diff options
| author | Tom Tucker <tom@opengridcomputing.com> | 2008-08-13 11:05:41 -0500 |
|---|---|---|
| committer | J. Bruce Fields <bfields@citi.umich.edu> | 2008-08-13 16:57:31 -0400 |
| commit | 24b8b44780a2c53ecb738f4a1c08d114f5eda27c (patch) | |
| tree | f772e59438783c6230158ea65bd5aeb3f84f4202 /net/sunrpc/xprtrdma | |
| parent | 30a2f3c60a84092c8084dfe788b710f8d0768cd4 (diff) | |
svcrdma: Fix race between svc_rdma_recvfrom thread and the dto_tasklet
RDMA_READ completions are kept on a separate queue from the general
I/O request queue. Since a separate lock is used to protect the RDMA_READ
completion queue, a race exists between the dto_tasklet and the
svc_rdma_recvfrom thread where the dto_tasklet sets the XPT_DATA
bit and adds I/O to the read-completion queue. Concurrently, the
recvfrom thread checks the generic queue, finds it empty and resets
the XPT_DATA bit. A subsequent svc_xprt_enqueue will fail to enqueue
the transport for I/O and cause the transport to "stall".
The fix is to protect both lists with the same lock and set the XPT_DATA
bit with this lock held.
Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: J. Bruce Fields <bfields@citi.umich.edu>
Diffstat (limited to 'net/sunrpc/xprtrdma')
| -rw-r--r-- | net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 8 | ||||
| -rw-r--r-- | net/sunrpc/xprtrdma/svc_rdma_transport.c | 5 |
2 files changed, 6 insertions, 7 deletions
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index b4b17f44cb2..74de31a0661 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -443,18 +443,18 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) dprintk("svcrdma: rqstp=%p\n", rqstp); - spin_lock_bh(&rdma_xprt->sc_read_complete_lock); + spin_lock_bh(&rdma_xprt->sc_rq_dto_lock); if (!list_empty(&rdma_xprt->sc_read_complete_q)) { ctxt = list_entry(rdma_xprt->sc_read_complete_q.next, struct svc_rdma_op_ctxt, dto_q); list_del_init(&ctxt->dto_q); } - spin_unlock_bh(&rdma_xprt->sc_read_complete_lock); - if (ctxt) + if (ctxt) { + spin_unlock_bh(&rdma_xprt->sc_rq_dto_lock); return rdma_read_complete(rqstp, ctxt); + } - spin_lock_bh(&rdma_xprt->sc_rq_dto_lock); if (!list_empty(&rdma_xprt->sc_rq_dto_q)) { ctxt = list_entry(rdma_xprt->sc_rq_dto_q.next, struct svc_rdma_op_ctxt, diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 19ddc382b77..900cb69728c 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -359,11 +359,11 @@ static void sq_cq_reap(struct svcxprt_rdma *xprt) if (test_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags)) { struct svc_rdma_op_ctxt *read_hdr = ctxt->read_hdr; BUG_ON(!read_hdr); + spin_lock_bh(&xprt->sc_rq_dto_lock); set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags); - spin_lock_bh(&xprt->sc_read_complete_lock); list_add_tail(&read_hdr->dto_q, &xprt->sc_read_complete_q); - spin_unlock_bh(&xprt->sc_read_complete_lock); + spin_unlock_bh(&xprt->sc_rq_dto_lock); svc_xprt_enqueue(&xprt->sc_xprt); } svc_rdma_put_context(ctxt, 0); @@ -428,7 +428,6 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv, init_waitqueue_head(&cma_xprt->sc_send_wait); spin_lock_init(&cma_xprt->sc_lock); - spin_lock_init(&cma_xprt->sc_read_complete_lock); spin_lock_init(&cma_xprt->sc_rq_dto_lock); cma_xprt->sc_ord = svcrdma_ord; |