netdev - [PATCH bpf 1/2] bpf: do not use bucket

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:   Wed, 2 Sep 2020 16:53:40 -0700
From:   Yonghong Song <yhs@...com>
To:     <bpf@...r.kernel.org>, Lorenz Bauer <lmb@...udflare.com>,
        Martin KaFai Lau <kafai@...com>, <netdev@...r.kernel.org>
CC:     Alexei Starovoitov <ast@...com>,
        Daniel Borkmann <daniel@...earbox.net>, <kernel-team@...com>
Subject: [PATCH bpf 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 <yhs@...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 78dfff6a501b..7df28a45c66b 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,
-- 
2.24.1