/**
* pagecache_isize_extended - update pagecache after extension of i_size
* @inode: inode for which i_size was extended
* @from: original inode size
* @to: new inode size
*
* Handle extension of inode size either caused by extending truncate or by
* write starting after current i_size. We mark the page straddling current
* i_size RO so that page_mkwrite() is called on the nearest write access to
* the page. This way filesystem can be sure that page_mkwrite() is called on
* the page before user writes to the page via mmap after the i_size has been
* changed.
*
* The function must be called after i_size is updated so that page fault
* coming after we unlock the page will already see the new i_size.
* The function must be called while we still hold i_mutex - this not only
* makes sure i_size is stable but also that userspace cannot observe new
* i_size value before we are prepared to store mmap writes at new inode size.
*/
void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to)
{
int bsize = 1 << inode->i_blkbits;
loff_t rounded_from;
struct page *page;
pgoff_t index;
WARN_ON(to > inode->i_size);
if (from >= to || bsize == PAGE_CACHE_SIZE)
return;
/* Page straddling @from will not have any hole block created? */
rounded_from = round_up(from, bsize);
if (to <= rounded_from || !(rounded_from & (PAGE_CACHE_SIZE - 1)))
return;
index = from >> PAGE_CACHE_SHIFT;
page = find_lock_page(inode->i_mapping, index);
/* Page not cached? Nothing to do */
if (!page)
return;
/*
* See clear_page_dirty_for_io() for details why set_page_dirty()
* is needed.
*/
if (page_mkclean(page))
set_page_dirty(page);
unlock_page(page);
page_cache_release(page);
}
/**
* nilfs_copy_back_pages -- copy back pages to original cache from shadow cache
* @dmap: destination page cache
* @smap: source page cache
*
* No pages must no be added to the cache during this process.
* This must be ensured by the caller.
*/
void nilfs_copy_back_pages(struct address_space *dmap,
struct address_space *smap)
{
struct pagevec pvec;
unsigned int i, n;
pgoff_t index = 0;
int err;
pagevec_init(&pvec);
repeat:
n = pagevec_lookup(&pvec, smap, &index);
if (!n)
return;
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i], *dpage;
pgoff_t offset = page->index;
lock_page(page);
dpage = find_lock_page(dmap, offset);
if (dpage) {
/* override existing page on the destination cache */
WARN_ON(PageDirty(dpage));
nilfs_copy_page(dpage, page, 0);
unlock_page(dpage);
put_page(dpage);
} else {
struct page *page2;
/* move the page to the destination cache */
spin_lock_irq(&smap->tree_lock);
page2 = radix_tree_delete(&smap->page_tree, offset);
WARN_ON(page2 != page);
smap->nrpages--;
spin_unlock_irq(&smap->tree_lock);
spin_lock_irq(&dmap->tree_lock);
err = radix_tree_insert(&dmap->page_tree, offset, page);
if (unlikely(err < 0)) {
WARN_ON(err == -EEXIST);
page->mapping = NULL;
put_page(page); /* for cache */
} else {
page->mapping = dmap;
dmap->nrpages++;
if (PageDirty(page))
radix_tree_tag_set(&dmap->page_tree,
offset,
PAGECACHE_TAG_DIRTY);
}
spin_unlock_irq(&dmap->tree_lock);
}
unlock_page(page);
}
pagevec_release(&pvec);
cond_resched();
goto repeat;
}
static int __bdev_writeseg(struct super_block *sb, u64 ofs, pgoff_t index,
size_t nr_pages)
{
struct logfs_super *super = logfs_super(sb);
struct address_space *mapping = super->s_mapping_inode->i_mapping;
struct bio *bio;
struct page *page;
struct request_queue *q = bdev_get_queue(sb->s_bdev);
unsigned int max_pages = queue_max_hw_sectors(q) >> (PAGE_SHIFT - 9);
int i;
if (max_pages > BIO_MAX_PAGES)
max_pages = BIO_MAX_PAGES;
bio = bio_alloc(GFP_NOFS, max_pages);
BUG_ON(!bio);
for (i = 0; i < nr_pages; i++) {
if (i >= max_pages) {
/* Block layer cannot split bios :( */
bio->bi_vcnt = i;
bio->bi_idx = 0;
bio->bi_size = i * PAGE_SIZE;
bio->bi_bdev = super->s_bdev;
bio->bi_sector = ofs >> 9;
bio->bi_private = sb;
bio->bi_end_io = writeseg_end_io;
atomic_inc(&super->s_pending_writes);
submit_bio(WRITE, bio);
ofs += i * PAGE_SIZE;
index += i;
nr_pages -= i;
i = 0;
bio = bio_alloc(GFP_NOFS, max_pages);
BUG_ON(!bio);
}
page = find_lock_page(mapping, index + i);
BUG_ON(!page);
bio->bi_io_vec[i].bv_page = page;
bio->bi_io_vec[i].bv_len = PAGE_SIZE;
bio->bi_io_vec[i].bv_offset = 0;
BUG_ON(PageWriteback(page));
set_page_writeback(page);
unlock_page(page);
}
struct buffer_head *nilfs_grab_buffer(struct inode *inode,
struct address_space *mapping,
unsigned long blkoff,
unsigned long b_state)
{
int blkbits = inode->i_blkbits;
pgoff_t index = blkoff >> (PAGE_CACHE_SHIFT - blkbits);
struct page *page, *opage;
struct buffer_head *bh, *obh;
page = grab_cache_page(mapping, index);
if (unlikely(!page))
return NULL;
bh = __nilfs_get_page_block(page, blkoff, index, blkbits, b_state);
if (unlikely(!bh)) {
unlock_page(page);
page_cache_release(page);
return NULL;
}
if (!buffer_uptodate(bh) && mapping->assoc_mapping != NULL) {
/*
* Shadow page cache uses assoc_mapping to point its original
* page cache. The following code tries the original cache
* if the given cache is a shadow and it didn't hit.
*/
opage = find_lock_page(mapping->assoc_mapping, index);
if (!opage)
return bh;
obh = __nilfs_get_page_block(opage, blkoff, index, blkbits,
b_state);
if (buffer_uptodate(obh)) {
nilfs_copy_buffer(bh, obh);
if (buffer_dirty(obh)) {
nilfs_mark_buffer_dirty(bh);
if (!buffer_nilfs_node(bh) && NILFS_MDT(inode))
nilfs_mdt_mark_dirty(inode);
}
}
brelse(obh);
unlock_page(opage);
page_cache_release(opage);
}
return bh;
}
struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create)
{
struct address_space *mapping = gl->gl_aspace->i_mapping;
struct gfs2_sbd *sdp = gl->gl_sbd;
struct page *page;
struct buffer_head *bh;
unsigned int shift;
unsigned long index;
unsigned int bufnum;
shift = PAGE_CACHE_SHIFT - sdp->sd_sb.sb_bsize_shift;
index = blkno >> shift; /* convert block to page */
bufnum = blkno - (index << shift); /* block buf index within page */
if (create) {
for (;;) {
page = grab_cache_page(mapping, index);
if (page)
break;
yield();
}
} else {
page = find_lock_page(mapping, index);
if (!page)
return NULL;
}
if (!page_has_buffers(page))
create_empty_buffers(page, sdp->sd_sb.sb_bsize, 0);
/* Locate header for our buffer within our page */
for (bh = page_buffers(page); bufnum--; bh = bh->b_this_page)
/* Do nothing */;
get_bh(bh);
if (!buffer_mapped(bh))
map_bh(bh, sdp->sd_vfs, blkno);
unlock_page(page);
mark_page_accessed(page);
page_cache_release(page);
return bh;
}
struct page * lookup_swap_cache(swp_entry_t entry)
{
struct page *found;
#ifdef SWAP_CACHE_INFO
swap_cache_find_total++;
#endif
while (1) {
/*
* Right now the pagecache is 32-bit only. But it's a 32 bit index. =)
*/
repeat:
found = find_lock_page(&swapper_space, entry.val);
if (!found)
return 0;
/*
* Though the "found" page was in the swap cache an instant
* earlier, it might have been removed by refill_inactive etc.
* Re search ... Since find_lock_page grabs a reference on
* the page, it can not be reused for anything else, namely
* it can not be associated with another swaphandle, so it
* is enough to check whether the page is still in the scache.
*/
if (!PageSwapCache(found)) {
UnlockPage(found);
page_cache_release(found);
goto repeat;
}
if (found->mapping != &swapper_space)
goto out_bad;
#ifdef SWAP_CACHE_INFO
swap_cache_find_success++;
#endif
UnlockPage(found);
return found;
}
out_bad:
printk (KERN_ERR "VM: Found a non-swapper swap page!\n");
UnlockPage(found);
page_cache_release(found);
return 0;
}
static struct dentry *
__dcache_find_get_entry(struct dentry *parent, u64 idx,
struct ceph_readdir_cache_control *cache_ctl)
{
struct inode *dir = d_inode(parent);
struct dentry *dentry;
unsigned idx_mask = (PAGE_SIZE / sizeof(struct dentry *)) - 1;
loff_t ptr_pos = idx * sizeof(struct dentry *);
pgoff_t ptr_pgoff = ptr_pos >> PAGE_SHIFT;
if (ptr_pos >= i_size_read(dir))
return NULL;
if (!cache_ctl->page || ptr_pgoff != page_index(cache_ctl->page)) {
ceph_readdir_cache_release(cache_ctl);
cache_ctl->page = find_lock_page(&dir->i_data, ptr_pgoff);
if (!cache_ctl->page) {
dout(" page %lu not found\n", ptr_pgoff);
return ERR_PTR(-EAGAIN);
}
/* reading/filling the cache are serialized by
i_mutex, no need to use page lock */
unlock_page(cache_ctl->page);
cache_ctl->dentries = kmap(cache_ctl->page);
}
cache_ctl->index = idx & idx_mask;
rcu_read_lock();
spin_lock(&parent->d_lock);
/* check i_size again here, because empty directory can be
* marked as complete while not holding the i_mutex. */
if (ceph_dir_is_complete_ordered(dir) && ptr_pos < i_size_read(dir))
dentry = cache_ctl->dentries[cache_ctl->index];
else
dentry = NULL;
spin_unlock(&parent->d_lock);
if (dentry && !lockref_get_not_dead(&dentry->d_lockref))
dentry = NULL;
rcu_read_unlock();
return dentry ? : ERR_PTR(-EAGAIN);
}
static void write_wbuf(struct super_block *sb, struct logfs_area *area,
void *wbuf)
{
struct logfs_super *super = logfs_super(sb);
struct address_space *mapping = super->s_mapping_inode->i_mapping;
u64 ofs;
pgoff_t index;
int page_ofs;
struct page *page;
ofs = dev_ofs(sb, area->a_segno,
area->a_used_bytes & ~(super->s_writesize - 1));
index = ofs >> PAGE_SHIFT;
page_ofs = ofs & (PAGE_SIZE - 1);
page = find_lock_page(mapping, index);
BUG_ON(!page);
memcpy(wbuf, page_address(page) + page_ofs, super->s_writesize);
unlock_page(page);
}
struct page *ufs_get_locked_page(struct address_space *mapping,
pgoff_t index)
{
struct page *page;
page = find_lock_page(mapping, index);
if (!page) {
page = read_mapping_page(mapping, index, NULL);
if (IS_ERR(page)) {
printk(KERN_ERR "ufs_change_blocknr: "
"read_mapping_page error: ino %lu, index: %lu\n",
mapping->host->i_ino, index);
goto out;
}
lock_page(page);
if (unlikely(page->mapping == NULL)) {
/* Truncate got there first */
unlock_page(page);
put_page(page);
page = NULL;
goto out;
}
if (!PageUptodate(page) || PageError(page)) {
unlock_page(page);
put_page(page);
printk(KERN_ERR "ufs_change_blocknr: "
"can not read page: ino %lu, index: %lu\n",
mapping->host->i_ino, index);
page = ERR_PTR(-EIO);
}
}
out:
return page;
}
/*
* Read a directory, using filldir to fill the dirent memory.
* smb_proc_readdir does the actual reading from the smb server.
*
* The cache code is almost directly taken from ncpfs
*/
static int
smb_readdir(struct file *filp, void *dirent, filldir_t filldir)
{
struct dentry *dentry = filp->f_path.dentry;
struct inode *dir = dentry->d_inode;
struct smb_sb_info *server = server_from_dentry(dentry);
union smb_dir_cache *cache = NULL;
struct smb_cache_control ctl;
struct page *page = NULL;
int result;
ctl.page = NULL;
ctl.cache = NULL;
VERBOSE("reading %s/%s, f_pos=%d\n",
DENTRY_PATH(dentry), (int) filp->f_pos);
result = 0;
lock_kernel();
switch ((unsigned int) filp->f_pos) {
case 0:
if (filldir(dirent, ".", 1, 0, dir->i_ino, DT_DIR) < 0)
goto out;
filp->f_pos = 1;
/* fallthrough */
case 1:
if (filldir(dirent, "..", 2, 1, parent_ino(dentry), DT_DIR) < 0)
goto out;
filp->f_pos = 2;
}
/*
* Make sure our inode is up-to-date.
*/
result = smb_revalidate_inode(dentry);
if (result)
goto out;
page = grab_cache_page(&dir->i_data, 0);
if (!page)
goto read_really;
ctl.cache = cache = kmap(page);
ctl.head = cache->head;
if (!PageUptodate(page) || !ctl.head.eof) {
VERBOSE("%s/%s, page uptodate=%d, eof=%d\n",
DENTRY_PATH(dentry), PageUptodate(page),ctl.head.eof);
goto init_cache;
}
if (filp->f_pos == 2) {
if (jiffies - ctl.head.time >= SMB_MAX_AGE(server))
goto init_cache;
/*
* N.B. ncpfs checks mtime of dentry too here, we don't.
* 1. common smb servers do not update mtime on dir changes
* 2. it requires an extra smb request
* (revalidate has the same timeout as ctl.head.time)
*
* Instead smbfs invalidates its own cache on local changes
* and remote changes are not seen until timeout.
*/
}
if (filp->f_pos > ctl.head.end)
goto finished;
ctl.fpos = filp->f_pos + (SMB_DIRCACHE_START - 2);
ctl.ofs = ctl.fpos / SMB_DIRCACHE_SIZE;
ctl.idx = ctl.fpos % SMB_DIRCACHE_SIZE;
for (;;) {
if (ctl.ofs != 0) {
ctl.page = find_lock_page(&dir->i_data, ctl.ofs);
if (!ctl.page)
goto invalid_cache;
ctl.cache = kmap(ctl.page);
if (!PageUptodate(ctl.page))
goto invalid_cache;
}
while (ctl.idx < SMB_DIRCACHE_SIZE) {
struct dentry *dent;
int res;
dent = smb_dget_fpos(ctl.cache->dentry[ctl.idx],
dentry, filp->f_pos);
if (!dent)
goto invalid_cache;
res = filldir(dirent, dent->d_name.name,
dent->d_name.len, filp->f_pos,
dent->d_inode->i_ino, DT_UNKNOWN);
dput(dent);
if (res)
goto finished;
filp->f_pos += 1;
ctl.idx += 1;
if (filp->f_pos > ctl.head.end)
goto finished;
}
if (ctl.page) {
kunmap(ctl.page);
SetPageUptodate(ctl.page);
unlock_page(ctl.page);
page_cache_release(ctl.page);
ctl.page = NULL;
}
ctl.idx = 0;
ctl.ofs += 1;
}
invalid_cache:
if (ctl.page) {
kunmap(ctl.page);
unlock_page(ctl.page);
page_cache_release(ctl.page);
ctl.page = NULL;
}
ctl.cache = cache;
init_cache:
smb_invalidate_dircache_entries(dentry);
ctl.head.time = jiffies;
ctl.head.eof = 0;
ctl.fpos = 2;
ctl.ofs = 0;
ctl.idx = SMB_DIRCACHE_START;
ctl.filled = 0;
ctl.valid = 1;
read_really:
result = server->ops->readdir(filp, dirent, filldir, &ctl);
if (result == -ERESTARTSYS && page)
ClearPageUptodate(page);
if (ctl.idx == -1)
goto invalid_cache; /* retry */
ctl.head.end = ctl.fpos - 1;
ctl.head.eof = ctl.valid;
finished:
if (page) {
cache->head = ctl.head;
kunmap(page);
if (result != -ERESTARTSYS)
SetPageUptodate(page);
unlock_page(page);
page_cache_release(page);
}
if (ctl.page) {
kunmap(ctl.page);
SetPageUptodate(ctl.page);
unlock_page(ctl.page);
page_cache_release(ctl.page);
}
out:
unlock_kernel();
return result;
}
/*
* This function was originally taken from fs/mpage.c, and customized for f2fs.
* Major change was from block_size == page_size in f2fs by default.
*/
static int f2fs_mpage_readpages(struct address_space *mapping,
struct list_head *pages, struct page *page,
unsigned nr_pages)
{
struct bio *bio = NULL;
unsigned page_idx;
sector_t last_block_in_bio = 0;
struct inode *inode = mapping->host;
const unsigned blkbits = inode->i_blkbits;
const unsigned blocksize = 1 << blkbits;
sector_t block_in_file;
sector_t last_block;
sector_t last_block_in_file;
sector_t block_nr;
struct block_device *bdev = inode->i_sb->s_bdev;
struct f2fs_map_blocks map;
map.m_pblk = 0;
map.m_lblk = 0;
map.m_len = 0;
map.m_flags = 0;
for (page_idx = 0; nr_pages; page_idx++, nr_pages--) {
prefetchw(&page->flags);
if (pages) {
page = list_entry(pages->prev, struct page, lru);
list_del(&page->lru);
if (add_to_page_cache_lru(page, mapping,
page->index, GFP_KERNEL))
goto next_page;
}
block_in_file = (sector_t)page->index;
last_block = block_in_file + nr_pages;
last_block_in_file = (i_size_read(inode) + blocksize - 1) >>
blkbits;
if (last_block > last_block_in_file)
last_block = last_block_in_file;
/*
* Map blocks using the previous result first.
*/
if ((map.m_flags & F2FS_MAP_MAPPED) &&
block_in_file > map.m_lblk &&
block_in_file < (map.m_lblk + map.m_len))
goto got_it;
/*
* Then do more f2fs_map_blocks() calls until we are
* done with this page.
*/
map.m_flags = 0;
if (block_in_file < last_block) {
map.m_lblk = block_in_file;
map.m_len = last_block - block_in_file;
if (f2fs_map_blocks(inode, &map, 0, false))
goto set_error_page;
}
got_it:
if ((map.m_flags & F2FS_MAP_MAPPED)) {
block_nr = map.m_pblk + block_in_file - map.m_lblk;
SetPageMappedToDisk(page);
if (!PageUptodate(page) && !cleancache_get_page(page)) {
SetPageUptodate(page);
goto confused;
}
} else {
zero_user_segment(page, 0, PAGE_CACHE_SIZE);
SetPageUptodate(page);
unlock_page(page);
goto next_page;
}
/*
* This page will go to BIO. Do we need to send this
* BIO off first?
*/
if (bio && (last_block_in_bio != block_nr - 1)) {
submit_and_realloc:
submit_bio(READ, bio);
bio = NULL;
}
if (bio == NULL) {
struct f2fs_crypto_ctx *ctx = NULL;
if (f2fs_encrypted_inode(inode) &&
S_ISREG(inode->i_mode)) {
struct page *cpage;
ctx = f2fs_get_crypto_ctx(inode);
if (IS_ERR(ctx))
goto set_error_page;
/* wait the page to be moved by cleaning */
cpage = find_lock_page(
META_MAPPING(F2FS_I_SB(inode)),
block_nr);
if (cpage) {
f2fs_wait_on_page_writeback(cpage,
DATA);
f2fs_put_page(cpage, 1);
}
}
bio = bio_alloc(GFP_KERNEL,
min_t(int, nr_pages, BIO_MAX_PAGES));
if (!bio) {
if (ctx)
f2fs_release_crypto_ctx(ctx);
goto set_error_page;
}
bio->bi_bdev = bdev;
bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(block_nr);
bio->bi_end_io = f2fs_read_end_io;
bio->bi_private = ctx;
}
if (bio_add_page(bio, page, blocksize, 0) < blocksize)
goto submit_and_realloc;
last_block_in_bio = block_nr;
goto next_page;
set_error_page:
SetPageError(page);
zero_user_segment(page, 0, PAGE_CACHE_SIZE);
unlock_page(page);
goto next_page;
confused:
if (bio) {
submit_bio(READ, bio);
bio = NULL;
}
unlock_page(page);
next_page:
if (pages)
page_cache_release(page);
}
BUG_ON(pages && !list_empty(pages));
if (bio)
submit_bio(READ, bio);
return 0;
}
/**
* truncate_inode_pages - truncate *all* the pages from an offset
* @mapping: mapping to truncate
* @lstart: offset from which to truncate
*
* Truncate the page cache at a set offset, removing the pages that are beyond
* that offset (and zeroing out partial pages).
*
* Truncate takes two passes - the first pass is nonblocking. It will not
* block on page locks and it will not block on writeback. The second pass
* will wait. This is to prevent as much IO as possible in the affected region.
* The first pass will remove most pages, so the search cost of the second pass
* is low.
*
* When looking at page->index outside the page lock we need to be careful to
* copy it into a local to avoid races (it could change at any time).
*
* We pass down the cache-hot hint to the page freeing code. Even if the
* mapping is large, it is probably the case that the final pages are the most
* recently touched, and freeing happens in ascending file offset order.
*
* Called under (and serialised by) inode->i_sem.
*/
void truncate_inode_pages(struct address_space *mapping, loff_t lstart)
{
const pgoff_t start = (lstart + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
const unsigned partial = lstart & (PAGE_CACHE_SIZE - 1);
struct pagevec pvec;
pgoff_t next;
int i;
if (mapping->nrpages == 0)
return;
pagevec_init(&pvec, 0);
next = start;
while (pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
pgoff_t page_index = page->index;
if (page_index > next)
next = page_index;
next++;
if (TestSetPageLocked(page))
continue;
if (PageWriteback(page)) {
unlock_page(page);
continue;
}
truncate_complete_page(mapping, page);
unlock_page(page);
}
pagevec_release(&pvec);
cond_resched();
}
if (partial) {
struct page *page = find_lock_page(mapping, start - 1);
if (page) {
wait_on_page_writeback(page);
truncate_partial_page(page, partial);
unlock_page(page);
page_cache_release(page);
}
}
next = start;
for ( ; ; ) {
cond_resched();
if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
if (next == start)
break;
next = start;
continue;
}
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
lock_page(page);
wait_on_page_writeback(page);
if (page->index > next)
next = page->index;
next++;
truncate_complete_page(mapping, page);
unlock_page(page);
}
pagevec_release(&pvec);
}
}
/**
* truncate_inode_pages_range - truncate range of pages specified by start & end byte offsets
* @mapping: mapping to truncate
* @lstart: offset from which to truncate
* @lend: offset to which to truncate (inclusive)
*
* Truncate the page cache, removing the pages that are between
* specified offsets (and zeroing out partial pages
* if lstart or lend + 1 is not page aligned).
*
* Truncate takes two passes - the first pass is nonblocking. It will not
* block on page locks and it will not block on writeback. The second pass
* will wait. This is to prevent as much IO as possible in the affected region.
* The first pass will remove most pages, so the search cost of the second pass
* is low.
*
* We pass down the cache-hot hint to the page freeing code. Even if the
* mapping is large, it is probably the case that the final pages are the most
* recently touched, and freeing happens in ascending file offset order.
*
* Note that since ->invalidatepage() accepts range to invalidate
* truncate_inode_pages_range is able to handle cases where lend + 1 is not
* page aligned properly.
*/
void truncate_inode_pages_range(struct address_space *mapping,
loff_t lstart, loff_t lend)
{
pgoff_t start; /* inclusive */
pgoff_t end; /* exclusive */
unsigned int partial_start; /* inclusive */
unsigned int partial_end; /* exclusive */
struct pagevec pvec;
pgoff_t indices[PAGEVEC_SIZE];
pgoff_t index;
int i;
cleancache_invalidate_inode(mapping);
if (mapping->nrpages == 0 && mapping->nrexceptional == 0)
return;
/* Offsets within partial pages */
partial_start = lstart & (PAGE_CACHE_SIZE - 1);
partial_end = (lend + 1) & (PAGE_CACHE_SIZE - 1);
/*
* 'start' and 'end' always covers the range of pages to be fully
* truncated. Partial pages are covered with 'partial_start' at the
* start of the range and 'partial_end' at the end of the range.
* Note that 'end' is exclusive while 'lend' is inclusive.
*/
start = (lstart + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
if (lend == -1)
/*
* lend == -1 indicates end-of-file so we have to set 'end'
* to the highest possible pgoff_t and since the type is
* unsigned we're using -1.
*/
end = -1;
else
end = (lend + 1) >> PAGE_CACHE_SHIFT;
pagevec_init(&pvec, 0);
index = start;
while (index < end && pagevec_lookup_entries(&pvec, mapping, index,
min(end - index, (pgoff_t)PAGEVEC_SIZE),
indices)) {
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
/* We rely upon deletion not changing page->index */
index = indices[i];
if (index >= end)
break;
if (radix_tree_exceptional_entry(page)) {
clear_exceptional_entry(mapping, index, page);
continue;
}
if (!trylock_page(page))
continue;
WARN_ON(page->index != index);
if (PageWriteback(page)) {
unlock_page(page);
continue;
}
truncate_inode_page(mapping, page);
unlock_page(page);
}
pagevec_remove_exceptionals(&pvec);
pagevec_release(&pvec);
cond_resched();
index++;
}
if (partial_start) {
struct page *page = find_lock_page(mapping, start - 1);
if (page) {
unsigned int top = PAGE_CACHE_SIZE;
if (start > end) {
/* Truncation within a single page */
top = partial_end;
partial_end = 0;
}
wait_on_page_writeback(page);
zero_user_segment(page, partial_start, top);
cleancache_invalidate_page(mapping, page);
if (page_has_private(page))
do_invalidatepage(page, partial_start,
top - partial_start);
unlock_page(page);
page_cache_release(page);
}
}
if (partial_end) {
struct page *page = find_lock_page(mapping, end);
if (page) {
wait_on_page_writeback(page);
zero_user_segment(page, 0, partial_end);
cleancache_invalidate_page(mapping, page);
if (page_has_private(page))
do_invalidatepage(page, 0,
partial_end);
unlock_page(page);
page_cache_release(page);
}
}
/*
* If the truncation happened within a single page no pages
* will be released, just zeroed, so we can bail out now.
*/
if (start >= end)
return;
index = start;
for ( ; ; ) {
cond_resched();
if (!pagevec_lookup_entries(&pvec, mapping, index,
min(end - index, (pgoff_t)PAGEVEC_SIZE), indices)) {
/* If all gone from start onwards, we're done */
if (index == start)
break;
/* Otherwise restart to make sure all gone */
index = start;
continue;
}
if (index == start && indices[0] >= end) {
/* All gone out of hole to be punched, we're done */
pagevec_remove_exceptionals(&pvec);
pagevec_release(&pvec);
break;
}
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
/* We rely upon deletion not changing page->index */
index = indices[i];
if (index >= end) {
/* Restart punch to make sure all gone */
index = start - 1;
break;
}
if (radix_tree_exceptional_entry(page)) {
clear_exceptional_entry(mapping, index, page);
continue;
}
lock_page(page);
WARN_ON(page->index != index);
wait_on_page_writeback(page);
truncate_inode_page(mapping, page);
unlock_page(page);
}
pagevec_remove_exceptionals(&pvec);
pagevec_release(&pvec);
index++;
}
cleancache_invalidate_inode(mapping);
}
/*
* This is a little more tricky than the file -> pipe splicing. There are
* basically three cases:
*
* - Destination page already exists in the address space and there
* are users of it. For that case we have no other option that
* copying the data. Tough luck.
* - Destination page already exists in the address space, but there
* are no users of it. Make sure it's uptodate, then drop it. Fall
* through to last case.
* - Destination page does not exist, we can add the pipe page to
* the page cache and avoid the copy.
*
* If asked to move pages to the output file (SPLICE_F_MOVE is set in
* sd->flags), we attempt to migrate pages from the pipe to the output
* file address space page cache. This is possible if no one else has
* the pipe page referenced outside of the pipe and page cache. If
* SPLICE_F_MOVE isn't set, or we cannot move the page, we simply create
* a new page in the output file page cache and fill/dirty that.
*/
static int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
struct splice_desc *sd)
{
struct file *file = sd->file;
struct address_space *mapping = file->f_mapping;
unsigned int offset, this_len;
struct page *page;
pgoff_t index;
int ret;
/*
* make sure the data in this buffer is uptodate
*/
ret = buf->ops->pin(pipe, buf);
if (unlikely(ret))
return ret;
index = sd->pos >> PAGE_CACHE_SHIFT;
offset = sd->pos & ~PAGE_CACHE_MASK;
this_len = sd->len;
if (this_len + offset > PAGE_CACHE_SIZE)
this_len = PAGE_CACHE_SIZE - offset;
/*
* Reuse buf page, if SPLICE_F_MOVE is set and we are doing a full
* page.
*/
if ((sd->flags & SPLICE_F_MOVE) && this_len == PAGE_CACHE_SIZE) {
/*
* If steal succeeds, buf->page is now pruned from the
* pagecache and we can reuse it. The page will also be
* locked on successful return.
*/
if (buf->ops->steal(pipe, buf))
goto find_page;
page = buf->page;
if (add_to_page_cache(page, mapping, index, GFP_KERNEL)) {
unlock_page(page);
goto find_page;
}
page_cache_get(page);
if (!(buf->flags & PIPE_BUF_FLAG_LRU))
lru_cache_add(page);
} else {
find_page:
page = find_lock_page(mapping, index);
if (!page) {
ret = -ENOMEM;
page = page_cache_alloc_cold(mapping);
if (unlikely(!page))
goto out_ret;
/*
* This will also lock the page
*/
ret = add_to_page_cache_lru(page, mapping, index,
GFP_KERNEL);
if (unlikely(ret))
goto out;
}
/*
* We get here with the page locked. If the page is also
* uptodate, we don't need to do more. If it isn't, we
* may need to bring it in if we are not going to overwrite
* the full page.
*/
if (!PageUptodate(page)) {
if (this_len < PAGE_CACHE_SIZE) {
ret = mapping->a_ops->readpage(file, page);
if (unlikely(ret))
goto out;
lock_page(page);
if (!PageUptodate(page)) {
/*
* Page got invalidated, repeat.
*/
if (!page->mapping) {
unlock_page(page);
page_cache_release(page);
goto find_page;
}
ret = -EIO;
goto out;
}
} else
SetPageUptodate(page);
}
}
ret = mapping->a_ops->prepare_write(file, page, offset, offset+this_len);
if (unlikely(ret)) {
loff_t isize = i_size_read(mapping->host);
if (ret != AOP_TRUNCATED_PAGE)
unlock_page(page);
page_cache_release(page);
if (ret == AOP_TRUNCATED_PAGE)
goto find_page;
/*
* prepare_write() may have instantiated a few blocks
* outside i_size. Trim these off again.
*/
if (sd->pos + this_len > isize)
vmtruncate(mapping->host, isize);
goto out_ret;
}
if (buf->page != page) {
/*
* Careful, ->map() uses KM_USER0!
*/
char *src = buf->ops->map(pipe, buf, 1);
char *dst = kmap_atomic(page, KM_USER1);
memcpy(dst + offset, src + buf->offset, this_len);
flush_dcache_page(page);
kunmap_atomic(dst, KM_USER1);
buf->ops->unmap(pipe, buf, src);
}
ret = mapping->a_ops->commit_write(file, page, offset, offset+this_len);
if (!ret) {
/*
* Return the number of bytes written and mark page as
* accessed, we are now done!
*/
ret = this_len;
mark_page_accessed(page);
balance_dirty_pages_ratelimited(mapping);
} else if (ret == AOP_TRUNCATED_PAGE) {
page_cache_release(page);
goto find_page;
}
out:
page_cache_release(page);
unlock_page(page);
out_ret:
return ret;
}
static int copy_user_bh(struct page *to, struct inode *inode,
struct buffer_head *bh, unsigned long vaddr)
{
struct blk_dax_ctl dax = {
.sector = to_sector(bh, inode),
.size = bh->b_size,
};
struct block_device *bdev = bh->b_bdev;
void *vto;
if (dax_map_atomic(bdev, &dax) < 0)
return PTR_ERR(dax.addr);
vto = kmap_atomic(to);
copy_user_page(vto, (void __force *)dax.addr, vaddr, to);
kunmap_atomic(vto);
dax_unmap_atomic(bdev, &dax);
return 0;
}
#define NO_SECTOR -1
#define DAX_PMD_INDEX(page_index) (page_index & (PMD_MASK >> PAGE_SHIFT))
static int dax_radix_entry(struct address_space *mapping, pgoff_t index,
sector_t sector, bool pmd_entry, bool dirty)
{
struct radix_tree_root *page_tree = &mapping->page_tree;
pgoff_t pmd_index = DAX_PMD_INDEX(index);
int type, error = 0;
void *entry;
WARN_ON_ONCE(pmd_entry && !dirty);
if (dirty)
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
spin_lock_irq(&mapping->tree_lock);
entry = radix_tree_lookup(page_tree, pmd_index);
if (entry && RADIX_DAX_TYPE(entry) == RADIX_DAX_PMD) {
index = pmd_index;
goto dirty;
}
entry = radix_tree_lookup(page_tree, index);
if (entry) {
type = RADIX_DAX_TYPE(entry);
if (WARN_ON_ONCE(type != RADIX_DAX_PTE &&
type != RADIX_DAX_PMD)) {
error = -EIO;
goto unlock;
}
if (!pmd_entry || type == RADIX_DAX_PMD)
goto dirty;
/*
* We only insert dirty PMD entries into the radix tree. This
* means we don't need to worry about removing a dirty PTE
* entry and inserting a clean PMD entry, thus reducing the
* range we would flush with a follow-up fsync/msync call.
*/
radix_tree_delete(&mapping->page_tree, index);
mapping->nrexceptional--;
}
if (sector == NO_SECTOR) {
/*
* This can happen during correct operation if our pfn_mkwrite
* fault raced against a hole punch operation. If this
* happens the pte that was hole punched will have been
* unmapped and the radix tree entry will have been removed by
* the time we are called, but the call will still happen. We
* will return all the way up to wp_pfn_shared(), where the
* pte_same() check will fail, eventually causing page fault
* to be retried by the CPU.
*/
goto unlock;
}
error = radix_tree_insert(page_tree, index,
RADIX_DAX_ENTRY(sector, pmd_entry));
if (error)
goto unlock;
mapping->nrexceptional++;
dirty:
if (dirty)
radix_tree_tag_set(page_tree, index, PAGECACHE_TAG_DIRTY);
unlock:
spin_unlock_irq(&mapping->tree_lock);
return error;
}
static int dax_writeback_one(struct block_device *bdev,
struct address_space *mapping, pgoff_t index, void *entry)
{
struct radix_tree_root *page_tree = &mapping->page_tree;
int type = RADIX_DAX_TYPE(entry);
struct radix_tree_node *node;
struct blk_dax_ctl dax;
void **slot;
int ret = 0;
spin_lock_irq(&mapping->tree_lock);
/*
* Regular page slots are stabilized by the page lock even
* without the tree itself locked. These unlocked entries
* need verification under the tree lock.
*/
if (!__radix_tree_lookup(page_tree, index, &node, &slot))
goto unlock;
if (*slot != entry)
goto unlock;
/* another fsync thread may have already written back this entry */
if (!radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE))
goto unlock;
if (WARN_ON_ONCE(type != RADIX_DAX_PTE && type != RADIX_DAX_PMD)) {
ret = -EIO;
goto unlock;
}
dax.sector = RADIX_DAX_SECTOR(entry);
dax.size = (type == RADIX_DAX_PMD ? PMD_SIZE : PAGE_SIZE);
spin_unlock_irq(&mapping->tree_lock);
/*
* We cannot hold tree_lock while calling dax_map_atomic() because it
* eventually calls cond_resched().
*/
ret = dax_map_atomic(bdev, &dax);
if (ret < 0)
return ret;
if (WARN_ON_ONCE(ret < dax.size)) {
ret = -EIO;
goto unmap;
}
wb_cache_pmem(dax.addr, dax.size);
spin_lock_irq(&mapping->tree_lock);
radix_tree_tag_clear(page_tree, index, PAGECACHE_TAG_TOWRITE);
spin_unlock_irq(&mapping->tree_lock);
unmap:
dax_unmap_atomic(bdev, &dax);
return ret;
unlock:
spin_unlock_irq(&mapping->tree_lock);
return ret;
}
/*
* Flush the mapping to the persistent domain within the byte range of [start,
* end]. This is required by data integrity operations to ensure file data is
* on persistent storage prior to completion of the operation.
*/
int dax_writeback_mapping_range(struct address_space *mapping,
struct block_device *bdev, struct writeback_control *wbc)
{
struct inode *inode = mapping->host;
pgoff_t start_index, end_index, pmd_index;
pgoff_t indices[PAGEVEC_SIZE];
struct pagevec pvec;
bool done = false;
int i, ret = 0;
void *entry;
if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT))
return -EIO;
if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL)
return 0;
start_index = wbc->range_start >> PAGE_SHIFT;
end_index = wbc->range_end >> PAGE_SHIFT;
pmd_index = DAX_PMD_INDEX(start_index);
rcu_read_lock();
entry = radix_tree_lookup(&mapping->page_tree, pmd_index);
rcu_read_unlock();
/* see if the start of our range is covered by a PMD entry */
if (entry && RADIX_DAX_TYPE(entry) == RADIX_DAX_PMD)
start_index = pmd_index;
tag_pages_for_writeback(mapping, start_index, end_index);
pagevec_init(&pvec, 0);
while (!done) {
pvec.nr = find_get_entries_tag(mapping, start_index,
PAGECACHE_TAG_TOWRITE, PAGEVEC_SIZE,
pvec.pages, indices);
if (pvec.nr == 0)
break;
for (i = 0; i < pvec.nr; i++) {
if (indices[i] > end_index) {
done = true;
break;
}
ret = dax_writeback_one(bdev, mapping, indices[i],
pvec.pages[i]);
if (ret < 0)
return ret;
}
}
wmb_pmem();
return 0;
}
EXPORT_SYMBOL_GPL(dax_writeback_mapping_range);
static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
struct vm_area_struct *vma, struct vm_fault *vmf)
{
unsigned long vaddr = (unsigned long)vmf->virtual_address;
struct address_space *mapping = inode->i_mapping;
struct block_device *bdev = bh->b_bdev;
struct blk_dax_ctl dax = {
.sector = to_sector(bh, inode),
.size = bh->b_size,
};
pgoff_t size;
int error;
i_mmap_lock_read(mapping);
/*
* Check truncate didn't happen while we were allocating a block.
* If it did, this block may or may not be still allocated to the
* file. We can't tell the filesystem to free it because we can't
* take i_mutex here. In the worst case, the file still has blocks
* allocated past the end of the file.
*/
size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (unlikely(vmf->pgoff >= size)) {
error = -EIO;
goto out;
}
if (dax_map_atomic(bdev, &dax) < 0) {
error = PTR_ERR(dax.addr);
goto out;
}
if (buffer_unwritten(bh) || buffer_new(bh)) {
clear_pmem(dax.addr, PAGE_SIZE);
wmb_pmem();
}
dax_unmap_atomic(bdev, &dax);
error = dax_radix_entry(mapping, vmf->pgoff, dax.sector, false,
vmf->flags & FAULT_FLAG_WRITE);
if (error)
goto out;
error = vm_insert_mixed(vma, vaddr, dax.pfn);
out:
i_mmap_unlock_read(mapping);
return error;
}
/**
* __dax_fault - handle a page fault on a DAX file
* @vma: The virtual memory area where the fault occurred
* @vmf: The description of the fault
* @get_block: The filesystem method used to translate file offsets to blocks
* @complete_unwritten: The filesystem method used to convert unwritten blocks
* to written so the data written to them is exposed. This is required for
* required by write faults for filesystems that will return unwritten
* extent mappings from @get_block, but it is optional for reads as
* dax_insert_mapping() will always zero unwritten blocks. If the fs does
* not support unwritten extents, the it should pass NULL.
*
* When a page fault occurs, filesystems may call this helper in their
* fault handler for DAX files. __dax_fault() assumes the caller has done all
* the necessary locking for the page fault to proceed successfully.
*/
int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
get_block_t get_block, dax_iodone_t complete_unwritten)
{
struct file *file = vma->vm_file;
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
struct page *page;
struct buffer_head bh;
unsigned long vaddr = (unsigned long)vmf->virtual_address;
unsigned blkbits = inode->i_blkbits;
sector_t block;
pgoff_t size;
int error;
int major = 0;
size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (vmf->pgoff >= size)
return VM_FAULT_SIGBUS;
memset(&bh, 0, sizeof(bh));
block = (sector_t)vmf->pgoff << (PAGE_SHIFT - blkbits);
bh.b_bdev = inode->i_sb->s_bdev;
bh.b_size = PAGE_SIZE;
repeat:
page = find_get_page(mapping, vmf->pgoff);
if (page) {
if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) {
put_page(page);
return VM_FAULT_RETRY;
}
if (unlikely(page->mapping != mapping)) {
unlock_page(page);
put_page(page);
goto repeat;
}
size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (unlikely(vmf->pgoff >= size)) {
/*
* We have a struct page covering a hole in the file
* from a read fault and we've raced with a truncate
*/
error = -EIO;
goto unlock_page;
}
}
error = get_block(inode, block, &bh, 0);
if (!error && (bh.b_size < PAGE_SIZE))
error = -EIO; /* fs corruption? */
if (error)
goto unlock_page;
if (!buffer_mapped(&bh) && !buffer_unwritten(&bh) && !vmf->cow_page) {
if (vmf->flags & FAULT_FLAG_WRITE) {
error = get_block(inode, block, &bh, 1);
count_vm_event(PGMAJFAULT);
mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
major = VM_FAULT_MAJOR;
if (!error && (bh.b_size < PAGE_SIZE))
error = -EIO;
if (error)
goto unlock_page;
} else {
return dax_load_hole(mapping, page, vmf);
}
}
if (vmf->cow_page) {
struct page *new_page = vmf->cow_page;
if (buffer_written(&bh))
error = copy_user_bh(new_page, inode, &bh, vaddr);
else
clear_user_highpage(new_page, vaddr);
if (error)
goto unlock_page;
vmf->page = page;
if (!page) {
i_mmap_lock_read(mapping);
/* Check we didn't race with truncate */
size = (i_size_read(inode) + PAGE_SIZE - 1) >>
PAGE_SHIFT;
if (vmf->pgoff >= size) {
i_mmap_unlock_read(mapping);
error = -EIO;
goto out;
}
}
return VM_FAULT_LOCKED;
}
/* Check we didn't race with a read fault installing a new page */
if (!page && major)
page = find_lock_page(mapping, vmf->pgoff);
if (page) {
unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT,
PAGE_SIZE, 0);
delete_from_page_cache(page);
unlock_page(page);
put_page(page);
page = NULL;
}
/*
* If we successfully insert the new mapping over an unwritten extent,
* we need to ensure we convert the unwritten extent. If there is an
* error inserting the mapping, the filesystem needs to leave it as
* unwritten to prevent exposure of the stale underlying data to
* userspace, but we still need to call the completion function so
* the private resources on the mapping buffer can be released. We
* indicate what the callback should do via the uptodate variable, same
* as for normal BH based IO completions.
*/
error = dax_insert_mapping(inode, &bh, vma, vmf);
if (buffer_unwritten(&bh)) {
if (complete_unwritten)
complete_unwritten(&bh, !error);
else
WARN_ON_ONCE(!(vmf->flags & FAULT_FLAG_WRITE));
}
out:
if (error == -ENOMEM)
return VM_FAULT_OOM | major;
/* -EBUSY is fine, somebody else faulted on the same PTE */
if ((error < 0) && (error != -EBUSY))
return VM_FAULT_SIGBUS | major;
return VM_FAULT_NOPAGE | major;
unlock_page:
if (page) {
unlock_page(page);
put_page(page);
}
goto out;
}
* negative error code is returned.
*
* %-EBUSY - page has an active buffer.
*
* %-ENOENT - page cache has no page addressed by the offset.
*/
int nilfs_mdt_forget_block(struct inode *inode, unsigned long block)
{
pgoff_t index = (pgoff_t)block >>
(PAGE_CACHE_SHIFT - inode->i_blkbits);
struct page *page;
unsigned long first_block;
int ret = 0;
int still_dirty;
page = find_lock_page(inode->i_mapping, index);
if (!page)
return -ENOENT;
wait_on_page_writeback(page);
first_block = (unsigned long)index <<
(PAGE_CACHE_SHIFT - inode->i_blkbits);
if (page_has_buffers(page)) {
struct buffer_head *bh;
bh = nilfs_page_get_nth_block(page, block - first_block);
nilfs_forget_buffer(bh);
}
still_dirty = PageDirty(page);
unlock_page(page);
/*
* This is a little more tricky than the file -> pipe splicing. There are
* basically three cases:
*
* - Destination page already exists in the address space and there
* are users of it. For that case we have no other option that
* copying the data. Tough luck.
* - Destination page already exists in the address space, but there
* are no users of it. Make sure it's uptodate, then drop it. Fall
* through to last case.
* - Destination page does not exist, we can add the pipe page to
* the page cache and avoid the copy.
*
* If asked to move pages to the output file (SPLICE_F_MOVE is set in
* sd->flags), we attempt to migrate pages from the pipe to the output
* file address space page cache. This is possible if no one else has
* the pipe page referenced outside of the pipe and page cache. If
* SPLICE_F_MOVE isn't set, or we cannot move the page, we simply create
* a new page in the output file page cache and fill/dirty that.
*/
static int pipe_to_file(struct pipe_inode_info *pipe, struct pipe_buffer *buf,
struct splice_desc *sd)
{
struct file *file = sd->file;
struct address_space *mapping = file->f_mapping;
unsigned int offset, this_len;
struct page *page;
pgoff_t index;
int ret;
/*
* make sure the data in this buffer is uptodate
*/
ret = buf->ops->pin(pipe, buf);
if (unlikely(ret))
return ret;
index = sd->pos >> PAGE_CACHE_SHIFT;
offset = sd->pos & ~PAGE_CACHE_MASK;
this_len = sd->len;
if (this_len + offset > PAGE_CACHE_SIZE)
this_len = PAGE_CACHE_SIZE - offset;
find_page:
page = find_lock_page(mapping, index);
if (!page) {
ret = -ENOMEM;
page = page_cache_alloc_cold(mapping);
if (unlikely(!page))
goto out_ret;
/*
* This will also lock the page
*/
ret = add_to_page_cache_lru(page, mapping, index,
GFP_KERNEL);
if (unlikely(ret))
goto out;
}
ret = mapping->a_ops->prepare_write(file, page, offset, offset+this_len);
if (unlikely(ret)) {
loff_t isize = i_size_read(mapping->host);
if (ret != AOP_TRUNCATED_PAGE)
unlock_page(page);
page_cache_release(page);
if (ret == AOP_TRUNCATED_PAGE)
goto find_page;
/*
* prepare_write() may have instantiated a few blocks
* outside i_size. Trim these off again.
*/
if (sd->pos + this_len > isize)
vmtruncate(mapping->host, isize);
goto out_ret;
}
if (buf->page != page) {
/*
* Careful, ->map() uses KM_USER0!
*/
char *src = buf->ops->map(pipe, buf, 1);
char *dst = kmap_atomic(page, KM_USER1);
memcpy(dst + offset, src + buf->offset, this_len);
flush_dcache_page(page);
kunmap_atomic(dst, KM_USER1);
buf->ops->unmap(pipe, buf, src);
}
ret = mapping->a_ops->commit_write(file, page, offset, offset+this_len);
if (ret) {
if (ret == AOP_TRUNCATED_PAGE) {
page_cache_release(page);
goto find_page;
}
if (ret < 0)
goto out;
/*
* Partial write has happened, so 'ret' already initialized by
* number of bytes written, Where is nothing we have to do here.
*/
} else
ret = this_len;
/*
* Return the number of bytes written and mark page as
* accessed, we are now done!
*/
mark_page_accessed(page);
balance_dirty_pages_ratelimited(mapping);
out:
page_cache_release(page);
unlock_page(page);
out_ret:
return ret;
}