#include <linux/vmalloc.h>
#include <linux/pagemap.h>
#include <linux/namei.h>
-#include <linux/shm.h>
+#include <linux/shmem_fs.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/ksm.h>
#include <linux/rmap.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/memcontrol.h>
#include <linux/poll.h>
+#include <linux/oom.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
}
/*
- * 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);
- 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
- * 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.
*/
#define SWAPFILE_CLUSTER 256
#define LATENCY_LIMIT 256
-static inline unsigned long scan_swap_map(struct swap_info_struct *si,
- unsigned char usage)
+static unsigned long scan_swap_map(struct swap_info_struct *si,
+ unsigned char usage)
{
unsigned long offset;
unsigned long scan_base;
disk->fops->swap_slot_free_notify(p->bdev, offset);
}
+ if (!swap_count(count)) {
+ mem_cgroup_uncharge_swap(entry);
+ if (p->notify_swap_entry_free_fn)
+ p->notify_swap_entry_free_fn(offset);
+ }
+
return usage;
}
static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, swp_entry_t entry, struct page *page)
{
- struct mem_cgroup *ptr = NULL;
+ struct mem_cgroup *ptr;
spinlock_t *ptl;
pte_t *pte;
int ret = 1;
pmd = pmd_offset(pud, addr);
do {
next = pmd_addr_end(addr, end);
- if (unlikely(pmd_trans_huge(*pmd)))
- continue;
- if (pmd_none_or_clear_bad(pmd))
+ if (pmd_none_or_trans_huge_or_clear_bad(pmd))
continue;
ret = unuse_pte_range(vma, pmd, addr, next, entry, page);
if (ret)
goto out;
}
+static void enable_swap_info(struct swap_info_struct *p, int prio,
+ unsigned char *swap_map)
+{
+ int i, prev;
+
+ spin_lock(&swap_lock);
+ if (prio >= 0)
+ p->prio = prio;
+ else
+ p->prio = --least_priority;
+ p->swap_map = swap_map;
+ p->flags |= SWP_WRITEOK;
+ nr_swap_pages += p->pages;
+ total_swap_pages += p->pages;
+
+ /* 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->type;
+ else
+ swap_info[prev]->next = p->type;
+ spin_unlock(&swap_lock);
+}
+
SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
{
struct swap_info_struct *p = NULL;
struct address_space *mapping;
struct inode *inode;
char *pathname;
+ int oom_score_adj;
int i, type, prev;
int err;
p->flags &= ~SWP_WRITEOK;
spin_unlock(&swap_lock);
- current->flags |= PF_OOM_ORIGIN;
+ oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX);
err = try_to_unuse(type);
- current->flags &= ~PF_OOM_ORIGIN;
+ compare_swap_oom_score_adj(OOM_SCORE_ADJ_MAX, oom_score_adj);
if (err) {
+ /*
+ * reading p->prio and p->swap_map outside the lock is
+ * safe here because only sys_swapon and sys_swapoff
+ * change them, and there can be no other sys_swapon or
+ * sys_swapoff for this swap_info_struct at this point.
+ */
/* 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 = type;
- else
- swap_info[prev]->next = type;
- nr_swap_pages += p->pages;
- total_swap_pages += p->pages;
- p->flags |= SWP_WRITEOK;
- spin_unlock(&swap_lock);
+ enable_swap_info(p, p->prio, p->swap_map);
goto out_dput;
}
- /* wait for any unplug function to finish */
- down_write(&swap_unplug_sem);
- up_write(&swap_unplug_sem);
-
destroy_swap_extents(p);
if (p->flags & SWP_CONTINUED)
free_swap_count_continuations(p);
}
#ifdef CONFIG_PROC_FS
-struct proc_swaps {
- struct seq_file seq;
- int event;
-};
-
static unsigned swaps_poll(struct file *file, poll_table *wait)
{
- struct proc_swaps *s = file->private_data;
+ struct seq_file *seq = file->private_data;
poll_wait(file, &proc_poll_wait, wait);
- if (s->event != atomic_read(&proc_poll_event)) {
- s->event = atomic_read(&proc_poll_event);
+ if (seq->poll_event != atomic_read(&proc_poll_event)) {
+ seq->poll_event = atomic_read(&proc_poll_event);
return POLLIN | POLLRDNORM | POLLERR | POLLPRI;
}
static int swaps_open(struct inode *inode, struct file *file)
{
- struct proc_swaps *s;
+ struct seq_file *seq;
int ret;
- s = kmalloc(sizeof(struct proc_swaps), GFP_KERNEL);
- if (!s)
- return -ENOMEM;
-
- file->private_data = s;
-
ret = seq_open(file, &swaps_op);
- if (ret) {
- kfree(s);
+ if (ret)
return ret;
- }
- s->seq.private = s;
- s->event = atomic_read(&proc_poll_event);
- return ret;
+ seq = file->private_data;
+ seq->poll_event = atomic_read(&proc_poll_event);
+ return 0;
}
static const struct file_operations proc_swaps_operations = {
/*
* 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
+ * device. There are three 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 swap pte as defined by the
+ * the different architectures, and 3) the number of free bits
+ * in an exceptional radix_tree entry. 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
+ * 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.
+ * swap pte. Then the same is done for a radix_tree entry.
*/
maxpages = swp_offset(pte_to_swp_entry(
- swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1;
+ swp_entry_to_pte(swp_entry(0, ~0UL))));
+ maxpages = swp_offset(radix_to_swp_entry(
+ swp_to_radix_entry(swp_entry(0, maxpages)))) + 1;
+
if (maxpages > swap_header->info.last_page) {
maxpages = swap_header->info.last_page + 1;
/* p->max is an unsigned int: don't overflow it */
sector_t *span)
{
int i;
- int error;
unsigned int nr_good_pages;
int nr_extents;
for (i = 0; i < swap_header->info.nr_badpages; i++) {
unsigned int page_nr = swap_header->info.badpages[i];
- if (page_nr == 0 || page_nr > swap_header->info.last_page) {
- error = -EINVAL;
- goto bad_swap;
- }
+ if (page_nr == 0 || page_nr > swap_header->info.last_page)
+ return -EINVAL;
if (page_nr < maxpages) {
swap_map[page_nr] = SWAP_MAP_BAD;
nr_good_pages--;
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;
- }
+ if (nr_extents < 0)
+ return nr_extents;
nr_good_pages = p->pages;
}
if (!nr_good_pages) {
printk(KERN_WARNING "Empty swap-file\n");
- error = -EINVAL;
- goto bad_swap;
+ return -EINVAL;
}
return nr_extents;
-
-bad_swap:
- return error;
}
SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
char *name;
struct file *swap_file = NULL;
struct address_space *mapping;
- int i, prev;
+ int i;
+ int prio;
int error;
union swap_header *swap_header;
- unsigned int nr_good_pages;
int nr_extents;
sector_t span;
unsigned long maxpages;
p->swap_file = swap_file;
mapping = swap_file->f_mapping;
- inode = mapping->host;
for (i = 0; i < nr_swapfiles; i++) {
struct swap_info_struct *q = swap_info[i];
}
}
+ inode = mapping->host;
+ /* If S_ISREG(inode->i_mode) will do mutex_lock(&inode->i_mutex); */
error = claim_swapfile(p, inode);
if (unlikely(error))
goto bad_swap;
error = nr_extents;
goto bad_swap;
}
- nr_good_pages = p->pages;
if (p->bdev) {
if (blk_queue_nonrot(bdev_get_queue(p->bdev))) {
}
mutex_lock(&swapon_mutex);
- spin_lock(&swap_lock);
+ prio = -1;
if (swap_flags & SWAP_FLAG_PREFER)
- p->prio =
+ 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;
+ enable_swap_info(p, prio, swap_map);
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,
+ p->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->type;
- else
- swap_info[prev]->next = p->type;
- spin_unlock(&swap_lock);
mutex_unlock(&swapon_mutex);
atomic_inc(&proc_poll_event);
wake_up_interruptible(&proc_poll_wait);
spin_unlock(&swap_lock);
vfree(swap_map);
if (swap_file) {
- if (inode && S_ISREG(inode->i_mode))
+ if (inode && S_ISREG(inode->i_mode)) {
mutex_unlock(&inode->i_mutex);
+ inode = NULL;
+ }
filp_close(swap_file, NULL);
}
out:
}
/*
+ * Sets callback for event when swap_map[offset] == 0
+ * i.e. page at this swap offset is not longer used.
+ *
+ * type: identifies swap file
+ * fn: callback function
+ */
+void set_notify_swap_entry_free(unsigned type, void (*fn) (unsigned long))
+{
+ struct swap_info_struct *sis;
+ sis = swap_info[type];
+ BUG_ON(!sis);
+ sis->notify_swap_entry_free_fn = fn;
+ return;
+}
+EXPORT_SYMBOL(set_notify_swap_entry_free);
+
+/*
* swap_lock prevents swap_map being freed. Don't grab an extra
* reference on the swaphandle, it doesn't matter if it becomes unused.
*/
projects / linux-flexiantxendom0.git / blobdiff