bpf: Only allow sleepable program for resched-able iterator

When a sleepable program is attached to a hash map iterator, might_fault()
will report "BUG: sleeping function called from invalid context..." if
CONFIG_DEBUG_ATOMIC_SLEEP is enabled. The reason is that rcu_read_lock()
is held in bpf_hash_map_seq_next() and won't be released until all elements
are traversed or bpf_hash_map_seq_stop() is called.

Fixing it by reusing BPF_ITER_RESCHED to indicate that only non-sleepable
program is allowed for iterator without BPF_ITER_RESCHED. We can revise
bpf_iter_link_attach() later if there are other conditions which may
cause rcu_read_lock() or spin_lock() issues.

Signed-off-by: Hou Tao <houtao1@huawei.com>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/r/20220810080538.1845898-7-houtao@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 2726a5950cfa69dd0beaa8cf13a5b625a5275f1c..24b755eca0b393320db530bf98ba9158cba5e3b3 100644 (file)
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -68,13 +68,18 @@ static void bpf_iter_done_stop(struct seq_file *seq)
        iter_priv->done_stop = true;
 }
 
+static inline bool bpf_iter_target_support_resched(const struct bpf_iter_target_info *tinfo)
+{
+       return tinfo->reg_info->feature & BPF_ITER_RESCHED;
+}
+
 static bool bpf_iter_support_resched(struct seq_file *seq)
 {
        struct bpf_iter_priv_data *iter_priv;
 
        iter_priv = container_of(seq->private, struct bpf_iter_priv_data,
                                 target_private);
-       return iter_priv->tinfo->reg_info->feature & BPF_ITER_RESCHED;
+       return bpf_iter_target_support_resched(iter_priv->tinfo);
 }
 
 /* maximum visited objects before bailing out */
@@ -537,6 +542,10 @@ int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr,
        if (!tinfo)
                return -ENOENT;
 
+       /* Only allow sleepable program for resched-able iterator */
+       if (prog->aux->sleepable && !bpf_iter_target_support_resched(tinfo))
+               return -EINVAL;
+
        link = kzalloc(sizeof(*link), GFP_USER | __GFP_NOWARN);
        if (!link)
                return -ENOMEM;