diff options
| -rw-r--r-- | Documentation/bpf/kfuncs.rst | 198 | ||||
| -rw-r--r-- | kernel/bpf/helpers.c | 4 |
2 files changed, 200 insertions, 2 deletions
diff --git a/Documentation/bpf/kfuncs.rst b/Documentation/bpf/kfuncs.rst index b027fe16ee66..9fd7fb539f85 100644 --- a/Documentation/bpf/kfuncs.rst +++ b/Documentation/bpf/kfuncs.rst @@ -222,3 +222,201 @@ type. An example is shown below:: return register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING, &bpf_task_kfunc_set); } late_initcall(init_subsystem); + +3. Core kfuncs +============== + +The BPF subsystem provides a number of "core" kfuncs that are potentially +applicable to a wide variety of different possible use cases and programs. +Those kfuncs are documented here. + +3.1 struct task_struct * kfuncs +------------------------------- + +There are a number of kfuncs that allow ``struct task_struct *`` objects to be +used as kptrs: + +.. kernel-doc:: kernel/bpf/helpers.c + :identifiers: bpf_task_acquire bpf_task_release + +These kfuncs are useful when you want to acquire or release a reference to a +``struct task_struct *`` that was passed as e.g. a tracepoint arg, or a +struct_ops callback arg. For example: + +.. code-block:: c + + /** + * A trivial example tracepoint program that shows how to + * acquire and release a struct task_struct * pointer. + */ + SEC("tp_btf/task_newtask") + int BPF_PROG(task_acquire_release_example, struct task_struct *task, u64 clone_flags) + { + struct task_struct *acquired; + + acquired = bpf_task_acquire(task); + + /* + * In a typical program you'd do something like store + * the task in a map, and the map will automatically + * release it later. Here, we release it manually. + */ + bpf_task_release(acquired); + return 0; + } + +---- + +A BPF program can also look up a task from a pid. This can be useful if the +caller doesn't have a trusted pointer to a ``struct task_struct *`` object that +it can acquire a reference on with bpf_task_acquire(). + +.. kernel-doc:: kernel/bpf/helpers.c + :identifiers: bpf_task_from_pid + +Here is an example of it being used: + +.. code-block:: c + + SEC("tp_btf/task_newtask") + int BPF_PROG(task_get_pid_example, struct task_struct *task, u64 clone_flags) + { + struct task_struct *lookup; + + lookup = bpf_task_from_pid(task->pid); + if (!lookup) + /* A task should always be found, as %task is a tracepoint arg. */ + return -ENOENT; + + if (lookup->pid != task->pid) { + /* bpf_task_from_pid() looks up the task via its + * globally-unique pid from the init_pid_ns. Thus, + * the pid of the lookup task should always be the + * same as the input task. + */ + bpf_task_release(lookup); + return -EINVAL; + } + + /* bpf_task_from_pid() returns an acquired reference, + * so it must be dropped before returning from the + * tracepoint handler. + */ + bpf_task_release(lookup); + return 0; + } + +3.2 struct cgroup * kfuncs +-------------------------- + +``struct cgroup *`` objects also have acquire and release functions: + +.. kernel-doc:: kernel/bpf/helpers.c + :identifiers: bpf_cgroup_acquire bpf_cgroup_release + +These kfuncs are used in exactly the same manner as bpf_task_acquire() and +bpf_task_release() respectively, so we won't provide examples for them. + +---- + +You may also acquire a reference to a ``struct cgroup`` kptr that's already +stored in a map using bpf_cgroup_kptr_get(): + +.. kernel-doc:: kernel/bpf/helpers.c + :identifiers: bpf_cgroup_kptr_get + +Here's an example of how it can be used: + +.. code-block:: c + + /* struct containing the struct task_struct kptr which is actually stored in the map. */ + struct __cgroups_kfunc_map_value { + struct cgroup __kptr_ref * cgroup; + }; + + /* The map containing struct __cgroups_kfunc_map_value entries. */ + struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, int); + __type(value, struct __cgroups_kfunc_map_value); + __uint(max_entries, 1); + } __cgroups_kfunc_map SEC(".maps"); + + /* ... */ + + /** + * A simple example tracepoint program showing how a + * struct cgroup kptr that is stored in a map can + * be acquired using the bpf_cgroup_kptr_get() kfunc. + */ + SEC("tp_btf/cgroup_mkdir") + int BPF_PROG(cgroup_kptr_get_example, struct cgroup *cgrp, const char *path) + { + struct cgroup *kptr; + struct __cgroups_kfunc_map_value *v; + s32 id = cgrp->self.id; + + /* Assume a cgroup kptr was previously stored in the map. */ + v = bpf_map_lookup_elem(&__cgroups_kfunc_map, &id); + if (!v) + return -ENOENT; + + /* Acquire a reference to the cgroup kptr that's already stored in the map. */ + kptr = bpf_cgroup_kptr_get(&v->cgroup); + if (!kptr) + /* If no cgroup was present in the map, it's because + * we're racing with another CPU that removed it with + * bpf_kptr_xchg() between the bpf_map_lookup_elem() + * above, and our call to bpf_cgroup_kptr_get(). + * bpf_cgroup_kptr_get() internally safely handles this + * race, and will return NULL if the task is no longer + * present in the map by the time we invoke the kfunc. + */ + return -EBUSY; + + /* Free the reference we just took above. Note that the + * original struct cgroup kptr is still in the map. It will + * be freed either at a later time if another context deletes + * it from the map, or automatically by the BPF subsystem if + * it's still present when the map is destroyed. + */ + bpf_cgroup_release(kptr); + + return 0; + } + +---- + +Another kfunc available for interacting with ``struct cgroup *`` objects is +bpf_cgroup_ancestor(). This allows callers to access the ancestor of a cgroup, +and return it as a cgroup kptr. + +.. kernel-doc:: kernel/bpf/helpers.c + :identifiers: bpf_cgroup_ancestor + +Eventually, BPF should be updated to allow this to happen with a normal memory +load in the program itself. This is currently not possible without more work in +the verifier. bpf_cgroup_ancestor() can be used as follows: + +.. code-block:: c + + /** + * Simple tracepoint example that illustrates how a cgroup's + * ancestor can be accessed using bpf_cgroup_ancestor(). + */ + SEC("tp_btf/cgroup_mkdir") + int BPF_PROG(cgrp_ancestor_example, struct cgroup *cgrp, const char *path) + { + struct cgroup *parent; + + /* The parent cgroup resides at the level before the current cgroup's level. */ + parent = bpf_cgroup_ancestor(cgrp, cgrp->level - 1); + if (!parent) + return -ENOENT; + + bpf_printk("Parent id is %d", parent->self.id); + + /* Return the parent cgroup that was acquired above. */ + bpf_cgroup_release(parent); + return 0; + } diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 284b3ffdbe48..6ed5875b97a3 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1904,7 +1904,7 @@ struct task_struct *bpf_task_kptr_get(struct task_struct **pp) } /** - * bpf_task_release - Release the reference acquired on a struct task_struct *. + * bpf_task_release - Release the reference acquired on a task. * @p: The task on which a reference is being released. */ void bpf_task_release(struct task_struct *p) @@ -1960,7 +1960,7 @@ struct cgroup *bpf_cgroup_kptr_get(struct cgroup **cgrpp) } /** - * bpf_cgroup_release - Release the reference acquired on a struct cgroup *. + * bpf_cgroup_release - Release the reference acquired on a cgroup. * If this kfunc is invoked in an RCU read region, the cgroup is guaranteed to * not be freed until the current grace period has ended, even if its refcount * drops to 0. |