[RFC PATCH bpf-next v3 3/7] bpf: add lookup_and_delete map operation

[Mauricio Vasquez B <mauricio.vasquez@polito.it>]

The following patch implements a bpf queue/stack maps that
provides the peek/pop/push functions.  There is not a direct
relationship between those functions and the current operations
supported by a map, hence a new lookup_and_delete map operation
is added, this operation would be used by the pop helper.

A pop operation is not added because it will too specific to
stack/queue maps, instead this new operation could be useful
for other maps as well.

Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it>
---
 include/linux/bpf.h      |    1 +
 include/uapi/linux/bpf.h |    1 +
 kernel/bpf/syscall.c     |   82 ++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 84 insertions(+)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 523481a3471b..c63a44381d3f 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -39,6 +39,7 @@ struct bpf_map_ops {
 	void *(*map_lookup_elem)(struct bpf_map *map, void *key);
 	int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags);
 	int (*map_delete_elem)(struct bpf_map *map, void *key);
+	void *(*map_lookup_and_delete_elem)(struct bpf_map *map, void *key);
 
 	/* funcs called by prog_array and perf_event_array map */
 	void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file,
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 66917a4eba27..4cda584c6640 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -103,6 +103,7 @@ enum bpf_cmd {
 	BPF_BTF_LOAD,
 	BPF_BTF_GET_FD_BY_ID,
 	BPF_TASK_FD_QUERY,
+	BPF_MAP_LOOKUP_AND_DELETE_ELEM,
 };
 
 enum bpf_map_type {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index f2d4e4f280dc..7d429123a298 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -968,6 +968,85 @@ static int map_get_next_key(union bpf_attr *attr)
 	return err;
 }
 
+#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD value
+
+static int map_lookup_and_delete_elem(union bpf_attr *attr)
+{
+	void __user *ukey = u64_to_user_ptr(attr->key);
+	void __user *uvalue = u64_to_user_ptr(attr->value);
+	int ufd = attr->map_fd;
+	struct bpf_map *map;
+	void *key, *value, *ptr;
+	u32 value_size;
+	struct fd f;
+	int err;
+
+	if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM))
+		return -EINVAL;
+
+	f = fdget(ufd);
+	map = __bpf_map_get(f);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+		err = -EPERM;
+		goto err_put;
+	}
+
+	if (!map->ops->map_lookup_and_delete_elem) {
+		err = -ENOTSUPP;
+		goto err_put;
+	}
+
+	key = __bpf_copy_key(ukey, map->key_size);
+	if (IS_ERR(key)) {
+		err = PTR_ERR(key);
+		goto err_put;
+	}
+
+	value_size = map->value_size;
+
+	err = -ENOMEM;
+	value = kmalloc(value_size, GFP_USER | __GFP_NOWARN);
+	if (!value)
+		goto free_key;
+
+	err = -EFAULT;
+	if (copy_from_user(value, uvalue, value_size) != 0)
+		goto free_value;
+
+	/* must increment bpf_prog_active to avoid kprobe+bpf triggering from
+	 * inside bpf map update or delete otherwise deadlocks are possible
+	 */
+	preempt_disable();
+	__this_cpu_inc(bpf_prog_active);
+	rcu_read_lock();
+	ptr = map->ops->map_lookup_and_delete_elem(map, key);
+	if (ptr)
+		memcpy(value, ptr, value_size);
+	rcu_read_unlock();
+		err = ptr ? 0 : -ENOENT;
+	__this_cpu_dec(bpf_prog_active);
+	preempt_enable();
+
+	if (err)
+		goto free_value;
+
+	if (copy_to_user(uvalue, value, value_size) != 0)
+		goto free_value;
+
+	err = 0;
+
+free_value:
+	kfree(value);
+free_key:
+	kfree(key);
+err_put:
+	fdput(f);
+	return err;
+}
+
 static const struct bpf_prog_ops * const bpf_prog_types[] = {
 #define BPF_PROG_TYPE(_id, _name) \
 	[_id] = & _name ## _prog_ops,
@@ -2428,6 +2507,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_TASK_FD_QUERY:
 		err = bpf_task_fd_query(&attr, uattr);
 		break;
+	case BPF_MAP_LOOKUP_AND_DELETE_ELEM:
+		err = map_lookup_and_delete_elem(&attr);
+		break;
 	default:
 		err = -EINVAL;
 		break;