summaryrefslogtreecommitdiff
path: root/drivers/infiniband
diff options
context:
space:
mode:
authorMike Marciniszyn <mike.marciniszyn@qlogic.com>2011-11-04 08:26:52 -0400
committerRoland Dreier <roland@purestorage.com>2011-11-04 09:35:44 -0700
commit30ab7e230b996f750d4fc24b6bf8214e83effa12 (patch)
tree83028e5d4700e44bd7d7e99c9e0251b39d5d3045 /drivers/infiniband
parentf470f8d4e702593ee1d0852871ad80373bce707b (diff)
IB/qib: Fix panic in RC error flushing logic
The following panic can occur when flushing a QP: RIP: 0010:[<ffffffffa0168e8b>] [<ffffffffa0168e8b>] qib_send_complete+0x3b/0x190 [ib_qib] RSP: 0018:ffff8803cdc6fc90 EFLAGS: 00010046 RAX: 0000000000000000 RBX: ffff8803d84ba000 RCX: 0000000000000000 RDX: 0000000000000005 RSI: ffffc90015a53430 RDI: ffff8803d84ba000 RBP: ffff8803cdc6fce0 R08: ffff8803cdc6fc90 R09: 0000000000000001 R10: 00000000ffffffff R11: 0000000000000000 R12: ffff8803d84ba0c0 R13: ffff8803d84ba5cc R14: 0000000000000800 R15: 0000000000000246 FS: 0000000000000000(0000) GS:ffff880036600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b CR2: 0000000000000034 CR3: 00000003e44f9000 CR4: 00000000000406f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process qib/0 (pid: 1350, threadinfo ffff8803cdc6e000, task ffff88042728a100) Stack: 53544c5553455201 0000000100000005 0000000000000000 ffff8803d84ba000 0000000000000000 0000000000000000 0000000000000000 0000000000000000 0000000000000000 0000000000000001 ffff8803cdc6fd30 ffffffffa0165d7a Call Trace: [<ffffffffa0165d7a>] qib_make_rc_req+0x36a/0xe80 [ib_qib] [<ffffffffa0165a10>] ? qib_make_rc_req+0x0/0xe80 [ib_qib] [<ffffffffa01698b3>] qib_do_send+0xf3/0xb60 [ib_qib] [<ffffffff814db757>] ? thread_return+0x4e/0x777 [<ffffffffa01697c0>] ? qib_do_send+0x0/0xb60 [ib_qib] [<ffffffff81088bf0>] worker_thread+0x170/0x2a0 [<ffffffff8108e530>] ? autoremove_wake_function+0x0/0x40 [<ffffffff81088a80>] ? worker_thread+0x0/0x2a0 [<ffffffff8108e1c6>] kthread+0x96/0xa0 [<ffffffff8100c1ca>] child_rip+0xa/0x20 [<ffffffff8108e130>] ? kthread+0x0/0xa0 [<ffffffff8100c1c0>] ? child_rip+0x0/0x20 RIP [<ffffffffa0168e8b>] qib_send_complete+0x3b/0x190 [ib_qib] The RC error state flush logic in qib_make_rc_req() could return all of the acked wqes and potentially have emptied the queue. It would then unconditionally try return a flush completion via qib_send_complete() for an invalid wqe, or worse a valid one that is not queued. The panic results when the completion code tries to maintain an MR reference count for a NULL MR. This fix modifies logic to only send one completion per qib_make_rc_req() call and changing the completion status from IB_WC_SUCCESS to IB_WC_WR_FLUSH_ERR as the completions progress. The outer loop will call as many times as necessary to flush the queue. Reviewed-by: Ram Vepa <ram.vepa@qlogic.com> Signed-off-by: Mike Marciniszyn <mike.marciniszyn@qlogic.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
Diffstat (limited to 'drivers/infiniband')
-rw-r--r--drivers/infiniband/hw/qib/qib_rc.c10
1 files changed, 3 insertions, 7 deletions
diff --git a/drivers/infiniband/hw/qib/qib_rc.c b/drivers/infiniband/hw/qib/qib_rc.c
index afaf4ac79f42..894afac26f3b 100644
--- a/drivers/infiniband/hw/qib/qib_rc.c
+++ b/drivers/infiniband/hw/qib/qib_rc.c
@@ -271,13 +271,9 @@ int qib_make_rc_req(struct qib_qp *qp)
goto bail;
}
wqe = get_swqe_ptr(qp, qp->s_last);
- while (qp->s_last != qp->s_acked) {
- qib_send_complete(qp, wqe, IB_WC_SUCCESS);
- if (++qp->s_last >= qp->s_size)
- qp->s_last = 0;
- wqe = get_swqe_ptr(qp, qp->s_last);
- }
- qib_send_complete(qp, wqe, IB_WC_WR_FLUSH_ERR);
+ qib_send_complete(qp, wqe, qp->s_last != qp->s_acked ?
+ IB_WC_SUCCESS : IB_WC_WR_FLUSH_ERR);
+ /* will get called again */
goto done;
}