RDMA/siw: Fix handling of zero-sized Read and Receive Queues.

During connection setup, the application may choose to zero-size inbound
and outbound READ queues, as well as the Receive queue.  This patch fixes
handling of zero-sized queues, but not prevents it.

Kamal Heib says in an initial error report:

 When running the blktests over siw the following shift-out-of-bounds is
 reported, this is happening because the passed IRD or ORD from the ulp
 could be zero which will lead to unexpected behavior when calling
 roundup_pow_of_two(), fix that by blocking zero values of ORD or IRD.

   UBSAN: shift-out-of-bounds in ./include/linux/log2.h:57:13
   shift exponent 64 is too large for 64-bit type 'long unsigned int'
   CPU: 20 PID: 3957 Comm: kworker/u64:13 Tainted: G S     5.10.0-rc6 #2
   Hardware name: Dell Inc. PowerEdge R630/02C2CP, BIOS 2.1.5 04/11/2016
   Workqueue: iw_cm_wq cm_work_handler [iw_cm]
   Call Trace:
    dump_stack+0x99/0xcb
    ubsan_epilogue+0x5/0x40
    __ubsan_handle_shift_out_of_bounds.cold.11+0xb4/0xf3
    ? down_write+0x183/0x3d0
    siw_qp_modify.cold.8+0x2d/0x32 [siw]
    ? __local_bh_enable_ip+0xa5/0xf0
    siw_accept+0x906/0x1b60 [siw]
    ? xa_load+0x147/0x1f0
    ? siw_connect+0x17a0/0x17a0 [siw]
    ? lock_downgrade+0x700/0x700
    ? siw_get_base_qp+0x1c2/0x340 [siw]
    ? _raw_spin_unlock_irqrestore+0x39/0x40
    iw_cm_accept+0x1f4/0x430 [iw_cm]
    rdma_accept+0x3fa/0xb10 [rdma_cm]
    ? check_flush_dependency+0x410/0x410
    ? cma_rep_recv+0x570/0x570 [rdma_cm]
    nvmet_rdma_queue_connect+0x1a62/0x2680 [nvmet_rdma]
    ? nvmet_rdma_alloc_cmds+0xce0/0xce0 [nvmet_rdma]
    ? lock_release+0x56e/0xcc0
    ? lock_downgrade+0x700/0x700
    ? lock_downgrade+0x700/0x700
    ? __xa_alloc_cyclic+0xef/0x350
    ? __xa_alloc+0x2d0/0x2d0
    ? rdma_restrack_add+0xbe/0x2c0 [ib_core]
    ? __ww_mutex_die+0x190/0x190
    cma_cm_event_handler+0xf2/0x500 [rdma_cm]
    iw_conn_req_handler+0x910/0xcb0 [rdma_cm]
    ? _raw_spin_unlock_irqrestore+0x39/0x40
    ? trace_hardirqs_on+0x1c/0x150
    ? cma_ib_handler+0x8a0/0x8a0 [rdma_cm]
    ? __kasan_kmalloc.constprop.7+0xc1/0xd0
    cm_work_handler+0x121c/0x17a0 [iw_cm]
    ? iw_cm_reject+0x190/0x190 [iw_cm]
    ? trace_hardirqs_on+0x1c/0x150
    process_one_work+0x8fb/0x16c0
    ? pwq_dec_nr_in_flight+0x320/0x320
    worker_thread+0x87/0xb40
    ? __kthread_parkme+0xd1/0x1a0
    ? process_one_work+0x16c0/0x16c0
    kthread+0x35f/0x430
    ? kthread_mod_delayed_work+0x180/0x180
    ret_from_fork+0x22/0x30

Fixes: a531975279f3 ("rdma/siw: main include file")
Fixes: f29dd55b0236 ("rdma/siw: queue pair methods")
Fixes: 8b6a361b8c48 ("rdma/siw: receive path")
Fixes: b9be6f18cf9e ("rdma/siw: transmit path")
Fixes: 303ae1cdfdf7 ("rdma/siw: application interface")
Link: https://lore.kernel.org/r/20210108125845.1803-1-bmt@zurich.ibm.com
Reported-by: Kamal Heib <kamalheib1@gmail.com>
Reported-by: Yi Zhang <yi.zhang@redhat.com>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Bernard Metzler <bmt@zurich.ibm.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

1 files changed, 14 insertions, 6 deletions

diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c
index 68fd053fc774..e389d44e5591 100644
--- a/drivers/infiniband/sw/siw/siw_verbs.c
+++ b/drivers/infiniband/sw/siw/siw_verbs.c
@@ -365,13 +365,23 @@ struct ib_qp *siw_create_qp(struct ib_pd *pd,
 	if (rv)
 		goto err_out;
 
+	num_sqe = attrs->cap.max_send_wr;
+	num_rqe = attrs->cap.max_recv_wr;
+
 	/* All queue indices are derived from modulo operations
 	 * on a free running 'get' (consumer) and 'put' (producer)
 	 * unsigned counter. Having queue sizes at power of two
 	 * avoids handling counter wrap around.
 	 */
-	num_sqe = roundup_pow_of_two(attrs->cap.max_send_wr);
-	num_rqe = roundup_pow_of_two(attrs->cap.max_recv_wr);
+	if (num_sqe)
+		num_sqe = roundup_pow_of_two(num_sqe);
+	else {
+		/* Zero sized SQ is not supported */
+		rv = -EINVAL;
+		goto err_out;
+	}
+	if (num_rqe)
+		num_rqe = roundup_pow_of_two(num_rqe);
 
 	if (udata)
 		qp->sendq = vmalloc_user(num_sqe * sizeof(struct siw_sqe));
@@ -379,7 +389,6 @@ struct ib_qp *siw_create_qp(struct ib_pd *pd,
 		qp->sendq = vzalloc(num_sqe * sizeof(struct siw_sqe));
 
 	if (qp->sendq == NULL) {
-		siw_dbg(base_dev, "SQ size %d alloc failed\n", num_sqe);
 		rv = -ENOMEM;
 		goto err_out_xa;
 	}
@@ -413,7 +422,6 @@ struct ib_qp *siw_create_qp(struct ib_pd *pd,
 			qp->recvq = vzalloc(num_rqe * sizeof(struct siw_rqe));
 
 		if (qp->recvq == NULL) {
-			siw_dbg(base_dev, "RQ size %d alloc failed\n", num_rqe);
 			rv = -ENOMEM;
 			goto err_out_xa;
 		}
@@ -966,9 +974,9 @@ int siw_post_receive(struct ib_qp *base_qp, const struct ib_recv_wr *wr,
 	unsigned long flags;
 	int rv = 0;
 
-	if (qp->srq) {
+	if (qp->srq || qp->attrs.rq_size == 0) {
 		*bad_wr = wr;
-		return -EOPNOTSUPP; /* what else from errno.h? */
+		return -EINVAL;
 	}
 	if (!rdma_is_kernel_res(&qp->base_qp.res)) {
 		siw_dbg_qp(qp, "no kernel post_recv for user mapped rq\n");