bpf: Implement cgroup storage available to non-cgroup-attached bpf progs

Similar to sk/inode/task storage, implement similar cgroup local storage.

There already exists a local storage implementation for cgroup-attached
bpf programs.  See map type BPF_MAP_TYPE_CGROUP_STORAGE and helper
bpf_get_local_storage(). But there are use cases such that non-cgroup
attached bpf progs wants to access cgroup local storage data. For example,
tc egress prog has access to sk and cgroup. It is possible to use
sk local storage to emulate cgroup local storage by storing data in socket.
But this is a waste as it could be lots of sockets belonging to a particular
cgroup. Alternatively, a separate map can be created with cgroup id as the key.
But this will introduce additional overhead to manipulate the new map.
A cgroup local storage, similar to existing sk/inode/task storage,
should help for this use case.

The life-cycle of storage is managed with the life-cycle of the
cgroup struct.  i.e. the storage is destroyed along with the owning cgroup
with a call to bpf_cgrp_storage_free() when cgroup itself
is deleted.

The userspace map operations can be done by using a cgroup fd as a key
passed to the lookup, update and delete operations.

Typically, the following code is used to get the current cgroup:
    struct task_struct *task = bpf_get_current_task_btf();
    ... task->cgroups->dfl_cgrp ...
and in structure task_struct definition:
    struct task_struct {
        ....
        struct css_set __rcu            *cgroups;
        ....
    }
With sleepable program, accessing task->cgroups is not protected by rcu_read_lock.
So the current implementation only supports non-sleepable program and supporting
sleepable program will be the next step together with adding rcu_read_lock
protection for rcu tagged structures.

Since map name BPF_MAP_TYPE_CGROUP_STORAGE has been used for old cgroup local
storage support, the new map name BPF_MAP_TYPE_CGRP_STORAGE is used
for cgroup storage available to non-cgroup-attached bpf programs. The old
cgroup storage supports bpf_get_local_storage() helper to get the cgroup data.
The new cgroup storage helper bpf_cgrp_storage_get() can provide similar
functionality. While old cgroup storage pre-allocates storage memory, the new
mechanism can also pre-allocate with a user space bpf_map_update_elem() call
to avoid potential run-time memory allocation failure.
Therefore, the new cgroup storage can provide all functionality w.r.t.
the old one. So in uapi bpf.h, the old BPF_MAP_TYPE_CGROUP_STORAGE is alias to
BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED to indicate the old cgroup storage can
be deprecated since the new one can provide the same functionality.

Acked-by: David Vernet <[email protected]>
Signed-off-by: Yonghong Song <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Alexei Starovoitov <[email protected]>

Author: yonghong-song

include/linux/bpf.h

@@ -2041,6 +2041,7 @@ struct bpf_link *bpf_link_by_id(u32 id);
 
 const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id);
 void bpf_task_storage_free(struct task_struct *task);
+void bpf_cgrp_storage_free(struct cgroup *cgroup);
 bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog);
 const struct btf_func_model *
 bpf_jit_find_kfunc_model(const struct bpf_prog *prog,
@@ -2295,6 +2296,10 @@ static inline bool has_current_bpf_ctx(void)
 static inline void bpf_prog_inc_misses_counter(struct bpf_prog *prog)
 {
 }
+
+static inline void bpf_cgrp_storage_free(struct cgroup *cgroup)
+{
+}
 #endif /* CONFIG_BPF_SYSCALL */
 
 void __bpf_free_used_btfs(struct bpf_prog_aux *aux,
@@ -2535,6 +2540,8 @@ extern const struct bpf_func_proto bpf_copy_from_user_task_proto;
 extern const struct bpf_func_proto bpf_set_retval_proto;
 extern const struct bpf_func_proto bpf_get_retval_proto;
 extern const struct bpf_func_proto bpf_user_ringbuf_drain_proto;
+extern const struct bpf_func_proto bpf_cgrp_storage_get_proto;
+extern const struct bpf_func_proto bpf_cgrp_storage_delete_proto;
 
 const struct bpf_func_proto *tracing_prog_func_proto(
   enum bpf_func_id func_id, const struct bpf_prog *prog);

include/linux/bpf_types.h

@@ -86,6 +86,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_PROG_ARRAY, prog_array_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_PERF_EVENT_ARRAY, perf_event_array_map_ops)
 #ifdef CONFIG_CGROUPS
 BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_ARRAY, cgroup_array_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_CGRP_STORAGE, cgrp_storage_map_ops)
 #endif
 #ifdef CONFIG_CGROUP_BPF
 BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_STORAGE, cgroup_storage_map_ops)

include/linux/cgroup-defs.h

@@ -504,6 +504,10 @@ struct cgroup {
 	/* Used to store internal freezer state */
 	struct cgroup_freezer_state freezer;
 
+#ifdef CONFIG_BPF_SYSCALL
+	struct bpf_local_storage __rcu  *bpf_cgrp_storage;
+#endif
+
 	/* All ancestors including self */
 	struct cgroup *ancestors[];
 };

include/uapi/linux/bpf.h

@@ -922,7 +922,14 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_CPUMAP,
 	BPF_MAP_TYPE_XSKMAP,
 	BPF_MAP_TYPE_SOCKHASH,
-	BPF_MAP_TYPE_CGROUP_STORAGE,
+	BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED,
+	/* BPF_MAP_TYPE_CGROUP_STORAGE is available to bpf programs attaching
+	 * to a cgroup. The newer BPF_MAP_TYPE_CGRP_STORAGE is available to
+	 * both cgroup-attached and other progs and supports all functionality
+	 * provided by BPF_MAP_TYPE_CGROUP_STORAGE. So mark
+	 * BPF_MAP_TYPE_CGROUP_STORAGE deprecated.
+	 */
+	BPF_MAP_TYPE_CGROUP_STORAGE = BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED,
 	BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
 	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
 	BPF_MAP_TYPE_QUEUE,
@@ -935,6 +942,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_TASK_STORAGE,
 	BPF_MAP_TYPE_BLOOM_FILTER,
 	BPF_MAP_TYPE_USER_RINGBUF,
+	BPF_MAP_TYPE_CGRP_STORAGE,
 };
 
 /* Note that tracing related programs such as
@@ -5435,6 +5443,44 @@ union bpf_attr {
  *		**-E2BIG** if user-space has tried to publish a sample which is
  *		larger than the size of the ring buffer, or which cannot fit
  *		within a struct bpf_dynptr.
+ *
+ * void *bpf_cgrp_storage_get(struct bpf_map *map, struct cgroup *cgroup, void *value, u64 flags)
+ *	Description
+ *		Get a bpf_local_storage from the *cgroup*.
+ *
+ *		Logically, it could be thought of as getting the value from
+ *		a *map* with *cgroup* as the **key**.  From this
+ *		perspective,  the usage is not much different from
+ *		**bpf_map_lookup_elem**\ (*map*, **&**\ *cgroup*) except this
+ *		helper enforces the key must be a cgroup struct and the map must also
+ *		be a **BPF_MAP_TYPE_CGRP_STORAGE**.
+ *
+ *		In reality, the local-storage value is embedded directly inside of the
+ *		*cgroup* object itself, rather than being located in the
+ *		**BPF_MAP_TYPE_CGRP_STORAGE** map. When the local-storage value is
+ *		queried for some *map* on a *cgroup* object, the kernel will perform an
+ *		O(n) iteration over all of the live local-storage values for that
+ *		*cgroup* object until the local-storage value for the *map* is found.
+ *
+ *		An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be
+ *		used such that a new bpf_local_storage will be
+ *		created if one does not exist.  *value* can be used
+ *		together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify
+ *		the initial value of a bpf_local_storage.  If *value* is
+ *		**NULL**, the new bpf_local_storage will be zero initialized.
+ *	Return
+ *		A bpf_local_storage pointer is returned on success.
+ *
+ *		**NULL** if not found or there was an error in adding
+ *		a new bpf_local_storage.
+ *
+ * long bpf_cgrp_storage_delete(struct bpf_map *map, struct cgroup *cgroup)
+ *	Description
+ *		Delete a bpf_local_storage from a *cgroup*.
+ *	Return
+ *		0 on success.
+ *
+ *		**-ENOENT** if the bpf_local_storage cannot be found.
  */
 #define ___BPF_FUNC_MAPPER(FN, ctx...)			\
 	FN(unspec, 0, ##ctx)				\
@@ -5647,6 +5693,8 @@ union bpf_attr {
 	FN(tcp_raw_check_syncookie_ipv6, 207, ##ctx)	\
 	FN(ktime_get_tai_ns, 208, ##ctx)		\
 	FN(user_ringbuf_drain, 209, ##ctx)		\
+	FN(cgrp_storage_get, 210, ##ctx)		\
+	FN(cgrp_storage_delete, 211, ##ctx)		\
 	/* */
 
 /* backwards-compatibility macros for users of __BPF_FUNC_MAPPER that don't

kernel/bpf/Makefile

@@ -25,7 +25,7 @@ ifeq ($(CONFIG_PERF_EVENTS),y)
 obj-$(CONFIG_BPF_SYSCALL) += stackmap.o
 endif
 ifeq ($(CONFIG_CGROUPS),y)
-obj-$(CONFIG_BPF_SYSCALL) += cgroup_iter.o
+obj-$(CONFIG_BPF_SYSCALL) += cgroup_iter.o bpf_cgrp_storage.o
 endif
 obj-$(CONFIG_CGROUP_BPF) += cgroup.o
 ifeq ($(CONFIG_INET),y)

kernel/bpf/bpf_cgrp_storage.c

@@ -0,0 +1,247 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2022 Meta Platforms, Inc. and affiliates.
+ */
+
+#include <linux/types.h>
+#include <linux/bpf.h>
+#include <linux/bpf_local_storage.h>
+#include <uapi/linux/btf.h>
+#include <linux/btf_ids.h>
+
+DEFINE_BPF_STORAGE_CACHE(cgroup_cache);
+
+static DEFINE_PER_CPU(int, bpf_cgrp_storage_busy);
+
+static void bpf_cgrp_storage_lock(void)
+{
+	migrate_disable();
+	this_cpu_inc(bpf_cgrp_storage_busy);
+}
+
+static void bpf_cgrp_storage_unlock(void)
+{
+	this_cpu_dec(bpf_cgrp_storage_busy);
+	migrate_enable();
+}
+
+static bool bpf_cgrp_storage_trylock(void)
+{
+	migrate_disable();
+	if (unlikely(this_cpu_inc_return(bpf_cgrp_storage_busy) != 1)) {
+		this_cpu_dec(bpf_cgrp_storage_busy);
+		migrate_enable();
+		return false;
+	}
+	return true;
+}
+
+static struct bpf_local_storage __rcu **cgroup_storage_ptr(void *owner)
+{
+	struct cgroup *cg = owner;
+
+	return &cg->bpf_cgrp_storage;
+}
+
+void bpf_cgrp_storage_free(struct cgroup *cgroup)
+{
+	struct bpf_local_storage *local_storage;
+	bool free_cgroup_storage = false;
+	unsigned long flags;
+
+	rcu_read_lock();
+	local_storage = rcu_dereference(cgroup->bpf_cgrp_storage);
+	if (!local_storage) {
+		rcu_read_unlock();
+		return;
+	}
+
+	bpf_cgrp_storage_lock();
+	raw_spin_lock_irqsave(&local_storage->lock, flags);
+	free_cgroup_storage = bpf_local_storage_unlink_nolock(local_storage);
+	raw_spin_unlock_irqrestore(&local_storage->lock, flags);
+	bpf_cgrp_storage_unlock();
+	rcu_read_unlock();
+
+	if (free_cgroup_storage)
+		kfree_rcu(local_storage, rcu);
+}
+
+static struct bpf_local_storage_data *
+cgroup_storage_lookup(struct cgroup *cgroup, struct bpf_map *map, bool cacheit_lockit)
+{
+	struct bpf_local_storage *cgroup_storage;
+	struct bpf_local_storage_map *smap;
+
+	cgroup_storage = rcu_dereference_check(cgroup->bpf_cgrp_storage,
+					       bpf_rcu_lock_held());
+	if (!cgroup_storage)
+		return NULL;
+
+	smap = (struct bpf_local_storage_map *)map;
+	return bpf_local_storage_lookup(cgroup_storage, smap, cacheit_lockit);
+}
+
+static void *bpf_cgrp_storage_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct bpf_local_storage_data *sdata;
+	struct cgroup *cgroup;
+	int fd;
+
+	fd = *(int *)key;
+	cgroup = cgroup_get_from_fd(fd);
+	if (IS_ERR(cgroup))
+		return ERR_CAST(cgroup);
+
+	bpf_cgrp_storage_lock();
+	sdata = cgroup_storage_lookup(cgroup, map, true);
+	bpf_cgrp_storage_unlock();
+	cgroup_put(cgroup);
+	return sdata ? sdata->data : NULL;
+}
+
+static int bpf_cgrp_storage_update_elem(struct bpf_map *map, void *key,
+					  void *value, u64 map_flags)
+{
+	struct bpf_local_storage_data *sdata;
+	struct cgroup *cgroup;
+	int fd;
+
+	fd = *(int *)key;
+	cgroup = cgroup_get_from_fd(fd);
+	if (IS_ERR(cgroup))
+		return PTR_ERR(cgroup);
+
+	bpf_cgrp_storage_lock();
+	sdata = bpf_local_storage_update(cgroup, (struct bpf_local_storage_map *)map,
+					 value, map_flags, GFP_ATOMIC);
+	bpf_cgrp_storage_unlock();
+	cgroup_put(cgroup);
+	return PTR_ERR_OR_ZERO(sdata);
+}
+
+static int cgroup_storage_delete(struct cgroup *cgroup, struct bpf_map *map)
+{
+	struct bpf_local_storage_data *sdata;
+
+	sdata = cgroup_storage_lookup(cgroup, map, false);
+	if (!sdata)
+		return -ENOENT;
+
+	bpf_selem_unlink(SELEM(sdata), true);
+	return 0;
+}
+
+static int bpf_cgrp_storage_delete_elem(struct bpf_map *map, void *key)
+{
+	struct cgroup *cgroup;
+	int err, fd;
+
+	fd = *(int *)key;
+	cgroup = cgroup_get_from_fd(fd);
+	if (IS_ERR(cgroup))
+		return PTR_ERR(cgroup);
+
+	bpf_cgrp_storage_lock();
+	err = cgroup_storage_delete(cgroup, map);
+	bpf_cgrp_storage_unlock();
+	cgroup_put(cgroup);
+	return err;
+}
+
+static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+	return -ENOTSUPP;
+}
+
+static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr)
+{
+	return bpf_local_storage_map_alloc(attr, &cgroup_cache);
+}
+
+static void cgroup_storage_map_free(struct bpf_map *map)
+{
+	bpf_local_storage_map_free(map, &cgroup_cache, NULL);
+}
+
+/* *gfp_flags* is a hidden argument provided by the verifier */
+BPF_CALL_5(bpf_cgrp_storage_get, struct bpf_map *, map, struct cgroup *, cgroup,
+	   void *, value, u64, flags, gfp_t, gfp_flags)
+{
+	struct bpf_local_storage_data *sdata;
+
+	WARN_ON_ONCE(!bpf_rcu_lock_held());
+	if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE))
+		return (unsigned long)NULL;
+
+	if (!cgroup)
+		return (unsigned long)NULL;
+
+	if (!bpf_cgrp_storage_trylock())
+		return (unsigned long)NULL;
+
+	sdata = cgroup_storage_lookup(cgroup, map, true);
+	if (sdata)
+		goto unlock;
+
+	/* only allocate new storage, when the cgroup is refcounted */
+	if (!percpu_ref_is_dying(&cgroup->self.refcnt) &&
+	    (flags & BPF_LOCAL_STORAGE_GET_F_CREATE))
+		sdata = bpf_local_storage_update(cgroup, (struct bpf_local_storage_map *)map,
+						 value, BPF_NOEXIST, gfp_flags);
+
+unlock:
+	bpf_cgrp_storage_unlock();
+	return IS_ERR_OR_NULL(sdata) ? (unsigned long)NULL : (unsigned long)sdata->data;
+}
+
+BPF_CALL_2(bpf_cgrp_storage_delete, struct bpf_map *, map, struct cgroup *, cgroup)
+{
+	int ret;
+
+	WARN_ON_ONCE(!bpf_rcu_lock_held());
+	if (!cgroup)
+		return -EINVAL;
+
+	if (!bpf_cgrp_storage_trylock())
+		return -EBUSY;
+
+	ret = cgroup_storage_delete(cgroup, map);
+	bpf_cgrp_storage_unlock();
+	return ret;
+}
+
+BTF_ID_LIST_SINGLE(cgroup_storage_map_btf_ids, struct, bpf_local_storage_map)
+const struct bpf_map_ops cgrp_storage_map_ops = {
+	.map_meta_equal = bpf_map_meta_equal,
+	.map_alloc_check = bpf_local_storage_map_alloc_check,
+	.map_alloc = cgroup_storage_map_alloc,
+	.map_free = cgroup_storage_map_free,
+	.map_get_next_key = notsupp_get_next_key,
+	.map_lookup_elem = bpf_cgrp_storage_lookup_elem,
+	.map_update_elem = bpf_cgrp_storage_update_elem,
+	.map_delete_elem = bpf_cgrp_storage_delete_elem,
+	.map_check_btf = bpf_local_storage_map_check_btf,
+	.map_btf_id = &cgroup_storage_map_btf_ids[0],
+	.map_owner_storage_ptr = cgroup_storage_ptr,
+};
+
+const struct bpf_func_proto bpf_cgrp_storage_get_proto = {
+	.func		= bpf_cgrp_storage_get,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_BTF_ID,
+	.arg2_btf_id	= &bpf_cgroup_btf_id[0],
+	.arg3_type	= ARG_PTR_TO_MAP_VALUE_OR_NULL,
+	.arg4_type	= ARG_ANYTHING,
+};
+
+const struct bpf_func_proto bpf_cgrp_storage_delete_proto = {
+	.func		= bpf_cgrp_storage_delete,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_BTF_ID,
+	.arg2_btf_id	= &bpf_cgroup_btf_id[0],
+};

kernel/bpf/helpers.c

@@ -1663,6 +1663,12 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_dynptr_write_proto;
 	case BPF_FUNC_dynptr_data:
 		return &bpf_dynptr_data_proto;
+#ifdef CONFIG_CGROUPS
+	case BPF_FUNC_cgrp_storage_get:
+		return &bpf_cgrp_storage_get_proto;
+	case BPF_FUNC_cgrp_storage_delete:
+		return &bpf_cgrp_storage_delete_proto;
+#endif
 	default:
 		break;
 	}