bpf: Support default .validate() and .update() behavior for struct_ops links
PATCH v2 1/1 bpf: Support default .validate() and .update() behavior for struct_ops links
Currently, if a struct_ops map is loaded with BPF_F_LINK, it must also define the .validate() and .update() callbacks in its corresponding struct bpf_struct_ops in the kernel. Enabling struct_ops link is useful in its own right to ensure that the map is unloaded if an application crashes. For example, with sched_ext, we want to automatically unload the host-wide scheduler if the application crashes. We would likely never support updating elements of a sched_ext struct_ops map, so we'd have to implement these callbacks showing that they _can't_ support element updates just to benefit from the basic lifetime management of struct_ops links.
Let's enable struct_ops maps to work with BPF_F_LINK even if they haven't defined these callbacks, by assuming that a struct_ops map element cannot be updated by default.
--- kernel/bpf/bpf_struct_ops.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-)
kernel/bpf/bpf_struct_ops.c +9 -6
@@ -509,9 +509,12 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, }if (st_map->map.map_flags &BPF_F_LINK ) { - err = st_ops->validate (kdata); -if (err) - goto reset_unlock; + err =0 ; +if (st_ops->validate) { + err = st_ops->validate (kdata); +if (err) + goto reset_unlock; + }set_memory_rox ((long )st_map->image,1 );/* Let bpf_link handle registration & unregistration. *
@@ -663,9 +666,6 @@ 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 || !st_ops->update)) -return ERR_PTR (-EOPNOTSUPP ); - t = st_ops->type; st_map_size = sizeof(*st_map) +
@@ -823,6 +823,9 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_mapif (!bpf_struct_ops_valid_to_reg (new_map))return -EINVAL ; +if (!st_map->st_ops->update) +return -EOPNOTSUPP ; +mutex_lock (&update_mutex); old_map =rcu_dereference_protected (st_link->map,lockdep_is_held (&update_mutex));
Signature · 1 line
2.41.0
LGTM!
Quoted 60 lines · David Vernet
Currently, if a
struct_opsmap is loaded withBPF_F_LINK, it must also define the .validate() and .update() callbacks in its corresponding structbpf_struct_opsin the kernel. Enablingstruct_opslink is useful in its own right to ensure that the map is unloaded if an application crashes. For example, withsched_ext, we want to automatically unload the host-wide scheduler if the application crashes. We would likely never support updating elements of asched_extstruct_opsmap, so we'd have to implement these callbacks showing that they _can't_ support element updates just to benefit from the basic lifetime management ofstruct_opslinks.Let's enable
struct_opsmaps to work withBPF_F_LINKeven if they haven't defined these callbacks, by assuming that astruct_opsmap element cannot be updated by default.Signed-off-by David Vernet <[email protected]>--- kernel/bpf/bpf_struct_ops.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-)kernel/bpf/bpf_struct_ops.c +9
-6@@ -509,9 +509,12 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, }if (st_map->map.map_flags &BPF_F_LINK ) { - err = st_ops->validate (kdata); -if (err) - goto reset_unlock; + err =0 ; +if (st_ops->validate) { + err = st_ops->validate (kdata); +if (err) + goto reset_unlock; + }set_memory_rox ((long )st_map->image,1 );/* Let bpf_link handle registration & unregistration. * @@ -663,9 +666,6 @@ 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 || !st_ops->update)) -return ERR_PTR (-EOPNOTSUPP ); - t = st_ops->type; st_map_size = sizeof(*st_map) +@@ -823,6 +823,9 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_mapif (!bpf_struct_ops_valid_to_reg (new_map))return -EINVAL ; +if (!st_map->st_ops->update) +return -EOPNOTSUPP ; +mutex_lock (&update_mutex); old_map =rcu_dereference_protected (st_link->map,lockdep_is_held (&update_mutex));