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>

2 files changed, 204 insertions, 3 deletions

diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 46d93e941f3d..be5986b7e5c6 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -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,
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index df9a95cbea3a..7e39cd654834 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -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)
 {