diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c index 8b97fd1f0ceaf8dbbe9086591c492eaa34f18cd3..28be17ce53c1869976b3eefcfa3ff8acfafb5a5f 100644 --- a/drivers/media/rc/bpf-lirc.c +++ b/drivers/media/rc/bpf-lirc.c @@ -73,6 +73,12 @@ lirc_mode2_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_map_update_elem_proto; case BPF_FUNC_map_delete_elem: return &bpf_map_delete_elem_proto; + case BPF_FUNC_map_push_elem: + return &bpf_map_push_elem_proto; + case BPF_FUNC_map_pop_elem: + return &bpf_map_pop_elem_proto; + case BPF_FUNC_map_peek_elem: + return &bpf_map_peek_elem_proto; case BPF_FUNC_ktime_get_ns: return &bpf_ktime_get_ns_proto; case BPF_FUNC_tail_call: diff --git a/include/linux/bpf.h b/include/linux/bpf.h index bcb4d59d97bccfa8d2366ba885ffed73da0b77c1..7109dbf297f32b6f4d838cf1222e7fa00f1e186c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -40,6 +40,9 @@ struct bpf_map_ops { void *(*map_lookup_elem)(struct bpf_map *map, void *key); int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags); int (*map_delete_elem)(struct bpf_map *map, void *key); + int (*map_push_elem)(struct bpf_map *map, void *value, u64 flags); + int (*map_pop_elem)(struct bpf_map *map, void *value); + int (*map_peek_elem)(struct bpf_map *map, void *value); /* funcs called by prog_array and perf_event_array map */ void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, @@ -144,6 +147,7 @@ enum bpf_arg_type { ARG_CONST_MAP_PTR, /* const argument used as pointer to bpf_map */ ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */ ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */ + ARG_PTR_TO_UNINIT_MAP_VALUE, /* pointer to valid memory used to store a map value */ /* the following constraints used to prototype bpf_memcmp() and other * functions that access data on eBPF program stack @@ -833,6 +837,9 @@ static inline int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, extern const struct bpf_func_proto bpf_map_lookup_elem_proto; extern const struct bpf_func_proto bpf_map_update_elem_proto; extern const struct bpf_func_proto bpf_map_delete_elem_proto; +extern const struct bpf_func_proto bpf_map_push_elem_proto; +extern const struct bpf_func_proto bpf_map_pop_elem_proto; +extern const struct bpf_func_proto bpf_map_peek_elem_proto; extern const struct bpf_func_proto bpf_get_prandom_u32_proto; extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index fa48343a5ea17be246b58dd2a0e5c42a1dd609b8..44d9ab4809bdb7764e075270524346a7e9eb0895 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -51,7 +51,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_LRU_HASH, htab_lru_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_LRU_PERCPU_HASH, htab_lru_percpu_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_LPM_TRIE, trie_map_ops) #ifdef CONFIG_PERF_EVENTS -BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_trace_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops) @@ -69,3 +69,5 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, reuseport_array_ops) #endif #endif +BPF_MAP_TYPE(BPF_MAP_TYPE_QUEUE, queue_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops) diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 3a357f91d51531dca4a1bb06fede2fb18f167251..0cbbeda20f6475b212dbc9563252da80e2d496bc 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -175,6 +175,7 @@ static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src, dst->sg.data[which] = src->sg.data[which]; dst->sg.data[which].length = size; dst->sg.size += size; + src->sg.size -= size; src->sg.data[which].length -= size; src->sg.data[which].offset += size; } diff --git a/include/net/strparser.h b/include/net/strparser.h index f177c87ce38bd1919eab1f07f14b8c07006883eb..ef0822d110a8681be491b4ae667e143b51fc207f 100644 --- a/include/net/strparser.h +++ b/include/net/strparser.h @@ -57,10 +57,24 @@ struct strp_msg { int offset; }; +struct _strp_msg { + /* Internal cb structure. struct strp_msg must be first for passing + * to upper layer. + */ + struct strp_msg strp; + int accum_len; +}; + +struct sk_skb_cb { +#define SK_SKB_CB_PRIV_LEN 20 + unsigned char data[SK_SKB_CB_PRIV_LEN]; + struct _strp_msg strp; +}; + static inline struct strp_msg *strp_msg(struct sk_buff *skb) { return (struct strp_msg *)((void *)skb->cb + - offsetof(struct qdisc_skb_cb, data)); + offsetof(struct sk_skb_cb, strp)); } /* Structure for an attached lower socket */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e9d5c881eebd18bd700a3cd0a2f6cba2669a33f6..7509c8f2ae0ae8b9016c60074f78a93ec10b4f48 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -103,6 +103,7 @@ enum bpf_cmd { BPF_BTF_LOAD, BPF_BTF_GET_FD_BY_ID, BPF_TASK_FD_QUERY, + BPF_MAP_LOOKUP_AND_DELETE_ELEM, }; enum bpf_map_type { @@ -128,6 +129,8 @@ enum bpf_map_type { BPF_MAP_TYPE_CGROUP_STORAGE, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, + BPF_MAP_TYPE_QUEUE, + BPF_MAP_TYPE_STACK, }; enum bpf_prog_type { @@ -464,6 +467,28 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * + * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags) + * Description + * Push an element *value* in *map*. *flags* is one of: + * + * **BPF_EXIST** + * If the queue/stack is full, the oldest element is removed to + * make room for this. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_pop_elem(struct bpf_map *map, void *value) + * Description + * Pop an element from *map*. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_peek_elem(struct bpf_map *map, void *value) + * Description + * Get an element from *map* without removing it. + * Return + * 0 on success, or a negative error in case of failure. + * * int bpf_probe_read(void *dst, u32 size, const void *src) * Description * For tracing programs, safely attempt to read *size* bytes from @@ -1435,7 +1460,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_adjust_room(struct sk_buff *skb, u32 len_diff, u32 mode, u64 flags) + * int bpf_skb_adjust_room(struct sk_buff *skb, s32 len_diff, u32 mode, u64 flags) * Description * Grow or shrink the room for data in the packet associated to * *skb* by *len_diff*, and according to the selected *mode*. @@ -2312,7 +2337,10 @@ union bpf_attr { FN(skb_ancestor_cgroup_id), \ FN(sk_lookup_tcp), \ FN(sk_lookup_udp), \ - FN(sk_release), + FN(sk_release), \ + FN(map_push_elem), \ + FN(map_pop_elem), \ + FN(map_peek_elem), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 47bbc691c98327bc4f44a87e99e5d71223ea9536..29d781061cd5158bef89746b8b966a793b76638b 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -4,7 +4,7 @@ CFLAGS_core.o += $(call cc-disable-warning, override-init) obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o -obj-$(CONFIG_BPF_SYSCALL) += local_storage.o +obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o obj-$(CONFIG_BPF_SYSCALL) += disasm.o obj-$(CONFIG_BPF_SYSCALL) += btf.o ifeq ($(CONFIG_NET),y) diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 897a9505bb76c24a675c071af04b45050529543c..6f1734e829015fd72aa4a86801c4b90bd6ed6cea 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -703,6 +703,12 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_map_update_elem_proto; case BPF_FUNC_map_delete_elem: return &bpf_map_delete_elem_proto; + case BPF_FUNC_map_push_elem: + return &bpf_map_push_elem_proto; + case BPF_FUNC_map_pop_elem: + return &bpf_map_pop_elem_proto; + case BPF_FUNC_map_peek_elem: + return &bpf_map_peek_elem_proto; case BPF_FUNC_get_current_uid_gid: return &bpf_get_current_uid_gid_proto; case BPF_FUNC_get_local_storage: diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 2dc67936b82bded36f8d384901cbc3d9b4842226..c256fc1fcfe681230d46a7443dcb9364b9c8ef21 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1853,6 +1853,9 @@ BPF_CALL_0(bpf_user_rnd_u32) const struct bpf_func_proto bpf_map_lookup_elem_proto __weak; const struct bpf_func_proto bpf_map_update_elem_proto __weak; const struct bpf_func_proto bpf_map_delete_elem_proto __weak; +const struct bpf_func_proto bpf_map_push_elem_proto __weak; +const struct bpf_func_proto bpf_map_pop_elem_proto __weak; +const struct bpf_func_proto bpf_map_peek_elem_proto __weak; const struct bpf_func_proto bpf_get_prandom_u32_proto __weak; const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 6502115e8f55ad87da765b93da61037825b38532..f6f0d6d272e88e72f6aeb938271cb9e5be2d8154 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -76,6 +76,47 @@ const struct bpf_func_proto bpf_map_delete_elem_proto = { .arg2_type = ARG_PTR_TO_MAP_KEY, }; +BPF_CALL_3(bpf_map_push_elem, struct bpf_map *, map, void *, value, u64, flags) +{ + return map->ops->map_push_elem(map, value, flags); +} + +const struct bpf_func_proto bpf_map_push_elem_proto = { + .func = bpf_map_push_elem, + .gpl_only = false, + .pkt_access = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_MAP_VALUE, + .arg3_type = ARG_ANYTHING, +}; + +BPF_CALL_2(bpf_map_pop_elem, struct bpf_map *, map, void *, value) +{ + return map->ops->map_pop_elem(map, value); +} + +const struct bpf_func_proto bpf_map_pop_elem_proto = { + .func = bpf_map_pop_elem, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE, +}; + +BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value) +{ + return map->ops->map_peek_elem(map, value); +} + +const struct bpf_func_proto bpf_map_peek_elem_proto = { + .func = bpf_map_peek_elem, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_UNINIT_MAP_VALUE, +}; + const struct bpf_func_proto bpf_get_prandom_u32_proto = { .func = bpf_user_rnd_u32, .gpl_only = false, diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c new file mode 100644 index 0000000000000000000000000000000000000000..b384ea9f3254987f1caa16dff0780900720d93ca --- /dev/null +++ b/kernel/bpf/queue_stack_maps.c @@ -0,0 +1,290 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * queue_stack_maps.c: BPF queue and stack maps + * + * Copyright (c) 2018 Politecnico di Torino + */ +#include +#include +#include +#include +#include "percpu_freelist.h" + +#define QUEUE_STACK_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) + + +struct bpf_queue_stack { + struct bpf_map map; + raw_spinlock_t lock; + u32 head, tail; + u32 size; /* max_entries + 1 */ + + char elements[0] __aligned(8); +}; + +static struct bpf_queue_stack *bpf_queue_stack(struct bpf_map *map) +{ + return container_of(map, struct bpf_queue_stack, map); +} + +static bool queue_stack_map_is_empty(struct bpf_queue_stack *qs) +{ + return qs->head == qs->tail; +} + +static bool queue_stack_map_is_full(struct bpf_queue_stack *qs) +{ + u32 head = qs->head + 1; + + if (unlikely(head >= qs->size)) + head = 0; + + return head == qs->tail; +} + +/* Called from syscall */ +static int queue_stack_map_alloc_check(union bpf_attr *attr) +{ + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + /* check sanity of attributes */ + if (attr->max_entries == 0 || attr->key_size != 0 || + attr->value_size == 0 || + attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK) + return -EINVAL; + + if (attr->value_size > KMALLOC_MAX_SIZE) + /* if value_size is bigger, the user space won't be able to + * access the elements. + */ + return -E2BIG; + + return 0; +} + +static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr) +{ + int ret, numa_node = bpf_map_attr_numa_node(attr); + struct bpf_queue_stack *qs; + u64 size, queue_size, cost; + + size = (u64) attr->max_entries + 1; + cost = queue_size = sizeof(*qs) + size * attr->value_size; + if (cost >= U32_MAX - PAGE_SIZE) + return ERR_PTR(-E2BIG); + + cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + ret = bpf_map_precharge_memlock(cost); + if (ret < 0) + return ERR_PTR(ret); + + qs = bpf_map_area_alloc(queue_size, numa_node); + if (!qs) + return ERR_PTR(-ENOMEM); + + memset(qs, 0, sizeof(*qs)); + + bpf_map_init_from_attr(&qs->map, attr); + + qs->map.pages = cost; + qs->size = size; + + raw_spin_lock_init(&qs->lock); + + return &qs->map; +} + +/* Called when map->refcnt goes to zero, either from workqueue or from syscall */ +static void queue_stack_map_free(struct bpf_map *map) +{ + struct bpf_queue_stack *qs = bpf_queue_stack(map); + + /* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, + * so the programs (can be more than one that used this map) were + * disconnected from events. Wait for outstanding critical sections in + * these programs to complete + */ + synchronize_rcu(); + + bpf_map_area_free(qs); +} + +static int __queue_map_get(struct bpf_map *map, void *value, bool delete) +{ + struct bpf_queue_stack *qs = bpf_queue_stack(map); + unsigned long flags; + int err = 0; + void *ptr; + + raw_spin_lock_irqsave(&qs->lock, flags); + + if (queue_stack_map_is_empty(qs)) { + memset(value, 0, qs->map.value_size); + err = -ENOENT; + goto out; + } + + ptr = &qs->elements[qs->tail * qs->map.value_size]; + memcpy(value, ptr, qs->map.value_size); + + if (delete) { + if (unlikely(++qs->tail >= qs->size)) + qs->tail = 0; + } + +out: + raw_spin_unlock_irqrestore(&qs->lock, flags); + return err; +} + + +static int __stack_map_get(struct bpf_map *map, void *value, bool delete) +{ + struct bpf_queue_stack *qs = bpf_queue_stack(map); + unsigned long flags; + int err = 0; + void *ptr; + u32 index; + + raw_spin_lock_irqsave(&qs->lock, flags); + + if (queue_stack_map_is_empty(qs)) { + memset(value, 0, qs->map.value_size); + err = -ENOENT; + goto out; + } + + index = qs->head - 1; + if (unlikely(index >= qs->size)) + index = qs->size - 1; + + ptr = &qs->elements[index * qs->map.value_size]; + memcpy(value, ptr, qs->map.value_size); + + if (delete) + qs->head = index; + +out: + raw_spin_unlock_irqrestore(&qs->lock, flags); + return err; +} + +/* Called from syscall or from eBPF program */ +static int queue_map_peek_elem(struct bpf_map *map, void *value) +{ + return __queue_map_get(map, value, false); +} + +/* Called from syscall or from eBPF program */ +static int stack_map_peek_elem(struct bpf_map *map, void *value) +{ + return __stack_map_get(map, value, false); +} + +/* Called from syscall or from eBPF program */ +static int queue_map_pop_elem(struct bpf_map *map, void *value) +{ + return __queue_map_get(map, value, true); +} + +/* Called from syscall or from eBPF program */ +static int stack_map_pop_elem(struct bpf_map *map, void *value) +{ + return __stack_map_get(map, value, true); +} + +/* Called from syscall or from eBPF program */ +static int queue_stack_map_push_elem(struct bpf_map *map, void *value, + u64 flags) +{ + struct bpf_queue_stack *qs = bpf_queue_stack(map); + unsigned long irq_flags; + int err = 0; + void *dst; + + /* BPF_EXIST is used to force making room for a new element in case the + * map is full + */ + bool replace = (flags & BPF_EXIST); + + /* Check supported flags for queue and stack maps */ + if (flags & BPF_NOEXIST || flags > BPF_EXIST) + return -EINVAL; + + raw_spin_lock_irqsave(&qs->lock, irq_flags); + + if (queue_stack_map_is_full(qs)) { + if (!replace) { + err = -E2BIG; + goto out; + } + /* advance tail pointer to overwrite oldest element */ + if (unlikely(++qs->tail >= qs->size)) + qs->tail = 0; + } + + dst = &qs->elements[qs->head * qs->map.value_size]; + memcpy(dst, value, qs->map.value_size); + + if (unlikely(++qs->head >= qs->size)) + qs->head = 0; + +out: + raw_spin_unlock_irqrestore(&qs->lock, irq_flags); + return err; +} + +/* Called from syscall or from eBPF program */ +static void *queue_stack_map_lookup_elem(struct bpf_map *map, void *key) +{ + return NULL; +} + +/* Called from syscall or from eBPF program */ +static int queue_stack_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + return -EINVAL; +} + +/* Called from syscall or from eBPF program */ +static int queue_stack_map_delete_elem(struct bpf_map *map, void *key) +{ + return -EINVAL; +} + +/* Called from syscall */ +static int queue_stack_map_get_next_key(struct bpf_map *map, void *key, + void *next_key) +{ + return -EINVAL; +} + +const struct bpf_map_ops queue_map_ops = { + .map_alloc_check = queue_stack_map_alloc_check, + .map_alloc = queue_stack_map_alloc, + .map_free = queue_stack_map_free, + .map_lookup_elem = queue_stack_map_lookup_elem, + .map_update_elem = queue_stack_map_update_elem, + .map_delete_elem = queue_stack_map_delete_elem, + .map_push_elem = queue_stack_map_push_elem, + .map_pop_elem = queue_map_pop_elem, + .map_peek_elem = queue_map_peek_elem, + .map_get_next_key = queue_stack_map_get_next_key, +}; + +const struct bpf_map_ops stack_map_ops = { + .map_alloc_check = queue_stack_map_alloc_check, + .map_alloc = queue_stack_map_alloc, + .map_free = queue_stack_map_free, + .map_lookup_elem = queue_stack_map_lookup_elem, + .map_update_elem = queue_stack_map_update_elem, + .map_delete_elem = queue_stack_map_delete_elem, + .map_push_elem = queue_stack_map_push_elem, + .map_pop_elem = stack_map_pop_elem, + .map_peek_elem = stack_map_peek_elem, + .map_get_next_key = queue_stack_map_get_next_key, +}; diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index c0f1152bc27b11a3f912d7714e6149621d3625ba..b036849f4adc22edc37599e388535b8dd32e74e0 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -613,7 +613,7 @@ static void stack_map_free(struct bpf_map *map) put_callchain_buffers(); } -const struct bpf_map_ops stack_map_ops = { +const struct bpf_map_ops stack_trace_map_ops = { .map_alloc = stack_map_alloc, .map_free = stack_map_free, .map_get_next_key = stack_map_get_next_key, diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 57dfd43a31263fbc03dfda2967d2c236cb07fef9..87f3b28cc40ecae6f77111faf854b51870b0f51b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -652,6 +652,17 @@ int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) return -ENOTSUPP; } +static void *__bpf_copy_key(void __user *ukey, u64 key_size) +{ + if (key_size) + return memdup_user(ukey, key_size); + + if (ukey) + return ERR_PTR(-EINVAL); + + return NULL; +} + /* last field in 'union bpf_attr' used by this command */ #define BPF_MAP_LOOKUP_ELEM_LAST_FIELD value @@ -679,7 +690,7 @@ static int map_lookup_elem(union bpf_attr *attr) goto err_put; } - key = memdup_user(ukey, map->key_size); + key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; @@ -722,6 +733,9 @@ static int map_lookup_elem(union bpf_attr *attr) err = bpf_fd_htab_map_lookup_elem(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { err = bpf_fd_reuseport_array_lookup_elem(map, key, value); + } else if (map->map_type == BPF_MAP_TYPE_QUEUE || + map->map_type == BPF_MAP_TYPE_STACK) { + err = map->ops->map_peek_elem(map, value); } else { rcu_read_lock(); if (map->ops->map_lookup_elem_sys_only) @@ -798,7 +812,7 @@ static int map_update_elem(union bpf_attr *attr) goto err_put; } - key = memdup_user(ukey, map->key_size); + key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; @@ -859,6 +873,9 @@ static int map_update_elem(union bpf_attr *attr) /* rcu_read_lock() is not needed */ err = bpf_fd_reuseport_array_update_elem(map, key, value, attr->flags); + } else if (map->map_type == BPF_MAP_TYPE_QUEUE || + map->map_type == BPF_MAP_TYPE_STACK) { + err = map->ops->map_push_elem(map, value, attr->flags); } else { rcu_read_lock(); err = map->ops->map_update_elem(map, key, value, attr->flags); @@ -901,7 +918,7 @@ static int map_delete_elem(union bpf_attr *attr) goto err_put; } - key = memdup_user(ukey, map->key_size); + key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; @@ -954,7 +971,7 @@ static int map_get_next_key(union bpf_attr *attr) } if (ukey) { - key = memdup_user(ukey, map->key_size); + key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; @@ -995,6 +1012,71 @@ static int map_get_next_key(union bpf_attr *attr) return err; } +#define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD value + +static int map_lookup_and_delete_elem(union bpf_attr *attr) +{ + void __user *ukey = u64_to_user_ptr(attr->key); + void __user *uvalue = u64_to_user_ptr(attr->value); + int ufd = attr->map_fd; + struct bpf_map *map; + void *key, *value; + u32 value_size; + struct fd f; + int err; + + if (CHECK_ATTR(BPF_MAP_LOOKUP_AND_DELETE_ELEM)) + return -EINVAL; + + f = fdget(ufd); + map = __bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + if (!(f.file->f_mode & FMODE_CAN_WRITE)) { + err = -EPERM; + goto err_put; + } + + key = __bpf_copy_key(ukey, map->key_size); + if (IS_ERR(key)) { + err = PTR_ERR(key); + goto err_put; + } + + value_size = map->value_size; + + err = -ENOMEM; + value = kmalloc(value_size, GFP_USER | __GFP_NOWARN); + if (!value) + goto free_key; + + if (map->map_type == BPF_MAP_TYPE_QUEUE || + map->map_type == BPF_MAP_TYPE_STACK) { + err = map->ops->map_pop_elem(map, value); + } else { + err = -ENOTSUPP; + } + + if (err) + goto free_value; + + if (copy_to_user(uvalue, value, value_size) != 0) { + err = -EFAULT; + goto free_value; + } + + err = 0; + +free_value: + kfree(value); +free_key: + kfree(key); +err_put: + fdput(f); + return err; +} + static const struct bpf_prog_ops * const bpf_prog_types[] = { #define BPF_PROG_TYPE(_id, _name) \ [_id] = & _name ## _prog_ops, @@ -2484,6 +2566,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_TASK_FD_QUERY: err = bpf_task_fd_query(&attr, uattr); break; + case BPF_MAP_LOOKUP_AND_DELETE_ELEM: + err = map_lookup_and_delete_elem(&attr); + break; default: err = -EINVAL; break; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index b0a1e040edb481891ba41979777d6c46c910e58e..9b840ff1d1c6008bc5fe8be97ca111b3d1492495 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2250,7 +2250,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, } if (arg_type == ARG_PTR_TO_MAP_KEY || - arg_type == ARG_PTR_TO_MAP_VALUE) { + arg_type == ARG_PTR_TO_MAP_VALUE || + arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) { expected_type = PTR_TO_STACK; if (!type_is_pkt_pointer(type) && type != PTR_TO_MAP_VALUE && type != expected_type) @@ -2320,7 +2321,8 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, err = check_helper_mem_access(env, regno, meta->map_ptr->key_size, false, NULL); - } else if (arg_type == ARG_PTR_TO_MAP_VALUE) { + } else if (arg_type == ARG_PTR_TO_MAP_VALUE || + arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) { /* bpf_map_xxx(..., map_ptr, ..., value) call: * check [value, value + map->value_size) validity */ @@ -2329,9 +2331,10 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, verbose(env, "invalid map_ptr to access map->value\n"); return -EACCES; } + meta->raw_mode = (arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE); err = check_helper_mem_access(env, regno, meta->map_ptr->value_size, false, - NULL); + meta); } else if (arg_type_is_mem_size(arg_type)) { bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO); @@ -2453,6 +2456,13 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (func_id != BPF_FUNC_sk_select_reuseport) goto error; break; + case BPF_MAP_TYPE_QUEUE: + case BPF_MAP_TYPE_STACK: + if (func_id != BPF_FUNC_map_peek_elem && + func_id != BPF_FUNC_map_pop_elem && + func_id != BPF_FUNC_map_push_elem) + goto error; + break; default: break; } @@ -2509,6 +2519,13 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) goto error; break; + case BPF_FUNC_map_peek_elem: + case BPF_FUNC_map_pop_elem: + case BPF_FUNC_map_push_elem: + if (map->map_type != BPF_MAP_TYPE_QUEUE && + map->map_type != BPF_MAP_TYPE_STACK) + goto error; + break; default: break; } @@ -2825,7 +2842,10 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta, if (func_id != BPF_FUNC_tail_call && func_id != BPF_FUNC_map_lookup_elem && func_id != BPF_FUNC_map_update_elem && - func_id != BPF_FUNC_map_delete_elem) + func_id != BPF_FUNC_map_delete_elem && + func_id != BPF_FUNC_map_push_elem && + func_id != BPF_FUNC_map_pop_elem && + func_id != BPF_FUNC_map_peek_elem) return 0; if (meta->map_ptr == NULL) { diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 83c4e76f513af33c179f7d9fa358b6e9f508b7f7..3fe987fae55d93e69f69d5317fa708bcd5c69d79 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -557,6 +557,12 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_map_update_elem_proto; case BPF_FUNC_map_delete_elem: return &bpf_map_delete_elem_proto; + case BPF_FUNC_map_push_elem: + return &bpf_map_push_elem_proto; + case BPF_FUNC_map_pop_elem: + return &bpf_map_pop_elem_proto; + case BPF_FUNC_map_peek_elem: + return &bpf_map_peek_elem_proto; case BPF_FUNC_probe_read: return &bpf_probe_read_proto; case BPF_FUNC_ktime_get_ns: diff --git a/net/core/filter.c b/net/core/filter.c index d85e3c6f29d247a0e505e5e4bf575431d3942377..12bfcae4920d481ca53f9dc579dc2896761e2644 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4856,6 +4856,12 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_map_update_elem_proto; case BPF_FUNC_map_delete_elem: return &bpf_map_delete_elem_proto; + case BPF_FUNC_map_push_elem: + return &bpf_map_push_elem_proto; + case BPF_FUNC_map_pop_elem: + return &bpf_map_pop_elem_proto; + case BPF_FUNC_map_peek_elem: + return &bpf_map_peek_elem_proto; case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; case BPF_FUNC_get_smp_processor_id: @@ -6850,6 +6856,25 @@ static u32 sk_skb_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_LDX_MEM(BPF_SIZEOF(void *), si->dst_reg, si->src_reg, off); break; + case offsetof(struct __sk_buff, cb[0]) ... + offsetofend(struct __sk_buff, cb[4]) - 1: + BUILD_BUG_ON(sizeof_field(struct sk_skb_cb, data) < 20); + BUILD_BUG_ON((offsetof(struct sk_buff, cb) + + offsetof(struct sk_skb_cb, data)) % + sizeof(__u64)); + + prog->cb_access = 1; + off = si->off; + off -= offsetof(struct __sk_buff, cb[0]); + off += offsetof(struct sk_buff, cb); + off += offsetof(struct sk_skb_cb, data); + if (type == BPF_WRITE) + *insn++ = BPF_STX_MEM(BPF_SIZE(si->code), si->dst_reg, + si->src_reg, off); + else + *insn++ = BPF_LDX_MEM(BPF_SIZE(si->code), si->dst_reg, + si->src_reg, off); + break; default: return bpf_convert_ctx_access(type, si, insn_buf, prog, target_size); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index ed3de15d8c874d00e6eeb451276661c17eae8e7d..1d30115150b13d079281a1b85ba972f916f805fe 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -26,6 +26,7 @@ int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len, int elem_first_coalesce) { struct page_frag *pfrag = sk_page_frag(sk); + u32 osize = msg->sg.size; int ret = 0; len -= msg->sg.size; @@ -34,13 +35,17 @@ int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len, u32 orig_offset; int use, i; - if (!sk_page_frag_refill(sk, pfrag)) - return -ENOMEM; + if (!sk_page_frag_refill(sk, pfrag)) { + ret = -ENOMEM; + goto msg_trim; + } orig_offset = pfrag->offset; use = min_t(int, len, pfrag->size - orig_offset); - if (!sk_wmem_schedule(sk, use)) - return -ENOMEM; + if (!sk_wmem_schedule(sk, use)) { + ret = -ENOMEM; + goto msg_trim; + } i = msg->sg.end; sk_msg_iter_var_prev(i); @@ -70,6 +75,10 @@ int sk_msg_alloc(struct sock *sk, struct sk_msg *msg, int len, } return ret; + +msg_trim: + sk_msg_trim(sk, msg, osize); + return ret; } EXPORT_SYMBOL_GPL(sk_msg_alloc); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 402ebfe273a14f0085af83a3b984d54d1ab6475f..79f39f8e22b5962d4eba8353084413c5e1c65469 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -249,11 +249,13 @@ static void sock_map_free(struct bpf_map *map) sk = xchg(psk, NULL); if (sk) { + sock_hold(sk); lock_sock(sk); rcu_read_lock(); sock_map_unref(sk, psk); rcu_read_unlock(); release_sock(sk); + sock_put(sk); } } @@ -866,6 +868,7 @@ static void sock_hash_free(struct bpf_map *map) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct bpf_htab_bucket *bucket; + struct hlist_head unlink_list; struct bpf_htab_elem *elem; struct hlist_node *node; int i; @@ -877,13 +880,32 @@ static void sock_hash_free(struct bpf_map *map) synchronize_rcu(); for (i = 0; i < htab->buckets_num; i++) { bucket = sock_hash_select_bucket(htab, i); - hlist_for_each_entry_safe(elem, node, &bucket->head, node) { - hlist_del_rcu(&elem->node); + + /* We are racing with sock_hash_delete_from_link to + * enter the spin-lock critical section. Every socket on + * the list is still linked to sockhash. Since link + * exists, psock exists and holds a ref to socket. That + * lets us to grab a socket ref too. + */ + raw_spin_lock_bh(&bucket->lock); + hlist_for_each_entry(elem, &bucket->head, node) + sock_hold(elem->sk); + hlist_move_list(&bucket->head, &unlink_list); + raw_spin_unlock_bh(&bucket->lock); + + /* Process removed entries out of atomic context to + * block for socket lock before deleting the psock's + * link to sockhash. + */ + hlist_for_each_entry_safe(elem, node, &unlink_list, node) { + hlist_del(&elem->node); lock_sock(elem->sk); rcu_read_lock(); sock_map_unref(elem->sk, elem); rcu_read_unlock(); release_sock(elem->sk); + sock_put(elem->sk); + sock_hash_free_elem(htab, elem); } } diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 30284cae4b2d76d5fa4e03122a5eb901e4214d0f..116484c92d40943d797656cd3c947154e896cd06 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -28,6 +28,9 @@ static int tcp_bpf_wait_data(struct sock *sk, struct sk_psock *psock, DEFINE_WAIT_FUNC(wait, woken_wake_function); int ret = 0; + if (sk->sk_shutdown & RCV_SHUTDOWN) + return 1; + if (!timeo) return ret; @@ -108,14 +111,17 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, struct sk_psock *psock; int copied, ret; + if (unlikely(flags & MSG_ERRQUEUE)) + return inet_recv_error(sk, msg, len, addr_len); + psock = sk_psock_get(sk); if (unlikely(!psock)) return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); - if (unlikely(flags & MSG_ERRQUEUE)) - return inet_recv_error(sk, msg, len, addr_len); if (!skb_queue_empty(&sk->sk_receive_queue) && - sk_psock_queue_empty(psock)) - return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); + sk_psock_queue_empty(psock)) { + sk_psock_put(sk, psock); + return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); + } lock_sock(sk); msg_bytes_ready: copied = __tcp_bpf_recvmsg(sk, psock, msg, len); @@ -180,14 +186,16 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, tmp->sg.end = i; if (apply) { apply_bytes -= size; - if (!apply_bytes) + if (!apply_bytes) { + if (sge->length) + sk_msg_iter_var_prev(i); break; + } } } while (i != msg->sg.end); if (!ret) { msg->sg.start = i; - msg->sg.size -= apply_bytes; sk_psock_queue_msg(psock, tmp); sk->sk_data_ready(sk); } else { @@ -264,10 +272,9 @@ int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg, struct sk_psock *psock = sk_psock_get(sk); int ret; - if (unlikely(!psock)) { - sk_msg_free(sk, msg); - return 0; - } + if (unlikely(!psock)) + return -EPIPE; + ret = ingress ? bpf_tcp_ingress(sk, psock, msg, bytes, flags) : tcp_bpf_push_locked(sk, msg, bytes, flags, false); sk_psock_put(sk, psock); @@ -280,7 +287,8 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, { bool cork = false, enospc = msg->sg.start == msg->sg.end; struct sock *sk_redir; - u32 tosend; + u32 tosend, origsize, sent; + u32 eval; int ret; more_data: @@ -303,6 +311,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, tosend = msg->sg.size; if (psock->apply_bytes && psock->apply_bytes < tosend) tosend = psock->apply_bytes; + eval = __SK_NONE; switch (psock->eval) { case __SK_PASS: @@ -316,13 +325,26 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, case __SK_REDIRECT: sk_redir = psock->sk_redir; sk_msg_apply_bytes(psock, tosend); + if (!psock->apply_bytes) { + /* Clean up before releasing the sock lock. */ + eval = psock->eval; + psock->eval = __SK_NONE; + psock->sk_redir = NULL; + } if (psock->cork) { cork = true; psock->cork = NULL; } sk_msg_return(sk, msg, tosend); release_sock(sk); + + origsize = msg->sg.size; ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags); + sent = origsize - msg->sg.size; + + if (eval == __SK_REDIRECT) + sock_put(sk_redir); + lock_sock(sk); if (unlikely(ret < 0)) { int free = sk_msg_free_nocharge(sk, msg); @@ -355,8 +377,11 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, } if (msg && msg->sg.data[msg->sg.start].page_link && - msg->sg.data[msg->sg.start].length) + msg->sg.data[msg->sg.start].length) { + if (eval == __SK_REDIRECT) + sk_mem_charge(sk, tosend - sent); goto more_data; + } } return ret; } @@ -592,7 +617,7 @@ static int __init tcp_bpf_v4_build_proto(void) tcp_bpf_rebuild_protos(tcp_bpf_prots[TCP_BPF_IPV4], &tcp_prot); return 0; } -core_initcall(tcp_bpf_v4_build_proto); +late_initcall(tcp_bpf_v4_build_proto); static void tcp_bpf_update_sk_prot(struct sock *sk, struct sk_psock *psock) { diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 667162acf8449f5e6966885774c63fb304c8abea..e46bad9bc160cf9668d74b1946d2de0f6afb31cb 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -198,10 +198,10 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, retv = -EBUSY; break; } - break; } else { break; } + if (sk->sk_state != TCP_ESTABLISHED) { retv = -ENOTCONN; break; diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index 0f4e427928781881f5fab3c281df621f5123352e..e57d25191c4d3e6a7716e36e4d36ddb4c12c0158 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -29,18 +29,10 @@ static struct workqueue_struct *strp_wq; -struct _strp_msg { - /* Internal cb structure. struct strp_msg must be first for passing - * to upper layer. - */ - struct strp_msg strp; - int accum_len; -}; - static inline struct _strp_msg *_strp_msg(struct sk_buff *skb) { return (struct _strp_msg *)((void *)skb->cb + - offsetof(struct qdisc_skb_cb, data)); + offsetof(struct sk_skb_cb, strp)); } /* Lower lock held */ diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index a6258bc8ec4f57d0cf1d5b35a95030fd66cbe881..3497f2d803284b1a80c89be3142ee4cdbead8355 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -15,13 +15,15 @@ SYNOPSIS *OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-f** | **--bpffs** } } *COMMANDS* := - { **show** | **list** | **dump** | **update** | **lookup** | **getnext** | **delete** - | **pin** | **help** } + { **show** | **list** | **create** | **dump** | **update** | **lookup** | **getnext** + | **delete** | **pin** | **help** } MAP COMMANDS ============= | **bpftool** **map { show | list }** [*MAP*] +| **bpftool** **map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* \ +| **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**dev** *NAME*] | **bpftool** **map dump** *MAP* | **bpftool** **map update** *MAP* **key** *DATA* **value** *VALUE* [*UPDATE_FLAGS*] | **bpftool** **map lookup** *MAP* **key** *DATA* @@ -36,6 +38,11 @@ MAP COMMANDS | *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } | *VALUE* := { *DATA* | *MAP* | *PROG* } | *UPDATE_FLAGS* := { **any** | **exist** | **noexist** } +| *TYPE* := { **hash** | **array** | **prog_array** | **perf_event_array** | **percpu_hash** +| | **percpu_array** | **stack_trace** | **cgroup_array** | **lru_hash** +| | **lru_percpu_hash** | **lpm_trie** | **array_of_maps** | **hash_of_maps** +| | **devmap** | **sockmap** | **cpumap** | **xskmap** | **sockhash** +| | **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage** } DESCRIPTION =========== @@ -47,6 +54,10 @@ DESCRIPTION Output will start with map ID followed by map type and zero or more named attributes (depending on kernel version). + **bpftool map create** *FILE* **type** *TYPE* **key** *KEY_SIZE* **value** *VALUE_SIZE* **entries** *MAX_ENTRIES* **name** *NAME* [**flags** *FLAGS*] [**dev** *NAME*] + Create a new map with given parameters and pin it to *bpffs* + as *FILE*. + **bpftool map dump** *MAP* Dump all entries in a given *MAP*. diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 64156a16d5300b64e0d9c2f5297605b88e6265b2..12c803003ab29fea648801c09b2e063621e8aa96 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -25,6 +25,8 @@ MAP COMMANDS | **bpftool** **prog dump jited** *PROG* [{**file** *FILE* | **opcodes**}] | **bpftool** **prog pin** *PROG* *FILE* | **bpftool** **prog load** *OBJ* *FILE* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*] +| **bpftool** **prog attach** *PROG* *ATTACH_TYPE* *MAP* +| **bpftool** **prog detach** *PROG* *ATTACH_TYPE* *MAP* | **bpftool** **prog help** | | *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } @@ -37,6 +39,7 @@ MAP COMMANDS | **cgroup/bind4** | **cgroup/bind6** | **cgroup/post_bind4** | **cgroup/post_bind6** | | **cgroup/connect4** | **cgroup/connect6** | **cgroup/sendmsg4** | **cgroup/sendmsg6** | } +| *ATTACH_TYPE* := { **msg_verdict** | **skb_verdict** | **skb_parse** } DESCRIPTION @@ -90,6 +93,14 @@ DESCRIPTION Note: *FILE* must be located in *bpffs* mount. + **bpftool prog attach** *PROG* *ATTACH_TYPE* *MAP* + Attach bpf program *PROG* (with type specified by *ATTACH_TYPE*) + to the map *MAP*. + + **bpftool prog detach** *PROG* *ATTACH_TYPE* *MAP* + Detach bpf program *PROG* (with type specified by *ATTACH_TYPE*) + from the map *MAP*. + **bpftool prog help** Print short help message. diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index 8dda77daeda968cc0cbfdf33c8d6537bc1842cf4..04cd4f92ab89c9dd8009180c3e4601c7b1956d1e 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -22,11 +22,11 @@ SYNOPSIS | { **-j** | **--json** } [{ **-p** | **--pretty** }] } *MAP-COMMANDS* := - { **show** | **list** | **dump** | **update** | **lookup** | **getnext** | **delete** - | **pin** | **event_pipe** | **help** } + { **show** | **list** | **create** | **dump** | **update** | **lookup** | **getnext** + | **delete** | **pin** | **event_pipe** | **help** } *PROG-COMMANDS* := { **show** | **list** | **dump jited** | **dump xlated** | **pin** - | **load** | **help** } + | **load** | **attach** | **detach** | **help** } *CGROUP-COMMANDS* := { **show** | **list** | **attach** | **detach** | **help** } @@ -57,6 +57,10 @@ OPTIONS -p, --pretty Generate human-readable JSON output. Implies **-j**. + -m, --mapcompat + Allow loading maps with unknown map definitions. + + SEE ALSO ======== **bpftool-map**\ (8), **bpftool-prog**\ (8), **bpftool-cgroup**\ (8) diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index ec577af2e5f0dfca1fed9fcdb314a861f889e898..9273c4afbc82be4bab8a3553d8af7fa08bd34b00 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -184,7 +184,7 @@ _bpftool() # Deal with options if [[ ${words[cword]} == -* ]]; then - local c='--version --json --pretty --bpffs' + local c='--version --json --pretty --bpffs --mapcompat' COMPREPLY=( $( compgen -W "$c" -- "$cur" ) ) return 0 fi @@ -243,16 +243,20 @@ _bpftool() # Completion depends on object and command in use case $object in prog) - if [[ $command != "load" ]]; then - case $prev in - id) - _bpftool_get_prog_ids - return 0 - ;; - esac - fi + # Complete id, only for subcommands that use prog (but no map) ids + case $command in + show|list|dump|pin) + case $prev in + id) + _bpftool_get_prog_ids + return 0 + ;; + esac + ;; + esac local PROG_TYPE='id pinned tag' + local MAP_TYPE='id pinned' case $command in show|list) [[ $prev != "$command" ]] && return 0 @@ -292,6 +296,45 @@ _bpftool() fi return 0 ;; + attach|detach) + case $cword in + 3) + COMPREPLY=( $( compgen -W "$PROG_TYPE" -- "$cur" ) ) + return 0 + ;; + 4) + case $prev in + id) + _bpftool_get_prog_ids + ;; + pinned) + _filedir + ;; + esac + return 0 + ;; + 5) + COMPREPLY=( $( compgen -W 'msg_verdict skb_verdict \ + skb_parse flow_dissector' -- "$cur" ) ) + return 0 + ;; + 6) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + return 0 + ;; + 7) + case $prev in + id) + _bpftool_get_map_ids + ;; + pinned) + _filedir + ;; + esac + return 0 + ;; + esac + ;; load) local obj @@ -347,7 +390,7 @@ _bpftool() ;; *) [[ $prev == $object ]] && \ - COMPREPLY=( $( compgen -W 'dump help pin load \ + COMPREPLY=( $( compgen -W 'dump help pin attach detach load \ show list' -- "$cur" ) ) ;; esac @@ -370,6 +413,42 @@ _bpftool() ;; esac ;; + create) + case $prev in + $command) + _filedir + return 0 + ;; + type) + COMPREPLY=( $( compgen -W 'hash array prog_array \ + perf_event_array percpu_hash percpu_array \ + stack_trace cgroup_array lru_hash \ + lru_percpu_hash lpm_trie array_of_maps \ + hash_of_maps devmap sockmap cpumap xskmap \ + sockhash cgroup_storage reuseport_sockarray \ + percpu_cgroup_storage' -- \ + "$cur" ) ) + return 0 + ;; + key|value|flags|name|entries) + return 0 + ;; + dev) + _sysfs_get_netdevs + return 0 + ;; + *) + _bpftool_once_attr 'type' + _bpftool_once_attr 'key' + _bpftool_once_attr 'value' + _bpftool_once_attr 'entries' + _bpftool_once_attr 'name' + _bpftool_once_attr 'flags' + _bpftool_once_attr 'dev' + return 0 + ;; + esac + ;; lookup|getnext|delete) case $prev in $command) @@ -483,7 +562,7 @@ _bpftool() *) [[ $prev == $object ]] && \ COMPREPLY=( $( compgen -W 'delete dump getnext help \ - lookup pin event_pipe show list update' -- \ + lookup pin event_pipe show list update create' -- \ "$cur" ) ) ;; esac diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 158469f57461d6fb52622df29b271e54c590a6db..e7bba3b7aaca26f3011fa2222b3fdea4115e9bc1 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -555,7 +555,9 @@ static int read_sysfs_netdev_hex_int(char *devname, const char *entry_name) return read_sysfs_hex_int(full_path); } -const char *ifindex_to_bfd_name_ns(__u32 ifindex, __u64 ns_dev, __u64 ns_ino) +const char * +ifindex_to_bfd_params(__u32 ifindex, __u64 ns_dev, __u64 ns_ino, + const char **opt) { char devname[IF_NAMESIZE]; int vendor_id; @@ -580,6 +582,7 @@ const char *ifindex_to_bfd_name_ns(__u32 ifindex, __u64 ns_dev, __u64 ns_ino) device_id != 0x6000 && device_id != 0x6003) p_info("Unknown NFP device ID, assuming it is NFP-6xxx arch"); + *opt = "ctx4"; return "NFP-6xxx"; default: p_err("Can't get bfd arch name for device vendor id 0x%04x", @@ -619,3 +622,24 @@ void print_dev_json(__u32 ifindex, __u64 ns_dev, __u64 ns_inode) jsonw_string_field(json_wtr, "ifname", name); jsonw_end_object(json_wtr); } + +int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what) +{ + char *endptr; + + NEXT_ARGP(); + + if (*val) { + p_err("%s already specified", what); + return -1; + } + + *val = strtoul(**argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as %s", **argv, what); + return -1; + } + NEXT_ARGP(); + + return 0; +} diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c index 73d7252729fad65bb2cdbda96ad625156bfd516d..b61f6b475e9579a8c378d93e29a5fdc7a8db7b6c 100644 --- a/tools/bpf/bpftool/jit_disasm.c +++ b/tools/bpf/bpftool/jit_disasm.c @@ -80,7 +80,7 @@ static int fprintf_json(void *out, const char *fmt, ...) } void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, - const char *arch) + const char *arch, const char *disassembler_options) { disassembler_ftype disassemble; struct disassemble_info info; @@ -119,6 +119,8 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, info.arch = bfd_get_arch(bfdf); info.mach = bfd_get_mach(bfdf); + if (disassembler_options) + info.disassembler_options = disassembler_options; info.buffer = image; info.buffer_length = len; diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index 79dc3f1935470f9fc3bda5a4afc5e91d7fb0f5f9..828dde30e9ecd17f5fb6df5312cc96356d7e3f4c 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -55,6 +55,7 @@ json_writer_t *json_wtr; bool pretty_output; bool json_output; bool show_pinned; +int bpf_flags; struct pinned_obj_table prog_table; struct pinned_obj_table map_table; @@ -341,6 +342,7 @@ int main(int argc, char **argv) { "pretty", no_argument, NULL, 'p' }, { "version", no_argument, NULL, 'V' }, { "bpffs", no_argument, NULL, 'f' }, + { "mapcompat", no_argument, NULL, 'm' }, { 0 } }; int opt, ret; @@ -355,7 +357,7 @@ int main(int argc, char **argv) hash_init(map_table.table); opterr = 0; - while ((opt = getopt_long(argc, argv, "Vhpjf", + while ((opt = getopt_long(argc, argv, "Vhpjfm", options, NULL)) >= 0) { switch (opt) { case 'V': @@ -379,6 +381,9 @@ int main(int argc, char **argv) case 'f': show_pinned = true; break; + case 'm': + bpf_flags = MAPS_RELAX_COMPAT; + break; default: p_err("unrecognized option '%s'", argv[optind - 1]); if (json_output) diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 38413a16ab92cc9dd3fec59c63f3661288a91bde..a8bf1e2d9818debfc200701f21d438d432e093fc 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -74,7 +74,7 @@ #define HELP_SPEC_PROGRAM \ "PROG := { id PROG_ID | pinned FILE | tag PROG_TAG }" #define HELP_SPEC_OPTIONS \ - "OPTIONS := { {-j|--json} [{-p|--pretty}] | {-f|--bpffs} }" + "OPTIONS := { {-j|--json} [{-p|--pretty}] | {-f|--bpffs} | {-m|--mapcompat}" #define HELP_SPEC_MAP \ "MAP := { id MAP_ID | pinned FILE }" @@ -89,6 +89,7 @@ extern const char *bin_name; extern json_writer_t *json_wtr; extern bool json_output; extern bool show_pinned; +extern int bpf_flags; extern struct pinned_obj_table prog_table; extern struct pinned_obj_table map_table; @@ -138,18 +139,21 @@ int do_cgroup(int argc, char **arg); int do_perf(int argc, char **arg); int do_net(int argc, char **arg); +int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what); int prog_parse_fd(int *argc, char ***argv); int map_parse_fd(int *argc, char ***argv); int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len); void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, - const char *arch); + const char *arch, const char *disassembler_options); void print_data_json(uint8_t *data, size_t len); void print_hex_data_json(uint8_t *data, size_t len); unsigned int get_page_size(void); unsigned int get_possible_cpus(void); -const char *ifindex_to_bfd_name_ns(__u32 ifindex, __u64 ns_dev, __u64 ns_ino); +const char * +ifindex_to_bfd_params(__u32 ifindex, __u64 ns_dev, __u64 ns_ino, + const char **opt); struct btf_dumper { const struct btf *btf; diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 37ca559e49cc2ff2d42d0ad124c215e15c8da3a2..c5e2c5ef6acbabb88f6d7ac11fc5df7e6880127c 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include #include @@ -94,6 +95,17 @@ static bool map_is_map_of_progs(__u32 type) return type == BPF_MAP_TYPE_PROG_ARRAY; } +static int map_type_from_str(const char *type) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(map_type_name); i++) + /* Don't allow prefixing in case of possible future shadowing */ + if (map_type_name[i] && !strcmp(map_type_name[i], type)) + return i; + return -1; +} + static void *alloc_value(struct bpf_map_info *info) { if (map_is_per_cpu(info->type)) @@ -1045,6 +1057,95 @@ static int do_pin(int argc, char **argv) return err; } +static int do_create(int argc, char **argv) +{ + struct bpf_create_map_attr attr = { NULL, }; + const char *pinfile; + int err, fd; + + if (!REQ_ARGS(7)) + return -1; + pinfile = GET_ARG(); + + while (argc) { + if (!REQ_ARGS(2)) + return -1; + + if (is_prefix(*argv, "type")) { + NEXT_ARG(); + + if (attr.map_type) { + p_err("map type already specified"); + return -1; + } + + attr.map_type = map_type_from_str(*argv); + if ((int)attr.map_type < 0) { + p_err("unrecognized map type: %s", *argv); + return -1; + } + NEXT_ARG(); + } else if (is_prefix(*argv, "name")) { + NEXT_ARG(); + attr.name = GET_ARG(); + } else if (is_prefix(*argv, "key")) { + if (parse_u32_arg(&argc, &argv, &attr.key_size, + "key size")) + return -1; + } else if (is_prefix(*argv, "value")) { + if (parse_u32_arg(&argc, &argv, &attr.value_size, + "value size")) + return -1; + } else if (is_prefix(*argv, "entries")) { + if (parse_u32_arg(&argc, &argv, &attr.max_entries, + "max entries")) + return -1; + } else if (is_prefix(*argv, "flags")) { + if (parse_u32_arg(&argc, &argv, &attr.map_flags, + "flags")) + return -1; + } else if (is_prefix(*argv, "dev")) { + NEXT_ARG(); + + if (attr.map_ifindex) { + p_err("offload device already specified"); + return -1; + } + + attr.map_ifindex = if_nametoindex(*argv); + if (!attr.map_ifindex) { + p_err("unrecognized netdevice '%s': %s", + *argv, strerror(errno)); + return -1; + } + NEXT_ARG(); + } else { + p_err("unknown arg %s", *argv); + return -1; + } + } + + if (!attr.name) { + p_err("map name not specified"); + return -1; + } + + fd = bpf_create_map_xattr(&attr); + if (fd < 0) { + p_err("map create failed: %s", strerror(errno)); + return -1; + } + + err = do_pin_fd(fd, pinfile); + close(fd); + if (err) + return err; + + if (json_output) + jsonw_null(json_wtr); + return 0; +} + static int do_help(int argc, char **argv) { if (json_output) { @@ -1054,6 +1155,9 @@ static int do_help(int argc, char **argv) fprintf(stderr, "Usage: %s %s { show | list } [MAP]\n" + " %s %s create FILE type TYPE key KEY_SIZE value VALUE_SIZE \\\n" + " entries MAX_ENTRIES name NAME [flags FLAGS] \\\n" + " [dev NAME]\n" " %s %s dump MAP\n" " %s %s update MAP key DATA value VALUE [UPDATE_FLAGS]\n" " %s %s lookup MAP key DATA\n" @@ -1068,11 +1172,17 @@ static int do_help(int argc, char **argv) " " HELP_SPEC_PROGRAM "\n" " VALUE := { DATA | MAP | PROG }\n" " UPDATE_FLAGS := { any | exist | noexist }\n" + " TYPE := { hash | array | prog_array | perf_event_array | percpu_hash |\n" + " percpu_array | stack_trace | cgroup_array | lru_hash |\n" + " lru_percpu_hash | lpm_trie | array_of_maps | hash_of_maps |\n" + " devmap | sockmap | cpumap | xskmap | sockhash |\n" + " cgroup_storage | reuseport_sockarray | percpu_cgroup_storage }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], - bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2]); + bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], + bin_name, argv[-2]); return 0; } @@ -1088,6 +1198,7 @@ static const struct cmd cmds[] = { { "delete", do_delete }, { "pin", do_pin }, { "event_pipe", do_event_pipe }, + { "create", do_create }, { 0 } }; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 108295f97d09ba2c02e4e79eff820e22d8ac8cd7..3a2bac48a9651c0eeb7bde55952e51deb818222b 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -77,6 +77,26 @@ static const char * const prog_type_name[] = { [BPF_PROG_TYPE_FLOW_DISSECTOR] = "flow_dissector", }; +static const char * const attach_type_strings[] = { + [BPF_SK_SKB_STREAM_PARSER] = "stream_parser", + [BPF_SK_SKB_STREAM_VERDICT] = "stream_verdict", + [BPF_SK_MSG_VERDICT] = "msg_verdict", + [__MAX_BPF_ATTACH_TYPE] = NULL, +}; + +enum bpf_attach_type parse_attach_type(const char *str) +{ + enum bpf_attach_type type; + + for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) { + if (attach_type_strings[type] && + is_prefix(str, attach_type_strings[type])) + return type; + } + + return __MAX_BPF_ATTACH_TYPE; +} + static void print_boot_time(__u64 nsecs, char *buf, unsigned int size) { struct timespec real_time_ts, boot_time_ts; @@ -432,6 +452,7 @@ static int do_dump(int argc, char **argv) unsigned long *func_ksyms = NULL; struct bpf_prog_info info = {}; unsigned int *func_lens = NULL; + const char *disasm_opt = NULL; unsigned int nr_func_ksyms; unsigned int nr_func_lens; struct dump_data dd = {}; @@ -590,9 +611,10 @@ static int do_dump(int argc, char **argv) const char *name = NULL; if (info.ifindex) { - name = ifindex_to_bfd_name_ns(info.ifindex, - info.netns_dev, - info.netns_ino); + name = ifindex_to_bfd_params(info.ifindex, + info.netns_dev, + info.netns_ino, + &disasm_opt); if (!name) goto err_free; } @@ -634,7 +656,8 @@ static int do_dump(int argc, char **argv) printf("%s:\n", sym_name); } - disasm_print_insn(img, lens[i], opcodes, name); + disasm_print_insn(img, lens[i], opcodes, name, + disasm_opt); img += lens[i]; if (json_output) @@ -646,7 +669,8 @@ static int do_dump(int argc, char **argv) if (json_output) jsonw_end_array(json_wtr); } else { - disasm_print_insn(buf, *member_len, opcodes, name); + disasm_print_insn(buf, *member_len, opcodes, name, + disasm_opt); } } else if (visual) { if (json_output) @@ -700,6 +724,77 @@ int map_replace_compar(const void *p1, const void *p2) return a->idx - b->idx; } +static int do_attach(int argc, char **argv) +{ + enum bpf_attach_type attach_type; + int err, mapfd, progfd; + + if (!REQ_ARGS(5)) { + p_err("too few parameters for map attach"); + return -EINVAL; + } + + progfd = prog_parse_fd(&argc, &argv); + if (progfd < 0) + return progfd; + + attach_type = parse_attach_type(*argv); + if (attach_type == __MAX_BPF_ATTACH_TYPE) { + p_err("invalid attach type"); + return -EINVAL; + } + NEXT_ARG(); + + mapfd = map_parse_fd(&argc, &argv); + if (mapfd < 0) + return mapfd; + + err = bpf_prog_attach(progfd, mapfd, attach_type, 0); + if (err) { + p_err("failed prog attach to map"); + return -EINVAL; + } + + if (json_output) + jsonw_null(json_wtr); + return 0; +} + +static int do_detach(int argc, char **argv) +{ + enum bpf_attach_type attach_type; + int err, mapfd, progfd; + + if (!REQ_ARGS(5)) { + p_err("too few parameters for map detach"); + return -EINVAL; + } + + progfd = prog_parse_fd(&argc, &argv); + if (progfd < 0) + return progfd; + + attach_type = parse_attach_type(*argv); + if (attach_type == __MAX_BPF_ATTACH_TYPE) { + p_err("invalid attach type"); + return -EINVAL; + } + NEXT_ARG(); + + mapfd = map_parse_fd(&argc, &argv); + if (mapfd < 0) + return mapfd; + + err = bpf_prog_detach2(progfd, mapfd, attach_type); + if (err) { + p_err("failed prog detach from map"); + return -EINVAL; + } + + if (json_output) + jsonw_null(json_wtr); + return 0; +} static int do_load(int argc, char **argv) { enum bpf_attach_type expected_attach_type; @@ -824,7 +919,7 @@ static int do_load(int argc, char **argv) } } - obj = bpf_object__open_xattr(&attr); + obj = __bpf_object__open_xattr(&attr, bpf_flags); if (IS_ERR_OR_NULL(obj)) { p_err("failed to open object file"); goto err_free_reuse_maps; @@ -949,6 +1044,8 @@ static int do_help(int argc, char **argv) " %s %s pin PROG FILE\n" " %s %s load OBJ FILE [type TYPE] [dev NAME] \\\n" " [map { idx IDX | name NAME } MAP]\n" + " %s %s attach PROG ATTACH_TYPE MAP\n" + " %s %s detach PROG ATTACH_TYPE MAP\n" " %s %s help\n" "\n" " " HELP_SPEC_MAP "\n" @@ -960,10 +1057,12 @@ static int do_help(int argc, char **argv) " cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n" " cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n" " cgroup/sendmsg4 | cgroup/sendmsg6 }\n" + " ATTACH_TYPE := { msg_verdict | skb_verdict | skb_parse }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], - bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2]); + bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], + bin_name, argv[-2], bin_name, argv[-2]); return 0; } @@ -975,6 +1074,8 @@ static const struct cmd cmds[] = { { "dump", do_dump }, { "pin", do_pin }, { "load", do_load }, + { "attach", do_attach }, + { "detach", do_detach }, { 0 } }; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 1f5c94f443ca94040de4511174e4efa9dc6bae46..e914942334d0f3d92a5f5a5c39c7f2e7f5e9c9bf 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -103,6 +103,7 @@ enum bpf_cmd { BPF_BTF_LOAD, BPF_BTF_GET_FD_BY_ID, BPF_TASK_FD_QUERY, + BPF_MAP_LOOKUP_AND_DELETE_ELEM, }; enum bpf_map_type { @@ -128,6 +129,8 @@ enum bpf_map_type { BPF_MAP_TYPE_CGROUP_STORAGE, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, + BPF_MAP_TYPE_QUEUE, + BPF_MAP_TYPE_STACK, }; enum bpf_prog_type { @@ -462,6 +465,28 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * + * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags) + * Description + * Push an element *value* in *map*. *flags* is one of: + * + * **BPF_EXIST** + * If the queue/stack is full, the oldest element is removed to + * make room for this. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_pop_elem(struct bpf_map *map, void *value) + * Description + * Pop an element from *map*. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_peek_elem(struct bpf_map *map, void *value) + * Description + * Get an element from *map* without removing it. + * Return + * 0 on success, or a negative error in case of failure. + * * int bpf_probe_read(void *dst, u32 size, const void *src) * Description * For tracing programs, safely attempt to read *size* bytes from @@ -1433,7 +1458,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * int bpf_skb_adjust_room(struct sk_buff *skb, u32 len_diff, u32 mode, u64 flags) + * int bpf_skb_adjust_room(struct sk_buff *skb, s32 len_diff, u32 mode, u64 flags) * Description * Grow or shrink the room for data in the packet associated to * *skb* by *len_diff*, and according to the selected *mode*. @@ -2311,7 +2336,10 @@ union bpf_attr { FN(skb_ancestor_cgroup_id), \ FN(sk_lookup_tcp), \ FN(sk_lookup_udp), \ - FN(sk_release), + FN(sk_release), \ + FN(map_push_elem), \ + FN(map_pop_elem), \ + FN(map_peek_elem), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index b5ff5565072431b16887d0056c0f96c2fbacaa9f..453df2623751b5cd701d3701699d60a7d77affee 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -125,6 +125,7 @@ override CFLAGS += $(EXTRA_WARNINGS) override CFLAGS += -Werror -Wall override CFLAGS += -fPIC override CFLAGS += $(INCLUDES) +override CFLAGS += -fvisibility=hidden ifeq ($(VERBOSE),1) Q = diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index f1ba022fd659e30a507daf0c603fbd3900f01d8d..bd003cc91f940b2852730f527a63f4e4bb1473d6 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -300,6 +300,18 @@ int bpf_map_lookup_elem(int fd, const void *key, void *value) return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr)); } +int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value) +{ + union bpf_attr attr; + + bzero(&attr, sizeof(attr)); + attr.map_fd = fd; + attr.key = ptr_to_u64(key); + attr.value = ptr_to_u64(value); + + return sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr)); +} + int bpf_map_delete_elem(int fd, const void *key) { union bpf_attr attr; diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index f57a2a09761df2022d4ce24ba996b53ee073bb1b..7ddc8a2d19810a61c20ee8980783cfa49b896842 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -28,6 +28,10 @@ #include #include +#ifndef LIBBPF_API +#define LIBBPF_API __attribute__((visibility("default"))) +#endif + struct bpf_create_map_attr { const char *name; enum bpf_map_type map_type; @@ -43,21 +47,24 @@ struct bpf_create_map_attr { __u32 inner_map_fd; }; -int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr); -int bpf_create_map_node(enum bpf_map_type map_type, const char *name, - int key_size, int value_size, int max_entries, - __u32 map_flags, int node); -int bpf_create_map_name(enum bpf_map_type map_type, const char *name, - int key_size, int value_size, int max_entries, - __u32 map_flags); -int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, - int max_entries, __u32 map_flags); -int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, - int key_size, int inner_map_fd, int max_entries, - __u32 map_flags, int node); -int bpf_create_map_in_map(enum bpf_map_type map_type, const char *name, - int key_size, int inner_map_fd, int max_entries, - __u32 map_flags); +LIBBPF_API int +bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr); +LIBBPF_API int bpf_create_map_node(enum bpf_map_type map_type, const char *name, + int key_size, int value_size, + int max_entries, __u32 map_flags, int node); +LIBBPF_API int bpf_create_map_name(enum bpf_map_type map_type, const char *name, + int key_size, int value_size, + int max_entries, __u32 map_flags); +LIBBPF_API int bpf_create_map(enum bpf_map_type map_type, int key_size, + int value_size, int max_entries, __u32 map_flags); +LIBBPF_API int bpf_create_map_in_map_node(enum bpf_map_type map_type, + const char *name, int key_size, + int inner_map_fd, int max_entries, + __u32 map_flags, int node); +LIBBPF_API int bpf_create_map_in_map(enum bpf_map_type map_type, + const char *name, int key_size, + int inner_map_fd, int max_entries, + __u32 map_flags); struct bpf_load_program_attr { enum bpf_prog_type prog_type; @@ -70,46 +77,56 @@ struct bpf_load_program_attr { __u32 prog_ifindex; }; +/* Flags to direct loading requirements */ +#define MAPS_RELAX_COMPAT 0x01 + /* Recommend log buffer size */ #define BPF_LOG_BUF_SIZE (256 * 1024) -int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, - char *log_buf, size_t log_buf_sz); -int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, - size_t insns_cnt, const char *license, - __u32 kern_version, char *log_buf, - size_t log_buf_sz); -int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, - size_t insns_cnt, int strict_alignment, - const char *license, __u32 kern_version, - char *log_buf, size_t log_buf_sz, int log_level); +LIBBPF_API int +bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, + char *log_buf, size_t log_buf_sz); +LIBBPF_API int bpf_load_program(enum bpf_prog_type type, + const struct bpf_insn *insns, size_t insns_cnt, + const char *license, __u32 kern_version, + char *log_buf, size_t log_buf_sz); +LIBBPF_API int bpf_verify_program(enum bpf_prog_type type, + const struct bpf_insn *insns, + size_t insns_cnt, int strict_alignment, + const char *license, __u32 kern_version, + char *log_buf, size_t log_buf_sz, + int log_level); -int bpf_map_update_elem(int fd, const void *key, const void *value, - __u64 flags); +LIBBPF_API int bpf_map_update_elem(int fd, const void *key, const void *value, + __u64 flags); -int bpf_map_lookup_elem(int fd, const void *key, void *value); -int bpf_map_delete_elem(int fd, const void *key); -int bpf_map_get_next_key(int fd, const void *key, void *next_key); -int bpf_obj_pin(int fd, const char *pathname); -int bpf_obj_get(const char *pathname); -int bpf_prog_attach(int prog_fd, int attachable_fd, enum bpf_attach_type type, - unsigned int flags); -int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type); -int bpf_prog_detach2(int prog_fd, int attachable_fd, enum bpf_attach_type type); -int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size, - void *data_out, __u32 *size_out, __u32 *retval, - __u32 *duration); -int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id); -int bpf_map_get_next_id(__u32 start_id, __u32 *next_id); -int bpf_prog_get_fd_by_id(__u32 id); -int bpf_map_get_fd_by_id(__u32 id); -int bpf_btf_get_fd_by_id(__u32 id); -int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len); -int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, - __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt); -int bpf_raw_tracepoint_open(const char *name, int prog_fd); -int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size, - bool do_log); -int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, __u32 *buf_len, - __u32 *prog_id, __u32 *fd_type, __u64 *probe_offset, - __u64 *probe_addr); +LIBBPF_API int bpf_map_lookup_elem(int fd, const void *key, void *value); +LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key, + void *value); +LIBBPF_API int bpf_map_delete_elem(int fd, const void *key); +LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key); +LIBBPF_API int bpf_obj_pin(int fd, const char *pathname); +LIBBPF_API int bpf_obj_get(const char *pathname); +LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd, + enum bpf_attach_type type, unsigned int flags); +LIBBPF_API int bpf_prog_detach(int attachable_fd, enum bpf_attach_type type); +LIBBPF_API int bpf_prog_detach2(int prog_fd, int attachable_fd, + enum bpf_attach_type type); +LIBBPF_API int bpf_prog_test_run(int prog_fd, int repeat, void *data, + __u32 size, void *data_out, __u32 *size_out, + __u32 *retval, __u32 *duration); +LIBBPF_API int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id); +LIBBPF_API int bpf_map_get_next_id(__u32 start_id, __u32 *next_id); +LIBBPF_API int bpf_prog_get_fd_by_id(__u32 id); +LIBBPF_API int bpf_map_get_fd_by_id(__u32 id); +LIBBPF_API int bpf_btf_get_fd_by_id(__u32 id); +LIBBPF_API int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len); +LIBBPF_API int bpf_prog_query(int target_fd, enum bpf_attach_type type, + __u32 query_flags, __u32 *attach_flags, + __u32 *prog_ids, __u32 *prog_cnt); +LIBBPF_API int bpf_raw_tracepoint_open(const char *name, int prog_fd); +LIBBPF_API int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, + __u32 log_buf_size, bool do_log); +LIBBPF_API int bpf_task_fd_query(int pid, int fd, __u32 flags, char *buf, + __u32 *buf_len, __u32 *prog_id, __u32 *fd_type, + __u64 *probe_offset, __u64 *probe_addr); #endif /* __LIBBPF_BPF_H */ diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 6db5462bb2ef9e0b8adab5fa984b6a434e40aea0..b77e7080f7e7389a6b5374ee096f6c4d05b176a6 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -6,6 +6,10 @@ #include +#ifndef LIBBPF_API +#define LIBBPF_API __attribute__((visibility("default"))) +#endif + #define BTF_ELF_SEC ".BTF" struct btf; @@ -14,13 +18,15 @@ struct btf_type; typedef int (*btf_print_fn_t)(const char *, ...) __attribute__((format(printf, 1, 2))); -void btf__free(struct btf *btf); -struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log); -__s32 btf__find_by_name(const struct btf *btf, const char *type_name); -const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 id); -__s64 btf__resolve_size(const struct btf *btf, __u32 type_id); -int btf__resolve_type(const struct btf *btf, __u32 type_id); -int btf__fd(const struct btf *btf); -const char *btf__name_by_offset(const struct btf *btf, __u32 offset); +LIBBPF_API void btf__free(struct btf *btf); +LIBBPF_API struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log); +LIBBPF_API __s32 btf__find_by_name(const struct btf *btf, + const char *type_name); +LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf, + __u32 id); +LIBBPF_API __s64 btf__resolve_size(const struct btf *btf, __u32 type_id); +LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id); +LIBBPF_API int btf__fd(const struct btf *btf); +LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset); #endif /* __LIBBPF_BTF_H */ diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 22f2702a4144588923b837b30959ab9f7fd4c13b..85c66abad69ae1d381a2a1ca886388b1ff305283 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -564,8 +564,9 @@ static int compare_bpf_map(const void *_a, const void *_b) } static int -bpf_object__init_maps(struct bpf_object *obj) +bpf_object__init_maps(struct bpf_object *obj, int flags) { + bool strict = !(flags & MAPS_RELAX_COMPAT); int i, map_idx, map_def_sz, nr_maps = 0; Elf_Scn *scn; Elf_Data *data; @@ -687,7 +688,8 @@ bpf_object__init_maps(struct bpf_object *obj) "has unrecognized, non-zero " "options\n", obj->path, map_name); - return -EINVAL; + if (strict) + return -EINVAL; } } memcpy(&obj->maps[map_idx].def, def, @@ -718,7 +720,7 @@ static bool section_have_execinstr(struct bpf_object *obj, int idx) return false; } -static int bpf_object__elf_collect(struct bpf_object *obj) +static int bpf_object__elf_collect(struct bpf_object *obj, int flags) { Elf *elf = obj->efile.elf; GElf_Ehdr *ep = &obj->efile.ehdr; @@ -845,7 +847,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj) return LIBBPF_ERRNO__FORMAT; } if (obj->efile.maps_shndx >= 0) { - err = bpf_object__init_maps(obj); + err = bpf_object__init_maps(obj, flags); if (err) goto out; } @@ -1517,7 +1519,7 @@ static int bpf_object__validate(struct bpf_object *obj, bool needs_kver) static struct bpf_object * __bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz, - bool needs_kver) + bool needs_kver, int flags) { struct bpf_object *obj; int err; @@ -1533,7 +1535,7 @@ __bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz, CHECK_ERR(bpf_object__elf_init(obj), err, out); CHECK_ERR(bpf_object__check_endianness(obj), err, out); - CHECK_ERR(bpf_object__elf_collect(obj), err, out); + CHECK_ERR(bpf_object__elf_collect(obj, flags), err, out); CHECK_ERR(bpf_object__collect_reloc(obj), err, out); CHECK_ERR(bpf_object__validate(obj, needs_kver), err, out); @@ -1544,7 +1546,8 @@ __bpf_object__open(const char *path, void *obj_buf, size_t obj_buf_sz, return ERR_PTR(err); } -struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr) +struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr, + int flags) { /* param validation */ if (!attr->file) @@ -1553,7 +1556,13 @@ struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr) pr_debug("loading %s\n", attr->file); return __bpf_object__open(attr->file, NULL, 0, - bpf_prog_type__needs_kver(attr->prog_type)); + bpf_prog_type__needs_kver(attr->prog_type), + flags); +} + +struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr) +{ + return __bpf_object__open_xattr(attr, 0); } struct bpf_object *bpf_object__open(const char *path) @@ -1586,7 +1595,7 @@ struct bpf_object *bpf_object__open_buffer(void *obj_buf, pr_debug("loading object '%s' from buffer\n", name); - return __bpf_object__open(name, obj_buf, obj_buf_sz, true); + return __bpf_object__open(name, obj_buf, obj_buf_sz, true, true); } int bpf_object__unload(struct bpf_object *obj) diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 8af8d36639910bd625cd17eb4c29a8084e60cf8f..1354cc9f8cbae817519fcbc9c7e68edfcca6ba3b 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -16,6 +16,10 @@ #include // for size_t #include +#ifndef LIBBPF_API +#define LIBBPF_API __attribute__((visibility("default"))) +#endif + enum libbpf_errno { __LIBBPF_ERRNO__START = 4000, @@ -37,7 +41,7 @@ enum libbpf_errno { __LIBBPF_ERRNO__END, }; -int libbpf_strerror(int err, char *buf, size_t size); +LIBBPF_API int libbpf_strerror(int err, char *buf, size_t size); /* * __printf is defined in include/linux/compiler-gcc.h. However, @@ -47,9 +51,9 @@ int libbpf_strerror(int err, char *buf, size_t size); typedef int (*libbpf_print_fn_t)(const char *, ...) __attribute__((format(printf, 1, 2))); -void libbpf_set_print(libbpf_print_fn_t warn, - libbpf_print_fn_t info, - libbpf_print_fn_t debug); +LIBBPF_API void libbpf_set_print(libbpf_print_fn_t warn, + libbpf_print_fn_t info, + libbpf_print_fn_t debug); /* Hide internal to user */ struct bpf_object; @@ -59,25 +63,28 @@ struct bpf_object_open_attr { enum bpf_prog_type prog_type; }; -struct bpf_object *bpf_object__open(const char *path); -struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr); -struct bpf_object *bpf_object__open_buffer(void *obj_buf, - size_t obj_buf_sz, - const char *name); -int bpf_object__pin(struct bpf_object *object, const char *path); -void bpf_object__close(struct bpf_object *object); +LIBBPF_API struct bpf_object *bpf_object__open(const char *path); +LIBBPF_API struct bpf_object * +bpf_object__open_xattr(struct bpf_object_open_attr *attr); +struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr, + int flags); +LIBBPF_API struct bpf_object *bpf_object__open_buffer(void *obj_buf, + size_t obj_buf_sz, + const char *name); +LIBBPF_API int bpf_object__pin(struct bpf_object *object, const char *path); +LIBBPF_API void bpf_object__close(struct bpf_object *object); /* Load/unload object into/from kernel */ -int bpf_object__load(struct bpf_object *obj); -int bpf_object__unload(struct bpf_object *obj); -const char *bpf_object__name(struct bpf_object *obj); -unsigned int bpf_object__kversion(struct bpf_object *obj); -int bpf_object__btf_fd(const struct bpf_object *obj); +LIBBPF_API int bpf_object__load(struct bpf_object *obj); +LIBBPF_API int bpf_object__unload(struct bpf_object *obj); +LIBBPF_API const char *bpf_object__name(struct bpf_object *obj); +LIBBPF_API unsigned int bpf_object__kversion(struct bpf_object *obj); +LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj); -struct bpf_program * +LIBBPF_API struct bpf_program * bpf_object__find_program_by_title(struct bpf_object *obj, const char *title); -struct bpf_object *bpf_object__next(struct bpf_object *prev); +LIBBPF_API struct bpf_object *bpf_object__next(struct bpf_object *prev); #define bpf_object__for_each_safe(pos, tmp) \ for ((pos) = bpf_object__next(NULL), \ (tmp) = bpf_object__next(pos); \ @@ -85,19 +92,20 @@ struct bpf_object *bpf_object__next(struct bpf_object *prev); (pos) = (tmp), (tmp) = bpf_object__next(tmp)) typedef void (*bpf_object_clear_priv_t)(struct bpf_object *, void *); -int bpf_object__set_priv(struct bpf_object *obj, void *priv, - bpf_object_clear_priv_t clear_priv); -void *bpf_object__priv(struct bpf_object *prog); +LIBBPF_API int bpf_object__set_priv(struct bpf_object *obj, void *priv, + bpf_object_clear_priv_t clear_priv); +LIBBPF_API void *bpf_object__priv(struct bpf_object *prog); -int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, - enum bpf_attach_type *expected_attach_type); -int libbpf_attach_type_by_name(const char *name, - enum bpf_attach_type *attach_type); +LIBBPF_API int +libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type, + enum bpf_attach_type *expected_attach_type); +LIBBPF_API int libbpf_attach_type_by_name(const char *name, + enum bpf_attach_type *attach_type); /* Accessors of bpf_program */ struct bpf_program; -struct bpf_program *bpf_program__next(struct bpf_program *prog, - struct bpf_object *obj); +LIBBPF_API struct bpf_program *bpf_program__next(struct bpf_program *prog, + struct bpf_object *obj); #define bpf_object__for_each_program(pos, obj) \ for ((pos) = bpf_program__next(NULL, (obj)); \ @@ -107,21 +115,24 @@ struct bpf_program *bpf_program__next(struct bpf_program *prog, typedef void (*bpf_program_clear_priv_t)(struct bpf_program *, void *); -int bpf_program__set_priv(struct bpf_program *prog, void *priv, - bpf_program_clear_priv_t clear_priv); +LIBBPF_API int bpf_program__set_priv(struct bpf_program *prog, void *priv, + bpf_program_clear_priv_t clear_priv); -void *bpf_program__priv(struct bpf_program *prog); -void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex); +LIBBPF_API void *bpf_program__priv(struct bpf_program *prog); +LIBBPF_API void bpf_program__set_ifindex(struct bpf_program *prog, + __u32 ifindex); -const char *bpf_program__title(struct bpf_program *prog, bool needs_copy); +LIBBPF_API const char *bpf_program__title(struct bpf_program *prog, + bool needs_copy); -int bpf_program__load(struct bpf_program *prog, char *license, - __u32 kern_version); -int bpf_program__fd(struct bpf_program *prog); -int bpf_program__pin_instance(struct bpf_program *prog, const char *path, - int instance); -int bpf_program__pin(struct bpf_program *prog, const char *path); -void bpf_program__unload(struct bpf_program *prog); +LIBBPF_API int bpf_program__load(struct bpf_program *prog, char *license, + __u32 kern_version); +LIBBPF_API int bpf_program__fd(struct bpf_program *prog); +LIBBPF_API int bpf_program__pin_instance(struct bpf_program *prog, + const char *path, + int instance); +LIBBPF_API int bpf_program__pin(struct bpf_program *prog, const char *path); +LIBBPF_API void bpf_program__unload(struct bpf_program *prog); struct bpf_insn; @@ -182,34 +193,36 @@ typedef int (*bpf_program_prep_t)(struct bpf_program *prog, int n, struct bpf_insn *insns, int insns_cnt, struct bpf_prog_prep_result *res); -int bpf_program__set_prep(struct bpf_program *prog, int nr_instance, - bpf_program_prep_t prep); +LIBBPF_API int bpf_program__set_prep(struct bpf_program *prog, int nr_instance, + bpf_program_prep_t prep); -int bpf_program__nth_fd(struct bpf_program *prog, int n); +LIBBPF_API int bpf_program__nth_fd(struct bpf_program *prog, int n); /* * Adjust type of BPF program. Default is kprobe. */ -int bpf_program__set_socket_filter(struct bpf_program *prog); -int bpf_program__set_tracepoint(struct bpf_program *prog); -int bpf_program__set_raw_tracepoint(struct bpf_program *prog); -int bpf_program__set_kprobe(struct bpf_program *prog); -int bpf_program__set_sched_cls(struct bpf_program *prog); -int bpf_program__set_sched_act(struct bpf_program *prog); -int bpf_program__set_xdp(struct bpf_program *prog); -int bpf_program__set_perf_event(struct bpf_program *prog); -void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type); -void bpf_program__set_expected_attach_type(struct bpf_program *prog, - enum bpf_attach_type type); - -bool bpf_program__is_socket_filter(struct bpf_program *prog); -bool bpf_program__is_tracepoint(struct bpf_program *prog); -bool bpf_program__is_raw_tracepoint(struct bpf_program *prog); -bool bpf_program__is_kprobe(struct bpf_program *prog); -bool bpf_program__is_sched_cls(struct bpf_program *prog); -bool bpf_program__is_sched_act(struct bpf_program *prog); -bool bpf_program__is_xdp(struct bpf_program *prog); -bool bpf_program__is_perf_event(struct bpf_program *prog); +LIBBPF_API int bpf_program__set_socket_filter(struct bpf_program *prog); +LIBBPF_API int bpf_program__set_tracepoint(struct bpf_program *prog); +LIBBPF_API int bpf_program__set_raw_tracepoint(struct bpf_program *prog); +LIBBPF_API int bpf_program__set_kprobe(struct bpf_program *prog); +LIBBPF_API int bpf_program__set_sched_cls(struct bpf_program *prog); +LIBBPF_API int bpf_program__set_sched_act(struct bpf_program *prog); +LIBBPF_API int bpf_program__set_xdp(struct bpf_program *prog); +LIBBPF_API int bpf_program__set_perf_event(struct bpf_program *prog); +LIBBPF_API void bpf_program__set_type(struct bpf_program *prog, + enum bpf_prog_type type); +LIBBPF_API void +bpf_program__set_expected_attach_type(struct bpf_program *prog, + enum bpf_attach_type type); + +LIBBPF_API bool bpf_program__is_socket_filter(struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_tracepoint(struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_raw_tracepoint(struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_kprobe(struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_sched_cls(struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_sched_act(struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_xdp(struct bpf_program *prog); +LIBBPF_API bool bpf_program__is_perf_event(struct bpf_program *prog); /* * No need for __attribute__((packed)), all members of 'bpf_map_def' @@ -230,39 +243,39 @@ struct bpf_map_def { * so no need to worry about a name clash. */ struct bpf_map; -struct bpf_map * +LIBBPF_API struct bpf_map * bpf_object__find_map_by_name(struct bpf_object *obj, const char *name); /* * Get bpf_map through the offset of corresponding struct bpf_map_def * in the BPF object file. */ -struct bpf_map * +LIBBPF_API struct bpf_map * bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset); -struct bpf_map * +LIBBPF_API struct bpf_map * bpf_map__next(struct bpf_map *map, struct bpf_object *obj); #define bpf_map__for_each(pos, obj) \ for ((pos) = bpf_map__next(NULL, (obj)); \ (pos) != NULL; \ (pos) = bpf_map__next((pos), (obj))) -int bpf_map__fd(struct bpf_map *map); -const struct bpf_map_def *bpf_map__def(struct bpf_map *map); -const char *bpf_map__name(struct bpf_map *map); -__u32 bpf_map__btf_key_type_id(const struct bpf_map *map); -__u32 bpf_map__btf_value_type_id(const struct bpf_map *map); +LIBBPF_API int bpf_map__fd(struct bpf_map *map); +LIBBPF_API const struct bpf_map_def *bpf_map__def(struct bpf_map *map); +LIBBPF_API const char *bpf_map__name(struct bpf_map *map); +LIBBPF_API __u32 bpf_map__btf_key_type_id(const struct bpf_map *map); +LIBBPF_API __u32 bpf_map__btf_value_type_id(const struct bpf_map *map); typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); -int bpf_map__set_priv(struct bpf_map *map, void *priv, - bpf_map_clear_priv_t clear_priv); -void *bpf_map__priv(struct bpf_map *map); -int bpf_map__reuse_fd(struct bpf_map *map, int fd); -bool bpf_map__is_offload_neutral(struct bpf_map *map); -void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex); -int bpf_map__pin(struct bpf_map *map, const char *path); +LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv, + bpf_map_clear_priv_t clear_priv); +LIBBPF_API void *bpf_map__priv(struct bpf_map *map); +LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd); +LIBBPF_API bool bpf_map__is_offload_neutral(struct bpf_map *map); +LIBBPF_API void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex); +LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path); -long libbpf_get_error(const void *ptr); +LIBBPF_API long libbpf_get_error(const void *ptr); struct bpf_prog_load_attr { const char *file; @@ -271,12 +284,12 @@ struct bpf_prog_load_attr { int ifindex; }; -int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, - struct bpf_object **pobj, int *prog_fd); -int bpf_prog_load(const char *file, enum bpf_prog_type type, - struct bpf_object **pobj, int *prog_fd); +LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, + struct bpf_object **pobj, int *prog_fd); +LIBBPF_API int bpf_prog_load(const char *file, enum bpf_prog_type type, + struct bpf_object **pobj, int *prog_fd); -int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); +LIBBPF_API int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); enum bpf_perf_event_ret { LIBBPF_PERF_EVENT_DONE = 0, @@ -286,10 +299,11 @@ enum bpf_perf_event_ret { typedef enum bpf_perf_event_ret (*bpf_perf_event_print_t)(void *event, void *priv); -int bpf_perf_event_read_simple(void *mem, unsigned long size, - unsigned long page_size, - void **buf, size_t *buf_len, - bpf_perf_event_print_t fn, void *priv); +LIBBPF_API int bpf_perf_event_read_simple(void *mem, unsigned long size, + unsigned long page_size, + void **buf, size_t *buf_len, + bpf_perf_event_print_t fn, + void *priv); struct nlattr; typedef int (*libbpf_dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb); diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 1dec3ab2fcdebb792c9cad32737f6546d0d01f82..cb0a9e90b1f807f076c25737166cd7345826d0e6 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -36,7 +36,8 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \ test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \ get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \ - test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o test_sk_lookup_kern.o + test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o test_sk_lookup_kern.o \ + test_queue_map.o test_stack_map.o # Order correspond to 'make run_tests' order TEST_PROGS := test_kmod.sh \ @@ -117,6 +118,9 @@ CLANG_FLAGS = -I. -I./include/uapi -I../../../include/uapi \ $(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline $(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline +$(OUTPUT)/test_queue_map.o: test_queue_stack_map.h +$(OUTPUT)/test_stack_map.o: test_queue_stack_map.h + BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris) BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF) BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm') diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index 8962331ed05fa44d7cca613571857fc0b99860a2..f51da393dc2225d98f793851bb40e9602615f879 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -16,6 +16,13 @@ static int (*bpf_map_update_elem)(void *map, void *key, void *value, (void *) BPF_FUNC_map_update_elem; static int (*bpf_map_delete_elem)(void *map, void *key) = (void *) BPF_FUNC_map_delete_elem; +static int (*bpf_map_push_elem)(void *map, void *value, + unsigned long long flags) = + (void *) BPF_FUNC_map_push_elem; +static int (*bpf_map_pop_elem)(void *map, void *value) = + (void *) BPF_FUNC_map_pop_elem; +static int (*bpf_map_peek_elem)(void *map, void *value) = + (void *) BPF_FUNC_map_peek_elem; static int (*bpf_probe_read)(void *dst, int size, void *unsafe_ptr) = (void *) BPF_FUNC_probe_read; static unsigned long long (*bpf_ktime_get_ns)(void) = diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index e5e62cb57ff7829754d1bc9aead0bd885a601cb8..7cab5d743dfcececf03d34844439742bf75c3aa9 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -471,6 +472,122 @@ static void test_devmap(int task, void *data) close(fd); } +static void test_queuemap(int task, void *data) +{ + const int MAP_SIZE = 32; + __u32 vals[MAP_SIZE + MAP_SIZE/2], val; + int fd, i; + + /* Fill test values to be used */ + for (i = 0; i < MAP_SIZE + MAP_SIZE/2; i++) + vals[i] = rand(); + + /* Invalid key size */ + fd = bpf_create_map(BPF_MAP_TYPE_QUEUE, 4, sizeof(val), MAP_SIZE, + map_flags); + assert(fd < 0 && errno == EINVAL); + + fd = bpf_create_map(BPF_MAP_TYPE_QUEUE, 0, sizeof(val), MAP_SIZE, + map_flags); + /* Queue map does not support BPF_F_NO_PREALLOC */ + if (map_flags & BPF_F_NO_PREALLOC) { + assert(fd < 0 && errno == EINVAL); + return; + } + if (fd < 0) { + printf("Failed to create queuemap '%s'!\n", strerror(errno)); + exit(1); + } + + /* Push MAP_SIZE elements */ + for (i = 0; i < MAP_SIZE; i++) + assert(bpf_map_update_elem(fd, NULL, &vals[i], 0) == 0); + + /* Check that element cannot be pushed due to max_entries limit */ + assert(bpf_map_update_elem(fd, NULL, &val, 0) == -1 && + errno == E2BIG); + + /* Peek element */ + assert(bpf_map_lookup_elem(fd, NULL, &val) == 0 && val == vals[0]); + + /* Replace half elements */ + for (i = MAP_SIZE; i < MAP_SIZE + MAP_SIZE/2; i++) + assert(bpf_map_update_elem(fd, NULL, &vals[i], BPF_EXIST) == 0); + + /* Pop all elements */ + for (i = MAP_SIZE/2; i < MAP_SIZE + MAP_SIZE/2; i++) + assert(bpf_map_lookup_and_delete_elem(fd, NULL, &val) == 0 && + val == vals[i]); + + /* Check that there are not elements left */ + assert(bpf_map_lookup_and_delete_elem(fd, NULL, &val) == -1 && + errno == ENOENT); + + /* Check that non supported functions set errno to EINVAL */ + assert(bpf_map_delete_elem(fd, NULL) == -1 && errno == EINVAL); + assert(bpf_map_get_next_key(fd, NULL, NULL) == -1 && errno == EINVAL); + + close(fd); +} + +static void test_stackmap(int task, void *data) +{ + const int MAP_SIZE = 32; + __u32 vals[MAP_SIZE + MAP_SIZE/2], val; + int fd, i; + + /* Fill test values to be used */ + for (i = 0; i < MAP_SIZE + MAP_SIZE/2; i++) + vals[i] = rand(); + + /* Invalid key size */ + fd = bpf_create_map(BPF_MAP_TYPE_STACK, 4, sizeof(val), MAP_SIZE, + map_flags); + assert(fd < 0 && errno == EINVAL); + + fd = bpf_create_map(BPF_MAP_TYPE_STACK, 0, sizeof(val), MAP_SIZE, + map_flags); + /* Stack map does not support BPF_F_NO_PREALLOC */ + if (map_flags & BPF_F_NO_PREALLOC) { + assert(fd < 0 && errno == EINVAL); + return; + } + if (fd < 0) { + printf("Failed to create stackmap '%s'!\n", strerror(errno)); + exit(1); + } + + /* Push MAP_SIZE elements */ + for (i = 0; i < MAP_SIZE; i++) + assert(bpf_map_update_elem(fd, NULL, &vals[i], 0) == 0); + + /* Check that element cannot be pushed due to max_entries limit */ + assert(bpf_map_update_elem(fd, NULL, &val, 0) == -1 && + errno == E2BIG); + + /* Peek element */ + assert(bpf_map_lookup_elem(fd, NULL, &val) == 0 && val == vals[i - 1]); + + /* Replace half elements */ + for (i = MAP_SIZE; i < MAP_SIZE + MAP_SIZE/2; i++) + assert(bpf_map_update_elem(fd, NULL, &vals[i], BPF_EXIST) == 0); + + /* Pop all elements */ + for (i = MAP_SIZE + MAP_SIZE/2 - 1; i >= MAP_SIZE/2; i--) + assert(bpf_map_lookup_and_delete_elem(fd, NULL, &val) == 0 && + val == vals[i]); + + /* Check that there are not elements left */ + assert(bpf_map_lookup_and_delete_elem(fd, NULL, &val) == -1 && + errno == ENOENT); + + /* Check that non supported functions set errno to EINVAL */ + assert(bpf_map_delete_elem(fd, NULL) == -1 && errno == EINVAL); + assert(bpf_map_get_next_key(fd, NULL, NULL) == -1 && errno == EINVAL); + + close(fd); +} + #include #include #include @@ -1434,10 +1551,15 @@ static void run_all_tests(void) test_map_wronly(); test_reuseport_array(); + + test_queuemap(0, NULL); + test_stackmap(0, NULL); } int main(void) { + srand(time(NULL)); + map_flags = 0; run_all_tests(); diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index fb540beef3245c15872312e7cf92e928c9a0dd71..3ec4ce156074cf8698a0e3bb08ca4e60a70650e4 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -1765,8 +1765,105 @@ static void test_reference_tracking() bpf_object__close(obj); } +enum { + QUEUE, + STACK, +}; + +static void test_queue_stack_map(int type) +{ + const int MAP_SIZE = 32; + __u32 vals[MAP_SIZE], duration, retval, size, val; + int i, err, prog_fd, map_in_fd, map_out_fd; + char file[32], buf[128]; + struct bpf_object *obj; + struct iphdr *iph = (void *)buf + sizeof(struct ethhdr); + + /* Fill test values to be used */ + for (i = 0; i < MAP_SIZE; i++) + vals[i] = rand(); + + if (type == QUEUE) + strncpy(file, "./test_queue_map.o", sizeof(file)); + else if (type == STACK) + strncpy(file, "./test_stack_map.o", sizeof(file)); + else + return; + + err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd); + if (err) { + error_cnt++; + return; + } + + map_in_fd = bpf_find_map(__func__, obj, "map_in"); + if (map_in_fd < 0) + goto out; + + map_out_fd = bpf_find_map(__func__, obj, "map_out"); + if (map_out_fd < 0) + goto out; + + /* Push 32 elements to the input map */ + for (i = 0; i < MAP_SIZE; i++) { + err = bpf_map_update_elem(map_in_fd, NULL, &vals[i], 0); + if (err) { + error_cnt++; + goto out; + } + } + + /* The eBPF program pushes iph.saddr in the output map, + * pops the input map and saves this value in iph.daddr + */ + for (i = 0; i < MAP_SIZE; i++) { + if (type == QUEUE) { + val = vals[i]; + pkt_v4.iph.saddr = vals[i] * 5; + } else if (type == STACK) { + val = vals[MAP_SIZE - 1 - i]; + pkt_v4.iph.saddr = vals[MAP_SIZE - 1 - i] * 5; + } + + err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), + buf, &size, &retval, &duration); + if (err || retval || size != sizeof(pkt_v4) || + iph->daddr != val) + break; + } + + CHECK(err || retval || size != sizeof(pkt_v4) || iph->daddr != val, + "bpf_map_pop_elem", + "err %d errno %d retval %d size %d iph->daddr %u\n", + err, errno, retval, size, iph->daddr); + + /* Queue is empty, program should return TC_ACT_SHOT */ + err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), + buf, &size, &retval, &duration); + CHECK(err || retval != 2 /* TC_ACT_SHOT */|| size != sizeof(pkt_v4), + "check-queue-stack-map-empty", + "err %d errno %d retval %d size %d\n", + err, errno, retval, size); + + /* Check that the program pushed elements correctly */ + for (i = 0; i < MAP_SIZE; i++) { + err = bpf_map_lookup_and_delete_elem(map_out_fd, NULL, &val); + if (err || val != vals[i] * 5) + break; + } + + CHECK(i != MAP_SIZE && (err || val != vals[i] * 5), + "bpf_map_push_elem", "err %d value %u\n", err, val); + +out: + pkt_v4.iph.saddr = 0; + bpf_object__close(obj); +} + int main(void) { + srand(time(NULL)); + jit_enabled = is_jit_enabled(); test_pkt_access(); @@ -1787,6 +1884,8 @@ int main(void) test_task_fd_query_rawtp(); test_task_fd_query_tp(); test_reference_tracking(); + test_queue_stack_map(QUEUE); + test_queue_stack_map(STACK); printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt); return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS; diff --git a/tools/testing/selftests/bpf/test_queue_map.c b/tools/testing/selftests/bpf/test_queue_map.c new file mode 100644 index 0000000000000000000000000000000000000000..87db1f9da33dbd94d1ef1347f13a972de3927bd5 --- /dev/null +++ b/tools/testing/selftests/bpf/test_queue_map.c @@ -0,0 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Politecnico di Torino +#define MAP_TYPE BPF_MAP_TYPE_QUEUE +#include "test_queue_stack_map.h" diff --git a/tools/testing/selftests/bpf/test_queue_stack_map.h b/tools/testing/selftests/bpf/test_queue_stack_map.h new file mode 100644 index 0000000000000000000000000000000000000000..295b9b3bc5c72d93c922b447ebac2d8d6318e9fd --- /dev/null +++ b/tools/testing/selftests/bpf/test_queue_stack_map.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +// Copyright (c) 2018 Politecnico di Torino +#include +#include +#include +#include +#include +#include +#include "bpf_helpers.h" + +int _version SEC("version") = 1; + +struct bpf_map_def __attribute__ ((section("maps"), used)) map_in = { + .type = MAP_TYPE, + .key_size = 0, + .value_size = sizeof(__u32), + .max_entries = 32, + .map_flags = 0, +}; + +struct bpf_map_def __attribute__ ((section("maps"), used)) map_out = { + .type = MAP_TYPE, + .key_size = 0, + .value_size = sizeof(__u32), + .max_entries = 32, + .map_flags = 0, +}; + +SEC("test") +int _test(struct __sk_buff *skb) +{ + void *data_end = (void *)(long)skb->data_end; + void *data = (void *)(long)skb->data; + struct ethhdr *eth = (struct ethhdr *)(data); + __u32 value; + int err; + + if (eth + 1 > data_end) + return TC_ACT_SHOT; + + struct iphdr *iph = (struct iphdr *)(eth + 1); + + if (iph + 1 > data_end) + return TC_ACT_SHOT; + + err = bpf_map_pop_elem(&map_in, &value); + if (err) + return TC_ACT_SHOT; + + iph->daddr = value; + + err = bpf_map_push_elem(&map_out, &iph->saddr, 0); + if (err) + return TC_ACT_SHOT; + + return TC_ACT_OK; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_stack_map.c b/tools/testing/selftests/bpf/test_stack_map.c new file mode 100644 index 0000000000000000000000000000000000000000..31c3880e6da008720f1498b61ee7ca206b2cb066 --- /dev/null +++ b/tools/testing/selftests/bpf/test_stack_map.c @@ -0,0 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Politecnico di Torino +#define MAP_TYPE BPF_MAP_TYPE_STACK +#include "test_queue_stack_map.h"