From 8ba651ed7fa1641f7c4941b79f2e3dd4ddb58aec Mon Sep 17 00:00:00 2001 From: David Vernet Date: Mon, 14 Aug 2023 13:59:07 -0500 Subject: [PATCH 1/2] 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. Acked-by: Kui-Feng Lee Signed-off-by: David Vernet Link: https://lore.kernel.org/r/20230814185908.700553-2-void@manifault.com Signed-off-by: Martin KaFai Lau --- 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)); From bb48cf1679d294d4fd3bfaa88289ed9004cbb025 Mon Sep 17 00:00:00 2001 From: David Vernet Date: Mon, 14 Aug 2023 13:59:08 -0500 Subject: [PATCH 2/2] bpf: Document struct bpf_struct_ops fields Subsystems that want to implement a struct bpf_struct_ops structure to enable struct_ops maps must currently reverse engineer how the structure works. Given that this is meant to be a way for subsystem maintainers to extend their subsystems using BPF, let's document it to make it a bit easier on them. Signed-off-by: David Vernet Link: https://lore.kernel.org/r/20230814185908.700553-3-void@manifault.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf.h | 47 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cfabbcf47bdb..eced6400f778 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1550,6 +1550,53 @@ struct bpf_struct_ops_value; struct btf_member; #define BPF_STRUCT_OPS_MAX_NR_MEMBERS 64 +/** + * struct bpf_struct_ops - A structure of callbacks allowing a subsystem to + * define a BPF_MAP_TYPE_STRUCT_OPS map type composed + * of BPF_PROG_TYPE_STRUCT_OPS progs. + * @verifier_ops: A structure of callbacks that are invoked by the verifier + * when determining whether the struct_ops progs in the + * struct_ops map are valid. + * @init: A callback that is invoked a single time, and before any other + * callback, to initialize the structure. A nonzero return value means + * the subsystem could not be initialized. + * @check_member: When defined, a callback invoked by the verifier to allow + * the subsystem to determine if an entry in the struct_ops map + * is valid. A nonzero return value means that the map is + * invalid and should be rejected by the verifier. + * @init_member: A callback that is invoked for each member of the struct_ops + * map to allow the subsystem to initialize the member. A nonzero + * value means the member could not be initialized. This callback + * is exclusive with the @type, @type_id, @value_type, and + * @value_id fields. + * @reg: A callback that is invoked when the struct_ops map has been + * initialized and is being attached to. Zero means the struct_ops map + * has been successfully registered and is live. A nonzero return value + * means the struct_ops map could not be registered. + * @unreg: A callback that is invoked when the struct_ops map should be + * unregistered. + * @update: A callback that is invoked when the live struct_ops map is being + * updated to contain new values. This callback is only invoked when + * the struct_ops map is loaded with BPF_F_LINK. If not defined, the + * it is assumed that the struct_ops map cannot be updated. + * @validate: A callback that is invoked after all of the members have been + * initialized. This callback should perform static checks on the + * map, meaning that it should either fail or succeed + * deterministically. A struct_ops map that has been validated may + * not necessarily succeed in being registered if the call to @reg + * fails. For example, a valid struct_ops map may be loaded, but + * then fail to be registered due to there being another active + * struct_ops map on the system in the subsystem already. For this + * reason, if this callback is not defined, the check is skipped as + * the struct_ops map will have final verification performed in + * @reg. + * @type: BTF type. + * @value_type: Value type. + * @name: The name of the struct bpf_struct_ops object. + * @func_models: Func models + * @type_id: BTF type id. + * @value_id: BTF value id. + */ struct bpf_struct_ops { const struct bpf_verifier_ops *verifier_ops; int (*init)(struct btf *btf);