ocfs2: implement ocfs2_direct_IO_write

Implement ocfs2_direct_IO_write.  Add the inode to orphan dir first, and
then delete it once append O_DIRECT finished.

This is to make sure block allocation and inode size are consistent.

[akpm@linux-foundation.org: fix it for "block: Add discard flag to blkdev_issue_zeroout() function"]
Signed-off-by: Joseph Qi <joseph.qi@huawei.com>
Cc: Weiwei Wang <wangww631@huawei.com>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Mark Fasheh <mfasheh@suse.com>
Cc: Xuejiufei <xuejiufei@huawei.com>
Cc: alex chen <alex.chen@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Joseph Qi 2015-02-16 16:00:00 -08:00 committed by Linus Torvalds
parent ed460cffc2
commit 24c40b329e
2 changed files with 204 additions and 3 deletions

View File

@ -28,6 +28,7 @@
#include <linux/pipe_fs_i.h>
#include <linux/mpage.h>
#include <linux/quotaops.h>
#include <linux/blkdev.h>
#include <cluster/masklog.h>
@ -47,6 +48,9 @@
#include "ocfs2_trace.h"
#include "buffer_head_io.h"
#include "dir.h"
#include "namei.h"
#include "sysfile.h"
static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
@ -597,6 +601,184 @@ static int ocfs2_releasepage(struct page *page, gfp_t wait)
return try_to_free_buffers(page);
}
static int ocfs2_is_overwrite(struct ocfs2_super *osb,
struct inode *inode, loff_t offset)
{
int ret = 0;
u32 v_cpos = 0;
u32 p_cpos = 0;
unsigned int num_clusters = 0;
unsigned int ext_flags = 0;
v_cpos = ocfs2_bytes_to_clusters(osb->sb, offset);
ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos,
&num_clusters, &ext_flags);
if (ret < 0) {
mlog_errno(ret);
return ret;
}
if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN))
return 1;
return 0;
}
static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
struct iov_iter *iter,
loff_t offset)
{
ssize_t ret = 0;
ssize_t written = 0;
bool orphaned = false;
int is_overwrite = 0;
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file)->i_mapping->host;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
struct buffer_head *di_bh = NULL;
size_t count = iter->count;
journal_t *journal = osb->journal->j_journal;
u32 zero_len;
int cluster_align;
loff_t final_size = offset + count;
int append_write = offset >= i_size_read(inode) ? 1 : 0;
unsigned int num_clusters = 0;
unsigned int ext_flags = 0;
{
u64 o = offset;
zero_len = do_div(o, 1 << osb->s_clustersize_bits);
cluster_align = !zero_len;
}
/*
* when final_size > inode->i_size, inode->i_size will be
* updated after direct write, so add the inode to orphan
* dir first.
*/
if (final_size > i_size_read(inode)) {
ret = ocfs2_add_inode_to_orphan(osb, inode);
if (ret < 0) {
mlog_errno(ret);
goto out;
}
orphaned = true;
}
if (append_write) {
ret = ocfs2_inode_lock(inode, &di_bh, 1);
if (ret < 0) {
mlog_errno(ret);
goto clean_orphan;
}
if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
ret = ocfs2_zero_extend(inode, di_bh, offset);
else
ret = ocfs2_extend_no_holes(inode, di_bh, offset,
offset);
if (ret < 0) {
mlog_errno(ret);
ocfs2_inode_unlock(inode, 1);
brelse(di_bh);
goto clean_orphan;
}
is_overwrite = ocfs2_is_overwrite(osb, inode, offset);
if (is_overwrite < 0) {
mlog_errno(is_overwrite);
ocfs2_inode_unlock(inode, 1);
brelse(di_bh);
goto clean_orphan;
}
ocfs2_inode_unlock(inode, 1);
brelse(di_bh);
di_bh = NULL;
}
written = __blockdev_direct_IO(WRITE, iocb, inode, inode->i_sb->s_bdev,
iter, offset,
ocfs2_direct_IO_get_blocks,
ocfs2_dio_end_io, NULL, 0);
if (unlikely(written < 0)) {
loff_t i_size = i_size_read(inode);
if (offset + count > i_size) {
ret = ocfs2_inode_lock(inode, &di_bh, 1);
if (ret < 0) {
mlog_errno(ret);
goto clean_orphan;
}
if (i_size == i_size_read(inode)) {
ret = ocfs2_truncate_file(inode, di_bh,
i_size);
if (ret < 0) {
if (ret != -ENOSPC)
mlog_errno(ret);
ocfs2_inode_unlock(inode, 1);
brelse(di_bh);
goto clean_orphan;
}
}
ocfs2_inode_unlock(inode, 1);
brelse(di_bh);
ret = jbd2_journal_force_commit(journal);
if (ret < 0)
mlog_errno(ret);
}
} else if (written < 0 && append_write && !is_overwrite &&
!cluster_align) {
u32 p_cpos = 0;
u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, offset);
ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos,
&num_clusters, &ext_flags);
if (ret < 0) {
mlog_errno(ret);
goto clean_orphan;
}
BUG_ON(!p_cpos || (ext_flags & OCFS2_EXT_UNWRITTEN));
ret = blkdev_issue_zeroout(osb->sb->s_bdev,
p_cpos << (osb->s_clustersize_bits - 9),
zero_len >> 9, GFP_KERNEL, false);
if (ret < 0)
mlog_errno(ret);
}
clean_orphan:
if (orphaned) {
int tmp_ret;
int update_isize = written > 0 ? 1 : 0;
loff_t end = update_isize ? offset + written : 0;
tmp_ret = ocfs2_del_inode_from_orphan(osb, inode,
update_isize, end);
if (tmp_ret < 0) {
ret = tmp_ret;
goto out;
}
tmp_ret = jbd2_journal_force_commit(journal);
if (tmp_ret < 0) {
ret = tmp_ret;
mlog_errno(tmp_ret);
}
}
out:
if (ret >= 0)
ret = written;
return ret;
}
static ssize_t ocfs2_direct_IO(int rw,
struct kiocb *iocb,
struct iov_iter *iter,
@ -604,6 +786,9 @@ static ssize_t ocfs2_direct_IO(int rw,
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file)->i_mapping->host;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
int full_coherency = !(osb->s_mount_opt &
OCFS2_MOUNT_COHERENCY_BUFFERED);
/*
* Fallback to buffered I/O if we see an inode without
@ -612,14 +797,20 @@ static ssize_t ocfs2_direct_IO(int rw,
if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
return 0;
/* Fallback to buffered I/O if we are appending. */
if (i_size_read(inode) <= offset)
/* Fallback to buffered I/O if we are appending and
* concurrent O_DIRECT writes are allowed.
*/
if (i_size_read(inode) <= offset && !full_coherency)
return 0;
return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev,
if (rw == READ)
return __blockdev_direct_IO(rw, iocb, inode,
inode->i_sb->s_bdev,
iter, offset,
ocfs2_direct_IO_get_blocks,
ocfs2_dio_end_io, NULL, 0);
else
return ocfs2_direct_IO_write(iocb, iter, offset);
}
static void ocfs2_figure_cluster_boundaries(struct ocfs2_super *osb,

View File

@ -731,6 +731,16 @@ static inline unsigned int ocfs2_clusters_for_bytes(struct super_block *sb,
return clusters;
}
static inline unsigned int ocfs2_bytes_to_clusters(struct super_block *sb,
u64 bytes)
{
int cl_bits = OCFS2_SB(sb)->s_clustersize_bits;
unsigned int clusters;
clusters = (unsigned int)(bytes >> cl_bits);
return clusters;
}
static inline u64 ocfs2_blocks_for_bytes(struct super_block *sb,
u64 bytes)
{