782347b6bc
XDP_REDIRECT works by a three-step process: the bpf_redirect() and bpf_redirect_map() helpers will lookup the target of the redirect and store it (along with some other metadata) in a per-CPU struct bpf_redirect_info. Next, when the program returns the XDP_REDIRECT return code, the driver will call xdp_do_redirect() which will use the information thus stored to actually enqueue the frame into a bulk queue structure (that differs slightly by map type, but shares the same principle). Finally, before exiting its NAPI poll loop, the driver will call xdp_do_flush(), which will flush all the different bulk queues, thus completing the redirect. Pointers to the map entries will be kept around for this whole sequence of steps, protected by RCU. However, there is no top-level rcu_read_lock() in the core code; instead drivers add their own rcu_read_lock() around the XDP portions of the code, but somewhat inconsistently as Martin discovered[0]. However, things still work because everything happens inside a single NAPI poll sequence, which means it's between a pair of calls to local_bh_disable()/local_bh_enable(). So Paul suggested[1] that we could document this intention by using rcu_dereference_check() with rcu_read_lock_bh_held() as a second parameter, thus allowing sparse and lockdep to verify that everything is done correctly. This patch does just that: we add an __rcu annotation to the map entry pointers and remove the various comments explaining the NAPI poll assurance strewn through devmap.c in favour of a longer explanation in filter.c. The goal is to have one coherent documentation of the entire flow, and rely on the RCU annotations as a "standard" way of communicating the flow in the map code (which can additionally be understood by sparse and lockdep). The RCU annotation replacements result in a fairly straight-forward replacement where READ_ONCE() becomes rcu_dereference_check(), WRITE_ONCE() becomes rcu_assign_pointer() and xchg() and cmpxchg() gets wrapped in the proper constructs to cast the pointer back and forth between __rcu and __kernel address space (for the benefit of sparse). The one complication is that xskmap has a few constructions where double-pointers are passed back and forth; these simply all gain __rcu annotations, and only the final reference/dereference to the inner-most pointer gets changed. With this, everything can be run through sparse without eliciting complaints, and lockdep can verify correctness even without the use of rcu_read_lock() in the drivers. Subsequent patches will clean these up from the drivers. [0] https://lore.kernel.org/bpf/20210415173551.7ma4slcbqeyiba2r@kafai-mbp.dhcp.thefacebook.com/ [1] https://lore.kernel.org/bpf/20210419165837.GA975577@paulmck-ThinkPad-P17-Gen-1/ Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20210624160609.292325-6-toke@redhat.com
49 lines
1.2 KiB
C
49 lines
1.2 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/* Copyright(c) 2019 Intel Corporation. */
|
|
|
|
#ifndef XSK_H_
|
|
#define XSK_H_
|
|
|
|
/* Masks for xdp_umem_page flags.
|
|
* The low 12-bits of the addr will be 0 since this is the page address, so we
|
|
* can use them for flags.
|
|
*/
|
|
#define XSK_NEXT_PG_CONTIG_SHIFT 0
|
|
#define XSK_NEXT_PG_CONTIG_MASK BIT_ULL(XSK_NEXT_PG_CONTIG_SHIFT)
|
|
|
|
struct xdp_ring_offset_v1 {
|
|
__u64 producer;
|
|
__u64 consumer;
|
|
__u64 desc;
|
|
};
|
|
|
|
struct xdp_mmap_offsets_v1 {
|
|
struct xdp_ring_offset_v1 rx;
|
|
struct xdp_ring_offset_v1 tx;
|
|
struct xdp_ring_offset_v1 fr;
|
|
struct xdp_ring_offset_v1 cr;
|
|
};
|
|
|
|
/* Nodes are linked in the struct xdp_sock map_list field, and used to
|
|
* track which maps a certain socket reside in.
|
|
*/
|
|
|
|
struct xsk_map_node {
|
|
struct list_head node;
|
|
struct xsk_map *map;
|
|
struct xdp_sock __rcu **map_entry;
|
|
};
|
|
|
|
static inline struct xdp_sock *xdp_sk(struct sock *sk)
|
|
{
|
|
return (struct xdp_sock *)sk;
|
|
}
|
|
|
|
void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
|
|
struct xdp_sock __rcu **map_entry);
|
|
void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id);
|
|
int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool,
|
|
u16 queue_id);
|
|
|
|
#endif /* XSK_H_ */
|