rds: fix rds_send_xmit() serialization

rds_send_xmit() was changed to hold an interrupt masking spinlock instead of a
mutex so that it could be called from the IB receive tasklet path.  This broke
the TCP transport because its xmit method can block and masks and unmasks
interrupts.

This patch serializes callers to rds_send_xmit() with a simple bit instead of
the current spinlock or previous mutex.  This enables rds_send_xmit() to be
called from any context and to call functions which block.  Getting rid of the
c_send_lock exposes the bare c_lock acquisitions which are changed to block
interrupts.

A waitqueue is added so that rds_conn_shutdown() can wait for callers to leave
rds_send_xmit() before tearing down partial send state.  This lets us get rid
of c_senders.

rds_send_xmit() is changed to check the conn state after acquiring the
RDS_IN_XMIT bit to resolve races with the shutdown path.  Previously both
worked with the conn state and then the lock in the same order, allowing them
to race and execute the paths concurrently.

rds_send_reset() isn't racing with rds_send_xmit() now that rds_conn_shutdown()
properly ensures that rds_send_xmit() can't start once the conn state has been
changed.  We can remove its previous use of the spinlock.

Finally, c_send_generation is redundant.  Callers can race to test the c_flags
bit by simply retrying instead of racing to test the c_send_generation atomic.

Signed-off-by: Zach Brown <zach.brown@oracle.com>

1 files changed, 2 insertions, 3 deletions

diff --git a/net/rds/rds.h b/net/rds/rds.h
index 270ded7..4510344 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -80,6 +80,7 @@ enum {
 /* Bits for c_flags */
 #define RDS_LL_SEND_FULL	0
 #define RDS_RECONNECT_PENDING	1
+#define RDS_IN_XMIT		2
 
 struct rds_connection {
 	struct hlist_node	c_hash_node;
@@ -91,9 +92,6 @@ struct rds_connection {
 	struct rds_cong_map	*c_lcong;
 	struct rds_cong_map	*c_fcong;
 
-	spinlock_t		c_send_lock;	/* protect send ring */
-	atomic_t		c_send_generation;
-	atomic_t		c_senders;
 	struct rds_message	*c_xmit_rm;
 	unsigned long		c_xmit_sg;
 	unsigned int		c_xmit_hdr_off;
@@ -120,6 +118,7 @@ struct rds_connection {
 	struct delayed_work	c_conn_w;
 	struct work_struct	c_down_w;
 	struct mutex		c_cm_lock;	/* protect conn state & cm */
+	wait_queue_head_t	c_waitq;
 
 	struct list_head	c_map_item;
 	unsigned long		c_map_queued;