/**
* write_one_page - write out a single page and optionally wait on I/O
* @page: the page to write
* @wait: if true, wait on writeout
*
* The page must be locked by the caller and will be unlocked upon return.
*
* write_one_page() returns a negative error code if I/O failed.
*/
int write_one_page(struct page *page, int wait)
{
struct address_space *mapping = page->mapping;
int ret = 0;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = 1,
};
BUG_ON(!PageLocked(page));
if (wait)
wait_on_page_writeback(page);
if (clear_page_dirty_for_io(page)) {
page_cache_get(page);
ret = mapping->a_ops->writepage(page, &wbc);
if (ret == 0 && wait) {
wait_on_page_writeback(page);
if (PageError(page))
ret = -EIO;
}
page_cache_release(page);
} else {
unlock_page(page);
}
return ret;
}
EXPORT_SYMBOL(write_one_page);
/*
* For address_spaces which do not use buffers nor write back.
*/
int __set_page_dirty_no_writeback(struct page *page)
{
if (!PageDirty(page))
SetPageDirty(page);
return 0;
}
/*
* Helper function for set_page_dirty family.
* NOTE: This relies on being atomic wrt interrupts.
*/
void account_page_dirtied(struct page *page, struct address_space *mapping)
{
if (mapping_cap_account_dirty(mapping)) {
__inc_zone_page_state(page, NR_FILE_DIRTY);
__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
task_dirty_inc(current);
task_io_account_write(PAGE_CACHE_SIZE);
}
}
/*
* For address_spaces which do not use buffers. Just tag the page as dirty in
* its radix tree.
*
* This is also used when a single buffer is being dirtied: we want to set the
* page dirty in that case, but not all the buffers. This is a "bottom-up"
* dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying.
*
* Most callers have locked the page, which pins the address_space in memory.
* But zap_pte_range() does not lock the page, however in that case the
* mapping is pinned by the vma's ->vm_file reference.
*
* We take care to handle the case where the page was truncated from the
* mapping by re-checking page_mapping() inside tree_lock.
*/
int __set_page_dirty_nobuffers(struct page *page)
{
if (!TestSetPageDirty(page)) {
struct address_space *mapping = page_mapping(page);
struct address_space *mapping2;
if (!mapping)
return 1;
spin_lock_irq(&mapping->tree_lock);
mapping2 = page_mapping(page);
if (mapping2) { /* Race with truncate? */
BUG_ON(mapping2 != mapping);
WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
account_page_dirtied(page, mapping);
radix_tree_tag_set(&mapping->page_tree,
page_index(page), PAGECACHE_TAG_DIRTY);
}
spin_unlock_irq(&mapping->tree_lock);
if (mapping->host) {
/* !PageAnon && !swapper_space */
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
}
return 1;
}
return 0;
}
EXPORT_SYMBOL(__set_page_dirty_nobuffers);
/*
* When a writepage implementation decides that it doesn't want to write this
* page for some reason, it should redirty the locked page via
* redirty_page_for_writepage() and it should then unlock the page and return 0
*/
int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page)
{
wbc->pages_skipped++;
return __set_page_dirty_nobuffers(page);
}
/**
* write_one_page - write out a single page and optionally wait on I/O
* @page: the page to write
* @wait: if true, wait on writeout
*
* The page must be locked by the caller and will be unlocked upon return.
*
* write_one_page() returns a negative error code if I/O failed.
*/
int write_one_page(struct page *page, int wait)
{
struct address_space *mapping = page->mapping;
int ret = 0;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = 1,
};
BUG_ON(!PageLocked(page));
if (wait)
wait_on_page_writeback(page);
if (clear_page_dirty_for_io(page)) {
page_cache_get(page);
ret = mapping->a_ops->writepage(page, &wbc);
if (ret == 0 && wait) {
wait_on_page_writeback(page);
if (PageError(page))
ret = -EIO;
}
page_cache_release(page);
} else {
unlock_page(page);
}
return ret;
}
EXPORT_SYMBOL(write_one_page);
/*
* For address_spaces which do not use buffers nor write back.
*/
int __set_page_dirty_no_writeback(struct page *page)
{
if (!PageDirty(page))
return !TestSetPageDirty(page);
return 0;
}
/*
* Helper function for set_page_dirty family.
* NOTE: This relies on being atomic wrt interrupts.
*/
void account_page_dirtied(struct page *page, struct address_space *mapping)
{
if (mapping_cap_account_dirty(mapping)) {
__inc_zone_page_state(page, NR_FILE_DIRTY);
__inc_zone_page_state(page, NR_DIRTIED);
__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
task_dirty_inc(current);
task_io_account_write(PAGE_CACHE_SIZE);
}
}
EXPORT_SYMBOL(account_page_dirtied);
/*
* Helper function for set_page_writeback family.
* NOTE: Unlike account_page_dirtied this does not rely on being atomic
* wrt interrupts.
*/
void account_page_writeback(struct page *page)
{
inc_zone_page_state(page, NR_WRITEBACK);
inc_zone_page_state(page, NR_WRITTEN);
}
/*
* Write a page synchronously.
* Offset is the data offset within the page.
*/
static int
nfs_writepage_sync(struct file *file, struct inode *inode, struct page *page,
unsigned int offset, unsigned int count)
{
struct rpc_cred *cred = NULL;
loff_t base;
unsigned int wsize = NFS_SERVER(inode)->wsize;
int result, refresh = 0, written = 0, flags;
u8 *buffer;
struct nfs_fattr fattr;
struct nfs_writeverf verf;
if (file)
cred = get_rpccred(nfs_file_cred(file));
if (!cred)
cred = get_rpccred(NFS_I(inode)->mm_cred);
dprintk("NFS: nfs_writepage_sync(%x/%Ld %d@%Ld)\n",
inode->i_dev, (long long)NFS_FILEID(inode),
count, (long long)(page_offset(page) + offset));
base = page_offset(page) + offset;
flags = ((IS_SWAPFILE(inode)) ? NFS_RW_SWAP : 0) | NFS_RW_SYNC;
do {
if (count < wsize && !IS_SWAPFILE(inode))
wsize = count;
result = NFS_PROTO(inode)->write(inode, cred, &fattr, flags,
offset, wsize, page, &verf);
nfs_write_attributes(inode, &fattr);
if (result < 0) {
/* Must mark the page invalid after I/O error */
ClearPageUptodate(page);
goto io_error;
}
if (result != wsize)
printk("NFS: short write, wsize=%u, result=%d\n",
wsize, result);
refresh = 1;
buffer += wsize;
base += wsize;
offset += wsize;
written += wsize;
count -= wsize;
/*
* If we've extended the file, update the inode
* now so we don't invalidate the cache.
*/
if (base > inode->i_size)
inode->i_size = base;
} while (count);
if (PageError(page))
ClearPageError(page);
io_error:
if (cred)
put_rpccred(cred);
return written? written : result;
}
void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask)
{
struct page_ext *page_ext = lookup_page_ext(page);
struct stack_trace trace = {
.nr_entries = 0,
.max_entries = ARRAY_SIZE(page_ext->trace_entries),
.entries = &page_ext->trace_entries[0],
.skip = 3,
};
save_stack_trace(&trace);
page_ext->order = order;
page_ext->gfp_mask = gfp_mask;
page_ext->nr_entries = trace.nr_entries;
__set_bit(PAGE_EXT_OWNER, &page_ext->flags);
}
static ssize_t
print_page_owner(char __user *buf, size_t count, unsigned long pfn,
struct page *page, struct page_ext *page_ext)
{
int ret;
int pageblock_mt, page_mt;
char *kbuf;
struct stack_trace trace = {
.nr_entries = page_ext->nr_entries,
.entries = &page_ext->trace_entries[0],
};
kbuf = kmalloc(count, GFP_KERNEL);
if (!kbuf)
return -ENOMEM;
ret = snprintf(kbuf, count,
"Page allocated via order %u, mask 0x%x\n",
page_ext->order, page_ext->gfp_mask);
if (ret >= count)
goto err;
/* Print information relevant to grouping pages by mobility */
pageblock_mt = get_pfnblock_migratetype(page, pfn);
page_mt = gfpflags_to_migratetype(page_ext->gfp_mask);
ret += snprintf(kbuf + ret, count - ret,
"PFN %lu Block %lu type %d %s Flags %s%s%s%s%s%s%s%s%s%s%s%s\n",
pfn,
pfn >> pageblock_order,
pageblock_mt,
pageblock_mt != page_mt ? "Fallback" : " ",
PageLocked(page) ? "K" : " ",
PageError(page) ? "E" : " ",
PageReferenced(page) ? "R" : " ",
PageUptodate(page) ? "U" : " ",
PageDirty(page) ? "D" : " ",
PageLRU(page) ? "L" : " ",
PageActive(page) ? "A" : " ",
PageSlab(page) ? "S" : " ",
PageWriteback(page) ? "W" : " ",
PageCompound(page) ? "C" : " ",
PageSwapCache(page) ? "B" : " ",
PageMappedToDisk(page) ? "M" : " ");
if (ret >= count)
goto err;
ret += snprint_stack_trace(kbuf + ret, count - ret, &trace, 0);
if (ret >= count)
goto err;
ret += snprintf(kbuf + ret, count - ret, "\n");
if (ret >= count)
goto err;
if (copy_to_user(buf, kbuf, ret))
ret = -EFAULT;
kfree(kbuf);
return ret;
err:
kfree(kbuf);
return -ENOMEM;
}
static ssize_t
read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
{
unsigned long pfn;
struct page *page;
struct page_ext *page_ext;
if (!page_owner_inited)
return -EINVAL;
page = NULL;
pfn = min_low_pfn + *ppos;
/* Find a valid PFN or the start of a MAX_ORDER_NR_PAGES area */
while (!pfn_valid(pfn) && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0)
pfn++;
drain_all_pages(NULL);
/* Find an allocated page */
for (; pfn < max_pfn; pfn++) {
/*
* If the new page is in a new MAX_ORDER_NR_PAGES area,
* validate the area as existing, skip it if not
*/
if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0 && !pfn_valid(pfn)) {
pfn += MAX_ORDER_NR_PAGES - 1;
continue;
}
/* Check for holes within a MAX_ORDER area */
if (!pfn_valid_within(pfn))
continue;
page = pfn_to_page(pfn);
if (PageBuddy(page)) {
unsigned long freepage_order = page_order_unsafe(page);
if (freepage_order < MAX_ORDER)
pfn += (1UL << freepage_order) - 1;
continue;
}
page_ext = lookup_page_ext(page);
/*
* Some pages could be missed by concurrent allocation or free,
* because we don't hold the zone lock.
*/
if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags))
continue;
/* Record the next PFN to read in the file offset */
*ppos = (pfn - min_low_pfn) + 1;
return print_page_owner(buf, count, pfn, page, page_ext);
}
return 0;
}
int write_one_page(struct page *page, int wait)
{
struct address_space *mapping = page->mapping;
int ret = 0;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = 1,
};
BUG_ON(!PageLocked(page));
if (wait)
wait_on_page_writeback(page);
if (clear_page_dirty_for_io(page)) {
page_cache_get(page);
ret = mapping->a_ops->writepage(page, &wbc);
if (ret == 0 && wait) {
wait_on_page_writeback(page);
if (PageError(page))
ret = -EIO;
}
page_cache_release(page);
} else {
unlock_page(page);
}
return ret;
}
EXPORT_SYMBOL(write_one_page);
int __set_page_dirty_no_writeback(struct page *page)
{
if (!PageDirty(page))
SetPageDirty(page);
return 0;
}
void account_page_dirtied(struct page *page, struct address_space *mapping)
{
if (mapping_cap_account_dirty(mapping)) {
__inc_zone_page_state(page, NR_FILE_DIRTY);
__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
task_dirty_inc(current);
task_io_account_write(PAGE_CACHE_SIZE);
}
}
int __set_page_dirty_nobuffers(struct page *page)
{
if (!TestSetPageDirty(page)) {
struct address_space *mapping = page_mapping(page);
struct address_space *mapping2;
if (!mapping)
return 1;
spin_lock_irq(&mapping->tree_lock);
mapping2 = page_mapping(page);
if (mapping2) { /* Race with truncate? */
BUG_ON(mapping2 != mapping);
WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
account_page_dirtied(page, mapping);
radix_tree_tag_set(&mapping->page_tree,
page_index(page), PAGECACHE_TAG_DIRTY);
}
spin_unlock_irq(&mapping->tree_lock);
if (mapping->host) {
/* !PageAnon && !swapper_space */
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
}
return 1;
}
return 0;
}
EXPORT_SYMBOL(__set_page_dirty_nobuffers);
int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page)
{
wbc->pages_skipped++;
return __set_page_dirty_nobuffers(page);
}
static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt)
{
struct afs_super_info *super;
struct vfsmount *mnt;
struct page *page;
size_t size;
char *buf, *devname, *options;
int ret;
_enter("{%s}", mntpt->d_name.name);
BUG_ON(!mntpt->d_inode);
ret = -EINVAL;
size = mntpt->d_inode->i_size;
if (size > PAGE_SIZE - 1)
goto error_no_devname;
ret = -ENOMEM;
devname = (char *) get_zeroed_page(GFP_KERNEL);
if (!devname)
goto error_no_devname;
options = (char *) get_zeroed_page(GFP_KERNEL);
if (!options)
goto error_no_options;
/* read the contents of the AFS special symlink */
page = read_mapping_page(mntpt->d_inode->i_mapping, 0, NULL);
if (IS_ERR(page)) {
ret = PTR_ERR(page);
goto error_no_page;
}
ret = -EIO;
if (PageError(page))
goto error;
buf = kmap_atomic(page, KM_USER0);
memcpy(devname, buf, size);
kunmap_atomic(buf, KM_USER0);
page_cache_release(page);
page = NULL;
/* work out what options we want */
super = AFS_FS_S(mntpt->d_sb);
memcpy(options, "cell=", 5);
strcpy(options + 5, super->volume->cell->name);
if (super->volume->type == AFSVL_RWVOL)
strcat(options, ",rwpath");
/* try and do the mount */
_debug("--- attempting mount %s -o %s ---", devname, options);
mnt = vfs_kern_mount(&afs_fs_type, 0, devname, options);
_debug("--- mount result %p ---", mnt);
free_page((unsigned long) devname);
free_page((unsigned long) options);
_leave(" = %p", mnt);
return mnt;
error:
page_cache_release(page);
error_no_page:
free_page((unsigned long) options);
error_no_options:
free_page((unsigned long) devname);
error_no_devname:
_leave(" = %d", ret);
return ERR_PTR(ret);
}
/*
* create a vfsmount to be automounted
*/
static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt)
{
struct afs_super_info *super;
struct vfsmount *mnt;
struct afs_vnode *vnode;
struct page *page;
char *devname, *options;
bool rwpath = false;
int ret;
_enter("{%pd}", mntpt);
BUG_ON(!d_inode(mntpt));
ret = -ENOMEM;
devname = (char *) get_zeroed_page(GFP_KERNEL);
if (!devname)
goto error_no_devname;
options = (char *) get_zeroed_page(GFP_KERNEL);
if (!options)
goto error_no_options;
vnode = AFS_FS_I(d_inode(mntpt));
if (test_bit(AFS_VNODE_PSEUDODIR, &vnode->flags)) {
/* if the directory is a pseudo directory, use the d_name */
static const char afs_root_cell[] = ":root.cell.";
unsigned size = mntpt->d_name.len;
ret = -ENOENT;
if (size < 2 || size > AFS_MAXCELLNAME)
goto error_no_page;
if (mntpt->d_name.name[0] == '.') {
devname[0] = '#';
memcpy(devname + 1, mntpt->d_name.name, size - 1);
memcpy(devname + size, afs_root_cell,
sizeof(afs_root_cell));
rwpath = true;
} else {
devname[0] = '%';
memcpy(devname + 1, mntpt->d_name.name, size);
memcpy(devname + size + 1, afs_root_cell,
sizeof(afs_root_cell));
}
} else {
/* read the contents of the AFS special symlink */
loff_t size = i_size_read(d_inode(mntpt));
char *buf;
ret = -EINVAL;
if (size > PAGE_SIZE - 1)
goto error_no_page;
page = read_mapping_page(d_inode(mntpt)->i_mapping, 0, NULL);
if (IS_ERR(page)) {
ret = PTR_ERR(page);
goto error_no_page;
}
ret = -EIO;
if (PageError(page))
goto error;
buf = kmap_atomic(page);
memcpy(devname, buf, size);
kunmap_atomic(buf);
put_page(page);
page = NULL;
}
/* work out what options we want */
super = AFS_FS_S(mntpt->d_sb);
memcpy(options, "cell=", 5);
strcpy(options + 5, super->volume->cell->name);
if (super->volume->type == AFSVL_RWVOL || rwpath)
strcat(options, ",rwpath");
/* try and do the mount */
_debug("--- attempting mount %s -o %s ---", devname, options);
mnt = vfs_submount(mntpt, &afs_fs_type, devname, options);
_debug("--- mount result %p ---", mnt);
free_page((unsigned long) devname);
free_page((unsigned long) options);
_leave(" = %p", mnt);
return mnt;
error:
put_page(page);
error_no_page:
free_page((unsigned long) options);
error_no_options:
free_page((unsigned long) devname);
error_no_devname:
_leave(" = %d", ret);
return ERR_PTR(ret);
}
/* attempts to compress and store an single page */
static int zswap_frontswap_store(unsigned type, pgoff_t offset,
struct page *page)
{
struct zswap_tree *tree = zswap_trees[type];
struct zswap_entry *entry, *dupentry;
int ret;
unsigned int dlen = PAGE_SIZE, len;
unsigned long handle;
char *buf;
u8 *src, *dst;
struct zswap_header *zhdr;
if (!tree) {
ret = -ENODEV;
goto reject;
}
/* if this page got EIO on pageout before, give up immediately */
if (PageError(page)) {
ret = -ENOMEM;
goto reject;
}
/* reclaim space if needed */
if (zswap_is_full()) {
zswap_pool_limit_hit++;
if (zpool_shrink(zswap_pool, 1, NULL)) {
zswap_reject_reclaim_fail++;
ret = -ENOMEM;
goto reject;
}
}
/* allocate entry */
entry = zswap_entry_cache_alloc(GFP_KERNEL);
if (!entry) {
zswap_reject_kmemcache_fail++;
ret = -ENOMEM;
goto reject;
}
/* compress */
src = kmap_atomic(page);
if (page_zero_filled(src)) {
atomic_inc(&zswap_zero_pages);
entry->zero_flag = 1;
kunmap_atomic(src);
handle = 0;
dlen = PAGE_SIZE;
goto zeropage_out;
}
dst = get_cpu_var(zswap_dstmem);
ret = zswap_comp_op(ZSWAP_COMPOP_COMPRESS, src, PAGE_SIZE, dst, &dlen);
kunmap_atomic(src);
if (ret) {
ret = -EINVAL;
goto freepage;
}
/* store */
len = dlen + sizeof(struct zswap_header);
ret = zpool_malloc(zswap_pool, len, __GFP_NORETRY | __GFP_NOWARN,
&handle);
if (ret == -ENOSPC) {
zswap_reject_compress_poor++;
goto freepage;
}
if (ret) {
zswap_reject_alloc_fail++;
goto freepage;
}
zhdr = zpool_map_handle(zswap_pool, handle, ZPOOL_MM_RW);
zhdr->swpentry = swp_entry(type, offset);
buf = (u8 *)(zhdr + 1);
memcpy(buf, dst, dlen);
zpool_unmap_handle(zswap_pool, handle);
put_cpu_var(zswap_dstmem);
zeropage_out:
/* populate entry */
entry->offset = offset;
entry->handle = handle;
entry->length = dlen;
/* map */
spin_lock(&tree->lock);
do {
ret = zswap_rb_insert(&tree->rbroot, entry, &dupentry);
if (ret == -EEXIST) {
zswap_duplicate_entry++;
/* remove from rbtree */
zswap_rb_erase(&tree->rbroot, dupentry);
zswap_entry_put(tree, dupentry);
}
} while (ret == -EEXIST);
spin_unlock(&tree->lock);
/* update stats */
atomic_inc(&zswap_stored_pages);
zswap_pool_total_size = zpool_get_total_size(zswap_pool);
zswap_pool_pages = zswap_pool_total_size >> PAGE_SHIFT;
return 0;
freepage:
put_cpu_var(zswap_dstmem);
zswap_entry_cache_free(entry);
reject:
return ret;
}