] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Cc: Balbir Singh <balbir@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 03:07:48 +01:00
mem_cgroup_commit_charge_swapin(page, ptr);
swap_free(entry);
/*
* Move the page to the active list so it is not
* immediately swapped out again after swapon.
*/
activate_page(page);
out:
pte_unmap_unlock(pte, ptl);
out_nolock:
return ret;
}
static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end,
swp_entry_t entry, struct page *page)
{
pte_t swp_pte = swp_entry_to_pte(entry);
pte_t *pte;
Memory controller: memory accounting Add the accounting hooks. The accounting is carried out for RSS and Page Cache (unmapped) pages. There is now a common limit and accounting for both. The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap() time. Page cache is accounted at add_to_page_cache(), __delete_from_page_cache(). Swap cache is also accounted for. Each page's page_cgroup is protected with the last bit of the page_cgroup pointer, this makes handling of race conditions involving simultaneous mappings of a page easier. A reference count is kept in the page_cgroup to deal with cases where a page might be unmapped from the RSS of all tasks, but still lives in the page cache. Credits go to Vaidyanathan Srinivasan for helping with reference counting work of the page cgroup. Almost all of the page cache accounting code has help from Vaidyanathan Srinivasan. [hugh@veritas.com: fix swapoff breakage] [akpm@linux-foundation.org: fix locking] Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: <Valdis.Kletnieks@vt.edu> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 09:13:53 +01:00
int ret = 0;
/*
* We don't actually need pte lock while scanning for swp_pte: since
* we hold page lock and mmap_sem, swp_pte cannot be inserted into the
* page table while we're scanning; though it could get zapped, and on
* some architectures (e.g. x86_32 with PAE) we might catch a glimpse
* of unmatched parts which look like swp_pte, so unuse_pte must
* recheck under pte lock. Scanning without pte lock lets it be
* preemptible whenever CONFIG_PREEMPT but not CONFIG_HIGHPTE.
*/
pte = pte_offset_map(pmd, addr);
do {
/*
* swapoff spends a _lot_ of time in this loop!
* Test inline before going to call unuse_pte.
*/
if (unlikely(pte_same(*pte, swp_pte))) {
pte_unmap(pte);
ret = unuse_pte(vma, pmd, addr, entry, page);
if (ret)
goto out;
pte = pte_offset_map(pmd, addr);
}
} while (pte++, addr += PAGE_SIZE, addr != end);
pte_unmap(pte - 1);
out:
Memory controller: memory accounting Add the accounting hooks. The accounting is carried out for RSS and Page Cache (unmapped) pages. There is now a common limit and accounting for both. The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap() time. Page cache is accounted at add_to_page_cache(), __delete_from_page_cache(). Swap cache is also accounted for. Each page's page_cgroup is protected with the last bit of the page_cgroup pointer, this makes handling of race conditions involving simultaneous mappings of a page easier. A reference count is kept in the page_cgroup to deal with cases where a page might be unmapped from the RSS of all tasks, but still lives in the page cache. Credits go to Vaidyanathan Srinivasan for helping with reference counting work of the page cgroup. Almost all of the page cache accounting code has help from Vaidyanathan Srinivasan. [hugh@veritas.com: fix swapoff breakage] [akpm@linux-foundation.org: fix locking] Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: <Valdis.Kletnieks@vt.edu> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 09:13:53 +01:00
return ret;
}
static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud,
unsigned long addr, unsigned long end,
swp_entry_t entry, struct page *page)
{
pmd_t *pmd;
unsigned long next;
Memory controller: memory accounting Add the accounting hooks. The accounting is carried out for RSS and Page Cache (unmapped) pages. There is now a common limit and accounting for both. The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap() time. Page cache is accounted at add_to_page_cache(), __delete_from_page_cache(). Swap cache is also accounted for. Each page's page_cgroup is protected with the last bit of the page_cgroup pointer, this makes handling of race conditions involving simultaneous mappings of a page easier. A reference count is kept in the page_cgroup to deal with cases where a page might be unmapped from the RSS of all tasks, but still lives in the page cache. Credits go to Vaidyanathan Srinivasan for helping with reference counting work of the page cgroup. Almost all of the page cache accounting code has help from Vaidyanathan Srinivasan. [hugh@veritas.com: fix swapoff breakage] [akpm@linux-foundation.org: fix locking] Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: <Valdis.Kletnieks@vt.edu> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 09:13:53 +01:00
int ret;
pmd = pmd_offset(pud, addr);
do {
next = pmd_addr_end(addr, end);
if (pmd_none_or_clear_bad(pmd))
continue;
Memory controller: memory accounting Add the accounting hooks. The accounting is carried out for RSS and Page Cache (unmapped) pages. There is now a common limit and accounting for both. The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap() time. Page cache is accounted at add_to_page_cache(), __delete_from_page_cache(). Swap cache is also accounted for. Each page's page_cgroup is protected with the last bit of the page_cgroup pointer, this makes handling of race conditions involving simultaneous mappings of a page easier. A reference count is kept in the page_cgroup to deal with cases where a page might be unmapped from the RSS of all tasks, but still lives in the page cache. Credits go to Vaidyanathan Srinivasan for helping with reference counting work of the page cgroup. Almost all of the page cache accounting code has help from Vaidyanathan Srinivasan. [hugh@veritas.com: fix swapoff breakage] [akpm@linux-foundation.org: fix locking] Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: <Valdis.Kletnieks@vt.edu> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 09:13:53 +01:00
ret = unuse_pte_range(vma, pmd, addr, next, entry, page);
if (ret)
return ret;
} while (pmd++, addr = next, addr != end);
return 0;
}
static inline int unuse_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
unsigned long addr, unsigned long end,
swp_entry_t entry, struct page *page)
{
pud_t *pud;
unsigned long next;
Memory controller: memory accounting Add the accounting hooks. The accounting is carried out for RSS and Page Cache (unmapped) pages. There is now a common limit and accounting for both. The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap() time. Page cache is accounted at add_to_page_cache(), __delete_from_page_cache(). Swap cache is also accounted for. Each page's page_cgroup is protected with the last bit of the page_cgroup pointer, this makes handling of race conditions involving simultaneous mappings of a page easier. A reference count is kept in the page_cgroup to deal with cases where a page might be unmapped from the RSS of all tasks, but still lives in the page cache. Credits go to Vaidyanathan Srinivasan for helping with reference counting work of the page cgroup. Almost all of the page cache accounting code has help from Vaidyanathan Srinivasan. [hugh@veritas.com: fix swapoff breakage] [akpm@linux-foundation.org: fix locking] Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: <Valdis.Kletnieks@vt.edu> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 09:13:53 +01:00
int ret;
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
continue;
Memory controller: memory accounting Add the accounting hooks. The accounting is carried out for RSS and Page Cache (unmapped) pages. There is now a common limit and accounting for both. The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap() time. Page cache is accounted at add_to_page_cache(), __delete_from_page_cache(). Swap cache is also accounted for. Each page's page_cgroup is protected with the last bit of the page_cgroup pointer, this makes handling of race conditions involving simultaneous mappings of a page easier. A reference count is kept in the page_cgroup to deal with cases where a page might be unmapped from the RSS of all tasks, but still lives in the page cache. Credits go to Vaidyanathan Srinivasan for helping with reference counting work of the page cgroup. Almost all of the page cache accounting code has help from Vaidyanathan Srinivasan. [hugh@veritas.com: fix swapoff breakage] [akpm@linux-foundation.org: fix locking] Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: <Valdis.Kletnieks@vt.edu> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 09:13:53 +01:00
ret = unuse_pmd_range(vma, pud, addr, next, entry, page);
if (ret)
return ret;
} while (pud++, addr = next, addr != end);
return 0;
}
static int unuse_vma(struct vm_area_struct *vma,
swp_entry_t entry, struct page *page)
{
pgd_t *pgd;
unsigned long addr, end, next;
Memory controller: memory accounting Add the accounting hooks. The accounting is carried out for RSS and Page Cache (unmapped) pages. There is now a common limit and accounting for both. The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap() time. Page cache is accounted at add_to_page_cache(), __delete_from_page_cache(). Swap cache is also accounted for. Each page's page_cgroup is protected with the last bit of the page_cgroup pointer, this makes handling of race conditions involving simultaneous mappings of a page easier. A reference count is kept in the page_cgroup to deal with cases where a page might be unmapped from the RSS of all tasks, but still lives in the page cache. Credits go to Vaidyanathan Srinivasan for helping with reference counting work of the page cgroup. Almost all of the page cache accounting code has help from Vaidyanathan Srinivasan. [hugh@veritas.com: fix swapoff breakage] [akpm@linux-foundation.org: fix locking] Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: <Valdis.Kletnieks@vt.edu> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 09:13:53 +01:00
int ret;
if (page->mapping) {
addr = page_address_in_vma(page, vma);
if (addr == -EFAULT)
return 0;
else
end = addr + PAGE_SIZE;
} else {
addr = vma->vm_start;
end = vma->vm_end;
}
pgd = pgd_offset(vma->vm_mm, addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
Memory controller: memory accounting Add the accounting hooks. The accounting is carried out for RSS and Page Cache (unmapped) pages. There is now a common limit and accounting for both. The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap() time. Page cache is accounted at add_to_page_cache(), __delete_from_page_cache(). Swap cache is also accounted for. Each page's page_cgroup is protected with the last bit of the page_cgroup pointer, this makes handling of race conditions involving simultaneous mappings of a page easier. A reference count is kept in the page_cgroup to deal with cases where a page might be unmapped from the RSS of all tasks, but still lives in the page cache. Credits go to Vaidyanathan Srinivasan for helping with reference counting work of the page cgroup. Almost all of the page cache accounting code has help from Vaidyanathan Srinivasan. [hugh@veritas.com: fix swapoff breakage] [akpm@linux-foundation.org: fix locking] Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: <Valdis.Kletnieks@vt.edu> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 09:13:53 +01:00
ret = unuse_pud_range(vma, pgd, addr, next, entry, page);
if (ret)
return ret;
} while (pgd++, addr = next, addr != end);
return 0;
}
static int unuse_mm(struct mm_struct *mm,
swp_entry_t entry, struct page *page)
{
struct vm_area_struct *vma;
Memory controller: memory accounting Add the accounting hooks. The accounting is carried out for RSS and Page Cache (unmapped) pages. There is now a common limit and accounting for both. The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap() time. Page cache is accounted at add_to_page_cache(), __delete_from_page_cache(). Swap cache is also accounted for. Each page's page_cgroup is protected with the last bit of the page_cgroup pointer, this makes handling of race conditions involving simultaneous mappings of a page easier. A reference count is kept in the page_cgroup to deal with cases where a page might be unmapped from the RSS of all tasks, but still lives in the page cache. Credits go to Vaidyanathan Srinivasan for helping with reference counting work of the page cgroup. Almost all of the page cache accounting code has help from Vaidyanathan Srinivasan. [hugh@veritas.com: fix swapoff breakage] [akpm@linux-foundation.org: fix locking] Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: <Valdis.Kletnieks@vt.edu> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 09:13:53 +01:00
int ret = 0;
if (!down_read_trylock(&mm->mmap_sem)) {
/*
* Activate page so shrink_inactive_list is unlikely to unmap
* its ptes while lock is dropped, so swapoff can make progress.
*/
activate_page(page);
unlock_page(page);
down_read(&mm->mmap_sem);
lock_page(page);
}
for (vma = mm->mmap; vma; vma = vma->vm_next) {
Memory controller: memory accounting Add the accounting hooks. The accounting is carried out for RSS and Page Cache (unmapped) pages. There is now a common limit and accounting for both. The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap() time. Page cache is accounted at add_to_page_cache(), __delete_from_page_cache(). Swap cache is also accounted for. Each page's page_cgroup is protected with the last bit of the page_cgroup pointer, this makes handling of race conditions involving simultaneous mappings of a page easier. A reference count is kept in the page_cgroup to deal with cases where a page might be unmapped from the RSS of all tasks, but still lives in the page cache. Credits go to Vaidyanathan Srinivasan for helping with reference counting work of the page cgroup. Almost all of the page cache accounting code has help from Vaidyanathan Srinivasan. [hugh@veritas.com: fix swapoff breakage] [akpm@linux-foundation.org: fix locking] Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: <Valdis.Kletnieks@vt.edu> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 09:13:53 +01:00
if (vma->anon_vma && (ret = unuse_vma(vma, entry, page)))
break;
}
up_read(&mm->mmap_sem);
Memory controller: memory accounting Add the accounting hooks. The accounting is carried out for RSS and Page Cache (unmapped) pages. There is now a common limit and accounting for both. The RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap() time. Page cache is accounted at add_to_page_cache(), __delete_from_page_cache(). Swap cache is also accounted for. Each page's page_cgroup is protected with the last bit of the page_cgroup pointer, this makes handling of race conditions involving simultaneous mappings of a page easier. A reference count is kept in the page_cgroup to deal with cases where a page might be unmapped from the RSS of all tasks, but still lives in the page cache. Credits go to Vaidyanathan Srinivasan for helping with reference counting work of the page cgroup. Almost all of the page cache accounting code has help from Vaidyanathan Srinivasan. [hugh@veritas.com: fix swapoff breakage] [akpm@linux-foundation.org: fix locking] Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Paul Menage <menage@google.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: Kirill Korotaev <dev@sw.ru> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: David Rientjes <rientjes@google.com> Cc: <Valdis.Kletnieks@vt.edu> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-07 09:13:53 +01:00
return (ret < 0)? ret: 0;
}
/*
* Scan swap_map from current position to next entry still in use.
* Recycle to start on reaching the end, returning 0 when empty.
*/
static unsigned int find_next_to_unuse(struct swap_info_struct *si,
unsigned int prev)
{
unsigned int max = si->max;
unsigned int i = prev;
int count;
/*
* No need for swap_lock here: we're just looking
* for whether an entry is in use, not modifying it; false
* hits are okay, and sys_swapoff() has already prevented new
* allocations from this area (while holding swap_lock).
*/
for (;;) {
if (++i >= max) {
if (!prev) {
i = 0;
break;
}
/*
* No entries in use at top of swap_map,
* loop back to start and recheck there.
*/
max = prev + 1;
prev = 0;
i = 1;
}
count = si->swap_map[i];
if (count && swap_count(count) != SWAP_MAP_BAD)
break;
}
return i;
}
/*
* We completely avoid races by reading each swap page in advance,
* and then search for the process using it. All the necessary
* page table adjustments can then be made atomically.
*/
static int try_to_unuse(unsigned int type)
{
struct swap_info_struct * si = &swap_info[type];
struct mm_struct *start_mm;
unsigned short *swap_map;
unsigned short swcount;
struct page *page;
swp_entry_t entry;
unsigned int i = 0;
int retval = 0;
int reset_overflow = 0;
int shmem;
/*
* When searching mms for an entry, a good strategy is to
* start at the first mm we freed the previous entry from
* (though actually we don't notice whether we or coincidence
* freed the entry). Initialize this start_mm with a hold.
*
* A simpler strategy would be to start at the last mm we
* freed the previous entry from; but that would take less
* advantage of mmlist ordering, which clusters forked mms
* together, child after parent. If we race with dup_mmap(), we
* prefer to resolve parent before child, lest we miss entries
* duplicated after we scanned child: using last mm would invert
* that. Though it's only a serious concern when an overflowed
* swap count is reset from SWAP_MAP_MAX, preventing a rescan.
*/
start_mm = &init_mm;
atomic_inc(&init_mm.mm_users);
/*
* Keep on scanning until all entries have gone. Usually,
* one pass through swap_map is enough, but not necessarily:
* there are races when an instance of an entry might be missed.
*/
while ((i = find_next_to_unuse(si, i)) != 0) {
if (signal_pending(current)) {
retval = -EINTR;
break;
}
/*
* Get a page for the entry, using the existing swap
* cache page if there is one. Otherwise, get a clean
* page and read the swap into it.
*/
swap_map = &si->swap_map[i];
entry = swp_entry(type, i);
page = read_swap_cache_async(entry,
GFP_HIGHUSER_MOVABLE, NULL, 0);
if (!page) {
/*
* Either swap_duplicate() failed because entry
* has been freed independently, and will not be
* reused since sys_swapoff() already disabled
* allocation from here, or alloc_page() failed.
*/
if (!*swap_map)
continue;
retval = -ENOMEM;
break;
}
/*
* Don't hold on to start_mm if it looks like exiting.
*/
if (atomic_read(&start_mm->mm_users) == 1) {
mmput(start_mm);
start_mm = &init_mm;
atomic_inc(&init_mm.mm_users);
}
/*
* Wait for and lock page. When do_swap_page races with
* try_to_unuse, do_swap_page can handle the fault much
* faster than try_to_unuse can locate the entry. This
* apparently redundant "wait_on_page_locked" lets try_to_unuse
* defer to do_swap_page in such a case - in some tests,
* do_swap_page and try_to_unuse repeatedly compete.
*/
wait_on_page_locked(page);
wait_on_page_writeback(page);
lock_page(page);
wait_on_page_writeback(page);
/*
* Remove all references to entry.
* Whenever we reach init_mm, there's no address space
* to search, but use it as a reminder to search shmem.
*/
shmem = 0;
swcount = *swap_map;
if (swap_count(swcount)) {
if (start_mm == &init_mm)
shmem = shmem_unuse(entry, page);
else
retval = unuse_mm(start_mm, entry, page);
}
if (swap_count(*swap_map)) {
int set_start_mm = (*swap_map >= swcount);
struct list_head *p = &start_mm->mmlist;
struct mm_struct *new_start_mm = start_mm;
struct mm_struct *prev_mm = start_mm;
struct mm_struct *mm;
atomic_inc(&new_start_mm->mm_users);
atomic_inc(&prev_mm->mm_users);
spin_lock(&mmlist_lock);
while (swap_count(*swap_map) && !retval && !shmem &&
(p = p->next) != &start_mm->mmlist) {
mm = list_entry(p, struct mm_struct, mmlist);
if (!atomic_inc_not_zero(&mm->mm_users))
continue;
spin_unlock(&mmlist_lock);
mmput(prev_mm);
prev_mm = mm;
cond_resched();
swcount = *swap_map;
if (!swap_count(swcount)) /* any usage ? */
;
else if (mm == &init_mm) {
set_start_mm = 1;
shmem = shmem_unuse(entry, page);
} else
retval = unuse_mm(mm, entry, page);
if (set_start_mm &&
swap_count(*swap_map) < swcount) {
mmput(new_start_mm);
atomic_inc(&mm->mm_users);
new_start_mm = mm;
set_start_mm = 0;
}
spin_lock(&mmlist_lock);
}
spin_unlock(&mmlist_lock);
mmput(prev_mm);
mmput(start_mm);
start_mm = new_start_mm;
}
if (shmem) {
/* page has already been unlocked and released */
if (shmem > 0)
continue;
retval = shmem;
break;
}
if (retval) {
unlock_page(page);
page_cache_release(page);
break;
}
/*
* How could swap count reach 0x7ffe ?
* There's no way to repeat a swap page within an mm
* (except in shmem, where it's the shared object which takes
* the reference count)?
* We believe SWAP_MAP_MAX cannot occur.(if occur, unsigned
* short is too small....)
* If that's wrong, then we should worry more about
* exit_mmap() and do_munmap() cases described above:
* we might be resetting SWAP_MAP_MAX too early here.
* We know "Undead"s can happen, they're okay, so don't
* report them; but do report if we reset SWAP_MAP_MAX.
*/
/* We might release the lock_page() in unuse_mm(). */
if (!PageSwapCache(page) || page_private(page) != entry.val)
goto retry;
if (swap_count(*swap_map) == SWAP_MAP_MAX) {
spin_lock(&swap_lock);
*swap_map = encode_swapmap(0, true);
spin_unlock(&swap_lock);
reset_overflow = 1;
}
/*
* If a reference remains (rare), we would like to leave
* the page in the swap cache; but try_to_unmap could
* then re-duplicate the entry once we drop page lock,
* so we might loop indefinitely; also, that page could
* not be swapped out to other storage meanwhile. So:
* delete from cache even if there's another reference,
* after ensuring that the data has been saved to disk -
* since if the reference remains (rarer), it will be
* read from disk into another page. Splitting into two
* pages would be incorrect if swap supported "shared
* private" pages, but they are handled by tmpfs files.
*/
if (swap_count(*swap_map) &&
PageDirty(page) && PageSwapCache(page)) {
struct writeback_control wbc = {
.sync_mode = WB_SYNC_NONE,
};
swap_writepage(page, &wbc);
lock_page(page);
wait_on_page_writeback(page);
}
mm: try_to_unuse check removing right swap There's a possible race in try_to_unuse() which Nick Piggin led me to two years ago. Where it does lock_page() after read_swap_cache_async(), what if another task removed that page from swapcache just before we locked it? It would sail though the (*swap_map > 1) tests doing nothing (because it could not have been removed from swapcache before its swap references were gone), until it reaches the delete_from_swap_cache(page) near the bottom. Now imagine that this page has been allocated to swap on a different swap area while we dropped page lock (perhaps at the top, perhaps in unuse_mm): we could wrongly remove from swap cache before the page has been written to swap, so a subsequent do_swap_page() would read in stale data from swap. I think this case could not happen before: remove_exclusive_swap_page() refused while page count was raised. But now with reuse_swap_page() and try_to_free_swap() removing from swap cache without minding page count, I think it could happen - the previous patch argued that it was safe because try_to_unuse() already ignored page count, but overlooked that it might be breaking the assumptions in try_to_unuse() itself. Signed-off-by: Hugh Dickins <hugh@veritas.com> Cc: Lee Schermerhorn <lee.schermerhorn@hp.com> Cc: Rik van Riel <riel@redhat.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Robin Holt <holt@sgi.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-06 23:39:37 +01:00
/*
* It is conceivable that a racing task removed this page from
* swap cache just before we acquired the page lock at the top,
* or while we dropped it in unuse_mm(). The page might even
* be back in swap cache on another swap area: that we must not
* delete, since it may not have been written out to swap yet.
*/
if (PageSwapCache(page) &&
likely(page_private(page) == entry.val))
delete_from_swap_cache(page);
/*
* So we could skip searching mms once swap count went
* to 1, we did not mark any present ptes as dirty: must
* mark page dirty so shrink_page_list will preserve it.
*/
SetPageDirty(page);
retry:
unlock_page(page);
page_cache_release(page);
/*
* Make sure that we aren't completely killing
* interactive performance.
*/
cond_resched();
}
mmput(start_mm);
if (reset_overflow) {
printk(KERN_WARNING "swapoff: cleared swap entry overflow\n");
swap_overflow = 0;
}
return retval;
}
/*
* After a successful try_to_unuse, if no swap is now in use, we know
* we can empty the mmlist. swap_lock must be held on entry and exit.
* Note that mmlist_lock nests inside swap_lock, and an mm must be
* added to the mmlist just after page_duplicate - before would be racy.
*/
static void drain_mmlist(void)
{
struct list_head *p, *next;
unsigned int i;
for (i = 0; i < nr_swapfiles; i++)
if (swap_info[i].inuse_pages)
return;
spin_lock(&mmlist_lock);
list_for_each_safe(p, next, &init_mm.mmlist)
list_del_init(p);
spin_unlock(&mmlist_lock);
}
/*
* Use this swapdev's extent info to locate the (PAGE_SIZE) block which
* corresponds to page offset `offset'.
*/
sector_t map_swap_page(struct swap_info_struct *sis, pgoff_t offset)
{
struct swap_extent *se = sis->curr_swap_extent;
struct swap_extent *start_se = se;
for ( ; ; ) {
struct list_head *lh;
if (se->start_page <= offset &&
offset < (se->start_page + se->nr_pages)) {
return se->start_block + (offset - se->start_page);
}
lh = se->list.next;
if (lh == &sis->extent_list)
lh = lh->next;
se = list_entry(lh, struct swap_extent, list);
sis->curr_swap_extent = se;
BUG_ON(se == start_se); /* It *must* be present */
}
}
#ifdef CONFIG_HIBERNATION
/*
* Get the (PAGE_SIZE) block corresponding to given offset on the swapdev
* corresponding to given index in swap_info (swap type).
*/
sector_t swapdev_block(int swap_type, pgoff_t offset)
{
struct swap_info_struct *sis;
if (swap_type >= nr_swapfiles)
return 0;
sis = swap_info + swap_type;
return (sis->flags & SWP_WRITEOK) ? map_swap_page(sis, offset) : 0;
}
#endif /* CONFIG_HIBERNATION */
/*
* Free all of a swapdev's extent information
*/
static void destroy_swap_extents(struct swap_info_struct *sis)
{
while (!list_empty(&sis->extent_list)) {
struct swap_extent *se;
se = list_entry(sis->extent_list.next,
struct swap_extent, list);
list_del(&se->list);
kfree(se);
}
}
/*
* Add a block range (and the corresponding page range) into this swapdev's
* extent list. The extent list is kept sorted in page order.
*
* This function rather assumes that it is called in ascending page order.
*/
static int
add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
unsigned long nr_pages, sector_t start_block)
{
struct swap_extent *se;
struct swap_extent *new_se;
struct list_head *lh;
lh = sis->extent_list.prev; /* The highest page extent */
if (lh != &sis->extent_list) {
se = list_entry(lh, struct swap_extent, list);
BUG_ON(se->start_page + se->nr_pages != start_page);
if (se->start_block + se->nr_pages == start_block) {
/* Merge it */
se->nr_pages += nr_pages;
return 0;
}
}
/*
* No merge. Insert a new extent, preserving ordering.
*/
new_se = kmalloc(sizeof(*se), GFP_KERNEL);
if (new_se == NULL)
return -ENOMEM;
new_se->start_page = start_page;
new_se->nr_pages = nr_pages;
new_se->start_block = start_block;
list_add_tail(&new_se->list, &sis->extent_list);
return 1;
}
/*
* A `swap extent' is a simple thing which maps a contiguous range of pages
* onto a contiguous range of disk blocks. An ordered list of swap extents
* is built at swapon time and is then used at swap_writepage/swap_readpage
* time for locating where on disk a page belongs.
*
* If the swapfile is an S_ISBLK block device, a single extent is installed.
* This is done so that the main operating code can treat S_ISBLK and S_ISREG
* swap files identically.
*
* Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap
* extent list operates in PAGE_SIZE disk blocks. Both S_ISREG and S_ISBLK
* swapfiles are handled *identically* after swapon time.
*
* For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks
* and will parse them into an ordered extent list, in PAGE_SIZE chunks. If
* some stray blocks are found which do not fall within the PAGE_SIZE alignment
* requirements, they are simply tossed out - we will never use those blocks
* for swapping.
*
* For S_ISREG swapfiles we set S_SWAPFILE across the life of the swapon. This
* prevents root from shooting her foot off by ftruncating an in-use swapfile,
* which will scribble on the fs.
*
* The amount of disk space which a single swap extent represents varies.
* Typically it is in the 1-4 megabyte range. So we can have hundreds of
* extents in the list. To avoid much list walking, we cache the previous
* search location in `curr_swap_extent', and start new searches from there.
* This is extremely effective. The average number of iterations in
* map_swap_page() has been measured at about 0.3 per page. - akpm.
*/
static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span)
{
struct inode *inode;
unsigned blocks_per_page;
unsigned long page_no;
unsigned blkbits;
sector_t probe_block;
sector_t last_block;
sector_t lowest_block = -1;
sector_t highest_block = 0;
int nr_extents = 0;
int ret;
inode = sis->swap_file->f_mapping->host;
if (S_ISBLK(inode->i_mode)) {
ret = add_swap_extent(sis, 0, sis->max, 0);
*span = sis->pages;
goto done;
}
blkbits = inode->i_blkbits;
blocks_per_page = PAGE_SIZE >> blkbits;
/*
* Map all the blocks into the extent list. This code doesn't try
* to be very smart.
*/
probe_block = 0;
page_no = 0;
last_block = i_size_read(inode) >> blkbits;
while ((probe_block + blocks_per_page) <= last_block &&
page_no < sis->max) {
unsigned block_in_page;
sector_t first_block;
first_block = bmap(inode, probe_block);
if (first_block == 0)
goto bad_bmap;
/*
* It must be PAGE_SIZE aligned on-disk
*/
if (first_block & (blocks_per_page - 1)) {
probe_block++;
goto reprobe;
}
for (block_in_page = 1; block_in_page < blocks_per_page;
block_in_page++) {
sector_t block;
block = bmap(inode, probe_block + block_in_page);
if (block == 0)
goto bad_bmap;
if (block != first_block + block_in_page) {
/* Discontiguity */
probe_block++;
goto reprobe;
}
}
first_block >>= (PAGE_SHIFT - blkbits);
if (page_no) { /* exclude the header page */
if (first_block < lowest_block)
lowest_block = first_block;
if (first_block > highest_block)
highest_block = first_block;
}
/*
* We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks
*/
ret = add_swap_extent(sis, page_no, 1, first_block);
if (ret < 0)
goto out;
nr_extents += ret;
page_no++;
probe_block += blocks_per_page;
reprobe:
continue;
}
ret = nr_extents;
*span = 1 + highest_block - lowest_block;
if (page_no == 0)
page_no = 1; /* force Empty message */
sis->max = page_no;
sis->pages = page_no - 1;
sis->highest_bit = page_no - 1;
done:
sis->curr_swap_extent = list_entry(sis->extent_list.prev,
struct swap_extent, list);
goto out;
bad_bmap:
printk(KERN_ERR "swapon: swapfile has holes\n");
ret = -EINVAL;
out:
return ret;
}
SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
{
struct swap_info_struct * p = NULL;
unsigned short *swap_map;
struct file *swap_file, *victim;
struct address_space *mapping;
struct inode *inode;
char * pathname;
int i, type, prev;
int err;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
pathname = getname(specialfile);
err = PTR_ERR(pathname);
if (IS_ERR(pathname))
goto out;
victim = filp_open(pathname, O_RDWR|O_LARGEFILE, 0);
putname(pathname);
err = PTR_ERR(victim);
if (IS_ERR(victim))
goto out;
mapping = victim->f_mapping;
prev = -1;
spin_lock(&swap_lock);
for (type = swap_list.head; type >= 0; type = swap_info[type].next) {
p = swap_info + type;
if (p->flags & SWP_WRITEOK) {
if (p->swap_file->f_mapping == mapping)
break;
}
prev = type;
}
if (type < 0) {
err = -EINVAL;
spin_unlock(&swap_lock);
goto out_dput;
}
if (!security_vm_enough_memory(p->pages))
vm_unacct_memory(p->pages);
else {
err = -ENOMEM;
spin_unlock(&swap_lock);
goto out_dput;
}
if (prev < 0) {
swap_list.head = p->next;
} else {
swap_info[prev].next = p->next;
}
if (type == swap_list.next) {
/* just pick something that's safe... */
swap_list.next = swap_list.head;
}
if (p->prio < 0) {
for (i = p->next; i >= 0; i = swap_info[i].next)
swap_info[i].prio = p->prio--;
least_priority++;
}
nr_swap_pages -= p->pages;
total_swap_pages -= p->pages;
p->flags &= ~SWP_WRITEOK;
spin_unlock(&swap_lock);
current->flags |= PF_SWAPOFF;
err = try_to_unuse(type);
current->flags &= ~PF_SWAPOFF;
if (err) {
/* re-insert swap space back into swap_list */
spin_lock(&swap_lock);
if (p->prio < 0)
p->prio = --least_priority;
prev = -1;
for (i = swap_list.head; i >= 0; i = swap_info[i].next) {
if (p->prio >= swap_info[i].prio)
break;
prev = i;
}
p->next = i;
if (prev < 0)
swap_list.head = swap_list.next = p - swap_info;
else
swap_info[prev].next = p - swap_info;
nr_swap_pages += p->pages;
total_swap_pages += p->pages;
p->flags |= SWP_WRITEOK;
spin_unlock(&swap_lock);
goto out_dput;
}
/* wait for any unplug function to finish */
down_write(&swap_unplug_sem);
up_write(&swap_unplug_sem);
destroy_swap_extents(p);
mutex_lock(&swapon_mutex);
spin_lock(&swap_lock);
drain_mmlist();
/* wait for anyone still in scan_swap_map */
p->highest_bit = 0; /* cuts scans short */
while (p->flags >= SWP_SCANNING) {
spin_unlock(&swap_lock);
schedule_timeout_uninterruptible(1);
spin_lock(&swap_lock);
}
swap_file = p->swap_file;
p->swap_file = NULL;
p->max = 0;
swap_map = p->swap_map;
p->swap_map = NULL;
p->flags = 0;
spin_unlock(&swap_lock);
mutex_unlock(&swapon_mutex);
vfree(swap_map);
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 03:07:58 +01:00
/* Destroy swap account informatin */
swap_cgroup_swapoff(type);
inode = mapping->host;
if (S_ISBLK(inode->i_mode)) {
struct block_device *bdev = I_BDEV(inode);
set_blocksize(bdev, p->old_block_size);
bd_release(bdev);
} else {
mutex_lock(&inode->i_mutex);
inode->i_flags &= ~S_SWAPFILE;
mutex_unlock(&inode->i_mutex);
}
filp_close(swap_file, NULL);
err = 0;
out_dput:
filp_close(victim, NULL);
out:
return err;
}
#ifdef CONFIG_PROC_FS
/* iterator */
static void *swap_start(struct seq_file *swap, loff_t *pos)
{
struct swap_info_struct *ptr = swap_info;
int i;
loff_t l = *pos;
mutex_lock(&swapon_mutex);
if (!l)
return SEQ_START_TOKEN;
for (i = 0; i < nr_swapfiles; i++, ptr++) {
if (!(ptr->flags & SWP_USED) || !ptr->swap_map)
continue;
if (!--l)
return ptr;
}
return NULL;
}
static void *swap_next(struct seq_file *swap, void *v, loff_t *pos)
{
struct swap_info_struct *ptr;
struct swap_info_struct *endptr = swap_info + nr_swapfiles;
if (v == SEQ_START_TOKEN)
ptr = swap_info;
else {
ptr = v;
ptr++;
}
for (; ptr < endptr; ptr++) {
if (!(ptr->flags & SWP_USED) || !ptr->swap_map)
continue;
++*pos;
return ptr;
}
return NULL;
}
static void swap_stop(struct seq_file *swap, void *v)
{
mutex_unlock(&swapon_mutex);
}
static int swap_show(struct seq_file *swap, void *v)
{
struct swap_info_struct *ptr = v;
struct file *file;
int len;
if (ptr == SEQ_START_TOKEN) {
seq_puts(swap,"Filename\t\t\t\tType\t\tSize\tUsed\tPriority\n");
return 0;
}
file = ptr->swap_file;
len = seq_path(swap, &file->f_path, " \t\n\\");
seq_printf(swap, "%*s%s\t%u\t%u\t%d\n",
len < 40 ? 40 - len : 1, " ",
S_ISBLK(file->f_path.dentry->d_inode->i_mode) ?
"partition" : "file\t",
ptr->pages << (PAGE_SHIFT - 10),
ptr->inuse_pages << (PAGE_SHIFT - 10),
ptr->prio);
return 0;
}
static const struct seq_operations swaps_op = {
.start = swap_start,
.next = swap_next,
.stop = swap_stop,
.show = swap_show
};
static int swaps_open(struct inode *inode, struct file *file)
{
return seq_open(file, &swaps_op);
}
static const struct file_operations proc_swaps_operations = {
.open = swaps_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
static int __init procswaps_init(void)
{
proc_create("swaps", 0, NULL, &proc_swaps_operations);
return 0;
}
__initcall(procswaps_init);
#endif /* CONFIG_PROC_FS */
#ifdef MAX_SWAPFILES_CHECK
static int __init max_swapfiles_check(void)
{
MAX_SWAPFILES_CHECK();
return 0;
}
late_initcall(max_swapfiles_check);
#endif
/*
* Written 01/25/92 by Simmule Turner, heavily changed by Linus.
*
* The swapon system call
*/
SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
{
struct swap_info_struct * p;
char *name = NULL;
struct block_device *bdev = NULL;
struct file *swap_file = NULL;
struct address_space *mapping;
unsigned int type;
int i, prev;
int error;
union swap_header *swap_header = NULL;
unsigned int nr_good_pages = 0;
int nr_extents = 0;
sector_t span;
unsigned long maxpages = 1;
unsigned long swapfilepages;
unsigned short *swap_map = NULL;
struct page *page = NULL;
struct inode *inode = NULL;
int did_down = 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
spin_lock(&swap_lock);
p = swap_info;
for (type = 0 ; type < nr_swapfiles ; type++,p++)
if (!(p->flags & SWP_USED))
break;
error = -EPERM;
[PATCH] Swapless page migration: add R/W migration entries Implement read/write migration ptes We take the upper two swapfiles for the two types of migration ptes and define a series of macros in swapops.h. The VM is modified to handle the migration entries. migration entries can only be encountered when the page they are pointing to is locked. This limits the number of places one has to fix. We also check in copy_pte_range and in mprotect_pte_range() for migration ptes. We check for migration ptes in do_swap_cache and call a function that will then wait on the page lock. This allows us to effectively stop all accesses to apge. Migration entries are created by try_to_unmap if called for migration and removed by local functions in migrate.c From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration (I've no NUMA, just hacking it up to migrate recklessly while running load), I've hit the BUG_ON(!PageLocked(p)) in migration_entry_to_page. This comes from an orphaned migration entry, unrelated to the current correctly locked migration, but hit by remove_anon_migration_ptes as it checks an address in each vma of the anon_vma list. Such an orphan may be left behind if an earlier migration raced with fork: copy_one_pte can duplicate a migration entry from parent to child, after remove_anon_migration_ptes has checked the child vma, but before it has removed it from the parent vma. (If the process were later to fault on this orphaned entry, it would hit the same BUG from migration_entry_wait.) This could be fixed by locking anon_vma in copy_one_pte, but we'd rather not. There's no such problem with file pages, because vma_prio_tree_add adds child vma after parent vma, and the page table locking at each end is enough to serialize. Follow that example with anon_vma: add new vmas to the tail instead of the head. (There's no corresponding problem when inserting migration entries, because a missed pte will leave the page count and mapcount high, which is allowed for. And there's no corresponding problem when migrating via swap, because a leftover swap entry will be correctly faulted. But the swapless method has no refcounting of its entries.) From: Ingo Molnar <mingo@elte.hu> pte_unmap_unlock() takes the pte pointer as an argument. From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration, gcc has tried to exec a pointer instead of a string: smells like COW mappings are not being properly write-protected on fork. The protection in copy_one_pte looks very convincing, until at last you realize that the second arg to make_migration_entry is a boolean "write", and SWP_MIGRATION_READ is 30. Anyway, it's better done like in change_pte_range, using is_write_migration_entry and make_migration_entry_read. From: Hugh Dickins <hugh@veritas.com> Remove unnecessary obfuscation from sys_swapon's range check on swap type, which blew up causing memory corruption once swapless migration made MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT. Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Christoph Lameter <clameter@engr.sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> From: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 11:03:35 +02:00
if (type >= MAX_SWAPFILES) {
spin_unlock(&swap_lock);
goto out;
}
if (type >= nr_swapfiles)
nr_swapfiles = type+1;
memset(p, 0, sizeof(*p));
INIT_LIST_HEAD(&p->extent_list);
p->flags = SWP_USED;
p->next = -1;
spin_unlock(&swap_lock);
name = getname(specialfile);
error = PTR_ERR(name);
if (IS_ERR(name)) {
name = NULL;
goto bad_swap_2;
}
swap_file = filp_open(name, O_RDWR|O_LARGEFILE, 0);
error = PTR_ERR(swap_file);
if (IS_ERR(swap_file)) {
swap_file = NULL;
goto bad_swap_2;
}
p->swap_file = swap_file;
mapping = swap_file->f_mapping;
inode = mapping->host;
error = -EBUSY;
for (i = 0; i < nr_swapfiles; i++) {
struct swap_info_struct *q = &swap_info[i];
if (i == type || !q->swap_file)
continue;
if (mapping == q->swap_file->f_mapping)
goto bad_swap;
}
error = -EINVAL;
if (S_ISBLK(inode->i_mode)) {
bdev = I_BDEV(inode);
error = bd_claim(bdev, sys_swapon);
if (error < 0) {
bdev = NULL;
error = -EINVAL;
goto bad_swap;
}
p->old_block_size = block_size(bdev);
error = set_blocksize(bdev, PAGE_SIZE);
if (error < 0)
goto bad_swap;
p->bdev = bdev;
} else if (S_ISREG(inode->i_mode)) {
p->bdev = inode->i_sb->s_bdev;
mutex_lock(&inode->i_mutex);
did_down = 1;
if (IS_SWAPFILE(inode)) {
error = -EBUSY;
goto bad_swap;
}
} else {
goto bad_swap;
}
swapfilepages = i_size_read(inode) >> PAGE_SHIFT;
/*
* Read the swap header.
*/
if (!mapping->a_ops->readpage) {
error = -EINVAL;
goto bad_swap;
}
page = read_mapping_page(mapping, 0, swap_file);
if (IS_ERR(page)) {
error = PTR_ERR(page);
goto bad_swap;
}
swap_header = kmap(page);
if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) {
printk(KERN_ERR "Unable to find swap-space signature\n");
error = -EINVAL;
goto bad_swap;
}
/* swap partition endianess hack... */
if (swab32(swap_header->info.version) == 1) {
swab32s(&swap_header->info.version);
swab32s(&swap_header->info.last_page);
swab32s(&swap_header->info.nr_badpages);
for (i = 0; i < swap_header->info.nr_badpages; i++)
swab32s(&swap_header->info.badpages[i]);
}
/* Check the swap header's sub-version */
if (swap_header->info.version != 1) {
printk(KERN_WARNING
"Unable to handle swap header version %d\n",
swap_header->info.version);
error = -EINVAL;
goto bad_swap;
}
p->lowest_bit = 1;
p->cluster_next = 1;
/*
* Find out how many pages are allowed for a single swap
* device. There are two limiting factors: 1) the number of
* bits for the swap offset in the swp_entry_t type and
* 2) the number of bits in the a swap pte as defined by
* the different architectures. In order to find the
* largest possible bit mask a swap entry with swap type 0
* and swap offset ~0UL is created, encoded to a swap pte,
* decoded to a swp_entry_t again and finally the swap
* offset is extracted. This will mask all the bits from
* the initial ~0UL mask that can't be encoded in either
* the swp_entry_t or the architecture definition of a
* swap pte.
*/
maxpages = swp_offset(pte_to_swp_entry(
swp_entry_to_pte(swp_entry(0, ~0UL)))) - 1;
if (maxpages > swap_header->info.last_page)
maxpages = swap_header->info.last_page;
p->highest_bit = maxpages - 1;
error = -EINVAL;
if (!maxpages)
goto bad_swap;
if (swapfilepages && maxpages > swapfilepages) {
printk(KERN_WARNING
"Swap area shorter than signature indicates\n");
goto bad_swap;
}
if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode))
goto bad_swap;
if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES)
goto bad_swap;
/* OK, set up the swap map and apply the bad block list */
swap_map = vmalloc(maxpages * sizeof(short));
if (!swap_map) {
error = -ENOMEM;
goto bad_swap;
}
memset(swap_map, 0, maxpages * sizeof(short));
for (i = 0; i < swap_header->info.nr_badpages; i++) {
int page_nr = swap_header->info.badpages[i];
if (page_nr <= 0 || page_nr >= swap_header->info.last_page) {
error = -EINVAL;
goto bad_swap;
}
swap_map[page_nr] = SWAP_MAP_BAD;
}
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 03:07:58 +01:00
error = swap_cgroup_swapon(type, maxpages);
if (error)
goto bad_swap;
nr_good_pages = swap_header->info.last_page -
swap_header->info.nr_badpages -
1 /* header page */;
if (nr_good_pages) {
swap_map[0] = SWAP_MAP_BAD;
p->max = maxpages;
p->pages = nr_good_pages;
nr_extents = setup_swap_extents(p, &span);
if (nr_extents < 0) {
error = nr_extents;
goto bad_swap;
}
nr_good_pages = p->pages;
}
if (!nr_good_pages) {
printk(KERN_WARNING "Empty swap-file\n");
error = -EINVAL;
goto bad_swap;
}
if (blk_queue_nonrot(bdev_get_queue(p->bdev))) {
p->flags |= SWP_SOLIDSTATE;
p->cluster_next = 1 + (random32() % p->highest_bit);
}
if (discard_swap(p) == 0)
p->flags |= SWP_DISCARDABLE;
mutex_lock(&swapon_mutex);
spin_lock(&swap_lock);
if (swap_flags & SWAP_FLAG_PREFER)
p->prio =
(swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT;
else
p->prio = --least_priority;
p->swap_map = swap_map;
p->flags |= SWP_WRITEOK;
nr_swap_pages += nr_good_pages;
total_swap_pages += nr_good_pages;
printk(KERN_INFO "Adding %uk swap on %s. "
"Priority:%d extents:%d across:%lluk %s%s\n",
nr_good_pages<<(PAGE_SHIFT-10), name, p->prio,
nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10),
(p->flags & SWP_SOLIDSTATE) ? "SS" : "",
(p->flags & SWP_DISCARDABLE) ? "D" : "");
/* insert swap space into swap_list: */
prev = -1;
for (i = swap_list.head; i >= 0; i = swap_info[i].next) {
if (p->prio >= swap_info[i].prio) {
break;
}
prev = i;
}
p->next = i;
if (prev < 0) {
swap_list.head = swap_list.next = p - swap_info;
} else {
swap_info[prev].next = p - swap_info;
}
spin_unlock(&swap_lock);
mutex_unlock(&swapon_mutex);
error = 0;
goto out;
bad_swap:
if (bdev) {
set_blocksize(bdev, p->old_block_size);
bd_release(bdev);
}
destroy_swap_extents(p);
memcg: swap cgroup for remembering usage For accounting swap, we need a record per swap entry, at least. This patch adds following function. - swap_cgroup_swapon() .... called from swapon - swap_cgroup_swapoff() ... called at the end of swapoff. - swap_cgroup_record() .... record information of swap entry. - swap_cgroup_lookup() .... lookup information of swap entry. This patch just implements "how to record information". No actual method for limit the usage of swap. These routine uses flat table to record and lookup. "wise" lookup system like radix-tree requires requires memory allocation at new records but swap-out is usually called under memory shortage (or memcg hits limit.) So, I used static allocation. (maybe dynamic allocation is not very hard but it adds additional memory allocation in memory shortage path.) Note1: In this, we use pointer to record information and this means 8bytes per swap entry. I think we can reduce this when we create "id of cgroup" in the range of 0-65535 or 0-255. Reported-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Reported-by: Hugh Dickins <hugh@veritas.com> Reported-by: Balbir Singh <balbir@linux.vnet.ibm.com> Reported-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Pavel Emelianov <xemul@openvz.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 03:07:58 +01:00
swap_cgroup_swapoff(type);
bad_swap_2:
spin_lock(&swap_lock);
p->swap_file = NULL;
p->flags = 0;
spin_unlock(&swap_lock);
vfree(swap_map);
if (swap_file)
filp_close(swap_file, NULL);
out:
if (page && !IS_ERR(page)) {
kunmap(page);
page_cache_release(page);
}
if (name)
putname(name);
if (did_down) {
if (!error)
inode->i_flags |= S_SWAPFILE;
mutex_unlock(&inode->i_mutex);
}
return error;
}
void si_swapinfo(struct sysinfo *val)
{
unsigned int i;
unsigned long nr_to_be_unused = 0;
spin_lock(&swap_lock);
for (i = 0; i < nr_swapfiles; i++) {
if (!(swap_info[i].flags & SWP_USED) ||
(swap_info[i].flags & SWP_WRITEOK))
continue;
nr_to_be_unused += swap_info[i].inuse_pages;
}
val->freeswap = nr_swap_pages + nr_to_be_unused;
val->totalswap = total_swap_pages + nr_to_be_unused;
spin_unlock(&swap_lock);
}
/*
* Verify that a swap entry is valid and increment its swap map count.
*
* Note: if swap_map[] reaches SWAP_MAP_MAX the entries are treated as
* "permanent", but will be reclaimed by the next swapoff.
* Returns error code in following case.
* - success -> 0
* - swp_entry is invalid -> EINVAL
* - swp_entry is migration entry -> EINVAL
* - swap-cache reference is requested but there is already one. -> EEXIST
* - swap-cache reference is requested but the entry is not used. -> ENOENT
*/
static int __swap_duplicate(swp_entry_t entry, bool cache)
{
struct swap_info_struct * p;
unsigned long offset, type;
int result = -EINVAL;
int count;
bool has_cache;
[PATCH] Swapless page migration: add R/W migration entries Implement read/write migration ptes We take the upper two swapfiles for the two types of migration ptes and define a series of macros in swapops.h. The VM is modified to handle the migration entries. migration entries can only be encountered when the page they are pointing to is locked. This limits the number of places one has to fix. We also check in copy_pte_range and in mprotect_pte_range() for migration ptes. We check for migration ptes in do_swap_cache and call a function that will then wait on the page lock. This allows us to effectively stop all accesses to apge. Migration entries are created by try_to_unmap if called for migration and removed by local functions in migrate.c From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration (I've no NUMA, just hacking it up to migrate recklessly while running load), I've hit the BUG_ON(!PageLocked(p)) in migration_entry_to_page. This comes from an orphaned migration entry, unrelated to the current correctly locked migration, but hit by remove_anon_migration_ptes as it checks an address in each vma of the anon_vma list. Such an orphan may be left behind if an earlier migration raced with fork: copy_one_pte can duplicate a migration entry from parent to child, after remove_anon_migration_ptes has checked the child vma, but before it has removed it from the parent vma. (If the process were later to fault on this orphaned entry, it would hit the same BUG from migration_entry_wait.) This could be fixed by locking anon_vma in copy_one_pte, but we'd rather not. There's no such problem with file pages, because vma_prio_tree_add adds child vma after parent vma, and the page table locking at each end is enough to serialize. Follow that example with anon_vma: add new vmas to the tail instead of the head. (There's no corresponding problem when inserting migration entries, because a missed pte will leave the page count and mapcount high, which is allowed for. And there's no corresponding problem when migrating via swap, because a leftover swap entry will be correctly faulted. But the swapless method has no refcounting of its entries.) From: Ingo Molnar <mingo@elte.hu> pte_unmap_unlock() takes the pte pointer as an argument. From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration, gcc has tried to exec a pointer instead of a string: smells like COW mappings are not being properly write-protected on fork. The protection in copy_one_pte looks very convincing, until at last you realize that the second arg to make_migration_entry is a boolean "write", and SWP_MIGRATION_READ is 30. Anyway, it's better done like in change_pte_range, using is_write_migration_entry and make_migration_entry_read. From: Hugh Dickins <hugh@veritas.com> Remove unnecessary obfuscation from sys_swapon's range check on swap type, which blew up causing memory corruption once swapless migration made MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT. Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Christoph Lameter <clameter@engr.sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> From: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 11:03:35 +02:00
if (is_migration_entry(entry))
return -EINVAL;
[PATCH] Swapless page migration: add R/W migration entries Implement read/write migration ptes We take the upper two swapfiles for the two types of migration ptes and define a series of macros in swapops.h. The VM is modified to handle the migration entries. migration entries can only be encountered when the page they are pointing to is locked. This limits the number of places one has to fix. We also check in copy_pte_range and in mprotect_pte_range() for migration ptes. We check for migration ptes in do_swap_cache and call a function that will then wait on the page lock. This allows us to effectively stop all accesses to apge. Migration entries are created by try_to_unmap if called for migration and removed by local functions in migrate.c From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration (I've no NUMA, just hacking it up to migrate recklessly while running load), I've hit the BUG_ON(!PageLocked(p)) in migration_entry_to_page. This comes from an orphaned migration entry, unrelated to the current correctly locked migration, but hit by remove_anon_migration_ptes as it checks an address in each vma of the anon_vma list. Such an orphan may be left behind if an earlier migration raced with fork: copy_one_pte can duplicate a migration entry from parent to child, after remove_anon_migration_ptes has checked the child vma, but before it has removed it from the parent vma. (If the process were later to fault on this orphaned entry, it would hit the same BUG from migration_entry_wait.) This could be fixed by locking anon_vma in copy_one_pte, but we'd rather not. There's no such problem with file pages, because vma_prio_tree_add adds child vma after parent vma, and the page table locking at each end is enough to serialize. Follow that example with anon_vma: add new vmas to the tail instead of the head. (There's no corresponding problem when inserting migration entries, because a missed pte will leave the page count and mapcount high, which is allowed for. And there's no corresponding problem when migrating via swap, because a leftover swap entry will be correctly faulted. But the swapless method has no refcounting of its entries.) From: Ingo Molnar <mingo@elte.hu> pte_unmap_unlock() takes the pte pointer as an argument. From: Hugh Dickins <hugh@veritas.com> Several times while testing swapless page migration, gcc has tried to exec a pointer instead of a string: smells like COW mappings are not being properly write-protected on fork. The protection in copy_one_pte looks very convincing, until at last you realize that the second arg to make_migration_entry is a boolean "write", and SWP_MIGRATION_READ is 30. Anyway, it's better done like in change_pte_range, using is_write_migration_entry and make_migration_entry_read. From: Hugh Dickins <hugh@veritas.com> Remove unnecessary obfuscation from sys_swapon's range check on swap type, which blew up causing memory corruption once swapless migration made MAX_SWAPFILES no longer 2 ^ MAX_SWAPFILES_SHIFT. Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Christoph Lameter <clameter@engr.sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu> From: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-06-23 11:03:35 +02:00
type = swp_type(entry);
if (type >= nr_swapfiles)
goto bad_file;
p = type + swap_info;
offset = swp_offset(entry);
spin_lock(&swap_lock);
if (unlikely(offset >= p->max))
goto unlock_out;
count = swap_count(p->swap_map[offset]);
has_cache = swap_has_cache(p->swap_map[offset]);
if (cache == SWAP_CACHE) { /* called for swapcache/swapin-readahead */
/* set SWAP_HAS_CACHE if there is no cache and entry is used */
if (!has_cache && count) {
p->swap_map[offset] = encode_swapmap(count, true);
result = 0;
} else if (has_cache) /* someone added cache */
result = -EEXIST;
else if (!count) /* no users */
result = -ENOENT;
} else if (count || has_cache) {
if (count < SWAP_MAP_MAX - 1) {
p->swap_map[offset] = encode_swapmap(count + 1,
has_cache);
result = 0;
} else if (count <= SWAP_MAP_MAX) {
if (swap_overflow++ < 5)
printk(KERN_WARNING
"swap_dup: swap entry overflow\n");
p->swap_map[offset] = encode_swapmap(SWAP_MAP_MAX,
has_cache);
result = 0;
}
} else
result = -ENOENT; /* unused swap entry */
unlock_out:
spin_unlock(&swap_lock);
out:
return result;
bad_file:
printk(KERN_ERR "swap_dup: %s%08lx\n", Bad_file, entry.val);
goto out;
}
/*
* increase reference count of swap entry by 1.
*/
void swap_duplicate(swp_entry_t entry)
{
__swap_duplicate(entry, SWAP_MAP);
}
/*
* @entry: swap entry for which we allocate swap cache.
*
* Called when allocating swap cache for exising swap entry,
* This can return error codes. Returns 0 at success.
* -EBUSY means there is a swap cache.
* Note: return code is different from swap_duplicate().
*/
int swapcache_prepare(swp_entry_t entry)
{
return __swap_duplicate(entry, SWAP_CACHE);
}
struct swap_info_struct *
get_swap_info_struct(unsigned type)
{
return &swap_info[type];
}
/*
* swap_lock prevents swap_map being freed. Don't grab an extra
* reference on the swaphandle, it doesn't matter if it becomes unused.
*/
int valid_swaphandles(swp_entry_t entry, unsigned long *offset)
{
struct swap_info_struct *si;
int our_page_cluster = page_cluster;
pgoff_t target, toff;
pgoff_t base, end;
int nr_pages = 0;
if (!our_page_cluster) /* no readahead */
return 0;
si = &swap_info[swp_type(entry)];
target = swp_offset(entry);
base = (target >> our_page_cluster) << our_page_cluster;
end = base + (1 << our_page_cluster);
if (!base) /* first page is swap header */
base++;
spin_lock(&swap_lock);
if (end > si->max) /* don't go beyond end of map */
end = si->max;
/* Count contiguous allocated slots above our target */
for (toff = target; ++toff < end; nr_pages++) {
/* Don't read in free or bad pages */
if (!si->swap_map[toff])
break;
if (swap_count(si->swap_map[toff]) == SWAP_MAP_BAD)
break;
}
/* Count contiguous allocated slots below our target */
for (toff = target; --toff >= base; nr_pages++) {
/* Don't read in free or bad pages */
if (!si->swap_map[toff])
break;
if (swap_count(si->swap_map[toff]) == SWAP_MAP_BAD)
break;
}
spin_unlock(&swap_lock);
/*
* Indicate starting offset, and return number of pages to get:
* if only 1, say 0, since there's then no readahead to be done.
*/
*offset = ++toff;
return nr_pages? ++nr_pages: 0;
}