RDMA/bnxt_re: Fix hang during driver unload

Driver unload hits a hang during stress testing of load/unload.

stack trace snippet -

tasklet_kill at ffffffff9aabb8b2
bnxt_qplib_nq_stop_irq at ffffffffc0a805fb [bnxt_re]
bnxt_qplib_disable_nq at ffffffffc0a80c5b [bnxt_re]
bnxt_re_dev_uninit at ffffffffc0a67d15 [bnxt_re]
bnxt_re_remove_device at ffffffffc0a6af1d [bnxt_re]

tasklet_kill can hang if the tasklet is scheduled after it is disabled.

Modified the sequences to disable the interrupt first and synchronize
irq before disabling the tasklet.

Fixes: 1ac5a4047975 ("RDMA/bnxt_re: Add bnxt_re RoCE driver")
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1689322969-25402-3-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>

diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index a12c7ade101a146057240a6ca2eb19e4fdf951ae..a42555623aedfe7eae7c47368e55e086e1f2e525 100644 (file)
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -420,19 +420,19 @@ void bnxt_qplib_nq_stop_irq(struct bnxt_qplib_nq *nq, bool kill)
        if (!nq->requested)
                return;
 
-       tasklet_disable(&nq->nq_tasklet);
+       nq->requested = false;
        /* Mask h/w interrupt */
        bnxt_qplib_ring_nq_db(&nq->nq_db.dbinfo, nq->res->cctx, false);
        /* Sync with last running IRQ handler */
        synchronize_irq(nq->msix_vec);
-       if (kill)
-               tasklet_kill(&nq->nq_tasklet);
-
        irq_set_affinity_hint(nq->msix_vec, NULL);
        free_irq(nq->msix_vec, nq);
        kfree(nq->name);
        nq->name = NULL;
-       nq->requested = false;
+
+       if (kill)
+               tasklet_kill(&nq->nq_tasklet);
+       tasklet_disable(&nq->nq_tasklet);
 }
 
 void bnxt_qplib_disable_nq(struct bnxt_qplib_nq *nq)

diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
index b30e66b64827b241bae8f5d121eff790febae227..bc3aea4592b9df35887903722494d38088e0aaf1 100644 (file)
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
@@ -989,19 +989,18 @@ void bnxt_qplib_rcfw_stop_irq(struct bnxt_qplib_rcfw *rcfw, bool kill)
        if (!creq->requested)
                return;
 
-       tasklet_disable(&creq->creq_tasklet);
+       creq->requested = false;
        /* Mask h/w interrupts */
        bnxt_qplib_ring_nq_db(&creq->creq_db.dbinfo, rcfw->res->cctx, false);
        /* Sync with last running IRQ-handler */
        synchronize_irq(creq->msix_vec);
-       if (kill)
-               tasklet_kill(&creq->creq_tasklet);
-
        free_irq(creq->msix_vec, rcfw);
        kfree(creq->irq_name);
        creq->irq_name = NULL;
-       creq->requested = false;
        atomic_set(&rcfw->rcfw_intr_enabled, 0);
+       if (kill)
+               tasklet_kill(&creq->creq_tasklet);
+       tasklet_disable(&creq->creq_tasklet);
 }
 
 void bnxt_qplib_disable_rcfw_channel(struct bnxt_qplib_rcfw *rcfw)