From e5c6d75b0f03958239c3d223472d00d54a6ea96a Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 14 May 2019 01:18:56 +0200 Subject: bpf, lru: avoid messing with eviction heuristics upon syscall lookup commit 50b045a8c0ccf44f76640ac3eea8d80ca53979a3 upstream. One of the biggest issues we face right now with picking LRU map over regular hash table is that a map walk out of user space, for example, to just dump the existing entries or to remove certain ones, will completely mess up LRU eviction heuristics and wrong entries such as just created ones will get evicted instead. The reason for this is that we mark an entry as "in use" via bpf_lru_node_set_ref() from system call lookup side as well. Thus upon walk, all entries are being marked, so information of actual least recently used ones are "lost". In case of Cilium where it can be used (besides others) as a BPF based connection tracker, this current behavior causes disruption upon control plane changes that need to walk the map from user space to evict certain entries. Discussion result from bpfconf [0] was that we should simply just remove marking from system call side as no good use case could be found where it's actually needed there. Therefore this patch removes marking for regular LRU and per-CPU flavor. If there ever should be a need in future, the behavior could be selected via map creation flag, but due to mentioned reason we avoid this here. [0] http://vger.kernel.org/bpfconf.html Fixes: 29ba732acbee ("bpf: Add BPF_MAP_TYPE_LRU_HASH") Fixes: 8f8449384ec3 ("bpf: Add BPF_MAP_TYPE_LRU_PERCPU_HASH") Signed-off-by: Daniel Borkmann Acked-by: Martin KaFai Lau Signed-off-by: Alexei Starovoitov Signed-off-by: Greg Kroah-Hartman --- kernel/bpf/hashtab.c | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index f9274114c88d..be5747a5337a 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -527,18 +527,30 @@ static u32 htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) return insn - insn_buf; } -static void *htab_lru_map_lookup_elem(struct bpf_map *map, void *key) +static __always_inline void *__htab_lru_map_lookup_elem(struct bpf_map *map, + void *key, const bool mark) { struct htab_elem *l = __htab_map_lookup_elem(map, key); if (l) { - bpf_lru_node_set_ref(&l->lru_node); + if (mark) + bpf_lru_node_set_ref(&l->lru_node); return l->key + round_up(map->key_size, 8); } return NULL; } +static void *htab_lru_map_lookup_elem(struct bpf_map *map, void *key) +{ + return __htab_lru_map_lookup_elem(map, key, true); +} + +static void *htab_lru_map_lookup_elem_sys(struct bpf_map *map, void *key) +{ + return __htab_lru_map_lookup_elem(map, key, false); +} + static u32 htab_lru_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { @@ -1215,6 +1227,7 @@ const struct bpf_map_ops htab_lru_map_ops = { .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, .map_lookup_elem = htab_lru_map_lookup_elem, + .map_lookup_elem_sys_only = htab_lru_map_lookup_elem_sys, .map_update_elem = htab_lru_map_update_elem, .map_delete_elem = htab_lru_map_delete_elem, .map_gen_lookup = htab_lru_map_gen_lookup, @@ -1246,7 +1259,6 @@ static void *htab_lru_percpu_map_lookup_elem(struct bpf_map *map, void *key) int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value) { - struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l; void __percpu *pptr; int ret = -ENOENT; @@ -1262,8 +1274,9 @@ int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value) l = __htab_map_lookup_elem(map, key); if (!l) goto out; - if (htab_is_lru(htab)) - bpf_lru_node_set_ref(&l->lru_node); + /* We do not mark LRU map element here in order to not mess up + * eviction heuristics when user space does a map walk. + */ pptr = htab_elem_get_ptr(l, map->key_size); for_each_possible_cpu(cpu) { bpf_long_memcpy(value + off, -- cgit v1.2.3