Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull rdma updates from Jason Gunthorpe:

 - Minor bug fixes in mlx5, mthca, pvrdma, rtrs, mlx4, hfi1, hns

 - Minor cleanups: coding style, useless includes and documentation

 - Reorganize how multicast processing works in rxe

 - Replace a red/black tree with xarray in rxe which improves performance

 - DSCP support and HW address handle re-use in irdma

 - Simplify the mailbox command handling in hns

 - Simplify iser now that FMR is eliminated

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (93 commits)
  RDMA/nldev: Prevent underflow in nldev_stat_set_counter_dynamic_doit()
  IB/iser: Fix error flow in case of registration failure
  IB/iser: Generalize map/unmap dma tasks
  IB/iser: Use iser_fr_desc as registration context
  IB/iser: Remove iser_reg_data_sg helper function
  RDMA/rxe: Use standard names for ref counting
  RDMA/rxe: Replace red-black trees by xarrays
  RDMA/rxe: Shorten pool names in rxe_pool.c
  RDMA/rxe: Move max_elem into rxe_type_info
  RDMA/rxe: Replace obj by elem in declaration
  RDMA/rxe: Delete _locked() APIs for pool objects
  RDMA/rxe: Reverse the sense of RXE_POOL_NO_ALLOC
  RDMA/rxe: Replace mr by rkey in responder resources
  RDMA/rxe: Fix ref error in rxe_av.c
  RDMA/hns: Use the reserved loopback QPs to free MR before destroying MPT
  RDMA/irdma: Add support for address handle re-use
  RDMA/qib: Fix typos in comments
  RDMA/mlx5: Fix memory leak in error flow for subscribe event routine
  Revert "RDMA/core: Fix ib_qp_usecnt_dec() called when error"
  RDMA/rxe: Remove useless argument for update_state()
  ...

4 files changed, 25 insertions, 22 deletions

diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt-sysfs.c b/drivers/infiniband/ulp/rtrs/rtrs-clt-sysfs.c
index b4fa473b7888..d3c436ead694 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt-sysfs.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt-sysfs.c
@@ -156,8 +156,7 @@ static DEVICE_ATTR_RW(mpath_policy);
 static ssize_t add_path_show(struct device *dev,
 			     struct device_attribute *attr, char *page)
 {
-	return sysfs_emit(
-		page,
+	return sysfs_emit(page,
 		"Usage: echo [<source addr>@]<destination addr> > %s\n\n*addr ::= [ ip:<ipv4|ipv6> | gid:<gid> ]\n",
 		attr->attr.name);
 }
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
index 759b85f03331..c2c860d0c56e 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
@@ -297,6 +297,7 @@ static bool rtrs_clt_change_state_from_to(struct rtrs_clt_path *clt_path,
 	return changed;
 }
 
+static void rtrs_clt_stop_and_destroy_conns(struct rtrs_clt_path *clt_path);
 static void rtrs_rdma_error_recovery(struct rtrs_clt_con *con)
 {
 	struct rtrs_clt_path *clt_path = to_clt_path(con->c.path);
@@ -304,16 +305,7 @@ static void rtrs_rdma_error_recovery(struct rtrs_clt_con *con)
 	if (rtrs_clt_change_state_from_to(clt_path,
 					   RTRS_CLT_CONNECTED,
 					   RTRS_CLT_RECONNECTING)) {
-		struct rtrs_clt_sess *clt = clt_path->clt;
-		unsigned int delay_ms;
-
-		/*
-		 * Normal scenario, reconnect if we were successfully connected
-		 */
-		delay_ms = clt->reconnect_delay_sec * 1000;
-		queue_delayed_work(rtrs_wq, &clt_path->reconnect_dwork,
-				   msecs_to_jiffies(delay_ms +
-						    prandom_u32() % RTRS_RECONNECT_SEED));
+		queue_work(rtrs_wq, &clt_path->err_recovery_work);
 	} else {
 		/*
 		 * Error can happen just on establishing new connection,
@@ -917,7 +909,7 @@ static inline void path_it_deinit(struct path_it *it)
 {
 	struct list_head *skip, *tmp;
 	/*
-	 * The skip_list is used only for the MIN_INFLIGHT policy.
+	 * The skip_list is used only for the MIN_INFLIGHT and MIN_LATENCY policies.
 	 * We need to remove paths from it, so that next IO can insert
 	 * paths (->mp_skip_entry) into a skip_list again.
 	 */
@@ -1511,6 +1503,22 @@ static void rtrs_clt_init_hb(struct rtrs_clt_path *clt_path)
 static void rtrs_clt_reconnect_work(struct work_struct *work);
 static void rtrs_clt_close_work(struct work_struct *work);
 
+static void rtrs_clt_err_recovery_work(struct work_struct *work)
+{
+	struct rtrs_clt_path *clt_path;
+	struct rtrs_clt_sess *clt;
+	int delay_ms;
+
+	clt_path = container_of(work, struct rtrs_clt_path, err_recovery_work);
+	clt = clt_path->clt;
+	delay_ms = clt->reconnect_delay_sec * 1000;
+	rtrs_clt_stop_and_destroy_conns(clt_path);
+	queue_delayed_work(rtrs_wq, &clt_path->reconnect_dwork,
+			   msecs_to_jiffies(delay_ms +
+					    prandom_u32() %
+					    RTRS_RECONNECT_SEED));
+}
+
 static struct rtrs_clt_path *alloc_path(struct rtrs_clt_sess *clt,
 					const struct rtrs_addr *path,
 					size_t con_num, u32 nr_poll_queues)
@@ -1562,6 +1570,7 @@ static struct rtrs_clt_path *alloc_path(struct rtrs_clt_sess *clt,
 	clt_path->state = RTRS_CLT_CONNECTING;
 	atomic_set(&clt_path->connected_cnt, 0);
 	INIT_WORK(&clt_path->close_work, rtrs_clt_close_work);
+	INIT_WORK(&clt_path->err_recovery_work, rtrs_clt_err_recovery_work);
 	INIT_DELAYED_WORK(&clt_path->reconnect_dwork, rtrs_clt_reconnect_work);
 	rtrs_clt_init_hb(clt_path);
 
@@ -2326,6 +2335,7 @@ static void rtrs_clt_close_work(struct work_struct *work)
 
 	clt_path = container_of(work, struct rtrs_clt_path, close_work);
 
+	cancel_work_sync(&clt_path->err_recovery_work);
 	cancel_delayed_work_sync(&clt_path->reconnect_dwork);
 	rtrs_clt_stop_and_destroy_conns(clt_path);
 	rtrs_clt_change_state_get_old(clt_path, RTRS_CLT_CLOSED, NULL);
@@ -2638,7 +2648,6 @@ static void rtrs_clt_reconnect_work(struct work_struct *work)
 {
 	struct rtrs_clt_path *clt_path;
 	struct rtrs_clt_sess *clt;
-	unsigned int delay_ms;
 	int err;
 
 	clt_path = container_of(to_delayed_work(work), struct rtrs_clt_path,
@@ -2655,8 +2664,6 @@ static void rtrs_clt_reconnect_work(struct work_struct *work)
 	}
 	clt_path->reconnect_attempts++;
 
-	/* Stop everything */
-	rtrs_clt_stop_and_destroy_conns(clt_path);
 	msleep(RTRS_RECONNECT_BACKOFF);
 	if (rtrs_clt_change_state_get_old(clt_path, RTRS_CLT_CONNECTING, NULL)) {
 		err = init_path(clt_path);
@@ -2669,11 +2676,7 @@ static void rtrs_clt_reconnect_work(struct work_struct *work)
 reconnect_again:
 	if (rtrs_clt_change_state_get_old(clt_path, RTRS_CLT_RECONNECTING, NULL)) {
 		clt_path->stats->reconnects.fail_cnt++;
-		delay_ms = clt->reconnect_delay_sec * 1000;
-		queue_delayed_work(rtrs_wq, &clt_path->reconnect_dwork,
-				   msecs_to_jiffies(delay_ms +
-						    prandom_u32() %
-						    RTRS_RECONNECT_SEED));
+		queue_work(rtrs_wq, &clt_path->err_recovery_work);
 	}
 }
 
@@ -2908,6 +2911,7 @@ int rtrs_clt_reconnect_from_sysfs(struct rtrs_clt_path *clt_path)
 						 &old_state);
 	if (changed) {
 		clt_path->reconnect_attempts = 0;
+		rtrs_clt_stop_and_destroy_conns(clt_path);
 		queue_delayed_work(rtrs_wq, &clt_path->reconnect_dwork, 0);
 	}
 	if (changed || old_state == RTRS_CLT_RECONNECTING) {
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.h b/drivers/infiniband/ulp/rtrs/rtrs-clt.h
index d1b18a154ae0..f848c0392d98 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.h
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.h
@@ -134,6 +134,7 @@ struct rtrs_clt_path {
 	struct rtrs_clt_io_req	*reqs;
 	struct delayed_work	reconnect_dwork;
 	struct work_struct	close_work;
+	struct work_struct	err_recovery_work;
 	unsigned int		reconnect_attempts;
 	bool			established;
 	struct rtrs_rbuf	*rbufs;
diff --git a/drivers/infiniband/ulp/rtrs/rtrs.c b/drivers/infiniband/ulp/rtrs/rtrs.c
index 4da889103a5f..60fa0b0160f4 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs.c
@@ -479,7 +479,6 @@ static int rtrs_str_to_sockaddr(const char *addr, size_t len,
  */
 int sockaddr_to_str(const struct sockaddr *addr, char *buf, size_t len)
 {
-
 	switch (addr->sa_family) {
 	case AF_IB:
 		return scnprintf(buf, len, "gid:%pI6",