Patch "xprtrdma: Fix DMAR failure in frwr_op_map() after reconnect" has been added to the 4.8-stable tree

@@ -44,18 +44,20 @@
  * being done.
  *
  * When the underlying transport disconnects, MRs are left in one of
- * three states:
+ * four states:
  *
  * INVALID:	The MR was not in use before the QP entered ERROR state.
- *		(Or, the LOCAL_INV WR has not completed or flushed yet).
- *
- * STALE:	The MR was being registered or unregistered when the QP
- *		entered ERROR state, and the pending WR was flushed.
  *
  * VALID:	The MR was registered before the QP entered ERROR state.
  *
- * When frwr_op_map encounters STALE and VALID MRs, they are recovered
- * with ib_dereg_mr and then are re-initialized. Beause MR recovery
+ * FLUSHED_FR:	The MR was being registered when the QP entered ERROR
+ *		state, and the pending WR was flushed.
+ *
+ * FLUSHED_LI:	The MR was being invalidated when the QP entered ERROR
+ *		state, and the pending WR was flushed.
+ *
+ * When frwr_op_map encounters FLUSHED and VALID MRs, they are recovered
+ * with ib_dereg_mr and then are re-initialized. Because MR recovery
  * allocates fresh resources, it is deferred to a workqueue, and the
  * recovered MRs are placed back on the rb_mws list when recovery is
  * complete. frwr_op_map allocates another MR for the current RPC while

@@ -175,12 +177,15 @@ __frwr_reset_mr(struct rpcrdma_ia *ia, s
 static void
 frwr_op_recover_mr(struct rpcrdma_mw *mw)
 {
+	enum rpcrdma_frmr_state state = mw->frmr.fr_state;
 	struct rpcrdma_xprt *r_xprt = mw->mw_xprt;
 	struct rpcrdma_ia *ia = &r_xprt->rx_ia;
 	int rc;
 
 	rc = __frwr_reset_mr(ia, mw);
-	ib_dma_unmap_sg(ia->ri_device, mw->mw_sg, mw->mw_nents, mw->mw_dir);
+	if (state != FRMR_FLUSHED_LI)
+		ib_dma_unmap_sg(ia->ri_device,
+				mw->mw_sg, mw->mw_nents, mw->mw_dir);
 	if (rc)
 		goto out_release;
 

@@ -261,10 +266,8 @@ frwr_op_maxpages(struct rpcrdma_xprt *r_
 }
 
 static void
-__frwr_sendcompletion_flush(struct ib_wc *wc, struct rpcrdma_frmr *frmr,
-			    const char *wr)
+__frwr_sendcompletion_flush(struct ib_wc *wc, const char *wr)
 {
-	frmr->fr_state = FRMR_IS_STALE;
 	if (wc->status != IB_WC_WR_FLUSH_ERR)
 		pr_err("rpcrdma: %s: %s (%u/0x%x)\n",
 		       wr, ib_wc_status_msg(wc->status),

@@ -287,7 +290,8 @@ frwr_wc_fastreg(struct ib_cq *cq, struct
 	if (wc->status != IB_WC_SUCCESS) {
 		cqe = wc->wr_cqe;
 		frmr = container_of(cqe, struct rpcrdma_frmr, fr_cqe);
-		__frwr_sendcompletion_flush(wc, frmr, "fastreg");
+		frmr->fr_state = FRMR_FLUSHED_FR;
+		__frwr_sendcompletion_flush(wc, "fastreg");
 	}
 }
 

@@ -307,7 +311,8 @@ frwr_wc_localinv(struct ib_cq *cq, struc
 	if (wc->status != IB_WC_SUCCESS) {
 		cqe = wc->wr_cqe;
 		frmr = container_of(cqe, struct rpcrdma_frmr, fr_cqe);
-		__frwr_sendcompletion_flush(wc, frmr, "localinv");
+		frmr->fr_state = FRMR_FLUSHED_LI;
+		__frwr_sendcompletion_flush(wc, "localinv");
 	}
 }
 

@@ -327,8 +332,10 @@ frwr_wc_localinv_wake(struct ib_cq *cq,
 	/* WARNING: Only wr_cqe and status are reliable at this point */
 	cqe = wc->wr_cqe;
 	frmr = container_of(cqe, struct rpcrdma_frmr, fr_cqe);
-	if (wc->status != IB_WC_SUCCESS)
-		__frwr_sendcompletion_flush(wc, frmr, "localinv");
+	if (wc->status != IB_WC_SUCCESS) {
+		frmr->fr_state = FRMR_FLUSHED_LI;
+		__frwr_sendcompletion_flush(wc, "localinv");
+	}
 	complete(&frmr->fr_linv_done);
 }
 

@@ -207,7 +207,8 @@ struct rpcrdma_rep {
 enum rpcrdma_frmr_state {
 	FRMR_IS_INVALID,	/* ready to be used */
 	FRMR_IS_VALID,		/* in use */
-	FRMR_IS_STALE,		/* failed completion */
+	FRMR_FLUSHED_FR,	/* flushed FASTREG WR */
+	FRMR_FLUSHED_LI,	/* flushed LOCALINV WR */
 };
 
 struct rpcrdma_frmr {