Message-Id: <20180327165919.17933-8-bjorn.topel@gmail.com>
Date:   Tue, 27 Mar 2018 18:59:12 +0200
From:   Björn Töpel <bjorn.topel@...il.com>
To:     bjorn.topel@...il.com, magnus.karlsson@...el.com,
        alexander.h.duyck@...el.com, alexander.duyck@...il.com,
        john.fastabend@...il.com, ast@...com, brouer@...hat.com,
        willemdebruijn.kernel@...il.com, daniel@...earbox.net,
        netdev@...r.kernel.org
Cc:     Björn Töpel <bjorn.topel@...el.com>,
        michael.lundkvist@...csson.com, jesse.brandeburg@...el.com,
        anjali.singhai@...el.com, qi.z.zhang@...el.com,
        ravineet.singh@...csson.com
Subject: [RFC PATCH v2 07/14] bpf: introduce new bpf AF_XDP map type BPF_MAP_TYPE_XSKMAP

From: Björn Töpel <bjorn.topel@...el.com>

The xskmap is yet another BPF map, very much inspired by
dev/cpu/sockmap, and is a holder of AF_XDP sockets. A user application
adds AF_XDP sockets into the map, and by using the bpf_redirect_map
helper, an XDP program can redirect XDP frames to an AF_XDP socket.

Note that a socket that is bound to certain ifindex/queue index will
*only* accept XDP frames from that netdev/queue index. If an XDP
program tries to redirect from a netdev/queue index other than what
the socket is bound to, the frame will not be received on the socket.

A socket can reside in multiple maps.

Signed-off-by: Björn Töpel <bjorn.topel@...el.com>
---
 include/linux/bpf.h       |  26 +++++
 include/linux/bpf_types.h |   3 +
 include/net/xdp_sock.h    |  34 ++++++
 include/uapi/linux/bpf.h  |   1 +
 kernel/bpf/Makefile       |   3 +
 kernel/bpf/verifier.c     |   8 +-
 kernel/bpf/xskmap.c       | 281 ++++++++++++++++++++++++++++++++++++++++++++++
 7 files changed, 354 insertions(+), 2 deletions(-)
 create mode 100644 include/net/xdp_sock.h
 create mode 100644 kernel/bpf/xskmap.c

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 819229c80eca..0fe9d080adc3 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -657,6 +657,32 @@ static inline int sock_map_prog(struct bpf_map *map,
 }
 #endif
 
+#if defined(CONFIG_XDP_SOCKETS)
+struct xdp_sock;
+struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key);
+int __xsk_map_redirect(struct bpf_map *map, u32 index,
+		       struct xdp_buff *xdp, struct xdp_sock *xs);
+void __xsk_map_flush(struct bpf_map *map);
+#else
+struct xdp_sock;
+static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
+						     u32 key)
+{
+	return NULL;
+}
+
+static inline int __xsk_map_redirect(struct bpf_map *map, u32 index,
+				     struct xdp_buff *xdp,
+				     struct xdp_sock *xs)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void __xsk_map_flush(struct bpf_map *map)
+{
+}
+#endif
+
 /* verifier prototypes for helper functions called from eBPF programs */
 extern const struct bpf_func_proto bpf_map_lookup_elem_proto;
 extern const struct bpf_func_proto bpf_map_update_elem_proto;
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 5e2e8a49fb21..b525862c98ab 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -47,4 +47,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops)
 #endif
 BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops)
+#if defined(CONFIG_XDP_SOCKETS)
+BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops)
+#endif
 #endif
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
new file mode 100644
index 000000000000..80d119a685b2
--- /dev/null
+++ b/include/net/xdp_sock.h
@@ -0,0 +1,34 @@
+/*
+ * AF_XDP internal functions
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.
+ */
+
+#ifndef _LINUX_XDP_SOCK_H
+#define _LINUX_XDP_SOCK_H
+
+struct xdp_sock;
+struct xdp_buff;
+#ifdef CONFIG_XDP_SOCKETS
+int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
+void xsk_flush(struct xdp_sock *xs);
+#else
+static inline int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
+{
+	return -ENOTSUPP;
+}
+
+static inline void xsk_flush(struct xdp_sock *xs)
+{
+}
+#endif /* CONFIG_XDP_SOCKETS */
+
+#endif /* _LINUX_XDP_SOCK_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 18b7c510c511..c8e1d2977712 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -114,6 +114,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_DEVMAP,
 	BPF_MAP_TYPE_SOCKMAP,
 	BPF_MAP_TYPE_CPUMAP,
+	BPF_MAP_TYPE_XSKMAP,
 };
 
 enum bpf_prog_type {
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index a713fd23ec88..3c59d9bcae14 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -7,6 +7,9 @@ obj-$(CONFIG_BPF_SYSCALL) += disasm.o
 ifeq ($(CONFIG_NET),y)
 obj-$(CONFIG_BPF_SYSCALL) += devmap.o
 obj-$(CONFIG_BPF_SYSCALL) += cpumap.o
+ifeq ($(CONFIG_XDP_SOCKETS),y)
+obj-$(CONFIG_BPF_SYSCALL) += xskmap.o
+endif
 obj-$(CONFIG_BPF_SYSCALL) += offload.o
 ifeq ($(CONFIG_STREAM_PARSER),y)
 ifeq ($(CONFIG_INET),y)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e9f7c20691c1..46d525539a3b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2059,8 +2059,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		if (func_id != BPF_FUNC_redirect_map)
 			goto error;
 		break;
-	/* Restrict bpf side of cpumap, open when use-cases appear */
+	/* Restrict bpf side of cpumap and xskmap, open when use-cases
+	 * appear.
+	 */
 	case BPF_MAP_TYPE_CPUMAP:
+	case BPF_MAP_TYPE_XSKMAP:
 		if (func_id != BPF_FUNC_redirect_map)
 			goto error;
 		break;
@@ -2107,7 +2110,8 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		break;
 	case BPF_FUNC_redirect_map:
 		if (map->map_type != BPF_MAP_TYPE_DEVMAP &&
-		    map->map_type != BPF_MAP_TYPE_CPUMAP)
+		    map->map_type != BPF_MAP_TYPE_CPUMAP &&
+		    map->map_type != BPF_MAP_TYPE_XSKMAP)
 			goto error;
 		break;
 	case BPF_FUNC_sk_redirect_map:
diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c
new file mode 100644
index 000000000000..77553f24daa2
--- /dev/null
+++ b/kernel/bpf/xskmap.c
@@ -0,0 +1,281 @@
+/*
+ * XSKMAP used for AF_XDP sockets
+ * Copyright(c) 2018 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.
+ */
+
+#include <linux/bpf.h>
+#include <linux/capability.h>
+#include <net/xdp_sock.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <net/sock.h>
+
+struct xsk_map_entry {
+	struct xdp_sock *xs;
+	struct rcu_head rcu;
+};
+
+struct xsk_map {
+	struct bpf_map map;
+	struct xsk_map_entry **xsk_map;
+	unsigned long __percpu *flush_needed;
+};
+
+static u64 xsk_map_bitmap_size(const union bpf_attr *attr)
+{
+	return BITS_TO_LONGS((u64) attr->max_entries) * sizeof(unsigned long);
+}
+
+static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
+{
+	struct xsk_map *m;
+	int err = -EINVAL;
+	u64 cost;
+
+	if (!capable(CAP_NET_ADMIN))
+		return ERR_PTR(-EPERM);
+
+	if (attr->max_entries == 0 || attr->key_size != 4 ||
+	    attr->value_size != 4 ||
+	    attr->map_flags & ~(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY))
+		return ERR_PTR(-EINVAL);
+
+	m = kzalloc(sizeof(*m), GFP_USER);
+	if (!m)
+		return ERR_PTR(-ENOMEM);
+
+	bpf_map_init_from_attr(&m->map, attr);
+
+	cost = (u64)m->map.max_entries * sizeof(struct xsk_map_entry *);
+	cost += xsk_map_bitmap_size(attr) * num_possible_cpus();
+	if (cost >= U32_MAX - PAGE_SIZE)
+		goto free_m;
+
+	m->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+	/* Notice returns -EPERM on if map size is larger than memlock limit */
+	err = bpf_map_precharge_memlock(m->map.pages);
+	if (err)
+		goto free_m;
+
+	m->flush_needed = __alloc_percpu(xsk_map_bitmap_size(attr),
+					    __alignof__(unsigned long));
+	if (!m->flush_needed)
+		goto free_m;
+
+	m->xsk_map = bpf_map_area_alloc(m->map.max_entries *
+					   sizeof(struct xsk_map_entry *),
+					   m->map.numa_node);
+	if (!m->xsk_map)
+		goto free_percpu;
+	return &m->map;
+
+free_percpu:
+	free_percpu(m->flush_needed);
+free_m:
+	kfree(m);
+	return ERR_PTR(err);
+}
+
+static void xsk_map_free(struct bpf_map *map)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	int i, cpu;
+
+	/* At this point bpf_prog->aux->refcnt == 0 and this
+	 * map->refcnt == 0, so the programs (can be more than one
+	 * that used this map) were disconnected from events. Wait for
+	 * outstanding critical sections in these programs to
+	 * complete. The rcu critical section only guarantees no
+	 * further reads against xsk_map. It does __not__ ensure
+	 * pending flush operations (if any) are complete.
+	 */
+
+	synchronize_rcu();
+
+	/* To ensure all pending flush operations have completed wait
+	 * for flush bitmap to indicate all flush_needed bits to be
+	 * zero on _all_ cpus.  Because the above synchronize_rcu()
+	 * ensures the map is disconnected from the program we can
+	 * assume no new bits will be set.
+	 */
+	for_each_online_cpu(cpu) {
+		unsigned long *bitmap = per_cpu_ptr(m->flush_needed, cpu);
+
+		while (!bitmap_empty(bitmap, map->max_entries))
+			cond_resched();
+	}
+
+	for (i = 0; i < map->max_entries; i++) {
+		struct xsk_map_entry *entry;
+
+		entry = m->xsk_map[i];
+		if (!entry)
+			continue;
+
+		sock_put((struct sock *)entry->xs);
+		kfree(entry);
+	}
+
+	free_percpu(m->flush_needed);
+	bpf_map_area_free(m->xsk_map);
+	kfree(m);
+}
+
+static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	u32 index = key ? *(u32 *)key : U32_MAX;
+	u32 *next = next_key;
+
+	if (index >= m->map.max_entries) {
+		*next = 0;
+		return 0;
+	}
+
+	if (index == m->map.max_entries - 1)
+		return -ENOENT;
+	*next = index + 1;
+	return 0;
+}
+
+struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	struct xsk_map_entry *entry;
+
+	if (key >= map->max_entries)
+		return NULL;
+
+	entry = READ_ONCE(m->xsk_map[key]);
+	return entry ? entry->xs : NULL;
+}
+
+int __xsk_map_redirect(struct bpf_map *map, u32 index,
+		       struct xdp_buff *xdp, struct xdp_sock *xs)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	unsigned long *bitmap = this_cpu_ptr(m->flush_needed);
+	int err;
+
+	err = xsk_rcv(xs, xdp);
+	if (err)
+		return err;
+
+	__set_bit(index, bitmap);
+	return 0;
+}
+
+void __xsk_map_flush(struct bpf_map *map)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	unsigned long *bitmap = this_cpu_ptr(m->flush_needed);
+	u32 bit;
+
+	for_each_set_bit(bit, bitmap, map->max_entries) {
+		struct xsk_map_entry *entry = READ_ONCE(m->xsk_map[bit]);
+
+		/* This is possible if the entry is removed by user
+		 * space between xdp redirect and flush op.
+		 */
+		if (unlikely(!entry))
+			continue;
+
+		__clear_bit(bit, bitmap);
+		xsk_flush(entry->xs);
+	}
+}
+
+static void *xsk_map_lookup_elem(struct bpf_map *map, void *key)
+{
+	return NULL;
+}
+
+static void __xsk_map_entry_free(struct rcu_head *rcu)
+{
+	struct xsk_map_entry *entry;
+
+	entry = container_of(rcu, struct xsk_map_entry, rcu);
+	xsk_flush(entry->xs);
+	sock_put((struct sock *)entry->xs);
+	kfree(entry);
+}
+
+static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
+			       u64 map_flags)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	struct xsk_map_entry *entry, *old_entry;
+	u32 i = *(u32 *)key, fd = *(u32 *)value;
+	struct socket *sock;
+	int err;
+
+	if (unlikely(map_flags > BPF_EXIST))
+		return -EINVAL;
+	if (unlikely(i >= m->map.max_entries))
+		return -E2BIG;
+	if (unlikely(map_flags == BPF_NOEXIST))
+		return -EEXIST;
+
+	sock = sockfd_lookup(fd, &err);
+	if (!sock)
+		return err;
+
+	if (sock->sk->sk_family != PF_XDP) {
+		sockfd_put(sock);
+		return -EOPNOTSUPP;
+	}
+
+	entry = kmalloc_node(sizeof(*entry), GFP_ATOMIC | __GFP_NOWARN,
+			     map->numa_node);
+	if (!entry) {
+		sockfd_put(sock);
+		return -ENOMEM;
+	}
+
+	sock_hold(sock->sk);
+	entry->xs = (struct xdp_sock *)sock->sk;
+
+	old_entry = xchg(&m->xsk_map[i], entry);
+	if (old_entry)
+		call_rcu(&old_entry->rcu, __xsk_map_entry_free);
+
+	sockfd_put(sock);
+	return 0;
+}
+
+static int xsk_map_delete_elem(struct bpf_map *map, void *key)
+{
+	struct xsk_map *m = container_of(map, struct xsk_map, map);
+	struct xsk_map_entry *old_entry;
+	int k = *(u32 *)key;
+
+	if (k >= map->max_entries)
+		return -EINVAL;
+
+	old_entry = xchg(&m->xsk_map[k], NULL);
+	if (old_entry)
+		call_rcu(&old_entry->rcu, __xsk_map_entry_free);
+
+	return 0;
+}
+
+const struct bpf_map_ops xsk_map_ops = {
+	.map_alloc = xsk_map_alloc,
+	.map_free = xsk_map_free,
+	.map_get_next_key = xsk_map_get_next_key,
+	.map_lookup_elem = xsk_map_lookup_elem,
+	.map_update_elem = xsk_map_update_elem,
+	.map_delete_elem = xsk_map_delete_elem,
+};
+
+
-- 
2.14.1

Powered by blists - more mailing lists