By improving the BPF_LINK_UPDATE command of bpf(), it should allow you
to conveniently switch between different struct_ops on a single
bpf_link. This would enable smoother transitions from one struct_ops
to another.
The struct_ops maps passing along with BPF_LINK_UPDATE should have the
BPF_F_LINK flag.
Signed-off-by: Kui-Feng Lee <kuifeng@xxxxxxxx>
---
include/linux/bpf.h | 3 +++
include/uapi/linux/bpf.h | 21 +++++++++++----
kernel/bpf/bpf_struct_ops.c | 48 +++++++++++++++++++++++++++++++++-
kernel/bpf/syscall.c | 34 ++++++++++++++++++++++++
net/ipv4/bpf_tcp_ca.c | 6 +++++
tools/include/uapi/linux/bpf.h | 21 +++++++++++----
6 files changed, 122 insertions(+), 11 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 2faf01fa3f04..29287a2d8b1b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1476,6 +1476,8 @@ struct bpf_link_ops {
void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq);
int (*fill_link_info)(const struct bpf_link *link,
struct bpf_link_info *info);
+ int (*update_map)(struct bpf_link *link, struct bpf_map *new_map,
+ struct bpf_map *old_map);
};
struct bpf_tramp_link {
@@ -1518,6 +1520,7 @@ struct bpf_struct_ops {
void *kdata, const void *udata);
int (*reg)(void *kdata);
void (*unreg)(void *kdata);
+ int (*update)(void *kdata, void *old_kdata);
int (*validate)(void *kdata);
const struct btf_type *type;
const struct btf_type *value_type;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 42f40ee083bf..e3d3b5160d26 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1555,12 +1555,23 @@ union bpf_attr {
struct { /* struct used by BPF_LINK_UPDATE command */
__u32 link_fd; /* link fd */
- /* new program fd to update link with */
- __u32 new_prog_fd;
+ union {
+ /* new program fd to update link with */
+ __u32 new_prog_fd;
+ /* new struct_ops map fd to update link with */
+ __u32 new_map_fd;
+ };
__u32 flags; /* extra flags */
- /* expected link's program fd; is specified only if
- * BPF_F_REPLACE flag is set in flags */
- __u32 old_prog_fd;
+ union {
+ /* expected link's program fd; is specified only if
+ * BPF_F_REPLACE flag is set in flags.
+ */
+ __u32 old_prog_fd;
+ /* expected link's map fd; is specified only
+ * if BPF_F_REPLACE flag is set.
+ */
+ __u32 old_map_fd;
+ };
} link_update;
struct {
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 5e77d1d4a7f5..71dd5d5d3ce5 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -65,6 +65,8 @@ struct bpf_struct_ops_link {
struct bpf_map __rcu *map;
};
+static DEFINE_MUTEX(update_mutex);
+
#define VALUE_PREFIX "bpf_struct_ops_"
#define VALUE_PREFIX_LEN (sizeof(VALUE_PREFIX) - 1)
@@ -660,7 +662,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
if (attr->value_size != vt->size)
return ERR_PTR(-EINVAL);
- if (attr->map_flags & BPF_F_LINK && !st_ops->validate)
+ if (attr->map_flags & BPF_F_LINK && (!st_ops->validate || !st_ops->update))
return ERR_PTR(-EOPNOTSUPP);
t = st_ops->type;
@@ -806,10 +808,54 @@ static int bpf_struct_ops_map_link_fill_link_info(const struct bpf_link *link,
return 0;
}
+static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map *new_map,
+ struct bpf_map *expected_old_map)
+{
+ struct bpf_struct_ops_map *st_map, *old_st_map;
+ struct bpf_map *old_map;
+ struct bpf_struct_ops_link *st_link;
+ int err = 0;
+
+ st_link = container_of(link, struct bpf_struct_ops_link, link);
+ st_map = container_of(new_map, struct bpf_struct_ops_map, map);
+
+ if (!bpf_struct_ops_valid_to_reg(new_map))
+ return -EINVAL;
+
+ mutex_lock(&update_mutex);
+
+ old_map = rcu_dereference_protected(st_link->map, lockdep_is_held(&update_mutex));
+ if (expected_old_map && old_map != expected_old_map) {
+ err = -EINVAL;
+ goto err_out;
+ }
+
+ old_st_map = container_of(old_map, struct bpf_struct_ops_map, map);
+ /* The new and old struct_ops must be the same type. */
+ if (st_map->st_ops != old_st_map->st_ops) {
+ err = -EINVAL;
+ goto err_out;
+ }
+
+ err = st_map->st_ops->update(st_map->kvalue.data, old_st_map->kvalue.data);
+ if (err)
+ goto err_out;
+
+ bpf_map_inc(new_map);
+ rcu_assign_pointer(st_link->map, new_map);
+ bpf_map_put(old_map);
+
+err_out:
+ mutex_unlock(&update_mutex);
+
+ return err;
+}
+
static const struct bpf_link_ops bpf_struct_ops_map_lops = {
.dealloc = bpf_struct_ops_map_link_dealloc,
.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,
};
int bpf_struct_ops_link_create(union bpf_attr *attr)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 21f76698875c..b4d758fa5981 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -4682,6 +4682,35 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
return ret;
}
+static int link_update_map(struct bpf_link *link, union bpf_attr *attr)
+{
+ struct bpf_map *new_map, *old_map = NULL;
+ int ret;
+
+ new_map = bpf_map_get(attr->link_update.new_map_fd);
+ if (IS_ERR(new_map))
+ return -EINVAL;
+
+ if (attr->link_update.flags & BPF_F_REPLACE) {
+ old_map = bpf_map_get(attr->link_update.old_map_fd);
+ if (IS_ERR(old_map)) {
+ ret = -EINVAL;
+ goto out_put;
+ }
+ } else if (attr->link_update.old_map_fd) {
+ ret = -EINVAL;
+ goto out_put;
+ }
+
+ ret = link->ops->update_map(link, new_map, old_map);
+
+ if (old_map)
+ bpf_map_put(old_map);
+out_put:
+ bpf_map_put(new_map);
+ return ret;
+}
+
#define BPF_LINK_UPDATE_LAST_FIELD link_update.old_prog_fd
static int link_update(union bpf_attr *attr)
@@ -4702,6 +4731,11 @@ static int link_update(union bpf_attr *attr)
if (IS_ERR(link))
return PTR_ERR(link);
+ if (link->ops->update_map) {
+ ret = link_update_map(link, attr);
+ goto out_put_link;
+ }
+
new_prog = bpf_prog_get(attr->link_update.new_prog_fd);
if (IS_ERR(new_prog)) {
ret = PTR_ERR(new_prog);
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index bbbd5eb94db2..e8b27826283e 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -264,6 +264,11 @@ static void bpf_tcp_ca_unreg(void *kdata)
tcp_unregister_congestion_control(kdata);
}
+static int bpf_tcp_ca_update(void *kdata, void *old_kdata)
+{
+ return tcp_update_congestion_control(kdata, old_kdata);
+}
+
static int bpf_tcp_ca_validate(void *kdata)
{
return tcp_validate_congestion_control(kdata);
@@ -273,6 +278,7 @@ struct bpf_struct_ops bpf_tcp_congestion_ops = {
.verifier_ops = &bpf_tcp_ca_verifier_ops,
.reg = bpf_tcp_ca_reg,
.unreg = bpf_tcp_ca_unreg,
+ .update = bpf_tcp_ca_update,
.check_member = bpf_tcp_ca_check_member,
.init_member = bpf_tcp_ca_init_member,
.init = bpf_tcp_ca_init,
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 9cf1deaf21f2..d6c5a022ae28 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1555,12 +1555,23 @@ union bpf_attr {
struct { /* struct used by BPF_LINK_UPDATE command */
__u32 link_fd; /* link fd */
- /* new program fd to update link with */
- __u32 new_prog_fd;
+ union {
+ /* new program fd to update link with */
+ __u32 new_prog_fd;
+ /* new struct_ops map fd to update link with */
+ __u32 new_map_fd;
+ };
__u32 flags; /* extra flags */
- /* expected link's program fd; is specified only if
- * BPF_F_REPLACE flag is set in flags */
- __u32 old_prog_fd;
+ union {
+ /* expected link's program fd; is specified only if
+ * BPF_F_REPLACE flag is set in flags.
+ */
+ __u32 old_prog_fd;
+ /* expected link's map fd; is specified only
+ * if BPF_F_REPLACE flag is set.
+ */
+ __u32 old_map_fd;
+ };
} link_update;
struct {
--
2.34.1
