From: Björn Töpel <bjorn.to...@intel.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.
v2: Removed one indirection in map lookup.
Signed-off-by: Björn Töpel <bjorn.to...@intel.com>
---
include/linux/bpf.h | 26 +++++
include/linux/bpf_types.h | 3 +
include/net/xdp_sock.h | 7 ++
include/uapi/linux/bpf.h | 1 +
kernel/bpf/Makefile | 3 +
kernel/bpf/verifier.c | 8 +-
kernel/bpf/xskmap.c | 272 ++++++++++++++++++++++++++++++++++++++++++++++
net/xdp/xsk.c | 5 +
8 files changed, 323 insertions(+), 2 deletions(-)
create mode 100644 kernel/bpf/xskmap.c
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 38ebbc61ed99..6b62509777a2 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -676,6 +676,32 @@ 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 2b28fcf6f6ae..d7df1b323082 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -49,4 +49,7 @@ 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
index ea54483f64bb..678a1d293579 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -28,6 +28,7 @@ struct xdp_sock {
struct xsk_queue *rx;
struct net_device *dev;
struct xdp_umem *umem;
+ struct rcu_head rcu;
u64 rx_dropped;
u16 queue_id;
/* Protects multiple processes in the control path */
@@ -39,6 +40,7 @@ struct xdp_buff;
int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
void xsk_flush(struct xdp_sock *xs);
+bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs);
#else
static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
{
@@ -53,6 +55,11 @@ static inline int xsk_rcv(struct xdp_sock *xs, struct
xdp_buff *xdp)
static inline void xsk_flush(struct xdp_sock *xs)
{
}
+
+static inline bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
+{
+ return false;
+}
#endif /* CONFIG_XDP_SOCKETS */
#endif /* _LINUX_XDP_SOCK_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index da77a9388947..7c16bc197ff5 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -116,6 +116,7 @@ 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 35c485fa9ea3..f27f5496d6fe 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -8,6 +8,9 @@ obj-$(CONFIG_BPF_SYSCALL) += btf.o
ifeq ($(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 eb1a596aebd3..0ac49d62dc0c 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2061,8 +2061,11 @@ 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;
@@ -2109,7 +2112,8 @@ 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..eb60824af070
--- /dev/null
+++ b/kernel/bpf/xskmap.c
@@ -0,0 +1,272 @@
+// SPDX-License-Identifier: GPL-2.0
+/* 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>
+
+struct xsk_map {
+ struct bpf_map map;
+ struct xdp_sock **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 xdp_sock *);
+ 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 xdp_sock *),
+ 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 xdp_sock *xs;
+
+ xs = m->xsk_map[i];
+ if (!xs)
+ continue;
+
+ sock_put((struct sock *)xs);
+ }
+
+ 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 xdp_sock *xs;
+
+ if (key >= map->max_entries)
+ return NULL;
+
+ xs = READ_ONCE(m->xsk_map[key]);
+ return xs;
+}
+
+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 xdp_sock *xs = 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(!xs))
+ continue;
+
+ __clear_bit(bit, bitmap);
+ xsk_flush(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 xdp_sock *xs;
+
+ xs = container_of(rcu, struct xdp_sock, rcu);
+ xsk_flush(xs);
+ sock_put((struct sock *)xs);
+}
+
+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);
+ u32 i = *(u32 *)key, fd = *(u32 *)value;
+ struct xdp_sock *xs, *old_xs;
+ 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;
+ }
+
+ xs = (struct xdp_sock *)sock->sk;
+
+ if (!xsk_is_setup_for_bpf_map(xs)) {
+ sockfd_put(sock);
+ return -EOPNOTSUPP;
+ }
+
+ sock_hold(sock->sk);
+
+ old_xs = xchg(&m->xsk_map[i], xs);
+ if (old_xs)
+ call_rcu(&old_xs->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 xdp_sock *old_xs;
+ int k = *(u32 *)key;
+
+ if (k >= map->max_entries)
+ return -EINVAL;
+
+ old_xs = xchg(&m->xsk_map[k], NULL);
+ if (old_xs)
+ call_rcu(&old_xs->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,
+};
+
+
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 4e1e6c581e1d..b931a0db5588 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -41,6 +41,11 @@ static struct xdp_sock *xdp_sk(struct sock *sk)
return (struct xdp_sock *)sk;
}
+bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
+{
+ return !!xs->rx;
+}
+
static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
{
u32 *id, len = xdp->data_end - xdp->data;
--
2.14.1
