[PATCH 5.10 26/80] bpf: Add schedule points in batch ops

[Greg Kroah-Hartman]

From: Eric Dumazet <edumazet@xxxxxxxxxx>

commit 75134f16e7dd0007aa474b281935c5f42e79f2c8 upstream.

syzbot reported various soft lockups caused by bpf batch operations.

 INFO: task kworker/1:1:27 blocked for more than 140 seconds.
 INFO: task hung in rcu_barrier

Nothing prevents batch ops to process huge amount of data,
we need to add schedule points in them.

Note that maybe_wait_bpf_programs(map) calls from
generic_map_delete_batch() can be factorized by moving
the call after the loop.

This will be done later in -next tree once we get this fix merged,
unless there is strong opinion doing this optimization sooner.

Fixes: aa2e93b8e58e ("bpf: Add generic support for update and delete batch ops")
Fixes: cb4d03ab499d ("bpf: Add generic support for lookup batch op")
Reported-by: syzbot <syzkaller@xxxxxxxxxxxxxxxx>
Signed-off-by: Eric Dumazet <edumazet@xxxxxxxxxx>
Signed-off-by: Alexei Starovoitov <ast@xxxxxxxxxx>
Reviewed-by: Stanislav Fomichev <sdf@xxxxxxxxxx>
Acked-by: Brian Vazquez <brianvv@xxxxxxxxxx>
Link: https://lore.kernel.org/bpf/20220217181902.808742-1-eric.dumazet@xxxxxxxxx
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
 kernel/bpf/syscall.c |    3 +++
 1 file changed, 3 insertions(+)

--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1308,6 +1308,7 @@ int generic_map_delete_batch(struct bpf_
 		maybe_wait_bpf_programs(map);
 		if (err)
 			break;
+		cond_resched();
 	}
 	if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp)))
 		err = -EFAULT;
@@ -1365,6 +1366,7 @@ int generic_map_update_batch(struct bpf_
 
 		if (err)
 			break;
+		cond_resched();
 	}
 
 	if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp)))
@@ -1462,6 +1464,7 @@ int generic_map_lookup_batch(struct bpf_
 		swap(prev_key, key);
 		retry = MAP_LOOKUP_RETRIES;
 		cp++;
+		cond_resched();
 	}
 
 	if (err == -EFAULT)