diff mbox series

[bpf,1/2] bpf: do not use bucket_lock for hashmap iterator

Message ID 20200902235340.2001375-1-yhs@fb.com
State New
Headers show
Series [bpf,1/2] bpf: do not use bucket_lock for hashmap iterator | expand

Commit Message

Yonghong Song Sept. 2, 2020, 11:53 p.m. UTC
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@fb.com>
---
 kernel/bpf/hashtab.c | 15 ++++-----------
 1 file changed, 4 insertions(+), 11 deletions(-)

Comments

Yonghong Song Sept. 3, 2020, 2:44 a.m. UTC | #1
On 9/2/20 6:25 PM, Andrii Nakryiko wrote:
> On Wed, Sep 2, 2020 at 4:56 PM Yonghong Song <yhs@fb.com> wrote:
>>
>> 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:
>>
> 
> [...]
> 
>>
>> 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
> 
> I agree, the only reliable way to iterate map without duplicates and
> missed elements is to not update that map during iteration (unless we
> start supporting point-in-time snapshots, which is a very different
> matter).
> 
> 
>> stale, missing/repeated accesses, bpf_map batch access syscall interface
>> can be used.
>>
>> Signed-off-by: Yonghong Song <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 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();
> 
> Just double checking as I don't yet completely understand all the
> sleepable BPF implications. If the map is used from a sleepable BPF
> program, we are still ok doing just rcu_read_lock/rcu_read_unlock when
> accessing BPF map elements, right? No need for extra
> rcu_read_lock_trace/rcu_read_unlock_trace?
I think it is fine now since currently bpf_iter program cannot be 
sleepable and the current sleepable program framework already allows the 
following scenario.
   - map1 is a preallocated hashmap shared by two programs,
     prog1_nosleep and prog2_sleepable

...				  ...
rcu_read_lock()			  rcu_read_lock_trace()
run prog1_nosleep                 run prog2_sleepable
   lookup/update/delete map1 elem    lookup/update/delete map1 elem
rcu_read_unlock()		  rcu_read_unlock_trace()
...				  ...

The prog1_nosleep could be a bpf_iter program or a networking problem.

Alexei, could you confirm the above scenario is properly supported now?

> 
>>                  skip_elems = 0;
>>          }
>>
> 
> [...]
>
diff mbox series

Patch

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,