[v22,22/31] ocfs2: Provide a splice-read wrapper

Commit Message

David Howells May 22, 2023, 1:50 p.m. UTC

Provide a splice_read wrapper for ocfs2.  This emits trace lines and does
an atime lock/update before calling filemap_splice_read().  Splicing from
direct I/O is handled by the caller.

A couple of new tracepoints are added for this purpose.

Signed-off-by: David Howells <[e-mail]>
Reviewed-by: Joseph Qi <[e-mail]>
cc: Christoph Hellwig <[e-mail]>
cc: Al Viro <[e-mail]>
cc: Jens Axboe <[e-mail]>
cc: Mark Fasheh <[e-mail]>
cc: Joel Becker <[e-mail]>
cc: [e-mail]
cc: [e-mail]
cc: [e-mail]
cc: [e-mail]
---

Notes:
    ver #22:
     - Adjust a couple of comments mentioning generic_file_splice_read().
     - Pass 1 to ocfs2_inode_lock_atomic() rather than true.
     - Pass the splice flags into the tracepoint.

 fs/ocfs2/file.c        | 41 +++++++++++++++++++++++++++++++++++++++--
 fs/ocfs2/ocfs2_trace.h |  3 +++
 2 files changed, 42 insertions(+), 2 deletions(-)

Patch

diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index efb09de4343d..86add13b5f23 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2552,7 +2552,7 @@  static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
 	 *
 	 * Take and drop the meta data lock to update inode fields
 	 * like i_size. This allows the checks down below
-	 * generic_file_read_iter() a chance of actually working.
+	 * copy_splice_read() a chance of actually working.
 	 */
 	ret = ocfs2_inode_lock_atime(inode, filp->f_path.mnt, &lock_level,
 				     !nowait);
@@ -2581,6 +2581,43 @@  static ssize_t ocfs2_file_read_iter(struct kiocb *iocb,
 	return ret;
 }
 
+static ssize_t ocfs2_file_splice_read(struct file *in, loff_t *ppos,
+				      struct pipe_inode_info *pipe,
+				      size_t len, unsigned int flags)
+{
+	struct inode *inode = file_inode(in);
+	ssize_t ret = 0;
+	int lock_level = 0;
+
+	trace_ocfs2_file_splice_read(inode, in, in->f_path.dentry,
+				     (unsigned long long)OCFS2_I(inode)->ip_blkno,
+				     in->f_path.dentry->d_name.len,
+				     in->f_path.dentry->d_name.name,
+				     flags);
+
+	/*
+	 * We're fine letting folks race truncates and extending writes with
+	 * read across the cluster, just like they can locally.  Hence no
+	 * rw_lock during read.
+	 *
+	 * Take and drop the meta data lock to update inode fields like i_size.
+	 * This allows the checks down below filemap_splice_read() a chance of
+	 * actually working.
+	 */
+	ret = ocfs2_inode_lock_atime(inode, in->f_path.mnt, &lock_level, 1);
+	if (ret < 0) {
+		if (ret != -EAGAIN)
+			mlog_errno(ret);
+		goto bail;
+	}
+	ocfs2_inode_unlock(inode, lock_level);
+
+	ret = filemap_splice_read(in, ppos, pipe, len, flags);
+	trace_filemap_splice_read_ret(ret);
+bail:
+	return ret;
+}
+
 /* Refer generic_file_llseek_unlocked() */
 static loff_t ocfs2_file_llseek(struct file *file, loff_t offset, int whence)
 {
@@ -2744,7 +2781,7 @@  const struct file_operations ocfs2_fops = {
 #endif
 	.lock		= ocfs2_lock,
 	.flock		= ocfs2_flock,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= ocfs2_file_splice_read,
 	.splice_write	= iter_file_splice_write,
 	.fallocate	= ocfs2_fallocate,
 	.remap_file_range = ocfs2_remap_file_range,
diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h
index dc4bce1649c1..b8c3d1702076 100644
--- a/fs/ocfs2/ocfs2_trace.h
+++ b/fs/ocfs2/ocfs2_trace.h
@@ -1319,6 +1319,8 @@  DEFINE_OCFS2_FILE_OPS(ocfs2_file_splice_write);
 
 DEFINE_OCFS2_FILE_OPS(ocfs2_file_read_iter);
 
+DEFINE_OCFS2_FILE_OPS(ocfs2_file_splice_read);
+
 DEFINE_OCFS2_ULL_ULL_ULL_EVENT(ocfs2_truncate_file);
 
 DEFINE_OCFS2_ULL_ULL_EVENT(ocfs2_truncate_file_error);
@@ -1470,6 +1472,7 @@  TRACE_EVENT(ocfs2_prepare_inode_for_write,
 );
 
 DEFINE_OCFS2_INT_EVENT(generic_file_read_iter_ret);
+DEFINE_OCFS2_INT_EVENT(filemap_splice_read_ret);
 
 /* End of trace events for fs/ocfs2/file.c. */