From 2872e9ac33a4440173418147351ed4f93177e763 Mon Sep 17 00:00:00 2001 From: Andrey Ignatov Date: Fri, 19 Jun 2020 14:11:44 -0700 Subject: bpf: Set map_btf_{name, id} for all map types Set map_btf_name and map_btf_id for all map types so that map fields can be accessed by bpf programs. Signed-off-by: Andrey Ignatov Signed-off-by: Daniel Borkmann Acked-by: John Fastabend Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/a825f808f22af52b018dbe82f1c7d29dab5fc978.1592600985.git.rdna@fb.com --- kernel/bpf/reuseport_array.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel/bpf/reuseport_array.c') diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c index 21cde24386db..a09922f656e4 100644 --- a/kernel/bpf/reuseport_array.c +++ b/kernel/bpf/reuseport_array.c @@ -345,6 +345,7 @@ static int reuseport_array_get_next_key(struct bpf_map *map, void *key, return 0; } +static int reuseport_array_map_btf_id; const struct bpf_map_ops reuseport_array_ops = { .map_alloc_check = reuseport_array_alloc_check, .map_alloc = reuseport_array_alloc, @@ -352,4 +353,6 @@ const struct bpf_map_ops reuseport_array_ops = { .map_lookup_elem = reuseport_array_lookup_elem, .map_get_next_key = reuseport_array_get_next_key, .map_delete_elem = reuseport_array_delete_elem, + .map_btf_name = "reuseport_array", + .map_btf_id = &reuseport_array_map_btf_id, }; -- cgit v1.2.3 From bba1dc0b55ac462d24ed1228ad49800c238cd6d7 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 29 Jun 2020 21:33:39 -0700 Subject: bpf: Remove redundant synchronize_rcu. bpf_free_used_maps() or close(map_fd) will trigger map_free callback. bpf_free_used_maps() is called after bpf prog is no longer executing: bpf_prog_put->call_rcu->bpf_prog_free->bpf_free_used_maps. Hence there is no need to call synchronize_rcu() to protect map elements. Note that hash_of_maps and array_of_maps update/delete inner maps via sys_bpf() that calls maybe_wait_bpf_programs() and synchronize_rcu(). Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Acked-by: Paul E. McKenney Link: https://lore.kernel.org/bpf/20200630043343.53195-2-alexei.starovoitov@gmail.com --- kernel/bpf/arraymap.c | 9 --------- kernel/bpf/hashtab.c | 8 +++----- kernel/bpf/lpm_trie.c | 5 ----- kernel/bpf/queue_stack_maps.c | 7 ------- kernel/bpf/reuseport_array.c | 2 -- kernel/bpf/ringbuf.c | 7 ------- kernel/bpf/stackmap.c | 3 --- 7 files changed, 3 insertions(+), 38 deletions(-) (limited to 'kernel/bpf/reuseport_array.c') diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index ec5cd11032aa..c66e8273fccd 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -386,13 +386,6 @@ static void array_map_free(struct bpf_map *map) { struct bpf_array *array = container_of(map, struct bpf_array, map); - /* 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 programs to complete - * and free the array - */ - synchronize_rcu(); - if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) bpf_array_free_percpu(array); @@ -546,8 +539,6 @@ static void fd_array_map_free(struct bpf_map *map) struct bpf_array *array = container_of(map, struct bpf_array, map); int i; - synchronize_rcu(); - /* make sure it's empty */ for (i = 0; i < array->map.max_entries; i++) BUG_ON(array->ptrs[i] != NULL); diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index acd06081d81d..d4378d7d442b 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -1290,12 +1290,10 @@ static void htab_map_free(struct bpf_map *map) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); - /* 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 + /* bpf_free_used_maps() or close(map_fd) will trigger this map_free callback. + * bpf_free_used_maps() is called after bpf prog is no longer executing. + * There is no need to synchronize_rcu() here to protect map elements. */ - synchronize_rcu(); /* some of free_htab_elem() callbacks for elements of this map may * not have executed. Wait for them. diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 1abd4e3f906d..44474bf3ab7a 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -589,11 +589,6 @@ static void trie_free(struct bpf_map *map) struct lpm_trie_node __rcu **slot; struct lpm_trie_node *node; - /* Wait for outstanding programs to complete - * update/lookup/delete/get_next_key and free the trie. - */ - synchronize_rcu(); - /* Always start at the root and walk down to a node that has no * children. Then free that node, nullify its reference in the parent * and start over. diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c index 80c66a6d7c54..44184f82916a 100644 --- a/kernel/bpf/queue_stack_maps.c +++ b/kernel/bpf/queue_stack_maps.c @@ -101,13 +101,6 @@ static void queue_stack_map_free(struct bpf_map *map) { struct bpf_queue_stack *qs = bpf_queue_stack(map); - /* 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 - */ - synchronize_rcu(); - bpf_map_area_free(qs); } diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c index a09922f656e4..3625c4fcc65c 100644 --- a/kernel/bpf/reuseport_array.c +++ b/kernel/bpf/reuseport_array.c @@ -96,8 +96,6 @@ static void reuseport_array_free(struct bpf_map *map) struct sock *sk; u32 i; - synchronize_rcu(); - /* * ops->map_*_elem() will not be able to access this * array now. Hence, this function only races with diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index dbf37aff4827..13a8d3967e07 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -215,13 +215,6 @@ static void ringbuf_map_free(struct bpf_map *map) { struct bpf_ringbuf_map *rb_map; - /* 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 - */ - synchronize_rcu(); - rb_map = container_of(map, struct bpf_ringbuf_map, map); bpf_ringbuf_free(rb_map->rb); kfree(rb_map); diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 27dc9b1b08a5..071f98d0f7c6 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -604,9 +604,6 @@ static void stack_map_free(struct bpf_map *map) { struct bpf_stack_map *smap = container_of(map, struct bpf_stack_map, map); - /* wait for bpf programs to complete before freeing stack map */ - synchronize_rcu(); - bpf_map_area_free(smap->elems); pcpu_freelist_destroy(&smap->freelist); bpf_map_area_free(smap); -- cgit v1.2.3 From f3dda7a679df183e798b86e7b6ec05ab35476de3 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 8 Jul 2020 23:11:04 -0700 Subject: bpf: net: Avoid copying sk_user_data of reuseport_array during sk_clone It makes little sense for copying sk_user_data of reuseport_array during sk_clone_lock(). This patch reuses the SK_USER_DATA_NOCOPY bit introduced in commit f1ff5ce2cd5e ("net, sk_msg: Clear sk_user_data pointer on clone if tagged"). It is used to mark the sk_user_data is not supposed to be copied to its clone. Although the cloned sk's sk_user_data will not be used/freed in bpf_sk_reuseport_detach(), this change can still allow the cloned sk's sk_user_data to be used by some other means. Freeing the reuseport_array's sk_user_data does not require a rcu grace period. Thus, the existing rcu_assign_sk_user_data_nocopy() is not used. Fixes: 5dc4c4b7d4e8 ("bpf: Introduce BPF_MAP_TYPE_REUSEPORT_SOCKARRAY") Signed-off-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20200709061104.4018798-1-kafai@fb.com --- kernel/bpf/reuseport_array.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'kernel/bpf/reuseport_array.c') diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c index 21cde24386db..a95bc8d7e812 100644 --- a/kernel/bpf/reuseport_array.c +++ b/kernel/bpf/reuseport_array.c @@ -20,11 +20,14 @@ static struct reuseport_array *reuseport_array(struct bpf_map *map) /* The caller must hold the reuseport_lock */ void bpf_sk_reuseport_detach(struct sock *sk) { - struct sock __rcu **socks; + uintptr_t sk_user_data; write_lock_bh(&sk->sk_callback_lock); - socks = sk->sk_user_data; - if (socks) { + sk_user_data = (uintptr_t)sk->sk_user_data; + if (sk_user_data) { + struct sock __rcu **socks; + + socks = (void *)(sk_user_data & SK_USER_DATA_PTRMASK); WRITE_ONCE(sk->sk_user_data, NULL); /* * Do not move this NULL assignment outside of @@ -252,6 +255,7 @@ int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, struct sock *free_osk = NULL, *osk, *nsk; struct sock_reuseport *reuse; u32 index = *(u32 *)key; + uintptr_t sk_user_data; struct socket *socket; int err, fd; @@ -305,7 +309,8 @@ int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, if (err) goto put_file_unlock; - WRITE_ONCE(nsk->sk_user_data, &array->ptrs[index]); + sk_user_data = (uintptr_t)&array->ptrs[index] | SK_USER_DATA_NOCOPY; + WRITE_ONCE(nsk->sk_user_data, (void *)sk_user_data); rcu_assign_pointer(array->ptrs[index], nsk); free_osk = osk; err = 0; -- cgit v1.2.3 From c9a368f1c0fbe2e3a21ebf231caeae58b18b2681 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Wed, 8 Jul 2020 23:11:10 -0700 Subject: bpf: net: Avoid incorrect bpf_sk_reuseport_detach call bpf_sk_reuseport_detach is currently called when sk->sk_user_data is not NULL. It is incorrect because sk->sk_user_data may not be managed by the bpf's reuseport_array. It has been reported in [1] that, the bpf_sk_reuseport_detach() which is called from udp_lib_unhash() has corrupted the sk_user_data managed by l2tp. This patch solves it by using another bit (defined as SK_USER_DATA_BPF) of the sk_user_data pointer value. It marks that a sk_user_data is managed/owned by BPF. The patch depends on a PTRMASK introduced in commit f1ff5ce2cd5e ("net, sk_msg: Clear sk_user_data pointer on clone if tagged"). [ Note: sk->sk_user_data is used by bpf's reuseport_array only when a sk is added to the bpf's reuseport_array. i.e. doing setsockopt(SO_REUSEPORT) and having "sk->sk_reuseport == 1" alone will not stop sk->sk_user_data being used by other means. ] [1]: https://lore.kernel.org/netdev/20200706121259.GA20199@katalix.com/ Fixes: 5dc4c4b7d4e8 ("bpf: Introduce BPF_MAP_TYPE_REUSEPORT_SOCKARRAY") Reported-by: James Chapman Reported-by: syzbot+9f092552ba9a5efca5df@syzkaller.appspotmail.com Signed-off-by: Martin KaFai Lau Signed-off-by: Daniel Borkmann Tested-by: James Chapman Acked-by: James Chapman Link: https://lore.kernel.org/bpf/20200709061110.4019316-1-kafai@fb.com --- include/net/sock.h | 3 ++- kernel/bpf/reuseport_array.c | 5 +++-- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'kernel/bpf/reuseport_array.c') diff --git a/include/net/sock.h b/include/net/sock.h index 3428619faae4..1183507df95b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -533,7 +533,8 @@ enum sk_pacing { * be copied. */ #define SK_USER_DATA_NOCOPY 1UL -#define SK_USER_DATA_PTRMASK ~(SK_USER_DATA_NOCOPY) +#define SK_USER_DATA_BPF 2UL /* Managed by BPF */ +#define SK_USER_DATA_PTRMASK ~(SK_USER_DATA_NOCOPY | SK_USER_DATA_BPF) /** * sk_user_data_is_nocopy - Test if sk_user_data pointer must not be copied diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c index a95bc8d7e812..cae9d505e04a 100644 --- a/kernel/bpf/reuseport_array.c +++ b/kernel/bpf/reuseport_array.c @@ -24,7 +24,7 @@ void bpf_sk_reuseport_detach(struct sock *sk) write_lock_bh(&sk->sk_callback_lock); sk_user_data = (uintptr_t)sk->sk_user_data; - if (sk_user_data) { + if (sk_user_data & SK_USER_DATA_BPF) { struct sock __rcu **socks; socks = (void *)(sk_user_data & SK_USER_DATA_PTRMASK); @@ -309,7 +309,8 @@ int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, if (err) goto put_file_unlock; - sk_user_data = (uintptr_t)&array->ptrs[index] | SK_USER_DATA_NOCOPY; + sk_user_data = (uintptr_t)&array->ptrs[index] | SK_USER_DATA_NOCOPY | + SK_USER_DATA_BPF; WRITE_ONCE(nsk->sk_user_data, (void *)sk_user_data); rcu_assign_pointer(array->ptrs[index], nsk); free_osk = osk; -- cgit v1.2.3