[bpf-next,v5,3/8] bpf: support epoll from bpf struct_ops links.

Commit Message

Kui-Feng Lee May 23, 2024, 11:08 p.m. UTC

Add epoll support to bpf struct_ops links to trigger EPOLLHUP event upon
detachment.

This patch implements the "poll" of the "struct file_operations" for BPF
links and introduces a new "poll" operator in the "struct bpf_link_ops". By
implementing "poll" of "struct bpf_link_ops" for the links of struct_ops,
the file descriptor of a struct_ops link can be added to an epoll file
descriptor to receive EPOLLHUP events.

Signed-off-by: Kui-Feng Lee <[e-mail]>
---
 include/linux/bpf.h         |  1 +
 kernel/bpf/bpf_struct_ops.c | 17 +++++++++++++++++
 kernel/bpf/syscall.c        | 31 ++++++++++++++++++++++++++-----
 3 files changed, 44 insertions(+), 5 deletions(-)

Patch

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b600767ebe02..5f7496ef8b7c 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1612,6 +1612,7 @@  struct bpf_link_ops {
 			      struct bpf_link_info *info);
 	int (*update_map)(struct bpf_link *link, struct bpf_map *new_map,
 			  struct bpf_map *old_map);
+	__poll_t (*poll)(struct file *file, struct poll_table_struct *pts);
 };
 
 struct bpf_tramp_link {
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index f2439acd9757..855a1b2b6e79 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -12,6 +12,7 @@ 
 #include <linux/mutex.h>
 #include <linux/btf_ids.h>
 #include <linux/rcupdate_wait.h>
+#include <linux/poll.h>
 
 struct bpf_struct_ops_value {
 	struct bpf_struct_ops_common_value common;
@@ -56,6 +57,7 @@  struct bpf_struct_ops_map {
 struct bpf_struct_ops_link {
 	struct bpf_link link;
 	struct bpf_map __rcu *map;
+	wait_queue_head_t wait_hup;
 };
 
 static DEFINE_MUTEX(update_mutex);
@@ -1167,15 +1169,28 @@  static int bpf_struct_ops_map_link_detach(struct bpf_link *link)
 
 	mutex_unlock(&update_mutex);
 
+	wake_up_interruptible_poll(&st_link->wait_hup, EPOLLHUP);
+
 	return 0;
 }
 
+static __poll_t bpf_struct_ops_map_link_poll(struct file *file,
+					     struct poll_table_struct *pts)
+{
+	struct bpf_struct_ops_link *st_link = file->private_data;
+
+	poll_wait(file, &st_link->wait_hup, pts);
+
+	return rcu_access_pointer(st_link->map) ? 0 : EPOLLHUP;
+}
+
 static const struct bpf_link_ops bpf_struct_ops_map_lops = {
 	.dealloc = bpf_struct_ops_map_link_dealloc,
 	.detach = bpf_struct_ops_map_link_detach,
 	.show_fdinfo = bpf_struct_ops_map_link_show_fdinfo,
 	.fill_link_info = bpf_struct_ops_map_link_fill_link_info,
 	.update_map = bpf_struct_ops_map_link_update,
+	.poll = bpf_struct_ops_map_link_poll,
 };
 
 int bpf_struct_ops_link_create(union bpf_attr *attr)
@@ -1213,6 +1228,8 @@  int bpf_struct_ops_link_create(union bpf_attr *attr)
 	 */
 	RCU_INIT_POINTER(link->map, map);
 
+	init_waitqueue_head(&link->wait_hup);
+
 	mutex_lock(&update_mutex);
 	err = st_map->st_ops_desc->st_ops->reg(st_map->kvalue.data, &link->link);
 	if (err) {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 13ad74ecf2cd..741f91153fe6 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3150,6 +3150,13 @@  static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp)
 }
 #endif
 
+static __poll_t bpf_link_poll(struct file *file, struct poll_table_struct *pts)
+{
+	struct bpf_link *link = file->private_data;
+
+	return link->ops->poll(file, pts);
+}
+
 static const struct file_operations bpf_link_fops = {
 #ifdef CONFIG_PROC_FS
 	.show_fdinfo	= bpf_link_show_fdinfo,
@@ -3159,6 +3166,16 @@  static const struct file_operations bpf_link_fops = {
 	.write		= bpf_dummy_write,
 };
 
+static const struct file_operations bpf_link_fops_poll = {
+#ifdef CONFIG_PROC_FS
+	.show_fdinfo	= bpf_link_show_fdinfo,
+#endif
+	.release	= bpf_link_release,
+	.read		= bpf_dummy_read,
+	.write		= bpf_dummy_write,
+	.poll		= bpf_link_poll,
+};
+
 static int bpf_link_alloc_id(struct bpf_link *link)
 {
 	int id;
@@ -3201,7 +3218,9 @@  int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer)
 		return id;
 	}
 
-	file = anon_inode_getfile("bpf_link", &bpf_link_fops, link, O_CLOEXEC);
+	file = anon_inode_getfile("bpf_link",
+				  link->ops->poll ? &bpf_link_fops_poll : &bpf_link_fops,
+				  link, O_CLOEXEC);
 	if (IS_ERR(file)) {
 		bpf_link_free_id(id);
 		put_unused_fd(fd);
@@ -3229,7 +3248,9 @@  int bpf_link_settle(struct bpf_link_primer *primer)
 
 int bpf_link_new_fd(struct bpf_link *link)
 {
-	return anon_inode_getfd("bpf-link", &bpf_link_fops, link, O_CLOEXEC);
+	return anon_inode_getfd("bpf-link",
+				link->ops->poll ? &bpf_link_fops_poll : &bpf_link_fops,
+				link, O_CLOEXEC);
 }
 
 struct bpf_link *bpf_link_get_from_fd(u32 ufd)
@@ -3239,7 +3260,7 @@  struct bpf_link *bpf_link_get_from_fd(u32 ufd)
 
 	if (!f.file)
 		return ERR_PTR(-EBADF);
-	if (f.file->f_op != &bpf_link_fops) {
+	if (f.file->f_op != &bpf_link_fops && f.file->f_op != &bpf_link_fops_poll) {
 		fdput(f);
 		return ERR_PTR(-EINVAL);
 	}
@@ -4966,7 +4987,7 @@  static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
 					     uattr);
 	else if (f.file->f_op == &btf_fops)
 		err = bpf_btf_get_info_by_fd(f.file, f.file->private_data, attr, uattr);
-	else if (f.file->f_op == &bpf_link_fops)
+	else if (f.file->f_op == &bpf_link_fops || f.file->f_op == &bpf_link_fops_poll)
 		err = bpf_link_get_info_by_fd(f.file, f.file->private_data,
 					      attr, uattr);
 	else
@@ -5101,7 +5122,7 @@  static int bpf_task_fd_query(const union bpf_attr *attr,
 	if (!file)
 		return -EBADF;
 
-	if (file->f_op == &bpf_link_fops) {
+	if (file->f_op == &bpf_link_fops || file->f_op == &bpf_link_fops_poll) {
 		struct bpf_link *link = file->private_data;
 
 		if (link->ops == &bpf_raw_tp_link_lops) {