From dc0988bbe1bd41e2fa555e4a6f890b819a34b49b Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 2 Sep 2020 16:53:40 -0700 Subject: [PATCH 1/2] bpf: Do not use bucket_lock for hashmap iterator Currently, for hashmap, the bpf iterator will grab a bucket lock, a spinlock, before traversing the elements in the bucket. This can ensure all bpf visted elements are valid. But this mechanism may cause deadlock if update/deletion happens to the same bucket of the visited map in the program. For example, if we added bpf_map_update_elem() call to the same visited element in selftests bpf_iter_bpf_hash_map.c, we will have the following deadlock: ============================================ WARNING: possible recursive locking detected 5.9.0-rc1+ #841 Not tainted -------------------------------------------- test_progs/1750 is trying to acquire lock: ffff9a5bb73c5e70 (&htab->buckets[i].raw_lock){....}-{2:2}, at: htab_map_update_elem+0x1cf/0x410 but task is already holding lock: ffff9a5bb73c5e20 (&htab->buckets[i].raw_lock){....}-{2:2}, at: bpf_hash_map_seq_find_next+0x94/0x120 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&htab->buckets[i].raw_lock); lock(&htab->buckets[i].raw_lock); *** DEADLOCK *** ... Call Trace: dump_stack+0x78/0xa0 __lock_acquire.cold.74+0x209/0x2e3 lock_acquire+0xba/0x380 ? htab_map_update_elem+0x1cf/0x410 ? __lock_acquire+0x639/0x20c0 _raw_spin_lock_irqsave+0x3b/0x80 ? htab_map_update_elem+0x1cf/0x410 htab_map_update_elem+0x1cf/0x410 ? lock_acquire+0xba/0x380 bpf_prog_ad6dab10433b135d_dump_bpf_hash_map+0x88/0xa9c ? find_held_lock+0x34/0xa0 bpf_iter_run_prog+0x81/0x16e __bpf_hash_map_seq_show+0x145/0x180 bpf_seq_read+0xff/0x3d0 vfs_read+0xad/0x1c0 ksys_read+0x5f/0xe0 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xa9 ... The bucket_lock first grabbed in seq_ops->next() called by bpf_seq_read(), and then grabbed again in htab_map_update_elem() in the bpf program, causing deadlocks. Actually, we do not need bucket_lock here, we can just use rcu_read_lock() similar to netlink iterator where the rcu_read_{lock,unlock} likes below: seq_ops->start(): rcu_read_lock(); seq_ops->next(): rcu_read_unlock(); /* next element */ rcu_read_lock(); seq_ops->stop(); rcu_read_unlock(); Compared to old bucket_lock mechanism, if concurrent updata/delete happens, we may visit stale elements, miss some elements, or repeat some elements. I think this is a reasonable compromise. For users wanting to avoid stale, missing/repeated accesses, bpf_map batch access syscall interface can be used. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200902235340.2001375-1-yhs@fb.com --- kernel/bpf/hashtab.c | 15 ++++----------- 1 file changed, 4 insertions(+), 11 deletions(-) diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 78dfff6a501b96..7df28a45c66bf3 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -1622,7 +1622,6 @@ struct bpf_iter_seq_hash_map_info { struct bpf_map *map; struct bpf_htab *htab; void *percpu_value_buf; // non-zero means percpu hash - unsigned long flags; u32 bucket_id; u32 skip_elems; }; @@ -1632,7 +1631,6 @@ bpf_hash_map_seq_find_next(struct bpf_iter_seq_hash_map_info *info, struct htab_elem *prev_elem) { const struct bpf_htab *htab = info->htab; - unsigned long flags = info->flags; u32 skip_elems = info->skip_elems; u32 bucket_id = info->bucket_id; struct hlist_nulls_head *head; @@ -1656,19 +1654,18 @@ bpf_hash_map_seq_find_next(struct bpf_iter_seq_hash_map_info *info, /* not found, unlock and go to the next bucket */ b = &htab->buckets[bucket_id++]; - htab_unlock_bucket(htab, b, flags); + rcu_read_unlock(); skip_elems = 0; } for (i = bucket_id; i < htab->n_buckets; i++) { b = &htab->buckets[i]; - flags = htab_lock_bucket(htab, b); + rcu_read_lock(); count = 0; head = &b->head; hlist_nulls_for_each_entry_rcu(elem, n, head, hash_node) { if (count >= skip_elems) { - info->flags = flags; info->bucket_id = i; info->skip_elems = count; return elem; @@ -1676,7 +1673,7 @@ bpf_hash_map_seq_find_next(struct bpf_iter_seq_hash_map_info *info, count++; } - htab_unlock_bucket(htab, b, flags); + rcu_read_unlock(); skip_elems = 0; } @@ -1754,14 +1751,10 @@ static int bpf_hash_map_seq_show(struct seq_file *seq, void *v) static void bpf_hash_map_seq_stop(struct seq_file *seq, void *v) { - struct bpf_iter_seq_hash_map_info *info = seq->private; - if (!v) (void)__bpf_hash_map_seq_show(seq, NULL); else - htab_unlock_bucket(info->htab, - &info->htab->buckets[info->bucket_id], - info->flags); + rcu_read_unlock(); } static int bpf_iter_init_hash_map(void *priv_data, From 4daab7132731ac5ec9384c8a070cdb9607dc38c8 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Wed, 2 Sep 2020 16:53:41 -0700 Subject: [PATCH 2/2] selftests/bpf: Add bpf_{update, delete}_map_elem in hashmap iter program Added bpf_{updata,delete}_map_elem to the very map element the iter program is visiting. Due to rcu protection, the visited map elements, although stale, should still contain correct values. $ ./test_progs -n 4/18 #4/18 bpf_hash_map:OK #4 bpf_iter:OK Summary: 1/1 PASSED, 0 SKIPPED, 0 FAILED Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200902235341.2001534-1-yhs@fb.com --- .../selftests/bpf/progs/bpf_iter_bpf_hash_map.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c index 07ddbfdbcab706..6dfce3fd68bc85 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c @@ -47,7 +47,10 @@ int dump_bpf_hash_map(struct bpf_iter__bpf_map_elem *ctx) __u32 seq_num = ctx->meta->seq_num; struct bpf_map *map = ctx->map; struct key_t *key = ctx->key; + struct key_t tmp_key; __u64 *val = ctx->value; + __u64 tmp_val = 0; + int ret; if (in_test_mode) { /* test mode is used by selftests to @@ -61,6 +64,18 @@ int dump_bpf_hash_map(struct bpf_iter__bpf_map_elem *ctx) if (key == (void *)0 || val == (void *)0) return 0; + /* update the value and then delete the pair. + * it should not impact the existing 'val' which is still + * accessible under rcu. + */ + __builtin_memcpy(&tmp_key, key, sizeof(struct key_t)); + ret = bpf_map_update_elem(&hashmap1, &tmp_key, &tmp_val, 0); + if (ret) + return 0; + ret = bpf_map_delete_elem(&hashmap1, &tmp_key); + if (ret) + return 0; + key_sum_a += key->a; key_sum_b += key->b; key_sum_c += key->c;