diff options
32 files changed, 1102 insertions, 189 deletions
diff --git a/Documentation/bpf/map_cgrp_storage.rst b/Documentation/bpf/map_cgrp_storage.rst new file mode 100644 index 000000000000..5d3f603efffa --- /dev/null +++ b/Documentation/bpf/map_cgrp_storage.rst @@ -0,0 +1,109 @@ +.. SPDX-License-Identifier: GPL-2.0-only +.. Copyright (C) 2022 Meta Platforms, Inc. and affiliates. + +========================= +BPF_MAP_TYPE_CGRP_STORAGE +========================= + +The ``BPF_MAP_TYPE_CGRP_STORAGE`` map type represents a local fix-sized +storage for cgroups. It is only available with ``CONFIG_CGROUPS``. +The programs are made available by the same Kconfig. The +data for a particular cgroup can be retrieved by looking up the map +with that cgroup. + +This document describes the usage and semantics of the +``BPF_MAP_TYPE_CGRP_STORAGE`` map type. + +Usage +===== + +The map key must be ``sizeof(int)`` representing a cgroup fd. +To access the storage in a program, use ``bpf_cgrp_storage_get``:: + + void *bpf_cgrp_storage_get(struct bpf_map *map, struct cgroup *cgroup, void *value, u64 flags) + +``flags`` could be 0 or ``BPF_LOCAL_STORAGE_GET_F_CREATE`` which indicates that +a new local storage will be created if one does not exist. + +The local storage can be removed with ``bpf_cgrp_storage_delete``:: + + long bpf_cgrp_storage_delete(struct bpf_map *map, struct cgroup *cgroup) + +The map is available to all program types. + +Examples +======== + +A BPF program example with BPF_MAP_TYPE_CGRP_STORAGE:: + + #include <vmlinux.h> + #include <bpf/bpf_helpers.h> + #include <bpf/bpf_tracing.h> + + struct { + __uint(type, BPF_MAP_TYPE_CGRP_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, long); + } cgrp_storage SEC(".maps"); + + SEC("tp_btf/sys_enter") + int BPF_PROG(on_enter, struct pt_regs *regs, long id) + { + struct task_struct *task = bpf_get_current_task_btf(); + long *ptr; + + ptr = bpf_cgrp_storage_get(&cgrp_storage, task->cgroups->dfl_cgrp, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (ptr) + __sync_fetch_and_add(ptr, 1); + + return 0; + } + +Userspace accessing map declared above:: + + #include <linux/bpf.h> + #include <linux/libbpf.h> + + __u32 map_lookup(struct bpf_map *map, int cgrp_fd) + { + __u32 *value; + value = bpf_map_lookup_elem(bpf_map__fd(map), &cgrp_fd); + if (value) + return *value; + return 0; + } + +Difference Between BPF_MAP_TYPE_CGRP_STORAGE and BPF_MAP_TYPE_CGROUP_STORAGE +============================================================================ + +The old cgroup storage map ``BPF_MAP_TYPE_CGROUP_STORAGE`` has been marked as +deprecated (renamed to ``BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED``). The new +``BPF_MAP_TYPE_CGRP_STORAGE`` map should be used instead. The following +illusates the main difference between ``BPF_MAP_TYPE_CGRP_STORAGE`` and +``BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED``. + +(1). ``BPF_MAP_TYPE_CGRP_STORAGE`` can be used by all program types while + ``BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED`` is available only to cgroup program types + like BPF_CGROUP_INET_INGRESS or BPF_CGROUP_SOCK_OPS, etc. + +(2). ``BPF_MAP_TYPE_CGRP_STORAGE`` supports local storage for more than one + cgroup while ``BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED`` only supports one cgroup + which is attached by a BPF program. + +(3). ``BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED`` allocates local storage at attach time so + ``bpf_get_local_storage()`` always returns non-NULL local storage. + ``BPF_MAP_TYPE_CGRP_STORAGE`` allocates local storage at runtime so + it is possible that ``bpf_cgrp_storage_get()`` may return null local storage. + To avoid such null local storage issue, user space can do + ``bpf_map_update_elem()`` to pre-allocate local storage before a BPF program + is attached. + +(4). ``BPF_MAP_TYPE_CGRP_STORAGE`` supports deleting local storage by a BPF program + while ``BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED`` only deletes storage during + prog detach time. + +So overall, ``BPF_MAP_TYPE_CGRP_STORAGE`` supports all ``BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED`` +functionality and beyond. It is recommended to use ``BPF_MAP_TYPE_CGRP_STORAGE`` +instead of ``BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED``. diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a5dbac8f5aba..9fd68b0b3e9c 100644 --- a/include/linux/bpf.h +++ b/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); diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index 7ea18d4da84b..6d37a40cd90e 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -116,21 +116,22 @@ static struct bpf_local_storage_cache name = { \ .idx_lock = __SPIN_LOCK_UNLOCKED(name.idx_lock), \ } -u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache); -void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, - u16 idx); - /* Helper functions for bpf_local_storage */ int bpf_local_storage_map_alloc_check(union bpf_attr *attr); -struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr); +struct bpf_map * +bpf_local_storage_map_alloc(union bpf_attr *attr, + struct bpf_local_storage_cache *cache); struct bpf_local_storage_data * bpf_local_storage_lookup(struct bpf_local_storage *local_storage, struct bpf_local_storage_map *smap, bool cacheit_lockit); -void bpf_local_storage_map_free(struct bpf_local_storage_map *smap, +bool bpf_local_storage_unlink_nolock(struct bpf_local_storage *local_storage); + +void bpf_local_storage_map_free(struct bpf_map *map, + struct bpf_local_storage_cache *cache, int __percpu *busy_counter); int bpf_local_storage_map_check_btf(const struct bpf_map *map, @@ -141,10 +142,6 @@ int bpf_local_storage_map_check_btf(const struct bpf_map *map, void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem); -bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, - struct bpf_local_storage_elem *selem, - bool uncharge_omem, bool use_trace_rcu); - void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool use_trace_rcu); void bpf_selem_link_map(struct bpf_local_storage_map *smap, diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 2c6a4f2562a7..d4ee3ccd3753 100644 --- a/include/linux/bpf_types.h +++ b/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) diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 2aea877d644f..c9744efd202f 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -265,5 +265,6 @@ MAX_BTF_TRACING_TYPE, }; extern u32 btf_tracing_ids[]; +extern u32 bpf_cgroup_btf_id[]; #endif diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 8f481d1b159a..c466fdc3a32a 100644 --- a/include/linux/cgroup-defs.h +++ b/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[]; }; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 17f61338f8f8..94659f6b3395 100644 --- a/include/uapi/linux/bpf.h +++ b/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 diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 341c94f208f4..3a12e6b400a2 100644 --- a/kernel/bpf/Makefile +++ b/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) diff --git a/kernel/bpf/bpf_cgrp_storage.c b/kernel/bpf/bpf_cgrp_storage.c new file mode 100644 index 000000000000..309403800f82 --- /dev/null +++ b/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], +}; diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c index 5f7683b19199..6a1d4d22816a 100644 --- a/kernel/bpf/bpf_inode_storage.c +++ b/kernel/bpf/bpf_inode_storage.c @@ -56,11 +56,9 @@ static struct bpf_local_storage_data *inode_storage_lookup(struct inode *inode, void bpf_inode_storage_free(struct inode *inode) { - struct bpf_local_storage_elem *selem; struct bpf_local_storage *local_storage; bool free_inode_storage = false; struct bpf_storage_blob *bsb; - struct hlist_node *n; bsb = bpf_inode(inode); if (!bsb) @@ -74,30 +72,11 @@ void bpf_inode_storage_free(struct inode *inode) return; } - /* Neither the bpf_prog nor the bpf-map's syscall - * could be modifying the local_storage->list now. - * Thus, no elem can be added-to or deleted-from the - * local_storage->list by the bpf_prog or by the bpf-map's syscall. - * - * It is racing with bpf_local_storage_map_free() alone - * when unlinking elem from the local_storage->list and - * the map's bucket->list. - */ raw_spin_lock_bh(&local_storage->lock); - hlist_for_each_entry_safe(selem, n, &local_storage->list, snode) { - /* Always unlink from map before unlinking from - * local_storage. - */ - bpf_selem_unlink_map(selem); - free_inode_storage = bpf_selem_unlink_storage_nolock( - local_storage, selem, false, false); - } + free_inode_storage = bpf_local_storage_unlink_nolock(local_storage); raw_spin_unlock_bh(&local_storage->lock); rcu_read_unlock(); - /* free_inoode_storage should always be true as long as - * local_storage->list was non-empty. - */ if (free_inode_storage) kfree_rcu(local_storage, rcu); } @@ -226,23 +205,12 @@ static int notsupp_get_next_key(struct bpf_map *map, void *key, static struct bpf_map *inode_storage_map_alloc(union bpf_attr *attr) { - struct bpf_local_storage_map *smap; - - smap = bpf_local_storage_map_alloc(attr); - if (IS_ERR(smap)) - return ERR_CAST(smap); - - smap->cache_idx = bpf_local_storage_cache_idx_get(&inode_cache); - return &smap->map; + return bpf_local_storage_map_alloc(attr, &inode_cache); } static void inode_storage_map_free(struct bpf_map *map) { - struct bpf_local_storage_map *smap; - - smap = (struct bpf_local_storage_map *)map; - bpf_local_storage_cache_idx_free(&inode_cache, smap->cache_idx); - bpf_local_storage_map_free(smap, NULL); + bpf_local_storage_map_free(map, &inode_cache, NULL); } BTF_ID_LIST_SINGLE(inode_storage_map_btf_ids, struct, diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index 781d14167140..93d9b1b17bc8 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -113,9 +113,9 @@ static void bpf_selem_free_rcu(struct rcu_head *rcu) * The caller must ensure selem->smap is still valid to be * dereferenced for its smap->elem_size and smap->cache_idx. */ -bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, - struct bpf_local_storage_elem *selem, - bool uncharge_mem, bool use_trace_rcu) +static bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, + struct bpf_local_storage_elem *selem, + bool uncharge_mem, bool use_trace_rcu) { struct bpf_local_storage_map *smap; bool free_local_storage; @@ -501,7 +501,7 @@ unlock_err: return ERR_PTR(err); } -u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache) +static u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache) { u64 min_usage = U64_MAX; u16 i, res = 0; @@ -525,76 +525,14 @@ u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache) return res; } -void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, - u16 idx) +static void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, + u16 idx) { spin_lock(&cache->idx_lock); cache->idx_usage_counts[idx]--; spin_unlock(&cache->idx_lock); } -void bpf_local_storage_map_free(struct bpf_local_storage_map *smap, - int __percpu *busy_counter) -{ - struct bpf_local_storage_elem *selem; - struct bpf_local_storage_map_bucket *b; - unsigned int i; - - /* Note that this map might be concurrently cloned from - * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone - * RCU read section to finish before proceeding. New RCU - * read sections should be prevented via bpf_map_inc_not_zero. - */ - synchronize_rcu(); - - /* bpf prog and the userspace can no longer access this map - * now. No new selem (of this map) can be added - * to the owner->storage or to the map bucket's list. - * - * The elem of this map can be cleaned up here - * or when the storage is freed e.g. - * by bpf_sk_storage_free() during __sk_destruct(). - */ - for (i = 0; i < (1U << smap->bucket_log); i++) { - b = &smap->buckets[i]; - - rcu_read_lock(); - /* No one is adding to b->list now */ - while ((selem = hlist_entry_safe( - rcu_dereference_raw(hlist_first_rcu(&b->list)), - struct bpf_local_storage_elem, map_node))) { - if (busy_counter) { - migrate_disable(); - this_cpu_inc(*busy_counter); - } - bpf_selem_unlink(selem, false); - if (busy_counter) { - this_cpu_dec(*busy_counter); - migrate_enable(); - } - cond_resched_rcu(); - } - rcu_read_unlock(); - } - - /* While freeing the storage we may still need to access the map. - * - * e.g. when bpf_sk_storage_free() has unlinked selem from the map - * which then made the above while((selem = ...)) loop - * exit immediately. - * - * However, while freeing the storage one still needs to access the - * smap->elem_size to do the uncharging in - * bpf_selem_unlink_storage_nolock(). - * - * Hence, wait another rcu grace period for the storage to be freed. - */ - synchronize_rcu(); - - kvfree(smap->buckets); - bpf_map_area_free(smap); -} - int bpf_local_storage_map_alloc_check(union bpf_attr *attr) { if (attr->map_flags & ~BPF_LOCAL_STORAGE_CREATE_FLAG_MASK || @@ -614,7 +552,7 @@ int bpf_local_storage_map_alloc_check(union bpf_attr *attr) return 0; } -struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr) +static struct bpf_local_storage_map *__bpf_local_storage_map_alloc(union bpf_attr *attr) { struct bpf_local_storage_map *smap; unsigned int i; @@ -664,3 +602,117 @@ int bpf_local_storage_map_check_btf(const struct bpf_map *map, return 0; } + +bool bpf_local_storage_unlink_nolock(struct bpf_local_storage *local_storage) +{ + struct bpf_local_storage_elem *selem; + bool free_storage = false; + struct hlist_node *n; + + /* Neither the bpf_prog nor the bpf_map's syscall + * could be modifying the local_storage->list now. + * Thus, no elem can be added to or deleted from the + * local_storage->list by the bpf_prog or by the bpf_map's syscall. + * + * It is racing with bpf_local_storage_map_free() alone + * when unlinking elem from the local_storage->list and + * the map's bucket->list. + */ + hlist_for_each_entry_safe(selem, n, &local_storage->list, snode) { + /* Always unlink from map before unlinking from + * local_storage. + */ + bpf_selem_unlink_map(selem); + /* If local_storage list has only one element, the + * bpf_selem_unlink_storage_nolock() will return true. + * Otherwise, it will return false. The current loop iteration + * intends to remove all local storage. So the last iteration + * of the loop will set the free_cgroup_storage to true. + */ + free_storage = bpf_selem_unlink_storage_nolock( + local_storage, selem, false, false); + } + + return free_storage; +} + +struct bpf_map * +bpf_local_storage_map_alloc(union bpf_attr *attr, + struct bpf_local_storage_cache *cache) +{ + struct bpf_local_storage_map *smap; + + smap = __bpf_local_storage_map_alloc(attr); + if (IS_ERR(smap)) + return ERR_CAST(smap); + + smap->cache_idx = bpf_local_storage_cache_idx_get(cache); + return &smap->map; +} + +void bpf_local_storage_map_free(struct bpf_map *map, + struct bpf_local_storage_cache *cache, + int __percpu *busy_counter) +{ + struct bpf_local_storage_map_bucket *b; + struct bpf_local_storage_elem *selem; + struct bpf_local_storage_map *smap; + unsigned int i; + + smap = (struct bpf_local_storage_map *)map; + bpf_local_storage_cache_idx_free(cache, smap->cache_idx); + + /* Note that this map might be concurrently cloned from + * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone + * RCU read section to finish before proceeding. New RCU + * read sections should be prevented via bpf_map_inc_not_zero. + */ + synchronize_rcu(); + + /* bpf prog and the userspace can no longer access this map + * now. No new selem (of this map) can be added + * to the owner->storage or to the map bucket's list. + * + * The elem of this map can be cleaned up here + * or when the storage is freed e.g. + * by bpf_sk_storage_free() during __sk_destruct(). + */ + for (i = 0; i < (1U << smap->bucket_log); i++) { + b = &smap->buckets[i]; + + rcu_read_lock(); + /* No one is adding to b->list now */ + while ((selem = hlist_entry_safe( + rcu_dereference_raw(hlist_first_rcu(&b->list)), + struct bpf_local_storage_elem, map_node))) { + if (busy_counter) { + migrate_disable(); + this_cpu_inc(*busy_counter); + } + bpf_selem_unlink(selem, false); + if (busy_counter) { + this_cpu_dec(*busy_counter); + migrate_enable(); + } + cond_resched_rcu(); + } + rcu_read_unlock(); + } + + /* While freeing the storage we may still need to access the map. + * + * e.g. when bpf_sk_storage_free() has unlinked selem from the map + * which then made the above while((selem = ...)) loop + * exit immediately. + * + * However, while freeing the storage one still needs to access the + * smap->elem_size to do the uncharging in + * bpf_selem_unlink_storage_nolock(). + * + * Hence, wait another rcu grace period for the storage to be freed. + */ + synchronize_rcu(); + + kvfree(smap->buckets); + bpf_map_area_free(smap); +} diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c index ba3fe72d1fa5..8e832db8151a 100644 --- a/kernel/bpf/bpf_task_storage.c +++ b/kernel/bpf/bpf_task_storage.c @@ -71,10 +71,8 @@ task_storage_lookup(struct task_struct *task, struct bpf_map *map, void bpf_task_storage_free(struct task_struct *task) { - struct bpf_local_storage_elem *selem; struct bpf_local_storage *local_storage; bool free_task_storage = false; - struct hlist_node *n; unsigned long flags; rcu_read_lock(); @@ -85,32 +83,13 @@ void bpf_task_storage_free(struct task_struct *task) return; } - /* Neither the bpf_prog nor the bpf-map's syscall - * could be modifying the local_storage->list now. - * Thus, no elem can be added-to or deleted-from the - * local_storage->list by the bpf_prog or by the bpf-map's syscall. - * - * It is racing with bpf_local_storage_map_free() alone - * when unlinking elem from the local_storage->list and - * the map's bucket->list. - */ bpf_task_storage_lock(); raw_spin_lock_irqsave(&local_storage->lock, flags); - hlist_for_each_entry_safe(selem, n, &local_storage->list, snode) { - /* Always unlink from map before unlinking from - * local_storage. - */ - bpf_selem_unlink_map(selem); - free_task_storage = bpf_selem_unlink_storage_nolock( - local_storage, selem, false, false); - } + free_task_storage = bpf_local_storage_unlink_nolock(local_storage); raw_spin_unlock_irqrestore(&local_storage->lock, flags); bpf_task_storage_unlock(); rcu_read_unlock(); - /* free_task_storage should always be true as long as - * local_storage->list was non-empty. - */ if (free_task_storage) kfree_rcu(local_storage, rcu); } @@ -337,23 +316,12 @@ static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key) static struct bpf_map *task_storage_map_alloc(union bpf_attr *attr) { - struct bpf_local_storage_map *smap; - - smap = bpf_local_storage_map_alloc(attr); - if (IS_ERR(smap)) - return ERR_CAST(smap); - - smap->cache_idx = bpf_local_storage_cache_idx_get(&task_cache); - return &smap->map; + return bpf_local_storage_map_alloc(attr, &task_cache); } static void task_storage_map_free(struct bpf_map *map) { - struct bpf_local_storage_map *smap; - - smap = (struct bpf_local_storage_map *)map; - bpf_local_storage_cache_idx_free(&task_cache, smap->cache_idx); - bpf_local_storage_map_free(smap, &bpf_task_storage_busy); + bpf_local_storage_map_free(map, &task_cache, &bpf_task_storage_busy); } BTF_ID_LIST_SINGLE(task_storage_map_btf_ids, struct, bpf_local_storage_map) diff --git a/kernel/bpf/cgroup_iter.c b/kernel/bpf/cgroup_iter.c index 0d200a993489..c6ffc706d583 100644 --- a/kernel/bpf/cgroup_iter.c +++ b/kernel/bpf/cgroup_iter.c @@ -157,7 +157,7 @@ static const struct seq_operations cgroup_iter_seq_ops = { .show = cgroup_iter_seq_show, }; -BTF_ID_LIST_SINGLE(bpf_cgroup_btf_id, struct, cgroup) +BTF_ID_LIST_GLOBAL_SINGLE(bpf_cgroup_btf_id, struct, cgroup) static int cgroup_iter_seq_init(void *priv, struct bpf_iter_aux_info *aux) { diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index a6b04faed282..124fd199ce5c 100644 --- a/kernel/bpf/helpers.c +++ b/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; } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a0b4266196a8..11df90962101 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1016,7 +1016,8 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && map->map_type != BPF_MAP_TYPE_SK_STORAGE && map->map_type != BPF_MAP_TYPE_INODE_STORAGE && - map->map_type != BPF_MAP_TYPE_TASK_STORAGE) + map->map_type != BPF_MAP_TYPE_TASK_STORAGE && + map->map_type != BPF_MAP_TYPE_CGRP_STORAGE) return -ENOTSUPP; if (map->spin_lock_off + sizeof(struct bpf_spin_lock) > map->value_size) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ddc1452cf023..8f849a763b79 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6350,6 +6350,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, func_id != BPF_FUNC_task_storage_delete) goto error; break; + case BPF_MAP_TYPE_CGRP_STORAGE: + if (func_id != BPF_FUNC_cgrp_storage_get && + func_id != BPF_FUNC_cgrp_storage_delete) + goto error; + break; case BPF_MAP_TYPE_BLOOM_FILTER: if (func_id != BPF_FUNC_map_peek_elem && func_id != BPF_FUNC_map_push_elem) @@ -6462,6 +6467,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (map->map_type != BPF_MAP_TYPE_TASK_STORAGE) goto error; break; + case BPF_FUNC_cgrp_storage_get: + case BPF_FUNC_cgrp_storage_delete: + if (map->map_type != BPF_MAP_TYPE_CGRP_STORAGE) + goto error; + break; default: break; } @@ -14139,7 +14149,8 @@ static int do_misc_fixups(struct bpf_verifier_env *env) if (insn->imm == BPF_FUNC_task_storage_get || insn->imm == BPF_FUNC_sk_storage_get || - insn->imm == BPF_FUNC_inode_storage_get) { + insn->imm == BPF_FUNC_inode_storage_get || + insn->imm == BPF_FUNC_cgrp_storage_get) { if (env->prog->aux->sleepable) insn_buf[0] = BPF_MOV64_IMM(BPF_REG_5, (__force __s32)GFP_KERNEL); else diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 764bdd5fd8d1..12001928511b 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5245,6 +5245,7 @@ static void css_free_rwork_fn(struct work_struct *work) atomic_dec(&cgrp->root->nr_cgrps); cgroup1_pidlist_destroy_all(cgrp); cancel_work_sync(&cgrp->release_agent_work); + bpf_cgrp_storage_free(cgrp); if (cgroup_parent(cgrp)) { /* diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index eed1bd952c3a..ce0228c72a93 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1455,6 +1455,10 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_current_cgroup_id_proto; case BPF_FUNC_get_current_ancestor_cgroup_id: return &bpf_get_current_ancestor_cgroup_id_proto; + 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 case BPF_FUNC_send_signal: return &bpf_send_signal_proto; diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 94374d529ea4..49884e7de080 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -48,10 +48,8 @@ static int bpf_sk_storage_del(struct sock *sk, struct bpf_map *map) /* Called by __sk_destruct() & bpf_sk_storage_clone() */ void bpf_sk_storage_free(struct sock *sk) { - struct bpf_local_storage_elem *selem; struct bpf_local_storage *sk_storage; bool free_sk_storage = false; - struct hlist_node *n; rcu_read_lock(); sk_storage = rcu_dereference(sk->sk_bpf_storage); @@ -60,24 +58,8 @@ void bpf_sk_storage_free(struct sock *sk) return; } - /* Netiher the bpf_prog nor the bpf-map's syscall - * could be modifying the sk_storage->list now. - * Thus, no elem can be added-to or deleted-from the - * sk_storage->list by the bpf_prog or by the bpf-map's syscall. - * - * It is racing with bpf_local_storage_map_free() alone - * when unlinking elem from the sk_storage->list and - * the map's bucket->list. - */ raw_spin_lock_bh(&sk_storage->lock); - hlist_for_each_entry_safe(selem, n, &sk_storage->list, snode) { - /* Always unlink from map before unlinking from - * sk_storage. - */ - bpf_selem_unlink_map(selem); - free_sk_storage = bpf_selem_unlink_storage_nolock( - sk_storage, selem, true, false); - } + free_sk_storage = bpf_local_storage_unlink_nolock(sk_storage); raw_spin_unlock_bh(&sk_storage->lock); rcu_read_unlock(); @@ -87,23 +69,12 @@ void bpf_sk_storage_free(struct sock *sk) static void bpf_sk_storage_map_free(struct bpf_map *map) { - struct bpf_local_storage_map *smap; - - smap = (struct bpf_local_storage_map *)map; - bpf_local_storage_cache_idx_free(&sk_cache, smap->cache_idx); - bpf_local_storage_map_free(smap, NULL); + bpf_local_storage_map_free(map, &sk_cache, NULL); } static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) { - struct bpf_local_storage_map *smap; - - smap = bpf_local_storage_map_alloc(attr); - if (IS_ERR(smap)) - return ERR_CAST(smap); - - smap->cache_idx = bpf_local_storage_cache_idx_get(&sk_cache); - return &smap->map; + return bpf_local_storage_map_alloc(attr, &sk_cache); } static int notsupp_get_next_key(struct bpf_map *map, void *key, diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py index c0e6690be82a..fdb0aff8cb5a 100755 --- a/scripts/bpf_doc.py +++ b/scripts/bpf_doc.py @@ -685,6 +685,7 @@ class PrinterHelpers(Printer): 'struct udp6_sock', 'struct unix_sock', 'struct task_struct', + 'struct cgroup', 'struct __sk_buff', 'struct sk_msg_md', @@ -742,6 +743,7 @@ class PrinterHelpers(Printer): 'struct udp6_sock', 'struct unix_sock', 'struct task_struct', + 'struct cgroup', 'struct path', 'struct btf_ptr', 'struct inode', diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 7f3b67a8b48f..11250c4734fe 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -55,7 +55,7 @@ MAP COMMANDS | | **devmap** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash** | | **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage** | | **queue** | **stack** | **sk_storage** | **struct_ops** | **ringbuf** | **inode_storage** -| | **task_storage** | **bloom_filter** | **user_ringbuf** } +| | **task_storage** | **bloom_filter** | **user_ringbuf** | **cgrp_storage** } DESCRIPTION =========== diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 3087ced658ad..f941ac5c7b73 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -1458,7 +1458,7 @@ static int do_help(int argc, char **argv) " devmap | devmap_hash | sockmap | cpumap | xskmap | sockhash |\n" " cgroup_storage | reuseport_sockarray | percpu_cgroup_storage |\n" " queue | stack | sk_storage | struct_ops | ringbuf | inode_storage |\n" - " task_storage | bloom_filter | user_ringbuf }\n" + " task_storage | bloom_filter | user_ringbuf | cgrp_storage }\n" " " HELP_SPEC_OPTIONS " |\n" " {-f|--bpffs} | {-n|--nomount} }\n" "", diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 17f61338f8f8..94659f6b3395 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/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 diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 027fd9565c16..5d7819edf074 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -164,6 +164,7 @@ static const char * const map_type_name[] = { [BPF_MAP_TYPE_TASK_STORAGE] = "task_storage", [BPF_MAP_TYPE_BLOOM_FILTER] = "bloom_filter", [BPF_MAP_TYPE_USER_RINGBUF] = "user_ringbuf", + [BPF_MAP_TYPE_CGRP_STORAGE] = "cgrp_storage", }; static const char * const prog_type_name[] = { diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index f3a8e8e74eb8..bdb83d467f9a 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -221,6 +221,7 @@ static int probe_map_create(enum bpf_map_type map_type) case BPF_MAP_TYPE_SK_STORAGE: case BPF_MAP_TYPE_INODE_STORAGE: case BPF_MAP_TYPE_TASK_STORAGE: + case BPF_MAP_TYPE_CGRP_STORAGE: btf_key_type_id = 1; btf_value_type_id = 3; value_size = 8; diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x index 520f12229b98..be4e3d47ea3e 100644 --- a/tools/testing/selftests/bpf/DENYLIST.s390x +++ b/tools/testing/selftests/bpf/DENYLIST.s390x @@ -10,6 +10,7 @@ bpf_nf # JIT does not support calling kernel f bpf_tcp_ca # JIT does not support calling kernel function (kfunc) cb_refs # expected error message unexpected error: -524 (trampoline) cgroup_hierarchical_stats # JIT does not support calling kernel function (kfunc) +cgrp_local_storage # prog_attach unexpected error: -524 (trampoline) core_read_macros # unknown func bpf_probe_read#4 (overlapping) d_path # failed to auto-attach program 'prog_stat': -524 (trampoline) deny_namespace # failed to attach: ERROR: strerror_r(-524)=22 (trampoline) diff --git a/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c new file mode 100644 index 000000000000..1c30412ba132 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c @@ -0,0 +1,171 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates.*/ + +#define _GNU_SOURCE +#include <unistd.h> +#include <sys/syscall.h> +#include <sys/types.h> +#include <test_progs.h> +#include "cgrp_ls_tp_btf.skel.h" +#include "cgrp_ls_recursion.skel.h" +#include "cgrp_ls_attach_cgroup.skel.h" +#include "cgrp_ls_negative.skel.h" +#include "network_helpers.h" + +struct socket_cookie { + __u64 cookie_key; + __u32 cookie_value; +}; + +static void test_tp_btf(int cgroup_fd) +{ + struct cgrp_ls_tp_btf *skel; + long val1 = 1, val2 = 0; + int err; + + skel = cgrp_ls_tp_btf__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) + return; + + /* populate a value in map_b */ + err = bpf_map_update_elem(bpf_map__fd(skel->maps.map_b), &cgroup_fd, &val1, BPF_ANY); + if (!ASSERT_OK(err, "map_update_elem")) + goto out; + + /* check value */ + err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.map_b), &cgroup_fd, &val2); + if (!ASSERT_OK(err, "map_lookup_elem")) + goto out; + if (!ASSERT_EQ(val2, 1, "map_lookup_elem, invalid val")) + goto out; + + /* delete value */ + err = bpf_map_delete_elem(bpf_map__fd(skel->maps.map_b), &cgroup_fd); + if (!ASSERT_OK(err, "map_delete_elem")) + goto out; + + skel->bss->target_pid = syscall(SYS_gettid); + + err = cgrp_ls_tp_btf__attach(skel); + if (!ASSERT_OK(err, "skel_attach")) + goto out; + + syscall(SYS_gettid); + syscall(SYS_gettid); + + skel->bss->target_pid = 0; + + /* 3x syscalls: 1x attach and 2x gettid */ + ASSERT_EQ(skel->bss->enter_cnt, 3, "enter_cnt"); + ASSERT_EQ(skel->bss->exit_cnt, 3, "exit_cnt"); + ASSERT_EQ(skel->bss->mismatch_cnt, 0, "mismatch_cnt"); +out: + cgrp_ls_tp_btf__destroy(skel); +} + +static void test_attach_cgroup(int cgroup_fd) +{ + int server_fd = 0, client_fd = 0, err = 0; + socklen_t addr_len = sizeof(struct sockaddr_in6); + struct cgrp_ls_attach_cgroup *skel; + __u32 cookie_expected_value; + struct sockaddr_in6 addr; + struct socket_cookie val; + + skel = cgrp_ls_attach_cgroup__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + return; + + skel->links.set_cookie = bpf_program__attach_cgroup( + skel->progs.set_cookie, cgroup_fd); + if (!ASSERT_OK_PTR(skel->links.set_cookie, "prog_attach")) + goto out; + + skel->links.update_cookie_sockops = bpf_program__attach_cgroup( + skel->progs.update_cookie_sockops, cgroup_fd); + if (!ASSERT_OK_PTR(skel->links.update_cookie_sockops, "prog_attach")) + goto out; + + skel->links.update_cookie_tracing = bpf_program__attach( + skel->progs.update_cookie_tracing); + if (!ASSERT_OK_PTR(skel->links.update_cookie_tracing, "prog_attach")) + goto out; + + server_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0); + if (!ASSERT_GE(server_fd, 0, "start_server")) + goto out; + + client_fd = connect_to_fd(server_fd, 0); + if (!ASSERT_GE(client_fd, 0, "connect_to_fd")) + goto close_server_fd; + + err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.socket_cookies), + &cgroup_fd, &val); + if (!ASSERT_OK(err, "map_lookup(socket_cookies)")) + goto close_client_fd; + + err = getsockname(client_fd, (struct sockaddr *)&addr, &addr_len); + if (!ASSERT_OK(err, "getsockname")) + goto close_client_fd; + + cookie_expected_value = (ntohs(addr.sin6_port) << 8) | 0xFF; + ASSERT_EQ(val.cookie_value, cookie_expected_value, "cookie_value"); + +close_client_fd: + close(client_fd); +close_server_fd: + close(server_fd); +out: + cgrp_ls_attach_cgroup__destroy(skel); +} + +static void test_recursion(int cgroup_fd) +{ + struct cgrp_ls_recursion *skel; + int err; + + skel = cgrp_ls_recursion__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_open_and_load")) + return; + + err = cgrp_ls_recursion__attach(skel); + if (!ASSERT_OK(err, "skel_attach")) + goto out; + + /* trigger sys_enter, make sure it does not cause deadlock */ + syscall(SYS_gettid); + +out: + cgrp_ls_recursion__destroy(skel); +} + +static void test_negative(void) +{ + struct cgrp_ls_negative *skel; + + skel = cgrp_ls_negative__open_and_load(); + if (!ASSERT_ERR_PTR(skel, "skel_open_and_load")) { + cgrp_ls_negative__destroy(skel); + return; + } +} + +void test_cgrp_local_storage(void) +{ + int cgroup_fd; + + cgroup_fd = test__join_cgroup("/cgrp_local_storage"); + if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup /cgrp_local_storage")) + return; + + if (test__start_subtest("tp_btf")) + test_tp_btf(cgroup_fd); + if (test__start_subtest("attach_cgroup")) + test_attach_cgroup(cgroup_fd); + if (test__start_subtest("recursion")) + test_recursion(cgroup_fd); + if (test__start_subtest("negative")) + test_negative(); + + close(cgroup_fd); +} diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c index 93e9cddaadcf..efb8bd43653c 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c @@ -139,6 +139,14 @@ static void test_libbpf_bpf_map_type_str(void) snprintf(buf, sizeof(buf), "BPF_MAP_TYPE_%s", map_type_str); uppercase(buf); + /* Special case for map_type_name BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED + * where it and BPF_MAP_TYPE_CGROUP_STORAGE have the same enum value + * (map_type). For this enum value, libbpf_bpf_map_type_str() picks + * BPF_MAP_TYPE_CGROUP_STORAGE. + */ + if (strcmp(map_type_name, "BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED") == 0) + continue; + ASSERT_STREQ(buf, map_type_name, "exp_str_value"); } diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_attach_cgroup.c b/tools/testing/selftests/bpf/progs/cgrp_ls_attach_cgroup.c new file mode 100644 index 000000000000..6652d18465b2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgrp_ls_attach_cgroup.c @@ -0,0 +1,101 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_tracing_net.h" + +char _license[] SEC("license") = "GPL"; + +struct socket_cookie { + __u64 cookie_key; + __u64 cookie_value; +}; + +struct { + __uint(type, BPF_MAP_TYPE_CGRP_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct socket_cookie); +} socket_cookies SEC(".maps"); + +SEC("cgroup/connect6") +int set_cookie(struct bpf_sock_addr *ctx) +{ + struct socket_cookie *p; + struct tcp_sock *tcp_sk; + struct bpf_sock *sk; + + if (ctx->family != AF_INET6 || ctx->user_family != AF_INET6) + return 1; + + sk = ctx->sk; + if (!sk) + return 1; + + tcp_sk = bpf_skc_to_tcp_sock(sk); + if (!tcp_sk) + return 1; + + p = bpf_cgrp_storage_get(&socket_cookies, + tcp_sk->inet_conn.icsk_inet.sk.sk_cgrp_data.cgroup, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!p) + return 1; + + p->cookie_value = 0xF; + p->cookie_key = bpf_get_socket_cookie(ctx); + return 1; +} + +SEC("sockops") +int update_cookie_sockops(struct bpf_sock_ops *ctx) +{ + struct socket_cookie *p; + struct tcp_sock *tcp_sk; + struct bpf_sock *sk; + + if (ctx->family != AF_INET6 || ctx->op != BPF_SOCK_OPS_TCP_CONNECT_CB) + return 1; + + sk = ctx->sk; + if (!sk) + return 1; + + tcp_sk = bpf_skc_to_tcp_sock(sk); + if (!tcp_sk) + return 1; + + p = bpf_cgrp_storage_get(&socket_cookies, + tcp_sk->inet_conn.icsk_inet.sk.sk_cgrp_data.cgroup, 0, 0); + if (!p) + return 1; + + if (p->cookie_key != bpf_get_socket_cookie(ctx)) + return 1; + + p->cookie_value |= (ctx->local_port << 8); + return 1; +} + +SEC("fexit/inet_stream_connect") +int BPF_PROG(update_cookie_tracing, struct socket *sock, + struct sockaddr *uaddr, int addr_len, int flags) +{ + struct socket_cookie *p; + struct tcp_sock *tcp_sk; + + if (uaddr->sa_family != AF_INET6) + return 0; + + p = bpf_cgrp_storage_get(&socket_cookies, sock->sk->sk_cgrp_data.cgroup, 0, 0); + if (!p) + return 0; + + if (p->cookie_key != bpf_get_socket_cookie(sock->sk)) + return 0; + + p->cookie_value |= 0xF0; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_negative.c b/tools/testing/selftests/bpf/progs/cgrp_ls_negative.c new file mode 100644 index 000000000000..d41f90e2ab64 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgrp_ls_negative.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_CGRP_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, long); +} map_a SEC(".maps"); + +SEC("tp_btf/sys_enter") +int BPF_PROG(on_enter, struct pt_regs *regs, long id) +{ + struct task_struct *task; + + task = bpf_get_current_task_btf(); + (void)bpf_cgrp_storage_get(&map_a, (struct cgroup *)task, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c b/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c new file mode 100644 index 000000000000..a043d8fefdac --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgrp_ls_recursion.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_CGRP_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, long); +} map_a SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_CGRP_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, long); +} map_b SEC(".maps"); + +SEC("fentry/bpf_local_storage_lookup") +int BPF_PROG(on_lookup) +{ + struct task_struct *task = bpf_get_current_task_btf(); + + bpf_cgrp_storage_delete(&map_a, task->cgroups->dfl_cgrp); + bpf_cgrp_storage_delete(&map_b, task->cgroups->dfl_cgrp); + return 0; +} + +SEC("fentry/bpf_local_storage_update") +int BPF_PROG(on_update) +{ + struct task_struct *task = bpf_get_current_task_btf(); + long *ptr; + + ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (ptr) + *ptr += 1; + + ptr = bpf_cgrp_storage_get(&map_b, task->cgroups->dfl_cgrp, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (ptr) + *ptr += 1; + + return 0; +} + +SEC("tp_btf/sys_enter") +int BPF_PROG(on_enter, struct pt_regs *regs, long id) +{ + struct task_struct *task; + long *ptr; + + task = bpf_get_current_task_btf(); + ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (ptr) + *ptr = 200; + + ptr = bpf_cgrp_storage_get(&map_b, task->cgroups->dfl_cgrp, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (ptr) + *ptr = 100; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/cgrp_ls_tp_btf.c b/tools/testing/selftests/bpf/progs/cgrp_ls_tp_btf.c new file mode 100644 index 000000000000..9ebb8e2fe541 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgrp_ls_tp_btf.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_CGRP_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, long); +} map_a SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_CGRP_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, long); +} map_b SEC(".maps"); + +#define MAGIC_VALUE 0xabcd1234 + +pid_t target_pid = 0; +int mismatch_cnt = 0; +int enter_cnt = 0; +int exit_cnt = 0; + +SEC("tp_btf/sys_enter") +int BPF_PROG(on_enter, struct pt_regs *regs, long id) +{ + struct task_struct *task; + long *ptr; + int err; + + task = bpf_get_current_task_btf(); + if (task->pid != target_pid) + return 0; + + /* populate value 0 */ + ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!ptr) + return 0; + + /* delete value 0 */ + err = bpf_cgrp_storage_delete(&map_a, task->cgroups->dfl_cgrp); + if (err) + return 0; + + /* value is not available */ + ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0, 0); + if (ptr) + return 0; + + /* re-populate the value */ + ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!ptr) + return 0; + __sync_fetch_and_add(&enter_cnt, 1); + *ptr = MAGIC_VALUE + enter_cnt; + + return 0; +} + +SEC("tp_btf/sys_exit") +int BPF_PROG(on_exit, struct pt_regs *regs, long id) +{ + struct task_struct *task; + long *ptr; + + task = bpf_get_current_task_btf(); + if (task->pid != target_pid) + return 0; + + ptr = bpf_cgrp_storage_get(&map_a, task->cgroups->dfl_cgrp, 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (!ptr) + return 0; + + __sync_fetch_and_add(&exit_cnt, 1); + if (*ptr != MAGIC_VALUE + exit_cnt) + __sync_fetch_and_add(&mismatch_cnt, 1); + return 0; +} |