xfs: use bios directly to write log buffers

Currently the XFS logging code uses the xfs_buf structure and
associated APIs to write the log buffers to disk.  This requires
various special cases in the log code and is generally not very
optimal.

Instead of using a buffer just allocate a kmem_alloc_larger region for
each log buffer, and use a bio and bio_vec array embedded in the iclog
structure to write the buffer to disk.  This also allows for using
the bio split and chaining case to deal with the case of a log
buffer wrapping around the end of the log.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
[darrick: don't split if/else with an #endif]
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>

1 files changed, 10 insertions, 8 deletions

diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index ac4bca257609..b9c90abb09a2 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -178,11 +178,12 @@ typedef struct xlog_ticket {
  *	the iclog.
  * - ic_forcewait is used to implement synchronous forcing of the iclog to disk.
  * - ic_next is the pointer to the next iclog in the ring.
- * - ic_bp is a pointer to the buffer used to write this incore log to disk.
  * - ic_log is a pointer back to the global log structure.
  * - ic_callback is a linked list of callback function/argument pairs to be
  *	called after an iclog finishes writing.
- * - ic_size is the full size of the header plus data.
+ * - ic_size is the full size of the log buffer, minus the cycle headers.
+ * - ic_io_size is the size of the currently pending log buffer write, which
+ *	might be smaller than ic_size
  * - ic_offset is the current number of bytes written to in this iclog.
  * - ic_refcnt is bumped when someone is writing to the log.
  * - ic_state is the state of the iclog.
@@ -205,11 +206,10 @@ typedef struct xlog_in_core {
 	wait_queue_head_t	ic_write_wait;
 	struct xlog_in_core	*ic_next;
 	struct xlog_in_core	*ic_prev;
-	struct xfs_buf		*ic_bp;
 	struct xlog		*ic_log;
-	int			ic_size;
-	int			ic_offset;
-	int			ic_bwritecnt;
+	u32			ic_size;
+	u32			ic_io_size;
+	u32			ic_offset;
 	unsigned short		ic_state;
 	char			*ic_datap;	/* pointer to iclog data */
 
@@ -225,6 +225,10 @@ typedef struct xlog_in_core {
 #ifdef DEBUG
 	bool			ic_fail_crc : 1;
 #endif
+	struct semaphore	ic_sema;
+	struct work_struct	ic_end_io_work;
+	struct bio		ic_bio;
+	struct bio_vec		ic_bvec[];
 } xlog_in_core_t;
 
 /*
@@ -352,8 +356,6 @@ struct xlog {
 	struct xfs_mount	*l_mp;	        /* mount point */
 	struct xfs_ail		*l_ailp;	/* AIL log is working with */
 	struct xfs_cil		*l_cilp;	/* CIL log is working with */
-	struct xfs_buf		*l_xbuf;        /* extra buffer for log
-						 * wrapping */
 	struct xfs_buftarg	*l_targ;        /* buftarg of log */
 	struct delayed_work	l_work;		/* background flush work */
 	uint			l_flags;