IB/hfi1: Resolve kernel panics by reference counting receive contexts

Base receive contexts can be used by sub contexts.  Because of this,
resources for the context cannot be completely freed until all sub
contexts are done using the base context.

Introduce a reference count so that the base receive context can be
freed only when all sub contexts are done with it.

Use the provided function call for setting default send context
integrity rather than the manual method.

The cleanup path does not set all variables back to NULL after freeing
resources.  Since the clean up code can get called more than once,
(e.g. during context close and on the error path), it is necessary to
make sure that all the variables are NULLed.

Possible crash are:

BUG: unable to handle kernel paging request at 0000000001908900
IP: read_csr+0x24/0x30 [hfi1]
RIP: 0010:read_csr+0x24/0x30 [hfi1]
Call Trace:
 sc_disable+0x40/0x110 [hfi1]
 hfi1_file_close+0x16f/0x360 [hfi1]
 __fput+0xe7/0x210
 ____fput+0xe/0x10

or

kernel BUG at mm/slub.c:3877!
RIP: 0010:kfree+0x14f/0x170
Call Trace:
 hfi1_free_ctxtdata+0x19a/0x2b0 [hfi1]
 ? hfi1_user_exp_rcv_grp_free+0x73/0x80 [hfi1]
 hfi1_file_close+0x20f/0x360 [hfi1]
 __fput+0xe7/0x210
 ____fput+0xe/0x10

Fixes: Commit 62239fc6e554 ("IB/hfi1: Clean up on context initialization failure")
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Reviewed-by: Sebastian Sanchez <sebastian.sanchez@intel.com>
Signed-off-by: Michael J. Ruhl <michael.j.ruhl@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

1 files changed, 7 insertions, 4 deletions

diff --git a/drivers/infiniband/hw/hfi1/vnic_main.c b/drivers/infiniband/hw/hfi1/vnic_main.c
index b601c2929f8f..950c1b4df442 100644
--- a/drivers/infiniband/hw/hfi1/vnic_main.c
+++ b/drivers/infiniband/hw/hfi1/vnic_main.c
@@ -156,11 +156,11 @@ static int allocate_vnic_ctxt(struct hfi1_devdata *dd,
 	return ret;
 bail:
 	/*
-	 * hfi1_free_ctxtdata() also releases send_context
-	 * structure if uctxt->sc is not null
+	 * hfi1_rcd_put() will call hfi1_free_ctxtdata(), which will
+	 * release send_context structure if uctxt->sc is not null
 	 */
 	dd->rcd[uctxt->ctxt] = NULL;
-	hfi1_free_ctxtdata(dd, uctxt);
+	hfi1_rcd_put(uctxt);
 	dd_dev_dbg(dd, "vnic allocation failed. rc %d\n", ret);
 	return ret;
 }
@@ -208,7 +208,7 @@ static void deallocate_vnic_ctxt(struct hfi1_devdata *dd,
 	hfi1_clear_ctxt_pkey(dd, uctxt);
 
 	hfi1_stats.sps_ctxts--;
-	hfi1_free_ctxtdata(dd, uctxt);
+	hfi1_rcd_put(uctxt);
 }
 
 void hfi1_vnic_setup(struct hfi1_devdata *dd)
@@ -751,6 +751,7 @@ static int hfi1_vnic_init(struct hfi1_vnic_vport_info *vinfo)
 		rc = hfi1_vnic_allot_ctxt(dd, &dd->vnic.ctxt[i]);
 		if (rc)
 			break;
+		hfi1_rcd_get(dd->vnic.ctxt[i]);
 		dd->vnic.ctxt[i]->vnic_q_idx = i;
 	}
 
@@ -762,6 +763,7 @@ static int hfi1_vnic_init(struct hfi1_vnic_vport_info *vinfo)
 		 */
 		while (i-- > dd->vnic.num_ctxt) {
 			deallocate_vnic_ctxt(dd, dd->vnic.ctxt[i]);
+			hfi1_rcd_put(dd->vnic.ctxt[i]);
 			dd->vnic.ctxt[i] = NULL;
 		}
 		goto alloc_fail;
@@ -791,6 +793,7 @@ static void hfi1_vnic_deinit(struct hfi1_vnic_vport_info *vinfo)
 	if (--dd->vnic.num_vports == 0) {
 		for (i = 0; i < dd->vnic.num_ctxt; i++) {
 			deallocate_vnic_ctxt(dd, dd->vnic.ctxt[i]);
+			hfi1_rcd_put(dd->vnic.ctxt[i]);
 			dd->vnic.ctxt[i] = NULL;
 		}
 		hfi1_deinit_vnic_rsm(dd);