Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Another merge window, another set of networking changes.  I've heard
  rumblings that the lightweight tunnels infrastructure has been voted
  networking change of the year.  But what do I know?

   1) Add conntrack support to openvswitch, from Joe Stringer.

   2) Initial support for VRF (Virtual Routing and Forwarding), which
      allows the segmentation of routing paths without using multiple
      devices.  There are some semantic kinks to work out still, but
      this is a reasonably strong foundation.  From David Ahern.

   3) Remove spinlock fro act_bpf fast path, from Alexei Starovoitov.

   4) Ignore route nexthops with a link down state in ipv6, just like
      ipv4.  From Andy Gospodarek.

   5) Remove spinlock from fast path of act_gact and act_mirred, from
      Eric Dumazet.

   6) Document the DSA layer, from Florian Fainelli.

   7) Add netconsole support to bcmgenet, systemport, and DSA.  Also
      from Florian Fainelli.

   8) Add Mellanox Switch Driver and core infrastructure, from Jiri
      Pirko.

   9) Add support for "light weight tunnels", which allow for
      encapsulation and decapsulation without bearing the overhead of a
      full blown netdevice.  From Thomas Graf, Jiri Benc, and a cast of
      others.

  10) Add Identifier Locator Addressing support for ipv6, from Tom
      Herbert.

  11) Support fragmented SKBs in iwlwifi, from Johannes Berg.

  12) Allow perf PMUs to be accessed from eBPF programs, from Kaixu Xia.

  13) Add BQL support to 3c59x driver, from Loganaden Velvindron.

  14) Stop using a zero TX queue length to mean that a device shouldn't
      have a qdisc attached, use an explicit flag instead.  From Phil
      Sutter.

  15) Use generic geneve netdevice infrastructure in openvswitch, from
      Pravin B Shelar.

  16) Add infrastructure to avoid re-forwarding a packet in software
      that was already forwarded by a hardware switch.  From Scott
      Feldman.

  17) Allow AF_PACKET fanout function to be implemented in a bpf
      program, from Willem de Bruijn"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1458 commits)
  netfilter: nf_conntrack: make nf_ct_zone_dflt built-in
  netfilter: nf_dup{4, 6}: fix build error when nf_conntrack disabled
  net: fec: clear receive interrupts before processing a packet
  ipv6: fix exthdrs offload registration in out_rt path
  xen-netback: add support for multicast control
  bgmac: Update fixed_phy_register()
  sock, diag: fix panic in sock_diag_put_filterinfo
  flow_dissector: Use 'const' where possible.
  flow_dissector: Fix function argument ordering dependency
  ixgbe: Resolve "initialized field overwritten" warnings
  ixgbe: Remove bimodal SR-IOV disabling
  ixgbe: Add support for reporting 2.5G link speed
  ixgbe: fix bounds checking in ixgbe_setup_tc for 82598
  ixgbe: support for ethtool set_rxfh
  ixgbe: Avoid needless PHY access on copper phys
  ixgbe: cleanup to use cached mask value
  ixgbe: Remove second instance of lan_id variable
  ixgbe: use kzalloc for allocating one thing
  flow: Move __get_hash_from_flowi{4,6} into flow_dissector.c
  ixgbe: Remove unused PCI bus types
  ...

1 files changed, 42 insertions, 15 deletions

diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index 657ba9f..251d1ce 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -83,6 +83,25 @@ struct rds_ib_mr_pool {
 	struct ib_fmr_attr	fmr_attr;
 };
 
+struct workqueue_struct *rds_ib_fmr_wq;
+
+int rds_ib_fmr_init(void)
+{
+	rds_ib_fmr_wq = create_workqueue("rds_fmr_flushd");
+	if (!rds_ib_fmr_wq)
+		return -ENOMEM;
+	return 0;
+}
+
+/* By the time this is called all the IB devices should have been torn down and
+ * had their pools freed.  As each pool is freed its work struct is waited on,
+ * so the pool flushing work queue should be idle by the time we get here.
+ */
+void rds_ib_fmr_exit(void)
+{
+	destroy_workqueue(rds_ib_fmr_wq);
+}
+
 static int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool, int free_all, struct rds_ib_mr **);
 static void rds_ib_teardown_mr(struct rds_ib_mr *ibmr);
 static void rds_ib_mr_pool_flush_worker(struct work_struct *work);
@@ -151,12 +170,17 @@ int rds_ib_update_ipaddr(struct rds_ib_device *rds_ibdev, __be32 ipaddr)
 	struct rds_ib_device *rds_ibdev_old;
 
 	rds_ibdev_old = rds_ib_get_device(ipaddr);
-	if (rds_ibdev_old) {
+	if (!rds_ibdev_old)
+		return rds_ib_add_ipaddr(rds_ibdev, ipaddr);
+
+	if (rds_ibdev_old != rds_ibdev) {
 		rds_ib_remove_ipaddr(rds_ibdev_old, ipaddr);
 		rds_ib_dev_put(rds_ibdev_old);
+		return rds_ib_add_ipaddr(rds_ibdev, ipaddr);
 	}
+	rds_ib_dev_put(rds_ibdev_old);
 
-	return rds_ib_add_ipaddr(rds_ibdev, ipaddr);
+	return 0;
 }
 
 void rds_ib_add_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn)
@@ -336,8 +360,6 @@ static struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *rds_ibdev)
 		goto out_no_cigar;
 	}
 
-	memset(ibmr, 0, sizeof(*ibmr));
-
 	ibmr->fmr = ib_alloc_fmr(rds_ibdev->pd,
 			(IB_ACCESS_LOCAL_WRITE |
 			 IB_ACCESS_REMOTE_READ |
@@ -485,7 +507,7 @@ static void __rds_ib_teardown_mr(struct rds_ib_mr *ibmr)
 
 			/* FIXME we need a way to tell a r/w MR
 			 * from a r/o MR */
-			BUG_ON(irqs_disabled());
+			WARN_ON(!page->mapping && irqs_disabled());
 			set_page_dirty(page);
 			put_page(page);
 		}
@@ -523,11 +545,13 @@ static inline unsigned int rds_ib_flush_goal(struct rds_ib_mr_pool *pool, int fr
 /*
  * given an llist of mrs, put them all into the list_head for more processing
  */
-static void llist_append_to_list(struct llist_head *llist, struct list_head *list)
+static unsigned int llist_append_to_list(struct llist_head *llist,
+					 struct list_head *list)
 {
 	struct rds_ib_mr *ibmr;
 	struct llist_node *node;
 	struct llist_node *next;
+	unsigned int count = 0;
 
 	node = llist_del_all(llist);
 	while (node) {
@@ -535,7 +559,9 @@ static void llist_append_to_list(struct llist_head *llist, struct list_head *lis
 		ibmr = llist_entry(node, struct rds_ib_mr, llnode);
 		list_add_tail(&ibmr->unmap_list, list);
 		node = next;
+		count++;
 	}
+	return count;
 }
 
 /*
@@ -576,7 +602,7 @@ static int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool,
 	LIST_HEAD(unmap_list);
 	LIST_HEAD(fmr_list);
 	unsigned long unpinned = 0;
-	unsigned int nfreed = 0, ncleaned = 0, free_goal;
+	unsigned int nfreed = 0, dirty_to_clean = 0, free_goal;
 	int ret = 0;
 
 	rds_ib_stats_inc(s_ib_rdma_mr_pool_flush);
@@ -618,8 +644,8 @@ static int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool,
 	/* Get the list of all MRs to be dropped. Ordering matters -
 	 * we want to put drop_list ahead of free_list.
 	 */
-	llist_append_to_list(&pool->drop_list, &unmap_list);
-	llist_append_to_list(&pool->free_list, &unmap_list);
+	dirty_to_clean = llist_append_to_list(&pool->drop_list, &unmap_list);
+	dirty_to_clean += llist_append_to_list(&pool->free_list, &unmap_list);
 	if (free_all)
 		llist_append_to_list(&pool->clean_list, &unmap_list);
 
@@ -647,7 +673,6 @@ static int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool,
 			kfree(ibmr);
 			nfreed++;
 		}
-		ncleaned++;
 	}
 
 	if (!list_empty(&unmap_list)) {
@@ -673,7 +698,7 @@ static int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool,
 	}
 
 	atomic_sub(unpinned, &pool->free_pinned);
-	atomic_sub(ncleaned, &pool->dirty_count);
+	atomic_sub(dirty_to_clean, &pool->dirty_count);
 	atomic_sub(nfreed, &pool->item_count);
 
 out:
@@ -710,16 +735,18 @@ void rds_ib_free_mr(void *trans_private, int invalidate)
 
 	/* If we've pinned too many pages, request a flush */
 	if (atomic_read(&pool->free_pinned) >= pool->max_free_pinned ||
-	    atomic_read(&pool->dirty_count) >= pool->max_items / 10)
-		schedule_delayed_work(&pool->flush_worker, 10);
+	    atomic_read(&pool->dirty_count) >= pool->max_items / 5)
+		queue_delayed_work(rds_ib_fmr_wq, &pool->flush_worker, 10);
 
 	if (invalidate) {
 		if (likely(!in_interrupt())) {
 			rds_ib_flush_mr_pool(pool, 0, NULL);
 		} else {
 			/* We get here if the user created a MR marked
-			 * as use_once and invalidate at the same time. */
-			schedule_delayed_work(&pool->flush_worker, 10);
+			 * as use_once and invalidate at the same time.
+			 */
+			queue_delayed_work(rds_ib_fmr_wq,
+					   &pool->flush_worker, 10);
 		}
 	}