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.

Signed-off-by: David Vernet <void@manifault.com>
---
 kernel/bpf/bpf_struct_ops.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index eaff04eefb31..fdc3e8705a3c 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -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_map
 	if (!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));
-- 
2.41.0

LGTM!

Acked-by: Kui-Feng Lee <thinker.li@gmail.com>


On 8/11/23 10:25, David Vernet wrote:
> 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.
> 
> Signed-off-by: David Vernet <void@manifault.com>
> ---
>   kernel/bpf/bpf_struct_ops.c | 15 +++++++++------
>   1 file changed, 9 insertions(+), 6 deletions(-)
> 
> diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
> index eaff04eefb31..fdc3e8705a3c 100644
> --- a/kernel/bpf/bpf_struct_ops.c
> +++ b/kernel/bpf/bpf_struct_ops.c
> @@ -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_map
>   	if (!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));