IB/rxe: Disable completion upcalls when a CQ is destroyed

This prevents the stack from accessing userspace objects while they
are being torn down.

One possible sequence of events:
 - Userspace program exits
 - ib_uverbs_cleanup_ucontext() runs, calling ib_destroy_qp(),
   ib_destroy_cq(), etc. and releasing/freeing the UCQ
   - The QP still has tasklets running, so it isn't destroyed yet
   - The CQ is referenced by the QP, so the CQ isn't destroyed yet
   - The UCQ is kfree()'d anyway
 - A send work request completes
 - rxe_send_complete() calls cq->ibcq.comp_handler()
 - ib_uverbs_comp_handler() runs and crashes; the event queue is checked
   for is_closed, but it has no way to check the ib_ucq_object before
   accessing it

The reference counting on the CQ doesn't protect against this since the CQ
hasn't been destroyed yet.
There's no available interface to deregister the UCQ from the CQ, and it
didn't appear that attempting to add reference counting to the UCQ was
going to be a good way to go since this solution is much simpler.

Fixes: 8700e3e7c485 ("Soft RoCE driver")
Signed-off-by: Andrew Boyer <andrew.boyer@dell.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

diff --git a/drivers/infiniband/sw/rxe/rxe_cq.c b/drivers/infiniband/sw/rxe/rxe_cq.c
index 49fe42c..c4aabf7 100644 (file)
--- a/drivers/infiniband/sw/rxe/rxe_cq.c
+++ b/drivers/infiniband/sw/rxe/rxe_cq.c
@@ -69,6 +69,14 @@ err1:
 static void rxe_send_complete(unsigned long data)
 {
        struct rxe_cq *cq = (struct rxe_cq *)data;
+       unsigned long flags;
+
+       spin_lock_irqsave(&cq->cq_lock, flags);
+       if (cq->is_dying) {
+               spin_unlock_irqrestore(&cq->cq_lock, flags);
+               return;
+       }
+       spin_unlock_irqrestore(&cq->cq_lock, flags);
 
        cq->ibcq.comp_handler(&cq->ibcq, cq->ibcq.cq_context);
 }
@@ -97,6 +105,8 @@ int rxe_cq_from_init(struct rxe_dev *rxe, struct rxe_cq *cq, int cqe,
        if (udata)
                cq->is_user = 1;
 
+       cq->is_dying = false;
+
        tasklet_init(&cq->comp_task, rxe_send_complete, (unsigned long)cq);
 
        spin_lock_init(&cq->cq_lock);
@@ -156,6 +166,15 @@ int rxe_cq_post(struct rxe_cq *cq, struct rxe_cqe *cqe, int solicited)
        return 0;
 }
 
+void rxe_cq_disable(struct rxe_cq *cq)
+{
+       unsigned long flags;
+
+       spin_lock_irqsave(&cq->cq_lock, flags);
+       cq->is_dying = true;
+       spin_unlock_irqrestore(&cq->cq_lock, flags);
+}
+
 void rxe_cq_cleanup(struct rxe_pool_entry *arg)
 {
        struct rxe_cq *cq = container_of(arg, typeof(*cq), pelem);

diff --git a/drivers/infiniband/sw/rxe/rxe_loc.h b/drivers/infiniband/sw/rxe/rxe_loc.h
index 6b65c01..8073f58 100644 (file)
--- a/drivers/infiniband/sw/rxe/rxe_loc.h
+++ b/drivers/infiniband/sw/rxe/rxe_loc.h
@@ -64,6 +64,8 @@ int rxe_cq_resize_queue(struct rxe_cq *cq, int new_cqe, struct ib_udata *udata);
 
 int rxe_cq_post(struct rxe_cq *cq, struct rxe_cqe *cqe, int solicited);
 
+void rxe_cq_disable(struct rxe_cq *cq);
+
 void rxe_cq_cleanup(struct rxe_pool_entry *arg);
 
 /* rxe_mcast.c */

diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index e611d0c..0b362f4 100644 (file)
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -919,6 +919,8 @@ static int rxe_destroy_cq(struct ib_cq *ibcq)
 {
        struct rxe_cq *cq = to_rcq(ibcq);
 
+       rxe_cq_disable(cq);
+
        rxe_drop_ref(cq);
        return 0;
 }

diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h
index 5a180fb..b09a9e2 100644 (file)
--- a/drivers/infiniband/sw/rxe/rxe_verbs.h
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.h
@@ -89,6 +89,7 @@ struct rxe_cq {
        struct rxe_queue        *queue;
        spinlock_t              cq_lock;
        u8                      notify;
+       bool                    is_dying;
        int                     is_user;
        struct tasklet_struct   comp_task;
 };