Message-ID: <155075021399.13610.12521373406832889226.stgit@alrua-x1>
Date:   Thu, 21 Feb 2019 12:56:54 +0100
From:   Toke Høiland-Jørgensen <toke@...hat.com>
To:     David Miller <davem@...emloft.net>
Cc:     netdev@...r.kernel.org, Jesper Dangaard Brouer <brouer@...hat.com>,
        Daniel Borkmann <daniel@...earbox.net>,
        Alexei Starovoitov <ast@...nel.org>
Subject: [PATCH net-next 1/2] xdp: Always use a devmap for XDP_REDIRECT to a
 device

An XDP program can redirect packets between interfaces using either the
xdp_redirect() helper or the xdp_redirect_map() helper. Apart from the
flexibility of updating maps from userspace, the redirect_map() helper also
uses the map structure to batch packets, which results in a significant
(around 50%) performance boost. However, the xdp_redirect() API is simpler
if one just wants to redirect to another interface, which means people tend
to use this interface and then wonder why they getter worse performance
than expected.

This patch seeks to close this performance difference between the two APIs.
It achieves this by changing xdp_redirect() to use a hidden devmap for
looking up destination interfaces, thus gaining the batching benefit with
no visible difference from the user API point of view.

A hidden per-namespace map is allocated when an XDP program that uses the
non-map xdp_redirect() helper is first loaded. This map is populated with
all available interfaces in its namespace, and kept up to date as
interfaces come and go. Once allocated, the map is kept around until the
namespace is removed.

The hidden map uses the ifindex as map key, which means they are limited to
ifindexes smaller than the map size of 64. A later patch introduces a new
map type to lift this restriction.

Performance numbers:

Before patch:
xdp_redirect:     5426035 pkt/s
xdp_redirect_map: 8412754 pkt/s

After patch:
xdp_redirect:     8314702 pkt/s
xdp_redirect_map: 8411854 pkt/s

This corresponds to a 53% increase in xdp_redirect performance, or a
reduction in per-packet processing time by 64 nanoseconds.

Signed-off-by: Toke Høiland-Jørgensen <toke@...hat.com>
---
 include/linux/bpf.h         |   12 +++
 include/net/net_namespace.h |    2 -
 include/net/netns/xdp.h     |    5 +
 kernel/bpf/devmap.c         |  159 +++++++++++++++++++++++++++++++++++--------
 kernel/bpf/verifier.c       |    6 ++
 net/core/filter.c           |   58 +---------------
 6 files changed, 157 insertions(+), 85 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index bd169a7bcc93..4f8f179df9fd 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -606,6 +606,8 @@ struct xdp_buff;
 struct sk_buff;
 
 struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key);
+struct bpf_map *__dev_map_get_default_map(struct net_device *dev);
+int dev_map_alloc_default_map(void);
 void __dev_map_insert_ctx(struct bpf_map *map, u32 index);
 void __dev_map_flush(struct bpf_map *map);
 int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
@@ -687,6 +689,16 @@ static inline struct net_device  *__dev_map_lookup_elem(struct bpf_map *map,
 	return NULL;
 }
 
+static inline struct bpf_map *__dev_map_get_default_map(struct net_device *dev)
+{
+	return NULL;
+}
+
+static inline int dev_map_alloc_default_map(void)
+{
+	return 0;
+}
+
 static inline void __dev_map_insert_ctx(struct bpf_map *map, u32 index)
 {
 }
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index a68ced28d8f4..6706ecc25d8f 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -162,7 +162,7 @@ struct net {
 #if IS_ENABLED(CONFIG_CAN)
 	struct netns_can	can;
 #endif
-#ifdef CONFIG_XDP_SOCKETS
+#ifdef CONFIG_BPF_SYSCALL
 	struct netns_xdp	xdp;
 #endif
 	struct sock		*diag_nlsk;
diff --git a/include/net/netns/xdp.h b/include/net/netns/xdp.h
index e5734261ba0a..4e2d6394b45d 100644
--- a/include/net/netns/xdp.h
+++ b/include/net/netns/xdp.h
@@ -5,9 +5,14 @@
 #include <linux/rculist.h>
 #include <linux/mutex.h>
 
+struct bpf_dtab;
+
 struct netns_xdp {
+#ifdef CONFIG_XDP_SOCKETS
 	struct mutex		lock;
 	struct hlist_head	list;
+#endif
+	struct bpf_dtab	*default_map;
 };
 
 #endif /* __NETNS_XDP_H__ */
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 191b79948424..425077664ac6 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -56,6 +56,7 @@
 	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
 
 #define DEV_MAP_BULK_SIZE 16
+#define DEV_MAP_DEFAULT_SIZE 64
 struct xdp_bulk_queue {
 	struct xdp_frame *q[DEV_MAP_BULK_SIZE];
 	struct net_device *dev_rx;
@@ -85,23 +86,11 @@ static u64 dev_map_bitmap_size(const union bpf_attr *attr)
 	return BITS_TO_LONGS((u64) attr->max_entries) * sizeof(unsigned long);
 }
 
-static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
+static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr,
+			    bool check_memlock)
 {
-	struct bpf_dtab *dtab;
-	int err = -EINVAL;
 	u64 cost;
-
-	if (!capable(CAP_NET_ADMIN))
-		return ERR_PTR(-EPERM);
-
-	/* check sanity of attributes */
-	if (attr->max_entries == 0 || attr->key_size != 4 ||
-	    attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK)
-		return ERR_PTR(-EINVAL);
-
-	dtab = kzalloc(sizeof(*dtab), GFP_USER);
-	if (!dtab)
-		return ERR_PTR(-ENOMEM);
+	int err;
 
 	bpf_map_init_from_attr(&dtab->map, attr);
 
@@ -109,39 +98,63 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
 	cost = (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *);
 	cost += dev_map_bitmap_size(attr) * num_possible_cpus();
 	if (cost >= U32_MAX - PAGE_SIZE)
-		goto free_dtab;
+		return -EINVAL;
 
 	dtab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
 
-	/* if map size is larger than memlock limit, reject it early */
-	err = bpf_map_precharge_memlock(dtab->map.pages);
-	if (err)
-		goto free_dtab;
-
-	err = -ENOMEM;
+	if (check_memlock) {
+		/* if map size is larger than memlock limit, reject it early */
+		err = bpf_map_precharge_memlock(dtab->map.pages);
+		if (err)
+			return -EINVAL;
+	}
 
 	/* A per cpu bitfield with a bit per possible net device */
 	dtab->flush_needed = __alloc_percpu_gfp(dev_map_bitmap_size(attr),
 						__alignof__(unsigned long),
 						GFP_KERNEL | __GFP_NOWARN);
 	if (!dtab->flush_needed)
-		goto free_dtab;
+		return -ENOMEM;
 
 	dtab->netdev_map = bpf_map_area_alloc(dtab->map.max_entries *
 					      sizeof(struct bpf_dtab_netdev *),
 					      dtab->map.numa_node);
-	if (!dtab->netdev_map)
-		goto free_dtab;
+	if (!dtab->netdev_map) {
+		free_percpu(dtab->flush_needed);
+		return -ENOMEM;
+	}
 
 	spin_lock(&dev_map_lock);
 	list_add_tail_rcu(&dtab->list, &dev_map_list);
 	spin_unlock(&dev_map_lock);
 
+	return 0;
+}
+
+static struct bpf_map *dev_map_alloc(union bpf_attr *attr)
+{
+	struct bpf_dtab *dtab;
+	int err = -EINVAL;
+
+	if (!capable(CAP_NET_ADMIN))
+		return ERR_PTR(-EPERM);
+
+	/* check sanity of attributes */
+	if (attr->max_entries == 0 || attr->key_size != 4 ||
+	    attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK)
+		return ERR_PTR(-EINVAL);
+
+	dtab = kzalloc(sizeof(*dtab), GFP_USER);
+	if (!dtab)
+		return ERR_PTR(-ENOMEM);
+
+	err = dev_map_init_map(dtab, attr, true);
+	if (err) {
+		kfree(dtab);
+		return ERR_PTR(err);
+	}
+
 	return &dtab->map;
-free_dtab:
-	free_percpu(dtab->flush_needed);
-	kfree(dtab);
-	return ERR_PTR(err);
 }
 
 static void dev_map_free(struct bpf_map *map)
@@ -311,6 +324,17 @@ struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
 	return obj;
 }
 
+/* This is only being called from xdp_do_redirect() if the xdp_redirect helper
+ * is used; the default map is allocated on XDP program load if the helper is
+ * used, so will always be available at this point.
+ */
+struct bpf_map *__dev_map_get_default_map(struct net_device *dev)
+{
+	struct net *net = dev_net(dev);
+
+	return &net->xdp.default_map->map;
+}
+
 /* Runs under RCU-read-side, plus in softirq under NAPI protection.
  * Thus, safe percpu variable access.
  */
@@ -496,10 +520,19 @@ static int dev_map_notification(struct notifier_block *notifier,
 				ulong event, void *ptr)
 {
 	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+	struct net *net = dev_net(netdev);
+	u32 idx = netdev->ifindex;
 	struct bpf_dtab *dtab;
 	int i;
 
 	switch (event) {
+	case NETDEV_REGISTER:
+		rcu_read_lock();
+		dtab = READ_ONCE(net->xdp.default_map);
+		if (dtab)
+			dev_map_update_elem(&dtab->map, &idx, &idx, 0);
+		rcu_read_unlock();
+		break;
 	case NETDEV_UNREGISTER:
 		/* This rcu_read_lock/unlock pair is needed because
 		 * dev_map_list is an RCU list AND to ensure a delete
@@ -528,16 +561,84 @@ static int dev_map_notification(struct notifier_block *notifier,
 	return NOTIFY_OK;
 }
 
+static void __net_exit dev_map_net_exit(struct net *net)
+{
+	struct bpf_dtab *dtab;
+
+	dtab = xchg(&net->xdp.default_map, NULL);
+	if (dtab)
+		dev_map_free(&dtab->map);
+}
+
 static struct notifier_block dev_map_notifier = {
 	.notifier_call = dev_map_notification,
 };
 
+static struct pernet_operations dev_map_net_ops = {
+	.exit = dev_map_net_exit,
+};
+
+int dev_map_alloc_default_map(void)
+{
+	struct net *net = current->nsproxy->net_ns;
+	struct bpf_dtab *dtab, *old_dtab;
+	struct net_device *netdev;
+	union bpf_attr attr = {};
+	u32 idx;
+	int err;
+
+	if (READ_ONCE(net->xdp.default_map))
+		return 0;
+
+	dtab = kzalloc(sizeof(*net->xdp.default_map), GFP_USER);
+	if (!dtab)
+		return -ENOMEM;
+
+	attr.max_entries = DEV_MAP_DEFAULT_SIZE;
+	attr.map_type = BPF_MAP_TYPE_DEVMAP;
+	attr.value_size = 4;
+	attr.key_size = 4;
+
+	err = dev_map_init_map(dtab, &attr, false);
+	if (err) {
+		kfree(dtab);
+		return err;
+	}
+
+	for_each_netdev(net, netdev) {
+		if (netdev->ifindex < DEV_MAP_DEFAULT_SIZE) {
+			idx = netdev->ifindex;
+			err = dev_map_update_elem(&dtab->map, &idx, &idx, 0);
+			if (err) {
+				dev_map_free(&dtab->map);
+				return err;
+			}
+		}
+	}
+
+	old_dtab = xchg(&net->xdp.default_map, dtab);
+	if (old_dtab)
+		dev_map_free(&old_dtab->map);
+
+	return 0;
+}
+
 static int __init dev_map_init(void)
 {
+	int err;
+
 	/* Assure tracepoint shadow struct _bpf_dtab_netdev is in sync */
 	BUILD_BUG_ON(offsetof(struct bpf_dtab_netdev, dev) !=
 		     offsetof(struct _bpf_dtab_netdev, dev));
+
 	register_netdevice_notifier(&dev_map_notifier);
+
+	err = register_pernet_subsys(&dev_map_net_ops);
+	if (err) {
+		unregister_netdevice_notifier(&dev_map_notifier);
+		return err;
+	}
+
 	return 0;
 }
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index b63bc77af2d1..629661db36ee 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -7527,6 +7527,12 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
 			prog->dst_needed = 1;
 		if (insn->imm == BPF_FUNC_get_prandom_u32)
 			bpf_user_rnd_init_once();
+		if (insn->imm == BPF_FUNC_redirect) {
+			int err = dev_map_alloc_default_map();
+
+			if (err)
+				return err;
+		}
 		if (insn->imm == BPF_FUNC_override_return)
 			prog->kprobe_override = 1;
 		if (insn->imm == BPF_FUNC_tail_call) {
diff --git a/net/core/filter.c b/net/core/filter.c
index b5a002d7b263..c709b1468bb6 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3326,58 +3326,6 @@ static const struct bpf_func_proto bpf_xdp_adjust_meta_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
-static int __bpf_tx_xdp(struct net_device *dev,
-			struct bpf_map *map,
-			struct xdp_buff *xdp,
-			u32 index)
-{
-	struct xdp_frame *xdpf;
-	int err, sent;
-
-	if (!dev->netdev_ops->ndo_xdp_xmit) {
-		return -EOPNOTSUPP;
-	}
-
-	err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
-	if (unlikely(err))
-		return err;
-
-	xdpf = convert_to_xdp_frame(xdp);
-	if (unlikely(!xdpf))
-		return -EOVERFLOW;
-
-	sent = dev->netdev_ops->ndo_xdp_xmit(dev, 1, &xdpf, XDP_XMIT_FLUSH);
-	if (sent <= 0)
-		return sent;
-	return 0;
-}
-
-static noinline int
-xdp_do_redirect_slow(struct net_device *dev, struct xdp_buff *xdp,
-		     struct bpf_prog *xdp_prog, struct bpf_redirect_info *ri)
-{
-	struct net_device *fwd;
-	u32 index = ri->ifindex;
-	int err;
-
-	fwd = dev_get_by_index_rcu(dev_net(dev), index);
-	ri->ifindex = 0;
-	if (unlikely(!fwd)) {
-		err = -EINVAL;
-		goto err;
-	}
-
-	err = __bpf_tx_xdp(fwd, NULL, xdp, 0);
-	if (unlikely(err))
-		goto err;
-
-	_trace_xdp_redirect(dev, xdp_prog, index);
-	return 0;
-err:
-	_trace_xdp_redirect_err(dev, xdp_prog, index, err);
-	return err;
-}
-
 static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
 			    struct bpf_map *map,
 			    struct xdp_buff *xdp,
@@ -3508,10 +3456,10 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 	struct bpf_map *map = READ_ONCE(ri->map);
 
-	if (likely(map))
-		return xdp_do_redirect_map(dev, xdp, xdp_prog, map, ri);
+	if (unlikely(!map))
+		map = __dev_map_get_default_map(dev);
 
-	return xdp_do_redirect_slow(dev, xdp, xdp_prog, ri);
+	return xdp_do_redirect_map(dev, xdp, xdp_prog, map, ri);
 }
 EXPORT_SYMBOL_GPL(xdp_do_redirect);
 

Powered by blists - more mailing lists