linux/include/net/xdp_sock.h
Magnus Karlsson f09ced4053 xsk: Fix race in SKB mode transmit with shared cq
Fix a race when multiple sockets are simultaneously calling sendto()
when the completion ring is shared in the SKB case. This is the case
when you share the same netdev and queue id through the
XDP_SHARED_UMEM bind flag. The problem is that multiple processes can
be in xsk_generic_xmit() and call the backpressure mechanism in
xskq_prod_reserve(xs->pool->cq). As this is a shared resource in this
specific scenario, a race might occur since the rings are
single-producer single-consumer.

Fix this by moving the tx_completion_lock from the socket to the pool
as the pool is shared between the sockets that share the completion
ring. (The pool is not shared when this is not the case.) And then
protect the accesses to xskq_prod_reserve() with this lock. The
tx_completion_lock is renamed cq_lock to better reflect that it
protects accesses to the potentially shared completion ring.

Fixes: 35fcde7f8d ("xsk: support for Tx")
Reported-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Link: https://lore.kernel.org/bpf/20201218134525.13119-2-magnus.karlsson@gmail.com
2020-12-18 16:10:21 +01:00

120 lines
2.4 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/* AF_XDP internal functions
* Copyright(c) 2018 Intel Corporation.
*/
#ifndef _LINUX_XDP_SOCK_H
#define _LINUX_XDP_SOCK_H
#include <linux/workqueue.h>
#include <linux/if_xdp.h>
#include <linux/mutex.h>
#include <linux/spinlock.h>
#include <linux/mm.h>
#include <net/sock.h>
struct net_device;
struct xsk_queue;
struct xdp_buff;
struct xdp_umem {
void *addrs;
u64 size;
u32 headroom;
u32 chunk_size;
u32 chunks;
u32 npgs;
struct user_struct *user;
refcount_t users;
u8 flags;
bool zc;
struct page **pgs;
int id;
struct list_head xsk_dma_list;
struct work_struct work;
};
struct xsk_map {
struct bpf_map map;
spinlock_t lock; /* Synchronize map updates */
struct xdp_sock *xsk_map[];
};
struct xdp_sock {
/* struct sock must be the first member of struct xdp_sock */
struct sock sk;
struct xsk_queue *rx ____cacheline_aligned_in_smp;
struct net_device *dev;
struct xdp_umem *umem;
struct list_head flush_node;
struct xsk_buff_pool *pool;
u16 queue_id;
bool zc;
enum {
XSK_READY = 0,
XSK_BOUND,
XSK_UNBOUND,
} state;
struct xsk_queue *tx ____cacheline_aligned_in_smp;
struct list_head tx_list;
/* Protects generic receive. */
spinlock_t rx_lock;
/* Statistics */
u64 rx_dropped;
u64 rx_queue_full;
struct list_head map_list;
/* Protects map_list */
spinlock_t map_list_lock;
/* Protects multiple processes in the control path */
struct mutex mutex;
struct xsk_queue *fq_tmp; /* Only as tmp storage before bind */
struct xsk_queue *cq_tmp; /* Only as tmp storage before bind */
};
#ifdef CONFIG_XDP_SOCKETS
int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp);
int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp);
void __xsk_map_flush(void);
static inline 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;
}
#else
static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
{
return -ENOTSUPP;
}
static inline int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp)
{
return -EOPNOTSUPP;
}
static inline void __xsk_map_flush(void)
{
}
static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
u32 key)
{
return NULL;
}
#endif /* CONFIG_XDP_SOCKETS */
#endif /* _LINUX_XDP_SOCK_H */