RDMA/cxgb4: Reset wait condition atomically

The driver was never really waiting for RDMA_WR/FINI completions
because the condition variable used to determine if the completion
happened was never reset, and this condition variable is reused for
both connection setup and teardown.  This causes various driver
crashes under heavy loads due to releasing resources too early.

The fix is to use atomic bits to correctly reset the condition
immediately after the completion is detected.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>

drivers/infiniband/hw/cxgb4/cm.c

@@ -1198,9 +1198,7 @@ static int pass_open_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 	}
 	PDBG("%s ep %p status %d error %d\n", __func__, ep,
 	     rpl->status, status2errno(rpl->status));
-	ep->com.wr_wait.ret = status2errno(rpl->status);
-	ep->com.wr_wait.done = 1;
-	wake_up(&ep->com.wr_wait.wait);
+	c4iw_wake_up(&ep->com.wr_wait, status2errno(rpl->status));
 
 	return 0;
 }
@@ -1234,9 +1232,7 @@ static int close_listsrv_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 	struct c4iw_listen_ep *ep = lookup_stid(t, stid);
 
 	PDBG("%s ep %p\n", __func__, ep);
-	ep->com.wr_wait.ret = status2errno(rpl->status);
-	ep->com.wr_wait.done = 1;
-	wake_up(&ep->com.wr_wait.wait);
+	c4iw_wake_up(&ep->com.wr_wait, status2errno(rpl->status));
 	return 0;
 }
 
@@ -1492,17 +1488,13 @@ static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb)
 		 * in rdma connection migration (see c4iw_accept_cr()).
 		 */
 		__state_set(&ep->com, CLOSING);
-		ep->com.wr_wait.done = 1;
-		ep->com.wr_wait.ret = -ECONNRESET;
 		PDBG("waking up ep %p tid %u\n", ep, ep->hwtid);
-		wake_up(&ep->com.wr_wait.wait);
+		c4iw_wake_up(&ep->com.wr_wait, -ECONNRESET);
 		break;
 	case MPA_REP_SENT:
 		__state_set(&ep->com, CLOSING);
-		ep->com.wr_wait.done = 1;
-		ep->com.wr_wait.ret = -ECONNRESET;
 		PDBG("waking up ep %p tid %u\n", ep, ep->hwtid);
-		wake_up(&ep->com.wr_wait.wait);
+		c4iw_wake_up(&ep->com.wr_wait, -ECONNRESET);
 		break;
 	case FPDU_MODE:
 		start_ep_timer(ep);
@@ -1579,9 +1571,7 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb)
 	/*
 	 * Wake up any threads in rdma_init() or rdma_fini().
 	 */
-	ep->com.wr_wait.done = 1;
-	ep->com.wr_wait.ret = -ECONNRESET;
-	wake_up(&ep->com.wr_wait.wait);
+	c4iw_wake_up(&ep->com.wr_wait, -ECONNRESET);
 
 	mutex_lock(&ep->com.mutex);
 	switch (ep->com.state) {
@@ -2294,14 +2284,8 @@ static int fw6_msg(struct c4iw_dev *dev, struct sk_buff *skb)
 		ret = (int)((be64_to_cpu(rpl->data[0]) >> 8) & 0xff);
 		wr_waitp = (struct c4iw_wr_wait *)(__force unsigned long) rpl->data[1];
 		PDBG("%s wr_waitp %p ret %u\n", __func__, wr_waitp, ret);
-		if (wr_waitp) {
-			if (ret)
-				wr_waitp->ret = -ret;
-			else
-				wr_waitp->ret = 0;
-			wr_waitp->done = 1;
-			wake_up(&wr_waitp->wait);
-		}
+		if (wr_waitp)
+			c4iw_wake_up(wr_waitp, ret ? -ret : 0);
 		kfree_skb(skb);
 		break;
 	case 2:

drivers/infiniband/hw/cxgb4/iw_cxgb4.h

@@ -131,42 +131,54 @@ static inline int c4iw_num_stags(struct c4iw_rdev *rdev)
 
 #define C4IW_WR_TO (10*HZ)
 
+enum {
+	REPLY_READY = 0,
+};
+
 struct c4iw_wr_wait {
 	wait_queue_head_t wait;
-	int done;
+	unsigned long status;
 	int ret;
 };
 
 static inline void c4iw_init_wr_wait(struct c4iw_wr_wait *wr_waitp)
 {
 	wr_waitp->ret = 0;
-	wr_waitp->done = 0;
+	wr_waitp->status = 0;
 	init_waitqueue_head(&wr_waitp->wait);
 }
 
+static inline void c4iw_wake_up(struct c4iw_wr_wait *wr_waitp, int ret)
+{
+	wr_waitp->ret = ret;
+	set_bit(REPLY_READY, &wr_waitp->status);
+	wake_up(&wr_waitp->wait);
+}
+
 static inline int c4iw_wait_for_reply(struct c4iw_rdev *rdev,
 				 struct c4iw_wr_wait *wr_waitp,
 				 u32 hwtid, u32 qpid,
 				 const char *func)
 {
 	unsigned to = C4IW_WR_TO;
-	do {
+	int ret;
 
-		wait_event_timeout(wr_waitp->wait, wr_waitp->done, to);
-		if (!wr_waitp->done) {
+	do {
+		ret = wait_event_timeout(wr_waitp->wait,
+			test_and_clear_bit(REPLY_READY, &wr_waitp->status), to);
+		if (!ret) {
 			printk(KERN_ERR MOD "%s - Device %s not responding - "
 			       "tid %u qpid %u\n", func,
 			       pci_name(rdev->lldi.pdev), hwtid, qpid);
 			to = to << 2;
 		}
-	} while (!wr_waitp->done);
+	} while (!ret);
 	if (wr_waitp->ret)
 		PDBG("%s: FW reply %d tid %u qpid %u\n",
 		     pci_name(rdev->lldi.pdev), wr_waitp->ret, hwtid, qpid);
 	return wr_waitp->ret;
 }
 
-
 struct c4iw_dev {
 	struct ib_device ibdev;
 	struct c4iw_rdev rdev;