Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/jesse/openvswitch

Jesse Gross says:

====================
Open vSwitch

A set of updates for net-next/3.13. Major changes are:
 * Restructure flow handling code to be more logically organized and
   easier to read.
 * Rehashing of the flow table is moved from a workqueue to flow
   installation time. Before, heavy load could block the workqueue for
   excessive periods of time.
 * Additional debugging information is provided to help diagnose megaflows.
 * It's now possible to match on TCP flags.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 592 insertions, 0 deletions

diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
new file mode 100644
index 000000000000..e42542706087
--- /dev/null
+++ b/net/openvswitch/flow_table.c
@@ -0,0 +1,592 @@
+/*
+ * Copyright (c) 2007-2013 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#include "flow.h"
+#include "datapath.h"
+#include <linux/uaccess.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <net/llc_pdu.h>
+#include <linux/kernel.h>
+#include <linux/jhash.h>
+#include <linux/jiffies.h>
+#include <linux/llc.h>
+#include <linux/module.h>
+#include <linux/in.h>
+#include <linux/rcupdate.h>
+#include <linux/if_arp.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/sctp.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/icmp.h>
+#include <linux/icmpv6.h>
+#include <linux/rculist.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/ndisc.h>
+
+#include "datapath.h"
+
+#define TBL_MIN_BUCKETS         1024
+#define REHASH_INTERVAL         (10 * 60 * HZ)
+
+static struct kmem_cache *flow_cache;
+
+static u16 range_n_bytes(const struct sw_flow_key_range *range)
+{
+        return range->end - range->start;
+}
+
+void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
+                       const struct sw_flow_mask *mask)
+{
+        const long *m = (long *)((u8 *)&mask->key + mask->range.start);
+        const long *s = (long *)((u8 *)src + mask->range.start);
+        long *d = (long *)((u8 *)dst + mask->range.start);
+        int i;
+
+        /* The memory outside of the 'mask->range' are not set since
+         * further operations on 'dst' only uses contents within
+         * 'mask->range'.
+         */
+        for (i = 0; i < range_n_bytes(&mask->range); i += sizeof(long))
+                *d++ = *s++ & *m++;
+}
+
+struct sw_flow *ovs_flow_alloc(void)
+{
+        struct sw_flow *flow;
+
+        flow = kmem_cache_alloc(flow_cache, GFP_KERNEL);
+        if (!flow)
+                return ERR_PTR(-ENOMEM);
+
+        spin_lock_init(&flow->lock);
+        flow->sf_acts = NULL;
+        flow->mask = NULL;
+
+        return flow;
+}
+
+int ovs_flow_tbl_count(struct flow_table *table)
+{
+        return table->count;
+}
+
+static struct flex_array *alloc_buckets(unsigned int n_buckets)
+{
+        struct flex_array *buckets;
+        int i, err;
+
+        buckets = flex_array_alloc(sizeof(struct hlist_head),
+                                   n_buckets, GFP_KERNEL);
+        if (!buckets)
+                return NULL;
+
+        err = flex_array_prealloc(buckets, 0, n_buckets, GFP_KERNEL);
+        if (err) {
+                flex_array_free(buckets);
+                return NULL;
+        }
+
+        for (i = 0; i < n_buckets; i++)
+                INIT_HLIST_HEAD((struct hlist_head *)
+                                        flex_array_get(buckets, i));
+
+        return buckets;
+}
+
+static void flow_free(struct sw_flow *flow)
+{
+        kfree((struct sf_flow_acts __force *)flow->sf_acts);
+        kmem_cache_free(flow_cache, flow);
+}
+
+static void rcu_free_flow_callback(struct rcu_head *rcu)
+{
+        struct sw_flow *flow = container_of(rcu, struct sw_flow, rcu);
+
+        flow_free(flow);
+}
+
+static void rcu_free_sw_flow_mask_cb(struct rcu_head *rcu)
+{
+        struct sw_flow_mask *mask = container_of(rcu, struct sw_flow_mask, rcu);
+
+        kfree(mask);
+}
+
+static void flow_mask_del_ref(struct sw_flow_mask *mask, bool deferred)
+{
+        if (!mask)
+                return;
+
+        BUG_ON(!mask->ref_count);
+        mask->ref_count--;
+
+        if (!mask->ref_count) {
+                list_del_rcu(&mask->list);
+                if (deferred)
+                        call_rcu(&mask->rcu, rcu_free_sw_flow_mask_cb);
+                else
+                        kfree(mask);
+        }
+}
+
+void ovs_flow_free(struct sw_flow *flow, bool deferred)
+{
+        if (!flow)
+                return;
+
+        flow_mask_del_ref(flow->mask, deferred);
+
+        if (deferred)
+                call_rcu(&flow->rcu, rcu_free_flow_callback);
+        else
+                flow_free(flow);
+}
+
+static void free_buckets(struct flex_array *buckets)
+{
+        flex_array_free(buckets);
+}
+
+static void __table_instance_destroy(struct table_instance *ti)
+{
+        int i;
+
+        if (ti->keep_flows)
+                goto skip_flows;
+
+        for (i = 0; i < ti->n_buckets; i++) {
+                struct sw_flow *flow;
+                struct hlist_head *head = flex_array_get(ti->buckets, i);
+                struct hlist_node *n;
+                int ver = ti->node_ver;
+
+                hlist_for_each_entry_safe(flow, n, head, hash_node[ver]) {
+                        hlist_del(&flow->hash_node[ver]);
+                        ovs_flow_free(flow, false);
+                }
+        }
+
+skip_flows:
+        free_buckets(ti->buckets);