/*
* Attempt to steal a page from a pipe buffer. This should perhaps go into
* a vm helper function, it's already simplified quite a bit by the
* addition of remove_mapping(). If success is returned, the caller may
* attempt to reuse this page for another destination.
*/
static int page_cache_pipe_buf_steal(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
struct page *page = buf->page;
struct address_space *mapping = page_mapping(page);
lock_page(page);
WARN_ON(!PageUptodate(page));
/*
* At least for ext2 with nobh option, we need to wait on writeback
* completing on this page, since we'll remove it from the pagecache.
* Otherwise truncate wont wait on the page, allowing the disk
* blocks to be reused by someone else before we actually wrote our
* data to them. fs corruption ensues.
*/
wait_on_page_writeback(page);
if (PagePrivate(page))
try_to_release_page(page, mapping_gfp_mask(mapping));
if (!remove_mapping(mapping, page)) {
unlock_page(page);
return 1;
}
buf->flags |= PIPE_BUF_FLAG_LRU;
return 0;
}
/*
* Retrieve a set of pages from FS-Cache
*/
int __cifs_readpages_from_fscache(struct inode *inode,
struct address_space *mapping,
struct list_head *pages,
unsigned *nr_pages)
{
int ret;
cFYI(1, "CIFS: __cifs_readpages_from_fscache (0x%p/%u/0x%p)",
CIFS_I(inode)->fscache, *nr_pages, inode);
ret = fscache_read_or_alloc_pages(CIFS_I(inode)->fscache, mapping,
pages, nr_pages,
cifs_readpage_from_fscache_complete,
NULL,
mapping_gfp_mask(mapping));
switch (ret) {
case 0: /* read submitted to the cache for all pages */
cFYI(1, "CIFS: readpages_from_fscache: submitted");
return ret;
case -ENOBUFS: /* some pages are not cached and can't be */
case -ENODATA: /* some pages are not cached */
cFYI(1, "CIFS: readpages_from_fscache: no page");
return 1;
default:
cFYI(1, "unknown error ret = %d", ret);
}
return ret;
}
int __v9fs_readpages_from_fscache(struct inode *inode,
struct address_space *mapping,
struct list_head *pages,
unsigned *nr_pages)
{
int ret;
const struct v9fs_inode *v9inode = V9FS_I(inode);
p9_debug(P9_DEBUG_FSC, "inode %p pages %u\n", inode, *nr_pages);
if (!v9inode->fscache)
return -ENOBUFS;
ret = fscache_read_or_alloc_pages(v9inode->fscache,
mapping, pages, nr_pages,
v9fs_vfs_readpage_complete,
NULL,
mapping_gfp_mask(mapping));
switch (ret) {
case -ENOBUFS:
case -ENODATA:
p9_debug(P9_DEBUG_FSC, "pages/inodes not in cache %d\n", ret);
return 1;
case 0:
BUG_ON(!list_empty(pages));
BUG_ON(*nr_pages != 0);
p9_debug(P9_DEBUG_FSC, "BIO submitted\n");
return ret;
default:
p9_debug(P9_DEBUG_FSC, "ret %d\n", ret);
return ret;
}
}
static int udl_gem_get_pages(struct udl_gem_object *obj, gfp_t gfpmask)
{
int page_count, i;
struct page *page;
struct inode *inode;
struct address_space *mapping;
if (obj->pages)
return 0;
page_count = obj->base.size / PAGE_SIZE;
BUG_ON(obj->pages != NULL);
obj->pages = drm_malloc_ab(page_count, sizeof(struct page *));
if (obj->pages == NULL)
return -ENOMEM;
inode = obj->base.filp->f_path.dentry->d_inode;
mapping = inode->i_mapping;
gfpmask |= mapping_gfp_mask(mapping);
for (i = 0; i < page_count; i++) {
page = shmem_read_mapping_page_gfp(mapping, i, gfpmask);
if (IS_ERR(page))
goto err_pages;
obj->pages[i] = page;
}
return 0;
err_pages:
while (i--)
page_cache_release(obj->pages[i]);
drm_free_large(obj->pages);
obj->pages = NULL;
return PTR_ERR(page);
}
/* part of tail2extent. replace tail items with extent one. Content of tail
items (@count bytes) being cut are copied already into
pages. extent_writepage method is called to create extents corresponding to
those pages */
static int replace(struct inode *inode, struct page **pages, unsigned nr_pages, int count)
{
int result;
unsigned i;
STORE_COUNTERS;
if (nr_pages == 0)
return 0;
assert("vs-596", pages[0]);
/* cut copied items */
result = cut_formatting_items(inode, page_offset(pages[0]), count);
if (result)
return result;
CHECK_COUNTERS;
/* put into tree replacement for just removed items: extent item, namely */
for (i = 0; i < nr_pages; i++) {
result = add_to_page_cache_lru(pages[i], inode->i_mapping,
pages[i]->index,
mapping_gfp_mask(inode->
i_mapping));
if (result)
break;
unlock_page(pages[i]);
result = find_or_create_extent(pages[i]);
if (result)
break;
SetPageUptodate(pages[i]);
}
return result;
}
int ttm_tt_swapout(struct ttm_tt *ttm, struct file *persistent_swap_storage)
{
struct address_space *swap_space;
struct file *swap_storage;
struct page *from_page;
struct page *to_page;
int i;
int ret = -ENOMEM;
BUG_ON(ttm->state != tt_unbound && ttm->state != tt_unpopulated);
BUG_ON(ttm->caching_state != tt_cached);
if (!persistent_swap_storage) {
swap_storage = shmem_file_setup("ttm swap",
ttm->num_pages << PAGE_SHIFT,
0);
if (IS_ERR(swap_storage)) {
pr_err("Failed allocating swap storage\n");
return PTR_ERR(swap_storage);
}
} else {
swap_storage = persistent_swap_storage;
}
swap_space = swap_storage->f_mapping;
for (i = 0; i < ttm->num_pages; ++i) {
gfp_t gfp_mask = mapping_gfp_mask(swap_space);
gfp_mask |= (ttm->page_flags & TTM_PAGE_FLAG_NO_RETRY ? __GFP_RETRY_MAYFAIL : 0);
from_page = ttm->pages[i];
if (unlikely(from_page == NULL))
continue;
to_page = shmem_read_mapping_page_gfp(swap_space, i, gfp_mask);
if (IS_ERR(to_page)) {
ret = PTR_ERR(to_page);
goto out_err;
}
copy_highpage(to_page, from_page);
set_page_dirty(to_page);
mark_page_accessed(to_page);
put_page(to_page);
}
ttm_tt_unpopulate(ttm);
ttm->swap_storage = swap_storage;
ttm->page_flags |= TTM_PAGE_FLAG_SWAPPED;
if (persistent_swap_storage)
ttm->page_flags |= TTM_PAGE_FLAG_PERSISTENT_SWAP;
return 0;
out_err:
if (!persistent_swap_storage)
fput(swap_storage);
return ret;
}
/*
* Initialize the Linux inode.
*
* When reading existing inodes from disk this is called directly from xfs_iget,
* when creating a new inode it is called from xfs_ialloc after setting up the
* inode. These callers have different criteria for clearing XFS_INEW, so leave
* it up to the caller to deal with unlocking the inode appropriately.
*/
void
xfs_setup_inode(
struct xfs_inode *ip)
{
struct inode *inode = &ip->i_vnode;
gfp_t gfp_mask;
inode->i_ino = ip->i_ino;
inode->i_state = I_NEW;
inode_sb_list_add(inode);
/* make the inode look hashed for the writeback code */
hlist_add_fake(&inode->i_hash);
inode->i_uid = xfs_uid_to_kuid(ip->i_d.di_uid);
inode->i_gid = xfs_gid_to_kgid(ip->i_d.di_gid);
switch (inode->i_mode & S_IFMT) {
case S_IFBLK:
case S_IFCHR:
inode->i_rdev =
MKDEV(sysv_major(ip->i_df.if_u2.if_rdev) & 0x1ff,
sysv_minor(ip->i_df.if_u2.if_rdev));
break;
default:
inode->i_rdev = 0;
break;
}
i_size_write(inode, ip->i_d.di_size);
xfs_diflags_to_iflags(inode, ip);
if (S_ISDIR(inode->i_mode)) {
lockdep_set_class(&ip->i_lock.mr_lock, &xfs_dir_ilock_class);
ip->d_ops = ip->i_mount->m_dir_inode_ops;
} else {
ip->d_ops = ip->i_mount->m_nondir_inode_ops;
lockdep_set_class(&ip->i_lock.mr_lock, &xfs_nondir_ilock_class);
}
/*
* Ensure all page cache allocations are done from GFP_NOFS context to
* prevent direct reclaim recursion back into the filesystem and blowing
* stacks or deadlocking.
*/
gfp_mask = mapping_gfp_mask(inode->i_mapping);
mapping_set_gfp_mask(inode->i_mapping, (gfp_mask & ~(__GFP_FS)));
/*
* If there is no attribute fork no ACL can exist on this inode,
* and it can't have any file capabilities attached to it either.
*/
if (!XFS_IFORK_Q(ip)) {
inode_has_no_xattr(inode);
cache_no_acl(inode);
}
}
static int afs_readpages(struct file *file, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages)
{
struct key *key = file->private_data;
struct afs_vnode *vnode;
int ret = 0;
_enter("{%d},{%lu},,%d",
key_serial(key), mapping->host->i_ino, nr_pages);
ASSERT(key != NULL);
vnode = AFS_FS_I(mapping->host);
if (vnode->flags & AFS_VNODE_DELETED) {
_leave(" = -ESTALE");
return -ESTALE;
}
/* attempt to read as many of the pages as possible */
#ifdef CONFIG_AFS_FSCACHE
ret = fscache_read_or_alloc_pages(vnode->cache,
mapping,
pages,
&nr_pages,
afs_file_readpage_read_complete,
NULL,
mapping_gfp_mask(mapping));
#else
ret = -ENOBUFS;
#endif
switch (ret) {
/* all pages are being read from the cache */
case 0:
BUG_ON(!list_empty(pages));
BUG_ON(nr_pages != 0);
_leave(" = 0 [reading all]");
return 0;
/* there were pages that couldn't be read from the cache */
case -ENODATA:
case -ENOBUFS:
break;
/* other error */
default:
_leave(" = %d", ret);
return ret;
}
/* load the missing pages from the network */
ret = read_cache_pages(mapping, pages, afs_page_filler, key);
_leave(" = %d [netting]", ret);
return ret;
}
/* added: begin address space operations definitions */
static int wrapfs_writepage(struct page *page, struct writeback_control *wbc){
int err = -EIO;
struct inode *inode;
struct inode *lower_inode;
struct page *lower_page;
struct address_space *lower_mapping; /* lower inode mapping */
gfp_t mask;
BUG_ON(!PageUptodate(page));
inode = page->mapping->host;
if (!inode || !WRAPFS_I(inode)){
err = 0;
goto out;
}
lower_inode = wrapfs_lower_inode(inode);
lower_mapping = lower_inode->i_mapping;
mask = mapping_gfp_mask(lower_mapping) & ~(__GFP_FS);
lower_page = find_or_create_page(lower_mapping, page->index, mask);
if (!lower_page) {
err = 0;
set_page_dirty(page);
goto out;
}
copy_highpage(lower_page, page);
flush_dcache_page(lower_page);
SetPageUptodate(lower_page);
set_page_dirty(lower_page);
if (wbc->for_reclaim) {
unlock_page(lower_page);
goto out_release;
}
BUG_ON(!lower_mapping->a_ops->writepage);
wait_on_page_writeback(lower_page); /* prevent multiple writers */
clear_page_dirty_for_io(lower_page); /* emulate VFS behavior */
err = lower_mapping->a_ops->writepage(lower_page, wbc);
if (err < 0)
goto out_release;
if (err == AOP_WRITEPAGE_ACTIVATE) {
err = 0;
unlock_page(lower_page);
}
fsstack_copy_attr_times(inode, lower_inode);
out_release:
page_cache_release(lower_page);
out:
unlock_page(page);
return err;
}
static int afs_file_readpages(struct file *filp, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages)
{
struct afs_vnode *vnode;
#if 0
struct pagevec lru_pvec;
unsigned page_idx;
#endif
int ret = 0;
_enter(",{%lu},,%d", mapping->host->i_ino, nr_pages);
vnode = AFS_FS_I(mapping->host);
if (vnode->flags & AFS_VNODE_DELETED) {
_leave(" = -ESTALE");
return -ESTALE;
}
/* attempt to read as many of the pages as possible */
ret = fscache_read_or_alloc_pages(vnode->cache,
mapping,
pages,
&nr_pages,
afs_file_readpage_read_complete,
NULL,
mapping_gfp_mask(mapping));
switch (ret) {
/* all pages are being read from the cache */
case 0:
BUG_ON(!list_empty(pages));
BUG_ON(nr_pages != 0);
_leave(" = 0 [reading all]");
return 0;
/* there were pages that couldn't be read from the cache */
case -ENODATA:
case -ENOBUFS:
break;
/* other error */
default:
_leave(" = %d", ret);
return ret;
}
/* load the missing pages from the network */
ret = read_cache_pages(mapping, pages,
(void *) afs_file_readpage, NULL);
_leave(" = %d [netting]", ret);
return ret;
} /* end afs_file_readpages() */
/*
* Retrieve a set of pages from fscache
*/
int __nfs_readpages_from_fscache(struct nfs_open_context *ctx,
struct inode *inode,
struct address_space *mapping,
struct list_head *pages,
unsigned *nr_pages)
{
unsigned npages = *nr_pages;
int ret;
// dfprintk(FSCACHE, "NFS: nfs_getpages_from_fscache (0x%p/%u/0x%p)\n",
;
ret = fscache_read_or_alloc_pages(NFS_I(inode)->fscache,
mapping, pages, nr_pages,
nfs_readpage_from_fscache_complete,
ctx,
mapping_gfp_mask(mapping));
if (*nr_pages < npages)
nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK,
npages);
if (*nr_pages > 0)
nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL,
*nr_pages);
switch (ret) {
case 0: /* read submitted to the cache for all pages */
BUG_ON(!list_empty(pages));
BUG_ON(*nr_pages != 0);
// dfprintk(FSCACHE,
;
return ret;
case -ENOBUFS: /* some pages aren't cached and can't be */
case -ENODATA: /* some pages aren't cached */
// dfprintk(FSCACHE,
;
return 1;
default:
// dfprintk(FSCACHE,
;
}
return ret;
}
static struct page *get_mapping_page(struct super_block *sb, pgoff_t index,
int use_filler)
{
struct logfs_super *super = logfs_super(sb);
struct address_space *mapping = super->s_mapping_inode->i_mapping;
filler_t *filler = super->s_devops->readpage;
struct page *page;
BUG_ON(mapping_gfp_mask(mapping) & __GFP_FS);
if (use_filler)
page = read_cache_page(mapping, index, filler, sb);
else {
page = find_or_create_page(mapping, index, GFP_NOFS);
unlock_page(page);
}
return page;
}
/* part of tail2extent. replace tail items with extent one. Content of tail
items (@count bytes) being cut are copied already into
pages. extent_writepage method is called to create extents corresponding to
those pages */
static int replace(struct inode *inode, struct page **pages, unsigned nr_pages, int count)
{
int result;
unsigned i;
STORE_COUNTERS;
if (nr_pages == 0)
return 0;
assert("vs-596", pages[0]);
/* cut copied items */
result = cut_formatting_items(inode, page_offset(pages[0]), count);
if (result)
return result;
CHECK_COUNTERS;
/* put into tree replacement for just removed items: extent item, namely */
for (i = 0; i < nr_pages; i++) {
result = add_to_page_cache_lru(pages[i], inode->i_mapping,
pages[i]->index,
mapping_gfp_mask(inode->
i_mapping));
if (result)
break;
unlock_page(pages[i]);
result = find_or_create_extent(pages[i]);
if (result) {
/*
* Unsuccess in critical place:
* tail has been removed,
* but extent hasn't been created
*/
warning("edward-1572",
"Report the error code %i to developers. Run FSCK",
result);
break;
}
SetPageUptodate(pages[i]);
}
return result;
}
struct page* bd_get_page(struct block_device *bdev, pgoff_t index)
{
struct inode *bd_inode = bdev->bd_inode;
struct address_space *mapping = bd_inode->i_mapping;
struct page *page;
int error;
BUG_ON(!mapping);
page = find_or_create_page(mapping, index, mapping_gfp_mask(mapping));
if( !PageUptodate(page) )
{
error = mapping->a_ops->readpage(NULL, page);
BUG_ON(error);
lock_page(page);
}
return page;
}
void nilfs_set_inode_flags(struct inode *inode)
{
unsigned int flags = NILFS_I(inode)->i_flags;
inode->i_flags &= ~(S_SYNC | S_APPEND | S_IMMUTABLE | S_NOATIME |
S_DIRSYNC);
if (flags & FS_SYNC_FL)
inode->i_flags |= S_SYNC;
if (flags & FS_APPEND_FL)
inode->i_flags |= S_APPEND;
if (flags & FS_IMMUTABLE_FL)
inode->i_flags |= S_IMMUTABLE;
if (flags & FS_NOATIME_FL)
inode->i_flags |= S_NOATIME;
if (flags & FS_DIRSYNC_FL)
inode->i_flags |= S_DIRSYNC;
mapping_set_gfp_mask(inode->i_mapping,
mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS);
}
struct page *sgx_get_backing(struct sgx_encl *encl,
struct sgx_encl_page *entry,
bool pcmd)
{
struct inode *inode;
struct address_space *mapping;
gfp_t gfpmask;
pgoff_t index;
if (pcmd)
inode = encl->pcmd->f_path.dentry->d_inode;
else
inode = encl->backing->f_path.dentry->d_inode;
mapping = inode->i_mapping;
gfpmask = mapping_gfp_mask(mapping);
if (pcmd)
index = (entry->addr - encl->base) >> (PAGE_SHIFT + 5);
else
int ttm_tt_swapin(struct ttm_tt *ttm)
{
struct address_space *swap_space;
struct file *swap_storage;
struct page *from_page;
struct page *to_page;
int i;
int ret = -ENOMEM;
swap_storage = ttm->swap_storage;
BUG_ON(swap_storage == NULL);
swap_space = swap_storage->f_mapping;
for (i = 0; i < ttm->num_pages; ++i) {
gfp_t gfp_mask = mapping_gfp_mask(swap_space);
gfp_mask |= (ttm->page_flags & TTM_PAGE_FLAG_NO_RETRY ? __GFP_RETRY_MAYFAIL : 0);
from_page = shmem_read_mapping_page_gfp(swap_space, i, gfp_mask);
if (IS_ERR(from_page)) {
ret = PTR_ERR(from_page);
goto out_err;
}
to_page = ttm->pages[i];
if (unlikely(to_page == NULL))
goto out_err;
copy_highpage(to_page, from_page);
put_page(from_page);
}
if (!(ttm->page_flags & TTM_PAGE_FLAG_PERSISTENT_SWAP))
fput(swap_storage);
ttm->swap_storage = NULL;
ttm->page_flags &= ~TTM_PAGE_FLAG_SWAPPED;
return 0;
out_err:
return ret;
}
static int
__generic_file_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags)
{
struct address_space *mapping = in->f_mapping;
unsigned int loff, nr_pages;
struct page *pages[PIPE_BUFFERS];
struct partial_page partial[PIPE_BUFFERS];
struct page *page;
pgoff_t index, end_index;
loff_t isize;
size_t total_len;
int error, page_nr;
struct splice_pipe_desc spd = {
.pages = pages,
.partial = partial,
.flags = flags,
.ops = &page_cache_pipe_buf_ops,
};
index = *ppos >> PAGE_CACHE_SHIFT;
loff = *ppos & ~PAGE_CACHE_MASK;
nr_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
if (nr_pages > PIPE_BUFFERS)
nr_pages = PIPE_BUFFERS;
/*
* Initiate read-ahead on this page range. however, don't call into
* read-ahead if this is a non-zero offset (we are likely doing small
* chunk splice and the page is already there) for a single page.
*/
if (!loff || nr_pages > 1)
page_cache_readahead(mapping, &in->f_ra, in, index, nr_pages);
/*
* Now fill in the holes:
*/
error = 0;
total_len = 0;
/*
* Lookup the (hopefully) full range of pages we need.
*/
spd.nr_pages = find_get_pages_contig(mapping, index, nr_pages, pages);
/*
* If find_get_pages_contig() returned fewer pages than we needed,
* allocate the rest.
*/
index += spd.nr_pages;
while (spd.nr_pages < nr_pages) {
/*
* Page could be there, find_get_pages_contig() breaks on
* the first hole.
*/
page = find_get_page(mapping, index);
if (!page) {
/*
* Make sure the read-ahead engine is notified
* about this failure.
*/
handle_ra_miss(mapping, &in->f_ra, index);
/*
* page didn't exist, allocate one.
*/
page = page_cache_alloc_cold(mapping);
if (!page)
break;
error = add_to_page_cache_lru(page, mapping, index,
mapping_gfp_mask(mapping));
if (unlikely(error)) {
page_cache_release(page);
if (error == -EEXIST)
continue;
break;
}
/*
* add_to_page_cache() locks the page, unlock it
* to avoid convoluting the logic below even more.
*/
unlock_page(page);
}
pages[spd.nr_pages++] = page;
index++;
}
/*
* Now loop over the map and see if we need to start IO on any
* pages, fill in the partial map, etc.
*/
index = *ppos >> PAGE_CACHE_SHIFT;
nr_pages = spd.nr_pages;
spd.nr_pages = 0;
for (page_nr = 0; page_nr < nr_pages; page_nr++) {
unsigned int this_len;
if (!len)
break;
/*
* this_len is the max we'll use from this page
*/
this_len = min_t(unsigned long, len, PAGE_CACHE_SIZE - loff);
page = pages[page_nr];
/*
* If the page isn't uptodate, we may need to start io on it
*/
if (!PageUptodate(page)) {
/*
* If in nonblock mode then dont block on waiting
* for an in-flight io page
*/
if (flags & SPLICE_F_NONBLOCK)
break;
lock_page(page);
/*
* page was truncated, stop here. if this isn't the
* first page, we'll just complete what we already
* added
*/
if (!page->mapping) {
unlock_page(page);
break;
}
/*
* page was already under io and is now done, great
*/
if (PageUptodate(page)) {
unlock_page(page);
goto fill_it;
}
/*
* need to read in the page
*/
error = mapping->a_ops->readpage(in, page);
if (unlikely(error)) {
/*
* We really should re-lookup the page here,
* but it complicates things a lot. Instead
* lets just do what we already stored, and
* we'll get it the next time we are called.
*/
if (error == AOP_TRUNCATED_PAGE)
error = 0;
break;
}
/*
* i_size must be checked after ->readpage().
*/
isize = i_size_read(mapping->host);
end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
if (unlikely(!isize || index > end_index))
break;
/*
* if this is the last page, see if we need to shrink
* the length and stop
*/
if (end_index == index) {
loff = PAGE_CACHE_SIZE - (isize & ~PAGE_CACHE_MASK);
if (total_len + loff > isize)
break;
/*
* force quit after adding this page
*/
len = this_len;
this_len = min(this_len, loff);
loff = 0;
}
}
fill_it:
partial[page_nr].offset = loff;
partial[page_nr].len = this_len;
len -= this_len;
total_len += this_len;
loff = 0;
spd.nr_pages++;
index++;
}
/*
* Release any pages at the end, if we quit early. 'i' is how far
* we got, 'nr_pages' is how many pages are in the map.
*/
while (page_nr < nr_pages)
page_cache_release(pages[page_nr++]);
if (spd.nr_pages)
return splice_to_pipe(pipe, &spd);
return error;
}
struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
{
struct super_block *sb = dir->i_sb;
struct the_nilfs *nilfs = sb->s_fs_info;
struct inode *inode;
struct nilfs_inode_info *ii;
struct nilfs_root *root;
int err = -ENOMEM;
ino_t ino;
inode = new_inode(sb);
if (unlikely(!inode))
goto failed;
mapping_set_gfp_mask(inode->i_mapping,
mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS);
root = NILFS_I(dir)->i_root;
ii = NILFS_I(inode);
ii->i_state = 1 << NILFS_I_NEW;
ii->i_root = root;
err = nilfs_ifile_create_inode(root->ifile, &ino, &ii->i_bh);
if (unlikely(err))
goto failed_ifile_create_inode;
/* reference count of i_bh inherits from nilfs_mdt_read_block() */
atomic_inc(&root->inodes_count);
inode_init_owner(inode, dir, mode);
inode->i_ino = ino;
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) {
err = nilfs_bmap_read(ii->i_bmap, NULL);
if (err < 0)
goto failed_bmap;
set_bit(NILFS_I_BMAP, &ii->i_state);
/* No lock is needed; iget() ensures it. */
}
ii->i_flags = nilfs_mask_flags(
mode, NILFS_I(dir)->i_flags & NILFS_FL_INHERITED);
/* ii->i_file_acl = 0; */
/* ii->i_dir_acl = 0; */
ii->i_dir_start_lookup = 0;
nilfs_set_inode_flags(inode);
spin_lock(&nilfs->ns_next_gen_lock);
inode->i_generation = nilfs->ns_next_generation++;
spin_unlock(&nilfs->ns_next_gen_lock);
insert_inode_hash(inode);
err = nilfs_init_acl(inode, dir);
if (unlikely(err))
goto failed_acl; /* never occur. When supporting
nilfs_init_acl(), proper cancellation of
above jobs should be considered */
return inode;
failed_acl:
failed_bmap:
clear_nlink(inode);
iput(inode); /* raw_inode will be deleted through
generic_delete_inode() */
goto failed;
failed_ifile_create_inode:
make_bad_inode(inode);
iput(inode); /* if i_nlink == 1, generic_forget_inode() will be
called */
failed:
return ERR_PTR(err);
}
/*
* 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;
gfp_t gfp_mask = mapping_gfp_mask(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_mask)) {
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_nomem;
/*
* This will also lock the page
*/
ret = add_to_page_cache_lru(page, mapping, index,
gfp_mask);
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;
}
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_nomem:
return ret;
}
static int wrapfs_writepage(struct page *page, struct writeback_control *wbc)
{
int err = -EIO;
struct inode *inode;
struct inode *lower_inode;
struct page *lower_page;
struct address_space *lower_mapping; /* lower inode mapping */
gfp_t mask;
char *lower_page_data = NULL;
/*#ifdef WRAPFS_CRYPTO
char *enc_buf = NULL;
#endif*/
wrapfs_debug_aops(
WRAPFS_SB(page->mapping->host->i_sb)->wrapfs_debug_a_ops, "");
wrapfs_debug("");
BUG_ON(!PageUptodate(page));
wrapfs_debug("");
inode = page->mapping->host;
/* if no lower inode, nothing to do */
if (!inode || !WRAPFS_I(inode) || WRAPFS_I(inode)->lower_inode) {
err = 0;
goto out;
}
lower_inode = wrapfs_lower_inode(inode);
lower_mapping = lower_inode->i_mapping;
/*
* find lower page (returns a locked page)
*
* We turn off __GFP_FS while we look for or create a new lower
* page. This prevents a recursion into the file system code, which
* under memory pressure conditions could lead to a deadlock. This
* is similar to how the loop driver behaves (see loop_set_fd in
* drivers/block/loop.c). If we can't find the lower page, we
* redirty our page and return "success" so that the VM will call us
* again in the (hopefully near) future.
*/
mask = mapping_gfp_mask(lower_mapping) & ~(__GFP_FS);
lower_page = find_or_create_page(lower_mapping, page->index, mask);
if (!lower_page) {
err = 0;
set_page_dirty(page);
goto out;
}
lower_page_data = (char *)kmap(lower_page);
/* copy page data from our upper page to the lower page */
copy_highpage(lower_page, page);
flush_dcache_page(lower_page);
SetPageUptodate(lower_page);
set_page_dirty(lower_page);
/*#ifdef WRAPFS_CRYPTO
enc_buf = kmalloc(PAGE_CACHE_SIZE, GFP_KERNEL);
if (enc_buf == NULL) {
wrapfs_debug("No memory!!");
err = -ENOMEM;
goto out_release;
}
err = my_encrypt(lower_page_data, PAGE_CACHE_SIZE, enc_buf,
PAGE_CACHE_SIZE,
WRAPFS_SB(inode->i_sb)->key,
WRAPFS_CRYPTO_KEY_LEN);
if (err < 0) {
wrapfs_debug("encrypt error!!");
kfree(enc_buf);
err = -EINVAL;
goto out_release;
}
memcpy(lower_page_data, enc_buf, PAGE_CACHE_SIZE);
kfree(enc_buf);
#endif*/
/*
* Call lower writepage (expects locked page). However, if we are
* called with wbc->for_reclaim, then the VFS/VM just wants to
* reclaim our page. Therefore, we don't need to call the lower
* ->writepage: just copy our data to the lower page (already done
* above), then mark the lower page dirty and unlock it, and return
* success.
*/
/*if (wbc->for_reclaim) {
unlock_page(lower_page);
goto out_release;
}*/
BUG_ON(!lower_mapping->a_ops->writepage);
wait_on_page_writeback(lower_page); /* prevent multiple writers */
clear_page_dirty_for_io(lower_page); /* emulate VFS behavior */
err = lower_mapping->a_ops->writepage(lower_page, wbc);
if (err < 0)
goto out_release;
/*
* Lower file systems such as ramfs and tmpfs, may return
* AOP_WRITEPAGE_ACTIVATE so that the VM won't try to (pointlessly)
* write the page again for a while. But those lower file systems
* also set the page dirty bit back again. Since we successfully
* copied our page data to the lower page, then the VM will come
* back to the lower page (directly) and try to flush it. So we can
* save the VM the hassle of coming back to our page and trying to
* flush too. Therefore, we don't re-dirty our own page, and we
* never return AOP_WRITEPAGE_ACTIVATE back to the VM (we consider
* this a success).
*
* We also unlock the lower page if the lower ->writepage returned
* AOP_WRITEPAGE_ACTIVATE. (This "anomalous" behaviour may be
* addressed in future shmem/VM code.)
*/
if (err == AOP_WRITEPAGE_ACTIVATE) {
err = 0;
unlock_page(lower_page);
}
out_release:
kunmap(lower_page);
/* b/c find_or_create_page increased refcnt */
page_cache_release(lower_page);
out:
/*
* We unlock our page unconditionally, because we never return
* AOP_WRITEPAGE_ACTIVATE.
*/
unlock_page(page);
wrapfs_debug_aops(WRAPFS_SB(inode->i_sb)->wrapfs_debug_a_ops,
"err : %d", err);
return err;
}
/*
* Initialize the Linux inode, set up the operation vectors and
* unlock the inode.
*
* When reading existing inodes from disk this is called directly
* from xfs_iget, when creating a new inode it is called from
* xfs_ialloc after setting up the inode.
*
* We are always called with an uninitialised linux inode here.
* We need to initialise the necessary fields and take a reference
* on it.
*/
void
xfs_setup_inode(
struct xfs_inode *ip)
{
struct inode *inode = &ip->i_vnode;
gfp_t gfp_mask;
inode->i_ino = ip->i_ino;
inode->i_state = I_NEW;
inode_sb_list_add(inode);
/* make the inode look hashed for the writeback code */
hlist_add_fake(&inode->i_hash);
inode->i_mode = ip->i_d.di_mode;
set_nlink(inode, ip->i_d.di_nlink);
inode->i_uid = xfs_uid_to_kuid(ip->i_d.di_uid);
inode->i_gid = xfs_gid_to_kgid(ip->i_d.di_gid);
switch (inode->i_mode & S_IFMT) {
case S_IFBLK:
case S_IFCHR:
inode->i_rdev =
MKDEV(sysv_major(ip->i_df.if_u2.if_rdev) & 0x1ff,
sysv_minor(ip->i_df.if_u2.if_rdev));
break;
default:
inode->i_rdev = 0;
break;
}
inode->i_generation = ip->i_d.di_gen;
i_size_write(inode, ip->i_d.di_size);
inode->i_atime.tv_sec = ip->i_d.di_atime.t_sec;
inode->i_atime.tv_nsec = ip->i_d.di_atime.t_nsec;
inode->i_mtime.tv_sec = ip->i_d.di_mtime.t_sec;
inode->i_mtime.tv_nsec = ip->i_d.di_mtime.t_nsec;
inode->i_ctime.tv_sec = ip->i_d.di_ctime.t_sec;
inode->i_ctime.tv_nsec = ip->i_d.di_ctime.t_nsec;
xfs_diflags_to_iflags(inode, ip);
ip->d_ops = ip->i_mount->m_nondir_inode_ops;
lockdep_set_class(&ip->i_lock.mr_lock, &xfs_nondir_ilock_class);
switch (inode->i_mode & S_IFMT) {
case S_IFREG:
inode->i_op = &xfs_inode_operations;
inode->i_fop = &xfs_file_operations;
inode->i_mapping->a_ops = &xfs_address_space_operations;
break;
case S_IFDIR:
lockdep_set_class(&ip->i_lock.mr_lock, &xfs_dir_ilock_class);
if (xfs_sb_version_hasasciici(&XFS_M(inode->i_sb)->m_sb))
inode->i_op = &xfs_dir_ci_inode_operations;
else
inode->i_op = &xfs_dir_inode_operations;
inode->i_fop = &xfs_dir_file_operations;
ip->d_ops = ip->i_mount->m_dir_inode_ops;
break;
case S_IFLNK:
inode->i_op = &xfs_symlink_inode_operations;
if (!(ip->i_df.if_flags & XFS_IFINLINE))
inode->i_mapping->a_ops = &xfs_address_space_operations;
break;
default:
inode->i_op = &xfs_inode_operations;
init_special_inode(inode, inode->i_mode, inode->i_rdev);
break;
}
/*
* Ensure all page cache allocations are done from GFP_NOFS context to
* prevent direct reclaim recursion back into the filesystem and blowing
* stacks or deadlocking.
*/
gfp_mask = mapping_gfp_mask(inode->i_mapping);
mapping_set_gfp_mask(inode->i_mapping, (gfp_mask & ~(__GFP_FS)));
/*
* If there is no attribute fork no ACL can exist on this inode,
* and it can't have any file capabilities attached to it either.
*/
if (!XFS_IFORK_Q(ip)) {
inode_has_no_xattr(inode);
cache_no_acl(inode);
}
xfs_iflags_clear(ip, XFS_INEW);
barrier();
unlock_new_inode(inode);
}
struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
{
struct super_block *sb = dir->i_sb;
struct the_nilfs *nilfs = sb->s_fs_info;
struct inode *inode;
struct nilfs_inode_info *ii;
struct nilfs_root *root;
int err = -ENOMEM;
ino_t ino;
inode = new_inode(sb);
if (unlikely(!inode))
goto failed;
mapping_set_gfp_mask(inode->i_mapping,
mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS);
root = NILFS_I(dir)->i_root;
ii = NILFS_I(inode);
ii->i_state = 1 << NILFS_I_NEW;
ii->i_root = root;
err = nilfs_ifile_create_inode(root->ifile, &ino, &ii->i_bh);
if (unlikely(err))
goto failed_ifile_create_inode;
atomic_inc(&root->inodes_count);
inode_init_owner(inode, dir, mode);
inode->i_ino = ino;
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) {
err = nilfs_bmap_read(ii->i_bmap, NULL);
if (err < 0)
goto failed_bmap;
set_bit(NILFS_I_BMAP, &ii->i_state);
}
ii->i_flags = nilfs_mask_flags(
mode, NILFS_I(dir)->i_flags & NILFS_FL_INHERITED);
ii->i_dir_start_lookup = 0;
nilfs_set_inode_flags(inode);
spin_lock(&nilfs->ns_next_gen_lock);
inode->i_generation = nilfs->ns_next_generation++;
spin_unlock(&nilfs->ns_next_gen_lock);
insert_inode_hash(inode);
err = nilfs_init_acl(inode, dir);
if (unlikely(err))
goto failed_acl;
return inode;
failed_acl:
failed_bmap:
clear_nlink(inode);
iput(inode);
goto failed;
failed_ifile_create_inode:
make_bad_inode(inode);
iput(inode);
failed:
return ERR_PTR(err);
}
/*
* Initialize the Linux inode, set up the operation vectors and
* unlock the inode.
*
* When reading existing inodes from disk this is called directly
* from xfs_iget, when creating a new inode it is called from
* xfs_ialloc after setting up the inode.
*
* We are always called with an uninitialised linux inode here.
* We need to initialise the necessary fields and take a reference
* on it.
*/
void
xfs_setup_inode(
struct xfs_inode *ip)
{
struct inode *inode = &ip->i_vnode;
gfp_t gfp_mask;
inode->i_ino = ip->i_ino;
inode->i_state = I_NEW|I_LOCK;
inode_add_to_lists(ip->i_mount->m_super, inode);
inode->i_mode = ip->i_d.di_mode;
inode->i_nlink = ip->i_d.di_nlink;
inode->i_uid = ip->i_d.di_uid;
inode->i_gid = ip->i_d.di_gid;
switch (inode->i_mode & S_IFMT) {
case S_IFBLK:
case S_IFCHR:
inode->i_rdev =
MKDEV(sysv_major(ip->i_df.if_u2.if_rdev) & 0x1ff,
sysv_minor(ip->i_df.if_u2.if_rdev));
break;
default:
inode->i_rdev = 0;
break;
}
inode->i_generation = ip->i_d.di_gen;
i_size_write(inode, ip->i_d.di_size);
inode->i_atime.tv_sec = ip->i_d.di_atime.t_sec;
inode->i_atime.tv_nsec = ip->i_d.di_atime.t_nsec;
inode->i_mtime.tv_sec = ip->i_d.di_mtime.t_sec;
inode->i_mtime.tv_nsec = ip->i_d.di_mtime.t_nsec;
inode->i_ctime.tv_sec = ip->i_d.di_ctime.t_sec;
inode->i_ctime.tv_nsec = ip->i_d.di_ctime.t_nsec;
xfs_diflags_to_iflags(inode, ip);
switch (inode->i_mode & S_IFMT) {
case S_IFREG:
inode->i_op = &xfs_inode_operations;
inode->i_fop = &xfs_file_operations;
inode->i_mapping->a_ops = &xfs_address_space_operations;
break;
case S_IFDIR:
if (xfs_sb_version_hasasciici(&XFS_M(inode->i_sb)->m_sb))
inode->i_op = &xfs_dir_ci_inode_operations;
else
inode->i_op = &xfs_dir_inode_operations;
inode->i_fop = &xfs_dir_file_operations;
break;
case S_IFLNK:
inode->i_op = &xfs_symlink_inode_operations;
if (!(ip->i_df.if_flags & XFS_IFINLINE))
inode->i_mapping->a_ops = &xfs_address_space_operations;
break;
default:
inode->i_op = &xfs_inode_operations;
init_special_inode(inode, inode->i_mode, inode->i_rdev);
break;
}
/*
* Ensure all page cache allocations are done from GFP_NOFS context to
* prevent direct reclaim recursion back into the filesystem and blowing
* stacks or deadlocking.
*/
gfp_mask = mapping_gfp_mask(inode->i_mapping);
mapping_set_gfp_mask(inode->i_mapping, (gfp_mask & ~(__GFP_FS)));
xfs_iflags_clear(ip, XFS_INEW);
barrier();
unlock_new_inode(inode);
}
struct inode *nilfs_new_inode(struct inode *dir, int mode)
{
struct super_block *sb = dir->i_sb;
struct nilfs_sb_info *sbi = NILFS_SB(sb);
struct inode *inode;
struct nilfs_inode_info *ii;
int err = -ENOMEM;
ino_t ino;
inode = new_inode(sb);
if (unlikely(!inode))
goto failed;
mapping_set_gfp_mask(inode->i_mapping,
mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS);
ii = NILFS_I(inode);
ii->i_state = 1 << NILFS_I_NEW;
err = nilfs_ifile_create_inode(sbi->s_ifile, &ino, &ii->i_bh);
if (unlikely(err))
goto failed_ifile_create_inode;
/* reference count of i_bh inherits from nilfs_mdt_read_block() */
atomic_inc(&sbi->s_inodes_count);
inode->i_uid = current_fsuid();
if (dir->i_mode & S_ISGID) {
inode->i_gid = dir->i_gid;
if (S_ISDIR(mode))
mode |= S_ISGID;
} else
inode->i_gid = current_fsgid();
inode->i_mode = mode;
inode->i_ino = ino;
inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) {
err = nilfs_bmap_read(ii->i_bmap, NULL);
if (err < 0)
goto failed_bmap;
set_bit(NILFS_I_BMAP, &ii->i_state);
/* No lock is needed; iget() ensures it. */
}
ii->i_flags = NILFS_I(dir)->i_flags;
if (S_ISLNK(mode))
ii->i_flags &= ~(NILFS_IMMUTABLE_FL | NILFS_APPEND_FL);
if (!S_ISDIR(mode))
ii->i_flags &= ~NILFS_DIRSYNC_FL;
/* ii->i_file_acl = 0; */
/* ii->i_dir_acl = 0; */
ii->i_dir_start_lookup = 0;
ii->i_cno = 0;
nilfs_set_inode_flags(inode);
spin_lock(&sbi->s_next_gen_lock);
inode->i_generation = sbi->s_next_generation++;
spin_unlock(&sbi->s_next_gen_lock);
insert_inode_hash(inode);
err = nilfs_init_acl(inode, dir);
if (unlikely(err))
goto failed_acl; /* never occur. When supporting
nilfs_init_acl(), proper cancellation of
above jobs should be considered */
mark_inode_dirty(inode);
return inode;
failed_acl:
failed_bmap:
inode->i_nlink = 0;
iput(inode); /* raw_inode will be deleted through
generic_delete_inode() */
goto failed;
failed_ifile_create_inode:
make_bad_inode(inode);
iput(inode); /* if i_nlink == 1, generic_forget_inode() will be
called */
failed:
return ERR_PTR(err);
}
static int wrapfs_writepage(struct page *page, struct writeback_control *wbc)
{
int err = -EIO;
struct inode *inode;
struct inode *lower_inode;
struct page *lower_page;
struct address_space *lower_mapping; /* lower inode mapping */
gfp_t mask;
/*printk(KERN_ALERT "in writepage() \n");*/
BUG_ON(!PageUptodate(page));
inode = page->mapping->host;
/* if no lower inode, nothing to do */
if (!inode || !WRAPFS_I(inode) || WRAPFS_I(inode)->lower_inode) {
err = 0;
goto out;
}
lower_inode = wrapfs_lower_inode(inode);
lower_mapping = lower_inode->i_mapping;
/*
* find lower page (returns a locked page)
*
* We turn off __GFP_FS while we look for or create a new lower
* page. This prevents a recursion into the file system code, which
* under memory pressure conditions could lead to a deadlock. This
* is similar to how the loop driver behaves (see loop_set_fd in
* drivers/block/loop.c). If we can't find the lower page, we
* redirty our page and return "success" so that the VM will call us
* again in the (hopefully near) future.
*/
mask = mapping_gfp_mask(lower_mapping) & ~(__GFP_FS);
lower_page = find_or_create_page(lower_mapping, page->index, mask);
if (!lower_page) {
err = 0;
set_page_dirty(page);
goto out;
}
/* copy page data from our upper page to the lower page */
copy_highpage(lower_page, page);
flush_dcache_page(lower_page);
SetPageUptodate(lower_page);
set_page_dirty(lower_page);
/*
* Call lower writepage (expects locked page). However, if we are
* called with wbc->for_reclaim, then the VFS/VM just wants to
* reclaim our page. Therefore, we don't need to call the lower
* ->writepage: just copy our data to the lower page (already done
* above), then mark the lower page dirty and unlock it, and return
* success.
*/
if (wbc->for_reclaim) {
unlock_page(lower_page);
goto out_release;
}
BUG_ON(!lower_mapping->a_ops->writepage);
wait_on_page_writeback(lower_page); /* prevent multiple writers */
clear_page_dirty_for_io(lower_page); /* emulate VFS behavior */
err = lower_mapping->a_ops->writepage(lower_page, wbc);
if (err < 0)
goto out_release;
/*
* Lower file systems such as ramfs and tmpfs, may return
* AOP_WRITEPAGE_ACTIVATE so that the VM won't try to (pointlessly)
* write the page again for a while. But those lower file systems
* also set the page dirty bit back again. Since we successfully
* copied our page data to the lower page, then the VM will come
* back to the lower page (directly) and try to flush it. So we can
* save the VM the hassle of coming back to our page and trying to
* flush too. Therefore, we don't re-dirty our own page, and we
* never return AOP_WRITEPAGE_ACTIVATE back to the VM (we consider
* this a success).
*
* We also unlock the lower page if the lower ->writepage returned
* AOP_WRITEPAGE_ACTIVATE. (This "anomalous" behaviour may be
* addressed in future shmem/VM code.)
*/
if (err == AOP_WRITEPAGE_ACTIVATE) {
err = 0;
unlock_page(lower_page);
}
/* all is well */
/* lower mtimes have changed: update ours */
/* fsstack_copy_inode_size(dentry->d_inode,
lower_file->f_path.dentry->d_inode);
fsstack_copy_attr_times(dentry->d_inode,
lower_file->f_path.dentry->d_inode);
*/
out_release:
/* b/c find_or_create_page increased refcnt */
page_cache_release(lower_page);
out:
/*
* We unlock our page unconditionally, because we never return
* AOP_WRITEPAGE_ACTIVATE.
*/
unlock_page(page);
return err;
}
