summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorYonatan Cohen <yonatanc@mellanox.com>2016-11-16 10:39:15 +0200
committerDoug Ledford <dledford@redhat.com>2016-11-16 20:03:44 -0500
commit002e062e13db10973adb8302f231e48b477c7ccf (patch)
treed8e35b3e448a1008581af2db04de0aa8c87a86d7
parent1454ca3a97e147bb91e98b087446c39cf6692a48 (diff)
IB/rxe: Fix handling of erroneous WR
To correctly handle a erroneous WR this fix does the following 1. Make sure the bad WQE causes a user completion event. 2. Call rxe_completer to handle the erred WQE. Before the fix, when rxe_requester found a bad WQE, it changed its status to IB_WC_LOC_PROT_ERR and exit with 0 for non RC QPs. If this was the 1st WQE then there would be no ACK to invoke the completer and this bad WQE would be stuck in the QP's send-q. On top of that the requester exiting with 0 caused rxe_do_task to endlessly invoke rxe_requester, resulting in a soft-lockup attached below. In case the WQE was not the 1st and rxe_completer did get a chance to handle the bad WQE, it did not cause a complete event since the WQE's IB_SEND_SIGNALED flag was not set. Setting WQE status to IB_SEND_SIGNALED is subject to IBA spec version 1.2.1, section 10.7.3.1 Signaled Completions. NMI watchdog: BUG: soft lockup - CPU#7 stuck for 22s! [<ffffffffa0590145>] ? rxe_pool_get_index+0x35/0xb0 [rdma_rxe] [<ffffffffa05952ec>] lookup_mem+0x3c/0xc0 [rdma_rxe] [<ffffffffa0595534>] copy_data+0x1c4/0x230 [rdma_rxe] [<ffffffffa058c180>] rxe_requester+0x9d0/0x1100 [rdma_rxe] [<ffffffff8158e98a>] ? kfree_skbmem+0x5a/0x60 [<ffffffffa05962c9>] rxe_do_task+0x89/0xf0 [rdma_rxe] [<ffffffffa05963e2>] rxe_run_task+0x12/0x30 [rdma_rxe] [<ffffffffa059110a>] rxe_post_send+0x41a/0x550 [rdma_rxe] [<ffffffff811ef922>] ? __kmalloc+0x182/0x200 [<ffffffff816ba512>] ? down_read+0x12/0x40 [<ffffffffa054bd32>] ib_uverbs_post_send+0x532/0x540 [ib_uverbs] [<ffffffff815f8722>] ? tcp_sendmsg+0x402/0xb80 [<ffffffffa05453dc>] ib_uverbs_write+0x18c/0x3f0 [ib_uverbs] [<ffffffff81623c2e>] ? inet_recvmsg+0x7e/0xb0 [<ffffffff8158764d>] ? sock_recvmsg+0x3d/0x50 [<ffffffff81215b87>] __vfs_write+0x37/0x140 [<ffffffff81216892>] vfs_write+0xb2/0x1b0 [<ffffffff81217ce5>] SyS_write+0x55/0xc0 [<ffffffff816bc672>] entry_SYSCALL_64_fastpath+0x1a/0xa Fixes: 8700e3e7c485 ("Soft RoCE driver") Signed-off-by: Yonatan Cohen <yonatanc@mellanox.com> Reviewed-by: Moni Shoua <monis@mellanox.com> Signed-off-by: Leon Romanovsky <leon@kernel.org> Signed-off-by: Doug Ledford <dledford@redhat.com>
-rw-r--r--drivers/infiniband/sw/rxe/rxe_req.c21
1 files changed, 13 insertions, 8 deletions
diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index 832846b73ea0..22bd9630dcd9 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -696,7 +696,8 @@ next_wqe:
qp->req.wqe_index);
wqe->state = wqe_state_done;
wqe->status = IB_WC_SUCCESS;
- goto complete;
+ __rxe_do_task(&qp->comp.task);
+ return 0;
}
payload = mtu;
}
@@ -745,13 +746,17 @@ err:
wqe->status = IB_WC_LOC_PROT_ERR;
wqe->state = wqe_state_error;
-complete:
- if (qp_type(qp) != IB_QPT_RC) {
- while (rxe_completer(qp) == 0)
- ;
- }
-
- return 0;
+ /*
+ * IBA Spec. Section 10.7.3.1 SIGNALED COMPLETIONS
+ * ---------8<---------8<-------------
+ * ...Note that if a completion error occurs, a Work Completion
+ * will always be generated, even if the signaling
+ * indicator requests an Unsignaled Completion.
+ * ---------8<---------8<-------------
+ */
+ wqe->wr.send_flags |= IB_SEND_SIGNALED;
+ __rxe_do_task(&qp->comp.task);
+ return -EAGAIN;
exit:
return -EAGAIN;