diff options
author | Zach Brown <zach.brown@oracle.com> | 2010-06-04 14:41:41 -0700 |
---|---|---|
committer | Andy Grover <andy.grover@oracle.com> | 2010-09-08 18:15:27 -0700 |
commit | 0f4b1c7e89e699f588807a914ec6e6396c851a72 (patch) | |
tree | 8b882f85f03089283f6d222bf8c7d5616a102ecd /net/rds/ib_send.c | |
parent | 501dcccdb7a2335cde07d4acb56e636182d62944 (diff) |
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>
Diffstat (limited to 'net/rds/ib_send.c')
-rw-r--r-- | net/rds/ib_send.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index 3f91e794eae9..e88cb4af009b 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -321,7 +321,7 @@ void rds_ib_send_cq_comp_handler(struct ib_cq *cq, void *context) * credits (see rds_ib_send_add_credits below). * * The RDS send code is essentially single-threaded; rds_send_xmit - * grabs c_send_lock to ensure exclusive access to the send ring. + * sets RDS_IN_XMIT to ensure exclusive access to the send ring. * However, the ACK sending code is independent and can race with * message SENDs. * |