Merge branch 'fixes for bpf map iterator'

Hou Tao says:

====================

From: Hou Tao <houtao1@huawei.com>

Hi,

The patchset constitues three fixes for bpf map iterator:

(1) patch 1~4: fix user-after-free during reading map iterator fd
It is possible when both the corresponding link fd and map fd are
closed bfore reading the iterator fd. I had squashed these four patches
into one, but it was not friendly for stable backport, so I break these
fixes into four single patches in the end. Patch 7 is its testing patch.

(2) patch 5: fix invalidity check for values in sk local storage map
Patch 8 adds two tests for it.

(3) patch 6: reject sleepable program for non-resched map iterator
Patch 9 add a test for it.

Please check the individual patches for more details. And comments are
always welcome.

Regards,
Tao

Changes since v2:
* patch 1~6: update commit messages (from Yonghong & Martin)
* patch 7: add more detailed comments (from Yonghong)
* patch 8: use NULL directly instead of (void *)0

v1: https://lore.kernel.org/bpf/20220806074019.2756957-1-houtao@huaweicloud.com
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

3 files changed, 18 insertions, 1 deletions

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index d3e734bf8056..624527401d4d 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -649,6 +649,11 @@ static int bpf_iter_init_array_map(void *priv_data,
 		seq_info->percpu_value_buf = value_buf;
 	}
 
+	/* bpf_iter_attach_map() acquires a map uref, and the uref may be
+	 * released before or in the middle of iterating map elements, so
+	 * acquire an extra map uref for iterator.
+	 */
+	bpf_map_inc_with_uref(map);
 	seq_info->map = map;
 	return 0;
 }
@@ -657,6 +662,7 @@ static void bpf_iter_fini_array_map(void *priv_data)
 {
 	struct bpf_iter_seq_array_map_info *seq_info = priv_data;
 
+	bpf_map_put_with_uref(seq_info->map);
 	kfree(seq_info->percpu_value_buf);
 }
 
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 2726a5950cfa..24b755eca0b3 100644
--- 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;
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 4d793a92301b..6c530a5e560a 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -2060,6 +2060,7 @@ static int bpf_iter_init_hash_map(void *priv_data,
 		seq_info->percpu_value_buf = value_buf;
 	}
 
+	bpf_map_inc_with_uref(map);
 	seq_info->map = map;
 	seq_info->htab = container_of(map, struct bpf_htab, map);
 	return 0;
@@ -2069,6 +2070,7 @@ static void bpf_iter_fini_hash_map(void *priv_data)
 {
 	struct bpf_iter_seq_hash_map_info *seq_info = priv_data;
 
+	bpf_map_put_with_uref(seq_info->map);
 	kfree(seq_info->percpu_value_buf);
 }