From: Michael J. Ruhl michael.j.ruhl@intel.com
The RC/UC code path can go through a software loopback. In this code path the receive side QP is manipulated.
If two threads are working on the QP receive side (i.e. post_send, and modify_qp to an error state), QP information can be corrupted.
(post_send via loopback) set r_sge loop update r_sge (modify_qp) take r_lock update r_sge <---- r_sge is now incorrect (post_send) update r_sge <---- crash, etc. ...
This can lead to one of the two following crashes:
BUG: unable to handle kernel NULL pointer dereference at (null) IP: hfi1_copy_sge+0xf1/0x2e0 [hfi1] PGD 8000001fe6a57067 PUD 1fd9e0c067 PMD 0 Call Trace: ruc_loopback+0x49b/0xbc0 [hfi1] hfi1_do_send+0x38e/0x3e0 [hfi1] _hfi1_do_send+0x1e/0x20 [hfi1] process_one_work+0x17f/0x440 worker_thread+0x126/0x3c0 kthread+0xd1/0xe0 ret_from_fork_nospec_begin+0x21/0x21
or:
BUG: unable to handle kernel NULL pointer dereference at 0000000000000048 IP: rvt_clear_mr_refs+0x45/0x370 [rdmavt] PGD 80000006ae5eb067 PUD ef15d0067 PMD 0 Call Trace: rvt_error_qp+0xaa/0x240 [rdmavt] rvt_modify_qp+0x47f/0xaa0 [rdmavt] ib_security_modify_qp+0x8f/0x400 [ib_core] ib_modify_qp_with_udata+0x44/0x70 [ib_core] modify_qp.isra.23+0x1eb/0x2b0 [ib_uverbs] ib_uverbs_modify_qp+0xaa/0xf0 [ib_uverbs] ib_uverbs_write+0x272/0x430 [ib_uverbs] vfs_write+0xc0/0x1f0 SyS_write+0x7f/0xf0 system_call_fastpath+0x1c/0x21
Fix by using the appropriate locking on the receiving QP.
Fixes: 15703461533a ("IB/{hfi1, qib, rdmavt}: Move ruc_loopback to rdmavt") Cc: stable@vger.kernel.org #v4.9+ Reviewed-by: Mike Marciniszyn mike.marciniszyn@intel.com Signed-off-by: Michael J. Ruhl michael.j.ruhl@intel.com Signed-off-by: Dennis Dalessandro dennis.dalessandro@intel.com --- drivers/infiniband/sw/rdmavt/qp.c | 33 +++++++++++++++++++++++---------- 1 files changed, 23 insertions(+), 10 deletions(-)
diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index 3373658..a34b9a2 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -2790,6 +2790,18 @@ void rvt_copy_sge(struct rvt_qp *qp, struct rvt_sge_state *ss, } EXPORT_SYMBOL(rvt_copy_sge);
+static enum ib_wc_status loopback_qp_drop(struct rvt_ibport *rvp, + struct rvt_qp *sqp) +{ + rvp->n_pkt_drops++; + /* + * For RC, the requester would timeout and retry so + * shortcut the timeouts and just signal too many retries. + */ + return sqp->ibqp.qp_type == IB_QPT_RC ? + IB_WC_RETRY_EXC_ERR : IB_WC_SUCCESS; +} + /** * ruc_loopback - handle UC and RC loopback requests * @sqp: the sending QP @@ -2862,17 +2874,14 @@ void rvt_ruc_loopback(struct rvt_qp *sqp) } spin_unlock_irqrestore(&sqp->s_lock, flags);
- if (!qp || !(ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK) || + if (!qp) { + send_status = loopback_qp_drop(rvp, sqp); + goto serr_no_r_lock; + } + spin_lock_irqsave(&qp->r_lock, flags); + if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK) || qp->ibqp.qp_type != sqp->ibqp.qp_type) { - rvp->n_pkt_drops++; - /* - * For RC, the requester would timeout and retry so - * shortcut the timeouts and just signal too many retries. - */ - if (sqp->ibqp.qp_type == IB_QPT_RC) - send_status = IB_WC_RETRY_EXC_ERR; - else - send_status = IB_WC_SUCCESS; + send_status = loopback_qp_drop(rvp, sqp); goto serr; }
@@ -3030,6 +3039,7 @@ void rvt_ruc_loopback(struct rvt_qp *sqp) wqe->wr.send_flags & IB_SEND_SOLICITED);
send_comp: + spin_unlock_irqrestore(&qp->r_lock, flags); spin_lock_irqsave(&sqp->s_lock, flags); rvp->n_loop_pkts++; flush_send: @@ -3056,6 +3066,7 @@ void rvt_ruc_loopback(struct rvt_qp *sqp) } if (sqp->s_rnr_retry_cnt < 7) sqp->s_rnr_retry--; + spin_unlock_irqrestore(&qp->r_lock, flags); spin_lock_irqsave(&sqp->s_lock, flags); if (!(ib_rvt_state_ops[sqp->state] & RVT_PROCESS_RECV_OK)) goto clr_busy; @@ -3084,6 +3095,8 @@ void rvt_ruc_loopback(struct rvt_qp *sqp) rvt_rc_error(qp, wc.status);
serr: + spin_unlock_irqrestore(&qp->r_lock, flags); +serr_no_r_lock: spin_lock_irqsave(&sqp->s_lock, flags); rvt_send_complete(sqp, wqe, send_status); if (sqp->ibqp.qp_type == IB_QPT_RC) {