* ->tree_lock (page_remove_rmap->set_page_dirty)
* bdi.wb->list_lock (page_remove_rmap->set_page_dirty)
* ->inode->i_lock (page_remove_rmap->set_page_dirty)
+ * ->memcg->move_lock (page_remove_rmap->mem_cgroup_begin_page_stat)
* bdi.wb->list_lock (zap_pte_range->set_page_dirty)
* ->inode->i_lock (zap_pte_range->set_page_dirty)
* ->private_lock (zap_pte_range->__set_page_dirty_buffers)
/*
* Delete a page from the page cache and free it. Caller has to make
* sure the page is locked and that nobody else uses it - or that usage
- * is safe. The caller must hold the mapping's tree_lock.
+ * is safe. The caller must hold the mapping's tree_lock and
+ * mem_cgroup_begin_page_stat().
*/
-void __delete_from_page_cache(struct page *page, void *shadow)
+void __delete_from_page_cache(struct page *page, void *shadow,
+ struct mem_cgroup *memcg)
{
struct address_space *mapping = page->mapping;
* anyway will be cleared before returning page into buddy allocator.
*/
if (WARN_ON_ONCE(PageDirty(page)))
- account_page_cleaned(page, mapping);
+ account_page_cleaned(page, mapping, memcg,
+ inode_to_wb(mapping->host));
}
/**
void delete_from_page_cache(struct page *page)
{
struct address_space *mapping = page->mapping;
+ struct mem_cgroup *memcg;
+ unsigned long flags;
+
void (*freepage)(struct page *);
BUG_ON(!PageLocked(page));
freepage = mapping->a_ops->freepage;
- spin_lock_irq(&mapping->tree_lock);
- __delete_from_page_cache(page, NULL);
- spin_unlock_irq(&mapping->tree_lock);
+
+ memcg = mem_cgroup_begin_page_stat(page);
+ spin_lock_irqsave(&mapping->tree_lock, flags);
+ __delete_from_page_cache(page, NULL, memcg);
+ spin_unlock_irqrestore(&mapping->tree_lock, flags);
+ mem_cgroup_end_page_stat(memcg);
if (freepage)
freepage(page);
if (!mapping_cap_writeback_dirty(mapping))
return 0;
+ wbc_attach_fdatawrite_inode(&wbc, mapping->host);
ret = do_writepages(mapping, &wbc);
+ wbc_detach_inode(&wbc);
return ret;
}
if (!error) {
struct address_space *mapping = old->mapping;
void (*freepage)(struct page *);
+ struct mem_cgroup *memcg;
+ unsigned long flags;
pgoff_t offset = old->index;
freepage = mapping->a_ops->freepage;
new->mapping = mapping;
new->index = offset;
- spin_lock_irq(&mapping->tree_lock);
- __delete_from_page_cache(old, NULL);
+ memcg = mem_cgroup_begin_page_stat(old);
+ spin_lock_irqsave(&mapping->tree_lock, flags);
+ __delete_from_page_cache(old, NULL, memcg);
error = radix_tree_insert(&mapping->page_tree, offset, new);
BUG_ON(error);
mapping->nrpages++;
__inc_zone_page_state(new, NR_FILE_PAGES);
if (PageSwapBacked(new))
__inc_zone_page_state(new, NR_SHMEM);
- spin_unlock_irq(&mapping->tree_lock);
+ spin_unlock_irqrestore(&mapping->tree_lock, flags);
+ mem_cgroup_end_page_stat(memcg);
mem_cgroup_migrate(old, new, true);
radix_tree_preload_end();
if (freepage)
loff_t *ppos = &iocb->ki_pos;
loff_t pos = *ppos;
- if (io_is_direct(file)) {
+ if (iocb->ki_flags & IOCB_DIRECT) {
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
size_t count = iov_iter_count(iter);
pos + count - 1);
if (!retval) {
struct iov_iter data = *iter;
- retval = mapping->a_ops->direct_IO(READ, iocb, &data, pos);
+ retval = mapping->a_ops->direct_IO(iocb, &data, pos);
}
if (retval > 0) {
* Returns appropriate error code that caller should return or
* zero in case that write should be allowed.
*/
-inline int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk)
+inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
{
+ struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
unsigned long limit = rlimit(RLIMIT_FSIZE);
+ loff_t pos;
- if (unlikely(*pos < 0))
- return -EINVAL;
+ if (!iov_iter_count(from))
+ return 0;
- if (!isblk) {
- /* FIXME: this is for backwards compatibility with 2.4 */
- if (file->f_flags & O_APPEND)
- *pos = i_size_read(inode);
+ /* FIXME: this is for backwards compatibility with 2.4 */
+ if (iocb->ki_flags & IOCB_APPEND)
+ iocb->ki_pos = i_size_read(inode);
- if (limit != RLIM_INFINITY) {
- if (*pos >= limit) {
- send_sig(SIGXFSZ, current, 0);
- return -EFBIG;
- }
- if (*count > limit - (typeof(limit))*pos) {
- *count = limit - (typeof(limit))*pos;
- }
+ pos = iocb->ki_pos;
+
+ if (limit != RLIM_INFINITY) {
+ if (iocb->ki_pos >= limit) {
+ send_sig(SIGXFSZ, current, 0);
+ return -EFBIG;
}
+ iov_iter_truncate(from, limit - (unsigned long)pos);
}
/*
* LFS rule
*/
- if (unlikely(*pos + *count > MAX_NON_LFS &&
+ if (unlikely(pos + iov_iter_count(from) > MAX_NON_LFS &&
!(file->f_flags & O_LARGEFILE))) {
- if (*pos >= MAX_NON_LFS) {
+ if (pos >= MAX_NON_LFS)
return -EFBIG;
- }
- if (*count > MAX_NON_LFS - (unsigned long)*pos) {
- *count = MAX_NON_LFS - (unsigned long)*pos;
- }
+ iov_iter_truncate(from, MAX_NON_LFS - (unsigned long)pos);
}
/*
* exceeded without writing data we send a signal and return EFBIG.
* Linus frestrict idea will clean these up nicely..
*/
- if (likely(!isblk)) {
- if (unlikely(*pos >= inode->i_sb->s_maxbytes)) {
- if (*count || *pos > inode->i_sb->s_maxbytes) {
- return -EFBIG;
- }
- /* zero-length writes at ->s_maxbytes are OK */
- }
+ if (unlikely(pos >= inode->i_sb->s_maxbytes))
+ return -EFBIG;
- if (unlikely(*pos + *count > inode->i_sb->s_maxbytes))
- *count = inode->i_sb->s_maxbytes - *pos;
- } else {
-#ifdef CONFIG_BLOCK
- loff_t isize;
- if (bdev_read_only(I_BDEV(inode)))
- return -EPERM;
- isize = i_size_read(inode);
- if (*pos >= isize) {
- if (*count || *pos > isize)
- return -ENOSPC;
- }
-
- if (*pos + *count > isize)
- *count = isize - *pos;
-#else
- return -EPERM;
-#endif
- }
- return 0;
+ iov_iter_truncate(from, inode->i_sb->s_maxbytes - pos);
+ return iov_iter_count(from);
}
EXPORT_SYMBOL(generic_write_checks);
}
data = *from;
- written = mapping->a_ops->direct_IO(WRITE, iocb, &data, pos);
+ written = mapping->a_ops->direct_IO(iocb, &data, pos);
/*
* Finally, try again to invalidate clean pages which might have been
struct file *file = iocb->ki_filp;
struct address_space * mapping = file->f_mapping;
struct inode *inode = mapping->host;
- loff_t pos = iocb->ki_pos;
ssize_t written = 0;
ssize_t err;
ssize_t status;
- size_t count = iov_iter_count(from);
/* We can write back this queue in page reclaim */
current->backing_dev_info = inode_to_bdi(inode);
- err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
- if (err)
- goto out;
-
- if (count == 0)
- goto out;
-
- iov_iter_truncate(from, count);
-
err = file_remove_suid(file);
if (err)
goto out;
if (err)
goto out;
- if (io_is_direct(file)) {
- loff_t endbyte;
+ if (iocb->ki_flags & IOCB_DIRECT) {
+ loff_t pos, endbyte;
- written = generic_file_direct_write(iocb, from, pos);
+ written = generic_file_direct_write(iocb, from, iocb->ki_pos);
/*
* If the write stopped short of completing, fall back to
* buffered writes. Some filesystems do this for writes to
* not succeed (even if it did, DAX does not handle dirty
* page-cache pages correctly).
*/
- if (written < 0 || written == count || IS_DAX(inode))
+ if (written < 0 || !iov_iter_count(from) || IS_DAX(inode))
goto out;
- pos += written;
- count -= written;
-
- status = generic_perform_write(file, from, pos);
+ status = generic_perform_write(file, from, pos = iocb->ki_pos);
/*
* If generic_perform_write() returned a synchronous error
* then we want to return the number of bytes which were
err = status;
goto out;
}
- iocb->ki_pos = pos + status;
/*
* We need to ensure that the page cache pages are written to
* disk and invalidated to preserve the expected O_DIRECT
* semantics.
*/
endbyte = pos + status - 1;
- err = filemap_write_and_wait_range(file->f_mapping, pos, endbyte);
+ err = filemap_write_and_wait_range(mapping, pos, endbyte);
if (err == 0) {
+ iocb->ki_pos = endbyte + 1;
written += status;
invalidate_mapping_pages(mapping,
pos >> PAGE_CACHE_SHIFT,
*/
}
} else {
- written = generic_perform_write(file, from, pos);
- if (likely(written >= 0))
- iocb->ki_pos = pos + written;
+ written = generic_perform_write(file, from, iocb->ki_pos);
+ if (likely(written > 0))
+ iocb->ki_pos += written;
}
out:
current->backing_dev_info = NULL;
ssize_t ret;
mutex_lock(&inode->i_mutex);
- ret = __generic_file_write_iter(iocb, from);
+ ret = generic_write_checks(iocb, from);
+ if (ret > 0)
+ ret = __generic_file_write_iter(iocb, from);
mutex_unlock(&inode->i_mutex);
if (ret > 0) {
projects / cascardo / linux.git / blobdiff